From 3a6c3e4a6ae09536dfeba3a2d5371dce861bb6c6 Mon Sep 17 00:00:00 2001
From: wassname <1103714+wassname@users.noreply.github.com>
Date: Sun, 25 Aug 2024 12:54:36 +0800
Subject: [PATCH] convert to pref data on hf

---
 .gitignore                                  |    7 +
 __pycache__/download_data.cpython-310.pyc   |  Bin 1215 -> 0 bytes
 nbs/01_mjc_convert_data_to_preference.ipynb | 2803 +++++++++++++++++++
 3 files changed, 2810 insertions(+)
 delete mode 100644 __pycache__/download_data.cpython-310.pyc
 create mode 100644 nbs/01_mjc_convert_data_to_preference.ipynb

diff --git a/.gitignore b/.gitignore
index 10fdd19..1a5c7ea 100644
--- a/.gitignore
+++ b/.gitignore
@@ -5,3 +5,10 @@ env/
 upload_data.py
 genies-datasets.tar
 distributions/
+.venv/
+__pycache__/
+*.pyc
+
+# jypter notebook
+.ipynb_checkpoints/
+
diff --git a/__pycache__/download_data.cpython-310.pyc b/__pycache__/download_data.cpython-310.pyc
deleted file mode 100644
index d694dc90880b10f6ed361df13c272a87011f6b62..0000000000000000000000000000000000000000
GIT binary patch
literal 0
HcmV?d00001

literal 1215
zcmZux&2H345O)7~re~5FSQhcGm8F#kW)+VXZU`YHAgjGZNQs2j7pvp$$vE-YLwB1Y
zBhM*Z5f6YOB}ZO?C*T?Sgv5#K9`^#(o=g<bcB!geRjsdny4q#0*Y#li>pzzteb4*i
zl=F*%@)%fegAkrTxfd^X6r)DRF>ZDe6M-caMA9J@RQPXb?2DFYzwzRhYzwxJ)g4KW
znQWaP1V~#Ahn=s0>}^^$%yL=qv9znAoECY>MIthlV&^_x40gv)fc0k(0@dDo?+DLv
z?afJz=G1t{sKzH~?$`bv78s%q4XKGBhxlE8-l|*26g<Am;RRGefes1s3ihX`!zoxD
z{R3=Tg4X1{C;TIF2zJxnV>NXZy~Ut)jvXpHaj5OOz1Ia_=k5QYZvTYZZBSQg3fQYh
zzQY#YmW$VOIlFq6wy?iB8;p#Z=m&$rt}HUC*9A8`()XiEuS>4Y`n`yc`K&DXR7Yt!
z9(?@-jj?#TGiz-?OM|u9?`y$`>tIL9B3SlTia=LsDzzR~d43RWhsZMdI@2a8_bpPO
z(g`=CS?@_%7+Dw{ltaL};jmuG1(<wo6i*FcnG$?>Et=ik;1IMiEJFomBm;N5QLtsW
zsdSK*LOuw>70Z--SxIfQCA-qZE4uL~&TnZsk%jfADl^iy(?u56pQx-b7MI$xG2fRk
zBHFeMS1y3<o@T`JJY>p^jv}rbq*8f&d6|$Di94OR`r_VM5pLXEMtV{f8sayI1fV~7
z>MEf8_s78Xey~^SQN@!qKNw3j`0Lr`-_N!NOYEe%p2>l|cxE|Gt_2YKHxOM+2_;>i
zRoq9nzFj1JNAPunT*m4;97%zHSgwj@>aW0ufw^xc5((_)dNDsC-JIQedir#-VmA<Q
znJU|<Oa}EtQ8fGY+yrT9bOf1M6opvz0ksL-6naiv1BdOMmEwxK4JPgW3k>y<y6FzE
zBpLIpNRqIlI$%)0IB@|)3|&;x63AqMzdY|=dXmI+1Kj80xjw5VD0?_AMU~4(2u%7C
Q2nG=yUBWD2w2$bw@9ZTy+5i9m

diff --git a/nbs/01_mjc_convert_data_to_preference.ipynb b/nbs/01_mjc_convert_data_to_preference.ipynb
new file mode 100644
index 0000000..cc807ce
--- /dev/null
+++ b/nbs/01_mjc_convert_data_to_preference.ipynb
@@ -0,0 +1,2803 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# convert `genies` datasets to [open_pref_eval](https://github.com/wassname/open_pref_eval)\n",
+    "\n",
+    "\n",
+    "Here I'm taking the GENIE datasets, and \n",
+    "1. converting them to preference (compatible with open_pref_eval)\n",
+    "2. hosting on huggingface"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "\n",
+    "## Setup\n",
+    "\n",
+    "```sh\n",
+    "python -m venv .venv --prompt GENIES\n",
+    ". .venv/bin/activate\n",
+    "pip install wheel fire requests\n",
+    "pip install -r requirements.txt\n",
+    "python ./download_data.py\n",
+    "```"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%reload_ext autoreload\n",
+    "%autoreload 2"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "from datasets import load_dataset\n",
+    "import datasets\n",
+    "\n",
+    "from pathlib import Path\n",
+    "import json"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[{'source': 'alpaca_easy', 'target': 'alpaca_hard'},\n",
+       " {'source': 'arc_easy', 'target': 'arc_hard'},\n",
+       " {'source': 'math_easy', 'target': 'math_hard'},\n",
+       " {'source': 'code_easy', 'target': 'code_hard'},\n",
+       " {'source': 'ranking_logic_easy', 'target': 'ranking_logic_hard'},\n",
+       " {'source': 'raven_easy', 'target': 'raven_matrices'},\n",
+       " {'source': 'alpaca_mmlu', 'target': 'spanish_input'},\n",
+       " {'source': 'alpaca_mmlu', 'target': 'spanish_output'},\n",
+       " {'source': 'alpaca_mmlu', 'target': 'comma_separated_input'},\n",
+       " {'source': 'alpaca_mmlu', 'target': 'comma_separated_output'},\n",
+       " {'source': 'alpaca_mmlu', 'target': 'ranking_logic'},\n",
+       " {'source': 'alpaca_mmlu', 'target': 'raven_matrices'},\n",
+       " {'source': 'alpaca_mmlu', 'target': 'word_swap'},\n",
+       " {'source': 'code', 'target': 'counterfactual_python'},\n",
+       " {'source': 'code', 'target': 'us_history'},\n",
+       " {'source': 'code', 'target': 'change_my_view'},\n",
+       " {'source': 'cooking', 'target': 'math'},\n",
+       " {'source': 'cooking', 'target': 'raven_matrices'},\n",
+       " {'source': 'math', 'target': 'change_my_view'},\n",
+       " {'source': 'math', 'target': 'cooking'},\n",
+       " {'source': 'change_my_view', 'target': 'raven_matrices'},\n",
+       " {'source': 'change_my_view', 'target': 'cooking'},\n",
+       " {'source': 'raven_matrices', 'target': 'us_history'},\n",
+       " {'source': 'raven_matrices', 'target': 'code'},\n",
+       " {'source': 'us_history', 'target': 'math'},\n",
+       " {'source': 'us_history', 'target': 'code'},\n",
+       " {'source': 'us_history', 'target': 'us_history_textbook'},\n",
+       " {'source': 'us_history_textbook', 'target': 'us_history_fiction'},\n",
+       " {'source': 'us_history_fiction', 'target': 'us_history_make_questions'},\n",
+       " {'source': 'us_history_make_questions', 'target': 'us_history'},\n",
+       " {'source': 'math', 'target': 'math_fiction'},\n",
+       " {'source': 'math_fiction', 'target': 'math_textbook'},\n",
+       " {'source': 'math_textbook', 'target': 'math_make_questions'},\n",
+       " {'source': 'math_make_questions', 'target': 'math'},\n",
+       " {'source': 'alpaca_low_quality', 'target': 'alpaca_high_quality'},\n",
+       " {'source': 'shp_low_quality', 'target': 'shp_high_quality'},\n",
+       " {'source': 'code_low_quality', 'target': 'code'},\n",
+       " {'source': 'alpaca_mmlu', 'target': 'truthful_qa'},\n",
+       " {'source': 'alpaca_mmlu', 'target': 'personality_traits'},\n",
+       " {'source': 'alpaca_mmlu', 'target': 'survival_influence'},\n",
+       " {'source': 'alpaca_mmlu', 'target': 'gender_bias'},\n",
+       " {'source': 'alpaca_mmlu', 'target': 'punishment_avoidance'},\n",
+       " {'source': 'alpaca_mmlu', 'target': 'reward_seeking'},\n",
+       " {'source': 'alpaca_mmlu', 'target': 'crt_1'},\n",
+       " {'source': 'alpaca_mmlu', 'target': 'crt_2'},\n",
+       " {'source': 'alpaca_mmlu', 'target': 'crt_3'},\n",
+       " {'source': 'alpaca_mmlu',\n",
+       "  'target': 'sycophancy_mimicry',\n",
+       "  'target_reference': 'quote_attribution'},\n",
+       " {'source': 'alpaca_mmlu',\n",
+       "  'target': 'sycophancy_answer',\n",
+       "  'target_reference': 'arc_easy'},\n",
+       " {'source': 'alpaca_mmlu',\n",
+       "  'target': 'sycophancy_feedback',\n",
+       "  'target_reference': 'code_is_correct'},\n",
+       " {'source': 'alpaca_chat',\n",
+       "  'target': 'sycophancy_are_you_sure',\n",
+       "  'target_reference': 'arc_easy'},\n",
+       " {'source': 'pursue_goals', 'target': 'relinquish_power'},\n",
+       " {'source': 'creative_writing', 'target': 'biology_with_literary_style'},\n",
+       " {'source': 'alpaca_short',\n",
+       "  'target': 'alpaca_long',\n",
+       "  'target_reference': 'alpaca_mmlu'},\n",
+       " {'source': 'alpaca_chat', 'target': 'illegal_dont_help'},\n",
+       " {'source': 'alpaca_mmlu', 'target': 'wrong_arc'},\n",
+       " {'source': 'alpaca_mmlu', 'target': 'unhelpful_alpaca'},\n",
+       " {'source': 'alpaca_mmlu', 'target': 'truthful_qa'},\n",
+       " {'source': 'alpaca_mmlu', 'target': 'personality_traits'},\n",
+       " {'source': 'alpaca_mmlu', 'target': 'gender_bias'},\n",
+       " {'source': 'alpaca_mmlu', 'target': 'survival_influence'},\n",
+       " {'source': 'alpaca_mmlu', 'target': 'punishment_avoidance'},\n",
+       " {'source': 'alpaca_mmlu', 'target': 'reward_seeking'},\n",
+       " {'source': 'alpaca_mmlu', 'target': 'crt_1'},\n",
+       " {'source': 'alpaca_mmlu', 'target': 'crt_2'},\n",
+       " {'source': 'alpaca_mmlu', 'target': 'crt_3'},\n",
+       " {'source': 'alpaca_mmlu',\n",
+       "  'target': 'sycophancy_mimicry',\n",
+       "  'target_reference': 'quote_attribution'},\n",
+       " {'source': 'alpaca_mmlu',\n",
+       "  'target': 'sycophancy_answer',\n",
+       "  'target_reference': 'arc_easy'},\n",
+       " {'source': 'alpaca_mmlu',\n",
+       "  'target': 'sycophancy_feedback',\n",
+       "  'target_reference': 'code_is_correct'},\n",
+       " {'source': 'alpaca_chat',\n",
+       "  'target': 'sycophancy_are_you_sure',\n",
+       "  'target_reference': 'arc_easy'}]"
+      ]
+     },
+     "execution_count": 8,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "path_to_distribution_shift_pairs = Path('../distribution_shifts/all.json')\n",
+    "pairs_data = json.load(open(path_to_distribution_shift_pairs))\n",
+    "pairs_data"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'id': 'alpaca_easy', 'external_datasets': [], 'overlapping_datasets': []}"
+      ]
+     },
+     "execution_count": 13,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 48,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from datasets import DatasetInfo, Dataset\n",
+    "\n",
+    "def genie2ds(train: list) -> pd.DataFrame:\n",
+    "    \"\"\"takes the GENIE format and convert it to to a dataframe of preference format.\"\"\"\n",
+    "    outs = []\n",
+    "    for i, row in enumerate(train):\n",
+    "        s = pd.Series(row['responses'])\n",
+    "        chosen = s[s==1].index[0]\n",
+    "        rejected = s[s==0].index\n",
+    "        outs += [dict(prompt=row['prompt'], chosen=chosen, rejected=r, i=i) for r in rejected]\n",
+    "\n",
+    "    df = pd.DataFrame(outs)\n",
+    "    return df\n",
+    "\n",
+    "\n",
+    "\n",
+    "def json2ds(source_dir: Path) -> Dataset:\n",
+    "    test = json.load(open(source_dir / 'test.json'))\n",
+    "    train = json.load(open(source_dir / 'train.json'))\n",
+    "    metadata = json.load(open(source_dir / 'metadata.json'))\n",
+    "    ds_info = DatasetInfo(\n",
+    "        description= f\"GENIE:{metadata['id']}\",\n",
+    "        citation= \"\"\"@misc{clymer2023generalizationanalogiestestbedgeneralizing,\n",
+    "        title={Generalization Analogies: A Testbed for Generalizing AI Oversight to Hard-To-Measure Domains}, \n",
+    "        author={Joshua Clymer and Garrett Baker and Rohan Subramani and Sam Wang},\n",
+    "        year={2023},\n",
+    "        eprint={2311.07723},\n",
+    "        archivePrefix={arXiv},\n",
+    "        primaryClass={cs.AI},\n",
+    "        url={https://arxiv.org/abs/2311.07723}, \n",
+    "    }\"\"\",\n",
+    "        homepage= \"https://joshuaclymer.github.io/generalization-analogies-website/\",\n",
+    "        license= \"MIT\",\n",
+    "        config_name=f\"{metadata['id']}\",\n",
+    "    )\n",
+    "\n",
+    "\n",
+    "    df_train = genie2ds(train)\n",
+    "    df_test = genie2ds(test)\n",
+    "    dataset2 = datasets.DatasetDict(\n",
+    "            {'train': datasets.Dataset.from_pandas(df_train, info=ds_info),\n",
+    "                'test': datasets.Dataset.from_pandas(df_test, info=ds_info)}\n",
+    "        )\n",
+    "    return dataset2"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 53,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "../distributions/alpaca_easy alpaca_easy\n"
+     ]
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "70cf450126b54157bab78571208e91d4",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Pushing dataset shards to the dataset hub:   0%|          | 0/1 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "4f8e24cda88f4fd88a44af913f193d89",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Pushing dataset shards to the dataset hub:   0%|          | 0/1 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "4f97820ed64b4f62838702a7af7212b4",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Downloading metadata:   0%|          | 0.00/679 [00:00<?, ?B/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "../distributions/alpaca_hard alpaca_hard\n"
+     ]
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "3a067ca3cea84ab3a55aa5514b1a73ce",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Pushing dataset shards to the dataset hub:   0%|          | 0/1 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "e0f09f44343f4a32a73e02a38dc14b1b",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Creating parquet from Arrow format:   0%|          | 0/2 [00:00<?, ?ba/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "9a6752efb7e242ba81b856ac1bbf05f9",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Pushing dataset shards to the dataset hub:   0%|          | 0/1 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "510c37c8b75844f4862cc64bd8f6af9a",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Creating parquet from Arrow format:   0%|          | 0/1 [00:00<?, ?ba/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "2de75849d76244cba0bb65ee3e3b4340",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Downloading metadata:   0%|          | 0.00/674 [00:00<?, ?B/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "../distributions/arc_easy arc_easy\n"
+     ]
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "9f7f957b14e84722baf0add558fd49f8",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Pushing dataset shards to the dataset hub:   0%|          | 0/1 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "97c9c5690e484f7c9c27eb2847affc9a",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Creating parquet from Arrow format:   0%|          | 0/2 [00:00<?, ?ba/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "8b011a5661dc40cfa67a9fa4ace303ec",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Pushing dataset shards to the dataset hub:   0%|          | 0/1 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "694c790e112541e2ac331caf9811b011",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Creating parquet from Arrow format:   0%|          | 0/1 [00:00<?, ?ba/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "0aa03337378e4f589f1991f3f0693d1c",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Downloading metadata:   0%|          | 0.00/1.16k [00:00<?, ?B/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "../distributions/arc_hard arc_hard\n"
+     ]
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "d91594b8801e428491dbb2b817915f6b",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Pushing dataset shards to the dataset hub:   0%|          | 0/1 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "6623777485d644ab9a9b4d69c97bbe16",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Creating parquet from Arrow format:   0%|          | 0/2 [00:00<?, ?ba/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "79195cbd6e344221be1bc42bf40d3526",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Pushing dataset shards to the dataset hub:   0%|          | 0/1 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "0dfc22ac337740f59d6b9c05a2e02d0c",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Creating parquet from Arrow format:   0%|          | 0/1 [00:00<?, ?ba/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "7c9b29ece5674deb9e99913941d72af6",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Downloading metadata:   0%|          | 0.00/1.63k [00:00<?, ?B/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "../distributions/math_easy math_easy\n"
+     ]
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "25259001f3cc4224836c27ca7618f8de",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Pushing dataset shards to the dataset hub:   0%|          | 0/1 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "f615931bc55c47bc862d1c31ca1d7b6f",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Creating parquet from Arrow format:   0%|          | 0/2 [00:00<?, ?ba/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "99e34166d5e14a878839bbd213ebf1b4",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Pushing dataset shards to the dataset hub:   0%|          | 0/1 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "1cac73b2aa904bec87ea805cdea1c8b1",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Creating parquet from Arrow format:   0%|          | 0/1 [00:00<?, ?ba/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "73d9750571154d74828eaf3c2e0959e8",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Downloading metadata:   0%|          | 0.00/2.11k [00:00<?, ?B/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "../distributions/math_hard math_hard\n"
+     ]
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "cea48d9e083d4440817cfc75f1c6cf8f",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Pushing dataset shards to the dataset hub:   0%|          | 0/1 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "ba81e23c99764c38a1b5eba4c5a2d45b",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Creating parquet from Arrow format:   0%|          | 0/2 [00:00<?, ?ba/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "9d9fb374680f4139b046e36a03e45852",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Pushing dataset shards to the dataset hub:   0%|          | 0/1 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "3900fbe7fe824075904dacf135066650",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Creating parquet from Arrow format:   0%|          | 0/1 [00:00<?, ?ba/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "ff0f32d7ff04443bafa9752ccedd8351",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Downloading metadata:   0%|          | 0.00/2.59k [00:00<?, ?B/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "../distributions/code_easy code_easy\n"
+     ]
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "b2db8dcd05ec417e82e5bb1f20ae83cb",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Pushing dataset shards to the dataset hub:   0%|          | 0/1 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "e3f33810d2bf42da87df75486f3ccdfc",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Creating parquet from Arrow format:   0%|          | 0/2 [00:00<?, ?ba/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "e0df73abe46d44f490f649514c17bfc2",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Pushing dataset shards to the dataset hub:   0%|          | 0/1 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "0337b348706e4940b8de997705a97bb4",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Creating parquet from Arrow format:   0%|          | 0/1 [00:00<?, ?ba/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "18569a0d8def4789bdfdb95f6b662abc",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Downloading metadata:   0%|          | 0.00/3.06k [00:00<?, ?B/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "../distributions/code_hard code_hard\n"
+     ]
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "e2061321c08547b786b212cbfff3f409",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Pushing dataset shards to the dataset hub:   0%|          | 0/1 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "d567b6d734c44bf592f8b82562ea5f31",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Creating parquet from Arrow format:   0%|          | 0/2 [00:00<?, ?ba/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "ecc9f6a76631437db203ad76f1b5e3f3",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Pushing dataset shards to the dataset hub:   0%|          | 0/1 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "b853a8bae71f479e9954fda4aca7a0c5",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Creating parquet from Arrow format:   0%|          | 0/1 [00:00<?, ?ba/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "633d2ae212434b32972f60f2878950b3",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Downloading metadata:   0%|          | 0.00/3.54k [00:00<?, ?B/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "../distributions/ranking_logic_easy ranking_logic_easy\n"
+     ]
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "1804e9bd6928466082fe8e30092823cf",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Pushing dataset shards to the dataset hub:   0%|          | 0/1 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "ef27c1b30ec24eaea73f2967957765a8",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Creating parquet from Arrow format:   0%|          | 0/2 [00:00<?, ?ba/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "1f3db37f4b444fa9a43ab6101817daa2",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Pushing dataset shards to the dataset hub:   0%|          | 0/1 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "5214a312c23f4106a7ca5656acde68ad",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Creating parquet from Arrow format:   0%|          | 0/1 [00:00<?, ?ba/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "b4af18181f59471cbb48a13627bf6a88",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Downloading metadata:   0%|          | 0.00/4.02k [00:00<?, ?B/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "../distributions/ranking_logic_hard ranking_logic_hard\n"
+     ]
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "da108c1060b445a79f4298fe2deb4fea",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Pushing dataset shards to the dataset hub:   0%|          | 0/1 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "02679bd280bc4b628a797748732a4396",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Creating parquet from Arrow format:   0%|          | 0/2 [00:00<?, ?ba/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "50177763c2e141d79479d610879848cb",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Pushing dataset shards to the dataset hub:   0%|          | 0/1 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "ca1e26d02ba74c0f98267f714ae4b1b2",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Creating parquet from Arrow format:   0%|          | 0/1 [00:00<?, ?ba/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "ea893c7b94e849e89ef42f319292d723",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Downloading metadata:   0%|          | 0.00/4.54k [00:00<?, ?B/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "../distributions/raven_easy raven_easy\n"
+     ]
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "5240ac5f375a488dba0ab12e2ff6e385",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Pushing dataset shards to the dataset hub:   0%|          | 0/1 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "a476745f9f1f42eb8cb9b6e370729376",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Creating parquet from Arrow format:   0%|          | 0/2 [00:00<?, ?ba/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "405c92534e964a21acd4e9e14e3b9a19",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Pushing dataset shards to the dataset hub:   0%|          | 0/1 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "06cb1da72e6145518f6425a45ced73a0",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Creating parquet from Arrow format:   0%|          | 0/1 [00:00<?, ?ba/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "3d4efe9a807d4a02ad7afa3c3c38f85e",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Downloading metadata:   0%|          | 0.00/5.05k [00:00<?, ?B/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "../distributions/raven_matrices raven_matrices\n"
+     ]
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "9fdff49603be40a09545a6829c61ebf4",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Pushing dataset shards to the dataset hub:   0%|          | 0/1 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "964893f8e1fe4a0c8fddcde5069d4229",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Creating parquet from Arrow format:   0%|          | 0/2 [00:00<?, ?ba/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "c1ae94e26f2d447ea37e1de14d62e21f",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Pushing dataset shards to the dataset hub:   0%|          | 0/1 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "459e9b87f6754056bf9dbcae720165ae",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Creating parquet from Arrow format:   0%|          | 0/1 [00:00<?, ?ba/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "93cc99f7ebd348db8be63a52e5d52c00",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Downloading metadata:   0%|          | 0.00/5.53k [00:00<?, ?B/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "../distributions/alpaca_mmlu alpaca_mmlu\n"
+     ]
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "e93c16f1284f4f4ba2d9272df5fe7d71",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Pushing dataset shards to the dataset hub:   0%|          | 0/1 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "408dad98e8bc412b9608fa9cd3a9d08b",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Creating parquet from Arrow format:   0%|          | 0/2 [00:00<?, ?ba/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "2bead6f43ade4c5e813549d9eb7a93fc",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Pushing dataset shards to the dataset hub:   0%|          | 0/1 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "de5e7d6e71004fdbbee4e860b26eeadc",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Creating parquet from Arrow format:   0%|          | 0/1 [00:00<?, ?ba/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "9022f4fcd12b47e185b19d67a42abee8",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Downloading metadata:   0%|          | 0.00/6.03k [00:00<?, ?B/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "../distributions/spanish_input spanish_input\n"
+     ]
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "d1705ba4f8e74c56804f98935433bbc9",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Pushing dataset shards to the dataset hub:   0%|          | 0/1 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "841482d4842942ef84b7203fb117608e",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Creating parquet from Arrow format:   0%|          | 0/2 [00:00<?, ?ba/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "fa040e24eb1d43e290a4ea16df0ad887",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Pushing dataset shards to the dataset hub:   0%|          | 0/1 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "cdc292ed773c4ce4b5e5efc0ee1f38d8",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Creating parquet from Arrow format:   0%|          | 0/1 [00:00<?, ?ba/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "677cb2055be744d6b48897d338b18a13",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Downloading metadata:   0%|          | 0.00/6.51k [00:00<?, ?B/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "../distributions/alpaca_mmlu alpaca_mmlu\n"
+     ]
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "7d1994457667457cb3095f2ce81a2fbb",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Pushing dataset shards to the dataset hub:   0%|          | 0/1 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "03c1d5ea26234772bc97d4b33b0228e6",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Pushing dataset shards to the dataset hub:   0%|          | 0/1 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "961410c7b3b04025b29cb3b48b2821b3",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Downloading metadata:   0%|          | 0.00/7.01k [00:00<?, ?B/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "../distributions/spanish_output spanish_output\n"
+     ]
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "0385ad64622c4fc9901d21a07788bdf4",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Pushing dataset shards to the dataset hub:   0%|          | 0/1 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "1b0d9779e45a411f8c560b81d2a937cc",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Creating parquet from Arrow format:   0%|          | 0/2 [00:00<?, ?ba/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "0191cf6b3fc94a6e847780d60e576de6",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Pushing dataset shards to the dataset hub:   0%|          | 0/1 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "386608379da9444e935f570a2f8a1a4c",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Creating parquet from Arrow format:   0%|          | 0/1 [00:00<?, ?ba/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "4b346bfb07384432a5e52c86369b4cb4",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Downloading metadata:   0%|          | 0.00/7.00k [00:00<?, ?B/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "../distributions/alpaca_mmlu alpaca_mmlu\n"
+     ]
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "032f832803d3422099e3069f578ea21c",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Pushing dataset shards to the dataset hub:   0%|          | 0/1 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "d2fc5b6437ad417e99e18277797a7265",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Pushing dataset shards to the dataset hub:   0%|          | 0/1 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "a4fa533498214e6285638081f8aaadef",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Downloading metadata:   0%|          | 0.00/7.50k [00:00<?, ?B/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "../distributions/comma_separated_input comma_separated_input\n"
+     ]
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "a33284a0d7a74f069afc809ad2ad8d6b",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Pushing dataset shards to the dataset hub:   0%|          | 0/1 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "c8c8455c07c84960910c7641f3283943",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Creating parquet from Arrow format:   0%|          | 0/2 [00:00<?, ?ba/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "1633fc996b6d41b09e871ff330cd8c8c",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Pushing dataset shards to the dataset hub:   0%|          | 0/1 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "06d60522baf64221a3623c2deeb56868",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Creating parquet from Arrow format:   0%|          | 0/1 [00:00<?, ?ba/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "../distributions/alpaca_mmlu alpaca_mmlu\n"
+     ]
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "080efdbbd39a4091aba709ddb6b34fe0",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Pushing dataset shards to the dataset hub:   0%|          | 0/1 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "ce47ab3a596c43aa94229e3a4e9ab52c",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Pushing dataset shards to the dataset hub:   0%|          | 0/1 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "7bb762c2d1a6464e8eaa51f91ff350b6",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Downloading metadata:   0%|          | 0.00/8.03k [00:00<?, ?B/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "../distributions/comma_separated_output comma_separated_output\n"
+     ]
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "929f5bf8b8bf4fd293dca660c6e45efb",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Pushing dataset shards to the dataset hub:   0%|          | 0/1 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "5d3462a92c9d4456bab69287339f7165",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Creating parquet from Arrow format:   0%|          | 0/2 [00:00<?, ?ba/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "13a7cc05f8944ce88b6ef374e897052d",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Pushing dataset shards to the dataset hub:   0%|          | 0/1 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "5c44d632247b44149be5abaa97207459",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Creating parquet from Arrow format:   0%|          | 0/1 [00:00<?, ?ba/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "../distributions/alpaca_mmlu alpaca_mmlu\n"
+     ]
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "6b8a59b5738c4037a2b7186b3a5ba194",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Pushing dataset shards to the dataset hub:   0%|          | 0/1 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "cb94ed5f06324ea184bfb72747224ae8",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Pushing dataset shards to the dataset hub:   0%|          | 0/1 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "fed593d4bd3d4c57836076d626353e63",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Downloading metadata:   0%|          | 0.00/8.56k [00:00<?, ?B/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "../distributions/ranking_logic ranking_logic\n"
+     ]
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "62a077b96d064a9fbacb81c0d48ab6b1",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Pushing dataset shards to the dataset hub:   0%|          | 0/1 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "3fedfa97bacd4b4bbb75622fc01084ee",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Creating parquet from Arrow format:   0%|          | 0/2 [00:00<?, ?ba/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "8815c00d76c646fda827ff1b0ea06cd9",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Pushing dataset shards to the dataset hub:   0%|          | 0/1 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "a649ae5ff24f4b2baf37258645d4700c",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Creating parquet from Arrow format:   0%|          | 0/1 [00:00<?, ?ba/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "../distributions/alpaca_mmlu alpaca_mmlu\n"
+     ]
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "b5f8d3ea72ed4a10ac4b58ebcca595db",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Pushing dataset shards to the dataset hub:   0%|          | 0/1 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "80fdd0deee0442ad8916fe421b6f4ba8",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Pushing dataset shards to the dataset hub:   0%|          | 0/1 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "a241a2cda70b45eaaf5b1b80aec21410",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Downloading metadata:   0%|          | 0.00/9.05k [00:00<?, ?B/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "../distributions/raven_matrices raven_matrices\n"
+     ]
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "ec555be2d25e46aca51438a9797e3eca",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Pushing dataset shards to the dataset hub:   0%|          | 0/1 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "127336e57b8241869f803130374d19a1",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Pushing dataset shards to the dataset hub:   0%|          | 0/1 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "../distributions/alpaca_mmlu alpaca_mmlu\n"
+     ]
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "05f321bb1eb54c3789593292b345e343",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Pushing dataset shards to the dataset hub:   0%|          | 0/1 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "86dc54cafbce4fdaae236648a8b75855",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Pushing dataset shards to the dataset hub:   0%|          | 0/1 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "ca6960afb93048838a18b7bc620eaa01",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Downloading metadata:   0%|          | 0.00/9.05k [00:00<?, ?B/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "../distributions/word_swap word_swap\n"
+     ]
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "4a889e3b1eef47d4866fe6c23f0750a2",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Pushing dataset shards to the dataset hub:   0%|          | 0/1 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "feb4976120f1440cb6f602f1f39ffcc8",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Creating parquet from Arrow format:   0%|          | 0/2 [00:00<?, ?ba/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "080ef0f26fb14e84a42f7318a5a44298",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Pushing dataset shards to the dataset hub:   0%|          | 0/1 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "f8c509e39c0d4e08883c1f4efd8cfd54",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Creating parquet from Arrow format:   0%|          | 0/1 [00:00<?, ?ba/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "../distributions/code code\n"
+     ]
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "090067555c7d416db66543636d518e07",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Pushing dataset shards to the dataset hub:   0%|          | 0/1 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "069d96db9cdc4bc2b3581c405d2c0548",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Creating parquet from Arrow format:   0%|          | 0/2 [00:00<?, ?ba/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "d74897c24d4142db88589bf39f4894d4",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Pushing dataset shards to the dataset hub:   0%|          | 0/1 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "a945c6cd28df45f0847e04387ce2633b",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Creating parquet from Arrow format:   0%|          | 0/1 [00:00<?, ?ba/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "f201d1e03cab4ec7a1205def34e785d9",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Downloading metadata:   0%|          | 0.00/9.53k [00:00<?, ?B/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "../distributions/counterfactual_python counterfactual_python\n"
+     ]
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "1f05fc0ea96d48edbe7f9f90229dcb6e",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Pushing dataset shards to the dataset hub:   0%|          | 0/1 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "6769f3b38b604d8d91a2aafaeb2650fb",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Creating parquet from Arrow format:   0%|          | 0/2 [00:00<?, ?ba/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "14244dbe1ac44873949e4036c337951f",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Pushing dataset shards to the dataset hub:   0%|          | 0/1 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "c87187e5096f4279a38992d8558d9273",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Creating parquet from Arrow format:   0%|          | 0/1 [00:00<?, ?ba/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "a9e3c4b29b544ae798f0f185eec986f9",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Downloading metadata:   0%|          | 0.00/9.98k [00:00<?, ?B/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "../distributions/code code\n"
+     ]
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "e09e8ca475db4e85a3db0dd48e583d7a",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Pushing dataset shards to the dataset hub:   0%|          | 0/1 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "b994a402238a4e6b8b88a1b2b7ddb982",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Pushing dataset shards to the dataset hub:   0%|          | 0/1 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "9857ce1c7b944a48b22f85517afc01f9",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Downloading metadata:   0%|          | 0.00/10.5k [00:00<?, ?B/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "../distributions/us_history us_history\n"
+     ]
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "cb7c4f68cc534d8daf231c38c29b868d",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Pushing dataset shards to the dataset hub:   0%|          | 0/1 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "d4c85f16e2ee4e1889c0a85eee426800",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Creating parquet from Arrow format:   0%|          | 0/2 [00:00<?, ?ba/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "fa50418f0acc41a99d406f9ace2c82fc",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Pushing dataset shards to the dataset hub:   0%|          | 0/1 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "1058f5660ac44bd799f01f0173db7015",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Creating parquet from Arrow format:   0%|          | 0/1 [00:00<?, ?ba/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "32d77b9216b44ba9a120b6191d89f0a0",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Downloading metadata:   0%|          | 0.00/10.5k [00:00<?, ?B/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "../distributions/code code\n"
+     ]
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "3a331282a4b1446584ae50dc2f077abc",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Pushing dataset shards to the dataset hub:   0%|          | 0/1 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "14e6076594674a4397aec17e3bb3ecb2",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Pushing dataset shards to the dataset hub:   0%|          | 0/1 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "bb7f46a630a04899bc549b6d9906384d",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Downloading metadata:   0%|          | 0.00/11.0k [00:00<?, ?B/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "../distributions/change_my_view change_my_view\n"
+     ]
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "472c0695cbbb406c8fb3558fc1d59232",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Pushing dataset shards to the dataset hub:   0%|          | 0/1 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "94ecf7077a754885b9d6d690b4620ed5",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Creating parquet from Arrow format:   0%|          | 0/1 [00:00<?, ?ba/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "d0b923256e92485da6846e8b7c3a4d18",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Pushing dataset shards to the dataset hub:   0%|          | 0/1 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "6b722b419158462e98b233d6b5bc7883",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Creating parquet from Arrow format:   0%|          | 0/1 [00:00<?, ?ba/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "../distributions/cooking cooking\n"
+     ]
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "d333a4d0887542cba1e74580116a11ac",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Pushing dataset shards to the dataset hub:   0%|          | 0/1 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "c20365b899594cc9803266aeb3793970",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Creating parquet from Arrow format:   0%|          | 0/2 [00:00<?, ?ba/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "289436f7af7d439ea4876f97f784dbc3",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Pushing dataset shards to the dataset hub:   0%|          | 0/1 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "e4e15c20e02d4a76b0fa6fca2d610b0c",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Creating parquet from Arrow format:   0%|          | 0/1 [00:00<?, ?ba/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "4674daf825ec4354b8197a7226d46681",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Downloading metadata:   0%|          | 0.00/11.5k [00:00<?, ?B/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "../distributions/math math\n"
+     ]
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "23cf103acbd945bfaad652ffbf452a50",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Pushing dataset shards to the dataset hub:   0%|          | 0/1 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "e6a67417737d4bc0a1b479c0010fd25c",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Creating parquet from Arrow format:   0%|          | 0/2 [00:00<?, ?ba/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "c6e4be62b521458cb6658d84546d2e72",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Pushing dataset shards to the dataset hub:   0%|          | 0/1 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "179498b802004634b8f00ee4250dacc9",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Creating parquet from Arrow format:   0%|          | 0/1 [00:00<?, ?ba/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "f355a2bfc16745eaaeaaea80bf0181ea",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Downloading metadata:   0%|          | 0.00/12.0k [00:00<?, ?B/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "../distributions/cooking cooking\n"
+     ]
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "075e2ea8d43d4774b1d902e43e995b20",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Pushing dataset shards to the dataset hub:   0%|          | 0/1 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "350625a2eece4885be68d2f877dfedd8",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Pushing dataset shards to the dataset hub:   0%|          | 0/1 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "2dada13df87b478092dbf69af392c786",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Downloading metadata:   0%|          | 0.00/12.4k [00:00<?, ?B/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "../distributions/raven_matrices raven_matrices\n"
+     ]
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "cc816e1257824d53bd9fc8508b00c235",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Pushing dataset shards to the dataset hub:   0%|          | 0/1 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "7d8ff5bc09ec4a97809c7168eb478672",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Pushing dataset shards to the dataset hub:   0%|          | 0/1 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "be79fe3d5d09460da1ead68386c81d1f",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Downloading metadata:   0%|          | 0.00/12.4k [00:00<?, ?B/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "../distributions/math math\n"
+     ]
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "65a4699f3bce4f6d83d94d5753a0d38d",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Pushing dataset shards to the dataset hub:   0%|          | 0/1 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "c8d9b3fb85bd4ca69c1b3d5480076712",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Pushing dataset shards to the dataset hub:   0%|          | 0/1 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "../distributions/change_my_view change_my_view\n"
+     ]
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "aa190d60040c4ce0afad8fd613f6b2bf",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Pushing dataset shards to the dataset hub:   0%|          | 0/1 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "15f4d31bdaf848e9820f66aa10218f73",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Pushing dataset shards to the dataset hub:   0%|          | 0/1 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "28070f55dee84e12a2edc95bd470a0f9",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Downloading metadata:   0%|          | 0.00/12.4k [00:00<?, ?B/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "../distributions/math math\n"
+     ]
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "9ed1dca5adc74f498c9d7f1633e483e0",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Pushing dataset shards to the dataset hub:   0%|          | 0/1 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "dc5c97ce90ce4d43b4af08aa1599bdea",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Pushing dataset shards to the dataset hub:   0%|          | 0/1 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "ac711755af7b4f91b79eded0e7c801fd",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Downloading metadata:   0%|          | 0.00/12.4k [00:00<?, ?B/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "../distributions/cooking cooking\n"
+     ]
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "ef451edfc4964e12be48fc6012aee5c7",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Pushing dataset shards to the dataset hub:   0%|          | 0/1 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "a25353c4e34d49019547b8c30d30e064",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Pushing dataset shards to the dataset hub:   0%|          | 0/1 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "dist_dir = Path('../distributions')\n",
+    "\n",
+    "for pair in  pairs_data:\n",
+    "    for key in ['source', 'target']:\n",
+    "        source_dir = dist_dir / pair[key]\n",
+    "\n",
+    "        dataset2 = json2ds(source_dir)\n",
+    "        config_name = dataset2['train'].info.config_name\n",
+    "        print(source_dir, config_name, dataset2)\n",
+    "\n",
+    "        dataset2.push_to_hub(\"wassname/genie_dpo\", config_name=config_name)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": ".venv",
+   "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": "3.10.12"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}