From 36c104413ba35f386f55e90173710361986b8a52 Mon Sep 17 00:00:00 2001
From: Carlos Paniagua <cpaniaguam@gmail.com>
Date: Thu, 23 Jul 2026 16:01:48 -0400
Subject: [PATCH 1/6] Simplify basic rl tutorial nb

---
 docs/tutorials/rlssm_basic.ipynb | 16693 +----------------------------
 1 file changed, 242 insertions(+), 16451 deletions(-)

diff --git a/docs/tutorials/rlssm_basic.ipynb b/docs/tutorials/rlssm_basic.ipynb
index 6396ff77b..6eecefcf4 100644
--- a/docs/tutorials/rlssm_basic.ipynb
+++ b/docs/tutorials/rlssm_basic.ipynb
@@ -6,38 +6,19 @@
    "metadata": {},
    "source": [
     "# RLSSM — Basic tutorial\n",
-    "\n",
-    "**Reinforcement-Learning Sequential Sampling Models (RLSSMs)** join two ideas that\n",
-    "cognitive scientists usually study separately:\n",
-    "\n",
-    "1. a **learning process** — how a participant updates their expectations from\n",
-    "   trial-to-trial feedback (here, the Rescorla–Wagner rule); and\n",
-    "2. a **decision process** — how, on each trial, those expectations are turned into\n",
-    "   an actual *choice* and a *response time* (here, a drift-diffusion–style\n",
-    "   sequential sampling model).\n",
-    "\n",
-    "A plain RL model explains *which* option is chosen but ignores *how long* the choice\n",
-    "took. A plain SSM explains the choice/RT on a single decision but assumes the\n",
-    "decision variables are fixed. An RLSSM closes the loop: the value a participant has\n",
-    "*learned* becomes the thing that *drives* the moment-to-moment decision, and it does\n",
-    "so on every trial. This lets us fit choices **and** response times jointly and\n",
-    "recover both the learning parameters (e.g. a learning rate) and the decision\n",
-    "parameters (e.g. boundary separation) from the same data.\n",
-    "\n",
-    "This tutorial is written for readers who are **new to HSSM, PyMC, and RLSSMs**. We\n",
-    "will go slowly and explain each object as it appears. By the end you will have:\n",
-    "\n",
+    "This tutorial is a first pass through an RLSSM workflow in HSSM. The goal is to\n",
+    "get from a preset model to a fitted hierarchical analysis without stopping on\n",
+    "every internal object along the way.\n",
+    "By the end you will have:\n",
     "- simulated a synthetic RLSSM dataset with [`ssm-simulators`](https://github.com/lnccbrown/ssm-simulators) (`ssms.rl`),\n",
-    "- **bridged** that model into HSSM with a single call (`RLSSMConfig.from_ssms_model`),\n",
-    "- fit a **hierarchical** (multi-participant) model with PyMC under the hood,\n",
-    "- checked **parameter recovery** at the group *and* individual level, and\n",
+    "- fit a **hierarchical** (multi-participant) RLSSM in HSSM from the named preset `2AB_RW_Angle`,\n",
+    "- checked a simple recovery summary, and\n",
     "- run a **posterior predictive check** tailored to RLSSMs.\n",
-    "\n",
     "> **Where this sits in the suite:** this is the entry point. Later tutorials build\n",
     "> *custom* learning/decision models\n",
     "> ([Custom models with ssms.rl](rlssm_advanced.ipynb) ·\n",
     "> [Restless learner](rlssm_restless_learner.ipynb)) and show HSSM-native\n",
-    "> registration ([Registering custom models in HSSM](rlssm_hssm_custom_models.ipynb))."
+    "> registration ([Registering custom models in HSSM](rlssm_hssm_custom_models.ipynb)).\n"
    ]
   },
   {
@@ -45,70 +26,47 @@
    "id": "9973c549",
    "metadata": {},
    "source": [
-    "## 1. The idea in a bit more detail\n",
-    "\n",
+    "## 1. The core idea\n",
     "### 1.1 The learning process: Rescorla–Wagner\n",
-    "\n",
     "Our task is a **two-armed bandit**: on each trial the participant picks one of two\n",
     "options and receives binary feedback (reward = 1, no reward = 0). The participant\n",
     "keeps a running value estimate $Q$ for each option and updates it using the\n",
     "**Rescorla–Wagner delta rule**. After choosing option $c$ and observing reward $r$:\n",
-    "\n",
     "$$\n",
     "Q_{c} \\leftarrow Q_{c} + \\alpha \\, \\underbrace{(r - Q_{c})}_{\\text{prediction error}}\n",
     "$$\n",
-    "\n",
     "- $Q_c$ is the current value estimate for the chosen option.\n",
     "- $r - Q_c$ is the **reward prediction error** — how surprising the outcome was.\n",
     "- $\\alpha \\in (0, 1)$ is the **learning rate** (`rl_alpha`): large $\\alpha$ means the\n",
     "  participant updates quickly and weights recent outcomes heavily; small $\\alpha$\n",
     "  means slow, stable learning. Only the chosen option's value is updated.\n",
-    "\n",
     "### 1.2 Coupling value to the decision: the drift rate\n",
-    "\n",
     "On each trial, the *difference* in learned value between the two options sets how\n",
     "strongly evidence flows toward one option during the decision. Concretely the\n",
     "**drift rate** $v$ of the decision process is\n",
-    "\n",
     "$$\n",
-    "v = \\big(Q_{1} - Q_{0}\\big)\\cdot \\texttt{scaler}\n",
+    "v = \\big(Q_{1} - Q_{0}\\big)\\cdot \\texttt{scaler},\n",
     "$$\n",
-    "\n",
     "where `scaler` converts a value difference into drift units. When the two options\n",
     "look equally good ($Q_1 \\approx Q_0$) drift is near zero and choices are slow and\n",
     "near-chance; as learning separates the values, $|v|$ grows and choices become faster\n",
     "and more consistent. **`v` is not a free parameter you estimate directly — it is\n",
     "*computed* from the learning process on every trial.** This is the heart of an RLSSM.\n",
-    "\n",
     "### 1.3 The decision process: the angle SSM (brief)\n",
-    "\n",
     "Given a drift rate, the decision itself is produced by a **sequential sampling\n",
     "model**. If you have seen the drift-diffusion model (DDM) before, this will be\n",
     "familiar: noisy evidence accumulates from a starting point until it hits one of two\n",
     "boundaries, and *which* boundary and *when* determine the choice and RT. We use the\n",
     "**angle** variant, whose only addition to the standard DDM is a **linearly\n",
     "collapsing boundary** — the decision threshold narrows over time, which helps capture\n",
-    "the fast errors often seen in speeded choice. Its parameters:\n",
-    "\n",
-    "| Param | Meaning |\n",
-    "|-------|---------|\n",
-    "| `v` | drift rate — **computed** from learned value (see above), not free |\n",
-    "| `a` | boundary separation (how much evidence is needed) |\n",
-    "| `z` | starting-point bias (0.5 = unbiased) |\n",
-    "| `t` | non-decision time (encoding + motor, in seconds) |\n",
-    "| `theta` | boundary collapse angle (0 = standard DDM) |\n",
-    "\n",
-    "We keep the SSM description short on purpose — the DDM family is covered in depth in\n",
-    "the other HSSM tutorials. The RLSSM-specific part is *only* the coupling in §1.2.\n",
-    "\n",
+    "fast errors often seen in speeded choice. Its parameters are `a`, `z`, `t`, and\n",
+    "`theta`, while `v` is supplied by the learning process.\n",
     "### 1.4 Why hierarchical?\n",
-    "\n",
-    "We rarely have one participant; we have many, each slightly different. A\n",
-    "**hierarchical** model estimates a group-level value for each parameter **and** a\n",
-    "per-participant deviation from it, letting participants share statistical strength\n",
-    "(\"partial pooling\"). We will specify exactly this below and then check that the\n",
-    "fitted model recovers both the group means and the individual differences we baked\n",
-    "into the simulation."
+    "We usually have many participants, each slightly different. A **hierarchical** model\n",
+    "estimates a group-level value for each parameter **and** a per-participant deviation\n",
+    "from it, letting participants share statistical strength (\"partial pooling\"). In\n",
+    "this tutorial we will use one reusable prior template for all free parameters rather\n",
+    "than introducing every modeling detail separately.\n"
    ]
   },
   {
@@ -117,62 +75,33 @@
    "metadata": {},
    "source": [
     "## 2. Setup\n",
-    "\n",
     "We import HSSM and the `ssms.rl` simulation API, then set two global options that\n",
     "matter for RLSSM work:\n",
-    "\n",
     "- **`hssm.set_floatX(\"float32\")`** — RLSSM likelihoods run through a JAX scan over\n",
     "  trials; single precision keeps this fast and is what the RLSSM pipeline is tuned\n",
     "  for.\n",
-    "- We silence a few noisy library warnings so the notebook output stays readable."
+    "- We silence a few noisy library warnings so the notebook output stays readable.\n"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": null,
    "id": "f090de8f",
-   "metadata": {
-    "execution": {
-     "iopub.execute_input": "2026-07-06T16:35:29.532450Z",
-     "iopub.status.busy": "2026-07-06T16:35:29.532007Z",
-     "iopub.status.idle": "2026-07-06T16:35:32.972953Z",
-     "shell.execute_reply": "2026-07-06T16:35:32.972626Z"
-    }
-   },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Setting PyTensor floatX type to float32.\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Setting \"jax_enable_x64\" to False. If this is not intended, please set `jax` to False.\n"
-     ]
-    }
-   ],
+   "metadata": {},
+   "outputs": [],
    "source": [
     "import logging\n",
-    "import os\n",
     "import warnings\n",
-    "\n",
     "import arviz as az\n",
     "import matplotlib.pyplot as plt\n",
     "import numpy as np\n",
     "import pandas as pd\n",
     "from ssms import rl\n",
-    "\n",
     "import hssm\n",
-    "\n",
     "warnings.filterwarnings(\"ignore\")\n",
     "logging.getLogger(\"jax._src.xla_bridge\").setLevel(logging.ERROR)\n",
-    "\n",
     "hssm.set_floatX(\"float32\", update_jax=True)\n",
-    "RANDOM_SEED = 20260704"
+    "RANDOM_SEED = 20260704\n"
    ]
   },
   {
@@ -180,49 +109,31 @@
    "id": "f1205a8b",
    "metadata": {},
    "source": [
-    "### Simulation scale\n",
-    "\n",
-    "Fitting a hierarchical RLSSM involves MCMC sampling, which is too heavy to run on\n",
-    "every documentation build. We therefore expose a single switch: the notebook runs at\n",
-    "a small **doc scale** by default, and at a fuller **`FULL_RUN`** scale (more\n",
-    "participants, trials, and draws) when the environment variable `FULL_RUN=1` is set.\n",
-    "The outputs committed to the docs come from a `FULL_RUN` execution."
+    "### Run size\n",
+    "This tutorial uses a quick configuration so readers can complete a full\n",
+    "end-to-end RLSSM workflow without long waits.\n",
+    "**Optional longer run (advanced):** after your first pass, increase the values\n",
+    "in the next cell (participants, trials, tune, and draws) to get tighter\n",
+    "recovery and PPC curves.\n"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": null,
    "id": "4a45b283",
-   "metadata": {
-    "execution": {
-     "iopub.execute_input": "2026-07-06T16:35:32.974331Z",
-     "iopub.status.busy": "2026-07-06T16:35:32.974242Z",
-     "iopub.status.idle": "2026-07-06T16:35:32.976205Z",
-     "shell.execute_reply": "2026-07-06T16:35:32.975844Z"
-    }
-   },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "FULL_RUN=True | participants=15 trials=150 tune=1000 draws=500\n"
-     ]
-    }
-   ],
+   "metadata": {},
+   "outputs": [],
    "source": [
-    "FULL_RUN = os.environ.get(\"FULL_RUN\", \"0\") == \"1\"\n",
-    "\n",
-    "N_PARTICIPANTS = 15 if FULL_RUN else 5\n",
-    "N_TRIALS = 150 if FULL_RUN else 70\n",
+    "N_PARTICIPANTS = 5\n",
+    "N_TRIALS = 70\n",
     "N_CHAINS = 2\n",
-    "N_TUNE = 1000 if FULL_RUN else 300\n",
-    "N_DRAWS = 500 if FULL_RUN else 300\n",
+    "N_TUNE = 300\n",
+    "N_DRAWS = 300\n",
     "\n",
     "print(\n",
-    "    f\"FULL_RUN={FULL_RUN} | participants={N_PARTICIPANTS} trials={N_TRIALS} \"\n",
+    "    f\"quick mode | participants={N_PARTICIPANTS} trials={N_TRIALS} \"\n",
     "    f\"tune={N_TUNE} draws={N_DRAWS}\"\n",
-    ")"
+    ")\n"
    ]
   },
   {
@@ -231,49 +142,20 @@
    "metadata": {},
    "source": [
     "## 3. Pick a model: the `2AB_RW_Angle` preset\n",
-    "\n",
     "`ssms.rl` ships **presets** that bundle a task environment, a learning rule, and a\n",
     "decision process into one ready-to-use model. `2AB_RW_Angle` is exactly the model we\n",
-    "described in §1: a **2**-**a**rmed **b**andit with **R**escorla–**W**agner learning\n",
+    "described in above: a **2**-**a**rmed **b**andit with **R**escorla–**W**agner learning\n",
     "and an **angle** decision process. `rl.preset.info(...)` prints a readable summary of\n",
-    "everything the preset contains."
+    "everything the preset contains.\n"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": null,
    "id": "81a5570b",
-   "metadata": {
-    "execution": {
-     "iopub.execute_input": "2026-07-06T16:35:32.977149Z",
-     "iopub.status.busy": "2026-07-06T16:35:32.977095Z",
-     "iopub.status.idle": "2026-07-06T16:35:32.978765Z",
-     "shell.execute_reply": "2026-07-06T16:35:32.978493Z"
-    }
-   },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Preset: 2AB_RW_Angle\n",
-      "Description: Two-armed bandit with a Rescorla-Wagner delta-rule learner and an angle decision process.\n",
-      "Task: two-armed Bernoulli bandit\n",
-      "Learning process: RescorlaWagnerDeltaRule\n",
-      "Decision process: angle\n",
-      "Required parameters: rl_alpha, scaler, a, z, t, theta\n",
-      "Default parameters: rl_alpha=0.2, scaler=2, a=1, z=0.5, t=0.001, theta=0\n",
-      "Response labels: (-1, 1)\n",
-      "Response to choice: {-1: 0, 1: 1}\n",
-      "Context fields: ['feedback']\n",
-      "Learning backend: jax\n",
-      "Gradient support: available\n",
-      "HSSM participant contract: yes\n"
-     ]
-    }
-   ],
+   "metadata": {},
+   "outputs": [],
    "source": [
-    "ssms_config = rl.preset.get(\"2AB_RW_Angle\")\n",
     "print(rl.preset.info(\"2AB_RW_Angle\"))"
    ]
   },
@@ -282,45 +164,25 @@
    "id": "f4b8f53f",
    "metadata": {},
    "source": [
-    "A few fields to note in that summary:\n",
+    "To fit this preset in HSSM, there are only two facts you need right away:\n",
+    "- the free parameters are `rl_alpha`, `scaler`, `a`, `z`, `t`, and `theta`, and\n",
+    "- the drift `v` is **computed** from the learning process rather than sampled.\n",
     "\n",
-    "- **Required parameters** are what we must supply to simulate: the learning\n",
-    "  parameters `rl_alpha`, `scaler` and the decision parameters `a`, `z`, `t`, `theta`.\n",
-    "  The drift `v` is *not* here — it is **computed** each trial from the learner.\n",
-    "- **Response labels** `(-1, 1)` are the two arms. In this preset arm `-1` is the\n",
-    "  *high-reward* arm (reward probability 0.7) and arm `1` is the low-reward arm (0.3).\n",
-    "- **Gradient support: available** means the learning process has a differentiable\n",
-    "  JAX implementation — a hard requirement for HSSM's gradient-based sampler. Let's\n",
-    "  confirm that explicitly:"
+    "We confirm that below.\n",
+    "\n"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": null,
    "id": "5a61fc70",
-   "metadata": {
-    "execution": {
-     "iopub.execute_input": "2026-07-06T16:35:32.979672Z",
-     "iopub.status.busy": "2026-07-06T16:35:32.979617Z",
-     "iopub.status.idle": "2026-07-06T16:35:32.981257Z",
-     "shell.execute_reply": "2026-07-06T16:35:32.980964Z"
-    }
-   },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "computed params (driven by the learner): ['v']\n",
-      "context fields (read from data each trial): ['feedback']\n"
-     ]
-    }
-   ],
+   "metadata": {},
+   "outputs": [],
    "source": [
+    "ssms_config = rl.preset.get(\"2AB_RW_Angle\")\n",
     "assembled = ssms_config.assemble(backend=\"jax\")\n",
     "print(\"computed params (driven by the learner):\", assembled.computed_params)\n",
-    "print(\"context fields (read from data each trial):\", assembled.context_fields)\n",
-    "assert assembled.gradient == \"available\", \"HSSM inference needs JAX gradients\""
+    "assert \"v\" in assembled.computed_params\n"
    ]
   },
   {
@@ -329,233 +191,21 @@
    "metadata": {},
    "source": [
     "## 4. Define ground-truth parameters\n",
-    "\n",
     "Because this is a tutorial, we *simulate* data from known parameters so we can later\n",
     "check whether the model recovers them. We choose a **group mean** for each parameter\n",
     "and give each participant a small random deviation around that mean, so participants\n",
     "genuinely differ — that is what the hierarchical model will try to recover.\n",
-    "\n",
     "`SDS` sets how spread out participants are for each parameter (bigger = more\n",
     "individual variability), and `BOUNDS` keeps every sampled value inside the range the\n",
-    "model supports."
+    "model supports.\n"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": null,
    "id": "6258c663",
-   "metadata": {
-    "execution": {
-     "iopub.execute_input": "2026-07-06T16:35:32.982233Z",
-     "iopub.status.busy": "2026-07-06T16:35:32.982174Z",
-     "iopub.status.idle": "2026-07-06T16:35:32.997826Z",
-     "shell.execute_reply": "2026-07-06T16:35:32.997506Z"
-    }
-   },
-   "outputs": [
-    {
-     "data": {
-      "text/html": [
-       "<div>\n",
-       "<style scoped>\n",
-       "    .dataframe tbody tr th:only-of-type {\n",
-       "        vertical-align: middle;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe tbody tr th {\n",
-       "        vertical-align: top;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe thead th {\n",
-       "        text-align: right;\n",
-       "    }\n",
-       "</style>\n",
-       "<table border=\"1\" class=\"dataframe\">\n",
-       "  <thead>\n",
-       "    <tr style=\"text-align: right;\">\n",
-       "      <th></th>\n",
-       "      <th>rl_alpha</th>\n",
-       "      <th>scaler</th>\n",
-       "      <th>a</th>\n",
-       "      <th>z</th>\n",
-       "      <th>t</th>\n",
-       "      <th>theta</th>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>participant_id</th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "    </tr>\n",
-       "  </thead>\n",
-       "  <tbody>\n",
-       "    <tr>\n",
-       "      <th>0</th>\n",
-       "      <td>0.048</td>\n",
-       "      <td>2.349</td>\n",
-       "      <td>1.156</td>\n",
-       "      <td>0.486</td>\n",
-       "      <td>0.258</td>\n",
-       "      <td>0.362</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>1</th>\n",
-       "      <td>0.118</td>\n",
-       "      <td>2.287</td>\n",
-       "      <td>0.921</td>\n",
-       "      <td>0.526</td>\n",
-       "      <td>0.277</td>\n",
-       "      <td>0.288</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2</th>\n",
-       "      <td>0.084</td>\n",
-       "      <td>2.307</td>\n",
-       "      <td>1.357</td>\n",
-       "      <td>0.513</td>\n",
-       "      <td>0.252</td>\n",
-       "      <td>0.441</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>3</th>\n",
-       "      <td>0.069</td>\n",
-       "      <td>2.491</td>\n",
-       "      <td>1.176</td>\n",
-       "      <td>0.480</td>\n",
-       "      <td>0.332</td>\n",
-       "      <td>0.433</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>4</th>\n",
-       "      <td>0.111</td>\n",
-       "      <td>1.808</td>\n",
-       "      <td>1.350</td>\n",
-       "      <td>0.439</td>\n",
-       "      <td>0.147</td>\n",
-       "      <td>0.312</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>5</th>\n",
-       "      <td>0.041</td>\n",
-       "      <td>2.433</td>\n",
-       "      <td>1.247</td>\n",
-       "      <td>0.555</td>\n",
-       "      <td>0.255</td>\n",
-       "      <td>0.485</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>6</th>\n",
-       "      <td>0.085</td>\n",
-       "      <td>1.841</td>\n",
-       "      <td>1.209</td>\n",
-       "      <td>0.443</td>\n",
-       "      <td>0.263</td>\n",
-       "      <td>0.389</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>7</th>\n",
-       "      <td>0.071</td>\n",
-       "      <td>3.062</td>\n",
-       "      <td>1.203</td>\n",
-       "      <td>0.546</td>\n",
-       "      <td>0.225</td>\n",
-       "      <td>0.096</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>8</th>\n",
-       "      <td>0.112</td>\n",
-       "      <td>1.977</td>\n",
-       "      <td>0.989</td>\n",
-       "      <td>0.498</td>\n",
-       "      <td>0.258</td>\n",
-       "      <td>0.305</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>9</th>\n",
-       "      <td>0.081</td>\n",
-       "      <td>2.672</td>\n",
-       "      <td>1.419</td>\n",
-       "      <td>0.532</td>\n",
-       "      <td>0.179</td>\n",
-       "      <td>0.324</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>10</th>\n",
-       "      <td>0.114</td>\n",
-       "      <td>2.621</td>\n",
-       "      <td>0.983</td>\n",
-       "      <td>0.588</td>\n",
-       "      <td>0.241</td>\n",
-       "      <td>0.158</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>11</th>\n",
-       "      <td>0.064</td>\n",
-       "      <td>2.123</td>\n",
-       "      <td>1.472</td>\n",
-       "      <td>0.470</td>\n",
-       "      <td>0.190</td>\n",
-       "      <td>0.382</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>12</th>\n",
-       "      <td>0.065</td>\n",
-       "      <td>2.453</td>\n",
-       "      <td>1.083</td>\n",
-       "      <td>0.660</td>\n",
-       "      <td>0.224</td>\n",
-       "      <td>0.451</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>13</th>\n",
-       "      <td>0.133</td>\n",
-       "      <td>2.393</td>\n",
-       "      <td>1.099</td>\n",
-       "      <td>0.525</td>\n",
-       "      <td>0.218</td>\n",
-       "      <td>0.358</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>14</th>\n",
-       "      <td>0.150</td>\n",
-       "      <td>2.959</td>\n",
-       "      <td>1.194</td>\n",
-       "      <td>0.447</td>\n",
-       "      <td>0.316</td>\n",
-       "      <td>0.320</td>\n",
-       "    </tr>\n",
-       "  </tbody>\n",
-       "</table>\n",
-       "</div>"
-      ],
-      "text/plain": [
-       "                rl_alpha  scaler      a      z      t  theta\n",
-       "participant_id                                              \n",
-       "0                  0.048   2.349  1.156  0.486  0.258  0.362\n",
-       "1                  0.118   2.287  0.921  0.526  0.277  0.288\n",
-       "2                  0.084   2.307  1.357  0.513  0.252  0.441\n",
-       "3                  0.069   2.491  1.176  0.480  0.332  0.433\n",
-       "4                  0.111   1.808  1.350  0.439  0.147  0.312\n",
-       "5                  0.041   2.433  1.247  0.555  0.255  0.485\n",
-       "6                  0.085   1.841  1.209  0.443  0.263  0.389\n",
-       "7                  0.071   3.062  1.203  0.546  0.225  0.096\n",
-       "8                  0.112   1.977  0.989  0.498  0.258  0.305\n",
-       "9                  0.081   2.672  1.419  0.532  0.179  0.324\n",
-       "10                 0.114   2.621  0.983  0.588  0.241  0.158\n",
-       "11                 0.064   2.123  1.472  0.470  0.190  0.382\n",
-       "12                 0.065   2.453  1.083  0.660  0.224  0.451\n",
-       "13                 0.133   2.393  1.099  0.525  0.218  0.358\n",
-       "14                 0.150   2.959  1.194  0.447  0.316  0.320"
-      ]
-     },
-     "execution_count": 5,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
+   "metadata": {},
+   "outputs": [],
    "source": [
     "GROUP_THETA = {\n",
     "    \"rl_alpha\": 0.08,  # learning rate (small -> gradual, visible learning)\n",
@@ -583,7 +233,7 @@
     "    \"t\": (0.05, 1.0),\n",
     "    \"theta\": (0.0, 1.2),\n",
     "}\n",
-    "LIST_PARAMS = list(GROUP_THETA)\n",
+    "LIST_PARAMS = list(GROUP_THETA);\n",
     "\n",
     "rng = np.random.default_rng(RANDOM_SEED)\n",
     "theta_arrays = {\n",
@@ -605,120 +255,18 @@
    "metadata": {},
    "source": [
     "## 5. Simulate the data\n",
-    "\n",
     "`rl.Simulator(config).simulate(...)` runs the full generative loop for every\n",
     "participant and trial: compute the drift from current Q-values → run the angle SSM to\n",
     "get a choice and RT → deliver feedback → update the Q-values. Passing **arrays** of\n",
-    "parameters (one value per participant) produces a balanced multi-participant panel."
+    "parameters (one value per participant) produces a balanced multi-participant panel.\n"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": null,
    "id": "887db61f",
-   "metadata": {
-    "execution": {
-     "iopub.execute_input": "2026-07-06T16:35:32.998842Z",
-     "iopub.status.busy": "2026-07-06T16:35:32.998783Z",
-     "iopub.status.idle": "2026-07-06T16:35:34.263819Z",
-     "shell.execute_reply": "2026-07-06T16:35:34.263339Z"
-    }
-   },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "rows: 2250 | columns: ['participant_id', 'trial_id', 'rt', 'response', 'feedback']\n"
-     ]
-    },
-    {
-     "data": {
-      "text/html": [
-       "<div>\n",
-       "<style scoped>\n",
-       "    .dataframe tbody tr th:only-of-type {\n",
-       "        vertical-align: middle;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe tbody tr th {\n",
-       "        vertical-align: top;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe thead th {\n",
-       "        text-align: right;\n",
-       "    }\n",
-       "</style>\n",
-       "<table border=\"1\" class=\"dataframe\">\n",
-       "  <thead>\n",
-       "    <tr style=\"text-align: right;\">\n",
-       "      <th></th>\n",
-       "      <th>participant_id</th>\n",
-       "      <th>trial_id</th>\n",
-       "      <th>rt</th>\n",
-       "      <th>response</th>\n",
-       "      <th>feedback</th>\n",
-       "    </tr>\n",
-       "  </thead>\n",
-       "  <tbody>\n",
-       "    <tr>\n",
-       "      <th>0</th>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>1.069821</td>\n",
-       "      <td>-1</td>\n",
-       "      <td>1.0</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>1</th>\n",
-       "      <td>0</td>\n",
-       "      <td>1</td>\n",
-       "      <td>1.998447</td>\n",
-       "      <td>-1</td>\n",
-       "      <td>1.0</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2</th>\n",
-       "      <td>0</td>\n",
-       "      <td>2</td>\n",
-       "      <td>1.560222</td>\n",
-       "      <td>-1</td>\n",
-       "      <td>1.0</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>3</th>\n",
-       "      <td>0</td>\n",
-       "      <td>3</td>\n",
-       "      <td>0.505802</td>\n",
-       "      <td>-1</td>\n",
-       "      <td>1.0</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>4</th>\n",
-       "      <td>0</td>\n",
-       "      <td>4</td>\n",
-       "      <td>1.074383</td>\n",
-       "      <td>-1</td>\n",
-       "      <td>1.0</td>\n",
-       "    </tr>\n",
-       "  </tbody>\n",
-       "</table>\n",
-       "</div>"
-      ],
-      "text/plain": [
-       "   participant_id  trial_id        rt  response  feedback\n",
-       "0               0         0  1.069821        -1       1.0\n",
-       "1               0         1  1.998447        -1       1.0\n",
-       "2               0         2  1.560222        -1       1.0\n",
-       "3               0         3  0.505802        -1       1.0\n",
-       "4               0         4  1.074383        -1       1.0"
-      ]
-     },
-     "execution_count": 6,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
+   "metadata": {},
+   "outputs": [],
    "source": [
     "data = rl.Simulator(ssms_config).simulate(\n",
     "    theta=theta_arrays,\n",
@@ -739,42 +287,26 @@
    "metadata": {},
    "source": [
     "Each row is one trial. The columns we care about:\n",
+    "- `participant_id`, `trial_id`: who and when.\n",
+    "- `response`: the chosen arm (-1 or 1).\n",
+    "- `rt`: response time in seconds.\n",
+    "- `feedback`: reward (0 or 1), used by the learner.\n",
     "\n",
-    "- **`participant_id`, `trial_id`** — who and when.\n",
-    "- **`response`** — the chosen arm (`-1` or `1`).\n",
-    "- **`rt`** — the response time in seconds.\n",
-    "- **`feedback`** — the reward delivered (`0` or `1`); the learner uses this to update.\n",
+    "The next cell is a quick sanity check that learning is visible in the simulated data.\n",
+    "It does three things:\n",
+    "1. bins trials into windows of 10;\n",
+    "2. computes choice accuracy as P(chose high-reward arm);\n",
+    "3. computes mean RT per bin.\n",
     "\n",
-    "Before modelling, let's confirm the participants actually **learned**. Learning shows\n",
-    "up two ways in the simulated data: choices should shift toward the high-reward arm\n",
-    "(`-1`), *and* responses should get **faster** as the value difference grows and drives\n",
-    "the drift rate up. We plot both, binned over trials:"
+    "Expected pattern: accuracy should rise above chance, and RT should decrease as values separate.\n"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": null,
    "id": "991e7115",
-   "metadata": {
-    "execution": {
-     "iopub.execute_input": "2026-07-06T16:35:34.265047Z",
-     "iopub.status.busy": "2026-07-06T16:35:34.264970Z",
-     "iopub.status.idle": "2026-07-06T16:35:34.382476Z",
-     "shell.execute_reply": "2026-07-06T16:35:34.382163Z"
-    }
-   },
-   "outputs": [
-    {
-     "data": {
-      "image/png": "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",
-      "text/plain": [
-       "<Figure size 1200x400 with 2 Axes>"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    }
-   ],
+   "metadata": {},
+   "outputs": [],
    "source": [
     "BIN = 10\n",
     "learn = data[data[\"rt\"] > 0].copy()\n",
@@ -806,62 +338,7 @@
    "id": "db9b5799",
    "metadata": {},
    "source": [
-    "## 6. Bridge the model into HSSM\n",
-    "\n",
-    "Here is the step that PR-era HSSM makes easy. `RLSSMConfig.from_ssms_model` takes the\n",
-    "**same** `ssms` model we simulated from and produces an HSSM configuration object.\n",
-    "Nothing about the model is re-specified by hand — the learning rule, the decision\n",
-    "process, the parameter list, and the crucial \"`v` is computed, not free\" fact all\n",
-    "carry over automatically."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 8,
-   "id": "e19d1bb7",
-   "metadata": {
-    "execution": {
-     "iopub.execute_input": "2026-07-06T16:35:34.383732Z",
-     "iopub.status.busy": "2026-07-06T16:35:34.383657Z",
-     "iopub.status.idle": "2026-07-06T16:35:34.695851Z",
-     "shell.execute_reply": "2026-07-06T16:35:34.695474Z"
-    }
-   },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "list_params (free params HSSM will estimate): ['rl_alpha', 'scaler', 'a', 'z', 't', 'theta']\n",
-      "extra_fields (columns read from data):        ['feedback']\n",
-      "computed (driven by the learner, not free):   {'v'}\n"
-     ]
-    }
-   ],
-   "source": [
-    "model_config = hssm.rl.RLSSMConfig.from_ssms_model(ssms_config)\n",
-    "\n",
-    "print(\"list_params (free params HSSM will estimate):\", model_config.list_params)\n",
-    "print(\"extra_fields (columns read from data):       \", model_config.extra_fields)\n",
-    "print(\n",
-    "    \"computed (driven by the learner, not free):  \",\n",
-    "    set(model_config.ssm_logp_func.computed),\n",
-    ")\n",
-    "\n",
-    "# Sanity check: the drift v is computed by the learner and is NOT a free parameter.\n",
-    "assert \"v\" in model_config.ssm_logp_func.computed\n",
-    "assert \"v\" not in model_config.list_params"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "b1f55587",
-   "metadata": {},
-   "source": [
-    "`model_config` is plain, inspectable **metadata** — parameter names, bounds, which\n",
-    "columns are read from the data, and which SSM inputs are computed by the learner. In\n",
-    "this basic tutorial we use it as-is; the later tutorials show how *editing* this\n",
-    "object (or the underlying `ssms` model) lets you build entirely custom RLSSMs."
+    "## 6. Build the HSSM model\n"
    ]
   },
   {
@@ -869,42 +346,16 @@
    "id": "f07adb27",
    "metadata": {},
    "source": [
-    "## 7. Specify hierarchical priors and build the model\n",
-    "\n",
-    "For each parameter we write a small **`hssm.Param`** describing a hierarchical\n",
-    "structure with a formula borrowed from regression notation:\n",
-    "\n",
-    "```\n",
-    "rl_alpha ~ 1 + (1 | participant_id)\n",
-    "```\n",
-    "\n",
-    "Read it as: *\"estimate a group-level intercept (`1`) plus a per-participant deviation\n",
-    "(`(1 | participant_id)`).\"* We attach two priors:\n",
-    "\n",
-    "- **`Intercept`** — a `TruncatedNormal` prior on the group mean, truncated to the\n",
-    "  parameter's valid range. This encodes a plausible starting guess without hard-coding\n",
-    "  the answer.\n",
-    "- **`1|participant_id`** — the spread of individual deviations. We give it mean **0**\n",
-    "  (so the group `Intercept` alone owns the overall location — this avoids a\n",
-    "  non-identifiability between the two) and a `HalfNormal` prior on how large the\n",
-    "  between-participant spread is.\n",
-    "\n",
-    "The helper below just stamps out this same structure for each parameter so the model\n",
-    "call stays readable."
+    "To keep this first fit readable, we use one small helper that applies the same\n",
+    "hierarchical template to every free parameter: one group mean plus participant-level\n",
+    "deviations. Later tutorials show how to customize these priors in more detail.\n"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": null,
    "id": "52e648b3",
-   "metadata": {
-    "execution": {
-     "iopub.execute_input": "2026-07-06T16:35:34.697135Z",
-     "iopub.status.busy": "2026-07-06T16:35:34.697059Z",
-     "iopub.status.idle": "2026-07-06T16:35:34.699038Z",
-     "shell.execute_reply": "2026-07-06T16:35:34.698745Z"
-    }
-   },
+   "metadata": {},
    "outputs": [],
    "source": [
     "# Prior on the per-participant deviations: mean 0, with a learned spread (sigma).\n",
@@ -926,7 +377,7 @@
     "            ),\n",
     "            \"1|participant_id\": PARTICIPANT_EFFECT_PRIOR,\n",
     "        },\n",
-    "    )"
+    "    )\n"
    ]
   },
   {
@@ -934,58 +385,23 @@
    "id": "f0cdcee8",
    "metadata": {},
    "source": [
-    "Now we build the model. A few arguments deserve a note:\n",
-    "\n",
-    "- **`data`** and **`model_config`** wire the trial panel to the bridged model.\n",
-    "- **`p_outlier=0` / `lapse=None`** turn off the outlier/lapse mixture — one fewer\n",
-    "  moving part for a first fit.\n",
-    "- **`process_initvals=False`** is **important for RLSSMs.** It tells HSSM to start the\n",
-    "  sampler from the prior rather than from processed initial values; the latter can\n",
-    "  place the RLSSM chain in a bad region where the gradient explodes and sampling\n",
-    "  stalls. (If you ever see the sampler make no progress with near-zero step size,\n",
-    "  this is the first thing to set.)"
+    "A few arguments deserve a quick note:\n",
+    "- **`model=\"2AB_RW_Angle\"`** tells HSSM to use the same preset we simulated from.\n",
+    "- **`include=[...]`** applies the same hierarchical prior template to each free parameter.\n",
+    "- **`p_outlier=0` / `lapse=None`** turn off the outlier/lapse mixture for this first fit.\n",
+    "- **`process_initvals=False`** is the main RLSSM-specific setting to remember.\n"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": null,
    "id": "f44b2a62",
-   "metadata": {
-    "execution": {
-     "iopub.execute_input": "2026-07-06T16:35:34.700155Z",
-     "iopub.status.busy": "2026-07-06T16:35:34.700090Z",
-     "iopub.status.idle": "2026-07-06T16:35:34.915394Z",
-     "shell.execute_reply": "2026-07-06T16:35:34.915018Z"
-    }
-   },
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "You supplied a model '2AB_RW_Angle', which is currently not supported in the ssm_simulators package. An error will be thrown when sampling from the random variable or when using any posterior or prior predictive sampling methods.\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Model initialized successfully.\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "participants: 15 | trials/participant: 150\n",
-      "free parameters: ['rl_alpha', 'scaler', 'a', 'z', 't', 'theta']\n"
-     ]
-    }
-   ],
+   "metadata": {},
+   "outputs": [],
    "source": [
     "model = hssm.RLSSM(\n",
     "    data=data,\n",
-    "    model_config=model_config,\n",
+    "    model=\"2AB_RW_Angle\",\n",
     "    p_outlier=0,\n",
     "    lapse=None,\n",
     "    process_initvals=False,\n",
@@ -1001,104 +417,9 @@
     "\n",
     "print(\"participants:\", model.n_participants, \"| trials/participant:\", model.n_trials)\n",
     "print(\"free parameters:\", list(model.params.keys()))\n",
+    "assert model.model_name == \"2AB_RW_Angle\"\n",
     "assert \"rl_alpha\" in model.params\n",
-    "assert \"v\" not in model.params  # computed by the learner, never sampled"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "d838b1ca",
-   "metadata": {},
-   "source": [
-    "HSSM builds on **bambi** (formula layer) and **PyMC** (sampling engine). You can\n",
-    "inspect both — handy for confirming the priors and likelihood wired up as intended:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 11,
-   "id": "f246503f",
-   "metadata": {
-    "execution": {
-     "iopub.execute_input": "2026-07-06T16:35:34.916996Z",
-     "iopub.status.busy": "2026-07-06T16:35:34.916633Z",
-     "iopub.status.idle": "2026-07-06T16:35:34.918989Z",
-     "shell.execute_reply": "2026-07-06T16:35:34.918625Z"
-    }
-   },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "       Formula: c(rt, response) ~ 1 + (1|participant_id)\n",
-      "                scaler ~ 1 + (1|participant_id)\n",
-      "                a ~ 1 + (1|participant_id)\n",
-      "                z ~ 1 + (1|participant_id)\n",
-      "                t ~ 1 + (1|participant_id)\n",
-      "                theta ~ 1 + (1|participant_id)\n",
-      "        Family: SSM Family\n",
-      "          Link: rl_alpha = identity\n",
-      "                scaler = identity\n",
-      "                a = identity\n",
-      "                z = identity\n",
-      "                t = identity\n",
-      "                theta = identity\n",
-      "  Observations: 2250\n",
-      "        Priors: \n",
-      "    target = rl_alpha\n",
-      "        Common-level effects\n",
-      "            Intercept ~ TruncatedNormal(lower: 0.009999999776482582, upper: 1.0, mu: 0.15000000596046448,\n",
-      "                sigma: 0.15000000596046448)\n",
-      "        \n",
-      "        \n",
-      "        Group-level effects\n",
-      "            1|participant_id ~ Normal(mu: 0.0, sigma: HalfNormal(sigma: 0.5))\n",
-      "    target = scaler\n",
-      "        Common-level effects\n",
-      "            scaler_Intercept ~ TruncatedNormal(lower: 0.10000000149011612, upper: 5.0, mu: 2.0, sigma:\n",
-      "                0.800000011920929)\n",
-      "        \n",
-      "        \n",
-      "        Group-level effects\n",
-      "            scaler_1|participant_id ~ Normal(mu: 0.0, sigma: HalfNormal(sigma: 0.5))\n",
-      "    target = a\n",
-      "        Common-level effects\n",
-      "            a_Intercept ~ TruncatedNormal(lower: 0.30000001192092896, upper: 2.5, mu: 1.100000023841858,\n",
-      "                sigma: 0.30000001192092896)\n",
-      "        \n",
-      "        \n",
-      "        Group-level effects\n",
-      "            a_1|participant_id ~ Normal(mu: 0.0, sigma: HalfNormal(sigma: 0.5))\n",
-      "    target = z\n",
-      "        Common-level effects\n",
-      "            z_Intercept ~ TruncatedNormal(lower: 0.10000000149011612, upper: 0.8999999761581421, mu: 0.5,\n",
-      "                sigma: 0.15000000596046448)\n",
-      "        \n",
-      "        \n",
-      "        Group-level effects\n",
-      "            z_1|participant_id ~ Normal(mu: 0.0, sigma: HalfNormal(sigma: 0.5))\n",
-      "    target = t\n",
-      "        Common-level effects\n",
-      "            t_Intercept ~ TruncatedNormal(lower: 0.05000000074505806, upper: 1.0, mu: 0.25, sigma:\n",
-      "                0.10000000149011612)\n",
-      "        \n",
-      "        \n",
-      "        Group-level effects\n",
-      "            t_1|participant_id ~ Normal(mu: 0.0, sigma: HalfNormal(sigma: 0.5))\n",
-      "    target = theta\n",
-      "        Common-level effects\n",
-      "            theta_Intercept ~ TruncatedNormal(lower: 0.0, upper: 1.2000000476837158, mu: 0.3499999940395355,\n",
-      "                sigma: 0.15000000596046448)\n",
-      "        \n",
-      "        \n",
-      "        Group-level effects\n",
-      "            theta_1|participant_id ~ Normal(mu: 0.0, sigma: HalfNormal(sigma: 0.5))\n"
-     ]
-    }
-   ],
-   "source": [
-    "print(model.model)"
+    "assert \"v\" not in model.params  # computed by the learner, never sampled\n"
    ]
   },
   {
@@ -1106,15304 +427,17 @@
    "id": "23ab0dd2",
    "metadata": {},
    "source": [
-    "## 8. Sample the posterior\n",
-    "\n",
-    "We draw from the posterior with the **NumPyro NUTS** sampler (fast, JAX-based). This\n",
-    "is the step that \"learns\" the parameters from data. At `FULL_RUN` scale this takes a\n",
-    "few minutes; at doc scale it is deliberately short."
+    "## 7. Sample the posterior\n",
+    "We now draw from the posterior. This is the step that learns the parameters from data. In this quick tutorial\n",
+    "setup, sampling is intentionally short.\n"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 12,
+   "execution_count": null,
    "id": "e4bb5cd3",
-   "metadata": {
-    "execution": {
-     "iopub.execute_input": "2026-07-06T16:35:34.919910Z",
-     "iopub.status.busy": "2026-07-06T16:35:34.919835Z",
-     "iopub.status.idle": "2026-07-06T16:44:43.617653Z",
-     "shell.execute_reply": "2026-07-06T16:44:43.617081Z"
-    }
-   },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Using default initvals. \n",
-      "\n"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "NUTS[numpyro]: [rl_alpha_Intercept, rl_alpha_1|participant_id_sigma, rl_alpha_1|participant_id_offset, scaler_Intercept, scaler_1|participant_id_sigma, scaler_1|participant_id_offset, a_Intercept, a_1|participant_id_sigma, a_1|participant_id_offset, z_Intercept, z_1|participant_id_sigma, z_1|participant_id_offset, t_Intercept, t_1|participant_id_sigma, t_1|participant_id_offset, theta_Intercept, theta_1|participant_id_sigma, theta_1|participant_id_offset]\n"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "  0%|          | 0/1500 [00:00<?, ?it/s]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   0%|          | 0/1500 [00:10<?, ?it/s, 255 steps of size 2.06e-02. acc. prob=0.84]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   3%|▎         | 42/1500 [00:10<05:49,  4.17it/s, 127 steps of size 1.03e-02. acc. prob=0.83]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   3%|▎         | 43/1500 [00:10<05:53,  4.12it/s, 255 steps of size 1.39e-02. acc. prob=0.84]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   3%|▎         | 44/1500 [00:10<05:58,  4.06it/s, 255 steps of size 1.20e-02. acc. prob=0.84]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   3%|▎         | 45/1500 [00:11<06:05,  3.98it/s, 255 steps of size 1.60e-02. acc. prob=0.84]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   3%|▎         | 46/1500 [00:11<06:13,  3.89it/s, 255 steps of size 1.49e-02. acc. prob=0.84]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   3%|▎         | 47/1500 [00:11<06:23,  3.79it/s, 255 steps of size 1.50e-02. acc. prob=0.84]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   3%|▎         | 48/1500 [00:12<06:34,  3.68it/s, 255 steps of size 9.76e-03. acc. prob=0.84]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   3%|▎         | 49/1500 [00:12<07:59,  3.03it/s, 511 steps of size 1.27e-02. acc. prob=0.84]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   3%|▎         | 50/1500 [00:13<07:58,  3.03it/s, 255 steps of size 1.66e-02. acc. prob=0.85]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   3%|▎         | 51/1500 [00:13<07:57,  3.04it/s, 255 steps of size 1.33e-02. acc. prob=0.84]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   3%|▎         | 52/1500 [00:13<07:55,  3.05it/s, 255 steps of size 1.30e-02. acc. prob=0.85]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   4%|▎         | 53/1500 [00:13<07:53,  3.06it/s, 255 steps of size 1.55e-02. acc. prob=0.85]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   4%|▎         | 54/1500 [00:14<07:53,  3.06it/s, 255 steps of size 8.92e-03. acc. prob=0.84]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   4%|▎         | 55/1500 [00:14<09:59,  2.41it/s, 511 steps of size 1.17e-02. acc. prob=0.85]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   4%|▎         | 56/1500 [00:15<09:22,  2.57it/s, 255 steps of size 1.38e-02. acc. prob=0.85]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   4%|▍         | 57/1500 [00:15<09:01,  2.66it/s, 255 steps of size 1.44e-02. acc. prob=0.85]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   4%|▍         | 58/1500 [00:15<08:41,  2.77it/s, 255 steps of size 1.79e-02. acc. prob=0.85]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   4%|▍         | 59/1500 [00:16<08:30,  2.83it/s, 255 steps of size 2.09e-02. acc. prob=0.85]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   4%|▍         | 60/1500 [00:16<07:08,  3.36it/s, 127 steps of size 9.32e-03. acc. prob=0.85]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   4%|▍         | 61/1500 [00:16<07:19,  3.27it/s, 255 steps of size 1.21e-02. acc. prob=0.85]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   4%|▍         | 62/1500 [00:17<07:27,  3.22it/s, 255 steps of size 1.53e-02. acc. prob=0.85]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   4%|▍         | 63/1500 [00:17<06:23,  3.75it/s, 127 steps of size 1.52e-02. acc. prob=0.85]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   4%|▍         | 64/1500 [00:17<06:47,  3.52it/s, 255 steps of size 1.33e-02. acc. prob=0.85]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   4%|▍         | 65/1500 [00:17<07:04,  3.38it/s, 255 steps of size 1.53e-02. acc. prob=0.85]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   4%|▍         | 66/1500 [00:18<07:16,  3.28it/s, 255 steps of size 1.32e-02. acc. prob=0.85]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   4%|▍         | 67/1500 [00:18<07:24,  3.22it/s, 255 steps of size 1.64e-02. acc. prob=0.85]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   5%|▍         | 68/1500 [00:18<07:30,  3.18it/s, 255 steps of size 9.29e-03. acc. prob=0.85]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   5%|▍         | 69/1500 [00:19<09:54,  2.41it/s, 511 steps of size 1.05e-02. acc. prob=0.85]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   5%|▍         | 70/1500 [00:20<11:35,  2.06it/s, 511 steps of size 1.10e-02. acc. prob=0.85]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   5%|▍         | 71/1500 [00:20<10:34,  2.25it/s, 255 steps of size 1.40e-02. acc. prob=0.86]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   5%|▍         | 72/1500 [00:20<09:46,  2.43it/s, 255 steps of size 7.65e-03. acc. prob=0.85]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   5%|▍         | 73/1500 [00:21<11:39,  2.04it/s, 511 steps of size 9.74e-03. acc. prob=0.85]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   5%|▍         | 74/1500 [00:21<10:28,  2.27it/s, 255 steps of size 1.21e-02. acc. prob=0.86]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   5%|▌         | 75/1500 [00:22<09:42,  2.45it/s, 255 steps of size 1.50e-02. acc. prob=0.86]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   5%|▌         | 76/1500 [00:22<09:14,  2.57it/s, 255 steps of size 1.89e-02. acc. prob=0.86]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   5%|▌         | 77/1500 [00:22<07:40,  3.09it/s, 127 steps of size 6.58e-03. acc. prob=0.85]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   5%|▌         | 78/1500 [00:23<10:05,  2.35it/s, 511 steps of size 8.28e-03. acc. prob=0.85]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   5%|▌         | 79/1500 [00:24<11:53,  1.99it/s, 511 steps of size 9.80e-03. acc. prob=0.86]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   5%|▌         | 80/1500 [00:24<10:37,  2.23it/s, 255 steps of size 1.14e-02. acc. prob=0.86]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   5%|▌         | 81/1500 [00:24<09:48,  2.41it/s, 255 steps of size 1.43e-02. acc. prob=0.86]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   5%|▌         | 82/1500 [00:24<08:03,  2.93it/s, 127 steps of size 7.53e-03. acc. prob=0.86]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   6%|▌         | 83/1500 [00:25<10:22,  2.28it/s, 511 steps of size 9.41e-03. acc. prob=0.86]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   6%|▌         | 84/1500 [00:26<11:56,  1.98it/s, 511 steps of size 1.01e-02. acc. prob=0.86]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   6%|▌         | 85/1500 [00:26<10:39,  2.21it/s, 255 steps of size 9.59e-03. acc. prob=0.86]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   6%|▌         | 86/1500 [00:26<09:44,  2.42it/s, 255 steps of size 1.07e-02. acc. prob=0.86]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   6%|▌         | 87/1500 [00:27<09:07,  2.58it/s, 255 steps of size 1.15e-02. acc. prob=0.86]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   6%|▌         | 88/1500 [00:27<08:40,  2.71it/s, 255 steps of size 1.43e-02. acc. prob=0.86]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   6%|▌         | 89/1500 [00:27<08:21,  2.81it/s, 255 steps of size 1.77e-02. acc. prob=0.86]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   6%|▌         | 90/1500 [00:28<08:08,  2.89it/s, 255 steps of size 1.53e-02. acc. prob=0.86]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   6%|▌         | 91/1500 [00:28<07:58,  2.94it/s, 255 steps of size 1.80e-02. acc. prob=0.86]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   6%|▌         | 92/1500 [00:28<07:54,  2.97it/s, 255 steps of size 2.23e-02. acc. prob=0.86]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   6%|▌         | 93/1500 [00:28<06:42,  3.49it/s, 127 steps of size 1.31e-02. acc. prob=0.86]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   6%|▋         | 94/1500 [00:29<07:00,  3.34it/s, 255 steps of size 1.53e-02. acc. prob=0.86]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   6%|▋         | 95/1500 [00:29<07:22,  3.17it/s, 255 steps of size 1.61e-02. acc. prob=0.86]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   6%|▋         | 96/1500 [00:30<07:30,  3.12it/s, 255 steps of size 1.92e-02. acc. prob=0.86]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   6%|▋         | 97/1500 [00:30<06:23,  3.65it/s, 127 steps of size 1.96e-02. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   7%|▋         | 98/1500 [00:30<05:39,  4.13it/s, 127 steps of size 2.29e-02. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   7%|▋         | 99/1500 [00:30<05:06,  4.58it/s, 127 steps of size 1.37e-02. acc. prob=0.86]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   7%|▋         | 100/1500 [00:30<05:54,  3.95it/s, 255 steps of size 1.66e-02. acc. prob=0.86]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   7%|▋         | 101/1500 [00:31<08:44,  2.67it/s, 511 steps of size 1.99e-01. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   7%|▋         | 103/1500 [00:31<05:47,  4.02it/s, 127 steps of size 6.92e-02. acc. prob=0.86]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   7%|▋         | 105/1500 [00:31<04:36,  5.04it/s, 127 steps of size 7.13e-02. acc. prob=0.86]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   7%|▋         | 107/1500 [00:32<03:57,  5.86it/s, 127 steps of size 9.14e-02. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   7%|▋         | 108/1500 [00:32<03:55,  5.91it/s, 127 steps of size 8.97e-02. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   7%|▋         | 110/1500 [00:32<03:30,  6.60it/s, 127 steps of size 8.98e-02. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   7%|▋         | 112/1500 [00:32<02:56,  7.88it/s, 63 steps of size 3.15e-02. acc. prob=0.86] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   8%|▊         | 113/1500 [00:33<03:53,  5.93it/s, 255 steps of size 4.29e-02. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   8%|▊         | 114/1500 [00:33<03:52,  5.96it/s, 127 steps of size 5.77e-02. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   8%|▊         | 115/1500 [00:33<03:51,  5.98it/s, 127 steps of size 7.05e-02. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   8%|▊         | 116/1500 [00:33<03:50,  6.00it/s, 127 steps of size 9.54e-02. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   8%|▊         | 118/1500 [00:33<03:01,  7.60it/s, 63 steps of size 6.72e-02. acc. prob=0.87] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   8%|▊         | 120/1500 [00:33<02:57,  7.78it/s, 127 steps of size 8.16e-02. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   8%|▊         | 122/1500 [00:34<02:35,  8.84it/s, 63 steps of size 1.30e-01. acc. prob=0.87] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   8%|▊         | 124/1500 [00:34<02:12, 10.39it/s, 63 steps of size 2.90e-02. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   8%|▊         | 125/1500 [00:34<03:15,  7.05it/s, 255 steps of size 3.90e-02. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   8%|▊         | 126/1500 [00:34<03:22,  6.80it/s, 127 steps of size 5.05e-02. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   8%|▊         | 127/1500 [00:34<03:34,  6.39it/s, 127 steps of size 6.09e-02. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   9%|▊         | 129/1500 [00:35<03:08,  7.26it/s, 127 steps of size 8.44e-02. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   9%|▊         | 131/1500 [00:35<03:00,  7.59it/s, 127 steps of size 1.10e-01. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   9%|▉         | 133/1500 [00:35<02:36,  8.74it/s, 63 steps of size 9.77e-02. acc. prob=0.87] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   9%|▉         | 135/1500 [00:36<03:16,  6.95it/s, 255 steps of size 3.17e-02. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   9%|▉         | 136/1500 [00:36<04:03,  5.60it/s, 255 steps of size 4.17e-02. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   9%|▉         | 137/1500 [00:36<03:58,  5.71it/s, 127 steps of size 5.46e-02. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   9%|▉         | 138/1500 [00:36<03:54,  5.80it/s, 127 steps of size 6.41e-02. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   9%|▉         | 140/1500 [00:36<03:26,  6.58it/s, 127 steps of size 8.34e-02. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   9%|▉         | 142/1500 [00:37<02:51,  7.93it/s, 63 steps of size 1.06e-01. acc. prob=0.87] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  10%|▉         | 144/1500 [00:37<02:20,  9.65it/s, 31 steps of size 1.56e-01. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  10%|▉         | 147/1500 [00:37<01:43, 13.04it/s, 31 steps of size 7.64e-02. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  10%|▉         | 149/1500 [00:37<01:45, 12.83it/s, 63 steps of size 6.66e-02. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  10%|█         | 151/1500 [00:37<01:46, 12.69it/s, 63 steps of size 8.01e-01. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  10%|█         | 154/1500 [00:37<01:48, 12.46it/s, 127 steps of size 6.08e-02. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  10%|█         | 156/1500 [00:38<01:48, 12.41it/s, 63 steps of size 8.28e-02. acc. prob=0.87] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  11%|█         | 158/1500 [00:38<02:03, 10.87it/s, 127 steps of size 6.18e-02. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  11%|█         | 160/1500 [00:38<01:59, 11.25it/s, 63 steps of size 8.58e-02. acc. prob=0.87] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  11%|█         | 162/1500 [00:38<01:53, 11.75it/s, 55 steps of size 1.08e-01. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  11%|█         | 164/1500 [00:38<01:44, 12.83it/s, 31 steps of size 2.81e-02. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  11%|█         | 165/1500 [00:39<02:41,  8.28it/s, 255 steps of size 3.82e-02. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  11%|█         | 166/1500 [00:39<02:52,  7.75it/s, 127 steps of size 5.12e-02. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  11%|█         | 167/1500 [00:39<03:02,  7.31it/s, 127 steps of size 6.79e-02. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  11%|█▏        | 169/1500 [00:39<02:23,  9.30it/s, 31 steps of size 1.12e-01. acc. prob=0.87] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  11%|█▏        | 171/1500 [00:39<02:10, 10.19it/s, 63 steps of size 1.94e-01. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  12%|█▏        | 173/1500 [00:40<02:48,  7.88it/s, 255 steps of size 3.45e-02. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  12%|█▏        | 174/1500 [00:40<02:57,  7.47it/s, 127 steps of size 4.65e-02. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  12%|█▏        | 175/1500 [00:40<03:05,  7.13it/s, 127 steps of size 6.31e-02. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  12%|█▏        | 177/1500 [00:40<02:35,  8.51it/s, 63 steps of size 7.68e-02. acc. prob=0.87] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  12%|█▏        | 179/1500 [00:40<02:18,  9.55it/s, 63 steps of size 1.22e-01. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  12%|█▏        | 181/1500 [00:40<02:07, 10.32it/s, 63 steps of size 1.32e-01. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  12%|█▏        | 182/1500 [00:40<02:15,  9.75it/s, 95 steps of size 1.32e-01. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  12%|█▏        | 184/1500 [00:41<01:55, 11.37it/s, 31 steps of size 9.23e-02. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  12%|█▏        | 186/1500 [00:41<01:52, 11.67it/s, 63 steps of size 1.19e-01. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  13%|█▎        | 188/1500 [00:41<01:41, 12.88it/s, 31 steps of size 1.35e-01. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  13%|█▎        | 191/1500 [00:41<01:43, 12.63it/s, 127 steps of size 5.55e-02. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  13%|█▎        | 193/1500 [00:41<01:59, 10.95it/s, 127 steps of size 6.88e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  13%|█▎        | 195/1500 [00:42<01:55, 11.31it/s, 63 steps of size 1.10e-01. acc. prob=0.88] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  13%|█▎        | 197/1500 [00:42<01:44, 12.43it/s, 63 steps of size 1.56e-01. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  13%|█▎        | 200/1500 [00:42<01:31, 14.26it/s, 63 steps of size 1.22e-01. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  14%|█▎        | 203/1500 [00:42<01:23, 15.55it/s, 63 steps of size 4.88e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  14%|█▎        | 204/1500 [00:42<01:41, 12.72it/s, 127 steps of size 6.00e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  14%|█▎        | 205/1500 [00:42<02:00, 10.75it/s, 127 steps of size 7.28e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  14%|█▍        | 207/1500 [00:42<01:55, 11.23it/s, 63 steps of size 8.17e-02. acc. prob=0.88] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  14%|█▍        | 209/1500 [00:43<01:52, 11.50it/s, 63 steps of size 8.45e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  14%|█▍        | 211/1500 [00:43<01:50, 11.64it/s, 63 steps of size 1.25e-01. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  14%|█▍        | 213/1500 [00:43<01:41, 12.68it/s, 31 steps of size 1.55e-01. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  14%|█▍        | 216/1500 [00:43<01:22, 15.60it/s, 31 steps of size 1.19e-01. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  15%|█▍        | 218/1500 [00:43<01:28, 14.49it/s, 63 steps of size 1.04e-01. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  15%|█▍        | 220/1500 [00:43<01:25, 14.98it/s, 31 steps of size 4.10e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  15%|█▍        | 221/1500 [00:43<01:46, 12.03it/s, 127 steps of size 5.11e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  15%|█▍        | 222/1500 [00:44<02:06, 10.14it/s, 127 steps of size 6.18e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  15%|█▍        | 223/1500 [00:44<02:23,  8.89it/s, 127 steps of size 7.02e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  15%|█▌        | 225/1500 [00:44<02:08,  9.95it/s, 63 steps of size 9.04e-02. acc. prob=0.88] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  15%|█▌        | 227/1500 [00:44<01:59, 10.67it/s, 63 steps of size 9.47e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  15%|█▌        | 229/1500 [00:44<01:53, 11.18it/s, 63 steps of size 3.08e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  15%|█▌        | 230/1500 [00:44<02:11,  9.64it/s, 127 steps of size 3.81e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  15%|█▌        | 231/1500 [00:45<02:27,  8.57it/s, 127 steps of size 4.63e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  15%|█▌        | 232/1500 [00:45<02:43,  7.75it/s, 127 steps of size 5.67e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  16%|█▌        | 234/1500 [00:45<02:19,  9.10it/s, 63 steps of size 6.80e-02. acc. prob=0.88] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  16%|█▌        | 236/1500 [00:45<02:06, 10.03it/s, 63 steps of size 9.40e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  16%|█▌        | 238/1500 [00:45<02:17,  9.19it/s, 127 steps of size 4.62e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  16%|█▌        | 239/1500 [00:46<02:31,  8.33it/s, 127 steps of size 5.32e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  16%|█▌        | 240/1500 [00:46<02:43,  7.69it/s, 127 steps of size 6.11e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  16%|█▌        | 242/1500 [00:46<02:20,  8.97it/s, 63 steps of size 7.77e-02. acc. prob=0.88] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  16%|█▋        | 244/1500 [00:46<02:06,  9.92it/s, 63 steps of size 1.09e-01. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  16%|█▋        | 246/1500 [00:46<01:58, 10.62it/s, 63 steps of size 6.17e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  16%|█▋        | 247/1500 [00:46<02:16,  9.20it/s, 127 steps of size 6.99e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  17%|█▋        | 249/1500 [00:47<02:03, 10.09it/s, 63 steps of size 8.62e-02. acc. prob=0.88] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  17%|█▋        | 251/1500 [00:47<01:47, 11.59it/s, 31 steps of size 6.82e-01. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  17%|█▋        | 254/1500 [00:47<01:45, 11.80it/s, 127 steps of size 4.70e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  17%|█▋        | 255/1500 [00:47<02:01, 10.23it/s, 127 steps of size 4.90e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  17%|█▋        | 256/1500 [00:47<02:17,  9.05it/s, 127 steps of size 6.02e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  17%|█▋        | 258/1500 [00:47<02:22,  8.70it/s, 127 steps of size 7.33e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  17%|█▋        | 260/1500 [00:48<02:25,  8.50it/s, 127 steps of size 4.33e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  17%|█▋        | 261/1500 [00:48<02:36,  7.91it/s, 127 steps of size 5.75e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  18%|█▊        | 263/1500 [00:48<02:16,  9.06it/s, 63 steps of size 8.41e-02. acc. prob=0.88] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  18%|█▊        | 265/1500 [00:48<02:04,  9.95it/s, 63 steps of size 2.07e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  18%|█▊        | 266/1500 [00:49<02:58,  6.92it/s, 255 steps of size 2.86e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  18%|█▊        | 267/1500 [00:49<03:03,  6.73it/s, 127 steps of size 3.98e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  18%|█▊        | 268/1500 [00:49<03:07,  6.57it/s, 127 steps of size 5.24e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  18%|█▊        | 269/1500 [00:49<03:10,  6.45it/s, 127 steps of size 7.05e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  18%|█▊        | 271/1500 [00:49<02:32,  8.06it/s, 63 steps of size 9.48e-02. acc. prob=0.88] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  18%|█▊        | 273/1500 [00:49<02:02,  9.99it/s, 31 steps of size 5.24e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  18%|█▊        | 274/1500 [00:49<02:19,  8.79it/s, 127 steps of size 7.15e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  18%|█▊        | 275/1500 [00:50<02:33,  7.97it/s, 127 steps of size 6.35e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  18%|█▊        | 277/1500 [00:50<02:11,  9.27it/s, 63 steps of size 4.80e-02. acc. prob=0.88] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  19%|█▊        | 278/1500 [00:50<02:26,  8.33it/s, 127 steps of size 6.45e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  19%|█▊        | 280/1500 [00:50<02:09,  9.42it/s, 63 steps of size 8.30e-02. acc. prob=0.88] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  19%|█▉        | 282/1500 [00:50<02:00, 10.14it/s, 63 steps of size 6.72e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  19%|█▉        | 284/1500 [00:50<01:52, 10.78it/s, 63 steps of size 9.87e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  19%|█▉        | 286/1500 [00:51<01:48, 11.22it/s, 63 steps of size 1.03e-01. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  19%|█▉        | 288/1500 [00:51<01:37, 12.41it/s, 31 steps of size 1.67e-01. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  19%|█▉        | 290/1500 [00:51<01:30, 13.35it/s, 63 steps of size 7.59e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  19%|█▉        | 292/1500 [00:51<01:33, 12.98it/s, 63 steps of size 5.49e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  20%|█▉        | 293/1500 [00:51<01:51, 10.80it/s, 127 steps of size 6.54e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  20%|█▉        | 295/1500 [00:51<01:47, 11.24it/s, 63 steps of size 9.59e-02. acc. prob=0.88] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  20%|█▉        | 297/1500 [00:52<01:43, 11.57it/s, 63 steps of size 1.01e-01. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  20%|█▉        | 299/1500 [00:52<02:13,  8.97it/s, 191 steps of size 2.84e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  20%|██        | 300/1500 [00:52<03:02,  6.58it/s, 255 steps of size 3.67e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  20%|██        | 301/1500 [00:52<03:05,  6.48it/s, 127 steps of size 4.73e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  20%|██        | 303/1500 [00:53<02:51,  6.99it/s, 127 steps of size 3.31e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  20%|██        | 304/1500 [00:53<02:56,  6.78it/s, 127 steps of size 4.21e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  20%|██        | 305/1500 [00:53<03:00,  6.61it/s, 127 steps of size 5.22e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  20%|██        | 307/1500 [00:53<02:27,  8.11it/s, 63 steps of size 8.19e-02. acc. prob=0.88] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  21%|██        | 309/1500 [00:53<02:09,  9.22it/s, 63 steps of size 5.99e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  21%|██        | 310/1500 [00:53<02:22,  8.34it/s, 127 steps of size 7.04e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  21%|██        | 312/1500 [00:54<02:23,  8.28it/s, 127 steps of size 4.55e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  21%|██        | 313/1500 [00:54<02:34,  7.70it/s, 127 steps of size 5.62e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  21%|██        | 314/1500 [00:54<02:43,  7.27it/s, 127 steps of size 6.92e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  21%|██        | 316/1500 [00:54<02:16,  8.68it/s, 63 steps of size 8.19e-02. acc. prob=0.88] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  21%|██        | 318/1500 [00:54<02:01,  9.72it/s, 63 steps of size 5.32e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  21%|██▏       | 319/1500 [00:54<02:16,  8.63it/s, 127 steps of size 6.24e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  21%|██▏       | 321/1500 [00:55<02:02,  9.61it/s, 63 steps of size 7.54e-02. acc. prob=0.88] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  22%|██▏       | 323/1500 [00:55<01:54, 10.28it/s, 63 steps of size 9.51e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  22%|██▏       | 325/1500 [00:55<01:48, 10.85it/s, 63 steps of size 1.20e-01. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  22%|██▏       | 327/1500 [00:55<01:59,  9.81it/s, 127 steps of size 5.19e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  22%|██▏       | 329/1500 [00:55<01:51, 10.47it/s, 63 steps of size 7.64e-02. acc. prob=0.88] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  22%|██▏       | 331/1500 [00:56<01:46, 10.96it/s, 63 steps of size 9.74e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  22%|██▏       | 333/1500 [00:56<01:43, 11.26it/s, 63 steps of size 9.43e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  22%|██▏       | 335/1500 [00:56<01:40, 11.60it/s, 63 steps of size 9.75e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  22%|██▏       | 337/1500 [00:56<01:31, 12.67it/s, 63 steps of size 1.25e-01. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  23%|██▎       | 339/1500 [00:56<01:32, 12.54it/s, 63 steps of size 8.90e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  23%|██▎       | 341/1500 [00:56<01:33, 12.40it/s, 63 steps of size 6.60e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  23%|██▎       | 342/1500 [00:56<01:50, 10.47it/s, 127 steps of size 5.79e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  23%|██▎       | 343/1500 [00:57<02:06,  9.15it/s, 127 steps of size 7.04e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  23%|██▎       | 345/1500 [00:57<01:54, 10.10it/s, 63 steps of size 1.04e-01. acc. prob=0.88] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  23%|██▎       | 347/1500 [00:57<01:47, 10.76it/s, 63 steps of size 9.87e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  23%|██▎       | 349/1500 [00:57<02:21,  8.14it/s, 255 steps of size 3.72e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  23%|██▎       | 350/1500 [00:58<02:30,  7.65it/s, 127 steps of size 4.39e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  23%|██▎       | 351/1500 [00:58<02:38,  7.27it/s, 127 steps of size 5.24e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  23%|██▎       | 352/1500 [00:58<02:46,  6.90it/s, 127 steps of size 2.27e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  24%|██▎       | 353/1500 [00:58<03:47,  5.05it/s, 255 steps of size 2.71e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  24%|██▎       | 354/1500 [00:59<04:27,  4.28it/s, 255 steps of size 3.13e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  24%|██▎       | 355/1500 [00:59<04:07,  4.62it/s, 127 steps of size 3.78e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  24%|██▎       | 356/1500 [00:59<03:51,  4.94it/s, 127 steps of size 4.51e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  24%|██▍       | 357/1500 [00:59<03:39,  5.21it/s, 127 steps of size 5.23e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  24%|██▍       | 358/1500 [00:59<03:31,  5.41it/s, 127 steps of size 6.21e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  24%|██▍       | 359/1500 [00:59<03:24,  5.58it/s, 127 steps of size 7.29e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  24%|██▍       | 361/1500 [01:00<02:54,  6.52it/s, 127 steps of size 2.27e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  24%|██▍       | 362/1500 [01:00<03:43,  5.10it/s, 255 steps of size 2.73e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  24%|██▍       | 363/1500 [01:00<04:21,  4.34it/s, 255 steps of size 3.29e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  24%|██▍       | 364/1500 [01:00<04:03,  4.66it/s, 127 steps of size 3.95e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  24%|██▍       | 365/1500 [01:01<03:34,  5.29it/s, 91 steps of size 4.04e-02. acc. prob=0.88] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  24%|██▍       | 366/1500 [01:01<03:17,  5.73it/s, 104 steps of size 4.57e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  24%|██▍       | 367/1500 [01:01<03:14,  5.82it/s, 127 steps of size 5.43e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  25%|██▍       | 368/1500 [01:01<03:13,  5.86it/s, 127 steps of size 6.20e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  25%|██▍       | 370/1500 [01:01<02:27,  7.68it/s, 63 steps of size 7.00e-02. acc. prob=0.88] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  25%|██▍       | 372/1500 [01:01<02:23,  7.86it/s, 127 steps of size 6.16e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  25%|██▍       | 374/1500 [01:02<02:05,  8.94it/s, 63 steps of size 7.11e-02. acc. prob=0.88] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  25%|██▌       | 376/1500 [01:02<01:48, 10.38it/s, 38 steps of size 8.51e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  25%|██▌       | 378/1500 [01:02<01:42, 10.93it/s, 63 steps of size 1.11e-01. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  25%|██▌       | 380/1500 [01:02<01:53,  9.88it/s, 127 steps of size 6.08e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  25%|██▌       | 382/1500 [01:02<01:46, 10.50it/s, 63 steps of size 3.78e-02. acc. prob=0.88] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  26%|██▌       | 383/1500 [01:02<02:00,  9.28it/s, 127 steps of size 4.32e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  26%|██▌       | 384/1500 [01:03<02:15,  8.21it/s, 127 steps of size 5.05e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  26%|██▌       | 385/1500 [01:03<02:26,  7.59it/s, 127 steps of size 5.57e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  26%|██▌       | 387/1500 [01:03<02:04,  8.94it/s, 63 steps of size 7.27e-02. acc. prob=0.88] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  26%|██▌       | 389/1500 [01:03<01:43, 10.75it/s, 29 steps of size 8.36e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  26%|██▌       | 391/1500 [01:03<01:38, 11.23it/s, 63 steps of size 3.37e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  26%|██▌       | 392/1500 [01:03<01:54,  9.66it/s, 127 steps of size 3.80e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  26%|██▌       | 393/1500 [01:04<02:09,  8.57it/s, 127 steps of size 4.46e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  26%|██▋       | 394/1500 [01:04<02:27,  7.52it/s, 127 steps of size 5.22e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  26%|██▋       | 395/1500 [01:04<02:37,  7.00it/s, 127 steps of size 6.02e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  26%|██▋       | 397/1500 [01:04<02:13,  8.25it/s, 63 steps of size 8.02e-02. acc. prob=0.88] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  27%|██▋       | 399/1500 [01:04<01:57,  9.36it/s, 63 steps of size 9.31e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  27%|██▋       | 401/1500 [01:04<01:47, 10.21it/s, 63 steps of size 6.34e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  27%|██▋       | 403/1500 [01:05<01:56,  9.43it/s, 127 steps of size 6.62e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  27%|██▋       | 405/1500 [01:05<01:52,  9.75it/s, 63 steps of size 8.70e-02. acc. prob=0.88] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  27%|██▋       | 406/1500 [01:05<02:05,  8.70it/s, 63 steps of size 9.88e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  27%|██▋       | 408/1500 [01:05<01:55,  9.48it/s, 63 steps of size 7.52e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  27%|██▋       | 409/1500 [01:05<01:56,  9.33it/s, 63 steps of size 8.79e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  27%|██▋       | 410/1500 [01:05<01:56,  9.33it/s, 63 steps of size 9.98e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  27%|██▋       | 412/1500 [01:06<02:04,  8.71it/s, 127 steps of size 4.48e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  28%|██▊       | 413/1500 [01:06<02:16,  7.96it/s, 127 steps of size 5.21e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  28%|██▊       | 414/1500 [01:06<02:26,  7.42it/s, 127 steps of size 5.64e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  28%|██▊       | 416/1500 [01:06<02:00,  9.03it/s, 63 steps of size 7.24e-02. acc. prob=0.88] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  28%|██▊       | 418/1500 [01:06<01:48, 10.00it/s, 63 steps of size 9.69e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  28%|██▊       | 420/1500 [01:07<01:41, 10.67it/s, 63 steps of size 1.13e-01. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  28%|██▊       | 422/1500 [01:07<01:36, 11.14it/s, 63 steps of size 1.00e-01. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  28%|██▊       | 424/1500 [01:07<01:33, 11.48it/s, 63 steps of size 4.49e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  28%|██▊       | 425/1500 [01:07<01:49,  9.84it/s, 127 steps of size 5.19e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  28%|██▊       | 426/1500 [01:07<02:03,  8.71it/s, 127 steps of size 5.72e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  29%|██▊       | 428/1500 [01:07<02:06,  8.48it/s, 127 steps of size 6.17e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  29%|██▊       | 429/1500 [01:08<02:16,  7.84it/s, 127 steps of size 2.54e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  29%|██▊       | 430/1500 [01:08<03:09,  5.65it/s, 255 steps of size 2.95e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  29%|██▊       | 431/1500 [01:08<03:49,  4.67it/s, 255 steps of size 3.38e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  29%|██▉       | 432/1500 [01:09<04:20,  4.10it/s, 255 steps of size 3.89e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  29%|██▉       | 433/1500 [01:09<03:56,  4.51it/s, 127 steps of size 3.78e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  29%|██▉       | 434/1500 [01:09<03:38,  4.87it/s, 127 steps of size 4.32e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  29%|██▉       | 435/1500 [01:09<03:26,  5.17it/s, 127 steps of size 4.96e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  29%|██▉       | 437/1500 [01:09<02:51,  6.19it/s, 127 steps of size 6.46e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  29%|██▉       | 438/1500 [01:09<02:52,  6.16it/s, 127 steps of size 5.87e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  29%|██▉       | 440/1500 [01:10<02:16,  7.74it/s, 63 steps of size 7.34e-02. acc. prob=0.88] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  29%|██▉       | 442/1500 [01:10<02:13,  7.91it/s, 127 steps of size 4.72e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  30%|██▉       | 443/1500 [01:10<02:27,  7.15it/s, 127 steps of size 5.34e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  30%|██▉       | 444/1500 [01:10<02:36,  6.77it/s, 127 steps of size 5.56e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  30%|██▉       | 445/1500 [01:10<02:40,  6.58it/s, 127 steps of size 6.40e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  30%|██▉       | 447/1500 [01:11<02:10,  8.10it/s, 63 steps of size 7.98e-02. acc. prob=0.88] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  30%|██▉       | 449/1500 [01:11<01:53,  9.27it/s, 63 steps of size 7.05e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  30%|███       | 451/1500 [01:11<01:43, 10.13it/s, 63 steps of size 7.74e-01. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  30%|███       | 454/1500 [01:11<01:35, 10.91it/s, 127 steps of size 5.97e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  30%|███       | 455/1500 [01:11<01:48,  9.63it/s, 127 steps of size 7.06e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  30%|███       | 457/1500 [01:11<01:40, 10.35it/s, 63 steps of size 1.01e-01. acc. prob=0.88] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  31%|███       | 459/1500 [01:12<01:36, 10.79it/s, 63 steps of size 1.19e-01. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  31%|███       | 461/1500 [01:12<01:26, 12.01it/s, 63 steps of size 8.34e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  31%|███       | 463/1500 [01:12<01:26, 12.04it/s, 63 steps of size 5.31e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  31%|███       | 465/1500 [01:12<01:25, 12.07it/s, 63 steps of size 9.50e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  31%|███       | 467/1500 [01:12<01:18, 13.09it/s, 31 steps of size 7.89e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  31%|███▏      | 469/1500 [01:12<01:20, 12.85it/s, 63 steps of size 7.53e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  31%|███▏      | 471/1500 [01:13<01:21, 12.67it/s, 63 steps of size 1.22e-01. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  32%|███▏      | 473/1500 [01:13<01:58,  8.66it/s, 255 steps of size 2.23e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  32%|███▏      | 474/1500 [01:13<02:37,  6.53it/s, 255 steps of size 2.99e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  32%|███▏      | 475/1500 [01:13<02:39,  6.44it/s, 127 steps of size 4.02e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  32%|███▏      | 476/1500 [01:14<02:40,  6.37it/s, 127 steps of size 5.18e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  32%|███▏      | 477/1500 [01:14<02:42,  6.31it/s, 127 steps of size 6.91e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  32%|███▏      | 479/1500 [01:14<02:11,  7.77it/s, 63 steps of size 9.78e-02. acc. prob=0.88] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  32%|███▏      | 481/1500 [01:14<01:46,  9.61it/s, 63 steps of size 1.19e-01. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  32%|███▏      | 484/1500 [01:14<01:21, 12.42it/s, 63 steps of size 1.08e-01. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  32%|███▏      | 486/1500 [01:14<01:22, 12.35it/s, 63 steps of size 4.35e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  32%|███▏      | 487/1500 [01:15<01:36, 10.48it/s, 127 steps of size 5.66e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  33%|███▎      | 488/1500 [01:15<01:50,  9.18it/s, 127 steps of size 5.49e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  33%|███▎      | 490/1500 [01:15<01:39, 10.11it/s, 63 steps of size 7.10e-02. acc. prob=0.88] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  33%|███▎      | 492/1500 [01:15<01:33, 10.76it/s, 63 steps of size 9.88e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  33%|███▎      | 494/1500 [01:15<01:29, 11.22it/s, 63 steps of size 1.30e-01. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  33%|███▎      | 496/1500 [01:16<02:06,  7.91it/s, 255 steps of size 3.48e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  33%|███▎      | 497/1500 [01:16<02:13,  7.50it/s, 127 steps of size 4.19e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  33%|███▎      | 498/1500 [01:16<02:19,  7.16it/s, 127 steps of size 4.97e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  33%|███▎      | 499/1500 [01:16<02:25,  6.89it/s, 127 steps of size 6.39e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  33%|███▎      | 500/1500 [01:16<02:29,  6.68it/s, 127 steps of size 7.54e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  33%|███▎      | 502/1500 [01:16<02:01,  8.24it/s, 63 steps of size 8.37e-02. acc. prob=0.88] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  34%|███▎      | 504/1500 [01:17<01:38, 10.13it/s, 31 steps of size 1.09e-01. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  34%|███▎      | 506/1500 [01:17<01:24, 11.70it/s, 31 steps of size 1.55e-01. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  34%|███▍      | 508/1500 [01:17<01:30, 11.01it/s, 127 steps of size 5.60e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  34%|███▍      | 509/1500 [01:17<01:43,  9.54it/s, 127 steps of size 6.20e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  34%|███▍      | 511/1500 [01:17<01:35, 10.36it/s, 63 steps of size 5.19e-02. acc. prob=0.88] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  34%|███▍      | 512/1500 [01:17<01:48,  9.09it/s, 127 steps of size 6.26e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  34%|███▍      | 514/1500 [01:18<01:38, 10.05it/s, 63 steps of size 9.81e-02. acc. prob=0.88] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  34%|███▍      | 516/1500 [01:18<01:45,  9.32it/s, 127 steps of size 7.54e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  35%|███▍      | 518/1500 [01:18<01:36, 10.13it/s, 63 steps of size 1.00e-01. acc. prob=0.88] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  35%|███▍      | 520/1500 [01:18<01:44,  9.41it/s, 127 steps of size 5.70e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  35%|███▍      | 522/1500 [01:18<01:36, 10.16it/s, 63 steps of size 8.24e-02. acc. prob=0.88] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  35%|███▍      | 524/1500 [01:19<01:31, 10.71it/s, 63 steps of size 1.19e-01. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  35%|███▌      | 526/1500 [01:19<01:21, 11.98it/s, 63 steps of size 8.72e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  35%|███▌      | 528/1500 [01:19<01:20, 12.09it/s, 63 steps of size 5.76e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  35%|███▌      | 529/1500 [01:19<01:34, 10.29it/s, 127 steps of size 7.04e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  35%|███▌      | 531/1500 [01:19<01:28, 10.90it/s, 63 steps of size 8.12e-02. acc. prob=0.88] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  36%|███▌      | 533/1500 [01:19<01:24, 11.40it/s, 59 steps of size 7.98e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  36%|███▌      | 535/1500 [01:19<01:22, 11.67it/s, 63 steps of size 8.47e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  36%|███▌      | 537/1500 [01:20<01:33, 10.30it/s, 127 steps of size 7.78e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  36%|███▌      | 539/1500 [01:20<01:28, 10.85it/s, 63 steps of size 6.76e-02. acc. prob=0.88] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  36%|███▌      | 541/1500 [01:20<01:25, 11.27it/s, 63 steps of size 8.48e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  36%|███▌      | 543/1500 [01:20<01:22, 11.57it/s, 63 steps of size 9.68e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  36%|███▋      | 545/1500 [01:20<01:21, 11.79it/s, 63 steps of size 1.20e-01. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  36%|███▋      | 547/1500 [01:20<01:12, 13.22it/s, 53 steps of size 9.27e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  37%|███▋      | 549/1500 [01:21<01:13, 12.93it/s, 63 steps of size 6.58e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  37%|███▋      | 551/1500 [01:21<01:14, 12.75it/s, 63 steps of size 7.59e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  37%|███▋      | 553/1500 [01:21<01:50,  8.59it/s, 255 steps of size 1.95e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  37%|███▋      | 554/1500 [01:22<02:25,  6.49it/s, 255 steps of size 2.29e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  37%|███▋      | 555/1500 [01:22<02:58,  5.28it/s, 255 steps of size 2.78e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  37%|███▋      | 556/1500 [01:22<02:53,  5.45it/s, 127 steps of size 3.36e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  37%|███▋      | 557/1500 [01:22<02:48,  5.60it/s, 127 steps of size 4.00e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  37%|███▋      | 558/1500 [01:22<02:44,  5.71it/s, 127 steps of size 4.71e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  37%|███▋      | 559/1500 [01:22<02:42,  5.81it/s, 127 steps of size 5.58e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  37%|███▋      | 561/1500 [01:23<02:06,  7.43it/s, 70 steps of size 7.26e-02. acc. prob=0.89] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  38%|███▊      | 563/1500 [01:23<01:47,  8.76it/s, 63 steps of size 5.67e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  38%|███▊      | 564/1500 [01:23<01:56,  8.01it/s, 127 steps of size 6.70e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  38%|███▊      | 566/1500 [01:23<01:41,  9.24it/s, 63 steps of size 8.25e-02. acc. prob=0.89] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  38%|███▊      | 568/1500 [01:23<01:32, 10.13it/s, 63 steps of size 9.80e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  38%|███▊      | 570/1500 [01:23<01:26, 10.76it/s, 63 steps of size 8.76e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  38%|███▊      | 572/1500 [01:24<01:22, 11.21it/s, 63 steps of size 7.07e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  38%|███▊      | 574/1500 [01:24<01:20, 11.53it/s, 63 steps of size 7.79e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  38%|███▊      | 576/1500 [01:24<01:18, 11.76it/s, 63 steps of size 7.81e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  39%|███▊      | 578/1500 [01:24<01:17, 11.93it/s, 63 steps of size 1.03e-01. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  39%|███▊      | 580/1500 [01:24<01:16, 12.04it/s, 63 steps of size 7.67e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  39%|███▉      | 582/1500 [01:24<01:15, 12.11it/s, 63 steps of size 9.22e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  39%|███▉      | 584/1500 [01:25<01:15, 12.18it/s, 63 steps of size 9.50e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  39%|███▉      | 586/1500 [01:25<01:14, 12.23it/s, 63 steps of size 9.24e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  39%|███▉      | 588/1500 [01:25<01:14, 12.25it/s, 63 steps of size 3.62e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  39%|███▉      | 589/1500 [01:25<01:27, 10.40it/s, 127 steps of size 4.11e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  39%|███▉      | 590/1500 [01:25<01:39,  9.11it/s, 127 steps of size 4.82e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  39%|███▉      | 591/1500 [01:25<01:51,  8.19it/s, 127 steps of size 5.61e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  40%|███▉      | 593/1500 [01:26<01:36,  9.41it/s, 63 steps of size 7.15e-02. acc. prob=0.89] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  40%|███▉      | 595/1500 [01:26<01:28, 10.27it/s, 63 steps of size 5.46e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  40%|███▉      | 596/1500 [01:26<01:40,  9.02it/s, 127 steps of size 5.26e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  40%|███▉      | 597/1500 [01:26<01:51,  8.13it/s, 127 steps of size 6.16e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  40%|███▉      | 598/1500 [01:26<02:00,  7.51it/s, 127 steps of size 7.23e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  40%|████      | 600/1500 [01:26<01:41,  8.89it/s, 63 steps of size 9.57e-02. acc. prob=0.89] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  40%|████      | 602/1500 [01:27<01:31,  9.86it/s, 63 steps of size 8.62e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  40%|████      | 604/1500 [01:27<01:25, 10.53it/s, 63 steps of size 5.03e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  40%|████      | 605/1500 [01:27<01:37,  9.20it/s, 127 steps of size 5.22e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  40%|████      | 607/1500 [01:27<01:41,  8.80it/s, 127 steps of size 6.87e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  41%|████      | 610/1500 [01:27<01:19, 11.14it/s, 63 steps of size 5.96e-02. acc. prob=0.89] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  41%|████      | 612/1500 [01:28<01:43,  8.58it/s, 255 steps of size 3.25e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  41%|████      | 613/1500 [01:28<01:51,  7.99it/s, 127 steps of size 3.59e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  41%|████      | 614/1500 [01:28<01:58,  7.47it/s, 127 steps of size 4.03e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  41%|████      | 615/1500 [01:28<02:04,  7.11it/s, 127 steps of size 4.52e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  41%|████      | 616/1500 [01:28<02:09,  6.81it/s, 127 steps of size 4.77e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  41%|████      | 617/1500 [01:29<02:13,  6.59it/s, 127 steps of size 5.55e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  41%|████      | 618/1500 [01:29<02:16,  6.45it/s, 127 steps of size 6.29e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  41%|████▏     | 620/1500 [01:29<01:51,  7.86it/s, 127 steps of size 3.69e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  41%|████▏     | 621/1500 [01:29<01:59,  7.38it/s, 127 steps of size 4.26e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  41%|████▏     | 622/1500 [01:29<02:05,  7.02it/s, 127 steps of size 4.92e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  42%|████▏     | 623/1500 [01:29<02:09,  6.75it/s, 127 steps of size 5.63e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  42%|████▏     | 624/1500 [01:30<02:13,  6.56it/s, 127 steps of size 6.21e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  42%|████▏     | 625/1500 [01:30<02:16,  6.43it/s, 127 steps of size 7.16e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  42%|████▏     | 627/1500 [01:30<01:46,  8.16it/s, 63 steps of size 7.94e-02. acc. prob=0.89] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  42%|████▏     | 629/1500 [01:30<01:32,  9.40it/s, 63 steps of size 8.88e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  42%|████▏     | 631/1500 [01:30<01:24, 10.27it/s, 63 steps of size 5.53e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  42%|████▏     | 633/1500 [01:30<01:31,  9.46it/s, 127 steps of size 7.25e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  42%|████▏     | 635/1500 [01:31<01:24, 10.24it/s, 63 steps of size 9.27e-02. acc. prob=0.89] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  42%|████▏     | 637/1500 [01:31<01:19, 10.81it/s, 63 steps of size 1.09e-01. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  43%|████▎     | 639/1500 [01:31<01:16, 11.23it/s, 63 steps of size 5.66e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  43%|████▎     | 641/1500 [01:31<01:14, 11.54it/s, 63 steps of size 4.82e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  43%|████▎     | 642/1500 [01:31<01:26,  9.95it/s, 127 steps of size 5.38e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  43%|████▎     | 643/1500 [01:31<01:37,  8.81it/s, 127 steps of size 5.80e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  43%|████▎     | 644/1500 [01:32<01:47,  7.98it/s, 127 steps of size 6.57e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  43%|████▎     | 646/1500 [01:32<01:29,  9.56it/s, 63 steps of size 7.49e-02. acc. prob=0.89] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  43%|████▎     | 648/1500 [01:32<01:21, 10.39it/s, 63 steps of size 7.69e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  43%|████▎     | 650/1500 [01:32<01:29,  9.51it/s, 127 steps of size 6.60e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  43%|████▎     | 652/1500 [01:32<01:22, 10.28it/s, 63 steps of size 6.78e-02. acc. prob=0.89] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  44%|████▎     | 654/1500 [01:33<01:29,  9.50it/s, 127 steps of size 4.13e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  44%|████▎     | 655/1500 [01:33<01:38,  8.61it/s, 127 steps of size 4.70e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  44%|████▍     | 658/1500 [01:33<01:27,  9.67it/s, 127 steps of size 5.35e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  44%|████▍     | 659/1500 [01:33<01:35,  8.78it/s, 127 steps of size 5.87e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  44%|████▍     | 661/1500 [01:33<01:26,  9.70it/s, 63 steps of size 7.21e-02. acc. prob=0.89] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  44%|████▍     | 663/1500 [01:33<01:20, 10.41it/s, 63 steps of size 7.99e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  44%|████▍     | 665/1500 [01:34<01:16, 10.94it/s, 63 steps of size 8.74e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  44%|████▍     | 667/1500 [01:34<01:13, 11.33it/s, 63 steps of size 8.58e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  45%|████▍     | 669/1500 [01:34<01:11, 11.61it/s, 63 steps of size 7.28e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  45%|████▍     | 671/1500 [01:34<01:10, 11.82it/s, 63 steps of size 9.00e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  45%|████▍     | 673/1500 [01:34<01:09, 11.96it/s, 63 steps of size 1.16e-01. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  45%|████▌     | 676/1500 [01:34<00:54, 15.04it/s, 31 steps of size 1.16e-01. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  45%|████▌     | 678/1500 [01:34<00:53, 15.41it/s, 63 steps of size 9.23e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  45%|████▌     | 680/1500 [01:35<00:57, 14.34it/s, 63 steps of size 7.28e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  45%|████▌     | 682/1500 [01:35<00:59, 13.68it/s, 63 steps of size 9.31e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  46%|████▌     | 684/1500 [01:35<00:56, 14.39it/s, 31 steps of size 1.01e-01. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  46%|████▌     | 686/1500 [01:35<00:59, 13.71it/s, 63 steps of size 1.04e-01. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  46%|████▌     | 688/1500 [01:35<01:01, 13.26it/s, 63 steps of size 5.35e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  46%|████▌     | 690/1500 [01:35<01:02, 12.97it/s, 63 steps of size 6.84e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  46%|████▌     | 692/1500 [01:36<01:03, 12.77it/s, 63 steps of size 8.26e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  46%|████▋     | 694/1500 [01:36<01:03, 12.63it/s, 63 steps of size 9.28e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  46%|████▋     | 696/1500 [01:36<01:04, 12.52it/s, 63 steps of size 9.76e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  47%|████▋     | 699/1500 [01:36<00:53, 15.11it/s, 31 steps of size 7.96e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  47%|████▋     | 701/1500 [01:36<00:56, 14.25it/s, 63 steps of size 9.16e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  47%|████▋     | 703/1500 [01:36<00:58, 13.65it/s, 63 steps of size 1.12e-01. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  47%|████▋     | 705/1500 [01:36<00:55, 14.35it/s, 31 steps of size 1.21e-01. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  47%|████▋     | 707/1500 [01:37<00:53, 14.87it/s, 63 steps of size 1.15e-01. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  47%|████▋     | 709/1500 [01:37<00:51, 15.29it/s, 31 steps of size 1.04e-01. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  47%|████▋     | 711/1500 [01:37<00:55, 14.28it/s, 63 steps of size 7.34e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  47%|████▋     | 712/1500 [01:37<01:08, 11.59it/s, 127 steps of size 7.90e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  48%|████▊     | 714/1500 [01:37<01:06, 11.82it/s, 63 steps of size 9.80e-02. acc. prob=0.89] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  48%|████▊     | 716/1500 [01:37<01:05, 11.96it/s, 63 steps of size 8.02e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  48%|████▊     | 718/1500 [01:38<01:04, 12.07it/s, 63 steps of size 9.48e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  48%|████▊     | 720/1500 [01:38<01:04, 12.13it/s, 63 steps of size 1.08e-01. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  48%|████▊     | 722/1500 [01:38<01:13, 10.56it/s, 127 steps of size 3.75e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  48%|████▊     | 723/1500 [01:38<01:23,  9.34it/s, 127 steps of size 4.20e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  48%|████▊     | 724/1500 [01:38<01:32,  8.43it/s, 127 steps of size 4.64e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  48%|████▊     | 725/1500 [01:38<01:39,  7.76it/s, 127 steps of size 5.18e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  48%|████▊     | 727/1500 [01:39<01:25,  9.08it/s, 63 steps of size 6.49e-02. acc. prob=0.89] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  49%|████▊     | 729/1500 [01:39<01:12, 10.60it/s, 63 steps of size 7.51e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  49%|████▊     | 731/1500 [01:39<01:09, 11.12it/s, 63 steps of size 9.50e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  49%|████▉     | 733/1500 [01:39<01:06, 11.49it/s, 63 steps of size 1.08e-01. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  49%|████▉     | 735/1500 [01:39<01:00, 12.71it/s, 63 steps of size 1.04e-01. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  49%|████▉     | 737/1500 [01:39<00:55, 13.68it/s, 31 steps of size 1.16e-01. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  49%|████▉     | 739/1500 [01:39<00:52, 14.43it/s, 31 steps of size 1.24e-01. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  49%|████▉     | 742/1500 [01:40<00:43, 17.27it/s, 31 steps of size 6.17e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  50%|████▉     | 744/1500 [01:40<00:48, 15.69it/s, 59 steps of size 6.98e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  50%|████▉     | 746/1500 [01:40<00:51, 14.53it/s, 63 steps of size 8.00e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  50%|████▉     | 748/1500 [01:40<00:54, 13.80it/s, 63 steps of size 6.81e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  50%|█████     | 750/1500 [01:40<00:56, 13.22it/s, 63 steps of size 8.26e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  50%|█████     | 752/1500 [01:40<00:58, 12.86it/s, 63 steps of size 6.56e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  50%|█████     | 754/1500 [01:41<00:58, 12.67it/s, 63 steps of size 7.28e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  50%|█████     | 756/1500 [01:41<00:59, 12.57it/s, 63 steps of size 7.98e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  51%|█████     | 758/1500 [01:41<00:59, 12.49it/s, 63 steps of size 8.44e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  51%|█████     | 760/1500 [01:41<00:59, 12.44it/s, 63 steps of size 7.58e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  51%|█████     | 762/1500 [01:41<00:59, 12.40it/s, 63 steps of size 8.42e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  51%|█████     | 764/1500 [01:41<00:59, 12.35it/s, 63 steps of size 9.44e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  51%|█████     | 766/1500 [01:42<00:59, 12.33it/s, 63 steps of size 7.70e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  51%|█████     | 768/1500 [01:42<00:59, 12.33it/s, 63 steps of size 7.37e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  51%|█████▏    | 770/1500 [01:42<00:59, 12.32it/s, 63 steps of size 6.99e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  51%|█████▏    | 772/1500 [01:42<00:59, 12.31it/s, 63 steps of size 6.47e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  52%|█████▏    | 773/1500 [01:42<01:09, 10.45it/s, 127 steps of size 4.69e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  52%|█████▏    | 774/1500 [01:42<01:19,  9.15it/s, 127 steps of size 5.25e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  52%|█████▏    | 775/1500 [01:42<01:28,  8.24it/s, 127 steps of size 4.51e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  52%|█████▏    | 776/1500 [01:43<01:35,  7.59it/s, 127 steps of size 4.69e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  52%|█████▏    | 778/1500 [01:43<01:32,  7.79it/s, 127 steps of size 4.39e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  52%|█████▏    | 779/1500 [01:43<01:38,  7.30it/s, 127 steps of size 4.90e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  52%|█████▏    | 780/1500 [01:43<01:43,  6.94it/s, 127 steps of size 5.44e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  52%|█████▏    | 781/1500 [01:43<01:47,  6.68it/s, 127 steps of size 6.04e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  52%|█████▏    | 783/1500 [01:44<01:40,  7.13it/s, 127 steps of size 5.03e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  52%|█████▏    | 784/1500 [01:44<01:44,  6.84it/s, 127 steps of size 5.57e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  52%|█████▏    | 786/1500 [01:44<01:26,  8.28it/s, 63 steps of size 6.72e-02. acc. prob=0.89] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  53%|█████▎    | 788/1500 [01:44<01:15,  9.39it/s, 63 steps of size 7.61e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  53%|█████▎    | 790/1500 [01:44<01:09, 10.21it/s, 63 steps of size 8.51e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  53%|█████▎    | 792/1500 [01:44<01:05, 10.80it/s, 63 steps of size 1.02e-01. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  53%|█████▎    | 794/1500 [01:45<01:02, 11.24it/s, 63 steps of size 8.97e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  53%|█████▎    | 796/1500 [01:45<01:00, 11.55it/s, 63 steps of size 1.10e-01. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  53%|█████▎    | 799/1500 [01:45<00:47, 14.72it/s, 31 steps of size 1.11e-01. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  53%|█████▎    | 801/1500 [01:45<00:46, 15.17it/s, 63 steps of size 1.09e-01. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  54%|█████▎    | 803/1500 [01:45<00:48, 14.23it/s, 63 steps of size 1.02e-01. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  54%|█████▎    | 805/1500 [01:45<00:51, 13.61it/s, 63 steps of size 8.49e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  54%|█████▍    | 807/1500 [01:46<00:52, 13.20it/s, 63 steps of size 8.77e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  54%|█████▍    | 809/1500 [01:46<00:53, 12.95it/s, 63 steps of size 7.16e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  54%|█████▍    | 811/1500 [01:46<00:54, 12.75it/s, 63 steps of size 5.33e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  54%|█████▍    | 812/1500 [01:46<01:04, 10.72it/s, 127 steps of size 5.65e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  54%|█████▍    | 813/1500 [01:46<01:13,  9.32it/s, 127 steps of size 5.16e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  54%|█████▍    | 815/1500 [01:46<01:17,  8.87it/s, 127 steps of size 4.02e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  54%|█████▍    | 816/1500 [01:47<01:24,  8.12it/s, 127 steps of size 4.43e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  54%|█████▍    | 817/1500 [01:47<01:30,  7.55it/s, 127 steps of size 4.86e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  55%|█████▍    | 818/1500 [01:47<01:35,  7.14it/s, 127 steps of size 5.24e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  55%|█████▍    | 819/1500 [01:47<01:39,  6.84it/s, 127 steps of size 4.95e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  55%|█████▍    | 820/1500 [01:47<01:42,  6.63it/s, 127 steps of size 5.15e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  55%|█████▍    | 821/1500 [01:47<01:44,  6.48it/s, 127 steps of size 5.61e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  55%|█████▍    | 822/1500 [01:48<01:46,  6.37it/s, 127 steps of size 6.14e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  55%|█████▍    | 824/1500 [01:48<01:23,  8.11it/s, 63 steps of size 7.07e-02. acc. prob=0.89] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  55%|█████▌    | 826/1500 [01:48<01:23,  8.09it/s, 127 steps of size 5.34e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  55%|█████▌    | 827/1500 [01:48<01:29,  7.53it/s, 127 steps of size 4.94e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  55%|█████▌    | 828/1500 [01:48<01:34,  7.11it/s, 127 steps of size 3.13e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  55%|█████▌    | 829/1500 [01:49<02:06,  5.32it/s, 255 steps of size 3.47e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  55%|█████▌    | 830/1500 [01:49<02:01,  5.51it/s, 127 steps of size 3.84e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  55%|█████▌    | 831/1500 [01:49<01:58,  5.66it/s, 127 steps of size 4.24e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  55%|█████▌    | 832/1500 [01:49<01:55,  5.78it/s, 127 steps of size 4.70e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  56%|█████▌    | 833/1500 [01:49<01:53,  5.88it/s, 127 steps of size 4.87e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  56%|█████▌    | 835/1500 [01:49<01:26,  7.69it/s, 63 steps of size 5.72e-02. acc. prob=0.89] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  56%|█████▌    | 837/1500 [01:50<01:13,  9.00it/s, 63 steps of size 6.16e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  56%|█████▌    | 839/1500 [01:50<01:06,  9.92it/s, 63 steps of size 7.18e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  56%|█████▌    | 841/1500 [01:50<01:02, 10.60it/s, 63 steps of size 6.68e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  56%|█████▌    | 843/1500 [01:50<00:59, 11.11it/s, 63 steps of size 7.75e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  56%|█████▋    | 845/1500 [01:50<00:57, 11.47it/s, 63 steps of size 7.24e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  56%|█████▋    | 847/1500 [01:50<00:55, 11.71it/s, 63 steps of size 8.44e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  57%|█████▋    | 849/1500 [01:51<00:54, 11.89it/s, 63 steps of size 8.43e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  57%|█████▋    | 851/1500 [01:51<00:54, 12.02it/s, 63 steps of size 7.64e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  57%|█████▋    | 853/1500 [01:51<00:53, 12.10it/s, 63 steps of size 6.75e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  57%|█████▋    | 855/1500 [01:51<00:52, 12.17it/s, 63 steps of size 6.14e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  57%|█████▋    | 857/1500 [01:51<00:52, 12.21it/s, 63 steps of size 7.05e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  57%|█████▋    | 859/1500 [01:51<00:52, 12.24it/s, 63 steps of size 8.39e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  57%|█████▋    | 861/1500 [01:52<00:52, 12.27it/s, 63 steps of size 9.09e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  58%|█████▊    | 863/1500 [01:52<00:51, 12.28it/s, 63 steps of size 8.50e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  58%|█████▊    | 865/1500 [01:52<00:51, 12.29it/s, 63 steps of size 8.23e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  58%|█████▊    | 867/1500 [01:52<00:51, 12.29it/s, 63 steps of size 9.23e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  58%|█████▊    | 869/1500 [01:52<00:59, 10.67it/s, 127 steps of size 5.70e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  58%|█████▊    | 871/1500 [01:52<00:56, 11.11it/s, 63 steps of size 6.53e-02. acc. prob=0.89] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  58%|█████▊    | 873/1500 [01:53<01:02, 10.02it/s, 127 steps of size 7.56e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  58%|█████▊    | 875/1500 [01:53<00:58, 10.59it/s, 63 steps of size 8.47e-02. acc. prob=0.89] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  58%|█████▊    | 877/1500 [01:53<00:56, 11.04it/s, 63 steps of size 7.11e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  59%|█████▊    | 879/1500 [01:53<00:54, 11.38it/s, 63 steps of size 8.18e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  59%|█████▊    | 881/1500 [01:53<00:53, 11.64it/s, 63 steps of size 7.12e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  59%|█████▉    | 883/1500 [01:54<00:52, 11.84it/s, 63 steps of size 5.46e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  59%|█████▉    | 884/1500 [01:54<01:00, 10.17it/s, 127 steps of size 5.92e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  59%|█████▉    | 886/1500 [01:54<00:56, 10.80it/s, 63 steps of size 6.34e-02. acc. prob=0.89] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  59%|█████▉    | 888/1500 [01:54<00:54, 11.24it/s, 63 steps of size 7.04e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  59%|█████▉    | 890/1500 [01:54<00:52, 11.56it/s, 63 steps of size 6.59e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  59%|█████▉    | 892/1500 [01:54<00:51, 11.78it/s, 63 steps of size 6.46e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  60%|█████▉    | 894/1500 [01:55<00:50, 11.93it/s, 63 steps of size 7.50e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  60%|█████▉    | 896/1500 [01:55<00:50, 12.05it/s, 63 steps of size 8.76e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  60%|█████▉    | 899/1500 [01:55<00:44, 13.52it/s, 63 steps of size 1.01e-01. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  60%|██████    | 900/1500 [01:55<00:52, 11.34it/s, 127 steps of size 9.66e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  60%|██████    | 902/1500 [01:55<00:47, 12.56it/s, 31 steps of size 9.63e-02. acc. prob=0.89] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  60%|██████    | 904/1500 [01:55<00:44, 13.54it/s, 31 steps of size 1.03e-01. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  60%|██████    | 906/1500 [01:56<00:52, 11.27it/s, 127 steps of size 6.16e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  61%|██████    | 908/1500 [01:56<00:51, 11.56it/s, 63 steps of size 6.67e-02. acc. prob=0.89] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  61%|██████    | 910/1500 [01:56<00:50, 11.77it/s, 63 steps of size 7.38e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  61%|██████    | 912/1500 [01:56<00:49, 11.85it/s, 63 steps of size 8.63e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  61%|██████    | 914/1500 [01:56<00:48, 11.98it/s, 63 steps of size 1.00e-01. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  61%|██████    | 916/1500 [01:56<00:48, 12.08it/s, 63 steps of size 8.75e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  61%|██████    | 918/1500 [01:56<00:47, 12.15it/s, 63 steps of size 9.00e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  61%|██████▏   | 920/1500 [01:57<00:47, 12.20it/s, 63 steps of size 8.61e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  61%|██████▏   | 922/1500 [01:57<00:47, 12.24it/s, 63 steps of size 9.51e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  62%|██████▏   | 924/1500 [01:57<00:47, 12.15it/s, 63 steps of size 9.67e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  62%|██████▏   | 926/1500 [01:57<00:48, 11.82it/s, 63 steps of size 9.13e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  62%|██████▏   | 928/1500 [01:57<00:44, 12.91it/s, 63 steps of size 9.39e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  62%|██████▏   | 930/1500 [01:58<00:51, 10.98it/s, 127 steps of size 5.38e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  62%|██████▏   | 931/1500 [01:58<00:59,  9.63it/s, 127 steps of size 5.78e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  62%|██████▏   | 933/1500 [01:58<00:54, 10.38it/s, 63 steps of size 6.50e-02. acc. prob=0.89] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  62%|██████▏   | 935/1500 [01:58<00:51, 10.93it/s, 63 steps of size 7.49e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  62%|██████▏   | 937/1500 [01:58<00:49, 11.33it/s, 63 steps of size 7.23e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  63%|██████▎   | 939/1500 [01:58<00:48, 11.61it/s, 63 steps of size 8.09e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  63%|██████▎   | 941/1500 [01:59<00:47, 11.81it/s, 63 steps of size 6.22e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  63%|██████▎   | 942/1500 [01:59<00:55, 10.13it/s, 127 steps of size 6.28e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  63%|██████▎   | 944/1500 [01:59<00:51, 10.78it/s, 63 steps of size 6.96e-02. acc. prob=0.89] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  63%|██████▎   | 946/1500 [01:59<00:49, 11.24it/s, 63 steps of size 7.92e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  63%|██████▎   | 948/1500 [01:59<00:47, 11.55it/s, 63 steps of size 8.85e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  63%|██████▎   | 950/1500 [01:59<00:46, 11.79it/s, 63 steps of size 9.29e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  64%|██████▎   | 953/1500 [01:59<00:36, 14.87it/s, 31 steps of size 1.22e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  64%|██████▎   | 954/1500 [02:00<01:28,  6.20it/s, 511 steps of size 1.18e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  64%|██████▎   | 955/1500 [02:00<01:44,  5.20it/s, 255 steps of size 1.32e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  64%|██████▎   | 956/1500 [02:01<02:37,  3.45it/s, 511 steps of size 1.58e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  64%|██████▍   | 957/1500 [02:01<02:41,  3.35it/s, 255 steps of size 2.02e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  64%|██████▍   | 958/1500 [02:02<02:45,  3.27it/s, 255 steps of size 2.66e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  64%|██████▍   | 959/1500 [02:02<02:25,  3.72it/s, 127 steps of size 3.58e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  64%|██████▍   | 960/1500 [02:02<02:34,  3.50it/s, 255 steps of size 4.88e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  64%|██████▍   | 961/1500 [02:02<02:15,  3.97it/s, 127 steps of size 5.99e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  64%|██████▍   | 963/1500 [02:03<01:34,  5.68it/s, 63 steps of size 1.13e-01. acc. prob=0.89] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  64%|██████▍   | 965/1500 [02:03<01:14,  7.18it/s, 63 steps of size 7.78e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  64%|██████▍   | 967/1500 [02:03<01:03,  8.43it/s, 63 steps of size 6.04e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  65%|██████▍   | 968/1500 [02:03<01:08,  7.82it/s, 127 steps of size 8.32e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  65%|██████▍   | 970/1500 [02:03<01:06,  7.95it/s, 127 steps of size 7.67e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  65%|██████▍   | 972/1500 [02:03<00:58,  9.05it/s, 63 steps of size 1.20e-01. acc. prob=0.89] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  65%|██████▌   | 975/1500 [02:04<00:45, 11.58it/s, 63 steps of size 4.19e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  65%|██████▌   | 976/1500 [02:04<00:52, 10.07it/s, 127 steps of size 5.65e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  65%|██████▌   | 977/1500 [02:04<00:58,  8.94it/s, 127 steps of size 7.47e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  65%|██████▌   | 979/1500 [02:04<00:52,  9.89it/s, 63 steps of size 7.01e-02. acc. prob=0.89] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  65%|██████▌   | 981/1500 [02:04<00:48, 10.60it/s, 63 steps of size 1.17e-01. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  66%|██████▌   | 983/1500 [02:04<00:46, 11.09it/s, 63 steps of size 8.04e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  66%|██████▌   | 985/1500 [02:05<00:44, 11.46it/s, 63 steps of size 1.01e-01. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  66%|██████▌   | 987/1500 [02:05<00:43, 11.71it/s, 63 steps of size 7.94e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  66%|██████▌   | 989/1500 [02:05<00:42, 11.90it/s, 63 steps of size 1.04e-01. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  66%|██████▌   | 991/1500 [02:05<00:42, 12.02it/s, 63 steps of size 7.94e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  66%|██████▌   | 993/1500 [02:05<00:41, 12.11it/s, 63 steps of size 1.04e-01. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  66%|██████▋   | 995/1500 [02:05<00:41, 12.14it/s, 63 steps of size 1.29e-01. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  67%|██████▋   | 998/1500 [02:06<00:41, 12.13it/s, 127 steps of size 5.70e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  67%|██████▋   | 1000/1500 [02:06<00:46, 10.72it/s, 127 steps of size 7.71e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  67%|██████▋   | 1002/1500 [02:06<00:44, 11.11it/s, 63 steps of size 7.71e-02. acc. prob=0.98] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  67%|██████▋   | 1004/1500 [02:06<00:43, 11.43it/s, 63 steps of size 7.71e-02. acc. prob=0.98]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  67%|██████▋   | 1006/1500 [02:06<00:42, 11.67it/s, 63 steps of size 7.71e-02. acc. prob=0.97]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  67%|██████▋   | 1008/1500 [02:07<00:41, 11.85it/s, 63 steps of size 7.71e-02. acc. prob=0.95]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  67%|██████▋   | 1010/1500 [02:07<00:40, 11.98it/s, 63 steps of size 7.71e-02. acc. prob=0.95]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  67%|██████▋   | 1012/1500 [02:07<00:40, 12.07it/s, 63 steps of size 7.71e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  68%|██████▊   | 1014/1500 [02:07<00:37, 13.04it/s, 63 steps of size 7.71e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  68%|██████▊   | 1016/1500 [02:07<00:37, 12.81it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  68%|██████▊   | 1018/1500 [02:07<00:38, 12.65it/s, 63 steps of size 7.71e-02. acc. prob=0.91]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  68%|██████▊   | 1020/1500 [02:07<00:38, 12.55it/s, 63 steps of size 7.71e-02. acc. prob=0.91]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  68%|██████▊   | 1022/1500 [02:08<00:38, 12.49it/s, 63 steps of size 7.71e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  68%|██████▊   | 1024/1500 [02:08<00:38, 12.43it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  68%|██████▊   | 1026/1500 [02:08<00:38, 12.39it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  69%|██████▊   | 1028/1500 [02:08<00:38, 12.37it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  69%|██████▊   | 1030/1500 [02:08<00:38, 12.35it/s, 63 steps of size 7.71e-02. acc. prob=0.91]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  69%|██████▉   | 1032/1500 [02:08<00:38, 12.30it/s, 63 steps of size 7.71e-02. acc. prob=0.91]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  69%|██████▉   | 1034/1500 [02:09<00:37, 12.30it/s, 63 steps of size 7.71e-02. acc. prob=0.91]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  69%|██████▉   | 1036/1500 [02:09<00:37, 12.30it/s, 63 steps of size 7.71e-02. acc. prob=0.91]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  69%|██████▉   | 1038/1500 [02:09<00:37, 12.30it/s, 63 steps of size 7.71e-02. acc. prob=0.91]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  69%|██████▉   | 1040/1500 [02:09<00:37, 12.30it/s, 63 steps of size 7.71e-02. acc. prob=0.91]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  69%|██████▉   | 1042/1500 [02:09<00:37, 12.29it/s, 63 steps of size 7.71e-02. acc. prob=0.91]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  70%|██████▉   | 1044/1500 [02:09<00:37, 12.29it/s, 63 steps of size 7.71e-02. acc. prob=0.91]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  70%|██████▉   | 1046/1500 [02:10<00:36, 12.30it/s, 63 steps of size 7.71e-02. acc. prob=0.91]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  70%|██████▉   | 1048/1500 [02:10<00:36, 12.30it/s, 63 steps of size 7.71e-02. acc. prob=0.91]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  70%|███████   | 1050/1500 [02:10<00:36, 12.30it/s, 63 steps of size 7.71e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  70%|███████   | 1052/1500 [02:10<00:36, 12.30it/s, 63 steps of size 7.71e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  70%|███████   | 1054/1500 [02:10<00:36, 12.31it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  70%|███████   | 1056/1500 [02:10<00:36, 12.29it/s, 63 steps of size 7.71e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  71%|███████   | 1058/1500 [02:11<00:36, 12.27it/s, 63 steps of size 7.71e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  71%|███████   | 1060/1500 [02:11<00:35, 12.28it/s, 63 steps of size 7.71e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  71%|███████   | 1062/1500 [02:11<00:35, 12.29it/s, 63 steps of size 7.71e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  71%|███████   | 1064/1500 [02:11<00:35, 12.28it/s, 63 steps of size 7.71e-02. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  71%|███████   | 1066/1500 [02:11<00:35, 12.28it/s, 63 steps of size 7.71e-02. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  71%|███████   | 1068/1500 [02:11<00:35, 12.30it/s, 63 steps of size 7.71e-02. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  71%|███████▏  | 1070/1500 [02:12<00:35, 12.26it/s, 63 steps of size 7.71e-02. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  71%|███████▏  | 1072/1500 [02:12<00:34, 12.25it/s, 63 steps of size 7.71e-02. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  72%|███████▏  | 1074/1500 [02:12<00:34, 12.26it/s, 63 steps of size 7.71e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  72%|███████▏  | 1076/1500 [02:12<00:34, 12.26it/s, 63 steps of size 7.71e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  72%|███████▏  | 1078/1500 [02:12<00:34, 12.28it/s, 63 steps of size 7.71e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  72%|███████▏  | 1080/1500 [02:12<00:34, 12.28it/s, 63 steps of size 7.71e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  72%|███████▏  | 1082/1500 [02:13<00:34, 12.27it/s, 63 steps of size 7.71e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  72%|███████▏  | 1084/1500 [02:13<00:33, 12.27it/s, 63 steps of size 7.71e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  72%|███████▏  | 1086/1500 [02:13<00:36, 11.26it/s, 63 steps of size 7.71e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  73%|███████▎  | 1088/1500 [02:13<00:36, 11.18it/s, 63 steps of size 7.71e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  73%|███████▎  | 1090/1500 [02:13<00:35, 11.45it/s, 63 steps of size 7.71e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  73%|███████▎  | 1092/1500 [02:13<00:34, 11.68it/s, 63 steps of size 7.71e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  73%|███████▎  | 1094/1500 [02:14<00:38, 10.57it/s, 63 steps of size 7.71e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  73%|███████▎  | 1096/1500 [02:14<00:40, 10.08it/s, 63 steps of size 7.71e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  73%|███████▎  | 1097/1500 [02:14<00:41,  9.76it/s, 63 steps of size 7.71e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  73%|███████▎  | 1098/1500 [02:14<00:42,  9.48it/s, 63 steps of size 7.71e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  73%|███████▎  | 1100/1500 [02:14<00:42,  9.43it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  73%|███████▎  | 1102/1500 [02:14<00:38, 10.22it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  74%|███████▎  | 1104/1500 [02:15<00:36, 10.80it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  74%|███████▎  | 1106/1500 [02:15<00:35, 11.24it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  74%|███████▍  | 1108/1500 [02:15<00:33, 11.54it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  74%|███████▍  | 1110/1500 [02:15<00:33, 11.75it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  74%|███████▍  | 1112/1500 [02:15<00:32, 11.88it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  74%|███████▍  | 1114/1500 [02:15<00:32, 12.03it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  74%|███████▍  | 1116/1500 [02:16<00:31, 12.14it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  75%|███████▍  | 1118/1500 [02:16<00:31, 12.18it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  75%|███████▍  | 1120/1500 [02:16<00:31, 12.22it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  75%|███████▍  | 1122/1500 [02:16<00:30, 12.24it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  75%|███████▍  | 1124/1500 [02:16<00:30, 12.26it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  75%|███████▌  | 1126/1500 [02:16<00:30, 12.27it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  75%|███████▌  | 1128/1500 [02:17<00:30, 12.29it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  75%|███████▌  | 1130/1500 [02:17<00:30, 12.30it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  75%|███████▌  | 1132/1500 [02:17<00:29, 12.31it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  76%|███████▌  | 1134/1500 [02:17<00:29, 12.30it/s, 63 steps of size 7.71e-02. acc. prob=0.91]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  76%|███████▌  | 1135/1500 [02:17<00:34, 10.43it/s, 127 steps of size 7.71e-02. acc. prob=0.91]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  76%|███████▌  | 1137/1500 [02:17<00:33, 10.99it/s, 63 steps of size 7.71e-02. acc. prob=0.91] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  76%|███████▌  | 1139/1500 [02:18<00:30, 11.98it/s, 42 steps of size 7.71e-02. acc. prob=0.91]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  76%|███████▌  | 1141/1500 [02:18<00:29, 12.09it/s, 63 steps of size 7.71e-02. acc. prob=0.91]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  76%|███████▌  | 1143/1500 [02:18<00:29, 12.15it/s, 63 steps of size 7.71e-02. acc. prob=0.91]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  76%|███████▋  | 1145/1500 [02:18<00:29, 12.20it/s, 63 steps of size 7.71e-02. acc. prob=0.91]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  76%|███████▋  | 1147/1500 [02:18<00:28, 12.23it/s, 63 steps of size 7.71e-02. acc. prob=0.91]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  77%|███████▋  | 1149/1500 [02:18<00:28, 12.23it/s, 63 steps of size 7.71e-02. acc. prob=0.91]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  77%|███████▋  | 1151/1500 [02:19<00:28, 12.24it/s, 63 steps of size 7.71e-02. acc. prob=0.91]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  77%|███████▋  | 1154/1500 [02:19<00:23, 14.82it/s, 29 steps of size 7.71e-02. acc. prob=0.91]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  77%|███████▋  | 1156/1500 [02:19<00:24, 14.04it/s, 63 steps of size 7.71e-02. acc. prob=0.91]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  77%|███████▋  | 1158/1500 [02:19<00:25, 13.49it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  77%|███████▋  | 1160/1500 [02:19<00:25, 13.13it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  77%|███████▋  | 1162/1500 [02:19<00:26, 12.89it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  78%|███████▊  | 1164/1500 [02:19<00:26, 12.71it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  78%|███████▊  | 1166/1500 [02:20<00:26, 12.59it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  78%|███████▊  | 1168/1500 [02:20<00:26, 12.51it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  78%|███████▊  | 1170/1500 [02:20<00:26, 12.44it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  78%|███████▊  | 1172/1500 [02:20<00:26, 12.39it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  78%|███████▊  | 1174/1500 [02:20<00:25, 12.88it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  78%|███████▊  | 1176/1500 [02:20<00:25, 12.69it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  79%|███████▊  | 1178/1500 [02:21<00:24, 13.04it/s, 48 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  79%|███████▊  | 1180/1500 [02:21<00:25, 12.79it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  79%|███████▉  | 1182/1500 [02:21<00:25, 12.60it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  79%|███████▉  | 1184/1500 [02:21<00:25, 12.45it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  79%|███████▉  | 1186/1500 [02:21<00:25, 12.36it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  79%|███████▉  | 1188/1500 [02:21<00:24, 12.57it/s, 53 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  79%|███████▉  | 1190/1500 [02:22<00:25, 12.38it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  79%|███████▉  | 1192/1500 [02:22<00:24, 12.33it/s, 63 steps of size 7.71e-02. acc. prob=0.91]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  80%|███████▉  | 1194/1500 [02:22<00:24, 12.31it/s, 63 steps of size 7.71e-02. acc. prob=0.91]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  80%|███████▉  | 1196/1500 [02:22<00:24, 12.30it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  80%|███████▉  | 1198/1500 [02:22<00:24, 12.31it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  80%|████████  | 1200/1500 [02:22<00:24, 12.31it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  80%|████████  | 1202/1500 [02:23<00:24, 12.31it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  80%|████████  | 1204/1500 [02:23<00:24, 12.32it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  80%|████████  | 1206/1500 [02:23<00:23, 12.31it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  81%|████████  | 1208/1500 [02:23<00:23, 12.26it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  81%|████████  | 1210/1500 [02:23<00:23, 12.19it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  81%|████████  | 1212/1500 [02:23<00:23, 12.06it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  81%|████████  | 1214/1500 [02:24<00:23, 12.03it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  81%|████████  | 1216/1500 [02:24<00:23, 12.03it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  81%|████████  | 1218/1500 [02:24<00:23, 12.03it/s, 63 steps of size 7.71e-02. acc. prob=0.91]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  81%|████████▏ | 1220/1500 [02:24<00:22, 12.27it/s, 57 steps of size 7.71e-02. acc. prob=0.91]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  81%|████████▏ | 1222/1500 [02:24<00:22, 12.27it/s, 63 steps of size 7.71e-02. acc. prob=0.91]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  82%|████████▏ | 1224/1500 [02:24<00:22, 12.28it/s, 63 steps of size 7.71e-02. acc. prob=0.91]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  82%|████████▏ | 1226/1500 [02:24<00:22, 12.25it/s, 63 steps of size 7.71e-02. acc. prob=0.91]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  82%|████████▏ | 1228/1500 [02:25<00:22, 12.27it/s, 63 steps of size 7.71e-02. acc. prob=0.91]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  82%|████████▏ | 1230/1500 [02:25<00:21, 12.28it/s, 63 steps of size 7.71e-02. acc. prob=0.91]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  82%|████████▏ | 1232/1500 [02:25<00:21, 12.27it/s, 63 steps of size 7.71e-02. acc. prob=0.91]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  82%|████████▏ | 1234/1500 [02:25<00:21, 12.28it/s, 63 steps of size 7.71e-02. acc. prob=0.91]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  82%|████████▏ | 1236/1500 [02:25<00:21, 12.29it/s, 63 steps of size 7.71e-02. acc. prob=0.91]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  83%|████████▎ | 1238/1500 [02:25<00:21, 12.29it/s, 63 steps of size 7.71e-02. acc. prob=0.91]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  83%|████████▎ | 1240/1500 [02:26<00:21, 12.15it/s, 63 steps of size 7.71e-02. acc. prob=0.91]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  83%|████████▎ | 1242/1500 [02:26<00:21, 12.10it/s, 63 steps of size 7.71e-02. acc. prob=0.91]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  83%|████████▎ | 1244/1500 [02:26<00:21, 11.76it/s, 63 steps of size 7.71e-02. acc. prob=0.91]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  83%|████████▎ | 1246/1500 [02:26<00:21, 11.88it/s, 63 steps of size 7.71e-02. acc. prob=0.91]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  83%|████████▎ | 1248/1500 [02:26<00:21, 11.99it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  83%|████████▎ | 1250/1500 [02:26<00:21, 11.88it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  83%|████████▎ | 1252/1500 [02:27<00:20, 11.97it/s, 63 steps of size 7.71e-02. acc. prob=0.91]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  84%|████████▎ | 1254/1500 [02:27<00:20, 12.06it/s, 63 steps of size 7.71e-02. acc. prob=0.91]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  84%|████████▎ | 1256/1500 [02:27<00:19, 12.32it/s, 56 steps of size 7.71e-02. acc. prob=0.91]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  84%|████████▍ | 1258/1500 [02:27<00:18, 13.30it/s, 63 steps of size 7.71e-02. acc. prob=0.91]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  84%|████████▍ | 1260/1500 [02:27<00:18, 12.97it/s, 63 steps of size 7.71e-02. acc. prob=0.91]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  84%|████████▍ | 1262/1500 [02:27<00:18, 12.76it/s, 63 steps of size 7.71e-02. acc. prob=0.91]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  84%|████████▍ | 1264/1500 [02:28<00:18, 12.56it/s, 63 steps of size 7.71e-02. acc. prob=0.91]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  84%|████████▍ | 1266/1500 [02:28<00:18, 12.45it/s, 63 steps of size 7.71e-02. acc. prob=0.91]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  85%|████████▍ | 1268/1500 [02:28<00:18, 12.41it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  85%|████████▍ | 1270/1500 [02:28<00:18, 12.37it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  85%|████████▍ | 1272/1500 [02:28<00:18, 12.35it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  85%|████████▍ | 1274/1500 [02:28<00:18, 12.33it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  85%|████████▌ | 1276/1500 [02:29<00:18, 12.32it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  85%|████████▌ | 1278/1500 [02:29<00:18, 12.32it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  85%|████████▌ | 1280/1500 [02:29<00:16, 13.50it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  86%|████████▌ | 1283/1500 [02:29<00:14, 15.01it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  86%|████████▌ | 1285/1500 [02:29<00:15, 14.16it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  86%|████████▌ | 1287/1500 [02:29<00:15, 13.59it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  86%|████████▌ | 1289/1500 [02:29<00:16, 13.18it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  86%|████████▌ | 1291/1500 [02:30<00:16, 12.91it/s, 63 steps of size 7.71e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  86%|████████▌ | 1293/1500 [02:30<00:16, 12.73it/s, 63 steps of size 7.71e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  86%|████████▋ | 1295/1500 [02:30<00:16, 12.59it/s, 63 steps of size 7.71e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  86%|████████▋ | 1297/1500 [02:30<00:15, 13.13it/s, 63 steps of size 7.71e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  87%|████████▋ | 1299/1500 [02:30<00:15, 12.88it/s, 63 steps of size 7.71e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  87%|████████▋ | 1301/1500 [02:30<00:15, 12.70it/s, 63 steps of size 7.71e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  87%|████████▋ | 1303/1500 [02:31<00:15, 12.57it/s, 63 steps of size 7.71e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  87%|████████▋ | 1305/1500 [02:31<00:15, 12.46it/s, 63 steps of size 7.71e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  87%|████████▋ | 1307/1500 [02:31<00:15, 12.41it/s, 63 steps of size 7.71e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  87%|████████▋ | 1309/1500 [02:31<00:15, 12.39it/s, 63 steps of size 7.71e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  87%|████████▋ | 1311/1500 [02:31<00:15, 12.36it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  88%|████████▊ | 1313/1500 [02:31<00:15, 12.40it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  88%|████████▊ | 1315/1500 [02:32<00:14, 12.37it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  88%|████████▊ | 1317/1500 [02:32<00:14, 12.39it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  88%|████████▊ | 1319/1500 [02:32<00:14, 12.36it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  88%|████████▊ | 1321/1500 [02:32<00:14, 12.34it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  88%|████████▊ | 1323/1500 [02:32<00:14, 12.34it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  88%|████████▊ | 1325/1500 [02:32<00:14, 12.33it/s, 63 steps of size 7.71e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  88%|████████▊ | 1327/1500 [02:33<00:14, 12.32it/s, 63 steps of size 7.71e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  89%|████████▊ | 1329/1500 [02:33<00:13, 12.32it/s, 63 steps of size 7.71e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  89%|████████▉ | 1332/1500 [02:33<00:11, 14.06it/s, 63 steps of size 7.71e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  89%|████████▉ | 1334/1500 [02:33<00:12, 13.53it/s, 63 steps of size 7.71e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  89%|████████▉ | 1335/1500 [02:33<00:14, 11.31it/s, 127 steps of size 7.71e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  89%|████████▉ | 1337/1500 [02:33<00:14, 11.60it/s, 63 steps of size 7.71e-02. acc. prob=0.89] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  89%|████████▉ | 1339/1500 [02:34<00:13, 11.82it/s, 63 steps of size 7.71e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  89%|████████▉ | 1341/1500 [02:34<00:13, 11.96it/s, 63 steps of size 7.71e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  90%|████████▉ | 1343/1500 [02:34<00:13, 12.04it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  90%|████████▉ | 1345/1500 [02:34<00:12, 12.11it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  90%|████████▉ | 1347/1500 [02:34<00:12, 12.17it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  90%|████████▉ | 1349/1500 [02:34<00:12, 12.22it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  90%|█████████ | 1351/1500 [02:35<00:12, 12.24it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  90%|█████████ | 1353/1500 [02:35<00:11, 12.26it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  90%|█████████ | 1355/1500 [02:35<00:11, 12.28it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  90%|█████████ | 1357/1500 [02:35<00:11, 12.27it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  91%|█████████ | 1359/1500 [02:35<00:11, 12.29it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  91%|█████████ | 1361/1500 [02:35<00:11, 12.29it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  91%|█████████ | 1363/1500 [02:35<00:11, 12.30it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  91%|█████████ | 1365/1500 [02:36<00:10, 12.30it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  91%|█████████ | 1367/1500 [02:36<00:10, 12.30it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  91%|█████████▏| 1369/1500 [02:36<00:10, 12.30it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  91%|█████████▏| 1371/1500 [02:36<00:10, 12.30it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  92%|█████████▏| 1373/1500 [02:36<00:10, 12.31it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  92%|█████████▏| 1374/1500 [02:36<00:11, 10.99it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  92%|█████████▏| 1376/1500 [02:37<00:10, 11.31it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  92%|█████████▏| 1378/1500 [02:37<00:10, 11.61it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  92%|█████████▏| 1380/1500 [02:37<00:10, 11.77it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  92%|█████████▏| 1382/1500 [02:37<00:09, 11.92it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  92%|█████████▏| 1384/1500 [02:37<00:09, 12.03it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  92%|█████████▏| 1386/1500 [02:37<00:09, 12.11it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  93%|█████████▎| 1388/1500 [02:38<00:09, 12.17it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  93%|█████████▎| 1390/1500 [02:38<00:09, 12.20it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  93%|█████████▎| 1392/1500 [02:38<00:08, 12.23it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  93%|█████████▎| 1394/1500 [02:38<00:08, 12.25it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  93%|█████████▎| 1396/1500 [02:38<00:08, 12.27it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  93%|█████████▎| 1398/1500 [02:38<00:08, 12.28it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  93%|█████████▎| 1400/1500 [02:39<00:08, 12.28it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  93%|█████████▎| 1402/1500 [02:39<00:07, 12.29it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  94%|█████████▎| 1404/1500 [02:39<00:07, 12.29it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  94%|█████████▎| 1406/1500 [02:39<00:07, 12.29it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  94%|█████████▍| 1408/1500 [02:39<00:07, 12.29it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  94%|█████████▍| 1410/1500 [02:39<00:07, 12.30it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  94%|█████████▍| 1412/1500 [02:40<00:07, 12.30it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  94%|█████████▍| 1414/1500 [02:40<00:06, 12.30it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  94%|█████████▍| 1416/1500 [02:40<00:06, 12.31it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  95%|█████████▍| 1418/1500 [02:40<00:06, 12.26it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  95%|█████████▍| 1420/1500 [02:40<00:06, 12.27it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  95%|█████████▍| 1422/1500 [02:40<00:06, 12.29it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  95%|█████████▍| 1424/1500 [02:40<00:06, 12.30it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  95%|█████████▌| 1426/1500 [02:41<00:06, 12.30it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  95%|█████████▌| 1428/1500 [02:41<00:05, 12.30it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  95%|█████████▌| 1430/1500 [02:41<00:05, 12.30it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  95%|█████████▌| 1432/1500 [02:41<00:05, 12.30it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  96%|█████████▌| 1434/1500 [02:41<00:05, 12.30it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  96%|█████████▌| 1436/1500 [02:41<00:05, 12.30it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  96%|█████████▌| 1438/1500 [02:42<00:05, 12.30it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  96%|█████████▌| 1441/1500 [02:42<00:04, 13.95it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  96%|█████████▌| 1443/1500 [02:42<00:04, 13.46it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  96%|█████████▋| 1445/1500 [02:42<00:04, 13.13it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  96%|█████████▋| 1447/1500 [02:42<00:04, 12.88it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  97%|█████████▋| 1449/1500 [02:42<00:04, 12.71it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  97%|█████████▋| 1451/1500 [02:43<00:03, 12.59it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  97%|█████████▋| 1453/1500 [02:43<00:03, 12.50it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  97%|█████████▋| 1455/1500 [02:43<00:03, 12.43it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  97%|█████████▋| 1457/1500 [02:43<00:03, 12.39it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  97%|█████████▋| 1459/1500 [02:43<00:03, 12.37it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  97%|█████████▋| 1461/1500 [02:43<00:03, 12.35it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  98%|█████████▊| 1463/1500 [02:44<00:02, 12.33it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  98%|█████████▊| 1465/1500 [02:44<00:02, 13.09it/s, 37 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  98%|█████████▊| 1467/1500 [02:44<00:02, 12.85it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  98%|█████████▊| 1469/1500 [02:44<00:02, 12.68it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  98%|█████████▊| 1471/1500 [02:44<00:02, 12.57it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  98%|█████████▊| 1473/1500 [02:44<00:02, 12.44it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  98%|█████████▊| 1475/1500 [02:45<00:02, 12.40it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  98%|█████████▊| 1477/1500 [02:45<00:02, 10.72it/s, 127 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  99%|█████████▊| 1479/1500 [02:45<00:01, 11.14it/s, 63 steps of size 7.71e-02. acc. prob=0.90] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  99%|█████████▊| 1481/1500 [02:45<00:01, 11.46it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  99%|█████████▉| 1483/1500 [02:45<00:01, 11.72it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  99%|█████████▉| 1485/1500 [02:45<00:01, 11.89it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  99%|█████████▉| 1487/1500 [02:46<00:01, 12.02it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  99%|█████████▉| 1489/1500 [02:46<00:00, 12.10it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  99%|█████████▉| 1491/1500 [02:46<00:00, 12.18it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample: 100%|█████████▉| 1493/1500 [02:46<00:00, 12.21it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample: 100%|█████████▉| 1495/1500 [02:46<00:00, 12.24it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample: 100%|█████████▉| 1497/1500 [02:46<00:00, 12.44it/s, 57 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample: 100%|█████████▉| 1499/1500 [02:47<00:00, 12.41it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample: 100%|██████████| 1500/1500 [02:47<00:00,  8.97it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\n"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "  0%|          | 0/1500 [00:00<?, ?it/s]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   0%|          | 0/1500 [00:12<?, ?it/s, 437 steps of size 1.05e-02. acc. prob=0.76]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   1%|          | 17/1500 [00:12<18:37,  1.33it/s, 511 steps of size 6.37e-03. acc. prob=0.76]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   1%|          | 18/1500 [00:13<18:37,  1.33it/s, 592 steps of size 7.32e-03. acc. prob=0.77]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   1%|▏         | 19/1500 [00:14<17:57,  1.37it/s, 378 steps of size 6.98e-03. acc. prob=0.77]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   1%|▏         | 20/1500 [00:14<17:44,  1.39it/s, 511 steps of size 1.74e-03. acc. prob=0.75]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   1%|▏         | 21/1500 [00:15<17:58,  1.37it/s, 612 steps of size 2.49e-03. acc. prob=0.77]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   1%|▏         | 22/1500 [00:16<20:31,  1.20it/s, 1023 steps of size 3.57e-03. acc. prob=0.78]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   2%|▏         | 23/1500 [00:17<21:08,  1.16it/s, 743 steps of size 4.95e-03. acc. prob=0.79] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   2%|▏         | 24/1500 [00:18<18:23,  1.34it/s, 282 steps of size 5.36e-03. acc. prob=0.79]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   2%|▏         | 25/1500 [00:18<16:04,  1.53it/s, 281 steps of size 7.15e-03. acc. prob=0.80]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   2%|▏         | 27/1500 [00:18<10:24,  2.36it/s, 66 steps of size 1.16e-02. acc. prob=0.81] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   2%|▏         | 29/1500 [00:18<07:05,  3.46it/s, 17 steps of size 8.27e-03. acc. prob=0.81]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   2%|▏         | 31/1500 [00:18<05:04,  4.82it/s, 46 steps of size 9.85e-03. acc. prob=0.82]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   2%|▏         | 36/1500 [00:19<02:33,  9.54it/s, 20 steps of size 1.20e-02. acc. prob=0.83]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   3%|▎         | 41/1500 [00:19<01:42, 14.29it/s, 28 steps of size 4.35e-03. acc. prob=0.82]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   3%|▎         | 42/1500 [00:19<01:54, 12.76it/s, 113 steps of size 5.76e-03. acc. prob=0.83]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   3%|▎         | 44/1500 [00:19<01:51, 13.03it/s, 64 steps of size 8.37e-03. acc. prob=0.83] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   3%|▎         | 45/1500 [00:19<02:02, 11.85it/s, 99 steps of size 9.85e-03. acc. prob=0.84]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   3%|▎         | 46/1500 [00:19<02:12, 10.99it/s, 94 steps of size 1.28e-02. acc. prob=0.84]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   3%|▎         | 47/1500 [00:19<02:28,  9.76it/s, 115 steps of size 1.28e-02. acc. prob=0.84]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   3%|▎         | 49/1500 [00:20<02:36,  9.25it/s, 133 steps of size 1.32e-02. acc. prob=0.84]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   4%|▎         | 54/1500 [00:20<01:29, 16.23it/s, 49 steps of size 5.91e-03. acc. prob=0.84] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   4%|▍         | 60/1500 [00:20<00:58, 24.75it/s, 31 steps of size 4.71e-03. acc. prob=0.84]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   4%|▍         | 63/1500 [00:20<00:58, 24.51it/s, 25 steps of size 7.02e-03. acc. prob=0.85]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   4%|▍         | 67/1500 [00:20<00:55, 26.03it/s, 44 steps of size 9.37e-03. acc. prob=0.85]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   5%|▍         | 69/1500 [00:20<01:10, 20.32it/s, 115 steps of size 6.50e-03. acc. prob=0.85]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   5%|▍         | 73/1500 [00:20<01:00, 23.60it/s, 15 steps of size 8.16e-03. acc. prob=0.85] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   5%|▌         | 75/1500 [00:21<01:31, 15.64it/s, 167 steps of size 1.06e-02. acc. prob=0.86]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   5%|▌         | 77/1500 [00:21<01:49, 13.03it/s, 147 steps of size 1.15e-02. acc. prob=0.86]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   5%|▌         | 79/1500 [00:21<02:22,  9.98it/s, 230 steps of size 1.04e-02. acc. prob=0.86]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   5%|▌         | 81/1500 [00:21<02:21, 10.00it/s, 114 steps of size 1.28e-02. acc. prob=0.86]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   6%|▌         | 83/1500 [00:22<02:10, 10.84it/s, 38 steps of size 9.83e-03. acc. prob=0.86] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   6%|▌         | 86/1500 [00:22<01:41, 13.99it/s, 31 steps of size 7.89e-03. acc. prob=0.86]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   6%|▌         | 88/1500 [00:22<01:48, 13.04it/s, 131 steps of size 9.47e-03. acc. prob=0.86]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   6%|▌         | 89/1500 [00:22<02:04, 11.30it/s, 118 steps of size 1.15e-02. acc. prob=0.86]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   6%|▌         | 90/1500 [00:22<02:11, 10.75it/s, 88 steps of size 1.37e-02. acc. prob=0.86] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   6%|▌         | 92/1500 [00:22<02:36,  8.99it/s, 189 steps of size 1.01e-02. acc. prob=0.86]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   6%|▋         | 94/1500 [00:23<02:41,  8.70it/s, 151 steps of size 1.33e-02. acc. prob=0.86]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   6%|▋         | 95/1500 [00:23<02:47,  8.41it/s, 105 steps of size 1.59e-02. acc. prob=0.86]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   6%|▋         | 96/1500 [00:23<03:01,  7.75it/s, 129 steps of size 1.88e-02. acc. prob=0.86]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   7%|▋         | 98/1500 [00:23<02:51,  8.15it/s, 106 steps of size 1.30e-02. acc. prob=0.86]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   7%|▋         | 100/1500 [00:23<02:32,  9.15it/s, 91 steps of size 1.37e-02. acc. prob=0.86]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   7%|▋         | 101/1500 [00:24<02:36,  8.96it/s, 94 steps of size 1.61e-01. acc. prob=0.86]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   7%|▋         | 103/1500 [00:24<02:29,  9.37it/s, 142 steps of size 2.56e-02. acc. prob=0.86]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   7%|▋         | 104/1500 [00:24<02:32,  9.16it/s, 92 steps of size 2.82e-02. acc. prob=0.86] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   7%|▋         | 105/1500 [00:24<03:01,  7.67it/s, 157 steps of size 2.74e-02. acc. prob=0.86]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   7%|▋         | 107/1500 [00:24<03:06,  7.47it/s, 158 steps of size 1.41e-02. acc. prob=0.86]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   7%|▋         | 108/1500 [00:25<03:35,  6.47it/s, 177 steps of size 1.85e-02. acc. prob=0.86]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   7%|▋         | 110/1500 [00:25<05:20,  4.33it/s, 511 steps of size 2.05e-02. acc. prob=0.86]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   7%|▋         | 111/1500 [00:26<06:36,  3.50it/s, 374 steps of size 2.63e-02. acc. prob=0.86]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   8%|▊         | 113/1500 [00:26<06:56,  3.33it/s, 471 steps of size 2.43e-03. acc. prob=0.86]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   8%|▊         | 114/1500 [00:28<11:58,  1.93it/s, 1023 steps of size 3.34e-03. acc. prob=0.86]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   8%|▊         | 115/1500 [00:29<15:45,  1.46it/s, 946 steps of size 4.65e-03. acc. prob=0.86] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   8%|▊         | 116/1500 [00:30<18:00,  1.28it/s, 835 steps of size 6.38e-03. acc. prob=0.86]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   8%|▊         | 117/1500 [00:31<19:28,  1.18it/s, 798 steps of size 7.21e-03. acc. prob=0.86]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   8%|▊         | 118/1500 [00:32<18:14,  1.26it/s, 503 steps of size 9.91e-03. acc. prob=0.86]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   8%|▊         | 119/1500 [00:32<16:34,  1.39it/s, 417 steps of size 1.33e-02. acc. prob=0.86]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   8%|▊         | 120/1500 [00:32<13:44,  1.67it/s, 227 steps of size 1.77e-02. acc. prob=0.86]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   8%|▊         | 121/1500 [00:33<11:08,  2.06it/s, 162 steps of size 1.80e-02. acc. prob=0.86]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   8%|▊         | 122/1500 [00:33<09:37,  2.39it/s, 203 steps of size 2.06e-02. acc. prob=0.86]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   8%|▊         | 123/1500 [00:33<07:45,  2.96it/s, 112 steps of size 2.61e-02. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   8%|▊         | 125/1500 [00:34<10:13,  2.24it/s, 835 steps of size 6.51e-03. acc. prob=0.86]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   8%|▊         | 126/1500 [00:35<12:44,  1.80it/s, 694 steps of size 8.83e-03. acc. prob=0.86]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   9%|▊         | 128/1500 [00:35<09:07,  2.51it/s, 196 steps of size 1.37e-02. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   9%|▊         | 129/1500 [00:36<08:20,  2.74it/s, 193 steps of size 1.70e-02. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   9%|▊         | 130/1500 [00:36<07:43,  2.96it/s, 198 steps of size 2.06e-02. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   9%|▊         | 131/1500 [00:36<07:05,  3.22it/s, 180 steps of size 2.49e-02. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   9%|▉         | 132/1500 [00:36<05:51,  3.89it/s, 87 steps of size 5.50e-03. acc. prob=0.86] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   9%|▉         | 133/1500 [00:38<12:34,  1.81it/s, 1023 steps of size 7.17e-03. acc. prob=0.86]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   9%|▉         | 134/1500 [00:38<12:38,  1.80it/s, 436 steps of size 9.47e-03. acc. prob=0.87] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   9%|▉         | 135/1500 [00:39<15:35,  1.46it/s, 780 steps of size 6.43e-03. acc. prob=0.86]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   9%|▉         | 136/1500 [00:41<19:46,  1.15it/s, 1023 steps of size 8.25e-03. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   9%|▉         | 137/1500 [00:41<19:11,  1.18it/s, 605 steps of size 1.05e-02. acc. prob=0.87] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   9%|▉         | 139/1500 [00:43<17:14,  1.32it/s, 1023 steps of size 1.42e-03. acc. prob=0.86]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   9%|▉         | 140/1500 [00:44<20:19,  1.12it/s, 1023 steps of size 1.87e-03. acc. prob=0.86]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   9%|▉         | 141/1500 [00:45<22:46,  1.01s/it, 1023 steps of size 2.48e-03. acc. prob=0.86]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:   9%|▉         | 142/1500 [00:47<24:38,  1.09s/it, 1023 steps of size 3.27e-03. acc. prob=0.86]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  10%|▉         | 143/1500 [00:47<21:44,  1.04it/s, 492 steps of size 4.18e-03. acc. prob=0.86] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  10%|▉         | 144/1500 [00:49<24:00,  1.06s/it, 1023 steps of size 5.46e-03. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  10%|▉         | 145/1500 [00:50<25:37,  1.13s/it, 1023 steps of size 7.03e-03. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  10%|▉         | 146/1500 [00:50<21:14,  1.06it/s, 368 steps of size 8.99e-03. acc. prob=0.87] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  10%|▉         | 147/1500 [00:51<19:00,  1.19it/s, 473 steps of size 1.16e-02. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  10%|▉         | 148/1500 [00:52<22:08,  1.02it/s, 1023 steps of size 1.49e-02. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  10%|▉         | 149/1500 [00:53<19:34,  1.15it/s, 468 steps of size 1.74e-02. acc. prob=0.87] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  10%|█         | 150/1500 [00:54<18:07,  1.24it/s, 511 steps of size 1.26e-02. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  10%|█         | 153/1500 [00:55<13:30,  1.66it/s, 1023 steps of size 1.36e-03. acc. prob=0.86]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  10%|█         | 154/1500 [00:56<17:03,  1.32it/s, 1023 steps of size 1.28e-03. acc. prob=0.86]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  10%|█         | 155/1500 [00:58<19:57,  1.12it/s, 1023 steps of size 1.41e-03. acc. prob=0.86]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  10%|█         | 156/1500 [00:59<22:19,  1.00it/s, 1023 steps of size 1.65e-03. acc. prob=0.86]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  10%|█         | 157/1500 [01:00<24:10,  1.08s/it, 1023 steps of size 2.10e-03. acc. prob=0.86]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  11%|█         | 158/1500 [01:01<25:34,  1.14s/it, 1023 steps of size 2.76e-03. acc. prob=0.86]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  11%|█         | 159/1500 [01:03<27:21,  1.22s/it, 1023 steps of size 3.25e-03. acc. prob=0.86]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  11%|█         | 160/1500 [01:04<27:54,  1.25s/it, 1023 steps of size 3.76e-03. acc. prob=0.86]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  11%|█         | 161/1500 [01:06<28:18,  1.27s/it, 1023 steps of size 4.36e-03. acc. prob=0.86]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  11%|█         | 162/1500 [01:07<28:51,  1.29s/it, 1023 steps of size 4.39e-03. acc. prob=0.86]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  11%|█         | 163/1500 [01:08<29:08,  1.31s/it, 1023 steps of size 5.88e-03. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  11%|█         | 164/1500 [01:10<29:22,  1.32s/it, 1023 steps of size 4.64e-03. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  11%|█         | 165/1500 [01:11<29:30,  1.33s/it, 1023 steps of size 6.42e-03. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  11%|█         | 166/1500 [01:11<22:52,  1.03s/it, 253 steps of size 7.45e-03. acc. prob=0.87] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  11%|█         | 167/1500 [01:13<24:45,  1.11s/it, 1023 steps of size 3.65e-03. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  11%|█         | 168/1500 [01:14<26:03,  1.17s/it, 1023 steps of size 4.84e-03. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  11%|█▏        | 169/1500 [01:15<23:54,  1.08s/it, 662 steps of size 6.50e-03. acc. prob=0.87] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  11%|█▏        | 170/1500 [01:16<25:42,  1.16s/it, 1023 steps of size 1.45e-03. acc. prob=0.86]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  11%|█▏        | 171/1500 [01:17<26:50,  1.21s/it, 1023 steps of size 2.03e-03. acc. prob=0.86]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  11%|█▏        | 172/1500 [01:19<27:47,  1.26s/it, 1023 steps of size 2.80e-03. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  12%|█▏        | 173/1500 [01:20<28:10,  1.27s/it, 1023 steps of size 3.69e-03. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  12%|█▏        | 174/1500 [01:21<28:27,  1.29s/it, 1023 steps of size 4.84e-03. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  12%|█▏        | 175/1500 [01:23<28:36,  1.30s/it, 1023 steps of size 5.83e-04. acc. prob=0.86]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  12%|█▏        | 176/1500 [01:24<28:43,  1.30s/it, 1023 steps of size 8.09e-04. acc. prob=0.86]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  12%|█▏        | 177/1500 [01:25<28:58,  1.31s/it, 1023 steps of size 1.12e-03. acc. prob=0.86]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  12%|█▏        | 178/1500 [01:27<29:00,  1.32s/it, 1023 steps of size 1.54e-03. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  12%|█▏        | 179/1500 [01:28<28:58,  1.32s/it, 1023 steps of size 2.10e-03. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  12%|█▏        | 180/1500 [01:29<28:56,  1.32s/it, 1023 steps of size 2.84e-03. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  12%|█▏        | 181/1500 [01:31<28:54,  1.32s/it, 1023 steps of size 3.52e-03. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  12%|█▏        | 182/1500 [01:32<28:53,  1.32s/it, 1023 steps of size 4.69e-03. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  12%|█▏        | 183/1500 [01:33<24:51,  1.13s/it, 544 steps of size 4.07e-03. acc. prob=0.87] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  12%|█▏        | 184/1500 [01:34<23:14,  1.06s/it, 674 steps of size 4.68e-03. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  12%|█▏        | 185/1500 [01:35<24:55,  1.14s/it, 1023 steps of size 5.95e-03. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  12%|█▏        | 186/1500 [01:35<19:10,  1.14it/s, 205 steps of size 2.48e-03. acc. prob=0.87] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  12%|█▏        | 187/1500 [01:35<14:26,  1.51it/s, 123 steps of size 3.24e-03. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  13%|█▎        | 188/1500 [01:35<11:32,  1.90it/s, 169 steps of size 4.17e-03. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  13%|█▎        | 189/1500 [01:37<16:40,  1.31it/s, 1023 steps of size 3.90e-03. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  13%|█▎        | 190/1500 [01:38<20:16,  1.08it/s, 1023 steps of size 4.71e-03. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  13%|█▎        | 191/1500 [01:39<22:47,  1.04s/it, 1023 steps of size 4.98e-03. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  13%|█▎        | 192/1500 [01:41<24:44,  1.13s/it, 1023 steps of size 4.04e-03. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  13%|█▎        | 193/1500 [01:42<25:54,  1.19s/it, 1023 steps of size 1.23e-03. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  13%|█▎        | 194/1500 [01:43<26:41,  1.23s/it, 1023 steps of size 1.63e-03. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  13%|█▎        | 195/1500 [01:45<27:24,  1.26s/it, 1023 steps of size 2.14e-03. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  13%|█▎        | 196/1500 [01:46<27:54,  1.28s/it, 1023 steps of size 2.80e-03. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  13%|█▎        | 197/1500 [01:47<28:37,  1.32s/it, 1023 steps of size 3.16e-03. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  13%|█▎        | 198/1500 [01:49<28:42,  1.32s/it, 1023 steps of size 4.11e-03. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  13%|█▎        | 199/1500 [01:50<28:45,  1.33s/it, 1023 steps of size 3.86e-03. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  13%|█▎        | 200/1500 [01:52<28:49,  1.33s/it, 1023 steps of size 2.00e-03. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  13%|█▎        | 201/1500 [01:53<28:47,  1.33s/it, 1023 steps of size 2.53e-03. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  13%|█▎        | 202/1500 [01:54<28:51,  1.33s/it, 1023 steps of size 3.26e-03. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  14%|█▎        | 203/1500 [01:56<28:50,  1.33s/it, 1023 steps of size 3.85e-03. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  14%|█▎        | 205/1500 [01:57<22:30,  1.04s/it, 1023 steps of size 2.24e-03. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  14%|█▎        | 206/1500 [01:58<23:56,  1.11s/it, 1023 steps of size 2.80e-03. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  14%|█▍        | 207/1500 [02:00<25:06,  1.17s/it, 1023 steps of size 3.47e-03. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  14%|█▍        | 208/1500 [02:01<26:06,  1.21s/it, 1023 steps of size 3.97e-03. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  14%|█▍        | 209/1500 [02:02<26:44,  1.24s/it, 1023 steps of size 3.84e-03. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  14%|█▍        | 210/1500 [02:04<27:10,  1.26s/it, 1023 steps of size 3.25e-03. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  14%|█▍        | 211/1500 [02:05<27:29,  1.28s/it, 1023 steps of size 3.92e-03. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  14%|█▍        | 212/1500 [02:06<27:42,  1.29s/it, 1023 steps of size 4.85e-03. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  14%|█▍        | 213/1500 [02:07<27:53,  1.30s/it, 1023 steps of size 4.76e-03. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  14%|█▍        | 214/1500 [02:09<28:05,  1.31s/it, 1023 steps of size 5.99e-03. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  14%|█▍        | 215/1500 [02:10<28:09,  1.32s/it, 1023 steps of size 6.78e-03. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  14%|█▍        | 216/1500 [02:11<25:23,  1.19s/it, 685 steps of size 3.43e-03. acc. prob=0.87] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  14%|█▍        | 217/1500 [02:12<26:10,  1.22s/it, 1023 steps of size 3.88e-03. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  15%|█▍        | 218/1500 [02:14<26:44,  1.25s/it, 1023 steps of size 4.88e-03. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  15%|█▍        | 219/1500 [02:15<27:06,  1.27s/it, 1023 steps of size 6.13e-03. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  15%|█▍        | 220/1500 [02:16<27:22,  1.28s/it, 1023 steps of size 4.12e-03. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  15%|█▍        | 221/1500 [02:18<27:34,  1.29s/it, 1023 steps of size 5.04e-03. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  15%|█▍        | 222/1500 [02:19<27:42,  1.30s/it, 1023 steps of size 6.06e-03. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  15%|█▍        | 223/1500 [02:20<27:49,  1.31s/it, 1023 steps of size 1.90e-03. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  15%|█▍        | 224/1500 [02:22<28:00,  1.32s/it, 1023 steps of size 2.39e-03. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  15%|█▌        | 225/1500 [02:23<28:03,  1.32s/it, 1023 steps of size 2.88e-03. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  15%|█▌        | 226/1500 [02:24<28:03,  1.32s/it, 1023 steps of size 3.57e-03. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  15%|█▌        | 227/1500 [02:26<28:00,  1.32s/it, 1023 steps of size 4.30e-03. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  15%|█▌        | 228/1500 [02:27<27:57,  1.32s/it, 1023 steps of size 2.70e-03. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  15%|█▌        | 229/1500 [02:28<27:57,  1.32s/it, 1023 steps of size 3.31e-03. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  15%|█▌        | 230/1500 [02:30<28:02,  1.33s/it, 1023 steps of size 3.93e-03. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  15%|█▌        | 231/1500 [02:31<27:57,  1.32s/it, 1023 steps of size 4.38e-03. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  15%|█▌        | 232/1500 [02:32<27:53,  1.32s/it, 1023 steps of size 4.59e-03. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  16%|█▌        | 233/1500 [02:33<27:50,  1.32s/it, 1023 steps of size 5.61e-03. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  16%|█▌        | 234/1500 [02:35<27:49,  1.32s/it, 1023 steps of size 6.53e-03. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  16%|█▌        | 235/1500 [02:36<27:46,  1.32s/it, 1023 steps of size 6.36e-03. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  16%|█▌        | 236/1500 [02:37<27:45,  1.32s/it, 1023 steps of size 4.10e-03. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  16%|█▌        | 237/1500 [02:39<27:50,  1.32s/it, 1023 steps of size 4.71e-03. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  16%|█▌        | 238/1500 [02:40<27:49,  1.32s/it, 1023 steps of size 5.56e-03. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  16%|█▌        | 239/1500 [02:41<27:45,  1.32s/it, 1023 steps of size 4.04e-03. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  16%|█▌        | 240/1500 [02:43<27:46,  1.32s/it, 1023 steps of size 4.83e-03. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  16%|█▌        | 241/1500 [02:44<27:43,  1.32s/it, 1023 steps of size 5.06e-03. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  16%|█▌        | 242/1500 [02:45<27:37,  1.32s/it, 1023 steps of size 4.94e-03. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  16%|█▌        | 243/1500 [02:47<27:34,  1.32s/it, 1023 steps of size 4.21e-03. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  16%|█▋        | 244/1500 [02:48<27:33,  1.32s/it, 1023 steps of size 5.15e-03. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  16%|█▋        | 245/1500 [02:49<27:31,  1.32s/it, 1023 steps of size 6.18e-03. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  16%|█▋        | 246/1500 [02:51<27:29,  1.32s/it, 1023 steps of size 5.69e-03. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  16%|█▋        | 247/1500 [02:52<27:27,  1.32s/it, 1023 steps of size 6.19e-03. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  17%|█▋        | 248/1500 [02:53<27:26,  1.31s/it, 1023 steps of size 7.20e-03. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  17%|█▋        | 249/1500 [02:54<23:18,  1.12s/it, 511 steps of size 8.59e-03. acc. prob=0.88] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  17%|█▋        | 250/1500 [02:54<18:13,  1.14it/s, 238 steps of size 8.39e-03. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  17%|█▋        | 251/1500 [02:55<16:50,  1.24it/s, 511 steps of size 1.00e-01. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  17%|█▋        | 253/1500 [02:56<12:12,  1.70it/s, 511 steps of size 1.29e-02. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  17%|█▋        | 254/1500 [02:56<12:33,  1.65it/s, 511 steps of size 6.97e-03. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  17%|█▋        | 255/1500 [02:57<16:10,  1.28it/s, 992 steps of size 8.35e-03. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  17%|█▋        | 256/1500 [02:58<15:28,  1.34it/s, 511 steps of size 1.05e-02. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  17%|█▋        | 257/1500 [02:59<14:56,  1.39it/s, 511 steps of size 1.32e-02. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  17%|█▋        | 258/1500 [02:59<14:31,  1.43it/s, 511 steps of size 1.34e-02. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  17%|█▋        | 259/1500 [03:00<12:16,  1.69it/s, 255 steps of size 1.74e-02. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  17%|█▋        | 260/1500 [03:00<10:38,  1.94it/s, 255 steps of size 2.37e-02. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  17%|█▋        | 261/1500 [03:00<09:29,  2.17it/s, 255 steps of size 3.16e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  17%|█▋        | 262/1500 [03:01<08:40,  2.38it/s, 255 steps of size 1.87e-03. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  18%|█▊        | 263/1500 [03:02<14:11,  1.45it/s, 1023 steps of size 2.59e-03. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  18%|█▊        | 264/1500 [03:03<18:04,  1.14it/s, 1023 steps of size 3.61e-03. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  18%|█▊        | 265/1500 [03:05<20:45,  1.01s/it, 1023 steps of size 4.98e-03. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  18%|█▊        | 266/1500 [03:06<22:41,  1.10s/it, 1023 steps of size 6.82e-03. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  18%|█▊        | 267/1500 [03:07<19:55,  1.03it/s, 511 steps of size 9.39e-03. acc. prob=0.87] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  18%|█▊        | 268/1500 [03:07<17:59,  1.14it/s, 511 steps of size 1.23e-02. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  18%|█▊        | 269/1500 [03:08<16:37,  1.23it/s, 511 steps of size 1.69e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  18%|█▊        | 270/1500 [03:08<13:38,  1.50it/s, 255 steps of size 2.24e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  18%|█▊        | 271/1500 [03:09<11:33,  1.77it/s, 255 steps of size 3.00e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  18%|█▊        | 272/1500 [03:09<10:06,  2.03it/s, 255 steps of size 9.46e-03. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  18%|█▊        | 273/1500 [03:10<11:08,  1.83it/s, 511 steps of size 1.29e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  18%|█▊        | 274/1500 [03:10<11:49,  1.73it/s, 511 steps of size 1.46e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  18%|█▊        | 275/1500 [03:11<10:17,  1.99it/s, 255 steps of size 1.87e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  18%|█▊        | 276/1500 [03:11<09:12,  2.22it/s, 255 steps of size 2.46e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  18%|█▊        | 277/1500 [03:11<08:26,  2.42it/s, 255 steps of size 1.60e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  19%|█▊        | 278/1500 [03:12<07:54,  2.58it/s, 255 steps of size 1.72e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  19%|█▊        | 279/1500 [03:12<07:32,  2.70it/s, 255 steps of size 2.17e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  19%|█▊        | 280/1500 [03:12<07:16,  2.79it/s, 255 steps of size 2.88e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  19%|█▊        | 281/1500 [03:13<07:05,  2.87it/s, 254 steps of size 6.51e-03. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  19%|█▉        | 282/1500 [03:14<12:57,  1.57it/s, 1023 steps of size 8.71e-03. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  19%|█▉        | 283/1500 [03:15<13:03,  1.55it/s, 511 steps of size 1.11e-02. acc. prob=0.88] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  19%|█▉        | 284/1500 [03:15<13:08,  1.54it/s, 511 steps of size 1.30e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  19%|█▉        | 285/1500 [03:16<11:10,  1.81it/s, 255 steps of size 1.42e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  19%|█▉        | 286/1500 [03:16<09:48,  2.06it/s, 255 steps of size 1.86e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  19%|█▉        | 287/1500 [03:16<08:51,  2.28it/s, 255 steps of size 2.41e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  19%|█▉        | 288/1500 [03:17<08:12,  2.46it/s, 255 steps of size 3.02e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  19%|█▉        | 289/1500 [03:17<07:46,  2.59it/s, 255 steps of size 5.20e-03. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  19%|█▉        | 290/1500 [03:18<13:28,  1.50it/s, 1023 steps of size 6.71e-03. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  19%|█▉        | 291/1500 [03:20<17:26,  1.16it/s, 1023 steps of size 8.73e-03. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  20%|█▉        | 293/1500 [03:20<12:39,  1.59it/s, 511 steps of size 1.37e-02. acc. prob=0.88] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  20%|█▉        | 294/1500 [03:21<12:47,  1.57it/s, 511 steps of size 1.77e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  20%|█▉        | 295/1500 [03:21<11:09,  1.80it/s, 255 steps of size 2.21e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  20%|█▉        | 296/1500 [03:22<09:54,  2.02it/s, 255 steps of size 2.74e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  20%|█▉        | 297/1500 [03:22<08:58,  2.24it/s, 255 steps of size 3.38e-03. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  20%|█▉        | 298/1500 [03:23<13:55,  1.44it/s, 1023 steps of size 4.33e-03. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  20%|█▉        | 299/1500 [03:25<18:00,  1.11it/s, 1023 steps of size 5.57e-03. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  20%|██        | 300/1500 [03:26<20:31,  1.03s/it, 1023 steps of size 7.17e-03. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  20%|██        | 301/1500 [03:27<22:12,  1.11s/it, 1023 steps of size 9.21e-03. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  20%|██        | 302/1500 [03:29<23:24,  1.17s/it, 1023 steps of size 1.18e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  20%|██        | 303/1500 [03:29<20:20,  1.02s/it, 511 steps of size 1.26e-02. acc. prob=0.88] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  20%|██        | 304/1500 [03:30<18:43,  1.06it/s, 511 steps of size 1.59e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  20%|██        | 305/1500 [03:31<17:06,  1.16it/s, 511 steps of size 1.90e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  20%|██        | 306/1500 [03:31<15:54,  1.25it/s, 511 steps of size 2.37e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  20%|██        | 307/1500 [03:32<13:05,  1.52it/s, 255 steps of size 1.75e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  21%|██        | 308/1500 [03:32<11:09,  1.78it/s, 255 steps of size 2.00e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  21%|██        | 309/1500 [03:32<09:48,  2.02it/s, 255 steps of size 2.09e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  21%|██        | 310/1500 [03:33<08:50,  2.24it/s, 255 steps of size 2.62e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  21%|██        | 311/1500 [03:33<07:11,  2.76it/s, 127 steps of size 3.65e-03. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  21%|██        | 312/1500 [03:34<12:52,  1.54it/s, 1023 steps of size 4.63e-03. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  21%|██        | 313/1500 [03:35<16:49,  1.18it/s, 1023 steps of size 5.85e-03. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  21%|██        | 314/1500 [03:37<19:33,  1.01it/s, 1023 steps of size 7.31e-03. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  21%|██        | 315/1500 [03:37<17:37,  1.12it/s, 517 steps of size 9.13e-03. acc. prob=0.88] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  21%|██        | 316/1500 [03:38<16:13,  1.22it/s, 511 steps of size 1.14e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  21%|██        | 317/1500 [03:39<15:15,  1.29it/s, 511 steps of size 1.42e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  21%|██        | 318/1500 [03:39<14:37,  1.35it/s, 511 steps of size 1.71e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  21%|██▏       | 319/1500 [03:40<12:13,  1.61it/s, 255 steps of size 2.08e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  21%|██▏       | 320/1500 [03:40<10:30,  1.87it/s, 255 steps of size 2.10e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  21%|██▏       | 321/1500 [03:40<09:17,  2.12it/s, 255 steps of size 2.29e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  21%|██▏       | 322/1500 [03:41<08:25,  2.33it/s, 255 steps of size 2.03e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  22%|██▏       | 323/1500 [03:41<07:50,  2.50it/s, 255 steps of size 2.46e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  22%|██▏       | 324/1500 [03:41<07:24,  2.64it/s, 255 steps of size 3.04e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  22%|██▏       | 325/1500 [03:42<07:06,  2.75it/s, 255 steps of size 1.53e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  22%|██▏       | 326/1500 [03:42<06:54,  2.83it/s, 255 steps of size 1.88e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  22%|██▏       | 327/1500 [03:42<06:44,  2.90it/s, 255 steps of size 2.30e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  22%|██▏       | 329/1500 [03:43<07:00,  2.79it/s, 511 steps of size 1.12e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  22%|██▏       | 330/1500 [03:44<08:26,  2.31it/s, 511 steps of size 1.33e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  22%|██▏       | 331/1500 [03:44<09:34,  2.03it/s, 511 steps of size 1.64e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  22%|██▏       | 332/1500 [03:45<10:27,  1.86it/s, 511 steps of size 2.01e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  22%|██▏       | 333/1500 [03:45<09:18,  2.09it/s, 255 steps of size 2.35e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  22%|██▏       | 334/1500 [03:46<08:27,  2.30it/s, 255 steps of size 2.76e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  22%|██▏       | 335/1500 [03:46<06:55,  2.80it/s, 127 steps of size 2.90e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  22%|██▏       | 336/1500 [03:46<05:49,  3.33it/s, 127 steps of size 2.83e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  23%|██▎       | 338/1500 [03:47<06:25,  3.02it/s, 511 steps of size 7.13e-03. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  23%|██▎       | 339/1500 [03:47<07:57,  2.43it/s, 511 steps of size 8.67e-03. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  23%|██▎       | 340/1500 [03:48<09:11,  2.10it/s, 511 steps of size 1.06e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  23%|██▎       | 341/1500 [03:49<09:39,  2.00it/s, 440 steps of size 1.27e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  23%|██▎       | 342/1500 [03:49<10:29,  1.84it/s, 511 steps of size 1.54e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  23%|██▎       | 343/1500 [03:50<09:17,  2.07it/s, 255 steps of size 1.83e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  23%|██▎       | 344/1500 [03:50<08:26,  2.28it/s, 255 steps of size 1.65e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  23%|██▎       | 345/1500 [03:50<07:48,  2.47it/s, 255 steps of size 1.95e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  23%|██▎       | 346/1500 [03:51<07:21,  2.61it/s, 255 steps of size 2.36e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  23%|██▎       | 347/1500 [03:51<07:02,  2.73it/s, 255 steps of size 2.22e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  23%|██▎       | 348/1500 [03:51<06:52,  2.79it/s, 255 steps of size 2.12e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  23%|██▎       | 349/1500 [03:52<06:46,  2.83it/s, 255 steps of size 2.32e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  23%|██▎       | 350/1500 [03:52<06:40,  2.87it/s, 255 steps of size 2.66e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  23%|██▎       | 351/1500 [03:52<05:37,  3.40it/s, 127 steps of size 3.07e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  23%|██▎       | 352/1500 [03:52<05:48,  3.29it/s, 255 steps of size 1.43e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  24%|██▎       | 353/1500 [03:53<05:56,  3.21it/s, 255 steps of size 1.72e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  24%|██▎       | 354/1500 [03:53<06:02,  3.16it/s, 255 steps of size 1.83e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  24%|██▎       | 355/1500 [03:53<06:06,  3.13it/s, 255 steps of size 2.02e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  24%|██▎       | 356/1500 [03:54<06:08,  3.10it/s, 255 steps of size 2.38e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  24%|██▍       | 357/1500 [03:54<06:10,  3.09it/s, 255 steps of size 2.76e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  24%|██▍       | 358/1500 [03:54<06:13,  3.06it/s, 255 steps of size 1.45e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  24%|██▍       | 359/1500 [03:55<08:05,  2.35it/s, 511 steps of size 1.43e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  24%|██▍       | 360/1500 [03:56<09:24,  2.02it/s, 511 steps of size 1.71e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  24%|██▍       | 361/1500 [03:56<08:27,  2.25it/s, 255 steps of size 1.87e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  24%|██▍       | 362/1500 [03:56<07:46,  2.44it/s, 255 steps of size 2.11e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  24%|██▍       | 363/1500 [03:57<07:18,  2.59it/s, 255 steps of size 2.00e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  24%|██▍       | 364/1500 [03:57<06:58,  2.72it/s, 255 steps of size 2.39e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  24%|██▍       | 365/1500 [03:57<05:48,  3.26it/s, 127 steps of size 2.64e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  24%|██▍       | 366/1500 [03:58<05:55,  3.19it/s, 255 steps of size 2.97e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  25%|██▍       | 368/1500 [03:58<05:00,  3.76it/s, 255 steps of size 2.43e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  25%|██▍       | 369/1500 [03:58<05:17,  3.56it/s, 255 steps of size 2.86e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  25%|██▍       | 370/1500 [03:59<04:42,  3.99it/s, 127 steps of size 6.65e-03. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  25%|██▍       | 371/1500 [03:59<06:47,  2.77it/s, 511 steps of size 7.93e-03. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  25%|██▍       | 372/1500 [04:00<08:20,  2.25it/s, 511 steps of size 9.14e-03. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  25%|██▍       | 373/1500 [04:00<09:29,  1.98it/s, 511 steps of size 1.06e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  25%|██▍       | 374/1500 [04:01<10:18,  1.82it/s, 511 steps of size 1.22e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  25%|██▌       | 375/1500 [04:02<10:53,  1.72it/s, 511 steps of size 1.43e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  25%|██▌       | 376/1500 [04:02<11:18,  1.66it/s, 511 steps of size 1.60e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  25%|██▌       | 377/1500 [04:03<09:46,  1.92it/s, 255 steps of size 1.63e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  25%|██▌       | 378/1500 [04:03<08:44,  2.14it/s, 255 steps of size 1.93e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  25%|██▌       | 379/1500 [04:03<07:58,  2.34it/s, 255 steps of size 2.26e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  25%|██▌       | 380/1500 [04:04<07:25,  2.51it/s, 255 steps of size 2.63e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  25%|██▌       | 382/1500 [04:05<09:50,  1.89it/s, 1023 steps of size 8.00e-03. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  26%|██▌       | 383/1500 [04:06<10:26,  1.78it/s, 511 steps of size 9.47e-03. acc. prob=0.88] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  26%|██▌       | 384/1500 [04:07<11:09,  1.67it/s, 511 steps of size 1.11e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  26%|██▌       | 385/1500 [04:07<11:31,  1.61it/s, 511 steps of size 1.29e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  26%|██▌       | 386/1500 [04:08<10:02,  1.85it/s, 255 steps of size 1.51e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  26%|██▌       | 387/1500 [04:08<10:40,  1.74it/s, 511 steps of size 1.72e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  26%|██▌       | 388/1500 [04:09<09:20,  1.98it/s, 255 steps of size 1.93e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  26%|██▌       | 389/1500 [04:09<08:22,  2.21it/s, 255 steps of size 1.70e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  26%|██▌       | 390/1500 [04:09<07:41,  2.40it/s, 255 steps of size 1.93e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  26%|██▌       | 391/1500 [04:09<07:12,  2.56it/s, 255 steps of size 1.53e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  26%|██▌       | 392/1500 [04:10<06:51,  2.69it/s, 255 steps of size 1.74e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  26%|██▌       | 393/1500 [04:10<06:37,  2.79it/s, 255 steps of size 1.87e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  26%|██▋       | 394/1500 [04:10<06:26,  2.86it/s, 255 steps of size 2.10e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  26%|██▋       | 395/1500 [04:11<06:19,  2.91it/s, 255 steps of size 2.33e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  26%|██▋       | 396/1500 [04:11<06:14,  2.95it/s, 255 steps of size 2.72e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  26%|██▋       | 397/1500 [04:11<05:16,  3.49it/s, 127 steps of size 1.07e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  27%|██▋       | 398/1500 [04:12<09:19,  1.97it/s, 511 steps of size 1.25e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  27%|██▋       | 399/1500 [04:13<08:25,  2.18it/s, 255 steps of size 1.44e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  27%|██▋       | 400/1500 [04:13<09:31,  1.93it/s, 511 steps of size 1.69e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  27%|██▋       | 401/1500 [04:14<08:27,  2.16it/s, 255 steps of size 1.97e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  27%|██▋       | 402/1500 [04:14<07:43,  2.37it/s, 255 steps of size 2.17e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  27%|██▋       | 403/1500 [04:14<07:12,  2.54it/s, 255 steps of size 1.99e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  27%|██▋       | 404/1500 [04:15<06:50,  2.67it/s, 255 steps of size 1.14e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  27%|██▋       | 405/1500 [04:15<08:23,  2.18it/s, 511 steps of size 1.32e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  27%|██▋       | 406/1500 [04:16<09:29,  1.92it/s, 511 steps of size 1.47e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  27%|██▋       | 407/1500 [04:17<10:14,  1.78it/s, 511 steps of size 1.71e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  27%|██▋       | 408/1500 [04:17<09:01,  2.02it/s, 255 steps of size 1.87e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  27%|██▋       | 409/1500 [04:17<08:06,  2.24it/s, 255 steps of size 2.16e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  27%|██▋       | 410/1500 [04:18<07:26,  2.44it/s, 255 steps of size 2.29e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  27%|██▋       | 411/1500 [04:18<06:59,  2.59it/s, 255 steps of size 2.63e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  27%|██▋       | 412/1500 [04:18<06:40,  2.72it/s, 255 steps of size 2.56e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  28%|██▊       | 413/1500 [04:18<05:33,  3.26it/s, 127 steps of size 2.95e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  28%|██▊       | 414/1500 [04:19<04:46,  3.79it/s, 127 steps of size 8.02e-03. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  28%|██▊       | 415/1500 [04:19<06:53,  2.62it/s, 511 steps of size 8.84e-03. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  28%|██▊       | 416/1500 [04:20<08:23,  2.15it/s, 511 steps of size 9.92e-03. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  28%|██▊       | 417/1500 [04:21<09:26,  1.91it/s, 511 steps of size 1.15e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  28%|██▊       | 418/1500 [04:21<10:09,  1.77it/s, 511 steps of size 1.32e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  28%|██▊       | 419/1500 [04:22<10:40,  1.69it/s, 511 steps of size 1.52e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  28%|██▊       | 420/1500 [04:22<09:14,  1.95it/s, 255 steps of size 1.31e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  28%|██▊       | 421/1500 [04:23<10:00,  1.80it/s, 511 steps of size 1.52e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  28%|██▊       | 422/1500 [04:23<08:51,  2.03it/s, 255 steps of size 1.75e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  28%|██▊       | 423/1500 [04:24<08:01,  2.24it/s, 255 steps of size 1.66e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  28%|██▊       | 424/1500 [04:24<07:39,  2.34it/s, 255 steps of size 1.90e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  28%|██▊       | 425/1500 [04:24<07:11,  2.49it/s, 255 steps of size 2.17e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  28%|██▊       | 426/1500 [04:25<06:51,  2.61it/s, 255 steps of size 2.51e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  28%|██▊       | 427/1500 [04:25<06:33,  2.73it/s, 255 steps of size 1.71e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  29%|██▊       | 428/1500 [04:26<08:07,  2.20it/s, 511 steps of size 1.97e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  29%|██▊       | 429/1500 [04:26<07:27,  2.39it/s, 255 steps of size 1.46e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  29%|██▊       | 430/1500 [04:27<08:49,  2.02it/s, 511 steps of size 1.64e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  29%|██▊       | 431/1500 [04:27<07:56,  2.24it/s, 255 steps of size 1.81e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  29%|██▉       | 432/1500 [04:27<07:18,  2.44it/s, 255 steps of size 1.74e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  29%|██▉       | 433/1500 [04:28<06:51,  2.59it/s, 255 steps of size 1.99e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  29%|██▉       | 434/1500 [04:28<08:17,  2.14it/s, 511 steps of size 2.25e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  29%|██▉       | 435/1500 [04:29<07:33,  2.35it/s, 255 steps of size 2.46e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  29%|██▉       | 436/1500 [04:29<06:48,  2.61it/s, 223 steps of size 2.02e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  29%|██▉       | 437/1500 [04:29<06:30,  2.72it/s, 255 steps of size 2.30e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  29%|██▉       | 438/1500 [04:30<06:17,  2.81it/s, 255 steps of size 2.57e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  29%|██▉       | 439/1500 [04:30<05:58,  2.96it/s, 230 steps of size 2.24e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  29%|██▉       | 440/1500 [04:30<05:54,  2.99it/s, 255 steps of size 1.94e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  29%|██▉       | 441/1500 [04:30<05:52,  3.01it/s, 255 steps of size 1.99e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  29%|██▉       | 442/1500 [04:31<05:50,  3.02it/s, 255 steps of size 2.20e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  30%|██▉       | 443/1500 [04:31<05:49,  3.03it/s, 255 steps of size 2.30e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  30%|██▉       | 444/1500 [04:31<05:47,  3.04it/s, 255 steps of size 1.87e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  30%|██▉       | 445/1500 [04:32<05:47,  3.04it/s, 255 steps of size 2.05e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  30%|██▉       | 446/1500 [04:32<05:46,  3.04it/s, 255 steps of size 2.16e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  30%|██▉       | 447/1500 [04:32<05:45,  3.05it/s, 255 steps of size 1.94e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  30%|██▉       | 448/1500 [04:33<05:45,  3.05it/s, 255 steps of size 2.18e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  30%|██▉       | 449/1500 [04:33<05:44,  3.05it/s, 255 steps of size 2.45e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  30%|███       | 450/1500 [04:33<05:09,  3.39it/s, 169 steps of size 1.29e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  30%|███       | 451/1500 [04:34<07:03,  2.48it/s, 511 steps of size 1.54e-01. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  30%|███       | 453/1500 [04:34<04:38,  3.76it/s, 127 steps of size 3.39e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  30%|███       | 454/1500 [04:34<04:12,  4.15it/s, 127 steps of size 4.10e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  30%|███       | 455/1500 [04:35<03:51,  4.52it/s, 127 steps of size 5.06e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  30%|███       | 456/1500 [04:35<03:35,  4.86it/s, 127 steps of size 6.64e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  31%|███       | 458/1500 [04:35<02:37,  6.60it/s, 63 steps of size 6.17e-02. acc. prob=0.88] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  31%|███       | 460/1500 [04:35<02:09,  8.03it/s, 63 steps of size 1.07e-01. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  31%|███       | 462/1500 [04:36<03:43,  4.65it/s, 511 steps of size 1.61e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  31%|███       | 463/1500 [04:36<05:17,  3.27it/s, 511 steps of size 2.16e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  31%|███       | 464/1500 [04:37<05:22,  3.22it/s, 255 steps of size 2.97e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  31%|███       | 465/1500 [04:37<04:45,  3.63it/s, 127 steps of size 4.00e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  31%|███       | 466/1500 [04:37<04:15,  4.05it/s, 127 steps of size 5.45e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  31%|███       | 468/1500 [04:37<03:02,  5.66it/s, 63 steps of size 9.05e-02. acc. prob=0.88] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  31%|███▏      | 470/1500 [04:38<02:43,  6.30it/s, 137 steps of size 2.76e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  31%|███▏      | 471/1500 [04:38<03:20,  5.14it/s, 255 steps of size 3.67e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  31%|███▏      | 472/1500 [04:38<03:11,  5.35it/s, 127 steps of size 4.96e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  32%|███▏      | 473/1500 [04:38<03:05,  5.54it/s, 127 steps of size 6.58e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  32%|███▏      | 474/1500 [04:38<03:00,  5.67it/s, 127 steps of size 3.29e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  32%|███▏      | 475/1500 [04:39<02:57,  5.78it/s, 127 steps of size 3.98e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  32%|███▏      | 476/1500 [04:39<02:54,  5.87it/s, 127 steps of size 4.76e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  32%|███▏      | 477/1500 [04:39<02:52,  5.94it/s, 127 steps of size 6.33e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  32%|███▏      | 479/1500 [04:39<02:11,  7.74it/s, 63 steps of size 8.91e-02. acc. prob=0.88] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  32%|███▏      | 481/1500 [04:39<01:52,  9.04it/s, 63 steps of size 1.08e-01. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  32%|███▏      | 483/1500 [04:39<01:41,  9.98it/s, 63 steps of size 9.86e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  32%|███▏      | 485/1500 [04:39<01:35, 10.65it/s, 63 steps of size 2.19e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  32%|███▏      | 486/1500 [04:40<02:21,  7.19it/s, 255 steps of size 2.82e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  32%|███▏      | 487/1500 [04:40<03:02,  5.54it/s, 255 steps of size 3.66e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  33%|███▎      | 488/1500 [04:40<03:38,  4.64it/s, 255 steps of size 4.75e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  33%|███▎      | 490/1500 [04:41<02:59,  5.62it/s, 127 steps of size 4.77e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  33%|███▎      | 491/1500 [04:41<02:56,  5.73it/s, 127 steps of size 6.11e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  33%|███▎      | 493/1500 [04:41<02:19,  7.24it/s, 63 steps of size 5.97e-02. acc. prob=0.88] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  33%|███▎      | 494/1500 [04:41<02:24,  6.97it/s, 127 steps of size 7.40e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  33%|███▎      | 496/1500 [04:41<01:57,  8.51it/s, 63 steps of size 9.30e-02. acc. prob=0.88] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  33%|███▎      | 498/1500 [04:41<01:37, 10.28it/s, 31 steps of size 1.30e-01. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  33%|███▎      | 501/1500 [04:42<01:12, 13.73it/s, 31 steps of size 1.78e-01. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  34%|███▎      | 503/1500 [04:42<01:09, 14.42it/s, 63 steps of size 6.86e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  34%|███▎      | 505/1500 [04:42<01:12, 13.72it/s, 63 steps of size 5.59e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  34%|███▎      | 506/1500 [04:42<01:28, 11.30it/s, 127 steps of size 6.72e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  34%|███▍      | 508/1500 [04:42<01:25, 11.61it/s, 63 steps of size 9.22e-02. acc. prob=0.88] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  34%|███▍      | 510/1500 [04:42<01:17, 12.83it/s, 31 steps of size 4.23e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  34%|███▍      | 511/1500 [04:42<01:32, 10.66it/s, 127 steps of size 5.16e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  34%|███▍      | 512/1500 [04:43<01:47,  9.22it/s, 127 steps of size 6.29e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  34%|███▍      | 513/1500 [04:43<01:59,  8.25it/s, 127 steps of size 7.40e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  34%|███▍      | 515/1500 [04:43<01:45,  9.33it/s, 63 steps of size 2.78e-02. acc. prob=0.88] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  34%|███▍      | 516/1500 [04:43<01:57,  8.36it/s, 127 steps of size 3.36e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  34%|███▍      | 517/1500 [04:43<02:08,  7.67it/s, 127 steps of size 4.03e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  35%|███▍      | 518/1500 [04:43<02:16,  7.19it/s, 127 steps of size 4.99e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  35%|███▍      | 519/1500 [04:44<02:22,  6.87it/s, 127 steps of size 6.04e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  35%|███▍      | 521/1500 [04:44<01:55,  8.50it/s, 63 steps of size 7.58e-02. acc. prob=0.89] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  35%|███▍      | 524/1500 [04:44<02:04,  7.87it/s, 255 steps of size 2.74e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  35%|███▌      | 525/1500 [04:45<02:40,  6.09it/s, 255 steps of size 3.36e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  35%|███▌      | 526/1500 [04:45<02:39,  6.09it/s, 127 steps of size 3.89e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  35%|███▌      | 527/1500 [04:45<02:39,  6.10it/s, 127 steps of size 4.44e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  35%|███▌      | 528/1500 [04:45<02:39,  6.10it/s, 127 steps of size 5.28e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  35%|███▌      | 529/1500 [04:45<02:39,  6.10it/s, 127 steps of size 6.33e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  35%|███▌      | 531/1500 [04:45<02:21,  6.85it/s, 127 steps of size 7.56e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  36%|███▌      | 533/1500 [04:46<01:49,  8.80it/s, 31 steps of size 1.04e-01. acc. prob=0.89] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  36%|███▌      | 535/1500 [04:46<01:38,  9.78it/s, 63 steps of size 6.73e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  36%|███▌      | 537/1500 [04:46<01:45,  9.15it/s, 127 steps of size 4.16e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  36%|███▌      | 538/1500 [04:46<01:55,  8.35it/s, 127 steps of size 4.69e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  36%|███▌      | 539/1500 [04:46<02:04,  7.74it/s, 127 steps of size 5.64e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  36%|███▌      | 541/1500 [04:46<01:46,  9.02it/s, 63 steps of size 7.65e-02. acc. prob=0.89] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  36%|███▌      | 543/1500 [04:47<01:36,  9.96it/s, 63 steps of size 1.47e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  36%|███▋      | 544/1500 [04:47<03:22,  4.71it/s, 511 steps of size 1.78e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  36%|███▋      | 545/1500 [04:48<03:47,  4.20it/s, 255 steps of size 2.16e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  36%|███▋      | 546/1500 [04:48<04:07,  3.85it/s, 255 steps of size 2.40e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  36%|███▋      | 547/1500 [04:48<03:44,  4.25it/s, 127 steps of size 2.86e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  37%|███▋      | 548/1500 [04:48<03:25,  4.63it/s, 127 steps of size 3.44e-02. acc. prob=0.88]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  37%|███▋      | 549/1500 [04:49<03:54,  4.05it/s, 255 steps of size 4.10e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  37%|███▋      | 550/1500 [04:49<03:32,  4.48it/s, 127 steps of size 4.66e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  37%|███▋      | 552/1500 [04:49<02:49,  5.60it/s, 127 steps of size 6.19e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  37%|███▋      | 554/1500 [04:49<02:13,  7.11it/s, 63 steps of size 7.27e-02. acc. prob=0.89] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  37%|███▋      | 556/1500 [04:49<01:52,  8.37it/s, 63 steps of size 5.90e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  37%|███▋      | 557/1500 [04:49<02:01,  7.79it/s, 127 steps of size 5.24e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  37%|███▋      | 558/1500 [04:50<02:08,  7.34it/s, 127 steps of size 6.19e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  37%|███▋      | 560/1500 [04:50<01:47,  8.71it/s, 63 steps of size 8.00e-02. acc. prob=0.89] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  37%|███▋      | 562/1500 [04:50<01:50,  8.50it/s, 127 steps of size 5.42e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  38%|███▊      | 563/1500 [04:50<01:59,  7.86it/s, 127 steps of size 6.14e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  38%|███▊      | 565/1500 [04:50<01:43,  9.06it/s, 63 steps of size 4.62e-02. acc. prob=0.89] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  38%|███▊      | 566/1500 [04:51<01:53,  8.22it/s, 127 steps of size 5.34e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  38%|███▊      | 567/1500 [04:51<02:02,  7.61it/s, 127 steps of size 4.94e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  38%|███▊      | 568/1500 [04:51<02:09,  7.17it/s, 127 steps of size 5.69e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  38%|███▊      | 570/1500 [04:51<01:47,  8.66it/s, 63 steps of size 5.89e-02. acc. prob=0.89] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  38%|███▊      | 572/1500 [04:51<01:35,  9.73it/s, 63 steps of size 7.80e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  38%|███▊      | 574/1500 [04:51<01:28, 10.48it/s, 63 steps of size 9.93e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  38%|███▊      | 576/1500 [04:52<01:36,  9.56it/s, 127 steps of size 5.06e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  39%|███▊      | 578/1500 [04:52<01:29, 10.28it/s, 63 steps of size 4.99e-02. acc. prob=0.89] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  39%|███▊      | 579/1500 [04:52<01:41,  9.09it/s, 127 steps of size 5.41e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  39%|███▊      | 581/1500 [04:52<01:45,  8.73it/s, 127 steps of size 3.19e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  39%|███▉      | 582/1500 [04:52<01:54,  8.03it/s, 127 steps of size 3.74e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  39%|███▉      | 583/1500 [04:53<02:02,  7.51it/s, 127 steps of size 4.40e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  39%|███▉      | 584/1500 [04:53<02:08,  7.12it/s, 127 steps of size 5.16e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  39%|███▉      | 586/1500 [04:53<01:46,  8.59it/s, 63 steps of size 6.83e-02. acc. prob=0.89] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  39%|███▉      | 588/1500 [04:53<01:48,  8.42it/s, 127 steps of size 4.59e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  39%|███▉      | 589/1500 [04:53<01:56,  7.81it/s, 127 steps of size 5.01e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  39%|███▉      | 590/1500 [04:53<02:03,  7.34it/s, 127 steps of size 5.82e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  39%|███▉      | 591/1500 [04:54<02:10,  6.99it/s, 127 steps of size 6.20e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  40%|███▉      | 593/1500 [04:54<01:44,  8.64it/s, 56 steps of size 6.10e-02. acc. prob=0.89] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  40%|███▉      | 595/1500 [04:54<01:33,  9.71it/s, 63 steps of size 6.93e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  40%|███▉      | 596/1500 [04:54<01:44,  8.65it/s, 127 steps of size 4.17e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  40%|███▉      | 597/1500 [04:54<01:54,  7.89it/s, 127 steps of size 4.85e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  40%|███▉      | 598/1500 [04:54<02:02,  7.35it/s, 127 steps of size 5.45e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  40%|███▉      | 599/1500 [04:55<02:09,  6.98it/s, 127 steps of size 5.48e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  40%|████      | 600/1500 [04:55<02:14,  6.72it/s, 127 steps of size 6.23e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  40%|████      | 602/1500 [04:55<01:47,  8.38it/s, 63 steps of size 7.86e-02. acc. prob=0.89] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  40%|████      | 604/1500 [04:55<01:48,  8.27it/s, 127 steps of size 3.01e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  40%|████      | 605/1500 [04:55<01:56,  7.68it/s, 127 steps of size 3.49e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  40%|████      | 606/1500 [04:55<02:03,  7.24it/s, 127 steps of size 3.82e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  40%|████      | 607/1500 [04:56<02:09,  6.91it/s, 127 steps of size 4.34e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  41%|████      | 608/1500 [04:56<02:13,  6.68it/s, 127 steps of size 4.99e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  41%|████      | 609/1500 [04:56<02:16,  6.51it/s, 127 steps of size 5.71e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  41%|████      | 611/1500 [04:56<01:48,  8.19it/s, 63 steps of size 6.90e-02. acc. prob=0.89] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  41%|████      | 613/1500 [04:56<01:34,  9.40it/s, 63 steps of size 8.95e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  41%|████      | 615/1500 [04:56<01:26, 10.26it/s, 63 steps of size 1.09e-01. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  41%|████      | 617/1500 [04:57<01:21, 10.87it/s, 63 steps of size 9.19e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  41%|████▏     | 619/1500 [04:57<01:17, 11.30it/s, 63 steps of size 7.36e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  41%|████▏     | 621/1500 [04:57<01:15, 11.60it/s, 63 steps of size 9.44e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  42%|████▏     | 623/1500 [04:57<01:14, 11.81it/s, 63 steps of size 8.04e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  42%|████▏     | 625/1500 [04:57<01:13, 11.95it/s, 63 steps of size 6.61e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  42%|████▏     | 627/1500 [04:57<01:12, 12.06it/s, 63 steps of size 8.50e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  42%|████▏     | 629/1500 [04:58<01:11, 12.14it/s, 63 steps of size 8.78e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  42%|████▏     | 631/1500 [04:58<01:11, 12.19it/s, 63 steps of size 8.38e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  42%|████▏     | 633/1500 [04:58<01:11, 12.21it/s, 63 steps of size 1.06e-01. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  42%|████▏     | 635/1500 [04:58<01:05, 13.22it/s, 63 steps of size 3.95e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  42%|████▏     | 636/1500 [04:58<01:19, 10.90it/s, 127 steps of size 4.35e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  42%|████▏     | 637/1500 [04:58<01:32,  9.38it/s, 127 steps of size 4.95e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  43%|████▎     | 638/1500 [04:59<01:42,  8.37it/s, 127 steps of size 5.64e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  43%|████▎     | 640/1500 [04:59<01:30,  9.55it/s, 63 steps of size 6.47e-02. acc. prob=0.89] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  43%|████▎     | 642/1500 [04:59<01:22, 10.39it/s, 63 steps of size 6.34e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  43%|████▎     | 644/1500 [04:59<01:18, 10.97it/s, 63 steps of size 6.96e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  43%|████▎     | 646/1500 [04:59<01:15, 11.37it/s, 63 steps of size 8.60e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  43%|████▎     | 648/1500 [04:59<01:13, 11.64it/s, 63 steps of size 9.36e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  43%|████▎     | 650/1500 [04:59<01:11, 11.85it/s, 63 steps of size 1.03e-01. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  43%|████▎     | 652/1500 [05:00<01:10, 11.99it/s, 63 steps of size 7.31e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  44%|████▎     | 654/1500 [05:00<01:10, 12.08it/s, 63 steps of size 9.12e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  44%|████▎     | 656/1500 [05:00<01:09, 12.14it/s, 63 steps of size 8.43e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  44%|████▍     | 658/1500 [05:00<01:09, 12.20it/s, 63 steps of size 9.92e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  44%|████▍     | 660/1500 [05:00<01:08, 12.23it/s, 63 steps of size 6.88e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  44%|████▍     | 662/1500 [05:00<01:08, 12.24it/s, 63 steps of size 8.78e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  44%|████▍     | 664/1500 [05:01<01:08, 12.25it/s, 63 steps of size 1.07e-01. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  44%|████▍     | 666/1500 [05:01<01:02, 13.28it/s, 31 steps of size 1.15e-01. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  45%|████▍     | 668/1500 [05:01<00:58, 14.10it/s, 63 steps of size 7.55e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  45%|████▍     | 670/1500 [05:01<01:11, 11.56it/s, 127 steps of size 5.22e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  45%|████▍     | 671/1500 [05:01<01:21, 10.14it/s, 119 steps of size 4.62e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  45%|████▍     | 672/1500 [05:01<01:26,  9.52it/s, 101 steps of size 4.85e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  45%|████▍     | 673/1500 [05:02<01:37,  8.46it/s, 127 steps of size 5.52e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  45%|████▍     | 674/1500 [05:02<01:46,  7.74it/s, 127 steps of size 5.02e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  45%|████▌     | 675/1500 [05:02<01:54,  7.23it/s, 127 steps of size 4.98e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  45%|████▌     | 676/1500 [05:02<01:59,  6.88it/s, 127 steps of size 5.57e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  45%|████▌     | 677/1500 [05:02<02:03,  6.65it/s, 127 steps of size 4.82e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  45%|████▌     | 678/1500 [05:02<02:06,  6.49it/s, 127 steps of size 5.35e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  45%|████▌     | 679/1500 [05:03<02:08,  6.38it/s, 127 steps of size 5.00e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  45%|████▌     | 680/1500 [05:03<02:10,  6.30it/s, 127 steps of size 5.57e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  45%|████▌     | 682/1500 [05:03<01:56,  7.03it/s, 127 steps of size 4.68e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  46%|████▌     | 683/1500 [05:03<02:00,  6.78it/s, 127 steps of size 5.29e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  46%|████▌     | 685/1500 [05:03<01:51,  7.29it/s, 127 steps of size 6.01e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  46%|████▌     | 686/1500 [05:04<01:56,  6.98it/s, 127 steps of size 6.39e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  46%|████▌     | 688/1500 [05:04<01:36,  8.41it/s, 63 steps of size 6.32e-02. acc. prob=0.89] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  46%|████▌     | 690/1500 [05:04<01:25,  9.48it/s, 63 steps of size 6.75e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  46%|████▌     | 692/1500 [05:04<01:18, 10.28it/s, 63 steps of size 8.53e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  46%|████▋     | 694/1500 [05:04<01:14, 10.85it/s, 63 steps of size 3.15e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  46%|████▋     | 695/1500 [05:04<01:25,  9.41it/s, 127 steps of size 3.54e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  46%|████▋     | 696/1500 [05:05<01:35,  8.43it/s, 127 steps of size 4.01e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  46%|████▋     | 697/1500 [05:05<01:43,  7.75it/s, 127 steps of size 4.36e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  47%|████▋     | 698/1500 [05:05<01:50,  7.26it/s, 127 steps of size 4.94e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  47%|████▋     | 699/1500 [05:05<01:55,  6.92it/s, 127 steps of size 5.19e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  47%|████▋     | 700/1500 [05:05<01:59,  6.68it/s, 127 steps of size 5.85e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  47%|████▋     | 701/1500 [05:05<02:02,  6.51it/s, 127 steps of size 6.50e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  47%|████▋     | 703/1500 [05:05<01:36,  8.24it/s, 63 steps of size 7.41e-02. acc. prob=0.89] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  47%|████▋     | 705/1500 [05:06<01:24,  9.46it/s, 63 steps of size 8.82e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  47%|████▋     | 707/1500 [05:06<01:16, 10.32it/s, 63 steps of size 9.52e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  47%|████▋     | 709/1500 [05:06<01:12, 10.90it/s, 63 steps of size 1.08e-01. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  47%|████▋     | 711/1500 [05:06<01:04, 12.28it/s, 31 steps of size 1.01e-01. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  48%|████▊     | 713/1500 [05:06<01:04, 12.28it/s, 63 steps of size 8.01e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  48%|████▊     | 715/1500 [05:06<01:03, 12.29it/s, 63 steps of size 8.61e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  48%|████▊     | 717/1500 [05:07<01:03, 12.30it/s, 63 steps of size 8.79e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  48%|████▊     | 719/1500 [05:07<01:03, 12.31it/s, 63 steps of size 6.48e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  48%|████▊     | 721/1500 [05:07<01:03, 12.29it/s, 63 steps of size 7.88e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  48%|████▊     | 723/1500 [05:07<01:03, 12.29it/s, 63 steps of size 6.91e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  48%|████▊     | 725/1500 [05:07<01:03, 12.29it/s, 63 steps of size 8.73e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  48%|████▊     | 727/1500 [05:07<01:03, 12.26it/s, 63 steps of size 1.02e-01. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  49%|████▊     | 729/1500 [05:08<01:02, 12.26it/s, 63 steps of size 1.02e-01. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  49%|████▊     | 731/1500 [05:08<00:57, 13.27it/s, 31 steps of size 1.10e-01. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  49%|████▉     | 734/1500 [05:08<00:51, 14.95it/s, 63 steps of size 1.09e-01. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  49%|████▉     | 736/1500 [05:08<00:54, 14.12it/s, 63 steps of size 8.92e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  49%|████▉     | 738/1500 [05:08<00:56, 13.54it/s, 63 steps of size 6.68e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  49%|████▉     | 740/1500 [05:08<00:53, 14.11it/s, 63 steps of size 7.35e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  49%|████▉     | 742/1500 [05:08<00:55, 13.54it/s, 63 steps of size 8.44e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  50%|████▉     | 745/1500 [05:09<00:56, 13.41it/s, 127 steps of size 2.71e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  50%|████▉     | 746/1500 [05:09<01:06, 11.33it/s, 127 steps of size 2.99e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  50%|████▉     | 747/1500 [05:09<01:39,  7.60it/s, 255 steps of size 3.34e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  50%|████▉     | 748/1500 [05:10<02:09,  5.81it/s, 255 steps of size 3.71e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  50%|████▉     | 749/1500 [05:10<02:07,  5.88it/s, 127 steps of size 3.58e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  50%|█████     | 750/1500 [05:10<02:06,  5.93it/s, 127 steps of size 4.00e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  50%|█████     | 751/1500 [05:10<02:05,  5.97it/s, 127 steps of size 4.38e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  50%|█████     | 752/1500 [05:10<02:04,  6.00it/s, 127 steps of size 4.71e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  50%|█████     | 753/1500 [05:10<02:03,  6.03it/s, 127 steps of size 5.17e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  50%|█████     | 754/1500 [05:11<02:03,  6.05it/s, 127 steps of size 5.57e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  50%|█████     | 755/1500 [05:11<02:02,  6.06it/s, 127 steps of size 6.17e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  50%|█████     | 757/1500 [05:11<01:34,  7.87it/s, 63 steps of size 7.12e-02. acc. prob=0.89] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  51%|█████     | 759/1500 [05:11<01:20,  9.17it/s, 63 steps of size 8.48e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  51%|█████     | 761/1500 [05:11<01:13, 10.08it/s, 63 steps of size 9.42e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  51%|█████     | 763/1500 [05:11<01:08, 10.75it/s, 63 steps of size 1.03e-01. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  51%|█████     | 765/1500 [05:11<01:05, 11.25it/s, 63 steps of size 1.02e-01. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  51%|█████     | 767/1500 [05:12<00:58, 12.51it/s, 63 steps of size 7.19e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  51%|█████▏    | 769/1500 [05:12<00:58, 12.42it/s, 63 steps of size 3.91e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  51%|█████▏    | 770/1500 [05:12<01:09, 10.45it/s, 127 steps of size 3.90e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  51%|█████▏    | 771/1500 [05:12<01:19,  9.11it/s, 127 steps of size 4.34e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  51%|█████▏    | 772/1500 [05:12<01:28,  8.22it/s, 127 steps of size 4.48e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  52%|█████▏    | 773/1500 [05:12<01:35,  7.58it/s, 127 steps of size 4.85e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  52%|█████▏    | 774/1500 [05:13<01:41,  7.13it/s, 127 steps of size 5.41e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  52%|█████▏    | 775/1500 [05:13<01:46,  6.82it/s, 127 steps of size 6.02e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  52%|█████▏    | 777/1500 [05:13<01:25,  8.46it/s, 63 steps of size 5.11e-02. acc. prob=0.89] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  52%|█████▏    | 779/1500 [05:13<01:14,  9.62it/s, 63 steps of size 5.73e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  52%|█████▏    | 780/1500 [05:13<01:24,  8.56it/s, 127 steps of size 6.08e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  52%|█████▏    | 782/1500 [05:13<01:25,  8.40it/s, 127 steps of size 3.95e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  52%|█████▏    | 783/1500 [05:14<01:32,  7.77it/s, 127 steps of size 4.36e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  52%|█████▏    | 784/1500 [05:14<01:38,  7.29it/s, 127 steps of size 4.30e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  52%|█████▏    | 785/1500 [05:14<01:43,  6.94it/s, 127 steps of size 3.71e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  52%|█████▏    | 786/1500 [05:14<01:46,  6.71it/s, 127 steps of size 4.00e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  52%|█████▏    | 787/1500 [05:14<01:49,  6.54it/s, 127 steps of size 4.40e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  53%|█████▎    | 788/1500 [05:14<01:53,  6.25it/s, 127 steps of size 4.82e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  53%|█████▎    | 789/1500 [05:15<01:54,  6.20it/s, 127 steps of size 5.29e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  53%|█████▎    | 790/1500 [05:15<01:54,  6.18it/s, 127 steps of size 5.86e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  53%|█████▎    | 792/1500 [05:15<01:28,  7.97it/s, 63 steps of size 4.77e-02. acc. prob=0.89] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  53%|█████▎    | 793/1500 [05:15<01:35,  7.43it/s, 127 steps of size 4.65e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  53%|█████▎    | 794/1500 [05:15<01:40,  7.03it/s, 127 steps of size 5.04e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  53%|█████▎    | 795/1500 [05:15<01:45,  6.70it/s, 127 steps of size 5.59e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  53%|█████▎    | 796/1500 [05:16<01:47,  6.52it/s, 127 steps of size 5.91e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  53%|█████▎    | 798/1500 [05:16<01:25,  8.23it/s, 63 steps of size 6.96e-02. acc. prob=0.89] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  53%|█████▎    | 800/1500 [05:16<01:14,  9.43it/s, 63 steps of size 8.15e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  53%|█████▎    | 802/1500 [05:16<01:07, 10.29it/s, 63 steps of size 9.18e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  54%|█████▎    | 804/1500 [05:16<00:59, 11.77it/s, 31 steps of size 5.73e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  54%|█████▎    | 806/1500 [05:16<01:07, 10.29it/s, 127 steps of size 6.87e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  54%|█████▍    | 808/1500 [05:17<01:03, 10.85it/s, 63 steps of size 5.58e-02. acc. prob=0.89] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  54%|█████▍    | 809/1500 [05:17<01:13,  9.46it/s, 127 steps of size 5.92e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  54%|█████▍    | 811/1500 [05:17<01:06, 10.28it/s, 63 steps of size 7.24e-02. acc. prob=0.89] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  54%|█████▍    | 813/1500 [05:17<01:03, 10.88it/s, 63 steps of size 7.38e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  54%|█████▍    | 815/1500 [05:17<01:00, 11.30it/s, 63 steps of size 7.37e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  54%|█████▍    | 817/1500 [05:17<00:58, 11.58it/s, 63 steps of size 8.09e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  55%|█████▍    | 819/1500 [05:18<00:57, 11.79it/s, 63 steps of size 9.69e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  55%|█████▍    | 821/1500 [05:18<01:01, 11.10it/s, 127 steps of size 6.17e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  55%|█████▍    | 822/1500 [05:18<01:09,  9.69it/s, 127 steps of size 6.83e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  55%|█████▍    | 824/1500 [05:18<01:04, 10.44it/s, 63 steps of size 7.88e-02. acc. prob=0.89] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  55%|█████▌    | 826/1500 [05:18<01:01, 10.98it/s, 63 steps of size 8.87e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  55%|█████▌    | 828/1500 [05:18<00:59, 11.37it/s, 63 steps of size 1.05e-01. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  55%|█████▌    | 830/1500 [05:19<00:53, 12.59it/s, 63 steps of size 7.83e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  55%|█████▌    | 832/1500 [05:19<00:53, 12.50it/s, 63 steps of size 8.98e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  56%|█████▌    | 834/1500 [05:19<00:53, 12.44it/s, 63 steps of size 1.01e-01. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  56%|█████▌    | 836/1500 [05:19<00:53, 12.39it/s, 63 steps of size 1.12e-01. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  56%|█████▌    | 838/1500 [05:19<01:02, 10.65it/s, 127 steps of size 5.95e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  56%|█████▌    | 839/1500 [05:19<01:10,  9.41it/s, 127 steps of size 6.44e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  56%|█████▌    | 841/1500 [05:20<01:04, 10.22it/s, 63 steps of size 7.18e-02. acc. prob=0.89] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  56%|█████▌    | 843/1500 [05:20<01:00, 10.80it/s, 63 steps of size 6.65e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  56%|█████▋    | 844/1500 [05:20<01:09,  9.43it/s, 127 steps of size 6.68e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  56%|█████▋    | 846/1500 [05:20<01:03, 10.26it/s, 63 steps of size 7.93e-02. acc. prob=0.89] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  57%|█████▋    | 848/1500 [05:20<00:59, 10.87it/s, 63 steps of size 7.11e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  57%|█████▋    | 850/1500 [05:20<00:57, 11.29it/s, 63 steps of size 4.45e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  57%|█████▋    | 851/1500 [05:21<01:06,  9.75it/s, 127 steps of size 4.84e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  57%|█████▋    | 852/1500 [05:21<01:14,  8.64it/s, 127 steps of size 5.16e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  57%|█████▋    | 854/1500 [05:21<01:08,  9.42it/s, 63 steps of size 6.14e-02. acc. prob=0.89] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  57%|█████▋    | 855/1500 [05:21<01:16,  8.44it/s, 127 steps of size 6.00e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  57%|█████▋    | 856/1500 [05:21<01:22,  7.76it/s, 127 steps of size 6.60e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  57%|█████▋    | 858/1500 [05:21<01:10,  9.09it/s, 63 steps of size 6.79e-02. acc. prob=0.89] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  57%|█████▋    | 860/1500 [05:22<01:03, 10.03it/s, 63 steps of size 6.77e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  57%|█████▋    | 861/1500 [05:22<01:12,  8.86it/s, 127 steps of size 7.19e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  58%|█████▊    | 863/1500 [05:22<01:04,  9.88it/s, 63 steps of size 8.64e-02. acc. prob=0.89] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  58%|█████▊    | 865/1500 [05:22<00:59, 10.60it/s, 63 steps of size 8.47e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  58%|█████▊    | 867/1500 [05:22<00:57, 11.09it/s, 63 steps of size 8.73e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  58%|█████▊    | 869/1500 [05:22<00:55, 11.44it/s, 63 steps of size 9.90e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  58%|█████▊    | 871/1500 [05:23<00:52, 11.91it/s, 55 steps of size 1.06e-01. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  58%|█████▊    | 873/1500 [05:23<00:52, 12.02it/s, 63 steps of size 6.77e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  58%|█████▊    | 875/1500 [05:23<00:51, 12.11it/s, 63 steps of size 7.44e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  58%|█████▊    | 877/1500 [05:23<00:51, 12.18it/s, 63 steps of size 8.32e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  59%|█████▊    | 879/1500 [05:23<00:51, 12.17it/s, 63 steps of size 7.15e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  59%|█████▊    | 881/1500 [05:23<00:50, 12.20it/s, 63 steps of size 8.18e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  59%|█████▉    | 883/1500 [05:24<00:50, 12.22it/s, 63 steps of size 6.73e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  59%|█████▉    | 885/1500 [05:24<00:50, 12.23it/s, 63 steps of size 4.15e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  59%|█████▉    | 886/1500 [05:24<00:59, 10.38it/s, 127 steps of size 4.46e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  59%|█████▉    | 887/1500 [05:24<01:07,  9.08it/s, 127 steps of size 4.85e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  59%|█████▉    | 888/1500 [05:24<01:15,  8.15it/s, 127 steps of size 5.20e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  59%|█████▉    | 889/1500 [05:24<01:21,  7.51it/s, 127 steps of size 5.51e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  59%|█████▉    | 890/1500 [05:25<01:26,  7.07it/s, 127 steps of size 6.06e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  59%|█████▉    | 892/1500 [05:25<01:10,  8.61it/s, 63 steps of size 5.91e-02. acc. prob=0.89] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  60%|█████▉    | 894/1500 [05:25<01:11,  8.43it/s, 127 steps of size 6.16e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  60%|█████▉    | 896/1500 [05:25<01:03,  9.46it/s, 63 steps of size 7.36e-02. acc. prob=0.89] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  60%|█████▉    | 898/1500 [05:25<00:58, 10.25it/s, 63 steps of size 7.69e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  60%|██████    | 900/1500 [05:25<00:55, 10.83it/s, 63 steps of size 9.06e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  60%|██████    | 902/1500 [05:26<00:53, 11.25it/s, 63 steps of size 8.37e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  60%|██████    | 904/1500 [05:26<00:51, 11.54it/s, 63 steps of size 8.09e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  60%|██████    | 906/1500 [05:26<00:50, 11.77it/s, 63 steps of size 8.72e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  61%|██████    | 908/1500 [05:26<00:45, 12.88it/s, 31 steps of size 1.01e-01. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  61%|██████    | 911/1500 [05:26<00:37, 15.91it/s, 31 steps of size 1.18e-01. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  61%|██████    | 912/1500 [05:26<00:50, 11.72it/s, 159 steps of size 7.81e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  61%|██████    | 914/1500 [05:27<00:49, 11.89it/s, 63 steps of size 7.15e-02. acc. prob=0.89] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  61%|██████    | 916/1500 [05:27<00:48, 12.00it/s, 63 steps of size 8.25e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  61%|██████    | 917/1500 [05:27<00:56, 10.23it/s, 127 steps of size 8.45e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  61%|██████▏   | 919/1500 [05:27<00:53, 10.84it/s, 63 steps of size 5.67e-02. acc. prob=0.89] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  61%|██████▏   | 921/1500 [05:27<00:59,  9.71it/s, 127 steps of size 5.17e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  62%|██████▏   | 923/1500 [05:27<00:55, 10.35it/s, 63 steps of size 5.91e-02. acc. prob=0.89] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  62%|██████▏   | 925/1500 [05:28<00:52, 10.87it/s, 63 steps of size 6.98e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  62%|██████▏   | 927/1500 [05:28<00:50, 11.28it/s, 63 steps of size 7.10e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  62%|██████▏   | 929/1500 [05:28<00:49, 11.55it/s, 63 steps of size 8.48e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  62%|██████▏   | 931/1500 [05:28<00:48, 11.75it/s, 63 steps of size 9.81e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  62%|██████▏   | 933/1500 [05:28<00:47, 11.91it/s, 63 steps of size 9.63e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  62%|██████▏   | 935/1500 [05:28<00:47, 12.01it/s, 63 steps of size 8.58e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  63%|██████▎   | 938/1500 [05:29<00:41, 13.55it/s, 63 steps of size 7.78e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  63%|██████▎   | 940/1500 [05:29<00:42, 13.27it/s, 60 steps of size 8.93e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  63%|██████▎   | 942/1500 [05:29<00:42, 12.99it/s, 63 steps of size 8.78e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  63%|██████▎   | 944/1500 [05:29<00:43, 12.77it/s, 63 steps of size 1.01e-01. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  63%|██████▎   | 946/1500 [05:29<00:43, 12.61it/s, 63 steps of size 1.06e-01. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  63%|██████▎   | 948/1500 [05:29<00:44, 12.49it/s, 63 steps of size 6.04e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  63%|██████▎   | 950/1500 [05:30<00:44, 12.44it/s, 63 steps of size 7.09e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  64%|██████▎   | 953/1500 [05:30<00:38, 14.20it/s, 63 steps of size 8.10e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  64%|██████▎   | 955/1500 [05:30<00:45, 11.85it/s, 127 steps of size 4.91e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  64%|██████▍   | 957/1500 [05:30<00:51, 10.52it/s, 127 steps of size 7.48e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  64%|██████▍   | 959/1500 [05:30<00:46, 11.52it/s, 39 steps of size 6.23e-02. acc. prob=0.89] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  64%|██████▍   | 961/1500 [05:31<00:46, 11.67it/s, 63 steps of size 7.49e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  64%|██████▍   | 963/1500 [05:31<00:45, 11.83it/s, 63 steps of size 7.38e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  64%|██████▍   | 965/1500 [05:31<00:44, 11.95it/s, 63 steps of size 1.35e-01. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  65%|██████▍   | 968/1500 [05:31<00:38, 13.84it/s, 63 steps of size 5.07e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  65%|██████▍   | 970/1500 [05:31<00:39, 13.39it/s, 63 steps of size 8.59e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  65%|██████▍   | 972/1500 [05:31<00:40, 13.06it/s, 63 steps of size 8.59e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  65%|██████▍   | 974/1500 [05:32<00:40, 12.83it/s, 63 steps of size 3.39e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  65%|██████▌   | 975/1500 [05:32<01:03,  8.31it/s, 255 steps of size 3.92e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  65%|██████▌   | 976/1500 [05:32<01:07,  7.76it/s, 127 steps of size 5.03e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  65%|██████▌   | 977/1500 [05:32<01:11,  7.32it/s, 127 steps of size 6.00e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  65%|██████▌   | 979/1500 [05:32<01:00,  8.66it/s, 63 steps of size 1.04e-01. acc. prob=0.89] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  65%|██████▌   | 981/1500 [05:33<00:53,  9.66it/s, 63 steps of size 5.62e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  65%|██████▌   | 982/1500 [05:33<00:59,  8.64it/s, 127 steps of size 7.31e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  66%|██████▌   | 984/1500 [05:33<00:53,  9.68it/s, 63 steps of size 6.64e-02. acc. prob=0.89] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  66%|██████▌   | 986/1500 [05:33<00:49, 10.43it/s, 63 steps of size 8.12e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  66%|██████▌   | 988/1500 [05:33<00:46, 10.97it/s, 63 steps of size 1.11e-01. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  66%|██████▌   | 990/1500 [05:33<00:51,  9.89it/s, 127 steps of size 6.25e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  66%|██████▌   | 992/1500 [05:34<00:48, 10.53it/s, 63 steps of size 9.20e-02. acc. prob=0.89] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  66%|██████▋   | 994/1500 [05:34<00:46, 10.97it/s, 63 steps of size 8.01e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  66%|██████▋   | 996/1500 [05:34<00:44, 11.34it/s, 63 steps of size 4.96e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  66%|██████▋   | 997/1500 [05:34<00:51,  9.83it/s, 127 steps of size 6.38e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "warmup:  67%|██████▋   | 999/1500 [05:34<00:47, 10.51it/s, 63 steps of size 8.27e-02. acc. prob=0.89] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  67%|██████▋   | 1001/1500 [05:34<00:45, 11.01it/s, 63 steps of size 7.17e-02. acc. prob=0.59]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  67%|██████▋   | 1003/1500 [05:35<00:43, 11.36it/s, 63 steps of size 7.17e-02. acc. prob=0.78]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  67%|██████▋   | 1005/1500 [05:35<00:42, 11.63it/s, 63 steps of size 7.17e-02. acc. prob=0.83]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  67%|██████▋   | 1007/1500 [05:35<00:41, 11.83it/s, 63 steps of size 7.17e-02. acc. prob=0.85]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  67%|██████▋   | 1009/1500 [05:35<00:41, 11.95it/s, 63 steps of size 7.17e-02. acc. prob=0.87]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  67%|██████▋   | 1011/1500 [05:35<00:40, 12.05it/s, 63 steps of size 7.17e-02. acc. prob=0.89]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  68%|██████▊   | 1013/1500 [05:35<00:40, 12.12it/s, 63 steps of size 7.17e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  68%|██████▊   | 1015/1500 [05:36<00:39, 12.17it/s, 63 steps of size 7.17e-02. acc. prob=0.90]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  68%|██████▊   | 1017/1500 [05:36<00:39, 12.20it/s, 63 steps of size 7.17e-02. acc. prob=0.91]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  68%|██████▊   | 1019/1500 [05:36<00:39, 12.22it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  68%|██████▊   | 1021/1500 [05:36<00:39, 12.23it/s, 63 steps of size 7.17e-02. acc. prob=0.93]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  68%|██████▊   | 1023/1500 [05:36<00:38, 12.25it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  68%|██████▊   | 1025/1500 [05:36<00:38, 12.27it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  68%|██████▊   | 1027/1500 [05:37<00:38, 12.27it/s, 63 steps of size 7.17e-02. acc. prob=0.93]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  69%|██████▊   | 1029/1500 [05:37<00:36, 13.07it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  69%|██████▊   | 1031/1500 [05:37<00:36, 12.79it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  69%|██████▉   | 1033/1500 [05:37<00:36, 12.63it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  69%|██████▉   | 1035/1500 [05:37<00:37, 12.54it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  69%|██████▉   | 1037/1500 [05:37<00:37, 12.47it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  69%|██████▉   | 1039/1500 [05:37<00:37, 12.42it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  69%|██████▉   | 1042/1500 [05:38<00:33, 13.78it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  70%|██████▉   | 1044/1500 [05:38<00:34, 13.34it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  70%|██████▉   | 1046/1500 [05:38<00:34, 13.03it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  70%|██████▉   | 1048/1500 [05:38<00:35, 12.81it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  70%|███████   | 1050/1500 [05:38<00:35, 12.66it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  70%|███████   | 1052/1500 [05:38<00:35, 12.55it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  70%|███████   | 1054/1500 [05:39<00:35, 12.48it/s, 63 steps of size 7.17e-02. acc. prob=0.93]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  70%|███████   | 1056/1500 [05:39<00:35, 12.42it/s, 63 steps of size 7.17e-02. acc. prob=0.93]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  71%|███████   | 1058/1500 [05:39<00:35, 12.35it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  71%|███████   | 1060/1500 [05:39<00:35, 12.33it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  71%|███████   | 1062/1500 [05:39<00:35, 12.32it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  71%|███████   | 1064/1500 [05:39<00:35, 12.29it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  71%|███████   | 1066/1500 [05:40<00:35, 12.29it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  71%|███████   | 1068/1500 [05:40<00:35, 12.26it/s, 63 steps of size 7.17e-02. acc. prob=0.93]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  71%|███████▏  | 1070/1500 [05:40<00:35, 12.26it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  71%|███████▏  | 1072/1500 [05:40<00:34, 12.27it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  72%|███████▏  | 1074/1500 [05:40<00:34, 12.26it/s, 63 steps of size 7.17e-02. acc. prob=0.91]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  72%|███████▏  | 1076/1500 [05:40<00:34, 12.26it/s, 63 steps of size 7.17e-02. acc. prob=0.91]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  72%|███████▏  | 1078/1500 [05:41<00:34, 12.27it/s, 63 steps of size 7.17e-02. acc. prob=0.91]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  72%|███████▏  | 1080/1500 [05:41<00:34, 12.27it/s, 63 steps of size 7.17e-02. acc. prob=0.91]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  72%|███████▏  | 1082/1500 [05:41<00:34, 12.28it/s, 63 steps of size 7.17e-02. acc. prob=0.91]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  72%|███████▏  | 1084/1500 [05:41<00:33, 12.29it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  72%|███████▏  | 1086/1500 [05:41<00:33, 12.30it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  73%|███████▎  | 1088/1500 [05:41<00:33, 12.30it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  73%|███████▎  | 1090/1500 [05:42<00:33, 12.29it/s, 63 steps of size 7.17e-02. acc. prob=0.91]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  73%|███████▎  | 1092/1500 [05:42<00:33, 12.30it/s, 63 steps of size 7.17e-02. acc. prob=0.91]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  73%|███████▎  | 1094/1500 [05:42<00:31, 13.01it/s, 63 steps of size 7.17e-02. acc. prob=0.91]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  73%|███████▎  | 1096/1500 [05:42<00:31, 12.78it/s, 63 steps of size 7.17e-02. acc. prob=0.91]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  73%|███████▎  | 1098/1500 [05:42<00:31, 12.63it/s, 63 steps of size 7.17e-02. acc. prob=0.91]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  73%|███████▎  | 1100/1500 [05:42<00:31, 12.54it/s, 63 steps of size 7.17e-02. acc. prob=0.91]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  73%|███████▎  | 1102/1500 [05:43<00:31, 12.52it/s, 63 steps of size 7.17e-02. acc. prob=0.91]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  74%|███████▎  | 1104/1500 [05:43<00:31, 12.45it/s, 63 steps of size 7.17e-02. acc. prob=0.91]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  74%|███████▎  | 1106/1500 [05:43<00:31, 12.47it/s, 63 steps of size 7.17e-02. acc. prob=0.91]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  74%|███████▍  | 1108/1500 [05:43<00:31, 12.42it/s, 63 steps of size 7.17e-02. acc. prob=0.91]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  74%|███████▍  | 1110/1500 [05:43<00:31, 12.36it/s, 63 steps of size 7.17e-02. acc. prob=0.91]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  74%|███████▍  | 1112/1500 [05:43<00:31, 12.30it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  74%|███████▍  | 1114/1500 [05:43<00:31, 12.29it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  74%|███████▍  | 1116/1500 [05:44<00:31, 12.30it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  75%|███████▍  | 1118/1500 [05:44<00:31, 12.28it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  75%|███████▍  | 1120/1500 [05:44<00:30, 12.30it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  75%|███████▍  | 1122/1500 [05:44<00:35, 10.72it/s, 127 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  75%|███████▍  | 1124/1500 [05:44<00:38,  9.80it/s, 127 steps of size 7.17e-02. acc. prob=0.91]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  75%|███████▌  | 1126/1500 [05:45<00:35, 10.43it/s, 63 steps of size 7.17e-02. acc. prob=0.91] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  75%|███████▌  | 1128/1500 [05:45<00:34, 10.92it/s, 63 steps of size 7.17e-02. acc. prob=0.91]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  75%|███████▌  | 1130/1500 [05:45<00:32, 11.30it/s, 63 steps of size 7.17e-02. acc. prob=0.91]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  75%|███████▌  | 1131/1500 [05:45<00:37,  9.84it/s, 127 steps of size 7.17e-02. acc. prob=0.91]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  76%|███████▌  | 1133/1500 [05:45<00:34, 10.61it/s, 63 steps of size 7.17e-02. acc. prob=0.91] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  76%|███████▌  | 1135/1500 [05:45<00:32, 11.10it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  76%|███████▌  | 1137/1500 [05:46<00:31, 11.44it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  76%|███████▌  | 1139/1500 [05:46<00:30, 11.68it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  76%|███████▌  | 1141/1500 [05:46<00:30, 11.85it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  76%|███████▌  | 1143/1500 [05:46<00:29, 11.97it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  76%|███████▋  | 1145/1500 [05:46<00:29, 12.09it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  76%|███████▋  | 1147/1500 [05:46<00:29, 12.13it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  77%|███████▋  | 1149/1500 [05:47<00:28, 12.18it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  77%|███████▋  | 1151/1500 [05:47<00:28, 12.22it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  77%|███████▋  | 1153/1500 [05:47<00:28, 12.26it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  77%|███████▋  | 1155/1500 [05:47<00:28, 12.28it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  77%|███████▋  | 1157/1500 [05:47<00:27, 12.29it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  77%|███████▋  | 1159/1500 [05:47<00:27, 12.30it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  77%|███████▋  | 1161/1500 [05:48<00:27, 12.29it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  78%|███████▊  | 1163/1500 [05:48<00:27, 12.29it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  78%|███████▊  | 1165/1500 [05:48<00:27, 12.29it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  78%|███████▊  | 1167/1500 [05:48<00:27, 12.30it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  78%|███████▊  | 1169/1500 [05:48<00:26, 12.30it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  78%|███████▊  | 1171/1500 [05:48<00:26, 12.30it/s, 63 steps of size 7.17e-02. acc. prob=0.91]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  78%|███████▊  | 1173/1500 [05:49<00:26, 12.31it/s, 63 steps of size 7.17e-02. acc. prob=0.91]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  78%|███████▊  | 1175/1500 [05:49<00:26, 12.31it/s, 63 steps of size 7.17e-02. acc. prob=0.91]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  78%|███████▊  | 1177/1500 [05:49<00:26, 12.30it/s, 63 steps of size 7.17e-02. acc. prob=0.91]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  79%|███████▊  | 1179/1500 [05:49<00:26, 12.30it/s, 63 steps of size 7.17e-02. acc. prob=0.91]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  79%|███████▊  | 1181/1500 [05:49<00:25, 12.29it/s, 63 steps of size 7.17e-02. acc. prob=0.91]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  79%|███████▉  | 1183/1500 [05:49<00:25, 12.30it/s, 63 steps of size 7.17e-02. acc. prob=0.91]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  79%|███████▉  | 1185/1500 [05:49<00:25, 12.25it/s, 63 steps of size 7.17e-02. acc. prob=0.91]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  79%|███████▉  | 1187/1500 [05:50<00:25, 12.24it/s, 63 steps of size 7.17e-02. acc. prob=0.91]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  79%|███████▉  | 1189/1500 [05:50<00:25, 12.26it/s, 63 steps of size 7.17e-02. acc. prob=0.91]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  79%|███████▉  | 1191/1500 [05:50<00:25, 12.27it/s, 63 steps of size 7.17e-02. acc. prob=0.91]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  80%|███████▉  | 1193/1500 [05:50<00:25, 12.27it/s, 63 steps of size 7.17e-02. acc. prob=0.91]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  80%|███████▉  | 1195/1500 [05:50<00:24, 12.28it/s, 63 steps of size 7.17e-02. acc. prob=0.91]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  80%|███████▉  | 1197/1500 [05:50<00:24, 12.29it/s, 63 steps of size 7.17e-02. acc. prob=0.91]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  80%|███████▉  | 1199/1500 [05:51<00:24, 12.30it/s, 63 steps of size 7.17e-02. acc. prob=0.91]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  80%|████████  | 1201/1500 [05:51<00:24, 12.30it/s, 63 steps of size 7.17e-02. acc. prob=0.91]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  80%|████████  | 1203/1500 [05:51<00:24, 12.31it/s, 63 steps of size 7.17e-02. acc. prob=0.91]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  80%|████████  | 1205/1500 [05:51<00:23, 12.31it/s, 63 steps of size 7.17e-02. acc. prob=0.91]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  80%|████████  | 1207/1500 [05:51<00:23, 12.54it/s, 55 steps of size 7.17e-02. acc. prob=0.91]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  81%|████████  | 1209/1500 [05:51<00:23, 12.46it/s, 63 steps of size 7.17e-02. acc. prob=0.91]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  81%|████████  | 1211/1500 [05:52<00:23, 12.40it/s, 63 steps of size 7.17e-02. acc. prob=0.91]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  81%|████████  | 1213/1500 [05:52<00:23, 12.37it/s, 63 steps of size 7.17e-02. acc. prob=0.91]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  81%|████████  | 1215/1500 [05:52<00:23, 12.35it/s, 63 steps of size 7.17e-02. acc. prob=0.91]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  81%|████████  | 1217/1500 [05:52<00:22, 12.34it/s, 63 steps of size 7.17e-02. acc. prob=0.91]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  81%|████████▏ | 1219/1500 [05:52<00:22, 12.33it/s, 63 steps of size 7.17e-02. acc. prob=0.91]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  81%|████████▏ | 1221/1500 [05:52<00:22, 12.32it/s, 63 steps of size 7.17e-02. acc. prob=0.91]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  82%|████████▏ | 1223/1500 [05:53<00:22, 12.26it/s, 63 steps of size 7.17e-02. acc. prob=0.91]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  82%|████████▏ | 1225/1500 [05:53<00:22, 12.26it/s, 63 steps of size 7.17e-02. acc. prob=0.91]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  82%|████████▏ | 1227/1500 [05:53<00:22, 12.26it/s, 63 steps of size 7.17e-02. acc. prob=0.91]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  82%|████████▏ | 1228/1500 [05:53<00:24, 11.00it/s, 104 steps of size 7.17e-02. acc. prob=0.91]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  82%|████████▏ | 1230/1500 [05:53<00:23, 11.40it/s, 63 steps of size 7.17e-02. acc. prob=0.91] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  82%|████████▏ | 1232/1500 [05:53<00:22, 11.68it/s, 63 steps of size 7.17e-02. acc. prob=0.91]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  82%|████████▏ | 1234/1500 [05:54<00:22, 11.87it/s, 63 steps of size 7.17e-02. acc. prob=0.91]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  82%|████████▏ | 1236/1500 [05:54<00:22, 12.00it/s, 63 steps of size 7.17e-02. acc. prob=0.91]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  83%|████████▎ | 1238/1500 [05:54<00:21, 12.09it/s, 63 steps of size 7.17e-02. acc. prob=0.91]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  83%|████████▎ | 1240/1500 [05:54<00:21, 12.15it/s, 63 steps of size 7.17e-02. acc. prob=0.91]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  83%|████████▎ | 1242/1500 [05:54<00:21, 12.18it/s, 63 steps of size 7.17e-02. acc. prob=0.91]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  83%|████████▎ | 1244/1500 [05:54<00:20, 12.20it/s, 63 steps of size 7.17e-02. acc. prob=0.91]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  83%|████████▎ | 1246/1500 [05:55<00:20, 12.22it/s, 63 steps of size 7.17e-02. acc. prob=0.91]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  83%|████████▎ | 1248/1500 [05:55<00:20, 12.24it/s, 63 steps of size 7.17e-02. acc. prob=0.91]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  83%|████████▎ | 1250/1500 [05:55<00:20, 12.25it/s, 63 steps of size 7.17e-02. acc. prob=0.91]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  83%|████████▎ | 1252/1500 [05:55<00:20, 12.27it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  84%|████████▎ | 1254/1500 [05:55<00:20, 12.27it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  84%|████████▎ | 1256/1500 [05:55<00:19, 12.29it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  84%|████████▍ | 1258/1500 [05:55<00:19, 12.29it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  84%|████████▍ | 1260/1500 [05:56<00:19, 12.28it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  84%|████████▍ | 1262/1500 [05:56<00:19, 12.25it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  84%|████████▍ | 1264/1500 [05:56<00:19, 12.25it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  84%|████████▍ | 1266/1500 [05:56<00:19, 12.27it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  85%|████████▍ | 1268/1500 [05:56<00:18, 12.27it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  85%|████████▍ | 1270/1500 [05:56<00:18, 12.28it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  85%|████████▍ | 1272/1500 [05:57<00:18, 12.29it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  85%|████████▍ | 1274/1500 [05:57<00:18, 12.29it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  85%|████████▌ | 1276/1500 [05:57<00:18, 12.29it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  85%|████████▌ | 1278/1500 [05:57<00:18, 12.31it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  85%|████████▌ | 1280/1500 [05:57<00:17, 12.31it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  85%|████████▌ | 1282/1500 [05:57<00:17, 12.31it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  86%|████████▌ | 1284/1500 [05:58<00:20, 10.67it/s, 127 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  86%|████████▌ | 1286/1500 [05:58<00:19, 11.11it/s, 63 steps of size 7.17e-02. acc. prob=0.92] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  86%|████████▌ | 1288/1500 [05:58<00:18, 11.44it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  86%|████████▌ | 1290/1500 [05:58<00:17, 11.67it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  86%|████████▌ | 1292/1500 [05:58<00:17, 11.86it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  86%|████████▋ | 1294/1500 [05:58<00:17, 11.97it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  86%|████████▋ | 1296/1500 [05:59<00:16, 12.06it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  87%|████████▋ | 1298/1500 [05:59<00:16, 12.10it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  87%|████████▋ | 1300/1500 [05:59<00:16, 12.16it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  87%|████████▋ | 1302/1500 [05:59<00:16, 12.17it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  87%|████████▋ | 1304/1500 [05:59<00:16, 12.20it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  87%|████████▋ | 1306/1500 [05:59<00:15, 12.23it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  87%|████████▋ | 1308/1500 [06:00<00:15, 12.49it/s, 55 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  87%|████████▋ | 1310/1500 [06:00<00:15, 12.41it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  87%|████████▋ | 1312/1500 [06:00<00:15, 12.37it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  88%|████████▊ | 1314/1500 [06:00<00:15, 12.23it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  88%|████████▊ | 1316/1500 [06:00<00:15, 12.21it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  88%|████████▊ | 1318/1500 [06:00<00:14, 12.23it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  88%|████████▊ | 1320/1500 [06:01<00:14, 12.24it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  88%|████████▊ | 1322/1500 [06:01<00:14, 12.25it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  88%|████████▊ | 1324/1500 [06:01<00:14, 12.27it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  88%|████████▊ | 1326/1500 [06:01<00:14, 12.27it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  89%|████████▊ | 1328/1500 [06:01<00:14, 12.27it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  89%|████████▊ | 1330/1500 [06:01<00:13, 12.28it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  89%|████████▉ | 1332/1500 [06:02<00:13, 12.28it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  89%|████████▉ | 1334/1500 [06:02<00:13, 12.27it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  89%|████████▉ | 1336/1500 [06:02<00:13, 12.24it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  89%|████████▉ | 1338/1500 [06:02<00:13, 12.24it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  89%|████████▉ | 1340/1500 [06:02<00:13, 12.26it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  89%|████████▉ | 1342/1500 [06:02<00:12, 12.26it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  90%|████████▉ | 1344/1500 [06:03<00:12, 12.28it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  90%|████████▉ | 1346/1500 [06:03<00:12, 12.28it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  90%|████████▉ | 1348/1500 [06:03<00:14, 10.68it/s, 127 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  90%|█████████ | 1350/1500 [06:03<00:13, 11.11it/s, 63 steps of size 7.17e-02. acc. prob=0.92] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  90%|█████████ | 1352/1500 [06:03<00:12, 11.44it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  90%|█████████ | 1354/1500 [06:03<00:12, 11.68it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  90%|█████████ | 1356/1500 [06:04<00:12, 11.85it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  91%|█████████ | 1358/1500 [06:04<00:11, 11.98it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  91%|█████████ | 1360/1500 [06:04<00:11, 12.07it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  91%|█████████ | 1362/1500 [06:04<00:11, 12.15it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  91%|█████████ | 1364/1500 [06:04<00:11, 12.18it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  91%|█████████ | 1366/1500 [06:04<00:10, 12.22it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  91%|█████████ | 1368/1500 [06:05<00:10, 12.25it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  91%|█████████▏| 1370/1500 [06:05<00:10, 12.27it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  91%|█████████▏| 1372/1500 [06:05<00:10, 12.28it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  92%|█████████▏| 1374/1500 [06:05<00:10, 12.30it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  92%|█████████▏| 1376/1500 [06:05<00:10, 12.30it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  92%|█████████▏| 1378/1500 [06:05<00:09, 12.29it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  92%|█████████▏| 1380/1500 [06:06<00:09, 12.29it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  92%|█████████▏| 1382/1500 [06:06<00:09, 12.30it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  92%|█████████▏| 1384/1500 [06:06<00:08, 13.14it/s, 36 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  92%|█████████▏| 1386/1500 [06:06<00:08, 12.90it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  93%|█████████▎| 1388/1500 [06:06<00:08, 12.70it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  93%|█████████▎| 1390/1500 [06:06<00:08, 12.57it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  93%|█████████▎| 1392/1500 [06:07<00:08, 12.49it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  93%|█████████▎| 1394/1500 [06:07<00:08, 12.43it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  93%|█████████▎| 1396/1500 [06:07<00:08, 12.39it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  93%|█████████▎| 1398/1500 [06:07<00:08, 12.36it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  93%|█████████▎| 1400/1500 [06:07<00:08, 12.33it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  93%|█████████▎| 1402/1500 [06:07<00:07, 12.32it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  94%|█████████▎| 1404/1500 [06:07<00:07, 12.31it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  94%|█████████▎| 1406/1500 [06:08<00:07, 12.31it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  94%|█████████▍| 1407/1500 [06:08<00:08, 10.39it/s, 127 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  94%|█████████▍| 1409/1500 [06:08<00:08, 10.95it/s, 63 steps of size 7.17e-02. acc. prob=0.92] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  94%|█████████▍| 1410/1500 [06:08<00:09,  9.50it/s, 127 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  94%|█████████▍| 1412/1500 [06:08<00:08, 10.32it/s, 63 steps of size 7.17e-02. acc. prob=0.92] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  94%|█████████▍| 1414/1500 [06:08<00:07, 10.90it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  94%|█████████▍| 1416/1500 [06:09<00:08,  9.83it/s, 127 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  95%|█████████▍| 1418/1500 [06:09<00:07, 10.50it/s, 63 steps of size 7.17e-02. acc. prob=0.92] "
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  95%|█████████▍| 1420/1500 [06:09<00:07, 11.00it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  95%|█████████▍| 1422/1500 [06:09<00:06, 11.38it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  95%|█████████▍| 1424/1500 [06:09<00:06, 11.64it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  95%|█████████▌| 1426/1500 [06:10<00:06, 11.83it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  95%|█████████▌| 1428/1500 [06:10<00:06, 11.96it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  95%|█████████▌| 1430/1500 [06:10<00:05, 12.05it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  95%|█████████▌| 1432/1500 [06:10<00:05, 12.13it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  96%|█████████▌| 1434/1500 [06:10<00:05, 12.17it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  96%|█████████▌| 1436/1500 [06:10<00:05, 12.22it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  96%|█████████▌| 1438/1500 [06:11<00:05, 12.24it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  96%|█████████▌| 1440/1500 [06:11<00:04, 12.26it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  96%|█████████▌| 1442/1500 [06:11<00:04, 12.27it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  96%|█████████▋| 1444/1500 [06:11<00:04, 12.28it/s, 63 steps of size 7.17e-02. acc. prob=0.93]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  96%|█████████▋| 1446/1500 [06:11<00:04, 12.29it/s, 63 steps of size 7.17e-02. acc. prob=0.93]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  97%|█████████▋| 1448/1500 [06:11<00:04, 12.29it/s, 63 steps of size 7.17e-02. acc. prob=0.93]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  97%|█████████▋| 1450/1500 [06:11<00:04, 12.29it/s, 63 steps of size 7.17e-02. acc. prob=0.93]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  97%|█████████▋| 1452/1500 [06:12<00:03, 12.25it/s, 63 steps of size 7.17e-02. acc. prob=0.93]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  97%|█████████▋| 1454/1500 [06:12<00:03, 12.25it/s, 63 steps of size 7.17e-02. acc. prob=0.93]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  97%|█████████▋| 1456/1500 [06:12<00:03, 12.24it/s, 63 steps of size 7.17e-02. acc. prob=0.93]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  97%|█████████▋| 1458/1500 [06:12<00:03, 12.25it/s, 63 steps of size 7.17e-02. acc. prob=0.93]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  97%|█████████▋| 1460/1500 [06:12<00:03, 12.27it/s, 63 steps of size 7.17e-02. acc. prob=0.93]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  97%|█████████▋| 1462/1500 [06:12<00:03, 12.28it/s, 63 steps of size 7.17e-02. acc. prob=0.93]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  98%|█████████▊| 1464/1500 [06:13<00:02, 12.27it/s, 63 steps of size 7.17e-02. acc. prob=0.93]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  98%|█████████▊| 1466/1500 [06:13<00:02, 12.27it/s, 63 steps of size 7.17e-02. acc. prob=0.93]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  98%|█████████▊| 1468/1500 [06:13<00:02, 12.26it/s, 63 steps of size 7.17e-02. acc. prob=0.93]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  98%|█████████▊| 1470/1500 [06:13<00:02, 12.27it/s, 63 steps of size 7.17e-02. acc. prob=0.93]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  98%|█████████▊| 1472/1500 [06:13<00:02, 12.28it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  98%|█████████▊| 1474/1500 [06:13<00:02, 12.28it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  98%|█████████▊| 1476/1500 [06:14<00:01, 12.28it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  99%|█████████▊| 1478/1500 [06:14<00:01, 12.26it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  99%|█████████▊| 1480/1500 [06:14<00:01, 12.26it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  99%|█████████▉| 1482/1500 [06:14<00:01, 12.27it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  99%|█████████▉| 1484/1500 [06:14<00:01, 12.24it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  99%|█████████▉| 1486/1500 [06:14<00:01, 12.24it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  99%|█████████▉| 1488/1500 [06:15<00:00, 12.24it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  99%|█████████▉| 1490/1500 [06:15<00:00, 12.25it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample:  99%|█████████▉| 1492/1500 [06:15<00:00, 12.21it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample: 100%|█████████▉| 1494/1500 [06:15<00:00, 12.22it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample: 100%|█████████▉| 1496/1500 [06:15<00:00, 12.24it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample: 100%|█████████▉| 1498/1500 [06:15<00:00, 12.25it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample: 100%|██████████| 1500/1500 [06:16<00:00, 12.26it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "sample: 100%|██████████| 1500/1500 [06:16<00:00,  3.99it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\n"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "There were 26 divergences after tuning. Increase `target_accept` or reparameterize.\n"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "We recommend running at least 4 chains for robust computation of convergence diagnostics\n"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "The rhat statistic is larger than 1.01 for some parameters. This indicates problems during sampling. See https://arxiv.org/abs/1903.08008 for details\n"
-     ]
-    },
-    {
-     "data": {
-      "text/html": [
-       "<div><svg style=\"position: absolute; width: 0; height: 0; overflow: hidden\">\n",
-       "<defs>\n",
-       "<symbol id=\"icon-database\" viewBox=\"0 0 32 32\">\n",
-       "<path d=\"M16 0c-8.837 0-16 2.239-16 5v4c0 2.761 7.163 5 16 5s16-2.239 16-5v-4c0-2.761-7.163-5-16-5z\"></path>\n",
-       "<path d=\"M16 17c-8.837 0-16-2.239-16-5v6c0 2.761 7.163 5 16 5s16-2.239 16-5v-6c0 2.761-7.163 5-16 5z\"></path>\n",
-       "<path d=\"M16 26c-8.837 0-16-2.239-16-5v6c0 2.761 7.163 5 16 5s16-2.239 16-5v-6c0 2.761-7.163 5-16 5z\"></path>\n",
-       "</symbol>\n",
-       "<symbol id=\"icon-file-text2\" viewBox=\"0 0 32 32\">\n",
-       "<path d=\"M28.681 7.159c-0.694-0.947-1.662-2.053-2.724-3.116s-2.169-2.030-3.116-2.724c-1.612-1.182-2.393-1.319-2.841-1.319h-15.5c-1.378 0-2.5 1.121-2.5 2.5v27c0 1.378 1.122 2.5 2.5 2.5h23c1.378 0 2.5-1.122 2.5-2.5v-19.5c0-0.448-0.137-1.23-1.319-2.841zM24.543 5.457c0.959 0.959 1.712 1.825 2.268 2.543h-4.811v-4.811c0.718 0.556 1.584 1.309 2.543 2.268zM28 29.5c0 0.271-0.229 0.5-0.5 0.5h-23c-0.271 0-0.5-0.229-0.5-0.5v-27c0-0.271 0.229-0.5 0.5-0.5 0 0 15.499-0 15.5 0v7c0 0.552 0.448 1 1 1h7v19.5z\"></path>\n",
-       "<path d=\"M23 26h-14c-0.552 0-1-0.448-1-1s0.448-1 1-1h14c0.552 0 1 0.448 1 1s-0.448 1-1 1z\"></path>\n",
-       "<path d=\"M23 22h-14c-0.552 0-1-0.448-1-1s0.448-1 1-1h14c0.552 0 1 0.448 1 1s-0.448 1-1 1z\"></path>\n",
-       "<path d=\"M23 18h-14c-0.552 0-1-0.448-1-1s0.448-1 1-1h14c0.552 0 1 0.448 1 1s-0.448 1-1 1z\"></path>\n",
-       "</symbol>\n",
-       "</defs>\n",
-       "</svg>\n",
-       "<style>/* CSS stylesheet for displaying xarray objects in notebooks */\n",
-       "\n",
-       ":root {\n",
-       "  --xr-font-color0: var(\n",
-       "    --jp-content-font-color0,\n",
-       "    var(--pst-color-text-base rgba(0, 0, 0, 1))\n",
-       "  );\n",
-       "  --xr-font-color2: var(\n",
-       "    --jp-content-font-color2,\n",
-       "    var(--pst-color-text-base, rgba(0, 0, 0, 0.54))\n",
-       "  );\n",
-       "  --xr-font-color3: var(\n",
-       "    --jp-content-font-color3,\n",
-       "    var(--pst-color-text-base, rgba(0, 0, 0, 0.38))\n",
-       "  );\n",
-       "  --xr-border-color: var(\n",
-       "    --jp-border-color2,\n",
-       "    hsl(from var(--pst-color-on-background, white) h s calc(l - 10))\n",
-       "  );\n",
-       "  --xr-disabled-color: var(\n",
-       "    --jp-layout-color3,\n",
-       "    hsl(from var(--pst-color-on-background, white) h s calc(l - 40))\n",
-       "  );\n",
-       "  --xr-background-color: var(\n",
-       "    --jp-layout-color0,\n",
-       "    var(--pst-color-on-background, white)\n",
-       "  );\n",
-       "  --xr-background-color-row-even: var(\n",
-       "    --jp-layout-color1,\n",
-       "    hsl(from var(--pst-color-on-background, white) h s calc(l - 5))\n",
-       "  );\n",
-       "  --xr-background-color-row-odd: var(\n",
-       "    --jp-layout-color2,\n",
-       "    hsl(from var(--pst-color-on-background, white) h s calc(l - 15))\n",
-       "  );\n",
-       "}\n",
-       "\n",
-       "html[theme=\"dark\"],\n",
-       "html[data-theme=\"dark\"],\n",
-       "body[data-theme=\"dark\"],\n",
-       "body.vscode-dark {\n",
-       "  --xr-font-color0: var(\n",
-       "    --jp-content-font-color0,\n",
-       "    var(--pst-color-text-base, rgba(255, 255, 255, 1))\n",
-       "  );\n",
-       "  --xr-font-color2: var(\n",
-       "    --jp-content-font-color2,\n",
-       "    var(--pst-color-text-base, rgba(255, 255, 255, 0.54))\n",
-       "  );\n",
-       "  --xr-font-color3: var(\n",
-       "    --jp-content-font-color3,\n",
-       "    var(--pst-color-text-base, rgba(255, 255, 255, 0.38))\n",
-       "  );\n",
-       "  --xr-border-color: var(\n",
-       "    --jp-border-color2,\n",
-       "    hsl(from var(--pst-color-on-background, #111111) h s calc(l + 10))\n",
-       "  );\n",
-       "  --xr-disabled-color: var(\n",
-       "    --jp-layout-color3,\n",
-       "    hsl(from var(--pst-color-on-background, #111111) h s calc(l + 40))\n",
-       "  );\n",
-       "  --xr-background-color: var(\n",
-       "    --jp-layout-color0,\n",
-       "    var(--pst-color-on-background, #111111)\n",
-       "  );\n",
-       "  --xr-background-color-row-even: var(\n",
-       "    --jp-layout-color1,\n",
-       "    hsl(from var(--pst-color-on-background, #111111) h s calc(l + 5))\n",
-       "  );\n",
-       "  --xr-background-color-row-odd: var(\n",
-       "    --jp-layout-color2,\n",
-       "    hsl(from var(--pst-color-on-background, #111111) h s calc(l + 15))\n",
-       "  );\n",
-       "}\n",
-       "\n",
-       ".xr-wrap {\n",
-       "  display: block !important;\n",
-       "  min-width: 300px;\n",
-       "  max-width: 700px;\n",
-       "  line-height: 1.6;\n",
-       "  padding-bottom: 4px;\n",
-       "}\n",
-       "\n",
-       ".xr-text-repr-fallback {\n",
-       "  /* fallback to plain text repr when CSS is not injected (untrusted notebook) */\n",
-       "  display: none;\n",
-       "}\n",
-       "\n",
-       ".xr-header {\n",
-       "  padding-top: 6px;\n",
-       "  padding-bottom: 6px;\n",
-       "}\n",
-       "\n",
-       ".xr-header {\n",
-       "  border-bottom: solid 1px var(--xr-border-color);\n",
-       "  margin-bottom: 4px;\n",
-       "}\n",
-       "\n",
-       ".xr-header > div,\n",
-       ".xr-header > ul {\n",
-       "  display: inline;\n",
-       "  margin-top: 0;\n",
-       "  margin-bottom: 0;\n",
-       "}\n",
-       "\n",
-       ".xr-obj-type,\n",
-       ".xr-obj-name {\n",
-       "  margin-left: 2px;\n",
-       "  margin-right: 10px;\n",
-       "}\n",
-       "\n",
-       ".xr-obj-type,\n",
-       ".xr-group-box-contents > label {\n",
-       "  color: var(--xr-font-color2);\n",
-       "  display: block;\n",
-       "}\n",
-       "\n",
-       ".xr-sections {\n",
-       "  padding-left: 0 !important;\n",
-       "  display: grid;\n",
-       "  grid-template-columns: 150px auto auto 1fr 0 20px 0 20px;\n",
-       "  margin-block-start: 0;\n",
-       "  margin-block-end: 0;\n",
-       "}\n",
-       "\n",
-       ".xr-section-item {\n",
-       "  display: contents;\n",
-       "}\n",
-       "\n",
-       ".xr-section-item > input,\n",
-       ".xr-group-box-contents > input,\n",
-       ".xr-array-wrap > input {\n",
-       "  display: block;\n",
-       "  opacity: 0;\n",
-       "  height: 0;\n",
-       "  margin: 0;\n",
-       "}\n",
-       "\n",
-       ".xr-section-item > input + label,\n",
-       ".xr-var-item > input + label {\n",
-       "  color: var(--xr-disabled-color);\n",
-       "}\n",
-       "\n",
-       ".xr-section-item > input:enabled + label,\n",
-       ".xr-var-item > input:enabled + label,\n",
-       ".xr-array-wrap > input:enabled + label,\n",
-       ".xr-group-box-contents > input:enabled + label {\n",
-       "  cursor: pointer;\n",
-       "  color: var(--xr-font-color2);\n",
-       "}\n",
-       "\n",
-       ".xr-section-item > input:focus-visible + label,\n",
-       ".xr-var-item > input:focus-visible + label,\n",
-       ".xr-array-wrap > input:focus-visible + label,\n",
-       ".xr-group-box-contents > input:focus-visible + label {\n",
-       "  outline: auto;\n",
-       "}\n",
-       "\n",
-       ".xr-section-item > input:enabled + label:hover,\n",
-       ".xr-var-item > input:enabled + label:hover,\n",
-       ".xr-array-wrap > input:enabled + label:hover,\n",
-       ".xr-group-box-contents > input:enabled + label:hover {\n",
-       "  color: var(--xr-font-color0);\n",
-       "}\n",
-       "\n",
-       ".xr-section-summary {\n",
-       "  grid-column: 1;\n",
-       "  color: var(--xr-font-color2);\n",
-       "  font-weight: 500;\n",
-       "  white-space: nowrap;\n",
-       "}\n",
-       "\n",
-       ".xr-section-summary > em {\n",
-       "  font-weight: normal;\n",
-       "}\n",
-       "\n",
-       ".xr-span-grid {\n",
-       "  grid-column-end: -1;\n",
-       "}\n",
-       "\n",
-       ".xr-section-summary > span {\n",
-       "  display: inline-block;\n",
-       "  padding-left: 0.3em;\n",
-       "}\n",
-       "\n",
-       ".xr-group-box-contents > input:checked + label > span {\n",
-       "  display: inline-block;\n",
-       "  padding-left: 0.6em;\n",
-       "}\n",
-       "\n",
-       ".xr-section-summary-in:disabled + label {\n",
-       "  color: var(--xr-font-color2);\n",
-       "}\n",
-       "\n",
-       ".xr-section-summary-in + label:before {\n",
-       "  display: inline-block;\n",
-       "  content: \"►\";\n",
-       "  font-size: 11px;\n",
-       "  width: 15px;\n",
-       "  text-align: center;\n",
-       "}\n",
-       "\n",
-       ".xr-section-summary-in:disabled + label:before {\n",
-       "  color: var(--xr-disabled-color);\n",
-       "}\n",
-       "\n",
-       ".xr-section-summary-in:checked + label:before {\n",
-       "  content: \"▼\";\n",
-       "}\n",
-       "\n",
-       ".xr-section-summary-in:checked + label > span {\n",
-       "  display: none;\n",
-       "}\n",
-       "\n",
-       ".xr-section-summary,\n",
-       ".xr-section-inline-details,\n",
-       ".xr-group-box-contents > label {\n",
-       "  padding-top: 4px;\n",
-       "}\n",
-       "\n",
-       ".xr-section-inline-details {\n",
-       "  grid-column: 2 / -1;\n",
-       "}\n",
-       "\n",
-       ".xr-section-details {\n",
-       "  grid-column: 1 / -1;\n",
-       "  margin-top: 4px;\n",
-       "  margin-bottom: 5px;\n",
-       "}\n",
-       "\n",
-       ".xr-section-summary-in ~ .xr-section-details {\n",
-       "  display: none;\n",
-       "}\n",
-       "\n",
-       ".xr-section-summary-in:checked ~ .xr-section-details {\n",
-       "  display: contents;\n",
-       "}\n",
-       "\n",
-       ".xr-children {\n",
-       "  display: inline-grid;\n",
-       "  grid-template-columns: 100%;\n",
-       "  grid-column: 1 / -1;\n",
-       "  padding-top: 4px;\n",
-       "}\n",
-       "\n",
-       ".xr-group-box {\n",
-       "  display: inline-grid;\n",
-       "  grid-template-columns: 0px 30px auto;\n",
-       "}\n",
-       "\n",
-       ".xr-group-box-vline {\n",
-       "  grid-column-start: 1;\n",
-       "  border-right: 0.2em solid;\n",
-       "  border-color: var(--xr-border-color);\n",
-       "  width: 0px;\n",
-       "}\n",
-       "\n",
-       ".xr-group-box-hline {\n",
-       "  grid-column-start: 2;\n",
-       "  grid-row-start: 1;\n",
-       "  height: 1em;\n",
-       "  width: 26px;\n",
-       "  border-bottom: 0.2em solid;\n",
-       "  border-color: var(--xr-border-color);\n",
-       "}\n",
-       "\n",
-       ".xr-group-box-contents {\n",
-       "  grid-column-start: 3;\n",
-       "  padding-bottom: 4px;\n",
-       "}\n",
-       "\n",
-       ".xr-group-box-contents > label::before {\n",
-       "  content: \"📂\";\n",
-       "  padding-right: 0.3em;\n",
-       "}\n",
-       "\n",
-       ".xr-group-box-contents > input:checked + label::before {\n",
-       "  content: \"📁\";\n",
-       "}\n",
-       "\n",
-       ".xr-group-box-contents > input:checked + label {\n",
-       "  padding-bottom: 0px;\n",
-       "}\n",
-       "\n",
-       ".xr-group-box-contents > input:checked ~ .xr-sections {\n",
-       "  display: none;\n",
-       "}\n",
-       "\n",
-       ".xr-group-box-contents > input + label > span {\n",
-       "  display: none;\n",
-       "}\n",
-       "\n",
-       ".xr-group-box-ellipsis {\n",
-       "  font-size: 1.4em;\n",
-       "  font-weight: 900;\n",
-       "  color: var(--xr-font-color2);\n",
-       "  letter-spacing: 0.15em;\n",
-       "  cursor: default;\n",
-       "}\n",
-       "\n",
-       ".xr-array-wrap {\n",
-       "  grid-column: 1 / -1;\n",
-       "  display: grid;\n",
-       "  grid-template-columns: 20px auto;\n",
-       "}\n",
-       "\n",
-       ".xr-array-wrap > label {\n",
-       "  grid-column: 1;\n",
-       "  vertical-align: top;\n",
-       "}\n",
-       "\n",
-       ".xr-preview {\n",
-       "  color: var(--xr-font-color3);\n",
-       "}\n",
-       "\n",
-       ".xr-array-preview,\n",
-       ".xr-array-data {\n",
-       "  padding: 0 5px !important;\n",
-       "  grid-column: 2;\n",
-       "}\n",
-       "\n",
-       ".xr-array-data,\n",
-       ".xr-array-in:checked ~ .xr-array-preview {\n",
-       "  display: none;\n",
-       "}\n",
-       "\n",
-       ".xr-array-in:checked ~ .xr-array-data,\n",
-       ".xr-array-preview {\n",
-       "  display: inline-block;\n",
-       "}\n",
-       "\n",
-       ".xr-dim-list {\n",
-       "  display: inline-block !important;\n",
-       "  list-style: none;\n",
-       "  padding: 0 !important;\n",
-       "  margin: 0;\n",
-       "}\n",
-       "\n",
-       ".xr-dim-list li {\n",
-       "  display: inline-block;\n",
-       "  padding: 0;\n",
-       "  margin: 0;\n",
-       "}\n",
-       "\n",
-       ".xr-dim-list:before {\n",
-       "  content: \"(\";\n",
-       "}\n",
-       "\n",
-       ".xr-dim-list:after {\n",
-       "  content: \")\";\n",
-       "}\n",
-       "\n",
-       ".xr-dim-list li:not(:last-child):after {\n",
-       "  content: \",\";\n",
-       "  padding-right: 5px;\n",
-       "}\n",
-       "\n",
-       ".xr-has-index {\n",
-       "  font-weight: bold;\n",
-       "}\n",
-       "\n",
-       ".xr-var-list,\n",
-       ".xr-var-item {\n",
-       "  display: contents;\n",
-       "}\n",
-       "\n",
-       ".xr-var-item > div,\n",
-       ".xr-var-item label,\n",
-       ".xr-var-item > .xr-var-name span {\n",
-       "  background-color: var(--xr-background-color-row-even);\n",
-       "  border-color: var(--xr-background-color-row-odd);\n",
-       "  margin-bottom: 0;\n",
-       "  padding-top: 2px;\n",
-       "}\n",
-       "\n",
-       ".xr-var-item > .xr-var-name:hover span {\n",
-       "  padding-right: 5px;\n",
-       "}\n",
-       "\n",
-       ".xr-var-list > li:nth-child(odd) > div,\n",
-       ".xr-var-list > li:nth-child(odd) > label,\n",
-       ".xr-var-list > li:nth-child(odd) > .xr-var-name span {\n",
-       "  background-color: var(--xr-background-color-row-odd);\n",
-       "  border-color: var(--xr-background-color-row-even);\n",
-       "}\n",
-       "\n",
-       ".xr-var-name {\n",
-       "  grid-column: 1;\n",
-       "}\n",
-       "\n",
-       ".xr-var-dims {\n",
-       "  grid-column: 2;\n",
-       "}\n",
-       "\n",
-       ".xr-var-dtype {\n",
-       "  grid-column: 3;\n",
-       "  text-align: right;\n",
-       "  color: var(--xr-font-color2);\n",
-       "}\n",
-       "\n",
-       ".xr-var-preview {\n",
-       "  grid-column: 4;\n",
-       "}\n",
-       "\n",
-       ".xr-index-preview {\n",
-       "  grid-column: 2 / 5;\n",
-       "  color: var(--xr-font-color2);\n",
-       "}\n",
-       "\n",
-       ".xr-var-name,\n",
-       ".xr-var-dims,\n",
-       ".xr-var-dtype,\n",
-       ".xr-preview,\n",
-       ".xr-attrs dt {\n",
-       "  white-space: nowrap;\n",
-       "  overflow: hidden;\n",
-       "  text-overflow: ellipsis;\n",
-       "  padding-right: 10px;\n",
-       "}\n",
-       "\n",
-       ".xr-var-name:hover,\n",
-       ".xr-var-dims:hover,\n",
-       ".xr-var-dtype:hover,\n",
-       ".xr-attrs dt:hover {\n",
-       "  overflow: visible;\n",
-       "  width: auto;\n",
-       "  z-index: 1;\n",
-       "}\n",
-       "\n",
-       ".xr-var-attrs,\n",
-       ".xr-var-data,\n",
-       ".xr-index-data {\n",
-       "  display: none;\n",
-       "  border-top: 2px dotted var(--xr-background-color);\n",
-       "  padding-bottom: 20px !important;\n",
-       "  padding-top: 10px !important;\n",
-       "}\n",
-       "\n",
-       ".xr-var-attrs-in + label,\n",
-       ".xr-var-data-in + label,\n",
-       ".xr-index-data-in + label {\n",
-       "  padding: 0 1px;\n",
-       "}\n",
-       "\n",
-       ".xr-var-attrs-in:checked ~ .xr-var-attrs,\n",
-       ".xr-var-data-in:checked ~ .xr-var-data,\n",
-       ".xr-index-data-in:checked ~ .xr-index-data {\n",
-       "  display: block;\n",
-       "}\n",
-       "\n",
-       ".xr-var-data > table {\n",
-       "  float: right;\n",
-       "}\n",
-       "\n",
-       ".xr-var-data > pre,\n",
-       ".xr-index-data > pre,\n",
-       ".xr-var-data > table > tbody > tr {\n",
-       "  background-color: transparent !important;\n",
-       "}\n",
-       "\n",
-       ".xr-var-name span,\n",
-       ".xr-var-data,\n",
-       ".xr-index-name div,\n",
-       ".xr-index-data,\n",
-       ".xr-attrs {\n",
-       "  padding-left: 25px !important;\n",
-       "}\n",
-       "\n",
-       ".xr-attrs,\n",
-       ".xr-var-attrs,\n",
-       ".xr-var-data,\n",
-       ".xr-index-data {\n",
-       "  grid-column: 1 / -1;\n",
-       "}\n",
-       "\n",
-       "dl.xr-attrs {\n",
-       "  padding: 0;\n",
-       "  margin: 0;\n",
-       "  display: grid;\n",
-       "  grid-template-columns: 125px auto;\n",
-       "}\n",
-       "\n",
-       ".xr-attrs dt,\n",
-       ".xr-attrs dd {\n",
-       "  padding: 0;\n",
-       "  margin: 0;\n",
-       "  float: left;\n",
-       "  padding-right: 10px;\n",
-       "  width: auto;\n",
-       "}\n",
-       "\n",
-       ".xr-attrs dt {\n",
-       "  font-weight: normal;\n",
-       "  grid-column: 1;\n",
-       "}\n",
-       "\n",
-       ".xr-attrs dt:hover span {\n",
-       "  display: inline-block;\n",
-       "  background: var(--xr-background-color);\n",
-       "  padding-right: 10px;\n",
-       "}\n",
-       "\n",
-       ".xr-attrs dd {\n",
-       "  grid-column: 2;\n",
-       "  white-space: pre-wrap;\n",
-       "  word-break: break-all;\n",
-       "}\n",
-       "\n",
-       ".xr-icon-database,\n",
-       ".xr-icon-file-text2,\n",
-       ".xr-no-icon {\n",
-       "  display: inline-block;\n",
-       "  vertical-align: middle;\n",
-       "  width: 1em;\n",
-       "  height: 1.5em !important;\n",
-       "  stroke-width: 0;\n",
-       "  stroke: currentColor;\n",
-       "  fill: currentColor;\n",
-       "}\n",
-       "\n",
-       ".xr-var-attrs-in:checked + label > .xr-icon-file-text2,\n",
-       ".xr-var-data-in:checked + label > .xr-icon-database,\n",
-       ".xr-index-data-in:checked + label > .xr-icon-database {\n",
-       "  color: var(--xr-font-color0);\n",
-       "  filter: drop-shadow(1px 1px 5px var(--xr-font-color2));\n",
-       "  stroke-width: 0.8px;\n",
-       "}\n",
-       "</style><pre class='xr-text-repr-fallback'>&lt;xarray.DataTree&gt;\n",
-       "Group: /\n",
-       "├── Group: /posterior\n",
-       "│       Dimensions:                                (chain: 2, draw: 500,\n",
-       "│                                                   participant_id__factor_dim: 15,\n",
-       "│                                                   rl_alpha_1|participant_id__factor_dim: 15)\n",
-       "│       Coordinates:\n",
-       "│         * chain                                  (chain) int64 16B 0 1\n",
-       "│         * draw                                   (draw) int64 4kB 0 1 2 ... 498 499\n",
-       "│         * participant_id__factor_dim             (participant_id__factor_dim) &lt;U2 120B ...\n",
-       "│         * rl_alpha_1|participant_id__factor_dim  (rl_alpha_1|participant_id__factor_dim) &lt;U2 120B ...\n",
-       "│       Data variables: (12/24)\n",
-       "│           t_1|participant_id_offset              (chain, draw, participant_id__factor_dim) float32 60kB ...\n",
-       "│           z_1|participant_id                     (chain, draw, participant_id__factor_dim) float32 60kB ...\n",
-       "│           z_1|participant_id_sigma               (chain, draw) float32 4kB ...\n",
-       "│           theta_1|participant_id                 (chain, draw, participant_id__factor_dim) float32 60kB ...\n",
-       "│           rl_alpha_Intercept                     (chain, draw) float32 4kB ...\n",
-       "│           t_Intercept                            (chain, draw) float32 4kB ...\n",
-       "│           ...                                     ...\n",
-       "│           theta_1|participant_id_offset          (chain, draw, participant_id__factor_dim) float32 60kB ...\n",
-       "│           a_1|participant_id_offset              (chain, draw, participant_id__factor_dim) float32 60kB ...\n",
-       "│           t_1|participant_id_sigma               (chain, draw) float32 4kB ...\n",
-       "│           t_1|participant_id                     (chain, draw, participant_id__factor_dim) float32 60kB ...\n",
-       "│           scaler_1|participant_id_offset         (chain, draw, participant_id__factor_dim) float32 60kB ...\n",
-       "│           rl_alpha_1|participant_id_offset       (chain, draw, rl_alpha_1|participant_id__factor_dim) float32 60kB ...\n",
-       "│       Attributes:\n",
-       "│           created_at:                  2026-07-06T16:44:41.787695+00:00\n",
-       "│           creation_library:            ArviZ\n",
-       "│           creation_library_version:    1.2.0\n",
-       "│           creation_library_language:   Python\n",
-       "│           sample_dims:                 [&#x27;chain&#x27;, &#x27;draw&#x27;]\n",
-       "│           inference_library:           numpyro\n",
-       "│           inference_library_version:   0.21.0\n",
-       "│           sampling_time:               545.10303\n",
-       "│           tuning_steps:                1000\n",
-       "│           modeling_interface:          bambi\n",
-       "│           modeling_interface_version:  0.18.0\n",
-       "├── Group: /sample_stats\n",
-       "│       Dimensions:          (chain: 2, draw: 500)\n",
-       "│       Coordinates:\n",
-       "│         * chain            (chain) int64 16B 0 1\n",
-       "│         * draw             (draw) int64 4kB 0 1 2 3 4 5 6 ... 494 495 496 497 498 499\n",
-       "│       Data variables:\n",
-       "│           acceptance_rate  (chain, draw) float32 4kB ...\n",
-       "│           step_size        (chain, draw) float32 4kB ...\n",
-       "│           diverging        (chain, draw) bool 1kB ...\n",
-       "│           energy           (chain, draw) float32 4kB ...\n",
-       "│           n_steps          (chain, draw) int32 4kB ...\n",
-       "│           tree_depth       (chain, draw) int64 8kB 6 6 6 6 6 6 6 6 ... 6 6 6 6 6 6 6 6\n",
-       "│           lp               (chain, draw) float32 4kB ...\n",
-       "│       Attributes:\n",
-       "│           created_at:                  2026-07-06T16:44:41.799808+00:00\n",
-       "│           creation_library:            ArviZ\n",
-       "│           creation_library_version:    1.2.0\n",
-       "│           creation_library_language:   Python\n",
-       "│           sample_dims:                 [&#x27;chain&#x27;, &#x27;draw&#x27;]\n",
-       "│           modeling_interface:          bambi\n",
-       "│           modeling_interface_version:  0.18.0\n",
-       "├── Group: /observed_data\n",
-       "│       Dimensions:                  (__obs__: 2250, rt,response_extra_dim_0: 2)\n",
-       "│       Coordinates:\n",
-       "│         * __obs__                  (__obs__) int64 18kB 0 1 2 3 ... 2247 2248 2249\n",
-       "│         * rt,response_extra_dim_0  (rt,response_extra_dim_0) int64 16B 0 1\n",
-       "│       Data variables:\n",
-       "│           rt,response              (__obs__, rt,response_extra_dim_0) float32 18kB ...\n",
-       "│       Attributes:\n",
-       "│           created_at:                  2026-07-06T16:44:41.800372+00:00\n",
-       "│           creation_library:            ArviZ\n",
-       "│           creation_library_version:    1.2.0\n",
-       "│           creation_library_language:   Python\n",
-       "│           sample_dims:                 []\n",
-       "│           modeling_interface:          bambi\n",
-       "│           modeling_interface_version:  0.18.0\n",
-       "├── Group: /constant_data\n",
-       "│       Attributes:\n",
-       "│           created_at:                  2026-07-06T16:44:41.800438+00:00\n",
-       "│           creation_library:            ArviZ\n",
-       "│           creation_library_version:    1.2.0\n",
-       "│           creation_library_language:   Python\n",
-       "│           sample_dims:                 []\n",
-       "│           modeling_interface:          bambi\n",
-       "│           modeling_interface_version:  0.18.0\n",
-       "└── Group: /log_likelihood\n",
-       "        Dimensions:      (chain: 2, draw: 500, __obs__: 2250)\n",
-       "        Coordinates:\n",
-       "          * chain        (chain) int64 16B 0 1\n",
-       "          * draw         (draw) int64 4kB 0 1 2 3 4 5 6 ... 493 494 495 496 497 498 499\n",
-       "          * __obs__      (__obs__) int64 18kB 0 1 2 3 4 5 ... 2245 2246 2247 2248 2249\n",
-       "        Data variables:\n",
-       "            rt,response  (chain, draw, __obs__) float64 18MB -0.9003 -2.705 ... 0.4514\n",
-       "        Attributes:\n",
-       "            modeling_interface:          bambi\n",
-       "            modeling_interface_version:  0.18.0</pre><div class='xr-wrap' style='display:none'><div class='xr-header'><div class='xr-obj-type'>xarray.DataTree</div></div><ul class='xr-sections'><li class='xr-section-item'><div class='xr-children'><div class='xr-group-box'><div class='xr-group-box-vline' style='height: 100%'></div><div class='xr-group-box-hline'></div><div class='xr-group-box-contents'><input id='group-ed896a7a-7be5-49f9-a1a7-71b46d773ce6' type='checkbox' checked /><label for='group-ed896a7a-7be5-49f9-a1a7-71b46d773ce6' title='Expand/collapse group'>/posterior<span>(39)</span></label><ul class='xr-sections'><li class='xr-section-item'><input id='section-7e93e9ed-3e11-48ac-96f3-b94ef9c042f8' class='xr-section-summary-in' type='checkbox' disabled /><label for='section-7e93e9ed-3e11-48ac-96f3-b94ef9c042f8' class='xr-section-summary'>Dimensions:</label><div class='xr-section-inline-details'><ul class='xr-dim-list'><li><span class='xr-has-index'>chain</span>: 2</li><li><span class='xr-has-index'>draw</span>: 500</li><li><span class='xr-has-index'>participant_id__factor_dim</span>: 15</li><li><span class='xr-has-index'>rl_alpha_1|participant_id__factor_dim</span>: 15</li></ul></div></li><li class='xr-section-item'><input id='section-9a035421-220f-4fc8-ad59-765b6b9de187' class='xr-section-summary-in' type='checkbox' checked /><label for='section-9a035421-220f-4fc8-ad59-765b6b9de187' class='xr-section-summary' title='Expand/collapse section'>Coordinates: <span>(4)</span></label><div class='xr-section-inline-details'></div><div class='xr-section-details'><ul class='xr-var-list'><li class='xr-var-item'><div class='xr-var-name'><span class='xr-has-index'>chain</span></div><div class='xr-var-dims'>(chain)</div><div class='xr-var-dtype'>int64</div><div class='xr-var-preview xr-preview'>0 1</div><input id='attrs-c22afb34-1973-4645-a231-254eb411d8d3' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-c22afb34-1973-4645-a231-254eb411d8d3' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-2ad84b02-25ab-4246-9d4d-f104d9c3018f' class='xr-var-data-in' type='checkbox'><label for='data-2ad84b02-25ab-4246-9d4d-f104d9c3018f' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>array([0, 1])</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span class='xr-has-index'>draw</span></div><div class='xr-var-dims'>(draw)</div><div class='xr-var-dtype'>int64</div><div class='xr-var-preview xr-preview'>0 1 2 3 4 5 ... 495 496 497 498 499</div><input id='attrs-4ccf4a63-edc1-4680-a285-a10dcd6918ef' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-4ccf4a63-edc1-4680-a285-a10dcd6918ef' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-8882c9b0-f554-4f51-8cce-ad2ce95fdbf2' class='xr-var-data-in' type='checkbox'><label for='data-8882c9b0-f554-4f51-8cce-ad2ce95fdbf2' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>array([  0,   1,   2, ..., 497, 498, 499], shape=(500,))</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span class='xr-has-index'>participant_id__factor_dim</span></div><div class='xr-var-dims'>(participant_id__factor_dim)</div><div class='xr-var-dtype'>&lt;U2</div><div class='xr-var-preview xr-preview'>&#x27;0&#x27; &#x27;1&#x27; &#x27;2&#x27; &#x27;3&#x27; ... &#x27;12&#x27; &#x27;13&#x27; &#x27;14&#x27;</div><input id='attrs-355a1f16-7695-4812-9cb1-05a587d2a400' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-355a1f16-7695-4812-9cb1-05a587d2a400' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-6d08b6a1-b43e-486f-9475-d615c09e37df' class='xr-var-data-in' type='checkbox'><label for='data-6d08b6a1-b43e-486f-9475-d615c09e37df' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>array([&#x27;0&#x27;, &#x27;1&#x27;, &#x27;2&#x27;, &#x27;3&#x27;, &#x27;4&#x27;, &#x27;5&#x27;, &#x27;6&#x27;, &#x27;7&#x27;, &#x27;8&#x27;, &#x27;9&#x27;, &#x27;10&#x27;, &#x27;11&#x27;, &#x27;12&#x27;,&#x27;13&#x27;, &#x27;14&#x27;], dtype=&#x27;&lt;U2&#x27;)</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span class='xr-has-index'>rl_alpha_1|participant_id__factor_dim</span></div><div class='xr-var-dims'>(rl_alpha_1|participant_id__factor_dim)</div><div class='xr-var-dtype'>&lt;U2</div><div class='xr-var-preview xr-preview'>&#x27;0&#x27; &#x27;1&#x27; &#x27;2&#x27; &#x27;3&#x27; ... &#x27;12&#x27; &#x27;13&#x27; &#x27;14&#x27;</div><input id='attrs-fae7df19-7f83-45dc-85c1-aa9927846e8e' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-fae7df19-7f83-45dc-85c1-aa9927846e8e' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-cfa28e13-e7c5-43e5-8f47-85afff3d3b2a' class='xr-var-data-in' type='checkbox'><label for='data-cfa28e13-e7c5-43e5-8f47-85afff3d3b2a' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>array([&#x27;0&#x27;, &#x27;1&#x27;, &#x27;2&#x27;, &#x27;3&#x27;, &#x27;4&#x27;, &#x27;5&#x27;, &#x27;6&#x27;, &#x27;7&#x27;, &#x27;8&#x27;, &#x27;9&#x27;, &#x27;10&#x27;, &#x27;11&#x27;, &#x27;12&#x27;,&#x27;13&#x27;, &#x27;14&#x27;], dtype=&#x27;&lt;U2&#x27;)</pre></div></li></ul></div></li><li class='xr-section-item'><input id='section-8376bcc8-984c-4021-99c7-eade8926b30a' class='xr-section-summary-in' type='checkbox' /><label for='section-8376bcc8-984c-4021-99c7-eade8926b30a' class='xr-section-summary' title='Expand/collapse section'>Data variables: <span>(24)</span></label><div class='xr-section-inline-details'></div><div class='xr-section-details'><ul class='xr-var-list'><li class='xr-var-item'><div class='xr-var-name'><span>t_1|participant_id_offset</span></div><div class='xr-var-dims'>(chain, draw, participant_id__factor_dim)</div><div class='xr-var-dtype'>float32</div><div class='xr-var-preview xr-preview'>...</div><input id='attrs-bd3c092a-2f5b-4731-bab8-14c09f51a2d6' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-bd3c092a-2f5b-4731-bab8-14c09f51a2d6' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-a0db2567-50f7-4237-94cf-6861b7fc4e53' class='xr-var-data-in' type='checkbox'><label for='data-a0db2567-50f7-4237-94cf-6861b7fc4e53' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>Array([[[-0.16254376,  1.248806  ,  1.2049413 , ..., -0.35088256,-0.98723644,  0.19908853],[ 0.53293073, -0.06829596, -0.18799886, ..., -0.7943104 ,-0.1128315 ,  0.7426409 ],[-0.2435882 , -0.16483803,  0.27149808, ..., -1.447299  ,0.33952236,  0.4255719 ],...,[ 0.9207672 , -0.07757746,  0.8061423 , ..., -0.90687597,0.8383891 ,  1.1370381 ],[ 1.2398256 ,  0.02268366,  0.9196439 , ..., -0.76721716,0.19704394,  1.1304141 ],[-0.18791993,  1.0984106 ,  0.7326622 , ..., -0.66376764,0.39801824,  1.1725343 ]],[[ 1.0569371 ,  0.5994698 ,  1.3556336 , ..., -0.54296976,0.08904155,  0.89630216],[ 0.39083105, -0.10916877,  0.07839733, ..., -1.3447152 ,0.30408728,  0.3357651 ],[-0.02153663,  0.38149425,  0.76267046, ..., -0.57446903,0.27328557,  0.40527076],...,[ 0.34855273,  0.8202057 , -0.76883537, ..., -0.64579374,-0.68481475,  0.7377882 ],[-0.11180106,  0.09231638,  0.15455687, ..., -1.2530384 ,-0.86452   ,  1.4573283 ],[ 0.08460666,  0.7168809 ,  0.47907665, ..., -0.20483425,0.63329244,  0.5582059 ]]], dtype=float32)</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span>z_1|participant_id</span></div><div class='xr-var-dims'>(chain, draw, participant_id__factor_dim)</div><div class='xr-var-dtype'>float32</div><div class='xr-var-preview xr-preview'>...</div><input id='attrs-0e59e0c0-9cf6-4f82-96f6-f4063fbe9efa' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-0e59e0c0-9cf6-4f82-96f6-f4063fbe9efa' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-5f2f484b-9151-4404-a817-20ff18ff1dc7' class='xr-var-data-in' type='checkbox'><label for='data-5f2f484b-9151-4404-a817-20ff18ff1dc7' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>Array([[[-0.04890735, -0.01714995, -0.04024272, ...,  0.0636134 ,0.00929059, -0.01745617],[-0.05370961, -0.04869624, -0.01511765, ...,  0.08492125,0.00951756, -0.07412069],[-0.00506077, -0.03876736,  0.04241635, ...,  0.08841018,0.00340768, -0.0132202 ],...,[-0.06426691, -0.02503901,  0.0479797 , ...,  0.10935511,-0.07242245, -0.07351919],[-0.03200135,  0.00878106, -0.00114083, ...,  0.11050082,0.04304891, -0.05242905],[ 0.0011186 , -0.07922951,  0.03307959, ...,  0.11846839,-0.01468282, -0.02137253]],[[-0.07088375, -0.09605353, -0.0870923 , ...,  0.05969601,-0.04490016, -0.08674914],[-0.04792272, -0.00552623,  0.04312531, ...,  0.07512051,-0.02942253, -0.01657942],[-0.02924686, -0.0083315 , -0.03119195, ...,  0.08836354,0.01749841, -0.08144853],...,[-0.0360165 , -0.04147609,  0.02005479, ...,  0.10100625,0.01419461, -0.05741529],[-0.01624438, -0.01840974,  0.01271305, ...,  0.09400898,-0.00146088, -0.0448955 ],[-0.04253309, -0.04165547,  0.00082437, ...,  0.10597158,-0.03005156, -0.0053229 ]]], dtype=float32)</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span>z_1|participant_id_sigma</span></div><div class='xr-var-dims'>(chain, draw)</div><div class='xr-var-dtype'>float32</div><div class='xr-var-preview xr-preview'>...</div><input id='attrs-8bcddafd-faca-4b34-ac01-df6829e8c6d1' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-8bcddafd-faca-4b34-ac01-df6829e8c6d1' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-fea287b9-ee5d-480f-8306-9b027b96095c' class='xr-var-data-in' type='checkbox'><label for='data-fea287b9-ee5d-480f-8306-9b027b96095c' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>Array([[0.03293062, 0.04601797, 0.06423832, 0.05636267, 0.05796819,0.06134144, 0.0483369 , 0.04921225, 0.04833033, 0.05441251,0.04620728, 0.0479633 , 0.03452729, 0.0386274 , 0.03991828,0.08373977, 0.04224537, 0.05382941, 0.04726394, 0.07637266,0.04189361, 0.04949851, 0.04115686, 0.06337816, 0.0780177 ,0.03676307, 0.04001185, 0.05428471, 0.04247198, 0.05729344,0.07990868, 0.04465702, 0.04353601, 0.06138485, 0.04859183,0.04971318, 0.05482906, 0.0436686 , 0.07940932, 0.06704625,0.05509457, 0.03813042, 0.04843035, 0.04730067, 0.05373441,0.06428806, 0.05400744, 0.03724943, 0.0355711 , 0.05929131,0.06595455, 0.03986346, 0.03633858, 0.03539714, 0.03488162,0.03621359, 0.03857179, 0.0488404 , 0.06313634, 0.04245935,0.06361253, 0.05027619, 0.05577793, 0.05144735, 0.04209995,0.05662366, 0.06502704, 0.06575407, 0.03448814, 0.04962358,0.03656469, 0.03594694, 0.05737396, 0.04568786, 0.04100513,0.04452945, 0.0613487 , 0.06975123, 0.03873817, 0.03852537,0.08069589, 0.07135563, 0.06050534, 0.0368136 , 0.0397923 ,0.04073238, 0.04736868, 0.05320646, 0.04280367, 0.05866715,0.06502071, 0.0377905 , 0.02894649, 0.03676869, 0.05530391,0.05709023, 0.0417349 , 0.03444916, 0.02514199, 0.08811139,...0.04683939, 0.05596058, 0.05729179, 0.0554338 , 0.05941771,0.04869968, 0.0338745 , 0.04034192, 0.05438074, 0.05291946,0.06297854, 0.06450481, 0.06334021, 0.04985338, 0.05522647,0.05100204, 0.0690545 , 0.0572174 , 0.08651043, 0.05349092,0.0417087 , 0.05088945, 0.06016496, 0.03786529, 0.03345714,0.03345449, 0.05921111, 0.03846884, 0.05701494, 0.03918625,0.04820742, 0.04054002, 0.03219448, 0.03846275, 0.05605682,0.05030427, 0.04396316, 0.04900967, 0.06020732, 0.0781012 ,0.03186815, 0.03226601, 0.04602415, 0.06291063, 0.0701552 ,0.03708128, 0.03425751, 0.06385265, 0.03037233, 0.06201604,0.03082344, 0.05530528, 0.07398713, 0.04353082, 0.0665229 ,0.05099551, 0.05165873, 0.04750815, 0.03001784, 0.05733846,0.04105543, 0.0345456 , 0.03688649, 0.05914934, 0.04190239,0.05295826, 0.04912997, 0.05513356, 0.07620168, 0.0876178 ,0.06015056, 0.07111558, 0.04171923, 0.04339175, 0.0569487 ,0.03581368, 0.05344849, 0.06791448, 0.09967433, 0.02767397,0.03546734, 0.0507259 , 0.05927493, 0.04497091, 0.05266746,0.034408  , 0.04410458, 0.07722101, 0.06945789, 0.05069859,0.05948353, 0.06180137, 0.04139225, 0.05232892, 0.04465526,0.04351337, 0.03549614, 0.066316  , 0.05802132, 0.04925322]],      dtype=float32)</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span>theta_1|participant_id</span></div><div class='xr-var-dims'>(chain, draw, participant_id__factor_dim)</div><div class='xr-var-dtype'>float32</div><div class='xr-var-preview xr-preview'>...</div><input id='attrs-29b2c905-77c1-4d11-9ec3-fd592c495d65' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-29b2c905-77c1-4d11-9ec3-fd592c495d65' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-c72db8eb-a820-4c4c-a1d4-93e725c6f681' class='xr-var-data-in' type='checkbox'><label for='data-c72db8eb-a820-4c4c-a1d4-93e725c6f681' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>Array([[[ 0.03904036, -0.11790815,  0.06401705, ..., -0.00879353,0.05540285, -0.09410584],[ 0.04629304, -0.04865622,  0.17682914, ...,  0.21104687,0.06391059,  0.04829139],[ 0.01484822, -0.03594987,  0.1471707 , ..., -0.01058516,-0.02735408, -0.03571864],...,[ 0.03095307,  0.02631363,  0.08744261, ...,  0.06861527,-0.02162858,  0.00600304],[-0.16356291,  0.00899921,  0.08847178, ...,  0.00225451,-0.02677025,  0.0317673 ],[-0.00190459, -0.15430528, -0.02188865, ...,  0.0449923 ,-0.13326651, -0.19474232]],[[-0.031715  ,  0.02763416,  0.07678115, ...,  0.14180295,0.02555301, -0.11768737],[ 0.05256386,  0.01420413,  0.10572291, ...,  0.09387959,0.01137982,  0.03732558],[ 0.03932681, -0.05735949,  0.10457171, ...,  0.08859626,-0.13791011,  0.03644061],...,[ 0.00380178, -0.03943419,  0.19472426, ...,  0.17305985,0.176755  , -0.01111225],[-0.02035765, -0.04905679,  0.1092951 , ...,  0.09651964,0.00233537, -0.0166672 ],[-0.01376625, -0.01282638,  0.15795128, ...,  0.02368554,-0.02139419, -0.05027936]]], dtype=float32)</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span>rl_alpha_Intercept</span></div><div class='xr-var-dims'>(chain, draw)</div><div class='xr-var-dtype'>float32</div><div class='xr-var-preview xr-preview'>...</div><input id='attrs-08f94a55-11e1-472a-b342-8df36a5a7950' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-08f94a55-11e1-472a-b342-8df36a5a7950' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-ef43094e-1d17-4c19-a3e1-2dae52f99ace' class='xr-var-data-in' type='checkbox'><label for='data-ef43094e-1d17-4c19-a3e1-2dae52f99ace' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>Array([[0.08339877, 0.09401349, 0.07509188, 0.09578697, 0.07873082,0.09526614, 0.08151589, 0.10334619, 0.09529855, 0.0965765 ,0.10570784, 0.13104622, 0.08414888, 0.08450262, 0.09625464,0.07404919, 0.07764632, 0.08778427, 0.08418833, 0.11374198,0.07769679, 0.1092982 , 0.07088748, 0.09111337, 0.09654032,0.07911403, 0.09517269, 0.08770812, 0.09182872, 0.09086402,0.08548225, 0.09448189, 0.10215986, 0.06940646, 0.09310148,0.0808863 , 0.09139363, 0.08559296, 0.08282399, 0.07452813,0.09097233, 0.10616863, 0.10437366, 0.07244094, 0.1155548 ,0.09530596, 0.07318923, 0.07628701, 0.07741083, 0.07709368,0.08468686, 0.09793549, 0.12132968, 0.06458864, 0.06502777,0.0654593 , 0.09522212, 0.08913235, 0.10462759, 0.07165165,0.08676013, 0.11060183, 0.10208908, 0.10101665, 0.10275162,0.08869769, 0.07232448, 0.06145713, 0.13523614, 0.10813602,0.08543563, 0.08550324, 0.08954515, 0.08427811, 0.08717028,0.09416861, 0.08358215, 0.08933859, 0.08827595, 0.07722708,0.09309002, 0.08115958, 0.07766241, 0.06486364, 0.07570716,0.08249017, 0.07290205, 0.09624349, 0.10354541, 0.08968219,0.07693598, 0.09104989, 0.10908881, 0.09502507, 0.08850181,0.09173732, 0.06884485, 0.08911377, 0.08900025, 0.0943078 ,...0.08913457, 0.09797468, 0.09776965, 0.09908408, 0.07672478,0.08149447, 0.08535516, 0.08708226, 0.07207926, 0.0636085 ,0.06150515, 0.0678369 , 0.09267832, 0.08925528, 0.07749525,0.08073492, 0.09148207, 0.09980344, 0.0832417 , 0.10896682,0.05814512, 0.07773247, 0.07409981, 0.1004692 , 0.10024794,0.07546061, 0.08527389, 0.1017699 , 0.08943605, 0.08845862,0.09193476, 0.07758117, 0.08403575, 0.08605895, 0.08079629,0.0959994 , 0.08665978, 0.06647552, 0.09200864, 0.10881364,0.07949512, 0.10227446, 0.09304504, 0.08845043, 0.08209582,0.08878889, 0.08925504, 0.07939752, 0.10166555, 0.07185205,0.07894938, 0.07360014, 0.12176114, 0.07398237, 0.08149993,0.08450171, 0.10938256, 0.07868705, 0.07958932, 0.10332488,0.06881358, 0.096546  , 0.10873863, 0.07847845, 0.08950131,0.0717323 , 0.08004267, 0.09561332, 0.06436922, 0.06803087,0.0758305 , 0.06860016, 0.11300618, 0.10920673, 0.08042723,0.09296833, 0.07756389, 0.06396382, 0.07937297, 0.08948173,0.08824449, 0.09404302, 0.08269445, 0.07238156, 0.11529844,0.07867333, 0.08724512, 0.10540936, 0.07639623, 0.10326978,0.06959617, 0.11709587, 0.07723632, 0.08186674, 0.09985832,0.07534098, 0.09051776, 0.08483773, 0.11205589, 0.08084299]],      dtype=float32)</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span>t_Intercept</span></div><div class='xr-var-dims'>(chain, draw)</div><div class='xr-var-dtype'>float32</div><div class='xr-var-preview xr-preview'>...</div><input id='attrs-ca7561ba-7088-4f8b-9fed-38f2a01f60c8' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-ca7561ba-7088-4f8b-9fed-38f2a01f60c8' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-39e03ae6-c46a-402b-b79f-2f9042905de2' class='xr-var-data-in' type='checkbox'><label for='data-39e03ae6-c46a-402b-b79f-2f9042905de2' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>Array([[0.24055146, 0.26297793, 0.2532536 , 0.23840445, 0.24094853,0.23523878, 0.21558915, 0.2089466 , 0.2540757 , 0.24214192,0.24329935, 0.25389352, 0.2561597 , 0.2670954 , 0.20611659,0.22941247, 0.21832478, 0.2482502 , 0.23182677, 0.24079631,0.23417313, 0.25976056, 0.23924696, 0.24616252, 0.25357765,0.22919478, 0.238018  , 0.24479333, 0.19550686, 0.2166697 ,0.24407089, 0.24508214, 0.25077483, 0.25210315, 0.2513383 ,0.25438148, 0.2526124 , 0.24682969, 0.25132862, 0.22421965,0.2567126 , 0.23714396, 0.22491539, 0.25020593, 0.23444995,0.26475617, 0.24417414, 0.2260893 , 0.23816557, 0.26804867,0.23675486, 0.23684642, 0.2514962 , 0.24706209, 0.24630617,0.24330308, 0.22950362, 0.22494626, 0.2473373 , 0.25438562,0.24478365, 0.24592146, 0.23915552, 0.24281389, 0.25412685,0.24680224, 0.24008502, 0.23853403, 0.22448763, 0.25434992,0.24954884, 0.21304768, 0.2241637 , 0.2649934 , 0.24149682,0.22781079, 0.25881094, 0.2449496 , 0.22732167, 0.24546987,0.24153583, 0.2567594 , 0.24787281, 0.2572875 , 0.2451181 ,0.25676763, 0.24803248, 0.28868124, 0.25788411, 0.25605693,0.2315649 , 0.2470646 , 0.2536237 , 0.24883428, 0.23500144,0.22902752, 0.23350163, 0.26587963, 0.23259133, 0.2632303 ,...0.24156353, 0.27120003, 0.26436752, 0.26205516, 0.20440833,0.1920309 , 0.23435204, 0.27001998, 0.216763  , 0.22503665,0.23118334, 0.24182668, 0.25751168, 0.2640584 , 0.24351938,0.2437246 , 0.2619751 , 0.2600293 , 0.21511403, 0.2379319 ,0.21166515, 0.2637904 , 0.25045294, 0.23942979, 0.24461219,0.21561456, 0.2671636 , 0.24367891, 0.26039347, 0.2550045 ,0.24213587, 0.22422251, 0.2461963 , 0.23416668, 0.23702729,0.24228603, 0.25220492, 0.24492651, 0.29494166, 0.28645995,0.24243319, 0.2562385 , 0.24823698, 0.25666827, 0.25462657,0.22712845, 0.23597284, 0.22510938, 0.23279528, 0.25705466,0.2439006 , 0.265837  , 0.26504868, 0.23905458, 0.24194017,0.24821366, 0.24430732, 0.2370417 , 0.24817847, 0.24655333,0.23331611, 0.26128206, 0.25072417, 0.2178059 , 0.26559216,0.25837705, 0.2660197 , 0.25395617, 0.22702119, 0.21787609,0.27173585, 0.26317707, 0.24478716, 0.24289808, 0.24315375,0.2332859 , 0.23505776, 0.2522117 , 0.22550945, 0.24611606,0.24999359, 0.23373622, 0.2434961 , 0.2365476 , 0.21732822,0.23602483, 0.24755009, 0.22881651, 0.24296643, 0.25895202,0.24868758, 0.24335268, 0.22566724, 0.22591355, 0.25201544,0.24391225, 0.27974078, 0.258906  , 0.25228128, 0.24252112]],      dtype=float32)</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span>theta_1|participant_id_sigma</span></div><div class='xr-var-dims'>(chain, draw)</div><div class='xr-var-dtype'>float32</div><div class='xr-var-preview xr-preview'>...</div><input id='attrs-4e303193-75c7-4046-8a6f-50ea2ef69efa' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-4e303193-75c7-4046-8a6f-50ea2ef69efa' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-cae9c528-cf60-42df-91f1-3ac7f5a66d6c' class='xr-var-data-in' type='checkbox'><label for='data-cae9c528-cf60-42df-91f1-3ac7f5a66d6c' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>Array([[0.08211927, 0.12152683, 0.1803771 , 0.18241598, 0.14088918,0.16910364, 0.11555008, 0.13623503, 0.19081278, 0.19932702,0.10230989, 0.1238358 , 0.10034673, 0.11500672, 0.1409985 ,0.19959114, 0.09851799, 0.12654142, 0.17879263, 0.10258928,0.15170214, 0.13257839, 0.11850856, 0.10240665, 0.11564635,0.15044616, 0.08050626, 0.10901254, 0.11962322, 0.1208349 ,0.1537336 , 0.14918795, 0.12364118, 0.10158639, 0.146466  ,0.1325695 , 0.1140629 , 0.1439923 , 0.16017926, 0.13542902,0.12235952, 0.11251878, 0.12204763, 0.12603275, 0.13458014,0.10735531, 0.10201473, 0.12916133, 0.19600078, 0.09506583,0.11667212, 0.12766123, 0.11141245, 0.109277  , 0.10582446,0.11360228, 0.11107797, 0.11416397, 0.20687628, 0.11212771,0.17568605, 0.13815276, 0.1327608 , 0.12422576, 0.12124977,0.11053389, 0.16251558, 0.10900281, 0.12685512, 0.11780042,0.1392319 , 0.12108459, 0.11853812, 0.12297858, 0.14108557,0.11266113, 0.17974299, 0.13721274, 0.1470162 , 0.10841182,0.14665163, 0.14632626, 0.14215174, 0.09886037, 0.1117485 ,0.10500623, 0.07525499, 0.11729182, 0.17342564, 0.13366619,0.13069826, 0.09771247, 0.11456653, 0.13017435, 0.16579992,0.17192821, 0.14304408, 0.11457995, 0.08254893, 0.1912589 ,...0.15656061, 0.14790991, 0.12909457, 0.12767833, 0.12376496,0.08309519, 0.10277783, 0.10988571, 0.1528269 , 0.15314177,0.10102541, 0.0906235 , 0.14177918, 0.16427064, 0.10554286,0.1243011 , 0.10721506, 0.1497033 , 0.11204939, 0.11393034,0.10072634, 0.10197014, 0.08871394, 0.22475974, 0.2522714 ,0.2586742 , 0.15751475, 0.12601665, 0.14155895, 0.13566975,0.11715233, 0.13079241, 0.14470358, 0.10882183, 0.11983951,0.13947348, 0.15703808, 0.15621054, 0.16325752, 0.1937927 ,0.1173453 , 0.11115527, 0.09137659, 0.09733868, 0.11232547,0.14588174, 0.14314787, 0.14032619, 0.11171387, 0.13139394,0.1257287 , 0.15068673, 0.0968051 , 0.10750285, 0.15304685,0.15391646, 0.11217437, 0.19393766, 0.17172258, 0.16248024,0.17235255, 0.20607652, 0.22781202, 0.16123842, 0.11976234,0.12497827, 0.11943106, 0.12135968, 0.13476421, 0.11129471,0.13284476, 0.15337339, 0.09841076, 0.10474165, 0.12312964,0.1849975 , 0.17029783, 0.20441192, 0.14092831, 0.16827245,0.1878952 , 0.09610923, 0.09367634, 0.1140778 , 0.10531558,0.11141633, 0.09821808, 0.12002609, 0.12939088, 0.14248379,0.14908588, 0.25098544, 0.42481202, 0.24036352, 0.10426454,0.12972245, 0.08343657, 0.11937316, 0.12408622, 0.10021736]],      dtype=float32)</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span>z_Intercept</span></div><div class='xr-var-dims'>(chain, draw)</div><div class='xr-var-dtype'>float32</div><div class='xr-var-preview xr-preview'>...</div><input id='attrs-fc1c74a7-2dce-418d-bafd-38a1e1558791' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-fc1c74a7-2dce-418d-bafd-38a1e1558791' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-f9c51e84-8951-4c9d-a5f1-8b5815e2377e' class='xr-var-data-in' type='checkbox'><label for='data-f9c51e84-8951-4c9d-a5f1-8b5815e2377e' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>Array([[0.526144  , 0.5197164 , 0.49877524, 0.5128483 , 0.5199616 ,0.5273984 , 0.5149499 , 0.52661425, 0.51875126, 0.5196322 ,0.5249877 , 0.51051575, 0.5096878 , 0.51614934, 0.52862984,0.55143845, 0.5297025 , 0.52774733, 0.53652906, 0.49928612,0.5291426 , 0.5117379 , 0.508382  , 0.5064903 , 0.5140194 ,0.51616746, 0.52036107, 0.49629882, 0.5477669 , 0.5575556 ,0.5634936 , 0.51523143, 0.49391115, 0.5352662 , 0.53043664,0.4988695 , 0.5244085 , 0.54043454, 0.5307034 , 0.52956086,0.5191317 , 0.50727683, 0.5044513 , 0.526546  , 0.50772464,0.5337866 , 0.5149825 , 0.53599834, 0.50951564, 0.5184962 ,0.48173258, 0.5258982 , 0.52199024, 0.5076832 , 0.50737673,0.5081572 , 0.51957923, 0.53550714, 0.5193449 , 0.51291126,0.52463585, 0.5094109 , 0.49642393, 0.49964526, 0.50879383,0.5110856 , 0.5106667 , 0.5129648 , 0.53004116, 0.5317686 ,0.53614765, 0.53531355, 0.5255071 , 0.53715575, 0.49941367,0.52526486, 0.4869722 , 0.5021167 , 0.5360987 , 0.5470226 ,0.51877457, 0.52258253, 0.50529206, 0.48358038, 0.51066613,0.5105191 , 0.52598315, 0.5133706 , 0.511638  , 0.51968116,0.5166543 , 0.52556705, 0.5313136 , 0.5231781 , 0.49996728,0.51078904, 0.525364  , 0.51134974, 0.5238894 , 0.5067926 ,...0.50840676, 0.52138704, 0.5226833 , 0.52166015, 0.5086821 ,0.49422428, 0.536477  , 0.50861406, 0.49529228, 0.49279946,0.48281488, 0.47639415, 0.49711943, 0.49765575, 0.5097337 ,0.5119549 , 0.5044497 , 0.51381385, 0.4744153 , 0.49990723,0.51336867, 0.47114524, 0.49124104, 0.51129943, 0.5287415 ,0.52409273, 0.5202361 , 0.5295168 , 0.4983795 , 0.5205554 ,0.53859526, 0.52703786, 0.51884854, 0.5287825 , 0.5179695 ,0.5143067 , 0.5217661 , 0.5199087 , 0.5180999 , 0.52539974,0.51909405, 0.5102024 , 0.5383264 , 0.490336  , 0.51137406,0.5275704 , 0.51471716, 0.52197737, 0.5354939 , 0.48957148,0.5086362 , 0.52109677, 0.5129573 , 0.4747152 , 0.4945604 ,0.505206  , 0.52385646, 0.5259679 , 0.51816046, 0.51469624,0.5087705 , 0.5033715 , 0.51598275, 0.5403621 , 0.528851  ,0.5522514 , 0.5280529 , 0.52380496, 0.48980537, 0.49569607,0.46852922, 0.49607813, 0.508683  , 0.51229864, 0.4898397 ,0.4922544 , 0.5068037 , 0.50056845, 0.49892503, 0.5276567 ,0.5056169 , 0.5231473 , 0.5220771 , 0.5183487 , 0.51720387,0.5184719 , 0.52890795, 0.49787265, 0.5211264 , 0.5144414 ,0.5185539 , 0.51622826, 0.49906328, 0.503311  , 0.5320201 ,0.5422829 , 0.5072723 , 0.5163751 , 0.51380265, 0.51091975]],      dtype=float32)</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span>scaler_1|participant_id</span></div><div class='xr-var-dims'>(chain, draw, participant_id__factor_dim)</div><div class='xr-var-dtype'>float32</div><div class='xr-var-preview xr-preview'>...</div><input id='attrs-f9b543f4-4fa6-4fd4-a39f-006b2b3552c3' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-f9b543f4-4fa6-4fd4-a39f-006b2b3552c3' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-95515548-5f53-4373-8b4c-891e160ce680' class='xr-var-data-in' type='checkbox'><label for='data-95515548-5f53-4373-8b4c-891e160ce680' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>Array([[[-0.0825239 ,  0.40123263, -0.06907374, ..., -1.5370672 ,1.1734446 ,  1.2603811 ],[ 0.79703623, -0.5740658 , -0.57822454, ..., -0.3610177 ,0.4681965 ,  1.2699469 ],[-0.25244528, -0.18862614,  0.3184729 , ..., -0.7352084 ,0.10893168,  0.39052492],...,[-0.51324904, -0.07518269,  0.56839526, ..., -0.22804312,-0.00746558,  0.5815969 ],[ 0.28905326,  0.260019  , -0.05298692, ..., -0.98465025,0.88931197,  1.2218753 ],[-0.1235831 , -0.44352224, -0.43404266, ..., -0.83272105,0.2852139 ,  0.37402296]],[[-0.44946128, -0.8226944 , -0.3496793 , ...,  0.16973211,-0.5333501 ,  0.82874984],[-0.3639215 , -0.36944598, -0.2730193 , ..., -1.2798036 ,0.25307533,  1.0631496 ],[ 0.7720291 ,  0.334045  ,  0.16923442, ..., -0.7168518 ,0.5736193 ,  0.6569187 ],...,[ 0.4162023 , -0.34379676,  0.06288593, ...,  0.05693482,0.17967916,  1.1616474 ],[ 0.7447304 , -0.27530825, -0.19876017, ..., -1.4185767 ,0.96193326,  1.0973251 ],[-0.314986  , -0.4679827 , -0.32641435, ..., -1.1741107 ,0.16977578,  1.2851646 ]]], dtype=float32)</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span>z_1|participant_id_offset</span></div><div class='xr-var-dims'>(chain, draw, participant_id__factor_dim)</div><div class='xr-var-dtype'>float32</div><div class='xr-var-preview xr-preview'>...</div><input id='attrs-cb38b6a2-bcba-4f38-8b8d-2b855d433765' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-cb38b6a2-bcba-4f38-8b8d-2b855d433765' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-c16474c0-0ad7-430c-8cf9-c96fc1d8941b' class='xr-var-data-in' type='checkbox'><label for='data-c16474c0-0ad7-430c-8cf9-c96fc1d8941b' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>Array([[[-1.4851637 , -0.52079034, -1.2220457 , ...,  1.9317403 ,0.28212628, -0.5300893 ],[-1.1671442 , -1.0582004 , -0.32851616, ...,  1.8453931 ,0.2068227 , -1.61069   ],[-0.07878117, -0.6034926 ,  0.66029656, ...,  1.376284  ,0.05304748, -0.20579927],...,[-0.8572554 , -0.33399504,  0.6400006 , ...,  1.4586864 ,-0.96604216, -0.9806715 ],[-0.6952542 ,  0.19077538, -0.02478537, ...,  2.4007165 ,0.9352711 , -1.139062  ],[ 0.02140189, -1.5158762 ,  0.6329025 , ...,  2.2666228 ,-0.28092223, -0.40891466]],[[-1.2016673 , -1.6283618 , -1.4764451 , ...,  1.0120056 ,-0.76117665, -1.4706277 ],[-1.279955  , -0.14759853,  1.1518223 , ...,  2.0063734 ,-0.78583854, -0.4428152 ],[-0.5242643 , -0.1493462 , -0.55913097, ...,  1.5839599 ,0.3136676 , -1.4600048 ],...,[-0.54310423, -0.62543106,  0.30241254, ...,  1.5231054 ,0.21404496, -0.8657834 ],[-0.27997258, -0.31729266,  0.21911001, ...,  1.620249  ,-0.02517838, -0.77377594],[-0.8635596 , -0.84574103,  0.01673728, ...,  2.1515667 ,-0.6101441 , -0.10807212]]], dtype=float32)</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span>theta_Intercept</span></div><div class='xr-var-dims'>(chain, draw)</div><div class='xr-var-dtype'>float32</div><div class='xr-var-preview xr-preview'>...</div><input id='attrs-b4b50d3e-9891-4cb2-8796-f137c2d8d031' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-b4b50d3e-9891-4cb2-8796-f137c2d8d031' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-6ca319d5-d500-4bed-8d53-fae9a08b9e23' class='xr-var-data-in' type='checkbox'><label for='data-6ca319d5-d500-4bed-8d53-fae9a08b9e23' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>Array([[0.3552481 , 0.3013985 , 0.38640156, 0.39485934, 0.4241807 ,0.27968866, 0.3982103 , 0.36310825, 0.29531062, 0.28816977,0.41063103, 0.41557094, 0.3476206 , 0.37716565, 0.32535195,0.28769615, 0.35519856, 0.2807338 , 0.29763845, 0.3455775 ,0.35247454, 0.30781704, 0.36452383, 0.32925045, 0.35698494,0.33118173, 0.35844785, 0.37240994, 0.3309184 , 0.3474236 ,0.3317736 , 0.3451702 , 0.35015416, 0.32127166, 0.33950675,0.34357172, 0.3908712 , 0.41671285, 0.38066918, 0.35678363,0.27798986, 0.3167232 , 0.32373995, 0.3343333 , 0.3027319 ,0.29217482, 0.34582755, 0.37266803, 0.39958265, 0.27938566,0.35168523, 0.39125967, 0.4135827 , 0.34963933, 0.35149196,0.34795058, 0.34195045, 0.32383543, 0.3500164 , 0.3295393 ,0.34454304, 0.30968103, 0.33335406, 0.33672726, 0.3110087 ,0.34953678, 0.28678384, 0.329792  , 0.3365853 , 0.34197807,0.31862167, 0.3273689 , 0.32907483, 0.37039706, 0.38491985,0.37413234, 0.33854932, 0.4401885 , 0.29974577, 0.32999387,0.31710994, 0.3489448 , 0.3600911 , 0.30548212, 0.31424004,0.28138685, 0.3367754 , 0.33807313, 0.34767902, 0.33958143,0.3072344 , 0.35341877, 0.33900306, 0.34969282, 0.36298603,0.38011116, 0.35730678, 0.30018878, 0.29877087, 0.39705804,...0.27038473, 0.3463017 , 0.3610196 , 0.3445343 , 0.39893928,0.41351977, 0.31203595, 0.34550622, 0.34808844, 0.3465422 ,0.36089918, 0.38781625, 0.32987538, 0.3632838 , 0.29903752,0.2892682 , 0.3482942 , 0.29359967, 0.3330115 , 0.31822687,0.46334845, 0.28992015, 0.3585063 , 0.3119138 , 0.31278002,0.31511357, 0.32773635, 0.3627659 , 0.34089133, 0.2896539 ,0.34861743, 0.37389022, 0.3987324 , 0.36085644, 0.32226527,0.37213537, 0.36554986, 0.34717536, 0.3152578 , 0.3304331 ,0.35534886, 0.35803527, 0.3484059 , 0.33215842, 0.3430177 ,0.3189776 , 0.28146946, 0.3256132 , 0.34424683, 0.36734343,0.342525  , 0.27543744, 0.34415388, 0.3745911 , 0.3503444 ,0.28243268, 0.36517245, 0.373744  , 0.29281542, 0.4189245 ,0.27210662, 0.30699572, 0.3355503 , 0.46151158, 0.34956253,0.36449   , 0.34697837, 0.3593932 , 0.3780759 , 0.35771227,0.37626633, 0.36919194, 0.28822234, 0.28913057, 0.3311901 ,0.33140334, 0.3816361 , 0.34800303, 0.34237146, 0.29663122,0.27408743, 0.33744058, 0.3103174 , 0.27669287, 0.32297292,0.37522933, 0.3449095 , 0.32999355, 0.30587748, 0.3222037 ,0.29078844, 0.3200222 , 0.30559266, 0.3294694 , 0.33669087,0.29976863, 0.28980273, 0.3076237 , 0.3864198 , 0.35746783]],      dtype=float32)</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span>a_1|participant_id</span></div><div class='xr-var-dims'>(chain, draw, participant_id__factor_dim)</div><div class='xr-var-dtype'>float32</div><div class='xr-var-preview xr-preview'>...</div><input id='attrs-0e2bdb11-8a14-42a8-a78d-ddcb9e029b0c' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-0e2bdb11-8a14-42a8-a78d-ddcb9e029b0c' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-87380954-ec4f-40a4-bad5-1f3fd573ded6' class='xr-var-data-in' type='checkbox'><label for='data-87380954-ec4f-40a4-bad5-1f3fd573ded6' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>Array([[[ 0.01943887, -0.28990746,  0.01171204, ..., -0.13932145,-0.00835499,  0.07710907],[-0.1275089 , -0.21761107,  0.08389812, ..., -0.07101207,-0.0868251 ,  0.02569814],[-0.03535444, -0.18084224,  0.16897197, ..., -0.09040066,-0.17199534,  0.09721121],...,[-0.05815013, -0.09153346,  0.06713159, ..., -0.03323395,-0.05651442,  0.1586283 ],[-0.21978328, -0.18473656,  0.10907363, ..., -0.2156294 ,-0.15861636,  0.19668248],[ 0.08667648, -0.19397978,  0.05726476, ...,  0.04881148,-0.06796885,  0.06858458]],[[-0.12440771, -0.1789094 ,  0.06703445, ..., -0.04250951,-0.12179139, -0.02336721],[-0.16264842, -0.26419523,  0.02624749, ..., -0.16626051,-0.24203207,  0.07164045],[-0.04889696, -0.2470351 ,  0.01126998, ..., -0.16283962,-0.28408068,  0.13527164],...,[-0.07554574, -0.27355313,  0.13488936, ...,  0.00176212,0.0444525 ,  0.01778561],[-0.00764989, -0.15440749,  0.11120858, ...,  0.02238644,0.01993163,  0.13843983],[-0.01592279, -0.1892518 ,  0.12524533, ..., -0.17752177,-0.12549305,  0.09375707]]], dtype=float32)</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span>scaler_1|participant_id_sigma</span></div><div class='xr-var-dims'>(chain, draw)</div><div class='xr-var-dtype'>float32</div><div class='xr-var-preview xr-preview'>...</div><input id='attrs-74924bdd-b002-4c40-8fa3-30f8d0ab2b1a' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-74924bdd-b002-4c40-8fa3-30f8d0ab2b1a' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-971b944d-3732-4667-8668-3607b5059dc2' class='xr-var-data-in' type='checkbox'><label for='data-971b944d-3732-4667-8668-3607b5059dc2' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>Array([[0.93023324, 0.53897643, 0.48963413, 0.6174706 , 0.42304003,0.5708074 , 0.37226444, 0.35192603, 0.16130874, 0.17198302,0.45427436, 0.38211763, 0.31307638, 0.33817288, 0.68450034,0.43935084, 0.39574695, 0.2535635 , 0.41185957, 0.41107693,0.6193277 , 0.3018944 , 0.57050294, 0.3559234 , 0.7611498 ,0.3757919 , 0.68066686, 0.3779762 , 0.6781505 , 0.50714993,0.50305265, 0.68087393, 0.3216825 , 0.61695206, 0.53099513,0.34043896, 0.73440206, 0.8589761 , 0.7341373 , 0.43235865,0.3981601 , 0.37185007, 0.61863226, 0.5571967 , 0.61429566,0.5378428 , 0.83365613, 0.50648093, 0.5868525 , 0.5578062 ,0.37781942, 0.45011353, 0.43705773, 0.53617424, 0.5242331 ,0.5636516 , 0.43458337, 0.43336564, 0.41821423, 0.24337058,0.48256022, 0.41150826, 0.40667972, 0.34099266, 0.2272453 ,0.1555774 , 0.17183785, 0.18725619, 0.3650881 , 0.566174  ,0.7093551 , 0.7289897 , 0.5299418 , 0.43461287, 0.4221521 ,0.5605597 , 0.4666971 , 0.42776054, 0.49937215, 0.40006334,0.50154066, 0.54462254, 0.18064281, 0.5617185 , 0.435736  ,0.82433516, 0.31800646, 0.4327926 , 0.23096529, 0.2122946 ,0.35029006, 0.5293883 , 0.46532995, 0.318337  , 0.33387682,0.6727953 , 0.59383816, 0.4840388 , 0.5450409 , 0.5229958 ,...0.45131448, 0.39519584, 0.54715836, 0.5262482 , 0.54841655,0.3641958 , 0.6615294 , 0.7283164 , 0.24442026, 0.27330482,0.24368048, 0.38103712, 0.25960597, 0.25364265, 0.13504471,0.12988876, 0.02258904, 0.1619046 , 0.07368641, 0.20707026,0.18645556, 0.3783922 , 0.2903843 , 0.54537326, 0.3928014 ,0.83421654, 0.42154872, 0.77224994, 0.55056036, 0.44704348,0.37801337, 0.64827657, 0.39143664, 0.5876289 , 0.2832373 ,0.14348316, 0.41187   , 0.5086255 , 0.2908306 , 0.35871696,0.3367724 , 0.25426966, 0.6783105 , 0.8067496 , 0.6614162 ,0.2587131 , 0.41162604, 0.4913569 , 0.719808  , 0.25041497,0.3473512 , 0.4606489 , 0.51377183, 0.51382   , 0.69352555,0.6796417 , 0.55859286, 0.22908388, 0.5833066 , 0.30387306,0.48045105, 0.57576483, 0.47256032, 0.5887618 , 0.55868775,0.42192388, 0.44142726, 0.2376179 , 0.35916477, 0.23281449,0.2004923 , 0.28936702, 0.25542942, 0.21727417, 0.31955254,0.4479393 , 0.4747098 , 0.4459323 , 0.50167906, 0.4135481 ,0.55785096, 0.5914136 , 0.38401377, 0.44223163, 0.52411646,0.40437514, 0.5329592 , 0.49012432, 0.664561  , 0.6664592 ,0.2972859 , 0.37979108, 0.38298374, 0.3983879 , 0.5983083 ,0.4552628 , 0.3901076 , 0.42054075, 0.59473956, 0.584964  ]],      dtype=float32)</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span>rl_alpha_1|participant_id</span></div><div class='xr-var-dims'>(chain, draw, rl_alpha_1|participant_id__factor_dim)</div><div class='xr-var-dtype'>float32</div><div class='xr-var-preview xr-preview'>...</div><input id='attrs-9a8fadbc-4c89-4267-8f7e-2d45c6f863b0' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-9a8fadbc-4c89-4267-8f7e-2d45c6f863b0' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-6eb61b37-ed78-42b5-a124-2f5c2c735718' class='xr-var-data-in' type='checkbox'><label for='data-6eb61b37-ed78-42b5-a124-2f5c2c735718' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>Array([[[-5.16329100e-03, -4.24605189e-03,  2.73190177e-04, ...,-2.50538555e-03,  3.09800403e-03,  2.33197678e-02],[-5.00286594e-02,  4.31097932e-02,  4.75624315e-02, ...,-4.94793663e-03,  2.70157307e-02,  6.01239689e-03],[ 2.50818525e-02, -4.09861356e-02, -7.40386173e-03, ...,-3.93748730e-02, -9.46600121e-05,  4.57976274e-02],...,[ 5.76162990e-03, -1.15891444e-02,  1.32887426e-03, ...,-7.51137584e-02, -5.02668554e-03,  5.09165898e-02],[-1.18898097e-02, -2.68039177e-03, -7.73932924e-03, ...,2.65687201e-02,  2.30196565e-02,  9.86334402e-03],[-5.29594906e-03,  1.04808472e-02,  4.25094925e-02, ...,-5.70127591e-02, -1.38783245e-04,  3.77612449e-02]],[[ 5.04416227e-02,  2.27998123e-02,  1.12966541e-02, ...,-5.57260774e-02,  6.10405467e-02,  7.60243274e-03],[ 8.38791113e-03,  1.70093551e-02, -2.16812434e-04, ...,-1.79600660e-02,  3.73614915e-02,  4.05667238e-02],[-2.48084012e-02, -3.52872871e-02,  1.59401447e-02, ...,-3.15591246e-02, -4.24523978e-03,  3.92101817e-02],...,[ 3.80959478e-03,  4.93291812e-03,  1.26215760e-02, ...,1.33393705e-02,  1.84277147e-02,  7.32390163e-03],[-3.37252840e-02,  5.93623705e-03,  2.60026511e-02, ...,2.40618940e-02, -7.81781692e-03, -2.55411956e-03],[ 1.00495704e-02,  5.36588021e-03, -5.35450410e-03, ...,-3.20321275e-03, -1.86908257e-03,  1.43138533e-02]]],      dtype=float32)</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span>a_1|participant_id_sigma</span></div><div class='xr-var-dims'>(chain, draw)</div><div class='xr-var-dtype'>float32</div><div class='xr-var-preview xr-preview'>...</div><input id='attrs-0e461e45-5ac8-46ee-b436-cfbbc583c153' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-0e461e45-5ac8-46ee-b436-cfbbc583c153' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-616a1eee-4010-4f99-9799-11a8cd21d57a' class='xr-var-data-in' type='checkbox'><label for='data-616a1eee-4010-4f99-9799-11a8cd21d57a' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>Array([[0.12287576, 0.09662483, 0.14338095, 0.14673802, 0.13664   ,0.22999114, 0.10301206, 0.11855426, 0.09092144, 0.10138003,0.10498659, 0.11227494, 0.1255388 , 0.13185993, 0.11013168,0.12445198, 0.09207194, 0.10761445, 0.13255705, 0.15069905,0.11432249, 0.16310123, 0.08695915, 0.12970951, 0.13763982,0.13303363, 0.25062534, 0.1503691 , 0.11748628, 0.10968388,0.17441991, 0.10899544, 0.10813346, 0.20315702, 0.26286587,0.15803519, 0.30458358, 0.28070965, 0.17553337, 0.12195044,0.13416238, 0.11886916, 0.101634  , 0.11266264, 0.11854329,0.18767051, 0.14460924, 0.1449916 , 0.13586959, 0.12929781,0.18343388, 0.1477806 , 0.13514046, 0.10010794, 0.10222672,0.1042623 , 0.1353807 , 0.15039556, 0.14085437, 0.09051365,0.17244184, 0.09697924, 0.09182678, 0.0837497 , 0.07910538,0.08998445, 0.15976736, 0.16474438, 0.1740869 , 0.11869927,0.15232553, 0.07803038, 0.11255328, 0.1376234 , 0.0954102 ,0.15142561, 0.11004145, 0.06154089, 0.14503609, 0.19269271,0.11745164, 0.13987495, 0.07032152, 0.15304367, 0.16855025,0.14807048, 0.15629576, 0.16038686, 0.20494698, 0.19710656,0.1294842 , 0.14255112, 0.16141704, 0.1900185 , 0.12275369,0.16739573, 0.16349965, 0.18503878, 0.115765  , 0.12191172,...0.0887571 , 0.08877314, 0.08456899, 0.08927037, 0.06657247,0.17416309, 0.11919101, 0.09581611, 0.14731292, 0.15717049,0.19326864, 0.13058588, 0.10920444, 0.10451993, 0.091511  ,0.09757789, 0.13591933, 0.11021923, 0.150132  , 0.12090415,0.18181878, 0.13834326, 0.14122118, 0.11195528, 0.12452339,0.1261363 , 0.13611624, 0.14782815, 0.09947543, 0.0674378 ,0.12425192, 0.14013603, 0.13880992, 0.12132091, 0.13845706,0.10970729, 0.1206345 , 0.09802898, 0.10542335, 0.12123807,0.12335575, 0.09940276, 0.13979861, 0.15771198, 0.10680015,0.16709697, 0.13262975, 0.1394571 , 0.14496306, 0.08933911,0.10307985, 0.10311399, 0.09609317, 0.21612561, 0.09281772,0.10089961, 0.1213874 , 0.16712084, 0.21831475, 0.11489763,0.15532377, 0.23182514, 0.2071341 , 0.12394462, 0.159975  ,0.26526418, 0.19320041, 0.20735146, 0.23198847, 0.17556763,0.22233488, 0.17329888, 0.11596961, 0.11474375, 0.13108523,0.15834138, 0.18225613, 0.1506119 , 0.12564443, 0.14282878,0.13499452, 0.10199007, 0.15985468, 0.15178512, 0.10860452,0.11850967, 0.14713459, 0.13987255, 0.12623966, 0.15942936,0.18080121, 0.13728058, 0.199864  , 0.17422438, 0.12904793,0.230905  , 0.09020548, 0.13791364, 0.11916628, 0.11624974]],      dtype=float32)</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span>rl_alpha_1|participant_id_sigma</span></div><div class='xr-var-dims'>(chain, draw)</div><div class='xr-var-dtype'>float32</div><div class='xr-var-preview xr-preview'>...</div><input id='attrs-ab89d421-72e4-4c51-87a3-25faa8211464' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-ab89d421-72e4-4c51-87a3-25faa8211464' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-e7e0a205-408b-4c69-b0db-ecb5ef451620' class='xr-var-data-in' type='checkbox'><label for='data-e7e0a205-408b-4c69-b0db-ecb5ef451620' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>Array([[0.00940554, 0.03883268, 0.02661478, 0.00912448, 0.00842057,0.01755037, 0.04212552, 0.04678946, 0.05847612, 0.05390489,0.0523567 , 0.07195131, 0.06489667, 0.044988  , 0.04398653,0.03234508, 0.02148418, 0.04997126, 0.02995301, 0.0281352 ,0.0149499 , 0.0461518 , 0.00975984, 0.02854685, 0.00401689,0.03321282, 0.02677509, 0.04428593, 0.01862407, 0.02051285,0.03052881, 0.03497297, 0.02414585, 0.02175467, 0.04401139,0.02428669, 0.01608121, 0.01304104, 0.02266776, 0.02133185,0.02016877, 0.04057767, 0.03410271, 0.01724584, 0.03069218,0.02916485, 0.02951236, 0.02786648, 0.03572839, 0.01722569,0.0392731 , 0.04630522, 0.02520433, 0.02876157, 0.02639317,0.03176436, 0.03896033, 0.03176073, 0.03514628, 0.05009513,0.03831931, 0.04071671, 0.0443655 , 0.04282123, 0.06279315,0.03321663, 0.03376927, 0.04287298, 0.06327441, 0.03585186,0.01819014, 0.00175038, 0.00308709, 0.00457176, 0.0197674 ,0.01686207, 0.02311906, 0.007847  , 0.02643853, 0.0257224 ,0.01576401, 0.02653836, 0.02499437, 0.01257072, 0.0286977 ,0.02753968, 0.02598947, 0.04254506, 0.04201829, 0.04134136,0.02629305, 0.02017902, 0.01527204, 0.02218483, 0.02018187,0.02190912, 0.00905274, 0.0219541 , 0.01518545, 0.00807064,...0.02970599, 0.03530545, 0.03629231, 0.03821672, 0.05638279,0.03610415, 0.03795462, 0.02628995, 0.03551039, 0.05030757,0.05645501, 0.03898134, 0.04761216, 0.05303231, 0.0415982 ,0.04606568, 0.0371465 , 0.03890002, 0.02531735, 0.03485283,0.02735647, 0.02320158, 0.01326837, 0.03279454, 0.03579356,0.03227867, 0.02468762, 0.02128073, 0.02509222, 0.0450146 ,0.03343969, 0.0387804 , 0.02239905, 0.02755079, 0.01877542,0.01869468, 0.02125533, 0.00652387, 0.00694416, 0.01067997,0.0223225 , 0.01791857, 0.01418798, 0.00535561, 0.00193876,0.02382599, 0.00800211, 0.01576751, 0.03944627, 0.03090653,0.04281355, 0.01984565, 0.0342838 , 0.01859722, 0.03355567,0.02501275, 0.03405639, 0.06447188, 0.04856206, 0.03015348,0.01448529, 0.0147165 , 0.0213957 , 0.00601297, 0.00858463,0.02534092, 0.04260521, 0.03080205, 0.044143  , 0.04127153,0.0371001 , 0.02504443, 0.04540465, 0.04260384, 0.03283921,0.04652949, 0.02372537, 0.0291871 , 0.02632089, 0.03797549,0.02857756, 0.02980958, 0.05693008, 0.04757477, 0.03701505,0.04959139, 0.0554931 , 0.01849554, 0.01871189, 0.0358445 ,0.00886048, 0.03806823, 0.03574646, 0.01712094, 0.03184194,0.04738443, 0.03324453, 0.01677426, 0.02849868, 0.01394366]],      dtype=float32)</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span>scaler_Intercept</span></div><div class='xr-var-dims'>(chain, draw)</div><div class='xr-var-dtype'>float32</div><div class='xr-var-preview xr-preview'>...</div><input id='attrs-0a784d78-f214-4afb-b7cc-742e7e7d04b5' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-0a784d78-f214-4afb-b7cc-742e7e7d04b5' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-68779ada-4bd8-434a-995d-ec88ca074859' class='xr-var-data-in' type='checkbox'><label for='data-68779ada-4bd8-434a-995d-ec88ca074859' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>Array([[2.193212 , 2.3223338, 2.4557893, 2.1263068, 2.5347822, 2.3628328,2.585216 , 2.4896088, 2.4593484, 2.4522562, 2.653245 , 2.4607575,2.5354073, 2.5288885, 2.1660855, 2.3720837, 2.3492672, 2.4883049,2.412933 , 2.4143786, 2.4515655, 2.3885796, 2.3705683, 2.3037114,2.6063623, 2.4340212, 2.4369934, 2.5372481, 2.5522597, 2.3276312,2.7623525, 2.1705995, 2.4116564, 2.3445966, 2.3701253, 2.4739711,2.7098598, 2.8039849, 2.54195  , 2.7317383, 2.3402555, 2.3373322,2.3970368, 2.358024 , 2.4621708, 2.6371021, 2.7115352, 2.7491078,2.657533 , 2.4155176, 2.3005528, 2.3035219, 2.3313074, 2.7762668,2.7691855, 2.7620049, 2.5080202, 2.449282 , 2.572289 , 2.5294323,2.5072134, 2.4769611, 2.6351972, 2.6179752, 2.549577 , 2.5396714,2.3960524, 2.7267473, 2.4378686, 2.4535246, 2.3427734, 2.4108734,2.568988 , 2.4755347, 2.3654196, 2.4218554, 2.5762436, 2.2727122,2.4218876, 2.446512 , 2.1709456, 2.3258588, 2.267409 , 2.5442293,2.559944 , 2.2926352, 2.5557115, 2.5678766, 2.4656463, 2.4515882,2.5571318, 2.405899 , 2.408258 , 2.392525 , 2.2882621, 2.3587554,2.789832 , 2.430566 , 2.4404747, 2.3086462, 2.613297 , 2.3432071,2.5797217, 2.442743 , 1.9782766, 2.471411 , 2.6116278, 2.6585057,2.5361059, 2.829606 , 2.3828447, 2.5434346, 2.4018257, 2.4587045,2.596726 , 2.3395452, 2.5685334, 2.50679  , 2.3756518, 2.6170456,...2.4537587, 2.4241347, 2.4174852, 2.6709146, 2.681181 , 2.2501388,2.7239487, 2.4644077, 2.4978323, 2.5288048, 2.4415278, 2.5403152,2.332818 , 2.3973172, 2.5949013, 2.2546992, 2.6187756, 2.5111134,2.5470736, 2.5403495, 2.609195 , 2.5944397, 2.5160391, 2.3398032,2.4918108, 2.363462 , 2.523704 , 2.2899604, 2.600224 , 2.4730332,2.3479862, 2.4305875, 2.4590406, 2.458142 , 2.5059316, 2.1695852,2.6311011, 2.4809377, 2.3746881, 2.4595351, 2.3714538, 2.7174802,2.384775 , 2.5304391, 2.3329825, 2.8056757, 2.413707 , 2.482876 ,2.288223 , 2.4325724, 2.30845  , 2.3370287, 2.6461926, 2.6740305,2.3434563, 2.3808696, 2.411139 , 2.2115245, 2.2176645, 2.0260818,2.4707205, 2.4716005, 2.2620597, 2.4935937, 2.5783935, 2.3794756,2.508218 , 2.2663102, 2.3126652, 2.517017 , 2.3438435, 2.4197652,2.1558766, 2.5551193, 2.7100592, 2.2707567, 2.795421 , 2.3397517,2.3699565, 2.3346741, 2.4885798, 2.5673513, 2.4631174, 2.4200542,2.62266  , 2.4320939, 2.5705388, 2.5728223, 2.4538136, 2.4839234,2.6419022, 2.564102 , 2.7116797, 2.5852952, 2.613393 , 2.2120159,2.2766242, 2.236385 , 2.3663568, 2.3611667, 2.3813567, 2.61588  ,2.5922997, 2.0609207, 2.4252884, 2.0232272, 2.6006017, 2.4090652,2.7772653, 2.5291936, 2.1812282, 2.296633 , 2.622905 , 2.2304323,2.22982  , 2.648877 ]], dtype=float32)</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span>a_Intercept</span></div><div class='xr-var-dims'>(chain, draw)</div><div class='xr-var-dtype'>float32</div><div class='xr-var-preview xr-preview'>...</div><input id='attrs-f4a647bc-64f1-495c-8c20-b0b58bb2548f' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-f4a647bc-64f1-495c-8c20-b0b58bb2548f' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-9ffaa54e-a321-4bfa-8eb7-64859ff5e0c6' class='xr-var-data-in' type='checkbox'><label for='data-9ffaa54e-a321-4bfa-8eb7-64859ff5e0c6' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>Array([[1.183458 , 1.2040536, 1.2006937, 1.1913921, 1.1959715, 1.1997964,1.2661519, 1.263392 , 1.17888  , 1.1932894, 1.2279503, 1.186108 ,1.1836196, 1.1794388, 1.1569911, 1.179696 , 1.2284083, 1.1699687,1.2165946, 1.2552807, 1.1964808, 1.1697224, 1.2115755, 1.19963  ,1.2173392, 1.1607764, 1.1549779, 1.2452866, 1.1552234, 1.1692606,1.1601253, 1.1995425, 1.1710659, 1.0843108, 1.1626683, 1.1051335,1.0803998, 1.1146191, 1.0824622, 1.1701407, 1.1336317, 1.2185988,1.2211105, 1.1660733, 1.1436782, 1.0951169, 1.1229011, 1.2392523,1.265769 , 1.1099052, 1.2202942, 1.1771287, 1.1763222, 1.1604654,1.1583316, 1.1584963, 1.166282 , 1.136948 , 1.1918981, 1.2105201,1.1908375, 1.1451422, 1.1565877, 1.1594745, 1.0941237, 1.2040765,1.1485051, 1.1842045, 1.1812524, 1.1906285, 1.1786603, 1.189068 ,1.1447725, 1.1089085, 1.1738164, 1.2343901, 1.238113 , 1.2753887,1.2083268, 1.1916978, 1.1925516, 1.2290684, 1.1780115, 1.1818844,1.1331463, 1.0870241, 1.1581247, 1.1074432, 1.1709328, 1.1904678,1.2263632, 1.1653227, 1.149176 , 1.1321964, 1.2279195, 1.2548943,1.0933236, 1.1668246, 1.174719 , 1.2199731, 1.1803108, 1.2457881,1.1864722, 1.1435558, 1.1326556, 1.2230551, 1.1896636, 1.1722233,1.1661587, 1.2021544, 1.1296724, 1.2510462, 1.1685284, 1.1731735,1.1779507, 1.2159293, 1.2781588, 1.1163732, 1.1456234, 1.0729984,...1.1753073, 1.1875433, 1.188452 , 1.1749985, 1.1734955, 1.2139442,1.2014905, 1.2002336, 1.1503592, 1.1610447, 1.2727231, 1.2096087,1.1636516, 1.1928722, 1.1418312, 1.259374 , 1.2517582, 1.2040211,1.2206504, 1.2178125, 1.1610733, 1.210534 , 1.1140188, 1.1243455,1.1515229, 1.171654 , 1.1502126, 1.1596718, 1.2183942, 1.1880552,1.1978918, 1.1708779, 1.1789646, 1.1387687, 1.2297926, 1.111624 ,1.3090267, 1.1596415, 1.2302604, 1.1724211, 1.1838446, 1.2299714,1.1306881, 1.2430613, 1.1833673, 1.1513002, 1.240965 , 1.2695524,1.1875305, 1.1712849, 1.160131 , 1.150634 , 1.2034178, 1.2018727,1.1682112, 1.1597188, 1.221483 , 1.1987331, 1.2024763, 1.1283069,1.1626377, 1.2242175, 1.1756959, 1.1618196, 1.1358573, 1.1767358,1.2336782, 1.1559314, 1.2175348, 1.1879745, 1.1681037, 1.1214364,1.1392041, 1.2878597, 1.2338924, 1.2681183, 1.1829672, 1.1870852,1.2026428, 1.2151827, 1.1957386, 1.2343966, 1.3209456, 1.3025799,1.1053115, 1.1293685, 1.1712866, 1.1530279, 1.1373143, 1.1379576,1.2002264, 1.1758096, 1.3317883, 1.2050427, 1.207042 , 1.1068281,1.1596934, 1.1756935, 1.2186834, 1.1186928, 1.2440548, 1.1746683,1.1362875, 1.171357 , 1.1387507, 1.1240953, 1.2251025, 1.2199557,1.2569194, 1.2373954, 1.1198025, 1.1407133, 1.0911114, 1.1848891,1.1639472, 1.1935548]], dtype=float32)</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span>theta_1|participant_id_offset</span></div><div class='xr-var-dims'>(chain, draw, participant_id__factor_dim)</div><div class='xr-var-dtype'>float32</div><div class='xr-var-preview xr-preview'>...</div><input id='attrs-4efdf025-dd8b-4df2-9514-a42568f55223' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-4efdf025-dd8b-4df2-9514-a42568f55223' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-87315af7-b5b3-4532-9f92-8c52834c33c0' class='xr-var-data-in' type='checkbox'><label for='data-87315af7-b5b3-4532-9f92-8c52834c33c0' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>Array([[[ 0.4754104 , -1.4358158 ,  0.7795619 , ..., -0.10708248,0.6746631 , -1.1459653 ],[ 0.38092852, -0.40037432,  1.4550626 , ...,  1.7366278 ,0.52589697,  0.39737228],[ 0.08231766, -0.19930397,  0.8159057 , ..., -0.05868349,-0.15164942, -0.19802205],...,[ 0.22593786,  0.19207291,  0.63827586, ...,  0.5008482 ,-0.15787496,  0.04381843],[-1.2154436 ,  0.06687358,  0.6574379 , ...,  0.01675334,-0.19893102,  0.23606433],[-0.01110104, -0.8993817 , -0.12757988, ...,  0.2622415 ,-0.77675545, -1.1350726 ]],[[-0.2563348 ,  0.22335169,  0.6205796 , ...,  1.146115  ,0.2065309 , -0.951202  ],[ 0.47843271,  0.12928507,  0.96228284, ...,  0.8544857 ,0.10357831,  0.33973488],[ 0.26521483, -0.3868249 ,  0.70521796, ...,  0.5974816 ,-0.93004775,  0.24575068],...,[ 0.03184786, -0.33034387,  1.6312232 , ...,  1.4497384 ,1.480693  , -0.09308832],[-0.16406052, -0.3953444 ,  0.8807997 , ...,  0.77784336,0.01882057, -0.1343195 ],[-0.13736394, -0.12798563,  1.576087  , ...,  0.2363417 ,-0.21347792, -0.5017031 ]]], dtype=float32)</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span>a_1|participant_id_offset</span></div><div class='xr-var-dims'>(chain, draw, participant_id__factor_dim)</div><div class='xr-var-dtype'>float32</div><div class='xr-var-preview xr-preview'>...</div><input id='attrs-7723662d-e4f3-43e9-9d77-9670a3043d13' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-7723662d-e4f3-43e9-9d77-9670a3043d13' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-babb70fb-c009-470f-be62-744481b1bbe7' class='xr-var-data-in' type='checkbox'><label for='data-babb70fb-c009-470f-be62-744481b1bbe7' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>Array([[[ 0.15819941, -2.3593543 ,  0.09531614, ..., -1.13384   ,-0.06799541,  0.62753683],[-1.3196286 , -2.2521238 ,  0.8682874 , ..., -0.7349257 ,-0.8985796 ,  0.2659579 ],[-0.24657696, -1.261271  ,  1.1784827 , ..., -0.6304928 ,-1.199569  ,  0.6779925 ],...,[-0.8317777 , -1.3092917 ,  0.9602481 , ..., -0.47537738,-0.80838054,  2.2690141 ],[-1.4759321 , -1.2405795 ,  0.73247284, ..., -1.4480371 ,-1.065172  ,  1.3208011 ],[ 0.7824508 , -1.7511053 ,  0.51694363, ...,  0.4406337 ,-0.61357224,  0.61913055]],[[-1.2573795 , -1.8082242 ,  0.6775122 , ..., -0.4296405 ,-1.2309365 , -0.23617072],[-1.270388  , -2.0635333 ,  0.20500964, ..., -1.2986007 ,-1.890425  ,  0.5595576 ],[-0.2599089 , -1.3131006 ,  0.05990489, ..., -0.86556447,-1.5100142 ,  0.7190285 ],...,[-0.5477757 , -1.9835103 ,  0.97807115, ...,  0.01277697,0.32232127,  0.12896195],[-0.0641951 , -1.2957313 ,  0.9332218 , ...,  0.1878588 ,0.16725893,  1.1617366 ],[-0.13697055, -1.6279761 ,  1.0773816 , ..., -1.5270723 ,-1.0795125 ,  0.80651426]]], dtype=float32)</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span>t_1|participant_id_sigma</span></div><div class='xr-var-dims'>(chain, draw)</div><div class='xr-var-dtype'>float32</div><div class='xr-var-preview xr-preview'>...</div><input id='attrs-60beb7eb-3112-409b-b781-a6c1d12e70aa' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-60beb7eb-3112-409b-b781-a6c1d12e70aa' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-6b1d5d32-a44d-478b-8fad-4c1196667699' class='xr-var-data-in' type='checkbox'><label for='data-6b1d5d32-a44d-478b-8fad-4c1196667699' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>Array([[0.03596601, 0.061406  , 0.03232551, 0.05704036, 0.0538063 ,0.04015049, 0.06206642, 0.07298196, 0.03447532, 0.04101518,0.0651294 , 0.04315342, 0.03863884, 0.04308423, 0.06590069,0.05615256, 0.04978955, 0.0417234 , 0.05189463, 0.04487877,0.04884426, 0.04087523, 0.07246603, 0.09584021, 0.06563202,0.0655999 , 0.06519988, 0.05370586, 0.06297199, 0.07050086,0.04165006, 0.04998374, 0.05530325, 0.03786358, 0.04561129,0.05646497, 0.06380224, 0.05479883, 0.0389541 , 0.05086587,0.04642481, 0.06137003, 0.06323136, 0.04728256, 0.05166631,0.03796814, 0.06630591, 0.05772693, 0.03851543, 0.05034225,0.09111027, 0.04110085, 0.05752716, 0.03379855, 0.03363495,0.03168694, 0.03984224, 0.03728975, 0.03958841, 0.03806417,0.05579345, 0.08219817, 0.0805493 , 0.07629279, 0.05414701,0.05797147, 0.09513626, 0.05022252, 0.04226573, 0.06349651,0.04750232, 0.05642273, 0.04109301, 0.05196493, 0.05513271,0.04334728, 0.03943839, 0.0408367 , 0.0524368 , 0.04853034,0.05494947, 0.0280705 , 0.07680098, 0.03051772, 0.0353305 ,0.08286601, 0.09630099, 0.0495839 , 0.08849209, 0.07979347,0.05963638, 0.05443042, 0.05265136, 0.04767279, 0.04902618,0.04946322, 0.03729624, 0.04741851, 0.0588044 , 0.0533393 ,...0.07266153, 0.0594317 , 0.0516734 , 0.05471806, 0.07383894,0.06030089, 0.08472469, 0.07645403, 0.04272125, 0.05032319,0.04732476, 0.06088003, 0.04858118, 0.0499448 , 0.04881439,0.04081423, 0.04446749, 0.08253112, 0.0508521 , 0.07730588,0.09139681, 0.03994676, 0.06678585, 0.04035666, 0.04472168,0.04677707, 0.02586557, 0.04340402, 0.04097631, 0.03974358,0.04098063, 0.04278688, 0.03652378, 0.04187592, 0.05723174,0.06526116, 0.04232044, 0.05752632, 0.05669267, 0.05052977,0.04962224, 0.04784748, 0.05280365, 0.06523649, 0.05897284,0.05076862, 0.0377617 , 0.0564557 , 0.04227414, 0.05213367,0.04863873, 0.06336666, 0.05225439, 0.05135005, 0.05636199,0.03718892, 0.05788331, 0.04527847, 0.03699484, 0.07857753,0.05156613, 0.05662766, 0.05176786, 0.03919731, 0.05188935,0.06421851, 0.04258887, 0.06410792, 0.03669105, 0.03306809,0.06609763, 0.08959222, 0.09952973, 0.09007412, 0.05369266,0.05426518, 0.04209291, 0.04803862, 0.04155161, 0.0546381 ,0.04567464, 0.05625111, 0.07281146, 0.05980903, 0.05719961,0.0342018 , 0.03719479, 0.04336066, 0.05329747, 0.04914393,0.03809091, 0.06890231, 0.04281218, 0.06666446, 0.03814296,0.032604  , 0.0623916 , 0.06291953, 0.04046745, 0.0610705 ]],      dtype=float32)</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span>t_1|participant_id</span></div><div class='xr-var-dims'>(chain, draw, participant_id__factor_dim)</div><div class='xr-var-dtype'>float32</div><div class='xr-var-preview xr-preview'>...</div><input id='attrs-23d71819-8a57-4d8e-abd5-4625d2ad0cc8' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-23d71819-8a57-4d8e-abd5-4625d2ad0cc8' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-4a799f65-d122-4c30-bf39-8cb456bc2270' class='xr-var-data-in' type='checkbox'><label for='data-4a799f65-d122-4c30-bf39-8cb456bc2270' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>Array([[[-0.00584605,  0.04491457,  0.04333693, ..., -0.01261985,-0.03550696,  0.00716042],[ 0.03272514, -0.00419378, -0.01154426, ..., -0.04877542,-0.00692853,  0.04560261],[-0.00787411, -0.00532847,  0.00877631, ..., -0.04678468,0.01097523,  0.01375683],...,[ 0.04970784, -0.00418804,  0.04351979, ..., -0.04895792,0.04526064,  0.06138328],[ 0.05499478,  0.00100618,  0.04079252, ..., -0.03403135,0.00874025,  0.05014163],[-0.0118642 ,  0.0693474 ,  0.04625613, ..., -0.04190652,0.02512861,  0.07402716]],[[ 0.0606204 ,  0.03438246,  0.07775207, ..., -0.03114191,0.00510696,  0.05140721],[ 0.02494527, -0.00696783,  0.00500381, ..., -0.08582811,0.01940875,  0.02143062],[-0.00112169,  0.01986936,  0.03972216, ..., -0.02992007,0.01423353,  0.02110771],...,[ 0.02193077,  0.05160695, -0.04837476, ..., -0.04063304,-0.04308822,  0.04642129],[-0.0045243 ,  0.00373581,  0.00625452, ..., -0.05070727,-0.03498492,  0.05897436],[ 0.00516697,  0.04378028,  0.02925745, ..., -0.01250933,0.03867549,  0.03408992]]], dtype=float32)</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span>scaler_1|participant_id_offset</span></div><div class='xr-var-dims'>(chain, draw, participant_id__factor_dim)</div><div class='xr-var-dtype'>float32</div><div class='xr-var-preview xr-preview'>...</div><input id='attrs-d3135724-52b7-4c3f-81da-5fa1de5b361d' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-d3135724-52b7-4c3f-81da-5fa1de5b361d' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-5ec8468f-ed85-4917-8d86-ad42eaccffc9' class='xr-var-data-in' type='checkbox'><label for='data-5ec8468f-ed85-4917-8d86-ad42eaccffc9' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>Array([[[-0.08871312,  0.43132475, -0.07425422, ..., -1.652346  ,1.2614521 ,  1.3549087 ],[ 1.4787961 , -1.0651038 , -1.0728197 , ..., -0.66982096,0.86867714,  2.3562198 ],[-0.5155794 , -0.38523895,  0.6504303 , ..., -1.5015465 ,0.22247566,  0.7975852 ],...,[-1.0129361 , -0.14837877,  1.1217713 , ..., -0.4500605 ,-0.0147339 ,  1.1478258 ],[ 0.603351  ,  0.5427468 , -0.11060146, ..., -2.055295  ,1.856292  ,  2.5504632 ],[-0.1714746 , -0.61539805, -0.6022449 , ..., -1.155421  ,0.3957413 ,  0.5189661 ]],[[-0.8070357 , -1.477199  , -0.6278709 , ...,  0.30476457,-0.9576633 ,  1.4880719 ],[-0.68563205, -0.6960402 , -0.51437134, ..., -2.4111638 ,0.47679666,  2.0029852 ],[ 1.0821705 ,  0.46823838,  0.23721969, ..., -1.0048273 ,0.8040551 ,  0.92081773],...,[ 0.9896837 , -0.8175112 ,  0.14953586, ...,  0.13538478,0.42725742,  2.762271  ],[ 1.2521958 , -0.46290556, -0.33419698, ..., -2.3852067 ,1.6174026 ,  1.8450514 ],[-0.53847075, -0.8000197 , -0.5580076 , ..., -2.0071504 ,0.2902329 ,  2.196998  ]]], dtype=float32)</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span>rl_alpha_1|participant_id_offset</span></div><div class='xr-var-dims'>(chain, draw, rl_alpha_1|participant_id__factor_dim)</div><div class='xr-var-dtype'>float32</div><div class='xr-var-preview xr-preview'>...</div><input id='attrs-e39ef35f-5534-47ed-b220-21de1f735ef1' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-e39ef35f-5534-47ed-b220-21de1f735ef1' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-25ffab21-2922-4bc0-a857-b938f320b391' class='xr-var-data-in' type='checkbox'><label for='data-25ffab21-2922-4bc0-a857-b938f320b391' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>Array([[[-0.5489629 , -0.4514417 ,  0.02904567, ..., -0.26637346,0.32938087,  2.4793658 ],[-1.2883135 ,  1.1101422 ,  1.2248044 , ..., -0.12741683,0.6956958 ,  0.1548283 ],[ 0.94240326, -1.5399766 , -0.2781861 , ..., -1.4794365 ,-0.00355667,  1.7207593 ],...,[ 0.17792071, -0.35787594,  0.041036  , ..., -2.3195333 ,-0.15522543,  1.5723182 ],[-0.41413367, -0.09336066, -0.26956838, ...,  0.9254144 ,0.80179703,  0.34354988],[-0.16741015,  0.33130985,  1.3437668 , ..., -1.8022293 ,-0.00438707,  1.19367   ]],[[ 1.3256326 ,  0.5991911 ,  0.29688206, ..., -1.4645108 ,1.604178  ,  0.19979596],[ 0.35778934,  0.7255401 , -0.00924821, ..., -0.7660931 ,1.5936677 ,  1.730388  ],[-1.2647667 , -1.7989948 ,  0.8126507 , ..., -1.6089278 ,-0.21642822,  1.9989895 ],...,[ 0.22710957,  0.29407665,  0.7524372 , ...,  0.7952286 ,1.098571  ,  0.4366155 ],[-1.1833979 ,  0.20829864,  0.9124158 , ...,  0.84431595,-0.27432203, -0.08962236],[ 0.72072685,  0.3848258 , -0.38400993, ..., -0.22972539,-0.13404533,  1.0265492 ]]], dtype=float32)</pre></div></li></ul></div></li><li class='xr-section-item'><input id='section-8331f5fe-be10-40aa-b5e0-31578ada9284' class='xr-section-summary-in' type='checkbox' /><label for='section-8331f5fe-be10-40aa-b5e0-31578ada9284' class='xr-section-summary' title='Expand/collapse section'>Attributes: <span>(11)</span></label><div class='xr-section-inline-details'></div><div class='xr-section-details'><dl class='xr-attrs'><dt><span>created_at :</span></dt><dd>2026-07-06T16:44:41.787695+00:00</dd><dt><span>creation_library :</span></dt><dd>ArviZ</dd><dt><span>creation_library_version :</span></dt><dd>1.2.0</dd><dt><span>creation_library_language :</span></dt><dd>Python</dd><dt><span>sample_dims :</span></dt><dd>[&#x27;chain&#x27;, &#x27;draw&#x27;]</dd><dt><span>inference_library :</span></dt><dd>numpyro</dd><dt><span>inference_library_version :</span></dt><dd>0.21.0</dd><dt><span>sampling_time :</span></dt><dd>545.10303</dd><dt><span>tuning_steps :</span></dt><dd>1000</dd><dt><span>modeling_interface :</span></dt><dd>bambi</dd><dt><span>modeling_interface_version :</span></dt><dd>0.18.0</dd></dl></div></li></ul></div></div><div class='xr-group-box'><div class='xr-group-box-vline' style='height: 100%'></div><div class='xr-group-box-hline'></div><div class='xr-group-box-contents'><input id='group-1451a15e-a091-4bf4-9064-b190ba9f911f' type='checkbox' checked /><label for='group-1451a15e-a091-4bf4-9064-b190ba9f911f' title='Expand/collapse group'>/sample_stats<span>(16)</span></label><ul class='xr-sections'><li class='xr-section-item'><input id='section-1d244b01-c143-49a8-a506-e0c07d7e54d5' class='xr-section-summary-in' type='checkbox' disabled /><label for='section-1d244b01-c143-49a8-a506-e0c07d7e54d5' class='xr-section-summary'>Dimensions:</label><div class='xr-section-inline-details'><ul class='xr-dim-list'><li><span class='xr-has-index'>chain</span>: 2</li><li><span class='xr-has-index'>draw</span>: 500</li></ul></div></li><li class='xr-section-item'><input id='section-14bc6040-e9ed-46a5-b304-d4a7db91c6d7' class='xr-section-summary-in' type='checkbox' checked /><label for='section-14bc6040-e9ed-46a5-b304-d4a7db91c6d7' class='xr-section-summary' title='Expand/collapse section'>Coordinates: <span>(2)</span></label><div class='xr-section-inline-details'></div><div class='xr-section-details'><ul class='xr-var-list'><li class='xr-var-item'><div class='xr-var-name'><span class='xr-has-index'>chain</span></div><div class='xr-var-dims'>(chain)</div><div class='xr-var-dtype'>int64</div><div class='xr-var-preview xr-preview'>0 1</div><input id='attrs-6e5cece5-e32d-4e7e-b670-baa9c3783cc7' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-6e5cece5-e32d-4e7e-b670-baa9c3783cc7' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-4f4bd12f-2a16-49f0-b05f-4b19cbac63bd' class='xr-var-data-in' type='checkbox'><label for='data-4f4bd12f-2a16-49f0-b05f-4b19cbac63bd' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>array([0, 1])</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span class='xr-has-index'>draw</span></div><div class='xr-var-dims'>(draw)</div><div class='xr-var-dtype'>int64</div><div class='xr-var-preview xr-preview'>0 1 2 3 4 5 ... 495 496 497 498 499</div><input id='attrs-233cae0b-35f5-455f-9a0f-d2c743e33584' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-233cae0b-35f5-455f-9a0f-d2c743e33584' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-6dd8233e-8b36-4cae-98bf-65f265fe82d0' class='xr-var-data-in' type='checkbox'><label for='data-6dd8233e-8b36-4cae-98bf-65f265fe82d0' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>array([  0,   1,   2, ..., 497, 498, 499], shape=(500,))</pre></div></li></ul></div></li><li class='xr-section-item'><input id='section-d6d6ff10-5518-4f65-b762-3b57bb2f65b7' class='xr-section-summary-in' type='checkbox' checked /><label for='section-d6d6ff10-5518-4f65-b762-3b57bb2f65b7' class='xr-section-summary' title='Expand/collapse section'>Data variables: <span>(7)</span></label><div class='xr-section-inline-details'></div><div class='xr-section-details'><ul class='xr-var-list'><li class='xr-var-item'><div class='xr-var-name'><span>acceptance_rate</span></div><div class='xr-var-dims'>(chain, draw)</div><div class='xr-var-dtype'>float32</div><div class='xr-var-preview xr-preview'>...</div><input id='attrs-1c72d3fc-c58d-4fa1-a4f8-c05ecbac8dd2' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-1c72d3fc-c58d-4fa1-a4f8-c05ecbac8dd2' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-223d63cb-3312-4714-b396-dfaa021a2ddc' class='xr-var-data-in' type='checkbox'><label for='data-223d63cb-3312-4714-b396-dfaa021a2ddc' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>Array([[0.97169363, 0.9880628 , 0.97164434, 0.9873408 , 0.91533816,0.96845293, 0.9626552 , 0.84128755, 0.929423  , 0.92346174,0.9868916 , 0.6420186 , 0.78590107, 0.56544447, 0.98704743,1.        , 0.97221404, 0.99523383, 0.96546507, 0.89959645,0.9300526 , 0.96619076, 0.5473487 , 0.9123282 , 0.8207011 ,0.9353398 , 0.9464746 , 0.90869904, 0.9685102 , 0.9666552 ,0.9820849 , 0.9309095 , 0.98522615, 0.9551941 , 0.9616885 ,0.7406718 , 0.99569625, 0.8977984 , 0.99834394, 0.5937008 ,0.9246183 , 0.9987386 , 0.9442148 , 0.8147475 , 0.88703674,0.98979366, 0.80543447, 0.93489707, 0.37167093, 0.7460009 ,0.94094014, 0.96179056, 0.99897635, 0.9802165 , 0.16962905,0.9736167 , 0.72783476, 1.        , 0.9972822 , 0.9859711 ,0.99151343, 0.98211825, 0.41465887, 0.07547581, 0.65181786,0.695491  , 0.98109657, 0.9835666 , 0.9385243 , 0.9719815 ,0.9290828 , 0.9167524 , 0.98369247, 0.94623184, 0.9508186 ,0.945351  , 0.9998319 , 0.92138374, 0.98171437, 0.9899889 ,0.92491126, 0.93999887, 0.9450985 , 0.98274887, 0.95808136,0.93212104, 0.9091506 , 0.98837835, 0.9873375 , 0.9341547 ,0.8635536 , 0.9394247 , 0.82323855, 0.9472887 , 0.99380904,0.9483032 , 0.9985422 , 0.9932333 , 0.9654208 , 0.9778529 ,...0.9096541 , 0.87522364, 0.9990538 , 0.9586893 , 0.9975242 ,0.94914186, 0.9971848 , 0.77027756, 0.957925  , 0.8920577 ,0.9833379 , 0.9721443 , 0.9836475 , 0.9925753 , 0.90919715,0.48149034, 0.9791743 , 0.9623135 , 0.9850539 , 0.90311044,0.9370831 , 0.92997617, 0.9648312 , 0.98540753, 0.93435127,0.9267238 , 0.736499  , 0.99717253, 0.9860583 , 0.95654804,0.94021755, 0.9980951 , 0.9484232 , 0.93542784, 0.997888  ,0.9770081 , 0.9369275 , 0.999731  , 0.99122596, 0.9887167 ,0.9486631 , 0.9746928 , 0.9811768 , 0.9927758 , 0.9996024 ,0.9914495 , 0.9367987 , 0.9867442 , 0.9522088 , 0.9545539 ,0.9792646 , 0.9945778 , 0.9671377 , 0.7720476 , 0.998342  ,0.95418096, 0.979838  , 0.93127465, 0.96172816, 0.9700763 ,0.9289468 , 0.93209404, 0.9743219 , 0.9925998 , 0.8773728 ,0.9918876 , 0.70234233, 0.9152298 , 0.96861666, 0.86027634,0.6116631 , 0.28927878, 0.95834464, 0.93972284, 0.90979755,0.9649892 , 0.52240187, 0.94394225, 0.99969965, 0.98426235,0.951257  , 0.9861354 , 0.9935202 , 0.9456914 , 0.99785274,0.9883302 , 0.9921799 , 0.94356865, 0.9767599 , 0.8985039 ,0.9888224 , 0.99989945, 0.9974184 , 0.5692893 , 0.6430561 ,0.986216  , 0.8644734 , 0.991267  , 0.969837  , 0.95106584]],      dtype=float32)</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span>step_size</span></div><div class='xr-var-dims'>(chain, draw)</div><div class='xr-var-dtype'>float32</div><div class='xr-var-preview xr-preview'>...</div><input id='attrs-cd5870ec-f546-4d5d-82fd-ead9ed984ac2' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-cd5870ec-f546-4d5d-82fd-ead9ed984ac2' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-f144cd92-761a-41b5-9cab-41c01febfe60' class='xr-var-data-in' type='checkbox'><label for='data-f144cd92-761a-41b5-9cab-41c01febfe60' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>Array([[0.07706155, 0.07706155, 0.07706155, 0.07706155, 0.07706155,0.07706155, 0.07706155, 0.07706155, 0.07706155, 0.07706155,0.07706155, 0.07706155, 0.07706155, 0.07706155, 0.07706155,0.07706155, 0.07706155, 0.07706155, 0.07706155, 0.07706155,0.07706155, 0.07706155, 0.07706155, 0.07706155, 0.07706155,0.07706155, 0.07706155, 0.07706155, 0.07706155, 0.07706155,0.07706155, 0.07706155, 0.07706155, 0.07706155, 0.07706155,0.07706155, 0.07706155, 0.07706155, 0.07706155, 0.07706155,0.07706155, 0.07706155, 0.07706155, 0.07706155, 0.07706155,0.07706155, 0.07706155, 0.07706155, 0.07706155, 0.07706155,0.07706155, 0.07706155, 0.07706155, 0.07706155, 0.07706155,0.07706155, 0.07706155, 0.07706155, 0.07706155, 0.07706155,0.07706155, 0.07706155, 0.07706155, 0.07706155, 0.07706155,0.07706155, 0.07706155, 0.07706155, 0.07706155, 0.07706155,0.07706155, 0.07706155, 0.07706155, 0.07706155, 0.07706155,0.07706155, 0.07706155, 0.07706155, 0.07706155, 0.07706155,0.07706155, 0.07706155, 0.07706155, 0.07706155, 0.07706155,0.07706155, 0.07706155, 0.07706155, 0.07706155, 0.07706155,0.07706155, 0.07706155, 0.07706155, 0.07706155, 0.07706155,0.07706155, 0.07706155, 0.07706155, 0.07706155, 0.07706155,...0.07169146, 0.07169146, 0.07169146, 0.07169146, 0.07169146,0.07169146, 0.07169146, 0.07169146, 0.07169146, 0.07169146,0.07169146, 0.07169146, 0.07169146, 0.07169146, 0.07169146,0.07169146, 0.07169146, 0.07169146, 0.07169146, 0.07169146,0.07169146, 0.07169146, 0.07169146, 0.07169146, 0.07169146,0.07169146, 0.07169146, 0.07169146, 0.07169146, 0.07169146,0.07169146, 0.07169146, 0.07169146, 0.07169146, 0.07169146,0.07169146, 0.07169146, 0.07169146, 0.07169146, 0.07169146,0.07169146, 0.07169146, 0.07169146, 0.07169146, 0.07169146,0.07169146, 0.07169146, 0.07169146, 0.07169146, 0.07169146,0.07169146, 0.07169146, 0.07169146, 0.07169146, 0.07169146,0.07169146, 0.07169146, 0.07169146, 0.07169146, 0.07169146,0.07169146, 0.07169146, 0.07169146, 0.07169146, 0.07169146,0.07169146, 0.07169146, 0.07169146, 0.07169146, 0.07169146,0.07169146, 0.07169146, 0.07169146, 0.07169146, 0.07169146,0.07169146, 0.07169146, 0.07169146, 0.07169146, 0.07169146,0.07169146, 0.07169146, 0.07169146, 0.07169146, 0.07169146,0.07169146, 0.07169146, 0.07169146, 0.07169146, 0.07169146,0.07169146, 0.07169146, 0.07169146, 0.07169146, 0.07169146,0.07169146, 0.07169146, 0.07169146, 0.07169146, 0.07169146]],      dtype=float32)</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span>diverging</span></div><div class='xr-var-dims'>(chain, draw)</div><div class='xr-var-dtype'>bool</div><div class='xr-var-preview xr-preview'>...</div><input id='attrs-a295f748-bc7d-4a16-959b-20c637cc6325' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-a295f748-bc7d-4a16-959b-20c637cc6325' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-d06e097f-4923-4dcd-8104-7d4b24ad81ff' class='xr-var-data-in' type='checkbox'><label for='data-d06e097f-4923-4dcd-8104-7d4b24ad81ff' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>Array([[False, False, False, False, False, False, False, False, False,False, False, False,  True, False, False, False, False, False,False, False, False, False, False, False, False, False, False,False, False, False, False, False, False, False, False, False,False, False, False, False, False, False, False, False, False,False, False, False, False, False, False, False, False, False,False, False, False, False, False, False, False, False, False,False, False, False, False, False, False, False, False, False,False, False, False, False, False, False, False, False, False,False, False, False, False, False, False, False, False, False,False, False, False, False, False, False, False, False, False,False, False, False, False, False, False, False, False, False,False, False, False, False, False, False, False, False, False,False, False, False, False, False, False, False, False, False,False, False, False, False, False, False, False, False, False,False, False, False,  True, False, False, False, False, False,False, False, False, False, False, False, False, False,  True,True, False, False, False, False, False, False, False, False,False, False, False, False, False, False, False, False, False,False,  True, False, False, False, False,  True, False, False,...False, False, False, False, False, False, False, False, False,False, False, False, False, False, False, False, False, False,False, False, False, False, False, False, False, False, False,False, False, False, False, False, False, False, False, False,False, False, False, False, False, False, False, False, False,False, False, False, False, False, False, False, False, False,False, False, False, False, False,  True, False, False, False,False, False, False, False, False, False, False, False, False,False, False, False, False, False, False, False, False, False,False, False, False, False, False, False, False, False, False,False, False, False, False, False, False, False, False, False,False, False, False, False, False, False, False, False, False,False, False, False, False, False, False, False, False, False,False, False, False, False, False, False, False, False, False,False, False, False, False, False, False, False, False, False,False, False, False, False, False, False, False, False, False,False, False, False, False, False, False, False, False, False,False, False, False, False, False, False, False, False, False,False, False, False, False, False, False, False, False, False,False, False, False, False, False]], dtype=bool)</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span>energy</span></div><div class='xr-var-dims'>(chain, draw)</div><div class='xr-var-dtype'>float32</div><div class='xr-var-preview xr-preview'>...</div><input id='attrs-2677c144-5044-463d-9c31-5edf24d19011' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-2677c144-5044-463d-9c31-5edf24d19011' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-1fc8ec7a-e619-4bc9-a0b5-c427e4539949' class='xr-var-data-in' type='checkbox'><label for='data-1fc8ec7a-e619-4bc9-a0b5-c427e4539949' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>Array([[2000.1201, 2008.9381, 1991.6708, 1979.9502, 1982.7324, 1994.5337,1984.4677, 1985.9924, 1995.0413, 2006.2045, 1996.0435, 1996.673 ,2003.1986, 1992.8812, 1994.3624, 1997.9321, 2014.704 , 2013.1753,2002.8738, 2001.6792, 1997.6985, 1998.7981, 1995.7241, 1999.7083,1999.2538, 1989.6049, 1989.7085, 1986.2863, 1991.9456, 1996.3589,1989.2448, 1985.6384, 2000.0952, 2000.3923, 1996.0682, 1980.726 ,1984.2157, 1976.341 , 1976.6584, 1985.6892, 1996.7349, 1996.9833,1989.3641, 2009.8849, 2007.8591, 1987.401 , 1989.4299, 1989.5753,1985.7817, 2009.4467, 2000.5605, 2009.0647, 2005.9186, 2010.2281,2015.6267, 2007.6523, 2007.3257, 2002.8633, 1996.1766, 1998.8014,1990.8413, 1979.255 , 1982.7402, 1980.9143, 1995.2625, 2014.1671,1992.8206, 1984.9806, 1981.6715, 1993.387 , 1988.2169, 1998.8143,2016.098 , 2018.1687, 2012.5457, 2004.6321, 1993.8975, 2004.8235,2013.6799, 1995.5444, 1998.8816, 1997.1836, 1995.312 , 2016.7595,2008.2471, 2001.2026, 2001.4695, 1998.7935, 1984.7642, 1978.0483,1988.384 , 1997.7885, 2019.2285, 2021.4402, 2015.3296, 2010.5247,2006.982 , 2016.1663, 2015.2845, 2008.8646, 2007.4055, 2011.5314,2023.4004, 2012.0573, 1999.2704, 1997.1251, 1988.1489, 2009.8112,2000.0894, 2009.9333, 2002.1974, 1993.602 , 1990.9814, 1996.0059,1986.8365, 1969.625 , 1974.3362, 1974.672 , 1971.4062, 1980.8599,...1998.4681, 1995.6593, 1995.9768, 2004.7526, 2003.7671, 2034.1945,2021.5533, 2011.4172, 2008.7725, 2008.8704, 1993.3832, 2001.3054,2001.2728, 2006.322 , 2003.628 , 1989.2168, 1995.3766, 2003.5121,2003.3501, 2004.498 , 1997.7001, 2003.0043, 2004.4985, 2003.1411,2000.3671, 1992.7561, 1993.5066, 1995.3756, 1998.7368, 1995.2668,1993.9747, 1990.3367, 1998.7848, 1996.384 , 2001.3242, 2004.6969,2007.7024, 2020.1068, 1999.8271, 1998.4836, 1994.8862, 1983.9783,2003.0559, 1998.0304, 2006.2023, 2025.3593, 2016.2717, 2002.9792,2003.127 , 2005.6697, 1990.8331, 2002.5963, 2002.0278, 2009.0454,2006.5773, 2020.2507, 2024.0498, 2016.1763, 2012.7279, 1999.7548,2010.733 , 2006.5205, 2018.5388, 1993.4911, 1983.1964, 2002.5482,2005.1333, 2002.1182, 1999.5131, 2017.7534, 2006.0867, 1999.8402,1992.5111, 1977.5326, 1995.1313, 1994.9269, 2006.7632, 2002.7848,1992.0134, 1995.2626, 2009.8235, 2002.9766, 2003.9635, 1993.975 ,1989.9164, 1993.4792, 2002.3339, 1995.4193, 1979.8629, 1994.8157,2000.2042, 1995.4048, 1993.4622, 2000.1344, 2002.4463, 1997.3129,2000.8055, 2002.0989, 1985.3743, 1992.5676, 1996.757 , 2007.0812,1995.4178, 2003.7782, 2008.5754, 2000.8224, 1994.8236, 1993.6113,1994.6339, 1993.8735, 1993.1821, 2003.8766, 2008.0428, 2002.8422,1995.7704, 1989.9429]], dtype=float32)</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span>n_steps</span></div><div class='xr-var-dims'>(chain, draw)</div><div class='xr-var-dtype'>int32</div><div class='xr-var-preview xr-preview'>...</div><input id='attrs-8704fb17-416e-4ad1-8069-a0c422afa401' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-8704fb17-416e-4ad1-8069-a0c422afa401' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-e49db5e3-4440-4bd5-9ec9-04a09a17b079' class='xr-var-data-in' type='checkbox'><label for='data-e49db5e3-4440-4bd5-9ec9-04a09a17b079' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>Array([[ 63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  33,63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,63,  63,  63,  63, 127,  63,  63,  63,  42,  63,  63,  63,  63,63,  63,  63,  63,  63,  63,  63,  63,  63,  14,  29,  63,  63,63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,63,  63,  63,  46,  63,  63,  63,  63,  48,  63,  63,  63,  63,63,  63,  63,  63,  63,  53,  63,  63,  63,  63,  63,  63,  63,63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  57,  63,63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,63,  63,  63,  63,  63,  63,  63,  63,  56,  31,  63,  63,  63,...63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,63,  63,  63,  63,  63,  63,  63,  63,  63,  63, 127,  63,  63,63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,63,  63,  63,  63,  63,  63,  63,  63,  55,  63,  63,  63,  63,63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,63,  63,  63,  63,  63,  63,  63,  63,  63, 127,  63,  63,  63,63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,63,  63,  63,  63,  63,  63,  36,  63,  63,  63,  63,  63,  63,63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,63,  63,  63, 127,  63,  63, 127,  63,  63,  63,  63,  63, 127,63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,63,  63,  63,  63,  63,  63]], dtype=int32)</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span>tree_depth</span></div><div class='xr-var-dims'>(chain, draw)</div><div class='xr-var-dtype'>int64</div><div class='xr-var-preview xr-preview'>6 6 6 6 6 6 6 6 ... 6 6 6 6 6 6 6 6</div><input id='attrs-8d1a4b4f-c231-4c87-9089-c7745034896a' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-8d1a4b4f-c231-4c87-9089-c7745034896a' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-baf190da-2369-4d1f-83aa-d7f7791bb1e9' class='xr-var-data-in' type='checkbox'><label for='data-baf190da-2369-4d1f-83aa-d7f7791bb1e9' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>array([[6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6,6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6,6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6,6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6,6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6,6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6,6, 6, 7, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 4, 5,6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6,6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6,6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6,6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6,6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 5, 6, 6, 6, 6, 6, 6, 6,6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 5, 6, 6, 2, 6, 6, 6, 6,6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6,6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 2,6, 6, 6, 6, 7, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6,6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6,6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6,6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6,6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 3, 6,...6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6,6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6,6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 7, 6, 7, 6, 6, 6, 6, 6, 6, 7, 6,6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6,6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6,6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6,6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6,6, 6, 6, 6, 6, 6, 6, 7, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6,6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6,6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 7, 6, 6,6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6,6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6,6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 7, 6, 6, 6, 6,6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6,6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6,6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 7, 6, 6, 7, 6, 6, 6, 6, 6, 7, 6, 6,6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6,6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6,6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6,6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6]])</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span>lp</span></div><div class='xr-var-dims'>(chain, draw)</div><div class='xr-var-dtype'>float32</div><div class='xr-var-preview xr-preview'>...</div><input id='attrs-02b4496a-dd56-41d8-af92-3ff1749a5e7b' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-02b4496a-dd56-41d8-af92-3ff1749a5e7b' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-41da9779-1c82-4b17-a2b5-e2f06a9c067e' class='xr-var-data-in' type='checkbox'><label for='data-41da9779-1c82-4b17-a2b5-e2f06a9c067e' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>Array([[1964.4095, 1948.3148, 1941.7513, 1934.0028, 1937.1644, 1930.9541,1932.641 , 1945.7921, 1953.3313, 1950.5594, 1945.1743, 1945.0361,1953.7217, 1951.825 , 1948.3881, 1949.1462, 1966.2217, 1951.8164,1951.9104, 1952.8829, 1946.551 , 1941.499 , 1945.9089, 1952.7385,1934.7157, 1941.1349, 1941.3654, 1937.0203, 1947.8462, 1943.2026,1937.925 , 1943.3264, 1954.8567, 1952.249 , 1941.2795, 1939.8005,1935.4092, 1934.297 , 1933.2043, 1942.8932, 1949.5048, 1942.3964,1947.7435, 1949.2378, 1945.1246, 1934.9556, 1934.3464, 1945.6146,1941.0223, 1943.8488, 1952.084 , 1954.7031, 1961.5858, 1954.4487,1954.2318, 1955.9055, 1960.6233, 1952.4982, 1949.6887, 1953.0427,1927.6989, 1939.6818, 1934.6565, 1939.7776, 1952.9052, 1952.3329,1941.3802, 1943.9385, 1941.1278, 1943.9907, 1941.5576, 1959.8483,1967.2902, 1956.2557, 1949.597 , 1948.7478, 1949.7277, 1966.023 ,1948.4059, 1951.3397, 1941.4507, 1948.4576, 1961.4414, 1971.008 ,1949.5508, 1945.1376, 1948.9148, 1939.8558, 1931.4396, 1938.6229,1947.3175, 1953.6385, 1966.0149, 1960.1417, 1956.759 , 1957.94  ,1964.5818, 1954.1478, 1963.715 , 1945.4519, 1960.9698, 1962.3295,1954.7211, 1956.431 , 1950.0563, 1942.2604, 1941.6611, 1949.8524,1952.568 , 1956.6936, 1946.4364, 1938.4451, 1945.0626, 1949.1433,1935.8982, 1924.7948, 1929.0122, 1926.9514, 1929.1702, 1938.8912,...1955.6075, 1946.6201, 1953.7701, 1952.9503, 1957.7897, 1975.5355,1956.7076, 1962.5419, 1954.0151, 1950.0134, 1946.391 , 1946.587 ,1946.9575, 1961.6006, 1941.7339, 1938.7993, 1942.7499, 1957.8021,1951.3011, 1955.3544, 1947.2863, 1955.9829, 1950.2819, 1946.5028,1941.8741, 1943.1283, 1943.9999, 1947.101 , 1948.3889, 1948.9551,1946.333 , 1948.69  , 1948.1433, 1952.1145, 1956.6344, 1952.9252,1961.0938, 1962.6243, 1953.0315, 1944.0703, 1940.8499, 1938.2295,1953.075 , 1948.6726, 1965.7073, 1967.664 , 1960.4905, 1944.6615,1954.5065, 1951.5527, 1951.1604, 1952.6173, 1961.524 , 1956.8971,1961.6323, 1964.9624, 1956.3516, 1962.6218, 1951.8044, 1956.1973,1957.6158, 1969.9862, 1956.201 , 1941.6528, 1939.8468, 1949.7965,1954.5817, 1945.9875, 1952.8431, 1962.1721, 1948.1432, 1945.9917,1938.6671, 1938.4241, 1943.1005, 1953.2786, 1953.5446, 1946.2394,1938.4893, 1952.5115, 1952.3281, 1942.2037, 1947.8806, 1940.6622,1942.6826, 1945.4612, 1946.1318, 1938.5596, 1943.5292, 1950.5172,1941.407 , 1944.1385, 1949.2346, 1946.9534, 1948.4958, 1951.2379,1955.9557, 1947.4752, 1930.7614, 1940.2855, 1948.7935, 1953.8732,1946.9984, 1949.1471, 1950.3441, 1951.2206, 1952.9559, 1942.2328,1946.4326, 1935.2657, 1957.5614, 1950.6019, 1960.5016, 1944.89  ,1944.306 , 1938.2903]], dtype=float32)</pre></div></li></ul></div></li><li class='xr-section-item'><input id='section-408943f0-624e-4efa-b2a6-7b069c4d1f82' class='xr-section-summary-in' type='checkbox' checked /><label for='section-408943f0-624e-4efa-b2a6-7b069c4d1f82' class='xr-section-summary' title='Expand/collapse section'>Attributes: <span>(7)</span></label><div class='xr-section-inline-details'></div><div class='xr-section-details'><dl class='xr-attrs'><dt><span>created_at :</span></dt><dd>2026-07-06T16:44:41.799808+00:00</dd><dt><span>creation_library :</span></dt><dd>ArviZ</dd><dt><span>creation_library_version :</span></dt><dd>1.2.0</dd><dt><span>creation_library_language :</span></dt><dd>Python</dd><dt><span>sample_dims :</span></dt><dd>[&#x27;chain&#x27;, &#x27;draw&#x27;]</dd><dt><span>modeling_interface :</span></dt><dd>bambi</dd><dt><span>modeling_interface_version :</span></dt><dd>0.18.0</dd></dl></div></li></ul></div></div><div class='xr-group-box'><div class='xr-group-box-vline' style='height: 100%'></div><div class='xr-group-box-hline'></div><div class='xr-group-box-contents'><input id='group-5b0778ff-24a2-4574-bb7c-666972b3d3b8' type='checkbox' checked /><label for='group-5b0778ff-24a2-4574-bb7c-666972b3d3b8' title='Expand/collapse group'>/observed_data<span>(10)</span></label><ul class='xr-sections'><li class='xr-section-item'><input id='section-814bd61a-c68d-4a5c-8eab-f486bed2523e' class='xr-section-summary-in' type='checkbox' disabled /><label for='section-814bd61a-c68d-4a5c-8eab-f486bed2523e' class='xr-section-summary'>Dimensions:</label><div class='xr-section-inline-details'><ul class='xr-dim-list'><li><span class='xr-has-index'>__obs__</span>: 2250</li><li><span class='xr-has-index'>rt,response_extra_dim_0</span>: 2</li></ul></div></li><li class='xr-section-item'><input id='section-48c09671-bab3-4594-872d-10cfc76a333e' class='xr-section-summary-in' type='checkbox' checked /><label for='section-48c09671-bab3-4594-872d-10cfc76a333e' class='xr-section-summary' title='Expand/collapse section'>Coordinates: <span>(2)</span></label><div class='xr-section-inline-details'></div><div class='xr-section-details'><ul class='xr-var-list'><li class='xr-var-item'><div class='xr-var-name'><span class='xr-has-index'>__obs__</span></div><div class='xr-var-dims'>(__obs__)</div><div class='xr-var-dtype'>int64</div><div class='xr-var-preview xr-preview'>0 1 2 3 4 ... 2246 2247 2248 2249</div><input id='attrs-817f9e93-2f49-457e-aa12-d1dfdd426c10' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-817f9e93-2f49-457e-aa12-d1dfdd426c10' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-3a9f46a4-f134-494d-badc-6685733ecd38' class='xr-var-data-in' type='checkbox'><label for='data-3a9f46a4-f134-494d-badc-6685733ecd38' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>array([   0,    1,    2, ..., 2247, 2248, 2249], shape=(2250,))</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span class='xr-has-index'>rt,response_extra_dim_0</span></div><div class='xr-var-dims'>(rt,response_extra_dim_0)</div><div class='xr-var-dtype'>int64</div><div class='xr-var-preview xr-preview'>0 1</div><input id='attrs-b85509b1-09ee-45fc-808f-80828c0f405c' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-b85509b1-09ee-45fc-808f-80828c0f405c' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-63b698b0-8ff7-4dd9-b149-f696fd8356de' class='xr-var-data-in' type='checkbox'><label for='data-63b698b0-8ff7-4dd9-b149-f696fd8356de' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>array([0, 1])</pre></div></li></ul></div></li><li class='xr-section-item'><input id='section-4d5c6672-cbd8-49d7-930d-b537d9d95f16' class='xr-section-summary-in' type='checkbox' checked /><label for='section-4d5c6672-cbd8-49d7-930d-b537d9d95f16' class='xr-section-summary' title='Expand/collapse section'>Data variables: <span>(1)</span></label><div class='xr-section-inline-details'></div><div class='xr-section-details'><ul class='xr-var-list'><li class='xr-var-item'><div class='xr-var-name'><span>rt,response</span></div><div class='xr-var-dims'>(__obs__, rt,response_extra_dim_0)</div><div class='xr-var-dtype'>float32</div><div class='xr-var-preview xr-preview'>1.07 -1.0 1.998 ... 1.0 0.6218 -1.0</div><input id='attrs-e9d076b8-97d5-4f30-a77b-a27ea01e6287' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-e9d076b8-97d5-4f30-a77b-a27ea01e6287' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-29f7b00e-0bb3-48de-8be1-0e010fd3f062' class='xr-var-data-in' type='checkbox'><label for='data-29f7b00e-0bb3-48de-8be1-0e010fd3f062' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>array([[ 1.0698211 , -1.        ],[ 1.9984472 , -1.        ],[ 1.5602216 , -1.        ],...,[ 1.2822655 , -1.        ],[ 1.0421401 ,  1.        ],[ 0.62177145, -1.        ]], shape=(2250, 2), dtype=float32)</pre></div></li></ul></div></li><li class='xr-section-item'><input id='section-5768384e-1c3d-4e55-9e87-ec207633461e' class='xr-section-summary-in' type='checkbox' checked /><label for='section-5768384e-1c3d-4e55-9e87-ec207633461e' class='xr-section-summary' title='Expand/collapse section'>Attributes: <span>(7)</span></label><div class='xr-section-inline-details'></div><div class='xr-section-details'><dl class='xr-attrs'><dt><span>created_at :</span></dt><dd>2026-07-06T16:44:41.800372+00:00</dd><dt><span>creation_library :</span></dt><dd>ArviZ</dd><dt><span>creation_library_version :</span></dt><dd>1.2.0</dd><dt><span>creation_library_language :</span></dt><dd>Python</dd><dt><span>sample_dims :</span></dt><dd>[]</dd><dt><span>modeling_interface :</span></dt><dd>bambi</dd><dt><span>modeling_interface_version :</span></dt><dd>0.18.0</dd></dl></div></li></ul></div></div><div class='xr-group-box'><div class='xr-group-box-vline' style='height: 100%'></div><div class='xr-group-box-hline'></div><div class='xr-group-box-contents'><input id='group-344440ea-e1df-468d-bcaf-ee117a2c93e2' type='checkbox' checked /><label for='group-344440ea-e1df-468d-bcaf-ee117a2c93e2' title='Expand/collapse group'>/constant_data<span>(7)</span></label><ul class='xr-sections'><li class='xr-section-item'><input id='section-37b7fbd2-5d48-4356-b40b-1c62cf60777f' class='xr-section-summary-in' type='checkbox' checked /><label for='section-37b7fbd2-5d48-4356-b40b-1c62cf60777f' class='xr-section-summary' title='Expand/collapse section'>Attributes: <span>(7)</span></label><div class='xr-section-inline-details'></div><div class='xr-section-details'><dl class='xr-attrs'><dt><span>created_at :</span></dt><dd>2026-07-06T16:44:41.800438+00:00</dd><dt><span>creation_library :</span></dt><dd>ArviZ</dd><dt><span>creation_library_version :</span></dt><dd>1.2.0</dd><dt><span>creation_library_language :</span></dt><dd>Python</dd><dt><span>sample_dims :</span></dt><dd>[]</dd><dt><span>modeling_interface :</span></dt><dd>bambi</dd><dt><span>modeling_interface_version :</span></dt><dd>0.18.0</dd></dl></div></li></ul></div></div><div class='xr-group-box'><div class='xr-group-box-vline' style='height: 1.2em'></div><div class='xr-group-box-hline'></div><div class='xr-group-box-contents'><input id='group-3572dbaa-d1ad-4803-a8e5-d87cb59628a6' type='checkbox' checked /><label for='group-3572dbaa-d1ad-4803-a8e5-d87cb59628a6' title='Expand/collapse group'>/log_likelihood<span>(6)</span></label><ul class='xr-sections'><li class='xr-section-item'><input id='section-95876814-a2b3-4435-a90a-a604f19df30b' class='xr-section-summary-in' type='checkbox' disabled /><label for='section-95876814-a2b3-4435-a90a-a604f19df30b' class='xr-section-summary'>Dimensions:</label><div class='xr-section-inline-details'><ul class='xr-dim-list'><li><span class='xr-has-index'>chain</span>: 2</li><li><span class='xr-has-index'>draw</span>: 500</li><li><span class='xr-has-index'>__obs__</span>: 2250</li></ul></div></li><li class='xr-section-item'><input id='section-0c43cef9-0ccc-4e9a-ba84-ae69e26f1261' class='xr-section-summary-in' type='checkbox' checked /><label for='section-0c43cef9-0ccc-4e9a-ba84-ae69e26f1261' class='xr-section-summary' title='Expand/collapse section'>Coordinates: <span>(3)</span></label><div class='xr-section-inline-details'></div><div class='xr-section-details'><ul class='xr-var-list'><li class='xr-var-item'><div class='xr-var-name'><span class='xr-has-index'>chain</span></div><div class='xr-var-dims'>(chain)</div><div class='xr-var-dtype'>int64</div><div class='xr-var-preview xr-preview'>0 1</div><input id='attrs-8478a7a9-7ca1-484f-98bd-eb61c5f2a66d' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-8478a7a9-7ca1-484f-98bd-eb61c5f2a66d' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-a107d9e6-fb82-4079-931f-222542e8b809' class='xr-var-data-in' type='checkbox'><label for='data-a107d9e6-fb82-4079-931f-222542e8b809' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>array([0, 1])</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span class='xr-has-index'>draw</span></div><div class='xr-var-dims'>(draw)</div><div class='xr-var-dtype'>int64</div><div class='xr-var-preview xr-preview'>0 1 2 3 4 5 ... 495 496 497 498 499</div><input id='attrs-adfed8b3-8bbf-4a82-9e7f-3327d7a970e4' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-adfed8b3-8bbf-4a82-9e7f-3327d7a970e4' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-3b03a1ca-9180-438b-b29f-82ec2d31b28b' class='xr-var-data-in' type='checkbox'><label for='data-3b03a1ca-9180-438b-b29f-82ec2d31b28b' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>array([  0,   1,   2, ..., 497, 498, 499], shape=(500,))</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span class='xr-has-index'>__obs__</span></div><div class='xr-var-dims'>(__obs__)</div><div class='xr-var-dtype'>int64</div><div class='xr-var-preview xr-preview'>0 1 2 3 4 ... 2246 2247 2248 2249</div><input id='attrs-4b69ef19-2eb3-41df-9f5f-6536654a0428' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-4b69ef19-2eb3-41df-9f5f-6536654a0428' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-31c05bb0-71a5-409b-82c3-7ebf4f2c61b0' class='xr-var-data-in' type='checkbox'><label for='data-31c05bb0-71a5-409b-82c3-7ebf4f2c61b0' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>array([   0,    1,    2, ..., 2247, 2248, 2249], shape=(2250,))</pre></div></li></ul></div></li><li class='xr-section-item'><input id='section-834a8363-377a-4847-9ab7-b0797d958d85' class='xr-section-summary-in' type='checkbox' checked /><label for='section-834a8363-377a-4847-9ab7-b0797d958d85' class='xr-section-summary' title='Expand/collapse section'>Data variables: <span>(1)</span></label><div class='xr-section-inline-details'></div><div class='xr-section-details'><ul class='xr-var-list'><li class='xr-var-item'><div class='xr-var-name'><span>rt,response</span></div><div class='xr-var-dims'>(chain, draw, __obs__)</div><div class='xr-var-dtype'>float64</div><div class='xr-var-preview xr-preview'>-0.9003 -2.705 ... -3.817 0.4514</div><input id='attrs-9e7381fd-09d3-4d2c-9a3d-d8078a2a28c4' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-9e7381fd-09d3-4d2c-9a3d-d8078a2a28c4' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-f74b28c5-e416-443f-afea-dae808507af0' class='xr-var-data-in' type='checkbox'><label for='data-f74b28c5-e416-443f-afea-dae808507af0' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>array([[[-0.9002651 , -2.70510006, -1.50032175, ..., -0.80871707,-3.53477788,  0.35698664],[-0.87976915, -2.99639964, -1.64367843, ..., -0.9917987 ,-3.60017061,  0.56391585],[-0.89330721, -3.00440907, -1.55672777, ..., -0.74742687,-2.99656725,  0.28471351],...,[-0.85784686, -3.12925029, -1.66228151, ..., -0.8490932 ,-3.55797029,  0.47211468],[-0.96338546, -2.608428  , -1.61300755, ..., -0.77893794,-3.78648973,  0.41193628],[-0.87420624, -3.0878253 , -1.5030005 , ..., -0.74170887,-3.16661811,  0.33100969]],[[-0.93991661, -2.64462161, -1.55485284, ..., -0.98575687,-3.70487523,  0.49665511],[-0.84236854, -3.22509384, -1.63678801, ..., -0.75963193,-3.66907811,  0.43347764],[-0.90852672, -2.73295927, -1.50674868, ..., -0.89023221,-3.70897794,  0.46702492],...,[-0.92299128, -2.55246878, -1.49743736, ..., -0.89620638,-3.3245585 ,  0.46194756],[-0.92174673, -2.72164321, -1.50951588, ..., -0.7725507 ,-3.41744447,  0.41824543],[-0.9264878 , -2.47148395, -1.46148992, ..., -0.82131016,-3.81700754,  0.45137346]]], shape=(2, 500, 2250))</pre></div></li></ul></div></li><li class='xr-section-item'><input id='section-bcbc928f-8125-4c08-ab9e-7767a0b86cee' class='xr-section-summary-in' type='checkbox' checked /><label for='section-bcbc928f-8125-4c08-ab9e-7767a0b86cee' class='xr-section-summary' title='Expand/collapse section'>Attributes: <span>(2)</span></label><div class='xr-section-inline-details'></div><div class='xr-section-details'><dl class='xr-attrs'><dt><span>modeling_interface :</span></dt><dd>bambi</dd><dt><span>modeling_interface_version :</span></dt><dd>0.18.0</dd></dl></div></li></ul></div></div></div></li></ul></div></div>"
-      ],
-      "text/plain": [
-       "<xarray.DataTree>\n",
-       "Group: /\n",
-       "├── Group: /posterior\n",
-       "│       Dimensions:                                (chain: 2, draw: 500,\n",
-       "│                                                   participant_id__factor_dim: 15,\n",
-       "│                                                   rl_alpha_1|participant_id__factor_dim: 15)\n",
-       "│       Coordinates:\n",
-       "│         * chain                                  (chain) int64 16B 0 1\n",
-       "│         * draw                                   (draw) int64 4kB 0 1 2 ... 498 499\n",
-       "│         * participant_id__factor_dim             (participant_id__factor_dim) <U2 120B ...\n",
-       "│         * rl_alpha_1|participant_id__factor_dim  (rl_alpha_1|participant_id__factor_dim) <U2 120B ...\n",
-       "│       Data variables: (12/24)\n",
-       "│           t_1|participant_id_offset              (chain, draw, participant_id__factor_dim) float32 60kB ...\n",
-       "│           z_1|participant_id                     (chain, draw, participant_id__factor_dim) float32 60kB ...\n",
-       "│           z_1|participant_id_sigma               (chain, draw) float32 4kB ...\n",
-       "│           theta_1|participant_id                 (chain, draw, participant_id__factor_dim) float32 60kB ...\n",
-       "│           rl_alpha_Intercept                     (chain, draw) float32 4kB ...\n",
-       "│           t_Intercept                            (chain, draw) float32 4kB ...\n",
-       "│           ...                                     ...\n",
-       "│           theta_1|participant_id_offset          (chain, draw, participant_id__factor_dim) float32 60kB ...\n",
-       "│           a_1|participant_id_offset              (chain, draw, participant_id__factor_dim) float32 60kB ...\n",
-       "│           t_1|participant_id_sigma               (chain, draw) float32 4kB ...\n",
-       "│           t_1|participant_id                     (chain, draw, participant_id__factor_dim) float32 60kB ...\n",
-       "│           scaler_1|participant_id_offset         (chain, draw, participant_id__factor_dim) float32 60kB ...\n",
-       "│           rl_alpha_1|participant_id_offset       (chain, draw, rl_alpha_1|participant_id__factor_dim) float32 60kB ...\n",
-       "│       Attributes:\n",
-       "│           created_at:                  2026-07-06T16:44:41.787695+00:00\n",
-       "│           creation_library:            ArviZ\n",
-       "│           creation_library_version:    1.2.0\n",
-       "│           creation_library_language:   Python\n",
-       "│           sample_dims:                 ['chain', 'draw']\n",
-       "│           inference_library:           numpyro\n",
-       "│           inference_library_version:   0.21.0\n",
-       "│           sampling_time:               545.10303\n",
-       "│           tuning_steps:                1000\n",
-       "│           modeling_interface:          bambi\n",
-       "│           modeling_interface_version:  0.18.0\n",
-       "├── Group: /sample_stats\n",
-       "│       Dimensions:          (chain: 2, draw: 500)\n",
-       "│       Coordinates:\n",
-       "│         * chain            (chain) int64 16B 0 1\n",
-       "│         * draw             (draw) int64 4kB 0 1 2 3 4 5 6 ... 494 495 496 497 498 499\n",
-       "│       Data variables:\n",
-       "│           acceptance_rate  (chain, draw) float32 4kB ...\n",
-       "│           step_size        (chain, draw) float32 4kB ...\n",
-       "│           diverging        (chain, draw) bool 1kB ...\n",
-       "│           energy           (chain, draw) float32 4kB ...\n",
-       "│           n_steps          (chain, draw) int32 4kB ...\n",
-       "│           tree_depth       (chain, draw) int64 8kB 6 6 6 6 6 6 6 6 ... 6 6 6 6 6 6 6 6\n",
-       "│           lp               (chain, draw) float32 4kB ...\n",
-       "│       Attributes:\n",
-       "│           created_at:                  2026-07-06T16:44:41.799808+00:00\n",
-       "│           creation_library:            ArviZ\n",
-       "│           creation_library_version:    1.2.0\n",
-       "│           creation_library_language:   Python\n",
-       "│           sample_dims:                 ['chain', 'draw']\n",
-       "│           modeling_interface:          bambi\n",
-       "│           modeling_interface_version:  0.18.0\n",
-       "├── Group: /observed_data\n",
-       "│       Dimensions:                  (__obs__: 2250, rt,response_extra_dim_0: 2)\n",
-       "│       Coordinates:\n",
-       "│         * __obs__                  (__obs__) int64 18kB 0 1 2 3 ... 2247 2248 2249\n",
-       "│         * rt,response_extra_dim_0  (rt,response_extra_dim_0) int64 16B 0 1\n",
-       "│       Data variables:\n",
-       "│           rt,response              (__obs__, rt,response_extra_dim_0) float32 18kB ...\n",
-       "│       Attributes:\n",
-       "│           created_at:                  2026-07-06T16:44:41.800372+00:00\n",
-       "│           creation_library:            ArviZ\n",
-       "│           creation_library_version:    1.2.0\n",
-       "│           creation_library_language:   Python\n",
-       "│           sample_dims:                 []\n",
-       "│           modeling_interface:          bambi\n",
-       "│           modeling_interface_version:  0.18.0\n",
-       "├── Group: /constant_data\n",
-       "│       Attributes:\n",
-       "│           created_at:                  2026-07-06T16:44:41.800438+00:00\n",
-       "│           creation_library:            ArviZ\n",
-       "│           creation_library_version:    1.2.0\n",
-       "│           creation_library_language:   Python\n",
-       "│           sample_dims:                 []\n",
-       "│           modeling_interface:          bambi\n",
-       "│           modeling_interface_version:  0.18.0\n",
-       "└── Group: /log_likelihood\n",
-       "        Dimensions:      (chain: 2, draw: 500, __obs__: 2250)\n",
-       "        Coordinates:\n",
-       "          * chain        (chain) int64 16B 0 1\n",
-       "          * draw         (draw) int64 4kB 0 1 2 3 4 5 6 ... 493 494 495 496 497 498 499\n",
-       "          * __obs__      (__obs__) int64 18kB 0 1 2 3 4 5 ... 2245 2246 2247 2248 2249\n",
-       "        Data variables:\n",
-       "            rt,response  (chain, draw, __obs__) float64 18MB -0.9003 -2.705 ... 0.4514\n",
-       "        Attributes:\n",
-       "            modeling_interface:          bambi\n",
-       "            modeling_interface_version:  0.18.0"
-      ]
-     },
-     "execution_count": 12,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
+   "metadata": {},
+   "outputs": [],
    "source": [
     "idata = model.sample(\n",
     "    sampler=\"numpyro\",\n",
@@ -16422,27 +456,18 @@
    "id": "ad91ad20",
    "metadata": {},
    "source": [
-    "## 9. Parameter recovery\n",
-    "\n",
-    "The real test: does the fitted model recover the parameters we simulated from? We\n",
-    "check at two levels — the **group means** and the **individual participants**. The\n",
-    "two helpers below do the plotting; the logic they rely on is simple because HSSM used\n",
-    "an *identity* link for every parameter here, so a participant's estimate is just\n",
-    "`Intercept + (their deviation)` on the natural scale."
+    "## 8. A quick recovery check\n",
+    "The first question after fitting is simple: did the model recover the group-level\n",
+    "values we simulated from? We start with that group-level check here. Participant-by-\n",
+    "participant recovery is useful too, but it is easier to read once the basic workflow\n",
+    "feels familiar.\n"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 13,
+   "execution_count": null,
    "id": "ae08ea78",
-   "metadata": {
-    "execution": {
-     "iopub.execute_input": "2026-07-06T16:44:43.619346Z",
-     "iopub.status.busy": "2026-07-06T16:44:43.619245Z",
-     "iopub.status.idle": "2026-07-06T16:44:43.622969Z",
-     "shell.execute_reply": "2026-07-06T16:44:43.622649Z"
-    }
-   },
+   "metadata": {},
    "outputs": [],
    "source": [
     "def group_recovery(idata, true_group):\n",
@@ -16479,42 +504,7 @@
     "    ax.legend()\n",
     "    fig.tight_layout()\n",
     "    plt.show()\n",
-    "    return summ\n",
-    "\n",
-    "\n",
-    "def participant_recovery(idata, true_params):\n",
-    "    \"\"\"Per-participant true vs. posterior-mean estimate, one panel per parameter.\"\"\"\n",
-    "    post = idata.posterior\n",
-    "    fig, axes = plt.subplots(2, 3, figsize=(12, 7), constrained_layout=True)\n",
-    "    for ax, name in zip(axes.ravel(), LIST_PARAMS):\n",
-    "        re = post[f\"{name}_1|participant_id\"]\n",
-    "        pid_dim = [d for d in re.dims if d not in (\"chain\", \"draw\")][0]\n",
-    "        draws = post[f\"{name}_Intercept\"] + re  # identity link -> natural scale\n",
-    "        rec_mean = draws.mean((\"chain\", \"draw\")).values\n",
-    "        lo = draws.quantile(0.03, (\"chain\", \"draw\")).values\n",
-    "        hi = draws.quantile(0.97, (\"chain\", \"draw\")).values\n",
-    "        ids = [int(v) for v in re[pid_dim].values]\n",
-    "        true_v = true_params.loc[ids, name].values\n",
-    "\n",
-    "        ax.errorbar(\n",
-    "            true_v,\n",
-    "            rec_mean,\n",
-    "            yerr=[rec_mean - lo, hi - rec_mean],\n",
-    "            fmt=\"o\",\n",
-    "            ecolor=\"0.7\",\n",
-    "            capsize=3,\n",
-    "        )\n",
-    "        lohi = [\n",
-    "            min(true_v.min(), rec_mean.min()) - 0.03,\n",
-    "            max(true_v.max(), rec_mean.max()) + 0.03,\n",
-    "        ]\n",
-    "        ax.plot(lohi, lohi, \"k--\", lw=1)\n",
-    "        ax.set_title(name)\n",
-    "        ax.set_xlabel(\"true\")\n",
-    "        ax.set_ylabel(\"recovered\")\n",
-    "        ax.grid(alpha=0.3)\n",
-    "    fig.suptitle(\"Participant-level recovery (points on the dashed line = perfect)\")\n",
-    "    plt.show()"
+    "    return summ\n"
    ]
   },
   {
@@ -16522,354 +512,164 @@
    "id": "f028a492",
    "metadata": {},
    "source": [
-    "### 9.1 Group-level recovery\n",
-    "\n",
-    "Each posterior interval (blue) should sit close to the corresponding true group mean\n",
-    "(red diamond)."
+    "### Group-level recovery\n",
+    "Each posterior interval (blue) should sit reasonably close to the corresponding true\n",
+    "group mean (red diamond).\n"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 14,
+   "execution_count": null,
    "id": "89a41288",
-   "metadata": {
-    "execution": {
-     "iopub.execute_input": "2026-07-06T16:44:43.624148Z",
-     "iopub.status.busy": "2026-07-06T16:44:43.624086Z",
-     "iopub.status.idle": "2026-07-06T16:44:43.751873Z",
-     "shell.execute_reply": "2026-07-06T16:44:43.751473Z"
-    }
-   },
-   "outputs": [
-    {
-     "data": {
-      "image/png": "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",
-      "text/plain": [
-       "<Figure size 800x450 with 1 Axes>"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "text/html": [
-       "<div>\n",
-       "<style scoped>\n",
-       "    .dataframe tbody tr th:only-of-type {\n",
-       "        vertical-align: middle;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe tbody tr th {\n",
-       "        vertical-align: top;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe thead th {\n",
-       "        text-align: right;\n",
-       "    }\n",
-       "</style>\n",
-       "<table border=\"1\" class=\"dataframe\">\n",
-       "  <thead>\n",
-       "    <tr style=\"text-align: right;\">\n",
-       "      <th></th>\n",
-       "      <th>mean</th>\n",
-       "      <th>hdi94_lb</th>\n",
-       "      <th>hdi94_ub</th>\n",
-       "      <th>true</th>\n",
-       "    </tr>\n",
-       "  </thead>\n",
-       "  <tbody>\n",
-       "    <tr>\n",
-       "      <th>rl_alpha</th>\n",
-       "      <td>0.088</td>\n",
-       "      <td>0.064</td>\n",
-       "      <td>0.115</td>\n",
-       "      <td>0.08</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>scaler</th>\n",
-       "      <td>2.447</td>\n",
-       "      <td>2.125</td>\n",
-       "      <td>2.779</td>\n",
-       "      <td>2.50</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>a</th>\n",
-       "      <td>1.190</td>\n",
-       "      <td>1.091</td>\n",
-       "      <td>1.288</td>\n",
-       "      <td>1.20</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>z</th>\n",
-       "      <td>0.515</td>\n",
-       "      <td>0.483</td>\n",
-       "      <td>0.546</td>\n",
-       "      <td>0.50</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>t</th>\n",
-       "      <td>0.244</td>\n",
-       "      <td>0.210</td>\n",
-       "      <td>0.273</td>\n",
-       "      <td>0.25</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>theta</th>\n",
-       "      <td>0.346</td>\n",
-       "      <td>0.274</td>\n",
-       "      <td>0.424</td>\n",
-       "      <td>0.35</td>\n",
-       "    </tr>\n",
-       "  </tbody>\n",
-       "</table>\n",
-       "</div>"
-      ],
-      "text/plain": [
-       "           mean  hdi94_lb  hdi94_ub  true\n",
-       "rl_alpha  0.088     0.064     0.115  0.08\n",
-       "scaler    2.447     2.125     2.779  2.50\n",
-       "a         1.190     1.091     1.288  1.20\n",
-       "z         0.515     0.483     0.546  0.50\n",
-       "t         0.244     0.210     0.273  0.25\n",
-       "theta     0.346     0.274     0.424  0.35"
-      ]
-     },
-     "execution_count": 14,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
+   "metadata": {},
+   "outputs": [],
    "source": [
     "group_summary = group_recovery(idata, GROUP_THETA)\n",
     "group_summary[[\"mean\", \"hdi94_lb\", \"hdi94_ub\", \"true\"]].round(3)"
    ]
   },
-  {
-   "cell_type": "markdown",
-   "id": "7fd6bd7d",
-   "metadata": {},
-   "source": [
-    "### 9.2 Participant-level recovery\n",
-    "\n",
-    "The stronger test: for each parameter, do the **individual** estimates track the\n",
-    "individual true values? Points hugging the dashed identity line indicate good\n",
-    "recovery. The decision parameters `a` and `z` are typically recovered most sharply\n",
-    "from choice+RT data; the learning parameters are harder and their points scatter more\n",
-    "— an honest reflection of how much a bandit task constrains them."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 15,
-   "id": "db75f20e",
-   "metadata": {
-    "execution": {
-     "iopub.execute_input": "2026-07-06T16:44:43.758119Z",
-     "iopub.status.busy": "2026-07-06T16:44:43.758037Z",
-     "iopub.status.idle": "2026-07-06T16:44:44.074731Z",
-     "shell.execute_reply": "2026-07-06T16:44:44.074271Z"
-    }
-   },
-   "outputs": [
-    {
-     "data": {
-      "image/png": "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",
-      "text/plain": [
-       "<Figure size 1200x700 with 6 Axes>"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    }
-   ],
-   "source": [
-    "participant_recovery(idata, true_params)"
-   ]
-  },
   {
    "cell_type": "markdown",
    "id": "055a0d0e",
    "metadata": {},
    "source": [
-    "## 10. Posterior predictive check (RLSSM-aware)\n",
-    "\n",
+    "## 9. Posterior predictive check (RLSSM-aware)\n",
     "A posterior predictive check (PPC) asks: *if we simulate new data from the fitted\n",
-    "parameters, does it look like the data we observed?* For an RLSSM there is a subtlety.\n",
-    "Generic posterior predictive sampling would ignore the reward history and let the\n",
-    "learner wander freely, producing learning trajectories unlike the participant's. The\n",
-    "`ssms.rl` simulator therefore offers **`mode=\"ppc\"`**, which **re-simulates each trial\n",
-    "while conditioning the learning trajectory on the participant's *observed* responses\n",
-    "and feedback.** In other words, it replays the real sequence of outcomes to keep the\n",
-    "Q-values on the same path the participant actually experienced, and only the SSM\n",
-    "choice/RT for each trial are freshly simulated from posterior parameters. This\n",
-    "isolates *decision* fit from extra bandit randomness.\n",
-    "\n",
-    "We draw several parameter sets from the posterior, run `mode=\"ppc\"` for each, and\n",
-    "compare the predicted learning curve and RT distribution to the observed data."
+    "parameters, does it look like the data we observed?* For an RLSSM there is one extra\n",
+    "wrinkle: the predicted behavior depends on the learning trajectory. The helper below\n",
+    "handles that bookkeeping by replaying each participant's observed reward history\n",
+    "during PPC simulation, then comparing the predicted learning curve and RT distribution\n",
+    "with the observed data.\n"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 16,
+   "execution_count": null,
    "id": "433a3627",
-   "metadata": {
-    "execution": {
-     "iopub.execute_input": "2026-07-06T16:44:44.075971Z",
-     "iopub.status.busy": "2026-07-06T16:44:44.075886Z",
-     "iopub.status.idle": "2026-07-06T16:45:07.941670Z",
-     "shell.execute_reply": "2026-07-06T16:45:07.941260Z"
-    }
-   },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "PPC datasets: 20 | total rows: 45000\n"
-     ]
-    }
-   ],
+   "metadata": {},
+   "outputs": [],
    "source": [
-    "def draw_posterior_theta(idata, draw_idx):\n",
-    "    \"\"\"Return a single posterior draw of per-participant parameters (natural scale).\"\"\"\n",
-    "    posterior = idata.posterior\n",
-    "    if hasattr(posterior, \"to_dataset\"):\n",
-    "        posterior = posterior.to_dataset()  # PyMC 6 returns a DataTree node\n",
-    "    post = posterior.stack(sample=(\"chain\", \"draw\"))\n",
-    "    theta = {}\n",
-    "    for name in LIST_PARAMS:\n",
-    "        re = post[f\"{name}_1|participant_id\"]\n",
-    "        pid_dim = [d for d in re.dims if d not in (\"sample\",)][0]\n",
-    "        vals = (post[f\"{name}_Intercept\"] + re).isel(sample=draw_idx)\n",
-    "        ids = [int(v) for v in re[pid_dim].values]\n",
-    "        s = pd.Series(np.asarray(vals.values), index=ids).sort_index()\n",
-    "        theta[name] = s.reindex(range(N_PARTICIPANTS)).to_numpy()\n",
-    "    return theta\n",
-    "\n",
-    "\n",
-    "N_PPC_DRAWS = 20 if FULL_RUN else 8\n",
-    "n_samples = idata.posterior.sizes[\"chain\"] * idata.posterior.sizes[\"draw\"]\n",
-    "ppc_rng = np.random.default_rng(RANDOM_SEED + 1)\n",
-    "draw_ids = ppc_rng.choice(n_samples, size=min(N_PPC_DRAWS, n_samples), replace=False)\n",
-    "\n",
-    "ppc_frames = []\n",
-    "for k, d in enumerate(draw_ids):\n",
-    "    theta_d = draw_posterior_theta(idata, int(d))\n",
-    "    ppc_d = rl.Simulator(ssms_config).simulate(\n",
-    "        theta=theta_d,\n",
-    "        mode=\"ppc\",\n",
-    "        observed_data=data,\n",
-    "        random_state=RANDOM_SEED + 100 + k,\n",
+    "def plot_rl_ppc(idata, observed_data, ssms_config, *, n_participants, random_seed):\n",
+    "    \"\"\"Simulate an RL-aware PPC and plot the main checks.\"\"\"\n",
+    "    def draw_posterior_theta(draw_idx):\n",
+    "        posterior = idata.posterior\n",
+    "        if hasattr(posterior, \"to_dataset\"):\n",
+    "            posterior = posterior.to_dataset()  # PyMC 6 returns a DataTree node\n",
+    "        post = posterior.stack(sample=(\"chain\", \"draw\"))\n",
+    "        theta = {}\n",
+    "        for name in LIST_PARAMS:\n",
+    "            re = post[f\"{name}_1|participant_id\"]\n",
+    "            pid_dim = [d for d in re.dims if d not in (\"sample\",)][0]\n",
+    "            vals = (post[f\"{name}_Intercept\"] + re).isel(sample=draw_idx)\n",
+    "            ids = [int(v) for v in re[pid_dim].values]\n",
+    "            series = pd.Series(np.asarray(vals.values), index=ids).sort_index()\n",
+    "            theta[name] = series.reindex(range(n_participants)).to_numpy()\n",
+    "        return theta\n",
+    "    def learning_curve(df, bin_size=10):\n",
+    "        d = df[df[\"rt\"] > -900].copy()\n",
+    "        d[\"chose_high\"] = (d[\"response\"] == -1).astype(float)\n",
+    "        d[\"trial_bin\"] = (d[\"trial_id\"] // bin_size) * bin_size\n",
+    "        return d.groupby(\"trial_bin\")[\"chose_high\"].mean()\n",
+    "    def signed_rt(df):\n",
+    "        d = df[df[\"rt\"] > -900].copy()\n",
+    "        return np.where(\n",
+    "            d[\"response\"].astype(int) == -1,\n",
+    "            -d[\"rt\"].astype(float),\n",
+    "            d[\"rt\"].astype(float),\n",
+    "        )\n",
+    "    n_ppc_draws = 8\n",
+    "    n_samples = idata.posterior.sizes[\"chain\"] * idata.posterior.sizes[\"draw\"]\n",
+    "    ppc_rng = np.random.default_rng(random_seed + 1)\n",
+    "    draw_ids = ppc_rng.choice(\n",
+    "        n_samples, size=min(n_ppc_draws, n_samples), replace=False\n",
+    "    )\n",
+    "    ppc_frames = []\n",
+    "    for offset, draw_id in enumerate(draw_ids):\n",
+    "        theta_d = draw_posterior_theta(int(draw_id))\n",
+    "        ppc_draw = rl.Simulator(ssms_config).simulate(\n",
+    "            theta=theta_d,\n",
+    "            mode=\"ppc\",\n",
+    "            observed_data=observed_data,\n",
+    "            random_state=random_seed + 100 + offset,\n",
+    "        )\n",
+    "        ppc_draw[\"ppc_draw\"] = offset\n",
+    "        ppc_frames.append(ppc_draw)\n",
+    "    ppc_data = pd.concat(ppc_frames, ignore_index=True)\n",
+    "    fig, axes = plt.subplots(1, 2, figsize=(12, 4.5), constrained_layout=True)\n",
+    "    obs_curve = learning_curve(observed_data)\n",
+    "    ppc_curves = pd.concat(\n",
+    "        [learning_curve(group).rename(draw) for draw, group in ppc_data.groupby(\"ppc_draw\")],\n",
+    "        axis=1,\n",
+    "    ).sort_index()\n",
+    "    centers = obs_curve.index + 5\n",
+    "    axes[0].fill_between(\n",
+    "        ppc_curves.index + 5,\n",
+    "        ppc_curves.quantile(0.03, axis=1),\n",
+    "        ppc_curves.quantile(0.97, axis=1),\n",
+    "        alpha=0.25,\n",
+    "        color=\"tab:blue\",\n",
+    "        label=\"PPC 94% band\",\n",
+    "    )\n",
+    "    axes[0].plot(\n",
+    "        ppc_curves.index + 5,\n",
+    "        ppc_curves.mean(axis=1),\n",
+    "        color=\"tab:blue\",\n",
+    "        lw=1.5,\n",
+    "        label=\"PPC mean\",\n",
+    "    )\n",
+    "    axes[0].plot(centers, obs_curve.values, \"o-\", color=\"black\", label=\"observed\")\n",
+    "    axes[0].axhline(0.5, color=\"0.7\", ls=\"--\", lw=1)\n",
+    "    axes[0].set(\n",
+    "        xlabel=\"Trial\",\n",
+    "        ylabel=\"P(chose high-reward arm)\",\n",
+    "        title=\"Learning-curve PPC\",\n",
+    "        ylim=(0, 1),\n",
+    "    )\n",
+    "    axes[0].legend(frameon=False)\n",
+    "    axes[1].hist(\n",
+    "        signed_rt(observed_data),\n",
+    "        bins=40,\n",
+    "        density=True,\n",
+    "        histtype=\"step\",\n",
+    "        lw=1.8,\n",
+    "        color=\"black\",\n",
+    "        label=\"observed\",\n",
+    "    )\n",
+    "    axes[1].hist(\n",
+    "        signed_rt(ppc_data),\n",
+    "        bins=40,\n",
+    "        density=True,\n",
+    "        histtype=\"step\",\n",
+    "        lw=1.8,\n",
+    "        color=\"tab:blue\",\n",
+    "        label=\"PPC\",\n",
     "    )\n",
-    "    ppc_d[\"ppc_draw\"] = k\n",
-    "    ppc_frames.append(ppc_d)\n",
-    "ppc_data = pd.concat(ppc_frames, ignore_index=True)\n",
-    "print(\"PPC datasets:\", len(draw_ids), \"| total rows:\", len(ppc_data))"
+    "    axes[1].axvline(0, color=\"0.6\", lw=1)\n",
+    "    axes[1].set(\n",
+    "        xlabel=\"Signed RT (negative = high-reward choice)\",\n",
+    "        ylabel=\"density\",\n",
+    "        title=\"Signed-RT PPC\",\n",
+    "    )\n",
+    "    axes[1].legend(frameon=False)\n",
+    "    plt.show()\n",
+    "    print(\"PPC datasets:\", len(draw_ids), \"| total rows:\", len(ppc_data))\n",
+    "    return ppc_data\n"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 17,
+   "execution_count": null,
    "id": "4a32f6f7",
-   "metadata": {
-    "execution": {
-     "iopub.execute_input": "2026-07-06T16:45:07.942880Z",
-     "iopub.status.busy": "2026-07-06T16:45:07.942808Z",
-     "iopub.status.idle": "2026-07-06T16:45:08.050560Z",
-     "shell.execute_reply": "2026-07-06T16:45:08.050055Z"
-    }
-   },
-   "outputs": [
-    {
-     "data": {
-      "image/png": "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",
-      "text/plain": [
-       "<Figure size 1200x450 with 2 Axes>"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    }
-   ],
+   "metadata": {},
+   "outputs": [],
    "source": [
-    "def learning_curve(df, bin_size=10):\n",
-    "    \"\"\"Compute P(chose the high-reward arm) over trial bins.\"\"\"\n",
-    "    d = df[df[\"rt\"] > -900].copy()\n",
-    "    d[\"chose_high\"] = (d[\"response\"] == -1).astype(float)  # -1 == high-reward arm\n",
-    "    d[\"trial_bin\"] = (d[\"trial_id\"] // bin_size) * bin_size\n",
-    "    return d.groupby(\"trial_bin\")[\"chose_high\"].mean()\n",
-    "\n",
-    "\n",
-    "def signed_rt(df):\n",
-    "    \"\"\"Return finite RTs signed by response (- = high reward, + = low reward).\"\"\"\n",
-    "    d = df[df[\"rt\"] > -900].copy()\n",
-    "    # sign encodes choice: negative = high-reward arm (-1), positive = low-reward arm\n",
-    "    return np.where(\n",
-    "        d[\"response\"].astype(int) == -1, -d[\"rt\"].astype(float), d[\"rt\"].astype(float)\n",
-    "    )\n",
-    "\n",
-    "\n",
-    "fig, axes = plt.subplots(1, 2, figsize=(12, 4.5), constrained_layout=True)\n",
-    "\n",
-    "# (a) Learning-curve PPC: observed vs. per-draw predicted band\n",
-    "obs_curve = learning_curve(data)\n",
-    "ppc_curves = pd.concat(\n",
-    "    [learning_curve(g).rename(k) for k, g in ppc_data.groupby(\"ppc_draw\")], axis=1\n",
-    ").sort_index()\n",
-    "centers = obs_curve.index + 5\n",
-    "axes[0].fill_between(\n",
-    "    ppc_curves.index + 5,\n",
-    "    ppc_curves.quantile(0.03, axis=1),\n",
-    "    ppc_curves.quantile(0.97, axis=1),\n",
-    "    alpha=0.25,\n",
-    "    color=\"tab:blue\",\n",
-    "    label=\"PPC 94% band\",\n",
-    ")\n",
-    "axes[0].plot(\n",
-    "    ppc_curves.index + 5,\n",
-    "    ppc_curves.mean(axis=1),\n",
-    "    color=\"tab:blue\",\n",
-    "    lw=1.5,\n",
-    "    label=\"PPC mean\",\n",
-    ")\n",
-    "axes[0].plot(centers, obs_curve.values, \"o-\", color=\"black\", label=\"observed\")\n",
-    "axes[0].axhline(0.5, color=\"0.7\", ls=\"--\", lw=1)\n",
-    "axes[0].set(\n",
-    "    xlabel=\"Trial\",\n",
-    "    ylabel=\"P(chose high-reward arm)\",\n",
-    "    title=\"Learning-curve PPC\",\n",
-    "    ylim=(0, 1),\n",
-    ")\n",
-    "axes[0].legend(frameon=False)\n",
-    "\n",
-    "# (b) Signed-RT PPC: observed vs. pooled predicted\n",
-    "axes[1].hist(\n",
-    "    signed_rt(data),\n",
-    "    bins=40,\n",
-    "    density=True,\n",
-    "    histtype=\"step\",\n",
-    "    lw=1.8,\n",
-    "    color=\"black\",\n",
-    "    label=\"observed\",\n",
-    ")\n",
-    "axes[1].hist(\n",
-    "    signed_rt(ppc_data),\n",
-    "    bins=40,\n",
-    "    density=True,\n",
-    "    histtype=\"step\",\n",
-    "    lw=1.8,\n",
-    "    color=\"tab:blue\",\n",
-    "    label=\"PPC\",\n",
-    ")\n",
-    "axes[1].axvline(0, color=\"0.6\", lw=1)\n",
-    "axes[1].set(\n",
-    "    xlabel=\"Signed RT (negative = high-reward choice)\",\n",
-    "    ylabel=\"density\",\n",
-    "    title=\"Signed-RT PPC\",\n",
-    ")\n",
-    "axes[1].legend(frameon=False)\n",
-    "plt.show()"
+    "ppc_data = plot_rl_ppc(\n",
+    "    idata,\n",
+    "    observed_data=data,\n",
+    "    ssms_config=ssms_config,\n",
+    "    n_participants=N_PARTICIPANTS,\n",
+    "    random_seed=RANDOM_SEED,\n",
+    ")\n"
    ]
   },
   {
@@ -16877,36 +677,28 @@
    "id": "a124489a",
    "metadata": {},
    "source": [
-    "## 11. Summary\n",
-    "\n",
-    "You have run a complete RLSSM workflow:\n",
-    "\n",
+    "## 10. Summary\n",
+    "You have run a complete beginner-friendly RLSSM workflow:\n",
     "1. **Chose a model** — the `2AB_RW_Angle` preset (Rescorla–Wagner learning + angle SSM).\n",
     "2. **Simulated** a hierarchical dataset from known parameters and confirmed learning.\n",
-    "3. **Bridged** it into HSSM with a single `RLSSMConfig.from_ssms_model` call — the\n",
-    "   learned drift `v` is *computed*, never fit.\n",
-    "4. **Fit** a hierarchical model with NumPyro (remembering `process_initvals=False`).\n",
-    "5. **Checked recovery** at the group and individual level.\n",
-    "6. **Ran an RLSSM-aware PPC** with `mode=\"ppc\"`, which conditions the learning\n",
-    "   trajectory on the observed reward history.\n",
-    "\n",
+    "3. **Fit** the same preset directly in HSSM with a hierarchical prior template.\n",
+    "4. **Sampled** the posterior with NumPyro using `process_initvals=False`.\n",
+    "5. **Checked** one recovery summary and an RL-aware PPC.\n",
     "### Where to go next\n",
-    "\n",
     "- **[Custom models with ssms.rl](rlssm_advanced.ipynb)** — build your own task\n",
     "  environment and learning rule instead of using a preset.\n",
     "- **[Restless learner](rlssm_restless_learner.ipynb)** — one learner driving *several*\n",
     "  decision parameters at once.\n",
     "- **[Registering custom models in HSSM](rlssm_hssm_custom_models.ipynb)** — the\n",
     "  HSSM-native registry path.\n",
-    "\n",
     "> **Note:** HSSM also supports *choice-only* reinforcement-learning models (no RT).\n",
-    "> Those are documented separately once fully validated against the current release."
+    "> Those are documented separately once fully validated against the current release.\n"
    ]
   }
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python 3",
+   "display_name": "hssm (3.13.1.final.0)",
    "language": "python",
    "name": "python3"
   },
@@ -16919,8 +711,7 @@
    "mimetype": "text/x-python",
    "name": "python",
    "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.12.11"
+   "pygments_lexer": "ipython3"
   }
  },
  "nbformat": 4,

From 96631f6a0bb29a25b769be4d8dbea0fc19d3a184 Mon Sep 17 00:00:00 2001
From: Carlos Paniagua <cpaniaguam@gmail.com>
Date: Thu, 23 Jul 2026 16:11:18 -0400
Subject: [PATCH 2/6] Simplify basic rl tutorial nb

---
 docs/tutorials/rlssm_basic.ipynb | 50 ++++++++++++++++++++------------
 1 file changed, 31 insertions(+), 19 deletions(-)

diff --git a/docs/tutorials/rlssm_basic.ipynb b/docs/tutorials/rlssm_basic.ipynb
index 6eecefcf4..953d41c74 100644
--- a/docs/tutorials/rlssm_basic.ipynb
+++ b/docs/tutorials/rlssm_basic.ipynb
@@ -6,18 +6,20 @@
    "metadata": {},
    "source": [
     "# RLSSM — Basic tutorial\n",
-    "This tutorial is a first pass through an RLSSM workflow in HSSM. The goal is to\n",
-    "get from a preset model to a fitted hierarchical analysis without stopping on\n",
-    "every internal object along the way.\n",
+    "\n",
+    "This notebook is written for first-time RLSSM users.\n",
+    "Run the cells from top to bottom; each section builds directly on the previous one.\n",
+    "\n",
     "By the end you will have:\n",
     "- simulated a synthetic RLSSM dataset with [`ssm-simulators`](https://github.com/lnccbrown/ssm-simulators) (`ssms.rl`),\n",
-    "- fit a **hierarchical** (multi-participant) RLSSM in HSSM from the named preset `2AB_RW_Angle`,\n",
+    "- fit a hierarchical (multi-participant) RLSSM in HSSM from the preset `2AB_RW_Angle`,\n",
     "- checked a simple recovery summary, and\n",
-    "- run a **posterior predictive check** tailored to RLSSMs.\n",
-    "> **Where this sits in the suite:** this is the entry point. Later tutorials build\n",
-    "> *custom* learning/decision models\n",
+    "- run an RLSSM-aware posterior predictive check.\n",
+    "\n",
+    "> Where this sits in the suite: this is the entry point. Later tutorials cover\n",
+    "> custom learning/decision models\n",
     "> ([Custom models with ssms.rl](rlssm_advanced.ipynb) ·\n",
-    "> [Restless learner](rlssm_restless_learner.ipynb)) and show HSSM-native\n",
+    "> [Restless learner](rlssm_restless_learner.ipynb)) and HSSM-native\n",
     "> registration ([Registering custom models in HSSM](rlssm_hssm_custom_models.ipynb)).\n"
    ]
   },
@@ -92,16 +94,19 @@
    "source": [
     "import logging\n",
     "import warnings\n",
+    "\n",
     "import arviz as az\n",
     "import matplotlib.pyplot as plt\n",
     "import numpy as np\n",
     "import pandas as pd\n",
     "from ssms import rl\n",
+    "\n",
     "import hssm\n",
+    "\n",
     "warnings.filterwarnings(\"ignore\")\n",
     "logging.getLogger(\"jax._src.xla_bridge\").setLevel(logging.ERROR)\n",
     "hssm.set_floatX(\"float32\", update_jax=True)\n",
-    "RANDOM_SEED = 20260704\n"
+    "RANDOM_SEED = 20260704"
    ]
   },
   {
@@ -133,7 +138,7 @@
     "print(\n",
     "    f\"quick mode | participants={N_PARTICIPANTS} trials={N_TRIALS} \"\n",
     "    f\"tune={N_TUNE} draws={N_DRAWS}\"\n",
-    ")\n"
+    ")"
    ]
   },
   {
@@ -144,7 +149,7 @@
     "## 3. Pick a model: the `2AB_RW_Angle` preset\n",
     "`ssms.rl` ships **presets** that bundle a task environment, a learning rule, and a\n",
     "decision process into one ready-to-use model. `2AB_RW_Angle` is exactly the model we\n",
-    "described in above: a **2**-**a**rmed **b**andit with **R**escorla–**W**agner learning\n",
+    "described above: a **2**-**a**rmed **b**andit with **R**escorla–**W**agner learning\n",
     "and an **angle** decision process. `rl.preset.info(...)` prints a readable summary of\n",
     "everything the preset contains.\n"
    ]
@@ -182,7 +187,7 @@
     "ssms_config = rl.preset.get(\"2AB_RW_Angle\")\n",
     "assembled = ssms_config.assemble(backend=\"jax\")\n",
     "print(\"computed params (driven by the learner):\", assembled.computed_params)\n",
-    "assert \"v\" in assembled.computed_params\n"
+    "assert \"v\" in assembled.computed_params"
    ]
   },
   {
@@ -233,7 +238,7 @@
     "    \"t\": (0.05, 1.0),\n",
     "    \"theta\": (0.0, 1.2),\n",
     "}\n",
-    "LIST_PARAMS = list(GROUP_THETA);\n",
+    "LIST_PARAMS = list(GROUP_THETA)\n",
     "\n",
     "rng = np.random.default_rng(RANDOM_SEED)\n",
     "theta_arrays = {\n",
@@ -377,7 +382,7 @@
     "            ),\n",
     "            \"1|participant_id\": PARTICIPANT_EFFECT_PRIOR,\n",
     "        },\n",
-    "    )\n"
+    "    )"
    ]
   },
   {
@@ -419,7 +424,7 @@
     "print(\"free parameters:\", list(model.params.keys()))\n",
     "assert model.model_name == \"2AB_RW_Angle\"\n",
     "assert \"rl_alpha\" in model.params\n",
-    "assert \"v\" not in model.params  # computed by the learner, never sampled\n"
+    "assert \"v\" not in model.params  # computed by the learner, never sampled"
    ]
   },
   {
@@ -504,7 +509,7 @@
     "    ax.legend()\n",
     "    fig.tight_layout()\n",
     "    plt.show()\n",
-    "    return summ\n"
+    "    return summ"
    ]
   },
   {
@@ -551,6 +556,7 @@
    "source": [
     "def plot_rl_ppc(idata, observed_data, ssms_config, *, n_participants, random_seed):\n",
     "    \"\"\"Simulate an RL-aware PPC and plot the main checks.\"\"\"\n",
+    "\n",
     "    def draw_posterior_theta(draw_idx):\n",
     "        posterior = idata.posterior\n",
     "        if hasattr(posterior, \"to_dataset\"):\n",
@@ -565,11 +571,13 @@
     "            series = pd.Series(np.asarray(vals.values), index=ids).sort_index()\n",
     "            theta[name] = series.reindex(range(n_participants)).to_numpy()\n",
     "        return theta\n",
+    "\n",
     "    def learning_curve(df, bin_size=10):\n",
     "        d = df[df[\"rt\"] > -900].copy()\n",
     "        d[\"chose_high\"] = (d[\"response\"] == -1).astype(float)\n",
     "        d[\"trial_bin\"] = (d[\"trial_id\"] // bin_size) * bin_size\n",
     "        return d.groupby(\"trial_bin\")[\"chose_high\"].mean()\n",
+    "\n",
     "    def signed_rt(df):\n",
     "        d = df[df[\"rt\"] > -900].copy()\n",
     "        return np.where(\n",
@@ -577,6 +585,7 @@
     "            -d[\"rt\"].astype(float),\n",
     "            d[\"rt\"].astype(float),\n",
     "        )\n",
+    "\n",
     "    n_ppc_draws = 8\n",
     "    n_samples = idata.posterior.sizes[\"chain\"] * idata.posterior.sizes[\"draw\"]\n",
     "    ppc_rng = np.random.default_rng(random_seed + 1)\n",
@@ -598,7 +607,10 @@
     "    fig, axes = plt.subplots(1, 2, figsize=(12, 4.5), constrained_layout=True)\n",
     "    obs_curve = learning_curve(observed_data)\n",
     "    ppc_curves = pd.concat(\n",
-    "        [learning_curve(group).rename(draw) for draw, group in ppc_data.groupby(\"ppc_draw\")],\n",
+    "        [\n",
+    "            learning_curve(group).rename(draw)\n",
+    "            for draw, group in ppc_data.groupby(\"ppc_draw\")\n",
+    "        ],\n",
     "        axis=1,\n",
     "    ).sort_index()\n",
     "    centers = obs_curve.index + 5\n",
@@ -653,7 +665,7 @@
     "    axes[1].legend(frameon=False)\n",
     "    plt.show()\n",
     "    print(\"PPC datasets:\", len(draw_ids), \"| total rows:\", len(ppc_data))\n",
-    "    return ppc_data\n"
+    "    return ppc_data"
    ]
   },
   {
@@ -669,7 +681,7 @@
     "    ssms_config=ssms_config,\n",
     "    n_participants=N_PARTICIPANTS,\n",
     "    random_seed=RANDOM_SEED,\n",
-    ")\n"
+    ")"
    ]
   },
   {

From cd965677f0ba330e20e0ceba8a27105456191fe6 Mon Sep 17 00:00:00 2001
From: Carlos Paniagua <cpaniaguam@gmail.com>
Date: Thu, 23 Jul 2026 17:06:14 -0400
Subject: [PATCH 3/6] Enhance RLSSM tutorial readability and structure

---
 docs/tutorials/rlssm_basic.ipynb | 46 +++++++++++++++++++++++---------
 1 file changed, 34 insertions(+), 12 deletions(-)

diff --git a/docs/tutorials/rlssm_basic.ipynb b/docs/tutorials/rlssm_basic.ipynb
index 953d41c74..56ff31518 100644
--- a/docs/tutorials/rlssm_basic.ipynb
+++ b/docs/tutorials/rlssm_basic.ipynb
@@ -1,11 +1,34 @@
 {
  "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "3e9f45e8",
+   "metadata": {},
+   "source": [
+    "# Reinforcement Learning with HSSM\n",
+    "**Reinforcement-Learning Sequential Sampling Models (RLSSMs)** join two ideas that cognitive scientists usually study separately:\n",
+    "    \n",
+    "- a **learning process** — how a participant updates their expectations from\n",
+    "    trial-to-trial feedback (here, the Rescorla–Wagner rule); and\n",
+    "- a **decision process** — how, on each trial, those expectations are turned into\n",
+    "    an actual *choice* and a *response time* (here, a drift-diffusion–style\n",
+    "    sequential sampling model).\n",
+    "\n",
+    "A plain RL model explains *which* option is chosen but ignores *how long* the choice\n",
+    "took. A plain SSM explains the choice/RT on a single decision but assumes the\n",
+    "decision variables are fixed. An RLSSM closes the loop: the value a participant has\n",
+    "*learned* becomes the thing that *drives* the moment-to-moment decision, and it does\n",
+    "so on every trial. This lets us fit choices **and** response times jointly and\n",
+    "recover both the learning parameters (e.g. a learning rate) and the decision\n",
+    "parameters (e.g. boundary separation) from the same data."
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "416c9a6f",
    "metadata": {},
    "source": [
-    "# RLSSM — Basic tutorial\n",
+    "## RLSSM — Basic tutorial\n",
     "\n",
     "This notebook is written for first-time RLSSM users.\n",
     "Run the cells from top to bottom; each section builds directly on the previous one.\n",
@@ -16,7 +39,7 @@
     "- checked a simple recovery summary, and\n",
     "- run an RLSSM-aware posterior predictive check.\n",
     "\n",
-    "> Where this sits in the suite: this is the entry point. Later tutorials cover\n",
+    "> Other utorials cover\n",
     "> custom learning/decision models\n",
     "> ([Custom models with ssms.rl](rlssm_advanced.ipynb) ·\n",
     "> [Restless learner](rlssm_restless_learner.ipynb)) and HSSM-native\n",
@@ -78,11 +101,7 @@
    "source": [
     "## 2. Setup\n",
     "We import HSSM and the `ssms.rl` simulation API, then set two global options that\n",
-    "matter for RLSSM work:\n",
-    "- **`hssm.set_floatX(\"float32\")`** — RLSSM likelihoods run through a JAX scan over\n",
-    "  trials; single precision keeps this fast and is what the RLSSM pipeline is tuned\n",
-    "  for.\n",
-    "- We silence a few noisy library warnings so the notebook output stays readable.\n"
+    "matter for RLSSM work.\n"
    ]
   },
   {
@@ -103,10 +122,12 @@
     "\n",
     "import hssm\n",
     "\n",
+    "# We silence a few noisy library warnings so the notebook output stays readable\n",
     "warnings.filterwarnings(\"ignore\")\n",
     "logging.getLogger(\"jax._src.xla_bridge\").setLevel(logging.ERROR)\n",
-    "hssm.set_floatX(\"float32\", update_jax=True)\n",
-    "RANDOM_SEED = 20260704"
+    "\n",
+    "hssm.set_floatX(\"float32\", update_jax=True) # set default float type to float32 for JAX operations\n",
+    "RANDOM_SEED = 20260704 # for reproducibility of pseudo-random draws used in simulation, posterior sampling, and PPC subsampling."
    ]
   },
   {
@@ -117,7 +138,8 @@
     "### Run size\n",
     "This tutorial uses a quick configuration so readers can complete a full\n",
     "end-to-end RLSSM workflow without long waits.\n",
-    "**Optional longer run (advanced):** after your first pass, increase the values\n",
+    "\n",
+    "> **Optional longer run (advanced):** after your first pass, increase the values\n",
     "in the next cell (participants, trials, tune, and draws) to get tighter\n",
     "recovery and PPC curves.\n"
    ]
@@ -196,7 +218,7 @@
    "metadata": {},
    "source": [
     "## 4. Define ground-truth parameters\n",
-    "Because this is a tutorial, we *simulate* data from known parameters so we can later\n",
+    "We *simulate* data from known parameters so we can later\n",
     "check whether the model recovers them. We choose a **group mean** for each parameter\n",
     "and give each participant a small random deviation around that mean, so participants\n",
     "genuinely differ — that is what the hierarchical model will try to recover.\n",
@@ -462,7 +484,7 @@
    "metadata": {},
    "source": [
     "## 8. A quick recovery check\n",
-    "The first question after fitting is simple: did the model recover the group-level\n",
+    "Having fit the model we now ask: did it recover the group-level\n",
     "values we simulated from? We start with that group-level check here. Participant-by-\n",
     "participant recovery is useful too, but it is easier to read once the basic workflow\n",
     "feels familiar.\n"

From ca7b46fa5637d93c39f27e23e452c756126d388a Mon Sep 17 00:00:00 2001
From: Carlos Paniagua <cpaniaguam@gmail.com>
Date: Fri, 24 Jul 2026 10:32:09 -0400
Subject: [PATCH 4/6] Add rlssm quickstart tutorial

---
 docs/tutorials/rlssm_quickstart.ipynb | 1871 +++++++++++++++++++++++++
 1 file changed, 1871 insertions(+)
 create mode 100644 docs/tutorials/rlssm_quickstart.ipynb

diff --git a/docs/tutorials/rlssm_quickstart.ipynb b/docs/tutorials/rlssm_quickstart.ipynb
new file mode 100644
index 000000000..ae1a454d2
--- /dev/null
+++ b/docs/tutorials/rlssm_quickstart.ipynb
@@ -0,0 +1,1871 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "3e9f45e8",
+   "metadata": {},
+   "source": [
+    "# Reinforcement Learning with HSSM\n",
+    "RLSSMs combine a reinforcement-learning update rule with a sequential sampling\n",
+    "model.\n",
+    "In practice, learned values are updated from feedback and then used to drive both\n",
+    "choices and response times across trials."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "416c9a6f",
+   "metadata": {},
+   "source": [
+    "## RLSSM quickstart\n",
+    "\n",
+    "This notebook is for a first RLSSM fit in HSSM.\n",
+    "It is organized as a practical workflow rather than a full conceptual\n",
+    "introduction.\n",
+    "\n",
+    "By the end you will have:\n",
+    "- simulated a synthetic RLSSM dataset with [`ssm-simulators`](https://github.com/lnccbrown/ssm-simulators) (`ssms.rl`),\n",
+    "- fit a hierarchical (multi-participant) RLSSM in HSSM from the preset `2AB_RW_Angle`,\n",
+    "- checked a simple recovery summary, and\n",
+    "- run an RLSSM-aware posterior predictive check.\n",
+    "\n",
+    "> Other tutorials cover\n",
+    "> custom learning/decision models\n",
+    "> ([Custom models with ssms.rl](rlssm_advanced.ipynb) ·\n",
+    "> [Restless learner](rlssm_restless_learner.ipynb)) and HSSM-native\n",
+    "> registration ([Registering custom models in HSSM](rlssm_hssm_custom_models.ipynb)).\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "9973c549",
+   "metadata": {},
+   "source": [
+    "## 1. What this model does\n",
+    "`2AB_RW_Angle` is a ready-made RLSSM for a two-armed bandit task.\n",
+    "At a high level, each trial has three moving parts:\n",
+    "1. updates option values from feedback with a Rescorla-Wagner learner;\n",
+    "2. converts the value difference into a drift rate with `scaler`;\n",
+    "3. turns that drift into a choice and response time with the angle SSM.\n",
+    "\n",
+    "For this tutorial, the main implementation detail to keep in mind is that the free\n",
+    "parameters are\n",
+    "`rl_alpha`, `scaler`, `a`, `z`, `t`, and `theta`.\n",
+    "The drift `v` is not sampled directly; it is computed from the learned values on each\n",
+    "trial.\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "b982c7b2",
+   "metadata": {},
+   "source": [
+    "## 2. Setup\n",
+    "Import HSSM and the `ssms.rl` API, then set two notebook-wide defaults."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "f090de8f",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/home/cpaniaguam/HSSM/.venv/lib/python3.13/site-packages/tqdm/auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
+      "  from .autonotebook import tqdm as notebook_tqdm\n",
+      "An NVIDIA GPU may be present on this machine, but a CUDA-enabled jaxlib is not installed. Falling back to cpu.\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Setting PyTensor floatX type to float32.\n",
+      "Setting \"jax_enable_x64\" to False. If this is not intended, please set `jax` to False.\n"
+     ]
+    }
+   ],
+   "source": [
+    "import logging\n",
+    "import warnings\n",
+    "\n",
+    "import arviz as az\n",
+    "import matplotlib.pyplot as plt\n",
+    "import numpy as np\n",
+    "import pandas as pd\n",
+    "from ssms import rl\n",
+    "\n",
+    "import hssm\n",
+    "\n",
+    "# We silence a few noisy library warnings so the notebook output stays readable\n",
+    "warnings.filterwarnings(\"ignore\")\n",
+    "logging.getLogger(\"jax._src.xla_bridge\").setLevel(logging.ERROR)\n",
+    "\n",
+    "hssm.set_floatX(\n",
+    "    \"float32\", update_jax=True\n",
+    ")  # set default float type to float32 for JAX operations\n",
+    "RANDOM_SEED = 20260704  # for reproducibility of pseudo-random draws used in simulation, posterior sampling, and PPC subsampling."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "f1205a8b",
+   "metadata": {},
+   "source": [
+    "### Run size\n",
+    "This notebook uses a quick configuration so you can run the full workflow without a\n",
+    "long wait.\n",
+    "\n",
+    "> **Optional longer run (advanced):** after your first pass, increase the values\n",
+    "in the next cell (participants, trials, tune, and draws) to get tighter\n",
+    "recovery and PPC curves.\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "4a45b283",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "quick mode | participants=5 trials=70 tune=300 draws=300\n"
+     ]
+    }
+   ],
+   "source": [
+    "N_PARTICIPANTS = 5\n",
+    "N_TRIALS = 70\n",
+    "N_CHAINS = 2\n",
+    "N_TUNE = 300\n",
+    "N_DRAWS = 300\n",
+    "\n",
+    "print(\n",
+    "    f\"quick mode | participants={N_PARTICIPANTS} trials={N_TRIALS} \"\n",
+    "    f\"tune={N_TUNE} draws={N_DRAWS}\"\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "ae6d444a",
+   "metadata": {},
+   "source": [
+    "## 3. Load the `2AB_RW_Angle` preset\n",
+    "`ssms.rl` presets bundle a task, a learning rule, and a decision model into one\n",
+    "ready-to-use configuration. Here we use `2AB_RW_Angle`: a two-armed bandit with\n",
+    "Rescorla-Wagner learning and an angle decision process.\n",
+    "The next two cells inspect the preset and confirm which parameters are sampled versus\n",
+    "computed.\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "81a5570b",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Preset: 2AB_RW_Angle\n",
+      "Description: Two-armed bandit with a Rescorla-Wagner delta-rule learner and an angle decision process.\n",
+      "Task: two-armed Bernoulli bandit\n",
+      "Learning process: RescorlaWagnerDrift\n",
+      "Decision process: angle\n",
+      "Required parameters: rl_alpha, scaler, a, z, t, theta\n",
+      "Default parameters: rl_alpha=0.2, scaler=2, a=1, z=0.5, t=0.001, theta=0\n",
+      "Response labels: (-1, 1)\n",
+      "Response to choice: {-1: 0, 1: 1}\n",
+      "Context fields: ['feedback']\n",
+      "Learning backend: jax\n",
+      "Gradient support: available\n",
+      "HSSM participant contract: yes\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(rl.preset.info(\"2AB_RW_Angle\"))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "f4b8f53f",
+   "metadata": {},
+   "source": [
+    "For this tutorial, the key distinction is simple: `rl_alpha`, `scaler`, `a`, `z`,\n",
+    "`t`, and `theta` are sampled, while `v` is computed from the learning process.\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "5a61fc70",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "computed params (driven by the learner): ['v']\n"
+     ]
+    }
+   ],
+   "source": [
+    "ssms_config = rl.preset.get(\"2AB_RW_Angle\")\n",
+    "assembled = ssms_config.assemble(backend=\"jax\")\n",
+    "print(\"computed params (driven by the learner):\", assembled.computed_params)\n",
+    "assert \"v\" in assembled.computed_params"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "33fe1561",
+   "metadata": {},
+   "source": [
+    "## 4. Define ground-truth parameters\n",
+    "We simulate data from known parameters so we can later ask whether the hierarchical\n",
+    "fit recovers them.\n",
+    "Each parameter gets a group mean plus participant-level variation. `SDS` controls how\n",
+    "much participants differ, and `BOUNDS` clips sampled values into the supported\n",
+    "ranges.\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "6258c663",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>rl_alpha</th>\n",
+       "      <th>scaler</th>\n",
+       "      <th>a</th>\n",
+       "      <th>z</th>\n",
+       "      <th>t</th>\n",
+       "      <th>theta</th>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>participant_id</th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>0.048</td>\n",
+       "      <td>1.976</td>\n",
+       "      <td>1.425</td>\n",
+       "      <td>0.477</td>\n",
+       "      <td>0.242</td>\n",
+       "      <td>0.380</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>0.118</td>\n",
+       "      <td>2.569</td>\n",
+       "      <td>1.092</td>\n",
+       "      <td>0.468</td>\n",
+       "      <td>0.168</td>\n",
+       "      <td>0.256</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>0.084</td>\n",
+       "      <td>2.381</td>\n",
+       "      <td>1.102</td>\n",
+       "      <td>0.471</td>\n",
+       "      <td>0.320</td>\n",
+       "      <td>0.338</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>0.069</td>\n",
+       "      <td>2.924</td>\n",
+       "      <td>1.554</td>\n",
+       "      <td>0.499</td>\n",
+       "      <td>0.185</td>\n",
+       "      <td>0.323</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>0.111</td>\n",
+       "      <td>2.508</td>\n",
+       "      <td>1.668</td>\n",
+       "      <td>0.396</td>\n",
+       "      <td>0.272</td>\n",
+       "      <td>0.465</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                rl_alpha  scaler      a      z      t  theta\n",
+       "participant_id                                              \n",
+       "0                  0.048   1.976  1.425  0.477  0.242  0.380\n",
+       "1                  0.118   2.569  1.092  0.468  0.168  0.256\n",
+       "2                  0.084   2.381  1.102  0.471  0.320  0.338\n",
+       "3                  0.069   2.924  1.554  0.499  0.185  0.323\n",
+       "4                  0.111   2.508  1.668  0.396  0.272  0.465"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "GROUP_THETA = {\n",
+    "    \"rl_alpha\": 0.08,  # learning rate (small -> gradual, visible learning)\n",
+    "    \"scaler\": 2.5,  # value-difference -> drift gain\n",
+    "    \"a\": 1.2,  # boundary separation\n",
+    "    \"z\": 0.5,  # starting-point bias (0.5 = unbiased)\n",
+    "    \"t\": 0.25,  # non-decision time (s)\n",
+    "    \"theta\": 0.35,  # boundary collapse angle\n",
+    "}\n",
+    "# Between-participant SD for each parameter (individual differences to recover).\n",
+    "SDS = {\n",
+    "    \"rl_alpha\": 0.03,\n",
+    "    \"scaler\": 0.40,\n",
+    "    \"a\": 0.20,\n",
+    "    \"z\": 0.06,\n",
+    "    \"t\": 0.05,\n",
+    "    \"theta\": 0.10,\n",
+    "}\n",
+    "# Keep sampled values inside supported ranges.\n",
+    "BOUNDS = {\n",
+    "    \"rl_alpha\": (0.01, 1.0),\n",
+    "    \"scaler\": (0.1, 5.0),\n",
+    "    \"a\": (0.3, 2.5),\n",
+    "    \"z\": (0.1, 0.9),\n",
+    "    \"t\": (0.05, 1.0),\n",
+    "    \"theta\": (0.0, 1.2),\n",
+    "}\n",
+    "LIST_PARAMS = list(GROUP_THETA)\n",
+    "\n",
+    "rng = np.random.default_rng(RANDOM_SEED)\n",
+    "theta_arrays = {\n",
+    "    name: np.clip(\n",
+    "        rng.normal(GROUP_THETA[name], SDS[name], N_PARTICIPANTS), *BOUNDS[name]\n",
+    "    )\n",
+    "    for name in LIST_PARAMS\n",
+    "}\n",
+    "\n",
+    "# One row per participant: their true parameter values (for the recovery check later).\n",
+    "true_params = pd.DataFrame(theta_arrays)\n",
+    "true_params.index.name = \"participant_id\"\n",
+    "true_params.round(3)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "4f7c7b70",
+   "metadata": {},
+   "source": [
+    "## 5. Simulate the data\n",
+    "`rl.Simulator(...).simulate(...)` runs the full generative loop and returns one row\n",
+    "per trial.\n",
+    "Passing parameter arrays gives each participant their own parameter values while\n",
+    "keeping the dataset balanced across participants.\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "887db61f",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "rows: 350 | columns: ['participant_id', 'trial_id', 'rt', 'response', 'feedback']\n"
+     ]
+    },
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>participant_id</th>\n",
+       "      <th>trial_id</th>\n",
+       "      <th>rt</th>\n",
+       "      <th>response</th>\n",
+       "      <th>feedback</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1.100926</td>\n",
+       "      <td>-1</td>\n",
+       "      <td>1.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>0</td>\n",
+       "      <td>1</td>\n",
+       "      <td>1.998554</td>\n",
+       "      <td>-1</td>\n",
+       "      <td>1.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>0</td>\n",
+       "      <td>2</td>\n",
+       "      <td>2.151356</td>\n",
+       "      <td>-1</td>\n",
+       "      <td>1.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>0</td>\n",
+       "      <td>3</td>\n",
+       "      <td>0.589906</td>\n",
+       "      <td>-1</td>\n",
+       "      <td>1.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>0</td>\n",
+       "      <td>4</td>\n",
+       "      <td>1.172487</td>\n",
+       "      <td>-1</td>\n",
+       "      <td>1.0</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "   participant_id  trial_id        rt  response  feedback\n",
+       "0               0         0  1.100926        -1       1.0\n",
+       "1               0         1  1.998554        -1       1.0\n",
+       "2               0         2  2.151356        -1       1.0\n",
+       "3               0         3  0.589906        -1       1.0\n",
+       "4               0         4  1.172487        -1       1.0"
+      ]
+     },
+     "execution_count": 11,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "data = rl.Simulator(ssms_config).simulate(\n",
+    "    theta=theta_arrays,\n",
+    "    n_trials=N_TRIALS,\n",
+    "    n_participants=N_PARTICIPANTS,\n",
+    "    random_state=RANDOM_SEED,\n",
+    ")\n",
+    "# Validate the panel matches what the model expects before doing anything else.\n",
+    "ssms_config.validate_data(data).raise_for_errors()\n",
+    "\n",
+    "print(\"rows:\", len(data), \"| columns:\", list(data.columns))\n",
+    "data.head()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "0b7a8618",
+   "metadata": {},
+   "source": [
+    "Each row is one trial. Column descriptions:\n",
+    "- `participant_id`, `trial_id`: who and when.\n",
+    "- `rt`: response time in seconds.\n",
+    "- `response`: the chosen arm (-1 or 1).\n",
+    "- `feedback`: reward (0 or 1), used by the learner.\n",
+    "\n",
+    "The next cell is a quick sanity check that the simulated data actually show\n",
+    "learning. It does three things:\n",
+    "1. bins trials into windows of 10;\n",
+    "2. computes choice accuracy as P(chose high-reward arm);\n",
+    "3. computes mean RT per bin.\n",
+    "\n",
+    "Expected pattern: accuracy should rise above chance, and RT should decrease as the\n",
+    "value difference becomes easier to act on.\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "id": "991e7115",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 1200x400 with 2 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "BIN = 10\n",
+    "learn = data[data[\"rt\"] > 0].copy()\n",
+    "learn[\"chose_high\"] = (learn[\"response\"] == -1).astype(float)  # -1 == high-reward arm\n",
+    "learn[\"trial_bin\"] = (learn[\"trial_id\"] // BIN) * BIN\n",
+    "acc_curve = learn.groupby(\"trial_bin\")[\"chose_high\"].mean()\n",
+    "rt_curve = learn.groupby(\"trial_bin\")[\"rt\"].mean()\n",
+    "centers = acc_curve.index + BIN / 2\n",
+    "\n",
+    "fig, axes = plt.subplots(1, 2, figsize=(12, 4), constrained_layout=True)\n",
+    "axes[0].plot(centers, acc_curve.values, \"o-\", color=\"tab:green\")\n",
+    "axes[0].axhline(0.5, color=\"0.7\", ls=\"--\", lw=1, label=\"chance\")\n",
+    "axes[0].set(\n",
+    "    xlabel=\"Trial\",\n",
+    "    ylabel=\"P(chose high-reward arm)\",\n",
+    "    title=\"Accuracy: choices shift to the good arm\",\n",
+    "    ylim=(0, 1),\n",
+    ")\n",
+    "axes[0].legend(frameon=False)\n",
+    "\n",
+    "axes[1].plot(centers, rt_curve.values, \"o-\", color=\"tab:purple\")\n",
+    "axes[1].set(xlabel=\"Trial\", ylabel=\"Mean RT (s)\", title=\"Speed: responses get faster\")\n",
+    "fig.suptitle(\"Learning curves (simulated data)\")\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "db9b5799",
+   "metadata": {},
+   "source": [
+    "## 6. Build the HSSM model\n",
+    "We now fit the same preset directly in HSSM.\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "f07adb27",
+   "metadata": {},
+   "source": [
+    "To keep the fit readable, we use one helper that applies the same hierarchical\n",
+    "template to every free parameter: one group intercept plus participant-level\n",
+    "deviations.\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "id": "52e648b3",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Prior on the per-participant deviations: mean 0, with a learned spread (sigma).\n",
+    "PARTICIPANT_EFFECT_PRIOR = {\n",
+    "    \"name\": \"Normal\",\n",
+    "    \"mu\": 0,\n",
+    "    \"sigma\": {\"name\": \"HalfNormal\", \"sigma\": 0.5},\n",
+    "}\n",
+    "\n",
+    "\n",
+    "def hierarchical_param(name, lower, upper, mu, sigma):\n",
+    "    \"\"\"Build a group intercept (TruncatedNormal) + per-participant random effect.\"\"\"\n",
+    "    return hssm.Param(\n",
+    "        name,\n",
+    "        formula=f\"{name} ~ 1 + (1|participant_id)\",\n",
+    "        prior={\n",
+    "            \"Intercept\": hssm.Prior(\n",
+    "                \"TruncatedNormal\", lower=lower, upper=upper, mu=mu, sigma=sigma\n",
+    "            ),\n",
+    "            \"1|participant_id\": PARTICIPANT_EFFECT_PRIOR,\n",
+    "        },\n",
+    "    )"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "f0cdcee8",
+   "metadata": {},
+   "source": [
+    "A few arguments deserve a quick note:\n",
+    "- **`model=\"2AB_RW_Angle\"`** tells HSSM to use the same preset we simulated from.\n",
+    "- **`include=[...]`** applies the same hierarchical prior template to each free parameter.\n",
+    "- **`p_outlier=0` / `lapse=None`** turn off the outlier/lapse mixture for this first fit.\n",
+    "- **`process_initvals=False`** is the main RLSSM-specific setting to remember in this\n",
+    "  basic workflow.\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "id": "f44b2a62",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Warning: You are sending unauthenticated requests to the HF Hub. Please set a HF_TOKEN to enable higher rate limits and faster downloads.\n",
+      "You supplied a model '2AB_RW_Angle', which is currently not supported in the ssm_simulators package. An error will be thrown when sampling from the random variable or when using any posterior or prior predictive sampling methods.\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Model initialized successfully.\n",
+      "participants: 5 | trials/participant: 70\n",
+      "free parameters: ['rl_alpha', 'scaler', 'a', 'z', 't', 'theta']\n"
+     ]
+    }
+   ],
+   "source": [
+    "model = hssm.RLSSM(\n",
+    "    data=data,\n",
+    "    model=\"2AB_RW_Angle\",\n",
+    "    p_outlier=0,\n",
+    "    lapse=None,\n",
+    "    process_initvals=False,\n",
+    "    include=[\n",
+    "        hierarchical_param(\"rl_alpha\", 0.01, 1.0, 0.15, 0.15),\n",
+    "        hierarchical_param(\"scaler\", 0.1, 5.0, 2.0, 0.8),\n",
+    "        hierarchical_param(\"a\", 0.3, 2.5, 1.1, 0.3),\n",
+    "        hierarchical_param(\"z\", 0.1, 0.9, 0.5, 0.15),\n",
+    "        hierarchical_param(\"t\", 0.05, 1.0, 0.25, 0.1),\n",
+    "        hierarchical_param(\"theta\", 0.0, 1.2, 0.35, 0.15),\n",
+    "    ],\n",
+    ")\n",
+    "\n",
+    "print(\"participants:\", model.n_participants, \"| trials/participant:\", model.n_trials)\n",
+    "print(\"free parameters:\", list(model.params.keys()))\n",
+    "assert model.model_name == \"2AB_RW_Angle\"\n",
+    "assert \"rl_alpha\" in model.params\n",
+    "assert \"v\" not in model.params  # computed by the learner, never sampled"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "23ab0dd2",
+   "metadata": {},
+   "source": [
+    "## 7. Sample the posterior\n",
+    "This is the estimation step.\n",
+    "The run is intentionally short so the notebook stays usable as a first-pass\n",
+    "workflow example.\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "id": "e4bb5cd3",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Using default initvals. \n",
+      "\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "NUTS[numpyro]: [rl_alpha_Intercept, rl_alpha_1|participant_id_sigma, rl_alpha_1|participant_id_offset, scaler_Intercept, scaler_1|participant_id_sigma, scaler_1|participant_id_offset, a_Intercept, a_1|participant_id_sigma, a_1|participant_id_offset, z_Intercept, z_1|participant_id_sigma, z_1|participant_id_offset, t_Intercept, t_1|participant_id_sigma, t_1|participant_id_offset, theta_Intercept, theta_1|participant_id_sigma, theta_1|participant_id_offset]\n",
+      "sample: 100%|██████████| 600/600 [00:50<00:00, 11.82it/s, 127 steps of size 4.31e-02. acc. prob=0.96]\n",
+      "sample: 100%|██████████| 600/600 [00:37<00:00, 16.16it/s, 127 steps of size 5.79e-02. acc. prob=0.93]\n",
+      "There were 80 divergences after tuning. Increase `target_accept` or reparameterize.\n",
+      "We recommend running at least 4 chains for robust computation of convergence diagnostics\n",
+      "The rhat statistic is larger than 1.01 for some parameters. This indicates problems during sampling. See https://arxiv.org/abs/1903.08008 for details\n",
+      "The effective sample size per chain is smaller than 100 for some parameters.  A higher number is needed for reliable rhat and ess computation. See https://arxiv.org/abs/1903.08008 for details\n"
+     ]
+    },
+    {
+     "data": {
+      "text/html": [
+       "<div><svg style=\"position: absolute; width: 0; height: 0; overflow: hidden\">\n",
+       "<defs>\n",
+       "<symbol id=\"icon-database\" viewBox=\"0 0 32 32\">\n",
+       "<path d=\"M16 0c-8.837 0-16 2.239-16 5v4c0 2.761 7.163 5 16 5s16-2.239 16-5v-4c0-2.761-7.163-5-16-5z\"></path>\n",
+       "<path d=\"M16 17c-8.837 0-16-2.239-16-5v6c0 2.761 7.163 5 16 5s16-2.239 16-5v-6c0 2.761-7.163 5-16 5z\"></path>\n",
+       "<path d=\"M16 26c-8.837 0-16-2.239-16-5v6c0 2.761 7.163 5 16 5s16-2.239 16-5v-6c0 2.761-7.163 5-16 5z\"></path>\n",
+       "</symbol>\n",
+       "<symbol id=\"icon-file-text2\" viewBox=\"0 0 32 32\">\n",
+       "<path d=\"M28.681 7.159c-0.694-0.947-1.662-2.053-2.724-3.116s-2.169-2.030-3.116-2.724c-1.612-1.182-2.393-1.319-2.841-1.319h-15.5c-1.378 0-2.5 1.121-2.5 2.5v27c0 1.378 1.122 2.5 2.5 2.5h23c1.378 0 2.5-1.122 2.5-2.5v-19.5c0-0.448-0.137-1.23-1.319-2.841zM24.543 5.457c0.959 0.959 1.712 1.825 2.268 2.543h-4.811v-4.811c0.718 0.556 1.584 1.309 2.543 2.268zM28 29.5c0 0.271-0.229 0.5-0.5 0.5h-23c-0.271 0-0.5-0.229-0.5-0.5v-27c0-0.271 0.229-0.5 0.5-0.5 0 0 15.499-0 15.5 0v7c0 0.552 0.448 1 1 1h7v19.5z\"></path>\n",
+       "<path d=\"M23 26h-14c-0.552 0-1-0.448-1-1s0.448-1 1-1h14c0.552 0 1 0.448 1 1s-0.448 1-1 1z\"></path>\n",
+       "<path d=\"M23 22h-14c-0.552 0-1-0.448-1-1s0.448-1 1-1h14c0.552 0 1 0.448 1 1s-0.448 1-1 1z\"></path>\n",
+       "<path d=\"M23 18h-14c-0.552 0-1-0.448-1-1s0.448-1 1-1h14c0.552 0 1 0.448 1 1s-0.448 1-1 1z\"></path>\n",
+       "</symbol>\n",
+       "</defs>\n",
+       "</svg>\n",
+       "<style>/* CSS stylesheet for displaying xarray objects in notebooks */\n",
+       "\n",
+       ":root {\n",
+       "  --xr-font-color0: var(\n",
+       "    --jp-content-font-color0,\n",
+       "    var(--pst-color-text-base rgba(0, 0, 0, 1))\n",
+       "  );\n",
+       "  --xr-font-color2: var(\n",
+       "    --jp-content-font-color2,\n",
+       "    var(--pst-color-text-base, rgba(0, 0, 0, 0.54))\n",
+       "  );\n",
+       "  --xr-font-color3: var(\n",
+       "    --jp-content-font-color3,\n",
+       "    var(--pst-color-text-base, rgba(0, 0, 0, 0.38))\n",
+       "  );\n",
+       "  --xr-border-color: var(\n",
+       "    --jp-border-color2,\n",
+       "    hsl(from var(--pst-color-on-background, white) h s calc(l - 10))\n",
+       "  );\n",
+       "  --xr-disabled-color: var(\n",
+       "    --jp-layout-color3,\n",
+       "    hsl(from var(--pst-color-on-background, white) h s calc(l - 40))\n",
+       "  );\n",
+       "  --xr-background-color: var(\n",
+       "    --jp-layout-color0,\n",
+       "    var(--pst-color-on-background, white)\n",
+       "  );\n",
+       "  --xr-background-color-row-even: var(\n",
+       "    --jp-layout-color1,\n",
+       "    hsl(from var(--pst-color-on-background, white) h s calc(l - 5))\n",
+       "  );\n",
+       "  --xr-background-color-row-odd: var(\n",
+       "    --jp-layout-color2,\n",
+       "    hsl(from var(--pst-color-on-background, white) h s calc(l - 15))\n",
+       "  );\n",
+       "}\n",
+       "\n",
+       "html[theme=\"dark\"],\n",
+       "html[data-theme=\"dark\"],\n",
+       "body[data-theme=\"dark\"],\n",
+       "body.vscode-dark {\n",
+       "  --xr-font-color0: var(\n",
+       "    --jp-content-font-color0,\n",
+       "    var(--pst-color-text-base, rgba(255, 255, 255, 1))\n",
+       "  );\n",
+       "  --xr-font-color2: var(\n",
+       "    --jp-content-font-color2,\n",
+       "    var(--pst-color-text-base, rgba(255, 255, 255, 0.54))\n",
+       "  );\n",
+       "  --xr-font-color3: var(\n",
+       "    --jp-content-font-color3,\n",
+       "    var(--pst-color-text-base, rgba(255, 255, 255, 0.38))\n",
+       "  );\n",
+       "  --xr-border-color: var(\n",
+       "    --jp-border-color2,\n",
+       "    hsl(from var(--pst-color-on-background, #111111) h s calc(l + 10))\n",
+       "  );\n",
+       "  --xr-disabled-color: var(\n",
+       "    --jp-layout-color3,\n",
+       "    hsl(from var(--pst-color-on-background, #111111) h s calc(l + 40))\n",
+       "  );\n",
+       "  --xr-background-color: var(\n",
+       "    --jp-layout-color0,\n",
+       "    var(--pst-color-on-background, #111111)\n",
+       "  );\n",
+       "  --xr-background-color-row-even: var(\n",
+       "    --jp-layout-color1,\n",
+       "    hsl(from var(--pst-color-on-background, #111111) h s calc(l + 5))\n",
+       "  );\n",
+       "  --xr-background-color-row-odd: var(\n",
+       "    --jp-layout-color2,\n",
+       "    hsl(from var(--pst-color-on-background, #111111) h s calc(l + 15))\n",
+       "  );\n",
+       "}\n",
+       "\n",
+       ".xr-wrap {\n",
+       "  display: block !important;\n",
+       "  min-width: 300px;\n",
+       "  max-width: 700px;\n",
+       "  line-height: 1.6;\n",
+       "  padding-bottom: 4px;\n",
+       "}\n",
+       "\n",
+       ".xr-text-repr-fallback {\n",
+       "  /* fallback to plain text repr when CSS is not injected (untrusted notebook) */\n",
+       "  display: none;\n",
+       "}\n",
+       "\n",
+       ".xr-header {\n",
+       "  padding-top: 6px;\n",
+       "  padding-bottom: 6px;\n",
+       "}\n",
+       "\n",
+       ".xr-header {\n",
+       "  border-bottom: solid 1px var(--xr-border-color);\n",
+       "  margin-bottom: 4px;\n",
+       "}\n",
+       "\n",
+       ".xr-header > div,\n",
+       ".xr-header > ul {\n",
+       "  display: inline;\n",
+       "  margin-top: 0;\n",
+       "  margin-bottom: 0;\n",
+       "}\n",
+       "\n",
+       ".xr-obj-type,\n",
+       ".xr-obj-name {\n",
+       "  margin-left: 2px;\n",
+       "  margin-right: 10px;\n",
+       "}\n",
+       "\n",
+       ".xr-obj-type,\n",
+       ".xr-group-box-contents > label {\n",
+       "  color: var(--xr-font-color2);\n",
+       "  display: block;\n",
+       "}\n",
+       "\n",
+       ".xr-sections {\n",
+       "  padding-left: 0 !important;\n",
+       "  display: grid;\n",
+       "  grid-template-columns: 150px auto auto 1fr 0 20px 0 20px;\n",
+       "  margin-block-start: 0;\n",
+       "  margin-block-end: 0;\n",
+       "}\n",
+       "\n",
+       ".xr-section-item {\n",
+       "  display: contents;\n",
+       "}\n",
+       "\n",
+       ".xr-section-item > input,\n",
+       ".xr-group-box-contents > input,\n",
+       ".xr-array-wrap > input {\n",
+       "  display: block;\n",
+       "  opacity: 0;\n",
+       "  height: 0;\n",
+       "  margin: 0;\n",
+       "}\n",
+       "\n",
+       ".xr-section-item > input + label,\n",
+       ".xr-var-item > input + label {\n",
+       "  color: var(--xr-disabled-color);\n",
+       "}\n",
+       "\n",
+       ".xr-section-item > input:enabled + label,\n",
+       ".xr-var-item > input:enabled + label,\n",
+       ".xr-array-wrap > input:enabled + label,\n",
+       ".xr-group-box-contents > input:enabled + label {\n",
+       "  cursor: pointer;\n",
+       "  color: var(--xr-font-color2);\n",
+       "}\n",
+       "\n",
+       ".xr-section-item > input:focus-visible + label,\n",
+       ".xr-var-item > input:focus-visible + label,\n",
+       ".xr-array-wrap > input:focus-visible + label,\n",
+       ".xr-group-box-contents > input:focus-visible + label {\n",
+       "  outline: auto;\n",
+       "}\n",
+       "\n",
+       ".xr-section-item > input:enabled + label:hover,\n",
+       ".xr-var-item > input:enabled + label:hover,\n",
+       ".xr-array-wrap > input:enabled + label:hover,\n",
+       ".xr-group-box-contents > input:enabled + label:hover {\n",
+       "  color: var(--xr-font-color0);\n",
+       "}\n",
+       "\n",
+       ".xr-section-summary {\n",
+       "  grid-column: 1;\n",
+       "  color: var(--xr-font-color2);\n",
+       "  font-weight: 500;\n",
+       "  white-space: nowrap;\n",
+       "}\n",
+       "\n",
+       ".xr-section-summary > em {\n",
+       "  font-weight: normal;\n",
+       "}\n",
+       "\n",
+       ".xr-span-grid {\n",
+       "  grid-column-end: -1;\n",
+       "}\n",
+       "\n",
+       ".xr-section-summary > span {\n",
+       "  display: inline-block;\n",
+       "  padding-left: 0.3em;\n",
+       "}\n",
+       "\n",
+       ".xr-group-box-contents > input:checked + label > span {\n",
+       "  display: inline-block;\n",
+       "  padding-left: 0.6em;\n",
+       "}\n",
+       "\n",
+       ".xr-section-summary-in:disabled + label {\n",
+       "  color: var(--xr-font-color2);\n",
+       "}\n",
+       "\n",
+       ".xr-section-summary-in + label:before {\n",
+       "  display: inline-block;\n",
+       "  content: \"►\";\n",
+       "  font-size: 11px;\n",
+       "  width: 15px;\n",
+       "  text-align: center;\n",
+       "}\n",
+       "\n",
+       ".xr-section-summary-in:disabled + label:before {\n",
+       "  color: var(--xr-disabled-color);\n",
+       "}\n",
+       "\n",
+       ".xr-section-summary-in:checked + label:before {\n",
+       "  content: \"▼\";\n",
+       "}\n",
+       "\n",
+       ".xr-section-summary-in:checked + label > span {\n",
+       "  display: none;\n",
+       "}\n",
+       "\n",
+       ".xr-section-summary,\n",
+       ".xr-section-inline-details,\n",
+       ".xr-group-box-contents > label {\n",
+       "  padding-top: 4px;\n",
+       "}\n",
+       "\n",
+       ".xr-section-inline-details {\n",
+       "  grid-column: 2 / -1;\n",
+       "}\n",
+       "\n",
+       ".xr-section-details {\n",
+       "  grid-column: 1 / -1;\n",
+       "  margin-top: 4px;\n",
+       "  margin-bottom: 5px;\n",
+       "}\n",
+       "\n",
+       ".xr-section-summary-in ~ .xr-section-details {\n",
+       "  display: none;\n",
+       "}\n",
+       "\n",
+       ".xr-section-summary-in:checked ~ .xr-section-details {\n",
+       "  display: contents;\n",
+       "}\n",
+       "\n",
+       ".xr-children {\n",
+       "  display: inline-grid;\n",
+       "  grid-template-columns: 100%;\n",
+       "  grid-column: 1 / -1;\n",
+       "  padding-top: 4px;\n",
+       "}\n",
+       "\n",
+       ".xr-group-box {\n",
+       "  display: inline-grid;\n",
+       "  grid-template-columns: 0px 30px auto;\n",
+       "}\n",
+       "\n",
+       ".xr-group-box-vline {\n",
+       "  grid-column-start: 1;\n",
+       "  border-right: 0.2em solid;\n",
+       "  border-color: var(--xr-border-color);\n",
+       "  width: 0px;\n",
+       "}\n",
+       "\n",
+       ".xr-group-box-hline {\n",
+       "  grid-column-start: 2;\n",
+       "  grid-row-start: 1;\n",
+       "  height: 1em;\n",
+       "  width: 26px;\n",
+       "  border-bottom: 0.2em solid;\n",
+       "  border-color: var(--xr-border-color);\n",
+       "}\n",
+       "\n",
+       ".xr-group-box-contents {\n",
+       "  grid-column-start: 3;\n",
+       "  padding-bottom: 4px;\n",
+       "}\n",
+       "\n",
+       ".xr-group-box-contents > label::before {\n",
+       "  content: \"📂\";\n",
+       "  padding-right: 0.3em;\n",
+       "}\n",
+       "\n",
+       ".xr-group-box-contents > input:checked + label::before {\n",
+       "  content: \"📁\";\n",
+       "}\n",
+       "\n",
+       ".xr-group-box-contents > input:checked + label {\n",
+       "  padding-bottom: 0px;\n",
+       "}\n",
+       "\n",
+       ".xr-group-box-contents > input:checked ~ .xr-sections {\n",
+       "  display: none;\n",
+       "}\n",
+       "\n",
+       ".xr-group-box-contents > input + label > span {\n",
+       "  display: none;\n",
+       "}\n",
+       "\n",
+       ".xr-group-box-ellipsis {\n",
+       "  font-size: 1.4em;\n",
+       "  font-weight: 900;\n",
+       "  color: var(--xr-font-color2);\n",
+       "  letter-spacing: 0.15em;\n",
+       "  cursor: default;\n",
+       "}\n",
+       "\n",
+       ".xr-array-wrap {\n",
+       "  grid-column: 1 / -1;\n",
+       "  display: grid;\n",
+       "  grid-template-columns: 20px auto;\n",
+       "}\n",
+       "\n",
+       ".xr-array-wrap > label {\n",
+       "  grid-column: 1;\n",
+       "  vertical-align: top;\n",
+       "}\n",
+       "\n",
+       ".xr-preview {\n",
+       "  color: var(--xr-font-color3);\n",
+       "}\n",
+       "\n",
+       ".xr-array-preview,\n",
+       ".xr-array-data {\n",
+       "  padding: 0 5px !important;\n",
+       "  grid-column: 2;\n",
+       "}\n",
+       "\n",
+       ".xr-array-data,\n",
+       ".xr-array-in:checked ~ .xr-array-preview {\n",
+       "  display: none;\n",
+       "}\n",
+       "\n",
+       ".xr-array-in:checked ~ .xr-array-data,\n",
+       ".xr-array-preview {\n",
+       "  display: inline-block;\n",
+       "}\n",
+       "\n",
+       ".xr-dim-list {\n",
+       "  display: inline-block !important;\n",
+       "  list-style: none;\n",
+       "  padding: 0 !important;\n",
+       "  margin: 0;\n",
+       "}\n",
+       "\n",
+       ".xr-dim-list li {\n",
+       "  display: inline-block;\n",
+       "  padding: 0;\n",
+       "  margin: 0;\n",
+       "}\n",
+       "\n",
+       ".xr-dim-list:before {\n",
+       "  content: \"(\";\n",
+       "}\n",
+       "\n",
+       ".xr-dim-list:after {\n",
+       "  content: \")\";\n",
+       "}\n",
+       "\n",
+       ".xr-dim-list li:not(:last-child):after {\n",
+       "  content: \",\";\n",
+       "  padding-right: 5px;\n",
+       "}\n",
+       "\n",
+       ".xr-has-index {\n",
+       "  font-weight: bold;\n",
+       "}\n",
+       "\n",
+       ".xr-var-list,\n",
+       ".xr-var-item {\n",
+       "  display: contents;\n",
+       "}\n",
+       "\n",
+       ".xr-var-item > div,\n",
+       ".xr-var-item label,\n",
+       ".xr-var-item > .xr-var-name span {\n",
+       "  background-color: var(--xr-background-color-row-even);\n",
+       "  border-color: var(--xr-background-color-row-odd);\n",
+       "  margin-bottom: 0;\n",
+       "  padding-top: 2px;\n",
+       "}\n",
+       "\n",
+       ".xr-var-item > .xr-var-name:hover span {\n",
+       "  padding-right: 5px;\n",
+       "}\n",
+       "\n",
+       ".xr-var-list > li:nth-child(odd) > div,\n",
+       ".xr-var-list > li:nth-child(odd) > label,\n",
+       ".xr-var-list > li:nth-child(odd) > .xr-var-name span {\n",
+       "  background-color: var(--xr-background-color-row-odd);\n",
+       "  border-color: var(--xr-background-color-row-even);\n",
+       "}\n",
+       "\n",
+       ".xr-var-name {\n",
+       "  grid-column: 1;\n",
+       "}\n",
+       "\n",
+       ".xr-var-dims {\n",
+       "  grid-column: 2;\n",
+       "}\n",
+       "\n",
+       ".xr-var-dtype {\n",
+       "  grid-column: 3;\n",
+       "  text-align: right;\n",
+       "  color: var(--xr-font-color2);\n",
+       "}\n",
+       "\n",
+       ".xr-var-preview {\n",
+       "  grid-column: 4;\n",
+       "}\n",
+       "\n",
+       ".xr-index-preview {\n",
+       "  grid-column: 2 / 5;\n",
+       "  color: var(--xr-font-color2);\n",
+       "}\n",
+       "\n",
+       ".xr-var-name,\n",
+       ".xr-var-dims,\n",
+       ".xr-var-dtype,\n",
+       ".xr-preview,\n",
+       ".xr-attrs dt {\n",
+       "  white-space: nowrap;\n",
+       "  overflow: hidden;\n",
+       "  text-overflow: ellipsis;\n",
+       "  padding-right: 10px;\n",
+       "}\n",
+       "\n",
+       ".xr-var-name:hover,\n",
+       ".xr-var-dims:hover,\n",
+       ".xr-var-dtype:hover,\n",
+       ".xr-attrs dt:hover {\n",
+       "  overflow: visible;\n",
+       "  width: auto;\n",
+       "  z-index: 1;\n",
+       "}\n",
+       "\n",
+       ".xr-var-attrs,\n",
+       ".xr-var-data,\n",
+       ".xr-index-data {\n",
+       "  display: none;\n",
+       "  border-top: 2px dotted var(--xr-background-color);\n",
+       "  padding-bottom: 20px !important;\n",
+       "  padding-top: 10px !important;\n",
+       "}\n",
+       "\n",
+       ".xr-var-attrs-in + label,\n",
+       ".xr-var-data-in + label,\n",
+       ".xr-index-data-in + label {\n",
+       "  padding: 0 1px;\n",
+       "}\n",
+       "\n",
+       ".xr-var-attrs-in:checked ~ .xr-var-attrs,\n",
+       ".xr-var-data-in:checked ~ .xr-var-data,\n",
+       ".xr-index-data-in:checked ~ .xr-index-data {\n",
+       "  display: block;\n",
+       "}\n",
+       "\n",
+       ".xr-var-data > table {\n",
+       "  float: right;\n",
+       "}\n",
+       "\n",
+       ".xr-var-data > pre,\n",
+       ".xr-index-data > pre,\n",
+       ".xr-var-data > table > tbody > tr {\n",
+       "  background-color: transparent !important;\n",
+       "}\n",
+       "\n",
+       ".xr-var-name span,\n",
+       ".xr-var-data,\n",
+       ".xr-index-name div,\n",
+       ".xr-index-data,\n",
+       ".xr-attrs {\n",
+       "  padding-left: 25px !important;\n",
+       "}\n",
+       "\n",
+       ".xr-attrs,\n",
+       ".xr-var-attrs,\n",
+       ".xr-var-data,\n",
+       ".xr-index-data {\n",
+       "  grid-column: 1 / -1;\n",
+       "}\n",
+       "\n",
+       "dl.xr-attrs {\n",
+       "  padding: 0;\n",
+       "  margin: 0;\n",
+       "  display: grid;\n",
+       "  grid-template-columns: 125px auto;\n",
+       "}\n",
+       "\n",
+       ".xr-attrs dt,\n",
+       ".xr-attrs dd {\n",
+       "  padding: 0;\n",
+       "  margin: 0;\n",
+       "  float: left;\n",
+       "  padding-right: 10px;\n",
+       "  width: auto;\n",
+       "}\n",
+       "\n",
+       ".xr-attrs dt {\n",
+       "  font-weight: normal;\n",
+       "  grid-column: 1;\n",
+       "}\n",
+       "\n",
+       ".xr-attrs dt:hover span {\n",
+       "  display: inline-block;\n",
+       "  background: var(--xr-background-color);\n",
+       "  padding-right: 10px;\n",
+       "}\n",
+       "\n",
+       ".xr-attrs dd {\n",
+       "  grid-column: 2;\n",
+       "  white-space: pre-wrap;\n",
+       "  word-break: break-all;\n",
+       "}\n",
+       "\n",
+       ".xr-icon-database,\n",
+       ".xr-icon-file-text2,\n",
+       ".xr-no-icon {\n",
+       "  display: inline-block;\n",
+       "  vertical-align: middle;\n",
+       "  width: 1em;\n",
+       "  height: 1.5em !important;\n",
+       "  stroke-width: 0;\n",
+       "  stroke: currentColor;\n",
+       "  fill: currentColor;\n",
+       "}\n",
+       "\n",
+       ".xr-var-attrs-in:checked + label > .xr-icon-file-text2,\n",
+       ".xr-var-data-in:checked + label > .xr-icon-database,\n",
+       ".xr-index-data-in:checked + label > .xr-icon-database {\n",
+       "  color: var(--xr-font-color0);\n",
+       "  filter: drop-shadow(1px 1px 5px var(--xr-font-color2));\n",
+       "  stroke-width: 0.8px;\n",
+       "}\n",
+       "</style><pre class='xr-text-repr-fallback'>&lt;xarray.DataTree&gt;\n",
+       "Group: /\n",
+       "├── Group: /posterior\n",
+       "│       Dimensions:                                (chain: 2, draw: 300,\n",
+       "│                                                   participant_id__factor_dim: 5,\n",
+       "│                                                   rl_alpha_1|participant_id__factor_dim: 5)\n",
+       "│       Coordinates:\n",
+       "│         * chain                                  (chain) int64 16B 0 1\n",
+       "│         * draw                                   (draw) int64 2kB 0 1 2 ... 298 299\n",
+       "│         * participant_id__factor_dim             (participant_id__factor_dim) &lt;U1 20B ...\n",
+       "│         * rl_alpha_1|participant_id__factor_dim  (rl_alpha_1|participant_id__factor_dim) &lt;U1 20B ...\n",
+       "│       Data variables: (12/24)\n",
+       "│           z_1|participant_id_offset              (chain, draw, participant_id__factor_dim) float32 12kB ...\n",
+       "│           z_Intercept                            (chain, draw) float32 2kB ...\n",
+       "│           scaler_1|participant_id_offset         (chain, draw, participant_id__factor_dim) float32 12kB ...\n",
+       "│           a_1|participant_id_offset              (chain, draw, participant_id__factor_dim) float32 12kB ...\n",
+       "│           a_1|participant_id                     (chain, draw, participant_id__factor_dim) float32 12kB ...\n",
+       "│           t_1|participant_id_sigma               (chain, draw) float32 2kB ...\n",
+       "│           ...                                     ...\n",
+       "│           z_1|participant_id_sigma               (chain, draw) float32 2kB ...\n",
+       "│           rl_alpha_1|participant_id_offset       (chain, draw, rl_alpha_1|participant_id__factor_dim) float32 12kB ...\n",
+       "│           scaler_Intercept                       (chain, draw) float32 2kB ...\n",
+       "│           t_1|participant_id                     (chain, draw, participant_id__factor_dim) float32 12kB ...\n",
+       "│           scaler_1|participant_id_sigma          (chain, draw) float32 2kB ...\n",
+       "│           t_1|participant_id_offset              (chain, draw, participant_id__factor_dim) float32 12kB ...\n",
+       "│       Attributes:\n",
+       "│           created_at:                  2026-07-24T14:18:40.484086+00:00\n",
+       "│           creation_library:            ArviZ\n",
+       "│           creation_library_version:    1.2.0\n",
+       "│           creation_library_language:   Python\n",
+       "│           sample_dims:                 [&#x27;chain&#x27;, &#x27;draw&#x27;]\n",
+       "│           inference_library:           numpyro\n",
+       "│           inference_library_version:   0.21.0\n",
+       "│           sampling_time:               92.736215\n",
+       "│           tuning_steps:                300\n",
+       "│           modeling_interface:          bambi\n",
+       "│           modeling_interface_version:  0.19.0\n",
+       "├── Group: /sample_stats\n",
+       "│       Dimensions:          (chain: 2, draw: 300)\n",
+       "│       Coordinates:\n",
+       "│         * chain            (chain) int64 16B 0 1\n",
+       "│         * draw             (draw) int64 2kB 0 1 2 3 4 5 6 ... 294 295 296 297 298 299\n",
+       "│       Data variables:\n",
+       "│           acceptance_rate  (chain, draw) float32 2kB ...\n",
+       "│           step_size        (chain, draw) float32 2kB ...\n",
+       "│           diverging        (chain, draw) bool 600B ...\n",
+       "│           energy           (chain, draw) float32 2kB ...\n",
+       "│           n_steps          (chain, draw) int32 2kB ...\n",
+       "│           tree_depth       (chain, draw) int64 5kB 7 7 7 7 7 7 7 7 ... 6 6 6 6 7 6 6 7\n",
+       "│           lp               (chain, draw) float32 2kB ...\n",
+       "│       Attributes:\n",
+       "│           created_at:                  2026-07-24T14:18:40.498297+00:00\n",
+       "│           creation_library:            ArviZ\n",
+       "│           creation_library_version:    1.2.0\n",
+       "│           creation_library_language:   Python\n",
+       "│           sample_dims:                 [&#x27;chain&#x27;, &#x27;draw&#x27;]\n",
+       "│           modeling_interface:          bambi\n",
+       "│           modeling_interface_version:  0.19.0\n",
+       "├── Group: /observed_data\n",
+       "│       Dimensions:                  (__obs__: 350, rt,response_extra_dim_0: 2)\n",
+       "│       Coordinates:\n",
+       "│         * __obs__                  (__obs__) int64 3kB 0 1 2 3 4 ... 346 347 348 349\n",
+       "│         * rt,response_extra_dim_0  (rt,response_extra_dim_0) int64 16B 0 1\n",
+       "│       Data variables:\n",
+       "│           rt,response              (__obs__, rt,response_extra_dim_0) float32 3kB 1...\n",
+       "│       Attributes:\n",
+       "│           created_at:                  2026-07-24T14:18:40.499371+00:00\n",
+       "│           creation_library:            ArviZ\n",
+       "│           creation_library_version:    1.2.0\n",
+       "│           creation_library_language:   Python\n",
+       "│           sample_dims:                 []\n",
+       "│           modeling_interface:          bambi\n",
+       "│           modeling_interface_version:  0.19.0\n",
+       "├── Group: /constant_data\n",
+       "│       Attributes:\n",
+       "│           created_at:                  2026-07-24T14:18:40.499495+00:00\n",
+       "│           creation_library:            ArviZ\n",
+       "│           creation_library_version:    1.2.0\n",
+       "│           creation_library_language:   Python\n",
+       "│           sample_dims:                 []\n",
+       "│           modeling_interface:          bambi\n",
+       "│           modeling_interface_version:  0.19.0\n",
+       "└── Group: /log_likelihood\n",
+       "        Dimensions:      (chain: 2, draw: 300, __obs__: 350)\n",
+       "        Coordinates:\n",
+       "          * chain        (chain) int64 16B 0 1\n",
+       "          * draw         (draw) int64 2kB 0 1 2 3 4 5 6 ... 293 294 295 296 297 298 299\n",
+       "          * __obs__      (__obs__) int64 3kB 0 1 2 3 4 5 6 ... 344 345 346 347 348 349\n",
+       "        Data variables:\n",
+       "            rt,response  (chain, draw, __obs__) float64 2MB -0.9516 -1.938 ... -0.2128\n",
+       "        Attributes:\n",
+       "            modeling_interface:          bambi\n",
+       "            modeling_interface_version:  0.19.0</pre><div class='xr-wrap' style='display:none'><div class='xr-header'><div class='xr-obj-type'>xarray.DataTree</div></div><ul class='xr-sections'><li class='xr-section-item'><div class='xr-children'><div class='xr-group-box'><div class='xr-group-box-vline' style='height: 100%'></div><div class='xr-group-box-hline'></div><div class='xr-group-box-contents'><input id='group-5997ee09-02eb-4eb1-965d-3b9925d4b080' type='checkbox' checked /><label for='group-5997ee09-02eb-4eb1-965d-3b9925d4b080' title='Expand/collapse group'>/posterior<span>(39)</span></label><ul class='xr-sections'><li class='xr-section-item'><input id='section-038e5b00-c340-41c0-bb0e-3be7767cbb8d' class='xr-section-summary-in' type='checkbox' disabled /><label for='section-038e5b00-c340-41c0-bb0e-3be7767cbb8d' class='xr-section-summary'>Dimensions:</label><div class='xr-section-inline-details'><ul class='xr-dim-list'><li><span class='xr-has-index'>chain</span>: 2</li><li><span class='xr-has-index'>draw</span>: 300</li><li><span class='xr-has-index'>participant_id__factor_dim</span>: 5</li><li><span class='xr-has-index'>rl_alpha_1|participant_id__factor_dim</span>: 5</li></ul></div></li><li class='xr-section-item'><input id='section-da4d6ce4-bc60-4a0f-b6a7-ce4af3f97756' class='xr-section-summary-in' type='checkbox' checked /><label for='section-da4d6ce4-bc60-4a0f-b6a7-ce4af3f97756' class='xr-section-summary' title='Expand/collapse section'>Coordinates: <span>(4)</span></label><div class='xr-section-inline-details'></div><div class='xr-section-details'><ul class='xr-var-list'><li class='xr-var-item'><div class='xr-var-name'><span class='xr-has-index'>chain</span></div><div class='xr-var-dims'>(chain)</div><div class='xr-var-dtype'>int64</div><div class='xr-var-preview xr-preview'>0 1</div><input id='attrs-cbc9ed68-4d98-42d1-9566-8c0b64134337' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-cbc9ed68-4d98-42d1-9566-8c0b64134337' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-f7d4477e-ecd2-4719-a1a7-f648fc72fb1d' class='xr-var-data-in' type='checkbox'><label for='data-f7d4477e-ecd2-4719-a1a7-f648fc72fb1d' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>array([0, 1])</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span class='xr-has-index'>draw</span></div><div class='xr-var-dims'>(draw)</div><div class='xr-var-dtype'>int64</div><div class='xr-var-preview xr-preview'>0 1 2 3 4 5 ... 295 296 297 298 299</div><input id='attrs-fd874f2d-9c78-4b8c-98e8-ac35f4683bf9' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-fd874f2d-9c78-4b8c-98e8-ac35f4683bf9' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-e02e2973-93fa-41cb-bdf2-839873382c55' class='xr-var-data-in' type='checkbox'><label for='data-e02e2973-93fa-41cb-bdf2-839873382c55' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>array([  0,   1,   2, ..., 297, 298, 299], shape=(300,))</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span class='xr-has-index'>participant_id__factor_dim</span></div><div class='xr-var-dims'>(participant_id__factor_dim)</div><div class='xr-var-dtype'>&lt;U1</div><div class='xr-var-preview xr-preview'>&#x27;0&#x27; &#x27;1&#x27; &#x27;2&#x27; &#x27;3&#x27; &#x27;4&#x27;</div><input id='attrs-6dea3372-5982-44b2-9fac-fa0a709b5585' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-6dea3372-5982-44b2-9fac-fa0a709b5585' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-3fe85664-55e7-4f76-8f83-397c62823826' class='xr-var-data-in' type='checkbox'><label for='data-3fe85664-55e7-4f76-8f83-397c62823826' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>array([&#x27;0&#x27;, &#x27;1&#x27;, &#x27;2&#x27;, &#x27;3&#x27;, &#x27;4&#x27;], dtype=&#x27;&lt;U1&#x27;)</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span class='xr-has-index'>rl_alpha_1|participant_id__factor_dim</span></div><div class='xr-var-dims'>(rl_alpha_1|participant_id__factor_dim)</div><div class='xr-var-dtype'>&lt;U1</div><div class='xr-var-preview xr-preview'>&#x27;0&#x27; &#x27;1&#x27; &#x27;2&#x27; &#x27;3&#x27; &#x27;4&#x27;</div><input id='attrs-9f37a20f-3af4-4aea-a4a7-c2d6d9636add' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-9f37a20f-3af4-4aea-a4a7-c2d6d9636add' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-ebd2f8d9-326f-4d20-b66b-3b5d77f6a882' class='xr-var-data-in' type='checkbox'><label for='data-ebd2f8d9-326f-4d20-b66b-3b5d77f6a882' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>array([&#x27;0&#x27;, &#x27;1&#x27;, &#x27;2&#x27;, &#x27;3&#x27;, &#x27;4&#x27;], dtype=&#x27;&lt;U1&#x27;)</pre></div></li></ul></div></li><li class='xr-section-item'><input id='section-cb766809-0590-4b0e-9b53-3ad57d3ce0cc' class='xr-section-summary-in' type='checkbox' /><label for='section-cb766809-0590-4b0e-9b53-3ad57d3ce0cc' class='xr-section-summary' title='Expand/collapse section'>Data variables: <span>(24)</span></label><div class='xr-section-inline-details'></div><div class='xr-section-details'><ul class='xr-var-list'><li class='xr-var-item'><div class='xr-var-name'><span>z_1|participant_id_offset</span></div><div class='xr-var-dims'>(chain, draw, participant_id__factor_dim)</div><div class='xr-var-dtype'>float32</div><div class='xr-var-preview xr-preview'>...</div><input id='attrs-1faf7fa3-56b9-4245-8c85-e96d72e3fb6e' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-1faf7fa3-56b9-4245-8c85-e96d72e3fb6e' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-ad8606ec-4baf-4087-8315-2a2dcaa39140' class='xr-var-data-in' type='checkbox'><label for='data-ad8606ec-4baf-4087-8315-2a2dcaa39140' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>Array([[[-0.37977803, -1.3202302 ,  0.99357563,  1.2452617 ,-0.96063745],[ 0.29738694, -0.36043775, -0.09967786,  0.9537308 ,-0.04068899],[ 0.20817943, -0.74547905,  0.12089647, -0.73478764,-0.20643847],...,[ 0.06152699,  0.12790847, -0.0311322 ,  0.007528  ,0.40625015],[-0.27289042, -0.48630723, -0.46683407, -0.02160617,-0.27687174],[ 0.14855248,  0.03735328, -0.28761744, -0.4117774 ,0.44747713]],[[ 0.459022  , -0.69009846,  0.2349177 ,  0.43148017,-0.12725346],[-0.2305573 , -0.75812167,  0.8415485 ,  0.14703952,-0.49016905],[-0.18346179, -0.9687703 ,  0.86490524, -0.26100773,-0.19201736],...,[ 1.5202386 , -0.9381562 , -1.3970687 , -1.1545174 ,-0.35185614],[ 1.0203205 , -0.63383865, -0.6122218 , -0.35593557,1.5102065 ],[ 0.29571873, -1.0704062 , -0.97366476, -0.8387281 ,0.9501065 ]]], dtype=float32)</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span>z_Intercept</span></div><div class='xr-var-dims'>(chain, draw)</div><div class='xr-var-dtype'>float32</div><div class='xr-var-preview xr-preview'>...</div><input id='attrs-01340046-fff9-488b-8ec9-0a1daa12444d' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-01340046-fff9-488b-8ec9-0a1daa12444d' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-06070167-663e-4c67-8fda-b03f1c26c047' class='xr-var-data-in' type='checkbox'><label for='data-06070167-663e-4c67-8fda-b03f1c26c047' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>Array([[0.43810156, 0.46288744, 0.44729123, 0.45391685, 0.44824877,0.47818336, 0.4491628 , 0.48833197, 0.46680626, 0.44796175,0.49705553, 0.44047597, 0.40736818, 0.4369636 , 0.52813184,0.45260948, 0.4639974 , 0.5043548 , 0.49714315, 0.46044195,0.45237204, 0.46286634, 0.47827375, 0.48243052, 0.45523348,0.47506616, 0.4417985 , 0.46910694, 0.4816084 , 0.5163118 ,0.4476718 , 0.46021476, 0.4804685 , 0.44545507, 0.45688593,0.47419128, 0.47262585, 0.4488729 , 0.47620028, 0.47956738,0.48468646, 0.46048534, 0.4807055 , 0.46126464, 0.44382495,0.46038976, 0.5063006 , 0.46753728, 0.46937254, 0.46442983,0.4786095 , 0.4327226 , 0.45326644, 0.47848183, 0.45342723,0.44081652, 0.45904118, 0.51334584, 0.49480584, 0.46788588,0.451869  , 0.47616223, 0.45944035, 0.4667494 , 0.5125132 ,0.45507005, 0.43462282, 0.41701815, 0.50169754, 0.47043464,0.43819973, 0.49664113, 0.5096987 , 0.5091189 , 0.5299184 ,0.60226333, 0.5789182 , 0.47559565, 0.5017734 , 0.4680516 ,0.45169032, 0.4943997 , 0.4729873 , 0.4980806 , 0.49876612,0.45165825, 0.42659461, 0.43338537, 0.44614878, 0.4349706 ,0.4424701 , 0.45540294, 0.4610213 , 0.44858086, 0.48006466,0.47851995, 0.46209776, 0.45665413, 0.44028294, 0.4490881 ,...0.5187649 , 0.45353866, 0.48912036, 0.44033894, 0.5060125 ,0.4597876 , 0.47743285, 0.51312786, 0.46577176, 0.47012648,0.45717204, 0.44630334, 0.4940574 , 0.45756724, 0.45762822,0.4597762 , 0.47555798, 0.47320604, 0.48181346, 0.4493194 ,0.48127472, 0.41511875, 0.4910433 , 0.4379605 , 0.4823554 ,0.4521853 , 0.46543276, 0.48972127, 0.468775  , 0.4406377 ,0.4256761 , 0.45245865, 0.47947335, 0.45194724, 0.4720495 ,0.42860445, 0.50623953, 0.47144273, 0.5083136 , 0.52316993,0.52316314, 0.4882317 , 0.44646323, 0.43935284, 0.45089057,0.44862008, 0.45973003, 0.43650502, 0.49331287, 0.5131802 ,0.53454965, 0.4045003 , 0.4930222 , 0.43029594, 0.46051088,0.45772412, 0.42591035, 0.44273937, 0.47896358, 0.47468936,0.46916077, 0.47341353, 0.4397351 , 0.44273388, 0.45895898,0.46435598, 0.4762592 , 0.47344095, 0.4690921 , 0.4528174 ,0.44089302, 0.49115288, 0.43923452, 0.48435104, 0.47371507,0.45536068, 0.44797638, 0.47240832, 0.45049715, 0.49826556,0.44557953, 0.4409158 , 0.43151632, 0.43992835, 0.5058638 ,0.4530669 , 0.47848144, 0.4684494 , 0.4726838 , 0.5123462 ,0.43523225, 0.4894514 , 0.49015474, 0.47721773, 0.47921914,0.44579637, 0.48978513, 0.46896696, 0.4428816 , 0.4634152 ]],      dtype=float32)</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span>scaler_1|participant_id_offset</span></div><div class='xr-var-dims'>(chain, draw, participant_id__factor_dim)</div><div class='xr-var-dtype'>float32</div><div class='xr-var-preview xr-preview'>...</div><input id='attrs-cf55672a-05da-41d7-b51d-f73fdbc921f2' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-cf55672a-05da-41d7-b51d-f73fdbc921f2' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-dd082812-24ef-4e8a-8961-2aa24726d982' class='xr-var-data-in' type='checkbox'><label for='data-dd082812-24ef-4e8a-8961-2aa24726d982' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>Array([[[-0.9537846 ,  0.71424687,  1.2582392 , -1.166728  ,-0.8019403 ],[-0.13598272,  0.42545968, -1.0588375 , -1.7518924 ,-0.20300576],[ 0.70126563,  1.7781789 ,  0.03423202, -1.2502952 ,2.1012952 ],...,[-0.6286079 ,  1.1691153 ,  0.33163664, -0.17816679,1.4159164 ],[-0.0182031 ,  0.13483706, -2.3213024 , -0.12893496,0.95835066],[ 0.22937673, -0.05597847, -2.2444768 , -0.7088203 ,0.65204895]],[[-1.5310904 ,  0.23064016, -0.5289061 ,  0.47817746,2.015074  ],[-0.42488685,  0.02927306, -0.40337285, -0.7104144 ,1.1158555 ],[-0.54081583,  0.14511298, -0.3898724 , -0.60666203,1.1581517 ],...,[-0.6559321 , -0.04831997,  0.0895692 , -1.2922366 ,-0.05792417],[-2.2017357 ,  0.9620459 ,  0.80016345, -0.89439005,1.6815922 ],[-1.927249  ,  0.13243762,  0.75082135, -0.9554217 ,1.7836976 ]]], dtype=float32)</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span>a_1|participant_id_offset</span></div><div class='xr-var-dims'>(chain, draw, participant_id__factor_dim)</div><div class='xr-var-dtype'>float32</div><div class='xr-var-preview xr-preview'>...</div><input id='attrs-f560bc08-da49-46fe-a825-33fb451e3286' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-f560bc08-da49-46fe-a825-33fb451e3286' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-cc9c2a57-d44c-425e-9c44-c6c48d2f2d28' class='xr-var-data-in' type='checkbox'><label for='data-cc9c2a57-d44c-425e-9c44-c6c48d2f2d28' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>Array([[[ 0.80176175, -0.09315851, -0.09444129,  1.8295711 ,0.77556884],[ 0.1934266 , -0.8159209 , -0.61145544,  1.7652677 ,0.32347506],[ 1.2752581 ,  0.46592703,  0.8170525 ,  1.2404062 ,1.7228385 ],...,[ 1.0206819 , -0.5481848 , -0.78312826,  0.10713051,-0.07759586],[-0.18818416,  0.43738905, -0.04730679,  1.3932551 ,0.1377107 ],[-0.6194624 ,  0.74891794,  0.24220978,  0.57498777,-0.10658807]],[[ 0.00428461, -0.62478256, -0.22838797,  0.1922633 ,1.1665165 ],[-0.05223541, -0.76193094, -0.4436986 ,  1.3225241 ,0.9495574 ],[-0.08977419, -0.78564876, -0.6068709 ,  1.102606  ,0.893325  ],...,[ 0.02544861,  0.987463  , -0.26977345,  1.7241178 ,0.9290584 ],[ 1.6277083 , -1.570625  ,  0.10294215,  0.8330429 ,0.43382525],[ 2.3311281 ,  0.4672795 ,  0.51288575,  1.4739922 ,0.29860765]]], dtype=float32)</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span>a_1|participant_id</span></div><div class='xr-var-dims'>(chain, draw, participant_id__factor_dim)</div><div class='xr-var-dtype'>float32</div><div class='xr-var-preview xr-preview'>...</div><input id='attrs-89d6a2f9-989e-418c-afb9-32156789049a' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-89d6a2f9-989e-418c-afb9-32156789049a' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-21b76dd2-fc47-40c3-80aa-3018aa8dc744' class='xr-var-data-in' type='checkbox'><label for='data-21b76dd2-fc47-40c3-80aa-3018aa8dc744' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>Array([[[ 0.2539387 , -0.02950571, -0.029912  ,  0.57947254,0.24564272],[ 0.04287091, -0.18084003, -0.13552247,  0.3912525 ,0.07169475],[ 0.36668763,  0.13397263,  0.23493521,  0.3566663 ,0.49538487],...,[ 0.34059027, -0.18292323, -0.26132128,  0.03574827,-0.02589288],[-0.05054246,  0.11747384, -0.01270565,  0.3742001 ,0.03698631],[-0.18555279,  0.22432971,  0.07255114,  0.17223093,-0.03192722]],[[ 0.00120715, -0.17602736, -0.06434643,  0.05416861,0.32865646],[-0.00756251, -0.11031047, -0.06423758,  0.19147174,0.13747455],[-0.01419216, -0.1242011 , -0.09593859,  0.17430803,0.14122334],...,[ 0.00317333,  0.1231323 , -0.03363957,  0.21498992,0.1158495 ],[ 0.15103416, -0.14573742,  0.00955195,  0.07729759,0.04025441],[ 0.3154992 ,  0.06324247,  0.06941491,  0.19949284,0.04041411]]], dtype=float32)</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span>t_1|participant_id_sigma</span></div><div class='xr-var-dims'>(chain, draw)</div><div class='xr-var-dtype'>float32</div><div class='xr-var-preview xr-preview'>...</div><input id='attrs-56433f0c-dcec-4acc-8827-a71f24fb8277' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-56433f0c-dcec-4acc-8827-a71f24fb8277' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-82914c68-38a6-4e68-8ad8-74367ce32704' class='xr-var-data-in' type='checkbox'><label for='data-82914c68-38a6-4e68-8ad8-74367ce32704' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>Array([[0.12788008, 0.09341314, 0.05869246, 0.10256022, 0.06010016,0.08222742, 0.14723861, 0.07347839, 0.14034072, 0.16463992,0.15046939, 0.10648254, 0.08302601, 0.15116726, 0.08852948,0.1739183 , 0.24462095, 0.14790119, 0.11227888, 0.09697863,0.12197539, 0.11465808, 0.13818936, 0.12886398, 0.09493202,0.33242834, 0.2255025 , 0.3126432 , 0.13817471, 0.1858792 ,0.06400914, 0.02898081, 0.0893888 , 0.13766381, 0.08857754,0.10303491, 0.05351119, 0.09065001, 0.02801558, 0.16311254,0.11045462, 0.12909462, 0.13340262, 0.08024183, 0.08731534,0.18741573, 0.19212604, 0.08633804, 0.21675098, 0.17542163,0.08995312, 0.06680594, 0.0724714 , 0.08985491, 0.07981052,0.07884666, 0.06912588, 0.07370168, 0.04694597, 0.04503932,0.08291916, 0.03870035, 0.07041407, 0.10311731, 0.27456862,0.07137986, 0.14962116, 0.12153555, 0.0419328 , 0.0595799 ,0.09629194, 0.0885628 , 0.09284765, 0.07424884, 0.07320907,0.06975651, 0.10072807, 0.03361692, 0.09813707, 0.07497881,0.1327513 , 0.126004  , 0.05130585, 0.11080284, 0.11504409,0.27364206, 0.16983533, 0.1235625 , 0.15829858, 0.08799049,0.04881898, 0.09782569, 0.20351562, 0.07057028, 0.08074385,0.07928611, 0.02924014, 0.02667093, 0.12533674, 0.02096564,...0.1319809 , 0.08602383, 0.24537212, 0.15951015, 0.06689127,0.14933436, 0.1382248 , 0.20401902, 0.1652324 , 0.19791663,0.15605325, 0.17547747, 0.10911676, 0.09735014, 0.08885829,0.07951523, 0.06826244, 0.10895309, 0.10594258, 0.05488332,0.05389532, 0.07328603, 0.03665099, 0.0524198 , 0.05232774,0.17334928, 0.19309829, 0.13698177, 0.08573239, 0.20355187,0.08561804, 0.10401478, 0.09066393, 0.1367881 , 0.15084012,0.0575625 , 0.06778014, 0.09334384, 0.13573836, 0.19616705,0.13987918, 0.13503364, 0.2404774 , 0.2690716 , 0.16764826,0.15184954, 0.14632899, 0.16276132, 0.14960486, 0.16636959,0.08192588, 0.13629693, 0.09055514, 0.08745189, 0.08129072,0.04278309, 0.04369488, 0.07500413, 0.12328439, 0.10795602,0.08843067, 0.07670043, 0.10128093, 0.10493976, 0.0870667 ,0.17598268, 0.06999016, 0.08625915, 0.09079   , 0.12901421,0.16924977, 0.16395816, 0.09120461, 0.18024778, 0.18761641,0.09198964, 0.1076943 , 0.12668736, 0.17759433, 0.10154702,0.03460439, 0.05878941, 0.06746382, 0.03967378, 0.08786997,0.02957597, 0.05918913, 0.05975368, 0.08176623, 0.09841913,0.16124691, 0.07855923, 0.0859447 , 0.09068227, 0.08346801,0.1083205 , 0.11274652, 0.21991411, 0.14502606, 0.1380404 ]],      dtype=float32)</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span>rl_alpha_1|participant_id_sigma</span></div><div class='xr-var-dims'>(chain, draw)</div><div class='xr-var-dtype'>float32</div><div class='xr-var-preview xr-preview'>...</div><input id='attrs-dcb63b52-463c-4383-bed4-9aa38ff2e5e5' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-dcb63b52-463c-4383-bed4-9aa38ff2e5e5' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-ed4bfa60-83ff-48e0-8f74-6a2fb3edf644' class='xr-var-data-in' type='checkbox'><label for='data-ed4bfa60-83ff-48e0-8f74-6a2fb3edf644' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>Array([[0.05052387, 0.0466326 , 0.01614147, 0.02898645, 0.03661774,0.02293684, 0.1420353 , 0.08122816, 0.01099153, 0.09243751,0.02176466, 0.11019109, 0.0438143 , 0.12296413, 0.00233299,0.1621094 , 0.16392156, 0.1055137 , 0.02535889, 0.05321867,0.07798212, 0.05655218, 0.02936044, 0.02421069, 0.03513669,0.04313827, 0.0754796 , 0.04016946, 0.01415837, 0.02721165,0.06341492, 0.13218026, 0.06278453, 0.08169598, 0.26004982,0.05431394, 0.04953069, 0.14423975, 0.08870009, 0.01647978,0.37209916, 0.01284611, 0.03055242, 0.06814249, 0.01996166,0.0333503 , 0.06630474, 0.05046037, 0.09745474, 0.05132292,0.10654631, 0.02383076, 0.04734759, 0.00682122, 0.00243572,0.00521409, 0.00587166, 0.08678462, 0.03161705, 0.04053465,0.09515801, 0.05154289, 0.02809209, 0.09743488, 0.00109092,0.0140544 , 0.10374082, 0.01948201, 0.10707416, 0.00383861,0.03807306, 0.09821733, 0.09002472, 0.07653557, 0.11545821,0.02088409, 0.08826473, 0.04517298, 0.03484462, 0.01524814,0.17889784, 0.00995813, 0.00606585, 0.00568568, 0.00229268,0.17551577, 0.11446287, 0.06559785, 0.14980412, 0.0251419 ,0.1032865 , 0.05204219, 0.1146855 , 0.03984366, 0.01046544,0.03206197, 0.02072228, 0.01943356, 0.00470368, 0.04573767,...0.07739387, 0.03004229, 0.17644584, 0.07432311, 0.07355759,0.00933311, 0.06226192, 0.00382108, 0.00623739, 0.03880155,0.00665353, 0.00620803, 0.00824256, 0.07214707, 0.03520095,0.12511335, 0.04285406, 0.0426644 , 0.06446527, 0.00988952,0.0357022 , 0.05853231, 0.03722038, 0.06594308, 0.02655746,0.01364536, 0.00824673, 0.0151094 , 0.01874005, 0.11234374,0.04386818, 0.0565354 , 0.07800592, 0.09487747, 0.04902403,0.05063468, 0.00285143, 0.00197309, 0.00344597, 0.01112833,0.01503352, 0.07088196, 0.05817474, 0.06597655, 0.02912555,0.03899373, 0.06349318, 0.05927014, 0.01373596, 0.01310365,0.02427816, 0.09890667, 0.06647529, 0.09665059, 0.111535  ,0.12698005, 0.1034904 , 0.05653459, 0.12507668, 0.08197233,0.04457568, 0.03855666, 0.09262034, 0.05714597, 0.16188642,0.14832228, 0.0579811 , 0.19891614, 0.01148802, 0.04959942,0.0457175 , 0.10939825, 0.11820649, 0.06631077, 0.07796591,0.1580621 , 0.01400556, 0.03410701, 0.02141508, 0.09413311,0.0160496 , 0.05914617, 0.03285921, 0.01368214, 0.05129209,0.00459732, 0.05580157, 0.04559195, 0.03554327, 0.06479176,0.05207197, 0.0601352 , 0.00407353, 0.02430042, 0.02142423,0.04488905, 0.11496425, 0.09634972, 0.35269666, 0.12958983]],      dtype=float32)</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span>rl_alpha_1|participant_id</span></div><div class='xr-var-dims'>(chain, draw, rl_alpha_1|participant_id__factor_dim)</div><div class='xr-var-dtype'>float32</div><div class='xr-var-preview xr-preview'>...</div><input id='attrs-c05fa075-dc46-41ca-9b02-a3e88f8816c7' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-c05fa075-dc46-41ca-9b02-a3e88f8816c7' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-a04accdd-80c1-43c7-8b89-3d3ba9745b95' class='xr-var-data-in' type='checkbox'><label for='data-a04accdd-80c1-43c7-8b89-3d3ba9745b95' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>Array([[[-0.07368127, -0.0092661 , -0.08930462, -0.04006366,0.01713065],[-0.04588036,  0.00617258, -0.01728664, -0.02436249,0.0336735 ],[ 0.01349712, -0.00041384,  0.00341723,  0.0157566 ,-0.00520289],...,[-0.00499554,  0.02323106, -0.04963632, -0.02636934,0.01991412],[-0.03239445,  0.02539502, -0.01446751, -0.08386853,0.02586374],[-0.04655728,  0.02318785,  0.01029579, -0.07023574,0.03077258]],[[ 0.04138274,  0.05603775, -0.00385761,  0.00719279,0.0819814 ],[ 0.01284022,  0.01884353,  0.01216657,  0.00880447,0.07059301],[ 0.00128598,  0.01660207,  0.00809954,  0.01382836,0.06592489],...,[ 0.09260341,  0.11456588,  0.04916794,  0.00680655,0.16000512],[ 0.12627453,  0.25525424,  0.01943824,  0.04143095,0.2244754 ],[ 0.08330165,  0.05728068,  0.02608114,  0.06805027,0.16756442]]], dtype=float32)</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span>theta_1|participant_id_sigma</span></div><div class='xr-var-dims'>(chain, draw)</div><div class='xr-var-dtype'>float32</div><div class='xr-var-preview xr-preview'>...</div><input id='attrs-74b2f2b7-8dd9-4b01-a772-2dfb52b04af9' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-74b2f2b7-8dd9-4b01-a772-2dfb52b04af9' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-353771f2-5e9c-4308-b9a9-ef468bc62cce' class='xr-var-data-in' type='checkbox'><label for='data-353771f2-5e9c-4308-b9a9-ef468bc62cce' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>Array([[1.18425237e-02, 4.52438146e-02, 5.33243902e-02, 3.40816341e-02,1.62465144e-02, 3.53252590e-02, 3.07731871e-02, 2.03333814e-02,3.11487168e-02, 7.39125609e-02, 8.73818994e-02, 1.23761572e-01,9.66661200e-02, 6.30611032e-02, 5.98968007e-03, 6.74801916e-02,4.42665592e-02, 2.64324844e-02, 2.84834970e-02, 5.58706783e-02,4.89298739e-02, 7.50835687e-02, 2.57473797e-01, 2.90921688e-01,7.69688888e-03, 5.53777404e-02, 5.05244359e-02, 7.90527742e-03,2.71408595e-02, 2.80832816e-02, 1.41754031e-01, 4.46193703e-02,1.03911303e-01, 9.16050049e-04, 1.14330312e-03, 2.44882831e-04,4.19494289e-04, 5.11225872e-03, 1.26035750e-01, 1.70340370e-02,6.30455911e-02, 8.83957669e-02, 7.89393187e-02, 4.86348085e-02,1.77184176e-02, 3.45989615e-02, 1.61673903e-01, 1.03413396e-01,7.28579462e-02, 6.54791370e-02, 9.01644677e-03, 3.05160750e-02,4.78065237e-02, 4.76034917e-02, 6.39392659e-02, 6.02147877e-02,4.25535217e-02, 1.88466579e-01, 2.01962050e-02, 1.63127780e-02,3.58021632e-02, 6.99456781e-02, 6.95798621e-02, 1.37094051e-01,6.57000840e-02, 2.93962583e-02, 6.41440898e-02, 6.15396835e-02,6.17828965e-03, 3.85482199e-02, 1.03886008e-01, 1.80604279e-01,1.43467590e-01, 1.97661296e-01, 2.22127605e-02, 1.70477945e-02,3.07503622e-02, 8.96943584e-02, 7.12721646e-02, 3.40516493e-02,...7.45423080e-04, 3.41218151e-02, 1.54531732e-01, 7.84808844e-02,1.88108180e-02, 3.59522477e-02, 1.21591605e-01, 1.52945101e-01,1.42223085e-03, 4.58281010e-01, 5.16790040e-02, 5.46567142e-02,8.43761116e-02, 7.87694380e-02, 1.00940950e-02, 1.08822271e-01,9.33273882e-02, 9.50257704e-02, 1.04170121e-01, 8.40816349e-02,7.05734789e-02, 5.88369966e-02, 7.96858668e-02, 9.97508466e-02,4.98882309e-02, 6.21972568e-02, 1.24955542e-01, 4.34508212e-02,5.84715195e-02, 1.04335286e-01, 6.86707795e-02, 1.15498379e-02,1.26117513e-01, 6.77583069e-02, 7.21892416e-02, 1.37475412e-02,1.30402043e-01, 1.07309431e-01, 1.05952434e-01, 7.65537843e-02,1.44930288e-01, 1.42422482e-01, 2.03539178e-01, 2.16979161e-01,1.08322755e-01, 1.30914692e-02, 2.83600055e-02, 8.44430029e-02,5.37691638e-02, 5.68959355e-01, 4.05440331e-01, 4.90408003e-01,5.90523370e-02, 1.02992810e-01, 1.15348622e-01, 4.14019004e-02,8.77699554e-02, 3.10697407e-02, 5.39648607e-02, 9.05185938e-02,2.66005937e-02, 2.68101250e-03, 1.31020672e-03, 7.24495272e-04,3.35424729e-02, 2.21541570e-03, 6.40414190e-03, 2.35637184e-02,5.90652339e-02, 1.47980098e-02, 6.96192086e-02, 2.98805814e-02,3.73423845e-02, 4.50966433e-02, 6.98166117e-02, 1.14630330e-02,1.37209088e-01, 5.48750944e-02, 2.64885545e-01, 1.89478055e-01]],      dtype=float32)</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span>a_1|participant_id_sigma</span></div><div class='xr-var-dims'>(chain, draw)</div><div class='xr-var-dtype'>float32</div><div class='xr-var-preview xr-preview'>...</div><input id='attrs-5115affc-a67e-4cdc-a09e-96b190d92b1f' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-5115affc-a67e-4cdc-a09e-96b190d92b1f' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-04fc9ab2-fb81-40ff-806c-cdb477654a1e' class='xr-var-data-in' type='checkbox'><label for='data-04fc9ab2-fb81-40ff-806c-cdb477654a1e' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>Array([[3.16725880e-01, 2.21639171e-01, 2.87539929e-01, 2.22846717e-01,2.46216312e-01, 1.95337325e-01, 1.72868580e-01, 1.98697299e-01,2.11782485e-01, 1.32234007e-01, 4.52544093e-01, 1.02116205e-01,2.99050212e-02, 1.00306548e-01, 7.58148551e-01, 2.22490653e-01,2.05303848e-01, 1.71804160e-01, 1.62673801e-01, 2.34092683e-01,1.00418366e-01, 4.09094930e-01, 3.31456989e-01, 3.15080374e-01,2.26549029e-01, 1.76101342e-01, 2.39336982e-01, 2.00386107e-01,2.12680995e-01, 3.52493435e-01, 2.35318497e-01, 3.62701982e-01,1.21054024e-01, 2.76855081e-01, 2.44839370e-01, 2.24151850e-01,2.93392360e-01, 1.96828425e-01, 1.64144397e-01, 1.82724625e-01,5.42932928e-01, 2.56969035e-01, 1.81647062e-01, 2.29855016e-01,1.35605991e-01, 8.72152895e-02, 4.01543915e-01, 2.41950512e-01,3.97168338e-01, 8.28934550e-01, 1.80615425e-01, 3.91743422e-01,4.23705041e-01, 2.33606815e-01, 2.18727380e-01, 3.59563410e-01,2.08027512e-01, 2.39172041e-01, 1.12204671e-01, 1.31758526e-01,3.22561376e-02, 1.49605960e-01, 2.13525817e-01, 2.28217870e-01,2.12676451e-01, 4.94154751e-01, 2.31465757e-01, 1.59658164e-01,1.91992521e-01, 1.24569505e-01, 4.60433990e-01, 2.17636526e-01,2.11909488e-01, 1.75582141e-01, 1.29796594e-01, 2.53370553e-01,3.54080439e-01, 2.90962160e-01, 2.28021473e-01, 2.73782939e-01,...3.80718291e-01, 3.31404567e-01, 4.86356795e-01, 5.50066710e-01,5.24289012e-01, 1.97699547e-01, 2.44645685e-01, 1.55488700e-01,5.11734366e-01, 2.28304774e-01, 1.82797641e-01, 1.12066932e-01,8.86270925e-02, 1.20074861e-01, 1.70748830e-01, 2.39450470e-01,1.70258284e-01, 1.67739421e-01, 1.64864168e-01, 1.36960462e-01,1.21939950e-01, 1.76436573e-01, 1.23987593e-01, 2.03384504e-01,2.35099733e-01, 2.41826057e-01, 4.61380601e-01, 4.63426948e-01,4.69807148e-01, 4.89432395e-01, 1.34712398e-01, 1.33159682e-01,3.90140682e-01, 1.98648289e-01, 1.64358944e-01, 2.56672591e-01,2.80783832e-01, 3.28194737e-01, 1.84304446e-01, 1.53424546e-01,1.29448682e-01, 1.26480818e-01, 5.54029234e-02, 9.95934159e-02,3.73568907e-02, 1.41826317e-01, 3.41472685e-01, 1.27942026e-01,3.55583668e-01, 3.55725110e-01, 2.93304503e-01, 3.22728813e-01,2.48056874e-01, 1.64984584e-01, 1.60378665e-01, 1.80157632e-01,2.10404515e-01, 3.41011584e-01, 1.77142918e-01, 1.26531616e-01,2.20022798e-01, 1.25885263e-01, 9.03150588e-02, 1.24015741e-01,1.35752618e-01, 3.00116301e-01, 2.97587335e-01, 1.19703390e-01,2.12765232e-01, 1.88280270e-01, 1.15718469e-01, 4.32706654e-01,1.15774021e-01, 8.99049714e-02, 1.10525616e-01, 2.35626906e-01,1.19963154e-01, 1.24695614e-01, 9.27894488e-02, 1.35341853e-01]],      dtype=float32)</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span>rl_alpha_Intercept</span></div><div class='xr-var-dims'>(chain, draw)</div><div class='xr-var-dtype'>float32</div><div class='xr-var-preview xr-preview'>...</div><input id='attrs-9f9b7bd1-e0c7-499c-895a-862eccf3c90e' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-9f9b7bd1-e0c7-499c-895a-862eccf3c90e' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-7417096c-65a0-4869-8e4f-1d94612b6a06' class='xr-var-data-in' type='checkbox'><label for='data-7417096c-65a0-4869-8e4f-1d94612b6a06' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>Array([[0.10286471, 0.08943062, 0.17955568, 0.15803216, 0.09911661,0.09295113, 0.10459666, 0.12686218, 0.12271165, 0.1916655 ,0.07884016, 0.16994469, 0.09388227, 0.10022449, 0.13731842,0.14035033, 0.16150372, 0.11766913, 0.11813252, 0.20438695,0.07599349, 0.21820042, 0.10063174, 0.1113665 , 0.08885348,0.07400026, 0.14469089, 0.12468687, 0.07154821, 0.18985786,0.09603208, 0.18315087, 0.14641514, 0.18811072, 0.31076062,0.1582401 , 0.18274872, 0.11416489, 0.14672132, 0.12285025,0.23739207, 0.15984508, 0.14678505, 0.14472416, 0.18341589,0.07093124, 0.12036532, 0.1452096 , 0.10967501, 0.05979099,0.06401648, 0.10210407, 0.11201061, 0.10726789, 0.1083173 ,0.1603242 , 0.19094937, 0.13683958, 0.13569312, 0.13227421,0.23600225, 0.09033255, 0.149067  , 0.13987267, 0.1920385 ,0.09075785, 0.2246392 , 0.13008827, 0.12839797, 0.12810865,0.1324735 , 0.19814894, 0.16928723, 0.1524229 , 0.16653065,0.11154612, 0.14256537, 0.11694307, 0.10768316, 0.15448757,0.17091852, 0.10705014, 0.10158286, 0.10499701, 0.11052303,0.21236806, 0.21771759, 0.32988632, 0.25447348, 0.16204837,0.12832208, 0.19650869, 0.13445438, 0.1259552 , 0.10271408,0.10547788, 0.16376194, 0.2041537 , 0.07054333, 0.1858308 ,...0.0188295 , 0.08483931, 0.16657603, 0.09742755, 0.19028284,0.09643128, 0.20265806, 0.09522405, 0.15089926, 0.13826077,0.14184938, 0.08600599, 0.1596359 , 0.20640606, 0.12878728,0.2769342 , 0.18326396, 0.14135608, 0.16724208, 0.11184826,0.12775132, 0.06442712, 0.14894687, 0.0893064 , 0.18114522,0.09217267, 0.13491227, 0.20027678, 0.12041173, 0.23339854,0.07730527, 0.14581738, 0.1858225 , 0.13429655, 0.12855378,0.23167253, 0.14268456, 0.12868054, 0.21519737, 0.07092083,0.0826511 , 0.17038867, 0.14341204, 0.16522148, 0.14762685,0.1345524 , 0.11852027, 0.15288097, 0.16691406, 0.18458663,0.08065777, 0.2117209 , 0.08449227, 0.18175459, 0.13922128,0.04083288, 0.07332   , 0.14281173, 0.03094278, 0.07096547,0.06665525, 0.1040766 , 0.03227734, 0.119567  , 0.10854691,0.09268203, 0.05791797, 0.27437654, 0.07446611, 0.10803057,0.11145823, 0.11100204, 0.09678085, 0.19946954, 0.20586564,0.16202287, 0.08150366, 0.25390908, 0.06168228, 0.26890856,0.06216256, 0.0958118 , 0.08395097, 0.04955864, 0.1295751 ,0.10990467, 0.17193767, 0.15092869, 0.13686249, 0.0781922 ,0.11807739, 0.18802452, 0.18511735, 0.058472  , 0.12454028,0.11713913, 0.05019283, 0.03157109, 0.01572806, 0.01208059]],      dtype=float32)</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span>theta_1|participant_id</span></div><div class='xr-var-dims'>(chain, draw, participant_id__factor_dim)</div><div class='xr-var-dtype'>float32</div><div class='xr-var-preview xr-preview'>...</div><input id='attrs-0cf69fdc-0d03-4db9-b6b1-c3a195e1ceb8' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-0cf69fdc-0d03-4db9-b6b1-c3a195e1ceb8' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-78c28180-421c-45c2-8ab4-f9a7431427ca' class='xr-var-data-in' type='checkbox'><label for='data-78c28180-421c-45c2-8ab4-f9a7431427ca' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>Array([[[-0.00108018, -0.00628014,  0.02013353, -0.00280711,-0.0017745 ],[ 0.01060137, -0.05309435, -0.06538451,  0.01214662,-0.03822519],[ 0.0321813 ,  0.05205196,  0.05391201, -0.02553851,0.03732627],...,[ 0.15937023, -0.02330265, -0.00944153, -0.11442047,-0.14221646],[-0.10126524,  0.08959548,  0.02413245, -0.04776207,-0.06359125],[-0.29332078,  0.08570864,  0.05178185, -0.12243122,-0.21775396]],[[-0.00340325, -0.01512029,  0.00498261, -0.05906741,-0.04535825],[-0.00054402, -0.03013075,  0.06588393, -0.10584361,-0.06482182],[ 0.00455833, -0.01927897,  0.07432349, -0.10439105,-0.06958108],...,[-0.04171532,  0.05226523,  0.01869536, -0.09216685,-0.08411029],[ 0.09289408, -0.15556468,  0.11323419, -0.18161625,0.04278227],[ 0.03663884,  0.04928331,  0.01287864, -0.11660655,-0.14774829]]], dtype=float32)</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span>theta_1|participant_id_offset</span></div><div class='xr-var-dims'>(chain, draw, participant_id__factor_dim)</div><div class='xr-var-dtype'>float32</div><div class='xr-var-preview xr-preview'>...</div><input id='attrs-1103ec43-979f-4fe7-91ae-c252171262ed' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-1103ec43-979f-4fe7-91ae-c252171262ed' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-4d55357a-262a-41e7-96a5-1ef4cfced49f' class='xr-var-data-in' type='checkbox'><label for='data-4d55357a-262a-41e7-96a5-1ef4cfced49f' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>Array([[[-0.09121197, -0.5303043 ,  1.7001044 , -0.23703678,-0.14984101],[ 0.23431647, -1.1735163 , -1.445159  ,  0.26847032,-0.844871  ],[ 0.6035006 ,  0.97613794,  1.0110197 , -0.47892743,0.69998485],...,[ 1.9560264 , -0.28600448, -0.11588039, -1.4043366 ,-1.74549   ],[-1.0060678 ,  0.890129  ,  0.23975532, -0.47451502,-0.6317776 ],[-1.975827  ,  0.57733876,  0.34880576, -0.82470435,-1.4668043 ]],[[-0.07040395, -0.31279707,  0.10307641, -1.2219417 ,-0.93833715],[-0.00589807, -0.3266654 ,  0.714287  , -1.1475136 ,-0.70277196],[ 0.052303  , -0.22121015,  0.8528002 , -1.1978005 ,-0.798385  ],...,[-0.76018685,  0.9524399 ,  0.3406894 , -1.6795752 ,-1.532759  ],[ 0.35069516, -0.58729017,  0.42748347, -0.68564045,0.16151229],[ 0.19336723,  0.26010036,  0.06796905, -0.61540926,-0.77976465]]], dtype=float32)</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span>theta_Intercept</span></div><div class='xr-var-dims'>(chain, draw)</div><div class='xr-var-dtype'>float32</div><div class='xr-var-preview xr-preview'>...</div><input id='attrs-8fb2fd65-7142-4e1b-b18f-fcda66cd2d1a' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-8fb2fd65-7142-4e1b-b18f-fcda66cd2d1a' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-4f050a30-4a04-4d41-a1d2-6cb43e6a92a0' class='xr-var-data-in' type='checkbox'><label for='data-4f050a30-4a04-4d41-a1d2-6cb43e6a92a0' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>Array([[0.45228416, 0.3721391 , 0.3536712 , 0.35287076, 0.33873868,0.35310993, 0.35577142, 0.33922622, 0.3426378 , 0.34885073,0.32409346, 0.36548293, 0.32934844, 0.34720978, 0.37085462,0.32788894, 0.37552935, 0.36861432, 0.3529239 , 0.4328839 ,0.3045775 , 0.4304789 , 0.50509393, 0.50183326, 0.3265922 ,0.33703768, 0.37476584, 0.30405128, 0.32725686, 0.3152092 ,0.4226447 , 0.37423137, 0.3728307 , 0.32494652, 0.34181947,0.35314795, 0.34970987, 0.31957716, 0.446829  , 0.35243025,0.44711396, 0.43235692, 0.3686926 , 0.33730164, 0.3893823 ,0.32816353, 0.25911736, 0.42515007, 0.33986694, 0.28239244,0.3651129 , 0.3529784 , 0.38247994, 0.45085973, 0.4059873 ,0.41067737, 0.393882  , 0.39416578, 0.32494524, 0.33058792,0.26102978, 0.34711263, 0.34274918, 0.40402323, 0.42387283,0.4391066 , 0.33964986, 0.30432534, 0.36290064, 0.33459115,0.4113082 , 0.34495488, 0.31951544, 0.30961248, 0.35546955,0.30171335, 0.4167938 , 0.37202913, 0.31025916, 0.3464192 ,0.27823117, 0.36579123, 0.35730237, 0.33584243, 0.32531607,0.38564804, 0.38342583, 0.27930662, 0.29981333, 0.33538717,0.32312748, 0.2916599 , 0.34699702, 0.33016443, 0.35075513,0.36518794, 0.29755273, 0.33692673, 0.39402378, 0.25506654,...0.33430472, 0.35423732, 0.3555208 , 0.4128714 , 0.38591662,0.38619995, 0.34499106, 0.35330814, 0.3957642 , 0.37799767,0.338541  , 0.34637952, 0.37260702, 0.267146  , 0.31983387,0.36471045, 0.43652892, 0.36015534, 0.36098957, 0.3239712 ,0.3841401 , 0.3274624 , 0.31669208, 0.42800346, 0.36098087,0.28824443, 0.31186667, 0.30272606, 0.353428  , 0.39189354,0.34567145, 0.32116437, 0.31167054, 0.3129508 , 0.37336347,0.31319988, 0.39308235, 0.39498392, 0.3816271 , 0.3050298 ,0.32106388, 0.2669167 , 0.41006637, 0.4667163 , 0.38344854,0.37696075, 0.26066437, 0.2924582 , 0.31851846, 0.29127046,0.35132825, 0.36552262, 0.38938266, 0.36622837, 0.3629257 ,0.34096867, 0.40084034, 0.41146883, 0.32172534, 0.40509486,0.40027276, 0.3508193 , 0.28873256, 0.35332644, 0.30482316,0.29915345, 0.37714294, 0.35313547, 0.47344336, 0.61988705,0.562859  , 0.61072844, 0.2726314 , 0.29526022, 0.29926032,0.29150608, 0.45306993, 0.29807234, 0.30812216, 0.27409393,0.36934087, 0.28669873, 0.2947067 , 0.36914438, 0.32046103,0.3784456 , 0.35312542, 0.3671639 , 0.45914024, 0.3870232 ,0.30736005, 0.44231108, 0.26440662, 0.27095717, 0.27826783,0.39750332, 0.32481682, 0.4026697 , 0.36318985, 0.36258382]],      dtype=float32)</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span>z_1|participant_id</span></div><div class='xr-var-dims'>(chain, draw, participant_id__factor_dim)</div><div class='xr-var-dtype'>float32</div><div class='xr-var-preview xr-preview'>...</div><input id='attrs-0e507dfd-b7e7-45dc-83f2-d27bf10c39d5' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-0e507dfd-b7e7-45dc-83f2-d27bf10c39d5' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-0c3a690a-e0fb-4197-a009-1dd4b9104c3f' class='xr-var-data-in' type='checkbox'><label for='data-0c3a690a-e0fb-4197-a009-1dd4b9104c3f' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>Array([[[-0.00152762, -0.00531048,  0.00399655,  0.00500893,-0.00386406],[ 0.00856414, -0.01037987, -0.00287052,  0.0274655 ,-0.00117176],[ 0.01648933, -0.05904736,  0.00957588, -0.05820052,-0.01635143],...,[ 0.0145725 ,  0.03029477, -0.00737358,  0.00178299,0.09621923],[-0.03816704, -0.06801599, -0.06529243, -0.00302189,-0.03872388],[ 0.02085033,  0.00524278, -0.04036902, -0.0577957 ,0.0628064 ]],[[ 0.03624653, -0.05449342,  0.0185502 ,  0.0340717 ,-0.01004853],[-0.00615751, -0.02024721,  0.0224753 ,  0.003927  ,-0.01309098],[-0.00512219, -0.02704774,  0.02414786, -0.00728725,-0.00536106],...,[ 0.01347608, -0.00831624, -0.01238425, -0.01023416,-0.00311901],[ 0.02446388, -0.01519733, -0.01467903, -0.00853415,0.0362097 ],[ 0.00706859, -0.02558602, -0.0232736 , -0.0200482 ,0.02271049]]], dtype=float32)</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span>a_Intercept</span></div><div class='xr-var-dims'>(chain, draw)</div><div class='xr-var-dtype'>float32</div><div class='xr-var-preview xr-preview'>...</div><input id='attrs-f2e51d43-5607-4b61-877c-7de92ef3afc2' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-f2e51d43-5607-4b61-877c-7de92ef3afc2' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-9b9c2d04-86a2-4aa4-832a-06c31f39006c' class='xr-var-data-in' type='checkbox'><label for='data-9b9c2d04-86a2-4aa4-832a-06c31f39006c' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>Array([[1.2684795 , 1.1991737 , 1.0729709 , 1.2488648 , 1.3389387 ,1.3918418 , 1.3362055 , 1.2444584 , 1.442184  , 1.3823261 ,1.3351955 , 1.200638  , 1.4366233 , 1.4238447 , 0.9671915 ,1.312595  , 1.3228288 , 1.4207268 , 1.3657233 , 1.3942413 ,1.3556252 , 1.2474568 , 0.95826834, 0.9713737 , 1.4608092 ,1.3343239 , 1.4897931 , 1.2164427 , 1.4206996 , 1.1842182 ,1.4668261 , 1.3606008 , 1.2877779 , 1.224715  , 1.2427652 ,1.2280475 , 1.3640418 , 1.2213793 , 1.4441583 , 1.3856096 ,1.355159  , 1.2137827 , 1.259018  , 1.4477049 , 1.3500743 ,1.2605615 , 1.3618308 , 1.4617825 , 1.1676052 , 0.9883976 ,1.1525701 , 1.2653346 , 1.2914594 , 1.4824603 , 1.3643179 ,1.3465466 , 1.3250558 , 1.3180401 , 1.2619693 , 1.2239132 ,1.2179544 , 1.3579661 , 1.311511  , 1.2277414 , 1.2076542 ,1.2422364 , 1.3891518 , 1.2159711 , 1.3345889 , 1.2452211 ,1.2429273 , 1.342675  , 1.4433756 , 1.4338367 , 1.3353238 ,1.2717611 , 1.2858913 , 1.418583  , 1.2045562 , 1.3998003 ,1.3214786 , 1.2111099 , 1.0366833 , 1.2018243 , 1.1990852 ,1.4218459 , 1.3604691 , 1.3180386 , 1.3878117 , 1.3803445 ,1.2660058 , 1.3165579 , 1.1985507 , 1.4630711 , 1.36143   ,1.2611161 , 1.2728775 , 1.1964376 , 1.3443307 , 1.339146  ,...1.1836145 , 1.1669254 , 1.2035089 , 1.4056509 , 1.1418431 ,0.8966577 , 0.891963  , 0.6152448 , 0.79655534, 0.7717408 ,1.1869099 , 1.202139  , 1.2955405 , 1.3649056 , 1.3104969 ,1.4641398 , 1.7085506 , 1.4805152 , 1.4331217 , 1.399699  ,1.3862162 , 1.1981647 , 1.1234413 , 1.4124444 , 1.2963744 ,1.2378123 , 1.2659993 , 1.2038934 , 1.3934321 , 1.6203713 ,1.3256226 , 1.2392617 , 1.2884889 , 1.202986  , 1.3743131 ,1.3255638 , 1.2302959 , 1.3092724 , 1.2134355 , 1.2935948 ,1.2994295 , 1.2765911 , 1.2814418 , 1.3545353 , 1.2349279 ,1.0951904 , 1.0391138 , 1.0005822 , 1.0176148 , 1.0688428 ,1.35657   , 1.2135618 , 1.4219955 , 1.3225292 , 1.2785586 ,1.275194  , 1.3355274 , 1.3949927 , 1.2883465 , 1.4057001 ,1.4236282 , 1.2925886 , 1.2891779 , 1.3144554 , 1.33754   ,1.3151662 , 1.2521679 , 1.2439616 , 1.6995414 , 1.3861445 ,1.3535012 , 1.2228161 , 1.3386501 , 1.3935357 , 1.3838186 ,1.4072384 , 1.4310058 , 1.2708198 , 1.3285922 , 1.1291428 ,1.2382853 , 1.3012738 , 1.287349  , 1.3014474 , 1.242337  ,1.3321948 , 1.3107737 , 1.3064048 , 1.4306538 , 1.3175644 ,1.2410822 , 1.4420744 , 1.1816049 , 1.1409183 , 1.1814541 ,1.4548798 , 1.2112384 , 1.2723444 , 1.3042331 , 1.2022628 ]],      dtype=float32)</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span>t_Intercept</span></div><div class='xr-var-dims'>(chain, draw)</div><div class='xr-var-dtype'>float32</div><div class='xr-var-preview xr-preview'>...</div><input id='attrs-48ca0d53-7bf5-4d04-afab-5276766f3a78' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-48ca0d53-7bf5-4d04-afab-5276766f3a78' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-1731fe6e-27bd-496e-a4c5-73b9ebd35ae1' class='xr-var-data-in' type='checkbox'><label for='data-1731fe6e-27bd-496e-a4c5-73b9ebd35ae1' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>Array([[0.20429376, 0.27498063, 0.27149004, 0.24850634, 0.20800616,0.17592594, 0.2827752 , 0.16293326, 0.18042724, 0.15242887,0.13310274, 0.2833843 , 0.20689206, 0.24024029, 0.21969108,0.23461413, 0.23430134, 0.22563031, 0.23676027, 0.18180935,0.26042518, 0.21082857, 0.28605375, 0.26917168, 0.27981052,0.32324323, 0.3117143 , 0.3158151 , 0.2946929 , 0.35113207,0.18214212, 0.19927621, 0.2912295 , 0.2009532 , 0.19001096,0.20238382, 0.22842707, 0.26465377, 0.17614901, 0.25123128,0.22956024, 0.33877334, 0.32412714, 0.17421147, 0.21836554,0.28820682, 0.2751492 , 0.24421856, 0.18106489, 0.17412643,0.20242536, 0.2742944 , 0.26172215, 0.29900795, 0.31204104,0.2840568 , 0.28127912, 0.22185218, 0.2293146 , 0.21943727,0.1475381 , 0.20838013, 0.21319397, 0.2746923 , 0.2502358 ,0.22667599, 0.21019271, 0.23774114, 0.1845732 , 0.31255582,0.20724636, 0.2695254 , 0.23273744, 0.2414947 , 0.22017175,0.23701364, 0.20395435, 0.18441007, 0.23664448, 0.23768073,0.3100226 , 0.19755265, 0.17696437, 0.1652838 , 0.16114983,0.187501  , 0.18047947, 0.1963631 , 0.14104663, 0.24363343,0.22869971, 0.27137607, 0.19386724, 0.2731886 , 0.2085296 ,0.23430413, 0.21213014, 0.2265982 , 0.20431696, 0.2624734 ,...0.23576783, 0.2838626 , 0.36330858, 0.31680593, 0.18617208,0.1410099 , 0.18431596, 0.18228133, 0.17017497, 0.17871214,0.26728824, 0.23208153, 0.1957871 , 0.26204523, 0.25057116,0.17894539, 0.12385643, 0.25029054, 0.21751842, 0.22168101,0.14737138, 0.30729863, 0.2266599 , 0.2606724 , 0.22195154,0.14530128, 0.14384688, 0.19351019, 0.20930724, 0.19907933,0.2417121 , 0.20244557, 0.17433299, 0.20197667, 0.13574073,0.2559069 , 0.22449666, 0.23018414, 0.2687618 , 0.24859042,0.25351402, 0.2528815 , 0.1284587 , 0.11956172, 0.13257085,0.1447229 , 0.20891517, 0.22897317, 0.21014303, 0.1806468 ,0.26666695, 0.21160907, 0.23099306, 0.22434522, 0.2143429 ,0.19290198, 0.21394768, 0.17724839, 0.18327431, 0.16961086,0.1906265 , 0.21848357, 0.2780559 , 0.23661724, 0.22229767,0.26746193, 0.14617145, 0.3304823 , 0.21047112, 0.2816949 ,0.29975668, 0.27747673, 0.2280325 , 0.26004705, 0.2546713 ,0.1729824 , 0.24456482, 0.22400004, 0.27717972, 0.2266901 ,0.2167627 , 0.24515252, 0.25458542, 0.26610032, 0.22853576,0.23231132, 0.22806127, 0.2244913 , 0.15446658, 0.15233354,0.32848677, 0.24847108, 0.19385687, 0.25275818, 0.23059538,0.22802487, 0.18646906, 0.18513606, 0.20173529, 0.2133292 ]],      dtype=float32)</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span>scaler_1|participant_id</span></div><div class='xr-var-dims'>(chain, draw, participant_id__factor_dim)</div><div class='xr-var-dtype'>float32</div><div class='xr-var-preview xr-preview'>...</div><input id='attrs-7078365d-b32a-45dc-b588-f70c6110d4cd' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-7078365d-b32a-45dc-b588-f70c6110d4cd' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-51adfda6-a2d4-4608-a43f-86552cfc1476' class='xr-var-data-in' type='checkbox'><label for='data-51adfda6-a2d4-4608-a43f-86552cfc1476' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>Array([[[-0.12724218,  0.09528601,  0.16785875, -0.15565047,-0.10698499],[-0.04740734,  0.14832704, -0.36914012, -0.61075824,-0.07077344],[ 0.31034276,  0.78692716,  0.01514927, -0.553314  ,0.9299212 ],...,[-0.4584201 ,  0.85259175,  0.24185011, -0.12993033,1.0325745 ],[-0.00693274,  0.05135338, -0.8840798 , -0.04910554,0.3649927 ],[ 0.10017202, -0.02444658, -0.98019433, -0.30955172,0.28475887]],[[-0.65730155,  0.09901449, -0.22706093,  0.20528297,0.86507714],[-0.3710161 ,  0.02556157, -0.3522298 , -0.620342  ,0.9743778 ],[-0.38454255,  0.10318137, -0.2772155 , -0.43136197,0.8234941 ],...,[-0.15088928, -0.01111543,  0.02060432, -0.29726344,-0.01332476],[-0.5262981 ,  0.22996534,  0.19126932, -0.21379304,0.40196413],[-0.97955716,  0.06731368,  0.38161775, -0.48560935,0.9065947 ]]], dtype=float32)</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span>z_1|participant_id_sigma</span></div><div class='xr-var-dims'>(chain, draw)</div><div class='xr-var-dtype'>float32</div><div class='xr-var-preview xr-preview'>...</div><input id='attrs-c863b63c-409f-4be1-a1a0-f9cbd483587f' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-c863b63c-409f-4be1-a1a0-f9cbd483587f' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-1b2f0c97-2e33-4979-b4af-c61af17b7674' class='xr-var-data-in' type='checkbox'><label for='data-1b2f0c97-2e33-4979-b4af-c61af17b7674' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>Array([[4.02238965e-03, 2.87979580e-02, 7.92072713e-02, 6.49871603e-02,1.91052333e-02, 5.68114035e-03, 5.05561046e-02, 1.52343186e-03,4.19553928e-03, 8.03923830e-02, 5.55189550e-02, 4.02201638e-02,4.12218124e-02, 5.11271432e-02, 1.73220396e-01, 2.56035794e-02,1.30079128e-02, 2.55139172e-02, 1.19191401e-01, 1.55012170e-02,2.62086391e-02, 2.34293099e-03, 3.08668520e-02, 4.08730470e-02,2.66522542e-02, 8.38199258e-03, 1.06914435e-03, 9.69493354e-04,1.99395046e-02, 3.29891518e-02, 2.19879486e-02, 2.89815124e-02,1.74515396e-02, 8.89875274e-03, 3.28566916e-02, 2.49697850e-03,2.47277096e-02, 7.50871655e-03, 2.20593344e-02, 7.20945373e-03,1.29083499e-01, 6.31475523e-02, 8.77866521e-02, 2.41498277e-02,6.59847856e-02, 7.50924647e-03, 3.05754133e-02, 9.26937908e-03,6.92105889e-02, 3.98685858e-02, 2.69465195e-03, 1.70740392e-02,2.13309452e-02, 8.25967873e-04, 1.23352557e-03, 3.67011060e-03,1.98769122e-02, 7.11905584e-03, 6.92360103e-02, 3.07033826e-02,4.35755402e-02, 3.62012573e-02, 4.90188599e-03, 9.53487493e-03,6.34571444e-03, 8.29555746e-03, 2.58541554e-02, 4.73310128e-02,1.19512780e-02, 1.73155721e-02, 8.96445010e-03, 5.18248715e-02,4.32774574e-02, 5.66207319e-02, 1.29134193e-01, 1.26093224e-01,1.39830127e-01, 3.00986581e-02, 4.84626889e-02, 1.51686464e-02,...6.08649664e-03, 2.35686339e-02, 7.94472173e-03, 6.77330093e-03,5.50006796e-03, 2.35077769e-05, 9.22667386e-05, 7.73358217e-04,7.44470069e-03, 2.25646850e-02, 3.03868279e-02, 4.74796817e-03,9.96968988e-03, 3.91883105e-02, 1.06445430e-02, 2.44146213e-02,2.74278875e-02, 2.22934298e-02, 1.02718621e-01, 9.11377072e-02,8.86202678e-02, 6.78165704e-02, 4.43549380e-02, 3.00379023e-02,2.23837309e-02, 2.75260936e-02, 2.26269457e-02, 2.00401545e-02,1.88557785e-02, 3.00001483e-02, 7.00094774e-02, 1.22483531e-02,5.07137645e-03, 5.12588024e-02, 1.61605049e-02, 1.61011163e-02,1.06769733e-01, 3.94076854e-02, 6.37028040e-03, 1.26305968e-02,1.08763315e-02, 1.32075534e-03, 4.26348448e-02, 3.04185487e-02,1.28451586e-02, 4.57582576e-03, 4.06834409e-02, 3.46370339e-02,4.25157845e-02, 1.06919892e-02, 9.81913134e-03, 1.14930756e-02,2.95253377e-02, 2.98112389e-02, 2.19243579e-02, 1.18478332e-02,4.23106439e-02, 1.48552759e-02, 8.27233959e-03, 1.62152480e-02,2.54498459e-02, 2.10803170e-02, 5.76325916e-02, 4.55326354e-03,1.58328861e-02, 5.07990550e-03, 1.60816275e-02, 4.46006432e-02,3.22351344e-02, 3.39215063e-02, 2.75400300e-02, 2.85395700e-02,8.48333724e-03, 2.93699801e-02, 3.32823023e-02, 1.34020839e-02,1.28975123e-01, 8.86445213e-03, 2.39766575e-02, 2.39030980e-02]],      dtype=float32)</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span>rl_alpha_1|participant_id_offset</span></div><div class='xr-var-dims'>(chain, draw, rl_alpha_1|participant_id__factor_dim)</div><div class='xr-var-dtype'>float32</div><div class='xr-var-preview xr-preview'>...</div><input id='attrs-8d8cd445-9274-41d6-89fe-7fbf376bd7b2' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-8d8cd445-9274-41d6-89fe-7fbf376bd7b2' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-690374bb-96cc-4bc4-94d7-86158a36316e' class='xr-var-data-in' type='checkbox'><label for='data-690374bb-96cc-4bc4-94d7-86158a36316e' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>Array([[[-1.4583458 , -0.1834005 , -1.7675729 , -0.7929651 ,0.33906054],[-0.9838688 ,  0.13236625, -0.37069857, -0.52243483,0.7221021 ],[ 0.83617693, -0.02563862,  0.21170521,  0.9761566 ,-0.3223305 ],...,[-0.20692724,  0.9622859 , -2.056054  , -1.0922807 ,0.8248903 ],[-0.7375505 ,  0.5781889 , -0.3293935 , -1.9095021 ,0.58886063],[-0.96234685,  0.47929683,  0.21281567, -1.4517846 ,0.63607436]],[[ 0.7071711 ,  0.957604  , -0.06592099,  0.12291435,1.4009433 ],[ 0.27850252,  0.40871337,  0.26389116,  0.19096756,1.5311518 ],[ 0.02674573,  0.34528947,  0.16845411,  0.287602  ,1.3711046 ],...,[ 0.9611176 ,  1.189063  ,  0.5103071 ,  0.07064422,1.6606704 ],[ 0.35802588,  0.72372174,  0.0551132 ,  0.11746906,0.6364546 ],[ 0.6428101 ,  0.44201526,  0.20125914,  0.5251205 ,1.2930368 ]]], dtype=float32)</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span>scaler_Intercept</span></div><div class='xr-var-dims'>(chain, draw)</div><div class='xr-var-dtype'>float32</div><div class='xr-var-preview xr-preview'>...</div><input id='attrs-4df8d0ff-1f58-417d-b4ff-7e25dc3263cb' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-4df8d0ff-1f58-417d-b4ff-7e25dc3263cb' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-b1ace3dc-bf49-45ab-82ce-f56f13eb2a34' class='xr-var-data-in' type='checkbox'><label for='data-b1ace3dc-bf49-45ab-82ce-f56f13eb2a34' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>Array([[2.5781446, 2.992829 , 1.5567404, 2.036927 , 2.536706 , 2.69148  ,1.9040236, 2.420907 , 2.0601294, 1.1375544, 2.6785386, 1.9031553,2.3323398, 2.1545026, 1.9566203, 2.369926 , 2.1081967, 2.6842592,2.235254 , 1.864192 , 2.293417 , 1.7800184, 2.4311817, 2.067805 ,2.1963649, 2.4584596, 2.14223  , 2.467307 , 2.4636774, 1.8615661,2.1479483, 2.2010355, 1.767842 , 2.1316552, 1.6828085, 2.268453 ,2.0911984, 1.9589835, 1.9607089, 2.5536306, 2.1101544, 1.5524306,1.6346022, 1.4950063, 1.541143 , 2.8682895, 1.7923349, 2.2662683,1.8786868, 2.60623  , 2.036839 , 2.054912 , 2.1625834, 2.2858214,1.7824197, 1.4908311, 1.5191097, 1.7530359, 2.4760888, 2.3066962,2.0962093, 2.613377 , 1.3162827, 2.0850432, 1.6497   , 2.259887 ,1.609937 , 1.3778927, 1.657495 , 2.4477644, 1.5300596, 2.1552336,2.8356192, 2.4232285, 1.9697496, 1.846558 , 2.895831 , 1.6034971,2.2969556, 1.9890816, 1.8510605, 1.9989823, 2.4571683, 2.9235003,3.0197678, 1.1969279, 1.6838187, 1.3303384, 1.9730204, 2.5390184,2.3290956, 2.2273798, 2.5758598, 1.1932049, 2.0154767, 2.0911512,1.9480443, 1.7723253, 2.4402046, 1.9540313, 1.0469239, 1.3538907,2.4495103, 2.1145554, 2.6570854, 3.0647   , 2.2599857, 1.9213729,1.3824644, 2.727355 , 2.230659 , 1.7583845, 1.9623467, 2.340105 ,2.152429 , 1.9553975, 2.6350238, 2.3475423, 1.7837088, 2.1389022,...2.4321432, 2.6689534, 2.251665 , 1.9547993, 1.6717618, 2.5578256,2.210853 , 2.3399084, 2.8077908, 1.5320876, 2.2213693, 2.031137 ,1.9557889, 1.8906813, 1.6619134, 1.4643192, 1.8486531, 2.4192598,2.1126966, 1.9710371, 2.703472 , 2.263426 , 1.8873937, 2.395034 ,2.076871 , 1.9643289, 2.0778146, 2.5234373, 2.304156 , 2.0006764,1.5076383, 1.6301254, 2.5118966, 1.7566262, 2.1303234, 1.7869241,1.6726425, 2.1054716, 1.8234112, 1.9675629, 1.7693186, 1.7126635,2.123502 , 1.8566015, 1.8256918, 2.485129 , 2.308    , 1.7532628,2.7108912, 1.4744066, 1.7965763, 1.9162788, 1.679426 , 2.1283855,2.196675 , 2.378937 , 2.595263 , 2.5286326, 1.972859 , 2.724022 ,2.500515 , 1.5593837, 1.5734426, 1.6225228, 1.9330986, 1.9890927,1.9212646, 1.9107966, 1.7317649, 1.9234849, 2.5846696, 1.3928509,2.6117628, 1.5355712, 2.1989849, 2.2920008, 1.9459088, 2.2474327,2.5494564, 2.7618148, 2.685565 , 2.4480748, 2.2261257, 2.4759278,1.5170454, 1.3756938, 3.0110514, 1.231868 , 3.405536 , 2.3134112,2.281167 , 1.9168472, 2.8940902, 1.9908631, 2.0990086, 1.8382933,2.5440907, 1.626494 , 2.3567607, 1.6649809, 2.9683652, 2.728997 ,2.7030623, 2.6111214, 2.2609172, 2.1119092, 2.2117121, 2.118388 ,2.013773 , 2.6923487, 1.6401695, 1.9889048, 2.286061 , 2.6280704,2.203427 , 2.3416474, 1.9519681, 2.2224522, 2.3075871, 2.592976 ]],      dtype=float32)</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span>t_1|participant_id</span></div><div class='xr-var-dims'>(chain, draw, participant_id__factor_dim)</div><div class='xr-var-dtype'>float32</div><div class='xr-var-preview xr-preview'>...</div><input id='attrs-a2ceeca4-8c06-450d-80ba-35f61a21d2ed' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-a2ceeca4-8c06-450d-80ba-35f61a21d2ed' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-43b5f6b6-7ed6-4bf5-beab-7c84005d92c7' class='xr-var-data-in' type='checkbox'><label for='data-43b5f6b6-7ed6-4bf5-beab-7c84005d92c7' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>Array([[[-0.06376672, -0.04993222,  0.13111302, -0.07813247,0.09242752],[ 0.02409178, -0.07048429,  0.03509193, -0.11638021,0.07817297],[-0.04921572, -0.12666981, -0.03316658, -0.02208503,-0.03093472],...,[-0.20125385, -0.20306695, -0.01818475, -0.14560078,-0.08889914],[ 0.15201482, -0.10619114,  0.13986848, -0.06103271,0.15117928],[ 0.16600633, -0.10836337,  0.11734632,  0.00866974,0.16442266]],[[-0.01259228, -0.10968252, -0.09148683, -0.08207267,-0.00364707],[-0.03686487, -0.18071397,  0.00871082, -0.1489712 ,0.00975429],[-0.03108446, -0.1730186 , -0.01905845, -0.14345048,0.02632551],...,[ 0.0857605 , -0.17882955,  0.11254551, -0.11909435,0.1165699 ],[ 0.04827872, -0.0177493 ,  0.1007153 , -0.02146922,0.11693235],[-0.04732214, -0.06630916,  0.05126338,  0.05879094,0.11040018]]], dtype=float32)</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span>scaler_1|participant_id_sigma</span></div><div class='xr-var-dims'>(chain, draw)</div><div class='xr-var-dtype'>float32</div><div class='xr-var-preview xr-preview'>...</div><input id='attrs-82d5b94c-c618-46c7-af67-ef619e97ccff' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-82d5b94c-c618-46c7-af67-ef619e97ccff' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-80867462-3297-4045-85e4-79ae214482e6' class='xr-var-data-in' type='checkbox'><label for='data-80867462-3297-4045-85e4-79ae214482e6' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>Array([[0.13340767, 0.34862772, 0.44254667, 0.32894582, 0.7568719 ,0.68209577, 0.4275481 , 0.4291643 , 0.4182442 , 0.95161235,0.1367785 , 0.1414208 , 0.17384905, 0.15425827, 0.6787505 ,0.72861636, 0.49945366, 0.5993028 , 0.7233461 , 0.5473998 ,1.1238606 , 0.27942935, 0.7574739 , 0.54566807, 0.33235288,0.736156  , 0.5862029 , 0.1611438 , 0.55082077, 0.2878541 ,0.6753079 , 0.6162547 , 0.58880866, 0.7178681 , 0.8018997 ,0.25592086, 0.24878518, 1.1680238 , 0.35061294, 0.38666484,0.07043374, 0.07760122, 0.05025742, 0.6429302 , 0.4432716 ,0.96289814, 0.43240345, 1.271362  , 0.22372411, 0.20080048,0.6861402 , 0.28101957, 0.36429602, 0.72767866, 0.5851836 ,0.6850953 , 0.63018185, 0.5115021 , 0.27640507, 0.39333704,0.8693793 , 0.6794719 , 0.8831148 , 0.4443033 , 0.7030417 ,0.6717287 , 0.68088615, 0.7362968 , 0.655773  , 0.5741432 ,0.32220313, 0.5149812 , 0.39010492, 0.42978236, 0.59684473,0.535463  , 1.0926379 , 0.5284777 , 0.8426983 , 0.39834523,0.29726127, 1.123578  , 0.65921074, 0.6085105 , 0.6174154 ,0.55322117, 0.37959534, 0.32937628, 0.4485484 , 0.5124198 ,0.73402846, 0.19666782, 0.7126062 , 1.1158915 , 0.19709478,0.11385109, 0.43480134, 0.5748188 , 0.46433115, 0.6183124 ,...1.1546807 , 0.24616243, 0.2668758 , 0.4954845 , 0.09883666,0.52970994, 0.6060829 , 0.9055898 , 0.4256684 , 1.1199917 ,0.64085084, 1.0786077 , 0.5424404 , 0.02797462, 0.7368654 ,0.76908815, 0.7076762 , 0.6968908 , 0.42555425, 0.63616204,0.61956984, 0.97388625, 1.0468934 , 0.46264985, 0.36818495,1.5588557 , 0.93727684, 0.34195602, 1.1557238 , 0.6586455 ,0.41250008, 0.79484975, 0.6359674 , 0.63107765, 0.6305326 ,0.99925953, 0.61341953, 0.90112567, 0.30519688, 0.900041  ,0.9486877 , 0.9190723 , 0.44299954, 0.26895276, 0.37199235,0.76625264, 0.17327608, 0.5124413 , 0.2806732 , 0.5236725 ,0.7537318 , 0.5743186 , 0.68010986, 1.1392426 , 0.4125771 ,0.00447324, 0.12689923, 0.4070306 , 0.35645762, 0.10485173,0.09973635, 0.05624477, 0.8146205 , 0.04609393, 0.42065716,0.73620117, 0.74923563, 0.46617177, 0.70935917, 0.75286764,0.8031564 , 0.4669776 , 0.5467308 , 0.42558643, 0.51609385,0.03881805, 0.31721568, 0.94562066, 0.5606836 , 0.20082773,0.01557604, 0.52448773, 1.0141231 , 0.43188125, 0.24663348,0.5484156 , 0.6781083 , 0.06291974, 0.06640424, 0.33060852,0.45117497, 0.4212089 , 0.89309   , 0.7188679 , 0.6207548 ,0.18691622, 1.1141196 , 0.23003794, 0.23903781, 0.50826705]],      dtype=float32)</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span>t_1|participant_id_offset</span></div><div class='xr-var-dims'>(chain, draw, participant_id__factor_dim)</div><div class='xr-var-dtype'>float32</div><div class='xr-var-preview xr-preview'>...</div><input id='attrs-d013bf51-73e9-441d-bd45-c605c9fba7cc' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-d013bf51-73e9-441d-bd45-c605c9fba7cc' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-ce9dba69-398a-48aa-8562-76981348a7b1' class='xr-var-data-in' type='checkbox'><label for='data-ce9dba69-398a-48aa-8562-76981348a7b1' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>Array([[[-0.49864465, -0.3904613 ,  1.0252811 , -0.6109823 ,0.7227672 ],[ 0.25790572, -0.75454354,  0.3756637 , -1.2458655 ,0.8368519 ],[-0.8385356 , -2.1581955 , -0.565091  , -0.37628388,-0.52706456],...,[-0.9326473 , -0.9410495 , -0.08427145, -0.67474073,-0.41197494],[ 1.1512989 , -0.8042488 ,  1.0593075 , -0.4622371 ,1.1449709 ],[ 1.2384009 , -0.8083866 ,  0.8753991 ,  0.0646759 ,1.2265868 ]],[[-0.06669051, -0.58089435, -0.48452738, -0.43466863,-0.01931539],[-0.19193982, -0.94090134,  0.04535358, -0.7756302 ,0.05078649],[-0.15727612, -0.8754117 , -0.09642889, -0.7258076 ,0.13319756],...,[ 0.38997272, -0.8131791 ,  0.5117703 , -0.5415494 ,0.5300701 ],[ 0.33289686, -0.12238698,  0.6944635 , -0.14803696,0.80628514],[-0.3428137 , -0.48036057,  0.3713651 ,  0.42589667,0.79976726]]], dtype=float32)</pre></div></li></ul></div></li><li class='xr-section-item'><input id='section-6a1f80b4-ab79-4e48-91a1-c1135c5c170d' class='xr-section-summary-in' type='checkbox' /><label for='section-6a1f80b4-ab79-4e48-91a1-c1135c5c170d' class='xr-section-summary' title='Expand/collapse section'>Attributes: <span>(11)</span></label><div class='xr-section-inline-details'></div><div class='xr-section-details'><dl class='xr-attrs'><dt><span>created_at :</span></dt><dd>2026-07-24T14:18:40.484086+00:00</dd><dt><span>creation_library :</span></dt><dd>ArviZ</dd><dt><span>creation_library_version :</span></dt><dd>1.2.0</dd><dt><span>creation_library_language :</span></dt><dd>Python</dd><dt><span>sample_dims :</span></dt><dd>[&#x27;chain&#x27;, &#x27;draw&#x27;]</dd><dt><span>inference_library :</span></dt><dd>numpyro</dd><dt><span>inference_library_version :</span></dt><dd>0.21.0</dd><dt><span>sampling_time :</span></dt><dd>92.736215</dd><dt><span>tuning_steps :</span></dt><dd>300</dd><dt><span>modeling_interface :</span></dt><dd>bambi</dd><dt><span>modeling_interface_version :</span></dt><dd>0.19.0</dd></dl></div></li></ul></div></div><div class='xr-group-box'><div class='xr-group-box-vline' style='height: 100%'></div><div class='xr-group-box-hline'></div><div class='xr-group-box-contents'><input id='group-58951af9-1f37-4399-b1ba-44017f3c6b68' type='checkbox' checked /><label for='group-58951af9-1f37-4399-b1ba-44017f3c6b68' title='Expand/collapse group'>/sample_stats<span>(16)</span></label><ul class='xr-sections'><li class='xr-section-item'><input id='section-2a4c6430-de5d-44ed-a20f-d11096e1ea6b' class='xr-section-summary-in' type='checkbox' disabled /><label for='section-2a4c6430-de5d-44ed-a20f-d11096e1ea6b' class='xr-section-summary'>Dimensions:</label><div class='xr-section-inline-details'><ul class='xr-dim-list'><li><span class='xr-has-index'>chain</span>: 2</li><li><span class='xr-has-index'>draw</span>: 300</li></ul></div></li><li class='xr-section-item'><input id='section-9eb60745-3274-45e7-8180-9e590d3af35d' class='xr-section-summary-in' type='checkbox' checked /><label for='section-9eb60745-3274-45e7-8180-9e590d3af35d' class='xr-section-summary' title='Expand/collapse section'>Coordinates: <span>(2)</span></label><div class='xr-section-inline-details'></div><div class='xr-section-details'><ul class='xr-var-list'><li class='xr-var-item'><div class='xr-var-name'><span class='xr-has-index'>chain</span></div><div class='xr-var-dims'>(chain)</div><div class='xr-var-dtype'>int64</div><div class='xr-var-preview xr-preview'>0 1</div><input id='attrs-396b0c55-ef8d-41b0-a0e5-94945102b88b' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-396b0c55-ef8d-41b0-a0e5-94945102b88b' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-b0d81740-737d-4bd5-8ef7-b94e97b5275b' class='xr-var-data-in' type='checkbox'><label for='data-b0d81740-737d-4bd5-8ef7-b94e97b5275b' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>array([0, 1])</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span class='xr-has-index'>draw</span></div><div class='xr-var-dims'>(draw)</div><div class='xr-var-dtype'>int64</div><div class='xr-var-preview xr-preview'>0 1 2 3 4 5 ... 295 296 297 298 299</div><input id='attrs-0d4dac36-ec71-4e99-8b9b-e5aa552253a0' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-0d4dac36-ec71-4e99-8b9b-e5aa552253a0' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-f42fc96d-24c0-4b20-adb6-63b77dae4f83' class='xr-var-data-in' type='checkbox'><label for='data-f42fc96d-24c0-4b20-adb6-63b77dae4f83' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>array([  0,   1,   2, ..., 297, 298, 299], shape=(300,))</pre></div></li></ul></div></li><li class='xr-section-item'><input id='section-dc39c12e-6a1a-4aaa-b0e9-4bd5088deeb5' class='xr-section-summary-in' type='checkbox' checked /><label for='section-dc39c12e-6a1a-4aaa-b0e9-4bd5088deeb5' class='xr-section-summary' title='Expand/collapse section'>Data variables: <span>(7)</span></label><div class='xr-section-inline-details'></div><div class='xr-section-details'><ul class='xr-var-list'><li class='xr-var-item'><div class='xr-var-name'><span>acceptance_rate</span></div><div class='xr-var-dims'>(chain, draw)</div><div class='xr-var-dtype'>float32</div><div class='xr-var-preview xr-preview'>...</div><input id='attrs-609efda6-e8ec-4ac1-b3ae-3edead5acffe' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-609efda6-e8ec-4ac1-b3ae-3edead5acffe' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-4b0988c6-cf20-41a7-ba28-e817793edb40' class='xr-var-data-in' type='checkbox'><label for='data-4b0988c6-cf20-41a7-ba28-e817793edb40' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>Array([[0.96033674, 0.8785385 , 0.9820714 , 0.9863686 , 0.994483  ,0.99023825, 0.99653745, 0.99282223, 0.90245646, 0.99534595,0.9904857 , 0.9891426 , 0.98611236, 0.9942626 , 0.9972338 ,0.9405561 , 0.95695835, 0.9882534 , 0.9969338 , 0.9875914 ,0.9887006 , 0.9916961 , 0.9960462 , 0.9837527 , 0.8990402 ,0.99206865, 0.9827689 , 0.9803307 , 0.943846  , 0.99702525,0.9990385 , 0.9496129 , 0.9940236 , 0.99469763, 0.95209885,0.9901723 , 0.9866789 , 0.98635125, 0.9987865 , 0.999542  ,0.9929037 , 0.28419018, 0.98511004, 0.9797076 , 0.9915367 ,0.98519486, 0.9839503 , 0.9619202 , 0.991879  , 0.94194764,0.99715704, 0.99976903, 0.96494406, 0.96217024, 0.98178136,0.9874852 , 0.997905  , 0.99511   , 0.96049774, 0.9961498 ,0.99443114, 0.93212795, 0.9857865 , 0.99933666, 0.87130153,0.9784243 , 0.99229795, 0.9779368 , 0.99347186, 0.9846669 ,0.9859598 , 0.998529  , 0.984862  , 0.996657  , 0.7236629 ,0.9970846 , 0.9886987 , 0.8694975 , 0.99935395, 0.972987  ,0.9969377 , 0.9579095 , 0.9886085 , 0.9313275 , 0.49333653,0.9847623 , 0.9744419 , 0.98128206, 0.9963799 , 0.98145014,0.98722523, 0.994483  , 0.9982593 , 0.9745124 , 0.9530094 ,0.9952149 , 0.9975513 , 0.99041146, 0.991592  , 0.9978259 ,...0.9586123 , 0.94658196, 0.98139423, 0.9751742 , 0.9874203 ,0.9638471 , 0.9976397 , 0.9840162 , 0.90788823, 0.9901285 ,0.95799446, 0.9735382 , 0.8768373 , 0.9757264 , 0.6301406 ,0.963528  , 0.93554217, 0.9928374 , 0.9536201 , 0.97160363,0.98371214, 0.99190116, 0.99053854, 0.7703814 , 0.96554214,0.91680616, 0.9677528 , 0.9942691 , 0.99903274, 0.9860314 ,0.8888703 , 0.97516924, 0.9188446 , 0.96756834, 0.9888423 ,0.99652183, 0.94525194, 0.99441636, 0.99364007, 0.9168337 ,0.9287331 , 0.89844596, 0.9495652 , 0.52007544, 0.9756007 ,0.9488158 , 0.8018742 , 0.9756092 , 0.92648005, 0.93386227,0.999375  , 0.99614424, 0.98527473, 0.9266179 , 0.8391148 ,0.9015719 , 0.9863369 , 1.        , 0.9396374 , 0.93610007,0.8777985 , 0.9849296 , 0.9919399 , 0.98869467, 0.95085484,0.9229436 , 0.95857227, 0.8998047 , 0.98646224, 0.9949147 ,0.9801192 , 0.90860146, 0.44431046, 0.6622707 , 0.964171  ,0.91531557, 0.9523704 , 0.9873122 , 0.98869765, 0.99862474,0.99509776, 0.97191894, 0.9766037 , 0.9545402 , 0.99979067,0.997041  , 0.9559865 , 0.98722875, 0.9506962 , 0.9985499 ,0.99033576, 0.98290193, 0.94678754, 0.9920247 , 0.99612945,0.98739576, 0.99450034, 0.82199144, 0.9111446 , 0.93137115]],      dtype=float32)</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span>step_size</span></div><div class='xr-var-dims'>(chain, draw)</div><div class='xr-var-dtype'>float32</div><div class='xr-var-preview xr-preview'>...</div><input id='attrs-b3820ffe-3995-4ada-85f3-7d0da81b73ed' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-b3820ffe-3995-4ada-85f3-7d0da81b73ed' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-bae67c10-9122-4345-b0cb-e50727104ee6' class='xr-var-data-in' type='checkbox'><label for='data-bae67c10-9122-4345-b0cb-e50727104ee6' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>Array([[0.04308953, 0.04308953, 0.04308953, 0.04308953, 0.04308953,0.04308953, 0.04308953, 0.04308953, 0.04308953, 0.04308953,0.04308953, 0.04308953, 0.04308953, 0.04308953, 0.04308953,0.04308953, 0.04308953, 0.04308953, 0.04308953, 0.04308953,0.04308953, 0.04308953, 0.04308953, 0.04308953, 0.04308953,0.04308953, 0.04308953, 0.04308953, 0.04308953, 0.04308953,0.04308953, 0.04308953, 0.04308953, 0.04308953, 0.04308953,0.04308953, 0.04308953, 0.04308953, 0.04308953, 0.04308953,0.04308953, 0.04308953, 0.04308953, 0.04308953, 0.04308953,0.04308953, 0.04308953, 0.04308953, 0.04308953, 0.04308953,0.04308953, 0.04308953, 0.04308953, 0.04308953, 0.04308953,0.04308953, 0.04308953, 0.04308953, 0.04308953, 0.04308953,0.04308953, 0.04308953, 0.04308953, 0.04308953, 0.04308953,0.04308953, 0.04308953, 0.04308953, 0.04308953, 0.04308953,0.04308953, 0.04308953, 0.04308953, 0.04308953, 0.04308953,0.04308953, 0.04308953, 0.04308953, 0.04308953, 0.04308953,0.04308953, 0.04308953, 0.04308953, 0.04308953, 0.04308953,0.04308953, 0.04308953, 0.04308953, 0.04308953, 0.04308953,0.04308953, 0.04308953, 0.04308953, 0.04308953, 0.04308953,0.04308953, 0.04308953, 0.04308953, 0.04308953, 0.04308953,...0.05788062, 0.05788062, 0.05788062, 0.05788062, 0.05788062,0.05788062, 0.05788062, 0.05788062, 0.05788062, 0.05788062,0.05788062, 0.05788062, 0.05788062, 0.05788062, 0.05788062,0.05788062, 0.05788062, 0.05788062, 0.05788062, 0.05788062,0.05788062, 0.05788062, 0.05788062, 0.05788062, 0.05788062,0.05788062, 0.05788062, 0.05788062, 0.05788062, 0.05788062,0.05788062, 0.05788062, 0.05788062, 0.05788062, 0.05788062,0.05788062, 0.05788062, 0.05788062, 0.05788062, 0.05788062,0.05788062, 0.05788062, 0.05788062, 0.05788062, 0.05788062,0.05788062, 0.05788062, 0.05788062, 0.05788062, 0.05788062,0.05788062, 0.05788062, 0.05788062, 0.05788062, 0.05788062,0.05788062, 0.05788062, 0.05788062, 0.05788062, 0.05788062,0.05788062, 0.05788062, 0.05788062, 0.05788062, 0.05788062,0.05788062, 0.05788062, 0.05788062, 0.05788062, 0.05788062,0.05788062, 0.05788062, 0.05788062, 0.05788062, 0.05788062,0.05788062, 0.05788062, 0.05788062, 0.05788062, 0.05788062,0.05788062, 0.05788062, 0.05788062, 0.05788062, 0.05788062,0.05788062, 0.05788062, 0.05788062, 0.05788062, 0.05788062,0.05788062, 0.05788062, 0.05788062, 0.05788062, 0.05788062,0.05788062, 0.05788062, 0.05788062, 0.05788062, 0.05788062]],      dtype=float32)</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span>diverging</span></div><div class='xr-var-dims'>(chain, draw)</div><div class='xr-var-dtype'>bool</div><div class='xr-var-preview xr-preview'>...</div><input id='attrs-8c2ad18f-866e-453d-9a79-946cd7e75c56' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-8c2ad18f-866e-453d-9a79-946cd7e75c56' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-d67bb0fa-2f26-40ec-b7ba-3cf9e7d21ac9' class='xr-var-data-in' type='checkbox'><label for='data-d67bb0fa-2f26-40ec-b7ba-3cf9e7d21ac9' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>Array([[False, False, False, False, False,  True, False, False, False,False, False, False, False, False, False, False,  True, False,False, False, False, False, False, False, False, False, False,False, False, False, False, False, False, False, False, False,False,  True, False, False, False, False,  True, False, False,False, False, False, False, False, False, False,  True, False,True,  True, False, False, False, False, False, False,  True,False, False, False, False, False, False, False, False, False,False, False, False, False, False, False, False, False, False,False,  True,  True, False, False,  True,  True, False, False,False, False, False, False, False, False, False, False, False,False, False, False, False,  True, False, False, False, False,False, False, False, False, False, False, False, False, False,False, False, False, False,  True,  True, False, False, False,False, False, False, False,  True, False, False, False, False,False, False, False, False, False, False, False,  True, False,False,  True, False, False, False, False, False, False, False,True, False, False, False, False, False, False, False, False,False, False, False, False,  True, False, False, False, False,False, False, False, False,  True, False, False, False, False,...False,  True,  True, False, False, False, False, False, False,False, False, False, False, False, False, False, False,  True,True,  True, False, False, False, False, False, False, False,True, False, False, False, False, False, False, False, False,False, False, False, False, False, False, False, False, False,False, False, False,  True, False, False, False, False, False,False, False, False, False, False, False, False, False, False,False, False, False, False, False, False, False, False, False,False, False, False, False, False, False, False, False, False,False, False, False, False, False, False, False, False, False,False, False, False, False, False, False, False, False, False,False,  True, False, False, False,  True, False, False, False,False, False, False, False, False, False,  True, False,  True,False, False,  True, False, False,  True, False, False, False,False, False, False, False, False, False, False, False,  True,False, False, False, False, False, False, False, False, False,False, False, False, False, False, False, False, False,  True,False, False, False,  True, False, False, False, False, False,False, False, False, False, False, False, False, False, False,False,  True, False]], dtype=bool)</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span>energy</span></div><div class='xr-var-dims'>(chain, draw)</div><div class='xr-var-dtype'>float32</div><div class='xr-var-preview xr-preview'>...</div><input id='attrs-6308e585-8421-405f-94b9-5b57a7f640b8' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-6308e585-8421-405f-94b9-5b57a7f640b8' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-b92645e5-e14a-45af-b716-2b0ebeaf145f' class='xr-var-data-in' type='checkbox'><label for='data-b92645e5-e14a-45af-b716-2b0ebeaf145f' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>Array([[417.37372, 408.13934, 411.51462, 423.3831 , 416.0995 , 420.82867,411.04047, 414.07523, 412.09937, 410.49966, 409.98077, 408.5478 ,409.17242, 411.05908, 408.84412, 398.4337 , 402.15662, 404.53802,400.0314 , 405.63333, 412.26804, 409.96353, 415.2818 , 400.69794,410.03928, 404.7884 , 402.45413, 407.39087, 417.2657 , 413.5756 ,407.51877, 404.95154, 404.1412 , 405.03818, 413.18018, 418.00397,415.174  , 416.11166, 418.48727, 414.06784, 409.79874, 406.51147,412.41028, 411.85272, 407.68625, 399.5388 , 403.39896, 399.15543,391.58862, 410.43857, 404.71637, 408.8736 , 410.99005, 422.84448,417.58075, 411.41858, 402.53528, 415.07983, 423.38907, 425.68658,431.3903 , 427.58386, 416.8509 , 400.5799 , 415.90247, 412.8284 ,411.9002 , 404.27402, 414.73978, 414.50424, 412.5673 , 403.12097,408.52753, 399.49133, 403.38492, 396.78308, 406.65125, 405.841  ,408.28235, 413.06073, 407.925  , 403.36963, 406.90506, 413.3538 ,412.60193, 411.3907 , 409.38342, 409.08984, 409.84793, 414.0578 ,418.22913, 418.16528, 417.35794, 410.15143, 416.78122, 425.46576,419.89603, 418.855  , 415.7962 , 411.71478, 414.01254, 426.361  ,419.96   , 410.82355, 403.54593, 402.2301 , 411.84314, 416.9576 ,413.51752, 413.6648 , 410.83038, 412.377  , 398.8613 , 401.78644,421.11856, 414.54956, 398.94305, 395.90332, 406.30173, 401.81247,...406.07404, 409.12964, 405.3146 , 403.73376, 400.04343, 405.356  ,405.7354 , 402.39514, 411.7399 , 412.24442, 402.36432, 403.7052 ,411.26385, 412.08636, 417.61224, 406.2213 , 401.955  , 412.8834 ,406.5622 , 395.654  , 404.09766, 410.14392, 413.85522, 417.7788 ,413.0369 , 425.33008, 419.6769 , 412.2022 , 405.09073, 398.33948,405.48914, 402.29477, 400.84103, 407.1877 , 421.64233, 416.09674,431.29767, 426.31082, 410.73077, 423.32614, 415.90036, 411.3552 ,411.91266, 406.854  , 417.52277, 421.64816, 409.49417, 414.96378,416.27026, 407.19144, 407.029  , 410.18478, 399.65857, 403.71484,407.206  , 408.16797, 411.33548, 406.61597, 397.60278, 407.44934,412.58295, 408.87952, 400.29532, 398.09726, 399.2009 , 403.94397,405.73438, 406.16138, 405.67126, 412.3213 , 416.19165, 412.16623,404.90594, 399.94357, 405.81232, 408.13043, 412.95157, 401.56046,408.51492, 416.84177, 414.6606 , 414.40808, 410.29498, 404.2446 ,409.4695 , 410.5826 , 417.79837, 409.90817, 417.7141 , 408.71362,395.64685, 406.03967, 404.6269 , 412.23822, 399.94223, 411.46286,411.27017, 408.50903, 413.5001 , 417.8953 , 436.79562, 433.7493 ,433.67606, 435.73825, 437.8208 , 434.51202, 431.99097, 417.06482,423.4579 , 410.41013, 405.3744 , 403.3717 , 416.26294, 410.8223 ,413.10056, 408.43378, 415.79883, 412.80518, 424.65152, 410.04996]],      dtype=float32)</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span>n_steps</span></div><div class='xr-var-dims'>(chain, draw)</div><div class='xr-var-dtype'>int32</div><div class='xr-var-preview xr-preview'>...</div><input id='attrs-c08b939c-0d62-4096-b3d7-556591099d44' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-c08b939c-0d62-4096-b3d7-556591099d44' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-8f076542-61fe-43a9-85e9-0ec6709b0aef' class='xr-var-data-in' type='checkbox'><label for='data-8f076542-61fe-43a9-85e9-0ec6709b0aef' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>Array([[127, 127, 127, 127, 127, 126, 127, 127, 127, 127, 127, 127, 127,127, 127, 127,  28, 127, 127, 127, 127, 127, 127, 127, 127, 127,127, 127, 127, 127, 127, 127, 127, 127,  63,  63, 127,  95, 127,127, 127, 127, 123, 127,  63, 127,  63, 127, 127, 127, 127,  63,41, 127,  61, 105,  63, 127, 127, 127,  63, 127, 133, 127, 127,63, 127, 127, 127, 127, 127, 127, 127,  63,  63, 127, 127, 127,127,  63, 127, 127, 103,  95, 127, 127,  42,  55, 127, 127, 127,127, 127, 127, 127, 127, 127, 127, 127, 127, 127, 127, 127,  84,127, 127, 127, 127, 127, 127, 127, 127, 127, 127, 127, 127, 127,127, 127, 127, 127, 119,  10, 127, 127,  63, 127, 127, 127, 127,71, 127, 127, 127,  63, 127, 127, 127, 127, 127, 127, 127,  63,127, 127, 102, 127, 127,  63, 127, 127, 127, 127,  68, 127, 127,127,  63, 127, 127, 127, 127, 127, 127, 127, 127, 118, 127, 127,63,  63, 127,  63, 127, 127,  59,  63, 127, 127, 127, 127, 127,127,  63, 127,   1, 127, 125, 127, 127, 127, 127,  26, 127,  63,127, 127, 127,  59, 127, 127, 127,  63, 127, 127, 127, 127, 127,23, 127, 127, 127, 127, 127, 127, 127, 127,  34, 127, 108, 127,127, 127,  87, 127, 127,  63, 127, 127, 127, 127, 127, 127,  47,127, 127, 127, 127, 127,  63,  51, 127,  63, 127,  63, 127,  84,63,  92,   4,   6,  65, 127, 127,  63, 127, 127, 127, 127, 127,...63, 127,  63,  63,  14,  63, 127,  63,  63, 127, 127, 127, 127,63,  63,  63,  63,  63,  87,  63,  63,  63, 127,  63,  54,  63,63,  63,  59,  63,  63, 191, 127, 127,  63,  63,  63,  63,  63,63, 127,  63, 127,  63,  63,  63,  63,  63, 127,  63,  63, 127,37,  40,  31, 127,  63,  63,  48,  63, 127,  63,  44, 127,  47,63,  63,  63,  63, 127, 127,  63, 127,  42,  63,  21,  35, 127,127,  63, 127,  63,  63,  63,  63,  63, 127,  63,  63, 127,  63,24,   9,  33, 127,  63,  63, 127,  63,  63,  63,  54,  63, 127,63, 127,  63,  63,  63,  63, 127,  63,  63, 127,  63,  63,  63,63, 127, 127,  63, 127,  61,  63,  63,  63,  63,  63,  63, 127,63, 127,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,63,  63,  63,  63,  63,  63,  63,  63,  63, 127,  63,  63, 127,63,  63, 127, 127, 127,  63,  63,  63,  63,  63,  63, 127,  63,63,  63,  63,  63,  63,  37, 127,  63,  63,  86,  63,  63,  63,63,  63, 127, 127,  63, 127,  19,  63,  94, 127,  63,  29,  63,63,  32,  63, 127,  63, 127,  63, 127, 127,  63,  63,  63,  63,9,  63, 127,  63,  63,  63, 127, 127, 127,  63,  63,  63, 127,63,  63, 127,  63,  63, 104,  63,  63,  63,  48,  63,  63,  63,63,  63,  63,  63, 127,  63,  63,  63,  63,  63, 127,  63,  32,127]], dtype=int32)</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span>tree_depth</span></div><div class='xr-var-dims'>(chain, draw)</div><div class='xr-var-dtype'>int64</div><div class='xr-var-preview xr-preview'>7 7 7 7 7 7 7 7 ... 6 6 6 6 7 6 6 7</div><input id='attrs-a99fc71e-606a-4a52-b480-3774f1b2f5e9' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-a99fc71e-606a-4a52-b480-3774f1b2f5e9' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-46ab0700-e273-49bf-8ed4-c248c0923cd4' class='xr-var-data-in' type='checkbox'><label for='data-46ab0700-e273-49bf-8ed4-c248c0923cd4' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>array([[7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 5, 7, 7, 7, 7, 7,7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 6, 6, 7, 7, 7, 7, 7, 7, 7, 7,6, 7, 6, 7, 7, 7, 7, 6, 6, 7, 6, 7, 6, 7, 7, 7, 6, 7, 8, 7, 7, 6,7, 7, 7, 7, 7, 7, 7, 6, 6, 7, 7, 7, 7, 6, 7, 7, 7, 7, 7, 7, 6, 6,7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7,7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 4, 7, 7, 6, 7, 7, 7, 7, 7, 7,7, 7, 6, 7, 7, 7, 7, 7, 7, 7, 6, 7, 7, 7, 7, 7, 6, 7, 7, 7, 7, 7,7, 7, 7, 6, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 6, 6, 7, 6, 7, 7, 6,6, 7, 7, 7, 7, 7, 7, 6, 7, 1, 7, 7, 7, 7, 7, 7, 5, 7, 6, 7, 7, 7,6, 7, 7, 7, 6, 7, 7, 7, 7, 7, 5, 7, 7, 7, 7, 7, 7, 7, 7, 6, 7, 7,7, 7, 7, 7, 7, 7, 6, 7, 7, 7, 7, 7, 7, 6, 7, 7, 7, 7, 7, 6, 6, 7,6, 7, 6, 7, 7, 6, 7, 3, 3, 7, 7, 7, 6, 7, 7, 7, 7, 7, 6, 7, 7, 6,7, 4, 4, 7, 7, 7, 7, 6, 7, 7, 6, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 6,7, 7, 7, 7, 7, 7, 6, 7, 7, 7, 6, 7, 7, 7],[6, 7, 4, 6, 7, 6, 6, 6, 6, 5, 7, 7, 6, 7, 8, 6, 6, 7, 6, 7, 7, 7,7, 6, 7, 6, 6, 7, 6, 5, 7, 4, 7, 7, 6, 6, 6, 6, 6, 6, 6, 7, 5, 6,6, 6, 6, 6, 6, 6, 6, 7, 6, 7, 6, 6, 4, 6, 7, 6, 6, 7, 7, 7, 7, 6,6, 6, 6, 6, 7, 6, 6, 6, 7, 6, 6, 6, 6, 6, 6, 6, 6, 8, 7, 7, 6, 6,6, 6, 6, 6, 7, 6, 7, 6, 6, 6, 6, 6, 7, 6, 6, 7, 6, 6, 5, 7, 6, 6,6, 6, 7, 6, 6, 7, 6, 6, 6, 6, 6, 7, 7, 6, 7, 6, 6, 5, 6, 7, 7, 6,7, 6, 6, 6, 6, 6, 7, 6, 6, 7, 6, 5, 4, 6, 7, 6, 6, 7, 6, 6, 6, 6,6, 7, 6, 7, 6, 6, 6, 6, 7, 6, 6, 7, 6, 6, 6, 6, 7, 7, 6, 7, 6, 6,6, 6, 6, 6, 6, 7, 6, 7, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6,6, 6, 6, 6, 6, 6, 7, 6, 6, 7, 6, 6, 7, 7, 7, 6, 6, 6, 6, 6, 6, 7,6, 6, 6, 6, 6, 6, 6, 7, 6, 6, 7, 6, 6, 6, 6, 6, 7, 7, 6, 7, 5, 6,7, 7, 6, 5, 6, 6, 6, 6, 7, 6, 7, 6, 7, 7, 6, 6, 6, 6, 4, 6, 7, 6,6, 6, 7, 7, 7, 6, 6, 6, 7, 6, 6, 7, 6, 6, 7, 6, 6, 6, 6, 6, 6, 6,6, 6, 6, 6, 7, 6, 6, 6, 6, 6, 7, 6, 6, 7]])</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span>lp</span></div><div class='xr-var-dims'>(chain, draw)</div><div class='xr-var-dtype'>float32</div><div class='xr-var-preview xr-preview'>...</div><input id='attrs-907ae2f8-3385-4f5c-890c-9beee75f220b' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-907ae2f8-3385-4f5c-890c-9beee75f220b' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-5509124a-4125-4a26-917a-d095eda98162' class='xr-var-data-in' type='checkbox'><label for='data-5509124a-4125-4a26-917a-d095eda98162' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>Array([[394.09488, 385.24164, 394.09894, 392.98367, 398.19366, 396.16614,389.39166, 392.44666, 390.1056 , 391.44098, 389.7625 , 385.6347 ,394.1698 , 386.14374, 384.53665, 377.542  , 380.098  , 382.04028,382.9939 , 389.99802, 390.9277 , 393.13336, 387.08823, 383.53122,386.62598, 380.52902, 381.90164, 391.71243, 395.4429 , 389.96368,380.98096, 387.51352, 385.5276 , 385.4507 , 396.64917, 395.83496,399.88086, 393.08517, 396.75653, 390.39752, 379.5471 , 391.10333,389.44705, 390.58466, 381.22632, 383.09775, 381.90286, 378.09183,380.40845, 386.13287, 390.25406, 385.08856, 387.60724, 399.43347,396.29776, 389.62177, 390.2033 , 397.4245 , 398.67514, 402.66806,408.36304, 391.68436, 389.3629 , 383.7178 , 394.76184, 390.36945,385.62396, 386.8156 , 396.98093, 393.03278, 386.061  , 384.66385,384.91193, 384.3248 , 381.0891 , 384.2008 , 385.19553, 389.8413 ,387.27322, 392.48593, 384.28033, 386.11975, 393.49155, 390.03232,392.39914, 388.2781 , 391.3805 , 392.83337, 387.7561 , 393.85938,394.05624, 402.64227, 389.06027, 388.23737, 398.97125, 400.7893 ,400.68414, 393.6961 , 395.65518, 391.2489 , 400.034  , 399.5839 ,394.92166, 384.89508, 381.01392, 385.98416, 389.2858 , 399.26538,394.44873, 390.3877 , 389.0716 , 386.76984, 381.46823, 390.16986,388.80273, 389.40396, 383.64572, 383.44525, 385.98376, 384.5776 ,...387.31036, 391.04813, 388.1021 , 384.10046, 383.3048 , 384.84616,388.69586, 388.36526, 384.31366, 390.39618, 384.40558, 390.05255,397.33487, 393.35535, 390.94333, 381.4787 , 387.54553, 391.50052,384.4722 , 379.66156, 389.633  , 388.5091 , 398.05276, 390.41934,395.02823, 401.96112, 390.9971 , 388.35275, 385.6041 , 381.0918 ,382.7286 , 382.68747, 384.25836, 395.06586, 390.55508, 395.54184,407.03973, 391.06882, 395.03125, 398.62344, 394.14188, 395.16306,390.99316, 388.56113, 391.829  , 393.51794, 390.0531 , 394.80585,389.49734, 386.38675, 388.55368, 386.15662, 388.2653 , 382.05295,390.35965, 393.2531 , 388.4096 , 384.47137, 384.96   , 392.69705,391.9715 , 378.9571 , 382.39584, 384.03677, 383.44534, 381.671  ,390.46152, 380.65805, 388.4502 , 391.27353, 392.64346, 391.17267,380.6573 , 383.9884 , 385.74582, 391.89484, 391.01627, 385.4204 ,395.70193, 395.3958 , 396.45096, 392.67157, 388.3678 , 389.58054,391.86057, 390.03   , 392.47473, 390.77863, 395.35724, 383.27362,378.5565 , 383.0009 , 383.97787, 388.6201 , 384.7961 , 395.34592,389.02432, 390.02808, 395.52524, 398.70428, 410.83957, 403.80197,403.4167 , 416.65277, 411.69925, 406.62695, 396.6117 , 397.29633,396.40714, 386.15137, 386.1772 , 385.79962, 394.91922, 391.08078,381.67746, 393.0481 , 387.06522, 393.55667, 392.8749 , 391.10416]],      dtype=float32)</pre></div></li></ul></div></li><li class='xr-section-item'><input id='section-0ba99af9-f440-4020-8eb0-30a0b060821f' class='xr-section-summary-in' type='checkbox' checked /><label for='section-0ba99af9-f440-4020-8eb0-30a0b060821f' class='xr-section-summary' title='Expand/collapse section'>Attributes: <span>(7)</span></label><div class='xr-section-inline-details'></div><div class='xr-section-details'><dl class='xr-attrs'><dt><span>created_at :</span></dt><dd>2026-07-24T14:18:40.498297+00:00</dd><dt><span>creation_library :</span></dt><dd>ArviZ</dd><dt><span>creation_library_version :</span></dt><dd>1.2.0</dd><dt><span>creation_library_language :</span></dt><dd>Python</dd><dt><span>sample_dims :</span></dt><dd>[&#x27;chain&#x27;, &#x27;draw&#x27;]</dd><dt><span>modeling_interface :</span></dt><dd>bambi</dd><dt><span>modeling_interface_version :</span></dt><dd>0.19.0</dd></dl></div></li></ul></div></div><div class='xr-group-box'><div class='xr-group-box-vline' style='height: 100%'></div><div class='xr-group-box-hline'></div><div class='xr-group-box-contents'><input id='group-c3420a6a-0af5-4e79-b468-32d759d718db' type='checkbox' checked /><label for='group-c3420a6a-0af5-4e79-b468-32d759d718db' title='Expand/collapse group'>/observed_data<span>(10)</span></label><ul class='xr-sections'><li class='xr-section-item'><input id='section-c63ce799-3471-49bb-abb1-d2e8ffb43e9a' class='xr-section-summary-in' type='checkbox' disabled /><label for='section-c63ce799-3471-49bb-abb1-d2e8ffb43e9a' class='xr-section-summary'>Dimensions:</label><div class='xr-section-inline-details'><ul class='xr-dim-list'><li><span class='xr-has-index'>__obs__</span>: 350</li><li><span class='xr-has-index'>rt,response_extra_dim_0</span>: 2</li></ul></div></li><li class='xr-section-item'><input id='section-f54ade9b-f6eb-47e2-b6f3-6f886aba3637' class='xr-section-summary-in' type='checkbox' checked /><label for='section-f54ade9b-f6eb-47e2-b6f3-6f886aba3637' class='xr-section-summary' title='Expand/collapse section'>Coordinates: <span>(2)</span></label><div class='xr-section-inline-details'></div><div class='xr-section-details'><ul class='xr-var-list'><li class='xr-var-item'><div class='xr-var-name'><span class='xr-has-index'>__obs__</span></div><div class='xr-var-dims'>(__obs__)</div><div class='xr-var-dtype'>int64</div><div class='xr-var-preview xr-preview'>0 1 2 3 4 5 ... 345 346 347 348 349</div><input id='attrs-1289ed2f-1f2c-4c24-9cc7-6894fe8f086f' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-1289ed2f-1f2c-4c24-9cc7-6894fe8f086f' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-40c3d818-32af-4b41-b979-4c2a51dec826' class='xr-var-data-in' type='checkbox'><label for='data-40c3d818-32af-4b41-b979-4c2a51dec826' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>array([  0,   1,   2, ..., 347, 348, 349], shape=(350,))</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span class='xr-has-index'>rt,response_extra_dim_0</span></div><div class='xr-var-dims'>(rt,response_extra_dim_0)</div><div class='xr-var-dtype'>int64</div><div class='xr-var-preview xr-preview'>0 1</div><input id='attrs-0bda907f-72b1-4f73-bad3-6b8d3049d237' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-0bda907f-72b1-4f73-bad3-6b8d3049d237' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-87a72a72-2098-46ad-87ed-80722fdb3e3a' class='xr-var-data-in' type='checkbox'><label for='data-87a72a72-2098-46ad-87ed-80722fdb3e3a' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>array([0, 1])</pre></div></li></ul></div></li><li class='xr-section-item'><input id='section-ee0479b7-572c-4809-8dd5-d04e201d87c0' class='xr-section-summary-in' type='checkbox' checked /><label for='section-ee0479b7-572c-4809-8dd5-d04e201d87c0' class='xr-section-summary' title='Expand/collapse section'>Data variables: <span>(1)</span></label><div class='xr-section-inline-details'></div><div class='xr-section-details'><ul class='xr-var-list'><li class='xr-var-item'><div class='xr-var-name'><span>rt,response</span></div><div class='xr-var-dims'>(__obs__, rt,response_extra_dim_0)</div><div class='xr-var-dtype'>float32</div><div class='xr-var-preview xr-preview'>1.101 -1.0 1.999 ... 1.009 -1.0</div><input id='attrs-57a3b8dd-dfe7-487c-8bae-180a8e331de2' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-57a3b8dd-dfe7-487c-8bae-180a8e331de2' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-0042acb3-cd22-44f1-8bd3-a320161740c0' class='xr-var-data-in' type='checkbox'><label for='data-0042acb3-cd22-44f1-8bd3-a320161740c0' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>array([[ 1.100926  , -1.        ],[ 1.9985536 , -1.        ],[ 2.1513555 , -1.        ],[ 0.58990616, -1.        ],[ 1.1724871 , -1.        ],[ 0.9756266 , -1.        ],[ 1.2626417 ,  1.        ],[ 1.1017668 , -1.        ],[ 0.80269176, -1.        ],[ 1.8350772 ,  1.        ],[ 1.0365586 , -1.        ],[ 1.8596222 , -1.        ],[ 1.2636248 ,  1.        ],[ 0.7060377 , -1.        ],[ 1.7817559 , -1.        ],[ 0.54377115, -1.        ],[ 0.5464994 , -1.        ],[ 1.9762948 , -1.        ],[ 1.3642769 ,  1.        ],[ 0.6310554 , -1.        ],...[ 1.2168534 , -1.        ],[ 0.85871667, -1.        ],[ 1.4025654 , -1.        ],[ 1.1067938 , -1.        ],[ 0.77304983, -1.        ],[ 0.6180564 , -1.        ],[ 0.6796331 , -1.        ],[ 1.6154934 , -1.        ],[ 1.8210009 , -1.        ],[ 0.74919015, -1.        ],[ 1.0277966 , -1.        ],[ 1.4953309 , -1.        ],[ 1.7121912 , -1.        ],[ 0.5577653 , -1.        ],[ 0.54850405, -1.        ],[ 1.1838193 ,  1.        ],[ 0.627454  , -1.        ],[ 1.32497   , -1.        ],[ 1.1755071 , -1.        ],[ 1.0086374 , -1.        ]], dtype=float32)</pre></div></li></ul></div></li><li class='xr-section-item'><input id='section-418d218f-1459-4b21-a0c7-4ce494f18d31' class='xr-section-summary-in' type='checkbox' checked /><label for='section-418d218f-1459-4b21-a0c7-4ce494f18d31' class='xr-section-summary' title='Expand/collapse section'>Attributes: <span>(7)</span></label><div class='xr-section-inline-details'></div><div class='xr-section-details'><dl class='xr-attrs'><dt><span>created_at :</span></dt><dd>2026-07-24T14:18:40.499371+00:00</dd><dt><span>creation_library :</span></dt><dd>ArviZ</dd><dt><span>creation_library_version :</span></dt><dd>1.2.0</dd><dt><span>creation_library_language :</span></dt><dd>Python</dd><dt><span>sample_dims :</span></dt><dd>[]</dd><dt><span>modeling_interface :</span></dt><dd>bambi</dd><dt><span>modeling_interface_version :</span></dt><dd>0.19.0</dd></dl></div></li></ul></div></div><div class='xr-group-box'><div class='xr-group-box-vline' style='height: 100%'></div><div class='xr-group-box-hline'></div><div class='xr-group-box-contents'><input id='group-05ce5b68-eefb-46d3-b16d-baf6f4fddce8' type='checkbox' checked /><label for='group-05ce5b68-eefb-46d3-b16d-baf6f4fddce8' title='Expand/collapse group'>/constant_data<span>(7)</span></label><ul class='xr-sections'><li class='xr-section-item'><input id='section-273fad1f-0489-4aad-9f52-abe6c4d14dc4' class='xr-section-summary-in' type='checkbox' checked /><label for='section-273fad1f-0489-4aad-9f52-abe6c4d14dc4' class='xr-section-summary' title='Expand/collapse section'>Attributes: <span>(7)</span></label><div class='xr-section-inline-details'></div><div class='xr-section-details'><dl class='xr-attrs'><dt><span>created_at :</span></dt><dd>2026-07-24T14:18:40.499495+00:00</dd><dt><span>creation_library :</span></dt><dd>ArviZ</dd><dt><span>creation_library_version :</span></dt><dd>1.2.0</dd><dt><span>creation_library_language :</span></dt><dd>Python</dd><dt><span>sample_dims :</span></dt><dd>[]</dd><dt><span>modeling_interface :</span></dt><dd>bambi</dd><dt><span>modeling_interface_version :</span></dt><dd>0.19.0</dd></dl></div></li></ul></div></div><div class='xr-group-box'><div class='xr-group-box-vline' style='height: 1.2em'></div><div class='xr-group-box-hline'></div><div class='xr-group-box-contents'><input id='group-1e7b562a-25bd-4028-9c01-32731f692695' type='checkbox' checked /><label for='group-1e7b562a-25bd-4028-9c01-32731f692695' title='Expand/collapse group'>/log_likelihood<span>(6)</span></label><ul class='xr-sections'><li class='xr-section-item'><input id='section-778fe204-2325-4b06-9f34-197b827b9400' class='xr-section-summary-in' type='checkbox' disabled /><label for='section-778fe204-2325-4b06-9f34-197b827b9400' class='xr-section-summary'>Dimensions:</label><div class='xr-section-inline-details'><ul class='xr-dim-list'><li><span class='xr-has-index'>chain</span>: 2</li><li><span class='xr-has-index'>draw</span>: 300</li><li><span class='xr-has-index'>__obs__</span>: 350</li></ul></div></li><li class='xr-section-item'><input id='section-fed9e6d8-fbf4-4ff9-950b-b13d473f9661' class='xr-section-summary-in' type='checkbox' checked /><label for='section-fed9e6d8-fbf4-4ff9-950b-b13d473f9661' class='xr-section-summary' title='Expand/collapse section'>Coordinates: <span>(3)</span></label><div class='xr-section-inline-details'></div><div class='xr-section-details'><ul class='xr-var-list'><li class='xr-var-item'><div class='xr-var-name'><span class='xr-has-index'>chain</span></div><div class='xr-var-dims'>(chain)</div><div class='xr-var-dtype'>int64</div><div class='xr-var-preview xr-preview'>0 1</div><input id='attrs-8965b9c5-f8b0-467f-a9ba-bc56dda8cc1f' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-8965b9c5-f8b0-467f-a9ba-bc56dda8cc1f' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-34bbf25e-a2d1-4172-be5c-23f0c77a5aa9' class='xr-var-data-in' type='checkbox'><label for='data-34bbf25e-a2d1-4172-be5c-23f0c77a5aa9' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>array([0, 1])</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span class='xr-has-index'>draw</span></div><div class='xr-var-dims'>(draw)</div><div class='xr-var-dtype'>int64</div><div class='xr-var-preview xr-preview'>0 1 2 3 4 5 ... 295 296 297 298 299</div><input id='attrs-1fa30427-777a-417b-af77-924ca7f144e2' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-1fa30427-777a-417b-af77-924ca7f144e2' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-c5154a5b-7de2-46ca-9852-3cd7609c1c71' class='xr-var-data-in' type='checkbox'><label for='data-c5154a5b-7de2-46ca-9852-3cd7609c1c71' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>array([  0,   1,   2, ..., 297, 298, 299], shape=(300,))</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span class='xr-has-index'>__obs__</span></div><div class='xr-var-dims'>(__obs__)</div><div class='xr-var-dtype'>int64</div><div class='xr-var-preview xr-preview'>0 1 2 3 4 5 ... 345 346 347 348 349</div><input id='attrs-143a1e91-bbb4-4ac7-ada3-0e222e2415d6' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-143a1e91-bbb4-4ac7-ada3-0e222e2415d6' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-cca6ea1f-3a3a-4355-a7fa-3672bc84ba49' class='xr-var-data-in' type='checkbox'><label for='data-cca6ea1f-3a3a-4355-a7fa-3672bc84ba49' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>array([  0,   1,   2, ..., 347, 348, 349], shape=(350,))</pre></div></li></ul></div></li><li class='xr-section-item'><input id='section-50482a15-9980-4a7d-9f14-fc6329ecd583' class='xr-section-summary-in' type='checkbox' checked /><label for='section-50482a15-9980-4a7d-9f14-fc6329ecd583' class='xr-section-summary' title='Expand/collapse section'>Data variables: <span>(1)</span></label><div class='xr-section-inline-details'></div><div class='xr-section-details'><ul class='xr-var-list'><li class='xr-var-item'><div class='xr-var-name'><span>rt,response</span></div><div class='xr-var-dims'>(chain, draw, __obs__)</div><div class='xr-var-dtype'>float64</div><div class='xr-var-preview xr-preview'>-0.9516 -1.938 ... -0.6732 -0.2128</div><input id='attrs-b9b93ef2-3868-44a4-b014-613badd2a477' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-b9b93ef2-3868-44a4-b014-613badd2a477' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-cbe90b0e-e705-42ad-a699-a743aef1928f' class='xr-var-data-in' type='checkbox'><label for='data-cbe90b0e-e705-42ad-a699-a743aef1928f' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>array([[[-0.95163041, -1.9377526 , -2.26808763, ..., -0.71993995,-0.44797689, -0.13487169],[-0.87594002, -2.2362287 , -2.66411352, ..., -0.80930352,-0.49260673, -0.1163418 ],[-0.97445178, -1.75210941, -2.00760913, ..., -0.80831838,-0.54027539, -0.21576402],...,[-0.9823854 , -1.61517644, -1.87649751, ..., -0.63673544,-0.36646456, -0.07604778],[-1.00356209, -1.9535886 , -2.17671299, ..., -0.76532316,-0.47597289, -0.12971124],[-1.14535391, -2.14524269, -2.2812984 , ..., -0.64430213,-0.35331348, -0.03097525]],[[-0.87596756, -1.91994739, -2.27408028, ..., -0.79342633,-0.46522176, -0.07652199],[-0.88144708, -2.00250196, -2.33182001, ..., -0.91400528,-0.57967585, -0.1750775 ],[-0.89691997, -1.96655369, -2.26612449, ..., -0.82059753,-0.50560611, -0.13100737],...,[-0.93633831, -2.05415273, -2.39878511, ..., -0.69802511,-0.44716901, -0.15773717],[-0.88594627, -1.85543263, -2.22275281, ..., -0.83603704,-0.51832235, -0.11384979],[-1.02542877, -1.74677694, -1.95633328, ..., -1.02392185,-0.67318541, -0.21278203]]], shape=(2, 300, 350))</pre></div></li></ul></div></li><li class='xr-section-item'><input id='section-f7720f4e-3190-4c3c-ab0c-dfac1d46cdac' class='xr-section-summary-in' type='checkbox' checked /><label for='section-f7720f4e-3190-4c3c-ab0c-dfac1d46cdac' class='xr-section-summary' title='Expand/collapse section'>Attributes: <span>(2)</span></label><div class='xr-section-inline-details'></div><div class='xr-section-details'><dl class='xr-attrs'><dt><span>modeling_interface :</span></dt><dd>bambi</dd><dt><span>modeling_interface_version :</span></dt><dd>0.19.0</dd></dl></div></li></ul></div></div></div></li></ul></div></div>"
+      ],
+      "text/plain": [
+       "<xarray.DataTree>\n",
+       "Group: /\n",
+       "├── Group: /posterior\n",
+       "│       Dimensions:                                (chain: 2, draw: 300,\n",
+       "│                                                   participant_id__factor_dim: 5,\n",
+       "│                                                   rl_alpha_1|participant_id__factor_dim: 5)\n",
+       "│       Coordinates:\n",
+       "│         * chain                                  (chain) int64 16B 0 1\n",
+       "│         * draw                                   (draw) int64 2kB 0 1 2 ... 298 299\n",
+       "│         * participant_id__factor_dim             (participant_id__factor_dim) <U1 20B ...\n",
+       "│         * rl_alpha_1|participant_id__factor_dim  (rl_alpha_1|participant_id__factor_dim) <U1 20B ...\n",
+       "│       Data variables: (12/24)\n",
+       "│           z_1|participant_id_offset              (chain, draw, participant_id__factor_dim) float32 12kB ...\n",
+       "│           z_Intercept                            (chain, draw) float32 2kB ...\n",
+       "│           scaler_1|participant_id_offset         (chain, draw, participant_id__factor_dim) float32 12kB ...\n",
+       "│           a_1|participant_id_offset              (chain, draw, participant_id__factor_dim) float32 12kB ...\n",
+       "│           a_1|participant_id                     (chain, draw, participant_id__factor_dim) float32 12kB ...\n",
+       "│           t_1|participant_id_sigma               (chain, draw) float32 2kB ...\n",
+       "│           ...                                     ...\n",
+       "│           z_1|participant_id_sigma               (chain, draw) float32 2kB ...\n",
+       "│           rl_alpha_1|participant_id_offset       (chain, draw, rl_alpha_1|participant_id__factor_dim) float32 12kB ...\n",
+       "│           scaler_Intercept                       (chain, draw) float32 2kB ...\n",
+       "│           t_1|participant_id                     (chain, draw, participant_id__factor_dim) float32 12kB ...\n",
+       "│           scaler_1|participant_id_sigma          (chain, draw) float32 2kB ...\n",
+       "│           t_1|participant_id_offset              (chain, draw, participant_id__factor_dim) float32 12kB ...\n",
+       "│       Attributes:\n",
+       "│           created_at:                  2026-07-24T14:18:40.484086+00:00\n",
+       "│           creation_library:            ArviZ\n",
+       "│           creation_library_version:    1.2.0\n",
+       "│           creation_library_language:   Python\n",
+       "│           sample_dims:                 ['chain', 'draw']\n",
+       "│           inference_library:           numpyro\n",
+       "│           inference_library_version:   0.21.0\n",
+       "│           sampling_time:               92.736215\n",
+       "│           tuning_steps:                300\n",
+       "│           modeling_interface:          bambi\n",
+       "│           modeling_interface_version:  0.19.0\n",
+       "├── Group: /sample_stats\n",
+       "│       Dimensions:          (chain: 2, draw: 300)\n",
+       "│       Coordinates:\n",
+       "│         * chain            (chain) int64 16B 0 1\n",
+       "│         * draw             (draw) int64 2kB 0 1 2 3 4 5 6 ... 294 295 296 297 298 299\n",
+       "│       Data variables:\n",
+       "│           acceptance_rate  (chain, draw) float32 2kB ...\n",
+       "│           step_size        (chain, draw) float32 2kB ...\n",
+       "│           diverging        (chain, draw) bool 600B ...\n",
+       "│           energy           (chain, draw) float32 2kB ...\n",
+       "│           n_steps          (chain, draw) int32 2kB ...\n",
+       "│           tree_depth       (chain, draw) int64 5kB 7 7 7 7 7 7 7 7 ... 6 6 6 6 7 6 6 7\n",
+       "│           lp               (chain, draw) float32 2kB ...\n",
+       "│       Attributes:\n",
+       "│           created_at:                  2026-07-24T14:18:40.498297+00:00\n",
+       "│           creation_library:            ArviZ\n",
+       "│           creation_library_version:    1.2.0\n",
+       "│           creation_library_language:   Python\n",
+       "│           sample_dims:                 ['chain', 'draw']\n",
+       "│           modeling_interface:          bambi\n",
+       "│           modeling_interface_version:  0.19.0\n",
+       "├── Group: /observed_data\n",
+       "│       Dimensions:                  (__obs__: 350, rt,response_extra_dim_0: 2)\n",
+       "│       Coordinates:\n",
+       "│         * __obs__                  (__obs__) int64 3kB 0 1 2 3 4 ... 346 347 348 349\n",
+       "│         * rt,response_extra_dim_0  (rt,response_extra_dim_0) int64 16B 0 1\n",
+       "│       Data variables:\n",
+       "│           rt,response              (__obs__, rt,response_extra_dim_0) float32 3kB 1...\n",
+       "│       Attributes:\n",
+       "│           created_at:                  2026-07-24T14:18:40.499371+00:00\n",
+       "│           creation_library:            ArviZ\n",
+       "│           creation_library_version:    1.2.0\n",
+       "│           creation_library_language:   Python\n",
+       "│           sample_dims:                 []\n",
+       "│           modeling_interface:          bambi\n",
+       "│           modeling_interface_version:  0.19.0\n",
+       "├── Group: /constant_data\n",
+       "│       Attributes:\n",
+       "│           created_at:                  2026-07-24T14:18:40.499495+00:00\n",
+       "│           creation_library:            ArviZ\n",
+       "│           creation_library_version:    1.2.0\n",
+       "│           creation_library_language:   Python\n",
+       "│           sample_dims:                 []\n",
+       "│           modeling_interface:          bambi\n",
+       "│           modeling_interface_version:  0.19.0\n",
+       "└── Group: /log_likelihood\n",
+       "        Dimensions:      (chain: 2, draw: 300, __obs__: 350)\n",
+       "        Coordinates:\n",
+       "          * chain        (chain) int64 16B 0 1\n",
+       "          * draw         (draw) int64 2kB 0 1 2 3 4 5 6 ... 293 294 295 296 297 298 299\n",
+       "          * __obs__      (__obs__) int64 3kB 0 1 2 3 4 5 6 ... 344 345 346 347 348 349\n",
+       "        Data variables:\n",
+       "            rt,response  (chain, draw, __obs__) float64 2MB -0.9516 -1.938 ... -0.2128\n",
+       "        Attributes:\n",
+       "            modeling_interface:          bambi\n",
+       "            modeling_interface_version:  0.19.0"
+      ]
+     },
+     "execution_count": 15,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "idata = model.sample(\n",
+    "    sampler=\"numpyro\",\n",
+    "    draws=N_DRAWS,\n",
+    "    tune=N_TUNE,\n",
+    "    chains=N_CHAINS,\n",
+    "    cores=N_CHAINS,\n",
+    "    target_accept=0.9,\n",
+    "    random_seed=RANDOM_SEED,\n",
+    ")\n",
+    "idata"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "ad91ad20",
+   "metadata": {},
+   "source": [
+    "## 8. A quick recovery check\n",
+    "First check: did the fit recover the group-level values we simulated from?\n",
+    "We keep this check at the group level because it is the fastest way to verify that\n",
+    "the workflow is behaving sensibly.\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "id": "ae08ea78",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def group_recovery(idata, true_group):\n",
+    "    \"\"\"Group intercept posterior vs. true group mean, per parameter.\"\"\"\n",
+    "    names = [f\"{p}_Intercept\" for p in LIST_PARAMS]\n",
+    "    summ = az.summary(\n",
+    "        idata,\n",
+    "        var_names=names,\n",
+    "        kind=\"stats\",\n",
+    "        ci_kind=\"hdi\",\n",
+    "        ci_prob=0.94,\n",
+    "        round_to=\"none\",\n",
+    "    )\n",
+    "    summ.index = LIST_PARAMS\n",
+    "    summ[\"true\"] = [true_group[p] for p in LIST_PARAMS]\n",
+    "\n",
+    "    fig, ax = plt.subplots(figsize=(8, 4.5))\n",
+    "    y = np.arange(len(LIST_PARAMS))\n",
+    "    ax.errorbar(\n",
+    "        summ[\"mean\"],\n",
+    "        y,\n",
+    "        xerr=[summ[\"mean\"] - summ[\"hdi94_lb\"], summ[\"hdi94_ub\"] - summ[\"mean\"]],\n",
+    "        fmt=\"o\",\n",
+    "        capsize=4,\n",
+    "        label=\"posterior (94% HDI)\",\n",
+    "    )\n",
+    "    ax.scatter(\n",
+    "        summ[\"true\"], y, color=\"crimson\", marker=\"D\", zorder=5, label=\"true group mean\"\n",
+    "    )\n",
+    "    ax.set_yticks(y)\n",
+    "    ax.set_yticklabels(LIST_PARAMS)\n",
+    "    ax.invert_yaxis()\n",
+    "    ax.set_title(\"Group-level recovery\")\n",
+    "    ax.legend()\n",
+    "    fig.tight_layout()\n",
+    "    plt.show()\n",
+    "    return summ"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "f028a492",
+   "metadata": {},
+   "source": [
+    "### Group-level recovery\n",
+    "Each posterior interval (blue) should land reasonably close to the corresponding\n",
+    "true group mean (red diamond).\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "id": "89a41288",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 800x450 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>mean</th>\n",
+       "      <th>hdi94_lb</th>\n",
+       "      <th>hdi94_ub</th>\n",
+       "      <th>true</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>rl_alpha</th>\n",
+       "      <td>0.135</td>\n",
+       "      <td>0.042</td>\n",
+       "      <td>0.249</td>\n",
+       "      <td>0.08</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>scaler</th>\n",
+       "      <td>2.121</td>\n",
+       "      <td>1.415</td>\n",
+       "      <td>2.875</td>\n",
+       "      <td>2.50</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>a</th>\n",
+       "      <td>1.315</td>\n",
+       "      <td>1.045</td>\n",
+       "      <td>1.591</td>\n",
+       "      <td>1.20</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>z</th>\n",
+       "      <td>0.466</td>\n",
+       "      <td>0.415</td>\n",
+       "      <td>0.519</td>\n",
+       "      <td>0.50</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>t</th>\n",
+       "      <td>0.231</td>\n",
+       "      <td>0.141</td>\n",
+       "      <td>0.328</td>\n",
+       "      <td>0.25</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>theta</th>\n",
+       "      <td>0.352</td>\n",
+       "      <td>0.240</td>\n",
+       "      <td>0.458</td>\n",
+       "      <td>0.35</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "           mean  hdi94_lb  hdi94_ub  true\n",
+       "rl_alpha  0.135     0.042     0.249  0.08\n",
+       "scaler    2.121     1.415     2.875  2.50\n",
+       "a         1.315     1.045     1.591  1.20\n",
+       "z         0.466     0.415     0.519  0.50\n",
+       "t         0.231     0.141     0.328  0.25\n",
+       "theta     0.352     0.240     0.458  0.35"
+      ]
+     },
+     "execution_count": 17,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "group_summary = group_recovery(idata, GROUP_THETA)\n",
+    "group_summary[[\"mean\", \"hdi94_lb\", \"hdi94_ub\", \"true\"]].round(3)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "055a0d0e",
+   "metadata": {},
+   "source": [
+    "## 9. Posterior predictive check (RLSSM-aware)\n",
+    "Second check: if we simulate new data from the fitted model, does it resemble the\n",
+    "observed dataset?\n",
+    "For RLSSMs, the PPC has to respect the learning history. The helper below replays each\n",
+    "participant's observed reward sequence before comparing predicted and observed\n",
+    "learning curves and RT distributions.\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "id": "433a3627",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def plot_rl_ppc(idata, observed_data, ssms_config, *, n_participants, random_seed):\n",
+    "    \"\"\"Simulate an RL-aware PPC and plot the main checks.\"\"\"\n",
+    "\n",
+    "    def draw_posterior_theta(draw_idx):\n",
+    "        posterior = idata.posterior\n",
+    "        if hasattr(posterior, \"to_dataset\"):\n",
+    "            posterior = posterior.to_dataset()  # PyMC 6 returns a DataTree node\n",
+    "        post = posterior.stack(sample=(\"chain\", \"draw\"))\n",
+    "        theta = {}\n",
+    "        for name in LIST_PARAMS:\n",
+    "            re = post[f\"{name}_1|participant_id\"]\n",
+    "            pid_dim = [d for d in re.dims if d not in (\"sample\",)][0]\n",
+    "            vals = (post[f\"{name}_Intercept\"] + re).isel(sample=draw_idx)\n",
+    "            ids = [int(v) for v in re[pid_dim].values]\n",
+    "            series = pd.Series(np.asarray(vals.values), index=ids).sort_index()\n",
+    "            theta[name] = series.reindex(range(n_participants)).to_numpy()\n",
+    "        return theta\n",
+    "\n",
+    "    def learning_curve(df, bin_size=10):\n",
+    "        d = df[df[\"rt\"] > -900].copy()\n",
+    "        d[\"chose_high\"] = (d[\"response\"] == -1).astype(float)\n",
+    "        d[\"trial_bin\"] = (d[\"trial_id\"] // bin_size) * bin_size\n",
+    "        return d.groupby(\"trial_bin\")[\"chose_high\"].mean()\n",
+    "\n",
+    "    def signed_rt(df):\n",
+    "        d = df[df[\"rt\"] > -900].copy()\n",
+    "        return np.where(\n",
+    "            d[\"response\"].astype(int) == -1,\n",
+    "            -d[\"rt\"].astype(float),\n",
+    "            d[\"rt\"].astype(float),\n",
+    "        )\n",
+    "\n",
+    "    n_ppc_draws = 8\n",
+    "    n_samples = idata.posterior.sizes[\"chain\"] * idata.posterior.sizes[\"draw\"]\n",
+    "    ppc_rng = np.random.default_rng(random_seed + 1)\n",
+    "    draw_ids = ppc_rng.choice(\n",
+    "        n_samples, size=min(n_ppc_draws, n_samples), replace=False\n",
+    "    )\n",
+    "    ppc_frames = []\n",
+    "    for offset, draw_id in enumerate(draw_ids):\n",
+    "        theta_d = draw_posterior_theta(int(draw_id))\n",
+    "        ppc_draw = rl.Simulator(ssms_config).simulate(\n",
+    "            theta=theta_d,\n",
+    "            mode=\"ppc\",\n",
+    "            observed_data=observed_data,\n",
+    "            random_state=random_seed + 100 + offset,\n",
+    "        )\n",
+    "        ppc_draw[\"ppc_draw\"] = offset\n",
+    "        ppc_frames.append(ppc_draw)\n",
+    "    ppc_data = pd.concat(ppc_frames, ignore_index=True)\n",
+    "    fig, axes = plt.subplots(1, 2, figsize=(12, 4.5), constrained_layout=True)\n",
+    "    obs_curve = learning_curve(observed_data)\n",
+    "    ppc_curves = pd.concat(\n",
+    "        [\n",
+    "            learning_curve(group).rename(draw)\n",
+    "            for draw, group in ppc_data.groupby(\"ppc_draw\")\n",
+    "        ],\n",
+    "        axis=1,\n",
+    "    ).sort_index()\n",
+    "    centers = obs_curve.index + 5\n",
+    "    axes[0].fill_between(\n",
+    "        ppc_curves.index + 5,\n",
+    "        ppc_curves.quantile(0.03, axis=1),\n",
+    "        ppc_curves.quantile(0.97, axis=1),\n",
+    "        alpha=0.25,\n",
+    "        color=\"tab:blue\",\n",
+    "        label=\"PPC 94% band\",\n",
+    "    )\n",
+    "    axes[0].plot(\n",
+    "        ppc_curves.index + 5,\n",
+    "        ppc_curves.mean(axis=1),\n",
+    "        color=\"tab:blue\",\n",
+    "        lw=1.5,\n",
+    "        label=\"PPC mean\",\n",
+    "    )\n",
+    "    axes[0].plot(centers, obs_curve.values, \"o-\", color=\"black\", label=\"observed\")\n",
+    "    axes[0].axhline(0.5, color=\"0.7\", ls=\"--\", lw=1)\n",
+    "    axes[0].set(\n",
+    "        xlabel=\"Trial\",\n",
+    "        ylabel=\"P(chose high-reward arm)\",\n",
+    "        title=\"Learning-curve PPC\",\n",
+    "        ylim=(0, 1),\n",
+    "    )\n",
+    "    axes[0].legend(frameon=False)\n",
+    "    axes[1].hist(\n",
+    "        signed_rt(observed_data),\n",
+    "        bins=40,\n",
+    "        density=True,\n",
+    "        histtype=\"step\",\n",
+    "        lw=1.8,\n",
+    "        color=\"black\",\n",
+    "        label=\"observed\",\n",
+    "    )\n",
+    "    axes[1].hist(\n",
+    "        signed_rt(ppc_data),\n",
+    "        bins=40,\n",
+    "        density=True,\n",
+    "        histtype=\"step\",\n",
+    "        lw=1.8,\n",
+    "        color=\"tab:blue\",\n",
+    "        label=\"PPC\",\n",
+    "    )\n",
+    "    axes[1].axvline(0, color=\"0.6\", lw=1)\n",
+    "    axes[1].set(\n",
+    "        xlabel=\"Signed RT (negative = high-reward choice)\",\n",
+    "        ylabel=\"density\",\n",
+    "        title=\"Signed-RT PPC\",\n",
+    "    )\n",
+    "    axes[1].legend(frameon=False)\n",
+    "    plt.show()\n",
+    "    print(\"PPC datasets:\", len(draw_ids), \"| total rows:\", len(ppc_data))\n",
+    "    return ppc_data"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "id": "4a32f6f7",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 1200x450 with 2 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "PPC datasets: 8 | total rows: 2800\n"
+     ]
+    }
+   ],
+   "source": [
+    "ppc_data = plot_rl_ppc(\n",
+    "    idata,\n",
+    "    observed_data=data,\n",
+    "    ssms_config=ssms_config,\n",
+    "    n_participants=N_PARTICIPANTS,\n",
+    "    random_seed=RANDOM_SEED,\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "a124489a",
+   "metadata": {},
+   "source": [
+    "## 10. Summary\n",
+    "You have run a compact RLSSM quickstart:\n",
+    "1. **Chose a model** — the `2AB_RW_Angle` preset (Rescorla–Wagner learning + angle SSM).\n",
+    "2. **Simulated** a hierarchical dataset from known parameters and confirmed learning.\n",
+    "3. **Fit** the same preset directly in HSSM with a hierarchical prior template.\n",
+    "4. **Sampled** the posterior with NumPyro using `process_initvals=False`.\n",
+    "5. **Checked** one recovery summary and an RL-aware PPC.\n",
+    "### Where to go next\n",
+    "- **[Custom models with ssms.rl](rlssm_advanced.ipynb)** — build your own task\n",
+    "  environment and learning rule instead of using a preset.\n",
+    "- **[Restless learner](rlssm_restless_learner.ipynb)** — one learner driving *several*\n",
+    "  decision parameters at once.\n",
+    "- **[Registering custom models in HSSM](rlssm_hssm_custom_models.ipynb)** — the\n",
+    "  HSSM-native registry path.\n",
+    "> **Note:** HSSM also supports *choice-only* reinforcement-learning models (no RT).\n",
+    "> Those are documented separately once fully validated against the current release.\n"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "hssm (3.13.1.final.0)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.13.1"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

From 49ca2023a739ccf6d4150e38613b74874aff8e2f Mon Sep 17 00:00:00 2001
From: Carlos Paniagua <cpaniaguam@gmail.com>
Date: Fri, 24 Jul 2026 10:44:55 -0400
Subject: [PATCH 5/6] Restore basic rlssm tutorial

---
 docs/tutorials/rlssm_basic.ipynb | 16711 ++++++++++++++++++++++++++++-
 1 file changed, 16443 insertions(+), 268 deletions(-)

diff --git a/docs/tutorials/rlssm_basic.ipynb b/docs/tutorials/rlssm_basic.ipynb
index 56ff31518..6396ff77b 100644
--- a/docs/tutorials/rlssm_basic.ipynb
+++ b/docs/tutorials/rlssm_basic.ipynb
@@ -2,17 +2,19 @@
  "cells": [
   {
    "cell_type": "markdown",
-   "id": "3e9f45e8",
+   "id": "416c9a6f",
    "metadata": {},
    "source": [
-    "# Reinforcement Learning with HSSM\n",
-    "**Reinforcement-Learning Sequential Sampling Models (RLSSMs)** join two ideas that cognitive scientists usually study separately:\n",
-    "    \n",
-    "- a **learning process** — how a participant updates their expectations from\n",
-    "    trial-to-trial feedback (here, the Rescorla–Wagner rule); and\n",
-    "- a **decision process** — how, on each trial, those expectations are turned into\n",
-    "    an actual *choice* and a *response time* (here, a drift-diffusion–style\n",
-    "    sequential sampling model).\n",
+    "# RLSSM — Basic tutorial\n",
+    "\n",
+    "**Reinforcement-Learning Sequential Sampling Models (RLSSMs)** join two ideas that\n",
+    "cognitive scientists usually study separately:\n",
+    "\n",
+    "1. a **learning process** — how a participant updates their expectations from\n",
+    "   trial-to-trial feedback (here, the Rescorla–Wagner rule); and\n",
+    "2. a **decision process** — how, on each trial, those expectations are turned into\n",
+    "   an actual *choice* and a *response time* (here, a drift-diffusion–style\n",
+    "   sequential sampling model).\n",
     "\n",
     "A plain RL model explains *which* option is chosen but ignores *how long* the choice\n",
     "took. A plain SSM explains the choice/RT on a single decision but assumes the\n",
@@ -20,30 +22,22 @@
     "*learned* becomes the thing that *drives* the moment-to-moment decision, and it does\n",
     "so on every trial. This lets us fit choices **and** response times jointly and\n",
     "recover both the learning parameters (e.g. a learning rate) and the decision\n",
-    "parameters (e.g. boundary separation) from the same data."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "416c9a6f",
-   "metadata": {},
-   "source": [
-    "## RLSSM — Basic tutorial\n",
+    "parameters (e.g. boundary separation) from the same data.\n",
     "\n",
-    "This notebook is written for first-time RLSSM users.\n",
-    "Run the cells from top to bottom; each section builds directly on the previous one.\n",
+    "This tutorial is written for readers who are **new to HSSM, PyMC, and RLSSMs**. We\n",
+    "will go slowly and explain each object as it appears. By the end you will have:\n",
     "\n",
-    "By the end you will have:\n",
     "- simulated a synthetic RLSSM dataset with [`ssm-simulators`](https://github.com/lnccbrown/ssm-simulators) (`ssms.rl`),\n",
-    "- fit a hierarchical (multi-participant) RLSSM in HSSM from the preset `2AB_RW_Angle`,\n",
-    "- checked a simple recovery summary, and\n",
-    "- run an RLSSM-aware posterior predictive check.\n",
+    "- **bridged** that model into HSSM with a single call (`RLSSMConfig.from_ssms_model`),\n",
+    "- fit a **hierarchical** (multi-participant) model with PyMC under the hood,\n",
+    "- checked **parameter recovery** at the group *and* individual level, and\n",
+    "- run a **posterior predictive check** tailored to RLSSMs.\n",
     "\n",
-    "> Other utorials cover\n",
-    "> custom learning/decision models\n",
+    "> **Where this sits in the suite:** this is the entry point. Later tutorials build\n",
+    "> *custom* learning/decision models\n",
     "> ([Custom models with ssms.rl](rlssm_advanced.ipynb) ·\n",
-    "> [Restless learner](rlssm_restless_learner.ipynb)) and HSSM-native\n",
-    "> registration ([Registering custom models in HSSM](rlssm_hssm_custom_models.ipynb)).\n"
+    "> [Restless learner](rlssm_restless_learner.ipynb)) and show HSSM-native\n",
+    "> registration ([Registering custom models in HSSM](rlssm_hssm_custom_models.ipynb))."
    ]
   },
   {
@@ -51,47 +45,70 @@
    "id": "9973c549",
    "metadata": {},
    "source": [
-    "## 1. The core idea\n",
+    "## 1. The idea in a bit more detail\n",
+    "\n",
     "### 1.1 The learning process: Rescorla–Wagner\n",
+    "\n",
     "Our task is a **two-armed bandit**: on each trial the participant picks one of two\n",
     "options and receives binary feedback (reward = 1, no reward = 0). The participant\n",
     "keeps a running value estimate $Q$ for each option and updates it using the\n",
     "**Rescorla–Wagner delta rule**. After choosing option $c$ and observing reward $r$:\n",
+    "\n",
     "$$\n",
     "Q_{c} \\leftarrow Q_{c} + \\alpha \\, \\underbrace{(r - Q_{c})}_{\\text{prediction error}}\n",
     "$$\n",
+    "\n",
     "- $Q_c$ is the current value estimate for the chosen option.\n",
     "- $r - Q_c$ is the **reward prediction error** — how surprising the outcome was.\n",
     "- $\\alpha \\in (0, 1)$ is the **learning rate** (`rl_alpha`): large $\\alpha$ means the\n",
     "  participant updates quickly and weights recent outcomes heavily; small $\\alpha$\n",
     "  means slow, stable learning. Only the chosen option's value is updated.\n",
+    "\n",
     "### 1.2 Coupling value to the decision: the drift rate\n",
+    "\n",
     "On each trial, the *difference* in learned value between the two options sets how\n",
     "strongly evidence flows toward one option during the decision. Concretely the\n",
     "**drift rate** $v$ of the decision process is\n",
+    "\n",
     "$$\n",
-    "v = \\big(Q_{1} - Q_{0}\\big)\\cdot \\texttt{scaler},\n",
+    "v = \\big(Q_{1} - Q_{0}\\big)\\cdot \\texttt{scaler}\n",
     "$$\n",
+    "\n",
     "where `scaler` converts a value difference into drift units. When the two options\n",
     "look equally good ($Q_1 \\approx Q_0$) drift is near zero and choices are slow and\n",
     "near-chance; as learning separates the values, $|v|$ grows and choices become faster\n",
     "and more consistent. **`v` is not a free parameter you estimate directly — it is\n",
     "*computed* from the learning process on every trial.** This is the heart of an RLSSM.\n",
+    "\n",
     "### 1.3 The decision process: the angle SSM (brief)\n",
+    "\n",
     "Given a drift rate, the decision itself is produced by a **sequential sampling\n",
     "model**. If you have seen the drift-diffusion model (DDM) before, this will be\n",
     "familiar: noisy evidence accumulates from a starting point until it hits one of two\n",
     "boundaries, and *which* boundary and *when* determine the choice and RT. We use the\n",
     "**angle** variant, whose only addition to the standard DDM is a **linearly\n",
     "collapsing boundary** — the decision threshold narrows over time, which helps capture\n",
-    "fast errors often seen in speeded choice. Its parameters are `a`, `z`, `t`, and\n",
-    "`theta`, while `v` is supplied by the learning process.\n",
+    "the fast errors often seen in speeded choice. Its parameters:\n",
+    "\n",
+    "| Param | Meaning |\n",
+    "|-------|---------|\n",
+    "| `v` | drift rate — **computed** from learned value (see above), not free |\n",
+    "| `a` | boundary separation (how much evidence is needed) |\n",
+    "| `z` | starting-point bias (0.5 = unbiased) |\n",
+    "| `t` | non-decision time (encoding + motor, in seconds) |\n",
+    "| `theta` | boundary collapse angle (0 = standard DDM) |\n",
+    "\n",
+    "We keep the SSM description short on purpose — the DDM family is covered in depth in\n",
+    "the other HSSM tutorials. The RLSSM-specific part is *only* the coupling in §1.2.\n",
+    "\n",
     "### 1.4 Why hierarchical?\n",
-    "We usually have many participants, each slightly different. A **hierarchical** model\n",
-    "estimates a group-level value for each parameter **and** a per-participant deviation\n",
-    "from it, letting participants share statistical strength (\"partial pooling\"). In\n",
-    "this tutorial we will use one reusable prior template for all free parameters rather\n",
-    "than introducing every modeling detail separately.\n"
+    "\n",
+    "We rarely have one participant; we have many, each slightly different. A\n",
+    "**hierarchical** model estimates a group-level value for each parameter **and** a\n",
+    "per-participant deviation from it, letting participants share statistical strength\n",
+    "(\"partial pooling\"). We will specify exactly this below and then check that the\n",
+    "fitted model recovers both the group means and the individual differences we baked\n",
+    "into the simulation."
    ]
   },
   {
@@ -100,18 +117,47 @@
    "metadata": {},
    "source": [
     "## 2. Setup\n",
+    "\n",
     "We import HSSM and the `ssms.rl` simulation API, then set two global options that\n",
-    "matter for RLSSM work.\n"
+    "matter for RLSSM work:\n",
+    "\n",
+    "- **`hssm.set_floatX(\"float32\")`** — RLSSM likelihoods run through a JAX scan over\n",
+    "  trials; single precision keeps this fast and is what the RLSSM pipeline is tuned\n",
+    "  for.\n",
+    "- We silence a few noisy library warnings so the notebook output stays readable."
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 1,
    "id": "f090de8f",
-   "metadata": {},
-   "outputs": [],
+   "metadata": {
+    "execution": {
+     "iopub.execute_input": "2026-07-06T16:35:29.532450Z",
+     "iopub.status.busy": "2026-07-06T16:35:29.532007Z",
+     "iopub.status.idle": "2026-07-06T16:35:32.972953Z",
+     "shell.execute_reply": "2026-07-06T16:35:32.972626Z"
+    }
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Setting PyTensor floatX type to float32.\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Setting \"jax_enable_x64\" to False. If this is not intended, please set `jax` to False.\n"
+     ]
+    }
+   ],
    "source": [
     "import logging\n",
+    "import os\n",
     "import warnings\n",
     "\n",
     "import arviz as az\n",
@@ -122,12 +168,11 @@
     "\n",
     "import hssm\n",
     "\n",
-    "# We silence a few noisy library warnings so the notebook output stays readable\n",
     "warnings.filterwarnings(\"ignore\")\n",
     "logging.getLogger(\"jax._src.xla_bridge\").setLevel(logging.ERROR)\n",
     "\n",
-    "hssm.set_floatX(\"float32\", update_jax=True) # set default float type to float32 for JAX operations\n",
-    "RANDOM_SEED = 20260704 # for reproducibility of pseudo-random draws used in simulation, posterior sampling, and PPC subsampling."
+    "hssm.set_floatX(\"float32\", update_jax=True)\n",
+    "RANDOM_SEED = 20260704"
    ]
   },
   {
@@ -135,30 +180,47 @@
    "id": "f1205a8b",
    "metadata": {},
    "source": [
-    "### Run size\n",
-    "This tutorial uses a quick configuration so readers can complete a full\n",
-    "end-to-end RLSSM workflow without long waits.\n",
+    "### Simulation scale\n",
     "\n",
-    "> **Optional longer run (advanced):** after your first pass, increase the values\n",
-    "in the next cell (participants, trials, tune, and draws) to get tighter\n",
-    "recovery and PPC curves.\n"
+    "Fitting a hierarchical RLSSM involves MCMC sampling, which is too heavy to run on\n",
+    "every documentation build. We therefore expose a single switch: the notebook runs at\n",
+    "a small **doc scale** by default, and at a fuller **`FULL_RUN`** scale (more\n",
+    "participants, trials, and draws) when the environment variable `FULL_RUN=1` is set.\n",
+    "The outputs committed to the docs come from a `FULL_RUN` execution."
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 2,
    "id": "4a45b283",
-   "metadata": {},
-   "outputs": [],
+   "metadata": {
+    "execution": {
+     "iopub.execute_input": "2026-07-06T16:35:32.974331Z",
+     "iopub.status.busy": "2026-07-06T16:35:32.974242Z",
+     "iopub.status.idle": "2026-07-06T16:35:32.976205Z",
+     "shell.execute_reply": "2026-07-06T16:35:32.975844Z"
+    }
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "FULL_RUN=True | participants=15 trials=150 tune=1000 draws=500\n"
+     ]
+    }
+   ],
    "source": [
-    "N_PARTICIPANTS = 5\n",
-    "N_TRIALS = 70\n",
+    "FULL_RUN = os.environ.get(\"FULL_RUN\", \"0\") == \"1\"\n",
+    "\n",
+    "N_PARTICIPANTS = 15 if FULL_RUN else 5\n",
+    "N_TRIALS = 150 if FULL_RUN else 70\n",
     "N_CHAINS = 2\n",
-    "N_TUNE = 300\n",
-    "N_DRAWS = 300\n",
+    "N_TUNE = 1000 if FULL_RUN else 300\n",
+    "N_DRAWS = 500 if FULL_RUN else 300\n",
     "\n",
     "print(\n",
-    "    f\"quick mode | participants={N_PARTICIPANTS} trials={N_TRIALS} \"\n",
+    "    f\"FULL_RUN={FULL_RUN} | participants={N_PARTICIPANTS} trials={N_TRIALS} \"\n",
     "    f\"tune={N_TUNE} draws={N_DRAWS}\"\n",
     ")"
    ]
@@ -169,20 +231,49 @@
    "metadata": {},
    "source": [
     "## 3. Pick a model: the `2AB_RW_Angle` preset\n",
+    "\n",
     "`ssms.rl` ships **presets** that bundle a task environment, a learning rule, and a\n",
     "decision process into one ready-to-use model. `2AB_RW_Angle` is exactly the model we\n",
-    "described above: a **2**-**a**rmed **b**andit with **R**escorla–**W**agner learning\n",
+    "described in §1: a **2**-**a**rmed **b**andit with **R**escorla–**W**agner learning\n",
     "and an **angle** decision process. `rl.preset.info(...)` prints a readable summary of\n",
-    "everything the preset contains.\n"
+    "everything the preset contains."
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 3,
    "id": "81a5570b",
-   "metadata": {},
-   "outputs": [],
+   "metadata": {
+    "execution": {
+     "iopub.execute_input": "2026-07-06T16:35:32.977149Z",
+     "iopub.status.busy": "2026-07-06T16:35:32.977095Z",
+     "iopub.status.idle": "2026-07-06T16:35:32.978765Z",
+     "shell.execute_reply": "2026-07-06T16:35:32.978493Z"
+    }
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Preset: 2AB_RW_Angle\n",
+      "Description: Two-armed bandit with a Rescorla-Wagner delta-rule learner and an angle decision process.\n",
+      "Task: two-armed Bernoulli bandit\n",
+      "Learning process: RescorlaWagnerDeltaRule\n",
+      "Decision process: angle\n",
+      "Required parameters: rl_alpha, scaler, a, z, t, theta\n",
+      "Default parameters: rl_alpha=0.2, scaler=2, a=1, z=0.5, t=0.001, theta=0\n",
+      "Response labels: (-1, 1)\n",
+      "Response to choice: {-1: 0, 1: 1}\n",
+      "Context fields: ['feedback']\n",
+      "Learning backend: jax\n",
+      "Gradient support: available\n",
+      "HSSM participant contract: yes\n"
+     ]
+    }
+   ],
    "source": [
+    "ssms_config = rl.preset.get(\"2AB_RW_Angle\")\n",
     "print(rl.preset.info(\"2AB_RW_Angle\"))"
    ]
   },
@@ -191,25 +282,45 @@
    "id": "f4b8f53f",
    "metadata": {},
    "source": [
-    "To fit this preset in HSSM, there are only two facts you need right away:\n",
-    "- the free parameters are `rl_alpha`, `scaler`, `a`, `z`, `t`, and `theta`, and\n",
-    "- the drift `v` is **computed** from the learning process rather than sampled.\n",
+    "A few fields to note in that summary:\n",
     "\n",
-    "We confirm that below.\n",
-    "\n"
+    "- **Required parameters** are what we must supply to simulate: the learning\n",
+    "  parameters `rl_alpha`, `scaler` and the decision parameters `a`, `z`, `t`, `theta`.\n",
+    "  The drift `v` is *not* here — it is **computed** each trial from the learner.\n",
+    "- **Response labels** `(-1, 1)` are the two arms. In this preset arm `-1` is the\n",
+    "  *high-reward* arm (reward probability 0.7) and arm `1` is the low-reward arm (0.3).\n",
+    "- **Gradient support: available** means the learning process has a differentiable\n",
+    "  JAX implementation — a hard requirement for HSSM's gradient-based sampler. Let's\n",
+    "  confirm that explicitly:"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 4,
    "id": "5a61fc70",
-   "metadata": {},
-   "outputs": [],
+   "metadata": {
+    "execution": {
+     "iopub.execute_input": "2026-07-06T16:35:32.979672Z",
+     "iopub.status.busy": "2026-07-06T16:35:32.979617Z",
+     "iopub.status.idle": "2026-07-06T16:35:32.981257Z",
+     "shell.execute_reply": "2026-07-06T16:35:32.980964Z"
+    }
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "computed params (driven by the learner): ['v']\n",
+      "context fields (read from data each trial): ['feedback']\n"
+     ]
+    }
+   ],
    "source": [
-    "ssms_config = rl.preset.get(\"2AB_RW_Angle\")\n",
     "assembled = ssms_config.assemble(backend=\"jax\")\n",
     "print(\"computed params (driven by the learner):\", assembled.computed_params)\n",
-    "assert \"v\" in assembled.computed_params"
+    "print(\"context fields (read from data each trial):\", assembled.context_fields)\n",
+    "assert assembled.gradient == \"available\", \"HSSM inference needs JAX gradients\""
    ]
   },
   {
@@ -218,21 +329,233 @@
    "metadata": {},
    "source": [
     "## 4. Define ground-truth parameters\n",
-    "We *simulate* data from known parameters so we can later\n",
+    "\n",
+    "Because this is a tutorial, we *simulate* data from known parameters so we can later\n",
     "check whether the model recovers them. We choose a **group mean** for each parameter\n",
     "and give each participant a small random deviation around that mean, so participants\n",
     "genuinely differ — that is what the hierarchical model will try to recover.\n",
+    "\n",
     "`SDS` sets how spread out participants are for each parameter (bigger = more\n",
     "individual variability), and `BOUNDS` keeps every sampled value inside the range the\n",
-    "model supports.\n"
+    "model supports."
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 5,
    "id": "6258c663",
-   "metadata": {},
-   "outputs": [],
+   "metadata": {
+    "execution": {
+     "iopub.execute_input": "2026-07-06T16:35:32.982233Z",
+     "iopub.status.busy": "2026-07-06T16:35:32.982174Z",
+     "iopub.status.idle": "2026-07-06T16:35:32.997826Z",
+     "shell.execute_reply": "2026-07-06T16:35:32.997506Z"
+    }
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>rl_alpha</th>\n",
+       "      <th>scaler</th>\n",
+       "      <th>a</th>\n",
+       "      <th>z</th>\n",
+       "      <th>t</th>\n",
+       "      <th>theta</th>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>participant_id</th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>0.048</td>\n",
+       "      <td>2.349</td>\n",
+       "      <td>1.156</td>\n",
+       "      <td>0.486</td>\n",
+       "      <td>0.258</td>\n",
+       "      <td>0.362</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>0.118</td>\n",
+       "      <td>2.287</td>\n",
+       "      <td>0.921</td>\n",
+       "      <td>0.526</td>\n",
+       "      <td>0.277</td>\n",
+       "      <td>0.288</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>0.084</td>\n",
+       "      <td>2.307</td>\n",
+       "      <td>1.357</td>\n",
+       "      <td>0.513</td>\n",
+       "      <td>0.252</td>\n",
+       "      <td>0.441</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>0.069</td>\n",
+       "      <td>2.491</td>\n",
+       "      <td>1.176</td>\n",
+       "      <td>0.480</td>\n",
+       "      <td>0.332</td>\n",
+       "      <td>0.433</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>0.111</td>\n",
+       "      <td>1.808</td>\n",
+       "      <td>1.350</td>\n",
+       "      <td>0.439</td>\n",
+       "      <td>0.147</td>\n",
+       "      <td>0.312</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>5</th>\n",
+       "      <td>0.041</td>\n",
+       "      <td>2.433</td>\n",
+       "      <td>1.247</td>\n",
+       "      <td>0.555</td>\n",
+       "      <td>0.255</td>\n",
+       "      <td>0.485</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>6</th>\n",
+       "      <td>0.085</td>\n",
+       "      <td>1.841</td>\n",
+       "      <td>1.209</td>\n",
+       "      <td>0.443</td>\n",
+       "      <td>0.263</td>\n",
+       "      <td>0.389</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>7</th>\n",
+       "      <td>0.071</td>\n",
+       "      <td>3.062</td>\n",
+       "      <td>1.203</td>\n",
+       "      <td>0.546</td>\n",
+       "      <td>0.225</td>\n",
+       "      <td>0.096</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>8</th>\n",
+       "      <td>0.112</td>\n",
+       "      <td>1.977</td>\n",
+       "      <td>0.989</td>\n",
+       "      <td>0.498</td>\n",
+       "      <td>0.258</td>\n",
+       "      <td>0.305</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9</th>\n",
+       "      <td>0.081</td>\n",
+       "      <td>2.672</td>\n",
+       "      <td>1.419</td>\n",
+       "      <td>0.532</td>\n",
+       "      <td>0.179</td>\n",
+       "      <td>0.324</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>10</th>\n",
+       "      <td>0.114</td>\n",
+       "      <td>2.621</td>\n",
+       "      <td>0.983</td>\n",
+       "      <td>0.588</td>\n",
+       "      <td>0.241</td>\n",
+       "      <td>0.158</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>11</th>\n",
+       "      <td>0.064</td>\n",
+       "      <td>2.123</td>\n",
+       "      <td>1.472</td>\n",
+       "      <td>0.470</td>\n",
+       "      <td>0.190</td>\n",
+       "      <td>0.382</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>12</th>\n",
+       "      <td>0.065</td>\n",
+       "      <td>2.453</td>\n",
+       "      <td>1.083</td>\n",
+       "      <td>0.660</td>\n",
+       "      <td>0.224</td>\n",
+       "      <td>0.451</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>13</th>\n",
+       "      <td>0.133</td>\n",
+       "      <td>2.393</td>\n",
+       "      <td>1.099</td>\n",
+       "      <td>0.525</td>\n",
+       "      <td>0.218</td>\n",
+       "      <td>0.358</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>14</th>\n",
+       "      <td>0.150</td>\n",
+       "      <td>2.959</td>\n",
+       "      <td>1.194</td>\n",
+       "      <td>0.447</td>\n",
+       "      <td>0.316</td>\n",
+       "      <td>0.320</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                rl_alpha  scaler      a      z      t  theta\n",
+       "participant_id                                              \n",
+       "0                  0.048   2.349  1.156  0.486  0.258  0.362\n",
+       "1                  0.118   2.287  0.921  0.526  0.277  0.288\n",
+       "2                  0.084   2.307  1.357  0.513  0.252  0.441\n",
+       "3                  0.069   2.491  1.176  0.480  0.332  0.433\n",
+       "4                  0.111   1.808  1.350  0.439  0.147  0.312\n",
+       "5                  0.041   2.433  1.247  0.555  0.255  0.485\n",
+       "6                  0.085   1.841  1.209  0.443  0.263  0.389\n",
+       "7                  0.071   3.062  1.203  0.546  0.225  0.096\n",
+       "8                  0.112   1.977  0.989  0.498  0.258  0.305\n",
+       "9                  0.081   2.672  1.419  0.532  0.179  0.324\n",
+       "10                 0.114   2.621  0.983  0.588  0.241  0.158\n",
+       "11                 0.064   2.123  1.472  0.470  0.190  0.382\n",
+       "12                 0.065   2.453  1.083  0.660  0.224  0.451\n",
+       "13                 0.133   2.393  1.099  0.525  0.218  0.358\n",
+       "14                 0.150   2.959  1.194  0.447  0.316  0.320"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
    "source": [
     "GROUP_THETA = {\n",
     "    \"rl_alpha\": 0.08,  # learning rate (small -> gradual, visible learning)\n",
@@ -282,18 +605,120 @@
    "metadata": {},
    "source": [
     "## 5. Simulate the data\n",
+    "\n",
     "`rl.Simulator(config).simulate(...)` runs the full generative loop for every\n",
     "participant and trial: compute the drift from current Q-values → run the angle SSM to\n",
     "get a choice and RT → deliver feedback → update the Q-values. Passing **arrays** of\n",
-    "parameters (one value per participant) produces a balanced multi-participant panel.\n"
+    "parameters (one value per participant) produces a balanced multi-participant panel."
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 6,
    "id": "887db61f",
-   "metadata": {},
-   "outputs": [],
+   "metadata": {
+    "execution": {
+     "iopub.execute_input": "2026-07-06T16:35:32.998842Z",
+     "iopub.status.busy": "2026-07-06T16:35:32.998783Z",
+     "iopub.status.idle": "2026-07-06T16:35:34.263819Z",
+     "shell.execute_reply": "2026-07-06T16:35:34.263339Z"
+    }
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "rows: 2250 | columns: ['participant_id', 'trial_id', 'rt', 'response', 'feedback']\n"
+     ]
+    },
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>participant_id</th>\n",
+       "      <th>trial_id</th>\n",
+       "      <th>rt</th>\n",
+       "      <th>response</th>\n",
+       "      <th>feedback</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1.069821</td>\n",
+       "      <td>-1</td>\n",
+       "      <td>1.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>0</td>\n",
+       "      <td>1</td>\n",
+       "      <td>1.998447</td>\n",
+       "      <td>-1</td>\n",
+       "      <td>1.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>0</td>\n",
+       "      <td>2</td>\n",
+       "      <td>1.560222</td>\n",
+       "      <td>-1</td>\n",
+       "      <td>1.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>0</td>\n",
+       "      <td>3</td>\n",
+       "      <td>0.505802</td>\n",
+       "      <td>-1</td>\n",
+       "      <td>1.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>0</td>\n",
+       "      <td>4</td>\n",
+       "      <td>1.074383</td>\n",
+       "      <td>-1</td>\n",
+       "      <td>1.0</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "   participant_id  trial_id        rt  response  feedback\n",
+       "0               0         0  1.069821        -1       1.0\n",
+       "1               0         1  1.998447        -1       1.0\n",
+       "2               0         2  1.560222        -1       1.0\n",
+       "3               0         3  0.505802        -1       1.0\n",
+       "4               0         4  1.074383        -1       1.0"
+      ]
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
    "source": [
     "data = rl.Simulator(ssms_config).simulate(\n",
     "    theta=theta_arrays,\n",
@@ -314,26 +739,42 @@
    "metadata": {},
    "source": [
     "Each row is one trial. The columns we care about:\n",
-    "- `participant_id`, `trial_id`: who and when.\n",
-    "- `response`: the chosen arm (-1 or 1).\n",
-    "- `rt`: response time in seconds.\n",
-    "- `feedback`: reward (0 or 1), used by the learner.\n",
     "\n",
-    "The next cell is a quick sanity check that learning is visible in the simulated data.\n",
-    "It does three things:\n",
-    "1. bins trials into windows of 10;\n",
-    "2. computes choice accuracy as P(chose high-reward arm);\n",
-    "3. computes mean RT per bin.\n",
+    "- **`participant_id`, `trial_id`** — who and when.\n",
+    "- **`response`** — the chosen arm (`-1` or `1`).\n",
+    "- **`rt`** — the response time in seconds.\n",
+    "- **`feedback`** — the reward delivered (`0` or `1`); the learner uses this to update.\n",
     "\n",
-    "Expected pattern: accuracy should rise above chance, and RT should decrease as values separate.\n"
+    "Before modelling, let's confirm the participants actually **learned**. Learning shows\n",
+    "up two ways in the simulated data: choices should shift toward the high-reward arm\n",
+    "(`-1`), *and* responses should get **faster** as the value difference grows and drives\n",
+    "the drift rate up. We plot both, binned over trials:"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 7,
    "id": "991e7115",
-   "metadata": {},
-   "outputs": [],
+   "metadata": {
+    "execution": {
+     "iopub.execute_input": "2026-07-06T16:35:34.265047Z",
+     "iopub.status.busy": "2026-07-06T16:35:34.264970Z",
+     "iopub.status.idle": "2026-07-06T16:35:34.382476Z",
+     "shell.execute_reply": "2026-07-06T16:35:34.382163Z"
+    }
+   },
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 1200x400 with 2 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
    "source": [
     "BIN = 10\n",
     "learn = data[data[\"rt\"] > 0].copy()\n",
@@ -365,7 +806,62 @@
    "id": "db9b5799",
    "metadata": {},
    "source": [
-    "## 6. Build the HSSM model\n"
+    "## 6. Bridge the model into HSSM\n",
+    "\n",
+    "Here is the step that PR-era HSSM makes easy. `RLSSMConfig.from_ssms_model` takes the\n",
+    "**same** `ssms` model we simulated from and produces an HSSM configuration object.\n",
+    "Nothing about the model is re-specified by hand — the learning rule, the decision\n",
+    "process, the parameter list, and the crucial \"`v` is computed, not free\" fact all\n",
+    "carry over automatically."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "e19d1bb7",
+   "metadata": {
+    "execution": {
+     "iopub.execute_input": "2026-07-06T16:35:34.383732Z",
+     "iopub.status.busy": "2026-07-06T16:35:34.383657Z",
+     "iopub.status.idle": "2026-07-06T16:35:34.695851Z",
+     "shell.execute_reply": "2026-07-06T16:35:34.695474Z"
+    }
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "list_params (free params HSSM will estimate): ['rl_alpha', 'scaler', 'a', 'z', 't', 'theta']\n",
+      "extra_fields (columns read from data):        ['feedback']\n",
+      "computed (driven by the learner, not free):   {'v'}\n"
+     ]
+    }
+   ],
+   "source": [
+    "model_config = hssm.rl.RLSSMConfig.from_ssms_model(ssms_config)\n",
+    "\n",
+    "print(\"list_params (free params HSSM will estimate):\", model_config.list_params)\n",
+    "print(\"extra_fields (columns read from data):       \", model_config.extra_fields)\n",
+    "print(\n",
+    "    \"computed (driven by the learner, not free):  \",\n",
+    "    set(model_config.ssm_logp_func.computed),\n",
+    ")\n",
+    "\n",
+    "# Sanity check: the drift v is computed by the learner and is NOT a free parameter.\n",
+    "assert \"v\" in model_config.ssm_logp_func.computed\n",
+    "assert \"v\" not in model_config.list_params"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "b1f55587",
+   "metadata": {},
+   "source": [
+    "`model_config` is plain, inspectable **metadata** — parameter names, bounds, which\n",
+    "columns are read from the data, and which SSM inputs are computed by the learner. In\n",
+    "this basic tutorial we use it as-is; the later tutorials show how *editing* this\n",
+    "object (or the underlying `ssms` model) lets you build entirely custom RLSSMs."
    ]
   },
   {
@@ -373,16 +869,42 @@
    "id": "f07adb27",
    "metadata": {},
    "source": [
-    "To keep this first fit readable, we use one small helper that applies the same\n",
-    "hierarchical template to every free parameter: one group mean plus participant-level\n",
-    "deviations. Later tutorials show how to customize these priors in more detail.\n"
+    "## 7. Specify hierarchical priors and build the model\n",
+    "\n",
+    "For each parameter we write a small **`hssm.Param`** describing a hierarchical\n",
+    "structure with a formula borrowed from regression notation:\n",
+    "\n",
+    "```\n",
+    "rl_alpha ~ 1 + (1 | participant_id)\n",
+    "```\n",
+    "\n",
+    "Read it as: *\"estimate a group-level intercept (`1`) plus a per-participant deviation\n",
+    "(`(1 | participant_id)`).\"* We attach two priors:\n",
+    "\n",
+    "- **`Intercept`** — a `TruncatedNormal` prior on the group mean, truncated to the\n",
+    "  parameter's valid range. This encodes a plausible starting guess without hard-coding\n",
+    "  the answer.\n",
+    "- **`1|participant_id`** — the spread of individual deviations. We give it mean **0**\n",
+    "  (so the group `Intercept` alone owns the overall location — this avoids a\n",
+    "  non-identifiability between the two) and a `HalfNormal` prior on how large the\n",
+    "  between-participant spread is.\n",
+    "\n",
+    "The helper below just stamps out this same structure for each parameter so the model\n",
+    "call stays readable."
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 9,
    "id": "52e648b3",
-   "metadata": {},
+   "metadata": {
+    "execution": {
+     "iopub.execute_input": "2026-07-06T16:35:34.697135Z",
+     "iopub.status.busy": "2026-07-06T16:35:34.697059Z",
+     "iopub.status.idle": "2026-07-06T16:35:34.699038Z",
+     "shell.execute_reply": "2026-07-06T16:35:34.698745Z"
+    }
+   },
    "outputs": [],
    "source": [
     "# Prior on the per-participant deviations: mean 0, with a learned spread (sigma).\n",
@@ -412,23 +934,58 @@
    "id": "f0cdcee8",
    "metadata": {},
    "source": [
-    "A few arguments deserve a quick note:\n",
-    "- **`model=\"2AB_RW_Angle\"`** tells HSSM to use the same preset we simulated from.\n",
-    "- **`include=[...]`** applies the same hierarchical prior template to each free parameter.\n",
-    "- **`p_outlier=0` / `lapse=None`** turn off the outlier/lapse mixture for this first fit.\n",
-    "- **`process_initvals=False`** is the main RLSSM-specific setting to remember.\n"
+    "Now we build the model. A few arguments deserve a note:\n",
+    "\n",
+    "- **`data`** and **`model_config`** wire the trial panel to the bridged model.\n",
+    "- **`p_outlier=0` / `lapse=None`** turn off the outlier/lapse mixture — one fewer\n",
+    "  moving part for a first fit.\n",
+    "- **`process_initvals=False`** is **important for RLSSMs.** It tells HSSM to start the\n",
+    "  sampler from the prior rather than from processed initial values; the latter can\n",
+    "  place the RLSSM chain in a bad region where the gradient explodes and sampling\n",
+    "  stalls. (If you ever see the sampler make no progress with near-zero step size,\n",
+    "  this is the first thing to set.)"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 10,
    "id": "f44b2a62",
-   "metadata": {},
-   "outputs": [],
+   "metadata": {
+    "execution": {
+     "iopub.execute_input": "2026-07-06T16:35:34.700155Z",
+     "iopub.status.busy": "2026-07-06T16:35:34.700090Z",
+     "iopub.status.idle": "2026-07-06T16:35:34.915394Z",
+     "shell.execute_reply": "2026-07-06T16:35:34.915018Z"
+    }
+   },
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "You supplied a model '2AB_RW_Angle', which is currently not supported in the ssm_simulators package. An error will be thrown when sampling from the random variable or when using any posterior or prior predictive sampling methods.\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Model initialized successfully.\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "participants: 15 | trials/participant: 150\n",
+      "free parameters: ['rl_alpha', 'scaler', 'a', 'z', 't', 'theta']\n"
+     ]
+    }
+   ],
    "source": [
     "model = hssm.RLSSM(\n",
     "    data=data,\n",
-    "    model=\"2AB_RW_Angle\",\n",
+    "    model_config=model_config,\n",
     "    p_outlier=0,\n",
     "    lapse=None,\n",
     "    process_initvals=False,\n",
@@ -444,27 +1001,15409 @@
     "\n",
     "print(\"participants:\", model.n_participants, \"| trials/participant:\", model.n_trials)\n",
     "print(\"free parameters:\", list(model.params.keys()))\n",
-    "assert model.model_name == \"2AB_RW_Angle\"\n",
     "assert \"rl_alpha\" in model.params\n",
     "assert \"v\" not in model.params  # computed by the learner, never sampled"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "d838b1ca",
+   "metadata": {},
+   "source": [
+    "HSSM builds on **bambi** (formula layer) and **PyMC** (sampling engine). You can\n",
+    "inspect both — handy for confirming the priors and likelihood wired up as intended:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "f246503f",
+   "metadata": {
+    "execution": {
+     "iopub.execute_input": "2026-07-06T16:35:34.916996Z",
+     "iopub.status.busy": "2026-07-06T16:35:34.916633Z",
+     "iopub.status.idle": "2026-07-06T16:35:34.918989Z",
+     "shell.execute_reply": "2026-07-06T16:35:34.918625Z"
+    }
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "       Formula: c(rt, response) ~ 1 + (1|participant_id)\n",
+      "                scaler ~ 1 + (1|participant_id)\n",
+      "                a ~ 1 + (1|participant_id)\n",
+      "                z ~ 1 + (1|participant_id)\n",
+      "                t ~ 1 + (1|participant_id)\n",
+      "                theta ~ 1 + (1|participant_id)\n",
+      "        Family: SSM Family\n",
+      "          Link: rl_alpha = identity\n",
+      "                scaler = identity\n",
+      "                a = identity\n",
+      "                z = identity\n",
+      "                t = identity\n",
+      "                theta = identity\n",
+      "  Observations: 2250\n",
+      "        Priors: \n",
+      "    target = rl_alpha\n",
+      "        Common-level effects\n",
+      "            Intercept ~ TruncatedNormal(lower: 0.009999999776482582, upper: 1.0, mu: 0.15000000596046448,\n",
+      "                sigma: 0.15000000596046448)\n",
+      "        \n",
+      "        \n",
+      "        Group-level effects\n",
+      "            1|participant_id ~ Normal(mu: 0.0, sigma: HalfNormal(sigma: 0.5))\n",
+      "    target = scaler\n",
+      "        Common-level effects\n",
+      "            scaler_Intercept ~ TruncatedNormal(lower: 0.10000000149011612, upper: 5.0, mu: 2.0, sigma:\n",
+      "                0.800000011920929)\n",
+      "        \n",
+      "        \n",
+      "        Group-level effects\n",
+      "            scaler_1|participant_id ~ Normal(mu: 0.0, sigma: HalfNormal(sigma: 0.5))\n",
+      "    target = a\n",
+      "        Common-level effects\n",
+      "            a_Intercept ~ TruncatedNormal(lower: 0.30000001192092896, upper: 2.5, mu: 1.100000023841858,\n",
+      "                sigma: 0.30000001192092896)\n",
+      "        \n",
+      "        \n",
+      "        Group-level effects\n",
+      "            a_1|participant_id ~ Normal(mu: 0.0, sigma: HalfNormal(sigma: 0.5))\n",
+      "    target = z\n",
+      "        Common-level effects\n",
+      "            z_Intercept ~ TruncatedNormal(lower: 0.10000000149011612, upper: 0.8999999761581421, mu: 0.5,\n",
+      "                sigma: 0.15000000596046448)\n",
+      "        \n",
+      "        \n",
+      "        Group-level effects\n",
+      "            z_1|participant_id ~ Normal(mu: 0.0, sigma: HalfNormal(sigma: 0.5))\n",
+      "    target = t\n",
+      "        Common-level effects\n",
+      "            t_Intercept ~ TruncatedNormal(lower: 0.05000000074505806, upper: 1.0, mu: 0.25, sigma:\n",
+      "                0.10000000149011612)\n",
+      "        \n",
+      "        \n",
+      "        Group-level effects\n",
+      "            t_1|participant_id ~ Normal(mu: 0.0, sigma: HalfNormal(sigma: 0.5))\n",
+      "    target = theta\n",
+      "        Common-level effects\n",
+      "            theta_Intercept ~ TruncatedNormal(lower: 0.0, upper: 1.2000000476837158, mu: 0.3499999940395355,\n",
+      "                sigma: 0.15000000596046448)\n",
+      "        \n",
+      "        \n",
+      "        Group-level effects\n",
+      "            theta_1|participant_id ~ Normal(mu: 0.0, sigma: HalfNormal(sigma: 0.5))\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(model.model)"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "23ab0dd2",
    "metadata": {},
    "source": [
-    "## 7. Sample the posterior\n",
-    "We now draw from the posterior. This is the step that learns the parameters from data. In this quick tutorial\n",
-    "setup, sampling is intentionally short.\n"
+    "## 8. Sample the posterior\n",
+    "\n",
+    "We draw from the posterior with the **NumPyro NUTS** sampler (fast, JAX-based). This\n",
+    "is the step that \"learns\" the parameters from data. At `FULL_RUN` scale this takes a\n",
+    "few minutes; at doc scale it is deliberately short."
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 12,
    "id": "e4bb5cd3",
-   "metadata": {},
-   "outputs": [],
+   "metadata": {
+    "execution": {
+     "iopub.execute_input": "2026-07-06T16:35:34.919910Z",
+     "iopub.status.busy": "2026-07-06T16:35:34.919835Z",
+     "iopub.status.idle": "2026-07-06T16:44:43.617653Z",
+     "shell.execute_reply": "2026-07-06T16:44:43.617081Z"
+    }
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Using default initvals. \n",
+      "\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "NUTS[numpyro]: [rl_alpha_Intercept, rl_alpha_1|participant_id_sigma, rl_alpha_1|participant_id_offset, scaler_Intercept, scaler_1|participant_id_sigma, scaler_1|participant_id_offset, a_Intercept, a_1|participant_id_sigma, a_1|participant_id_offset, z_Intercept, z_1|participant_id_sigma, z_1|participant_id_offset, t_Intercept, t_1|participant_id_sigma, t_1|participant_id_offset, theta_Intercept, theta_1|participant_id_sigma, theta_1|participant_id_offset]\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "  0%|          | 0/1500 [00:00<?, ?it/s]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   0%|          | 0/1500 [00:10<?, ?it/s, 255 steps of size 2.06e-02. acc. prob=0.84]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   3%|▎         | 42/1500 [00:10<05:49,  4.17it/s, 127 steps of size 1.03e-02. acc. prob=0.83]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   3%|▎         | 43/1500 [00:10<05:53,  4.12it/s, 255 steps of size 1.39e-02. acc. prob=0.84]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   3%|▎         | 44/1500 [00:10<05:58,  4.06it/s, 255 steps of size 1.20e-02. acc. prob=0.84]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   3%|▎         | 45/1500 [00:11<06:05,  3.98it/s, 255 steps of size 1.60e-02. acc. prob=0.84]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   3%|▎         | 46/1500 [00:11<06:13,  3.89it/s, 255 steps of size 1.49e-02. acc. prob=0.84]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   3%|▎         | 47/1500 [00:11<06:23,  3.79it/s, 255 steps of size 1.50e-02. acc. prob=0.84]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   3%|▎         | 48/1500 [00:12<06:34,  3.68it/s, 255 steps of size 9.76e-03. acc. prob=0.84]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   3%|▎         | 49/1500 [00:12<07:59,  3.03it/s, 511 steps of size 1.27e-02. acc. prob=0.84]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   3%|▎         | 50/1500 [00:13<07:58,  3.03it/s, 255 steps of size 1.66e-02. acc. prob=0.85]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   3%|▎         | 51/1500 [00:13<07:57,  3.04it/s, 255 steps of size 1.33e-02. acc. prob=0.84]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   3%|▎         | 52/1500 [00:13<07:55,  3.05it/s, 255 steps of size 1.30e-02. acc. prob=0.85]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   4%|▎         | 53/1500 [00:13<07:53,  3.06it/s, 255 steps of size 1.55e-02. acc. prob=0.85]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   4%|▎         | 54/1500 [00:14<07:53,  3.06it/s, 255 steps of size 8.92e-03. acc. prob=0.84]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   4%|▎         | 55/1500 [00:14<09:59,  2.41it/s, 511 steps of size 1.17e-02. acc. prob=0.85]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   4%|▎         | 56/1500 [00:15<09:22,  2.57it/s, 255 steps of size 1.38e-02. acc. prob=0.85]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   4%|▍         | 57/1500 [00:15<09:01,  2.66it/s, 255 steps of size 1.44e-02. acc. prob=0.85]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   4%|▍         | 58/1500 [00:15<08:41,  2.77it/s, 255 steps of size 1.79e-02. acc. prob=0.85]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   4%|▍         | 59/1500 [00:16<08:30,  2.83it/s, 255 steps of size 2.09e-02. acc. prob=0.85]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   4%|▍         | 60/1500 [00:16<07:08,  3.36it/s, 127 steps of size 9.32e-03. acc. prob=0.85]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   4%|▍         | 61/1500 [00:16<07:19,  3.27it/s, 255 steps of size 1.21e-02. acc. prob=0.85]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   4%|▍         | 62/1500 [00:17<07:27,  3.22it/s, 255 steps of size 1.53e-02. acc. prob=0.85]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   4%|▍         | 63/1500 [00:17<06:23,  3.75it/s, 127 steps of size 1.52e-02. acc. prob=0.85]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   4%|▍         | 64/1500 [00:17<06:47,  3.52it/s, 255 steps of size 1.33e-02. acc. prob=0.85]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   4%|▍         | 65/1500 [00:17<07:04,  3.38it/s, 255 steps of size 1.53e-02. acc. prob=0.85]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   4%|▍         | 66/1500 [00:18<07:16,  3.28it/s, 255 steps of size 1.32e-02. acc. prob=0.85]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   4%|▍         | 67/1500 [00:18<07:24,  3.22it/s, 255 steps of size 1.64e-02. acc. prob=0.85]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   5%|▍         | 68/1500 [00:18<07:30,  3.18it/s, 255 steps of size 9.29e-03. acc. prob=0.85]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   5%|▍         | 69/1500 [00:19<09:54,  2.41it/s, 511 steps of size 1.05e-02. acc. prob=0.85]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   5%|▍         | 70/1500 [00:20<11:35,  2.06it/s, 511 steps of size 1.10e-02. acc. prob=0.85]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   5%|▍         | 71/1500 [00:20<10:34,  2.25it/s, 255 steps of size 1.40e-02. acc. prob=0.86]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   5%|▍         | 72/1500 [00:20<09:46,  2.43it/s, 255 steps of size 7.65e-03. acc. prob=0.85]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   5%|▍         | 73/1500 [00:21<11:39,  2.04it/s, 511 steps of size 9.74e-03. acc. prob=0.85]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   5%|▍         | 74/1500 [00:21<10:28,  2.27it/s, 255 steps of size 1.21e-02. acc. prob=0.86]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   5%|▌         | 75/1500 [00:22<09:42,  2.45it/s, 255 steps of size 1.50e-02. acc. prob=0.86]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   5%|▌         | 76/1500 [00:22<09:14,  2.57it/s, 255 steps of size 1.89e-02. acc. prob=0.86]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   5%|▌         | 77/1500 [00:22<07:40,  3.09it/s, 127 steps of size 6.58e-03. acc. prob=0.85]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   5%|▌         | 78/1500 [00:23<10:05,  2.35it/s, 511 steps of size 8.28e-03. acc. prob=0.85]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   5%|▌         | 79/1500 [00:24<11:53,  1.99it/s, 511 steps of size 9.80e-03. acc. prob=0.86]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   5%|▌         | 80/1500 [00:24<10:37,  2.23it/s, 255 steps of size 1.14e-02. acc. prob=0.86]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   5%|▌         | 81/1500 [00:24<09:48,  2.41it/s, 255 steps of size 1.43e-02. acc. prob=0.86]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   5%|▌         | 82/1500 [00:24<08:03,  2.93it/s, 127 steps of size 7.53e-03. acc. prob=0.86]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   6%|▌         | 83/1500 [00:25<10:22,  2.28it/s, 511 steps of size 9.41e-03. acc. prob=0.86]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   6%|▌         | 84/1500 [00:26<11:56,  1.98it/s, 511 steps of size 1.01e-02. acc. prob=0.86]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   6%|▌         | 85/1500 [00:26<10:39,  2.21it/s, 255 steps of size 9.59e-03. acc. prob=0.86]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   6%|▌         | 86/1500 [00:26<09:44,  2.42it/s, 255 steps of size 1.07e-02. acc. prob=0.86]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   6%|▌         | 87/1500 [00:27<09:07,  2.58it/s, 255 steps of size 1.15e-02. acc. prob=0.86]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   6%|▌         | 88/1500 [00:27<08:40,  2.71it/s, 255 steps of size 1.43e-02. acc. prob=0.86]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   6%|▌         | 89/1500 [00:27<08:21,  2.81it/s, 255 steps of size 1.77e-02. acc. prob=0.86]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   6%|▌         | 90/1500 [00:28<08:08,  2.89it/s, 255 steps of size 1.53e-02. acc. prob=0.86]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   6%|▌         | 91/1500 [00:28<07:58,  2.94it/s, 255 steps of size 1.80e-02. acc. prob=0.86]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   6%|▌         | 92/1500 [00:28<07:54,  2.97it/s, 255 steps of size 2.23e-02. acc. prob=0.86]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   6%|▌         | 93/1500 [00:28<06:42,  3.49it/s, 127 steps of size 1.31e-02. acc. prob=0.86]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   6%|▋         | 94/1500 [00:29<07:00,  3.34it/s, 255 steps of size 1.53e-02. acc. prob=0.86]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   6%|▋         | 95/1500 [00:29<07:22,  3.17it/s, 255 steps of size 1.61e-02. acc. prob=0.86]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   6%|▋         | 96/1500 [00:30<07:30,  3.12it/s, 255 steps of size 1.92e-02. acc. prob=0.86]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   6%|▋         | 97/1500 [00:30<06:23,  3.65it/s, 127 steps of size 1.96e-02. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   7%|▋         | 98/1500 [00:30<05:39,  4.13it/s, 127 steps of size 2.29e-02. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   7%|▋         | 99/1500 [00:30<05:06,  4.58it/s, 127 steps of size 1.37e-02. acc. prob=0.86]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   7%|▋         | 100/1500 [00:30<05:54,  3.95it/s, 255 steps of size 1.66e-02. acc. prob=0.86]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   7%|▋         | 101/1500 [00:31<08:44,  2.67it/s, 511 steps of size 1.99e-01. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   7%|▋         | 103/1500 [00:31<05:47,  4.02it/s, 127 steps of size 6.92e-02. acc. prob=0.86]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   7%|▋         | 105/1500 [00:31<04:36,  5.04it/s, 127 steps of size 7.13e-02. acc. prob=0.86]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   7%|▋         | 107/1500 [00:32<03:57,  5.86it/s, 127 steps of size 9.14e-02. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   7%|▋         | 108/1500 [00:32<03:55,  5.91it/s, 127 steps of size 8.97e-02. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   7%|▋         | 110/1500 [00:32<03:30,  6.60it/s, 127 steps of size 8.98e-02. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   7%|▋         | 112/1500 [00:32<02:56,  7.88it/s, 63 steps of size 3.15e-02. acc. prob=0.86] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   8%|▊         | 113/1500 [00:33<03:53,  5.93it/s, 255 steps of size 4.29e-02. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   8%|▊         | 114/1500 [00:33<03:52,  5.96it/s, 127 steps of size 5.77e-02. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   8%|▊         | 115/1500 [00:33<03:51,  5.98it/s, 127 steps of size 7.05e-02. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   8%|▊         | 116/1500 [00:33<03:50,  6.00it/s, 127 steps of size 9.54e-02. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   8%|▊         | 118/1500 [00:33<03:01,  7.60it/s, 63 steps of size 6.72e-02. acc. prob=0.87] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   8%|▊         | 120/1500 [00:33<02:57,  7.78it/s, 127 steps of size 8.16e-02. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   8%|▊         | 122/1500 [00:34<02:35,  8.84it/s, 63 steps of size 1.30e-01. acc. prob=0.87] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   8%|▊         | 124/1500 [00:34<02:12, 10.39it/s, 63 steps of size 2.90e-02. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   8%|▊         | 125/1500 [00:34<03:15,  7.05it/s, 255 steps of size 3.90e-02. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   8%|▊         | 126/1500 [00:34<03:22,  6.80it/s, 127 steps of size 5.05e-02. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   8%|▊         | 127/1500 [00:34<03:34,  6.39it/s, 127 steps of size 6.09e-02. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   9%|▊         | 129/1500 [00:35<03:08,  7.26it/s, 127 steps of size 8.44e-02. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   9%|▊         | 131/1500 [00:35<03:00,  7.59it/s, 127 steps of size 1.10e-01. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   9%|▉         | 133/1500 [00:35<02:36,  8.74it/s, 63 steps of size 9.77e-02. acc. prob=0.87] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   9%|▉         | 135/1500 [00:36<03:16,  6.95it/s, 255 steps of size 3.17e-02. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   9%|▉         | 136/1500 [00:36<04:03,  5.60it/s, 255 steps of size 4.17e-02. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   9%|▉         | 137/1500 [00:36<03:58,  5.71it/s, 127 steps of size 5.46e-02. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   9%|▉         | 138/1500 [00:36<03:54,  5.80it/s, 127 steps of size 6.41e-02. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   9%|▉         | 140/1500 [00:36<03:26,  6.58it/s, 127 steps of size 8.34e-02. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   9%|▉         | 142/1500 [00:37<02:51,  7.93it/s, 63 steps of size 1.06e-01. acc. prob=0.87] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  10%|▉         | 144/1500 [00:37<02:20,  9.65it/s, 31 steps of size 1.56e-01. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  10%|▉         | 147/1500 [00:37<01:43, 13.04it/s, 31 steps of size 7.64e-02. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  10%|▉         | 149/1500 [00:37<01:45, 12.83it/s, 63 steps of size 6.66e-02. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  10%|█         | 151/1500 [00:37<01:46, 12.69it/s, 63 steps of size 8.01e-01. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  10%|█         | 154/1500 [00:37<01:48, 12.46it/s, 127 steps of size 6.08e-02. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  10%|█         | 156/1500 [00:38<01:48, 12.41it/s, 63 steps of size 8.28e-02. acc. prob=0.87] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  11%|█         | 158/1500 [00:38<02:03, 10.87it/s, 127 steps of size 6.18e-02. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  11%|█         | 160/1500 [00:38<01:59, 11.25it/s, 63 steps of size 8.58e-02. acc. prob=0.87] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  11%|█         | 162/1500 [00:38<01:53, 11.75it/s, 55 steps of size 1.08e-01. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  11%|█         | 164/1500 [00:38<01:44, 12.83it/s, 31 steps of size 2.81e-02. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  11%|█         | 165/1500 [00:39<02:41,  8.28it/s, 255 steps of size 3.82e-02. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  11%|█         | 166/1500 [00:39<02:52,  7.75it/s, 127 steps of size 5.12e-02. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  11%|█         | 167/1500 [00:39<03:02,  7.31it/s, 127 steps of size 6.79e-02. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  11%|█▏        | 169/1500 [00:39<02:23,  9.30it/s, 31 steps of size 1.12e-01. acc. prob=0.87] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  11%|█▏        | 171/1500 [00:39<02:10, 10.19it/s, 63 steps of size 1.94e-01. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  12%|█▏        | 173/1500 [00:40<02:48,  7.88it/s, 255 steps of size 3.45e-02. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  12%|█▏        | 174/1500 [00:40<02:57,  7.47it/s, 127 steps of size 4.65e-02. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  12%|█▏        | 175/1500 [00:40<03:05,  7.13it/s, 127 steps of size 6.31e-02. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  12%|█▏        | 177/1500 [00:40<02:35,  8.51it/s, 63 steps of size 7.68e-02. acc. prob=0.87] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  12%|█▏        | 179/1500 [00:40<02:18,  9.55it/s, 63 steps of size 1.22e-01. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  12%|█▏        | 181/1500 [00:40<02:07, 10.32it/s, 63 steps of size 1.32e-01. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  12%|█▏        | 182/1500 [00:40<02:15,  9.75it/s, 95 steps of size 1.32e-01. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  12%|█▏        | 184/1500 [00:41<01:55, 11.37it/s, 31 steps of size 9.23e-02. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  12%|█▏        | 186/1500 [00:41<01:52, 11.67it/s, 63 steps of size 1.19e-01. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  13%|█▎        | 188/1500 [00:41<01:41, 12.88it/s, 31 steps of size 1.35e-01. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  13%|█▎        | 191/1500 [00:41<01:43, 12.63it/s, 127 steps of size 5.55e-02. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  13%|█▎        | 193/1500 [00:41<01:59, 10.95it/s, 127 steps of size 6.88e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  13%|█▎        | 195/1500 [00:42<01:55, 11.31it/s, 63 steps of size 1.10e-01. acc. prob=0.88] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  13%|█▎        | 197/1500 [00:42<01:44, 12.43it/s, 63 steps of size 1.56e-01. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  13%|█▎        | 200/1500 [00:42<01:31, 14.26it/s, 63 steps of size 1.22e-01. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  14%|█▎        | 203/1500 [00:42<01:23, 15.55it/s, 63 steps of size 4.88e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  14%|█▎        | 204/1500 [00:42<01:41, 12.72it/s, 127 steps of size 6.00e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  14%|█▎        | 205/1500 [00:42<02:00, 10.75it/s, 127 steps of size 7.28e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  14%|█▍        | 207/1500 [00:42<01:55, 11.23it/s, 63 steps of size 8.17e-02. acc. prob=0.88] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  14%|█▍        | 209/1500 [00:43<01:52, 11.50it/s, 63 steps of size 8.45e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  14%|█▍        | 211/1500 [00:43<01:50, 11.64it/s, 63 steps of size 1.25e-01. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  14%|█▍        | 213/1500 [00:43<01:41, 12.68it/s, 31 steps of size 1.55e-01. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  14%|█▍        | 216/1500 [00:43<01:22, 15.60it/s, 31 steps of size 1.19e-01. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  15%|█▍        | 218/1500 [00:43<01:28, 14.49it/s, 63 steps of size 1.04e-01. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  15%|█▍        | 220/1500 [00:43<01:25, 14.98it/s, 31 steps of size 4.10e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  15%|█▍        | 221/1500 [00:43<01:46, 12.03it/s, 127 steps of size 5.11e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  15%|█▍        | 222/1500 [00:44<02:06, 10.14it/s, 127 steps of size 6.18e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  15%|█▍        | 223/1500 [00:44<02:23,  8.89it/s, 127 steps of size 7.02e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  15%|█▌        | 225/1500 [00:44<02:08,  9.95it/s, 63 steps of size 9.04e-02. acc. prob=0.88] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  15%|█▌        | 227/1500 [00:44<01:59, 10.67it/s, 63 steps of size 9.47e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  15%|█▌        | 229/1500 [00:44<01:53, 11.18it/s, 63 steps of size 3.08e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  15%|█▌        | 230/1500 [00:44<02:11,  9.64it/s, 127 steps of size 3.81e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  15%|█▌        | 231/1500 [00:45<02:27,  8.57it/s, 127 steps of size 4.63e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  15%|█▌        | 232/1500 [00:45<02:43,  7.75it/s, 127 steps of size 5.67e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  16%|█▌        | 234/1500 [00:45<02:19,  9.10it/s, 63 steps of size 6.80e-02. acc. prob=0.88] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  16%|█▌        | 236/1500 [00:45<02:06, 10.03it/s, 63 steps of size 9.40e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  16%|█▌        | 238/1500 [00:45<02:17,  9.19it/s, 127 steps of size 4.62e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  16%|█▌        | 239/1500 [00:46<02:31,  8.33it/s, 127 steps of size 5.32e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  16%|█▌        | 240/1500 [00:46<02:43,  7.69it/s, 127 steps of size 6.11e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  16%|█▌        | 242/1500 [00:46<02:20,  8.97it/s, 63 steps of size 7.77e-02. acc. prob=0.88] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  16%|█▋        | 244/1500 [00:46<02:06,  9.92it/s, 63 steps of size 1.09e-01. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  16%|█▋        | 246/1500 [00:46<01:58, 10.62it/s, 63 steps of size 6.17e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  16%|█▋        | 247/1500 [00:46<02:16,  9.20it/s, 127 steps of size 6.99e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  17%|█▋        | 249/1500 [00:47<02:03, 10.09it/s, 63 steps of size 8.62e-02. acc. prob=0.88] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  17%|█▋        | 251/1500 [00:47<01:47, 11.59it/s, 31 steps of size 6.82e-01. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  17%|█▋        | 254/1500 [00:47<01:45, 11.80it/s, 127 steps of size 4.70e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  17%|█▋        | 255/1500 [00:47<02:01, 10.23it/s, 127 steps of size 4.90e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  17%|█▋        | 256/1500 [00:47<02:17,  9.05it/s, 127 steps of size 6.02e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  17%|█▋        | 258/1500 [00:47<02:22,  8.70it/s, 127 steps of size 7.33e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  17%|█▋        | 260/1500 [00:48<02:25,  8.50it/s, 127 steps of size 4.33e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  17%|█▋        | 261/1500 [00:48<02:36,  7.91it/s, 127 steps of size 5.75e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  18%|█▊        | 263/1500 [00:48<02:16,  9.06it/s, 63 steps of size 8.41e-02. acc. prob=0.88] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  18%|█▊        | 265/1500 [00:48<02:04,  9.95it/s, 63 steps of size 2.07e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  18%|█▊        | 266/1500 [00:49<02:58,  6.92it/s, 255 steps of size 2.86e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  18%|█▊        | 267/1500 [00:49<03:03,  6.73it/s, 127 steps of size 3.98e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  18%|█▊        | 268/1500 [00:49<03:07,  6.57it/s, 127 steps of size 5.24e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  18%|█▊        | 269/1500 [00:49<03:10,  6.45it/s, 127 steps of size 7.05e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  18%|█▊        | 271/1500 [00:49<02:32,  8.06it/s, 63 steps of size 9.48e-02. acc. prob=0.88] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  18%|█▊        | 273/1500 [00:49<02:02,  9.99it/s, 31 steps of size 5.24e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  18%|█▊        | 274/1500 [00:49<02:19,  8.79it/s, 127 steps of size 7.15e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  18%|█▊        | 275/1500 [00:50<02:33,  7.97it/s, 127 steps of size 6.35e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  18%|█▊        | 277/1500 [00:50<02:11,  9.27it/s, 63 steps of size 4.80e-02. acc. prob=0.88] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  19%|█▊        | 278/1500 [00:50<02:26,  8.33it/s, 127 steps of size 6.45e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  19%|█▊        | 280/1500 [00:50<02:09,  9.42it/s, 63 steps of size 8.30e-02. acc. prob=0.88] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  19%|█▉        | 282/1500 [00:50<02:00, 10.14it/s, 63 steps of size 6.72e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  19%|█▉        | 284/1500 [00:50<01:52, 10.78it/s, 63 steps of size 9.87e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  19%|█▉        | 286/1500 [00:51<01:48, 11.22it/s, 63 steps of size 1.03e-01. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  19%|█▉        | 288/1500 [00:51<01:37, 12.41it/s, 31 steps of size 1.67e-01. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  19%|█▉        | 290/1500 [00:51<01:30, 13.35it/s, 63 steps of size 7.59e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  19%|█▉        | 292/1500 [00:51<01:33, 12.98it/s, 63 steps of size 5.49e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  20%|█▉        | 293/1500 [00:51<01:51, 10.80it/s, 127 steps of size 6.54e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  20%|█▉        | 295/1500 [00:51<01:47, 11.24it/s, 63 steps of size 9.59e-02. acc. prob=0.88] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  20%|█▉        | 297/1500 [00:52<01:43, 11.57it/s, 63 steps of size 1.01e-01. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  20%|█▉        | 299/1500 [00:52<02:13,  8.97it/s, 191 steps of size 2.84e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  20%|██        | 300/1500 [00:52<03:02,  6.58it/s, 255 steps of size 3.67e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  20%|██        | 301/1500 [00:52<03:05,  6.48it/s, 127 steps of size 4.73e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  20%|██        | 303/1500 [00:53<02:51,  6.99it/s, 127 steps of size 3.31e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  20%|██        | 304/1500 [00:53<02:56,  6.78it/s, 127 steps of size 4.21e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  20%|██        | 305/1500 [00:53<03:00,  6.61it/s, 127 steps of size 5.22e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  20%|██        | 307/1500 [00:53<02:27,  8.11it/s, 63 steps of size 8.19e-02. acc. prob=0.88] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  21%|██        | 309/1500 [00:53<02:09,  9.22it/s, 63 steps of size 5.99e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  21%|██        | 310/1500 [00:53<02:22,  8.34it/s, 127 steps of size 7.04e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  21%|██        | 312/1500 [00:54<02:23,  8.28it/s, 127 steps of size 4.55e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  21%|██        | 313/1500 [00:54<02:34,  7.70it/s, 127 steps of size 5.62e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  21%|██        | 314/1500 [00:54<02:43,  7.27it/s, 127 steps of size 6.92e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  21%|██        | 316/1500 [00:54<02:16,  8.68it/s, 63 steps of size 8.19e-02. acc. prob=0.88] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  21%|██        | 318/1500 [00:54<02:01,  9.72it/s, 63 steps of size 5.32e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  21%|██▏       | 319/1500 [00:54<02:16,  8.63it/s, 127 steps of size 6.24e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  21%|██▏       | 321/1500 [00:55<02:02,  9.61it/s, 63 steps of size 7.54e-02. acc. prob=0.88] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  22%|██▏       | 323/1500 [00:55<01:54, 10.28it/s, 63 steps of size 9.51e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  22%|██▏       | 325/1500 [00:55<01:48, 10.85it/s, 63 steps of size 1.20e-01. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  22%|██▏       | 327/1500 [00:55<01:59,  9.81it/s, 127 steps of size 5.19e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  22%|██▏       | 329/1500 [00:55<01:51, 10.47it/s, 63 steps of size 7.64e-02. acc. prob=0.88] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  22%|██▏       | 331/1500 [00:56<01:46, 10.96it/s, 63 steps of size 9.74e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  22%|██▏       | 333/1500 [00:56<01:43, 11.26it/s, 63 steps of size 9.43e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  22%|██▏       | 335/1500 [00:56<01:40, 11.60it/s, 63 steps of size 9.75e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  22%|██▏       | 337/1500 [00:56<01:31, 12.67it/s, 63 steps of size 1.25e-01. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  23%|██▎       | 339/1500 [00:56<01:32, 12.54it/s, 63 steps of size 8.90e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  23%|██▎       | 341/1500 [00:56<01:33, 12.40it/s, 63 steps of size 6.60e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  23%|██▎       | 342/1500 [00:56<01:50, 10.47it/s, 127 steps of size 5.79e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  23%|██▎       | 343/1500 [00:57<02:06,  9.15it/s, 127 steps of size 7.04e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  23%|██▎       | 345/1500 [00:57<01:54, 10.10it/s, 63 steps of size 1.04e-01. acc. prob=0.88] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  23%|██▎       | 347/1500 [00:57<01:47, 10.76it/s, 63 steps of size 9.87e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  23%|██▎       | 349/1500 [00:57<02:21,  8.14it/s, 255 steps of size 3.72e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  23%|██▎       | 350/1500 [00:58<02:30,  7.65it/s, 127 steps of size 4.39e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  23%|██▎       | 351/1500 [00:58<02:38,  7.27it/s, 127 steps of size 5.24e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  23%|██▎       | 352/1500 [00:58<02:46,  6.90it/s, 127 steps of size 2.27e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  24%|██▎       | 353/1500 [00:58<03:47,  5.05it/s, 255 steps of size 2.71e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  24%|██▎       | 354/1500 [00:59<04:27,  4.28it/s, 255 steps of size 3.13e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  24%|██▎       | 355/1500 [00:59<04:07,  4.62it/s, 127 steps of size 3.78e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  24%|██▎       | 356/1500 [00:59<03:51,  4.94it/s, 127 steps of size 4.51e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  24%|██▍       | 357/1500 [00:59<03:39,  5.21it/s, 127 steps of size 5.23e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  24%|██▍       | 358/1500 [00:59<03:31,  5.41it/s, 127 steps of size 6.21e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  24%|██▍       | 359/1500 [00:59<03:24,  5.58it/s, 127 steps of size 7.29e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  24%|██▍       | 361/1500 [01:00<02:54,  6.52it/s, 127 steps of size 2.27e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  24%|██▍       | 362/1500 [01:00<03:43,  5.10it/s, 255 steps of size 2.73e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  24%|██▍       | 363/1500 [01:00<04:21,  4.34it/s, 255 steps of size 3.29e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  24%|██▍       | 364/1500 [01:00<04:03,  4.66it/s, 127 steps of size 3.95e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  24%|██▍       | 365/1500 [01:01<03:34,  5.29it/s, 91 steps of size 4.04e-02. acc. prob=0.88] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  24%|██▍       | 366/1500 [01:01<03:17,  5.73it/s, 104 steps of size 4.57e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  24%|██▍       | 367/1500 [01:01<03:14,  5.82it/s, 127 steps of size 5.43e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  25%|██▍       | 368/1500 [01:01<03:13,  5.86it/s, 127 steps of size 6.20e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  25%|██▍       | 370/1500 [01:01<02:27,  7.68it/s, 63 steps of size 7.00e-02. acc. prob=0.88] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  25%|██▍       | 372/1500 [01:01<02:23,  7.86it/s, 127 steps of size 6.16e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  25%|██▍       | 374/1500 [01:02<02:05,  8.94it/s, 63 steps of size 7.11e-02. acc. prob=0.88] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  25%|██▌       | 376/1500 [01:02<01:48, 10.38it/s, 38 steps of size 8.51e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  25%|██▌       | 378/1500 [01:02<01:42, 10.93it/s, 63 steps of size 1.11e-01. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  25%|██▌       | 380/1500 [01:02<01:53,  9.88it/s, 127 steps of size 6.08e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  25%|██▌       | 382/1500 [01:02<01:46, 10.50it/s, 63 steps of size 3.78e-02. acc. prob=0.88] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  26%|██▌       | 383/1500 [01:02<02:00,  9.28it/s, 127 steps of size 4.32e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  26%|██▌       | 384/1500 [01:03<02:15,  8.21it/s, 127 steps of size 5.05e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  26%|██▌       | 385/1500 [01:03<02:26,  7.59it/s, 127 steps of size 5.57e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  26%|██▌       | 387/1500 [01:03<02:04,  8.94it/s, 63 steps of size 7.27e-02. acc. prob=0.88] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  26%|██▌       | 389/1500 [01:03<01:43, 10.75it/s, 29 steps of size 8.36e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  26%|██▌       | 391/1500 [01:03<01:38, 11.23it/s, 63 steps of size 3.37e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  26%|██▌       | 392/1500 [01:03<01:54,  9.66it/s, 127 steps of size 3.80e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  26%|██▌       | 393/1500 [01:04<02:09,  8.57it/s, 127 steps of size 4.46e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  26%|██▋       | 394/1500 [01:04<02:27,  7.52it/s, 127 steps of size 5.22e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  26%|██▋       | 395/1500 [01:04<02:37,  7.00it/s, 127 steps of size 6.02e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  26%|██▋       | 397/1500 [01:04<02:13,  8.25it/s, 63 steps of size 8.02e-02. acc. prob=0.88] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  27%|██▋       | 399/1500 [01:04<01:57,  9.36it/s, 63 steps of size 9.31e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  27%|██▋       | 401/1500 [01:04<01:47, 10.21it/s, 63 steps of size 6.34e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  27%|██▋       | 403/1500 [01:05<01:56,  9.43it/s, 127 steps of size 6.62e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  27%|██▋       | 405/1500 [01:05<01:52,  9.75it/s, 63 steps of size 8.70e-02. acc. prob=0.88] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  27%|██▋       | 406/1500 [01:05<02:05,  8.70it/s, 63 steps of size 9.88e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  27%|██▋       | 408/1500 [01:05<01:55,  9.48it/s, 63 steps of size 7.52e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  27%|██▋       | 409/1500 [01:05<01:56,  9.33it/s, 63 steps of size 8.79e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  27%|██▋       | 410/1500 [01:05<01:56,  9.33it/s, 63 steps of size 9.98e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  27%|██▋       | 412/1500 [01:06<02:04,  8.71it/s, 127 steps of size 4.48e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  28%|██▊       | 413/1500 [01:06<02:16,  7.96it/s, 127 steps of size 5.21e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  28%|██▊       | 414/1500 [01:06<02:26,  7.42it/s, 127 steps of size 5.64e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  28%|██▊       | 416/1500 [01:06<02:00,  9.03it/s, 63 steps of size 7.24e-02. acc. prob=0.88] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  28%|██▊       | 418/1500 [01:06<01:48, 10.00it/s, 63 steps of size 9.69e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  28%|██▊       | 420/1500 [01:07<01:41, 10.67it/s, 63 steps of size 1.13e-01. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  28%|██▊       | 422/1500 [01:07<01:36, 11.14it/s, 63 steps of size 1.00e-01. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  28%|██▊       | 424/1500 [01:07<01:33, 11.48it/s, 63 steps of size 4.49e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  28%|██▊       | 425/1500 [01:07<01:49,  9.84it/s, 127 steps of size 5.19e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  28%|██▊       | 426/1500 [01:07<02:03,  8.71it/s, 127 steps of size 5.72e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  29%|██▊       | 428/1500 [01:07<02:06,  8.48it/s, 127 steps of size 6.17e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  29%|██▊       | 429/1500 [01:08<02:16,  7.84it/s, 127 steps of size 2.54e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  29%|██▊       | 430/1500 [01:08<03:09,  5.65it/s, 255 steps of size 2.95e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  29%|██▊       | 431/1500 [01:08<03:49,  4.67it/s, 255 steps of size 3.38e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  29%|██▉       | 432/1500 [01:09<04:20,  4.10it/s, 255 steps of size 3.89e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  29%|██▉       | 433/1500 [01:09<03:56,  4.51it/s, 127 steps of size 3.78e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  29%|██▉       | 434/1500 [01:09<03:38,  4.87it/s, 127 steps of size 4.32e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  29%|██▉       | 435/1500 [01:09<03:26,  5.17it/s, 127 steps of size 4.96e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  29%|██▉       | 437/1500 [01:09<02:51,  6.19it/s, 127 steps of size 6.46e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  29%|██▉       | 438/1500 [01:09<02:52,  6.16it/s, 127 steps of size 5.87e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  29%|██▉       | 440/1500 [01:10<02:16,  7.74it/s, 63 steps of size 7.34e-02. acc. prob=0.88] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  29%|██▉       | 442/1500 [01:10<02:13,  7.91it/s, 127 steps of size 4.72e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  30%|██▉       | 443/1500 [01:10<02:27,  7.15it/s, 127 steps of size 5.34e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  30%|██▉       | 444/1500 [01:10<02:36,  6.77it/s, 127 steps of size 5.56e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  30%|██▉       | 445/1500 [01:10<02:40,  6.58it/s, 127 steps of size 6.40e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  30%|██▉       | 447/1500 [01:11<02:10,  8.10it/s, 63 steps of size 7.98e-02. acc. prob=0.88] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  30%|██▉       | 449/1500 [01:11<01:53,  9.27it/s, 63 steps of size 7.05e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  30%|███       | 451/1500 [01:11<01:43, 10.13it/s, 63 steps of size 7.74e-01. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  30%|███       | 454/1500 [01:11<01:35, 10.91it/s, 127 steps of size 5.97e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  30%|███       | 455/1500 [01:11<01:48,  9.63it/s, 127 steps of size 7.06e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  30%|███       | 457/1500 [01:11<01:40, 10.35it/s, 63 steps of size 1.01e-01. acc. prob=0.88] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  31%|███       | 459/1500 [01:12<01:36, 10.79it/s, 63 steps of size 1.19e-01. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  31%|███       | 461/1500 [01:12<01:26, 12.01it/s, 63 steps of size 8.34e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  31%|███       | 463/1500 [01:12<01:26, 12.04it/s, 63 steps of size 5.31e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  31%|███       | 465/1500 [01:12<01:25, 12.07it/s, 63 steps of size 9.50e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  31%|███       | 467/1500 [01:12<01:18, 13.09it/s, 31 steps of size 7.89e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  31%|███▏      | 469/1500 [01:12<01:20, 12.85it/s, 63 steps of size 7.53e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  31%|███▏      | 471/1500 [01:13<01:21, 12.67it/s, 63 steps of size 1.22e-01. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  32%|███▏      | 473/1500 [01:13<01:58,  8.66it/s, 255 steps of size 2.23e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  32%|███▏      | 474/1500 [01:13<02:37,  6.53it/s, 255 steps of size 2.99e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  32%|███▏      | 475/1500 [01:13<02:39,  6.44it/s, 127 steps of size 4.02e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  32%|███▏      | 476/1500 [01:14<02:40,  6.37it/s, 127 steps of size 5.18e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  32%|███▏      | 477/1500 [01:14<02:42,  6.31it/s, 127 steps of size 6.91e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  32%|███▏      | 479/1500 [01:14<02:11,  7.77it/s, 63 steps of size 9.78e-02. acc. prob=0.88] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  32%|███▏      | 481/1500 [01:14<01:46,  9.61it/s, 63 steps of size 1.19e-01. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  32%|███▏      | 484/1500 [01:14<01:21, 12.42it/s, 63 steps of size 1.08e-01. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  32%|███▏      | 486/1500 [01:14<01:22, 12.35it/s, 63 steps of size 4.35e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  32%|███▏      | 487/1500 [01:15<01:36, 10.48it/s, 127 steps of size 5.66e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  33%|███▎      | 488/1500 [01:15<01:50,  9.18it/s, 127 steps of size 5.49e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  33%|███▎      | 490/1500 [01:15<01:39, 10.11it/s, 63 steps of size 7.10e-02. acc. prob=0.88] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  33%|███▎      | 492/1500 [01:15<01:33, 10.76it/s, 63 steps of size 9.88e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  33%|███▎      | 494/1500 [01:15<01:29, 11.22it/s, 63 steps of size 1.30e-01. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  33%|███▎      | 496/1500 [01:16<02:06,  7.91it/s, 255 steps of size 3.48e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  33%|███▎      | 497/1500 [01:16<02:13,  7.50it/s, 127 steps of size 4.19e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  33%|███▎      | 498/1500 [01:16<02:19,  7.16it/s, 127 steps of size 4.97e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  33%|███▎      | 499/1500 [01:16<02:25,  6.89it/s, 127 steps of size 6.39e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  33%|███▎      | 500/1500 [01:16<02:29,  6.68it/s, 127 steps of size 7.54e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  33%|███▎      | 502/1500 [01:16<02:01,  8.24it/s, 63 steps of size 8.37e-02. acc. prob=0.88] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  34%|███▎      | 504/1500 [01:17<01:38, 10.13it/s, 31 steps of size 1.09e-01. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  34%|███▎      | 506/1500 [01:17<01:24, 11.70it/s, 31 steps of size 1.55e-01. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  34%|███▍      | 508/1500 [01:17<01:30, 11.01it/s, 127 steps of size 5.60e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  34%|███▍      | 509/1500 [01:17<01:43,  9.54it/s, 127 steps of size 6.20e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  34%|███▍      | 511/1500 [01:17<01:35, 10.36it/s, 63 steps of size 5.19e-02. acc. prob=0.88] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  34%|███▍      | 512/1500 [01:17<01:48,  9.09it/s, 127 steps of size 6.26e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  34%|███▍      | 514/1500 [01:18<01:38, 10.05it/s, 63 steps of size 9.81e-02. acc. prob=0.88] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  34%|███▍      | 516/1500 [01:18<01:45,  9.32it/s, 127 steps of size 7.54e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  35%|███▍      | 518/1500 [01:18<01:36, 10.13it/s, 63 steps of size 1.00e-01. acc. prob=0.88] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  35%|███▍      | 520/1500 [01:18<01:44,  9.41it/s, 127 steps of size 5.70e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  35%|███▍      | 522/1500 [01:18<01:36, 10.16it/s, 63 steps of size 8.24e-02. acc. prob=0.88] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  35%|███▍      | 524/1500 [01:19<01:31, 10.71it/s, 63 steps of size 1.19e-01. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  35%|███▌      | 526/1500 [01:19<01:21, 11.98it/s, 63 steps of size 8.72e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  35%|███▌      | 528/1500 [01:19<01:20, 12.09it/s, 63 steps of size 5.76e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  35%|███▌      | 529/1500 [01:19<01:34, 10.29it/s, 127 steps of size 7.04e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  35%|███▌      | 531/1500 [01:19<01:28, 10.90it/s, 63 steps of size 8.12e-02. acc. prob=0.88] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  36%|███▌      | 533/1500 [01:19<01:24, 11.40it/s, 59 steps of size 7.98e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  36%|███▌      | 535/1500 [01:19<01:22, 11.67it/s, 63 steps of size 8.47e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  36%|███▌      | 537/1500 [01:20<01:33, 10.30it/s, 127 steps of size 7.78e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  36%|███▌      | 539/1500 [01:20<01:28, 10.85it/s, 63 steps of size 6.76e-02. acc. prob=0.88] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  36%|███▌      | 541/1500 [01:20<01:25, 11.27it/s, 63 steps of size 8.48e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  36%|███▌      | 543/1500 [01:20<01:22, 11.57it/s, 63 steps of size 9.68e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  36%|███▋      | 545/1500 [01:20<01:21, 11.79it/s, 63 steps of size 1.20e-01. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  36%|███▋      | 547/1500 [01:20<01:12, 13.22it/s, 53 steps of size 9.27e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  37%|███▋      | 549/1500 [01:21<01:13, 12.93it/s, 63 steps of size 6.58e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  37%|███▋      | 551/1500 [01:21<01:14, 12.75it/s, 63 steps of size 7.59e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  37%|███▋      | 553/1500 [01:21<01:50,  8.59it/s, 255 steps of size 1.95e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  37%|███▋      | 554/1500 [01:22<02:25,  6.49it/s, 255 steps of size 2.29e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  37%|███▋      | 555/1500 [01:22<02:58,  5.28it/s, 255 steps of size 2.78e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  37%|███▋      | 556/1500 [01:22<02:53,  5.45it/s, 127 steps of size 3.36e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  37%|███▋      | 557/1500 [01:22<02:48,  5.60it/s, 127 steps of size 4.00e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  37%|███▋      | 558/1500 [01:22<02:44,  5.71it/s, 127 steps of size 4.71e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  37%|███▋      | 559/1500 [01:22<02:42,  5.81it/s, 127 steps of size 5.58e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  37%|███▋      | 561/1500 [01:23<02:06,  7.43it/s, 70 steps of size 7.26e-02. acc. prob=0.89] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  38%|███▊      | 563/1500 [01:23<01:47,  8.76it/s, 63 steps of size 5.67e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  38%|███▊      | 564/1500 [01:23<01:56,  8.01it/s, 127 steps of size 6.70e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  38%|███▊      | 566/1500 [01:23<01:41,  9.24it/s, 63 steps of size 8.25e-02. acc. prob=0.89] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  38%|███▊      | 568/1500 [01:23<01:32, 10.13it/s, 63 steps of size 9.80e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  38%|███▊      | 570/1500 [01:23<01:26, 10.76it/s, 63 steps of size 8.76e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  38%|███▊      | 572/1500 [01:24<01:22, 11.21it/s, 63 steps of size 7.07e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  38%|███▊      | 574/1500 [01:24<01:20, 11.53it/s, 63 steps of size 7.79e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  38%|███▊      | 576/1500 [01:24<01:18, 11.76it/s, 63 steps of size 7.81e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  39%|███▊      | 578/1500 [01:24<01:17, 11.93it/s, 63 steps of size 1.03e-01. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  39%|███▊      | 580/1500 [01:24<01:16, 12.04it/s, 63 steps of size 7.67e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  39%|███▉      | 582/1500 [01:24<01:15, 12.11it/s, 63 steps of size 9.22e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  39%|███▉      | 584/1500 [01:25<01:15, 12.18it/s, 63 steps of size 9.50e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  39%|███▉      | 586/1500 [01:25<01:14, 12.23it/s, 63 steps of size 9.24e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  39%|███▉      | 588/1500 [01:25<01:14, 12.25it/s, 63 steps of size 3.62e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  39%|███▉      | 589/1500 [01:25<01:27, 10.40it/s, 127 steps of size 4.11e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  39%|███▉      | 590/1500 [01:25<01:39,  9.11it/s, 127 steps of size 4.82e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  39%|███▉      | 591/1500 [01:25<01:51,  8.19it/s, 127 steps of size 5.61e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  40%|███▉      | 593/1500 [01:26<01:36,  9.41it/s, 63 steps of size 7.15e-02. acc. prob=0.89] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  40%|███▉      | 595/1500 [01:26<01:28, 10.27it/s, 63 steps of size 5.46e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  40%|███▉      | 596/1500 [01:26<01:40,  9.02it/s, 127 steps of size 5.26e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  40%|███▉      | 597/1500 [01:26<01:51,  8.13it/s, 127 steps of size 6.16e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  40%|███▉      | 598/1500 [01:26<02:00,  7.51it/s, 127 steps of size 7.23e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  40%|████      | 600/1500 [01:26<01:41,  8.89it/s, 63 steps of size 9.57e-02. acc. prob=0.89] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  40%|████      | 602/1500 [01:27<01:31,  9.86it/s, 63 steps of size 8.62e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  40%|████      | 604/1500 [01:27<01:25, 10.53it/s, 63 steps of size 5.03e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  40%|████      | 605/1500 [01:27<01:37,  9.20it/s, 127 steps of size 5.22e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  40%|████      | 607/1500 [01:27<01:41,  8.80it/s, 127 steps of size 6.87e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  41%|████      | 610/1500 [01:27<01:19, 11.14it/s, 63 steps of size 5.96e-02. acc. prob=0.89] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  41%|████      | 612/1500 [01:28<01:43,  8.58it/s, 255 steps of size 3.25e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  41%|████      | 613/1500 [01:28<01:51,  7.99it/s, 127 steps of size 3.59e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  41%|████      | 614/1500 [01:28<01:58,  7.47it/s, 127 steps of size 4.03e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  41%|████      | 615/1500 [01:28<02:04,  7.11it/s, 127 steps of size 4.52e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  41%|████      | 616/1500 [01:28<02:09,  6.81it/s, 127 steps of size 4.77e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  41%|████      | 617/1500 [01:29<02:13,  6.59it/s, 127 steps of size 5.55e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  41%|████      | 618/1500 [01:29<02:16,  6.45it/s, 127 steps of size 6.29e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  41%|████▏     | 620/1500 [01:29<01:51,  7.86it/s, 127 steps of size 3.69e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  41%|████▏     | 621/1500 [01:29<01:59,  7.38it/s, 127 steps of size 4.26e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  41%|████▏     | 622/1500 [01:29<02:05,  7.02it/s, 127 steps of size 4.92e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  42%|████▏     | 623/1500 [01:29<02:09,  6.75it/s, 127 steps of size 5.63e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  42%|████▏     | 624/1500 [01:30<02:13,  6.56it/s, 127 steps of size 6.21e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  42%|████▏     | 625/1500 [01:30<02:16,  6.43it/s, 127 steps of size 7.16e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  42%|████▏     | 627/1500 [01:30<01:46,  8.16it/s, 63 steps of size 7.94e-02. acc. prob=0.89] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  42%|████▏     | 629/1500 [01:30<01:32,  9.40it/s, 63 steps of size 8.88e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  42%|████▏     | 631/1500 [01:30<01:24, 10.27it/s, 63 steps of size 5.53e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  42%|████▏     | 633/1500 [01:30<01:31,  9.46it/s, 127 steps of size 7.25e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  42%|████▏     | 635/1500 [01:31<01:24, 10.24it/s, 63 steps of size 9.27e-02. acc. prob=0.89] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  42%|████▏     | 637/1500 [01:31<01:19, 10.81it/s, 63 steps of size 1.09e-01. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  43%|████▎     | 639/1500 [01:31<01:16, 11.23it/s, 63 steps of size 5.66e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  43%|████▎     | 641/1500 [01:31<01:14, 11.54it/s, 63 steps of size 4.82e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  43%|████▎     | 642/1500 [01:31<01:26,  9.95it/s, 127 steps of size 5.38e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  43%|████▎     | 643/1500 [01:31<01:37,  8.81it/s, 127 steps of size 5.80e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  43%|████▎     | 644/1500 [01:32<01:47,  7.98it/s, 127 steps of size 6.57e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  43%|████▎     | 646/1500 [01:32<01:29,  9.56it/s, 63 steps of size 7.49e-02. acc. prob=0.89] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  43%|████▎     | 648/1500 [01:32<01:21, 10.39it/s, 63 steps of size 7.69e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  43%|████▎     | 650/1500 [01:32<01:29,  9.51it/s, 127 steps of size 6.60e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  43%|████▎     | 652/1500 [01:32<01:22, 10.28it/s, 63 steps of size 6.78e-02. acc. prob=0.89] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  44%|████▎     | 654/1500 [01:33<01:29,  9.50it/s, 127 steps of size 4.13e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  44%|████▎     | 655/1500 [01:33<01:38,  8.61it/s, 127 steps of size 4.70e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  44%|████▍     | 658/1500 [01:33<01:27,  9.67it/s, 127 steps of size 5.35e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  44%|████▍     | 659/1500 [01:33<01:35,  8.78it/s, 127 steps of size 5.87e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  44%|████▍     | 661/1500 [01:33<01:26,  9.70it/s, 63 steps of size 7.21e-02. acc. prob=0.89] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  44%|████▍     | 663/1500 [01:33<01:20, 10.41it/s, 63 steps of size 7.99e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  44%|████▍     | 665/1500 [01:34<01:16, 10.94it/s, 63 steps of size 8.74e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  44%|████▍     | 667/1500 [01:34<01:13, 11.33it/s, 63 steps of size 8.58e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  45%|████▍     | 669/1500 [01:34<01:11, 11.61it/s, 63 steps of size 7.28e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  45%|████▍     | 671/1500 [01:34<01:10, 11.82it/s, 63 steps of size 9.00e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  45%|████▍     | 673/1500 [01:34<01:09, 11.96it/s, 63 steps of size 1.16e-01. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  45%|████▌     | 676/1500 [01:34<00:54, 15.04it/s, 31 steps of size 1.16e-01. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  45%|████▌     | 678/1500 [01:34<00:53, 15.41it/s, 63 steps of size 9.23e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  45%|████▌     | 680/1500 [01:35<00:57, 14.34it/s, 63 steps of size 7.28e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  45%|████▌     | 682/1500 [01:35<00:59, 13.68it/s, 63 steps of size 9.31e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  46%|████▌     | 684/1500 [01:35<00:56, 14.39it/s, 31 steps of size 1.01e-01. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  46%|████▌     | 686/1500 [01:35<00:59, 13.71it/s, 63 steps of size 1.04e-01. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  46%|████▌     | 688/1500 [01:35<01:01, 13.26it/s, 63 steps of size 5.35e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  46%|████▌     | 690/1500 [01:35<01:02, 12.97it/s, 63 steps of size 6.84e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  46%|████▌     | 692/1500 [01:36<01:03, 12.77it/s, 63 steps of size 8.26e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  46%|████▋     | 694/1500 [01:36<01:03, 12.63it/s, 63 steps of size 9.28e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  46%|████▋     | 696/1500 [01:36<01:04, 12.52it/s, 63 steps of size 9.76e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  47%|████▋     | 699/1500 [01:36<00:53, 15.11it/s, 31 steps of size 7.96e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  47%|████▋     | 701/1500 [01:36<00:56, 14.25it/s, 63 steps of size 9.16e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  47%|████▋     | 703/1500 [01:36<00:58, 13.65it/s, 63 steps of size 1.12e-01. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  47%|████▋     | 705/1500 [01:36<00:55, 14.35it/s, 31 steps of size 1.21e-01. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  47%|████▋     | 707/1500 [01:37<00:53, 14.87it/s, 63 steps of size 1.15e-01. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  47%|████▋     | 709/1500 [01:37<00:51, 15.29it/s, 31 steps of size 1.04e-01. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  47%|████▋     | 711/1500 [01:37<00:55, 14.28it/s, 63 steps of size 7.34e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  47%|████▋     | 712/1500 [01:37<01:08, 11.59it/s, 127 steps of size 7.90e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  48%|████▊     | 714/1500 [01:37<01:06, 11.82it/s, 63 steps of size 9.80e-02. acc. prob=0.89] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  48%|████▊     | 716/1500 [01:37<01:05, 11.96it/s, 63 steps of size 8.02e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  48%|████▊     | 718/1500 [01:38<01:04, 12.07it/s, 63 steps of size 9.48e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  48%|████▊     | 720/1500 [01:38<01:04, 12.13it/s, 63 steps of size 1.08e-01. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  48%|████▊     | 722/1500 [01:38<01:13, 10.56it/s, 127 steps of size 3.75e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  48%|████▊     | 723/1500 [01:38<01:23,  9.34it/s, 127 steps of size 4.20e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  48%|████▊     | 724/1500 [01:38<01:32,  8.43it/s, 127 steps of size 4.64e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  48%|████▊     | 725/1500 [01:38<01:39,  7.76it/s, 127 steps of size 5.18e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  48%|████▊     | 727/1500 [01:39<01:25,  9.08it/s, 63 steps of size 6.49e-02. acc. prob=0.89] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  49%|████▊     | 729/1500 [01:39<01:12, 10.60it/s, 63 steps of size 7.51e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  49%|████▊     | 731/1500 [01:39<01:09, 11.12it/s, 63 steps of size 9.50e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  49%|████▉     | 733/1500 [01:39<01:06, 11.49it/s, 63 steps of size 1.08e-01. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  49%|████▉     | 735/1500 [01:39<01:00, 12.71it/s, 63 steps of size 1.04e-01. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  49%|████▉     | 737/1500 [01:39<00:55, 13.68it/s, 31 steps of size 1.16e-01. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  49%|████▉     | 739/1500 [01:39<00:52, 14.43it/s, 31 steps of size 1.24e-01. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  49%|████▉     | 742/1500 [01:40<00:43, 17.27it/s, 31 steps of size 6.17e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  50%|████▉     | 744/1500 [01:40<00:48, 15.69it/s, 59 steps of size 6.98e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  50%|████▉     | 746/1500 [01:40<00:51, 14.53it/s, 63 steps of size 8.00e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  50%|████▉     | 748/1500 [01:40<00:54, 13.80it/s, 63 steps of size 6.81e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  50%|█████     | 750/1500 [01:40<00:56, 13.22it/s, 63 steps of size 8.26e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  50%|█████     | 752/1500 [01:40<00:58, 12.86it/s, 63 steps of size 6.56e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  50%|█████     | 754/1500 [01:41<00:58, 12.67it/s, 63 steps of size 7.28e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  50%|█████     | 756/1500 [01:41<00:59, 12.57it/s, 63 steps of size 7.98e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  51%|█████     | 758/1500 [01:41<00:59, 12.49it/s, 63 steps of size 8.44e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  51%|█████     | 760/1500 [01:41<00:59, 12.44it/s, 63 steps of size 7.58e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  51%|█████     | 762/1500 [01:41<00:59, 12.40it/s, 63 steps of size 8.42e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  51%|█████     | 764/1500 [01:41<00:59, 12.35it/s, 63 steps of size 9.44e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  51%|█████     | 766/1500 [01:42<00:59, 12.33it/s, 63 steps of size 7.70e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  51%|█████     | 768/1500 [01:42<00:59, 12.33it/s, 63 steps of size 7.37e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  51%|█████▏    | 770/1500 [01:42<00:59, 12.32it/s, 63 steps of size 6.99e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  51%|█████▏    | 772/1500 [01:42<00:59, 12.31it/s, 63 steps of size 6.47e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  52%|█████▏    | 773/1500 [01:42<01:09, 10.45it/s, 127 steps of size 4.69e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  52%|█████▏    | 774/1500 [01:42<01:19,  9.15it/s, 127 steps of size 5.25e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  52%|█████▏    | 775/1500 [01:42<01:28,  8.24it/s, 127 steps of size 4.51e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  52%|█████▏    | 776/1500 [01:43<01:35,  7.59it/s, 127 steps of size 4.69e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  52%|█████▏    | 778/1500 [01:43<01:32,  7.79it/s, 127 steps of size 4.39e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  52%|█████▏    | 779/1500 [01:43<01:38,  7.30it/s, 127 steps of size 4.90e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  52%|█████▏    | 780/1500 [01:43<01:43,  6.94it/s, 127 steps of size 5.44e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  52%|█████▏    | 781/1500 [01:43<01:47,  6.68it/s, 127 steps of size 6.04e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  52%|█████▏    | 783/1500 [01:44<01:40,  7.13it/s, 127 steps of size 5.03e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  52%|█████▏    | 784/1500 [01:44<01:44,  6.84it/s, 127 steps of size 5.57e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  52%|█████▏    | 786/1500 [01:44<01:26,  8.28it/s, 63 steps of size 6.72e-02. acc. prob=0.89] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  53%|█████▎    | 788/1500 [01:44<01:15,  9.39it/s, 63 steps of size 7.61e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  53%|█████▎    | 790/1500 [01:44<01:09, 10.21it/s, 63 steps of size 8.51e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  53%|█████▎    | 792/1500 [01:44<01:05, 10.80it/s, 63 steps of size 1.02e-01. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  53%|█████▎    | 794/1500 [01:45<01:02, 11.24it/s, 63 steps of size 8.97e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  53%|█████▎    | 796/1500 [01:45<01:00, 11.55it/s, 63 steps of size 1.10e-01. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  53%|█████▎    | 799/1500 [01:45<00:47, 14.72it/s, 31 steps of size 1.11e-01. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  53%|█████▎    | 801/1500 [01:45<00:46, 15.17it/s, 63 steps of size 1.09e-01. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  54%|█████▎    | 803/1500 [01:45<00:48, 14.23it/s, 63 steps of size 1.02e-01. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  54%|█████▎    | 805/1500 [01:45<00:51, 13.61it/s, 63 steps of size 8.49e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  54%|█████▍    | 807/1500 [01:46<00:52, 13.20it/s, 63 steps of size 8.77e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  54%|█████▍    | 809/1500 [01:46<00:53, 12.95it/s, 63 steps of size 7.16e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  54%|█████▍    | 811/1500 [01:46<00:54, 12.75it/s, 63 steps of size 5.33e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  54%|█████▍    | 812/1500 [01:46<01:04, 10.72it/s, 127 steps of size 5.65e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  54%|█████▍    | 813/1500 [01:46<01:13,  9.32it/s, 127 steps of size 5.16e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  54%|█████▍    | 815/1500 [01:46<01:17,  8.87it/s, 127 steps of size 4.02e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  54%|█████▍    | 816/1500 [01:47<01:24,  8.12it/s, 127 steps of size 4.43e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  54%|█████▍    | 817/1500 [01:47<01:30,  7.55it/s, 127 steps of size 4.86e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  55%|█████▍    | 818/1500 [01:47<01:35,  7.14it/s, 127 steps of size 5.24e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  55%|█████▍    | 819/1500 [01:47<01:39,  6.84it/s, 127 steps of size 4.95e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  55%|█████▍    | 820/1500 [01:47<01:42,  6.63it/s, 127 steps of size 5.15e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  55%|█████▍    | 821/1500 [01:47<01:44,  6.48it/s, 127 steps of size 5.61e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  55%|█████▍    | 822/1500 [01:48<01:46,  6.37it/s, 127 steps of size 6.14e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  55%|█████▍    | 824/1500 [01:48<01:23,  8.11it/s, 63 steps of size 7.07e-02. acc. prob=0.89] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  55%|█████▌    | 826/1500 [01:48<01:23,  8.09it/s, 127 steps of size 5.34e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  55%|█████▌    | 827/1500 [01:48<01:29,  7.53it/s, 127 steps of size 4.94e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  55%|█████▌    | 828/1500 [01:48<01:34,  7.11it/s, 127 steps of size 3.13e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  55%|█████▌    | 829/1500 [01:49<02:06,  5.32it/s, 255 steps of size 3.47e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  55%|█████▌    | 830/1500 [01:49<02:01,  5.51it/s, 127 steps of size 3.84e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  55%|█████▌    | 831/1500 [01:49<01:58,  5.66it/s, 127 steps of size 4.24e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  55%|█████▌    | 832/1500 [01:49<01:55,  5.78it/s, 127 steps of size 4.70e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  56%|█████▌    | 833/1500 [01:49<01:53,  5.88it/s, 127 steps of size 4.87e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  56%|█████▌    | 835/1500 [01:49<01:26,  7.69it/s, 63 steps of size 5.72e-02. acc. prob=0.89] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  56%|█████▌    | 837/1500 [01:50<01:13,  9.00it/s, 63 steps of size 6.16e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  56%|█████▌    | 839/1500 [01:50<01:06,  9.92it/s, 63 steps of size 7.18e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  56%|█████▌    | 841/1500 [01:50<01:02, 10.60it/s, 63 steps of size 6.68e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  56%|█████▌    | 843/1500 [01:50<00:59, 11.11it/s, 63 steps of size 7.75e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  56%|█████▋    | 845/1500 [01:50<00:57, 11.47it/s, 63 steps of size 7.24e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  56%|█████▋    | 847/1500 [01:50<00:55, 11.71it/s, 63 steps of size 8.44e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  57%|█████▋    | 849/1500 [01:51<00:54, 11.89it/s, 63 steps of size 8.43e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  57%|█████▋    | 851/1500 [01:51<00:54, 12.02it/s, 63 steps of size 7.64e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  57%|█████▋    | 853/1500 [01:51<00:53, 12.10it/s, 63 steps of size 6.75e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  57%|█████▋    | 855/1500 [01:51<00:52, 12.17it/s, 63 steps of size 6.14e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  57%|█████▋    | 857/1500 [01:51<00:52, 12.21it/s, 63 steps of size 7.05e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  57%|█████▋    | 859/1500 [01:51<00:52, 12.24it/s, 63 steps of size 8.39e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  57%|█████▋    | 861/1500 [01:52<00:52, 12.27it/s, 63 steps of size 9.09e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  58%|█████▊    | 863/1500 [01:52<00:51, 12.28it/s, 63 steps of size 8.50e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  58%|█████▊    | 865/1500 [01:52<00:51, 12.29it/s, 63 steps of size 8.23e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  58%|█████▊    | 867/1500 [01:52<00:51, 12.29it/s, 63 steps of size 9.23e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  58%|█████▊    | 869/1500 [01:52<00:59, 10.67it/s, 127 steps of size 5.70e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  58%|█████▊    | 871/1500 [01:52<00:56, 11.11it/s, 63 steps of size 6.53e-02. acc. prob=0.89] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  58%|█████▊    | 873/1500 [01:53<01:02, 10.02it/s, 127 steps of size 7.56e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  58%|█████▊    | 875/1500 [01:53<00:58, 10.59it/s, 63 steps of size 8.47e-02. acc. prob=0.89] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  58%|█████▊    | 877/1500 [01:53<00:56, 11.04it/s, 63 steps of size 7.11e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  59%|█████▊    | 879/1500 [01:53<00:54, 11.38it/s, 63 steps of size 8.18e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  59%|█████▊    | 881/1500 [01:53<00:53, 11.64it/s, 63 steps of size 7.12e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  59%|█████▉    | 883/1500 [01:54<00:52, 11.84it/s, 63 steps of size 5.46e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  59%|█████▉    | 884/1500 [01:54<01:00, 10.17it/s, 127 steps of size 5.92e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  59%|█████▉    | 886/1500 [01:54<00:56, 10.80it/s, 63 steps of size 6.34e-02. acc. prob=0.89] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  59%|█████▉    | 888/1500 [01:54<00:54, 11.24it/s, 63 steps of size 7.04e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  59%|█████▉    | 890/1500 [01:54<00:52, 11.56it/s, 63 steps of size 6.59e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  59%|█████▉    | 892/1500 [01:54<00:51, 11.78it/s, 63 steps of size 6.46e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  60%|█████▉    | 894/1500 [01:55<00:50, 11.93it/s, 63 steps of size 7.50e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  60%|█████▉    | 896/1500 [01:55<00:50, 12.05it/s, 63 steps of size 8.76e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  60%|█████▉    | 899/1500 [01:55<00:44, 13.52it/s, 63 steps of size 1.01e-01. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  60%|██████    | 900/1500 [01:55<00:52, 11.34it/s, 127 steps of size 9.66e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  60%|██████    | 902/1500 [01:55<00:47, 12.56it/s, 31 steps of size 9.63e-02. acc. prob=0.89] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  60%|██████    | 904/1500 [01:55<00:44, 13.54it/s, 31 steps of size 1.03e-01. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  60%|██████    | 906/1500 [01:56<00:52, 11.27it/s, 127 steps of size 6.16e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  61%|██████    | 908/1500 [01:56<00:51, 11.56it/s, 63 steps of size 6.67e-02. acc. prob=0.89] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  61%|██████    | 910/1500 [01:56<00:50, 11.77it/s, 63 steps of size 7.38e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  61%|██████    | 912/1500 [01:56<00:49, 11.85it/s, 63 steps of size 8.63e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  61%|██████    | 914/1500 [01:56<00:48, 11.98it/s, 63 steps of size 1.00e-01. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  61%|██████    | 916/1500 [01:56<00:48, 12.08it/s, 63 steps of size 8.75e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  61%|██████    | 918/1500 [01:56<00:47, 12.15it/s, 63 steps of size 9.00e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  61%|██████▏   | 920/1500 [01:57<00:47, 12.20it/s, 63 steps of size 8.61e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  61%|██████▏   | 922/1500 [01:57<00:47, 12.24it/s, 63 steps of size 9.51e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  62%|██████▏   | 924/1500 [01:57<00:47, 12.15it/s, 63 steps of size 9.67e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  62%|██████▏   | 926/1500 [01:57<00:48, 11.82it/s, 63 steps of size 9.13e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  62%|██████▏   | 928/1500 [01:57<00:44, 12.91it/s, 63 steps of size 9.39e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  62%|██████▏   | 930/1500 [01:58<00:51, 10.98it/s, 127 steps of size 5.38e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  62%|██████▏   | 931/1500 [01:58<00:59,  9.63it/s, 127 steps of size 5.78e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  62%|██████▏   | 933/1500 [01:58<00:54, 10.38it/s, 63 steps of size 6.50e-02. acc. prob=0.89] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  62%|██████▏   | 935/1500 [01:58<00:51, 10.93it/s, 63 steps of size 7.49e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  62%|██████▏   | 937/1500 [01:58<00:49, 11.33it/s, 63 steps of size 7.23e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  63%|██████▎   | 939/1500 [01:58<00:48, 11.61it/s, 63 steps of size 8.09e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  63%|██████▎   | 941/1500 [01:59<00:47, 11.81it/s, 63 steps of size 6.22e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  63%|██████▎   | 942/1500 [01:59<00:55, 10.13it/s, 127 steps of size 6.28e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  63%|██████▎   | 944/1500 [01:59<00:51, 10.78it/s, 63 steps of size 6.96e-02. acc. prob=0.89] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  63%|██████▎   | 946/1500 [01:59<00:49, 11.24it/s, 63 steps of size 7.92e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  63%|██████▎   | 948/1500 [01:59<00:47, 11.55it/s, 63 steps of size 8.85e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  63%|██████▎   | 950/1500 [01:59<00:46, 11.79it/s, 63 steps of size 9.29e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  64%|██████▎   | 953/1500 [01:59<00:36, 14.87it/s, 31 steps of size 1.22e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  64%|██████▎   | 954/1500 [02:00<01:28,  6.20it/s, 511 steps of size 1.18e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  64%|██████▎   | 955/1500 [02:00<01:44,  5.20it/s, 255 steps of size 1.32e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  64%|██████▎   | 956/1500 [02:01<02:37,  3.45it/s, 511 steps of size 1.58e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  64%|██████▍   | 957/1500 [02:01<02:41,  3.35it/s, 255 steps of size 2.02e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  64%|██████▍   | 958/1500 [02:02<02:45,  3.27it/s, 255 steps of size 2.66e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  64%|██████▍   | 959/1500 [02:02<02:25,  3.72it/s, 127 steps of size 3.58e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  64%|██████▍   | 960/1500 [02:02<02:34,  3.50it/s, 255 steps of size 4.88e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  64%|██████▍   | 961/1500 [02:02<02:15,  3.97it/s, 127 steps of size 5.99e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  64%|██████▍   | 963/1500 [02:03<01:34,  5.68it/s, 63 steps of size 1.13e-01. acc. prob=0.89] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  64%|██████▍   | 965/1500 [02:03<01:14,  7.18it/s, 63 steps of size 7.78e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  64%|██████▍   | 967/1500 [02:03<01:03,  8.43it/s, 63 steps of size 6.04e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  65%|██████▍   | 968/1500 [02:03<01:08,  7.82it/s, 127 steps of size 8.32e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  65%|██████▍   | 970/1500 [02:03<01:06,  7.95it/s, 127 steps of size 7.67e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  65%|██████▍   | 972/1500 [02:03<00:58,  9.05it/s, 63 steps of size 1.20e-01. acc. prob=0.89] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  65%|██████▌   | 975/1500 [02:04<00:45, 11.58it/s, 63 steps of size 4.19e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  65%|██████▌   | 976/1500 [02:04<00:52, 10.07it/s, 127 steps of size 5.65e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  65%|██████▌   | 977/1500 [02:04<00:58,  8.94it/s, 127 steps of size 7.47e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  65%|██████▌   | 979/1500 [02:04<00:52,  9.89it/s, 63 steps of size 7.01e-02. acc. prob=0.89] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  65%|██████▌   | 981/1500 [02:04<00:48, 10.60it/s, 63 steps of size 1.17e-01. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  66%|██████▌   | 983/1500 [02:04<00:46, 11.09it/s, 63 steps of size 8.04e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  66%|██████▌   | 985/1500 [02:05<00:44, 11.46it/s, 63 steps of size 1.01e-01. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  66%|██████▌   | 987/1500 [02:05<00:43, 11.71it/s, 63 steps of size 7.94e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  66%|██████▌   | 989/1500 [02:05<00:42, 11.90it/s, 63 steps of size 1.04e-01. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  66%|██████▌   | 991/1500 [02:05<00:42, 12.02it/s, 63 steps of size 7.94e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  66%|██████▌   | 993/1500 [02:05<00:41, 12.11it/s, 63 steps of size 1.04e-01. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  66%|██████▋   | 995/1500 [02:05<00:41, 12.14it/s, 63 steps of size 1.29e-01. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  67%|██████▋   | 998/1500 [02:06<00:41, 12.13it/s, 127 steps of size 5.70e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  67%|██████▋   | 1000/1500 [02:06<00:46, 10.72it/s, 127 steps of size 7.71e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  67%|██████▋   | 1002/1500 [02:06<00:44, 11.11it/s, 63 steps of size 7.71e-02. acc. prob=0.98] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  67%|██████▋   | 1004/1500 [02:06<00:43, 11.43it/s, 63 steps of size 7.71e-02. acc. prob=0.98]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  67%|██████▋   | 1006/1500 [02:06<00:42, 11.67it/s, 63 steps of size 7.71e-02. acc. prob=0.97]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  67%|██████▋   | 1008/1500 [02:07<00:41, 11.85it/s, 63 steps of size 7.71e-02. acc. prob=0.95]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  67%|██████▋   | 1010/1500 [02:07<00:40, 11.98it/s, 63 steps of size 7.71e-02. acc. prob=0.95]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  67%|██████▋   | 1012/1500 [02:07<00:40, 12.07it/s, 63 steps of size 7.71e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  68%|██████▊   | 1014/1500 [02:07<00:37, 13.04it/s, 63 steps of size 7.71e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  68%|██████▊   | 1016/1500 [02:07<00:37, 12.81it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  68%|██████▊   | 1018/1500 [02:07<00:38, 12.65it/s, 63 steps of size 7.71e-02. acc. prob=0.91]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  68%|██████▊   | 1020/1500 [02:07<00:38, 12.55it/s, 63 steps of size 7.71e-02. acc. prob=0.91]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  68%|██████▊   | 1022/1500 [02:08<00:38, 12.49it/s, 63 steps of size 7.71e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  68%|██████▊   | 1024/1500 [02:08<00:38, 12.43it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  68%|██████▊   | 1026/1500 [02:08<00:38, 12.39it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  69%|██████▊   | 1028/1500 [02:08<00:38, 12.37it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  69%|██████▊   | 1030/1500 [02:08<00:38, 12.35it/s, 63 steps of size 7.71e-02. acc. prob=0.91]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  69%|██████▉   | 1032/1500 [02:08<00:38, 12.30it/s, 63 steps of size 7.71e-02. acc. prob=0.91]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  69%|██████▉   | 1034/1500 [02:09<00:37, 12.30it/s, 63 steps of size 7.71e-02. acc. prob=0.91]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  69%|██████▉   | 1036/1500 [02:09<00:37, 12.30it/s, 63 steps of size 7.71e-02. acc. prob=0.91]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  69%|██████▉   | 1038/1500 [02:09<00:37, 12.30it/s, 63 steps of size 7.71e-02. acc. prob=0.91]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  69%|██████▉   | 1040/1500 [02:09<00:37, 12.30it/s, 63 steps of size 7.71e-02. acc. prob=0.91]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  69%|██████▉   | 1042/1500 [02:09<00:37, 12.29it/s, 63 steps of size 7.71e-02. acc. prob=0.91]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  70%|██████▉   | 1044/1500 [02:09<00:37, 12.29it/s, 63 steps of size 7.71e-02. acc. prob=0.91]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  70%|██████▉   | 1046/1500 [02:10<00:36, 12.30it/s, 63 steps of size 7.71e-02. acc. prob=0.91]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  70%|██████▉   | 1048/1500 [02:10<00:36, 12.30it/s, 63 steps of size 7.71e-02. acc. prob=0.91]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  70%|███████   | 1050/1500 [02:10<00:36, 12.30it/s, 63 steps of size 7.71e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  70%|███████   | 1052/1500 [02:10<00:36, 12.30it/s, 63 steps of size 7.71e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  70%|███████   | 1054/1500 [02:10<00:36, 12.31it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  70%|███████   | 1056/1500 [02:10<00:36, 12.29it/s, 63 steps of size 7.71e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  71%|███████   | 1058/1500 [02:11<00:36, 12.27it/s, 63 steps of size 7.71e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  71%|███████   | 1060/1500 [02:11<00:35, 12.28it/s, 63 steps of size 7.71e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  71%|███████   | 1062/1500 [02:11<00:35, 12.29it/s, 63 steps of size 7.71e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  71%|███████   | 1064/1500 [02:11<00:35, 12.28it/s, 63 steps of size 7.71e-02. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  71%|███████   | 1066/1500 [02:11<00:35, 12.28it/s, 63 steps of size 7.71e-02. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  71%|███████   | 1068/1500 [02:11<00:35, 12.30it/s, 63 steps of size 7.71e-02. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  71%|███████▏  | 1070/1500 [02:12<00:35, 12.26it/s, 63 steps of size 7.71e-02. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  71%|███████▏  | 1072/1500 [02:12<00:34, 12.25it/s, 63 steps of size 7.71e-02. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  72%|███████▏  | 1074/1500 [02:12<00:34, 12.26it/s, 63 steps of size 7.71e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  72%|███████▏  | 1076/1500 [02:12<00:34, 12.26it/s, 63 steps of size 7.71e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  72%|███████▏  | 1078/1500 [02:12<00:34, 12.28it/s, 63 steps of size 7.71e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  72%|███████▏  | 1080/1500 [02:12<00:34, 12.28it/s, 63 steps of size 7.71e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  72%|███████▏  | 1082/1500 [02:13<00:34, 12.27it/s, 63 steps of size 7.71e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  72%|███████▏  | 1084/1500 [02:13<00:33, 12.27it/s, 63 steps of size 7.71e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  72%|███████▏  | 1086/1500 [02:13<00:36, 11.26it/s, 63 steps of size 7.71e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  73%|███████▎  | 1088/1500 [02:13<00:36, 11.18it/s, 63 steps of size 7.71e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  73%|███████▎  | 1090/1500 [02:13<00:35, 11.45it/s, 63 steps of size 7.71e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  73%|███████▎  | 1092/1500 [02:13<00:34, 11.68it/s, 63 steps of size 7.71e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  73%|███████▎  | 1094/1500 [02:14<00:38, 10.57it/s, 63 steps of size 7.71e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  73%|███████▎  | 1096/1500 [02:14<00:40, 10.08it/s, 63 steps of size 7.71e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  73%|███████▎  | 1097/1500 [02:14<00:41,  9.76it/s, 63 steps of size 7.71e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  73%|███████▎  | 1098/1500 [02:14<00:42,  9.48it/s, 63 steps of size 7.71e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  73%|███████▎  | 1100/1500 [02:14<00:42,  9.43it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  73%|███████▎  | 1102/1500 [02:14<00:38, 10.22it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  74%|███████▎  | 1104/1500 [02:15<00:36, 10.80it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  74%|███████▎  | 1106/1500 [02:15<00:35, 11.24it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  74%|███████▍  | 1108/1500 [02:15<00:33, 11.54it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  74%|███████▍  | 1110/1500 [02:15<00:33, 11.75it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  74%|███████▍  | 1112/1500 [02:15<00:32, 11.88it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  74%|███████▍  | 1114/1500 [02:15<00:32, 12.03it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  74%|███████▍  | 1116/1500 [02:16<00:31, 12.14it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  75%|███████▍  | 1118/1500 [02:16<00:31, 12.18it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  75%|███████▍  | 1120/1500 [02:16<00:31, 12.22it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  75%|███████▍  | 1122/1500 [02:16<00:30, 12.24it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  75%|███████▍  | 1124/1500 [02:16<00:30, 12.26it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  75%|███████▌  | 1126/1500 [02:16<00:30, 12.27it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  75%|███████▌  | 1128/1500 [02:17<00:30, 12.29it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  75%|███████▌  | 1130/1500 [02:17<00:30, 12.30it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  75%|███████▌  | 1132/1500 [02:17<00:29, 12.31it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  76%|███████▌  | 1134/1500 [02:17<00:29, 12.30it/s, 63 steps of size 7.71e-02. acc. prob=0.91]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  76%|███████▌  | 1135/1500 [02:17<00:34, 10.43it/s, 127 steps of size 7.71e-02. acc. prob=0.91]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  76%|███████▌  | 1137/1500 [02:17<00:33, 10.99it/s, 63 steps of size 7.71e-02. acc. prob=0.91] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  76%|███████▌  | 1139/1500 [02:18<00:30, 11.98it/s, 42 steps of size 7.71e-02. acc. prob=0.91]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  76%|███████▌  | 1141/1500 [02:18<00:29, 12.09it/s, 63 steps of size 7.71e-02. acc. prob=0.91]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  76%|███████▌  | 1143/1500 [02:18<00:29, 12.15it/s, 63 steps of size 7.71e-02. acc. prob=0.91]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  76%|███████▋  | 1145/1500 [02:18<00:29, 12.20it/s, 63 steps of size 7.71e-02. acc. prob=0.91]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  76%|███████▋  | 1147/1500 [02:18<00:28, 12.23it/s, 63 steps of size 7.71e-02. acc. prob=0.91]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  77%|███████▋  | 1149/1500 [02:18<00:28, 12.23it/s, 63 steps of size 7.71e-02. acc. prob=0.91]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  77%|███████▋  | 1151/1500 [02:19<00:28, 12.24it/s, 63 steps of size 7.71e-02. acc. prob=0.91]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  77%|███████▋  | 1154/1500 [02:19<00:23, 14.82it/s, 29 steps of size 7.71e-02. acc. prob=0.91]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  77%|███████▋  | 1156/1500 [02:19<00:24, 14.04it/s, 63 steps of size 7.71e-02. acc. prob=0.91]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  77%|███████▋  | 1158/1500 [02:19<00:25, 13.49it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  77%|███████▋  | 1160/1500 [02:19<00:25, 13.13it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  77%|███████▋  | 1162/1500 [02:19<00:26, 12.89it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  78%|███████▊  | 1164/1500 [02:19<00:26, 12.71it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  78%|███████▊  | 1166/1500 [02:20<00:26, 12.59it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  78%|███████▊  | 1168/1500 [02:20<00:26, 12.51it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  78%|███████▊  | 1170/1500 [02:20<00:26, 12.44it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  78%|███████▊  | 1172/1500 [02:20<00:26, 12.39it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  78%|███████▊  | 1174/1500 [02:20<00:25, 12.88it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  78%|███████▊  | 1176/1500 [02:20<00:25, 12.69it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  79%|███████▊  | 1178/1500 [02:21<00:24, 13.04it/s, 48 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  79%|███████▊  | 1180/1500 [02:21<00:25, 12.79it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  79%|███████▉  | 1182/1500 [02:21<00:25, 12.60it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  79%|███████▉  | 1184/1500 [02:21<00:25, 12.45it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  79%|███████▉  | 1186/1500 [02:21<00:25, 12.36it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  79%|███████▉  | 1188/1500 [02:21<00:24, 12.57it/s, 53 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  79%|███████▉  | 1190/1500 [02:22<00:25, 12.38it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  79%|███████▉  | 1192/1500 [02:22<00:24, 12.33it/s, 63 steps of size 7.71e-02. acc. prob=0.91]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  80%|███████▉  | 1194/1500 [02:22<00:24, 12.31it/s, 63 steps of size 7.71e-02. acc. prob=0.91]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  80%|███████▉  | 1196/1500 [02:22<00:24, 12.30it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  80%|███████▉  | 1198/1500 [02:22<00:24, 12.31it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  80%|████████  | 1200/1500 [02:22<00:24, 12.31it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  80%|████████  | 1202/1500 [02:23<00:24, 12.31it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  80%|████████  | 1204/1500 [02:23<00:24, 12.32it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  80%|████████  | 1206/1500 [02:23<00:23, 12.31it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  81%|████████  | 1208/1500 [02:23<00:23, 12.26it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  81%|████████  | 1210/1500 [02:23<00:23, 12.19it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  81%|████████  | 1212/1500 [02:23<00:23, 12.06it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  81%|████████  | 1214/1500 [02:24<00:23, 12.03it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  81%|████████  | 1216/1500 [02:24<00:23, 12.03it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  81%|████████  | 1218/1500 [02:24<00:23, 12.03it/s, 63 steps of size 7.71e-02. acc. prob=0.91]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  81%|████████▏ | 1220/1500 [02:24<00:22, 12.27it/s, 57 steps of size 7.71e-02. acc. prob=0.91]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  81%|████████▏ | 1222/1500 [02:24<00:22, 12.27it/s, 63 steps of size 7.71e-02. acc. prob=0.91]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  82%|████████▏ | 1224/1500 [02:24<00:22, 12.28it/s, 63 steps of size 7.71e-02. acc. prob=0.91]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  82%|████████▏ | 1226/1500 [02:24<00:22, 12.25it/s, 63 steps of size 7.71e-02. acc. prob=0.91]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  82%|████████▏ | 1228/1500 [02:25<00:22, 12.27it/s, 63 steps of size 7.71e-02. acc. prob=0.91]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  82%|████████▏ | 1230/1500 [02:25<00:21, 12.28it/s, 63 steps of size 7.71e-02. acc. prob=0.91]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  82%|████████▏ | 1232/1500 [02:25<00:21, 12.27it/s, 63 steps of size 7.71e-02. acc. prob=0.91]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  82%|████████▏ | 1234/1500 [02:25<00:21, 12.28it/s, 63 steps of size 7.71e-02. acc. prob=0.91]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  82%|████████▏ | 1236/1500 [02:25<00:21, 12.29it/s, 63 steps of size 7.71e-02. acc. prob=0.91]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  83%|████████▎ | 1238/1500 [02:25<00:21, 12.29it/s, 63 steps of size 7.71e-02. acc. prob=0.91]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  83%|████████▎ | 1240/1500 [02:26<00:21, 12.15it/s, 63 steps of size 7.71e-02. acc. prob=0.91]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  83%|████████▎ | 1242/1500 [02:26<00:21, 12.10it/s, 63 steps of size 7.71e-02. acc. prob=0.91]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  83%|████████▎ | 1244/1500 [02:26<00:21, 11.76it/s, 63 steps of size 7.71e-02. acc. prob=0.91]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  83%|████████▎ | 1246/1500 [02:26<00:21, 11.88it/s, 63 steps of size 7.71e-02. acc. prob=0.91]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  83%|████████▎ | 1248/1500 [02:26<00:21, 11.99it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  83%|████████▎ | 1250/1500 [02:26<00:21, 11.88it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  83%|████████▎ | 1252/1500 [02:27<00:20, 11.97it/s, 63 steps of size 7.71e-02. acc. prob=0.91]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  84%|████████▎ | 1254/1500 [02:27<00:20, 12.06it/s, 63 steps of size 7.71e-02. acc. prob=0.91]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  84%|████████▎ | 1256/1500 [02:27<00:19, 12.32it/s, 56 steps of size 7.71e-02. acc. prob=0.91]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  84%|████████▍ | 1258/1500 [02:27<00:18, 13.30it/s, 63 steps of size 7.71e-02. acc. prob=0.91]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  84%|████████▍ | 1260/1500 [02:27<00:18, 12.97it/s, 63 steps of size 7.71e-02. acc. prob=0.91]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  84%|████████▍ | 1262/1500 [02:27<00:18, 12.76it/s, 63 steps of size 7.71e-02. acc. prob=0.91]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  84%|████████▍ | 1264/1500 [02:28<00:18, 12.56it/s, 63 steps of size 7.71e-02. acc. prob=0.91]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  84%|████████▍ | 1266/1500 [02:28<00:18, 12.45it/s, 63 steps of size 7.71e-02. acc. prob=0.91]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  85%|████████▍ | 1268/1500 [02:28<00:18, 12.41it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  85%|████████▍ | 1270/1500 [02:28<00:18, 12.37it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  85%|████████▍ | 1272/1500 [02:28<00:18, 12.35it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  85%|████████▍ | 1274/1500 [02:28<00:18, 12.33it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  85%|████████▌ | 1276/1500 [02:29<00:18, 12.32it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  85%|████████▌ | 1278/1500 [02:29<00:18, 12.32it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  85%|████████▌ | 1280/1500 [02:29<00:16, 13.50it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  86%|████████▌ | 1283/1500 [02:29<00:14, 15.01it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  86%|████████▌ | 1285/1500 [02:29<00:15, 14.16it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  86%|████████▌ | 1287/1500 [02:29<00:15, 13.59it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  86%|████████▌ | 1289/1500 [02:29<00:16, 13.18it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  86%|████████▌ | 1291/1500 [02:30<00:16, 12.91it/s, 63 steps of size 7.71e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  86%|████████▌ | 1293/1500 [02:30<00:16, 12.73it/s, 63 steps of size 7.71e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  86%|████████▋ | 1295/1500 [02:30<00:16, 12.59it/s, 63 steps of size 7.71e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  86%|████████▋ | 1297/1500 [02:30<00:15, 13.13it/s, 63 steps of size 7.71e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  87%|████████▋ | 1299/1500 [02:30<00:15, 12.88it/s, 63 steps of size 7.71e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  87%|████████▋ | 1301/1500 [02:30<00:15, 12.70it/s, 63 steps of size 7.71e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  87%|████████▋ | 1303/1500 [02:31<00:15, 12.57it/s, 63 steps of size 7.71e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  87%|████████▋ | 1305/1500 [02:31<00:15, 12.46it/s, 63 steps of size 7.71e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  87%|████████▋ | 1307/1500 [02:31<00:15, 12.41it/s, 63 steps of size 7.71e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  87%|████████▋ | 1309/1500 [02:31<00:15, 12.39it/s, 63 steps of size 7.71e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  87%|████████▋ | 1311/1500 [02:31<00:15, 12.36it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  88%|████████▊ | 1313/1500 [02:31<00:15, 12.40it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  88%|████████▊ | 1315/1500 [02:32<00:14, 12.37it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  88%|████████▊ | 1317/1500 [02:32<00:14, 12.39it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  88%|████████▊ | 1319/1500 [02:32<00:14, 12.36it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  88%|████████▊ | 1321/1500 [02:32<00:14, 12.34it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  88%|████████▊ | 1323/1500 [02:32<00:14, 12.34it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  88%|████████▊ | 1325/1500 [02:32<00:14, 12.33it/s, 63 steps of size 7.71e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  88%|████████▊ | 1327/1500 [02:33<00:14, 12.32it/s, 63 steps of size 7.71e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  89%|████████▊ | 1329/1500 [02:33<00:13, 12.32it/s, 63 steps of size 7.71e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  89%|████████▉ | 1332/1500 [02:33<00:11, 14.06it/s, 63 steps of size 7.71e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  89%|████████▉ | 1334/1500 [02:33<00:12, 13.53it/s, 63 steps of size 7.71e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  89%|████████▉ | 1335/1500 [02:33<00:14, 11.31it/s, 127 steps of size 7.71e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  89%|████████▉ | 1337/1500 [02:33<00:14, 11.60it/s, 63 steps of size 7.71e-02. acc. prob=0.89] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  89%|████████▉ | 1339/1500 [02:34<00:13, 11.82it/s, 63 steps of size 7.71e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  89%|████████▉ | 1341/1500 [02:34<00:13, 11.96it/s, 63 steps of size 7.71e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  90%|████████▉ | 1343/1500 [02:34<00:13, 12.04it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  90%|████████▉ | 1345/1500 [02:34<00:12, 12.11it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  90%|████████▉ | 1347/1500 [02:34<00:12, 12.17it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  90%|████████▉ | 1349/1500 [02:34<00:12, 12.22it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  90%|█████████ | 1351/1500 [02:35<00:12, 12.24it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  90%|█████████ | 1353/1500 [02:35<00:11, 12.26it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  90%|█████████ | 1355/1500 [02:35<00:11, 12.28it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  90%|█████████ | 1357/1500 [02:35<00:11, 12.27it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  91%|█████████ | 1359/1500 [02:35<00:11, 12.29it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  91%|█████████ | 1361/1500 [02:35<00:11, 12.29it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  91%|█████████ | 1363/1500 [02:35<00:11, 12.30it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  91%|█████████ | 1365/1500 [02:36<00:10, 12.30it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  91%|█████████ | 1367/1500 [02:36<00:10, 12.30it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  91%|█████████▏| 1369/1500 [02:36<00:10, 12.30it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  91%|█████████▏| 1371/1500 [02:36<00:10, 12.30it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  92%|█████████▏| 1373/1500 [02:36<00:10, 12.31it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  92%|█████████▏| 1374/1500 [02:36<00:11, 10.99it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  92%|█████████▏| 1376/1500 [02:37<00:10, 11.31it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  92%|█████████▏| 1378/1500 [02:37<00:10, 11.61it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  92%|█████████▏| 1380/1500 [02:37<00:10, 11.77it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  92%|█████████▏| 1382/1500 [02:37<00:09, 11.92it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  92%|█████████▏| 1384/1500 [02:37<00:09, 12.03it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  92%|█████████▏| 1386/1500 [02:37<00:09, 12.11it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  93%|█████████▎| 1388/1500 [02:38<00:09, 12.17it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  93%|█████████▎| 1390/1500 [02:38<00:09, 12.20it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  93%|█████████▎| 1392/1500 [02:38<00:08, 12.23it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  93%|█████████▎| 1394/1500 [02:38<00:08, 12.25it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  93%|█████████▎| 1396/1500 [02:38<00:08, 12.27it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  93%|█████████▎| 1398/1500 [02:38<00:08, 12.28it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  93%|█████████▎| 1400/1500 [02:39<00:08, 12.28it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  93%|█████████▎| 1402/1500 [02:39<00:07, 12.29it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  94%|█████████▎| 1404/1500 [02:39<00:07, 12.29it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  94%|█████████▎| 1406/1500 [02:39<00:07, 12.29it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  94%|█████████▍| 1408/1500 [02:39<00:07, 12.29it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  94%|█████████▍| 1410/1500 [02:39<00:07, 12.30it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  94%|█████████▍| 1412/1500 [02:40<00:07, 12.30it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  94%|█████████▍| 1414/1500 [02:40<00:06, 12.30it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  94%|█████████▍| 1416/1500 [02:40<00:06, 12.31it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  95%|█████████▍| 1418/1500 [02:40<00:06, 12.26it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  95%|█████████▍| 1420/1500 [02:40<00:06, 12.27it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  95%|█████████▍| 1422/1500 [02:40<00:06, 12.29it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  95%|█████████▍| 1424/1500 [02:40<00:06, 12.30it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  95%|█████████▌| 1426/1500 [02:41<00:06, 12.30it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  95%|█████████▌| 1428/1500 [02:41<00:05, 12.30it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  95%|█████████▌| 1430/1500 [02:41<00:05, 12.30it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  95%|█████████▌| 1432/1500 [02:41<00:05, 12.30it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  96%|█████████▌| 1434/1500 [02:41<00:05, 12.30it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  96%|█████████▌| 1436/1500 [02:41<00:05, 12.30it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  96%|█████████▌| 1438/1500 [02:42<00:05, 12.30it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  96%|█████████▌| 1441/1500 [02:42<00:04, 13.95it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  96%|█████████▌| 1443/1500 [02:42<00:04, 13.46it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  96%|█████████▋| 1445/1500 [02:42<00:04, 13.13it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  96%|█████████▋| 1447/1500 [02:42<00:04, 12.88it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  97%|█████████▋| 1449/1500 [02:42<00:04, 12.71it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  97%|█████████▋| 1451/1500 [02:43<00:03, 12.59it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  97%|█████████▋| 1453/1500 [02:43<00:03, 12.50it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  97%|█████████▋| 1455/1500 [02:43<00:03, 12.43it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  97%|█████████▋| 1457/1500 [02:43<00:03, 12.39it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  97%|█████████▋| 1459/1500 [02:43<00:03, 12.37it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  97%|█████████▋| 1461/1500 [02:43<00:03, 12.35it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  98%|█████████▊| 1463/1500 [02:44<00:02, 12.33it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  98%|█████████▊| 1465/1500 [02:44<00:02, 13.09it/s, 37 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  98%|█████████▊| 1467/1500 [02:44<00:02, 12.85it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  98%|█████████▊| 1469/1500 [02:44<00:02, 12.68it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  98%|█████████▊| 1471/1500 [02:44<00:02, 12.57it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  98%|█████████▊| 1473/1500 [02:44<00:02, 12.44it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  98%|█████████▊| 1475/1500 [02:45<00:02, 12.40it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  98%|█████████▊| 1477/1500 [02:45<00:02, 10.72it/s, 127 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  99%|█████████▊| 1479/1500 [02:45<00:01, 11.14it/s, 63 steps of size 7.71e-02. acc. prob=0.90] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  99%|█████████▊| 1481/1500 [02:45<00:01, 11.46it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  99%|█████████▉| 1483/1500 [02:45<00:01, 11.72it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  99%|█████████▉| 1485/1500 [02:45<00:01, 11.89it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  99%|█████████▉| 1487/1500 [02:46<00:01, 12.02it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  99%|█████████▉| 1489/1500 [02:46<00:00, 12.10it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  99%|█████████▉| 1491/1500 [02:46<00:00, 12.18it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample: 100%|█████████▉| 1493/1500 [02:46<00:00, 12.21it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample: 100%|█████████▉| 1495/1500 [02:46<00:00, 12.24it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample: 100%|█████████▉| 1497/1500 [02:46<00:00, 12.44it/s, 57 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample: 100%|█████████▉| 1499/1500 [02:47<00:00, 12.41it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample: 100%|██████████| 1500/1500 [02:47<00:00,  8.97it/s, 63 steps of size 7.71e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "  0%|          | 0/1500 [00:00<?, ?it/s]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   0%|          | 0/1500 [00:12<?, ?it/s, 437 steps of size 1.05e-02. acc. prob=0.76]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   1%|          | 17/1500 [00:12<18:37,  1.33it/s, 511 steps of size 6.37e-03. acc. prob=0.76]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   1%|          | 18/1500 [00:13<18:37,  1.33it/s, 592 steps of size 7.32e-03. acc. prob=0.77]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   1%|▏         | 19/1500 [00:14<17:57,  1.37it/s, 378 steps of size 6.98e-03. acc. prob=0.77]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   1%|▏         | 20/1500 [00:14<17:44,  1.39it/s, 511 steps of size 1.74e-03. acc. prob=0.75]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   1%|▏         | 21/1500 [00:15<17:58,  1.37it/s, 612 steps of size 2.49e-03. acc. prob=0.77]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   1%|▏         | 22/1500 [00:16<20:31,  1.20it/s, 1023 steps of size 3.57e-03. acc. prob=0.78]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   2%|▏         | 23/1500 [00:17<21:08,  1.16it/s, 743 steps of size 4.95e-03. acc. prob=0.79] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   2%|▏         | 24/1500 [00:18<18:23,  1.34it/s, 282 steps of size 5.36e-03. acc. prob=0.79]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   2%|▏         | 25/1500 [00:18<16:04,  1.53it/s, 281 steps of size 7.15e-03. acc. prob=0.80]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   2%|▏         | 27/1500 [00:18<10:24,  2.36it/s, 66 steps of size 1.16e-02. acc. prob=0.81] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   2%|▏         | 29/1500 [00:18<07:05,  3.46it/s, 17 steps of size 8.27e-03. acc. prob=0.81]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   2%|▏         | 31/1500 [00:18<05:04,  4.82it/s, 46 steps of size 9.85e-03. acc. prob=0.82]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   2%|▏         | 36/1500 [00:19<02:33,  9.54it/s, 20 steps of size 1.20e-02. acc. prob=0.83]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   3%|▎         | 41/1500 [00:19<01:42, 14.29it/s, 28 steps of size 4.35e-03. acc. prob=0.82]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   3%|▎         | 42/1500 [00:19<01:54, 12.76it/s, 113 steps of size 5.76e-03. acc. prob=0.83]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   3%|▎         | 44/1500 [00:19<01:51, 13.03it/s, 64 steps of size 8.37e-03. acc. prob=0.83] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   3%|▎         | 45/1500 [00:19<02:02, 11.85it/s, 99 steps of size 9.85e-03. acc. prob=0.84]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   3%|▎         | 46/1500 [00:19<02:12, 10.99it/s, 94 steps of size 1.28e-02. acc. prob=0.84]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   3%|▎         | 47/1500 [00:19<02:28,  9.76it/s, 115 steps of size 1.28e-02. acc. prob=0.84]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   3%|▎         | 49/1500 [00:20<02:36,  9.25it/s, 133 steps of size 1.32e-02. acc. prob=0.84]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   4%|▎         | 54/1500 [00:20<01:29, 16.23it/s, 49 steps of size 5.91e-03. acc. prob=0.84] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   4%|▍         | 60/1500 [00:20<00:58, 24.75it/s, 31 steps of size 4.71e-03. acc. prob=0.84]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   4%|▍         | 63/1500 [00:20<00:58, 24.51it/s, 25 steps of size 7.02e-03. acc. prob=0.85]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   4%|▍         | 67/1500 [00:20<00:55, 26.03it/s, 44 steps of size 9.37e-03. acc. prob=0.85]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   5%|▍         | 69/1500 [00:20<01:10, 20.32it/s, 115 steps of size 6.50e-03. acc. prob=0.85]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   5%|▍         | 73/1500 [00:20<01:00, 23.60it/s, 15 steps of size 8.16e-03. acc. prob=0.85] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   5%|▌         | 75/1500 [00:21<01:31, 15.64it/s, 167 steps of size 1.06e-02. acc. prob=0.86]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   5%|▌         | 77/1500 [00:21<01:49, 13.03it/s, 147 steps of size 1.15e-02. acc. prob=0.86]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   5%|▌         | 79/1500 [00:21<02:22,  9.98it/s, 230 steps of size 1.04e-02. acc. prob=0.86]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   5%|▌         | 81/1500 [00:21<02:21, 10.00it/s, 114 steps of size 1.28e-02. acc. prob=0.86]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   6%|▌         | 83/1500 [00:22<02:10, 10.84it/s, 38 steps of size 9.83e-03. acc. prob=0.86] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   6%|▌         | 86/1500 [00:22<01:41, 13.99it/s, 31 steps of size 7.89e-03. acc. prob=0.86]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   6%|▌         | 88/1500 [00:22<01:48, 13.04it/s, 131 steps of size 9.47e-03. acc. prob=0.86]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   6%|▌         | 89/1500 [00:22<02:04, 11.30it/s, 118 steps of size 1.15e-02. acc. prob=0.86]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   6%|▌         | 90/1500 [00:22<02:11, 10.75it/s, 88 steps of size 1.37e-02. acc. prob=0.86] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   6%|▌         | 92/1500 [00:22<02:36,  8.99it/s, 189 steps of size 1.01e-02. acc. prob=0.86]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   6%|▋         | 94/1500 [00:23<02:41,  8.70it/s, 151 steps of size 1.33e-02. acc. prob=0.86]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   6%|▋         | 95/1500 [00:23<02:47,  8.41it/s, 105 steps of size 1.59e-02. acc. prob=0.86]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   6%|▋         | 96/1500 [00:23<03:01,  7.75it/s, 129 steps of size 1.88e-02. acc. prob=0.86]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   7%|▋         | 98/1500 [00:23<02:51,  8.15it/s, 106 steps of size 1.30e-02. acc. prob=0.86]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   7%|▋         | 100/1500 [00:23<02:32,  9.15it/s, 91 steps of size 1.37e-02. acc. prob=0.86]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   7%|▋         | 101/1500 [00:24<02:36,  8.96it/s, 94 steps of size 1.61e-01. acc. prob=0.86]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   7%|▋         | 103/1500 [00:24<02:29,  9.37it/s, 142 steps of size 2.56e-02. acc. prob=0.86]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   7%|▋         | 104/1500 [00:24<02:32,  9.16it/s, 92 steps of size 2.82e-02. acc. prob=0.86] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   7%|▋         | 105/1500 [00:24<03:01,  7.67it/s, 157 steps of size 2.74e-02. acc. prob=0.86]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   7%|▋         | 107/1500 [00:24<03:06,  7.47it/s, 158 steps of size 1.41e-02. acc. prob=0.86]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   7%|▋         | 108/1500 [00:25<03:35,  6.47it/s, 177 steps of size 1.85e-02. acc. prob=0.86]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   7%|▋         | 110/1500 [00:25<05:20,  4.33it/s, 511 steps of size 2.05e-02. acc. prob=0.86]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   7%|▋         | 111/1500 [00:26<06:36,  3.50it/s, 374 steps of size 2.63e-02. acc. prob=0.86]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   8%|▊         | 113/1500 [00:26<06:56,  3.33it/s, 471 steps of size 2.43e-03. acc. prob=0.86]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   8%|▊         | 114/1500 [00:28<11:58,  1.93it/s, 1023 steps of size 3.34e-03. acc. prob=0.86]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   8%|▊         | 115/1500 [00:29<15:45,  1.46it/s, 946 steps of size 4.65e-03. acc. prob=0.86] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   8%|▊         | 116/1500 [00:30<18:00,  1.28it/s, 835 steps of size 6.38e-03. acc. prob=0.86]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   8%|▊         | 117/1500 [00:31<19:28,  1.18it/s, 798 steps of size 7.21e-03. acc. prob=0.86]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   8%|▊         | 118/1500 [00:32<18:14,  1.26it/s, 503 steps of size 9.91e-03. acc. prob=0.86]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   8%|▊         | 119/1500 [00:32<16:34,  1.39it/s, 417 steps of size 1.33e-02. acc. prob=0.86]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   8%|▊         | 120/1500 [00:32<13:44,  1.67it/s, 227 steps of size 1.77e-02. acc. prob=0.86]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   8%|▊         | 121/1500 [00:33<11:08,  2.06it/s, 162 steps of size 1.80e-02. acc. prob=0.86]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   8%|▊         | 122/1500 [00:33<09:37,  2.39it/s, 203 steps of size 2.06e-02. acc. prob=0.86]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   8%|▊         | 123/1500 [00:33<07:45,  2.96it/s, 112 steps of size 2.61e-02. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   8%|▊         | 125/1500 [00:34<10:13,  2.24it/s, 835 steps of size 6.51e-03. acc. prob=0.86]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   8%|▊         | 126/1500 [00:35<12:44,  1.80it/s, 694 steps of size 8.83e-03. acc. prob=0.86]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   9%|▊         | 128/1500 [00:35<09:07,  2.51it/s, 196 steps of size 1.37e-02. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   9%|▊         | 129/1500 [00:36<08:20,  2.74it/s, 193 steps of size 1.70e-02. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   9%|▊         | 130/1500 [00:36<07:43,  2.96it/s, 198 steps of size 2.06e-02. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   9%|▊         | 131/1500 [00:36<07:05,  3.22it/s, 180 steps of size 2.49e-02. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   9%|▉         | 132/1500 [00:36<05:51,  3.89it/s, 87 steps of size 5.50e-03. acc. prob=0.86] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   9%|▉         | 133/1500 [00:38<12:34,  1.81it/s, 1023 steps of size 7.17e-03. acc. prob=0.86]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   9%|▉         | 134/1500 [00:38<12:38,  1.80it/s, 436 steps of size 9.47e-03. acc. prob=0.87] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   9%|▉         | 135/1500 [00:39<15:35,  1.46it/s, 780 steps of size 6.43e-03. acc. prob=0.86]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   9%|▉         | 136/1500 [00:41<19:46,  1.15it/s, 1023 steps of size 8.25e-03. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   9%|▉         | 137/1500 [00:41<19:11,  1.18it/s, 605 steps of size 1.05e-02. acc. prob=0.87] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   9%|▉         | 139/1500 [00:43<17:14,  1.32it/s, 1023 steps of size 1.42e-03. acc. prob=0.86]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   9%|▉         | 140/1500 [00:44<20:19,  1.12it/s, 1023 steps of size 1.87e-03. acc. prob=0.86]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   9%|▉         | 141/1500 [00:45<22:46,  1.01s/it, 1023 steps of size 2.48e-03. acc. prob=0.86]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:   9%|▉         | 142/1500 [00:47<24:38,  1.09s/it, 1023 steps of size 3.27e-03. acc. prob=0.86]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  10%|▉         | 143/1500 [00:47<21:44,  1.04it/s, 492 steps of size 4.18e-03. acc. prob=0.86] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  10%|▉         | 144/1500 [00:49<24:00,  1.06s/it, 1023 steps of size 5.46e-03. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  10%|▉         | 145/1500 [00:50<25:37,  1.13s/it, 1023 steps of size 7.03e-03. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  10%|▉         | 146/1500 [00:50<21:14,  1.06it/s, 368 steps of size 8.99e-03. acc. prob=0.87] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  10%|▉         | 147/1500 [00:51<19:00,  1.19it/s, 473 steps of size 1.16e-02. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  10%|▉         | 148/1500 [00:52<22:08,  1.02it/s, 1023 steps of size 1.49e-02. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  10%|▉         | 149/1500 [00:53<19:34,  1.15it/s, 468 steps of size 1.74e-02. acc. prob=0.87] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  10%|█         | 150/1500 [00:54<18:07,  1.24it/s, 511 steps of size 1.26e-02. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  10%|█         | 153/1500 [00:55<13:30,  1.66it/s, 1023 steps of size 1.36e-03. acc. prob=0.86]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  10%|█         | 154/1500 [00:56<17:03,  1.32it/s, 1023 steps of size 1.28e-03. acc. prob=0.86]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  10%|█         | 155/1500 [00:58<19:57,  1.12it/s, 1023 steps of size 1.41e-03. acc. prob=0.86]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  10%|█         | 156/1500 [00:59<22:19,  1.00it/s, 1023 steps of size 1.65e-03. acc. prob=0.86]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  10%|█         | 157/1500 [01:00<24:10,  1.08s/it, 1023 steps of size 2.10e-03. acc. prob=0.86]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  11%|█         | 158/1500 [01:01<25:34,  1.14s/it, 1023 steps of size 2.76e-03. acc. prob=0.86]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  11%|█         | 159/1500 [01:03<27:21,  1.22s/it, 1023 steps of size 3.25e-03. acc. prob=0.86]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  11%|█         | 160/1500 [01:04<27:54,  1.25s/it, 1023 steps of size 3.76e-03. acc. prob=0.86]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  11%|█         | 161/1500 [01:06<28:18,  1.27s/it, 1023 steps of size 4.36e-03. acc. prob=0.86]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  11%|█         | 162/1500 [01:07<28:51,  1.29s/it, 1023 steps of size 4.39e-03. acc. prob=0.86]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  11%|█         | 163/1500 [01:08<29:08,  1.31s/it, 1023 steps of size 5.88e-03. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  11%|█         | 164/1500 [01:10<29:22,  1.32s/it, 1023 steps of size 4.64e-03. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  11%|█         | 165/1500 [01:11<29:30,  1.33s/it, 1023 steps of size 6.42e-03. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  11%|█         | 166/1500 [01:11<22:52,  1.03s/it, 253 steps of size 7.45e-03. acc. prob=0.87] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  11%|█         | 167/1500 [01:13<24:45,  1.11s/it, 1023 steps of size 3.65e-03. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  11%|█         | 168/1500 [01:14<26:03,  1.17s/it, 1023 steps of size 4.84e-03. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  11%|█▏        | 169/1500 [01:15<23:54,  1.08s/it, 662 steps of size 6.50e-03. acc. prob=0.87] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  11%|█▏        | 170/1500 [01:16<25:42,  1.16s/it, 1023 steps of size 1.45e-03. acc. prob=0.86]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  11%|█▏        | 171/1500 [01:17<26:50,  1.21s/it, 1023 steps of size 2.03e-03. acc. prob=0.86]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  11%|█▏        | 172/1500 [01:19<27:47,  1.26s/it, 1023 steps of size 2.80e-03. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  12%|█▏        | 173/1500 [01:20<28:10,  1.27s/it, 1023 steps of size 3.69e-03. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  12%|█▏        | 174/1500 [01:21<28:27,  1.29s/it, 1023 steps of size 4.84e-03. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  12%|█▏        | 175/1500 [01:23<28:36,  1.30s/it, 1023 steps of size 5.83e-04. acc. prob=0.86]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  12%|█▏        | 176/1500 [01:24<28:43,  1.30s/it, 1023 steps of size 8.09e-04. acc. prob=0.86]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  12%|█▏        | 177/1500 [01:25<28:58,  1.31s/it, 1023 steps of size 1.12e-03. acc. prob=0.86]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  12%|█▏        | 178/1500 [01:27<29:00,  1.32s/it, 1023 steps of size 1.54e-03. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  12%|█▏        | 179/1500 [01:28<28:58,  1.32s/it, 1023 steps of size 2.10e-03. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  12%|█▏        | 180/1500 [01:29<28:56,  1.32s/it, 1023 steps of size 2.84e-03. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  12%|█▏        | 181/1500 [01:31<28:54,  1.32s/it, 1023 steps of size 3.52e-03. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  12%|█▏        | 182/1500 [01:32<28:53,  1.32s/it, 1023 steps of size 4.69e-03. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  12%|█▏        | 183/1500 [01:33<24:51,  1.13s/it, 544 steps of size 4.07e-03. acc. prob=0.87] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  12%|█▏        | 184/1500 [01:34<23:14,  1.06s/it, 674 steps of size 4.68e-03. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  12%|█▏        | 185/1500 [01:35<24:55,  1.14s/it, 1023 steps of size 5.95e-03. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  12%|█▏        | 186/1500 [01:35<19:10,  1.14it/s, 205 steps of size 2.48e-03. acc. prob=0.87] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  12%|█▏        | 187/1500 [01:35<14:26,  1.51it/s, 123 steps of size 3.24e-03. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  13%|█▎        | 188/1500 [01:35<11:32,  1.90it/s, 169 steps of size 4.17e-03. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  13%|█▎        | 189/1500 [01:37<16:40,  1.31it/s, 1023 steps of size 3.90e-03. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  13%|█▎        | 190/1500 [01:38<20:16,  1.08it/s, 1023 steps of size 4.71e-03. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  13%|█▎        | 191/1500 [01:39<22:47,  1.04s/it, 1023 steps of size 4.98e-03. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  13%|█▎        | 192/1500 [01:41<24:44,  1.13s/it, 1023 steps of size 4.04e-03. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  13%|█▎        | 193/1500 [01:42<25:54,  1.19s/it, 1023 steps of size 1.23e-03. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  13%|█▎        | 194/1500 [01:43<26:41,  1.23s/it, 1023 steps of size 1.63e-03. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  13%|█▎        | 195/1500 [01:45<27:24,  1.26s/it, 1023 steps of size 2.14e-03. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  13%|█▎        | 196/1500 [01:46<27:54,  1.28s/it, 1023 steps of size 2.80e-03. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  13%|█▎        | 197/1500 [01:47<28:37,  1.32s/it, 1023 steps of size 3.16e-03. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  13%|█▎        | 198/1500 [01:49<28:42,  1.32s/it, 1023 steps of size 4.11e-03. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  13%|█▎        | 199/1500 [01:50<28:45,  1.33s/it, 1023 steps of size 3.86e-03. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  13%|█▎        | 200/1500 [01:52<28:49,  1.33s/it, 1023 steps of size 2.00e-03. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  13%|█▎        | 201/1500 [01:53<28:47,  1.33s/it, 1023 steps of size 2.53e-03. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  13%|█▎        | 202/1500 [01:54<28:51,  1.33s/it, 1023 steps of size 3.26e-03. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  14%|█▎        | 203/1500 [01:56<28:50,  1.33s/it, 1023 steps of size 3.85e-03. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  14%|█▎        | 205/1500 [01:57<22:30,  1.04s/it, 1023 steps of size 2.24e-03. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  14%|█▎        | 206/1500 [01:58<23:56,  1.11s/it, 1023 steps of size 2.80e-03. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  14%|█▍        | 207/1500 [02:00<25:06,  1.17s/it, 1023 steps of size 3.47e-03. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  14%|█▍        | 208/1500 [02:01<26:06,  1.21s/it, 1023 steps of size 3.97e-03. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  14%|█▍        | 209/1500 [02:02<26:44,  1.24s/it, 1023 steps of size 3.84e-03. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  14%|█▍        | 210/1500 [02:04<27:10,  1.26s/it, 1023 steps of size 3.25e-03. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  14%|█▍        | 211/1500 [02:05<27:29,  1.28s/it, 1023 steps of size 3.92e-03. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  14%|█▍        | 212/1500 [02:06<27:42,  1.29s/it, 1023 steps of size 4.85e-03. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  14%|█▍        | 213/1500 [02:07<27:53,  1.30s/it, 1023 steps of size 4.76e-03. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  14%|█▍        | 214/1500 [02:09<28:05,  1.31s/it, 1023 steps of size 5.99e-03. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  14%|█▍        | 215/1500 [02:10<28:09,  1.32s/it, 1023 steps of size 6.78e-03. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  14%|█▍        | 216/1500 [02:11<25:23,  1.19s/it, 685 steps of size 3.43e-03. acc. prob=0.87] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  14%|█▍        | 217/1500 [02:12<26:10,  1.22s/it, 1023 steps of size 3.88e-03. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  15%|█▍        | 218/1500 [02:14<26:44,  1.25s/it, 1023 steps of size 4.88e-03. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  15%|█▍        | 219/1500 [02:15<27:06,  1.27s/it, 1023 steps of size 6.13e-03. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  15%|█▍        | 220/1500 [02:16<27:22,  1.28s/it, 1023 steps of size 4.12e-03. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  15%|█▍        | 221/1500 [02:18<27:34,  1.29s/it, 1023 steps of size 5.04e-03. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  15%|█▍        | 222/1500 [02:19<27:42,  1.30s/it, 1023 steps of size 6.06e-03. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  15%|█▍        | 223/1500 [02:20<27:49,  1.31s/it, 1023 steps of size 1.90e-03. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  15%|█▍        | 224/1500 [02:22<28:00,  1.32s/it, 1023 steps of size 2.39e-03. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  15%|█▌        | 225/1500 [02:23<28:03,  1.32s/it, 1023 steps of size 2.88e-03. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  15%|█▌        | 226/1500 [02:24<28:03,  1.32s/it, 1023 steps of size 3.57e-03. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  15%|█▌        | 227/1500 [02:26<28:00,  1.32s/it, 1023 steps of size 4.30e-03. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  15%|█▌        | 228/1500 [02:27<27:57,  1.32s/it, 1023 steps of size 2.70e-03. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  15%|█▌        | 229/1500 [02:28<27:57,  1.32s/it, 1023 steps of size 3.31e-03. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  15%|█▌        | 230/1500 [02:30<28:02,  1.33s/it, 1023 steps of size 3.93e-03. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  15%|█▌        | 231/1500 [02:31<27:57,  1.32s/it, 1023 steps of size 4.38e-03. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  15%|█▌        | 232/1500 [02:32<27:53,  1.32s/it, 1023 steps of size 4.59e-03. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  16%|█▌        | 233/1500 [02:33<27:50,  1.32s/it, 1023 steps of size 5.61e-03. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  16%|█▌        | 234/1500 [02:35<27:49,  1.32s/it, 1023 steps of size 6.53e-03. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  16%|█▌        | 235/1500 [02:36<27:46,  1.32s/it, 1023 steps of size 6.36e-03. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  16%|█▌        | 236/1500 [02:37<27:45,  1.32s/it, 1023 steps of size 4.10e-03. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  16%|█▌        | 237/1500 [02:39<27:50,  1.32s/it, 1023 steps of size 4.71e-03. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  16%|█▌        | 238/1500 [02:40<27:49,  1.32s/it, 1023 steps of size 5.56e-03. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  16%|█▌        | 239/1500 [02:41<27:45,  1.32s/it, 1023 steps of size 4.04e-03. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  16%|█▌        | 240/1500 [02:43<27:46,  1.32s/it, 1023 steps of size 4.83e-03. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  16%|█▌        | 241/1500 [02:44<27:43,  1.32s/it, 1023 steps of size 5.06e-03. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  16%|█▌        | 242/1500 [02:45<27:37,  1.32s/it, 1023 steps of size 4.94e-03. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  16%|█▌        | 243/1500 [02:47<27:34,  1.32s/it, 1023 steps of size 4.21e-03. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  16%|█▋        | 244/1500 [02:48<27:33,  1.32s/it, 1023 steps of size 5.15e-03. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  16%|█▋        | 245/1500 [02:49<27:31,  1.32s/it, 1023 steps of size 6.18e-03. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  16%|█▋        | 246/1500 [02:51<27:29,  1.32s/it, 1023 steps of size 5.69e-03. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  16%|█▋        | 247/1500 [02:52<27:27,  1.32s/it, 1023 steps of size 6.19e-03. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  17%|█▋        | 248/1500 [02:53<27:26,  1.31s/it, 1023 steps of size 7.20e-03. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  17%|█▋        | 249/1500 [02:54<23:18,  1.12s/it, 511 steps of size 8.59e-03. acc. prob=0.88] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  17%|█▋        | 250/1500 [02:54<18:13,  1.14it/s, 238 steps of size 8.39e-03. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  17%|█▋        | 251/1500 [02:55<16:50,  1.24it/s, 511 steps of size 1.00e-01. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  17%|█▋        | 253/1500 [02:56<12:12,  1.70it/s, 511 steps of size 1.29e-02. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  17%|█▋        | 254/1500 [02:56<12:33,  1.65it/s, 511 steps of size 6.97e-03. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  17%|█▋        | 255/1500 [02:57<16:10,  1.28it/s, 992 steps of size 8.35e-03. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  17%|█▋        | 256/1500 [02:58<15:28,  1.34it/s, 511 steps of size 1.05e-02. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  17%|█▋        | 257/1500 [02:59<14:56,  1.39it/s, 511 steps of size 1.32e-02. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  17%|█▋        | 258/1500 [02:59<14:31,  1.43it/s, 511 steps of size 1.34e-02. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  17%|█▋        | 259/1500 [03:00<12:16,  1.69it/s, 255 steps of size 1.74e-02. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  17%|█▋        | 260/1500 [03:00<10:38,  1.94it/s, 255 steps of size 2.37e-02. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  17%|█▋        | 261/1500 [03:00<09:29,  2.17it/s, 255 steps of size 3.16e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  17%|█▋        | 262/1500 [03:01<08:40,  2.38it/s, 255 steps of size 1.87e-03. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  18%|█▊        | 263/1500 [03:02<14:11,  1.45it/s, 1023 steps of size 2.59e-03. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  18%|█▊        | 264/1500 [03:03<18:04,  1.14it/s, 1023 steps of size 3.61e-03. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  18%|█▊        | 265/1500 [03:05<20:45,  1.01s/it, 1023 steps of size 4.98e-03. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  18%|█▊        | 266/1500 [03:06<22:41,  1.10s/it, 1023 steps of size 6.82e-03. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  18%|█▊        | 267/1500 [03:07<19:55,  1.03it/s, 511 steps of size 9.39e-03. acc. prob=0.87] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  18%|█▊        | 268/1500 [03:07<17:59,  1.14it/s, 511 steps of size 1.23e-02. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  18%|█▊        | 269/1500 [03:08<16:37,  1.23it/s, 511 steps of size 1.69e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  18%|█▊        | 270/1500 [03:08<13:38,  1.50it/s, 255 steps of size 2.24e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  18%|█▊        | 271/1500 [03:09<11:33,  1.77it/s, 255 steps of size 3.00e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  18%|█▊        | 272/1500 [03:09<10:06,  2.03it/s, 255 steps of size 9.46e-03. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  18%|█▊        | 273/1500 [03:10<11:08,  1.83it/s, 511 steps of size 1.29e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  18%|█▊        | 274/1500 [03:10<11:49,  1.73it/s, 511 steps of size 1.46e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  18%|█▊        | 275/1500 [03:11<10:17,  1.99it/s, 255 steps of size 1.87e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  18%|█▊        | 276/1500 [03:11<09:12,  2.22it/s, 255 steps of size 2.46e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  18%|█▊        | 277/1500 [03:11<08:26,  2.42it/s, 255 steps of size 1.60e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  19%|█▊        | 278/1500 [03:12<07:54,  2.58it/s, 255 steps of size 1.72e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  19%|█▊        | 279/1500 [03:12<07:32,  2.70it/s, 255 steps of size 2.17e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  19%|█▊        | 280/1500 [03:12<07:16,  2.79it/s, 255 steps of size 2.88e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  19%|█▊        | 281/1500 [03:13<07:05,  2.87it/s, 254 steps of size 6.51e-03. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  19%|█▉        | 282/1500 [03:14<12:57,  1.57it/s, 1023 steps of size 8.71e-03. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  19%|█▉        | 283/1500 [03:15<13:03,  1.55it/s, 511 steps of size 1.11e-02. acc. prob=0.88] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  19%|█▉        | 284/1500 [03:15<13:08,  1.54it/s, 511 steps of size 1.30e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  19%|█▉        | 285/1500 [03:16<11:10,  1.81it/s, 255 steps of size 1.42e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  19%|█▉        | 286/1500 [03:16<09:48,  2.06it/s, 255 steps of size 1.86e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  19%|█▉        | 287/1500 [03:16<08:51,  2.28it/s, 255 steps of size 2.41e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  19%|█▉        | 288/1500 [03:17<08:12,  2.46it/s, 255 steps of size 3.02e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  19%|█▉        | 289/1500 [03:17<07:46,  2.59it/s, 255 steps of size 5.20e-03. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  19%|█▉        | 290/1500 [03:18<13:28,  1.50it/s, 1023 steps of size 6.71e-03. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  19%|█▉        | 291/1500 [03:20<17:26,  1.16it/s, 1023 steps of size 8.73e-03. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  20%|█▉        | 293/1500 [03:20<12:39,  1.59it/s, 511 steps of size 1.37e-02. acc. prob=0.88] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  20%|█▉        | 294/1500 [03:21<12:47,  1.57it/s, 511 steps of size 1.77e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  20%|█▉        | 295/1500 [03:21<11:09,  1.80it/s, 255 steps of size 2.21e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  20%|█▉        | 296/1500 [03:22<09:54,  2.02it/s, 255 steps of size 2.74e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  20%|█▉        | 297/1500 [03:22<08:58,  2.24it/s, 255 steps of size 3.38e-03. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  20%|█▉        | 298/1500 [03:23<13:55,  1.44it/s, 1023 steps of size 4.33e-03. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  20%|█▉        | 299/1500 [03:25<18:00,  1.11it/s, 1023 steps of size 5.57e-03. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  20%|██        | 300/1500 [03:26<20:31,  1.03s/it, 1023 steps of size 7.17e-03. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  20%|██        | 301/1500 [03:27<22:12,  1.11s/it, 1023 steps of size 9.21e-03. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  20%|██        | 302/1500 [03:29<23:24,  1.17s/it, 1023 steps of size 1.18e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  20%|██        | 303/1500 [03:29<20:20,  1.02s/it, 511 steps of size 1.26e-02. acc. prob=0.88] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  20%|██        | 304/1500 [03:30<18:43,  1.06it/s, 511 steps of size 1.59e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  20%|██        | 305/1500 [03:31<17:06,  1.16it/s, 511 steps of size 1.90e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  20%|██        | 306/1500 [03:31<15:54,  1.25it/s, 511 steps of size 2.37e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  20%|██        | 307/1500 [03:32<13:05,  1.52it/s, 255 steps of size 1.75e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  21%|██        | 308/1500 [03:32<11:09,  1.78it/s, 255 steps of size 2.00e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  21%|██        | 309/1500 [03:32<09:48,  2.02it/s, 255 steps of size 2.09e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  21%|██        | 310/1500 [03:33<08:50,  2.24it/s, 255 steps of size 2.62e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  21%|██        | 311/1500 [03:33<07:11,  2.76it/s, 127 steps of size 3.65e-03. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  21%|██        | 312/1500 [03:34<12:52,  1.54it/s, 1023 steps of size 4.63e-03. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  21%|██        | 313/1500 [03:35<16:49,  1.18it/s, 1023 steps of size 5.85e-03. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  21%|██        | 314/1500 [03:37<19:33,  1.01it/s, 1023 steps of size 7.31e-03. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  21%|██        | 315/1500 [03:37<17:37,  1.12it/s, 517 steps of size 9.13e-03. acc. prob=0.88] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  21%|██        | 316/1500 [03:38<16:13,  1.22it/s, 511 steps of size 1.14e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  21%|██        | 317/1500 [03:39<15:15,  1.29it/s, 511 steps of size 1.42e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  21%|██        | 318/1500 [03:39<14:37,  1.35it/s, 511 steps of size 1.71e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  21%|██▏       | 319/1500 [03:40<12:13,  1.61it/s, 255 steps of size 2.08e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  21%|██▏       | 320/1500 [03:40<10:30,  1.87it/s, 255 steps of size 2.10e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  21%|██▏       | 321/1500 [03:40<09:17,  2.12it/s, 255 steps of size 2.29e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  21%|██▏       | 322/1500 [03:41<08:25,  2.33it/s, 255 steps of size 2.03e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  22%|██▏       | 323/1500 [03:41<07:50,  2.50it/s, 255 steps of size 2.46e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  22%|██▏       | 324/1500 [03:41<07:24,  2.64it/s, 255 steps of size 3.04e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  22%|██▏       | 325/1500 [03:42<07:06,  2.75it/s, 255 steps of size 1.53e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  22%|██▏       | 326/1500 [03:42<06:54,  2.83it/s, 255 steps of size 1.88e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  22%|██▏       | 327/1500 [03:42<06:44,  2.90it/s, 255 steps of size 2.30e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  22%|██▏       | 329/1500 [03:43<07:00,  2.79it/s, 511 steps of size 1.12e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  22%|██▏       | 330/1500 [03:44<08:26,  2.31it/s, 511 steps of size 1.33e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  22%|██▏       | 331/1500 [03:44<09:34,  2.03it/s, 511 steps of size 1.64e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  22%|██▏       | 332/1500 [03:45<10:27,  1.86it/s, 511 steps of size 2.01e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  22%|██▏       | 333/1500 [03:45<09:18,  2.09it/s, 255 steps of size 2.35e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  22%|██▏       | 334/1500 [03:46<08:27,  2.30it/s, 255 steps of size 2.76e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  22%|██▏       | 335/1500 [03:46<06:55,  2.80it/s, 127 steps of size 2.90e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  22%|██▏       | 336/1500 [03:46<05:49,  3.33it/s, 127 steps of size 2.83e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  23%|██▎       | 338/1500 [03:47<06:25,  3.02it/s, 511 steps of size 7.13e-03. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  23%|██▎       | 339/1500 [03:47<07:57,  2.43it/s, 511 steps of size 8.67e-03. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  23%|██▎       | 340/1500 [03:48<09:11,  2.10it/s, 511 steps of size 1.06e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  23%|██▎       | 341/1500 [03:49<09:39,  2.00it/s, 440 steps of size 1.27e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  23%|██▎       | 342/1500 [03:49<10:29,  1.84it/s, 511 steps of size 1.54e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  23%|██▎       | 343/1500 [03:50<09:17,  2.07it/s, 255 steps of size 1.83e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  23%|██▎       | 344/1500 [03:50<08:26,  2.28it/s, 255 steps of size 1.65e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  23%|██▎       | 345/1500 [03:50<07:48,  2.47it/s, 255 steps of size 1.95e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  23%|██▎       | 346/1500 [03:51<07:21,  2.61it/s, 255 steps of size 2.36e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  23%|██▎       | 347/1500 [03:51<07:02,  2.73it/s, 255 steps of size 2.22e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  23%|██▎       | 348/1500 [03:51<06:52,  2.79it/s, 255 steps of size 2.12e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  23%|██▎       | 349/1500 [03:52<06:46,  2.83it/s, 255 steps of size 2.32e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  23%|██▎       | 350/1500 [03:52<06:40,  2.87it/s, 255 steps of size 2.66e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  23%|██▎       | 351/1500 [03:52<05:37,  3.40it/s, 127 steps of size 3.07e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  23%|██▎       | 352/1500 [03:52<05:48,  3.29it/s, 255 steps of size 1.43e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  24%|██▎       | 353/1500 [03:53<05:56,  3.21it/s, 255 steps of size 1.72e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  24%|██▎       | 354/1500 [03:53<06:02,  3.16it/s, 255 steps of size 1.83e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  24%|██▎       | 355/1500 [03:53<06:06,  3.13it/s, 255 steps of size 2.02e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  24%|██▎       | 356/1500 [03:54<06:08,  3.10it/s, 255 steps of size 2.38e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  24%|██▍       | 357/1500 [03:54<06:10,  3.09it/s, 255 steps of size 2.76e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  24%|██▍       | 358/1500 [03:54<06:13,  3.06it/s, 255 steps of size 1.45e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  24%|██▍       | 359/1500 [03:55<08:05,  2.35it/s, 511 steps of size 1.43e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  24%|██▍       | 360/1500 [03:56<09:24,  2.02it/s, 511 steps of size 1.71e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  24%|██▍       | 361/1500 [03:56<08:27,  2.25it/s, 255 steps of size 1.87e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  24%|██▍       | 362/1500 [03:56<07:46,  2.44it/s, 255 steps of size 2.11e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  24%|██▍       | 363/1500 [03:57<07:18,  2.59it/s, 255 steps of size 2.00e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  24%|██▍       | 364/1500 [03:57<06:58,  2.72it/s, 255 steps of size 2.39e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  24%|██▍       | 365/1500 [03:57<05:48,  3.26it/s, 127 steps of size 2.64e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  24%|██▍       | 366/1500 [03:58<05:55,  3.19it/s, 255 steps of size 2.97e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  25%|██▍       | 368/1500 [03:58<05:00,  3.76it/s, 255 steps of size 2.43e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  25%|██▍       | 369/1500 [03:58<05:17,  3.56it/s, 255 steps of size 2.86e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  25%|██▍       | 370/1500 [03:59<04:42,  3.99it/s, 127 steps of size 6.65e-03. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  25%|██▍       | 371/1500 [03:59<06:47,  2.77it/s, 511 steps of size 7.93e-03. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  25%|██▍       | 372/1500 [04:00<08:20,  2.25it/s, 511 steps of size 9.14e-03. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  25%|██▍       | 373/1500 [04:00<09:29,  1.98it/s, 511 steps of size 1.06e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  25%|██▍       | 374/1500 [04:01<10:18,  1.82it/s, 511 steps of size 1.22e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  25%|██▌       | 375/1500 [04:02<10:53,  1.72it/s, 511 steps of size 1.43e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  25%|██▌       | 376/1500 [04:02<11:18,  1.66it/s, 511 steps of size 1.60e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  25%|██▌       | 377/1500 [04:03<09:46,  1.92it/s, 255 steps of size 1.63e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  25%|██▌       | 378/1500 [04:03<08:44,  2.14it/s, 255 steps of size 1.93e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  25%|██▌       | 379/1500 [04:03<07:58,  2.34it/s, 255 steps of size 2.26e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  25%|██▌       | 380/1500 [04:04<07:25,  2.51it/s, 255 steps of size 2.63e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  25%|██▌       | 382/1500 [04:05<09:50,  1.89it/s, 1023 steps of size 8.00e-03. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  26%|██▌       | 383/1500 [04:06<10:26,  1.78it/s, 511 steps of size 9.47e-03. acc. prob=0.88] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  26%|██▌       | 384/1500 [04:07<11:09,  1.67it/s, 511 steps of size 1.11e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  26%|██▌       | 385/1500 [04:07<11:31,  1.61it/s, 511 steps of size 1.29e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  26%|██▌       | 386/1500 [04:08<10:02,  1.85it/s, 255 steps of size 1.51e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  26%|██▌       | 387/1500 [04:08<10:40,  1.74it/s, 511 steps of size 1.72e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  26%|██▌       | 388/1500 [04:09<09:20,  1.98it/s, 255 steps of size 1.93e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  26%|██▌       | 389/1500 [04:09<08:22,  2.21it/s, 255 steps of size 1.70e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  26%|██▌       | 390/1500 [04:09<07:41,  2.40it/s, 255 steps of size 1.93e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  26%|██▌       | 391/1500 [04:09<07:12,  2.56it/s, 255 steps of size 1.53e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  26%|██▌       | 392/1500 [04:10<06:51,  2.69it/s, 255 steps of size 1.74e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  26%|██▌       | 393/1500 [04:10<06:37,  2.79it/s, 255 steps of size 1.87e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  26%|██▋       | 394/1500 [04:10<06:26,  2.86it/s, 255 steps of size 2.10e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  26%|██▋       | 395/1500 [04:11<06:19,  2.91it/s, 255 steps of size 2.33e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  26%|██▋       | 396/1500 [04:11<06:14,  2.95it/s, 255 steps of size 2.72e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  26%|██▋       | 397/1500 [04:11<05:16,  3.49it/s, 127 steps of size 1.07e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  27%|██▋       | 398/1500 [04:12<09:19,  1.97it/s, 511 steps of size 1.25e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  27%|██▋       | 399/1500 [04:13<08:25,  2.18it/s, 255 steps of size 1.44e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  27%|██▋       | 400/1500 [04:13<09:31,  1.93it/s, 511 steps of size 1.69e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  27%|██▋       | 401/1500 [04:14<08:27,  2.16it/s, 255 steps of size 1.97e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  27%|██▋       | 402/1500 [04:14<07:43,  2.37it/s, 255 steps of size 2.17e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  27%|██▋       | 403/1500 [04:14<07:12,  2.54it/s, 255 steps of size 1.99e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  27%|██▋       | 404/1500 [04:15<06:50,  2.67it/s, 255 steps of size 1.14e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  27%|██▋       | 405/1500 [04:15<08:23,  2.18it/s, 511 steps of size 1.32e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  27%|██▋       | 406/1500 [04:16<09:29,  1.92it/s, 511 steps of size 1.47e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  27%|██▋       | 407/1500 [04:17<10:14,  1.78it/s, 511 steps of size 1.71e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  27%|██▋       | 408/1500 [04:17<09:01,  2.02it/s, 255 steps of size 1.87e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  27%|██▋       | 409/1500 [04:17<08:06,  2.24it/s, 255 steps of size 2.16e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  27%|██▋       | 410/1500 [04:18<07:26,  2.44it/s, 255 steps of size 2.29e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  27%|██▋       | 411/1500 [04:18<06:59,  2.59it/s, 255 steps of size 2.63e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  27%|██▋       | 412/1500 [04:18<06:40,  2.72it/s, 255 steps of size 2.56e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  28%|██▊       | 413/1500 [04:18<05:33,  3.26it/s, 127 steps of size 2.95e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  28%|██▊       | 414/1500 [04:19<04:46,  3.79it/s, 127 steps of size 8.02e-03. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  28%|██▊       | 415/1500 [04:19<06:53,  2.62it/s, 511 steps of size 8.84e-03. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  28%|██▊       | 416/1500 [04:20<08:23,  2.15it/s, 511 steps of size 9.92e-03. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  28%|██▊       | 417/1500 [04:21<09:26,  1.91it/s, 511 steps of size 1.15e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  28%|██▊       | 418/1500 [04:21<10:09,  1.77it/s, 511 steps of size 1.32e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  28%|██▊       | 419/1500 [04:22<10:40,  1.69it/s, 511 steps of size 1.52e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  28%|██▊       | 420/1500 [04:22<09:14,  1.95it/s, 255 steps of size 1.31e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  28%|██▊       | 421/1500 [04:23<10:00,  1.80it/s, 511 steps of size 1.52e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  28%|██▊       | 422/1500 [04:23<08:51,  2.03it/s, 255 steps of size 1.75e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  28%|██▊       | 423/1500 [04:24<08:01,  2.24it/s, 255 steps of size 1.66e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  28%|██▊       | 424/1500 [04:24<07:39,  2.34it/s, 255 steps of size 1.90e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  28%|██▊       | 425/1500 [04:24<07:11,  2.49it/s, 255 steps of size 2.17e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  28%|██▊       | 426/1500 [04:25<06:51,  2.61it/s, 255 steps of size 2.51e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  28%|██▊       | 427/1500 [04:25<06:33,  2.73it/s, 255 steps of size 1.71e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  29%|██▊       | 428/1500 [04:26<08:07,  2.20it/s, 511 steps of size 1.97e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  29%|██▊       | 429/1500 [04:26<07:27,  2.39it/s, 255 steps of size 1.46e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  29%|██▊       | 430/1500 [04:27<08:49,  2.02it/s, 511 steps of size 1.64e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  29%|██▊       | 431/1500 [04:27<07:56,  2.24it/s, 255 steps of size 1.81e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  29%|██▉       | 432/1500 [04:27<07:18,  2.44it/s, 255 steps of size 1.74e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  29%|██▉       | 433/1500 [04:28<06:51,  2.59it/s, 255 steps of size 1.99e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  29%|██▉       | 434/1500 [04:28<08:17,  2.14it/s, 511 steps of size 2.25e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  29%|██▉       | 435/1500 [04:29<07:33,  2.35it/s, 255 steps of size 2.46e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  29%|██▉       | 436/1500 [04:29<06:48,  2.61it/s, 223 steps of size 2.02e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  29%|██▉       | 437/1500 [04:29<06:30,  2.72it/s, 255 steps of size 2.30e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  29%|██▉       | 438/1500 [04:30<06:17,  2.81it/s, 255 steps of size 2.57e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  29%|██▉       | 439/1500 [04:30<05:58,  2.96it/s, 230 steps of size 2.24e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  29%|██▉       | 440/1500 [04:30<05:54,  2.99it/s, 255 steps of size 1.94e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  29%|██▉       | 441/1500 [04:30<05:52,  3.01it/s, 255 steps of size 1.99e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  29%|██▉       | 442/1500 [04:31<05:50,  3.02it/s, 255 steps of size 2.20e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  30%|██▉       | 443/1500 [04:31<05:49,  3.03it/s, 255 steps of size 2.30e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  30%|██▉       | 444/1500 [04:31<05:47,  3.04it/s, 255 steps of size 1.87e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  30%|██▉       | 445/1500 [04:32<05:47,  3.04it/s, 255 steps of size 2.05e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  30%|██▉       | 446/1500 [04:32<05:46,  3.04it/s, 255 steps of size 2.16e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  30%|██▉       | 447/1500 [04:32<05:45,  3.05it/s, 255 steps of size 1.94e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  30%|██▉       | 448/1500 [04:33<05:45,  3.05it/s, 255 steps of size 2.18e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  30%|██▉       | 449/1500 [04:33<05:44,  3.05it/s, 255 steps of size 2.45e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  30%|███       | 450/1500 [04:33<05:09,  3.39it/s, 169 steps of size 1.29e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  30%|███       | 451/1500 [04:34<07:03,  2.48it/s, 511 steps of size 1.54e-01. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  30%|███       | 453/1500 [04:34<04:38,  3.76it/s, 127 steps of size 3.39e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  30%|███       | 454/1500 [04:34<04:12,  4.15it/s, 127 steps of size 4.10e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  30%|███       | 455/1500 [04:35<03:51,  4.52it/s, 127 steps of size 5.06e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  30%|███       | 456/1500 [04:35<03:35,  4.86it/s, 127 steps of size 6.64e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  31%|███       | 458/1500 [04:35<02:37,  6.60it/s, 63 steps of size 6.17e-02. acc. prob=0.88] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  31%|███       | 460/1500 [04:35<02:09,  8.03it/s, 63 steps of size 1.07e-01. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  31%|███       | 462/1500 [04:36<03:43,  4.65it/s, 511 steps of size 1.61e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  31%|███       | 463/1500 [04:36<05:17,  3.27it/s, 511 steps of size 2.16e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  31%|███       | 464/1500 [04:37<05:22,  3.22it/s, 255 steps of size 2.97e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  31%|███       | 465/1500 [04:37<04:45,  3.63it/s, 127 steps of size 4.00e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  31%|███       | 466/1500 [04:37<04:15,  4.05it/s, 127 steps of size 5.45e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  31%|███       | 468/1500 [04:37<03:02,  5.66it/s, 63 steps of size 9.05e-02. acc. prob=0.88] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  31%|███▏      | 470/1500 [04:38<02:43,  6.30it/s, 137 steps of size 2.76e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  31%|███▏      | 471/1500 [04:38<03:20,  5.14it/s, 255 steps of size 3.67e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  31%|███▏      | 472/1500 [04:38<03:11,  5.35it/s, 127 steps of size 4.96e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  32%|███▏      | 473/1500 [04:38<03:05,  5.54it/s, 127 steps of size 6.58e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  32%|███▏      | 474/1500 [04:38<03:00,  5.67it/s, 127 steps of size 3.29e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  32%|███▏      | 475/1500 [04:39<02:57,  5.78it/s, 127 steps of size 3.98e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  32%|███▏      | 476/1500 [04:39<02:54,  5.87it/s, 127 steps of size 4.76e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  32%|███▏      | 477/1500 [04:39<02:52,  5.94it/s, 127 steps of size 6.33e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  32%|███▏      | 479/1500 [04:39<02:11,  7.74it/s, 63 steps of size 8.91e-02. acc. prob=0.88] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  32%|███▏      | 481/1500 [04:39<01:52,  9.04it/s, 63 steps of size 1.08e-01. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  32%|███▏      | 483/1500 [04:39<01:41,  9.98it/s, 63 steps of size 9.86e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  32%|███▏      | 485/1500 [04:39<01:35, 10.65it/s, 63 steps of size 2.19e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  32%|███▏      | 486/1500 [04:40<02:21,  7.19it/s, 255 steps of size 2.82e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  32%|███▏      | 487/1500 [04:40<03:02,  5.54it/s, 255 steps of size 3.66e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  33%|███▎      | 488/1500 [04:40<03:38,  4.64it/s, 255 steps of size 4.75e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  33%|███▎      | 490/1500 [04:41<02:59,  5.62it/s, 127 steps of size 4.77e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  33%|███▎      | 491/1500 [04:41<02:56,  5.73it/s, 127 steps of size 6.11e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  33%|███▎      | 493/1500 [04:41<02:19,  7.24it/s, 63 steps of size 5.97e-02. acc. prob=0.88] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  33%|███▎      | 494/1500 [04:41<02:24,  6.97it/s, 127 steps of size 7.40e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  33%|███▎      | 496/1500 [04:41<01:57,  8.51it/s, 63 steps of size 9.30e-02. acc. prob=0.88] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  33%|███▎      | 498/1500 [04:41<01:37, 10.28it/s, 31 steps of size 1.30e-01. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  33%|███▎      | 501/1500 [04:42<01:12, 13.73it/s, 31 steps of size 1.78e-01. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  34%|███▎      | 503/1500 [04:42<01:09, 14.42it/s, 63 steps of size 6.86e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  34%|███▎      | 505/1500 [04:42<01:12, 13.72it/s, 63 steps of size 5.59e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  34%|███▎      | 506/1500 [04:42<01:28, 11.30it/s, 127 steps of size 6.72e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  34%|███▍      | 508/1500 [04:42<01:25, 11.61it/s, 63 steps of size 9.22e-02. acc. prob=0.88] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  34%|███▍      | 510/1500 [04:42<01:17, 12.83it/s, 31 steps of size 4.23e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  34%|███▍      | 511/1500 [04:42<01:32, 10.66it/s, 127 steps of size 5.16e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  34%|███▍      | 512/1500 [04:43<01:47,  9.22it/s, 127 steps of size 6.29e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  34%|███▍      | 513/1500 [04:43<01:59,  8.25it/s, 127 steps of size 7.40e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  34%|███▍      | 515/1500 [04:43<01:45,  9.33it/s, 63 steps of size 2.78e-02. acc. prob=0.88] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  34%|███▍      | 516/1500 [04:43<01:57,  8.36it/s, 127 steps of size 3.36e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  34%|███▍      | 517/1500 [04:43<02:08,  7.67it/s, 127 steps of size 4.03e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  35%|███▍      | 518/1500 [04:43<02:16,  7.19it/s, 127 steps of size 4.99e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  35%|███▍      | 519/1500 [04:44<02:22,  6.87it/s, 127 steps of size 6.04e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  35%|███▍      | 521/1500 [04:44<01:55,  8.50it/s, 63 steps of size 7.58e-02. acc. prob=0.89] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  35%|███▍      | 524/1500 [04:44<02:04,  7.87it/s, 255 steps of size 2.74e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  35%|███▌      | 525/1500 [04:45<02:40,  6.09it/s, 255 steps of size 3.36e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  35%|███▌      | 526/1500 [04:45<02:39,  6.09it/s, 127 steps of size 3.89e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  35%|███▌      | 527/1500 [04:45<02:39,  6.10it/s, 127 steps of size 4.44e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  35%|███▌      | 528/1500 [04:45<02:39,  6.10it/s, 127 steps of size 5.28e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  35%|███▌      | 529/1500 [04:45<02:39,  6.10it/s, 127 steps of size 6.33e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  35%|███▌      | 531/1500 [04:45<02:21,  6.85it/s, 127 steps of size 7.56e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  36%|███▌      | 533/1500 [04:46<01:49,  8.80it/s, 31 steps of size 1.04e-01. acc. prob=0.89] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  36%|███▌      | 535/1500 [04:46<01:38,  9.78it/s, 63 steps of size 6.73e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  36%|███▌      | 537/1500 [04:46<01:45,  9.15it/s, 127 steps of size 4.16e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  36%|███▌      | 538/1500 [04:46<01:55,  8.35it/s, 127 steps of size 4.69e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  36%|███▌      | 539/1500 [04:46<02:04,  7.74it/s, 127 steps of size 5.64e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  36%|███▌      | 541/1500 [04:46<01:46,  9.02it/s, 63 steps of size 7.65e-02. acc. prob=0.89] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  36%|███▌      | 543/1500 [04:47<01:36,  9.96it/s, 63 steps of size 1.47e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  36%|███▋      | 544/1500 [04:47<03:22,  4.71it/s, 511 steps of size 1.78e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  36%|███▋      | 545/1500 [04:48<03:47,  4.20it/s, 255 steps of size 2.16e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  36%|███▋      | 546/1500 [04:48<04:07,  3.85it/s, 255 steps of size 2.40e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  36%|███▋      | 547/1500 [04:48<03:44,  4.25it/s, 127 steps of size 2.86e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  37%|███▋      | 548/1500 [04:48<03:25,  4.63it/s, 127 steps of size 3.44e-02. acc. prob=0.88]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  37%|███▋      | 549/1500 [04:49<03:54,  4.05it/s, 255 steps of size 4.10e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  37%|███▋      | 550/1500 [04:49<03:32,  4.48it/s, 127 steps of size 4.66e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  37%|███▋      | 552/1500 [04:49<02:49,  5.60it/s, 127 steps of size 6.19e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  37%|███▋      | 554/1500 [04:49<02:13,  7.11it/s, 63 steps of size 7.27e-02. acc. prob=0.89] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  37%|███▋      | 556/1500 [04:49<01:52,  8.37it/s, 63 steps of size 5.90e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  37%|███▋      | 557/1500 [04:49<02:01,  7.79it/s, 127 steps of size 5.24e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  37%|███▋      | 558/1500 [04:50<02:08,  7.34it/s, 127 steps of size 6.19e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  37%|███▋      | 560/1500 [04:50<01:47,  8.71it/s, 63 steps of size 8.00e-02. acc. prob=0.89] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  37%|███▋      | 562/1500 [04:50<01:50,  8.50it/s, 127 steps of size 5.42e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  38%|███▊      | 563/1500 [04:50<01:59,  7.86it/s, 127 steps of size 6.14e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  38%|███▊      | 565/1500 [04:50<01:43,  9.06it/s, 63 steps of size 4.62e-02. acc. prob=0.89] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  38%|███▊      | 566/1500 [04:51<01:53,  8.22it/s, 127 steps of size 5.34e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  38%|███▊      | 567/1500 [04:51<02:02,  7.61it/s, 127 steps of size 4.94e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  38%|███▊      | 568/1500 [04:51<02:09,  7.17it/s, 127 steps of size 5.69e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  38%|███▊      | 570/1500 [04:51<01:47,  8.66it/s, 63 steps of size 5.89e-02. acc. prob=0.89] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  38%|███▊      | 572/1500 [04:51<01:35,  9.73it/s, 63 steps of size 7.80e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  38%|███▊      | 574/1500 [04:51<01:28, 10.48it/s, 63 steps of size 9.93e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  38%|███▊      | 576/1500 [04:52<01:36,  9.56it/s, 127 steps of size 5.06e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  39%|███▊      | 578/1500 [04:52<01:29, 10.28it/s, 63 steps of size 4.99e-02. acc. prob=0.89] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  39%|███▊      | 579/1500 [04:52<01:41,  9.09it/s, 127 steps of size 5.41e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  39%|███▊      | 581/1500 [04:52<01:45,  8.73it/s, 127 steps of size 3.19e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  39%|███▉      | 582/1500 [04:52<01:54,  8.03it/s, 127 steps of size 3.74e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  39%|███▉      | 583/1500 [04:53<02:02,  7.51it/s, 127 steps of size 4.40e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  39%|███▉      | 584/1500 [04:53<02:08,  7.12it/s, 127 steps of size 5.16e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  39%|███▉      | 586/1500 [04:53<01:46,  8.59it/s, 63 steps of size 6.83e-02. acc. prob=0.89] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  39%|███▉      | 588/1500 [04:53<01:48,  8.42it/s, 127 steps of size 4.59e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  39%|███▉      | 589/1500 [04:53<01:56,  7.81it/s, 127 steps of size 5.01e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  39%|███▉      | 590/1500 [04:53<02:03,  7.34it/s, 127 steps of size 5.82e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  39%|███▉      | 591/1500 [04:54<02:10,  6.99it/s, 127 steps of size 6.20e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  40%|███▉      | 593/1500 [04:54<01:44,  8.64it/s, 56 steps of size 6.10e-02. acc. prob=0.89] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  40%|███▉      | 595/1500 [04:54<01:33,  9.71it/s, 63 steps of size 6.93e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  40%|███▉      | 596/1500 [04:54<01:44,  8.65it/s, 127 steps of size 4.17e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  40%|███▉      | 597/1500 [04:54<01:54,  7.89it/s, 127 steps of size 4.85e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  40%|███▉      | 598/1500 [04:54<02:02,  7.35it/s, 127 steps of size 5.45e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  40%|███▉      | 599/1500 [04:55<02:09,  6.98it/s, 127 steps of size 5.48e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  40%|████      | 600/1500 [04:55<02:14,  6.72it/s, 127 steps of size 6.23e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  40%|████      | 602/1500 [04:55<01:47,  8.38it/s, 63 steps of size 7.86e-02. acc. prob=0.89] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  40%|████      | 604/1500 [04:55<01:48,  8.27it/s, 127 steps of size 3.01e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  40%|████      | 605/1500 [04:55<01:56,  7.68it/s, 127 steps of size 3.49e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  40%|████      | 606/1500 [04:55<02:03,  7.24it/s, 127 steps of size 3.82e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  40%|████      | 607/1500 [04:56<02:09,  6.91it/s, 127 steps of size 4.34e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  41%|████      | 608/1500 [04:56<02:13,  6.68it/s, 127 steps of size 4.99e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  41%|████      | 609/1500 [04:56<02:16,  6.51it/s, 127 steps of size 5.71e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  41%|████      | 611/1500 [04:56<01:48,  8.19it/s, 63 steps of size 6.90e-02. acc. prob=0.89] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  41%|████      | 613/1500 [04:56<01:34,  9.40it/s, 63 steps of size 8.95e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  41%|████      | 615/1500 [04:56<01:26, 10.26it/s, 63 steps of size 1.09e-01. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  41%|████      | 617/1500 [04:57<01:21, 10.87it/s, 63 steps of size 9.19e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  41%|████▏     | 619/1500 [04:57<01:17, 11.30it/s, 63 steps of size 7.36e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  41%|████▏     | 621/1500 [04:57<01:15, 11.60it/s, 63 steps of size 9.44e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  42%|████▏     | 623/1500 [04:57<01:14, 11.81it/s, 63 steps of size 8.04e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  42%|████▏     | 625/1500 [04:57<01:13, 11.95it/s, 63 steps of size 6.61e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  42%|████▏     | 627/1500 [04:57<01:12, 12.06it/s, 63 steps of size 8.50e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  42%|████▏     | 629/1500 [04:58<01:11, 12.14it/s, 63 steps of size 8.78e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  42%|████▏     | 631/1500 [04:58<01:11, 12.19it/s, 63 steps of size 8.38e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  42%|████▏     | 633/1500 [04:58<01:11, 12.21it/s, 63 steps of size 1.06e-01. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  42%|████▏     | 635/1500 [04:58<01:05, 13.22it/s, 63 steps of size 3.95e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  42%|████▏     | 636/1500 [04:58<01:19, 10.90it/s, 127 steps of size 4.35e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  42%|████▏     | 637/1500 [04:58<01:32,  9.38it/s, 127 steps of size 4.95e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  43%|████▎     | 638/1500 [04:59<01:42,  8.37it/s, 127 steps of size 5.64e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  43%|████▎     | 640/1500 [04:59<01:30,  9.55it/s, 63 steps of size 6.47e-02. acc. prob=0.89] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  43%|████▎     | 642/1500 [04:59<01:22, 10.39it/s, 63 steps of size 6.34e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  43%|████▎     | 644/1500 [04:59<01:18, 10.97it/s, 63 steps of size 6.96e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  43%|████▎     | 646/1500 [04:59<01:15, 11.37it/s, 63 steps of size 8.60e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  43%|████▎     | 648/1500 [04:59<01:13, 11.64it/s, 63 steps of size 9.36e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  43%|████▎     | 650/1500 [04:59<01:11, 11.85it/s, 63 steps of size 1.03e-01. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  43%|████▎     | 652/1500 [05:00<01:10, 11.99it/s, 63 steps of size 7.31e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  44%|████▎     | 654/1500 [05:00<01:10, 12.08it/s, 63 steps of size 9.12e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  44%|████▎     | 656/1500 [05:00<01:09, 12.14it/s, 63 steps of size 8.43e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  44%|████▍     | 658/1500 [05:00<01:09, 12.20it/s, 63 steps of size 9.92e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  44%|████▍     | 660/1500 [05:00<01:08, 12.23it/s, 63 steps of size 6.88e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  44%|████▍     | 662/1500 [05:00<01:08, 12.24it/s, 63 steps of size 8.78e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  44%|████▍     | 664/1500 [05:01<01:08, 12.25it/s, 63 steps of size 1.07e-01. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  44%|████▍     | 666/1500 [05:01<01:02, 13.28it/s, 31 steps of size 1.15e-01. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  45%|████▍     | 668/1500 [05:01<00:58, 14.10it/s, 63 steps of size 7.55e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  45%|████▍     | 670/1500 [05:01<01:11, 11.56it/s, 127 steps of size 5.22e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  45%|████▍     | 671/1500 [05:01<01:21, 10.14it/s, 119 steps of size 4.62e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  45%|████▍     | 672/1500 [05:01<01:26,  9.52it/s, 101 steps of size 4.85e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  45%|████▍     | 673/1500 [05:02<01:37,  8.46it/s, 127 steps of size 5.52e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  45%|████▍     | 674/1500 [05:02<01:46,  7.74it/s, 127 steps of size 5.02e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  45%|████▌     | 675/1500 [05:02<01:54,  7.23it/s, 127 steps of size 4.98e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  45%|████▌     | 676/1500 [05:02<01:59,  6.88it/s, 127 steps of size 5.57e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  45%|████▌     | 677/1500 [05:02<02:03,  6.65it/s, 127 steps of size 4.82e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  45%|████▌     | 678/1500 [05:02<02:06,  6.49it/s, 127 steps of size 5.35e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  45%|████▌     | 679/1500 [05:03<02:08,  6.38it/s, 127 steps of size 5.00e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  45%|████▌     | 680/1500 [05:03<02:10,  6.30it/s, 127 steps of size 5.57e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  45%|████▌     | 682/1500 [05:03<01:56,  7.03it/s, 127 steps of size 4.68e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  46%|████▌     | 683/1500 [05:03<02:00,  6.78it/s, 127 steps of size 5.29e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  46%|████▌     | 685/1500 [05:03<01:51,  7.29it/s, 127 steps of size 6.01e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  46%|████▌     | 686/1500 [05:04<01:56,  6.98it/s, 127 steps of size 6.39e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  46%|████▌     | 688/1500 [05:04<01:36,  8.41it/s, 63 steps of size 6.32e-02. acc. prob=0.89] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  46%|████▌     | 690/1500 [05:04<01:25,  9.48it/s, 63 steps of size 6.75e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  46%|████▌     | 692/1500 [05:04<01:18, 10.28it/s, 63 steps of size 8.53e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  46%|████▋     | 694/1500 [05:04<01:14, 10.85it/s, 63 steps of size 3.15e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  46%|████▋     | 695/1500 [05:04<01:25,  9.41it/s, 127 steps of size 3.54e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  46%|████▋     | 696/1500 [05:05<01:35,  8.43it/s, 127 steps of size 4.01e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  46%|████▋     | 697/1500 [05:05<01:43,  7.75it/s, 127 steps of size 4.36e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  47%|████▋     | 698/1500 [05:05<01:50,  7.26it/s, 127 steps of size 4.94e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  47%|████▋     | 699/1500 [05:05<01:55,  6.92it/s, 127 steps of size 5.19e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  47%|████▋     | 700/1500 [05:05<01:59,  6.68it/s, 127 steps of size 5.85e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  47%|████▋     | 701/1500 [05:05<02:02,  6.51it/s, 127 steps of size 6.50e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  47%|████▋     | 703/1500 [05:05<01:36,  8.24it/s, 63 steps of size 7.41e-02. acc. prob=0.89] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  47%|████▋     | 705/1500 [05:06<01:24,  9.46it/s, 63 steps of size 8.82e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  47%|████▋     | 707/1500 [05:06<01:16, 10.32it/s, 63 steps of size 9.52e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  47%|████▋     | 709/1500 [05:06<01:12, 10.90it/s, 63 steps of size 1.08e-01. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  47%|████▋     | 711/1500 [05:06<01:04, 12.28it/s, 31 steps of size 1.01e-01. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  48%|████▊     | 713/1500 [05:06<01:04, 12.28it/s, 63 steps of size 8.01e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  48%|████▊     | 715/1500 [05:06<01:03, 12.29it/s, 63 steps of size 8.61e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  48%|████▊     | 717/1500 [05:07<01:03, 12.30it/s, 63 steps of size 8.79e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  48%|████▊     | 719/1500 [05:07<01:03, 12.31it/s, 63 steps of size 6.48e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  48%|████▊     | 721/1500 [05:07<01:03, 12.29it/s, 63 steps of size 7.88e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  48%|████▊     | 723/1500 [05:07<01:03, 12.29it/s, 63 steps of size 6.91e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  48%|████▊     | 725/1500 [05:07<01:03, 12.29it/s, 63 steps of size 8.73e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  48%|████▊     | 727/1500 [05:07<01:03, 12.26it/s, 63 steps of size 1.02e-01. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  49%|████▊     | 729/1500 [05:08<01:02, 12.26it/s, 63 steps of size 1.02e-01. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  49%|████▊     | 731/1500 [05:08<00:57, 13.27it/s, 31 steps of size 1.10e-01. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  49%|████▉     | 734/1500 [05:08<00:51, 14.95it/s, 63 steps of size 1.09e-01. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  49%|████▉     | 736/1500 [05:08<00:54, 14.12it/s, 63 steps of size 8.92e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  49%|████▉     | 738/1500 [05:08<00:56, 13.54it/s, 63 steps of size 6.68e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  49%|████▉     | 740/1500 [05:08<00:53, 14.11it/s, 63 steps of size 7.35e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  49%|████▉     | 742/1500 [05:08<00:55, 13.54it/s, 63 steps of size 8.44e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  50%|████▉     | 745/1500 [05:09<00:56, 13.41it/s, 127 steps of size 2.71e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  50%|████▉     | 746/1500 [05:09<01:06, 11.33it/s, 127 steps of size 2.99e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  50%|████▉     | 747/1500 [05:09<01:39,  7.60it/s, 255 steps of size 3.34e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  50%|████▉     | 748/1500 [05:10<02:09,  5.81it/s, 255 steps of size 3.71e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  50%|████▉     | 749/1500 [05:10<02:07,  5.88it/s, 127 steps of size 3.58e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  50%|█████     | 750/1500 [05:10<02:06,  5.93it/s, 127 steps of size 4.00e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  50%|█████     | 751/1500 [05:10<02:05,  5.97it/s, 127 steps of size 4.38e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  50%|█████     | 752/1500 [05:10<02:04,  6.00it/s, 127 steps of size 4.71e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  50%|█████     | 753/1500 [05:10<02:03,  6.03it/s, 127 steps of size 5.17e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  50%|█████     | 754/1500 [05:11<02:03,  6.05it/s, 127 steps of size 5.57e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  50%|█████     | 755/1500 [05:11<02:02,  6.06it/s, 127 steps of size 6.17e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  50%|█████     | 757/1500 [05:11<01:34,  7.87it/s, 63 steps of size 7.12e-02. acc. prob=0.89] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  51%|█████     | 759/1500 [05:11<01:20,  9.17it/s, 63 steps of size 8.48e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  51%|█████     | 761/1500 [05:11<01:13, 10.08it/s, 63 steps of size 9.42e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  51%|█████     | 763/1500 [05:11<01:08, 10.75it/s, 63 steps of size 1.03e-01. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  51%|█████     | 765/1500 [05:11<01:05, 11.25it/s, 63 steps of size 1.02e-01. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  51%|█████     | 767/1500 [05:12<00:58, 12.51it/s, 63 steps of size 7.19e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  51%|█████▏    | 769/1500 [05:12<00:58, 12.42it/s, 63 steps of size 3.91e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  51%|█████▏    | 770/1500 [05:12<01:09, 10.45it/s, 127 steps of size 3.90e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  51%|█████▏    | 771/1500 [05:12<01:19,  9.11it/s, 127 steps of size 4.34e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  51%|█████▏    | 772/1500 [05:12<01:28,  8.22it/s, 127 steps of size 4.48e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  52%|█████▏    | 773/1500 [05:12<01:35,  7.58it/s, 127 steps of size 4.85e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  52%|█████▏    | 774/1500 [05:13<01:41,  7.13it/s, 127 steps of size 5.41e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  52%|█████▏    | 775/1500 [05:13<01:46,  6.82it/s, 127 steps of size 6.02e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  52%|█████▏    | 777/1500 [05:13<01:25,  8.46it/s, 63 steps of size 5.11e-02. acc. prob=0.89] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  52%|█████▏    | 779/1500 [05:13<01:14,  9.62it/s, 63 steps of size 5.73e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  52%|█████▏    | 780/1500 [05:13<01:24,  8.56it/s, 127 steps of size 6.08e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  52%|█████▏    | 782/1500 [05:13<01:25,  8.40it/s, 127 steps of size 3.95e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  52%|█████▏    | 783/1500 [05:14<01:32,  7.77it/s, 127 steps of size 4.36e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  52%|█████▏    | 784/1500 [05:14<01:38,  7.29it/s, 127 steps of size 4.30e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  52%|█████▏    | 785/1500 [05:14<01:43,  6.94it/s, 127 steps of size 3.71e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  52%|█████▏    | 786/1500 [05:14<01:46,  6.71it/s, 127 steps of size 4.00e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  52%|█████▏    | 787/1500 [05:14<01:49,  6.54it/s, 127 steps of size 4.40e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  53%|█████▎    | 788/1500 [05:14<01:53,  6.25it/s, 127 steps of size 4.82e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  53%|█████▎    | 789/1500 [05:15<01:54,  6.20it/s, 127 steps of size 5.29e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  53%|█████▎    | 790/1500 [05:15<01:54,  6.18it/s, 127 steps of size 5.86e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  53%|█████▎    | 792/1500 [05:15<01:28,  7.97it/s, 63 steps of size 4.77e-02. acc. prob=0.89] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  53%|█████▎    | 793/1500 [05:15<01:35,  7.43it/s, 127 steps of size 4.65e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  53%|█████▎    | 794/1500 [05:15<01:40,  7.03it/s, 127 steps of size 5.04e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  53%|█████▎    | 795/1500 [05:15<01:45,  6.70it/s, 127 steps of size 5.59e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  53%|█████▎    | 796/1500 [05:16<01:47,  6.52it/s, 127 steps of size 5.91e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  53%|█████▎    | 798/1500 [05:16<01:25,  8.23it/s, 63 steps of size 6.96e-02. acc. prob=0.89] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  53%|█████▎    | 800/1500 [05:16<01:14,  9.43it/s, 63 steps of size 8.15e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  53%|█████▎    | 802/1500 [05:16<01:07, 10.29it/s, 63 steps of size 9.18e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  54%|█████▎    | 804/1500 [05:16<00:59, 11.77it/s, 31 steps of size 5.73e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  54%|█████▎    | 806/1500 [05:16<01:07, 10.29it/s, 127 steps of size 6.87e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  54%|█████▍    | 808/1500 [05:17<01:03, 10.85it/s, 63 steps of size 5.58e-02. acc. prob=0.89] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  54%|█████▍    | 809/1500 [05:17<01:13,  9.46it/s, 127 steps of size 5.92e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  54%|█████▍    | 811/1500 [05:17<01:06, 10.28it/s, 63 steps of size 7.24e-02. acc. prob=0.89] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  54%|█████▍    | 813/1500 [05:17<01:03, 10.88it/s, 63 steps of size 7.38e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  54%|█████▍    | 815/1500 [05:17<01:00, 11.30it/s, 63 steps of size 7.37e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  54%|█████▍    | 817/1500 [05:17<00:58, 11.58it/s, 63 steps of size 8.09e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  55%|█████▍    | 819/1500 [05:18<00:57, 11.79it/s, 63 steps of size 9.69e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  55%|█████▍    | 821/1500 [05:18<01:01, 11.10it/s, 127 steps of size 6.17e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  55%|█████▍    | 822/1500 [05:18<01:09,  9.69it/s, 127 steps of size 6.83e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  55%|█████▍    | 824/1500 [05:18<01:04, 10.44it/s, 63 steps of size 7.88e-02. acc. prob=0.89] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  55%|█████▌    | 826/1500 [05:18<01:01, 10.98it/s, 63 steps of size 8.87e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  55%|█████▌    | 828/1500 [05:18<00:59, 11.37it/s, 63 steps of size 1.05e-01. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  55%|█████▌    | 830/1500 [05:19<00:53, 12.59it/s, 63 steps of size 7.83e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  55%|█████▌    | 832/1500 [05:19<00:53, 12.50it/s, 63 steps of size 8.98e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  56%|█████▌    | 834/1500 [05:19<00:53, 12.44it/s, 63 steps of size 1.01e-01. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  56%|█████▌    | 836/1500 [05:19<00:53, 12.39it/s, 63 steps of size 1.12e-01. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  56%|█████▌    | 838/1500 [05:19<01:02, 10.65it/s, 127 steps of size 5.95e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  56%|█████▌    | 839/1500 [05:19<01:10,  9.41it/s, 127 steps of size 6.44e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  56%|█████▌    | 841/1500 [05:20<01:04, 10.22it/s, 63 steps of size 7.18e-02. acc. prob=0.89] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  56%|█████▌    | 843/1500 [05:20<01:00, 10.80it/s, 63 steps of size 6.65e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  56%|█████▋    | 844/1500 [05:20<01:09,  9.43it/s, 127 steps of size 6.68e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  56%|█████▋    | 846/1500 [05:20<01:03, 10.26it/s, 63 steps of size 7.93e-02. acc. prob=0.89] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  57%|█████▋    | 848/1500 [05:20<00:59, 10.87it/s, 63 steps of size 7.11e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  57%|█████▋    | 850/1500 [05:20<00:57, 11.29it/s, 63 steps of size 4.45e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  57%|█████▋    | 851/1500 [05:21<01:06,  9.75it/s, 127 steps of size 4.84e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  57%|█████▋    | 852/1500 [05:21<01:14,  8.64it/s, 127 steps of size 5.16e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  57%|█████▋    | 854/1500 [05:21<01:08,  9.42it/s, 63 steps of size 6.14e-02. acc. prob=0.89] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  57%|█████▋    | 855/1500 [05:21<01:16,  8.44it/s, 127 steps of size 6.00e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  57%|█████▋    | 856/1500 [05:21<01:22,  7.76it/s, 127 steps of size 6.60e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  57%|█████▋    | 858/1500 [05:21<01:10,  9.09it/s, 63 steps of size 6.79e-02. acc. prob=0.89] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  57%|█████▋    | 860/1500 [05:22<01:03, 10.03it/s, 63 steps of size 6.77e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  57%|█████▋    | 861/1500 [05:22<01:12,  8.86it/s, 127 steps of size 7.19e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  58%|█████▊    | 863/1500 [05:22<01:04,  9.88it/s, 63 steps of size 8.64e-02. acc. prob=0.89] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  58%|█████▊    | 865/1500 [05:22<00:59, 10.60it/s, 63 steps of size 8.47e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  58%|█████▊    | 867/1500 [05:22<00:57, 11.09it/s, 63 steps of size 8.73e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  58%|█████▊    | 869/1500 [05:22<00:55, 11.44it/s, 63 steps of size 9.90e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  58%|█████▊    | 871/1500 [05:23<00:52, 11.91it/s, 55 steps of size 1.06e-01. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  58%|█████▊    | 873/1500 [05:23<00:52, 12.02it/s, 63 steps of size 6.77e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  58%|█████▊    | 875/1500 [05:23<00:51, 12.11it/s, 63 steps of size 7.44e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  58%|█████▊    | 877/1500 [05:23<00:51, 12.18it/s, 63 steps of size 8.32e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  59%|█████▊    | 879/1500 [05:23<00:51, 12.17it/s, 63 steps of size 7.15e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  59%|█████▊    | 881/1500 [05:23<00:50, 12.20it/s, 63 steps of size 8.18e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  59%|█████▉    | 883/1500 [05:24<00:50, 12.22it/s, 63 steps of size 6.73e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  59%|█████▉    | 885/1500 [05:24<00:50, 12.23it/s, 63 steps of size 4.15e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  59%|█████▉    | 886/1500 [05:24<00:59, 10.38it/s, 127 steps of size 4.46e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  59%|█████▉    | 887/1500 [05:24<01:07,  9.08it/s, 127 steps of size 4.85e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  59%|█████▉    | 888/1500 [05:24<01:15,  8.15it/s, 127 steps of size 5.20e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  59%|█████▉    | 889/1500 [05:24<01:21,  7.51it/s, 127 steps of size 5.51e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  59%|█████▉    | 890/1500 [05:25<01:26,  7.07it/s, 127 steps of size 6.06e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  59%|█████▉    | 892/1500 [05:25<01:10,  8.61it/s, 63 steps of size 5.91e-02. acc. prob=0.89] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  60%|█████▉    | 894/1500 [05:25<01:11,  8.43it/s, 127 steps of size 6.16e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  60%|█████▉    | 896/1500 [05:25<01:03,  9.46it/s, 63 steps of size 7.36e-02. acc. prob=0.89] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  60%|█████▉    | 898/1500 [05:25<00:58, 10.25it/s, 63 steps of size 7.69e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  60%|██████    | 900/1500 [05:25<00:55, 10.83it/s, 63 steps of size 9.06e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  60%|██████    | 902/1500 [05:26<00:53, 11.25it/s, 63 steps of size 8.37e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  60%|██████    | 904/1500 [05:26<00:51, 11.54it/s, 63 steps of size 8.09e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  60%|██████    | 906/1500 [05:26<00:50, 11.77it/s, 63 steps of size 8.72e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  61%|██████    | 908/1500 [05:26<00:45, 12.88it/s, 31 steps of size 1.01e-01. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  61%|██████    | 911/1500 [05:26<00:37, 15.91it/s, 31 steps of size 1.18e-01. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  61%|██████    | 912/1500 [05:26<00:50, 11.72it/s, 159 steps of size 7.81e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  61%|██████    | 914/1500 [05:27<00:49, 11.89it/s, 63 steps of size 7.15e-02. acc. prob=0.89] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  61%|██████    | 916/1500 [05:27<00:48, 12.00it/s, 63 steps of size 8.25e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  61%|██████    | 917/1500 [05:27<00:56, 10.23it/s, 127 steps of size 8.45e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  61%|██████▏   | 919/1500 [05:27<00:53, 10.84it/s, 63 steps of size 5.67e-02. acc. prob=0.89] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  61%|██████▏   | 921/1500 [05:27<00:59,  9.71it/s, 127 steps of size 5.17e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  62%|██████▏   | 923/1500 [05:27<00:55, 10.35it/s, 63 steps of size 5.91e-02. acc. prob=0.89] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  62%|██████▏   | 925/1500 [05:28<00:52, 10.87it/s, 63 steps of size 6.98e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  62%|██████▏   | 927/1500 [05:28<00:50, 11.28it/s, 63 steps of size 7.10e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  62%|██████▏   | 929/1500 [05:28<00:49, 11.55it/s, 63 steps of size 8.48e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  62%|██████▏   | 931/1500 [05:28<00:48, 11.75it/s, 63 steps of size 9.81e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  62%|██████▏   | 933/1500 [05:28<00:47, 11.91it/s, 63 steps of size 9.63e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  62%|██████▏   | 935/1500 [05:28<00:47, 12.01it/s, 63 steps of size 8.58e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  63%|██████▎   | 938/1500 [05:29<00:41, 13.55it/s, 63 steps of size 7.78e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  63%|██████▎   | 940/1500 [05:29<00:42, 13.27it/s, 60 steps of size 8.93e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  63%|██████▎   | 942/1500 [05:29<00:42, 12.99it/s, 63 steps of size 8.78e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  63%|██████▎   | 944/1500 [05:29<00:43, 12.77it/s, 63 steps of size 1.01e-01. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  63%|██████▎   | 946/1500 [05:29<00:43, 12.61it/s, 63 steps of size 1.06e-01. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  63%|██████▎   | 948/1500 [05:29<00:44, 12.49it/s, 63 steps of size 6.04e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  63%|██████▎   | 950/1500 [05:30<00:44, 12.44it/s, 63 steps of size 7.09e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  64%|██████▎   | 953/1500 [05:30<00:38, 14.20it/s, 63 steps of size 8.10e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  64%|██████▎   | 955/1500 [05:30<00:45, 11.85it/s, 127 steps of size 4.91e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  64%|██████▍   | 957/1500 [05:30<00:51, 10.52it/s, 127 steps of size 7.48e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  64%|██████▍   | 959/1500 [05:30<00:46, 11.52it/s, 39 steps of size 6.23e-02. acc. prob=0.89] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  64%|██████▍   | 961/1500 [05:31<00:46, 11.67it/s, 63 steps of size 7.49e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  64%|██████▍   | 963/1500 [05:31<00:45, 11.83it/s, 63 steps of size 7.38e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  64%|██████▍   | 965/1500 [05:31<00:44, 11.95it/s, 63 steps of size 1.35e-01. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  65%|██████▍   | 968/1500 [05:31<00:38, 13.84it/s, 63 steps of size 5.07e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  65%|██████▍   | 970/1500 [05:31<00:39, 13.39it/s, 63 steps of size 8.59e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  65%|██████▍   | 972/1500 [05:31<00:40, 13.06it/s, 63 steps of size 8.59e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  65%|██████▍   | 974/1500 [05:32<00:40, 12.83it/s, 63 steps of size 3.39e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  65%|██████▌   | 975/1500 [05:32<01:03,  8.31it/s, 255 steps of size 3.92e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  65%|██████▌   | 976/1500 [05:32<01:07,  7.76it/s, 127 steps of size 5.03e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  65%|██████▌   | 977/1500 [05:32<01:11,  7.32it/s, 127 steps of size 6.00e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  65%|██████▌   | 979/1500 [05:32<01:00,  8.66it/s, 63 steps of size 1.04e-01. acc. prob=0.89] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  65%|██████▌   | 981/1500 [05:33<00:53,  9.66it/s, 63 steps of size 5.62e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  65%|██████▌   | 982/1500 [05:33<00:59,  8.64it/s, 127 steps of size 7.31e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  66%|██████▌   | 984/1500 [05:33<00:53,  9.68it/s, 63 steps of size 6.64e-02. acc. prob=0.89] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  66%|██████▌   | 986/1500 [05:33<00:49, 10.43it/s, 63 steps of size 8.12e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  66%|██████▌   | 988/1500 [05:33<00:46, 10.97it/s, 63 steps of size 1.11e-01. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  66%|██████▌   | 990/1500 [05:33<00:51,  9.89it/s, 127 steps of size 6.25e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  66%|██████▌   | 992/1500 [05:34<00:48, 10.53it/s, 63 steps of size 9.20e-02. acc. prob=0.89] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  66%|██████▋   | 994/1500 [05:34<00:46, 10.97it/s, 63 steps of size 8.01e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  66%|██████▋   | 996/1500 [05:34<00:44, 11.34it/s, 63 steps of size 4.96e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  66%|██████▋   | 997/1500 [05:34<00:51,  9.83it/s, 127 steps of size 6.38e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "warmup:  67%|██████▋   | 999/1500 [05:34<00:47, 10.51it/s, 63 steps of size 8.27e-02. acc. prob=0.89] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  67%|██████▋   | 1001/1500 [05:34<00:45, 11.01it/s, 63 steps of size 7.17e-02. acc. prob=0.59]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  67%|██████▋   | 1003/1500 [05:35<00:43, 11.36it/s, 63 steps of size 7.17e-02. acc. prob=0.78]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  67%|██████▋   | 1005/1500 [05:35<00:42, 11.63it/s, 63 steps of size 7.17e-02. acc. prob=0.83]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  67%|██████▋   | 1007/1500 [05:35<00:41, 11.83it/s, 63 steps of size 7.17e-02. acc. prob=0.85]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  67%|██████▋   | 1009/1500 [05:35<00:41, 11.95it/s, 63 steps of size 7.17e-02. acc. prob=0.87]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  67%|██████▋   | 1011/1500 [05:35<00:40, 12.05it/s, 63 steps of size 7.17e-02. acc. prob=0.89]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  68%|██████▊   | 1013/1500 [05:35<00:40, 12.12it/s, 63 steps of size 7.17e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  68%|██████▊   | 1015/1500 [05:36<00:39, 12.17it/s, 63 steps of size 7.17e-02. acc. prob=0.90]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  68%|██████▊   | 1017/1500 [05:36<00:39, 12.20it/s, 63 steps of size 7.17e-02. acc. prob=0.91]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  68%|██████▊   | 1019/1500 [05:36<00:39, 12.22it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  68%|██████▊   | 1021/1500 [05:36<00:39, 12.23it/s, 63 steps of size 7.17e-02. acc. prob=0.93]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  68%|██████▊   | 1023/1500 [05:36<00:38, 12.25it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  68%|██████▊   | 1025/1500 [05:36<00:38, 12.27it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  68%|██████▊   | 1027/1500 [05:37<00:38, 12.27it/s, 63 steps of size 7.17e-02. acc. prob=0.93]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  69%|██████▊   | 1029/1500 [05:37<00:36, 13.07it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  69%|██████▊   | 1031/1500 [05:37<00:36, 12.79it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  69%|██████▉   | 1033/1500 [05:37<00:36, 12.63it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  69%|██████▉   | 1035/1500 [05:37<00:37, 12.54it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  69%|██████▉   | 1037/1500 [05:37<00:37, 12.47it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  69%|██████▉   | 1039/1500 [05:37<00:37, 12.42it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  69%|██████▉   | 1042/1500 [05:38<00:33, 13.78it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  70%|██████▉   | 1044/1500 [05:38<00:34, 13.34it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  70%|██████▉   | 1046/1500 [05:38<00:34, 13.03it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  70%|██████▉   | 1048/1500 [05:38<00:35, 12.81it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  70%|███████   | 1050/1500 [05:38<00:35, 12.66it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  70%|███████   | 1052/1500 [05:38<00:35, 12.55it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  70%|███████   | 1054/1500 [05:39<00:35, 12.48it/s, 63 steps of size 7.17e-02. acc. prob=0.93]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  70%|███████   | 1056/1500 [05:39<00:35, 12.42it/s, 63 steps of size 7.17e-02. acc. prob=0.93]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  71%|███████   | 1058/1500 [05:39<00:35, 12.35it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  71%|███████   | 1060/1500 [05:39<00:35, 12.33it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  71%|███████   | 1062/1500 [05:39<00:35, 12.32it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  71%|███████   | 1064/1500 [05:39<00:35, 12.29it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  71%|███████   | 1066/1500 [05:40<00:35, 12.29it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  71%|███████   | 1068/1500 [05:40<00:35, 12.26it/s, 63 steps of size 7.17e-02. acc. prob=0.93]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  71%|███████▏  | 1070/1500 [05:40<00:35, 12.26it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  71%|███████▏  | 1072/1500 [05:40<00:34, 12.27it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  72%|███████▏  | 1074/1500 [05:40<00:34, 12.26it/s, 63 steps of size 7.17e-02. acc. prob=0.91]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  72%|███████▏  | 1076/1500 [05:40<00:34, 12.26it/s, 63 steps of size 7.17e-02. acc. prob=0.91]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  72%|███████▏  | 1078/1500 [05:41<00:34, 12.27it/s, 63 steps of size 7.17e-02. acc. prob=0.91]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  72%|███████▏  | 1080/1500 [05:41<00:34, 12.27it/s, 63 steps of size 7.17e-02. acc. prob=0.91]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  72%|███████▏  | 1082/1500 [05:41<00:34, 12.28it/s, 63 steps of size 7.17e-02. acc. prob=0.91]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  72%|███████▏  | 1084/1500 [05:41<00:33, 12.29it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  72%|███████▏  | 1086/1500 [05:41<00:33, 12.30it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  73%|███████▎  | 1088/1500 [05:41<00:33, 12.30it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  73%|███████▎  | 1090/1500 [05:42<00:33, 12.29it/s, 63 steps of size 7.17e-02. acc. prob=0.91]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  73%|███████▎  | 1092/1500 [05:42<00:33, 12.30it/s, 63 steps of size 7.17e-02. acc. prob=0.91]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  73%|███████▎  | 1094/1500 [05:42<00:31, 13.01it/s, 63 steps of size 7.17e-02. acc. prob=0.91]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  73%|███████▎  | 1096/1500 [05:42<00:31, 12.78it/s, 63 steps of size 7.17e-02. acc. prob=0.91]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  73%|███████▎  | 1098/1500 [05:42<00:31, 12.63it/s, 63 steps of size 7.17e-02. acc. prob=0.91]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  73%|███████▎  | 1100/1500 [05:42<00:31, 12.54it/s, 63 steps of size 7.17e-02. acc. prob=0.91]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  73%|███████▎  | 1102/1500 [05:43<00:31, 12.52it/s, 63 steps of size 7.17e-02. acc. prob=0.91]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  74%|███████▎  | 1104/1500 [05:43<00:31, 12.45it/s, 63 steps of size 7.17e-02. acc. prob=0.91]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  74%|███████▎  | 1106/1500 [05:43<00:31, 12.47it/s, 63 steps of size 7.17e-02. acc. prob=0.91]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  74%|███████▍  | 1108/1500 [05:43<00:31, 12.42it/s, 63 steps of size 7.17e-02. acc. prob=0.91]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  74%|███████▍  | 1110/1500 [05:43<00:31, 12.36it/s, 63 steps of size 7.17e-02. acc. prob=0.91]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  74%|███████▍  | 1112/1500 [05:43<00:31, 12.30it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  74%|███████▍  | 1114/1500 [05:43<00:31, 12.29it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  74%|███████▍  | 1116/1500 [05:44<00:31, 12.30it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  75%|███████▍  | 1118/1500 [05:44<00:31, 12.28it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  75%|███████▍  | 1120/1500 [05:44<00:30, 12.30it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  75%|███████▍  | 1122/1500 [05:44<00:35, 10.72it/s, 127 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  75%|███████▍  | 1124/1500 [05:44<00:38,  9.80it/s, 127 steps of size 7.17e-02. acc. prob=0.91]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  75%|███████▌  | 1126/1500 [05:45<00:35, 10.43it/s, 63 steps of size 7.17e-02. acc. prob=0.91] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  75%|███████▌  | 1128/1500 [05:45<00:34, 10.92it/s, 63 steps of size 7.17e-02. acc. prob=0.91]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  75%|███████▌  | 1130/1500 [05:45<00:32, 11.30it/s, 63 steps of size 7.17e-02. acc. prob=0.91]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  75%|███████▌  | 1131/1500 [05:45<00:37,  9.84it/s, 127 steps of size 7.17e-02. acc. prob=0.91]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  76%|███████▌  | 1133/1500 [05:45<00:34, 10.61it/s, 63 steps of size 7.17e-02. acc. prob=0.91] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  76%|███████▌  | 1135/1500 [05:45<00:32, 11.10it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  76%|███████▌  | 1137/1500 [05:46<00:31, 11.44it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  76%|███████▌  | 1139/1500 [05:46<00:30, 11.68it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  76%|███████▌  | 1141/1500 [05:46<00:30, 11.85it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  76%|███████▌  | 1143/1500 [05:46<00:29, 11.97it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  76%|███████▋  | 1145/1500 [05:46<00:29, 12.09it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  76%|███████▋  | 1147/1500 [05:46<00:29, 12.13it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  77%|███████▋  | 1149/1500 [05:47<00:28, 12.18it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  77%|███████▋  | 1151/1500 [05:47<00:28, 12.22it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  77%|███████▋  | 1153/1500 [05:47<00:28, 12.26it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  77%|███████▋  | 1155/1500 [05:47<00:28, 12.28it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  77%|███████▋  | 1157/1500 [05:47<00:27, 12.29it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  77%|███████▋  | 1159/1500 [05:47<00:27, 12.30it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  77%|███████▋  | 1161/1500 [05:48<00:27, 12.29it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  78%|███████▊  | 1163/1500 [05:48<00:27, 12.29it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  78%|███████▊  | 1165/1500 [05:48<00:27, 12.29it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  78%|███████▊  | 1167/1500 [05:48<00:27, 12.30it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  78%|███████▊  | 1169/1500 [05:48<00:26, 12.30it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  78%|███████▊  | 1171/1500 [05:48<00:26, 12.30it/s, 63 steps of size 7.17e-02. acc. prob=0.91]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  78%|███████▊  | 1173/1500 [05:49<00:26, 12.31it/s, 63 steps of size 7.17e-02. acc. prob=0.91]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  78%|███████▊  | 1175/1500 [05:49<00:26, 12.31it/s, 63 steps of size 7.17e-02. acc. prob=0.91]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  78%|███████▊  | 1177/1500 [05:49<00:26, 12.30it/s, 63 steps of size 7.17e-02. acc. prob=0.91]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  79%|███████▊  | 1179/1500 [05:49<00:26, 12.30it/s, 63 steps of size 7.17e-02. acc. prob=0.91]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  79%|███████▊  | 1181/1500 [05:49<00:25, 12.29it/s, 63 steps of size 7.17e-02. acc. prob=0.91]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  79%|███████▉  | 1183/1500 [05:49<00:25, 12.30it/s, 63 steps of size 7.17e-02. acc. prob=0.91]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  79%|███████▉  | 1185/1500 [05:49<00:25, 12.25it/s, 63 steps of size 7.17e-02. acc. prob=0.91]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  79%|███████▉  | 1187/1500 [05:50<00:25, 12.24it/s, 63 steps of size 7.17e-02. acc. prob=0.91]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  79%|███████▉  | 1189/1500 [05:50<00:25, 12.26it/s, 63 steps of size 7.17e-02. acc. prob=0.91]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  79%|███████▉  | 1191/1500 [05:50<00:25, 12.27it/s, 63 steps of size 7.17e-02. acc. prob=0.91]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  80%|███████▉  | 1193/1500 [05:50<00:25, 12.27it/s, 63 steps of size 7.17e-02. acc. prob=0.91]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  80%|███████▉  | 1195/1500 [05:50<00:24, 12.28it/s, 63 steps of size 7.17e-02. acc. prob=0.91]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  80%|███████▉  | 1197/1500 [05:50<00:24, 12.29it/s, 63 steps of size 7.17e-02. acc. prob=0.91]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  80%|███████▉  | 1199/1500 [05:51<00:24, 12.30it/s, 63 steps of size 7.17e-02. acc. prob=0.91]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  80%|████████  | 1201/1500 [05:51<00:24, 12.30it/s, 63 steps of size 7.17e-02. acc. prob=0.91]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  80%|████████  | 1203/1500 [05:51<00:24, 12.31it/s, 63 steps of size 7.17e-02. acc. prob=0.91]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  80%|████████  | 1205/1500 [05:51<00:23, 12.31it/s, 63 steps of size 7.17e-02. acc. prob=0.91]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  80%|████████  | 1207/1500 [05:51<00:23, 12.54it/s, 55 steps of size 7.17e-02. acc. prob=0.91]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  81%|████████  | 1209/1500 [05:51<00:23, 12.46it/s, 63 steps of size 7.17e-02. acc. prob=0.91]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  81%|████████  | 1211/1500 [05:52<00:23, 12.40it/s, 63 steps of size 7.17e-02. acc. prob=0.91]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  81%|████████  | 1213/1500 [05:52<00:23, 12.37it/s, 63 steps of size 7.17e-02. acc. prob=0.91]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  81%|████████  | 1215/1500 [05:52<00:23, 12.35it/s, 63 steps of size 7.17e-02. acc. prob=0.91]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  81%|████████  | 1217/1500 [05:52<00:22, 12.34it/s, 63 steps of size 7.17e-02. acc. prob=0.91]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  81%|████████▏ | 1219/1500 [05:52<00:22, 12.33it/s, 63 steps of size 7.17e-02. acc. prob=0.91]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  81%|████████▏ | 1221/1500 [05:52<00:22, 12.32it/s, 63 steps of size 7.17e-02. acc. prob=0.91]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  82%|████████▏ | 1223/1500 [05:53<00:22, 12.26it/s, 63 steps of size 7.17e-02. acc. prob=0.91]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  82%|████████▏ | 1225/1500 [05:53<00:22, 12.26it/s, 63 steps of size 7.17e-02. acc. prob=0.91]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  82%|████████▏ | 1227/1500 [05:53<00:22, 12.26it/s, 63 steps of size 7.17e-02. acc. prob=0.91]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  82%|████████▏ | 1228/1500 [05:53<00:24, 11.00it/s, 104 steps of size 7.17e-02. acc. prob=0.91]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  82%|████████▏ | 1230/1500 [05:53<00:23, 11.40it/s, 63 steps of size 7.17e-02. acc. prob=0.91] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  82%|████████▏ | 1232/1500 [05:53<00:22, 11.68it/s, 63 steps of size 7.17e-02. acc. prob=0.91]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  82%|████████▏ | 1234/1500 [05:54<00:22, 11.87it/s, 63 steps of size 7.17e-02. acc. prob=0.91]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  82%|████████▏ | 1236/1500 [05:54<00:22, 12.00it/s, 63 steps of size 7.17e-02. acc. prob=0.91]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  83%|████████▎ | 1238/1500 [05:54<00:21, 12.09it/s, 63 steps of size 7.17e-02. acc. prob=0.91]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  83%|████████▎ | 1240/1500 [05:54<00:21, 12.15it/s, 63 steps of size 7.17e-02. acc. prob=0.91]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  83%|████████▎ | 1242/1500 [05:54<00:21, 12.18it/s, 63 steps of size 7.17e-02. acc. prob=0.91]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  83%|████████▎ | 1244/1500 [05:54<00:20, 12.20it/s, 63 steps of size 7.17e-02. acc. prob=0.91]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  83%|████████▎ | 1246/1500 [05:55<00:20, 12.22it/s, 63 steps of size 7.17e-02. acc. prob=0.91]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  83%|████████▎ | 1248/1500 [05:55<00:20, 12.24it/s, 63 steps of size 7.17e-02. acc. prob=0.91]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  83%|████████▎ | 1250/1500 [05:55<00:20, 12.25it/s, 63 steps of size 7.17e-02. acc. prob=0.91]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  83%|████████▎ | 1252/1500 [05:55<00:20, 12.27it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  84%|████████▎ | 1254/1500 [05:55<00:20, 12.27it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  84%|████████▎ | 1256/1500 [05:55<00:19, 12.29it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  84%|████████▍ | 1258/1500 [05:55<00:19, 12.29it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  84%|████████▍ | 1260/1500 [05:56<00:19, 12.28it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  84%|████████▍ | 1262/1500 [05:56<00:19, 12.25it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  84%|████████▍ | 1264/1500 [05:56<00:19, 12.25it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  84%|████████▍ | 1266/1500 [05:56<00:19, 12.27it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  85%|████████▍ | 1268/1500 [05:56<00:18, 12.27it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  85%|████████▍ | 1270/1500 [05:56<00:18, 12.28it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  85%|████████▍ | 1272/1500 [05:57<00:18, 12.29it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  85%|████████▍ | 1274/1500 [05:57<00:18, 12.29it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  85%|████████▌ | 1276/1500 [05:57<00:18, 12.29it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  85%|████████▌ | 1278/1500 [05:57<00:18, 12.31it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  85%|████████▌ | 1280/1500 [05:57<00:17, 12.31it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  85%|████████▌ | 1282/1500 [05:57<00:17, 12.31it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  86%|████████▌ | 1284/1500 [05:58<00:20, 10.67it/s, 127 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  86%|████████▌ | 1286/1500 [05:58<00:19, 11.11it/s, 63 steps of size 7.17e-02. acc. prob=0.92] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  86%|████████▌ | 1288/1500 [05:58<00:18, 11.44it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  86%|████████▌ | 1290/1500 [05:58<00:17, 11.67it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  86%|████████▌ | 1292/1500 [05:58<00:17, 11.86it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  86%|████████▋ | 1294/1500 [05:58<00:17, 11.97it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  86%|████████▋ | 1296/1500 [05:59<00:16, 12.06it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  87%|████████▋ | 1298/1500 [05:59<00:16, 12.10it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  87%|████████▋ | 1300/1500 [05:59<00:16, 12.16it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  87%|████████▋ | 1302/1500 [05:59<00:16, 12.17it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  87%|████████▋ | 1304/1500 [05:59<00:16, 12.20it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  87%|████████▋ | 1306/1500 [05:59<00:15, 12.23it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  87%|████████▋ | 1308/1500 [06:00<00:15, 12.49it/s, 55 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  87%|████████▋ | 1310/1500 [06:00<00:15, 12.41it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  87%|████████▋ | 1312/1500 [06:00<00:15, 12.37it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  88%|████████▊ | 1314/1500 [06:00<00:15, 12.23it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  88%|████████▊ | 1316/1500 [06:00<00:15, 12.21it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  88%|████████▊ | 1318/1500 [06:00<00:14, 12.23it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  88%|████████▊ | 1320/1500 [06:01<00:14, 12.24it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  88%|████████▊ | 1322/1500 [06:01<00:14, 12.25it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  88%|████████▊ | 1324/1500 [06:01<00:14, 12.27it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  88%|████████▊ | 1326/1500 [06:01<00:14, 12.27it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  89%|████████▊ | 1328/1500 [06:01<00:14, 12.27it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  89%|████████▊ | 1330/1500 [06:01<00:13, 12.28it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  89%|████████▉ | 1332/1500 [06:02<00:13, 12.28it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  89%|████████▉ | 1334/1500 [06:02<00:13, 12.27it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  89%|████████▉ | 1336/1500 [06:02<00:13, 12.24it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  89%|████████▉ | 1338/1500 [06:02<00:13, 12.24it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  89%|████████▉ | 1340/1500 [06:02<00:13, 12.26it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  89%|████████▉ | 1342/1500 [06:02<00:12, 12.26it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  90%|████████▉ | 1344/1500 [06:03<00:12, 12.28it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  90%|████████▉ | 1346/1500 [06:03<00:12, 12.28it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  90%|████████▉ | 1348/1500 [06:03<00:14, 10.68it/s, 127 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  90%|█████████ | 1350/1500 [06:03<00:13, 11.11it/s, 63 steps of size 7.17e-02. acc. prob=0.92] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  90%|█████████ | 1352/1500 [06:03<00:12, 11.44it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  90%|█████████ | 1354/1500 [06:03<00:12, 11.68it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  90%|█████████ | 1356/1500 [06:04<00:12, 11.85it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  91%|█████████ | 1358/1500 [06:04<00:11, 11.98it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  91%|█████████ | 1360/1500 [06:04<00:11, 12.07it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  91%|█████████ | 1362/1500 [06:04<00:11, 12.15it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  91%|█████████ | 1364/1500 [06:04<00:11, 12.18it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  91%|█████████ | 1366/1500 [06:04<00:10, 12.22it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  91%|█████████ | 1368/1500 [06:05<00:10, 12.25it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  91%|█████████▏| 1370/1500 [06:05<00:10, 12.27it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  91%|█████████▏| 1372/1500 [06:05<00:10, 12.28it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  92%|█████████▏| 1374/1500 [06:05<00:10, 12.30it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  92%|█████████▏| 1376/1500 [06:05<00:10, 12.30it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  92%|█████████▏| 1378/1500 [06:05<00:09, 12.29it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  92%|█████████▏| 1380/1500 [06:06<00:09, 12.29it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  92%|█████████▏| 1382/1500 [06:06<00:09, 12.30it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  92%|█████████▏| 1384/1500 [06:06<00:08, 13.14it/s, 36 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  92%|█████████▏| 1386/1500 [06:06<00:08, 12.90it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  93%|█████████▎| 1388/1500 [06:06<00:08, 12.70it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  93%|█████████▎| 1390/1500 [06:06<00:08, 12.57it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  93%|█████████▎| 1392/1500 [06:07<00:08, 12.49it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  93%|█████████▎| 1394/1500 [06:07<00:08, 12.43it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  93%|█████████▎| 1396/1500 [06:07<00:08, 12.39it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  93%|█████████▎| 1398/1500 [06:07<00:08, 12.36it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  93%|█████████▎| 1400/1500 [06:07<00:08, 12.33it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  93%|█████████▎| 1402/1500 [06:07<00:07, 12.32it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  94%|█████████▎| 1404/1500 [06:07<00:07, 12.31it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  94%|█████████▎| 1406/1500 [06:08<00:07, 12.31it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  94%|█████████▍| 1407/1500 [06:08<00:08, 10.39it/s, 127 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  94%|█████████▍| 1409/1500 [06:08<00:08, 10.95it/s, 63 steps of size 7.17e-02. acc. prob=0.92] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  94%|█████████▍| 1410/1500 [06:08<00:09,  9.50it/s, 127 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  94%|█████████▍| 1412/1500 [06:08<00:08, 10.32it/s, 63 steps of size 7.17e-02. acc. prob=0.92] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  94%|█████████▍| 1414/1500 [06:08<00:07, 10.90it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  94%|█████████▍| 1416/1500 [06:09<00:08,  9.83it/s, 127 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  95%|█████████▍| 1418/1500 [06:09<00:07, 10.50it/s, 63 steps of size 7.17e-02. acc. prob=0.92] "
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  95%|█████████▍| 1420/1500 [06:09<00:07, 11.00it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  95%|█████████▍| 1422/1500 [06:09<00:06, 11.38it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  95%|█████████▍| 1424/1500 [06:09<00:06, 11.64it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  95%|█████████▌| 1426/1500 [06:10<00:06, 11.83it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  95%|█████████▌| 1428/1500 [06:10<00:06, 11.96it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  95%|█████████▌| 1430/1500 [06:10<00:05, 12.05it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  95%|█████████▌| 1432/1500 [06:10<00:05, 12.13it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  96%|█████████▌| 1434/1500 [06:10<00:05, 12.17it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  96%|█████████▌| 1436/1500 [06:10<00:05, 12.22it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  96%|█████████▌| 1438/1500 [06:11<00:05, 12.24it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  96%|█████████▌| 1440/1500 [06:11<00:04, 12.26it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  96%|█████████▌| 1442/1500 [06:11<00:04, 12.27it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  96%|█████████▋| 1444/1500 [06:11<00:04, 12.28it/s, 63 steps of size 7.17e-02. acc. prob=0.93]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  96%|█████████▋| 1446/1500 [06:11<00:04, 12.29it/s, 63 steps of size 7.17e-02. acc. prob=0.93]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  97%|█████████▋| 1448/1500 [06:11<00:04, 12.29it/s, 63 steps of size 7.17e-02. acc. prob=0.93]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  97%|█████████▋| 1450/1500 [06:11<00:04, 12.29it/s, 63 steps of size 7.17e-02. acc. prob=0.93]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  97%|█████████▋| 1452/1500 [06:12<00:03, 12.25it/s, 63 steps of size 7.17e-02. acc. prob=0.93]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  97%|█████████▋| 1454/1500 [06:12<00:03, 12.25it/s, 63 steps of size 7.17e-02. acc. prob=0.93]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  97%|█████████▋| 1456/1500 [06:12<00:03, 12.24it/s, 63 steps of size 7.17e-02. acc. prob=0.93]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  97%|█████████▋| 1458/1500 [06:12<00:03, 12.25it/s, 63 steps of size 7.17e-02. acc. prob=0.93]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  97%|█████████▋| 1460/1500 [06:12<00:03, 12.27it/s, 63 steps of size 7.17e-02. acc. prob=0.93]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  97%|█████████▋| 1462/1500 [06:12<00:03, 12.28it/s, 63 steps of size 7.17e-02. acc. prob=0.93]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  98%|█████████▊| 1464/1500 [06:13<00:02, 12.27it/s, 63 steps of size 7.17e-02. acc. prob=0.93]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  98%|█████████▊| 1466/1500 [06:13<00:02, 12.27it/s, 63 steps of size 7.17e-02. acc. prob=0.93]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  98%|█████████▊| 1468/1500 [06:13<00:02, 12.26it/s, 63 steps of size 7.17e-02. acc. prob=0.93]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  98%|█████████▊| 1470/1500 [06:13<00:02, 12.27it/s, 63 steps of size 7.17e-02. acc. prob=0.93]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  98%|█████████▊| 1472/1500 [06:13<00:02, 12.28it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  98%|█████████▊| 1474/1500 [06:13<00:02, 12.28it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  98%|█████████▊| 1476/1500 [06:14<00:01, 12.28it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  99%|█████████▊| 1478/1500 [06:14<00:01, 12.26it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  99%|█████████▊| 1480/1500 [06:14<00:01, 12.26it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  99%|█████████▉| 1482/1500 [06:14<00:01, 12.27it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  99%|█████████▉| 1484/1500 [06:14<00:01, 12.24it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  99%|█████████▉| 1486/1500 [06:14<00:01, 12.24it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  99%|█████████▉| 1488/1500 [06:15<00:00, 12.24it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  99%|█████████▉| 1490/1500 [06:15<00:00, 12.25it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample:  99%|█████████▉| 1492/1500 [06:15<00:00, 12.21it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample: 100%|█████████▉| 1494/1500 [06:15<00:00, 12.22it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample: 100%|█████████▉| 1496/1500 [06:15<00:00, 12.24it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample: 100%|█████████▉| 1498/1500 [06:15<00:00, 12.25it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample: 100%|██████████| 1500/1500 [06:16<00:00, 12.26it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "sample: 100%|██████████| 1500/1500 [06:16<00:00,  3.99it/s, 63 steps of size 7.17e-02. acc. prob=0.92]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "There were 26 divergences after tuning. Increase `target_accept` or reparameterize.\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "We recommend running at least 4 chains for robust computation of convergence diagnostics\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "The rhat statistic is larger than 1.01 for some parameters. This indicates problems during sampling. See https://arxiv.org/abs/1903.08008 for details\n"
+     ]
+    },
+    {
+     "data": {
+      "text/html": [
+       "<div><svg style=\"position: absolute; width: 0; height: 0; overflow: hidden\">\n",
+       "<defs>\n",
+       "<symbol id=\"icon-database\" viewBox=\"0 0 32 32\">\n",
+       "<path d=\"M16 0c-8.837 0-16 2.239-16 5v4c0 2.761 7.163 5 16 5s16-2.239 16-5v-4c0-2.761-7.163-5-16-5z\"></path>\n",
+       "<path d=\"M16 17c-8.837 0-16-2.239-16-5v6c0 2.761 7.163 5 16 5s16-2.239 16-5v-6c0 2.761-7.163 5-16 5z\"></path>\n",
+       "<path d=\"M16 26c-8.837 0-16-2.239-16-5v6c0 2.761 7.163 5 16 5s16-2.239 16-5v-6c0 2.761-7.163 5-16 5z\"></path>\n",
+       "</symbol>\n",
+       "<symbol id=\"icon-file-text2\" viewBox=\"0 0 32 32\">\n",
+       "<path d=\"M28.681 7.159c-0.694-0.947-1.662-2.053-2.724-3.116s-2.169-2.030-3.116-2.724c-1.612-1.182-2.393-1.319-2.841-1.319h-15.5c-1.378 0-2.5 1.121-2.5 2.5v27c0 1.378 1.122 2.5 2.5 2.5h23c1.378 0 2.5-1.122 2.5-2.5v-19.5c0-0.448-0.137-1.23-1.319-2.841zM24.543 5.457c0.959 0.959 1.712 1.825 2.268 2.543h-4.811v-4.811c0.718 0.556 1.584 1.309 2.543 2.268zM28 29.5c0 0.271-0.229 0.5-0.5 0.5h-23c-0.271 0-0.5-0.229-0.5-0.5v-27c0-0.271 0.229-0.5 0.5-0.5 0 0 15.499-0 15.5 0v7c0 0.552 0.448 1 1 1h7v19.5z\"></path>\n",
+       "<path d=\"M23 26h-14c-0.552 0-1-0.448-1-1s0.448-1 1-1h14c0.552 0 1 0.448 1 1s-0.448 1-1 1z\"></path>\n",
+       "<path d=\"M23 22h-14c-0.552 0-1-0.448-1-1s0.448-1 1-1h14c0.552 0 1 0.448 1 1s-0.448 1-1 1z\"></path>\n",
+       "<path d=\"M23 18h-14c-0.552 0-1-0.448-1-1s0.448-1 1-1h14c0.552 0 1 0.448 1 1s-0.448 1-1 1z\"></path>\n",
+       "</symbol>\n",
+       "</defs>\n",
+       "</svg>\n",
+       "<style>/* CSS stylesheet for displaying xarray objects in notebooks */\n",
+       "\n",
+       ":root {\n",
+       "  --xr-font-color0: var(\n",
+       "    --jp-content-font-color0,\n",
+       "    var(--pst-color-text-base rgba(0, 0, 0, 1))\n",
+       "  );\n",
+       "  --xr-font-color2: var(\n",
+       "    --jp-content-font-color2,\n",
+       "    var(--pst-color-text-base, rgba(0, 0, 0, 0.54))\n",
+       "  );\n",
+       "  --xr-font-color3: var(\n",
+       "    --jp-content-font-color3,\n",
+       "    var(--pst-color-text-base, rgba(0, 0, 0, 0.38))\n",
+       "  );\n",
+       "  --xr-border-color: var(\n",
+       "    --jp-border-color2,\n",
+       "    hsl(from var(--pst-color-on-background, white) h s calc(l - 10))\n",
+       "  );\n",
+       "  --xr-disabled-color: var(\n",
+       "    --jp-layout-color3,\n",
+       "    hsl(from var(--pst-color-on-background, white) h s calc(l - 40))\n",
+       "  );\n",
+       "  --xr-background-color: var(\n",
+       "    --jp-layout-color0,\n",
+       "    var(--pst-color-on-background, white)\n",
+       "  );\n",
+       "  --xr-background-color-row-even: var(\n",
+       "    --jp-layout-color1,\n",
+       "    hsl(from var(--pst-color-on-background, white) h s calc(l - 5))\n",
+       "  );\n",
+       "  --xr-background-color-row-odd: var(\n",
+       "    --jp-layout-color2,\n",
+       "    hsl(from var(--pst-color-on-background, white) h s calc(l - 15))\n",
+       "  );\n",
+       "}\n",
+       "\n",
+       "html[theme=\"dark\"],\n",
+       "html[data-theme=\"dark\"],\n",
+       "body[data-theme=\"dark\"],\n",
+       "body.vscode-dark {\n",
+       "  --xr-font-color0: var(\n",
+       "    --jp-content-font-color0,\n",
+       "    var(--pst-color-text-base, rgba(255, 255, 255, 1))\n",
+       "  );\n",
+       "  --xr-font-color2: var(\n",
+       "    --jp-content-font-color2,\n",
+       "    var(--pst-color-text-base, rgba(255, 255, 255, 0.54))\n",
+       "  );\n",
+       "  --xr-font-color3: var(\n",
+       "    --jp-content-font-color3,\n",
+       "    var(--pst-color-text-base, rgba(255, 255, 255, 0.38))\n",
+       "  );\n",
+       "  --xr-border-color: var(\n",
+       "    --jp-border-color2,\n",
+       "    hsl(from var(--pst-color-on-background, #111111) h s calc(l + 10))\n",
+       "  );\n",
+       "  --xr-disabled-color: var(\n",
+       "    --jp-layout-color3,\n",
+       "    hsl(from var(--pst-color-on-background, #111111) h s calc(l + 40))\n",
+       "  );\n",
+       "  --xr-background-color: var(\n",
+       "    --jp-layout-color0,\n",
+       "    var(--pst-color-on-background, #111111)\n",
+       "  );\n",
+       "  --xr-background-color-row-even: var(\n",
+       "    --jp-layout-color1,\n",
+       "    hsl(from var(--pst-color-on-background, #111111) h s calc(l + 5))\n",
+       "  );\n",
+       "  --xr-background-color-row-odd: var(\n",
+       "    --jp-layout-color2,\n",
+       "    hsl(from var(--pst-color-on-background, #111111) h s calc(l + 15))\n",
+       "  );\n",
+       "}\n",
+       "\n",
+       ".xr-wrap {\n",
+       "  display: block !important;\n",
+       "  min-width: 300px;\n",
+       "  max-width: 700px;\n",
+       "  line-height: 1.6;\n",
+       "  padding-bottom: 4px;\n",
+       "}\n",
+       "\n",
+       ".xr-text-repr-fallback {\n",
+       "  /* fallback to plain text repr when CSS is not injected (untrusted notebook) */\n",
+       "  display: none;\n",
+       "}\n",
+       "\n",
+       ".xr-header {\n",
+       "  padding-top: 6px;\n",
+       "  padding-bottom: 6px;\n",
+       "}\n",
+       "\n",
+       ".xr-header {\n",
+       "  border-bottom: solid 1px var(--xr-border-color);\n",
+       "  margin-bottom: 4px;\n",
+       "}\n",
+       "\n",
+       ".xr-header > div,\n",
+       ".xr-header > ul {\n",
+       "  display: inline;\n",
+       "  margin-top: 0;\n",
+       "  margin-bottom: 0;\n",
+       "}\n",
+       "\n",
+       ".xr-obj-type,\n",
+       ".xr-obj-name {\n",
+       "  margin-left: 2px;\n",
+       "  margin-right: 10px;\n",
+       "}\n",
+       "\n",
+       ".xr-obj-type,\n",
+       ".xr-group-box-contents > label {\n",
+       "  color: var(--xr-font-color2);\n",
+       "  display: block;\n",
+       "}\n",
+       "\n",
+       ".xr-sections {\n",
+       "  padding-left: 0 !important;\n",
+       "  display: grid;\n",
+       "  grid-template-columns: 150px auto auto 1fr 0 20px 0 20px;\n",
+       "  margin-block-start: 0;\n",
+       "  margin-block-end: 0;\n",
+       "}\n",
+       "\n",
+       ".xr-section-item {\n",
+       "  display: contents;\n",
+       "}\n",
+       "\n",
+       ".xr-section-item > input,\n",
+       ".xr-group-box-contents > input,\n",
+       ".xr-array-wrap > input {\n",
+       "  display: block;\n",
+       "  opacity: 0;\n",
+       "  height: 0;\n",
+       "  margin: 0;\n",
+       "}\n",
+       "\n",
+       ".xr-section-item > input + label,\n",
+       ".xr-var-item > input + label {\n",
+       "  color: var(--xr-disabled-color);\n",
+       "}\n",
+       "\n",
+       ".xr-section-item > input:enabled + label,\n",
+       ".xr-var-item > input:enabled + label,\n",
+       ".xr-array-wrap > input:enabled + label,\n",
+       ".xr-group-box-contents > input:enabled + label {\n",
+       "  cursor: pointer;\n",
+       "  color: var(--xr-font-color2);\n",
+       "}\n",
+       "\n",
+       ".xr-section-item > input:focus-visible + label,\n",
+       ".xr-var-item > input:focus-visible + label,\n",
+       ".xr-array-wrap > input:focus-visible + label,\n",
+       ".xr-group-box-contents > input:focus-visible + label {\n",
+       "  outline: auto;\n",
+       "}\n",
+       "\n",
+       ".xr-section-item > input:enabled + label:hover,\n",
+       ".xr-var-item > input:enabled + label:hover,\n",
+       ".xr-array-wrap > input:enabled + label:hover,\n",
+       ".xr-group-box-contents > input:enabled + label:hover {\n",
+       "  color: var(--xr-font-color0);\n",
+       "}\n",
+       "\n",
+       ".xr-section-summary {\n",
+       "  grid-column: 1;\n",
+       "  color: var(--xr-font-color2);\n",
+       "  font-weight: 500;\n",
+       "  white-space: nowrap;\n",
+       "}\n",
+       "\n",
+       ".xr-section-summary > em {\n",
+       "  font-weight: normal;\n",
+       "}\n",
+       "\n",
+       ".xr-span-grid {\n",
+       "  grid-column-end: -1;\n",
+       "}\n",
+       "\n",
+       ".xr-section-summary > span {\n",
+       "  display: inline-block;\n",
+       "  padding-left: 0.3em;\n",
+       "}\n",
+       "\n",
+       ".xr-group-box-contents > input:checked + label > span {\n",
+       "  display: inline-block;\n",
+       "  padding-left: 0.6em;\n",
+       "}\n",
+       "\n",
+       ".xr-section-summary-in:disabled + label {\n",
+       "  color: var(--xr-font-color2);\n",
+       "}\n",
+       "\n",
+       ".xr-section-summary-in + label:before {\n",
+       "  display: inline-block;\n",
+       "  content: \"►\";\n",
+       "  font-size: 11px;\n",
+       "  width: 15px;\n",
+       "  text-align: center;\n",
+       "}\n",
+       "\n",
+       ".xr-section-summary-in:disabled + label:before {\n",
+       "  color: var(--xr-disabled-color);\n",
+       "}\n",
+       "\n",
+       ".xr-section-summary-in:checked + label:before {\n",
+       "  content: \"▼\";\n",
+       "}\n",
+       "\n",
+       ".xr-section-summary-in:checked + label > span {\n",
+       "  display: none;\n",
+       "}\n",
+       "\n",
+       ".xr-section-summary,\n",
+       ".xr-section-inline-details,\n",
+       ".xr-group-box-contents > label {\n",
+       "  padding-top: 4px;\n",
+       "}\n",
+       "\n",
+       ".xr-section-inline-details {\n",
+       "  grid-column: 2 / -1;\n",
+       "}\n",
+       "\n",
+       ".xr-section-details {\n",
+       "  grid-column: 1 / -1;\n",
+       "  margin-top: 4px;\n",
+       "  margin-bottom: 5px;\n",
+       "}\n",
+       "\n",
+       ".xr-section-summary-in ~ .xr-section-details {\n",
+       "  display: none;\n",
+       "}\n",
+       "\n",
+       ".xr-section-summary-in:checked ~ .xr-section-details {\n",
+       "  display: contents;\n",
+       "}\n",
+       "\n",
+       ".xr-children {\n",
+       "  display: inline-grid;\n",
+       "  grid-template-columns: 100%;\n",
+       "  grid-column: 1 / -1;\n",
+       "  padding-top: 4px;\n",
+       "}\n",
+       "\n",
+       ".xr-group-box {\n",
+       "  display: inline-grid;\n",
+       "  grid-template-columns: 0px 30px auto;\n",
+       "}\n",
+       "\n",
+       ".xr-group-box-vline {\n",
+       "  grid-column-start: 1;\n",
+       "  border-right: 0.2em solid;\n",
+       "  border-color: var(--xr-border-color);\n",
+       "  width: 0px;\n",
+       "}\n",
+       "\n",
+       ".xr-group-box-hline {\n",
+       "  grid-column-start: 2;\n",
+       "  grid-row-start: 1;\n",
+       "  height: 1em;\n",
+       "  width: 26px;\n",
+       "  border-bottom: 0.2em solid;\n",
+       "  border-color: var(--xr-border-color);\n",
+       "}\n",
+       "\n",
+       ".xr-group-box-contents {\n",
+       "  grid-column-start: 3;\n",
+       "  padding-bottom: 4px;\n",
+       "}\n",
+       "\n",
+       ".xr-group-box-contents > label::before {\n",
+       "  content: \"📂\";\n",
+       "  padding-right: 0.3em;\n",
+       "}\n",
+       "\n",
+       ".xr-group-box-contents > input:checked + label::before {\n",
+       "  content: \"📁\";\n",
+       "}\n",
+       "\n",
+       ".xr-group-box-contents > input:checked + label {\n",
+       "  padding-bottom: 0px;\n",
+       "}\n",
+       "\n",
+       ".xr-group-box-contents > input:checked ~ .xr-sections {\n",
+       "  display: none;\n",
+       "}\n",
+       "\n",
+       ".xr-group-box-contents > input + label > span {\n",
+       "  display: none;\n",
+       "}\n",
+       "\n",
+       ".xr-group-box-ellipsis {\n",
+       "  font-size: 1.4em;\n",
+       "  font-weight: 900;\n",
+       "  color: var(--xr-font-color2);\n",
+       "  letter-spacing: 0.15em;\n",
+       "  cursor: default;\n",
+       "}\n",
+       "\n",
+       ".xr-array-wrap {\n",
+       "  grid-column: 1 / -1;\n",
+       "  display: grid;\n",
+       "  grid-template-columns: 20px auto;\n",
+       "}\n",
+       "\n",
+       ".xr-array-wrap > label {\n",
+       "  grid-column: 1;\n",
+       "  vertical-align: top;\n",
+       "}\n",
+       "\n",
+       ".xr-preview {\n",
+       "  color: var(--xr-font-color3);\n",
+       "}\n",
+       "\n",
+       ".xr-array-preview,\n",
+       ".xr-array-data {\n",
+       "  padding: 0 5px !important;\n",
+       "  grid-column: 2;\n",
+       "}\n",
+       "\n",
+       ".xr-array-data,\n",
+       ".xr-array-in:checked ~ .xr-array-preview {\n",
+       "  display: none;\n",
+       "}\n",
+       "\n",
+       ".xr-array-in:checked ~ .xr-array-data,\n",
+       ".xr-array-preview {\n",
+       "  display: inline-block;\n",
+       "}\n",
+       "\n",
+       ".xr-dim-list {\n",
+       "  display: inline-block !important;\n",
+       "  list-style: none;\n",
+       "  padding: 0 !important;\n",
+       "  margin: 0;\n",
+       "}\n",
+       "\n",
+       ".xr-dim-list li {\n",
+       "  display: inline-block;\n",
+       "  padding: 0;\n",
+       "  margin: 0;\n",
+       "}\n",
+       "\n",
+       ".xr-dim-list:before {\n",
+       "  content: \"(\";\n",
+       "}\n",
+       "\n",
+       ".xr-dim-list:after {\n",
+       "  content: \")\";\n",
+       "}\n",
+       "\n",
+       ".xr-dim-list li:not(:last-child):after {\n",
+       "  content: \",\";\n",
+       "  padding-right: 5px;\n",
+       "}\n",
+       "\n",
+       ".xr-has-index {\n",
+       "  font-weight: bold;\n",
+       "}\n",
+       "\n",
+       ".xr-var-list,\n",
+       ".xr-var-item {\n",
+       "  display: contents;\n",
+       "}\n",
+       "\n",
+       ".xr-var-item > div,\n",
+       ".xr-var-item label,\n",
+       ".xr-var-item > .xr-var-name span {\n",
+       "  background-color: var(--xr-background-color-row-even);\n",
+       "  border-color: var(--xr-background-color-row-odd);\n",
+       "  margin-bottom: 0;\n",
+       "  padding-top: 2px;\n",
+       "}\n",
+       "\n",
+       ".xr-var-item > .xr-var-name:hover span {\n",
+       "  padding-right: 5px;\n",
+       "}\n",
+       "\n",
+       ".xr-var-list > li:nth-child(odd) > div,\n",
+       ".xr-var-list > li:nth-child(odd) > label,\n",
+       ".xr-var-list > li:nth-child(odd) > .xr-var-name span {\n",
+       "  background-color: var(--xr-background-color-row-odd);\n",
+       "  border-color: var(--xr-background-color-row-even);\n",
+       "}\n",
+       "\n",
+       ".xr-var-name {\n",
+       "  grid-column: 1;\n",
+       "}\n",
+       "\n",
+       ".xr-var-dims {\n",
+       "  grid-column: 2;\n",
+       "}\n",
+       "\n",
+       ".xr-var-dtype {\n",
+       "  grid-column: 3;\n",
+       "  text-align: right;\n",
+       "  color: var(--xr-font-color2);\n",
+       "}\n",
+       "\n",
+       ".xr-var-preview {\n",
+       "  grid-column: 4;\n",
+       "}\n",
+       "\n",
+       ".xr-index-preview {\n",
+       "  grid-column: 2 / 5;\n",
+       "  color: var(--xr-font-color2);\n",
+       "}\n",
+       "\n",
+       ".xr-var-name,\n",
+       ".xr-var-dims,\n",
+       ".xr-var-dtype,\n",
+       ".xr-preview,\n",
+       ".xr-attrs dt {\n",
+       "  white-space: nowrap;\n",
+       "  overflow: hidden;\n",
+       "  text-overflow: ellipsis;\n",
+       "  padding-right: 10px;\n",
+       "}\n",
+       "\n",
+       ".xr-var-name:hover,\n",
+       ".xr-var-dims:hover,\n",
+       ".xr-var-dtype:hover,\n",
+       ".xr-attrs dt:hover {\n",
+       "  overflow: visible;\n",
+       "  width: auto;\n",
+       "  z-index: 1;\n",
+       "}\n",
+       "\n",
+       ".xr-var-attrs,\n",
+       ".xr-var-data,\n",
+       ".xr-index-data {\n",
+       "  display: none;\n",
+       "  border-top: 2px dotted var(--xr-background-color);\n",
+       "  padding-bottom: 20px !important;\n",
+       "  padding-top: 10px !important;\n",
+       "}\n",
+       "\n",
+       ".xr-var-attrs-in + label,\n",
+       ".xr-var-data-in + label,\n",
+       ".xr-index-data-in + label {\n",
+       "  padding: 0 1px;\n",
+       "}\n",
+       "\n",
+       ".xr-var-attrs-in:checked ~ .xr-var-attrs,\n",
+       ".xr-var-data-in:checked ~ .xr-var-data,\n",
+       ".xr-index-data-in:checked ~ .xr-index-data {\n",
+       "  display: block;\n",
+       "}\n",
+       "\n",
+       ".xr-var-data > table {\n",
+       "  float: right;\n",
+       "}\n",
+       "\n",
+       ".xr-var-data > pre,\n",
+       ".xr-index-data > pre,\n",
+       ".xr-var-data > table > tbody > tr {\n",
+       "  background-color: transparent !important;\n",
+       "}\n",
+       "\n",
+       ".xr-var-name span,\n",
+       ".xr-var-data,\n",
+       ".xr-index-name div,\n",
+       ".xr-index-data,\n",
+       ".xr-attrs {\n",
+       "  padding-left: 25px !important;\n",
+       "}\n",
+       "\n",
+       ".xr-attrs,\n",
+       ".xr-var-attrs,\n",
+       ".xr-var-data,\n",
+       ".xr-index-data {\n",
+       "  grid-column: 1 / -1;\n",
+       "}\n",
+       "\n",
+       "dl.xr-attrs {\n",
+       "  padding: 0;\n",
+       "  margin: 0;\n",
+       "  display: grid;\n",
+       "  grid-template-columns: 125px auto;\n",
+       "}\n",
+       "\n",
+       ".xr-attrs dt,\n",
+       ".xr-attrs dd {\n",
+       "  padding: 0;\n",
+       "  margin: 0;\n",
+       "  float: left;\n",
+       "  padding-right: 10px;\n",
+       "  width: auto;\n",
+       "}\n",
+       "\n",
+       ".xr-attrs dt {\n",
+       "  font-weight: normal;\n",
+       "  grid-column: 1;\n",
+       "}\n",
+       "\n",
+       ".xr-attrs dt:hover span {\n",
+       "  display: inline-block;\n",
+       "  background: var(--xr-background-color);\n",
+       "  padding-right: 10px;\n",
+       "}\n",
+       "\n",
+       ".xr-attrs dd {\n",
+       "  grid-column: 2;\n",
+       "  white-space: pre-wrap;\n",
+       "  word-break: break-all;\n",
+       "}\n",
+       "\n",
+       ".xr-icon-database,\n",
+       ".xr-icon-file-text2,\n",
+       ".xr-no-icon {\n",
+       "  display: inline-block;\n",
+       "  vertical-align: middle;\n",
+       "  width: 1em;\n",
+       "  height: 1.5em !important;\n",
+       "  stroke-width: 0;\n",
+       "  stroke: currentColor;\n",
+       "  fill: currentColor;\n",
+       "}\n",
+       "\n",
+       ".xr-var-attrs-in:checked + label > .xr-icon-file-text2,\n",
+       ".xr-var-data-in:checked + label > .xr-icon-database,\n",
+       ".xr-index-data-in:checked + label > .xr-icon-database {\n",
+       "  color: var(--xr-font-color0);\n",
+       "  filter: drop-shadow(1px 1px 5px var(--xr-font-color2));\n",
+       "  stroke-width: 0.8px;\n",
+       "}\n",
+       "</style><pre class='xr-text-repr-fallback'>&lt;xarray.DataTree&gt;\n",
+       "Group: /\n",
+       "├── Group: /posterior\n",
+       "│       Dimensions:                                (chain: 2, draw: 500,\n",
+       "│                                                   participant_id__factor_dim: 15,\n",
+       "│                                                   rl_alpha_1|participant_id__factor_dim: 15)\n",
+       "│       Coordinates:\n",
+       "│         * chain                                  (chain) int64 16B 0 1\n",
+       "│         * draw                                   (draw) int64 4kB 0 1 2 ... 498 499\n",
+       "│         * participant_id__factor_dim             (participant_id__factor_dim) &lt;U2 120B ...\n",
+       "│         * rl_alpha_1|participant_id__factor_dim  (rl_alpha_1|participant_id__factor_dim) &lt;U2 120B ...\n",
+       "│       Data variables: (12/24)\n",
+       "│           t_1|participant_id_offset              (chain, draw, participant_id__factor_dim) float32 60kB ...\n",
+       "│           z_1|participant_id                     (chain, draw, participant_id__factor_dim) float32 60kB ...\n",
+       "│           z_1|participant_id_sigma               (chain, draw) float32 4kB ...\n",
+       "│           theta_1|participant_id                 (chain, draw, participant_id__factor_dim) float32 60kB ...\n",
+       "│           rl_alpha_Intercept                     (chain, draw) float32 4kB ...\n",
+       "│           t_Intercept                            (chain, draw) float32 4kB ...\n",
+       "│           ...                                     ...\n",
+       "│           theta_1|participant_id_offset          (chain, draw, participant_id__factor_dim) float32 60kB ...\n",
+       "│           a_1|participant_id_offset              (chain, draw, participant_id__factor_dim) float32 60kB ...\n",
+       "│           t_1|participant_id_sigma               (chain, draw) float32 4kB ...\n",
+       "│           t_1|participant_id                     (chain, draw, participant_id__factor_dim) float32 60kB ...\n",
+       "│           scaler_1|participant_id_offset         (chain, draw, participant_id__factor_dim) float32 60kB ...\n",
+       "│           rl_alpha_1|participant_id_offset       (chain, draw, rl_alpha_1|participant_id__factor_dim) float32 60kB ...\n",
+       "│       Attributes:\n",
+       "│           created_at:                  2026-07-06T16:44:41.787695+00:00\n",
+       "│           creation_library:            ArviZ\n",
+       "│           creation_library_version:    1.2.0\n",
+       "│           creation_library_language:   Python\n",
+       "│           sample_dims:                 [&#x27;chain&#x27;, &#x27;draw&#x27;]\n",
+       "│           inference_library:           numpyro\n",
+       "│           inference_library_version:   0.21.0\n",
+       "│           sampling_time:               545.10303\n",
+       "│           tuning_steps:                1000\n",
+       "│           modeling_interface:          bambi\n",
+       "│           modeling_interface_version:  0.18.0\n",
+       "├── Group: /sample_stats\n",
+       "│       Dimensions:          (chain: 2, draw: 500)\n",
+       "│       Coordinates:\n",
+       "│         * chain            (chain) int64 16B 0 1\n",
+       "│         * draw             (draw) int64 4kB 0 1 2 3 4 5 6 ... 494 495 496 497 498 499\n",
+       "│       Data variables:\n",
+       "│           acceptance_rate  (chain, draw) float32 4kB ...\n",
+       "│           step_size        (chain, draw) float32 4kB ...\n",
+       "│           diverging        (chain, draw) bool 1kB ...\n",
+       "│           energy           (chain, draw) float32 4kB ...\n",
+       "│           n_steps          (chain, draw) int32 4kB ...\n",
+       "│           tree_depth       (chain, draw) int64 8kB 6 6 6 6 6 6 6 6 ... 6 6 6 6 6 6 6 6\n",
+       "│           lp               (chain, draw) float32 4kB ...\n",
+       "│       Attributes:\n",
+       "│           created_at:                  2026-07-06T16:44:41.799808+00:00\n",
+       "│           creation_library:            ArviZ\n",
+       "│           creation_library_version:    1.2.0\n",
+       "│           creation_library_language:   Python\n",
+       "│           sample_dims:                 [&#x27;chain&#x27;, &#x27;draw&#x27;]\n",
+       "│           modeling_interface:          bambi\n",
+       "│           modeling_interface_version:  0.18.0\n",
+       "├── Group: /observed_data\n",
+       "│       Dimensions:                  (__obs__: 2250, rt,response_extra_dim_0: 2)\n",
+       "│       Coordinates:\n",
+       "│         * __obs__                  (__obs__) int64 18kB 0 1 2 3 ... 2247 2248 2249\n",
+       "│         * rt,response_extra_dim_0  (rt,response_extra_dim_0) int64 16B 0 1\n",
+       "│       Data variables:\n",
+       "│           rt,response              (__obs__, rt,response_extra_dim_0) float32 18kB ...\n",
+       "│       Attributes:\n",
+       "│           created_at:                  2026-07-06T16:44:41.800372+00:00\n",
+       "│           creation_library:            ArviZ\n",
+       "│           creation_library_version:    1.2.0\n",
+       "│           creation_library_language:   Python\n",
+       "│           sample_dims:                 []\n",
+       "│           modeling_interface:          bambi\n",
+       "│           modeling_interface_version:  0.18.0\n",
+       "├── Group: /constant_data\n",
+       "│       Attributes:\n",
+       "│           created_at:                  2026-07-06T16:44:41.800438+00:00\n",
+       "│           creation_library:            ArviZ\n",
+       "│           creation_library_version:    1.2.0\n",
+       "│           creation_library_language:   Python\n",
+       "│           sample_dims:                 []\n",
+       "│           modeling_interface:          bambi\n",
+       "│           modeling_interface_version:  0.18.0\n",
+       "└── Group: /log_likelihood\n",
+       "        Dimensions:      (chain: 2, draw: 500, __obs__: 2250)\n",
+       "        Coordinates:\n",
+       "          * chain        (chain) int64 16B 0 1\n",
+       "          * draw         (draw) int64 4kB 0 1 2 3 4 5 6 ... 493 494 495 496 497 498 499\n",
+       "          * __obs__      (__obs__) int64 18kB 0 1 2 3 4 5 ... 2245 2246 2247 2248 2249\n",
+       "        Data variables:\n",
+       "            rt,response  (chain, draw, __obs__) float64 18MB -0.9003 -2.705 ... 0.4514\n",
+       "        Attributes:\n",
+       "            modeling_interface:          bambi\n",
+       "            modeling_interface_version:  0.18.0</pre><div class='xr-wrap' style='display:none'><div class='xr-header'><div class='xr-obj-type'>xarray.DataTree</div></div><ul class='xr-sections'><li class='xr-section-item'><div class='xr-children'><div class='xr-group-box'><div class='xr-group-box-vline' style='height: 100%'></div><div class='xr-group-box-hline'></div><div class='xr-group-box-contents'><input id='group-ed896a7a-7be5-49f9-a1a7-71b46d773ce6' type='checkbox' checked /><label for='group-ed896a7a-7be5-49f9-a1a7-71b46d773ce6' title='Expand/collapse group'>/posterior<span>(39)</span></label><ul class='xr-sections'><li class='xr-section-item'><input id='section-7e93e9ed-3e11-48ac-96f3-b94ef9c042f8' class='xr-section-summary-in' type='checkbox' disabled /><label for='section-7e93e9ed-3e11-48ac-96f3-b94ef9c042f8' class='xr-section-summary'>Dimensions:</label><div class='xr-section-inline-details'><ul class='xr-dim-list'><li><span class='xr-has-index'>chain</span>: 2</li><li><span class='xr-has-index'>draw</span>: 500</li><li><span class='xr-has-index'>participant_id__factor_dim</span>: 15</li><li><span class='xr-has-index'>rl_alpha_1|participant_id__factor_dim</span>: 15</li></ul></div></li><li class='xr-section-item'><input id='section-9a035421-220f-4fc8-ad59-765b6b9de187' class='xr-section-summary-in' type='checkbox' checked /><label for='section-9a035421-220f-4fc8-ad59-765b6b9de187' class='xr-section-summary' title='Expand/collapse section'>Coordinates: <span>(4)</span></label><div class='xr-section-inline-details'></div><div class='xr-section-details'><ul class='xr-var-list'><li class='xr-var-item'><div class='xr-var-name'><span class='xr-has-index'>chain</span></div><div class='xr-var-dims'>(chain)</div><div class='xr-var-dtype'>int64</div><div class='xr-var-preview xr-preview'>0 1</div><input id='attrs-c22afb34-1973-4645-a231-254eb411d8d3' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-c22afb34-1973-4645-a231-254eb411d8d3' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-2ad84b02-25ab-4246-9d4d-f104d9c3018f' class='xr-var-data-in' type='checkbox'><label for='data-2ad84b02-25ab-4246-9d4d-f104d9c3018f' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>array([0, 1])</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span class='xr-has-index'>draw</span></div><div class='xr-var-dims'>(draw)</div><div class='xr-var-dtype'>int64</div><div class='xr-var-preview xr-preview'>0 1 2 3 4 5 ... 495 496 497 498 499</div><input id='attrs-4ccf4a63-edc1-4680-a285-a10dcd6918ef' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-4ccf4a63-edc1-4680-a285-a10dcd6918ef' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-8882c9b0-f554-4f51-8cce-ad2ce95fdbf2' class='xr-var-data-in' type='checkbox'><label for='data-8882c9b0-f554-4f51-8cce-ad2ce95fdbf2' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>array([  0,   1,   2, ..., 497, 498, 499], shape=(500,))</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span class='xr-has-index'>participant_id__factor_dim</span></div><div class='xr-var-dims'>(participant_id__factor_dim)</div><div class='xr-var-dtype'>&lt;U2</div><div class='xr-var-preview xr-preview'>&#x27;0&#x27; &#x27;1&#x27; &#x27;2&#x27; &#x27;3&#x27; ... &#x27;12&#x27; &#x27;13&#x27; &#x27;14&#x27;</div><input id='attrs-355a1f16-7695-4812-9cb1-05a587d2a400' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-355a1f16-7695-4812-9cb1-05a587d2a400' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-6d08b6a1-b43e-486f-9475-d615c09e37df' class='xr-var-data-in' type='checkbox'><label for='data-6d08b6a1-b43e-486f-9475-d615c09e37df' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>array([&#x27;0&#x27;, &#x27;1&#x27;, &#x27;2&#x27;, &#x27;3&#x27;, &#x27;4&#x27;, &#x27;5&#x27;, &#x27;6&#x27;, &#x27;7&#x27;, &#x27;8&#x27;, &#x27;9&#x27;, &#x27;10&#x27;, &#x27;11&#x27;, &#x27;12&#x27;,&#x27;13&#x27;, &#x27;14&#x27;], dtype=&#x27;&lt;U2&#x27;)</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span class='xr-has-index'>rl_alpha_1|participant_id__factor_dim</span></div><div class='xr-var-dims'>(rl_alpha_1|participant_id__factor_dim)</div><div class='xr-var-dtype'>&lt;U2</div><div class='xr-var-preview xr-preview'>&#x27;0&#x27; &#x27;1&#x27; &#x27;2&#x27; &#x27;3&#x27; ... &#x27;12&#x27; &#x27;13&#x27; &#x27;14&#x27;</div><input id='attrs-fae7df19-7f83-45dc-85c1-aa9927846e8e' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-fae7df19-7f83-45dc-85c1-aa9927846e8e' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-cfa28e13-e7c5-43e5-8f47-85afff3d3b2a' class='xr-var-data-in' type='checkbox'><label for='data-cfa28e13-e7c5-43e5-8f47-85afff3d3b2a' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>array([&#x27;0&#x27;, &#x27;1&#x27;, &#x27;2&#x27;, &#x27;3&#x27;, &#x27;4&#x27;, &#x27;5&#x27;, &#x27;6&#x27;, &#x27;7&#x27;, &#x27;8&#x27;, &#x27;9&#x27;, &#x27;10&#x27;, &#x27;11&#x27;, &#x27;12&#x27;,&#x27;13&#x27;, &#x27;14&#x27;], dtype=&#x27;&lt;U2&#x27;)</pre></div></li></ul></div></li><li class='xr-section-item'><input id='section-8376bcc8-984c-4021-99c7-eade8926b30a' class='xr-section-summary-in' type='checkbox' /><label for='section-8376bcc8-984c-4021-99c7-eade8926b30a' class='xr-section-summary' title='Expand/collapse section'>Data variables: <span>(24)</span></label><div class='xr-section-inline-details'></div><div class='xr-section-details'><ul class='xr-var-list'><li class='xr-var-item'><div class='xr-var-name'><span>t_1|participant_id_offset</span></div><div class='xr-var-dims'>(chain, draw, participant_id__factor_dim)</div><div class='xr-var-dtype'>float32</div><div class='xr-var-preview xr-preview'>...</div><input id='attrs-bd3c092a-2f5b-4731-bab8-14c09f51a2d6' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-bd3c092a-2f5b-4731-bab8-14c09f51a2d6' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-a0db2567-50f7-4237-94cf-6861b7fc4e53' class='xr-var-data-in' type='checkbox'><label for='data-a0db2567-50f7-4237-94cf-6861b7fc4e53' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>Array([[[-0.16254376,  1.248806  ,  1.2049413 , ..., -0.35088256,-0.98723644,  0.19908853],[ 0.53293073, -0.06829596, -0.18799886, ..., -0.7943104 ,-0.1128315 ,  0.7426409 ],[-0.2435882 , -0.16483803,  0.27149808, ..., -1.447299  ,0.33952236,  0.4255719 ],...,[ 0.9207672 , -0.07757746,  0.8061423 , ..., -0.90687597,0.8383891 ,  1.1370381 ],[ 1.2398256 ,  0.02268366,  0.9196439 , ..., -0.76721716,0.19704394,  1.1304141 ],[-0.18791993,  1.0984106 ,  0.7326622 , ..., -0.66376764,0.39801824,  1.1725343 ]],[[ 1.0569371 ,  0.5994698 ,  1.3556336 , ..., -0.54296976,0.08904155,  0.89630216],[ 0.39083105, -0.10916877,  0.07839733, ..., -1.3447152 ,0.30408728,  0.3357651 ],[-0.02153663,  0.38149425,  0.76267046, ..., -0.57446903,0.27328557,  0.40527076],...,[ 0.34855273,  0.8202057 , -0.76883537, ..., -0.64579374,-0.68481475,  0.7377882 ],[-0.11180106,  0.09231638,  0.15455687, ..., -1.2530384 ,-0.86452   ,  1.4573283 ],[ 0.08460666,  0.7168809 ,  0.47907665, ..., -0.20483425,0.63329244,  0.5582059 ]]], dtype=float32)</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span>z_1|participant_id</span></div><div class='xr-var-dims'>(chain, draw, participant_id__factor_dim)</div><div class='xr-var-dtype'>float32</div><div class='xr-var-preview xr-preview'>...</div><input id='attrs-0e59e0c0-9cf6-4f82-96f6-f4063fbe9efa' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-0e59e0c0-9cf6-4f82-96f6-f4063fbe9efa' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-5f2f484b-9151-4404-a817-20ff18ff1dc7' class='xr-var-data-in' type='checkbox'><label for='data-5f2f484b-9151-4404-a817-20ff18ff1dc7' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>Array([[[-0.04890735, -0.01714995, -0.04024272, ...,  0.0636134 ,0.00929059, -0.01745617],[-0.05370961, -0.04869624, -0.01511765, ...,  0.08492125,0.00951756, -0.07412069],[-0.00506077, -0.03876736,  0.04241635, ...,  0.08841018,0.00340768, -0.0132202 ],...,[-0.06426691, -0.02503901,  0.0479797 , ...,  0.10935511,-0.07242245, -0.07351919],[-0.03200135,  0.00878106, -0.00114083, ...,  0.11050082,0.04304891, -0.05242905],[ 0.0011186 , -0.07922951,  0.03307959, ...,  0.11846839,-0.01468282, -0.02137253]],[[-0.07088375, -0.09605353, -0.0870923 , ...,  0.05969601,-0.04490016, -0.08674914],[-0.04792272, -0.00552623,  0.04312531, ...,  0.07512051,-0.02942253, -0.01657942],[-0.02924686, -0.0083315 , -0.03119195, ...,  0.08836354,0.01749841, -0.08144853],...,[-0.0360165 , -0.04147609,  0.02005479, ...,  0.10100625,0.01419461, -0.05741529],[-0.01624438, -0.01840974,  0.01271305, ...,  0.09400898,-0.00146088, -0.0448955 ],[-0.04253309, -0.04165547,  0.00082437, ...,  0.10597158,-0.03005156, -0.0053229 ]]], dtype=float32)</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span>z_1|participant_id_sigma</span></div><div class='xr-var-dims'>(chain, draw)</div><div class='xr-var-dtype'>float32</div><div class='xr-var-preview xr-preview'>...</div><input id='attrs-8bcddafd-faca-4b34-ac01-df6829e8c6d1' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-8bcddafd-faca-4b34-ac01-df6829e8c6d1' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-fea287b9-ee5d-480f-8306-9b027b96095c' class='xr-var-data-in' type='checkbox'><label for='data-fea287b9-ee5d-480f-8306-9b027b96095c' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>Array([[0.03293062, 0.04601797, 0.06423832, 0.05636267, 0.05796819,0.06134144, 0.0483369 , 0.04921225, 0.04833033, 0.05441251,0.04620728, 0.0479633 , 0.03452729, 0.0386274 , 0.03991828,0.08373977, 0.04224537, 0.05382941, 0.04726394, 0.07637266,0.04189361, 0.04949851, 0.04115686, 0.06337816, 0.0780177 ,0.03676307, 0.04001185, 0.05428471, 0.04247198, 0.05729344,0.07990868, 0.04465702, 0.04353601, 0.06138485, 0.04859183,0.04971318, 0.05482906, 0.0436686 , 0.07940932, 0.06704625,0.05509457, 0.03813042, 0.04843035, 0.04730067, 0.05373441,0.06428806, 0.05400744, 0.03724943, 0.0355711 , 0.05929131,0.06595455, 0.03986346, 0.03633858, 0.03539714, 0.03488162,0.03621359, 0.03857179, 0.0488404 , 0.06313634, 0.04245935,0.06361253, 0.05027619, 0.05577793, 0.05144735, 0.04209995,0.05662366, 0.06502704, 0.06575407, 0.03448814, 0.04962358,0.03656469, 0.03594694, 0.05737396, 0.04568786, 0.04100513,0.04452945, 0.0613487 , 0.06975123, 0.03873817, 0.03852537,0.08069589, 0.07135563, 0.06050534, 0.0368136 , 0.0397923 ,0.04073238, 0.04736868, 0.05320646, 0.04280367, 0.05866715,0.06502071, 0.0377905 , 0.02894649, 0.03676869, 0.05530391,0.05709023, 0.0417349 , 0.03444916, 0.02514199, 0.08811139,...0.04683939, 0.05596058, 0.05729179, 0.0554338 , 0.05941771,0.04869968, 0.0338745 , 0.04034192, 0.05438074, 0.05291946,0.06297854, 0.06450481, 0.06334021, 0.04985338, 0.05522647,0.05100204, 0.0690545 , 0.0572174 , 0.08651043, 0.05349092,0.0417087 , 0.05088945, 0.06016496, 0.03786529, 0.03345714,0.03345449, 0.05921111, 0.03846884, 0.05701494, 0.03918625,0.04820742, 0.04054002, 0.03219448, 0.03846275, 0.05605682,0.05030427, 0.04396316, 0.04900967, 0.06020732, 0.0781012 ,0.03186815, 0.03226601, 0.04602415, 0.06291063, 0.0701552 ,0.03708128, 0.03425751, 0.06385265, 0.03037233, 0.06201604,0.03082344, 0.05530528, 0.07398713, 0.04353082, 0.0665229 ,0.05099551, 0.05165873, 0.04750815, 0.03001784, 0.05733846,0.04105543, 0.0345456 , 0.03688649, 0.05914934, 0.04190239,0.05295826, 0.04912997, 0.05513356, 0.07620168, 0.0876178 ,0.06015056, 0.07111558, 0.04171923, 0.04339175, 0.0569487 ,0.03581368, 0.05344849, 0.06791448, 0.09967433, 0.02767397,0.03546734, 0.0507259 , 0.05927493, 0.04497091, 0.05266746,0.034408  , 0.04410458, 0.07722101, 0.06945789, 0.05069859,0.05948353, 0.06180137, 0.04139225, 0.05232892, 0.04465526,0.04351337, 0.03549614, 0.066316  , 0.05802132, 0.04925322]],      dtype=float32)</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span>theta_1|participant_id</span></div><div class='xr-var-dims'>(chain, draw, participant_id__factor_dim)</div><div class='xr-var-dtype'>float32</div><div class='xr-var-preview xr-preview'>...</div><input id='attrs-29b2c905-77c1-4d11-9ec3-fd592c495d65' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-29b2c905-77c1-4d11-9ec3-fd592c495d65' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-c72db8eb-a820-4c4c-a1d4-93e725c6f681' class='xr-var-data-in' type='checkbox'><label for='data-c72db8eb-a820-4c4c-a1d4-93e725c6f681' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>Array([[[ 0.03904036, -0.11790815,  0.06401705, ..., -0.00879353,0.05540285, -0.09410584],[ 0.04629304, -0.04865622,  0.17682914, ...,  0.21104687,0.06391059,  0.04829139],[ 0.01484822, -0.03594987,  0.1471707 , ..., -0.01058516,-0.02735408, -0.03571864],...,[ 0.03095307,  0.02631363,  0.08744261, ...,  0.06861527,-0.02162858,  0.00600304],[-0.16356291,  0.00899921,  0.08847178, ...,  0.00225451,-0.02677025,  0.0317673 ],[-0.00190459, -0.15430528, -0.02188865, ...,  0.0449923 ,-0.13326651, -0.19474232]],[[-0.031715  ,  0.02763416,  0.07678115, ...,  0.14180295,0.02555301, -0.11768737],[ 0.05256386,  0.01420413,  0.10572291, ...,  0.09387959,0.01137982,  0.03732558],[ 0.03932681, -0.05735949,  0.10457171, ...,  0.08859626,-0.13791011,  0.03644061],...,[ 0.00380178, -0.03943419,  0.19472426, ...,  0.17305985,0.176755  , -0.01111225],[-0.02035765, -0.04905679,  0.1092951 , ...,  0.09651964,0.00233537, -0.0166672 ],[-0.01376625, -0.01282638,  0.15795128, ...,  0.02368554,-0.02139419, -0.05027936]]], dtype=float32)</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span>rl_alpha_Intercept</span></div><div class='xr-var-dims'>(chain, draw)</div><div class='xr-var-dtype'>float32</div><div class='xr-var-preview xr-preview'>...</div><input id='attrs-08f94a55-11e1-472a-b342-8df36a5a7950' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-08f94a55-11e1-472a-b342-8df36a5a7950' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-ef43094e-1d17-4c19-a3e1-2dae52f99ace' class='xr-var-data-in' type='checkbox'><label for='data-ef43094e-1d17-4c19-a3e1-2dae52f99ace' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>Array([[0.08339877, 0.09401349, 0.07509188, 0.09578697, 0.07873082,0.09526614, 0.08151589, 0.10334619, 0.09529855, 0.0965765 ,0.10570784, 0.13104622, 0.08414888, 0.08450262, 0.09625464,0.07404919, 0.07764632, 0.08778427, 0.08418833, 0.11374198,0.07769679, 0.1092982 , 0.07088748, 0.09111337, 0.09654032,0.07911403, 0.09517269, 0.08770812, 0.09182872, 0.09086402,0.08548225, 0.09448189, 0.10215986, 0.06940646, 0.09310148,0.0808863 , 0.09139363, 0.08559296, 0.08282399, 0.07452813,0.09097233, 0.10616863, 0.10437366, 0.07244094, 0.1155548 ,0.09530596, 0.07318923, 0.07628701, 0.07741083, 0.07709368,0.08468686, 0.09793549, 0.12132968, 0.06458864, 0.06502777,0.0654593 , 0.09522212, 0.08913235, 0.10462759, 0.07165165,0.08676013, 0.11060183, 0.10208908, 0.10101665, 0.10275162,0.08869769, 0.07232448, 0.06145713, 0.13523614, 0.10813602,0.08543563, 0.08550324, 0.08954515, 0.08427811, 0.08717028,0.09416861, 0.08358215, 0.08933859, 0.08827595, 0.07722708,0.09309002, 0.08115958, 0.07766241, 0.06486364, 0.07570716,0.08249017, 0.07290205, 0.09624349, 0.10354541, 0.08968219,0.07693598, 0.09104989, 0.10908881, 0.09502507, 0.08850181,0.09173732, 0.06884485, 0.08911377, 0.08900025, 0.0943078 ,...0.08913457, 0.09797468, 0.09776965, 0.09908408, 0.07672478,0.08149447, 0.08535516, 0.08708226, 0.07207926, 0.0636085 ,0.06150515, 0.0678369 , 0.09267832, 0.08925528, 0.07749525,0.08073492, 0.09148207, 0.09980344, 0.0832417 , 0.10896682,0.05814512, 0.07773247, 0.07409981, 0.1004692 , 0.10024794,0.07546061, 0.08527389, 0.1017699 , 0.08943605, 0.08845862,0.09193476, 0.07758117, 0.08403575, 0.08605895, 0.08079629,0.0959994 , 0.08665978, 0.06647552, 0.09200864, 0.10881364,0.07949512, 0.10227446, 0.09304504, 0.08845043, 0.08209582,0.08878889, 0.08925504, 0.07939752, 0.10166555, 0.07185205,0.07894938, 0.07360014, 0.12176114, 0.07398237, 0.08149993,0.08450171, 0.10938256, 0.07868705, 0.07958932, 0.10332488,0.06881358, 0.096546  , 0.10873863, 0.07847845, 0.08950131,0.0717323 , 0.08004267, 0.09561332, 0.06436922, 0.06803087,0.0758305 , 0.06860016, 0.11300618, 0.10920673, 0.08042723,0.09296833, 0.07756389, 0.06396382, 0.07937297, 0.08948173,0.08824449, 0.09404302, 0.08269445, 0.07238156, 0.11529844,0.07867333, 0.08724512, 0.10540936, 0.07639623, 0.10326978,0.06959617, 0.11709587, 0.07723632, 0.08186674, 0.09985832,0.07534098, 0.09051776, 0.08483773, 0.11205589, 0.08084299]],      dtype=float32)</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span>t_Intercept</span></div><div class='xr-var-dims'>(chain, draw)</div><div class='xr-var-dtype'>float32</div><div class='xr-var-preview xr-preview'>...</div><input id='attrs-ca7561ba-7088-4f8b-9fed-38f2a01f60c8' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-ca7561ba-7088-4f8b-9fed-38f2a01f60c8' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-39e03ae6-c46a-402b-b79f-2f9042905de2' class='xr-var-data-in' type='checkbox'><label for='data-39e03ae6-c46a-402b-b79f-2f9042905de2' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>Array([[0.24055146, 0.26297793, 0.2532536 , 0.23840445, 0.24094853,0.23523878, 0.21558915, 0.2089466 , 0.2540757 , 0.24214192,0.24329935, 0.25389352, 0.2561597 , 0.2670954 , 0.20611659,0.22941247, 0.21832478, 0.2482502 , 0.23182677, 0.24079631,0.23417313, 0.25976056, 0.23924696, 0.24616252, 0.25357765,0.22919478, 0.238018  , 0.24479333, 0.19550686, 0.2166697 ,0.24407089, 0.24508214, 0.25077483, 0.25210315, 0.2513383 ,0.25438148, 0.2526124 , 0.24682969, 0.25132862, 0.22421965,0.2567126 , 0.23714396, 0.22491539, 0.25020593, 0.23444995,0.26475617, 0.24417414, 0.2260893 , 0.23816557, 0.26804867,0.23675486, 0.23684642, 0.2514962 , 0.24706209, 0.24630617,0.24330308, 0.22950362, 0.22494626, 0.2473373 , 0.25438562,0.24478365, 0.24592146, 0.23915552, 0.24281389, 0.25412685,0.24680224, 0.24008502, 0.23853403, 0.22448763, 0.25434992,0.24954884, 0.21304768, 0.2241637 , 0.2649934 , 0.24149682,0.22781079, 0.25881094, 0.2449496 , 0.22732167, 0.24546987,0.24153583, 0.2567594 , 0.24787281, 0.2572875 , 0.2451181 ,0.25676763, 0.24803248, 0.28868124, 0.25788411, 0.25605693,0.2315649 , 0.2470646 , 0.2536237 , 0.24883428, 0.23500144,0.22902752, 0.23350163, 0.26587963, 0.23259133, 0.2632303 ,...0.24156353, 0.27120003, 0.26436752, 0.26205516, 0.20440833,0.1920309 , 0.23435204, 0.27001998, 0.216763  , 0.22503665,0.23118334, 0.24182668, 0.25751168, 0.2640584 , 0.24351938,0.2437246 , 0.2619751 , 0.2600293 , 0.21511403, 0.2379319 ,0.21166515, 0.2637904 , 0.25045294, 0.23942979, 0.24461219,0.21561456, 0.2671636 , 0.24367891, 0.26039347, 0.2550045 ,0.24213587, 0.22422251, 0.2461963 , 0.23416668, 0.23702729,0.24228603, 0.25220492, 0.24492651, 0.29494166, 0.28645995,0.24243319, 0.2562385 , 0.24823698, 0.25666827, 0.25462657,0.22712845, 0.23597284, 0.22510938, 0.23279528, 0.25705466,0.2439006 , 0.265837  , 0.26504868, 0.23905458, 0.24194017,0.24821366, 0.24430732, 0.2370417 , 0.24817847, 0.24655333,0.23331611, 0.26128206, 0.25072417, 0.2178059 , 0.26559216,0.25837705, 0.2660197 , 0.25395617, 0.22702119, 0.21787609,0.27173585, 0.26317707, 0.24478716, 0.24289808, 0.24315375,0.2332859 , 0.23505776, 0.2522117 , 0.22550945, 0.24611606,0.24999359, 0.23373622, 0.2434961 , 0.2365476 , 0.21732822,0.23602483, 0.24755009, 0.22881651, 0.24296643, 0.25895202,0.24868758, 0.24335268, 0.22566724, 0.22591355, 0.25201544,0.24391225, 0.27974078, 0.258906  , 0.25228128, 0.24252112]],      dtype=float32)</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span>theta_1|participant_id_sigma</span></div><div class='xr-var-dims'>(chain, draw)</div><div class='xr-var-dtype'>float32</div><div class='xr-var-preview xr-preview'>...</div><input id='attrs-4e303193-75c7-4046-8a6f-50ea2ef69efa' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-4e303193-75c7-4046-8a6f-50ea2ef69efa' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-cae9c528-cf60-42df-91f1-3ac7f5a66d6c' class='xr-var-data-in' type='checkbox'><label for='data-cae9c528-cf60-42df-91f1-3ac7f5a66d6c' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>Array([[0.08211927, 0.12152683, 0.1803771 , 0.18241598, 0.14088918,0.16910364, 0.11555008, 0.13623503, 0.19081278, 0.19932702,0.10230989, 0.1238358 , 0.10034673, 0.11500672, 0.1409985 ,0.19959114, 0.09851799, 0.12654142, 0.17879263, 0.10258928,0.15170214, 0.13257839, 0.11850856, 0.10240665, 0.11564635,0.15044616, 0.08050626, 0.10901254, 0.11962322, 0.1208349 ,0.1537336 , 0.14918795, 0.12364118, 0.10158639, 0.146466  ,0.1325695 , 0.1140629 , 0.1439923 , 0.16017926, 0.13542902,0.12235952, 0.11251878, 0.12204763, 0.12603275, 0.13458014,0.10735531, 0.10201473, 0.12916133, 0.19600078, 0.09506583,0.11667212, 0.12766123, 0.11141245, 0.109277  , 0.10582446,0.11360228, 0.11107797, 0.11416397, 0.20687628, 0.11212771,0.17568605, 0.13815276, 0.1327608 , 0.12422576, 0.12124977,0.11053389, 0.16251558, 0.10900281, 0.12685512, 0.11780042,0.1392319 , 0.12108459, 0.11853812, 0.12297858, 0.14108557,0.11266113, 0.17974299, 0.13721274, 0.1470162 , 0.10841182,0.14665163, 0.14632626, 0.14215174, 0.09886037, 0.1117485 ,0.10500623, 0.07525499, 0.11729182, 0.17342564, 0.13366619,0.13069826, 0.09771247, 0.11456653, 0.13017435, 0.16579992,0.17192821, 0.14304408, 0.11457995, 0.08254893, 0.1912589 ,...0.15656061, 0.14790991, 0.12909457, 0.12767833, 0.12376496,0.08309519, 0.10277783, 0.10988571, 0.1528269 , 0.15314177,0.10102541, 0.0906235 , 0.14177918, 0.16427064, 0.10554286,0.1243011 , 0.10721506, 0.1497033 , 0.11204939, 0.11393034,0.10072634, 0.10197014, 0.08871394, 0.22475974, 0.2522714 ,0.2586742 , 0.15751475, 0.12601665, 0.14155895, 0.13566975,0.11715233, 0.13079241, 0.14470358, 0.10882183, 0.11983951,0.13947348, 0.15703808, 0.15621054, 0.16325752, 0.1937927 ,0.1173453 , 0.11115527, 0.09137659, 0.09733868, 0.11232547,0.14588174, 0.14314787, 0.14032619, 0.11171387, 0.13139394,0.1257287 , 0.15068673, 0.0968051 , 0.10750285, 0.15304685,0.15391646, 0.11217437, 0.19393766, 0.17172258, 0.16248024,0.17235255, 0.20607652, 0.22781202, 0.16123842, 0.11976234,0.12497827, 0.11943106, 0.12135968, 0.13476421, 0.11129471,0.13284476, 0.15337339, 0.09841076, 0.10474165, 0.12312964,0.1849975 , 0.17029783, 0.20441192, 0.14092831, 0.16827245,0.1878952 , 0.09610923, 0.09367634, 0.1140778 , 0.10531558,0.11141633, 0.09821808, 0.12002609, 0.12939088, 0.14248379,0.14908588, 0.25098544, 0.42481202, 0.24036352, 0.10426454,0.12972245, 0.08343657, 0.11937316, 0.12408622, 0.10021736]],      dtype=float32)</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span>z_Intercept</span></div><div class='xr-var-dims'>(chain, draw)</div><div class='xr-var-dtype'>float32</div><div class='xr-var-preview xr-preview'>...</div><input id='attrs-fc1c74a7-2dce-418d-bafd-38a1e1558791' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-fc1c74a7-2dce-418d-bafd-38a1e1558791' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-f9c51e84-8951-4c9d-a5f1-8b5815e2377e' class='xr-var-data-in' type='checkbox'><label for='data-f9c51e84-8951-4c9d-a5f1-8b5815e2377e' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>Array([[0.526144  , 0.5197164 , 0.49877524, 0.5128483 , 0.5199616 ,0.5273984 , 0.5149499 , 0.52661425, 0.51875126, 0.5196322 ,0.5249877 , 0.51051575, 0.5096878 , 0.51614934, 0.52862984,0.55143845, 0.5297025 , 0.52774733, 0.53652906, 0.49928612,0.5291426 , 0.5117379 , 0.508382  , 0.5064903 , 0.5140194 ,0.51616746, 0.52036107, 0.49629882, 0.5477669 , 0.5575556 ,0.5634936 , 0.51523143, 0.49391115, 0.5352662 , 0.53043664,0.4988695 , 0.5244085 , 0.54043454, 0.5307034 , 0.52956086,0.5191317 , 0.50727683, 0.5044513 , 0.526546  , 0.50772464,0.5337866 , 0.5149825 , 0.53599834, 0.50951564, 0.5184962 ,0.48173258, 0.5258982 , 0.52199024, 0.5076832 , 0.50737673,0.5081572 , 0.51957923, 0.53550714, 0.5193449 , 0.51291126,0.52463585, 0.5094109 , 0.49642393, 0.49964526, 0.50879383,0.5110856 , 0.5106667 , 0.5129648 , 0.53004116, 0.5317686 ,0.53614765, 0.53531355, 0.5255071 , 0.53715575, 0.49941367,0.52526486, 0.4869722 , 0.5021167 , 0.5360987 , 0.5470226 ,0.51877457, 0.52258253, 0.50529206, 0.48358038, 0.51066613,0.5105191 , 0.52598315, 0.5133706 , 0.511638  , 0.51968116,0.5166543 , 0.52556705, 0.5313136 , 0.5231781 , 0.49996728,0.51078904, 0.525364  , 0.51134974, 0.5238894 , 0.5067926 ,...0.50840676, 0.52138704, 0.5226833 , 0.52166015, 0.5086821 ,0.49422428, 0.536477  , 0.50861406, 0.49529228, 0.49279946,0.48281488, 0.47639415, 0.49711943, 0.49765575, 0.5097337 ,0.5119549 , 0.5044497 , 0.51381385, 0.4744153 , 0.49990723,0.51336867, 0.47114524, 0.49124104, 0.51129943, 0.5287415 ,0.52409273, 0.5202361 , 0.5295168 , 0.4983795 , 0.5205554 ,0.53859526, 0.52703786, 0.51884854, 0.5287825 , 0.5179695 ,0.5143067 , 0.5217661 , 0.5199087 , 0.5180999 , 0.52539974,0.51909405, 0.5102024 , 0.5383264 , 0.490336  , 0.51137406,0.5275704 , 0.51471716, 0.52197737, 0.5354939 , 0.48957148,0.5086362 , 0.52109677, 0.5129573 , 0.4747152 , 0.4945604 ,0.505206  , 0.52385646, 0.5259679 , 0.51816046, 0.51469624,0.5087705 , 0.5033715 , 0.51598275, 0.5403621 , 0.528851  ,0.5522514 , 0.5280529 , 0.52380496, 0.48980537, 0.49569607,0.46852922, 0.49607813, 0.508683  , 0.51229864, 0.4898397 ,0.4922544 , 0.5068037 , 0.50056845, 0.49892503, 0.5276567 ,0.5056169 , 0.5231473 , 0.5220771 , 0.5183487 , 0.51720387,0.5184719 , 0.52890795, 0.49787265, 0.5211264 , 0.5144414 ,0.5185539 , 0.51622826, 0.49906328, 0.503311  , 0.5320201 ,0.5422829 , 0.5072723 , 0.5163751 , 0.51380265, 0.51091975]],      dtype=float32)</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span>scaler_1|participant_id</span></div><div class='xr-var-dims'>(chain, draw, participant_id__factor_dim)</div><div class='xr-var-dtype'>float32</div><div class='xr-var-preview xr-preview'>...</div><input id='attrs-f9b543f4-4fa6-4fd4-a39f-006b2b3552c3' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-f9b543f4-4fa6-4fd4-a39f-006b2b3552c3' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-95515548-5f53-4373-8b4c-891e160ce680' class='xr-var-data-in' type='checkbox'><label for='data-95515548-5f53-4373-8b4c-891e160ce680' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>Array([[[-0.0825239 ,  0.40123263, -0.06907374, ..., -1.5370672 ,1.1734446 ,  1.2603811 ],[ 0.79703623, -0.5740658 , -0.57822454, ..., -0.3610177 ,0.4681965 ,  1.2699469 ],[-0.25244528, -0.18862614,  0.3184729 , ..., -0.7352084 ,0.10893168,  0.39052492],...,[-0.51324904, -0.07518269,  0.56839526, ..., -0.22804312,-0.00746558,  0.5815969 ],[ 0.28905326,  0.260019  , -0.05298692, ..., -0.98465025,0.88931197,  1.2218753 ],[-0.1235831 , -0.44352224, -0.43404266, ..., -0.83272105,0.2852139 ,  0.37402296]],[[-0.44946128, -0.8226944 , -0.3496793 , ...,  0.16973211,-0.5333501 ,  0.82874984],[-0.3639215 , -0.36944598, -0.2730193 , ..., -1.2798036 ,0.25307533,  1.0631496 ],[ 0.7720291 ,  0.334045  ,  0.16923442, ..., -0.7168518 ,0.5736193 ,  0.6569187 ],...,[ 0.4162023 , -0.34379676,  0.06288593, ...,  0.05693482,0.17967916,  1.1616474 ],[ 0.7447304 , -0.27530825, -0.19876017, ..., -1.4185767 ,0.96193326,  1.0973251 ],[-0.314986  , -0.4679827 , -0.32641435, ..., -1.1741107 ,0.16977578,  1.2851646 ]]], dtype=float32)</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span>z_1|participant_id_offset</span></div><div class='xr-var-dims'>(chain, draw, participant_id__factor_dim)</div><div class='xr-var-dtype'>float32</div><div class='xr-var-preview xr-preview'>...</div><input id='attrs-cb38b6a2-bcba-4f38-8b8d-2b855d433765' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-cb38b6a2-bcba-4f38-8b8d-2b855d433765' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-c16474c0-0ad7-430c-8cf9-c96fc1d8941b' class='xr-var-data-in' type='checkbox'><label for='data-c16474c0-0ad7-430c-8cf9-c96fc1d8941b' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>Array([[[-1.4851637 , -0.52079034, -1.2220457 , ...,  1.9317403 ,0.28212628, -0.5300893 ],[-1.1671442 , -1.0582004 , -0.32851616, ...,  1.8453931 ,0.2068227 , -1.61069   ],[-0.07878117, -0.6034926 ,  0.66029656, ...,  1.376284  ,0.05304748, -0.20579927],...,[-0.8572554 , -0.33399504,  0.6400006 , ...,  1.4586864 ,-0.96604216, -0.9806715 ],[-0.6952542 ,  0.19077538, -0.02478537, ...,  2.4007165 ,0.9352711 , -1.139062  ],[ 0.02140189, -1.5158762 ,  0.6329025 , ...,  2.2666228 ,-0.28092223, -0.40891466]],[[-1.2016673 , -1.6283618 , -1.4764451 , ...,  1.0120056 ,-0.76117665, -1.4706277 ],[-1.279955  , -0.14759853,  1.1518223 , ...,  2.0063734 ,-0.78583854, -0.4428152 ],[-0.5242643 , -0.1493462 , -0.55913097, ...,  1.5839599 ,0.3136676 , -1.4600048 ],...,[-0.54310423, -0.62543106,  0.30241254, ...,  1.5231054 ,0.21404496, -0.8657834 ],[-0.27997258, -0.31729266,  0.21911001, ...,  1.620249  ,-0.02517838, -0.77377594],[-0.8635596 , -0.84574103,  0.01673728, ...,  2.1515667 ,-0.6101441 , -0.10807212]]], dtype=float32)</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span>theta_Intercept</span></div><div class='xr-var-dims'>(chain, draw)</div><div class='xr-var-dtype'>float32</div><div class='xr-var-preview xr-preview'>...</div><input id='attrs-b4b50d3e-9891-4cb2-8796-f137c2d8d031' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-b4b50d3e-9891-4cb2-8796-f137c2d8d031' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-6ca319d5-d500-4bed-8d53-fae9a08b9e23' class='xr-var-data-in' type='checkbox'><label for='data-6ca319d5-d500-4bed-8d53-fae9a08b9e23' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>Array([[0.3552481 , 0.3013985 , 0.38640156, 0.39485934, 0.4241807 ,0.27968866, 0.3982103 , 0.36310825, 0.29531062, 0.28816977,0.41063103, 0.41557094, 0.3476206 , 0.37716565, 0.32535195,0.28769615, 0.35519856, 0.2807338 , 0.29763845, 0.3455775 ,0.35247454, 0.30781704, 0.36452383, 0.32925045, 0.35698494,0.33118173, 0.35844785, 0.37240994, 0.3309184 , 0.3474236 ,0.3317736 , 0.3451702 , 0.35015416, 0.32127166, 0.33950675,0.34357172, 0.3908712 , 0.41671285, 0.38066918, 0.35678363,0.27798986, 0.3167232 , 0.32373995, 0.3343333 , 0.3027319 ,0.29217482, 0.34582755, 0.37266803, 0.39958265, 0.27938566,0.35168523, 0.39125967, 0.4135827 , 0.34963933, 0.35149196,0.34795058, 0.34195045, 0.32383543, 0.3500164 , 0.3295393 ,0.34454304, 0.30968103, 0.33335406, 0.33672726, 0.3110087 ,0.34953678, 0.28678384, 0.329792  , 0.3365853 , 0.34197807,0.31862167, 0.3273689 , 0.32907483, 0.37039706, 0.38491985,0.37413234, 0.33854932, 0.4401885 , 0.29974577, 0.32999387,0.31710994, 0.3489448 , 0.3600911 , 0.30548212, 0.31424004,0.28138685, 0.3367754 , 0.33807313, 0.34767902, 0.33958143,0.3072344 , 0.35341877, 0.33900306, 0.34969282, 0.36298603,0.38011116, 0.35730678, 0.30018878, 0.29877087, 0.39705804,...0.27038473, 0.3463017 , 0.3610196 , 0.3445343 , 0.39893928,0.41351977, 0.31203595, 0.34550622, 0.34808844, 0.3465422 ,0.36089918, 0.38781625, 0.32987538, 0.3632838 , 0.29903752,0.2892682 , 0.3482942 , 0.29359967, 0.3330115 , 0.31822687,0.46334845, 0.28992015, 0.3585063 , 0.3119138 , 0.31278002,0.31511357, 0.32773635, 0.3627659 , 0.34089133, 0.2896539 ,0.34861743, 0.37389022, 0.3987324 , 0.36085644, 0.32226527,0.37213537, 0.36554986, 0.34717536, 0.3152578 , 0.3304331 ,0.35534886, 0.35803527, 0.3484059 , 0.33215842, 0.3430177 ,0.3189776 , 0.28146946, 0.3256132 , 0.34424683, 0.36734343,0.342525  , 0.27543744, 0.34415388, 0.3745911 , 0.3503444 ,0.28243268, 0.36517245, 0.373744  , 0.29281542, 0.4189245 ,0.27210662, 0.30699572, 0.3355503 , 0.46151158, 0.34956253,0.36449   , 0.34697837, 0.3593932 , 0.3780759 , 0.35771227,0.37626633, 0.36919194, 0.28822234, 0.28913057, 0.3311901 ,0.33140334, 0.3816361 , 0.34800303, 0.34237146, 0.29663122,0.27408743, 0.33744058, 0.3103174 , 0.27669287, 0.32297292,0.37522933, 0.3449095 , 0.32999355, 0.30587748, 0.3222037 ,0.29078844, 0.3200222 , 0.30559266, 0.3294694 , 0.33669087,0.29976863, 0.28980273, 0.3076237 , 0.3864198 , 0.35746783]],      dtype=float32)</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span>a_1|participant_id</span></div><div class='xr-var-dims'>(chain, draw, participant_id__factor_dim)</div><div class='xr-var-dtype'>float32</div><div class='xr-var-preview xr-preview'>...</div><input id='attrs-0e2bdb11-8a14-42a8-a78d-ddcb9e029b0c' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-0e2bdb11-8a14-42a8-a78d-ddcb9e029b0c' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-87380954-ec4f-40a4-bad5-1f3fd573ded6' class='xr-var-data-in' type='checkbox'><label for='data-87380954-ec4f-40a4-bad5-1f3fd573ded6' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>Array([[[ 0.01943887, -0.28990746,  0.01171204, ..., -0.13932145,-0.00835499,  0.07710907],[-0.1275089 , -0.21761107,  0.08389812, ..., -0.07101207,-0.0868251 ,  0.02569814],[-0.03535444, -0.18084224,  0.16897197, ..., -0.09040066,-0.17199534,  0.09721121],...,[-0.05815013, -0.09153346,  0.06713159, ..., -0.03323395,-0.05651442,  0.1586283 ],[-0.21978328, -0.18473656,  0.10907363, ..., -0.2156294 ,-0.15861636,  0.19668248],[ 0.08667648, -0.19397978,  0.05726476, ...,  0.04881148,-0.06796885,  0.06858458]],[[-0.12440771, -0.1789094 ,  0.06703445, ..., -0.04250951,-0.12179139, -0.02336721],[-0.16264842, -0.26419523,  0.02624749, ..., -0.16626051,-0.24203207,  0.07164045],[-0.04889696, -0.2470351 ,  0.01126998, ..., -0.16283962,-0.28408068,  0.13527164],...,[-0.07554574, -0.27355313,  0.13488936, ...,  0.00176212,0.0444525 ,  0.01778561],[-0.00764989, -0.15440749,  0.11120858, ...,  0.02238644,0.01993163,  0.13843983],[-0.01592279, -0.1892518 ,  0.12524533, ..., -0.17752177,-0.12549305,  0.09375707]]], dtype=float32)</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span>scaler_1|participant_id_sigma</span></div><div class='xr-var-dims'>(chain, draw)</div><div class='xr-var-dtype'>float32</div><div class='xr-var-preview xr-preview'>...</div><input id='attrs-74924bdd-b002-4c40-8fa3-30f8d0ab2b1a' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-74924bdd-b002-4c40-8fa3-30f8d0ab2b1a' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-971b944d-3732-4667-8668-3607b5059dc2' class='xr-var-data-in' type='checkbox'><label for='data-971b944d-3732-4667-8668-3607b5059dc2' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>Array([[0.93023324, 0.53897643, 0.48963413, 0.6174706 , 0.42304003,0.5708074 , 0.37226444, 0.35192603, 0.16130874, 0.17198302,0.45427436, 0.38211763, 0.31307638, 0.33817288, 0.68450034,0.43935084, 0.39574695, 0.2535635 , 0.41185957, 0.41107693,0.6193277 , 0.3018944 , 0.57050294, 0.3559234 , 0.7611498 ,0.3757919 , 0.68066686, 0.3779762 , 0.6781505 , 0.50714993,0.50305265, 0.68087393, 0.3216825 , 0.61695206, 0.53099513,0.34043896, 0.73440206, 0.8589761 , 0.7341373 , 0.43235865,0.3981601 , 0.37185007, 0.61863226, 0.5571967 , 0.61429566,0.5378428 , 0.83365613, 0.50648093, 0.5868525 , 0.5578062 ,0.37781942, 0.45011353, 0.43705773, 0.53617424, 0.5242331 ,0.5636516 , 0.43458337, 0.43336564, 0.41821423, 0.24337058,0.48256022, 0.41150826, 0.40667972, 0.34099266, 0.2272453 ,0.1555774 , 0.17183785, 0.18725619, 0.3650881 , 0.566174  ,0.7093551 , 0.7289897 , 0.5299418 , 0.43461287, 0.4221521 ,0.5605597 , 0.4666971 , 0.42776054, 0.49937215, 0.40006334,0.50154066, 0.54462254, 0.18064281, 0.5617185 , 0.435736  ,0.82433516, 0.31800646, 0.4327926 , 0.23096529, 0.2122946 ,0.35029006, 0.5293883 , 0.46532995, 0.318337  , 0.33387682,0.6727953 , 0.59383816, 0.4840388 , 0.5450409 , 0.5229958 ,...0.45131448, 0.39519584, 0.54715836, 0.5262482 , 0.54841655,0.3641958 , 0.6615294 , 0.7283164 , 0.24442026, 0.27330482,0.24368048, 0.38103712, 0.25960597, 0.25364265, 0.13504471,0.12988876, 0.02258904, 0.1619046 , 0.07368641, 0.20707026,0.18645556, 0.3783922 , 0.2903843 , 0.54537326, 0.3928014 ,0.83421654, 0.42154872, 0.77224994, 0.55056036, 0.44704348,0.37801337, 0.64827657, 0.39143664, 0.5876289 , 0.2832373 ,0.14348316, 0.41187   , 0.5086255 , 0.2908306 , 0.35871696,0.3367724 , 0.25426966, 0.6783105 , 0.8067496 , 0.6614162 ,0.2587131 , 0.41162604, 0.4913569 , 0.719808  , 0.25041497,0.3473512 , 0.4606489 , 0.51377183, 0.51382   , 0.69352555,0.6796417 , 0.55859286, 0.22908388, 0.5833066 , 0.30387306,0.48045105, 0.57576483, 0.47256032, 0.5887618 , 0.55868775,0.42192388, 0.44142726, 0.2376179 , 0.35916477, 0.23281449,0.2004923 , 0.28936702, 0.25542942, 0.21727417, 0.31955254,0.4479393 , 0.4747098 , 0.4459323 , 0.50167906, 0.4135481 ,0.55785096, 0.5914136 , 0.38401377, 0.44223163, 0.52411646,0.40437514, 0.5329592 , 0.49012432, 0.664561  , 0.6664592 ,0.2972859 , 0.37979108, 0.38298374, 0.3983879 , 0.5983083 ,0.4552628 , 0.3901076 , 0.42054075, 0.59473956, 0.584964  ]],      dtype=float32)</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span>rl_alpha_1|participant_id</span></div><div class='xr-var-dims'>(chain, draw, rl_alpha_1|participant_id__factor_dim)</div><div class='xr-var-dtype'>float32</div><div class='xr-var-preview xr-preview'>...</div><input id='attrs-9a8fadbc-4c89-4267-8f7e-2d45c6f863b0' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-9a8fadbc-4c89-4267-8f7e-2d45c6f863b0' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-6eb61b37-ed78-42b5-a124-2f5c2c735718' class='xr-var-data-in' type='checkbox'><label for='data-6eb61b37-ed78-42b5-a124-2f5c2c735718' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>Array([[[-5.16329100e-03, -4.24605189e-03,  2.73190177e-04, ...,-2.50538555e-03,  3.09800403e-03,  2.33197678e-02],[-5.00286594e-02,  4.31097932e-02,  4.75624315e-02, ...,-4.94793663e-03,  2.70157307e-02,  6.01239689e-03],[ 2.50818525e-02, -4.09861356e-02, -7.40386173e-03, ...,-3.93748730e-02, -9.46600121e-05,  4.57976274e-02],...,[ 5.76162990e-03, -1.15891444e-02,  1.32887426e-03, ...,-7.51137584e-02, -5.02668554e-03,  5.09165898e-02],[-1.18898097e-02, -2.68039177e-03, -7.73932924e-03, ...,2.65687201e-02,  2.30196565e-02,  9.86334402e-03],[-5.29594906e-03,  1.04808472e-02,  4.25094925e-02, ...,-5.70127591e-02, -1.38783245e-04,  3.77612449e-02]],[[ 5.04416227e-02,  2.27998123e-02,  1.12966541e-02, ...,-5.57260774e-02,  6.10405467e-02,  7.60243274e-03],[ 8.38791113e-03,  1.70093551e-02, -2.16812434e-04, ...,-1.79600660e-02,  3.73614915e-02,  4.05667238e-02],[-2.48084012e-02, -3.52872871e-02,  1.59401447e-02, ...,-3.15591246e-02, -4.24523978e-03,  3.92101817e-02],...,[ 3.80959478e-03,  4.93291812e-03,  1.26215760e-02, ...,1.33393705e-02,  1.84277147e-02,  7.32390163e-03],[-3.37252840e-02,  5.93623705e-03,  2.60026511e-02, ...,2.40618940e-02, -7.81781692e-03, -2.55411956e-03],[ 1.00495704e-02,  5.36588021e-03, -5.35450410e-03, ...,-3.20321275e-03, -1.86908257e-03,  1.43138533e-02]]],      dtype=float32)</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span>a_1|participant_id_sigma</span></div><div class='xr-var-dims'>(chain, draw)</div><div class='xr-var-dtype'>float32</div><div class='xr-var-preview xr-preview'>...</div><input id='attrs-0e461e45-5ac8-46ee-b436-cfbbc583c153' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-0e461e45-5ac8-46ee-b436-cfbbc583c153' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-616a1eee-4010-4f99-9799-11a8cd21d57a' class='xr-var-data-in' type='checkbox'><label for='data-616a1eee-4010-4f99-9799-11a8cd21d57a' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>Array([[0.12287576, 0.09662483, 0.14338095, 0.14673802, 0.13664   ,0.22999114, 0.10301206, 0.11855426, 0.09092144, 0.10138003,0.10498659, 0.11227494, 0.1255388 , 0.13185993, 0.11013168,0.12445198, 0.09207194, 0.10761445, 0.13255705, 0.15069905,0.11432249, 0.16310123, 0.08695915, 0.12970951, 0.13763982,0.13303363, 0.25062534, 0.1503691 , 0.11748628, 0.10968388,0.17441991, 0.10899544, 0.10813346, 0.20315702, 0.26286587,0.15803519, 0.30458358, 0.28070965, 0.17553337, 0.12195044,0.13416238, 0.11886916, 0.101634  , 0.11266264, 0.11854329,0.18767051, 0.14460924, 0.1449916 , 0.13586959, 0.12929781,0.18343388, 0.1477806 , 0.13514046, 0.10010794, 0.10222672,0.1042623 , 0.1353807 , 0.15039556, 0.14085437, 0.09051365,0.17244184, 0.09697924, 0.09182678, 0.0837497 , 0.07910538,0.08998445, 0.15976736, 0.16474438, 0.1740869 , 0.11869927,0.15232553, 0.07803038, 0.11255328, 0.1376234 , 0.0954102 ,0.15142561, 0.11004145, 0.06154089, 0.14503609, 0.19269271,0.11745164, 0.13987495, 0.07032152, 0.15304367, 0.16855025,0.14807048, 0.15629576, 0.16038686, 0.20494698, 0.19710656,0.1294842 , 0.14255112, 0.16141704, 0.1900185 , 0.12275369,0.16739573, 0.16349965, 0.18503878, 0.115765  , 0.12191172,...0.0887571 , 0.08877314, 0.08456899, 0.08927037, 0.06657247,0.17416309, 0.11919101, 0.09581611, 0.14731292, 0.15717049,0.19326864, 0.13058588, 0.10920444, 0.10451993, 0.091511  ,0.09757789, 0.13591933, 0.11021923, 0.150132  , 0.12090415,0.18181878, 0.13834326, 0.14122118, 0.11195528, 0.12452339,0.1261363 , 0.13611624, 0.14782815, 0.09947543, 0.0674378 ,0.12425192, 0.14013603, 0.13880992, 0.12132091, 0.13845706,0.10970729, 0.1206345 , 0.09802898, 0.10542335, 0.12123807,0.12335575, 0.09940276, 0.13979861, 0.15771198, 0.10680015,0.16709697, 0.13262975, 0.1394571 , 0.14496306, 0.08933911,0.10307985, 0.10311399, 0.09609317, 0.21612561, 0.09281772,0.10089961, 0.1213874 , 0.16712084, 0.21831475, 0.11489763,0.15532377, 0.23182514, 0.2071341 , 0.12394462, 0.159975  ,0.26526418, 0.19320041, 0.20735146, 0.23198847, 0.17556763,0.22233488, 0.17329888, 0.11596961, 0.11474375, 0.13108523,0.15834138, 0.18225613, 0.1506119 , 0.12564443, 0.14282878,0.13499452, 0.10199007, 0.15985468, 0.15178512, 0.10860452,0.11850967, 0.14713459, 0.13987255, 0.12623966, 0.15942936,0.18080121, 0.13728058, 0.199864  , 0.17422438, 0.12904793,0.230905  , 0.09020548, 0.13791364, 0.11916628, 0.11624974]],      dtype=float32)</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span>rl_alpha_1|participant_id_sigma</span></div><div class='xr-var-dims'>(chain, draw)</div><div class='xr-var-dtype'>float32</div><div class='xr-var-preview xr-preview'>...</div><input id='attrs-ab89d421-72e4-4c51-87a3-25faa8211464' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-ab89d421-72e4-4c51-87a3-25faa8211464' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-e7e0a205-408b-4c69-b0db-ecb5ef451620' class='xr-var-data-in' type='checkbox'><label for='data-e7e0a205-408b-4c69-b0db-ecb5ef451620' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>Array([[0.00940554, 0.03883268, 0.02661478, 0.00912448, 0.00842057,0.01755037, 0.04212552, 0.04678946, 0.05847612, 0.05390489,0.0523567 , 0.07195131, 0.06489667, 0.044988  , 0.04398653,0.03234508, 0.02148418, 0.04997126, 0.02995301, 0.0281352 ,0.0149499 , 0.0461518 , 0.00975984, 0.02854685, 0.00401689,0.03321282, 0.02677509, 0.04428593, 0.01862407, 0.02051285,0.03052881, 0.03497297, 0.02414585, 0.02175467, 0.04401139,0.02428669, 0.01608121, 0.01304104, 0.02266776, 0.02133185,0.02016877, 0.04057767, 0.03410271, 0.01724584, 0.03069218,0.02916485, 0.02951236, 0.02786648, 0.03572839, 0.01722569,0.0392731 , 0.04630522, 0.02520433, 0.02876157, 0.02639317,0.03176436, 0.03896033, 0.03176073, 0.03514628, 0.05009513,0.03831931, 0.04071671, 0.0443655 , 0.04282123, 0.06279315,0.03321663, 0.03376927, 0.04287298, 0.06327441, 0.03585186,0.01819014, 0.00175038, 0.00308709, 0.00457176, 0.0197674 ,0.01686207, 0.02311906, 0.007847  , 0.02643853, 0.0257224 ,0.01576401, 0.02653836, 0.02499437, 0.01257072, 0.0286977 ,0.02753968, 0.02598947, 0.04254506, 0.04201829, 0.04134136,0.02629305, 0.02017902, 0.01527204, 0.02218483, 0.02018187,0.02190912, 0.00905274, 0.0219541 , 0.01518545, 0.00807064,...0.02970599, 0.03530545, 0.03629231, 0.03821672, 0.05638279,0.03610415, 0.03795462, 0.02628995, 0.03551039, 0.05030757,0.05645501, 0.03898134, 0.04761216, 0.05303231, 0.0415982 ,0.04606568, 0.0371465 , 0.03890002, 0.02531735, 0.03485283,0.02735647, 0.02320158, 0.01326837, 0.03279454, 0.03579356,0.03227867, 0.02468762, 0.02128073, 0.02509222, 0.0450146 ,0.03343969, 0.0387804 , 0.02239905, 0.02755079, 0.01877542,0.01869468, 0.02125533, 0.00652387, 0.00694416, 0.01067997,0.0223225 , 0.01791857, 0.01418798, 0.00535561, 0.00193876,0.02382599, 0.00800211, 0.01576751, 0.03944627, 0.03090653,0.04281355, 0.01984565, 0.0342838 , 0.01859722, 0.03355567,0.02501275, 0.03405639, 0.06447188, 0.04856206, 0.03015348,0.01448529, 0.0147165 , 0.0213957 , 0.00601297, 0.00858463,0.02534092, 0.04260521, 0.03080205, 0.044143  , 0.04127153,0.0371001 , 0.02504443, 0.04540465, 0.04260384, 0.03283921,0.04652949, 0.02372537, 0.0291871 , 0.02632089, 0.03797549,0.02857756, 0.02980958, 0.05693008, 0.04757477, 0.03701505,0.04959139, 0.0554931 , 0.01849554, 0.01871189, 0.0358445 ,0.00886048, 0.03806823, 0.03574646, 0.01712094, 0.03184194,0.04738443, 0.03324453, 0.01677426, 0.02849868, 0.01394366]],      dtype=float32)</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span>scaler_Intercept</span></div><div class='xr-var-dims'>(chain, draw)</div><div class='xr-var-dtype'>float32</div><div class='xr-var-preview xr-preview'>...</div><input id='attrs-0a784d78-f214-4afb-b7cc-742e7e7d04b5' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-0a784d78-f214-4afb-b7cc-742e7e7d04b5' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-68779ada-4bd8-434a-995d-ec88ca074859' class='xr-var-data-in' type='checkbox'><label for='data-68779ada-4bd8-434a-995d-ec88ca074859' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>Array([[2.193212 , 2.3223338, 2.4557893, 2.1263068, 2.5347822, 2.3628328,2.585216 , 2.4896088, 2.4593484, 2.4522562, 2.653245 , 2.4607575,2.5354073, 2.5288885, 2.1660855, 2.3720837, 2.3492672, 2.4883049,2.412933 , 2.4143786, 2.4515655, 2.3885796, 2.3705683, 2.3037114,2.6063623, 2.4340212, 2.4369934, 2.5372481, 2.5522597, 2.3276312,2.7623525, 2.1705995, 2.4116564, 2.3445966, 2.3701253, 2.4739711,2.7098598, 2.8039849, 2.54195  , 2.7317383, 2.3402555, 2.3373322,2.3970368, 2.358024 , 2.4621708, 2.6371021, 2.7115352, 2.7491078,2.657533 , 2.4155176, 2.3005528, 2.3035219, 2.3313074, 2.7762668,2.7691855, 2.7620049, 2.5080202, 2.449282 , 2.572289 , 2.5294323,2.5072134, 2.4769611, 2.6351972, 2.6179752, 2.549577 , 2.5396714,2.3960524, 2.7267473, 2.4378686, 2.4535246, 2.3427734, 2.4108734,2.568988 , 2.4755347, 2.3654196, 2.4218554, 2.5762436, 2.2727122,2.4218876, 2.446512 , 2.1709456, 2.3258588, 2.267409 , 2.5442293,2.559944 , 2.2926352, 2.5557115, 2.5678766, 2.4656463, 2.4515882,2.5571318, 2.405899 , 2.408258 , 2.392525 , 2.2882621, 2.3587554,2.789832 , 2.430566 , 2.4404747, 2.3086462, 2.613297 , 2.3432071,2.5797217, 2.442743 , 1.9782766, 2.471411 , 2.6116278, 2.6585057,2.5361059, 2.829606 , 2.3828447, 2.5434346, 2.4018257, 2.4587045,2.596726 , 2.3395452, 2.5685334, 2.50679  , 2.3756518, 2.6170456,...2.4537587, 2.4241347, 2.4174852, 2.6709146, 2.681181 , 2.2501388,2.7239487, 2.4644077, 2.4978323, 2.5288048, 2.4415278, 2.5403152,2.332818 , 2.3973172, 2.5949013, 2.2546992, 2.6187756, 2.5111134,2.5470736, 2.5403495, 2.609195 , 2.5944397, 2.5160391, 2.3398032,2.4918108, 2.363462 , 2.523704 , 2.2899604, 2.600224 , 2.4730332,2.3479862, 2.4305875, 2.4590406, 2.458142 , 2.5059316, 2.1695852,2.6311011, 2.4809377, 2.3746881, 2.4595351, 2.3714538, 2.7174802,2.384775 , 2.5304391, 2.3329825, 2.8056757, 2.413707 , 2.482876 ,2.288223 , 2.4325724, 2.30845  , 2.3370287, 2.6461926, 2.6740305,2.3434563, 2.3808696, 2.411139 , 2.2115245, 2.2176645, 2.0260818,2.4707205, 2.4716005, 2.2620597, 2.4935937, 2.5783935, 2.3794756,2.508218 , 2.2663102, 2.3126652, 2.517017 , 2.3438435, 2.4197652,2.1558766, 2.5551193, 2.7100592, 2.2707567, 2.795421 , 2.3397517,2.3699565, 2.3346741, 2.4885798, 2.5673513, 2.4631174, 2.4200542,2.62266  , 2.4320939, 2.5705388, 2.5728223, 2.4538136, 2.4839234,2.6419022, 2.564102 , 2.7116797, 2.5852952, 2.613393 , 2.2120159,2.2766242, 2.236385 , 2.3663568, 2.3611667, 2.3813567, 2.61588  ,2.5922997, 2.0609207, 2.4252884, 2.0232272, 2.6006017, 2.4090652,2.7772653, 2.5291936, 2.1812282, 2.296633 , 2.622905 , 2.2304323,2.22982  , 2.648877 ]], dtype=float32)</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span>a_Intercept</span></div><div class='xr-var-dims'>(chain, draw)</div><div class='xr-var-dtype'>float32</div><div class='xr-var-preview xr-preview'>...</div><input id='attrs-f4a647bc-64f1-495c-8c20-b0b58bb2548f' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-f4a647bc-64f1-495c-8c20-b0b58bb2548f' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-9ffaa54e-a321-4bfa-8eb7-64859ff5e0c6' class='xr-var-data-in' type='checkbox'><label for='data-9ffaa54e-a321-4bfa-8eb7-64859ff5e0c6' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>Array([[1.183458 , 1.2040536, 1.2006937, 1.1913921, 1.1959715, 1.1997964,1.2661519, 1.263392 , 1.17888  , 1.1932894, 1.2279503, 1.186108 ,1.1836196, 1.1794388, 1.1569911, 1.179696 , 1.2284083, 1.1699687,1.2165946, 1.2552807, 1.1964808, 1.1697224, 1.2115755, 1.19963  ,1.2173392, 1.1607764, 1.1549779, 1.2452866, 1.1552234, 1.1692606,1.1601253, 1.1995425, 1.1710659, 1.0843108, 1.1626683, 1.1051335,1.0803998, 1.1146191, 1.0824622, 1.1701407, 1.1336317, 1.2185988,1.2211105, 1.1660733, 1.1436782, 1.0951169, 1.1229011, 1.2392523,1.265769 , 1.1099052, 1.2202942, 1.1771287, 1.1763222, 1.1604654,1.1583316, 1.1584963, 1.166282 , 1.136948 , 1.1918981, 1.2105201,1.1908375, 1.1451422, 1.1565877, 1.1594745, 1.0941237, 1.2040765,1.1485051, 1.1842045, 1.1812524, 1.1906285, 1.1786603, 1.189068 ,1.1447725, 1.1089085, 1.1738164, 1.2343901, 1.238113 , 1.2753887,1.2083268, 1.1916978, 1.1925516, 1.2290684, 1.1780115, 1.1818844,1.1331463, 1.0870241, 1.1581247, 1.1074432, 1.1709328, 1.1904678,1.2263632, 1.1653227, 1.149176 , 1.1321964, 1.2279195, 1.2548943,1.0933236, 1.1668246, 1.174719 , 1.2199731, 1.1803108, 1.2457881,1.1864722, 1.1435558, 1.1326556, 1.2230551, 1.1896636, 1.1722233,1.1661587, 1.2021544, 1.1296724, 1.2510462, 1.1685284, 1.1731735,1.1779507, 1.2159293, 1.2781588, 1.1163732, 1.1456234, 1.0729984,...1.1753073, 1.1875433, 1.188452 , 1.1749985, 1.1734955, 1.2139442,1.2014905, 1.2002336, 1.1503592, 1.1610447, 1.2727231, 1.2096087,1.1636516, 1.1928722, 1.1418312, 1.259374 , 1.2517582, 1.2040211,1.2206504, 1.2178125, 1.1610733, 1.210534 , 1.1140188, 1.1243455,1.1515229, 1.171654 , 1.1502126, 1.1596718, 1.2183942, 1.1880552,1.1978918, 1.1708779, 1.1789646, 1.1387687, 1.2297926, 1.111624 ,1.3090267, 1.1596415, 1.2302604, 1.1724211, 1.1838446, 1.2299714,1.1306881, 1.2430613, 1.1833673, 1.1513002, 1.240965 , 1.2695524,1.1875305, 1.1712849, 1.160131 , 1.150634 , 1.2034178, 1.2018727,1.1682112, 1.1597188, 1.221483 , 1.1987331, 1.2024763, 1.1283069,1.1626377, 1.2242175, 1.1756959, 1.1618196, 1.1358573, 1.1767358,1.2336782, 1.1559314, 1.2175348, 1.1879745, 1.1681037, 1.1214364,1.1392041, 1.2878597, 1.2338924, 1.2681183, 1.1829672, 1.1870852,1.2026428, 1.2151827, 1.1957386, 1.2343966, 1.3209456, 1.3025799,1.1053115, 1.1293685, 1.1712866, 1.1530279, 1.1373143, 1.1379576,1.2002264, 1.1758096, 1.3317883, 1.2050427, 1.207042 , 1.1068281,1.1596934, 1.1756935, 1.2186834, 1.1186928, 1.2440548, 1.1746683,1.1362875, 1.171357 , 1.1387507, 1.1240953, 1.2251025, 1.2199557,1.2569194, 1.2373954, 1.1198025, 1.1407133, 1.0911114, 1.1848891,1.1639472, 1.1935548]], dtype=float32)</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span>theta_1|participant_id_offset</span></div><div class='xr-var-dims'>(chain, draw, participant_id__factor_dim)</div><div class='xr-var-dtype'>float32</div><div class='xr-var-preview xr-preview'>...</div><input id='attrs-4efdf025-dd8b-4df2-9514-a42568f55223' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-4efdf025-dd8b-4df2-9514-a42568f55223' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-87315af7-b5b3-4532-9f92-8c52834c33c0' class='xr-var-data-in' type='checkbox'><label for='data-87315af7-b5b3-4532-9f92-8c52834c33c0' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>Array([[[ 0.4754104 , -1.4358158 ,  0.7795619 , ..., -0.10708248,0.6746631 , -1.1459653 ],[ 0.38092852, -0.40037432,  1.4550626 , ...,  1.7366278 ,0.52589697,  0.39737228],[ 0.08231766, -0.19930397,  0.8159057 , ..., -0.05868349,-0.15164942, -0.19802205],...,[ 0.22593786,  0.19207291,  0.63827586, ...,  0.5008482 ,-0.15787496,  0.04381843],[-1.2154436 ,  0.06687358,  0.6574379 , ...,  0.01675334,-0.19893102,  0.23606433],[-0.01110104, -0.8993817 , -0.12757988, ...,  0.2622415 ,-0.77675545, -1.1350726 ]],[[-0.2563348 ,  0.22335169,  0.6205796 , ...,  1.146115  ,0.2065309 , -0.951202  ],[ 0.47843271,  0.12928507,  0.96228284, ...,  0.8544857 ,0.10357831,  0.33973488],[ 0.26521483, -0.3868249 ,  0.70521796, ...,  0.5974816 ,-0.93004775,  0.24575068],...,[ 0.03184786, -0.33034387,  1.6312232 , ...,  1.4497384 ,1.480693  , -0.09308832],[-0.16406052, -0.3953444 ,  0.8807997 , ...,  0.77784336,0.01882057, -0.1343195 ],[-0.13736394, -0.12798563,  1.576087  , ...,  0.2363417 ,-0.21347792, -0.5017031 ]]], dtype=float32)</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span>a_1|participant_id_offset</span></div><div class='xr-var-dims'>(chain, draw, participant_id__factor_dim)</div><div class='xr-var-dtype'>float32</div><div class='xr-var-preview xr-preview'>...</div><input id='attrs-7723662d-e4f3-43e9-9d77-9670a3043d13' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-7723662d-e4f3-43e9-9d77-9670a3043d13' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-babb70fb-c009-470f-be62-744481b1bbe7' class='xr-var-data-in' type='checkbox'><label for='data-babb70fb-c009-470f-be62-744481b1bbe7' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>Array([[[ 0.15819941, -2.3593543 ,  0.09531614, ..., -1.13384   ,-0.06799541,  0.62753683],[-1.3196286 , -2.2521238 ,  0.8682874 , ..., -0.7349257 ,-0.8985796 ,  0.2659579 ],[-0.24657696, -1.261271  ,  1.1784827 , ..., -0.6304928 ,-1.199569  ,  0.6779925 ],...,[-0.8317777 , -1.3092917 ,  0.9602481 , ..., -0.47537738,-0.80838054,  2.2690141 ],[-1.4759321 , -1.2405795 ,  0.73247284, ..., -1.4480371 ,-1.065172  ,  1.3208011 ],[ 0.7824508 , -1.7511053 ,  0.51694363, ...,  0.4406337 ,-0.61357224,  0.61913055]],[[-1.2573795 , -1.8082242 ,  0.6775122 , ..., -0.4296405 ,-1.2309365 , -0.23617072],[-1.270388  , -2.0635333 ,  0.20500964, ..., -1.2986007 ,-1.890425  ,  0.5595576 ],[-0.2599089 , -1.3131006 ,  0.05990489, ..., -0.86556447,-1.5100142 ,  0.7190285 ],...,[-0.5477757 , -1.9835103 ,  0.97807115, ...,  0.01277697,0.32232127,  0.12896195],[-0.0641951 , -1.2957313 ,  0.9332218 , ...,  0.1878588 ,0.16725893,  1.1617366 ],[-0.13697055, -1.6279761 ,  1.0773816 , ..., -1.5270723 ,-1.0795125 ,  0.80651426]]], dtype=float32)</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span>t_1|participant_id_sigma</span></div><div class='xr-var-dims'>(chain, draw)</div><div class='xr-var-dtype'>float32</div><div class='xr-var-preview xr-preview'>...</div><input id='attrs-60beb7eb-3112-409b-b781-a6c1d12e70aa' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-60beb7eb-3112-409b-b781-a6c1d12e70aa' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-6b1d5d32-a44d-478b-8fad-4c1196667699' class='xr-var-data-in' type='checkbox'><label for='data-6b1d5d32-a44d-478b-8fad-4c1196667699' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>Array([[0.03596601, 0.061406  , 0.03232551, 0.05704036, 0.0538063 ,0.04015049, 0.06206642, 0.07298196, 0.03447532, 0.04101518,0.0651294 , 0.04315342, 0.03863884, 0.04308423, 0.06590069,0.05615256, 0.04978955, 0.0417234 , 0.05189463, 0.04487877,0.04884426, 0.04087523, 0.07246603, 0.09584021, 0.06563202,0.0655999 , 0.06519988, 0.05370586, 0.06297199, 0.07050086,0.04165006, 0.04998374, 0.05530325, 0.03786358, 0.04561129,0.05646497, 0.06380224, 0.05479883, 0.0389541 , 0.05086587,0.04642481, 0.06137003, 0.06323136, 0.04728256, 0.05166631,0.03796814, 0.06630591, 0.05772693, 0.03851543, 0.05034225,0.09111027, 0.04110085, 0.05752716, 0.03379855, 0.03363495,0.03168694, 0.03984224, 0.03728975, 0.03958841, 0.03806417,0.05579345, 0.08219817, 0.0805493 , 0.07629279, 0.05414701,0.05797147, 0.09513626, 0.05022252, 0.04226573, 0.06349651,0.04750232, 0.05642273, 0.04109301, 0.05196493, 0.05513271,0.04334728, 0.03943839, 0.0408367 , 0.0524368 , 0.04853034,0.05494947, 0.0280705 , 0.07680098, 0.03051772, 0.0353305 ,0.08286601, 0.09630099, 0.0495839 , 0.08849209, 0.07979347,0.05963638, 0.05443042, 0.05265136, 0.04767279, 0.04902618,0.04946322, 0.03729624, 0.04741851, 0.0588044 , 0.0533393 ,...0.07266153, 0.0594317 , 0.0516734 , 0.05471806, 0.07383894,0.06030089, 0.08472469, 0.07645403, 0.04272125, 0.05032319,0.04732476, 0.06088003, 0.04858118, 0.0499448 , 0.04881439,0.04081423, 0.04446749, 0.08253112, 0.0508521 , 0.07730588,0.09139681, 0.03994676, 0.06678585, 0.04035666, 0.04472168,0.04677707, 0.02586557, 0.04340402, 0.04097631, 0.03974358,0.04098063, 0.04278688, 0.03652378, 0.04187592, 0.05723174,0.06526116, 0.04232044, 0.05752632, 0.05669267, 0.05052977,0.04962224, 0.04784748, 0.05280365, 0.06523649, 0.05897284,0.05076862, 0.0377617 , 0.0564557 , 0.04227414, 0.05213367,0.04863873, 0.06336666, 0.05225439, 0.05135005, 0.05636199,0.03718892, 0.05788331, 0.04527847, 0.03699484, 0.07857753,0.05156613, 0.05662766, 0.05176786, 0.03919731, 0.05188935,0.06421851, 0.04258887, 0.06410792, 0.03669105, 0.03306809,0.06609763, 0.08959222, 0.09952973, 0.09007412, 0.05369266,0.05426518, 0.04209291, 0.04803862, 0.04155161, 0.0546381 ,0.04567464, 0.05625111, 0.07281146, 0.05980903, 0.05719961,0.0342018 , 0.03719479, 0.04336066, 0.05329747, 0.04914393,0.03809091, 0.06890231, 0.04281218, 0.06666446, 0.03814296,0.032604  , 0.0623916 , 0.06291953, 0.04046745, 0.0610705 ]],      dtype=float32)</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span>t_1|participant_id</span></div><div class='xr-var-dims'>(chain, draw, participant_id__factor_dim)</div><div class='xr-var-dtype'>float32</div><div class='xr-var-preview xr-preview'>...</div><input id='attrs-23d71819-8a57-4d8e-abd5-4625d2ad0cc8' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-23d71819-8a57-4d8e-abd5-4625d2ad0cc8' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-4a799f65-d122-4c30-bf39-8cb456bc2270' class='xr-var-data-in' type='checkbox'><label for='data-4a799f65-d122-4c30-bf39-8cb456bc2270' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>Array([[[-0.00584605,  0.04491457,  0.04333693, ..., -0.01261985,-0.03550696,  0.00716042],[ 0.03272514, -0.00419378, -0.01154426, ..., -0.04877542,-0.00692853,  0.04560261],[-0.00787411, -0.00532847,  0.00877631, ..., -0.04678468,0.01097523,  0.01375683],...,[ 0.04970784, -0.00418804,  0.04351979, ..., -0.04895792,0.04526064,  0.06138328],[ 0.05499478,  0.00100618,  0.04079252, ..., -0.03403135,0.00874025,  0.05014163],[-0.0118642 ,  0.0693474 ,  0.04625613, ..., -0.04190652,0.02512861,  0.07402716]],[[ 0.0606204 ,  0.03438246,  0.07775207, ..., -0.03114191,0.00510696,  0.05140721],[ 0.02494527, -0.00696783,  0.00500381, ..., -0.08582811,0.01940875,  0.02143062],[-0.00112169,  0.01986936,  0.03972216, ..., -0.02992007,0.01423353,  0.02110771],...,[ 0.02193077,  0.05160695, -0.04837476, ..., -0.04063304,-0.04308822,  0.04642129],[-0.0045243 ,  0.00373581,  0.00625452, ..., -0.05070727,-0.03498492,  0.05897436],[ 0.00516697,  0.04378028,  0.02925745, ..., -0.01250933,0.03867549,  0.03408992]]], dtype=float32)</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span>scaler_1|participant_id_offset</span></div><div class='xr-var-dims'>(chain, draw, participant_id__factor_dim)</div><div class='xr-var-dtype'>float32</div><div class='xr-var-preview xr-preview'>...</div><input id='attrs-d3135724-52b7-4c3f-81da-5fa1de5b361d' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-d3135724-52b7-4c3f-81da-5fa1de5b361d' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-5ec8468f-ed85-4917-8d86-ad42eaccffc9' class='xr-var-data-in' type='checkbox'><label for='data-5ec8468f-ed85-4917-8d86-ad42eaccffc9' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>Array([[[-0.08871312,  0.43132475, -0.07425422, ..., -1.652346  ,1.2614521 ,  1.3549087 ],[ 1.4787961 , -1.0651038 , -1.0728197 , ..., -0.66982096,0.86867714,  2.3562198 ],[-0.5155794 , -0.38523895,  0.6504303 , ..., -1.5015465 ,0.22247566,  0.7975852 ],...,[-1.0129361 , -0.14837877,  1.1217713 , ..., -0.4500605 ,-0.0147339 ,  1.1478258 ],[ 0.603351  ,  0.5427468 , -0.11060146, ..., -2.055295  ,1.856292  ,  2.5504632 ],[-0.1714746 , -0.61539805, -0.6022449 , ..., -1.155421  ,0.3957413 ,  0.5189661 ]],[[-0.8070357 , -1.477199  , -0.6278709 , ...,  0.30476457,-0.9576633 ,  1.4880719 ],[-0.68563205, -0.6960402 , -0.51437134, ..., -2.4111638 ,0.47679666,  2.0029852 ],[ 1.0821705 ,  0.46823838,  0.23721969, ..., -1.0048273 ,0.8040551 ,  0.92081773],...,[ 0.9896837 , -0.8175112 ,  0.14953586, ...,  0.13538478,0.42725742,  2.762271  ],[ 1.2521958 , -0.46290556, -0.33419698, ..., -2.3852067 ,1.6174026 ,  1.8450514 ],[-0.53847075, -0.8000197 , -0.5580076 , ..., -2.0071504 ,0.2902329 ,  2.196998  ]]], dtype=float32)</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span>rl_alpha_1|participant_id_offset</span></div><div class='xr-var-dims'>(chain, draw, rl_alpha_1|participant_id__factor_dim)</div><div class='xr-var-dtype'>float32</div><div class='xr-var-preview xr-preview'>...</div><input id='attrs-e39ef35f-5534-47ed-b220-21de1f735ef1' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-e39ef35f-5534-47ed-b220-21de1f735ef1' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-25ffab21-2922-4bc0-a857-b938f320b391' class='xr-var-data-in' type='checkbox'><label for='data-25ffab21-2922-4bc0-a857-b938f320b391' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>Array([[[-0.5489629 , -0.4514417 ,  0.02904567, ..., -0.26637346,0.32938087,  2.4793658 ],[-1.2883135 ,  1.1101422 ,  1.2248044 , ..., -0.12741683,0.6956958 ,  0.1548283 ],[ 0.94240326, -1.5399766 , -0.2781861 , ..., -1.4794365 ,-0.00355667,  1.7207593 ],...,[ 0.17792071, -0.35787594,  0.041036  , ..., -2.3195333 ,-0.15522543,  1.5723182 ],[-0.41413367, -0.09336066, -0.26956838, ...,  0.9254144 ,0.80179703,  0.34354988],[-0.16741015,  0.33130985,  1.3437668 , ..., -1.8022293 ,-0.00438707,  1.19367   ]],[[ 1.3256326 ,  0.5991911 ,  0.29688206, ..., -1.4645108 ,1.604178  ,  0.19979596],[ 0.35778934,  0.7255401 , -0.00924821, ..., -0.7660931 ,1.5936677 ,  1.730388  ],[-1.2647667 , -1.7989948 ,  0.8126507 , ..., -1.6089278 ,-0.21642822,  1.9989895 ],...,[ 0.22710957,  0.29407665,  0.7524372 , ...,  0.7952286 ,1.098571  ,  0.4366155 ],[-1.1833979 ,  0.20829864,  0.9124158 , ...,  0.84431595,-0.27432203, -0.08962236],[ 0.72072685,  0.3848258 , -0.38400993, ..., -0.22972539,-0.13404533,  1.0265492 ]]], dtype=float32)</pre></div></li></ul></div></li><li class='xr-section-item'><input id='section-8331f5fe-be10-40aa-b5e0-31578ada9284' class='xr-section-summary-in' type='checkbox' /><label for='section-8331f5fe-be10-40aa-b5e0-31578ada9284' class='xr-section-summary' title='Expand/collapse section'>Attributes: <span>(11)</span></label><div class='xr-section-inline-details'></div><div class='xr-section-details'><dl class='xr-attrs'><dt><span>created_at :</span></dt><dd>2026-07-06T16:44:41.787695+00:00</dd><dt><span>creation_library :</span></dt><dd>ArviZ</dd><dt><span>creation_library_version :</span></dt><dd>1.2.0</dd><dt><span>creation_library_language :</span></dt><dd>Python</dd><dt><span>sample_dims :</span></dt><dd>[&#x27;chain&#x27;, &#x27;draw&#x27;]</dd><dt><span>inference_library :</span></dt><dd>numpyro</dd><dt><span>inference_library_version :</span></dt><dd>0.21.0</dd><dt><span>sampling_time :</span></dt><dd>545.10303</dd><dt><span>tuning_steps :</span></dt><dd>1000</dd><dt><span>modeling_interface :</span></dt><dd>bambi</dd><dt><span>modeling_interface_version :</span></dt><dd>0.18.0</dd></dl></div></li></ul></div></div><div class='xr-group-box'><div class='xr-group-box-vline' style='height: 100%'></div><div class='xr-group-box-hline'></div><div class='xr-group-box-contents'><input id='group-1451a15e-a091-4bf4-9064-b190ba9f911f' type='checkbox' checked /><label for='group-1451a15e-a091-4bf4-9064-b190ba9f911f' title='Expand/collapse group'>/sample_stats<span>(16)</span></label><ul class='xr-sections'><li class='xr-section-item'><input id='section-1d244b01-c143-49a8-a506-e0c07d7e54d5' class='xr-section-summary-in' type='checkbox' disabled /><label for='section-1d244b01-c143-49a8-a506-e0c07d7e54d5' class='xr-section-summary'>Dimensions:</label><div class='xr-section-inline-details'><ul class='xr-dim-list'><li><span class='xr-has-index'>chain</span>: 2</li><li><span class='xr-has-index'>draw</span>: 500</li></ul></div></li><li class='xr-section-item'><input id='section-14bc6040-e9ed-46a5-b304-d4a7db91c6d7' class='xr-section-summary-in' type='checkbox' checked /><label for='section-14bc6040-e9ed-46a5-b304-d4a7db91c6d7' class='xr-section-summary' title='Expand/collapse section'>Coordinates: <span>(2)</span></label><div class='xr-section-inline-details'></div><div class='xr-section-details'><ul class='xr-var-list'><li class='xr-var-item'><div class='xr-var-name'><span class='xr-has-index'>chain</span></div><div class='xr-var-dims'>(chain)</div><div class='xr-var-dtype'>int64</div><div class='xr-var-preview xr-preview'>0 1</div><input id='attrs-6e5cece5-e32d-4e7e-b670-baa9c3783cc7' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-6e5cece5-e32d-4e7e-b670-baa9c3783cc7' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-4f4bd12f-2a16-49f0-b05f-4b19cbac63bd' class='xr-var-data-in' type='checkbox'><label for='data-4f4bd12f-2a16-49f0-b05f-4b19cbac63bd' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>array([0, 1])</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span class='xr-has-index'>draw</span></div><div class='xr-var-dims'>(draw)</div><div class='xr-var-dtype'>int64</div><div class='xr-var-preview xr-preview'>0 1 2 3 4 5 ... 495 496 497 498 499</div><input id='attrs-233cae0b-35f5-455f-9a0f-d2c743e33584' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-233cae0b-35f5-455f-9a0f-d2c743e33584' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-6dd8233e-8b36-4cae-98bf-65f265fe82d0' class='xr-var-data-in' type='checkbox'><label for='data-6dd8233e-8b36-4cae-98bf-65f265fe82d0' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>array([  0,   1,   2, ..., 497, 498, 499], shape=(500,))</pre></div></li></ul></div></li><li class='xr-section-item'><input id='section-d6d6ff10-5518-4f65-b762-3b57bb2f65b7' class='xr-section-summary-in' type='checkbox' checked /><label for='section-d6d6ff10-5518-4f65-b762-3b57bb2f65b7' class='xr-section-summary' title='Expand/collapse section'>Data variables: <span>(7)</span></label><div class='xr-section-inline-details'></div><div class='xr-section-details'><ul class='xr-var-list'><li class='xr-var-item'><div class='xr-var-name'><span>acceptance_rate</span></div><div class='xr-var-dims'>(chain, draw)</div><div class='xr-var-dtype'>float32</div><div class='xr-var-preview xr-preview'>...</div><input id='attrs-1c72d3fc-c58d-4fa1-a4f8-c05ecbac8dd2' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-1c72d3fc-c58d-4fa1-a4f8-c05ecbac8dd2' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-223d63cb-3312-4714-b396-dfaa021a2ddc' class='xr-var-data-in' type='checkbox'><label for='data-223d63cb-3312-4714-b396-dfaa021a2ddc' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>Array([[0.97169363, 0.9880628 , 0.97164434, 0.9873408 , 0.91533816,0.96845293, 0.9626552 , 0.84128755, 0.929423  , 0.92346174,0.9868916 , 0.6420186 , 0.78590107, 0.56544447, 0.98704743,1.        , 0.97221404, 0.99523383, 0.96546507, 0.89959645,0.9300526 , 0.96619076, 0.5473487 , 0.9123282 , 0.8207011 ,0.9353398 , 0.9464746 , 0.90869904, 0.9685102 , 0.9666552 ,0.9820849 , 0.9309095 , 0.98522615, 0.9551941 , 0.9616885 ,0.7406718 , 0.99569625, 0.8977984 , 0.99834394, 0.5937008 ,0.9246183 , 0.9987386 , 0.9442148 , 0.8147475 , 0.88703674,0.98979366, 0.80543447, 0.93489707, 0.37167093, 0.7460009 ,0.94094014, 0.96179056, 0.99897635, 0.9802165 , 0.16962905,0.9736167 , 0.72783476, 1.        , 0.9972822 , 0.9859711 ,0.99151343, 0.98211825, 0.41465887, 0.07547581, 0.65181786,0.695491  , 0.98109657, 0.9835666 , 0.9385243 , 0.9719815 ,0.9290828 , 0.9167524 , 0.98369247, 0.94623184, 0.9508186 ,0.945351  , 0.9998319 , 0.92138374, 0.98171437, 0.9899889 ,0.92491126, 0.93999887, 0.9450985 , 0.98274887, 0.95808136,0.93212104, 0.9091506 , 0.98837835, 0.9873375 , 0.9341547 ,0.8635536 , 0.9394247 , 0.82323855, 0.9472887 , 0.99380904,0.9483032 , 0.9985422 , 0.9932333 , 0.9654208 , 0.9778529 ,...0.9096541 , 0.87522364, 0.9990538 , 0.9586893 , 0.9975242 ,0.94914186, 0.9971848 , 0.77027756, 0.957925  , 0.8920577 ,0.9833379 , 0.9721443 , 0.9836475 , 0.9925753 , 0.90919715,0.48149034, 0.9791743 , 0.9623135 , 0.9850539 , 0.90311044,0.9370831 , 0.92997617, 0.9648312 , 0.98540753, 0.93435127,0.9267238 , 0.736499  , 0.99717253, 0.9860583 , 0.95654804,0.94021755, 0.9980951 , 0.9484232 , 0.93542784, 0.997888  ,0.9770081 , 0.9369275 , 0.999731  , 0.99122596, 0.9887167 ,0.9486631 , 0.9746928 , 0.9811768 , 0.9927758 , 0.9996024 ,0.9914495 , 0.9367987 , 0.9867442 , 0.9522088 , 0.9545539 ,0.9792646 , 0.9945778 , 0.9671377 , 0.7720476 , 0.998342  ,0.95418096, 0.979838  , 0.93127465, 0.96172816, 0.9700763 ,0.9289468 , 0.93209404, 0.9743219 , 0.9925998 , 0.8773728 ,0.9918876 , 0.70234233, 0.9152298 , 0.96861666, 0.86027634,0.6116631 , 0.28927878, 0.95834464, 0.93972284, 0.90979755,0.9649892 , 0.52240187, 0.94394225, 0.99969965, 0.98426235,0.951257  , 0.9861354 , 0.9935202 , 0.9456914 , 0.99785274,0.9883302 , 0.9921799 , 0.94356865, 0.9767599 , 0.8985039 ,0.9888224 , 0.99989945, 0.9974184 , 0.5692893 , 0.6430561 ,0.986216  , 0.8644734 , 0.991267  , 0.969837  , 0.95106584]],      dtype=float32)</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span>step_size</span></div><div class='xr-var-dims'>(chain, draw)</div><div class='xr-var-dtype'>float32</div><div class='xr-var-preview xr-preview'>...</div><input id='attrs-cd5870ec-f546-4d5d-82fd-ead9ed984ac2' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-cd5870ec-f546-4d5d-82fd-ead9ed984ac2' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-f144cd92-761a-41b5-9cab-41c01febfe60' class='xr-var-data-in' type='checkbox'><label for='data-f144cd92-761a-41b5-9cab-41c01febfe60' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>Array([[0.07706155, 0.07706155, 0.07706155, 0.07706155, 0.07706155,0.07706155, 0.07706155, 0.07706155, 0.07706155, 0.07706155,0.07706155, 0.07706155, 0.07706155, 0.07706155, 0.07706155,0.07706155, 0.07706155, 0.07706155, 0.07706155, 0.07706155,0.07706155, 0.07706155, 0.07706155, 0.07706155, 0.07706155,0.07706155, 0.07706155, 0.07706155, 0.07706155, 0.07706155,0.07706155, 0.07706155, 0.07706155, 0.07706155, 0.07706155,0.07706155, 0.07706155, 0.07706155, 0.07706155, 0.07706155,0.07706155, 0.07706155, 0.07706155, 0.07706155, 0.07706155,0.07706155, 0.07706155, 0.07706155, 0.07706155, 0.07706155,0.07706155, 0.07706155, 0.07706155, 0.07706155, 0.07706155,0.07706155, 0.07706155, 0.07706155, 0.07706155, 0.07706155,0.07706155, 0.07706155, 0.07706155, 0.07706155, 0.07706155,0.07706155, 0.07706155, 0.07706155, 0.07706155, 0.07706155,0.07706155, 0.07706155, 0.07706155, 0.07706155, 0.07706155,0.07706155, 0.07706155, 0.07706155, 0.07706155, 0.07706155,0.07706155, 0.07706155, 0.07706155, 0.07706155, 0.07706155,0.07706155, 0.07706155, 0.07706155, 0.07706155, 0.07706155,0.07706155, 0.07706155, 0.07706155, 0.07706155, 0.07706155,0.07706155, 0.07706155, 0.07706155, 0.07706155, 0.07706155,...0.07169146, 0.07169146, 0.07169146, 0.07169146, 0.07169146,0.07169146, 0.07169146, 0.07169146, 0.07169146, 0.07169146,0.07169146, 0.07169146, 0.07169146, 0.07169146, 0.07169146,0.07169146, 0.07169146, 0.07169146, 0.07169146, 0.07169146,0.07169146, 0.07169146, 0.07169146, 0.07169146, 0.07169146,0.07169146, 0.07169146, 0.07169146, 0.07169146, 0.07169146,0.07169146, 0.07169146, 0.07169146, 0.07169146, 0.07169146,0.07169146, 0.07169146, 0.07169146, 0.07169146, 0.07169146,0.07169146, 0.07169146, 0.07169146, 0.07169146, 0.07169146,0.07169146, 0.07169146, 0.07169146, 0.07169146, 0.07169146,0.07169146, 0.07169146, 0.07169146, 0.07169146, 0.07169146,0.07169146, 0.07169146, 0.07169146, 0.07169146, 0.07169146,0.07169146, 0.07169146, 0.07169146, 0.07169146, 0.07169146,0.07169146, 0.07169146, 0.07169146, 0.07169146, 0.07169146,0.07169146, 0.07169146, 0.07169146, 0.07169146, 0.07169146,0.07169146, 0.07169146, 0.07169146, 0.07169146, 0.07169146,0.07169146, 0.07169146, 0.07169146, 0.07169146, 0.07169146,0.07169146, 0.07169146, 0.07169146, 0.07169146, 0.07169146,0.07169146, 0.07169146, 0.07169146, 0.07169146, 0.07169146,0.07169146, 0.07169146, 0.07169146, 0.07169146, 0.07169146]],      dtype=float32)</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span>diverging</span></div><div class='xr-var-dims'>(chain, draw)</div><div class='xr-var-dtype'>bool</div><div class='xr-var-preview xr-preview'>...</div><input id='attrs-a295f748-bc7d-4a16-959b-20c637cc6325' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-a295f748-bc7d-4a16-959b-20c637cc6325' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-d06e097f-4923-4dcd-8104-7d4b24ad81ff' class='xr-var-data-in' type='checkbox'><label for='data-d06e097f-4923-4dcd-8104-7d4b24ad81ff' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>Array([[False, False, False, False, False, False, False, False, False,False, False, False,  True, False, False, False, False, False,False, False, False, False, False, False, False, False, False,False, False, False, False, False, False, False, False, False,False, False, False, False, False, False, False, False, False,False, False, False, False, False, False, False, False, False,False, False, False, False, False, False, False, False, False,False, False, False, False, False, False, False, False, False,False, False, False, False, False, False, False, False, False,False, False, False, False, False, False, False, False, False,False, False, False, False, False, False, False, False, False,False, False, False, False, False, False, False, False, False,False, False, False, False, False, False, False, False, False,False, False, False, False, False, False, False, False, False,False, False, False, False, False, False, False, False, False,False, False, False,  True, False, False, False, False, False,False, False, False, False, False, False, False, False,  True,True, False, False, False, False, False, False, False, False,False, False, False, False, False, False, False, False, False,False,  True, False, False, False, False,  True, False, False,...False, False, False, False, False, False, False, False, False,False, False, False, False, False, False, False, False, False,False, False, False, False, False, False, False, False, False,False, False, False, False, False, False, False, False, False,False, False, False, False, False, False, False, False, False,False, False, False, False, False, False, False, False, False,False, False, False, False, False,  True, False, False, False,False, False, False, False, False, False, False, False, False,False, False, False, False, False, False, False, False, False,False, False, False, False, False, False, False, False, False,False, False, False, False, False, False, False, False, False,False, False, False, False, False, False, False, False, False,False, False, False, False, False, False, False, False, False,False, False, False, False, False, False, False, False, False,False, False, False, False, False, False, False, False, False,False, False, False, False, False, False, False, False, False,False, False, False, False, False, False, False, False, False,False, False, False, False, False, False, False, False, False,False, False, False, False, False, False, False, False, False,False, False, False, False, False]], dtype=bool)</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span>energy</span></div><div class='xr-var-dims'>(chain, draw)</div><div class='xr-var-dtype'>float32</div><div class='xr-var-preview xr-preview'>...</div><input id='attrs-2677c144-5044-463d-9c31-5edf24d19011' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-2677c144-5044-463d-9c31-5edf24d19011' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-1fc8ec7a-e619-4bc9-a0b5-c427e4539949' class='xr-var-data-in' type='checkbox'><label for='data-1fc8ec7a-e619-4bc9-a0b5-c427e4539949' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>Array([[2000.1201, 2008.9381, 1991.6708, 1979.9502, 1982.7324, 1994.5337,1984.4677, 1985.9924, 1995.0413, 2006.2045, 1996.0435, 1996.673 ,2003.1986, 1992.8812, 1994.3624, 1997.9321, 2014.704 , 2013.1753,2002.8738, 2001.6792, 1997.6985, 1998.7981, 1995.7241, 1999.7083,1999.2538, 1989.6049, 1989.7085, 1986.2863, 1991.9456, 1996.3589,1989.2448, 1985.6384, 2000.0952, 2000.3923, 1996.0682, 1980.726 ,1984.2157, 1976.341 , 1976.6584, 1985.6892, 1996.7349, 1996.9833,1989.3641, 2009.8849, 2007.8591, 1987.401 , 1989.4299, 1989.5753,1985.7817, 2009.4467, 2000.5605, 2009.0647, 2005.9186, 2010.2281,2015.6267, 2007.6523, 2007.3257, 2002.8633, 1996.1766, 1998.8014,1990.8413, 1979.255 , 1982.7402, 1980.9143, 1995.2625, 2014.1671,1992.8206, 1984.9806, 1981.6715, 1993.387 , 1988.2169, 1998.8143,2016.098 , 2018.1687, 2012.5457, 2004.6321, 1993.8975, 2004.8235,2013.6799, 1995.5444, 1998.8816, 1997.1836, 1995.312 , 2016.7595,2008.2471, 2001.2026, 2001.4695, 1998.7935, 1984.7642, 1978.0483,1988.384 , 1997.7885, 2019.2285, 2021.4402, 2015.3296, 2010.5247,2006.982 , 2016.1663, 2015.2845, 2008.8646, 2007.4055, 2011.5314,2023.4004, 2012.0573, 1999.2704, 1997.1251, 1988.1489, 2009.8112,2000.0894, 2009.9333, 2002.1974, 1993.602 , 1990.9814, 1996.0059,1986.8365, 1969.625 , 1974.3362, 1974.672 , 1971.4062, 1980.8599,...1998.4681, 1995.6593, 1995.9768, 2004.7526, 2003.7671, 2034.1945,2021.5533, 2011.4172, 2008.7725, 2008.8704, 1993.3832, 2001.3054,2001.2728, 2006.322 , 2003.628 , 1989.2168, 1995.3766, 2003.5121,2003.3501, 2004.498 , 1997.7001, 2003.0043, 2004.4985, 2003.1411,2000.3671, 1992.7561, 1993.5066, 1995.3756, 1998.7368, 1995.2668,1993.9747, 1990.3367, 1998.7848, 1996.384 , 2001.3242, 2004.6969,2007.7024, 2020.1068, 1999.8271, 1998.4836, 1994.8862, 1983.9783,2003.0559, 1998.0304, 2006.2023, 2025.3593, 2016.2717, 2002.9792,2003.127 , 2005.6697, 1990.8331, 2002.5963, 2002.0278, 2009.0454,2006.5773, 2020.2507, 2024.0498, 2016.1763, 2012.7279, 1999.7548,2010.733 , 2006.5205, 2018.5388, 1993.4911, 1983.1964, 2002.5482,2005.1333, 2002.1182, 1999.5131, 2017.7534, 2006.0867, 1999.8402,1992.5111, 1977.5326, 1995.1313, 1994.9269, 2006.7632, 2002.7848,1992.0134, 1995.2626, 2009.8235, 2002.9766, 2003.9635, 1993.975 ,1989.9164, 1993.4792, 2002.3339, 1995.4193, 1979.8629, 1994.8157,2000.2042, 1995.4048, 1993.4622, 2000.1344, 2002.4463, 1997.3129,2000.8055, 2002.0989, 1985.3743, 1992.5676, 1996.757 , 2007.0812,1995.4178, 2003.7782, 2008.5754, 2000.8224, 1994.8236, 1993.6113,1994.6339, 1993.8735, 1993.1821, 2003.8766, 2008.0428, 2002.8422,1995.7704, 1989.9429]], dtype=float32)</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span>n_steps</span></div><div class='xr-var-dims'>(chain, draw)</div><div class='xr-var-dtype'>int32</div><div class='xr-var-preview xr-preview'>...</div><input id='attrs-8704fb17-416e-4ad1-8069-a0c422afa401' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-8704fb17-416e-4ad1-8069-a0c422afa401' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-e49db5e3-4440-4bd5-9ec9-04a09a17b079' class='xr-var-data-in' type='checkbox'><label for='data-e49db5e3-4440-4bd5-9ec9-04a09a17b079' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>Array([[ 63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  33,63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,63,  63,  63,  63, 127,  63,  63,  63,  42,  63,  63,  63,  63,63,  63,  63,  63,  63,  63,  63,  63,  63,  14,  29,  63,  63,63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,63,  63,  63,  46,  63,  63,  63,  63,  48,  63,  63,  63,  63,63,  63,  63,  63,  63,  53,  63,  63,  63,  63,  63,  63,  63,63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  57,  63,63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,63,  63,  63,  63,  63,  63,  63,  63,  56,  31,  63,  63,  63,...63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,63,  63,  63,  63,  63,  63,  63,  63,  63,  63, 127,  63,  63,63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,63,  63,  63,  63,  63,  63,  63,  63,  55,  63,  63,  63,  63,63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,63,  63,  63,  63,  63,  63,  63,  63,  63, 127,  63,  63,  63,63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,63,  63,  63,  63,  63,  63,  36,  63,  63,  63,  63,  63,  63,63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,63,  63,  63, 127,  63,  63, 127,  63,  63,  63,  63,  63, 127,63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,63,  63,  63,  63,  63,  63]], dtype=int32)</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span>tree_depth</span></div><div class='xr-var-dims'>(chain, draw)</div><div class='xr-var-dtype'>int64</div><div class='xr-var-preview xr-preview'>6 6 6 6 6 6 6 6 ... 6 6 6 6 6 6 6 6</div><input id='attrs-8d1a4b4f-c231-4c87-9089-c7745034896a' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-8d1a4b4f-c231-4c87-9089-c7745034896a' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-baf190da-2369-4d1f-83aa-d7f7791bb1e9' class='xr-var-data-in' type='checkbox'><label for='data-baf190da-2369-4d1f-83aa-d7f7791bb1e9' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>array([[6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6,6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6,6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6,6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6,6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6,6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6,6, 6, 7, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 4, 5,6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6,6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6,6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6,6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6,6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 5, 6, 6, 6, 6, 6, 6, 6,6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 5, 6, 6, 2, 6, 6, 6, 6,6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6,6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 2,6, 6, 6, 6, 7, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6,6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6,6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6,6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6,6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 3, 6,...6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6,6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6,6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 7, 6, 7, 6, 6, 6, 6, 6, 6, 7, 6,6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6,6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6,6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6,6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6,6, 6, 6, 6, 6, 6, 6, 7, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6,6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6,6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 7, 6, 6,6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6,6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6,6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 7, 6, 6, 6, 6,6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6,6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6,6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 7, 6, 6, 7, 6, 6, 6, 6, 6, 7, 6, 6,6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6,6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6,6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6,6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6]])</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span>lp</span></div><div class='xr-var-dims'>(chain, draw)</div><div class='xr-var-dtype'>float32</div><div class='xr-var-preview xr-preview'>...</div><input id='attrs-02b4496a-dd56-41d8-af92-3ff1749a5e7b' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-02b4496a-dd56-41d8-af92-3ff1749a5e7b' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-41da9779-1c82-4b17-a2b5-e2f06a9c067e' class='xr-var-data-in' type='checkbox'><label for='data-41da9779-1c82-4b17-a2b5-e2f06a9c067e' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>Array([[1964.4095, 1948.3148, 1941.7513, 1934.0028, 1937.1644, 1930.9541,1932.641 , 1945.7921, 1953.3313, 1950.5594, 1945.1743, 1945.0361,1953.7217, 1951.825 , 1948.3881, 1949.1462, 1966.2217, 1951.8164,1951.9104, 1952.8829, 1946.551 , 1941.499 , 1945.9089, 1952.7385,1934.7157, 1941.1349, 1941.3654, 1937.0203, 1947.8462, 1943.2026,1937.925 , 1943.3264, 1954.8567, 1952.249 , 1941.2795, 1939.8005,1935.4092, 1934.297 , 1933.2043, 1942.8932, 1949.5048, 1942.3964,1947.7435, 1949.2378, 1945.1246, 1934.9556, 1934.3464, 1945.6146,1941.0223, 1943.8488, 1952.084 , 1954.7031, 1961.5858, 1954.4487,1954.2318, 1955.9055, 1960.6233, 1952.4982, 1949.6887, 1953.0427,1927.6989, 1939.6818, 1934.6565, 1939.7776, 1952.9052, 1952.3329,1941.3802, 1943.9385, 1941.1278, 1943.9907, 1941.5576, 1959.8483,1967.2902, 1956.2557, 1949.597 , 1948.7478, 1949.7277, 1966.023 ,1948.4059, 1951.3397, 1941.4507, 1948.4576, 1961.4414, 1971.008 ,1949.5508, 1945.1376, 1948.9148, 1939.8558, 1931.4396, 1938.6229,1947.3175, 1953.6385, 1966.0149, 1960.1417, 1956.759 , 1957.94  ,1964.5818, 1954.1478, 1963.715 , 1945.4519, 1960.9698, 1962.3295,1954.7211, 1956.431 , 1950.0563, 1942.2604, 1941.6611, 1949.8524,1952.568 , 1956.6936, 1946.4364, 1938.4451, 1945.0626, 1949.1433,1935.8982, 1924.7948, 1929.0122, 1926.9514, 1929.1702, 1938.8912,...1955.6075, 1946.6201, 1953.7701, 1952.9503, 1957.7897, 1975.5355,1956.7076, 1962.5419, 1954.0151, 1950.0134, 1946.391 , 1946.587 ,1946.9575, 1961.6006, 1941.7339, 1938.7993, 1942.7499, 1957.8021,1951.3011, 1955.3544, 1947.2863, 1955.9829, 1950.2819, 1946.5028,1941.8741, 1943.1283, 1943.9999, 1947.101 , 1948.3889, 1948.9551,1946.333 , 1948.69  , 1948.1433, 1952.1145, 1956.6344, 1952.9252,1961.0938, 1962.6243, 1953.0315, 1944.0703, 1940.8499, 1938.2295,1953.075 , 1948.6726, 1965.7073, 1967.664 , 1960.4905, 1944.6615,1954.5065, 1951.5527, 1951.1604, 1952.6173, 1961.524 , 1956.8971,1961.6323, 1964.9624, 1956.3516, 1962.6218, 1951.8044, 1956.1973,1957.6158, 1969.9862, 1956.201 , 1941.6528, 1939.8468, 1949.7965,1954.5817, 1945.9875, 1952.8431, 1962.1721, 1948.1432, 1945.9917,1938.6671, 1938.4241, 1943.1005, 1953.2786, 1953.5446, 1946.2394,1938.4893, 1952.5115, 1952.3281, 1942.2037, 1947.8806, 1940.6622,1942.6826, 1945.4612, 1946.1318, 1938.5596, 1943.5292, 1950.5172,1941.407 , 1944.1385, 1949.2346, 1946.9534, 1948.4958, 1951.2379,1955.9557, 1947.4752, 1930.7614, 1940.2855, 1948.7935, 1953.8732,1946.9984, 1949.1471, 1950.3441, 1951.2206, 1952.9559, 1942.2328,1946.4326, 1935.2657, 1957.5614, 1950.6019, 1960.5016, 1944.89  ,1944.306 , 1938.2903]], dtype=float32)</pre></div></li></ul></div></li><li class='xr-section-item'><input id='section-408943f0-624e-4efa-b2a6-7b069c4d1f82' class='xr-section-summary-in' type='checkbox' checked /><label for='section-408943f0-624e-4efa-b2a6-7b069c4d1f82' class='xr-section-summary' title='Expand/collapse section'>Attributes: <span>(7)</span></label><div class='xr-section-inline-details'></div><div class='xr-section-details'><dl class='xr-attrs'><dt><span>created_at :</span></dt><dd>2026-07-06T16:44:41.799808+00:00</dd><dt><span>creation_library :</span></dt><dd>ArviZ</dd><dt><span>creation_library_version :</span></dt><dd>1.2.0</dd><dt><span>creation_library_language :</span></dt><dd>Python</dd><dt><span>sample_dims :</span></dt><dd>[&#x27;chain&#x27;, &#x27;draw&#x27;]</dd><dt><span>modeling_interface :</span></dt><dd>bambi</dd><dt><span>modeling_interface_version :</span></dt><dd>0.18.0</dd></dl></div></li></ul></div></div><div class='xr-group-box'><div class='xr-group-box-vline' style='height: 100%'></div><div class='xr-group-box-hline'></div><div class='xr-group-box-contents'><input id='group-5b0778ff-24a2-4574-bb7c-666972b3d3b8' type='checkbox' checked /><label for='group-5b0778ff-24a2-4574-bb7c-666972b3d3b8' title='Expand/collapse group'>/observed_data<span>(10)</span></label><ul class='xr-sections'><li class='xr-section-item'><input id='section-814bd61a-c68d-4a5c-8eab-f486bed2523e' class='xr-section-summary-in' type='checkbox' disabled /><label for='section-814bd61a-c68d-4a5c-8eab-f486bed2523e' class='xr-section-summary'>Dimensions:</label><div class='xr-section-inline-details'><ul class='xr-dim-list'><li><span class='xr-has-index'>__obs__</span>: 2250</li><li><span class='xr-has-index'>rt,response_extra_dim_0</span>: 2</li></ul></div></li><li class='xr-section-item'><input id='section-48c09671-bab3-4594-872d-10cfc76a333e' class='xr-section-summary-in' type='checkbox' checked /><label for='section-48c09671-bab3-4594-872d-10cfc76a333e' class='xr-section-summary' title='Expand/collapse section'>Coordinates: <span>(2)</span></label><div class='xr-section-inline-details'></div><div class='xr-section-details'><ul class='xr-var-list'><li class='xr-var-item'><div class='xr-var-name'><span class='xr-has-index'>__obs__</span></div><div class='xr-var-dims'>(__obs__)</div><div class='xr-var-dtype'>int64</div><div class='xr-var-preview xr-preview'>0 1 2 3 4 ... 2246 2247 2248 2249</div><input id='attrs-817f9e93-2f49-457e-aa12-d1dfdd426c10' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-817f9e93-2f49-457e-aa12-d1dfdd426c10' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-3a9f46a4-f134-494d-badc-6685733ecd38' class='xr-var-data-in' type='checkbox'><label for='data-3a9f46a4-f134-494d-badc-6685733ecd38' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>array([   0,    1,    2, ..., 2247, 2248, 2249], shape=(2250,))</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span class='xr-has-index'>rt,response_extra_dim_0</span></div><div class='xr-var-dims'>(rt,response_extra_dim_0)</div><div class='xr-var-dtype'>int64</div><div class='xr-var-preview xr-preview'>0 1</div><input id='attrs-b85509b1-09ee-45fc-808f-80828c0f405c' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-b85509b1-09ee-45fc-808f-80828c0f405c' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-63b698b0-8ff7-4dd9-b149-f696fd8356de' class='xr-var-data-in' type='checkbox'><label for='data-63b698b0-8ff7-4dd9-b149-f696fd8356de' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>array([0, 1])</pre></div></li></ul></div></li><li class='xr-section-item'><input id='section-4d5c6672-cbd8-49d7-930d-b537d9d95f16' class='xr-section-summary-in' type='checkbox' checked /><label for='section-4d5c6672-cbd8-49d7-930d-b537d9d95f16' class='xr-section-summary' title='Expand/collapse section'>Data variables: <span>(1)</span></label><div class='xr-section-inline-details'></div><div class='xr-section-details'><ul class='xr-var-list'><li class='xr-var-item'><div class='xr-var-name'><span>rt,response</span></div><div class='xr-var-dims'>(__obs__, rt,response_extra_dim_0)</div><div class='xr-var-dtype'>float32</div><div class='xr-var-preview xr-preview'>1.07 -1.0 1.998 ... 1.0 0.6218 -1.0</div><input id='attrs-e9d076b8-97d5-4f30-a77b-a27ea01e6287' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-e9d076b8-97d5-4f30-a77b-a27ea01e6287' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-29f7b00e-0bb3-48de-8be1-0e010fd3f062' class='xr-var-data-in' type='checkbox'><label for='data-29f7b00e-0bb3-48de-8be1-0e010fd3f062' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>array([[ 1.0698211 , -1.        ],[ 1.9984472 , -1.        ],[ 1.5602216 , -1.        ],...,[ 1.2822655 , -1.        ],[ 1.0421401 ,  1.        ],[ 0.62177145, -1.        ]], shape=(2250, 2), dtype=float32)</pre></div></li></ul></div></li><li class='xr-section-item'><input id='section-5768384e-1c3d-4e55-9e87-ec207633461e' class='xr-section-summary-in' type='checkbox' checked /><label for='section-5768384e-1c3d-4e55-9e87-ec207633461e' class='xr-section-summary' title='Expand/collapse section'>Attributes: <span>(7)</span></label><div class='xr-section-inline-details'></div><div class='xr-section-details'><dl class='xr-attrs'><dt><span>created_at :</span></dt><dd>2026-07-06T16:44:41.800372+00:00</dd><dt><span>creation_library :</span></dt><dd>ArviZ</dd><dt><span>creation_library_version :</span></dt><dd>1.2.0</dd><dt><span>creation_library_language :</span></dt><dd>Python</dd><dt><span>sample_dims :</span></dt><dd>[]</dd><dt><span>modeling_interface :</span></dt><dd>bambi</dd><dt><span>modeling_interface_version :</span></dt><dd>0.18.0</dd></dl></div></li></ul></div></div><div class='xr-group-box'><div class='xr-group-box-vline' style='height: 100%'></div><div class='xr-group-box-hline'></div><div class='xr-group-box-contents'><input id='group-344440ea-e1df-468d-bcaf-ee117a2c93e2' type='checkbox' checked /><label for='group-344440ea-e1df-468d-bcaf-ee117a2c93e2' title='Expand/collapse group'>/constant_data<span>(7)</span></label><ul class='xr-sections'><li class='xr-section-item'><input id='section-37b7fbd2-5d48-4356-b40b-1c62cf60777f' class='xr-section-summary-in' type='checkbox' checked /><label for='section-37b7fbd2-5d48-4356-b40b-1c62cf60777f' class='xr-section-summary' title='Expand/collapse section'>Attributes: <span>(7)</span></label><div class='xr-section-inline-details'></div><div class='xr-section-details'><dl class='xr-attrs'><dt><span>created_at :</span></dt><dd>2026-07-06T16:44:41.800438+00:00</dd><dt><span>creation_library :</span></dt><dd>ArviZ</dd><dt><span>creation_library_version :</span></dt><dd>1.2.0</dd><dt><span>creation_library_language :</span></dt><dd>Python</dd><dt><span>sample_dims :</span></dt><dd>[]</dd><dt><span>modeling_interface :</span></dt><dd>bambi</dd><dt><span>modeling_interface_version :</span></dt><dd>0.18.0</dd></dl></div></li></ul></div></div><div class='xr-group-box'><div class='xr-group-box-vline' style='height: 1.2em'></div><div class='xr-group-box-hline'></div><div class='xr-group-box-contents'><input id='group-3572dbaa-d1ad-4803-a8e5-d87cb59628a6' type='checkbox' checked /><label for='group-3572dbaa-d1ad-4803-a8e5-d87cb59628a6' title='Expand/collapse group'>/log_likelihood<span>(6)</span></label><ul class='xr-sections'><li class='xr-section-item'><input id='section-95876814-a2b3-4435-a90a-a604f19df30b' class='xr-section-summary-in' type='checkbox' disabled /><label for='section-95876814-a2b3-4435-a90a-a604f19df30b' class='xr-section-summary'>Dimensions:</label><div class='xr-section-inline-details'><ul class='xr-dim-list'><li><span class='xr-has-index'>chain</span>: 2</li><li><span class='xr-has-index'>draw</span>: 500</li><li><span class='xr-has-index'>__obs__</span>: 2250</li></ul></div></li><li class='xr-section-item'><input id='section-0c43cef9-0ccc-4e9a-ba84-ae69e26f1261' class='xr-section-summary-in' type='checkbox' checked /><label for='section-0c43cef9-0ccc-4e9a-ba84-ae69e26f1261' class='xr-section-summary' title='Expand/collapse section'>Coordinates: <span>(3)</span></label><div class='xr-section-inline-details'></div><div class='xr-section-details'><ul class='xr-var-list'><li class='xr-var-item'><div class='xr-var-name'><span class='xr-has-index'>chain</span></div><div class='xr-var-dims'>(chain)</div><div class='xr-var-dtype'>int64</div><div class='xr-var-preview xr-preview'>0 1</div><input id='attrs-8478a7a9-7ca1-484f-98bd-eb61c5f2a66d' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-8478a7a9-7ca1-484f-98bd-eb61c5f2a66d' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-a107d9e6-fb82-4079-931f-222542e8b809' class='xr-var-data-in' type='checkbox'><label for='data-a107d9e6-fb82-4079-931f-222542e8b809' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>array([0, 1])</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span class='xr-has-index'>draw</span></div><div class='xr-var-dims'>(draw)</div><div class='xr-var-dtype'>int64</div><div class='xr-var-preview xr-preview'>0 1 2 3 4 5 ... 495 496 497 498 499</div><input id='attrs-adfed8b3-8bbf-4a82-9e7f-3327d7a970e4' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-adfed8b3-8bbf-4a82-9e7f-3327d7a970e4' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-3b03a1ca-9180-438b-b29f-82ec2d31b28b' class='xr-var-data-in' type='checkbox'><label for='data-3b03a1ca-9180-438b-b29f-82ec2d31b28b' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>array([  0,   1,   2, ..., 497, 498, 499], shape=(500,))</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span class='xr-has-index'>__obs__</span></div><div class='xr-var-dims'>(__obs__)</div><div class='xr-var-dtype'>int64</div><div class='xr-var-preview xr-preview'>0 1 2 3 4 ... 2246 2247 2248 2249</div><input id='attrs-4b69ef19-2eb3-41df-9f5f-6536654a0428' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-4b69ef19-2eb3-41df-9f5f-6536654a0428' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-31c05bb0-71a5-409b-82c3-7ebf4f2c61b0' class='xr-var-data-in' type='checkbox'><label for='data-31c05bb0-71a5-409b-82c3-7ebf4f2c61b0' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>array([   0,    1,    2, ..., 2247, 2248, 2249], shape=(2250,))</pre></div></li></ul></div></li><li class='xr-section-item'><input id='section-834a8363-377a-4847-9ab7-b0797d958d85' class='xr-section-summary-in' type='checkbox' checked /><label for='section-834a8363-377a-4847-9ab7-b0797d958d85' class='xr-section-summary' title='Expand/collapse section'>Data variables: <span>(1)</span></label><div class='xr-section-inline-details'></div><div class='xr-section-details'><ul class='xr-var-list'><li class='xr-var-item'><div class='xr-var-name'><span>rt,response</span></div><div class='xr-var-dims'>(chain, draw, __obs__)</div><div class='xr-var-dtype'>float64</div><div class='xr-var-preview xr-preview'>-0.9003 -2.705 ... -3.817 0.4514</div><input id='attrs-9e7381fd-09d3-4d2c-9a3d-d8078a2a28c4' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-9e7381fd-09d3-4d2c-9a3d-d8078a2a28c4' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-f74b28c5-e416-443f-afea-dae808507af0' class='xr-var-data-in' type='checkbox'><label for='data-f74b28c5-e416-443f-afea-dae808507af0' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>array([[[-0.9002651 , -2.70510006, -1.50032175, ..., -0.80871707,-3.53477788,  0.35698664],[-0.87976915, -2.99639964, -1.64367843, ..., -0.9917987 ,-3.60017061,  0.56391585],[-0.89330721, -3.00440907, -1.55672777, ..., -0.74742687,-2.99656725,  0.28471351],...,[-0.85784686, -3.12925029, -1.66228151, ..., -0.8490932 ,-3.55797029,  0.47211468],[-0.96338546, -2.608428  , -1.61300755, ..., -0.77893794,-3.78648973,  0.41193628],[-0.87420624, -3.0878253 , -1.5030005 , ..., -0.74170887,-3.16661811,  0.33100969]],[[-0.93991661, -2.64462161, -1.55485284, ..., -0.98575687,-3.70487523,  0.49665511],[-0.84236854, -3.22509384, -1.63678801, ..., -0.75963193,-3.66907811,  0.43347764],[-0.90852672, -2.73295927, -1.50674868, ..., -0.89023221,-3.70897794,  0.46702492],...,[-0.92299128, -2.55246878, -1.49743736, ..., -0.89620638,-3.3245585 ,  0.46194756],[-0.92174673, -2.72164321, -1.50951588, ..., -0.7725507 ,-3.41744447,  0.41824543],[-0.9264878 , -2.47148395, -1.46148992, ..., -0.82131016,-3.81700754,  0.45137346]]], shape=(2, 500, 2250))</pre></div></li></ul></div></li><li class='xr-section-item'><input id='section-bcbc928f-8125-4c08-ab9e-7767a0b86cee' class='xr-section-summary-in' type='checkbox' checked /><label for='section-bcbc928f-8125-4c08-ab9e-7767a0b86cee' class='xr-section-summary' title='Expand/collapse section'>Attributes: <span>(2)</span></label><div class='xr-section-inline-details'></div><div class='xr-section-details'><dl class='xr-attrs'><dt><span>modeling_interface :</span></dt><dd>bambi</dd><dt><span>modeling_interface_version :</span></dt><dd>0.18.0</dd></dl></div></li></ul></div></div></div></li></ul></div></div>"
+      ],
+      "text/plain": [
+       "<xarray.DataTree>\n",
+       "Group: /\n",
+       "├── Group: /posterior\n",
+       "│       Dimensions:                                (chain: 2, draw: 500,\n",
+       "│                                                   participant_id__factor_dim: 15,\n",
+       "│                                                   rl_alpha_1|participant_id__factor_dim: 15)\n",
+       "│       Coordinates:\n",
+       "│         * chain                                  (chain) int64 16B 0 1\n",
+       "│         * draw                                   (draw) int64 4kB 0 1 2 ... 498 499\n",
+       "│         * participant_id__factor_dim             (participant_id__factor_dim) <U2 120B ...\n",
+       "│         * rl_alpha_1|participant_id__factor_dim  (rl_alpha_1|participant_id__factor_dim) <U2 120B ...\n",
+       "│       Data variables: (12/24)\n",
+       "│           t_1|participant_id_offset              (chain, draw, participant_id__factor_dim) float32 60kB ...\n",
+       "│           z_1|participant_id                     (chain, draw, participant_id__factor_dim) float32 60kB ...\n",
+       "│           z_1|participant_id_sigma               (chain, draw) float32 4kB ...\n",
+       "│           theta_1|participant_id                 (chain, draw, participant_id__factor_dim) float32 60kB ...\n",
+       "│           rl_alpha_Intercept                     (chain, draw) float32 4kB ...\n",
+       "│           t_Intercept                            (chain, draw) float32 4kB ...\n",
+       "│           ...                                     ...\n",
+       "│           theta_1|participant_id_offset          (chain, draw, participant_id__factor_dim) float32 60kB ...\n",
+       "│           a_1|participant_id_offset              (chain, draw, participant_id__factor_dim) float32 60kB ...\n",
+       "│           t_1|participant_id_sigma               (chain, draw) float32 4kB ...\n",
+       "│           t_1|participant_id                     (chain, draw, participant_id__factor_dim) float32 60kB ...\n",
+       "│           scaler_1|participant_id_offset         (chain, draw, participant_id__factor_dim) float32 60kB ...\n",
+       "│           rl_alpha_1|participant_id_offset       (chain, draw, rl_alpha_1|participant_id__factor_dim) float32 60kB ...\n",
+       "│       Attributes:\n",
+       "│           created_at:                  2026-07-06T16:44:41.787695+00:00\n",
+       "│           creation_library:            ArviZ\n",
+       "│           creation_library_version:    1.2.0\n",
+       "│           creation_library_language:   Python\n",
+       "│           sample_dims:                 ['chain', 'draw']\n",
+       "│           inference_library:           numpyro\n",
+       "│           inference_library_version:   0.21.0\n",
+       "│           sampling_time:               545.10303\n",
+       "│           tuning_steps:                1000\n",
+       "│           modeling_interface:          bambi\n",
+       "│           modeling_interface_version:  0.18.0\n",
+       "├── Group: /sample_stats\n",
+       "│       Dimensions:          (chain: 2, draw: 500)\n",
+       "│       Coordinates:\n",
+       "│         * chain            (chain) int64 16B 0 1\n",
+       "│         * draw             (draw) int64 4kB 0 1 2 3 4 5 6 ... 494 495 496 497 498 499\n",
+       "│       Data variables:\n",
+       "│           acceptance_rate  (chain, draw) float32 4kB ...\n",
+       "│           step_size        (chain, draw) float32 4kB ...\n",
+       "│           diverging        (chain, draw) bool 1kB ...\n",
+       "│           energy           (chain, draw) float32 4kB ...\n",
+       "│           n_steps          (chain, draw) int32 4kB ...\n",
+       "│           tree_depth       (chain, draw) int64 8kB 6 6 6 6 6 6 6 6 ... 6 6 6 6 6 6 6 6\n",
+       "│           lp               (chain, draw) float32 4kB ...\n",
+       "│       Attributes:\n",
+       "│           created_at:                  2026-07-06T16:44:41.799808+00:00\n",
+       "│           creation_library:            ArviZ\n",
+       "│           creation_library_version:    1.2.0\n",
+       "│           creation_library_language:   Python\n",
+       "│           sample_dims:                 ['chain', 'draw']\n",
+       "│           modeling_interface:          bambi\n",
+       "│           modeling_interface_version:  0.18.0\n",
+       "├── Group: /observed_data\n",
+       "│       Dimensions:                  (__obs__: 2250, rt,response_extra_dim_0: 2)\n",
+       "│       Coordinates:\n",
+       "│         * __obs__                  (__obs__) int64 18kB 0 1 2 3 ... 2247 2248 2249\n",
+       "│         * rt,response_extra_dim_0  (rt,response_extra_dim_0) int64 16B 0 1\n",
+       "│       Data variables:\n",
+       "│           rt,response              (__obs__, rt,response_extra_dim_0) float32 18kB ...\n",
+       "│       Attributes:\n",
+       "│           created_at:                  2026-07-06T16:44:41.800372+00:00\n",
+       "│           creation_library:            ArviZ\n",
+       "│           creation_library_version:    1.2.0\n",
+       "│           creation_library_language:   Python\n",
+       "│           sample_dims:                 []\n",
+       "│           modeling_interface:          bambi\n",
+       "│           modeling_interface_version:  0.18.0\n",
+       "├── Group: /constant_data\n",
+       "│       Attributes:\n",
+       "│           created_at:                  2026-07-06T16:44:41.800438+00:00\n",
+       "│           creation_library:            ArviZ\n",
+       "│           creation_library_version:    1.2.0\n",
+       "│           creation_library_language:   Python\n",
+       "│           sample_dims:                 []\n",
+       "│           modeling_interface:          bambi\n",
+       "│           modeling_interface_version:  0.18.0\n",
+       "└── Group: /log_likelihood\n",
+       "        Dimensions:      (chain: 2, draw: 500, __obs__: 2250)\n",
+       "        Coordinates:\n",
+       "          * chain        (chain) int64 16B 0 1\n",
+       "          * draw         (draw) int64 4kB 0 1 2 3 4 5 6 ... 493 494 495 496 497 498 499\n",
+       "          * __obs__      (__obs__) int64 18kB 0 1 2 3 4 5 ... 2245 2246 2247 2248 2249\n",
+       "        Data variables:\n",
+       "            rt,response  (chain, draw, __obs__) float64 18MB -0.9003 -2.705 ... 0.4514\n",
+       "        Attributes:\n",
+       "            modeling_interface:          bambi\n",
+       "            modeling_interface_version:  0.18.0"
+      ]
+     },
+     "execution_count": 12,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
    "source": [
     "idata = model.sample(\n",
     "    sampler=\"numpyro\",\n",
@@ -483,18 +16422,27 @@
    "id": "ad91ad20",
    "metadata": {},
    "source": [
-    "## 8. A quick recovery check\n",
-    "Having fit the model we now ask: did it recover the group-level\n",
-    "values we simulated from? We start with that group-level check here. Participant-by-\n",
-    "participant recovery is useful too, but it is easier to read once the basic workflow\n",
-    "feels familiar.\n"
+    "## 9. Parameter recovery\n",
+    "\n",
+    "The real test: does the fitted model recover the parameters we simulated from? We\n",
+    "check at two levels — the **group means** and the **individual participants**. The\n",
+    "two helpers below do the plotting; the logic they rely on is simple because HSSM used\n",
+    "an *identity* link for every parameter here, so a participant's estimate is just\n",
+    "`Intercept + (their deviation)` on the natural scale."
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 13,
    "id": "ae08ea78",
-   "metadata": {},
+   "metadata": {
+    "execution": {
+     "iopub.execute_input": "2026-07-06T16:44:43.619346Z",
+     "iopub.status.busy": "2026-07-06T16:44:43.619245Z",
+     "iopub.status.idle": "2026-07-06T16:44:43.622969Z",
+     "shell.execute_reply": "2026-07-06T16:44:43.622649Z"
+    }
+   },
    "outputs": [],
    "source": [
     "def group_recovery(idata, true_group):\n",
@@ -531,7 +16479,42 @@
     "    ax.legend()\n",
     "    fig.tight_layout()\n",
     "    plt.show()\n",
-    "    return summ"
+    "    return summ\n",
+    "\n",
+    "\n",
+    "def participant_recovery(idata, true_params):\n",
+    "    \"\"\"Per-participant true vs. posterior-mean estimate, one panel per parameter.\"\"\"\n",
+    "    post = idata.posterior\n",
+    "    fig, axes = plt.subplots(2, 3, figsize=(12, 7), constrained_layout=True)\n",
+    "    for ax, name in zip(axes.ravel(), LIST_PARAMS):\n",
+    "        re = post[f\"{name}_1|participant_id\"]\n",
+    "        pid_dim = [d for d in re.dims if d not in (\"chain\", \"draw\")][0]\n",
+    "        draws = post[f\"{name}_Intercept\"] + re  # identity link -> natural scale\n",
+    "        rec_mean = draws.mean((\"chain\", \"draw\")).values\n",
+    "        lo = draws.quantile(0.03, (\"chain\", \"draw\")).values\n",
+    "        hi = draws.quantile(0.97, (\"chain\", \"draw\")).values\n",
+    "        ids = [int(v) for v in re[pid_dim].values]\n",
+    "        true_v = true_params.loc[ids, name].values\n",
+    "\n",
+    "        ax.errorbar(\n",
+    "            true_v,\n",
+    "            rec_mean,\n",
+    "            yerr=[rec_mean - lo, hi - rec_mean],\n",
+    "            fmt=\"o\",\n",
+    "            ecolor=\"0.7\",\n",
+    "            capsize=3,\n",
+    "        )\n",
+    "        lohi = [\n",
+    "            min(true_v.min(), rec_mean.min()) - 0.03,\n",
+    "            max(true_v.max(), rec_mean.max()) + 0.03,\n",
+    "        ]\n",
+    "        ax.plot(lohi, lohi, \"k--\", lw=1)\n",
+    "        ax.set_title(name)\n",
+    "        ax.set_xlabel(\"true\")\n",
+    "        ax.set_ylabel(\"recovered\")\n",
+    "        ax.grid(alpha=0.3)\n",
+    "    fig.suptitle(\"Participant-level recovery (points on the dashed line = perfect)\")\n",
+    "    plt.show()"
    ]
   },
   {
@@ -539,171 +16522,354 @@
    "id": "f028a492",
    "metadata": {},
    "source": [
-    "### Group-level recovery\n",
-    "Each posterior interval (blue) should sit reasonably close to the corresponding true\n",
-    "group mean (red diamond).\n"
+    "### 9.1 Group-level recovery\n",
+    "\n",
+    "Each posterior interval (blue) should sit close to the corresponding true group mean\n",
+    "(red diamond)."
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 14,
    "id": "89a41288",
-   "metadata": {},
-   "outputs": [],
+   "metadata": {
+    "execution": {
+     "iopub.execute_input": "2026-07-06T16:44:43.624148Z",
+     "iopub.status.busy": "2026-07-06T16:44:43.624086Z",
+     "iopub.status.idle": "2026-07-06T16:44:43.751873Z",
+     "shell.execute_reply": "2026-07-06T16:44:43.751473Z"
+    }
+   },
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 800x450 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>mean</th>\n",
+       "      <th>hdi94_lb</th>\n",
+       "      <th>hdi94_ub</th>\n",
+       "      <th>true</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>rl_alpha</th>\n",
+       "      <td>0.088</td>\n",
+       "      <td>0.064</td>\n",
+       "      <td>0.115</td>\n",
+       "      <td>0.08</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>scaler</th>\n",
+       "      <td>2.447</td>\n",
+       "      <td>2.125</td>\n",
+       "      <td>2.779</td>\n",
+       "      <td>2.50</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>a</th>\n",
+       "      <td>1.190</td>\n",
+       "      <td>1.091</td>\n",
+       "      <td>1.288</td>\n",
+       "      <td>1.20</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>z</th>\n",
+       "      <td>0.515</td>\n",
+       "      <td>0.483</td>\n",
+       "      <td>0.546</td>\n",
+       "      <td>0.50</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>t</th>\n",
+       "      <td>0.244</td>\n",
+       "      <td>0.210</td>\n",
+       "      <td>0.273</td>\n",
+       "      <td>0.25</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>theta</th>\n",
+       "      <td>0.346</td>\n",
+       "      <td>0.274</td>\n",
+       "      <td>0.424</td>\n",
+       "      <td>0.35</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "           mean  hdi94_lb  hdi94_ub  true\n",
+       "rl_alpha  0.088     0.064     0.115  0.08\n",
+       "scaler    2.447     2.125     2.779  2.50\n",
+       "a         1.190     1.091     1.288  1.20\n",
+       "z         0.515     0.483     0.546  0.50\n",
+       "t         0.244     0.210     0.273  0.25\n",
+       "theta     0.346     0.274     0.424  0.35"
+      ]
+     },
+     "execution_count": 14,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
    "source": [
     "group_summary = group_recovery(idata, GROUP_THETA)\n",
     "group_summary[[\"mean\", \"hdi94_lb\", \"hdi94_ub\", \"true\"]].round(3)"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "7fd6bd7d",
+   "metadata": {},
+   "source": [
+    "### 9.2 Participant-level recovery\n",
+    "\n",
+    "The stronger test: for each parameter, do the **individual** estimates track the\n",
+    "individual true values? Points hugging the dashed identity line indicate good\n",
+    "recovery. The decision parameters `a` and `z` are typically recovered most sharply\n",
+    "from choice+RT data; the learning parameters are harder and their points scatter more\n",
+    "— an honest reflection of how much a bandit task constrains them."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "id": "db75f20e",
+   "metadata": {
+    "execution": {
+     "iopub.execute_input": "2026-07-06T16:44:43.758119Z",
+     "iopub.status.busy": "2026-07-06T16:44:43.758037Z",
+     "iopub.status.idle": "2026-07-06T16:44:44.074731Z",
+     "shell.execute_reply": "2026-07-06T16:44:44.074271Z"
+    }
+   },
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 1200x700 with 6 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "participant_recovery(idata, true_params)"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "055a0d0e",
    "metadata": {},
    "source": [
-    "## 9. Posterior predictive check (RLSSM-aware)\n",
+    "## 10. Posterior predictive check (RLSSM-aware)\n",
+    "\n",
     "A posterior predictive check (PPC) asks: *if we simulate new data from the fitted\n",
-    "parameters, does it look like the data we observed?* For an RLSSM there is one extra\n",
-    "wrinkle: the predicted behavior depends on the learning trajectory. The helper below\n",
-    "handles that bookkeeping by replaying each participant's observed reward history\n",
-    "during PPC simulation, then comparing the predicted learning curve and RT distribution\n",
-    "with the observed data.\n"
+    "parameters, does it look like the data we observed?* For an RLSSM there is a subtlety.\n",
+    "Generic posterior predictive sampling would ignore the reward history and let the\n",
+    "learner wander freely, producing learning trajectories unlike the participant's. The\n",
+    "`ssms.rl` simulator therefore offers **`mode=\"ppc\"`**, which **re-simulates each trial\n",
+    "while conditioning the learning trajectory on the participant's *observed* responses\n",
+    "and feedback.** In other words, it replays the real sequence of outcomes to keep the\n",
+    "Q-values on the same path the participant actually experienced, and only the SSM\n",
+    "choice/RT for each trial are freshly simulated from posterior parameters. This\n",
+    "isolates *decision* fit from extra bandit randomness.\n",
+    "\n",
+    "We draw several parameter sets from the posterior, run `mode=\"ppc\"` for each, and\n",
+    "compare the predicted learning curve and RT distribution to the observed data."
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 16,
    "id": "433a3627",
-   "metadata": {},
-   "outputs": [],
+   "metadata": {
+    "execution": {
+     "iopub.execute_input": "2026-07-06T16:44:44.075971Z",
+     "iopub.status.busy": "2026-07-06T16:44:44.075886Z",
+     "iopub.status.idle": "2026-07-06T16:45:07.941670Z",
+     "shell.execute_reply": "2026-07-06T16:45:07.941260Z"
+    }
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "PPC datasets: 20 | total rows: 45000\n"
+     ]
+    }
+   ],
    "source": [
-    "def plot_rl_ppc(idata, observed_data, ssms_config, *, n_participants, random_seed):\n",
-    "    \"\"\"Simulate an RL-aware PPC and plot the main checks.\"\"\"\n",
-    "\n",
-    "    def draw_posterior_theta(draw_idx):\n",
-    "        posterior = idata.posterior\n",
-    "        if hasattr(posterior, \"to_dataset\"):\n",
-    "            posterior = posterior.to_dataset()  # PyMC 6 returns a DataTree node\n",
-    "        post = posterior.stack(sample=(\"chain\", \"draw\"))\n",
-    "        theta = {}\n",
-    "        for name in LIST_PARAMS:\n",
-    "            re = post[f\"{name}_1|participant_id\"]\n",
-    "            pid_dim = [d for d in re.dims if d not in (\"sample\",)][0]\n",
-    "            vals = (post[f\"{name}_Intercept\"] + re).isel(sample=draw_idx)\n",
-    "            ids = [int(v) for v in re[pid_dim].values]\n",
-    "            series = pd.Series(np.asarray(vals.values), index=ids).sort_index()\n",
-    "            theta[name] = series.reindex(range(n_participants)).to_numpy()\n",
-    "        return theta\n",
-    "\n",
-    "    def learning_curve(df, bin_size=10):\n",
-    "        d = df[df[\"rt\"] > -900].copy()\n",
-    "        d[\"chose_high\"] = (d[\"response\"] == -1).astype(float)\n",
-    "        d[\"trial_bin\"] = (d[\"trial_id\"] // bin_size) * bin_size\n",
-    "        return d.groupby(\"trial_bin\")[\"chose_high\"].mean()\n",
-    "\n",
-    "    def signed_rt(df):\n",
-    "        d = df[df[\"rt\"] > -900].copy()\n",
-    "        return np.where(\n",
-    "            d[\"response\"].astype(int) == -1,\n",
-    "            -d[\"rt\"].astype(float),\n",
-    "            d[\"rt\"].astype(float),\n",
-    "        )\n",
+    "def draw_posterior_theta(idata, draw_idx):\n",
+    "    \"\"\"Return a single posterior draw of per-participant parameters (natural scale).\"\"\"\n",
+    "    posterior = idata.posterior\n",
+    "    if hasattr(posterior, \"to_dataset\"):\n",
+    "        posterior = posterior.to_dataset()  # PyMC 6 returns a DataTree node\n",
+    "    post = posterior.stack(sample=(\"chain\", \"draw\"))\n",
+    "    theta = {}\n",
+    "    for name in LIST_PARAMS:\n",
+    "        re = post[f\"{name}_1|participant_id\"]\n",
+    "        pid_dim = [d for d in re.dims if d not in (\"sample\",)][0]\n",
+    "        vals = (post[f\"{name}_Intercept\"] + re).isel(sample=draw_idx)\n",
+    "        ids = [int(v) for v in re[pid_dim].values]\n",
+    "        s = pd.Series(np.asarray(vals.values), index=ids).sort_index()\n",
+    "        theta[name] = s.reindex(range(N_PARTICIPANTS)).to_numpy()\n",
+    "    return theta\n",
     "\n",
-    "    n_ppc_draws = 8\n",
-    "    n_samples = idata.posterior.sizes[\"chain\"] * idata.posterior.sizes[\"draw\"]\n",
-    "    ppc_rng = np.random.default_rng(random_seed + 1)\n",
-    "    draw_ids = ppc_rng.choice(\n",
-    "        n_samples, size=min(n_ppc_draws, n_samples), replace=False\n",
-    "    )\n",
-    "    ppc_frames = []\n",
-    "    for offset, draw_id in enumerate(draw_ids):\n",
-    "        theta_d = draw_posterior_theta(int(draw_id))\n",
-    "        ppc_draw = rl.Simulator(ssms_config).simulate(\n",
-    "            theta=theta_d,\n",
-    "            mode=\"ppc\",\n",
-    "            observed_data=observed_data,\n",
-    "            random_state=random_seed + 100 + offset,\n",
-    "        )\n",
-    "        ppc_draw[\"ppc_draw\"] = offset\n",
-    "        ppc_frames.append(ppc_draw)\n",
-    "    ppc_data = pd.concat(ppc_frames, ignore_index=True)\n",
-    "    fig, axes = plt.subplots(1, 2, figsize=(12, 4.5), constrained_layout=True)\n",
-    "    obs_curve = learning_curve(observed_data)\n",
-    "    ppc_curves = pd.concat(\n",
-    "        [\n",
-    "            learning_curve(group).rename(draw)\n",
-    "            for draw, group in ppc_data.groupby(\"ppc_draw\")\n",
-    "        ],\n",
-    "        axis=1,\n",
-    "    ).sort_index()\n",
-    "    centers = obs_curve.index + 5\n",
-    "    axes[0].fill_between(\n",
-    "        ppc_curves.index + 5,\n",
-    "        ppc_curves.quantile(0.03, axis=1),\n",
-    "        ppc_curves.quantile(0.97, axis=1),\n",
-    "        alpha=0.25,\n",
-    "        color=\"tab:blue\",\n",
-    "        label=\"PPC 94% band\",\n",
-    "    )\n",
-    "    axes[0].plot(\n",
-    "        ppc_curves.index + 5,\n",
-    "        ppc_curves.mean(axis=1),\n",
-    "        color=\"tab:blue\",\n",
-    "        lw=1.5,\n",
-    "        label=\"PPC mean\",\n",
-    "    )\n",
-    "    axes[0].plot(centers, obs_curve.values, \"o-\", color=\"black\", label=\"observed\")\n",
-    "    axes[0].axhline(0.5, color=\"0.7\", ls=\"--\", lw=1)\n",
-    "    axes[0].set(\n",
-    "        xlabel=\"Trial\",\n",
-    "        ylabel=\"P(chose high-reward arm)\",\n",
-    "        title=\"Learning-curve PPC\",\n",
-    "        ylim=(0, 1),\n",
-    "    )\n",
-    "    axes[0].legend(frameon=False)\n",
-    "    axes[1].hist(\n",
-    "        signed_rt(observed_data),\n",
-    "        bins=40,\n",
-    "        density=True,\n",
-    "        histtype=\"step\",\n",
-    "        lw=1.8,\n",
-    "        color=\"black\",\n",
-    "        label=\"observed\",\n",
-    "    )\n",
-    "    axes[1].hist(\n",
-    "        signed_rt(ppc_data),\n",
-    "        bins=40,\n",
-    "        density=True,\n",
-    "        histtype=\"step\",\n",
-    "        lw=1.8,\n",
-    "        color=\"tab:blue\",\n",
-    "        label=\"PPC\",\n",
-    "    )\n",
-    "    axes[1].axvline(0, color=\"0.6\", lw=1)\n",
-    "    axes[1].set(\n",
-    "        xlabel=\"Signed RT (negative = high-reward choice)\",\n",
-    "        ylabel=\"density\",\n",
-    "        title=\"Signed-RT PPC\",\n",
+    "\n",
+    "N_PPC_DRAWS = 20 if FULL_RUN else 8\n",
+    "n_samples = idata.posterior.sizes[\"chain\"] * idata.posterior.sizes[\"draw\"]\n",
+    "ppc_rng = np.random.default_rng(RANDOM_SEED + 1)\n",
+    "draw_ids = ppc_rng.choice(n_samples, size=min(N_PPC_DRAWS, n_samples), replace=False)\n",
+    "\n",
+    "ppc_frames = []\n",
+    "for k, d in enumerate(draw_ids):\n",
+    "    theta_d = draw_posterior_theta(idata, int(d))\n",
+    "    ppc_d = rl.Simulator(ssms_config).simulate(\n",
+    "        theta=theta_d,\n",
+    "        mode=\"ppc\",\n",
+    "        observed_data=data,\n",
+    "        random_state=RANDOM_SEED + 100 + k,\n",
     "    )\n",
-    "    axes[1].legend(frameon=False)\n",
-    "    plt.show()\n",
-    "    print(\"PPC datasets:\", len(draw_ids), \"| total rows:\", len(ppc_data))\n",
-    "    return ppc_data"
+    "    ppc_d[\"ppc_draw\"] = k\n",
+    "    ppc_frames.append(ppc_d)\n",
+    "ppc_data = pd.concat(ppc_frames, ignore_index=True)\n",
+    "print(\"PPC datasets:\", len(draw_ids), \"| total rows:\", len(ppc_data))"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 17,
    "id": "4a32f6f7",
-   "metadata": {},
-   "outputs": [],
+   "metadata": {
+    "execution": {
+     "iopub.execute_input": "2026-07-06T16:45:07.942880Z",
+     "iopub.status.busy": "2026-07-06T16:45:07.942808Z",
+     "iopub.status.idle": "2026-07-06T16:45:08.050560Z",
+     "shell.execute_reply": "2026-07-06T16:45:08.050055Z"
+    }
+   },
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 1200x450 with 2 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
    "source": [
-    "ppc_data = plot_rl_ppc(\n",
-    "    idata,\n",
-    "    observed_data=data,\n",
-    "    ssms_config=ssms_config,\n",
-    "    n_participants=N_PARTICIPANTS,\n",
-    "    random_seed=RANDOM_SEED,\n",
-    ")"
+    "def learning_curve(df, bin_size=10):\n",
+    "    \"\"\"Compute P(chose the high-reward arm) over trial bins.\"\"\"\n",
+    "    d = df[df[\"rt\"] > -900].copy()\n",
+    "    d[\"chose_high\"] = (d[\"response\"] == -1).astype(float)  # -1 == high-reward arm\n",
+    "    d[\"trial_bin\"] = (d[\"trial_id\"] // bin_size) * bin_size\n",
+    "    return d.groupby(\"trial_bin\")[\"chose_high\"].mean()\n",
+    "\n",
+    "\n",
+    "def signed_rt(df):\n",
+    "    \"\"\"Return finite RTs signed by response (- = high reward, + = low reward).\"\"\"\n",
+    "    d = df[df[\"rt\"] > -900].copy()\n",
+    "    # sign encodes choice: negative = high-reward arm (-1), positive = low-reward arm\n",
+    "    return np.where(\n",
+    "        d[\"response\"].astype(int) == -1, -d[\"rt\"].astype(float), d[\"rt\"].astype(float)\n",
+    "    )\n",
+    "\n",
+    "\n",
+    "fig, axes = plt.subplots(1, 2, figsize=(12, 4.5), constrained_layout=True)\n",
+    "\n",
+    "# (a) Learning-curve PPC: observed vs. per-draw predicted band\n",
+    "obs_curve = learning_curve(data)\n",
+    "ppc_curves = pd.concat(\n",
+    "    [learning_curve(g).rename(k) for k, g in ppc_data.groupby(\"ppc_draw\")], axis=1\n",
+    ").sort_index()\n",
+    "centers = obs_curve.index + 5\n",
+    "axes[0].fill_between(\n",
+    "    ppc_curves.index + 5,\n",
+    "    ppc_curves.quantile(0.03, axis=1),\n",
+    "    ppc_curves.quantile(0.97, axis=1),\n",
+    "    alpha=0.25,\n",
+    "    color=\"tab:blue\",\n",
+    "    label=\"PPC 94% band\",\n",
+    ")\n",
+    "axes[0].plot(\n",
+    "    ppc_curves.index + 5,\n",
+    "    ppc_curves.mean(axis=1),\n",
+    "    color=\"tab:blue\",\n",
+    "    lw=1.5,\n",
+    "    label=\"PPC mean\",\n",
+    ")\n",
+    "axes[0].plot(centers, obs_curve.values, \"o-\", color=\"black\", label=\"observed\")\n",
+    "axes[0].axhline(0.5, color=\"0.7\", ls=\"--\", lw=1)\n",
+    "axes[0].set(\n",
+    "    xlabel=\"Trial\",\n",
+    "    ylabel=\"P(chose high-reward arm)\",\n",
+    "    title=\"Learning-curve PPC\",\n",
+    "    ylim=(0, 1),\n",
+    ")\n",
+    "axes[0].legend(frameon=False)\n",
+    "\n",
+    "# (b) Signed-RT PPC: observed vs. pooled predicted\n",
+    "axes[1].hist(\n",
+    "    signed_rt(data),\n",
+    "    bins=40,\n",
+    "    density=True,\n",
+    "    histtype=\"step\",\n",
+    "    lw=1.8,\n",
+    "    color=\"black\",\n",
+    "    label=\"observed\",\n",
+    ")\n",
+    "axes[1].hist(\n",
+    "    signed_rt(ppc_data),\n",
+    "    bins=40,\n",
+    "    density=True,\n",
+    "    histtype=\"step\",\n",
+    "    lw=1.8,\n",
+    "    color=\"tab:blue\",\n",
+    "    label=\"PPC\",\n",
+    ")\n",
+    "axes[1].axvline(0, color=\"0.6\", lw=1)\n",
+    "axes[1].set(\n",
+    "    xlabel=\"Signed RT (negative = high-reward choice)\",\n",
+    "    ylabel=\"density\",\n",
+    "    title=\"Signed-RT PPC\",\n",
+    ")\n",
+    "axes[1].legend(frameon=False)\n",
+    "plt.show()"
    ]
   },
   {
@@ -711,28 +16877,36 @@
    "id": "a124489a",
    "metadata": {},
    "source": [
-    "## 10. Summary\n",
-    "You have run a complete beginner-friendly RLSSM workflow:\n",
+    "## 11. Summary\n",
+    "\n",
+    "You have run a complete RLSSM workflow:\n",
+    "\n",
     "1. **Chose a model** — the `2AB_RW_Angle` preset (Rescorla–Wagner learning + angle SSM).\n",
     "2. **Simulated** a hierarchical dataset from known parameters and confirmed learning.\n",
-    "3. **Fit** the same preset directly in HSSM with a hierarchical prior template.\n",
-    "4. **Sampled** the posterior with NumPyro using `process_initvals=False`.\n",
-    "5. **Checked** one recovery summary and an RL-aware PPC.\n",
+    "3. **Bridged** it into HSSM with a single `RLSSMConfig.from_ssms_model` call — the\n",
+    "   learned drift `v` is *computed*, never fit.\n",
+    "4. **Fit** a hierarchical model with NumPyro (remembering `process_initvals=False`).\n",
+    "5. **Checked recovery** at the group and individual level.\n",
+    "6. **Ran an RLSSM-aware PPC** with `mode=\"ppc\"`, which conditions the learning\n",
+    "   trajectory on the observed reward history.\n",
+    "\n",
     "### Where to go next\n",
+    "\n",
     "- **[Custom models with ssms.rl](rlssm_advanced.ipynb)** — build your own task\n",
     "  environment and learning rule instead of using a preset.\n",
     "- **[Restless learner](rlssm_restless_learner.ipynb)** — one learner driving *several*\n",
     "  decision parameters at once.\n",
     "- **[Registering custom models in HSSM](rlssm_hssm_custom_models.ipynb)** — the\n",
     "  HSSM-native registry path.\n",
+    "\n",
     "> **Note:** HSSM also supports *choice-only* reinforcement-learning models (no RT).\n",
-    "> Those are documented separately once fully validated against the current release.\n"
+    "> Those are documented separately once fully validated against the current release."
    ]
   }
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "hssm (3.13.1.final.0)",
+   "display_name": "Python 3",
    "language": "python",
    "name": "python3"
   },
@@ -745,7 +16919,8 @@
    "mimetype": "text/x-python",
    "name": "python",
    "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3"
+   "pygments_lexer": "ipython3",
+   "version": "3.12.11"
   }
  },
  "nbformat": 4,

From b3bcfc9bd3f19ae8994906a051a0d848d03c5fd9 Mon Sep 17 00:00:00 2001
From: Carlos Paniagua <cpaniaguam@gmail.com>
Date: Fri, 24 Jul 2026 10:46:39 -0400
Subject: [PATCH 6/6] nb clean nb

---
 docs/tutorials/rlssm_quickstart.ipynb | 1211 +------------------------
 1 file changed, 26 insertions(+), 1185 deletions(-)

diff --git a/docs/tutorials/rlssm_quickstart.ipynb b/docs/tutorials/rlssm_quickstart.ipynb
index ae1a454d2..f832a4daf 100644
--- a/docs/tutorials/rlssm_quickstart.ipynb
+++ b/docs/tutorials/rlssm_quickstart.ipynb
@@ -66,28 +66,10 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": null,
    "id": "f090de8f",
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "/home/cpaniaguam/HSSM/.venv/lib/python3.13/site-packages/tqdm/auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
-      "  from .autonotebook import tqdm as notebook_tqdm\n",
-      "An NVIDIA GPU may be present on this machine, but a CUDA-enabled jaxlib is not installed. Falling back to cpu.\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Setting PyTensor floatX type to float32.\n",
-      "Setting \"jax_enable_x64\" to False. If this is not intended, please set `jax` to False.\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "import logging\n",
     "import warnings\n",
@@ -126,18 +108,10 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": null,
    "id": "4a45b283",
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "quick mode | participants=5 trials=70 tune=300 draws=300\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "N_PARTICIPANTS = 5\n",
     "N_TRIALS = 70\n",
@@ -166,30 +140,10 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": null,
    "id": "81a5570b",
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Preset: 2AB_RW_Angle\n",
-      "Description: Two-armed bandit with a Rescorla-Wagner delta-rule learner and an angle decision process.\n",
-      "Task: two-armed Bernoulli bandit\n",
-      "Learning process: RescorlaWagnerDrift\n",
-      "Decision process: angle\n",
-      "Required parameters: rl_alpha, scaler, a, z, t, theta\n",
-      "Default parameters: rl_alpha=0.2, scaler=2, a=1, z=0.5, t=0.001, theta=0\n",
-      "Response labels: (-1, 1)\n",
-      "Response to choice: {-1: 0, 1: 1}\n",
-      "Context fields: ['feedback']\n",
-      "Learning backend: jax\n",
-      "Gradient support: available\n",
-      "HSSM participant contract: yes\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "print(rl.preset.info(\"2AB_RW_Angle\"))"
    ]
@@ -206,18 +160,10 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": null,
    "id": "5a61fc70",
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "computed params (driven by the learner): ['v']\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "ssms_config = rl.preset.get(\"2AB_RW_Angle\")\n",
     "assembled = ssms_config.assemble(backend=\"jax\")\n",
@@ -240,113 +186,10 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": null,
    "id": "6258c663",
    "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/html": [
-       "<div>\n",
-       "<style scoped>\n",
-       "    .dataframe tbody tr th:only-of-type {\n",
-       "        vertical-align: middle;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe tbody tr th {\n",
-       "        vertical-align: top;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe thead th {\n",
-       "        text-align: right;\n",
-       "    }\n",
-       "</style>\n",
-       "<table border=\"1\" class=\"dataframe\">\n",
-       "  <thead>\n",
-       "    <tr style=\"text-align: right;\">\n",
-       "      <th></th>\n",
-       "      <th>rl_alpha</th>\n",
-       "      <th>scaler</th>\n",
-       "      <th>a</th>\n",
-       "      <th>z</th>\n",
-       "      <th>t</th>\n",
-       "      <th>theta</th>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>participant_id</th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "    </tr>\n",
-       "  </thead>\n",
-       "  <tbody>\n",
-       "    <tr>\n",
-       "      <th>0</th>\n",
-       "      <td>0.048</td>\n",
-       "      <td>1.976</td>\n",
-       "      <td>1.425</td>\n",
-       "      <td>0.477</td>\n",
-       "      <td>0.242</td>\n",
-       "      <td>0.380</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>1</th>\n",
-       "      <td>0.118</td>\n",
-       "      <td>2.569</td>\n",
-       "      <td>1.092</td>\n",
-       "      <td>0.468</td>\n",
-       "      <td>0.168</td>\n",
-       "      <td>0.256</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2</th>\n",
-       "      <td>0.084</td>\n",
-       "      <td>2.381</td>\n",
-       "      <td>1.102</td>\n",
-       "      <td>0.471</td>\n",
-       "      <td>0.320</td>\n",
-       "      <td>0.338</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>3</th>\n",
-       "      <td>0.069</td>\n",
-       "      <td>2.924</td>\n",
-       "      <td>1.554</td>\n",
-       "      <td>0.499</td>\n",
-       "      <td>0.185</td>\n",
-       "      <td>0.323</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>4</th>\n",
-       "      <td>0.111</td>\n",
-       "      <td>2.508</td>\n",
-       "      <td>1.668</td>\n",
-       "      <td>0.396</td>\n",
-       "      <td>0.272</td>\n",
-       "      <td>0.465</td>\n",
-       "    </tr>\n",
-       "  </tbody>\n",
-       "</table>\n",
-       "</div>"
-      ],
-      "text/plain": [
-       "                rl_alpha  scaler      a      z      t  theta\n",
-       "participant_id                                              \n",
-       "0                  0.048   1.976  1.425  0.477  0.242  0.380\n",
-       "1                  0.118   2.569  1.092  0.468  0.168  0.256\n",
-       "2                  0.084   2.381  1.102  0.471  0.320  0.338\n",
-       "3                  0.069   2.924  1.554  0.499  0.185  0.323\n",
-       "4                  0.111   2.508  1.668  0.396  0.272  0.465"
-      ]
-     },
-     "execution_count": 5,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
+   "outputs": [],
    "source": [
     "GROUP_THETA = {\n",
     "    \"rl_alpha\": 0.08,  # learning rate (small -> gradual, visible learning)\n",
@@ -404,104 +247,10 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": null,
    "id": "887db61f",
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "rows: 350 | columns: ['participant_id', 'trial_id', 'rt', 'response', 'feedback']\n"
-     ]
-    },
-    {
-     "data": {
-      "text/html": [
-       "<div>\n",
-       "<style scoped>\n",
-       "    .dataframe tbody tr th:only-of-type {\n",
-       "        vertical-align: middle;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe tbody tr th {\n",
-       "        vertical-align: top;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe thead th {\n",
-       "        text-align: right;\n",
-       "    }\n",
-       "</style>\n",
-       "<table border=\"1\" class=\"dataframe\">\n",
-       "  <thead>\n",
-       "    <tr style=\"text-align: right;\">\n",
-       "      <th></th>\n",
-       "      <th>participant_id</th>\n",
-       "      <th>trial_id</th>\n",
-       "      <th>rt</th>\n",
-       "      <th>response</th>\n",
-       "      <th>feedback</th>\n",
-       "    </tr>\n",
-       "  </thead>\n",
-       "  <tbody>\n",
-       "    <tr>\n",
-       "      <th>0</th>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>1.100926</td>\n",
-       "      <td>-1</td>\n",
-       "      <td>1.0</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>1</th>\n",
-       "      <td>0</td>\n",
-       "      <td>1</td>\n",
-       "      <td>1.998554</td>\n",
-       "      <td>-1</td>\n",
-       "      <td>1.0</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2</th>\n",
-       "      <td>0</td>\n",
-       "      <td>2</td>\n",
-       "      <td>2.151356</td>\n",
-       "      <td>-1</td>\n",
-       "      <td>1.0</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>3</th>\n",
-       "      <td>0</td>\n",
-       "      <td>3</td>\n",
-       "      <td>0.589906</td>\n",
-       "      <td>-1</td>\n",
-       "      <td>1.0</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>4</th>\n",
-       "      <td>0</td>\n",
-       "      <td>4</td>\n",
-       "      <td>1.172487</td>\n",
-       "      <td>-1</td>\n",
-       "      <td>1.0</td>\n",
-       "    </tr>\n",
-       "  </tbody>\n",
-       "</table>\n",
-       "</div>"
-      ],
-      "text/plain": [
-       "   participant_id  trial_id        rt  response  feedback\n",
-       "0               0         0  1.100926        -1       1.0\n",
-       "1               0         1  1.998554        -1       1.0\n",
-       "2               0         2  2.151356        -1       1.0\n",
-       "3               0         3  0.589906        -1       1.0\n",
-       "4               0         4  1.172487        -1       1.0"
-      ]
-     },
-     "execution_count": 11,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
+   "outputs": [],
    "source": [
     "data = rl.Simulator(ssms_config).simulate(\n",
     "    theta=theta_arrays,\n",
@@ -539,21 +288,10 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 12,
+   "execution_count": null,
    "id": "991e7115",
    "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "image/png": "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",
-      "text/plain": [
-       "<Figure size 1200x400 with 2 Axes>"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    }
-   ],
+   "outputs": [],
    "source": [
     "BIN = 10\n",
     "learn = data[data[\"rt\"] > 0].copy()\n",
@@ -601,7 +339,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 13,
+   "execution_count": null,
    "id": "52e648b3",
    "metadata": {},
    "outputs": [],
@@ -643,28 +381,10 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 14,
+   "execution_count": null,
    "id": "f44b2a62",
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "Warning: You are sending unauthenticated requests to the HF Hub. Please set a HF_TOKEN to enable higher rate limits and faster downloads.\n",
-      "You supplied a model '2AB_RW_Angle', which is currently not supported in the ssm_simulators package. An error will be thrown when sampling from the random variable or when using any posterior or prior predictive sampling methods.\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Model initialized successfully.\n",
-      "participants: 5 | trials/participant: 70\n",
-      "free parameters: ['rl_alpha', 'scaler', 'a', 'z', 't', 'theta']\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "model = hssm.RLSSM(\n",
     "    data=data,\n",
@@ -702,771 +422,10 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 15,
+   "execution_count": null,
    "id": "e4bb5cd3",
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Using default initvals. \n",
-      "\n"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "NUTS[numpyro]: [rl_alpha_Intercept, rl_alpha_1|participant_id_sigma, rl_alpha_1|participant_id_offset, scaler_Intercept, scaler_1|participant_id_sigma, scaler_1|participant_id_offset, a_Intercept, a_1|participant_id_sigma, a_1|participant_id_offset, z_Intercept, z_1|participant_id_sigma, z_1|participant_id_offset, t_Intercept, t_1|participant_id_sigma, t_1|participant_id_offset, theta_Intercept, theta_1|participant_id_sigma, theta_1|participant_id_offset]\n",
-      "sample: 100%|██████████| 600/600 [00:50<00:00, 11.82it/s, 127 steps of size 4.31e-02. acc. prob=0.96]\n",
-      "sample: 100%|██████████| 600/600 [00:37<00:00, 16.16it/s, 127 steps of size 5.79e-02. acc. prob=0.93]\n",
-      "There were 80 divergences after tuning. Increase `target_accept` or reparameterize.\n",
-      "We recommend running at least 4 chains for robust computation of convergence diagnostics\n",
-      "The rhat statistic is larger than 1.01 for some parameters. This indicates problems during sampling. See https://arxiv.org/abs/1903.08008 for details\n",
-      "The effective sample size per chain is smaller than 100 for some parameters.  A higher number is needed for reliable rhat and ess computation. See https://arxiv.org/abs/1903.08008 for details\n"
-     ]
-    },
-    {
-     "data": {
-      "text/html": [
-       "<div><svg style=\"position: absolute; width: 0; height: 0; overflow: hidden\">\n",
-       "<defs>\n",
-       "<symbol id=\"icon-database\" viewBox=\"0 0 32 32\">\n",
-       "<path d=\"M16 0c-8.837 0-16 2.239-16 5v4c0 2.761 7.163 5 16 5s16-2.239 16-5v-4c0-2.761-7.163-5-16-5z\"></path>\n",
-       "<path d=\"M16 17c-8.837 0-16-2.239-16-5v6c0 2.761 7.163 5 16 5s16-2.239 16-5v-6c0 2.761-7.163 5-16 5z\"></path>\n",
-       "<path d=\"M16 26c-8.837 0-16-2.239-16-5v6c0 2.761 7.163 5 16 5s16-2.239 16-5v-6c0 2.761-7.163 5-16 5z\"></path>\n",
-       "</symbol>\n",
-       "<symbol id=\"icon-file-text2\" viewBox=\"0 0 32 32\">\n",
-       "<path d=\"M28.681 7.159c-0.694-0.947-1.662-2.053-2.724-3.116s-2.169-2.030-3.116-2.724c-1.612-1.182-2.393-1.319-2.841-1.319h-15.5c-1.378 0-2.5 1.121-2.5 2.5v27c0 1.378 1.122 2.5 2.5 2.5h23c1.378 0 2.5-1.122 2.5-2.5v-19.5c0-0.448-0.137-1.23-1.319-2.841zM24.543 5.457c0.959 0.959 1.712 1.825 2.268 2.543h-4.811v-4.811c0.718 0.556 1.584 1.309 2.543 2.268zM28 29.5c0 0.271-0.229 0.5-0.5 0.5h-23c-0.271 0-0.5-0.229-0.5-0.5v-27c0-0.271 0.229-0.5 0.5-0.5 0 0 15.499-0 15.5 0v7c0 0.552 0.448 1 1 1h7v19.5z\"></path>\n",
-       "<path d=\"M23 26h-14c-0.552 0-1-0.448-1-1s0.448-1 1-1h14c0.552 0 1 0.448 1 1s-0.448 1-1 1z\"></path>\n",
-       "<path d=\"M23 22h-14c-0.552 0-1-0.448-1-1s0.448-1 1-1h14c0.552 0 1 0.448 1 1s-0.448 1-1 1z\"></path>\n",
-       "<path d=\"M23 18h-14c-0.552 0-1-0.448-1-1s0.448-1 1-1h14c0.552 0 1 0.448 1 1s-0.448 1-1 1z\"></path>\n",
-       "</symbol>\n",
-       "</defs>\n",
-       "</svg>\n",
-       "<style>/* CSS stylesheet for displaying xarray objects in notebooks */\n",
-       "\n",
-       ":root {\n",
-       "  --xr-font-color0: var(\n",
-       "    --jp-content-font-color0,\n",
-       "    var(--pst-color-text-base rgba(0, 0, 0, 1))\n",
-       "  );\n",
-       "  --xr-font-color2: var(\n",
-       "    --jp-content-font-color2,\n",
-       "    var(--pst-color-text-base, rgba(0, 0, 0, 0.54))\n",
-       "  );\n",
-       "  --xr-font-color3: var(\n",
-       "    --jp-content-font-color3,\n",
-       "    var(--pst-color-text-base, rgba(0, 0, 0, 0.38))\n",
-       "  );\n",
-       "  --xr-border-color: var(\n",
-       "    --jp-border-color2,\n",
-       "    hsl(from var(--pst-color-on-background, white) h s calc(l - 10))\n",
-       "  );\n",
-       "  --xr-disabled-color: var(\n",
-       "    --jp-layout-color3,\n",
-       "    hsl(from var(--pst-color-on-background, white) h s calc(l - 40))\n",
-       "  );\n",
-       "  --xr-background-color: var(\n",
-       "    --jp-layout-color0,\n",
-       "    var(--pst-color-on-background, white)\n",
-       "  );\n",
-       "  --xr-background-color-row-even: var(\n",
-       "    --jp-layout-color1,\n",
-       "    hsl(from var(--pst-color-on-background, white) h s calc(l - 5))\n",
-       "  );\n",
-       "  --xr-background-color-row-odd: var(\n",
-       "    --jp-layout-color2,\n",
-       "    hsl(from var(--pst-color-on-background, white) h s calc(l - 15))\n",
-       "  );\n",
-       "}\n",
-       "\n",
-       "html[theme=\"dark\"],\n",
-       "html[data-theme=\"dark\"],\n",
-       "body[data-theme=\"dark\"],\n",
-       "body.vscode-dark {\n",
-       "  --xr-font-color0: var(\n",
-       "    --jp-content-font-color0,\n",
-       "    var(--pst-color-text-base, rgba(255, 255, 255, 1))\n",
-       "  );\n",
-       "  --xr-font-color2: var(\n",
-       "    --jp-content-font-color2,\n",
-       "    var(--pst-color-text-base, rgba(255, 255, 255, 0.54))\n",
-       "  );\n",
-       "  --xr-font-color3: var(\n",
-       "    --jp-content-font-color3,\n",
-       "    var(--pst-color-text-base, rgba(255, 255, 255, 0.38))\n",
-       "  );\n",
-       "  --xr-border-color: var(\n",
-       "    --jp-border-color2,\n",
-       "    hsl(from var(--pst-color-on-background, #111111) h s calc(l + 10))\n",
-       "  );\n",
-       "  --xr-disabled-color: var(\n",
-       "    --jp-layout-color3,\n",
-       "    hsl(from var(--pst-color-on-background, #111111) h s calc(l + 40))\n",
-       "  );\n",
-       "  --xr-background-color: var(\n",
-       "    --jp-layout-color0,\n",
-       "    var(--pst-color-on-background, #111111)\n",
-       "  );\n",
-       "  --xr-background-color-row-even: var(\n",
-       "    --jp-layout-color1,\n",
-       "    hsl(from var(--pst-color-on-background, #111111) h s calc(l + 5))\n",
-       "  );\n",
-       "  --xr-background-color-row-odd: var(\n",
-       "    --jp-layout-color2,\n",
-       "    hsl(from var(--pst-color-on-background, #111111) h s calc(l + 15))\n",
-       "  );\n",
-       "}\n",
-       "\n",
-       ".xr-wrap {\n",
-       "  display: block !important;\n",
-       "  min-width: 300px;\n",
-       "  max-width: 700px;\n",
-       "  line-height: 1.6;\n",
-       "  padding-bottom: 4px;\n",
-       "}\n",
-       "\n",
-       ".xr-text-repr-fallback {\n",
-       "  /* fallback to plain text repr when CSS is not injected (untrusted notebook) */\n",
-       "  display: none;\n",
-       "}\n",
-       "\n",
-       ".xr-header {\n",
-       "  padding-top: 6px;\n",
-       "  padding-bottom: 6px;\n",
-       "}\n",
-       "\n",
-       ".xr-header {\n",
-       "  border-bottom: solid 1px var(--xr-border-color);\n",
-       "  margin-bottom: 4px;\n",
-       "}\n",
-       "\n",
-       ".xr-header > div,\n",
-       ".xr-header > ul {\n",
-       "  display: inline;\n",
-       "  margin-top: 0;\n",
-       "  margin-bottom: 0;\n",
-       "}\n",
-       "\n",
-       ".xr-obj-type,\n",
-       ".xr-obj-name {\n",
-       "  margin-left: 2px;\n",
-       "  margin-right: 10px;\n",
-       "}\n",
-       "\n",
-       ".xr-obj-type,\n",
-       ".xr-group-box-contents > label {\n",
-       "  color: var(--xr-font-color2);\n",
-       "  display: block;\n",
-       "}\n",
-       "\n",
-       ".xr-sections {\n",
-       "  padding-left: 0 !important;\n",
-       "  display: grid;\n",
-       "  grid-template-columns: 150px auto auto 1fr 0 20px 0 20px;\n",
-       "  margin-block-start: 0;\n",
-       "  margin-block-end: 0;\n",
-       "}\n",
-       "\n",
-       ".xr-section-item {\n",
-       "  display: contents;\n",
-       "}\n",
-       "\n",
-       ".xr-section-item > input,\n",
-       ".xr-group-box-contents > input,\n",
-       ".xr-array-wrap > input {\n",
-       "  display: block;\n",
-       "  opacity: 0;\n",
-       "  height: 0;\n",
-       "  margin: 0;\n",
-       "}\n",
-       "\n",
-       ".xr-section-item > input + label,\n",
-       ".xr-var-item > input + label {\n",
-       "  color: var(--xr-disabled-color);\n",
-       "}\n",
-       "\n",
-       ".xr-section-item > input:enabled + label,\n",
-       ".xr-var-item > input:enabled + label,\n",
-       ".xr-array-wrap > input:enabled + label,\n",
-       ".xr-group-box-contents > input:enabled + label {\n",
-       "  cursor: pointer;\n",
-       "  color: var(--xr-font-color2);\n",
-       "}\n",
-       "\n",
-       ".xr-section-item > input:focus-visible + label,\n",
-       ".xr-var-item > input:focus-visible + label,\n",
-       ".xr-array-wrap > input:focus-visible + label,\n",
-       ".xr-group-box-contents > input:focus-visible + label {\n",
-       "  outline: auto;\n",
-       "}\n",
-       "\n",
-       ".xr-section-item > input:enabled + label:hover,\n",
-       ".xr-var-item > input:enabled + label:hover,\n",
-       ".xr-array-wrap > input:enabled + label:hover,\n",
-       ".xr-group-box-contents > input:enabled + label:hover {\n",
-       "  color: var(--xr-font-color0);\n",
-       "}\n",
-       "\n",
-       ".xr-section-summary {\n",
-       "  grid-column: 1;\n",
-       "  color: var(--xr-font-color2);\n",
-       "  font-weight: 500;\n",
-       "  white-space: nowrap;\n",
-       "}\n",
-       "\n",
-       ".xr-section-summary > em {\n",
-       "  font-weight: normal;\n",
-       "}\n",
-       "\n",
-       ".xr-span-grid {\n",
-       "  grid-column-end: -1;\n",
-       "}\n",
-       "\n",
-       ".xr-section-summary > span {\n",
-       "  display: inline-block;\n",
-       "  padding-left: 0.3em;\n",
-       "}\n",
-       "\n",
-       ".xr-group-box-contents > input:checked + label > span {\n",
-       "  display: inline-block;\n",
-       "  padding-left: 0.6em;\n",
-       "}\n",
-       "\n",
-       ".xr-section-summary-in:disabled + label {\n",
-       "  color: var(--xr-font-color2);\n",
-       "}\n",
-       "\n",
-       ".xr-section-summary-in + label:before {\n",
-       "  display: inline-block;\n",
-       "  content: \"►\";\n",
-       "  font-size: 11px;\n",
-       "  width: 15px;\n",
-       "  text-align: center;\n",
-       "}\n",
-       "\n",
-       ".xr-section-summary-in:disabled + label:before {\n",
-       "  color: var(--xr-disabled-color);\n",
-       "}\n",
-       "\n",
-       ".xr-section-summary-in:checked + label:before {\n",
-       "  content: \"▼\";\n",
-       "}\n",
-       "\n",
-       ".xr-section-summary-in:checked + label > span {\n",
-       "  display: none;\n",
-       "}\n",
-       "\n",
-       ".xr-section-summary,\n",
-       ".xr-section-inline-details,\n",
-       ".xr-group-box-contents > label {\n",
-       "  padding-top: 4px;\n",
-       "}\n",
-       "\n",
-       ".xr-section-inline-details {\n",
-       "  grid-column: 2 / -1;\n",
-       "}\n",
-       "\n",
-       ".xr-section-details {\n",
-       "  grid-column: 1 / -1;\n",
-       "  margin-top: 4px;\n",
-       "  margin-bottom: 5px;\n",
-       "}\n",
-       "\n",
-       ".xr-section-summary-in ~ .xr-section-details {\n",
-       "  display: none;\n",
-       "}\n",
-       "\n",
-       ".xr-section-summary-in:checked ~ .xr-section-details {\n",
-       "  display: contents;\n",
-       "}\n",
-       "\n",
-       ".xr-children {\n",
-       "  display: inline-grid;\n",
-       "  grid-template-columns: 100%;\n",
-       "  grid-column: 1 / -1;\n",
-       "  padding-top: 4px;\n",
-       "}\n",
-       "\n",
-       ".xr-group-box {\n",
-       "  display: inline-grid;\n",
-       "  grid-template-columns: 0px 30px auto;\n",
-       "}\n",
-       "\n",
-       ".xr-group-box-vline {\n",
-       "  grid-column-start: 1;\n",
-       "  border-right: 0.2em solid;\n",
-       "  border-color: var(--xr-border-color);\n",
-       "  width: 0px;\n",
-       "}\n",
-       "\n",
-       ".xr-group-box-hline {\n",
-       "  grid-column-start: 2;\n",
-       "  grid-row-start: 1;\n",
-       "  height: 1em;\n",
-       "  width: 26px;\n",
-       "  border-bottom: 0.2em solid;\n",
-       "  border-color: var(--xr-border-color);\n",
-       "}\n",
-       "\n",
-       ".xr-group-box-contents {\n",
-       "  grid-column-start: 3;\n",
-       "  padding-bottom: 4px;\n",
-       "}\n",
-       "\n",
-       ".xr-group-box-contents > label::before {\n",
-       "  content: \"📂\";\n",
-       "  padding-right: 0.3em;\n",
-       "}\n",
-       "\n",
-       ".xr-group-box-contents > input:checked + label::before {\n",
-       "  content: \"📁\";\n",
-       "}\n",
-       "\n",
-       ".xr-group-box-contents > input:checked + label {\n",
-       "  padding-bottom: 0px;\n",
-       "}\n",
-       "\n",
-       ".xr-group-box-contents > input:checked ~ .xr-sections {\n",
-       "  display: none;\n",
-       "}\n",
-       "\n",
-       ".xr-group-box-contents > input + label > span {\n",
-       "  display: none;\n",
-       "}\n",
-       "\n",
-       ".xr-group-box-ellipsis {\n",
-       "  font-size: 1.4em;\n",
-       "  font-weight: 900;\n",
-       "  color: var(--xr-font-color2);\n",
-       "  letter-spacing: 0.15em;\n",
-       "  cursor: default;\n",
-       "}\n",
-       "\n",
-       ".xr-array-wrap {\n",
-       "  grid-column: 1 / -1;\n",
-       "  display: grid;\n",
-       "  grid-template-columns: 20px auto;\n",
-       "}\n",
-       "\n",
-       ".xr-array-wrap > label {\n",
-       "  grid-column: 1;\n",
-       "  vertical-align: top;\n",
-       "}\n",
-       "\n",
-       ".xr-preview {\n",
-       "  color: var(--xr-font-color3);\n",
-       "}\n",
-       "\n",
-       ".xr-array-preview,\n",
-       ".xr-array-data {\n",
-       "  padding: 0 5px !important;\n",
-       "  grid-column: 2;\n",
-       "}\n",
-       "\n",
-       ".xr-array-data,\n",
-       ".xr-array-in:checked ~ .xr-array-preview {\n",
-       "  display: none;\n",
-       "}\n",
-       "\n",
-       ".xr-array-in:checked ~ .xr-array-data,\n",
-       ".xr-array-preview {\n",
-       "  display: inline-block;\n",
-       "}\n",
-       "\n",
-       ".xr-dim-list {\n",
-       "  display: inline-block !important;\n",
-       "  list-style: none;\n",
-       "  padding: 0 !important;\n",
-       "  margin: 0;\n",
-       "}\n",
-       "\n",
-       ".xr-dim-list li {\n",
-       "  display: inline-block;\n",
-       "  padding: 0;\n",
-       "  margin: 0;\n",
-       "}\n",
-       "\n",
-       ".xr-dim-list:before {\n",
-       "  content: \"(\";\n",
-       "}\n",
-       "\n",
-       ".xr-dim-list:after {\n",
-       "  content: \")\";\n",
-       "}\n",
-       "\n",
-       ".xr-dim-list li:not(:last-child):after {\n",
-       "  content: \",\";\n",
-       "  padding-right: 5px;\n",
-       "}\n",
-       "\n",
-       ".xr-has-index {\n",
-       "  font-weight: bold;\n",
-       "}\n",
-       "\n",
-       ".xr-var-list,\n",
-       ".xr-var-item {\n",
-       "  display: contents;\n",
-       "}\n",
-       "\n",
-       ".xr-var-item > div,\n",
-       ".xr-var-item label,\n",
-       ".xr-var-item > .xr-var-name span {\n",
-       "  background-color: var(--xr-background-color-row-even);\n",
-       "  border-color: var(--xr-background-color-row-odd);\n",
-       "  margin-bottom: 0;\n",
-       "  padding-top: 2px;\n",
-       "}\n",
-       "\n",
-       ".xr-var-item > .xr-var-name:hover span {\n",
-       "  padding-right: 5px;\n",
-       "}\n",
-       "\n",
-       ".xr-var-list > li:nth-child(odd) > div,\n",
-       ".xr-var-list > li:nth-child(odd) > label,\n",
-       ".xr-var-list > li:nth-child(odd) > .xr-var-name span {\n",
-       "  background-color: var(--xr-background-color-row-odd);\n",
-       "  border-color: var(--xr-background-color-row-even);\n",
-       "}\n",
-       "\n",
-       ".xr-var-name {\n",
-       "  grid-column: 1;\n",
-       "}\n",
-       "\n",
-       ".xr-var-dims {\n",
-       "  grid-column: 2;\n",
-       "}\n",
-       "\n",
-       ".xr-var-dtype {\n",
-       "  grid-column: 3;\n",
-       "  text-align: right;\n",
-       "  color: var(--xr-font-color2);\n",
-       "}\n",
-       "\n",
-       ".xr-var-preview {\n",
-       "  grid-column: 4;\n",
-       "}\n",
-       "\n",
-       ".xr-index-preview {\n",
-       "  grid-column: 2 / 5;\n",
-       "  color: var(--xr-font-color2);\n",
-       "}\n",
-       "\n",
-       ".xr-var-name,\n",
-       ".xr-var-dims,\n",
-       ".xr-var-dtype,\n",
-       ".xr-preview,\n",
-       ".xr-attrs dt {\n",
-       "  white-space: nowrap;\n",
-       "  overflow: hidden;\n",
-       "  text-overflow: ellipsis;\n",
-       "  padding-right: 10px;\n",
-       "}\n",
-       "\n",
-       ".xr-var-name:hover,\n",
-       ".xr-var-dims:hover,\n",
-       ".xr-var-dtype:hover,\n",
-       ".xr-attrs dt:hover {\n",
-       "  overflow: visible;\n",
-       "  width: auto;\n",
-       "  z-index: 1;\n",
-       "}\n",
-       "\n",
-       ".xr-var-attrs,\n",
-       ".xr-var-data,\n",
-       ".xr-index-data {\n",
-       "  display: none;\n",
-       "  border-top: 2px dotted var(--xr-background-color);\n",
-       "  padding-bottom: 20px !important;\n",
-       "  padding-top: 10px !important;\n",
-       "}\n",
-       "\n",
-       ".xr-var-attrs-in + label,\n",
-       ".xr-var-data-in + label,\n",
-       ".xr-index-data-in + label {\n",
-       "  padding: 0 1px;\n",
-       "}\n",
-       "\n",
-       ".xr-var-attrs-in:checked ~ .xr-var-attrs,\n",
-       ".xr-var-data-in:checked ~ .xr-var-data,\n",
-       ".xr-index-data-in:checked ~ .xr-index-data {\n",
-       "  display: block;\n",
-       "}\n",
-       "\n",
-       ".xr-var-data > table {\n",
-       "  float: right;\n",
-       "}\n",
-       "\n",
-       ".xr-var-data > pre,\n",
-       ".xr-index-data > pre,\n",
-       ".xr-var-data > table > tbody > tr {\n",
-       "  background-color: transparent !important;\n",
-       "}\n",
-       "\n",
-       ".xr-var-name span,\n",
-       ".xr-var-data,\n",
-       ".xr-index-name div,\n",
-       ".xr-index-data,\n",
-       ".xr-attrs {\n",
-       "  padding-left: 25px !important;\n",
-       "}\n",
-       "\n",
-       ".xr-attrs,\n",
-       ".xr-var-attrs,\n",
-       ".xr-var-data,\n",
-       ".xr-index-data {\n",
-       "  grid-column: 1 / -1;\n",
-       "}\n",
-       "\n",
-       "dl.xr-attrs {\n",
-       "  padding: 0;\n",
-       "  margin: 0;\n",
-       "  display: grid;\n",
-       "  grid-template-columns: 125px auto;\n",
-       "}\n",
-       "\n",
-       ".xr-attrs dt,\n",
-       ".xr-attrs dd {\n",
-       "  padding: 0;\n",
-       "  margin: 0;\n",
-       "  float: left;\n",
-       "  padding-right: 10px;\n",
-       "  width: auto;\n",
-       "}\n",
-       "\n",
-       ".xr-attrs dt {\n",
-       "  font-weight: normal;\n",
-       "  grid-column: 1;\n",
-       "}\n",
-       "\n",
-       ".xr-attrs dt:hover span {\n",
-       "  display: inline-block;\n",
-       "  background: var(--xr-background-color);\n",
-       "  padding-right: 10px;\n",
-       "}\n",
-       "\n",
-       ".xr-attrs dd {\n",
-       "  grid-column: 2;\n",
-       "  white-space: pre-wrap;\n",
-       "  word-break: break-all;\n",
-       "}\n",
-       "\n",
-       ".xr-icon-database,\n",
-       ".xr-icon-file-text2,\n",
-       ".xr-no-icon {\n",
-       "  display: inline-block;\n",
-       "  vertical-align: middle;\n",
-       "  width: 1em;\n",
-       "  height: 1.5em !important;\n",
-       "  stroke-width: 0;\n",
-       "  stroke: currentColor;\n",
-       "  fill: currentColor;\n",
-       "}\n",
-       "\n",
-       ".xr-var-attrs-in:checked + label > .xr-icon-file-text2,\n",
-       ".xr-var-data-in:checked + label > .xr-icon-database,\n",
-       ".xr-index-data-in:checked + label > .xr-icon-database {\n",
-       "  color: var(--xr-font-color0);\n",
-       "  filter: drop-shadow(1px 1px 5px var(--xr-font-color2));\n",
-       "  stroke-width: 0.8px;\n",
-       "}\n",
-       "</style><pre class='xr-text-repr-fallback'>&lt;xarray.DataTree&gt;\n",
-       "Group: /\n",
-       "├── Group: /posterior\n",
-       "│       Dimensions:                                (chain: 2, draw: 300,\n",
-       "│                                                   participant_id__factor_dim: 5,\n",
-       "│                                                   rl_alpha_1|participant_id__factor_dim: 5)\n",
-       "│       Coordinates:\n",
-       "│         * chain                                  (chain) int64 16B 0 1\n",
-       "│         * draw                                   (draw) int64 2kB 0 1 2 ... 298 299\n",
-       "│         * participant_id__factor_dim             (participant_id__factor_dim) &lt;U1 20B ...\n",
-       "│         * rl_alpha_1|participant_id__factor_dim  (rl_alpha_1|participant_id__factor_dim) &lt;U1 20B ...\n",
-       "│       Data variables: (12/24)\n",
-       "│           z_1|participant_id_offset              (chain, draw, participant_id__factor_dim) float32 12kB ...\n",
-       "│           z_Intercept                            (chain, draw) float32 2kB ...\n",
-       "│           scaler_1|participant_id_offset         (chain, draw, participant_id__factor_dim) float32 12kB ...\n",
-       "│           a_1|participant_id_offset              (chain, draw, participant_id__factor_dim) float32 12kB ...\n",
-       "│           a_1|participant_id                     (chain, draw, participant_id__factor_dim) float32 12kB ...\n",
-       "│           t_1|participant_id_sigma               (chain, draw) float32 2kB ...\n",
-       "│           ...                                     ...\n",
-       "│           z_1|participant_id_sigma               (chain, draw) float32 2kB ...\n",
-       "│           rl_alpha_1|participant_id_offset       (chain, draw, rl_alpha_1|participant_id__factor_dim) float32 12kB ...\n",
-       "│           scaler_Intercept                       (chain, draw) float32 2kB ...\n",
-       "│           t_1|participant_id                     (chain, draw, participant_id__factor_dim) float32 12kB ...\n",
-       "│           scaler_1|participant_id_sigma          (chain, draw) float32 2kB ...\n",
-       "│           t_1|participant_id_offset              (chain, draw, participant_id__factor_dim) float32 12kB ...\n",
-       "│       Attributes:\n",
-       "│           created_at:                  2026-07-24T14:18:40.484086+00:00\n",
-       "│           creation_library:            ArviZ\n",
-       "│           creation_library_version:    1.2.0\n",
-       "│           creation_library_language:   Python\n",
-       "│           sample_dims:                 [&#x27;chain&#x27;, &#x27;draw&#x27;]\n",
-       "│           inference_library:           numpyro\n",
-       "│           inference_library_version:   0.21.0\n",
-       "│           sampling_time:               92.736215\n",
-       "│           tuning_steps:                300\n",
-       "│           modeling_interface:          bambi\n",
-       "│           modeling_interface_version:  0.19.0\n",
-       "├── Group: /sample_stats\n",
-       "│       Dimensions:          (chain: 2, draw: 300)\n",
-       "│       Coordinates:\n",
-       "│         * chain            (chain) int64 16B 0 1\n",
-       "│         * draw             (draw) int64 2kB 0 1 2 3 4 5 6 ... 294 295 296 297 298 299\n",
-       "│       Data variables:\n",
-       "│           acceptance_rate  (chain, draw) float32 2kB ...\n",
-       "│           step_size        (chain, draw) float32 2kB ...\n",
-       "│           diverging        (chain, draw) bool 600B ...\n",
-       "│           energy           (chain, draw) float32 2kB ...\n",
-       "│           n_steps          (chain, draw) int32 2kB ...\n",
-       "│           tree_depth       (chain, draw) int64 5kB 7 7 7 7 7 7 7 7 ... 6 6 6 6 7 6 6 7\n",
-       "│           lp               (chain, draw) float32 2kB ...\n",
-       "│       Attributes:\n",
-       "│           created_at:                  2026-07-24T14:18:40.498297+00:00\n",
-       "│           creation_library:            ArviZ\n",
-       "│           creation_library_version:    1.2.0\n",
-       "│           creation_library_language:   Python\n",
-       "│           sample_dims:                 [&#x27;chain&#x27;, &#x27;draw&#x27;]\n",
-       "│           modeling_interface:          bambi\n",
-       "│           modeling_interface_version:  0.19.0\n",
-       "├── Group: /observed_data\n",
-       "│       Dimensions:                  (__obs__: 350, rt,response_extra_dim_0: 2)\n",
-       "│       Coordinates:\n",
-       "│         * __obs__                  (__obs__) int64 3kB 0 1 2 3 4 ... 346 347 348 349\n",
-       "│         * rt,response_extra_dim_0  (rt,response_extra_dim_0) int64 16B 0 1\n",
-       "│       Data variables:\n",
-       "│           rt,response              (__obs__, rt,response_extra_dim_0) float32 3kB 1...\n",
-       "│       Attributes:\n",
-       "│           created_at:                  2026-07-24T14:18:40.499371+00:00\n",
-       "│           creation_library:            ArviZ\n",
-       "│           creation_library_version:    1.2.0\n",
-       "│           creation_library_language:   Python\n",
-       "│           sample_dims:                 []\n",
-       "│           modeling_interface:          bambi\n",
-       "│           modeling_interface_version:  0.19.0\n",
-       "├── Group: /constant_data\n",
-       "│       Attributes:\n",
-       "│           created_at:                  2026-07-24T14:18:40.499495+00:00\n",
-       "│           creation_library:            ArviZ\n",
-       "│           creation_library_version:    1.2.0\n",
-       "│           creation_library_language:   Python\n",
-       "│           sample_dims:                 []\n",
-       "│           modeling_interface:          bambi\n",
-       "│           modeling_interface_version:  0.19.0\n",
-       "└── Group: /log_likelihood\n",
-       "        Dimensions:      (chain: 2, draw: 300, __obs__: 350)\n",
-       "        Coordinates:\n",
-       "          * chain        (chain) int64 16B 0 1\n",
-       "          * draw         (draw) int64 2kB 0 1 2 3 4 5 6 ... 293 294 295 296 297 298 299\n",
-       "          * __obs__      (__obs__) int64 3kB 0 1 2 3 4 5 6 ... 344 345 346 347 348 349\n",
-       "        Data variables:\n",
-       "            rt,response  (chain, draw, __obs__) float64 2MB -0.9516 -1.938 ... -0.2128\n",
-       "        Attributes:\n",
-       "            modeling_interface:          bambi\n",
-       "            modeling_interface_version:  0.19.0</pre><div class='xr-wrap' style='display:none'><div class='xr-header'><div class='xr-obj-type'>xarray.DataTree</div></div><ul class='xr-sections'><li class='xr-section-item'><div class='xr-children'><div class='xr-group-box'><div class='xr-group-box-vline' style='height: 100%'></div><div class='xr-group-box-hline'></div><div class='xr-group-box-contents'><input id='group-5997ee09-02eb-4eb1-965d-3b9925d4b080' type='checkbox' checked /><label for='group-5997ee09-02eb-4eb1-965d-3b9925d4b080' title='Expand/collapse group'>/posterior<span>(39)</span></label><ul class='xr-sections'><li class='xr-section-item'><input id='section-038e5b00-c340-41c0-bb0e-3be7767cbb8d' class='xr-section-summary-in' type='checkbox' disabled /><label for='section-038e5b00-c340-41c0-bb0e-3be7767cbb8d' class='xr-section-summary'>Dimensions:</label><div class='xr-section-inline-details'><ul class='xr-dim-list'><li><span class='xr-has-index'>chain</span>: 2</li><li><span class='xr-has-index'>draw</span>: 300</li><li><span class='xr-has-index'>participant_id__factor_dim</span>: 5</li><li><span class='xr-has-index'>rl_alpha_1|participant_id__factor_dim</span>: 5</li></ul></div></li><li class='xr-section-item'><input id='section-da4d6ce4-bc60-4a0f-b6a7-ce4af3f97756' class='xr-section-summary-in' type='checkbox' checked /><label for='section-da4d6ce4-bc60-4a0f-b6a7-ce4af3f97756' class='xr-section-summary' title='Expand/collapse section'>Coordinates: <span>(4)</span></label><div class='xr-section-inline-details'></div><div class='xr-section-details'><ul class='xr-var-list'><li class='xr-var-item'><div class='xr-var-name'><span class='xr-has-index'>chain</span></div><div class='xr-var-dims'>(chain)</div><div class='xr-var-dtype'>int64</div><div class='xr-var-preview xr-preview'>0 1</div><input id='attrs-cbc9ed68-4d98-42d1-9566-8c0b64134337' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-cbc9ed68-4d98-42d1-9566-8c0b64134337' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-f7d4477e-ecd2-4719-a1a7-f648fc72fb1d' class='xr-var-data-in' type='checkbox'><label for='data-f7d4477e-ecd2-4719-a1a7-f648fc72fb1d' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>array([0, 1])</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span class='xr-has-index'>draw</span></div><div class='xr-var-dims'>(draw)</div><div class='xr-var-dtype'>int64</div><div class='xr-var-preview xr-preview'>0 1 2 3 4 5 ... 295 296 297 298 299</div><input id='attrs-fd874f2d-9c78-4b8c-98e8-ac35f4683bf9' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-fd874f2d-9c78-4b8c-98e8-ac35f4683bf9' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-e02e2973-93fa-41cb-bdf2-839873382c55' class='xr-var-data-in' type='checkbox'><label for='data-e02e2973-93fa-41cb-bdf2-839873382c55' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>array([  0,   1,   2, ..., 297, 298, 299], shape=(300,))</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span class='xr-has-index'>participant_id__factor_dim</span></div><div class='xr-var-dims'>(participant_id__factor_dim)</div><div class='xr-var-dtype'>&lt;U1</div><div class='xr-var-preview xr-preview'>&#x27;0&#x27; &#x27;1&#x27; &#x27;2&#x27; &#x27;3&#x27; &#x27;4&#x27;</div><input id='attrs-6dea3372-5982-44b2-9fac-fa0a709b5585' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-6dea3372-5982-44b2-9fac-fa0a709b5585' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-3fe85664-55e7-4f76-8f83-397c62823826' class='xr-var-data-in' type='checkbox'><label for='data-3fe85664-55e7-4f76-8f83-397c62823826' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>array([&#x27;0&#x27;, &#x27;1&#x27;, &#x27;2&#x27;, &#x27;3&#x27;, &#x27;4&#x27;], dtype=&#x27;&lt;U1&#x27;)</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span class='xr-has-index'>rl_alpha_1|participant_id__factor_dim</span></div><div class='xr-var-dims'>(rl_alpha_1|participant_id__factor_dim)</div><div class='xr-var-dtype'>&lt;U1</div><div class='xr-var-preview xr-preview'>&#x27;0&#x27; &#x27;1&#x27; &#x27;2&#x27; &#x27;3&#x27; &#x27;4&#x27;</div><input id='attrs-9f37a20f-3af4-4aea-a4a7-c2d6d9636add' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-9f37a20f-3af4-4aea-a4a7-c2d6d9636add' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-ebd2f8d9-326f-4d20-b66b-3b5d77f6a882' class='xr-var-data-in' type='checkbox'><label for='data-ebd2f8d9-326f-4d20-b66b-3b5d77f6a882' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>array([&#x27;0&#x27;, &#x27;1&#x27;, &#x27;2&#x27;, &#x27;3&#x27;, &#x27;4&#x27;], dtype=&#x27;&lt;U1&#x27;)</pre></div></li></ul></div></li><li class='xr-section-item'><input id='section-cb766809-0590-4b0e-9b53-3ad57d3ce0cc' class='xr-section-summary-in' type='checkbox' /><label for='section-cb766809-0590-4b0e-9b53-3ad57d3ce0cc' class='xr-section-summary' title='Expand/collapse section'>Data variables: <span>(24)</span></label><div class='xr-section-inline-details'></div><div class='xr-section-details'><ul class='xr-var-list'><li class='xr-var-item'><div class='xr-var-name'><span>z_1|participant_id_offset</span></div><div class='xr-var-dims'>(chain, draw, participant_id__factor_dim)</div><div class='xr-var-dtype'>float32</div><div class='xr-var-preview xr-preview'>...</div><input id='attrs-1faf7fa3-56b9-4245-8c85-e96d72e3fb6e' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-1faf7fa3-56b9-4245-8c85-e96d72e3fb6e' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-ad8606ec-4baf-4087-8315-2a2dcaa39140' class='xr-var-data-in' type='checkbox'><label for='data-ad8606ec-4baf-4087-8315-2a2dcaa39140' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>Array([[[-0.37977803, -1.3202302 ,  0.99357563,  1.2452617 ,-0.96063745],[ 0.29738694, -0.36043775, -0.09967786,  0.9537308 ,-0.04068899],[ 0.20817943, -0.74547905,  0.12089647, -0.73478764,-0.20643847],...,[ 0.06152699,  0.12790847, -0.0311322 ,  0.007528  ,0.40625015],[-0.27289042, -0.48630723, -0.46683407, -0.02160617,-0.27687174],[ 0.14855248,  0.03735328, -0.28761744, -0.4117774 ,0.44747713]],[[ 0.459022  , -0.69009846,  0.2349177 ,  0.43148017,-0.12725346],[-0.2305573 , -0.75812167,  0.8415485 ,  0.14703952,-0.49016905],[-0.18346179, -0.9687703 ,  0.86490524, -0.26100773,-0.19201736],...,[ 1.5202386 , -0.9381562 , -1.3970687 , -1.1545174 ,-0.35185614],[ 1.0203205 , -0.63383865, -0.6122218 , -0.35593557,1.5102065 ],[ 0.29571873, -1.0704062 , -0.97366476, -0.8387281 ,0.9501065 ]]], dtype=float32)</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span>z_Intercept</span></div><div class='xr-var-dims'>(chain, draw)</div><div class='xr-var-dtype'>float32</div><div class='xr-var-preview xr-preview'>...</div><input id='attrs-01340046-fff9-488b-8ec9-0a1daa12444d' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-01340046-fff9-488b-8ec9-0a1daa12444d' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-06070167-663e-4c67-8fda-b03f1c26c047' class='xr-var-data-in' type='checkbox'><label for='data-06070167-663e-4c67-8fda-b03f1c26c047' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>Array([[0.43810156, 0.46288744, 0.44729123, 0.45391685, 0.44824877,0.47818336, 0.4491628 , 0.48833197, 0.46680626, 0.44796175,0.49705553, 0.44047597, 0.40736818, 0.4369636 , 0.52813184,0.45260948, 0.4639974 , 0.5043548 , 0.49714315, 0.46044195,0.45237204, 0.46286634, 0.47827375, 0.48243052, 0.45523348,0.47506616, 0.4417985 , 0.46910694, 0.4816084 , 0.5163118 ,0.4476718 , 0.46021476, 0.4804685 , 0.44545507, 0.45688593,0.47419128, 0.47262585, 0.4488729 , 0.47620028, 0.47956738,0.48468646, 0.46048534, 0.4807055 , 0.46126464, 0.44382495,0.46038976, 0.5063006 , 0.46753728, 0.46937254, 0.46442983,0.4786095 , 0.4327226 , 0.45326644, 0.47848183, 0.45342723,0.44081652, 0.45904118, 0.51334584, 0.49480584, 0.46788588,0.451869  , 0.47616223, 0.45944035, 0.4667494 , 0.5125132 ,0.45507005, 0.43462282, 0.41701815, 0.50169754, 0.47043464,0.43819973, 0.49664113, 0.5096987 , 0.5091189 , 0.5299184 ,0.60226333, 0.5789182 , 0.47559565, 0.5017734 , 0.4680516 ,0.45169032, 0.4943997 , 0.4729873 , 0.4980806 , 0.49876612,0.45165825, 0.42659461, 0.43338537, 0.44614878, 0.4349706 ,0.4424701 , 0.45540294, 0.4610213 , 0.44858086, 0.48006466,0.47851995, 0.46209776, 0.45665413, 0.44028294, 0.4490881 ,...0.5187649 , 0.45353866, 0.48912036, 0.44033894, 0.5060125 ,0.4597876 , 0.47743285, 0.51312786, 0.46577176, 0.47012648,0.45717204, 0.44630334, 0.4940574 , 0.45756724, 0.45762822,0.4597762 , 0.47555798, 0.47320604, 0.48181346, 0.4493194 ,0.48127472, 0.41511875, 0.4910433 , 0.4379605 , 0.4823554 ,0.4521853 , 0.46543276, 0.48972127, 0.468775  , 0.4406377 ,0.4256761 , 0.45245865, 0.47947335, 0.45194724, 0.4720495 ,0.42860445, 0.50623953, 0.47144273, 0.5083136 , 0.52316993,0.52316314, 0.4882317 , 0.44646323, 0.43935284, 0.45089057,0.44862008, 0.45973003, 0.43650502, 0.49331287, 0.5131802 ,0.53454965, 0.4045003 , 0.4930222 , 0.43029594, 0.46051088,0.45772412, 0.42591035, 0.44273937, 0.47896358, 0.47468936,0.46916077, 0.47341353, 0.4397351 , 0.44273388, 0.45895898,0.46435598, 0.4762592 , 0.47344095, 0.4690921 , 0.4528174 ,0.44089302, 0.49115288, 0.43923452, 0.48435104, 0.47371507,0.45536068, 0.44797638, 0.47240832, 0.45049715, 0.49826556,0.44557953, 0.4409158 , 0.43151632, 0.43992835, 0.5058638 ,0.4530669 , 0.47848144, 0.4684494 , 0.4726838 , 0.5123462 ,0.43523225, 0.4894514 , 0.49015474, 0.47721773, 0.47921914,0.44579637, 0.48978513, 0.46896696, 0.4428816 , 0.4634152 ]],      dtype=float32)</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span>scaler_1|participant_id_offset</span></div><div class='xr-var-dims'>(chain, draw, participant_id__factor_dim)</div><div class='xr-var-dtype'>float32</div><div class='xr-var-preview xr-preview'>...</div><input id='attrs-cf55672a-05da-41d7-b51d-f73fdbc921f2' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-cf55672a-05da-41d7-b51d-f73fdbc921f2' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-dd082812-24ef-4e8a-8961-2aa24726d982' class='xr-var-data-in' type='checkbox'><label for='data-dd082812-24ef-4e8a-8961-2aa24726d982' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>Array([[[-0.9537846 ,  0.71424687,  1.2582392 , -1.166728  ,-0.8019403 ],[-0.13598272,  0.42545968, -1.0588375 , -1.7518924 ,-0.20300576],[ 0.70126563,  1.7781789 ,  0.03423202, -1.2502952 ,2.1012952 ],...,[-0.6286079 ,  1.1691153 ,  0.33163664, -0.17816679,1.4159164 ],[-0.0182031 ,  0.13483706, -2.3213024 , -0.12893496,0.95835066],[ 0.22937673, -0.05597847, -2.2444768 , -0.7088203 ,0.65204895]],[[-1.5310904 ,  0.23064016, -0.5289061 ,  0.47817746,2.015074  ],[-0.42488685,  0.02927306, -0.40337285, -0.7104144 ,1.1158555 ],[-0.54081583,  0.14511298, -0.3898724 , -0.60666203,1.1581517 ],...,[-0.6559321 , -0.04831997,  0.0895692 , -1.2922366 ,-0.05792417],[-2.2017357 ,  0.9620459 ,  0.80016345, -0.89439005,1.6815922 ],[-1.927249  ,  0.13243762,  0.75082135, -0.9554217 ,1.7836976 ]]], dtype=float32)</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span>a_1|participant_id_offset</span></div><div class='xr-var-dims'>(chain, draw, participant_id__factor_dim)</div><div class='xr-var-dtype'>float32</div><div class='xr-var-preview xr-preview'>...</div><input id='attrs-f560bc08-da49-46fe-a825-33fb451e3286' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-f560bc08-da49-46fe-a825-33fb451e3286' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-cc9c2a57-d44c-425e-9c44-c6c48d2f2d28' class='xr-var-data-in' type='checkbox'><label for='data-cc9c2a57-d44c-425e-9c44-c6c48d2f2d28' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>Array([[[ 0.80176175, -0.09315851, -0.09444129,  1.8295711 ,0.77556884],[ 0.1934266 , -0.8159209 , -0.61145544,  1.7652677 ,0.32347506],[ 1.2752581 ,  0.46592703,  0.8170525 ,  1.2404062 ,1.7228385 ],...,[ 1.0206819 , -0.5481848 , -0.78312826,  0.10713051,-0.07759586],[-0.18818416,  0.43738905, -0.04730679,  1.3932551 ,0.1377107 ],[-0.6194624 ,  0.74891794,  0.24220978,  0.57498777,-0.10658807]],[[ 0.00428461, -0.62478256, -0.22838797,  0.1922633 ,1.1665165 ],[-0.05223541, -0.76193094, -0.4436986 ,  1.3225241 ,0.9495574 ],[-0.08977419, -0.78564876, -0.6068709 ,  1.102606  ,0.893325  ],...,[ 0.02544861,  0.987463  , -0.26977345,  1.7241178 ,0.9290584 ],[ 1.6277083 , -1.570625  ,  0.10294215,  0.8330429 ,0.43382525],[ 2.3311281 ,  0.4672795 ,  0.51288575,  1.4739922 ,0.29860765]]], dtype=float32)</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span>a_1|participant_id</span></div><div class='xr-var-dims'>(chain, draw, participant_id__factor_dim)</div><div class='xr-var-dtype'>float32</div><div class='xr-var-preview xr-preview'>...</div><input id='attrs-89d6a2f9-989e-418c-afb9-32156789049a' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-89d6a2f9-989e-418c-afb9-32156789049a' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-21b76dd2-fc47-40c3-80aa-3018aa8dc744' class='xr-var-data-in' type='checkbox'><label for='data-21b76dd2-fc47-40c3-80aa-3018aa8dc744' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>Array([[[ 0.2539387 , -0.02950571, -0.029912  ,  0.57947254,0.24564272],[ 0.04287091, -0.18084003, -0.13552247,  0.3912525 ,0.07169475],[ 0.36668763,  0.13397263,  0.23493521,  0.3566663 ,0.49538487],...,[ 0.34059027, -0.18292323, -0.26132128,  0.03574827,-0.02589288],[-0.05054246,  0.11747384, -0.01270565,  0.3742001 ,0.03698631],[-0.18555279,  0.22432971,  0.07255114,  0.17223093,-0.03192722]],[[ 0.00120715, -0.17602736, -0.06434643,  0.05416861,0.32865646],[-0.00756251, -0.11031047, -0.06423758,  0.19147174,0.13747455],[-0.01419216, -0.1242011 , -0.09593859,  0.17430803,0.14122334],...,[ 0.00317333,  0.1231323 , -0.03363957,  0.21498992,0.1158495 ],[ 0.15103416, -0.14573742,  0.00955195,  0.07729759,0.04025441],[ 0.3154992 ,  0.06324247,  0.06941491,  0.19949284,0.04041411]]], dtype=float32)</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span>t_1|participant_id_sigma</span></div><div class='xr-var-dims'>(chain, draw)</div><div class='xr-var-dtype'>float32</div><div class='xr-var-preview xr-preview'>...</div><input id='attrs-56433f0c-dcec-4acc-8827-a71f24fb8277' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-56433f0c-dcec-4acc-8827-a71f24fb8277' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-82914c68-38a6-4e68-8ad8-74367ce32704' class='xr-var-data-in' type='checkbox'><label for='data-82914c68-38a6-4e68-8ad8-74367ce32704' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>Array([[0.12788008, 0.09341314, 0.05869246, 0.10256022, 0.06010016,0.08222742, 0.14723861, 0.07347839, 0.14034072, 0.16463992,0.15046939, 0.10648254, 0.08302601, 0.15116726, 0.08852948,0.1739183 , 0.24462095, 0.14790119, 0.11227888, 0.09697863,0.12197539, 0.11465808, 0.13818936, 0.12886398, 0.09493202,0.33242834, 0.2255025 , 0.3126432 , 0.13817471, 0.1858792 ,0.06400914, 0.02898081, 0.0893888 , 0.13766381, 0.08857754,0.10303491, 0.05351119, 0.09065001, 0.02801558, 0.16311254,0.11045462, 0.12909462, 0.13340262, 0.08024183, 0.08731534,0.18741573, 0.19212604, 0.08633804, 0.21675098, 0.17542163,0.08995312, 0.06680594, 0.0724714 , 0.08985491, 0.07981052,0.07884666, 0.06912588, 0.07370168, 0.04694597, 0.04503932,0.08291916, 0.03870035, 0.07041407, 0.10311731, 0.27456862,0.07137986, 0.14962116, 0.12153555, 0.0419328 , 0.0595799 ,0.09629194, 0.0885628 , 0.09284765, 0.07424884, 0.07320907,0.06975651, 0.10072807, 0.03361692, 0.09813707, 0.07497881,0.1327513 , 0.126004  , 0.05130585, 0.11080284, 0.11504409,0.27364206, 0.16983533, 0.1235625 , 0.15829858, 0.08799049,0.04881898, 0.09782569, 0.20351562, 0.07057028, 0.08074385,0.07928611, 0.02924014, 0.02667093, 0.12533674, 0.02096564,...0.1319809 , 0.08602383, 0.24537212, 0.15951015, 0.06689127,0.14933436, 0.1382248 , 0.20401902, 0.1652324 , 0.19791663,0.15605325, 0.17547747, 0.10911676, 0.09735014, 0.08885829,0.07951523, 0.06826244, 0.10895309, 0.10594258, 0.05488332,0.05389532, 0.07328603, 0.03665099, 0.0524198 , 0.05232774,0.17334928, 0.19309829, 0.13698177, 0.08573239, 0.20355187,0.08561804, 0.10401478, 0.09066393, 0.1367881 , 0.15084012,0.0575625 , 0.06778014, 0.09334384, 0.13573836, 0.19616705,0.13987918, 0.13503364, 0.2404774 , 0.2690716 , 0.16764826,0.15184954, 0.14632899, 0.16276132, 0.14960486, 0.16636959,0.08192588, 0.13629693, 0.09055514, 0.08745189, 0.08129072,0.04278309, 0.04369488, 0.07500413, 0.12328439, 0.10795602,0.08843067, 0.07670043, 0.10128093, 0.10493976, 0.0870667 ,0.17598268, 0.06999016, 0.08625915, 0.09079   , 0.12901421,0.16924977, 0.16395816, 0.09120461, 0.18024778, 0.18761641,0.09198964, 0.1076943 , 0.12668736, 0.17759433, 0.10154702,0.03460439, 0.05878941, 0.06746382, 0.03967378, 0.08786997,0.02957597, 0.05918913, 0.05975368, 0.08176623, 0.09841913,0.16124691, 0.07855923, 0.0859447 , 0.09068227, 0.08346801,0.1083205 , 0.11274652, 0.21991411, 0.14502606, 0.1380404 ]],      dtype=float32)</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span>rl_alpha_1|participant_id_sigma</span></div><div class='xr-var-dims'>(chain, draw)</div><div class='xr-var-dtype'>float32</div><div class='xr-var-preview xr-preview'>...</div><input id='attrs-dcb63b52-463c-4383-bed4-9aa38ff2e5e5' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-dcb63b52-463c-4383-bed4-9aa38ff2e5e5' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-ed4bfa60-83ff-48e0-8f74-6a2fb3edf644' class='xr-var-data-in' type='checkbox'><label for='data-ed4bfa60-83ff-48e0-8f74-6a2fb3edf644' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>Array([[0.05052387, 0.0466326 , 0.01614147, 0.02898645, 0.03661774,0.02293684, 0.1420353 , 0.08122816, 0.01099153, 0.09243751,0.02176466, 0.11019109, 0.0438143 , 0.12296413, 0.00233299,0.1621094 , 0.16392156, 0.1055137 , 0.02535889, 0.05321867,0.07798212, 0.05655218, 0.02936044, 0.02421069, 0.03513669,0.04313827, 0.0754796 , 0.04016946, 0.01415837, 0.02721165,0.06341492, 0.13218026, 0.06278453, 0.08169598, 0.26004982,0.05431394, 0.04953069, 0.14423975, 0.08870009, 0.01647978,0.37209916, 0.01284611, 0.03055242, 0.06814249, 0.01996166,0.0333503 , 0.06630474, 0.05046037, 0.09745474, 0.05132292,0.10654631, 0.02383076, 0.04734759, 0.00682122, 0.00243572,0.00521409, 0.00587166, 0.08678462, 0.03161705, 0.04053465,0.09515801, 0.05154289, 0.02809209, 0.09743488, 0.00109092,0.0140544 , 0.10374082, 0.01948201, 0.10707416, 0.00383861,0.03807306, 0.09821733, 0.09002472, 0.07653557, 0.11545821,0.02088409, 0.08826473, 0.04517298, 0.03484462, 0.01524814,0.17889784, 0.00995813, 0.00606585, 0.00568568, 0.00229268,0.17551577, 0.11446287, 0.06559785, 0.14980412, 0.0251419 ,0.1032865 , 0.05204219, 0.1146855 , 0.03984366, 0.01046544,0.03206197, 0.02072228, 0.01943356, 0.00470368, 0.04573767,...0.07739387, 0.03004229, 0.17644584, 0.07432311, 0.07355759,0.00933311, 0.06226192, 0.00382108, 0.00623739, 0.03880155,0.00665353, 0.00620803, 0.00824256, 0.07214707, 0.03520095,0.12511335, 0.04285406, 0.0426644 , 0.06446527, 0.00988952,0.0357022 , 0.05853231, 0.03722038, 0.06594308, 0.02655746,0.01364536, 0.00824673, 0.0151094 , 0.01874005, 0.11234374,0.04386818, 0.0565354 , 0.07800592, 0.09487747, 0.04902403,0.05063468, 0.00285143, 0.00197309, 0.00344597, 0.01112833,0.01503352, 0.07088196, 0.05817474, 0.06597655, 0.02912555,0.03899373, 0.06349318, 0.05927014, 0.01373596, 0.01310365,0.02427816, 0.09890667, 0.06647529, 0.09665059, 0.111535  ,0.12698005, 0.1034904 , 0.05653459, 0.12507668, 0.08197233,0.04457568, 0.03855666, 0.09262034, 0.05714597, 0.16188642,0.14832228, 0.0579811 , 0.19891614, 0.01148802, 0.04959942,0.0457175 , 0.10939825, 0.11820649, 0.06631077, 0.07796591,0.1580621 , 0.01400556, 0.03410701, 0.02141508, 0.09413311,0.0160496 , 0.05914617, 0.03285921, 0.01368214, 0.05129209,0.00459732, 0.05580157, 0.04559195, 0.03554327, 0.06479176,0.05207197, 0.0601352 , 0.00407353, 0.02430042, 0.02142423,0.04488905, 0.11496425, 0.09634972, 0.35269666, 0.12958983]],      dtype=float32)</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span>rl_alpha_1|participant_id</span></div><div class='xr-var-dims'>(chain, draw, rl_alpha_1|participant_id__factor_dim)</div><div class='xr-var-dtype'>float32</div><div class='xr-var-preview xr-preview'>...</div><input id='attrs-c05fa075-dc46-41ca-9b02-a3e88f8816c7' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-c05fa075-dc46-41ca-9b02-a3e88f8816c7' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-a04accdd-80c1-43c7-8b89-3d3ba9745b95' class='xr-var-data-in' type='checkbox'><label for='data-a04accdd-80c1-43c7-8b89-3d3ba9745b95' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>Array([[[-0.07368127, -0.0092661 , -0.08930462, -0.04006366,0.01713065],[-0.04588036,  0.00617258, -0.01728664, -0.02436249,0.0336735 ],[ 0.01349712, -0.00041384,  0.00341723,  0.0157566 ,-0.00520289],...,[-0.00499554,  0.02323106, -0.04963632, -0.02636934,0.01991412],[-0.03239445,  0.02539502, -0.01446751, -0.08386853,0.02586374],[-0.04655728,  0.02318785,  0.01029579, -0.07023574,0.03077258]],[[ 0.04138274,  0.05603775, -0.00385761,  0.00719279,0.0819814 ],[ 0.01284022,  0.01884353,  0.01216657,  0.00880447,0.07059301],[ 0.00128598,  0.01660207,  0.00809954,  0.01382836,0.06592489],...,[ 0.09260341,  0.11456588,  0.04916794,  0.00680655,0.16000512],[ 0.12627453,  0.25525424,  0.01943824,  0.04143095,0.2244754 ],[ 0.08330165,  0.05728068,  0.02608114,  0.06805027,0.16756442]]], dtype=float32)</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span>theta_1|participant_id_sigma</span></div><div class='xr-var-dims'>(chain, draw)</div><div class='xr-var-dtype'>float32</div><div class='xr-var-preview xr-preview'>...</div><input id='attrs-74b2f2b7-8dd9-4b01-a772-2dfb52b04af9' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-74b2f2b7-8dd9-4b01-a772-2dfb52b04af9' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-353771f2-5e9c-4308-b9a9-ef468bc62cce' class='xr-var-data-in' type='checkbox'><label for='data-353771f2-5e9c-4308-b9a9-ef468bc62cce' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>Array([[1.18425237e-02, 4.52438146e-02, 5.33243902e-02, 3.40816341e-02,1.62465144e-02, 3.53252590e-02, 3.07731871e-02, 2.03333814e-02,3.11487168e-02, 7.39125609e-02, 8.73818994e-02, 1.23761572e-01,9.66661200e-02, 6.30611032e-02, 5.98968007e-03, 6.74801916e-02,4.42665592e-02, 2.64324844e-02, 2.84834970e-02, 5.58706783e-02,4.89298739e-02, 7.50835687e-02, 2.57473797e-01, 2.90921688e-01,7.69688888e-03, 5.53777404e-02, 5.05244359e-02, 7.90527742e-03,2.71408595e-02, 2.80832816e-02, 1.41754031e-01, 4.46193703e-02,1.03911303e-01, 9.16050049e-04, 1.14330312e-03, 2.44882831e-04,4.19494289e-04, 5.11225872e-03, 1.26035750e-01, 1.70340370e-02,6.30455911e-02, 8.83957669e-02, 7.89393187e-02, 4.86348085e-02,1.77184176e-02, 3.45989615e-02, 1.61673903e-01, 1.03413396e-01,7.28579462e-02, 6.54791370e-02, 9.01644677e-03, 3.05160750e-02,4.78065237e-02, 4.76034917e-02, 6.39392659e-02, 6.02147877e-02,4.25535217e-02, 1.88466579e-01, 2.01962050e-02, 1.63127780e-02,3.58021632e-02, 6.99456781e-02, 6.95798621e-02, 1.37094051e-01,6.57000840e-02, 2.93962583e-02, 6.41440898e-02, 6.15396835e-02,6.17828965e-03, 3.85482199e-02, 1.03886008e-01, 1.80604279e-01,1.43467590e-01, 1.97661296e-01, 2.22127605e-02, 1.70477945e-02,3.07503622e-02, 8.96943584e-02, 7.12721646e-02, 3.40516493e-02,...7.45423080e-04, 3.41218151e-02, 1.54531732e-01, 7.84808844e-02,1.88108180e-02, 3.59522477e-02, 1.21591605e-01, 1.52945101e-01,1.42223085e-03, 4.58281010e-01, 5.16790040e-02, 5.46567142e-02,8.43761116e-02, 7.87694380e-02, 1.00940950e-02, 1.08822271e-01,9.33273882e-02, 9.50257704e-02, 1.04170121e-01, 8.40816349e-02,7.05734789e-02, 5.88369966e-02, 7.96858668e-02, 9.97508466e-02,4.98882309e-02, 6.21972568e-02, 1.24955542e-01, 4.34508212e-02,5.84715195e-02, 1.04335286e-01, 6.86707795e-02, 1.15498379e-02,1.26117513e-01, 6.77583069e-02, 7.21892416e-02, 1.37475412e-02,1.30402043e-01, 1.07309431e-01, 1.05952434e-01, 7.65537843e-02,1.44930288e-01, 1.42422482e-01, 2.03539178e-01, 2.16979161e-01,1.08322755e-01, 1.30914692e-02, 2.83600055e-02, 8.44430029e-02,5.37691638e-02, 5.68959355e-01, 4.05440331e-01, 4.90408003e-01,5.90523370e-02, 1.02992810e-01, 1.15348622e-01, 4.14019004e-02,8.77699554e-02, 3.10697407e-02, 5.39648607e-02, 9.05185938e-02,2.66005937e-02, 2.68101250e-03, 1.31020672e-03, 7.24495272e-04,3.35424729e-02, 2.21541570e-03, 6.40414190e-03, 2.35637184e-02,5.90652339e-02, 1.47980098e-02, 6.96192086e-02, 2.98805814e-02,3.73423845e-02, 4.50966433e-02, 6.98166117e-02, 1.14630330e-02,1.37209088e-01, 5.48750944e-02, 2.64885545e-01, 1.89478055e-01]],      dtype=float32)</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span>a_1|participant_id_sigma</span></div><div class='xr-var-dims'>(chain, draw)</div><div class='xr-var-dtype'>float32</div><div class='xr-var-preview xr-preview'>...</div><input id='attrs-5115affc-a67e-4cdc-a09e-96b190d92b1f' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-5115affc-a67e-4cdc-a09e-96b190d92b1f' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-04fc9ab2-fb81-40ff-806c-cdb477654a1e' class='xr-var-data-in' type='checkbox'><label for='data-04fc9ab2-fb81-40ff-806c-cdb477654a1e' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>Array([[3.16725880e-01, 2.21639171e-01, 2.87539929e-01, 2.22846717e-01,2.46216312e-01, 1.95337325e-01, 1.72868580e-01, 1.98697299e-01,2.11782485e-01, 1.32234007e-01, 4.52544093e-01, 1.02116205e-01,2.99050212e-02, 1.00306548e-01, 7.58148551e-01, 2.22490653e-01,2.05303848e-01, 1.71804160e-01, 1.62673801e-01, 2.34092683e-01,1.00418366e-01, 4.09094930e-01, 3.31456989e-01, 3.15080374e-01,2.26549029e-01, 1.76101342e-01, 2.39336982e-01, 2.00386107e-01,2.12680995e-01, 3.52493435e-01, 2.35318497e-01, 3.62701982e-01,1.21054024e-01, 2.76855081e-01, 2.44839370e-01, 2.24151850e-01,2.93392360e-01, 1.96828425e-01, 1.64144397e-01, 1.82724625e-01,5.42932928e-01, 2.56969035e-01, 1.81647062e-01, 2.29855016e-01,1.35605991e-01, 8.72152895e-02, 4.01543915e-01, 2.41950512e-01,3.97168338e-01, 8.28934550e-01, 1.80615425e-01, 3.91743422e-01,4.23705041e-01, 2.33606815e-01, 2.18727380e-01, 3.59563410e-01,2.08027512e-01, 2.39172041e-01, 1.12204671e-01, 1.31758526e-01,3.22561376e-02, 1.49605960e-01, 2.13525817e-01, 2.28217870e-01,2.12676451e-01, 4.94154751e-01, 2.31465757e-01, 1.59658164e-01,1.91992521e-01, 1.24569505e-01, 4.60433990e-01, 2.17636526e-01,2.11909488e-01, 1.75582141e-01, 1.29796594e-01, 2.53370553e-01,3.54080439e-01, 2.90962160e-01, 2.28021473e-01, 2.73782939e-01,...3.80718291e-01, 3.31404567e-01, 4.86356795e-01, 5.50066710e-01,5.24289012e-01, 1.97699547e-01, 2.44645685e-01, 1.55488700e-01,5.11734366e-01, 2.28304774e-01, 1.82797641e-01, 1.12066932e-01,8.86270925e-02, 1.20074861e-01, 1.70748830e-01, 2.39450470e-01,1.70258284e-01, 1.67739421e-01, 1.64864168e-01, 1.36960462e-01,1.21939950e-01, 1.76436573e-01, 1.23987593e-01, 2.03384504e-01,2.35099733e-01, 2.41826057e-01, 4.61380601e-01, 4.63426948e-01,4.69807148e-01, 4.89432395e-01, 1.34712398e-01, 1.33159682e-01,3.90140682e-01, 1.98648289e-01, 1.64358944e-01, 2.56672591e-01,2.80783832e-01, 3.28194737e-01, 1.84304446e-01, 1.53424546e-01,1.29448682e-01, 1.26480818e-01, 5.54029234e-02, 9.95934159e-02,3.73568907e-02, 1.41826317e-01, 3.41472685e-01, 1.27942026e-01,3.55583668e-01, 3.55725110e-01, 2.93304503e-01, 3.22728813e-01,2.48056874e-01, 1.64984584e-01, 1.60378665e-01, 1.80157632e-01,2.10404515e-01, 3.41011584e-01, 1.77142918e-01, 1.26531616e-01,2.20022798e-01, 1.25885263e-01, 9.03150588e-02, 1.24015741e-01,1.35752618e-01, 3.00116301e-01, 2.97587335e-01, 1.19703390e-01,2.12765232e-01, 1.88280270e-01, 1.15718469e-01, 4.32706654e-01,1.15774021e-01, 8.99049714e-02, 1.10525616e-01, 2.35626906e-01,1.19963154e-01, 1.24695614e-01, 9.27894488e-02, 1.35341853e-01]],      dtype=float32)</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span>rl_alpha_Intercept</span></div><div class='xr-var-dims'>(chain, draw)</div><div class='xr-var-dtype'>float32</div><div class='xr-var-preview xr-preview'>...</div><input id='attrs-9f9b7bd1-e0c7-499c-895a-862eccf3c90e' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-9f9b7bd1-e0c7-499c-895a-862eccf3c90e' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-7417096c-65a0-4869-8e4f-1d94612b6a06' class='xr-var-data-in' type='checkbox'><label for='data-7417096c-65a0-4869-8e4f-1d94612b6a06' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>Array([[0.10286471, 0.08943062, 0.17955568, 0.15803216, 0.09911661,0.09295113, 0.10459666, 0.12686218, 0.12271165, 0.1916655 ,0.07884016, 0.16994469, 0.09388227, 0.10022449, 0.13731842,0.14035033, 0.16150372, 0.11766913, 0.11813252, 0.20438695,0.07599349, 0.21820042, 0.10063174, 0.1113665 , 0.08885348,0.07400026, 0.14469089, 0.12468687, 0.07154821, 0.18985786,0.09603208, 0.18315087, 0.14641514, 0.18811072, 0.31076062,0.1582401 , 0.18274872, 0.11416489, 0.14672132, 0.12285025,0.23739207, 0.15984508, 0.14678505, 0.14472416, 0.18341589,0.07093124, 0.12036532, 0.1452096 , 0.10967501, 0.05979099,0.06401648, 0.10210407, 0.11201061, 0.10726789, 0.1083173 ,0.1603242 , 0.19094937, 0.13683958, 0.13569312, 0.13227421,0.23600225, 0.09033255, 0.149067  , 0.13987267, 0.1920385 ,0.09075785, 0.2246392 , 0.13008827, 0.12839797, 0.12810865,0.1324735 , 0.19814894, 0.16928723, 0.1524229 , 0.16653065,0.11154612, 0.14256537, 0.11694307, 0.10768316, 0.15448757,0.17091852, 0.10705014, 0.10158286, 0.10499701, 0.11052303,0.21236806, 0.21771759, 0.32988632, 0.25447348, 0.16204837,0.12832208, 0.19650869, 0.13445438, 0.1259552 , 0.10271408,0.10547788, 0.16376194, 0.2041537 , 0.07054333, 0.1858308 ,...0.0188295 , 0.08483931, 0.16657603, 0.09742755, 0.19028284,0.09643128, 0.20265806, 0.09522405, 0.15089926, 0.13826077,0.14184938, 0.08600599, 0.1596359 , 0.20640606, 0.12878728,0.2769342 , 0.18326396, 0.14135608, 0.16724208, 0.11184826,0.12775132, 0.06442712, 0.14894687, 0.0893064 , 0.18114522,0.09217267, 0.13491227, 0.20027678, 0.12041173, 0.23339854,0.07730527, 0.14581738, 0.1858225 , 0.13429655, 0.12855378,0.23167253, 0.14268456, 0.12868054, 0.21519737, 0.07092083,0.0826511 , 0.17038867, 0.14341204, 0.16522148, 0.14762685,0.1345524 , 0.11852027, 0.15288097, 0.16691406, 0.18458663,0.08065777, 0.2117209 , 0.08449227, 0.18175459, 0.13922128,0.04083288, 0.07332   , 0.14281173, 0.03094278, 0.07096547,0.06665525, 0.1040766 , 0.03227734, 0.119567  , 0.10854691,0.09268203, 0.05791797, 0.27437654, 0.07446611, 0.10803057,0.11145823, 0.11100204, 0.09678085, 0.19946954, 0.20586564,0.16202287, 0.08150366, 0.25390908, 0.06168228, 0.26890856,0.06216256, 0.0958118 , 0.08395097, 0.04955864, 0.1295751 ,0.10990467, 0.17193767, 0.15092869, 0.13686249, 0.0781922 ,0.11807739, 0.18802452, 0.18511735, 0.058472  , 0.12454028,0.11713913, 0.05019283, 0.03157109, 0.01572806, 0.01208059]],      dtype=float32)</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span>theta_1|participant_id</span></div><div class='xr-var-dims'>(chain, draw, participant_id__factor_dim)</div><div class='xr-var-dtype'>float32</div><div class='xr-var-preview xr-preview'>...</div><input id='attrs-0cf69fdc-0d03-4db9-b6b1-c3a195e1ceb8' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-0cf69fdc-0d03-4db9-b6b1-c3a195e1ceb8' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-78c28180-421c-45c2-8ab4-f9a7431427ca' class='xr-var-data-in' type='checkbox'><label for='data-78c28180-421c-45c2-8ab4-f9a7431427ca' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>Array([[[-0.00108018, -0.00628014,  0.02013353, -0.00280711,-0.0017745 ],[ 0.01060137, -0.05309435, -0.06538451,  0.01214662,-0.03822519],[ 0.0321813 ,  0.05205196,  0.05391201, -0.02553851,0.03732627],...,[ 0.15937023, -0.02330265, -0.00944153, -0.11442047,-0.14221646],[-0.10126524,  0.08959548,  0.02413245, -0.04776207,-0.06359125],[-0.29332078,  0.08570864,  0.05178185, -0.12243122,-0.21775396]],[[-0.00340325, -0.01512029,  0.00498261, -0.05906741,-0.04535825],[-0.00054402, -0.03013075,  0.06588393, -0.10584361,-0.06482182],[ 0.00455833, -0.01927897,  0.07432349, -0.10439105,-0.06958108],...,[-0.04171532,  0.05226523,  0.01869536, -0.09216685,-0.08411029],[ 0.09289408, -0.15556468,  0.11323419, -0.18161625,0.04278227],[ 0.03663884,  0.04928331,  0.01287864, -0.11660655,-0.14774829]]], dtype=float32)</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span>theta_1|participant_id_offset</span></div><div class='xr-var-dims'>(chain, draw, participant_id__factor_dim)</div><div class='xr-var-dtype'>float32</div><div class='xr-var-preview xr-preview'>...</div><input id='attrs-1103ec43-979f-4fe7-91ae-c252171262ed' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-1103ec43-979f-4fe7-91ae-c252171262ed' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-4d55357a-262a-41e7-96a5-1ef4cfced49f' class='xr-var-data-in' type='checkbox'><label for='data-4d55357a-262a-41e7-96a5-1ef4cfced49f' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>Array([[[-0.09121197, -0.5303043 ,  1.7001044 , -0.23703678,-0.14984101],[ 0.23431647, -1.1735163 , -1.445159  ,  0.26847032,-0.844871  ],[ 0.6035006 ,  0.97613794,  1.0110197 , -0.47892743,0.69998485],...,[ 1.9560264 , -0.28600448, -0.11588039, -1.4043366 ,-1.74549   ],[-1.0060678 ,  0.890129  ,  0.23975532, -0.47451502,-0.6317776 ],[-1.975827  ,  0.57733876,  0.34880576, -0.82470435,-1.4668043 ]],[[-0.07040395, -0.31279707,  0.10307641, -1.2219417 ,-0.93833715],[-0.00589807, -0.3266654 ,  0.714287  , -1.1475136 ,-0.70277196],[ 0.052303  , -0.22121015,  0.8528002 , -1.1978005 ,-0.798385  ],...,[-0.76018685,  0.9524399 ,  0.3406894 , -1.6795752 ,-1.532759  ],[ 0.35069516, -0.58729017,  0.42748347, -0.68564045,0.16151229],[ 0.19336723,  0.26010036,  0.06796905, -0.61540926,-0.77976465]]], dtype=float32)</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span>theta_Intercept</span></div><div class='xr-var-dims'>(chain, draw)</div><div class='xr-var-dtype'>float32</div><div class='xr-var-preview xr-preview'>...</div><input id='attrs-8fb2fd65-7142-4e1b-b18f-fcda66cd2d1a' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-8fb2fd65-7142-4e1b-b18f-fcda66cd2d1a' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-4f050a30-4a04-4d41-a1d2-6cb43e6a92a0' class='xr-var-data-in' type='checkbox'><label for='data-4f050a30-4a04-4d41-a1d2-6cb43e6a92a0' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>Array([[0.45228416, 0.3721391 , 0.3536712 , 0.35287076, 0.33873868,0.35310993, 0.35577142, 0.33922622, 0.3426378 , 0.34885073,0.32409346, 0.36548293, 0.32934844, 0.34720978, 0.37085462,0.32788894, 0.37552935, 0.36861432, 0.3529239 , 0.4328839 ,0.3045775 , 0.4304789 , 0.50509393, 0.50183326, 0.3265922 ,0.33703768, 0.37476584, 0.30405128, 0.32725686, 0.3152092 ,0.4226447 , 0.37423137, 0.3728307 , 0.32494652, 0.34181947,0.35314795, 0.34970987, 0.31957716, 0.446829  , 0.35243025,0.44711396, 0.43235692, 0.3686926 , 0.33730164, 0.3893823 ,0.32816353, 0.25911736, 0.42515007, 0.33986694, 0.28239244,0.3651129 , 0.3529784 , 0.38247994, 0.45085973, 0.4059873 ,0.41067737, 0.393882  , 0.39416578, 0.32494524, 0.33058792,0.26102978, 0.34711263, 0.34274918, 0.40402323, 0.42387283,0.4391066 , 0.33964986, 0.30432534, 0.36290064, 0.33459115,0.4113082 , 0.34495488, 0.31951544, 0.30961248, 0.35546955,0.30171335, 0.4167938 , 0.37202913, 0.31025916, 0.3464192 ,0.27823117, 0.36579123, 0.35730237, 0.33584243, 0.32531607,0.38564804, 0.38342583, 0.27930662, 0.29981333, 0.33538717,0.32312748, 0.2916599 , 0.34699702, 0.33016443, 0.35075513,0.36518794, 0.29755273, 0.33692673, 0.39402378, 0.25506654,...0.33430472, 0.35423732, 0.3555208 , 0.4128714 , 0.38591662,0.38619995, 0.34499106, 0.35330814, 0.3957642 , 0.37799767,0.338541  , 0.34637952, 0.37260702, 0.267146  , 0.31983387,0.36471045, 0.43652892, 0.36015534, 0.36098957, 0.3239712 ,0.3841401 , 0.3274624 , 0.31669208, 0.42800346, 0.36098087,0.28824443, 0.31186667, 0.30272606, 0.353428  , 0.39189354,0.34567145, 0.32116437, 0.31167054, 0.3129508 , 0.37336347,0.31319988, 0.39308235, 0.39498392, 0.3816271 , 0.3050298 ,0.32106388, 0.2669167 , 0.41006637, 0.4667163 , 0.38344854,0.37696075, 0.26066437, 0.2924582 , 0.31851846, 0.29127046,0.35132825, 0.36552262, 0.38938266, 0.36622837, 0.3629257 ,0.34096867, 0.40084034, 0.41146883, 0.32172534, 0.40509486,0.40027276, 0.3508193 , 0.28873256, 0.35332644, 0.30482316,0.29915345, 0.37714294, 0.35313547, 0.47344336, 0.61988705,0.562859  , 0.61072844, 0.2726314 , 0.29526022, 0.29926032,0.29150608, 0.45306993, 0.29807234, 0.30812216, 0.27409393,0.36934087, 0.28669873, 0.2947067 , 0.36914438, 0.32046103,0.3784456 , 0.35312542, 0.3671639 , 0.45914024, 0.3870232 ,0.30736005, 0.44231108, 0.26440662, 0.27095717, 0.27826783,0.39750332, 0.32481682, 0.4026697 , 0.36318985, 0.36258382]],      dtype=float32)</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span>z_1|participant_id</span></div><div class='xr-var-dims'>(chain, draw, participant_id__factor_dim)</div><div class='xr-var-dtype'>float32</div><div class='xr-var-preview xr-preview'>...</div><input id='attrs-0e507dfd-b7e7-45dc-83f2-d27bf10c39d5' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-0e507dfd-b7e7-45dc-83f2-d27bf10c39d5' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-0c3a690a-e0fb-4197-a009-1dd4b9104c3f' class='xr-var-data-in' type='checkbox'><label for='data-0c3a690a-e0fb-4197-a009-1dd4b9104c3f' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>Array([[[-0.00152762, -0.00531048,  0.00399655,  0.00500893,-0.00386406],[ 0.00856414, -0.01037987, -0.00287052,  0.0274655 ,-0.00117176],[ 0.01648933, -0.05904736,  0.00957588, -0.05820052,-0.01635143],...,[ 0.0145725 ,  0.03029477, -0.00737358,  0.00178299,0.09621923],[-0.03816704, -0.06801599, -0.06529243, -0.00302189,-0.03872388],[ 0.02085033,  0.00524278, -0.04036902, -0.0577957 ,0.0628064 ]],[[ 0.03624653, -0.05449342,  0.0185502 ,  0.0340717 ,-0.01004853],[-0.00615751, -0.02024721,  0.0224753 ,  0.003927  ,-0.01309098],[-0.00512219, -0.02704774,  0.02414786, -0.00728725,-0.00536106],...,[ 0.01347608, -0.00831624, -0.01238425, -0.01023416,-0.00311901],[ 0.02446388, -0.01519733, -0.01467903, -0.00853415,0.0362097 ],[ 0.00706859, -0.02558602, -0.0232736 , -0.0200482 ,0.02271049]]], dtype=float32)</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span>a_Intercept</span></div><div class='xr-var-dims'>(chain, draw)</div><div class='xr-var-dtype'>float32</div><div class='xr-var-preview xr-preview'>...</div><input id='attrs-f2e51d43-5607-4b61-877c-7de92ef3afc2' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-f2e51d43-5607-4b61-877c-7de92ef3afc2' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-9b9c2d04-86a2-4aa4-832a-06c31f39006c' class='xr-var-data-in' type='checkbox'><label for='data-9b9c2d04-86a2-4aa4-832a-06c31f39006c' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>Array([[1.2684795 , 1.1991737 , 1.0729709 , 1.2488648 , 1.3389387 ,1.3918418 , 1.3362055 , 1.2444584 , 1.442184  , 1.3823261 ,1.3351955 , 1.200638  , 1.4366233 , 1.4238447 , 0.9671915 ,1.312595  , 1.3228288 , 1.4207268 , 1.3657233 , 1.3942413 ,1.3556252 , 1.2474568 , 0.95826834, 0.9713737 , 1.4608092 ,1.3343239 , 1.4897931 , 1.2164427 , 1.4206996 , 1.1842182 ,1.4668261 , 1.3606008 , 1.2877779 , 1.224715  , 1.2427652 ,1.2280475 , 1.3640418 , 1.2213793 , 1.4441583 , 1.3856096 ,1.355159  , 1.2137827 , 1.259018  , 1.4477049 , 1.3500743 ,1.2605615 , 1.3618308 , 1.4617825 , 1.1676052 , 0.9883976 ,1.1525701 , 1.2653346 , 1.2914594 , 1.4824603 , 1.3643179 ,1.3465466 , 1.3250558 , 1.3180401 , 1.2619693 , 1.2239132 ,1.2179544 , 1.3579661 , 1.311511  , 1.2277414 , 1.2076542 ,1.2422364 , 1.3891518 , 1.2159711 , 1.3345889 , 1.2452211 ,1.2429273 , 1.342675  , 1.4433756 , 1.4338367 , 1.3353238 ,1.2717611 , 1.2858913 , 1.418583  , 1.2045562 , 1.3998003 ,1.3214786 , 1.2111099 , 1.0366833 , 1.2018243 , 1.1990852 ,1.4218459 , 1.3604691 , 1.3180386 , 1.3878117 , 1.3803445 ,1.2660058 , 1.3165579 , 1.1985507 , 1.4630711 , 1.36143   ,1.2611161 , 1.2728775 , 1.1964376 , 1.3443307 , 1.339146  ,...1.1836145 , 1.1669254 , 1.2035089 , 1.4056509 , 1.1418431 ,0.8966577 , 0.891963  , 0.6152448 , 0.79655534, 0.7717408 ,1.1869099 , 1.202139  , 1.2955405 , 1.3649056 , 1.3104969 ,1.4641398 , 1.7085506 , 1.4805152 , 1.4331217 , 1.399699  ,1.3862162 , 1.1981647 , 1.1234413 , 1.4124444 , 1.2963744 ,1.2378123 , 1.2659993 , 1.2038934 , 1.3934321 , 1.6203713 ,1.3256226 , 1.2392617 , 1.2884889 , 1.202986  , 1.3743131 ,1.3255638 , 1.2302959 , 1.3092724 , 1.2134355 , 1.2935948 ,1.2994295 , 1.2765911 , 1.2814418 , 1.3545353 , 1.2349279 ,1.0951904 , 1.0391138 , 1.0005822 , 1.0176148 , 1.0688428 ,1.35657   , 1.2135618 , 1.4219955 , 1.3225292 , 1.2785586 ,1.275194  , 1.3355274 , 1.3949927 , 1.2883465 , 1.4057001 ,1.4236282 , 1.2925886 , 1.2891779 , 1.3144554 , 1.33754   ,1.3151662 , 1.2521679 , 1.2439616 , 1.6995414 , 1.3861445 ,1.3535012 , 1.2228161 , 1.3386501 , 1.3935357 , 1.3838186 ,1.4072384 , 1.4310058 , 1.2708198 , 1.3285922 , 1.1291428 ,1.2382853 , 1.3012738 , 1.287349  , 1.3014474 , 1.242337  ,1.3321948 , 1.3107737 , 1.3064048 , 1.4306538 , 1.3175644 ,1.2410822 , 1.4420744 , 1.1816049 , 1.1409183 , 1.1814541 ,1.4548798 , 1.2112384 , 1.2723444 , 1.3042331 , 1.2022628 ]],      dtype=float32)</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span>t_Intercept</span></div><div class='xr-var-dims'>(chain, draw)</div><div class='xr-var-dtype'>float32</div><div class='xr-var-preview xr-preview'>...</div><input id='attrs-48ca0d53-7bf5-4d04-afab-5276766f3a78' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-48ca0d53-7bf5-4d04-afab-5276766f3a78' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-1731fe6e-27bd-496e-a4c5-73b9ebd35ae1' class='xr-var-data-in' type='checkbox'><label for='data-1731fe6e-27bd-496e-a4c5-73b9ebd35ae1' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>Array([[0.20429376, 0.27498063, 0.27149004, 0.24850634, 0.20800616,0.17592594, 0.2827752 , 0.16293326, 0.18042724, 0.15242887,0.13310274, 0.2833843 , 0.20689206, 0.24024029, 0.21969108,0.23461413, 0.23430134, 0.22563031, 0.23676027, 0.18180935,0.26042518, 0.21082857, 0.28605375, 0.26917168, 0.27981052,0.32324323, 0.3117143 , 0.3158151 , 0.2946929 , 0.35113207,0.18214212, 0.19927621, 0.2912295 , 0.2009532 , 0.19001096,0.20238382, 0.22842707, 0.26465377, 0.17614901, 0.25123128,0.22956024, 0.33877334, 0.32412714, 0.17421147, 0.21836554,0.28820682, 0.2751492 , 0.24421856, 0.18106489, 0.17412643,0.20242536, 0.2742944 , 0.26172215, 0.29900795, 0.31204104,0.2840568 , 0.28127912, 0.22185218, 0.2293146 , 0.21943727,0.1475381 , 0.20838013, 0.21319397, 0.2746923 , 0.2502358 ,0.22667599, 0.21019271, 0.23774114, 0.1845732 , 0.31255582,0.20724636, 0.2695254 , 0.23273744, 0.2414947 , 0.22017175,0.23701364, 0.20395435, 0.18441007, 0.23664448, 0.23768073,0.3100226 , 0.19755265, 0.17696437, 0.1652838 , 0.16114983,0.187501  , 0.18047947, 0.1963631 , 0.14104663, 0.24363343,0.22869971, 0.27137607, 0.19386724, 0.2731886 , 0.2085296 ,0.23430413, 0.21213014, 0.2265982 , 0.20431696, 0.2624734 ,...0.23576783, 0.2838626 , 0.36330858, 0.31680593, 0.18617208,0.1410099 , 0.18431596, 0.18228133, 0.17017497, 0.17871214,0.26728824, 0.23208153, 0.1957871 , 0.26204523, 0.25057116,0.17894539, 0.12385643, 0.25029054, 0.21751842, 0.22168101,0.14737138, 0.30729863, 0.2266599 , 0.2606724 , 0.22195154,0.14530128, 0.14384688, 0.19351019, 0.20930724, 0.19907933,0.2417121 , 0.20244557, 0.17433299, 0.20197667, 0.13574073,0.2559069 , 0.22449666, 0.23018414, 0.2687618 , 0.24859042,0.25351402, 0.2528815 , 0.1284587 , 0.11956172, 0.13257085,0.1447229 , 0.20891517, 0.22897317, 0.21014303, 0.1806468 ,0.26666695, 0.21160907, 0.23099306, 0.22434522, 0.2143429 ,0.19290198, 0.21394768, 0.17724839, 0.18327431, 0.16961086,0.1906265 , 0.21848357, 0.2780559 , 0.23661724, 0.22229767,0.26746193, 0.14617145, 0.3304823 , 0.21047112, 0.2816949 ,0.29975668, 0.27747673, 0.2280325 , 0.26004705, 0.2546713 ,0.1729824 , 0.24456482, 0.22400004, 0.27717972, 0.2266901 ,0.2167627 , 0.24515252, 0.25458542, 0.26610032, 0.22853576,0.23231132, 0.22806127, 0.2244913 , 0.15446658, 0.15233354,0.32848677, 0.24847108, 0.19385687, 0.25275818, 0.23059538,0.22802487, 0.18646906, 0.18513606, 0.20173529, 0.2133292 ]],      dtype=float32)</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span>scaler_1|participant_id</span></div><div class='xr-var-dims'>(chain, draw, participant_id__factor_dim)</div><div class='xr-var-dtype'>float32</div><div class='xr-var-preview xr-preview'>...</div><input id='attrs-7078365d-b32a-45dc-b588-f70c6110d4cd' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-7078365d-b32a-45dc-b588-f70c6110d4cd' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-51adfda6-a2d4-4608-a43f-86552cfc1476' class='xr-var-data-in' type='checkbox'><label for='data-51adfda6-a2d4-4608-a43f-86552cfc1476' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>Array([[[-0.12724218,  0.09528601,  0.16785875, -0.15565047,-0.10698499],[-0.04740734,  0.14832704, -0.36914012, -0.61075824,-0.07077344],[ 0.31034276,  0.78692716,  0.01514927, -0.553314  ,0.9299212 ],...,[-0.4584201 ,  0.85259175,  0.24185011, -0.12993033,1.0325745 ],[-0.00693274,  0.05135338, -0.8840798 , -0.04910554,0.3649927 ],[ 0.10017202, -0.02444658, -0.98019433, -0.30955172,0.28475887]],[[-0.65730155,  0.09901449, -0.22706093,  0.20528297,0.86507714],[-0.3710161 ,  0.02556157, -0.3522298 , -0.620342  ,0.9743778 ],[-0.38454255,  0.10318137, -0.2772155 , -0.43136197,0.8234941 ],...,[-0.15088928, -0.01111543,  0.02060432, -0.29726344,-0.01332476],[-0.5262981 ,  0.22996534,  0.19126932, -0.21379304,0.40196413],[-0.97955716,  0.06731368,  0.38161775, -0.48560935,0.9065947 ]]], dtype=float32)</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span>z_1|participant_id_sigma</span></div><div class='xr-var-dims'>(chain, draw)</div><div class='xr-var-dtype'>float32</div><div class='xr-var-preview xr-preview'>...</div><input id='attrs-c863b63c-409f-4be1-a1a0-f9cbd483587f' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-c863b63c-409f-4be1-a1a0-f9cbd483587f' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-1b2f0c97-2e33-4979-b4af-c61af17b7674' class='xr-var-data-in' type='checkbox'><label for='data-1b2f0c97-2e33-4979-b4af-c61af17b7674' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>Array([[4.02238965e-03, 2.87979580e-02, 7.92072713e-02, 6.49871603e-02,1.91052333e-02, 5.68114035e-03, 5.05561046e-02, 1.52343186e-03,4.19553928e-03, 8.03923830e-02, 5.55189550e-02, 4.02201638e-02,4.12218124e-02, 5.11271432e-02, 1.73220396e-01, 2.56035794e-02,1.30079128e-02, 2.55139172e-02, 1.19191401e-01, 1.55012170e-02,2.62086391e-02, 2.34293099e-03, 3.08668520e-02, 4.08730470e-02,2.66522542e-02, 8.38199258e-03, 1.06914435e-03, 9.69493354e-04,1.99395046e-02, 3.29891518e-02, 2.19879486e-02, 2.89815124e-02,1.74515396e-02, 8.89875274e-03, 3.28566916e-02, 2.49697850e-03,2.47277096e-02, 7.50871655e-03, 2.20593344e-02, 7.20945373e-03,1.29083499e-01, 6.31475523e-02, 8.77866521e-02, 2.41498277e-02,6.59847856e-02, 7.50924647e-03, 3.05754133e-02, 9.26937908e-03,6.92105889e-02, 3.98685858e-02, 2.69465195e-03, 1.70740392e-02,2.13309452e-02, 8.25967873e-04, 1.23352557e-03, 3.67011060e-03,1.98769122e-02, 7.11905584e-03, 6.92360103e-02, 3.07033826e-02,4.35755402e-02, 3.62012573e-02, 4.90188599e-03, 9.53487493e-03,6.34571444e-03, 8.29555746e-03, 2.58541554e-02, 4.73310128e-02,1.19512780e-02, 1.73155721e-02, 8.96445010e-03, 5.18248715e-02,4.32774574e-02, 5.66207319e-02, 1.29134193e-01, 1.26093224e-01,1.39830127e-01, 3.00986581e-02, 4.84626889e-02, 1.51686464e-02,...6.08649664e-03, 2.35686339e-02, 7.94472173e-03, 6.77330093e-03,5.50006796e-03, 2.35077769e-05, 9.22667386e-05, 7.73358217e-04,7.44470069e-03, 2.25646850e-02, 3.03868279e-02, 4.74796817e-03,9.96968988e-03, 3.91883105e-02, 1.06445430e-02, 2.44146213e-02,2.74278875e-02, 2.22934298e-02, 1.02718621e-01, 9.11377072e-02,8.86202678e-02, 6.78165704e-02, 4.43549380e-02, 3.00379023e-02,2.23837309e-02, 2.75260936e-02, 2.26269457e-02, 2.00401545e-02,1.88557785e-02, 3.00001483e-02, 7.00094774e-02, 1.22483531e-02,5.07137645e-03, 5.12588024e-02, 1.61605049e-02, 1.61011163e-02,1.06769733e-01, 3.94076854e-02, 6.37028040e-03, 1.26305968e-02,1.08763315e-02, 1.32075534e-03, 4.26348448e-02, 3.04185487e-02,1.28451586e-02, 4.57582576e-03, 4.06834409e-02, 3.46370339e-02,4.25157845e-02, 1.06919892e-02, 9.81913134e-03, 1.14930756e-02,2.95253377e-02, 2.98112389e-02, 2.19243579e-02, 1.18478332e-02,4.23106439e-02, 1.48552759e-02, 8.27233959e-03, 1.62152480e-02,2.54498459e-02, 2.10803170e-02, 5.76325916e-02, 4.55326354e-03,1.58328861e-02, 5.07990550e-03, 1.60816275e-02, 4.46006432e-02,3.22351344e-02, 3.39215063e-02, 2.75400300e-02, 2.85395700e-02,8.48333724e-03, 2.93699801e-02, 3.32823023e-02, 1.34020839e-02,1.28975123e-01, 8.86445213e-03, 2.39766575e-02, 2.39030980e-02]],      dtype=float32)</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span>rl_alpha_1|participant_id_offset</span></div><div class='xr-var-dims'>(chain, draw, rl_alpha_1|participant_id__factor_dim)</div><div class='xr-var-dtype'>float32</div><div class='xr-var-preview xr-preview'>...</div><input id='attrs-8d8cd445-9274-41d6-89fe-7fbf376bd7b2' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-8d8cd445-9274-41d6-89fe-7fbf376bd7b2' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-690374bb-96cc-4bc4-94d7-86158a36316e' class='xr-var-data-in' type='checkbox'><label for='data-690374bb-96cc-4bc4-94d7-86158a36316e' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>Array([[[-1.4583458 , -0.1834005 , -1.7675729 , -0.7929651 ,0.33906054],[-0.9838688 ,  0.13236625, -0.37069857, -0.52243483,0.7221021 ],[ 0.83617693, -0.02563862,  0.21170521,  0.9761566 ,-0.3223305 ],...,[-0.20692724,  0.9622859 , -2.056054  , -1.0922807 ,0.8248903 ],[-0.7375505 ,  0.5781889 , -0.3293935 , -1.9095021 ,0.58886063],[-0.96234685,  0.47929683,  0.21281567, -1.4517846 ,0.63607436]],[[ 0.7071711 ,  0.957604  , -0.06592099,  0.12291435,1.4009433 ],[ 0.27850252,  0.40871337,  0.26389116,  0.19096756,1.5311518 ],[ 0.02674573,  0.34528947,  0.16845411,  0.287602  ,1.3711046 ],...,[ 0.9611176 ,  1.189063  ,  0.5103071 ,  0.07064422,1.6606704 ],[ 0.35802588,  0.72372174,  0.0551132 ,  0.11746906,0.6364546 ],[ 0.6428101 ,  0.44201526,  0.20125914,  0.5251205 ,1.2930368 ]]], dtype=float32)</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span>scaler_Intercept</span></div><div class='xr-var-dims'>(chain, draw)</div><div class='xr-var-dtype'>float32</div><div class='xr-var-preview xr-preview'>...</div><input id='attrs-4df8d0ff-1f58-417d-b4ff-7e25dc3263cb' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-4df8d0ff-1f58-417d-b4ff-7e25dc3263cb' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-b1ace3dc-bf49-45ab-82ce-f56f13eb2a34' class='xr-var-data-in' type='checkbox'><label for='data-b1ace3dc-bf49-45ab-82ce-f56f13eb2a34' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>Array([[2.5781446, 2.992829 , 1.5567404, 2.036927 , 2.536706 , 2.69148  ,1.9040236, 2.420907 , 2.0601294, 1.1375544, 2.6785386, 1.9031553,2.3323398, 2.1545026, 1.9566203, 2.369926 , 2.1081967, 2.6842592,2.235254 , 1.864192 , 2.293417 , 1.7800184, 2.4311817, 2.067805 ,2.1963649, 2.4584596, 2.14223  , 2.467307 , 2.4636774, 1.8615661,2.1479483, 2.2010355, 1.767842 , 2.1316552, 1.6828085, 2.268453 ,2.0911984, 1.9589835, 1.9607089, 2.5536306, 2.1101544, 1.5524306,1.6346022, 1.4950063, 1.541143 , 2.8682895, 1.7923349, 2.2662683,1.8786868, 2.60623  , 2.036839 , 2.054912 , 2.1625834, 2.2858214,1.7824197, 1.4908311, 1.5191097, 1.7530359, 2.4760888, 2.3066962,2.0962093, 2.613377 , 1.3162827, 2.0850432, 1.6497   , 2.259887 ,1.609937 , 1.3778927, 1.657495 , 2.4477644, 1.5300596, 2.1552336,2.8356192, 2.4232285, 1.9697496, 1.846558 , 2.895831 , 1.6034971,2.2969556, 1.9890816, 1.8510605, 1.9989823, 2.4571683, 2.9235003,3.0197678, 1.1969279, 1.6838187, 1.3303384, 1.9730204, 2.5390184,2.3290956, 2.2273798, 2.5758598, 1.1932049, 2.0154767, 2.0911512,1.9480443, 1.7723253, 2.4402046, 1.9540313, 1.0469239, 1.3538907,2.4495103, 2.1145554, 2.6570854, 3.0647   , 2.2599857, 1.9213729,1.3824644, 2.727355 , 2.230659 , 1.7583845, 1.9623467, 2.340105 ,2.152429 , 1.9553975, 2.6350238, 2.3475423, 1.7837088, 2.1389022,...2.4321432, 2.6689534, 2.251665 , 1.9547993, 1.6717618, 2.5578256,2.210853 , 2.3399084, 2.8077908, 1.5320876, 2.2213693, 2.031137 ,1.9557889, 1.8906813, 1.6619134, 1.4643192, 1.8486531, 2.4192598,2.1126966, 1.9710371, 2.703472 , 2.263426 , 1.8873937, 2.395034 ,2.076871 , 1.9643289, 2.0778146, 2.5234373, 2.304156 , 2.0006764,1.5076383, 1.6301254, 2.5118966, 1.7566262, 2.1303234, 1.7869241,1.6726425, 2.1054716, 1.8234112, 1.9675629, 1.7693186, 1.7126635,2.123502 , 1.8566015, 1.8256918, 2.485129 , 2.308    , 1.7532628,2.7108912, 1.4744066, 1.7965763, 1.9162788, 1.679426 , 2.1283855,2.196675 , 2.378937 , 2.595263 , 2.5286326, 1.972859 , 2.724022 ,2.500515 , 1.5593837, 1.5734426, 1.6225228, 1.9330986, 1.9890927,1.9212646, 1.9107966, 1.7317649, 1.9234849, 2.5846696, 1.3928509,2.6117628, 1.5355712, 2.1989849, 2.2920008, 1.9459088, 2.2474327,2.5494564, 2.7618148, 2.685565 , 2.4480748, 2.2261257, 2.4759278,1.5170454, 1.3756938, 3.0110514, 1.231868 , 3.405536 , 2.3134112,2.281167 , 1.9168472, 2.8940902, 1.9908631, 2.0990086, 1.8382933,2.5440907, 1.626494 , 2.3567607, 1.6649809, 2.9683652, 2.728997 ,2.7030623, 2.6111214, 2.2609172, 2.1119092, 2.2117121, 2.118388 ,2.013773 , 2.6923487, 1.6401695, 1.9889048, 2.286061 , 2.6280704,2.203427 , 2.3416474, 1.9519681, 2.2224522, 2.3075871, 2.592976 ]],      dtype=float32)</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span>t_1|participant_id</span></div><div class='xr-var-dims'>(chain, draw, participant_id__factor_dim)</div><div class='xr-var-dtype'>float32</div><div class='xr-var-preview xr-preview'>...</div><input id='attrs-a2ceeca4-8c06-450d-80ba-35f61a21d2ed' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-a2ceeca4-8c06-450d-80ba-35f61a21d2ed' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-43b5f6b6-7ed6-4bf5-beab-7c84005d92c7' class='xr-var-data-in' type='checkbox'><label for='data-43b5f6b6-7ed6-4bf5-beab-7c84005d92c7' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>Array([[[-0.06376672, -0.04993222,  0.13111302, -0.07813247,0.09242752],[ 0.02409178, -0.07048429,  0.03509193, -0.11638021,0.07817297],[-0.04921572, -0.12666981, -0.03316658, -0.02208503,-0.03093472],...,[-0.20125385, -0.20306695, -0.01818475, -0.14560078,-0.08889914],[ 0.15201482, -0.10619114,  0.13986848, -0.06103271,0.15117928],[ 0.16600633, -0.10836337,  0.11734632,  0.00866974,0.16442266]],[[-0.01259228, -0.10968252, -0.09148683, -0.08207267,-0.00364707],[-0.03686487, -0.18071397,  0.00871082, -0.1489712 ,0.00975429],[-0.03108446, -0.1730186 , -0.01905845, -0.14345048,0.02632551],...,[ 0.0857605 , -0.17882955,  0.11254551, -0.11909435,0.1165699 ],[ 0.04827872, -0.0177493 ,  0.1007153 , -0.02146922,0.11693235],[-0.04732214, -0.06630916,  0.05126338,  0.05879094,0.11040018]]], dtype=float32)</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span>scaler_1|participant_id_sigma</span></div><div class='xr-var-dims'>(chain, draw)</div><div class='xr-var-dtype'>float32</div><div class='xr-var-preview xr-preview'>...</div><input id='attrs-82d5b94c-c618-46c7-af67-ef619e97ccff' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-82d5b94c-c618-46c7-af67-ef619e97ccff' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-80867462-3297-4045-85e4-79ae214482e6' class='xr-var-data-in' type='checkbox'><label for='data-80867462-3297-4045-85e4-79ae214482e6' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>Array([[0.13340767, 0.34862772, 0.44254667, 0.32894582, 0.7568719 ,0.68209577, 0.4275481 , 0.4291643 , 0.4182442 , 0.95161235,0.1367785 , 0.1414208 , 0.17384905, 0.15425827, 0.6787505 ,0.72861636, 0.49945366, 0.5993028 , 0.7233461 , 0.5473998 ,1.1238606 , 0.27942935, 0.7574739 , 0.54566807, 0.33235288,0.736156  , 0.5862029 , 0.1611438 , 0.55082077, 0.2878541 ,0.6753079 , 0.6162547 , 0.58880866, 0.7178681 , 0.8018997 ,0.25592086, 0.24878518, 1.1680238 , 0.35061294, 0.38666484,0.07043374, 0.07760122, 0.05025742, 0.6429302 , 0.4432716 ,0.96289814, 0.43240345, 1.271362  , 0.22372411, 0.20080048,0.6861402 , 0.28101957, 0.36429602, 0.72767866, 0.5851836 ,0.6850953 , 0.63018185, 0.5115021 , 0.27640507, 0.39333704,0.8693793 , 0.6794719 , 0.8831148 , 0.4443033 , 0.7030417 ,0.6717287 , 0.68088615, 0.7362968 , 0.655773  , 0.5741432 ,0.32220313, 0.5149812 , 0.39010492, 0.42978236, 0.59684473,0.535463  , 1.0926379 , 0.5284777 , 0.8426983 , 0.39834523,0.29726127, 1.123578  , 0.65921074, 0.6085105 , 0.6174154 ,0.55322117, 0.37959534, 0.32937628, 0.4485484 , 0.5124198 ,0.73402846, 0.19666782, 0.7126062 , 1.1158915 , 0.19709478,0.11385109, 0.43480134, 0.5748188 , 0.46433115, 0.6183124 ,...1.1546807 , 0.24616243, 0.2668758 , 0.4954845 , 0.09883666,0.52970994, 0.6060829 , 0.9055898 , 0.4256684 , 1.1199917 ,0.64085084, 1.0786077 , 0.5424404 , 0.02797462, 0.7368654 ,0.76908815, 0.7076762 , 0.6968908 , 0.42555425, 0.63616204,0.61956984, 0.97388625, 1.0468934 , 0.46264985, 0.36818495,1.5588557 , 0.93727684, 0.34195602, 1.1557238 , 0.6586455 ,0.41250008, 0.79484975, 0.6359674 , 0.63107765, 0.6305326 ,0.99925953, 0.61341953, 0.90112567, 0.30519688, 0.900041  ,0.9486877 , 0.9190723 , 0.44299954, 0.26895276, 0.37199235,0.76625264, 0.17327608, 0.5124413 , 0.2806732 , 0.5236725 ,0.7537318 , 0.5743186 , 0.68010986, 1.1392426 , 0.4125771 ,0.00447324, 0.12689923, 0.4070306 , 0.35645762, 0.10485173,0.09973635, 0.05624477, 0.8146205 , 0.04609393, 0.42065716,0.73620117, 0.74923563, 0.46617177, 0.70935917, 0.75286764,0.8031564 , 0.4669776 , 0.5467308 , 0.42558643, 0.51609385,0.03881805, 0.31721568, 0.94562066, 0.5606836 , 0.20082773,0.01557604, 0.52448773, 1.0141231 , 0.43188125, 0.24663348,0.5484156 , 0.6781083 , 0.06291974, 0.06640424, 0.33060852,0.45117497, 0.4212089 , 0.89309   , 0.7188679 , 0.6207548 ,0.18691622, 1.1141196 , 0.23003794, 0.23903781, 0.50826705]],      dtype=float32)</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span>t_1|participant_id_offset</span></div><div class='xr-var-dims'>(chain, draw, participant_id__factor_dim)</div><div class='xr-var-dtype'>float32</div><div class='xr-var-preview xr-preview'>...</div><input id='attrs-d013bf51-73e9-441d-bd45-c605c9fba7cc' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-d013bf51-73e9-441d-bd45-c605c9fba7cc' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-ce9dba69-398a-48aa-8562-76981348a7b1' class='xr-var-data-in' type='checkbox'><label for='data-ce9dba69-398a-48aa-8562-76981348a7b1' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>Array([[[-0.49864465, -0.3904613 ,  1.0252811 , -0.6109823 ,0.7227672 ],[ 0.25790572, -0.75454354,  0.3756637 , -1.2458655 ,0.8368519 ],[-0.8385356 , -2.1581955 , -0.565091  , -0.37628388,-0.52706456],...,[-0.9326473 , -0.9410495 , -0.08427145, -0.67474073,-0.41197494],[ 1.1512989 , -0.8042488 ,  1.0593075 , -0.4622371 ,1.1449709 ],[ 1.2384009 , -0.8083866 ,  0.8753991 ,  0.0646759 ,1.2265868 ]],[[-0.06669051, -0.58089435, -0.48452738, -0.43466863,-0.01931539],[-0.19193982, -0.94090134,  0.04535358, -0.7756302 ,0.05078649],[-0.15727612, -0.8754117 , -0.09642889, -0.7258076 ,0.13319756],...,[ 0.38997272, -0.8131791 ,  0.5117703 , -0.5415494 ,0.5300701 ],[ 0.33289686, -0.12238698,  0.6944635 , -0.14803696,0.80628514],[-0.3428137 , -0.48036057,  0.3713651 ,  0.42589667,0.79976726]]], dtype=float32)</pre></div></li></ul></div></li><li class='xr-section-item'><input id='section-6a1f80b4-ab79-4e48-91a1-c1135c5c170d' class='xr-section-summary-in' type='checkbox' /><label for='section-6a1f80b4-ab79-4e48-91a1-c1135c5c170d' class='xr-section-summary' title='Expand/collapse section'>Attributes: <span>(11)</span></label><div class='xr-section-inline-details'></div><div class='xr-section-details'><dl class='xr-attrs'><dt><span>created_at :</span></dt><dd>2026-07-24T14:18:40.484086+00:00</dd><dt><span>creation_library :</span></dt><dd>ArviZ</dd><dt><span>creation_library_version :</span></dt><dd>1.2.0</dd><dt><span>creation_library_language :</span></dt><dd>Python</dd><dt><span>sample_dims :</span></dt><dd>[&#x27;chain&#x27;, &#x27;draw&#x27;]</dd><dt><span>inference_library :</span></dt><dd>numpyro</dd><dt><span>inference_library_version :</span></dt><dd>0.21.0</dd><dt><span>sampling_time :</span></dt><dd>92.736215</dd><dt><span>tuning_steps :</span></dt><dd>300</dd><dt><span>modeling_interface :</span></dt><dd>bambi</dd><dt><span>modeling_interface_version :</span></dt><dd>0.19.0</dd></dl></div></li></ul></div></div><div class='xr-group-box'><div class='xr-group-box-vline' style='height: 100%'></div><div class='xr-group-box-hline'></div><div class='xr-group-box-contents'><input id='group-58951af9-1f37-4399-b1ba-44017f3c6b68' type='checkbox' checked /><label for='group-58951af9-1f37-4399-b1ba-44017f3c6b68' title='Expand/collapse group'>/sample_stats<span>(16)</span></label><ul class='xr-sections'><li class='xr-section-item'><input id='section-2a4c6430-de5d-44ed-a20f-d11096e1ea6b' class='xr-section-summary-in' type='checkbox' disabled /><label for='section-2a4c6430-de5d-44ed-a20f-d11096e1ea6b' class='xr-section-summary'>Dimensions:</label><div class='xr-section-inline-details'><ul class='xr-dim-list'><li><span class='xr-has-index'>chain</span>: 2</li><li><span class='xr-has-index'>draw</span>: 300</li></ul></div></li><li class='xr-section-item'><input id='section-9eb60745-3274-45e7-8180-9e590d3af35d' class='xr-section-summary-in' type='checkbox' checked /><label for='section-9eb60745-3274-45e7-8180-9e590d3af35d' class='xr-section-summary' title='Expand/collapse section'>Coordinates: <span>(2)</span></label><div class='xr-section-inline-details'></div><div class='xr-section-details'><ul class='xr-var-list'><li class='xr-var-item'><div class='xr-var-name'><span class='xr-has-index'>chain</span></div><div class='xr-var-dims'>(chain)</div><div class='xr-var-dtype'>int64</div><div class='xr-var-preview xr-preview'>0 1</div><input id='attrs-396b0c55-ef8d-41b0-a0e5-94945102b88b' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-396b0c55-ef8d-41b0-a0e5-94945102b88b' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-b0d81740-737d-4bd5-8ef7-b94e97b5275b' class='xr-var-data-in' type='checkbox'><label for='data-b0d81740-737d-4bd5-8ef7-b94e97b5275b' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>array([0, 1])</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span class='xr-has-index'>draw</span></div><div class='xr-var-dims'>(draw)</div><div class='xr-var-dtype'>int64</div><div class='xr-var-preview xr-preview'>0 1 2 3 4 5 ... 295 296 297 298 299</div><input id='attrs-0d4dac36-ec71-4e99-8b9b-e5aa552253a0' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-0d4dac36-ec71-4e99-8b9b-e5aa552253a0' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-f42fc96d-24c0-4b20-adb6-63b77dae4f83' class='xr-var-data-in' type='checkbox'><label for='data-f42fc96d-24c0-4b20-adb6-63b77dae4f83' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>array([  0,   1,   2, ..., 297, 298, 299], shape=(300,))</pre></div></li></ul></div></li><li class='xr-section-item'><input id='section-dc39c12e-6a1a-4aaa-b0e9-4bd5088deeb5' class='xr-section-summary-in' type='checkbox' checked /><label for='section-dc39c12e-6a1a-4aaa-b0e9-4bd5088deeb5' class='xr-section-summary' title='Expand/collapse section'>Data variables: <span>(7)</span></label><div class='xr-section-inline-details'></div><div class='xr-section-details'><ul class='xr-var-list'><li class='xr-var-item'><div class='xr-var-name'><span>acceptance_rate</span></div><div class='xr-var-dims'>(chain, draw)</div><div class='xr-var-dtype'>float32</div><div class='xr-var-preview xr-preview'>...</div><input id='attrs-609efda6-e8ec-4ac1-b3ae-3edead5acffe' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-609efda6-e8ec-4ac1-b3ae-3edead5acffe' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-4b0988c6-cf20-41a7-ba28-e817793edb40' class='xr-var-data-in' type='checkbox'><label for='data-4b0988c6-cf20-41a7-ba28-e817793edb40' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>Array([[0.96033674, 0.8785385 , 0.9820714 , 0.9863686 , 0.994483  ,0.99023825, 0.99653745, 0.99282223, 0.90245646, 0.99534595,0.9904857 , 0.9891426 , 0.98611236, 0.9942626 , 0.9972338 ,0.9405561 , 0.95695835, 0.9882534 , 0.9969338 , 0.9875914 ,0.9887006 , 0.9916961 , 0.9960462 , 0.9837527 , 0.8990402 ,0.99206865, 0.9827689 , 0.9803307 , 0.943846  , 0.99702525,0.9990385 , 0.9496129 , 0.9940236 , 0.99469763, 0.95209885,0.9901723 , 0.9866789 , 0.98635125, 0.9987865 , 0.999542  ,0.9929037 , 0.28419018, 0.98511004, 0.9797076 , 0.9915367 ,0.98519486, 0.9839503 , 0.9619202 , 0.991879  , 0.94194764,0.99715704, 0.99976903, 0.96494406, 0.96217024, 0.98178136,0.9874852 , 0.997905  , 0.99511   , 0.96049774, 0.9961498 ,0.99443114, 0.93212795, 0.9857865 , 0.99933666, 0.87130153,0.9784243 , 0.99229795, 0.9779368 , 0.99347186, 0.9846669 ,0.9859598 , 0.998529  , 0.984862  , 0.996657  , 0.7236629 ,0.9970846 , 0.9886987 , 0.8694975 , 0.99935395, 0.972987  ,0.9969377 , 0.9579095 , 0.9886085 , 0.9313275 , 0.49333653,0.9847623 , 0.9744419 , 0.98128206, 0.9963799 , 0.98145014,0.98722523, 0.994483  , 0.9982593 , 0.9745124 , 0.9530094 ,0.9952149 , 0.9975513 , 0.99041146, 0.991592  , 0.9978259 ,...0.9586123 , 0.94658196, 0.98139423, 0.9751742 , 0.9874203 ,0.9638471 , 0.9976397 , 0.9840162 , 0.90788823, 0.9901285 ,0.95799446, 0.9735382 , 0.8768373 , 0.9757264 , 0.6301406 ,0.963528  , 0.93554217, 0.9928374 , 0.9536201 , 0.97160363,0.98371214, 0.99190116, 0.99053854, 0.7703814 , 0.96554214,0.91680616, 0.9677528 , 0.9942691 , 0.99903274, 0.9860314 ,0.8888703 , 0.97516924, 0.9188446 , 0.96756834, 0.9888423 ,0.99652183, 0.94525194, 0.99441636, 0.99364007, 0.9168337 ,0.9287331 , 0.89844596, 0.9495652 , 0.52007544, 0.9756007 ,0.9488158 , 0.8018742 , 0.9756092 , 0.92648005, 0.93386227,0.999375  , 0.99614424, 0.98527473, 0.9266179 , 0.8391148 ,0.9015719 , 0.9863369 , 1.        , 0.9396374 , 0.93610007,0.8777985 , 0.9849296 , 0.9919399 , 0.98869467, 0.95085484,0.9229436 , 0.95857227, 0.8998047 , 0.98646224, 0.9949147 ,0.9801192 , 0.90860146, 0.44431046, 0.6622707 , 0.964171  ,0.91531557, 0.9523704 , 0.9873122 , 0.98869765, 0.99862474,0.99509776, 0.97191894, 0.9766037 , 0.9545402 , 0.99979067,0.997041  , 0.9559865 , 0.98722875, 0.9506962 , 0.9985499 ,0.99033576, 0.98290193, 0.94678754, 0.9920247 , 0.99612945,0.98739576, 0.99450034, 0.82199144, 0.9111446 , 0.93137115]],      dtype=float32)</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span>step_size</span></div><div class='xr-var-dims'>(chain, draw)</div><div class='xr-var-dtype'>float32</div><div class='xr-var-preview xr-preview'>...</div><input id='attrs-b3820ffe-3995-4ada-85f3-7d0da81b73ed' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-b3820ffe-3995-4ada-85f3-7d0da81b73ed' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-bae67c10-9122-4345-b0cb-e50727104ee6' class='xr-var-data-in' type='checkbox'><label for='data-bae67c10-9122-4345-b0cb-e50727104ee6' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>Array([[0.04308953, 0.04308953, 0.04308953, 0.04308953, 0.04308953,0.04308953, 0.04308953, 0.04308953, 0.04308953, 0.04308953,0.04308953, 0.04308953, 0.04308953, 0.04308953, 0.04308953,0.04308953, 0.04308953, 0.04308953, 0.04308953, 0.04308953,0.04308953, 0.04308953, 0.04308953, 0.04308953, 0.04308953,0.04308953, 0.04308953, 0.04308953, 0.04308953, 0.04308953,0.04308953, 0.04308953, 0.04308953, 0.04308953, 0.04308953,0.04308953, 0.04308953, 0.04308953, 0.04308953, 0.04308953,0.04308953, 0.04308953, 0.04308953, 0.04308953, 0.04308953,0.04308953, 0.04308953, 0.04308953, 0.04308953, 0.04308953,0.04308953, 0.04308953, 0.04308953, 0.04308953, 0.04308953,0.04308953, 0.04308953, 0.04308953, 0.04308953, 0.04308953,0.04308953, 0.04308953, 0.04308953, 0.04308953, 0.04308953,0.04308953, 0.04308953, 0.04308953, 0.04308953, 0.04308953,0.04308953, 0.04308953, 0.04308953, 0.04308953, 0.04308953,0.04308953, 0.04308953, 0.04308953, 0.04308953, 0.04308953,0.04308953, 0.04308953, 0.04308953, 0.04308953, 0.04308953,0.04308953, 0.04308953, 0.04308953, 0.04308953, 0.04308953,0.04308953, 0.04308953, 0.04308953, 0.04308953, 0.04308953,0.04308953, 0.04308953, 0.04308953, 0.04308953, 0.04308953,...0.05788062, 0.05788062, 0.05788062, 0.05788062, 0.05788062,0.05788062, 0.05788062, 0.05788062, 0.05788062, 0.05788062,0.05788062, 0.05788062, 0.05788062, 0.05788062, 0.05788062,0.05788062, 0.05788062, 0.05788062, 0.05788062, 0.05788062,0.05788062, 0.05788062, 0.05788062, 0.05788062, 0.05788062,0.05788062, 0.05788062, 0.05788062, 0.05788062, 0.05788062,0.05788062, 0.05788062, 0.05788062, 0.05788062, 0.05788062,0.05788062, 0.05788062, 0.05788062, 0.05788062, 0.05788062,0.05788062, 0.05788062, 0.05788062, 0.05788062, 0.05788062,0.05788062, 0.05788062, 0.05788062, 0.05788062, 0.05788062,0.05788062, 0.05788062, 0.05788062, 0.05788062, 0.05788062,0.05788062, 0.05788062, 0.05788062, 0.05788062, 0.05788062,0.05788062, 0.05788062, 0.05788062, 0.05788062, 0.05788062,0.05788062, 0.05788062, 0.05788062, 0.05788062, 0.05788062,0.05788062, 0.05788062, 0.05788062, 0.05788062, 0.05788062,0.05788062, 0.05788062, 0.05788062, 0.05788062, 0.05788062,0.05788062, 0.05788062, 0.05788062, 0.05788062, 0.05788062,0.05788062, 0.05788062, 0.05788062, 0.05788062, 0.05788062,0.05788062, 0.05788062, 0.05788062, 0.05788062, 0.05788062,0.05788062, 0.05788062, 0.05788062, 0.05788062, 0.05788062]],      dtype=float32)</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span>diverging</span></div><div class='xr-var-dims'>(chain, draw)</div><div class='xr-var-dtype'>bool</div><div class='xr-var-preview xr-preview'>...</div><input id='attrs-8c2ad18f-866e-453d-9a79-946cd7e75c56' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-8c2ad18f-866e-453d-9a79-946cd7e75c56' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-d67bb0fa-2f26-40ec-b7ba-3cf9e7d21ac9' class='xr-var-data-in' type='checkbox'><label for='data-d67bb0fa-2f26-40ec-b7ba-3cf9e7d21ac9' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>Array([[False, False, False, False, False,  True, False, False, False,False, False, False, False, False, False, False,  True, False,False, False, False, False, False, False, False, False, False,False, False, False, False, False, False, False, False, False,False,  True, False, False, False, False,  True, False, False,False, False, False, False, False, False, False,  True, False,True,  True, False, False, False, False, False, False,  True,False, False, False, False, False, False, False, False, False,False, False, False, False, False, False, False, False, False,False,  True,  True, False, False,  True,  True, False, False,False, False, False, False, False, False, False, False, False,False, False, False, False,  True, False, False, False, False,False, False, False, False, False, False, False, False, False,False, False, False, False,  True,  True, False, False, False,False, False, False, False,  True, False, False, False, False,False, False, False, False, False, False, False,  True, False,False,  True, False, False, False, False, False, False, False,True, False, False, False, False, False, False, False, False,False, False, False, False,  True, False, False, False, False,False, False, False, False,  True, False, False, False, False,...False,  True,  True, False, False, False, False, False, False,False, False, False, False, False, False, False, False,  True,True,  True, False, False, False, False, False, False, False,True, False, False, False, False, False, False, False, False,False, False, False, False, False, False, False, False, False,False, False, False,  True, False, False, False, False, False,False, False, False, False, False, False, False, False, False,False, False, False, False, False, False, False, False, False,False, False, False, False, False, False, False, False, False,False, False, False, False, False, False, False, False, False,False, False, False, False, False, False, False, False, False,False,  True, False, False, False,  True, False, False, False,False, False, False, False, False, False,  True, False,  True,False, False,  True, False, False,  True, False, False, False,False, False, False, False, False, False, False, False,  True,False, False, False, False, False, False, False, False, False,False, False, False, False, False, False, False, False,  True,False, False, False,  True, False, False, False, False, False,False, False, False, False, False, False, False, False, False,False,  True, False]], dtype=bool)</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span>energy</span></div><div class='xr-var-dims'>(chain, draw)</div><div class='xr-var-dtype'>float32</div><div class='xr-var-preview xr-preview'>...</div><input id='attrs-6308e585-8421-405f-94b9-5b57a7f640b8' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-6308e585-8421-405f-94b9-5b57a7f640b8' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-b92645e5-e14a-45af-b716-2b0ebeaf145f' class='xr-var-data-in' type='checkbox'><label for='data-b92645e5-e14a-45af-b716-2b0ebeaf145f' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>Array([[417.37372, 408.13934, 411.51462, 423.3831 , 416.0995 , 420.82867,411.04047, 414.07523, 412.09937, 410.49966, 409.98077, 408.5478 ,409.17242, 411.05908, 408.84412, 398.4337 , 402.15662, 404.53802,400.0314 , 405.63333, 412.26804, 409.96353, 415.2818 , 400.69794,410.03928, 404.7884 , 402.45413, 407.39087, 417.2657 , 413.5756 ,407.51877, 404.95154, 404.1412 , 405.03818, 413.18018, 418.00397,415.174  , 416.11166, 418.48727, 414.06784, 409.79874, 406.51147,412.41028, 411.85272, 407.68625, 399.5388 , 403.39896, 399.15543,391.58862, 410.43857, 404.71637, 408.8736 , 410.99005, 422.84448,417.58075, 411.41858, 402.53528, 415.07983, 423.38907, 425.68658,431.3903 , 427.58386, 416.8509 , 400.5799 , 415.90247, 412.8284 ,411.9002 , 404.27402, 414.73978, 414.50424, 412.5673 , 403.12097,408.52753, 399.49133, 403.38492, 396.78308, 406.65125, 405.841  ,408.28235, 413.06073, 407.925  , 403.36963, 406.90506, 413.3538 ,412.60193, 411.3907 , 409.38342, 409.08984, 409.84793, 414.0578 ,418.22913, 418.16528, 417.35794, 410.15143, 416.78122, 425.46576,419.89603, 418.855  , 415.7962 , 411.71478, 414.01254, 426.361  ,419.96   , 410.82355, 403.54593, 402.2301 , 411.84314, 416.9576 ,413.51752, 413.6648 , 410.83038, 412.377  , 398.8613 , 401.78644,421.11856, 414.54956, 398.94305, 395.90332, 406.30173, 401.81247,...406.07404, 409.12964, 405.3146 , 403.73376, 400.04343, 405.356  ,405.7354 , 402.39514, 411.7399 , 412.24442, 402.36432, 403.7052 ,411.26385, 412.08636, 417.61224, 406.2213 , 401.955  , 412.8834 ,406.5622 , 395.654  , 404.09766, 410.14392, 413.85522, 417.7788 ,413.0369 , 425.33008, 419.6769 , 412.2022 , 405.09073, 398.33948,405.48914, 402.29477, 400.84103, 407.1877 , 421.64233, 416.09674,431.29767, 426.31082, 410.73077, 423.32614, 415.90036, 411.3552 ,411.91266, 406.854  , 417.52277, 421.64816, 409.49417, 414.96378,416.27026, 407.19144, 407.029  , 410.18478, 399.65857, 403.71484,407.206  , 408.16797, 411.33548, 406.61597, 397.60278, 407.44934,412.58295, 408.87952, 400.29532, 398.09726, 399.2009 , 403.94397,405.73438, 406.16138, 405.67126, 412.3213 , 416.19165, 412.16623,404.90594, 399.94357, 405.81232, 408.13043, 412.95157, 401.56046,408.51492, 416.84177, 414.6606 , 414.40808, 410.29498, 404.2446 ,409.4695 , 410.5826 , 417.79837, 409.90817, 417.7141 , 408.71362,395.64685, 406.03967, 404.6269 , 412.23822, 399.94223, 411.46286,411.27017, 408.50903, 413.5001 , 417.8953 , 436.79562, 433.7493 ,433.67606, 435.73825, 437.8208 , 434.51202, 431.99097, 417.06482,423.4579 , 410.41013, 405.3744 , 403.3717 , 416.26294, 410.8223 ,413.10056, 408.43378, 415.79883, 412.80518, 424.65152, 410.04996]],      dtype=float32)</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span>n_steps</span></div><div class='xr-var-dims'>(chain, draw)</div><div class='xr-var-dtype'>int32</div><div class='xr-var-preview xr-preview'>...</div><input id='attrs-c08b939c-0d62-4096-b3d7-556591099d44' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-c08b939c-0d62-4096-b3d7-556591099d44' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-8f076542-61fe-43a9-85e9-0ec6709b0aef' class='xr-var-data-in' type='checkbox'><label for='data-8f076542-61fe-43a9-85e9-0ec6709b0aef' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>Array([[127, 127, 127, 127, 127, 126, 127, 127, 127, 127, 127, 127, 127,127, 127, 127,  28, 127, 127, 127, 127, 127, 127, 127, 127, 127,127, 127, 127, 127, 127, 127, 127, 127,  63,  63, 127,  95, 127,127, 127, 127, 123, 127,  63, 127,  63, 127, 127, 127, 127,  63,41, 127,  61, 105,  63, 127, 127, 127,  63, 127, 133, 127, 127,63, 127, 127, 127, 127, 127, 127, 127,  63,  63, 127, 127, 127,127,  63, 127, 127, 103,  95, 127, 127,  42,  55, 127, 127, 127,127, 127, 127, 127, 127, 127, 127, 127, 127, 127, 127, 127,  84,127, 127, 127, 127, 127, 127, 127, 127, 127, 127, 127, 127, 127,127, 127, 127, 127, 119,  10, 127, 127,  63, 127, 127, 127, 127,71, 127, 127, 127,  63, 127, 127, 127, 127, 127, 127, 127,  63,127, 127, 102, 127, 127,  63, 127, 127, 127, 127,  68, 127, 127,127,  63, 127, 127, 127, 127, 127, 127, 127, 127, 118, 127, 127,63,  63, 127,  63, 127, 127,  59,  63, 127, 127, 127, 127, 127,127,  63, 127,   1, 127, 125, 127, 127, 127, 127,  26, 127,  63,127, 127, 127,  59, 127, 127, 127,  63, 127, 127, 127, 127, 127,23, 127, 127, 127, 127, 127, 127, 127, 127,  34, 127, 108, 127,127, 127,  87, 127, 127,  63, 127, 127, 127, 127, 127, 127,  47,127, 127, 127, 127, 127,  63,  51, 127,  63, 127,  63, 127,  84,63,  92,   4,   6,  65, 127, 127,  63, 127, 127, 127, 127, 127,...63, 127,  63,  63,  14,  63, 127,  63,  63, 127, 127, 127, 127,63,  63,  63,  63,  63,  87,  63,  63,  63, 127,  63,  54,  63,63,  63,  59,  63,  63, 191, 127, 127,  63,  63,  63,  63,  63,63, 127,  63, 127,  63,  63,  63,  63,  63, 127,  63,  63, 127,37,  40,  31, 127,  63,  63,  48,  63, 127,  63,  44, 127,  47,63,  63,  63,  63, 127, 127,  63, 127,  42,  63,  21,  35, 127,127,  63, 127,  63,  63,  63,  63,  63, 127,  63,  63, 127,  63,24,   9,  33, 127,  63,  63, 127,  63,  63,  63,  54,  63, 127,63, 127,  63,  63,  63,  63, 127,  63,  63, 127,  63,  63,  63,63, 127, 127,  63, 127,  61,  63,  63,  63,  63,  63,  63, 127,63, 127,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,  63,63,  63,  63,  63,  63,  63,  63,  63,  63, 127,  63,  63, 127,63,  63, 127, 127, 127,  63,  63,  63,  63,  63,  63, 127,  63,63,  63,  63,  63,  63,  37, 127,  63,  63,  86,  63,  63,  63,63,  63, 127, 127,  63, 127,  19,  63,  94, 127,  63,  29,  63,63,  32,  63, 127,  63, 127,  63, 127, 127,  63,  63,  63,  63,9,  63, 127,  63,  63,  63, 127, 127, 127,  63,  63,  63, 127,63,  63, 127,  63,  63, 104,  63,  63,  63,  48,  63,  63,  63,63,  63,  63,  63, 127,  63,  63,  63,  63,  63, 127,  63,  32,127]], dtype=int32)</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span>tree_depth</span></div><div class='xr-var-dims'>(chain, draw)</div><div class='xr-var-dtype'>int64</div><div class='xr-var-preview xr-preview'>7 7 7 7 7 7 7 7 ... 6 6 6 6 7 6 6 7</div><input id='attrs-a99fc71e-606a-4a52-b480-3774f1b2f5e9' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-a99fc71e-606a-4a52-b480-3774f1b2f5e9' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-46ab0700-e273-49bf-8ed4-c248c0923cd4' class='xr-var-data-in' type='checkbox'><label for='data-46ab0700-e273-49bf-8ed4-c248c0923cd4' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>array([[7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 5, 7, 7, 7, 7, 7,7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 6, 6, 7, 7, 7, 7, 7, 7, 7, 7,6, 7, 6, 7, 7, 7, 7, 6, 6, 7, 6, 7, 6, 7, 7, 7, 6, 7, 8, 7, 7, 6,7, 7, 7, 7, 7, 7, 7, 6, 6, 7, 7, 7, 7, 6, 7, 7, 7, 7, 7, 7, 6, 6,7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7,7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 4, 7, 7, 6, 7, 7, 7, 7, 7, 7,7, 7, 6, 7, 7, 7, 7, 7, 7, 7, 6, 7, 7, 7, 7, 7, 6, 7, 7, 7, 7, 7,7, 7, 7, 6, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 6, 6, 7, 6, 7, 7, 6,6, 7, 7, 7, 7, 7, 7, 6, 7, 1, 7, 7, 7, 7, 7, 7, 5, 7, 6, 7, 7, 7,6, 7, 7, 7, 6, 7, 7, 7, 7, 7, 5, 7, 7, 7, 7, 7, 7, 7, 7, 6, 7, 7,7, 7, 7, 7, 7, 7, 6, 7, 7, 7, 7, 7, 7, 6, 7, 7, 7, 7, 7, 6, 6, 7,6, 7, 6, 7, 7, 6, 7, 3, 3, 7, 7, 7, 6, 7, 7, 7, 7, 7, 6, 7, 7, 6,7, 4, 4, 7, 7, 7, 7, 6, 7, 7, 6, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 6,7, 7, 7, 7, 7, 7, 6, 7, 7, 7, 6, 7, 7, 7],[6, 7, 4, 6, 7, 6, 6, 6, 6, 5, 7, 7, 6, 7, 8, 6, 6, 7, 6, 7, 7, 7,7, 6, 7, 6, 6, 7, 6, 5, 7, 4, 7, 7, 6, 6, 6, 6, 6, 6, 6, 7, 5, 6,6, 6, 6, 6, 6, 6, 6, 7, 6, 7, 6, 6, 4, 6, 7, 6, 6, 7, 7, 7, 7, 6,6, 6, 6, 6, 7, 6, 6, 6, 7, 6, 6, 6, 6, 6, 6, 6, 6, 8, 7, 7, 6, 6,6, 6, 6, 6, 7, 6, 7, 6, 6, 6, 6, 6, 7, 6, 6, 7, 6, 6, 5, 7, 6, 6,6, 6, 7, 6, 6, 7, 6, 6, 6, 6, 6, 7, 7, 6, 7, 6, 6, 5, 6, 7, 7, 6,7, 6, 6, 6, 6, 6, 7, 6, 6, 7, 6, 5, 4, 6, 7, 6, 6, 7, 6, 6, 6, 6,6, 7, 6, 7, 6, 6, 6, 6, 7, 6, 6, 7, 6, 6, 6, 6, 7, 7, 6, 7, 6, 6,6, 6, 6, 6, 6, 7, 6, 7, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6,6, 6, 6, 6, 6, 6, 7, 6, 6, 7, 6, 6, 7, 7, 7, 6, 6, 6, 6, 6, 6, 7,6, 6, 6, 6, 6, 6, 6, 7, 6, 6, 7, 6, 6, 6, 6, 6, 7, 7, 6, 7, 5, 6,7, 7, 6, 5, 6, 6, 6, 6, 7, 6, 7, 6, 7, 7, 6, 6, 6, 6, 4, 6, 7, 6,6, 6, 7, 7, 7, 6, 6, 6, 7, 6, 6, 7, 6, 6, 7, 6, 6, 6, 6, 6, 6, 6,6, 6, 6, 6, 7, 6, 6, 6, 6, 6, 7, 6, 6, 7]])</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span>lp</span></div><div class='xr-var-dims'>(chain, draw)</div><div class='xr-var-dtype'>float32</div><div class='xr-var-preview xr-preview'>...</div><input id='attrs-907ae2f8-3385-4f5c-890c-9beee75f220b' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-907ae2f8-3385-4f5c-890c-9beee75f220b' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-5509124a-4125-4a26-917a-d095eda98162' class='xr-var-data-in' type='checkbox'><label for='data-5509124a-4125-4a26-917a-d095eda98162' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>Array([[394.09488, 385.24164, 394.09894, 392.98367, 398.19366, 396.16614,389.39166, 392.44666, 390.1056 , 391.44098, 389.7625 , 385.6347 ,394.1698 , 386.14374, 384.53665, 377.542  , 380.098  , 382.04028,382.9939 , 389.99802, 390.9277 , 393.13336, 387.08823, 383.53122,386.62598, 380.52902, 381.90164, 391.71243, 395.4429 , 389.96368,380.98096, 387.51352, 385.5276 , 385.4507 , 396.64917, 395.83496,399.88086, 393.08517, 396.75653, 390.39752, 379.5471 , 391.10333,389.44705, 390.58466, 381.22632, 383.09775, 381.90286, 378.09183,380.40845, 386.13287, 390.25406, 385.08856, 387.60724, 399.43347,396.29776, 389.62177, 390.2033 , 397.4245 , 398.67514, 402.66806,408.36304, 391.68436, 389.3629 , 383.7178 , 394.76184, 390.36945,385.62396, 386.8156 , 396.98093, 393.03278, 386.061  , 384.66385,384.91193, 384.3248 , 381.0891 , 384.2008 , 385.19553, 389.8413 ,387.27322, 392.48593, 384.28033, 386.11975, 393.49155, 390.03232,392.39914, 388.2781 , 391.3805 , 392.83337, 387.7561 , 393.85938,394.05624, 402.64227, 389.06027, 388.23737, 398.97125, 400.7893 ,400.68414, 393.6961 , 395.65518, 391.2489 , 400.034  , 399.5839 ,394.92166, 384.89508, 381.01392, 385.98416, 389.2858 , 399.26538,394.44873, 390.3877 , 389.0716 , 386.76984, 381.46823, 390.16986,388.80273, 389.40396, 383.64572, 383.44525, 385.98376, 384.5776 ,...387.31036, 391.04813, 388.1021 , 384.10046, 383.3048 , 384.84616,388.69586, 388.36526, 384.31366, 390.39618, 384.40558, 390.05255,397.33487, 393.35535, 390.94333, 381.4787 , 387.54553, 391.50052,384.4722 , 379.66156, 389.633  , 388.5091 , 398.05276, 390.41934,395.02823, 401.96112, 390.9971 , 388.35275, 385.6041 , 381.0918 ,382.7286 , 382.68747, 384.25836, 395.06586, 390.55508, 395.54184,407.03973, 391.06882, 395.03125, 398.62344, 394.14188, 395.16306,390.99316, 388.56113, 391.829  , 393.51794, 390.0531 , 394.80585,389.49734, 386.38675, 388.55368, 386.15662, 388.2653 , 382.05295,390.35965, 393.2531 , 388.4096 , 384.47137, 384.96   , 392.69705,391.9715 , 378.9571 , 382.39584, 384.03677, 383.44534, 381.671  ,390.46152, 380.65805, 388.4502 , 391.27353, 392.64346, 391.17267,380.6573 , 383.9884 , 385.74582, 391.89484, 391.01627, 385.4204 ,395.70193, 395.3958 , 396.45096, 392.67157, 388.3678 , 389.58054,391.86057, 390.03   , 392.47473, 390.77863, 395.35724, 383.27362,378.5565 , 383.0009 , 383.97787, 388.6201 , 384.7961 , 395.34592,389.02432, 390.02808, 395.52524, 398.70428, 410.83957, 403.80197,403.4167 , 416.65277, 411.69925, 406.62695, 396.6117 , 397.29633,396.40714, 386.15137, 386.1772 , 385.79962, 394.91922, 391.08078,381.67746, 393.0481 , 387.06522, 393.55667, 392.8749 , 391.10416]],      dtype=float32)</pre></div></li></ul></div></li><li class='xr-section-item'><input id='section-0ba99af9-f440-4020-8eb0-30a0b060821f' class='xr-section-summary-in' type='checkbox' checked /><label for='section-0ba99af9-f440-4020-8eb0-30a0b060821f' class='xr-section-summary' title='Expand/collapse section'>Attributes: <span>(7)</span></label><div class='xr-section-inline-details'></div><div class='xr-section-details'><dl class='xr-attrs'><dt><span>created_at :</span></dt><dd>2026-07-24T14:18:40.498297+00:00</dd><dt><span>creation_library :</span></dt><dd>ArviZ</dd><dt><span>creation_library_version :</span></dt><dd>1.2.0</dd><dt><span>creation_library_language :</span></dt><dd>Python</dd><dt><span>sample_dims :</span></dt><dd>[&#x27;chain&#x27;, &#x27;draw&#x27;]</dd><dt><span>modeling_interface :</span></dt><dd>bambi</dd><dt><span>modeling_interface_version :</span></dt><dd>0.19.0</dd></dl></div></li></ul></div></div><div class='xr-group-box'><div class='xr-group-box-vline' style='height: 100%'></div><div class='xr-group-box-hline'></div><div class='xr-group-box-contents'><input id='group-c3420a6a-0af5-4e79-b468-32d759d718db' type='checkbox' checked /><label for='group-c3420a6a-0af5-4e79-b468-32d759d718db' title='Expand/collapse group'>/observed_data<span>(10)</span></label><ul class='xr-sections'><li class='xr-section-item'><input id='section-c63ce799-3471-49bb-abb1-d2e8ffb43e9a' class='xr-section-summary-in' type='checkbox' disabled /><label for='section-c63ce799-3471-49bb-abb1-d2e8ffb43e9a' class='xr-section-summary'>Dimensions:</label><div class='xr-section-inline-details'><ul class='xr-dim-list'><li><span class='xr-has-index'>__obs__</span>: 350</li><li><span class='xr-has-index'>rt,response_extra_dim_0</span>: 2</li></ul></div></li><li class='xr-section-item'><input id='section-f54ade9b-f6eb-47e2-b6f3-6f886aba3637' class='xr-section-summary-in' type='checkbox' checked /><label for='section-f54ade9b-f6eb-47e2-b6f3-6f886aba3637' class='xr-section-summary' title='Expand/collapse section'>Coordinates: <span>(2)</span></label><div class='xr-section-inline-details'></div><div class='xr-section-details'><ul class='xr-var-list'><li class='xr-var-item'><div class='xr-var-name'><span class='xr-has-index'>__obs__</span></div><div class='xr-var-dims'>(__obs__)</div><div class='xr-var-dtype'>int64</div><div class='xr-var-preview xr-preview'>0 1 2 3 4 5 ... 345 346 347 348 349</div><input id='attrs-1289ed2f-1f2c-4c24-9cc7-6894fe8f086f' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-1289ed2f-1f2c-4c24-9cc7-6894fe8f086f' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-40c3d818-32af-4b41-b979-4c2a51dec826' class='xr-var-data-in' type='checkbox'><label for='data-40c3d818-32af-4b41-b979-4c2a51dec826' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>array([  0,   1,   2, ..., 347, 348, 349], shape=(350,))</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span class='xr-has-index'>rt,response_extra_dim_0</span></div><div class='xr-var-dims'>(rt,response_extra_dim_0)</div><div class='xr-var-dtype'>int64</div><div class='xr-var-preview xr-preview'>0 1</div><input id='attrs-0bda907f-72b1-4f73-bad3-6b8d3049d237' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-0bda907f-72b1-4f73-bad3-6b8d3049d237' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-87a72a72-2098-46ad-87ed-80722fdb3e3a' class='xr-var-data-in' type='checkbox'><label for='data-87a72a72-2098-46ad-87ed-80722fdb3e3a' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>array([0, 1])</pre></div></li></ul></div></li><li class='xr-section-item'><input id='section-ee0479b7-572c-4809-8dd5-d04e201d87c0' class='xr-section-summary-in' type='checkbox' checked /><label for='section-ee0479b7-572c-4809-8dd5-d04e201d87c0' class='xr-section-summary' title='Expand/collapse section'>Data variables: <span>(1)</span></label><div class='xr-section-inline-details'></div><div class='xr-section-details'><ul class='xr-var-list'><li class='xr-var-item'><div class='xr-var-name'><span>rt,response</span></div><div class='xr-var-dims'>(__obs__, rt,response_extra_dim_0)</div><div class='xr-var-dtype'>float32</div><div class='xr-var-preview xr-preview'>1.101 -1.0 1.999 ... 1.009 -1.0</div><input id='attrs-57a3b8dd-dfe7-487c-8bae-180a8e331de2' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-57a3b8dd-dfe7-487c-8bae-180a8e331de2' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-0042acb3-cd22-44f1-8bd3-a320161740c0' class='xr-var-data-in' type='checkbox'><label for='data-0042acb3-cd22-44f1-8bd3-a320161740c0' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>array([[ 1.100926  , -1.        ],[ 1.9985536 , -1.        ],[ 2.1513555 , -1.        ],[ 0.58990616, -1.        ],[ 1.1724871 , -1.        ],[ 0.9756266 , -1.        ],[ 1.2626417 ,  1.        ],[ 1.1017668 , -1.        ],[ 0.80269176, -1.        ],[ 1.8350772 ,  1.        ],[ 1.0365586 , -1.        ],[ 1.8596222 , -1.        ],[ 1.2636248 ,  1.        ],[ 0.7060377 , -1.        ],[ 1.7817559 , -1.        ],[ 0.54377115, -1.        ],[ 0.5464994 , -1.        ],[ 1.9762948 , -1.        ],[ 1.3642769 ,  1.        ],[ 0.6310554 , -1.        ],...[ 1.2168534 , -1.        ],[ 0.85871667, -1.        ],[ 1.4025654 , -1.        ],[ 1.1067938 , -1.        ],[ 0.77304983, -1.        ],[ 0.6180564 , -1.        ],[ 0.6796331 , -1.        ],[ 1.6154934 , -1.        ],[ 1.8210009 , -1.        ],[ 0.74919015, -1.        ],[ 1.0277966 , -1.        ],[ 1.4953309 , -1.        ],[ 1.7121912 , -1.        ],[ 0.5577653 , -1.        ],[ 0.54850405, -1.        ],[ 1.1838193 ,  1.        ],[ 0.627454  , -1.        ],[ 1.32497   , -1.        ],[ 1.1755071 , -1.        ],[ 1.0086374 , -1.        ]], dtype=float32)</pre></div></li></ul></div></li><li class='xr-section-item'><input id='section-418d218f-1459-4b21-a0c7-4ce494f18d31' class='xr-section-summary-in' type='checkbox' checked /><label for='section-418d218f-1459-4b21-a0c7-4ce494f18d31' class='xr-section-summary' title='Expand/collapse section'>Attributes: <span>(7)</span></label><div class='xr-section-inline-details'></div><div class='xr-section-details'><dl class='xr-attrs'><dt><span>created_at :</span></dt><dd>2026-07-24T14:18:40.499371+00:00</dd><dt><span>creation_library :</span></dt><dd>ArviZ</dd><dt><span>creation_library_version :</span></dt><dd>1.2.0</dd><dt><span>creation_library_language :</span></dt><dd>Python</dd><dt><span>sample_dims :</span></dt><dd>[]</dd><dt><span>modeling_interface :</span></dt><dd>bambi</dd><dt><span>modeling_interface_version :</span></dt><dd>0.19.0</dd></dl></div></li></ul></div></div><div class='xr-group-box'><div class='xr-group-box-vline' style='height: 100%'></div><div class='xr-group-box-hline'></div><div class='xr-group-box-contents'><input id='group-05ce5b68-eefb-46d3-b16d-baf6f4fddce8' type='checkbox' checked /><label for='group-05ce5b68-eefb-46d3-b16d-baf6f4fddce8' title='Expand/collapse group'>/constant_data<span>(7)</span></label><ul class='xr-sections'><li class='xr-section-item'><input id='section-273fad1f-0489-4aad-9f52-abe6c4d14dc4' class='xr-section-summary-in' type='checkbox' checked /><label for='section-273fad1f-0489-4aad-9f52-abe6c4d14dc4' class='xr-section-summary' title='Expand/collapse section'>Attributes: <span>(7)</span></label><div class='xr-section-inline-details'></div><div class='xr-section-details'><dl class='xr-attrs'><dt><span>created_at :</span></dt><dd>2026-07-24T14:18:40.499495+00:00</dd><dt><span>creation_library :</span></dt><dd>ArviZ</dd><dt><span>creation_library_version :</span></dt><dd>1.2.0</dd><dt><span>creation_library_language :</span></dt><dd>Python</dd><dt><span>sample_dims :</span></dt><dd>[]</dd><dt><span>modeling_interface :</span></dt><dd>bambi</dd><dt><span>modeling_interface_version :</span></dt><dd>0.19.0</dd></dl></div></li></ul></div></div><div class='xr-group-box'><div class='xr-group-box-vline' style='height: 1.2em'></div><div class='xr-group-box-hline'></div><div class='xr-group-box-contents'><input id='group-1e7b562a-25bd-4028-9c01-32731f692695' type='checkbox' checked /><label for='group-1e7b562a-25bd-4028-9c01-32731f692695' title='Expand/collapse group'>/log_likelihood<span>(6)</span></label><ul class='xr-sections'><li class='xr-section-item'><input id='section-778fe204-2325-4b06-9f34-197b827b9400' class='xr-section-summary-in' type='checkbox' disabled /><label for='section-778fe204-2325-4b06-9f34-197b827b9400' class='xr-section-summary'>Dimensions:</label><div class='xr-section-inline-details'><ul class='xr-dim-list'><li><span class='xr-has-index'>chain</span>: 2</li><li><span class='xr-has-index'>draw</span>: 300</li><li><span class='xr-has-index'>__obs__</span>: 350</li></ul></div></li><li class='xr-section-item'><input id='section-fed9e6d8-fbf4-4ff9-950b-b13d473f9661' class='xr-section-summary-in' type='checkbox' checked /><label for='section-fed9e6d8-fbf4-4ff9-950b-b13d473f9661' class='xr-section-summary' title='Expand/collapse section'>Coordinates: <span>(3)</span></label><div class='xr-section-inline-details'></div><div class='xr-section-details'><ul class='xr-var-list'><li class='xr-var-item'><div class='xr-var-name'><span class='xr-has-index'>chain</span></div><div class='xr-var-dims'>(chain)</div><div class='xr-var-dtype'>int64</div><div class='xr-var-preview xr-preview'>0 1</div><input id='attrs-8965b9c5-f8b0-467f-a9ba-bc56dda8cc1f' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-8965b9c5-f8b0-467f-a9ba-bc56dda8cc1f' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-34bbf25e-a2d1-4172-be5c-23f0c77a5aa9' class='xr-var-data-in' type='checkbox'><label for='data-34bbf25e-a2d1-4172-be5c-23f0c77a5aa9' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>array([0, 1])</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span class='xr-has-index'>draw</span></div><div class='xr-var-dims'>(draw)</div><div class='xr-var-dtype'>int64</div><div class='xr-var-preview xr-preview'>0 1 2 3 4 5 ... 295 296 297 298 299</div><input id='attrs-1fa30427-777a-417b-af77-924ca7f144e2' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-1fa30427-777a-417b-af77-924ca7f144e2' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-c5154a5b-7de2-46ca-9852-3cd7609c1c71' class='xr-var-data-in' type='checkbox'><label for='data-c5154a5b-7de2-46ca-9852-3cd7609c1c71' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>array([  0,   1,   2, ..., 297, 298, 299], shape=(300,))</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span class='xr-has-index'>__obs__</span></div><div class='xr-var-dims'>(__obs__)</div><div class='xr-var-dtype'>int64</div><div class='xr-var-preview xr-preview'>0 1 2 3 4 5 ... 345 346 347 348 349</div><input id='attrs-143a1e91-bbb4-4ac7-ada3-0e222e2415d6' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-143a1e91-bbb4-4ac7-ada3-0e222e2415d6' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-cca6ea1f-3a3a-4355-a7fa-3672bc84ba49' class='xr-var-data-in' type='checkbox'><label for='data-cca6ea1f-3a3a-4355-a7fa-3672bc84ba49' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>array([  0,   1,   2, ..., 347, 348, 349], shape=(350,))</pre></div></li></ul></div></li><li class='xr-section-item'><input id='section-50482a15-9980-4a7d-9f14-fc6329ecd583' class='xr-section-summary-in' type='checkbox' checked /><label for='section-50482a15-9980-4a7d-9f14-fc6329ecd583' class='xr-section-summary' title='Expand/collapse section'>Data variables: <span>(1)</span></label><div class='xr-section-inline-details'></div><div class='xr-section-details'><ul class='xr-var-list'><li class='xr-var-item'><div class='xr-var-name'><span>rt,response</span></div><div class='xr-var-dims'>(chain, draw, __obs__)</div><div class='xr-var-dtype'>float64</div><div class='xr-var-preview xr-preview'>-0.9516 -1.938 ... -0.6732 -0.2128</div><input id='attrs-b9b93ef2-3868-44a4-b014-613badd2a477' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-b9b93ef2-3868-44a4-b014-613badd2a477' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-cbe90b0e-e705-42ad-a699-a743aef1928f' class='xr-var-data-in' type='checkbox'><label for='data-cbe90b0e-e705-42ad-a699-a743aef1928f' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>array([[[-0.95163041, -1.9377526 , -2.26808763, ..., -0.71993995,-0.44797689, -0.13487169],[-0.87594002, -2.2362287 , -2.66411352, ..., -0.80930352,-0.49260673, -0.1163418 ],[-0.97445178, -1.75210941, -2.00760913, ..., -0.80831838,-0.54027539, -0.21576402],...,[-0.9823854 , -1.61517644, -1.87649751, ..., -0.63673544,-0.36646456, -0.07604778],[-1.00356209, -1.9535886 , -2.17671299, ..., -0.76532316,-0.47597289, -0.12971124],[-1.14535391, -2.14524269, -2.2812984 , ..., -0.64430213,-0.35331348, -0.03097525]],[[-0.87596756, -1.91994739, -2.27408028, ..., -0.79342633,-0.46522176, -0.07652199],[-0.88144708, -2.00250196, -2.33182001, ..., -0.91400528,-0.57967585, -0.1750775 ],[-0.89691997, -1.96655369, -2.26612449, ..., -0.82059753,-0.50560611, -0.13100737],...,[-0.93633831, -2.05415273, -2.39878511, ..., -0.69802511,-0.44716901, -0.15773717],[-0.88594627, -1.85543263, -2.22275281, ..., -0.83603704,-0.51832235, -0.11384979],[-1.02542877, -1.74677694, -1.95633328, ..., -1.02392185,-0.67318541, -0.21278203]]], shape=(2, 300, 350))</pre></div></li></ul></div></li><li class='xr-section-item'><input id='section-f7720f4e-3190-4c3c-ab0c-dfac1d46cdac' class='xr-section-summary-in' type='checkbox' checked /><label for='section-f7720f4e-3190-4c3c-ab0c-dfac1d46cdac' class='xr-section-summary' title='Expand/collapse section'>Attributes: <span>(2)</span></label><div class='xr-section-inline-details'></div><div class='xr-section-details'><dl class='xr-attrs'><dt><span>modeling_interface :</span></dt><dd>bambi</dd><dt><span>modeling_interface_version :</span></dt><dd>0.19.0</dd></dl></div></li></ul></div></div></div></li></ul></div></div>"
-      ],
-      "text/plain": [
-       "<xarray.DataTree>\n",
-       "Group: /\n",
-       "├── Group: /posterior\n",
-       "│       Dimensions:                                (chain: 2, draw: 300,\n",
-       "│                                                   participant_id__factor_dim: 5,\n",
-       "│                                                   rl_alpha_1|participant_id__factor_dim: 5)\n",
-       "│       Coordinates:\n",
-       "│         * chain                                  (chain) int64 16B 0 1\n",
-       "│         * draw                                   (draw) int64 2kB 0 1 2 ... 298 299\n",
-       "│         * participant_id__factor_dim             (participant_id__factor_dim) <U1 20B ...\n",
-       "│         * rl_alpha_1|participant_id__factor_dim  (rl_alpha_1|participant_id__factor_dim) <U1 20B ...\n",
-       "│       Data variables: (12/24)\n",
-       "│           z_1|participant_id_offset              (chain, draw, participant_id__factor_dim) float32 12kB ...\n",
-       "│           z_Intercept                            (chain, draw) float32 2kB ...\n",
-       "│           scaler_1|participant_id_offset         (chain, draw, participant_id__factor_dim) float32 12kB ...\n",
-       "│           a_1|participant_id_offset              (chain, draw, participant_id__factor_dim) float32 12kB ...\n",
-       "│           a_1|participant_id                     (chain, draw, participant_id__factor_dim) float32 12kB ...\n",
-       "│           t_1|participant_id_sigma               (chain, draw) float32 2kB ...\n",
-       "│           ...                                     ...\n",
-       "│           z_1|participant_id_sigma               (chain, draw) float32 2kB ...\n",
-       "│           rl_alpha_1|participant_id_offset       (chain, draw, rl_alpha_1|participant_id__factor_dim) float32 12kB ...\n",
-       "│           scaler_Intercept                       (chain, draw) float32 2kB ...\n",
-       "│           t_1|participant_id                     (chain, draw, participant_id__factor_dim) float32 12kB ...\n",
-       "│           scaler_1|participant_id_sigma          (chain, draw) float32 2kB ...\n",
-       "│           t_1|participant_id_offset              (chain, draw, participant_id__factor_dim) float32 12kB ...\n",
-       "│       Attributes:\n",
-       "│           created_at:                  2026-07-24T14:18:40.484086+00:00\n",
-       "│           creation_library:            ArviZ\n",
-       "│           creation_library_version:    1.2.0\n",
-       "│           creation_library_language:   Python\n",
-       "│           sample_dims:                 ['chain', 'draw']\n",
-       "│           inference_library:           numpyro\n",
-       "│           inference_library_version:   0.21.0\n",
-       "│           sampling_time:               92.736215\n",
-       "│           tuning_steps:                300\n",
-       "│           modeling_interface:          bambi\n",
-       "│           modeling_interface_version:  0.19.0\n",
-       "├── Group: /sample_stats\n",
-       "│       Dimensions:          (chain: 2, draw: 300)\n",
-       "│       Coordinates:\n",
-       "│         * chain            (chain) int64 16B 0 1\n",
-       "│         * draw             (draw) int64 2kB 0 1 2 3 4 5 6 ... 294 295 296 297 298 299\n",
-       "│       Data variables:\n",
-       "│           acceptance_rate  (chain, draw) float32 2kB ...\n",
-       "│           step_size        (chain, draw) float32 2kB ...\n",
-       "│           diverging        (chain, draw) bool 600B ...\n",
-       "│           energy           (chain, draw) float32 2kB ...\n",
-       "│           n_steps          (chain, draw) int32 2kB ...\n",
-       "│           tree_depth       (chain, draw) int64 5kB 7 7 7 7 7 7 7 7 ... 6 6 6 6 7 6 6 7\n",
-       "│           lp               (chain, draw) float32 2kB ...\n",
-       "│       Attributes:\n",
-       "│           created_at:                  2026-07-24T14:18:40.498297+00:00\n",
-       "│           creation_library:            ArviZ\n",
-       "│           creation_library_version:    1.2.0\n",
-       "│           creation_library_language:   Python\n",
-       "│           sample_dims:                 ['chain', 'draw']\n",
-       "│           modeling_interface:          bambi\n",
-       "│           modeling_interface_version:  0.19.0\n",
-       "├── Group: /observed_data\n",
-       "│       Dimensions:                  (__obs__: 350, rt,response_extra_dim_0: 2)\n",
-       "│       Coordinates:\n",
-       "│         * __obs__                  (__obs__) int64 3kB 0 1 2 3 4 ... 346 347 348 349\n",
-       "│         * rt,response_extra_dim_0  (rt,response_extra_dim_0) int64 16B 0 1\n",
-       "│       Data variables:\n",
-       "│           rt,response              (__obs__, rt,response_extra_dim_0) float32 3kB 1...\n",
-       "│       Attributes:\n",
-       "│           created_at:                  2026-07-24T14:18:40.499371+00:00\n",
-       "│           creation_library:            ArviZ\n",
-       "│           creation_library_version:    1.2.0\n",
-       "│           creation_library_language:   Python\n",
-       "│           sample_dims:                 []\n",
-       "│           modeling_interface:          bambi\n",
-       "│           modeling_interface_version:  0.19.0\n",
-       "├── Group: /constant_data\n",
-       "│       Attributes:\n",
-       "│           created_at:                  2026-07-24T14:18:40.499495+00:00\n",
-       "│           creation_library:            ArviZ\n",
-       "│           creation_library_version:    1.2.0\n",
-       "│           creation_library_language:   Python\n",
-       "│           sample_dims:                 []\n",
-       "│           modeling_interface:          bambi\n",
-       "│           modeling_interface_version:  0.19.0\n",
-       "└── Group: /log_likelihood\n",
-       "        Dimensions:      (chain: 2, draw: 300, __obs__: 350)\n",
-       "        Coordinates:\n",
-       "          * chain        (chain) int64 16B 0 1\n",
-       "          * draw         (draw) int64 2kB 0 1 2 3 4 5 6 ... 293 294 295 296 297 298 299\n",
-       "          * __obs__      (__obs__) int64 3kB 0 1 2 3 4 5 6 ... 344 345 346 347 348 349\n",
-       "        Data variables:\n",
-       "            rt,response  (chain, draw, __obs__) float64 2MB -0.9516 -1.938 ... -0.2128\n",
-       "        Attributes:\n",
-       "            modeling_interface:          bambi\n",
-       "            modeling_interface_version:  0.19.0"
-      ]
-     },
-     "execution_count": 15,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
+   "outputs": [],
    "source": [
     "idata = model.sample(\n",
     "    sampler=\"numpyro\",\n",
@@ -1493,7 +452,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 16,
+   "execution_count": null,
    "id": "ae08ea78",
    "metadata": {},
    "outputs": [],
@@ -1547,109 +506,10 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 17,
+   "execution_count": null,
    "id": "89a41288",
    "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "image/png": "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",
-      "text/plain": [
-       "<Figure size 800x450 with 1 Axes>"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "text/html": [
-       "<div>\n",
-       "<style scoped>\n",
-       "    .dataframe tbody tr th:only-of-type {\n",
-       "        vertical-align: middle;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe tbody tr th {\n",
-       "        vertical-align: top;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe thead th {\n",
-       "        text-align: right;\n",
-       "    }\n",
-       "</style>\n",
-       "<table border=\"1\" class=\"dataframe\">\n",
-       "  <thead>\n",
-       "    <tr style=\"text-align: right;\">\n",
-       "      <th></th>\n",
-       "      <th>mean</th>\n",
-       "      <th>hdi94_lb</th>\n",
-       "      <th>hdi94_ub</th>\n",
-       "      <th>true</th>\n",
-       "    </tr>\n",
-       "  </thead>\n",
-       "  <tbody>\n",
-       "    <tr>\n",
-       "      <th>rl_alpha</th>\n",
-       "      <td>0.135</td>\n",
-       "      <td>0.042</td>\n",
-       "      <td>0.249</td>\n",
-       "      <td>0.08</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>scaler</th>\n",
-       "      <td>2.121</td>\n",
-       "      <td>1.415</td>\n",
-       "      <td>2.875</td>\n",
-       "      <td>2.50</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>a</th>\n",
-       "      <td>1.315</td>\n",
-       "      <td>1.045</td>\n",
-       "      <td>1.591</td>\n",
-       "      <td>1.20</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>z</th>\n",
-       "      <td>0.466</td>\n",
-       "      <td>0.415</td>\n",
-       "      <td>0.519</td>\n",
-       "      <td>0.50</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>t</th>\n",
-       "      <td>0.231</td>\n",
-       "      <td>0.141</td>\n",
-       "      <td>0.328</td>\n",
-       "      <td>0.25</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>theta</th>\n",
-       "      <td>0.352</td>\n",
-       "      <td>0.240</td>\n",
-       "      <td>0.458</td>\n",
-       "      <td>0.35</td>\n",
-       "    </tr>\n",
-       "  </tbody>\n",
-       "</table>\n",
-       "</div>"
-      ],
-      "text/plain": [
-       "           mean  hdi94_lb  hdi94_ub  true\n",
-       "rl_alpha  0.135     0.042     0.249  0.08\n",
-       "scaler    2.121     1.415     2.875  2.50\n",
-       "a         1.315     1.045     1.591  1.20\n",
-       "z         0.466     0.415     0.519  0.50\n",
-       "t         0.231     0.141     0.328  0.25\n",
-       "theta     0.352     0.240     0.458  0.35"
-      ]
-     },
-     "execution_count": 17,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
+   "outputs": [],
    "source": [
     "group_summary = group_recovery(idata, GROUP_THETA)\n",
     "group_summary[[\"mean\", \"hdi94_lb\", \"hdi94_ub\", \"true\"]].round(3)"
@@ -1670,7 +530,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 18,
+   "execution_count": null,
    "id": "433a3627",
    "metadata": {},
    "outputs": [],
@@ -1791,28 +651,10 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 19,
+   "execution_count": null,
    "id": "4a32f6f7",
    "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "image/png": "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",
-      "text/plain": [
-       "<Figure size 1200x450 with 2 Axes>"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "PPC datasets: 8 | total rows: 2800\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "ppc_data = plot_rl_ppc(\n",
     "    idata,\n",
@@ -1862,8 +704,7 @@
    "mimetype": "text/x-python",
    "name": "python",
    "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.13.1"
+   "pygments_lexer": "ipython3"
   }
  },
  "nbformat": 4,