diff --git a/research/mistral/add_not_add.ipynb b/research/mistral/add_not_add.ipynb new file mode 100644 index 0000000..4be9924 --- /dev/null +++ b/research/mistral/add_not_add.ipynb @@ -0,0 +1,7059 @@ +{ + "cells": [ + { + "cell_type": "code", + "execution_count": 1, + "metadata": { + "id": "3sqPzXakzsjr" + }, + "outputs": [], + "source": [ + "import locale\n", + "locale.getpreferredencoding = lambda: \"UTF-8\"" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "2RN7-BfNmL_a" + }, + "source": [ + "Set up Python environment" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "xjSiIqgfkRBm" + }, + "source": [ + "***fine-tune LLaMA 2 models on datasets***\n", + "\n" + ] + }, + { + "cell_type": "code", + "execution_count": 2, + "metadata": { + "id": "RlCJkFt-SOcR" + }, + "outputs": [], + "source": [ + "import argparse\n", + "import bitsandbytes as bnb\n", + "from datasets import load_dataset\n", + "from functools import partial\n", + "import os\n", + "from peft import LoraConfig, get_peft_model, prepare_model_for_kbit_training, AutoPeftModelForCausalLM\n", + "import torch\n", + "from transformers import AutoModelForCausalLM, AutoTokenizer, set_seed, Trainer, TrainingArguments, BitsAndBytesConfig, \\\n", + " DataCollatorForLanguageModeling, Trainer, TrainingArguments" + ] + }, + { + "cell_type": "code", + "execution_count": 4, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "Yv3eCc3lkSax", + "outputId": "0c37df8e-e0f7-4498-8594-47b3f0ab0598" + }, + "outputs": [ + { + "data": { + "text/plain": [ + "True" + ] + }, + "execution_count": 4, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "import torch\n", + "torch.cuda.is_available()" + ] + }, + { + "cell_type": "code", + "execution_count": 31, + "metadata": { + "id": "qe37RE3_ok1u" + }, + "outputs": [], + "source": [ + "import pandas as pd\n", + "import time" + ] + }, + { + "cell_type": "code", + "execution_count": 32, + "metadata": { + "id": "TrsDmPP_p5WN" + }, + "outputs": [], + "source": [ + "file_path = \"/home/nasrallah_hassan/AmharicAI-AdGen/data/parsed/all_data.csv\"\n", + "dataset_file_path = \"/content/drive/My Drive/Datasets/W_7/ad-not-add.csv\"" + ] + }, + { + "cell_type": "code", + "execution_count": 33, + "metadata": { + "id": "9qe5fS_7txOv" + }, + "outputs": [], + "source": [ + "df = pd.read_csv(file_path)" + ] + }, + { + "cell_type": "code", + "execution_count": 34, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 206 + }, + "id": "JB_c6v95wWRm", + "outputId": "e73473cc-34bb-4299-8d8a-7ea7c836f2fc" + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
textlabel
4701የኑዌር ዞን በርካታ ደጋፊዎች ጅማ እስታዲየም በመገኘት ጨዋታውን እያደመቁ...Not ad
4702🇪🇹 #የኢትዮጵያ_አንደኛ_ሊግ_ምድብ_ለ_ሶዶ ⌚️85' ✅ #ካማሺ_ከተማ...Not ad
4703ጎልልልልልልልል ነጌሌ ቦረና 77'⚽️አዲሱ ተሰማNot ad
4704ጎልልልልልልልልልልል ካማሺ ከተማ 90+1'Not ad
4705🇪🇹 #የኢትዮጵያ_አንደኛ_ሊግ_ምድብ_ሀ ⌚️85' ✅ #ነጌሌ_ቦረና 1-...Not ad
\n", + "
" + ], + "text/plain": [ + " text label\n", + "4701 የኑዌር ዞን በርካታ ደጋፊዎች ጅማ እስታዲየም በመገኘት ጨዋታውን እያደመቁ... Not ad\n", + "4702 🇪🇹 #የኢትዮጵያ_አንደኛ_ሊግ_ምድብ_ለ_ሶዶ ⌚️85' ✅ #ካማሺ_ከተማ... Not ad\n", + "4703 ጎልልልልልልልል ነጌሌ ቦረና 77'⚽️አዲሱ ተሰማ Not ad\n", + "4704 ጎልልልልልልልልልልል ካማሺ ከተማ 90+1' Not ad\n", + "4705 🇪🇹 #የኢትዮጵያ_አንደኛ_ሊግ_ምድብ_ሀ ⌚️85' ✅ #ነጌሌ_ቦረና 1-... Not ad" + ] + }, + "execution_count": 34, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df.tail()" + ] + }, + { + "cell_type": "code", + "execution_count": 35, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 206 + }, + "id": "_o6EC87Dwvqe", + "outputId": "c5924c12-b8fd-44f3-c63c-45c92004d96d" + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
textlabel
0Tecno Spark 20 pro + \\n\\nአስገራሚ የቴክኖሎጂ ውጤቶችን ያካ...Ad
1#DELL PRECISION \\n#EUROPE STANDARD \\n🅑︎🅡︎🅐︎🅝︎🅓...Ad
2አይብ በሚዘጋጅበት ጊዜ ከቅቤው ከሚለየው ወተት ውስጥ ካለው የውሃ ክፍል ...Ad
3👨🏾‍⚕️🐠የአሳ ዘይት(ኦሜጋ -3 ፋቲ አሲድ)ለሰዉነታችን አስፈላጊ ከሚባሉ...Ad
4ቴሌግራም👉 👨🏾‍⚕️የአሳ ዘይት(ኦሜጋ -3 ፋቲ አሲድ)ለሰዉነታችን አስፈላ...Ad
\n", + "
" + ], + "text/plain": [ + " text label\n", + "0 Tecno Spark 20 pro + \\n\\nአስገራሚ የቴክኖሎጂ ውጤቶችን ያካ... Ad\n", + "1 #DELL PRECISION \\n#EUROPE STANDARD \\n🅑︎🅡︎🅐︎🅝︎🅓... Ad\n", + "2 አይብ በሚዘጋጅበት ጊዜ ከቅቤው ከሚለየው ወተት ውስጥ ካለው የውሃ ክፍል ... Ad\n", + "3 👨🏾‍⚕️🐠የአሳ ዘይት(ኦሜጋ -3 ፋቲ አሲድ)ለሰዉነታችን አስፈላጊ ከሚባሉ... Ad\n", + "4 ቴሌግራም👉 👨🏾‍⚕️የአሳ ዘይት(ኦሜጋ -3 ፋቲ አሲድ)ለሰዉነታችን አስፈላ... Ad" + ] + }, + "execution_count": 35, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "dataset = df[['text','label']]\n", + "dataset.head()" + ] + }, + { + "cell_type": "code", + "execution_count": 36, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "nFfm1ETLvD0_", + "outputId": "5760ce68-5a33-4db7-f3b5-2ae6dcfddc32" + }, + "outputs": [ + { + "data": { + "text/plain": [ + "(4706, 2)" + ] + }, + "execution_count": 36, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "dataset.shape" + ] + }, + { + "cell_type": "code", + "execution_count": 37, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
textlabel
0Tecno Spark 20 pro + \\n\\nአስገራሚ የቴክኖሎጂ ውጤቶችን ያካ...Ad
1#DELL PRECISION \\n#EUROPE STANDARD \\n🅑︎🅡︎🅐︎🅝︎🅓...Ad
2አይብ በሚዘጋጅበት ጊዜ ከቅቤው ከሚለየው ወተት ውስጥ ካለው የውሃ ክፍል ...Ad
3👨🏾‍⚕️🐠የአሳ ዘይት(ኦሜጋ -3 ፋቲ አሲድ)ለሰዉነታችን አስፈላጊ ከሚባሉ...Ad
4ቴሌግራም👉 👨🏾‍⚕️የአሳ ዘይት(ኦሜጋ -3 ፋቲ አሲድ)ለሰዉነታችን አስፈላ...Ad
.........
4701የኑዌር ዞን በርካታ ደጋፊዎች ጅማ እስታዲየም በመገኘት ጨዋታውን እያደመቁ...Not ad
4702🇪🇹 #የኢትዮጵያ_አንደኛ_ሊግ_ምድብ_ለ_ሶዶ ⌚️85' ✅ #ካማሺ_ከተማ...Not ad
4703ጎልልልልልልልል ነጌሌ ቦረና 77'⚽️አዲሱ ተሰማNot ad
4704ጎልልልልልልልልልልል ካማሺ ከተማ 90+1'Not ad
4705🇪🇹 #የኢትዮጵያ_አንደኛ_ሊግ_ምድብ_ሀ ⌚️85' ✅ #ነጌሌ_ቦረና 1-...Not ad
\n", + "

4706 rows × 2 columns

\n", + "
" + ], + "text/plain": [ + " text label\n", + "0 Tecno Spark 20 pro + \\n\\nአስገራሚ የቴክኖሎጂ ውጤቶችን ያካ... Ad\n", + "1 #DELL PRECISION \\n#EUROPE STANDARD \\n🅑︎🅡︎🅐︎🅝︎🅓... Ad\n", + "2 አይብ በሚዘጋጅበት ጊዜ ከቅቤው ከሚለየው ወተት ውስጥ ካለው የውሃ ክፍል ... Ad\n", + "3 👨🏾‍⚕️🐠የአሳ ዘይት(ኦሜጋ -3 ፋቲ አሲድ)ለሰዉነታችን አስፈላጊ ከሚባሉ... Ad\n", + "4 ቴሌግራም👉 👨🏾‍⚕️የአሳ ዘይት(ኦሜጋ -3 ፋቲ አሲድ)ለሰዉነታችን አስፈላ... Ad\n", + "... ... ...\n", + "4701 የኑዌር ዞን በርካታ ደጋፊዎች ጅማ እስታዲየም በመገኘት ጨዋታውን እያደመቁ... Not ad\n", + "4702 🇪🇹 #የኢትዮጵያ_አንደኛ_ሊግ_ምድብ_ለ_ሶዶ ⌚️85' ✅ #ካማሺ_ከተማ... Not ad\n", + "4703 ጎልልልልልልልል ነጌሌ ቦረና 77'⚽️አዲሱ ተሰማ Not ad\n", + "4704 ጎልልልልልልልልልልል ካማሺ ከተማ 90+1' Not ad\n", + "4705 🇪🇹 #የኢትዮጵያ_አንደኛ_ሊግ_ምድብ_ሀ ⌚️85' ✅ #ነጌሌ_ቦረና 1-... Not ad\n", + "\n", + "[4706 rows x 2 columns]" + ] + }, + "execution_count": 37, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "dataset" + ] + }, + { + "cell_type": "code", + "execution_count": 38, + "metadata": { + "id": "xHtbKDZJziL1" + }, + "outputs": [], + "source": [ + "from datasets import Dataset\n", + "dataset['text'] = dataset['text'].astype(str)\n", + "data_dict = {\"text\": dataset['text'].tolist(), \"label\": dataset['label'].tolist()}\n", + "dataset = Dataset.from_dict(data_dict)" + ] + }, + { + "cell_type": "code", + "execution_count": 39, + "metadata": {}, + "outputs": [], + "source": [ + "import random\n", + "from math import ceil\n", + "total_indices = len(dataset)\n", + "\n", + "random.seed(150)\n", + "train_size = ceil(0.8 * total_indices)\n", + "train_indices = random.sample(range(total_indices), train_size)" + ] + }, + { + "cell_type": "code", + "execution_count": 40, + "metadata": {}, + "outputs": [], + "source": [ + "test_indices= [i for i in range(total_indices) if i not in train_indices]" + ] + }, + { + "cell_type": "code", + "execution_count": 41, + "metadata": { + "id": "Pu9HWrDC5caf" + }, + "outputs": [], + "source": [ + "train_dataset = dataset.select(train_indices)\n", + "test_dataset = dataset.select(test_indices)\n", + "dataset = train_dataset\n", + "dataset_subset = test_dataset" + ] + }, + { + "cell_type": "code", + "execution_count": 42, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "Counter({'Ad': 1888, 'Not ad': 1876, 'label': 1})" + ] + }, + "execution_count": 42, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "from collections import Counter\n", + "Counter(dataset['label'])" + ] + }, + { + "cell_type": "code", + "execution_count": 43, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "axcMEZl85cTv", + "outputId": "4503a157-9a63-41f4-e801-4661702fbdb0" + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "ባንካችን ተደራሽነቱን ይበልጥ በማስፋፋት ከታች በሰንጠረዡ ከ274 እስከ 276ኛ የተገለፁትን ቅርንጫፎች ነሀሴ 13 ቀን 2015 ኣም በመክፈት አገልግሎት መስጠት መጀመሩን በደስታ እንገልፃለን፡፡ አማራ ባንክ ከባንክ ባሻገር! የአማራ ባንክ ትክክለኛ የማህበራዊ ትስስር ገፆች : : : : : : :\n" + ] + } + ], + "source": [ + "print(dataset['text'][0])" + ] + }, + { + "cell_type": "code", + "execution_count": 44, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "_Cp6VQ096npb", + "outputId": "63acbb48-3cc8-42fe-f5be-e64fa6b31136" + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "ቴሌግራም👉 🏋️‍♀️()ብራንችድ ቼን አሚኖ አሲድ የሶስት አይነት ኤሰንሽያል አሚኖ አሲዶች :- ሉሲን፣ አይሶሶሉሲን እና ቫሊን ዉቅር ሲሆን፡። 👩🏽‍⚕️እነዚህ ኤሰንሽያል አሚኖ አሲዶች ሰውነት ዉስጥ ሊመረቱ የማይችሉ እና ከምግብ ወይም ከ ሰፕሊመንቶች መገኘት ያአለባቸው የአሚኖ አሲድ አይነቶች ናቸዉ። 👉ከእንቅስቃሴ ጋር ሲወሰድ ደግሞ የጡንቻ መጠን ሳይቀንስ የሰዉነት ስብን ለመቀነስ() ለማድረግ 👉 ጡንቻን ለመገንባት 👉በተጨማሪም የጡንቻን ጉዳት ለመከላከል ወይም ለመቀነስ 👉 የጉበት በሽታ ምልክቶችን ለማሻሻል በሆስፒታል ውስጥ በተሳካ ሁኔታ ጥቅም ላይ በመዋል ላይ ይገኛል። 📍ባህርዳር - ዋርካው (ምስራቅ ፀሀይ)የገበያ ማእከል ዋናው ገበያ ፒያሳ ህንፃ ጎን 1ኛ ፎቅ 83 ቁጥር 📍 አዳማ - ፖስታ ቤት ሶሬቲ ህንፃ ፊትለፊት ጀርመን ሲቲ ሞል 1ኛ ፎቅ ሱቅ ቁጥር 110 ⏱መደብራችን ከሰኞ - ቅዳሜ ከጠዋት 2 ሰኣት እስከ ምሽት 1ሰኣት, እሁድ ከጠዋቱ 3 ሰኣት እስከ ምሽቱ 11 ሰኣት ክፍት ነው። 📫ከቅርንጫፎቻችን ውጪ በሆኑ በየትኛውም የሀገሪቱ ክፍል ለምትገኙ በፓስታ ቤት በፍጥነት እንልካለን በመደወል ማዘዝ ይችላሉ ☎️9369 ላይ አሁኑኑ ይደውሉ ☎️\n" + ] + } + ], + "source": [ + "print(dataset_subset['text'][2])" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "9qbd6aX5QgMQ" + }, + "source": [ + "Function to download LLaMA 2 model and its tokenizer. It requires a bitsandbytes configuration" + ] + }, + { + "cell_type": "code", + "execution_count": 45, + "metadata": { + "id": "P-j9fm5WSbKG" + }, + "outputs": [], + "source": [ + "from transformers import PreTrainedTokenizerFast\n", + "def load_model(model_name, bnb_config, ):\n", + " n_gpus = torch.cuda.device_count()\n", + " max_memory = f'{23000}MB'\n", + "\n", + " model = AutoModelForCausalLM.from_pretrained(\n", + " model_name,\n", + " quantization_config=bnb_config,\n", + " device_map=\"auto\", \n", + " max_memory = {i: max_memory for i in range(n_gpus)},\n", + " trust_remote_code=True\n", + " )\n", + "\n", + " # tokenizer = spm.SentencePieceProcessor(model_file=str(tokenizer_model))\n", + " # tokenizer = SentencePieceBPETokenizer(vocab_file='token.vocab')\n", + " tokenizer = AutoTokenizer.from_pretrained(\"misge10/amharic-tokenizer\", use_auth_token=True)\n", + " # tokenizer = PreTrainedTokenizerFast.from_pretrained(\"misge10/am-token\")\n", + " # tokenizer = PreTrainedTokenizerFast.from_pretrained(\"tokenizer\")\n", + " tokenizer.pad_token = tokenizer.eos_token\n", + "\n", + " return model, tokenizer" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "g2yfDXvSTeAh" + }, + "source": [ + "\n", + "Pre-processing dataset\n", + "\n", + "\n" + ] + }, + { + "cell_type": "code", + "execution_count": 46, + "metadata": { + "id": "oVwsZvBmTTZR" + }, + "outputs": [], + "source": [ + "def create_prompt_formats(sample):\n", + " \"\"\"\n", + " Format various fields of the sample ('text', 'label',)\n", + " Then concatenate them using two newline characters\n", + " :param sample: Sample dictionary\n", + " :return: Modified sample dictionary with the formatted prompt\n", + " \"\"\"\n", + "\n", + " INTRO_BLURB = \"You are tasked with classifying messages as either advertisements (Ad) or non-advertisements (Not Ad) based on a comprehensive analysis of various factors.\"\n", + "\n", + " INSTRUCTION_KEY = \"### Text:\"\n", + " RESPONSE_KEY = \"Classification:\"\n", + " END_KEY = \"### End\"\n", + "\n", + " blurb = f\"{INTRO_BLURB}\\n\\n\"\n", + " text = f\"{INSTRUCTION_KEY}\\n{sample['text']}\\n\\n\"\n", + " response = f\"{RESPONSE_KEY}\\n{sample['label']}\\n\\n\"\n", + " end = f\"{END_KEY}\"\n", + "\n", + " formatted_prompt = blurb + text + response + end\n", + "\n", + " sample[\"text\"] = formatted_prompt\n", + "\n", + " return sample\n" + ] + }, + { + "cell_type": "code", + "execution_count": 47, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "{'text': 'ባንካችን ተደራሽነቱን ይበልጥ በማስፋፋት ከታች በሰንጠረዡ ከ274 እስከ 276ኛ የተገለፁትን ቅርንጫፎች ነሀሴ 13 ቀን 2015 ኣም በመክፈት አገልግሎት መስጠት መጀመሩን በደስታ እንገልፃለን፡፡ አማራ ባንክ ከባንክ ባሻገር! የአማራ ባንክ ትክክለኛ የማህበራዊ ትስስር ገፆች : : : : : : :',\n", + " 'label': 'Not ad'}" + ] + }, + "execution_count": 47, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "dataset[0]" + ] + }, + { + "cell_type": "code", + "execution_count": 48, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "{'text': 'You are tasked with classifying messages as either advertisements (Ad) or non-advertisements (Not Ad) based on a comprehensive analysis of various factors.\\n\\n### Text:\\nባንካችን ተደራሽነቱን ይበልጥ በማስፋፋት ከታች በሰንጠረዡ ከ274 እስከ 276ኛ የተገለፁትን ቅርንጫፎች ነሀሴ 13 ቀን 2015 ኣም በመክፈት አገልግሎት መስጠት መጀመሩን በደስታ እንገልፃለን፡፡ አማራ ባንክ ከባንክ ባሻገር! የአማራ ባንክ ትክክለኛ የማህበራዊ ትስስር ገፆች : : : : : : :\\n\\nClassification:\\nNot ad\\n\\n### End',\n", + " 'label': 'Not ad'}" + ] + }, + "execution_count": 48, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "create_prompt_formats(dataset[0])" + ] + }, + { + "cell_type": "code", + "execution_count": 49, + "metadata": { + "id": "TxPb4NvLTl4l" + }, + "outputs": [], + "source": [ + "def get_max_length(model):\n", + " conf = model.config\n", + " max_length = None\n", + " for length_setting in [\"n_positions\", \"max_position_embeddings\", \"seq_length\"]:\n", + " max_length = getattr(model.config, length_setting, None)\n", + " if max_length:\n", + " print(f\"Found max lenth: {max_length}\")\n", + " break\n", + " if not max_length:\n", + " max_length = 1024\n", + " print(f\"Using default max length: {max_length}\")\n", + " return max_length\n", + "\n", + "\n", + "def preprocess_batch(batch, tokenizer, max_length):\n", + " \"\"\"\n", + " Tokenizing a batch\n", + " \"\"\"\n", + " return tokenizer(\n", + " batch[\"text\"],\n", + " max_length=max_length,\n", + " truncation=True,\n", + " )\n", + "\n", + "\n", + "def preprocess_dataset(tokenizer, max_length: int, seed, dataset):\n", + " \"\"\"Format & tokenize it so it is ready for training\n", + " :param tokenizer (AutoTokenizer): Model Tokenizer\n", + " :param max_length (int): Maximum number of tokens to emit from tokenizer\n", + " \"\"\"\n", + "\n", + " print(\"Preprocessing dataset...\")\n", + " dataset = dataset.map(create_prompt_formats)\n", + "\n", + " _preprocessing_function = partial(preprocess_batch, max_length=max_length, tokenizer=tokenizer)\n", + " dataset = dataset.map(\n", + " _preprocessing_function,\n", + " batched=True,\n", + " remove_columns=[\"text\", \"label\"],\n", + " )\n", + "\n", + " dataset = dataset.filter(lambda sample: len(sample[\"input_ids\"]) < max_length)\n", + "\n", + " dataset = dataset.shuffle(seed=seed)\n", + "\n", + " return dataset" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "S8KglT2yT0gc" + }, + "source": [ + "**Create a bitsandbytes configuration**\n", + "\n" + ] + }, + { + "cell_type": "code", + "execution_count": 50, + "metadata": { + "id": "lPVyx5osTv_y" + }, + "outputs": [], + "source": [ + "''' This function, create_bnb_config(), is designed to create and return a\n", + "configuration object for quantization using the Bits and Bytes (BNB)\n", + "quantization scheme. '''\n", + "def create_bnb_config():\n", + " bnb_config = BitsAndBytesConfig(\n", + " load_in_4bit=True,\n", + " bnb_4bit_use_double_quant=True,\n", + " bnb_4bit_quant_type=\"nf4\",\n", + " bnb_4bit_compute_dtype=torch.bfloat16,\n", + " )\n", + "\n", + " return bnb_config" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "q6cN4wENTR3z" + }, + "source": [ + "** LoRa configuration**\n", + "\n" + ] + }, + { + "cell_type": "code", + "execution_count": 51, + "metadata": { + "id": "cbcQLbDJT1it" + }, + "outputs": [], + "source": [ + "def create_peft_config(modules):\n", + " \"\"\"\n", + " Create Parameter-Efficient Fine-Tuning config for the model\n", + " :param modules: Names of the modules to apply Lora to\n", + " \"\"\"\n", + " config = LoraConfig(\n", + " r=16, \n", + " lora_alpha=64, \n", + " target_modules=modules,\n", + " lora_dropout=0.1, \n", + " bias=\"none\",\n", + " task_type=\"CAUSAL_LM\",\n", + " # layers_to_transform=\n", + " )\n", + "\n", + " return config" + ] + }, + { + "cell_type": "code", + "execution_count": 52, + "metadata": { + "id": "6yi6TI1ST-lV" + }, + "outputs": [], + "source": [ + "def find_all_linear_names(model):\n", + " cls = bnb.nn.Linear4bit \n", + " lora_module_names = set()\n", + " for name, module in model.named_modules():\n", + " if isinstance(module, cls):\n", + " names = name.split('.')\n", + " lora_module_names.add(names[0] if len(names) == 1 else names[-1])\n", + "\n", + " if 'lm_head' in lora_module_names: \n", + " lora_module_names.remove('lm_head')\n", + " return list(lora_module_names)" + ] + }, + { + "cell_type": "code", + "execution_count": 53, + "metadata": { + "id": "sc9ff9v0UEXJ" + }, + "outputs": [], + "source": [ + "def print_trainable_parameters(model, use_4bit=False):\n", + " \"\"\"\n", + " Prints the number of trainable parameters in the model.\n", + " \"\"\"\n", + " trainable_params = 0\n", + " all_param = 0\n", + " for _, param in model.named_parameters():\n", + " num_params = param.numel()\n", + " \n", + " if num_params == 0 and hasattr(param, \"ds_numel\"):\n", + " num_params = param.ds_numel\n", + "\n", + " all_param += num_params\n", + " if param.requires_grad:\n", + " trainable_params += num_params\n", + " if use_4bit:\n", + " trainable_params /= 2\n", + " print(\n", + " f\"all params: {all_param:,d} || trainable params: {trainable_params:,d} || trainable%: {100 * trainable_params / all_param}\"\n", + " )\n" + ] + }, + { + "cell_type": "code", + "execution_count": 54, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Requirement already satisfied: python-dotenv in /opt/miniconda/lib/python3.11/site-packages (1.0.1)\n", + "Requirement already satisfied: sentencepiece in /opt/miniconda/lib/python3.11/site-packages (0.1.99)\n" + ] + } + ], + "source": [ + "!pip install python-dotenv sentencepiece" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "pc3xSbFwUP3t" + }, + "source": [ + "**Train**\n", + "\n", + "Now, we can pre-process our dataset and load our model using the set configurations\n" + ] + }, + { + "cell_type": "code", + "execution_count": 55, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "UQ1ygyYmjav9", + "outputId": "2e276454-d7ab-42a3-9dda-09120d5838aa" + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Token will not been saved to git credential helper. Pass `add_to_git_credential=True` if you want to set the git credential as well.\n", + "Token is valid (permission: read).\n", + "Your token has been saved to /home/nasrallah_hassan/.cache/huggingface/token\n", + "Login successful\n" + ] + } + ], + "source": [ + "from dotenv import load_dotenv\n", + "from huggingface_hub import login\n", + "\n", + "load_dotenv()\n", + "token = os.environ[\"huggingface_token\"]\n", + "login(token)" + ] + }, + { + "cell_type": "code", + "execution_count": 56, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "/bin/bash: -c: line 1: syntax error: unexpected end of file\n" + ] + } + ], + "source": [ + "!torch.cuda.empty_cache()" + ] + }, + { + "cell_type": "code", + "execution_count": 57, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 528, + "referenced_widgets": [ + "9e4adea806be46d49b7f37e92748a338", + "9f27bdce93994bc0bc5655c97879d637", + "07c82a6818454130be13570faf77d1a7", + "2df80d3d454b442388a2e3127e736e3e", + "7651d0f306884b53848bd64bc56df500", + "17de6afe24e94ff2960760c0bbbb7146", + "70b33dfa18db4e768458fa6930d00a4a", + "a3e05d1e704f46f7bfdca2cefc04a610", + "60a679a1d13b475c835785c765012444", + "900a336dc6a744cf8f6221bc63aaa633", + "0539d23c4c064f4a90296fe22a8a84b3", + "0a0e8f6c7a2645bfbd2df9509a21909d", + "afaa2c18a1eb47dc955ae934c4968a01", + "b36b878e0b7347e59fe87bb0de806cfb", + "87570f6d2e644c318196678a46bcf922", + "db589f37bf4c419284f21c6267d6f408", + "407f7d85e7964983a1ec685b6db14f1c", + "c6ed5de47d194f56899a01f4795274ce", + "46be584dddd84634b539117fcecdc4b7", + "c71a37bd40a448d1aa9bd760fd8692ee", + "a37699cadc064618bcc850ba37b01145", + "5fc5433f4f9f48e59dac63c0c3bd156a", + "74233ec9e4b94e64ba5ed3bfc544cab1", + "1142fcef536a4f0a914322bbce538054", + "9ab388c3b879402a899fc953e650a117", + "0fe7a638601c4d62ab15a1edaab7f5e1", + "51985bec0a1947fead86dabe1b605193", + "353889488fb941ab9de818997d64d6b7", + "64f4d807b9d04a89b7abe9792236dc4a", + "6c64e8c244134d07a92a76bd5903c519", + "db11269c0c2143e79c8e1be2a3fe29a0", + "b2f36e79b411454b9c648f07a7053bf7", + "e7091d8f4455432795782b522d5ee9b6", + "5c1f9ab6c1594871b8b5afdf51e19726", + "3f7c91d894b2499591501e8b70b51dc9", + "92a8a3349bf942fe8a91fb36efad1e60", + "4b78213b465e416d9f7fd547d11059af", + "77b5a275d26e4f4ba826f2c9198e0d65", + "98f1e2e0824f40ab92048e9f5a2ed067", + "3eb3fd49d093408a8dff8097bad6c2f6", + "bc482a1b71e846008d64347303e8da53", + "4a5bbd81ea2b424c953ddabce0633d90", + "215483dd3721466ebdb9a383eac7580a", + "7f2597d2478a4320bc191e878697d5a7", + "055187fe1d204467892336b850a986c5", + "c47945ffea92487ab3b5f0184fcd4aac", + "c2473c5645dc47f585d63c11536b097a", + "0e51aad4b7e844f69f5c81f97d3673a7", + "31e1bb79a79e48f4aaefbd145a6ccb0e", + "ffa4f33221a64507bf53a25574e8a4e3", + "393f451ec81940b181e259c5fbb62e84", + "1af6d6ba6365401a96a6a4e6d2b39b87", + "6776efc6b05a43149515f8a9ab8c4102", + "f642eeb766eb4c33b6e42e43d2108d5a", + "52b4491a79564237829ab02c8500e089", + "deae19c5a56e4ec58e33701f22872455", + "b9c70871f78b41aaa579b26621dd79a7", + "9b81c580bd7a4b24b9aeadc891f8bb41", + "edad5b919b974aa3bbb6af0ebf988bee", + "b42bae80865e46478356dfe1658db451", + "7f7ef54bc5b14f709279b53311b48524", + "1fe6f1ef4e924bc9b08495077671c39d", + "ac51732e189445098e1a60011e4aebd5", + "7650d6d7fd5f490d9901f0bf8b970eff", + "12fc2f4a906e4806b50fcd145f7726e1", + "9d34c0676891432e8fbcb20a1dda07c0", + "89a6f68b747f4a7f9708081dd205e995", + "ba98a5af142a46ac979d43f45c7f1bc2", + "ceb1be11f57d4c57893ad22ef99b6653", + "6c87c5570fac4712a1a77c9e78aa9105", + "4105500f56514764856fdd104feb4a63", + "3ade97e55b8247c2a2f440db4b56bced", + "e7296da44e6d4f1ab1708f5c1d344f44", + "1dac838ad78c4f89844d34309ff71013", + "7c1fc07ce3b64a23835ec167bd9e11a7", + "004123701b5c4085b7bbaf6024a1c6a0", + "b994b8fcf9d64f46bce1ededbd2d0042", + "6a00fd4fd52d4f87a7d1df2e86ce25d6", + "7928cbeebc5c48ee826531612770ad7f", + "8d3330dcb56242cf881ed948978d8dc5", + "6eb867a7932a482c8095054be7a62f0c", + "7e3cdef7cafb48d6a11549b90cbd14a4", + "0531d921ee994496bc356b165f843918", + "10a27dc44b1f43ba9c774564169c617f", + "6733d61830d143af9dcdfea0a1200e60", + "94a3ee09029a46cf8a62f2ea03a8bc62", + "cf84406cd1be464ca9caf07b3ab7cecf", + "cd21e232645e41d4834badc1fb0a860d", + "379912692baf4f0a8e629d9273071984", + "02c0da9b2dd24f2186e0b80eba63728b", + "2e11546d6bab47b9917cd7751651e04e", + "d0327ceb4e9a4e8f93624c522450f8f6", + "2d1801b723f74ee6ade584e95f23696e", + "6b7c3bd8a0aa422cbfe29eba10281783", + "3cde60fe9c314ab1890c56b3e22982fb", + "b91fa9edc65a4093a13931160210d5e5", + "adbc64a4b9f245ab86258cbffa805241", + "6e6dfc7b5e7c4393b32440417c759a0f", + "48c4888d267e46a69fbd7648250b5a93", + "b65badf0c84c4bfdb720944a7206df18", + "9576b1746f414e0890747c5113880148", + "14206e17bdf14c9f8a81ed30bea678cf", + "cfe5eb2326654c4a92ef520bf059d7e1", + "a55ac6497b434d328caaccd03833459a", + "081c408abd914a29b48faf34ee12a6cd", + "ca09604bb55249b7913c84e681c348dc", + "fcc9664580b6482dbe8ad7f4c2fabb09", + "a94f5ffc1e864be6b95a7372c471d9bf", + "a2d7c8e9d87d43389e8b70cfe59a1232", + "2acdb638a06d4764b2479c861605b266", + "68a2dd2fbcdf45f4b96ac5ab1d33c32b", + "64133685cf1043149c999e654c5e247f", + "86090b230d71463989f09b6860f8d2c6", + "66febca78ca84452b72499635a8b259b", + "226b0ff5917b49a5bbdd6ec45fa307d9", + "fef86b2372094c71b7f75ac7dd0caabd", + "1057a900755a44ee973109682bd1a285", + "2ee7f2e534c24c8ba888f01db059bdbb", + "7c50fd8a551846c4a1c3d1244f6f9f46", + "87efe32842c741918e411eb68a3fe69f", + "0dd65cecc4f84cfc9cf58ecd5d610c01" + ] + }, + "id": "Ce7JRmR1UL0w", + "outputId": "824a4762-f9ff-4118-ccee-01efba073ba8" + }, + "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "You are calling `save_pretrained` to a 4-bit converted model, but your `bitsandbytes` version doesn't support it. If you want to save 4-bit models, make sure to have `bitsandbytes>=0.41.3` installed.\n", + "/opt/miniconda/lib/python3.11/site-packages/transformers/models/auto/tokenization_auto.py:712: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.\n", + " warnings.warn(\n" + ] + } + ], + "source": [ + "model_name = \"stabilityai/stablelm-zephyr-3b\"\n", + "bnb_config = create_bnb_config()\n", + "\n", + "model, tokenizer2 = load_model(model_name, bnb_config)" + ] + }, + { + "cell_type": "code", + "execution_count": 58, + "metadata": { + "id": "nGgvfWPk_KiS" + }, + "outputs": [], + "source": [ + "# tokenizer = Tokenizer.from_pretrained(\"dagim/amharic_tokenizer\") " + ] + }, + { + "cell_type": "code", + "execution_count": 63, + "metadata": { + "id": "qkArdKaUlSck" + }, + "outputs": [], + "source": [ + "import random\n", + "\n", + "seed = 42\n", + "random.seed(50)" + ] + }, + { + "cell_type": "code", + "execution_count": 64, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 52, + "referenced_widgets": [ + "baafa594d8814e3a9584dc3f2c42bf45", + "719ee4a0fe29440c8185eaec857cbc0d", + "d045cc3593b74209b7bf149dbf9b2e61", + "bdb4f2de960d4529810d1ad3eefea59c", + "18454784ad24444ca34b726f83ce8248", + "d63611b41599470a84357222964933e7", + "54de021924594864b79016c42242f9e9", + "d5e7af0cff5c411d96b89ba43d6979fb", + "48d300a81ab544708d44ac7049a0bd3a", + "ff6e5ac3180c47d69aa7630246c71e6f", + "c2f438f50dee4f23904602a7c2c7f41b", + "70918a1c19a443b380bed9b87978cf51", + "43ef1a6f9cef4e08bc9237b3ec7856e5", + "aad494542dc1422abe803ecdb6c77e76", + "a05250531071414585d29876f1f05319", + "7bb63bb641034fe7b0f3f422eec3b9d4", + "7435a21f09ea4131bd61284634db5b7a", + "7a714cab0fa24fa3b11f5eb626d51efd", + "ea67d69c64fd4420bb8986c3887eb7e9", + "c4292de9659d416c8b08c44faf1bb5cf", + "97cb7a52ca3543a1be62650e0bf026f1", + "d875bfc9ce5b4bc4a8e2329bf24987fb", + "28bb7249f8e54cdfa8ea222ccb5482c6", + "684a973060d9456a86d444fbbeaa2133", + "089965f75c0840b2a668241d75e6ed92", + "a7712b27e6c94e45aa2a060ab49f0e04", + "bb1f598f9aea44f1a7fe4da9b3d869fb", + "f3b6da9b49f547c7ad92d1b86af2fa78", + "77dc8fce07a04fc1988737496ef09c09", + "929e7cc6c8c6468b98ac4b9f9ed37947", + "2408301332bf46028f478451e29e27d0", + "8a0340af2ed54f47a3b7e585ea80cb43", + "c419f2587cc74ae6b0dde962caec6159" + ] + }, + "id": "LGqPljuB6T8x", + "outputId": "05d13237-fc27-4b2b-d496-d17a66711313" + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Found max lenth: 4096\n", + "Preprocessing dataset...\n" + ] + }, + { + "data": { + "application/vnd.jupyter.widget-view+json": { + "model_id": "c32a0c6760594d5badc627dc3a540d1e", + "version_major": 2, + "version_minor": 0 + }, + "text/plain": [ + "Map: 0%| | 0/3765 [00:00 3\u001b[0m dataset \u001b[38;5;241m=\u001b[39m preprocess_dataset(tokenizer2, max_length, seed, dataset)\n", + "Cell \u001b[0;32mIn[49], line 33\u001b[0m, in \u001b[0;36mpreprocess_dataset\u001b[0;34m(tokenizer, max_length, seed, dataset)\u001b[0m\n\u001b[1;32m 27\u001b[0m \u001b[38;5;250m\u001b[39m\u001b[38;5;124;03m\"\"\"Format & tokenize it so it is ready for training\u001b[39;00m\n\u001b[1;32m 28\u001b[0m \u001b[38;5;124;03m:param tokenizer (AutoTokenizer): Model Tokenizer\u001b[39;00m\n\u001b[1;32m 29\u001b[0m \u001b[38;5;124;03m:param max_length (int): Maximum number of tokens to emit from tokenizer\u001b[39;00m\n\u001b[1;32m 30\u001b[0m \u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[1;32m 32\u001b[0m \u001b[38;5;28mprint\u001b[39m(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mPreprocessing dataset...\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[0;32m---> 33\u001b[0m dataset \u001b[38;5;241m=\u001b[39m dataset\u001b[38;5;241m.\u001b[39mmap(create_prompt_formats)\n\u001b[1;32m 35\u001b[0m _preprocessing_function \u001b[38;5;241m=\u001b[39m partial(preprocess_batch, max_length\u001b[38;5;241m=\u001b[39mmax_length, tokenizer\u001b[38;5;241m=\u001b[39mtokenizer)\n\u001b[1;32m 36\u001b[0m dataset \u001b[38;5;241m=\u001b[39m dataset\u001b[38;5;241m.\u001b[39mmap(\n\u001b[1;32m 37\u001b[0m _preprocessing_function,\n\u001b[1;32m 38\u001b[0m batched\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mTrue\u001b[39;00m,\n\u001b[1;32m 39\u001b[0m remove_columns\u001b[38;5;241m=\u001b[39m[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mtext\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mlabel\u001b[39m\u001b[38;5;124m\"\u001b[39m],\n\u001b[1;32m 40\u001b[0m )\n", + "File \u001b[0;32m/opt/miniconda/lib/python3.11/site-packages/datasets/arrow_dataset.py:580\u001b[0m, in \u001b[0;36mtransmit_tasks..wrapper\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m 578\u001b[0m \u001b[38;5;28mself\u001b[39m: \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mDataset\u001b[39m\u001b[38;5;124m\"\u001b[39m \u001b[38;5;241m=\u001b[39m kwargs\u001b[38;5;241m.\u001b[39mpop(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mself\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[1;32m 579\u001b[0m \u001b[38;5;66;03m# apply actual function\u001b[39;00m\n\u001b[0;32m--> 580\u001b[0m out: Union[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mDataset\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mDatasetDict\u001b[39m\u001b[38;5;124m\"\u001b[39m] \u001b[38;5;241m=\u001b[39m func(\u001b[38;5;28mself\u001b[39m, \u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n\u001b[1;32m 581\u001b[0m datasets: List[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mDataset\u001b[39m\u001b[38;5;124m\"\u001b[39m] \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mlist\u001b[39m(out\u001b[38;5;241m.\u001b[39mvalues()) \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(out, \u001b[38;5;28mdict\u001b[39m) \u001b[38;5;28;01melse\u001b[39;00m [out]\n\u001b[1;32m 582\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m dataset \u001b[38;5;129;01min\u001b[39;00m datasets:\n\u001b[1;32m 583\u001b[0m \u001b[38;5;66;03m# Remove task templates if a column mapping of the template is no longer valid\u001b[39;00m\n", + "File \u001b[0;32m/opt/miniconda/lib/python3.11/site-packages/datasets/arrow_dataset.py:545\u001b[0m, in \u001b[0;36mtransmit_format..wrapper\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m 538\u001b[0m self_format \u001b[38;5;241m=\u001b[39m {\n\u001b[1;32m 539\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mtype\u001b[39m\u001b[38;5;124m\"\u001b[39m: \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_format_type,\n\u001b[1;32m 540\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mformat_kwargs\u001b[39m\u001b[38;5;124m\"\u001b[39m: \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_format_kwargs,\n\u001b[1;32m 541\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mcolumns\u001b[39m\u001b[38;5;124m\"\u001b[39m: \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_format_columns,\n\u001b[1;32m 542\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124moutput_all_columns\u001b[39m\u001b[38;5;124m\"\u001b[39m: \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_output_all_columns,\n\u001b[1;32m 543\u001b[0m }\n\u001b[1;32m 544\u001b[0m \u001b[38;5;66;03m# apply actual function\u001b[39;00m\n\u001b[0;32m--> 545\u001b[0m out: Union[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mDataset\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mDatasetDict\u001b[39m\u001b[38;5;124m\"\u001b[39m] \u001b[38;5;241m=\u001b[39m func(\u001b[38;5;28mself\u001b[39m, \u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n\u001b[1;32m 546\u001b[0m datasets: List[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mDataset\u001b[39m\u001b[38;5;124m\"\u001b[39m] \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mlist\u001b[39m(out\u001b[38;5;241m.\u001b[39mvalues()) \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(out, \u001b[38;5;28mdict\u001b[39m) \u001b[38;5;28;01melse\u001b[39;00m [out]\n\u001b[1;32m 547\u001b[0m \u001b[38;5;66;03m# re-apply format to the output\u001b[39;00m\n", + "File \u001b[0;32m/opt/miniconda/lib/python3.11/site-packages/datasets/arrow_dataset.py:3087\u001b[0m, in \u001b[0;36mDataset.map\u001b[0;34m(self, function, with_indices, with_rank, input_columns, batched, batch_size, drop_last_batch, remove_columns, keep_in_memory, load_from_cache_file, cache_file_name, writer_batch_size, features, disable_nullable, fn_kwargs, num_proc, suffix_template, new_fingerprint, desc)\u001b[0m\n\u001b[1;32m 3079\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m transformed_dataset \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[1;32m 3080\u001b[0m \u001b[38;5;28;01mwith\u001b[39;00m logging\u001b[38;5;241m.\u001b[39mtqdm(\n\u001b[1;32m 3081\u001b[0m disable\u001b[38;5;241m=\u001b[39m\u001b[38;5;129;01mnot\u001b[39;00m logging\u001b[38;5;241m.\u001b[39mis_progress_bar_enabled(),\n\u001b[1;32m 3082\u001b[0m unit\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m examples\u001b[39m\u001b[38;5;124m\"\u001b[39m,\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 3085\u001b[0m desc\u001b[38;5;241m=\u001b[39mdesc \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mMap\u001b[39m\u001b[38;5;124m\"\u001b[39m,\n\u001b[1;32m 3086\u001b[0m ) \u001b[38;5;28;01mas\u001b[39;00m pbar:\n\u001b[0;32m-> 3087\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m rank, done, content \u001b[38;5;129;01min\u001b[39;00m Dataset\u001b[38;5;241m.\u001b[39m_map_single(\u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mdataset_kwargs):\n\u001b[1;32m 3088\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m done:\n\u001b[1;32m 3089\u001b[0m shards_done \u001b[38;5;241m+\u001b[39m\u001b[38;5;241m=\u001b[39m \u001b[38;5;241m1\u001b[39m\n", + "File \u001b[0;32m/opt/miniconda/lib/python3.11/site-packages/datasets/arrow_dataset.py:3441\u001b[0m, in \u001b[0;36mDataset._map_single\u001b[0;34m(shard, function, with_indices, with_rank, input_columns, batched, batch_size, drop_last_batch, remove_columns, keep_in_memory, cache_file_name, writer_batch_size, features, disable_nullable, fn_kwargs, new_fingerprint, rank, offset)\u001b[0m\n\u001b[1;32m 3439\u001b[0m _time \u001b[38;5;241m=\u001b[39m time\u001b[38;5;241m.\u001b[39mtime()\n\u001b[1;32m 3440\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m i, example \u001b[38;5;129;01min\u001b[39;00m shard_iterable:\n\u001b[0;32m-> 3441\u001b[0m example \u001b[38;5;241m=\u001b[39m apply_function_on_filtered_inputs(example, i, offset\u001b[38;5;241m=\u001b[39moffset)\n\u001b[1;32m 3442\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m update_data:\n\u001b[1;32m 3443\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m i \u001b[38;5;241m==\u001b[39m \u001b[38;5;241m0\u001b[39m:\n", + "File \u001b[0;32m/opt/miniconda/lib/python3.11/site-packages/datasets/arrow_dataset.py:3344\u001b[0m, in \u001b[0;36mDataset._map_single..apply_function_on_filtered_inputs\u001b[0;34m(pa_inputs, indices, check_same_num_examples, offset)\u001b[0m\n\u001b[1;32m 3342\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m with_rank:\n\u001b[1;32m 3343\u001b[0m additional_args \u001b[38;5;241m+\u001b[39m\u001b[38;5;241m=\u001b[39m (rank,)\n\u001b[0;32m-> 3344\u001b[0m processed_inputs \u001b[38;5;241m=\u001b[39m function(\u001b[38;5;241m*\u001b[39mfn_args, \u001b[38;5;241m*\u001b[39madditional_args, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mfn_kwargs)\n\u001b[1;32m 3345\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(processed_inputs, LazyDict):\n\u001b[1;32m 3346\u001b[0m processed_inputs \u001b[38;5;241m=\u001b[39m {\n\u001b[1;32m 3347\u001b[0m k: v \u001b[38;5;28;01mfor\u001b[39;00m k, v \u001b[38;5;129;01min\u001b[39;00m processed_inputs\u001b[38;5;241m.\u001b[39mdata\u001b[38;5;241m.\u001b[39mitems() \u001b[38;5;28;01mif\u001b[39;00m k \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;129;01min\u001b[39;00m processed_inputs\u001b[38;5;241m.\u001b[39mkeys_to_format\n\u001b[1;32m 3348\u001b[0m }\n", + "Cell \u001b[0;32mIn[46], line 16\u001b[0m, in \u001b[0;36mcreate_prompt_formats\u001b[0;34m(sample)\u001b[0m\n\u001b[1;32m 13\u001b[0m END_KEY \u001b[38;5;241m=\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m### End\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 15\u001b[0m blurb \u001b[38;5;241m=\u001b[39m \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;132;01m{\u001b[39;00mINTRO_BLURB\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;130;01m\\n\u001b[39;00m\u001b[38;5;130;01m\\n\u001b[39;00m\u001b[38;5;124m\"\u001b[39m\n\u001b[0;32m---> 16\u001b[0m text \u001b[38;5;241m=\u001b[39m \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;132;01m{\u001b[39;00mINSTRUCTION_KEY\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;130;01m\\n\u001b[39;00m\u001b[38;5;132;01m{\u001b[39;00msample[\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mtext\u001b[39m\u001b[38;5;124m'\u001b[39m]\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;130;01m\\n\u001b[39;00m\u001b[38;5;130;01m\\n\u001b[39;00m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 17\u001b[0m response \u001b[38;5;241m=\u001b[39m \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;132;01m{\u001b[39;00mRESPONSE_KEY\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;130;01m\\n\u001b[39;00m\u001b[38;5;132;01m{\u001b[39;00msample[\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mlabel\u001b[39m\u001b[38;5;124m'\u001b[39m]\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;130;01m\\n\u001b[39;00m\u001b[38;5;130;01m\\n\u001b[39;00m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 18\u001b[0m end \u001b[38;5;241m=\u001b[39m \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;132;01m{\u001b[39;00mEND_KEY\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m\"\u001b[39m\n", + "File \u001b[0;32m/opt/miniconda/lib/python3.11/site-packages/datasets/formatting/formatting.py:270\u001b[0m, in \u001b[0;36mLazyDict.__getitem__\u001b[0;34m(self, key)\u001b[0m\n\u001b[1;32m 269\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21m__getitem__\u001b[39m(\u001b[38;5;28mself\u001b[39m, key):\n\u001b[0;32m--> 270\u001b[0m value \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mdata[key]\n\u001b[1;32m 271\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m key \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mkeys_to_format:\n\u001b[1;32m 272\u001b[0m value \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mformat(key)\n", + "\u001b[0;31mKeyError\u001b[0m: 'text'" + ] + } + ], + "source": [ + "max_length = get_max_length(model)\n", + "\n", + "dataset = preprocess_dataset(tokenizer2, max_length, seed, dataset)" + ] + }, + { + "cell_type": "code", + "execution_count": 65, + "metadata": {}, + "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "\u001b[34m\u001b[1mwandb\u001b[0m: \u001b[33mWARNING\u001b[0m Calling wandb.login() after wandb.init() has no effect.\n" + ] + }, + { + "data": { + "text/html": [ + "Finishing last run (ID:hzykxa2v) before initializing another..." + ], + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "application/vnd.jupyter.widget-view+json": { + "model_id": "", + "version_major": 2, + "version_minor": 0 + }, + "text/plain": [ + "VBox(children=(Label(value='0.002 MB of 0.002 MB uploaded\\r'), FloatProgress(value=1.0, max=1.0)))" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "text/html": [ + " View run vibrant-blaze-35 at: https://wandb.ai/mulabr673/amh_lama/runs/hzykxa2v
View job at https://wandb.ai/mulabr673/amh_lama/jobs/QXJ0aWZhY3RDb2xsZWN0aW9uOjEzNjU3ODg2Mg==/version_details/v0
Synced 6 W&B file(s), 0 media file(s), 2 artifact file(s) and 0 other file(s)" + ], + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "text/html": [ + "Find logs at: ./wandb/run-20240203_010914-hzykxa2v/logs" + ], + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "text/html": [ + "Successfully finished last run (ID:hzykxa2v). Initializing new run:
" + ], + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "application/vnd.jupyter.widget-view+json": { + "model_id": "b994b433ee9b4c4e87a59d20f6a5feca", + "version_major": 2, + "version_minor": 0 + }, + "text/plain": [ + "VBox(children=(Label(value='Waiting for wandb.init()...\\r'), FloatProgress(value=0.01111218141126705, max=1.0)…" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "text/html": [ + "Tracking run with wandb version 0.16.2" + ], + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "text/html": [ + "Run data is saved locally in /home/nasrallah_hassan/AmharicAI-AdGen/research/mistral/wandb/run-20240203_010942-blpg8i17" + ], + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "text/html": [ + "Syncing run light-frost-36 to Weights & Biases (docs)
" + ], + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "text/html": [ + " View project at https://wandb.ai/mulabr673/amh_lama" + ], + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "text/html": [ + " View run at https://wandb.ai/mulabr673/amh_lama/runs/blpg8i17" + ], + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "text/html": [ + "" + ], + "text/plain": [ + "" + ] + }, + "execution_count": 65, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "import wandb, os\n", + "wandb.login()\n", + "# start a new wandb run to track this script\n", + "wandb.init(\n", + " # set the wandb project where this run will be logged\n", + " project=\"amh_lama\",\n", + " # track hyperparameters and run metadata\n", + " config={\n", + " \"learning_rate\": 0.02,\n", + " \"architecture\": \"CNN\",\n", + " \"dataset\": \"CIFAR-100\",\n", + " \"epochs\": 10,\n", + " }\n", + ")" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "-OiiPORDUlDS" + }, + "source": [ + "**Fine-tuning process using Single GPU**" + ] + }, + { + "cell_type": "code", + "execution_count": 66, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 1000 + }, + "id": "TLio1IovUqqz", + "outputId": "20938320-d716-49b9-b4c5-41687d082e38" + }, + "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "You are using an old version of the checkpointing format that is deprecated (We will also silently ignore `gradient_checkpointing_kwargs` in case you passed it).Please update to the new format on your modeling file. To use the new format, you need to completely remove the definition of the method `_set_gradient_checkpointing` in your model.\n", + "You are using an old version of the checkpointing format that is deprecated (We will also silently ignore `gradient_checkpointing_kwargs` in case you passed it).Please update to the new format on your modeling file. To use the new format, you need to completely remove the definition of the method `_set_gradient_checkpointing` in your model.\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "all params: 1,551,700,992 || trainable params: 25,034,752 || trainable%: 1.6133747499724482\n", + "torch.float32 282924032 0.1823315403280995\n", + "torch.uint8 1268776960 0.8176684596719005\n", + "Training...\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/opt/miniconda/lib/python3.11/site-packages/torch/utils/checkpoint.py:460: UserWarning: torch.utils.checkpoint: please pass in use_reentrant=True or use_reentrant=False explicitly. The default value of use_reentrant will be updated to be False in the future. To maintain current behavior, pass use_reentrant=True. It is recommended that you use use_reentrant=False. Refer to docs for more details on the differences between the two variants.\n", + " warnings.warn(\n", + "../aten/src/ATen/native/cuda/Indexing.cu:1290: indexSelectLargeIndex: block: [478,0,0], thread: [64,0,0] Assertion `srcIndex < srcSelectDimSize` failed.\n", + "../aten/src/ATen/native/cuda/Indexing.cu:1290: indexSelectLargeIndex: block: [478,0,0], thread: [65,0,0] Assertion `srcIndex < srcSelectDimSize` failed.\n", + "../aten/src/ATen/native/cuda/Indexing.cu:1290: indexSelectLargeIndex: block: [478,0,0], thread: [66,0,0] Assertion `srcIndex < srcSelectDimSize` failed.\n", + "../aten/src/ATen/native/cuda/Indexing.cu:1290: indexSelectLargeIndex: block: [478,0,0], thread: [67,0,0] Assertion `srcIndex < srcSelectDimSize` failed.\n", + "../aten/src/ATen/native/cuda/Indexing.cu:1290: indexSelectLargeIndex: block: [478,0,0], thread: [68,0,0] Assertion `srcIndex < srcSelectDimSize` failed.\n", + "../aten/src/ATen/native/cuda/Indexing.cu:1290: indexSelectLargeIndex: block: [478,0,0], thread: [69,0,0] Assertion `srcIndex < srcSelectDimSize` failed.\n", + "../aten/src/ATen/native/cuda/Indexing.cu:1290: indexSelectLargeIndex: block: [478,0,0], thread: [70,0,0] Assertion `srcIndex < srcSelectDimSize` failed.\n", + "../aten/src/ATen/native/cuda/Indexing.cu:1290: indexSelectLargeIndex: block: [478,0,0], thread: [71,0,0] Assertion `srcIndex < srcSelectDimSize` failed.\n", + "../aten/src/ATen/native/cuda/Indexing.cu:1290: indexSelectLargeIndex: block: [478,0,0], thread: [72,0,0] Assertion `srcIndex < srcSelectDimSize` failed.\n", + "../aten/src/ATen/native/cuda/Indexing.cu:1290: indexSelectLargeIndex: block: [478,0,0], thread: [73,0,0] Assertion `srcIndex < srcSelectDimSize` failed.\n", + "../aten/src/ATen/native/cuda/Indexing.cu:1290: indexSelectLargeIndex: block: [478,0,0], thread: [74,0,0] Assertion `srcIndex < srcSelectDimSize` failed.\n", + "../aten/src/ATen/native/cuda/Indexing.cu:1290: indexSelectLargeIndex: block: [478,0,0], thread: [75,0,0] Assertion `srcIndex < srcSelectDimSize` failed.\n", + "../aten/src/ATen/native/cuda/Indexing.cu:1290: indexSelectLargeIndex: block: [478,0,0], thread: [76,0,0] Assertion `srcIndex < srcSelectDimSize` failed.\n", + "../aten/src/ATen/native/cuda/Indexing.cu:1290: indexSelectLargeIndex: block: [478,0,0], thread: [77,0,0] Assertion `srcIndex < srcSelectDimSize` failed.\n", + "../aten/src/ATen/native/cuda/Indexing.cu:1290: indexSelectLargeIndex: block: [478,0,0], thread: [78,0,0] Assertion `srcIndex < srcSelectDimSize` failed.\n", + "../aten/src/ATen/native/cuda/Indexing.cu:1290: indexSelectLargeIndex: block: [478,0,0], thread: [79,0,0] Assertion `srcIndex < srcSelectDimSize` failed.\n", + "../aten/src/ATen/native/cuda/Indexing.cu:1290: indexSelectLargeIndex: block: [478,0,0], thread: [80,0,0] Assertion `srcIndex < srcSelectDimSize` failed.\n", + "../aten/src/ATen/native/cuda/Indexing.cu:1290: indexSelectLargeIndex: block: [478,0,0], thread: [81,0,0] Assertion `srcIndex < srcSelectDimSize` failed.\n", + "../aten/src/ATen/native/cuda/Indexing.cu:1290: indexSelectLargeIndex: block: [478,0,0], thread: [82,0,0] Assertion `srcIndex < srcSelectDimSize` failed.\n", + "../aten/src/ATen/native/cuda/Indexing.cu:1290: indexSelectLargeIndex: block: [478,0,0], thread: [83,0,0] Assertion `srcIndex < srcSelectDimSize` failed.\n", + "../aten/src/ATen/native/cuda/Indexing.cu:1290: indexSelectLargeIndex: block: [478,0,0], thread: [84,0,0] Assertion `srcIndex < srcSelectDimSize` failed.\n", + "../aten/src/ATen/native/cuda/Indexing.cu:1290: indexSelectLargeIndex: block: [478,0,0], thread: [85,0,0] Assertion `srcIndex < srcSelectDimSize` failed.\n", + "../aten/src/ATen/native/cuda/Indexing.cu:1290: indexSelectLargeIndex: block: [478,0,0], thread: [86,0,0] Assertion `srcIndex < srcSelectDimSize` failed.\n", + "../aten/src/ATen/native/cuda/Indexing.cu:1290: indexSelectLargeIndex: block: [478,0,0], thread: [87,0,0] Assertion `srcIndex < srcSelectDimSize` failed.\n", + "../aten/src/ATen/native/cuda/Indexing.cu:1290: indexSelectLargeIndex: block: [478,0,0], thread: [88,0,0] Assertion `srcIndex < srcSelectDimSize` failed.\n", + "../aten/src/ATen/native/cuda/Indexing.cu:1290: indexSelectLargeIndex: block: [478,0,0], thread: [89,0,0] Assertion `srcIndex < srcSelectDimSize` failed.\n", + "../aten/src/ATen/native/cuda/Indexing.cu:1290: indexSelectLargeIndex: block: [478,0,0], thread: [90,0,0] Assertion `srcIndex < srcSelectDimSize` failed.\n", + "../aten/src/ATen/native/cuda/Indexing.cu:1290: indexSelectLargeIndex: block: [478,0,0], thread: [91,0,0] Assertion `srcIndex < srcSelectDimSize` failed.\n", + "../aten/src/ATen/native/cuda/Indexing.cu:1290: indexSelectLargeIndex: block: [478,0,0], thread: [92,0,0] Assertion `srcIndex < srcSelectDimSize` failed.\n", + "../aten/src/ATen/native/cuda/Indexing.cu:1290: indexSelectLargeIndex: block: [478,0,0], thread: [93,0,0] Assertion `srcIndex < srcSelectDimSize` failed.\n", + "../aten/src/ATen/native/cuda/Indexing.cu:1290: indexSelectLargeIndex: block: [478,0,0], thread: [94,0,0] Assertion `srcIndex < srcSelectDimSize` failed.\n", + "../aten/src/ATen/native/cuda/Indexing.cu:1290: indexSelectLargeIndex: block: [478,0,0], thread: [95,0,0] Assertion `srcIndex < srcSelectDimSize` failed.\n" + ] + }, + { + "ename": "RuntimeError", + "evalue": "CUDA error: CUBLAS_STATUS_NOT_INITIALIZED when calling `cublasCreate(handle)`", + "output_type": "error", + "traceback": [ + "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m", + "\u001b[0;31mRuntimeError\u001b[0m Traceback (most recent call last)", + "Cell \u001b[0;32mIn[66], line 73\u001b[0m\n\u001b[1;32m 71\u001b[0m repo_name \u001b[38;5;241m=\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mstableai\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 72\u001b[0m output_dir \u001b[38;5;241m=\u001b[39m \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;132;01m{\u001b[39;00mnamespace\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m/\u001b[39m\u001b[38;5;132;01m{\u001b[39;00mrepo_name\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m\"\u001b[39m\n\u001b[0;32m---> 73\u001b[0m train(model, tokenizer2, dataset, output_dir)\n", + "Cell \u001b[0;32mIn[66], line 52\u001b[0m, in \u001b[0;36mtrain\u001b[0;34m(model, tokenizer, dataset, output_dir)\u001b[0m\n\u001b[1;32m 49\u001b[0m \u001b[38;5;28mprint\u001b[39m(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mTraining...\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[1;32m 51\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m do_train:\n\u001b[0;32m---> 52\u001b[0m train_result \u001b[38;5;241m=\u001b[39m trainer\u001b[38;5;241m.\u001b[39mtrain()\n\u001b[1;32m 53\u001b[0m metrics \u001b[38;5;241m=\u001b[39m train_result\u001b[38;5;241m.\u001b[39mmetrics\n\u001b[1;32m 54\u001b[0m trainer\u001b[38;5;241m.\u001b[39mlog_metrics(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mtrain\u001b[39m\u001b[38;5;124m\"\u001b[39m, metrics)\n", + "File \u001b[0;32m/opt/miniconda/lib/python3.11/site-packages/transformers/trainer.py:1561\u001b[0m, in \u001b[0;36mTrainer.train\u001b[0;34m(self, resume_from_checkpoint, trial, ignore_keys_for_eval, **kwargs)\u001b[0m\n\u001b[1;32m 1559\u001b[0m hf_hub_utils\u001b[38;5;241m.\u001b[39menable_progress_bars()\n\u001b[1;32m 1560\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m-> 1561\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m inner_training_loop(\n\u001b[1;32m 1562\u001b[0m args\u001b[38;5;241m=\u001b[39margs,\n\u001b[1;32m 1563\u001b[0m resume_from_checkpoint\u001b[38;5;241m=\u001b[39mresume_from_checkpoint,\n\u001b[1;32m 1564\u001b[0m trial\u001b[38;5;241m=\u001b[39mtrial,\n\u001b[1;32m 1565\u001b[0m ignore_keys_for_eval\u001b[38;5;241m=\u001b[39mignore_keys_for_eval,\n\u001b[1;32m 1566\u001b[0m )\n", + "File \u001b[0;32m/opt/miniconda/lib/python3.11/site-packages/transformers/trainer.py:1893\u001b[0m, in \u001b[0;36mTrainer._inner_training_loop\u001b[0;34m(self, batch_size, args, resume_from_checkpoint, trial, ignore_keys_for_eval)\u001b[0m\n\u001b[1;32m 1890\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mcontrol \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mcallback_handler\u001b[38;5;241m.\u001b[39mon_step_begin(args, \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mstate, \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mcontrol)\n\u001b[1;32m 1892\u001b[0m \u001b[38;5;28;01mwith\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39maccelerator\u001b[38;5;241m.\u001b[39maccumulate(model):\n\u001b[0;32m-> 1893\u001b[0m tr_loss_step \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mtraining_step(model, inputs)\n\u001b[1;32m 1895\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m (\n\u001b[1;32m 1896\u001b[0m args\u001b[38;5;241m.\u001b[39mlogging_nan_inf_filter\n\u001b[1;32m 1897\u001b[0m \u001b[38;5;129;01mand\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m is_torch_tpu_available()\n\u001b[1;32m 1898\u001b[0m \u001b[38;5;129;01mand\u001b[39;00m (torch\u001b[38;5;241m.\u001b[39misnan(tr_loss_step) \u001b[38;5;129;01mor\u001b[39;00m torch\u001b[38;5;241m.\u001b[39misinf(tr_loss_step))\n\u001b[1;32m 1899\u001b[0m ):\n\u001b[1;32m 1900\u001b[0m \u001b[38;5;66;03m# if loss is nan or inf simply add the average of previous logged losses\u001b[39;00m\n\u001b[1;32m 1901\u001b[0m tr_loss \u001b[38;5;241m+\u001b[39m\u001b[38;5;241m=\u001b[39m tr_loss \u001b[38;5;241m/\u001b[39m (\u001b[38;5;241m1\u001b[39m \u001b[38;5;241m+\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mstate\u001b[38;5;241m.\u001b[39mglobal_step \u001b[38;5;241m-\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_globalstep_last_logged)\n", + "File \u001b[0;32m/opt/miniconda/lib/python3.11/site-packages/transformers/trainer.py:2813\u001b[0m, in \u001b[0;36mTrainer.training_step\u001b[0;34m(self, model, inputs)\u001b[0m\n\u001b[1;32m 2810\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m loss_mb\u001b[38;5;241m.\u001b[39mreduce_mean()\u001b[38;5;241m.\u001b[39mdetach()\u001b[38;5;241m.\u001b[39mto(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39margs\u001b[38;5;241m.\u001b[39mdevice)\n\u001b[1;32m 2812\u001b[0m \u001b[38;5;28;01mwith\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mcompute_loss_context_manager():\n\u001b[0;32m-> 2813\u001b[0m loss \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mcompute_loss(model, inputs)\n\u001b[1;32m 2815\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39margs\u001b[38;5;241m.\u001b[39mn_gpu \u001b[38;5;241m>\u001b[39m \u001b[38;5;241m1\u001b[39m:\n\u001b[1;32m 2816\u001b[0m loss \u001b[38;5;241m=\u001b[39m loss\u001b[38;5;241m.\u001b[39mmean() \u001b[38;5;66;03m# mean() to average on multi-gpu parallel training\u001b[39;00m\n", + "File \u001b[0;32m/opt/miniconda/lib/python3.11/site-packages/transformers/trainer.py:2836\u001b[0m, in \u001b[0;36mTrainer.compute_loss\u001b[0;34m(self, model, inputs, return_outputs)\u001b[0m\n\u001b[1;32m 2834\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m 2835\u001b[0m labels \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[0;32m-> 2836\u001b[0m outputs \u001b[38;5;241m=\u001b[39m model(\u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39minputs)\n\u001b[1;32m 2837\u001b[0m \u001b[38;5;66;03m# Save past state if it exists\u001b[39;00m\n\u001b[1;32m 2838\u001b[0m \u001b[38;5;66;03m# TODO: this needs to be fixed and made cleaner later.\u001b[39;00m\n\u001b[1;32m 2839\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39margs\u001b[38;5;241m.\u001b[39mpast_index \u001b[38;5;241m>\u001b[39m\u001b[38;5;241m=\u001b[39m \u001b[38;5;241m0\u001b[39m:\n", + "File \u001b[0;32m/opt/miniconda/lib/python3.11/site-packages/torch/nn/modules/module.py:1511\u001b[0m, in \u001b[0;36mModule._wrapped_call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m 1509\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_compiled_call_impl(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs) \u001b[38;5;66;03m# type: ignore[misc]\u001b[39;00m\n\u001b[1;32m 1510\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m-> 1511\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_call_impl(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n", + "File \u001b[0;32m/opt/miniconda/lib/python3.11/site-packages/torch/nn/modules/module.py:1520\u001b[0m, in \u001b[0;36mModule._call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m 1515\u001b[0m \u001b[38;5;66;03m# If we don't have any hooks, we want to skip the rest of the logic in\u001b[39;00m\n\u001b[1;32m 1516\u001b[0m \u001b[38;5;66;03m# this function, and just call forward.\u001b[39;00m\n\u001b[1;32m 1517\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m (\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_pre_hooks\n\u001b[1;32m 1518\u001b[0m \u001b[38;5;129;01mor\u001b[39;00m _global_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_backward_hooks\n\u001b[1;32m 1519\u001b[0m \u001b[38;5;129;01mor\u001b[39;00m _global_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_forward_pre_hooks):\n\u001b[0;32m-> 1520\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m forward_call(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n\u001b[1;32m 1522\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m 1523\u001b[0m result \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n", + "File \u001b[0;32m/opt/miniconda/lib/python3.11/site-packages/accelerate/utils/operations.py:687\u001b[0m, in \u001b[0;36mconvert_outputs_to_fp32..forward\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m 686\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mforward\u001b[39m(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs):\n\u001b[0;32m--> 687\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m model_forward(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n", + "File \u001b[0;32m/opt/miniconda/lib/python3.11/site-packages/accelerate/utils/operations.py:675\u001b[0m, in \u001b[0;36mConvertOutputsToFp32.__call__\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m 674\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21m__call__\u001b[39m(\u001b[38;5;28mself\u001b[39m, \u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs):\n\u001b[0;32m--> 675\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m convert_to_fp32(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mmodel_forward(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs))\n", + "File \u001b[0;32m/opt/miniconda/lib/python3.11/site-packages/torch/amp/autocast_mode.py:16\u001b[0m, in \u001b[0;36mautocast_decorator..decorate_autocast\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m 13\u001b[0m \u001b[38;5;129m@functools\u001b[39m\u001b[38;5;241m.\u001b[39mwraps(func)\n\u001b[1;32m 14\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mdecorate_autocast\u001b[39m(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs):\n\u001b[1;32m 15\u001b[0m \u001b[38;5;28;01mwith\u001b[39;00m autocast_instance:\n\u001b[0;32m---> 16\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m func(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n", + "File \u001b[0;32m/opt/miniconda/lib/python3.11/site-packages/peft/peft_model.py:1083\u001b[0m, in \u001b[0;36mPeftModelForCausalLM.forward\u001b[0;34m(self, input_ids, attention_mask, inputs_embeds, labels, output_attentions, output_hidden_states, return_dict, task_ids, **kwargs)\u001b[0m\n\u001b[1;32m 1081\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m peft_config\u001b[38;5;241m.\u001b[39mpeft_type \u001b[38;5;241m==\u001b[39m PeftType\u001b[38;5;241m.\u001b[39mPOLY:\n\u001b[1;32m 1082\u001b[0m kwargs[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mtask_ids\u001b[39m\u001b[38;5;124m\"\u001b[39m] \u001b[38;5;241m=\u001b[39m task_ids\n\u001b[0;32m-> 1083\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mbase_model(\n\u001b[1;32m 1084\u001b[0m input_ids\u001b[38;5;241m=\u001b[39minput_ids,\n\u001b[1;32m 1085\u001b[0m attention_mask\u001b[38;5;241m=\u001b[39mattention_mask,\n\u001b[1;32m 1086\u001b[0m inputs_embeds\u001b[38;5;241m=\u001b[39minputs_embeds,\n\u001b[1;32m 1087\u001b[0m labels\u001b[38;5;241m=\u001b[39mlabels,\n\u001b[1;32m 1088\u001b[0m output_attentions\u001b[38;5;241m=\u001b[39moutput_attentions,\n\u001b[1;32m 1089\u001b[0m output_hidden_states\u001b[38;5;241m=\u001b[39moutput_hidden_states,\n\u001b[1;32m 1090\u001b[0m return_dict\u001b[38;5;241m=\u001b[39mreturn_dict,\n\u001b[1;32m 1091\u001b[0m \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs,\n\u001b[1;32m 1092\u001b[0m )\n\u001b[1;32m 1094\u001b[0m batch_size \u001b[38;5;241m=\u001b[39m _get_batch_size(input_ids, inputs_embeds)\n\u001b[1;32m 1095\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m attention_mask \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[1;32m 1096\u001b[0m \u001b[38;5;66;03m# concat prompt attention mask\u001b[39;00m\n", + "File \u001b[0;32m/opt/miniconda/lib/python3.11/site-packages/torch/nn/modules/module.py:1511\u001b[0m, in \u001b[0;36mModule._wrapped_call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m 1509\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_compiled_call_impl(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs) \u001b[38;5;66;03m# type: ignore[misc]\u001b[39;00m\n\u001b[1;32m 1510\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m-> 1511\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_call_impl(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n", + "File \u001b[0;32m/opt/miniconda/lib/python3.11/site-packages/torch/nn/modules/module.py:1520\u001b[0m, in \u001b[0;36mModule._call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m 1515\u001b[0m \u001b[38;5;66;03m# If we don't have any hooks, we want to skip the rest of the logic in\u001b[39;00m\n\u001b[1;32m 1516\u001b[0m \u001b[38;5;66;03m# this function, and just call forward.\u001b[39;00m\n\u001b[1;32m 1517\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m (\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_pre_hooks\n\u001b[1;32m 1518\u001b[0m \u001b[38;5;129;01mor\u001b[39;00m _global_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_backward_hooks\n\u001b[1;32m 1519\u001b[0m \u001b[38;5;129;01mor\u001b[39;00m _global_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_forward_pre_hooks):\n\u001b[0;32m-> 1520\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m forward_call(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n\u001b[1;32m 1522\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m 1523\u001b[0m result \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n", + "File \u001b[0;32m/opt/miniconda/lib/python3.11/site-packages/peft/tuners/tuners_utils.py:161\u001b[0m, in \u001b[0;36mBaseTuner.forward\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m 160\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mforward\u001b[39m(\u001b[38;5;28mself\u001b[39m, \u001b[38;5;241m*\u001b[39margs: Any, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs: Any):\n\u001b[0;32m--> 161\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mmodel\u001b[38;5;241m.\u001b[39mforward(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n", + "File \u001b[0;32m/opt/miniconda/lib/python3.11/site-packages/accelerate/hooks.py:166\u001b[0m, in \u001b[0;36madd_hook_to_module..new_forward\u001b[0;34m(module, *args, **kwargs)\u001b[0m\n\u001b[1;32m 164\u001b[0m output \u001b[38;5;241m=\u001b[39m module\u001b[38;5;241m.\u001b[39m_old_forward(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n\u001b[1;32m 165\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m--> 166\u001b[0m output \u001b[38;5;241m=\u001b[39m module\u001b[38;5;241m.\u001b[39m_old_forward(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n\u001b[1;32m 167\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m module\u001b[38;5;241m.\u001b[39m_hf_hook\u001b[38;5;241m.\u001b[39mpost_forward(module, output)\n", + "File \u001b[0;32m~/.cache/huggingface/modules/transformers_modules/stabilityai/stablelm-zephyr-3b/e20b0d644459c889294d51be537c7d15971f9fb1/modeling_stablelm_epoch.py:819\u001b[0m, in \u001b[0;36mStableLMEpochForCausalLM.forward\u001b[0;34m(self, input_ids, attention_mask, position_ids, past_key_values, inputs_embeds, labels, use_cache, output_attentions, output_hidden_states, return_dict)\u001b[0m\n\u001b[1;32m 814\u001b[0m return_dict \u001b[38;5;241m=\u001b[39m (\n\u001b[1;32m 815\u001b[0m return_dict \u001b[38;5;28;01mif\u001b[39;00m return_dict \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;28;01melse\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mconfig\u001b[38;5;241m.\u001b[39muse_return_dict\n\u001b[1;32m 816\u001b[0m )\n\u001b[1;32m 818\u001b[0m \u001b[38;5;66;03m# decoder outputs consists of (dec_features, layer_state, dec_hidden, dec_attn)\u001b[39;00m\n\u001b[0;32m--> 819\u001b[0m outputs \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mmodel(\n\u001b[1;32m 820\u001b[0m input_ids,\n\u001b[1;32m 821\u001b[0m attention_mask\u001b[38;5;241m=\u001b[39mattention_mask,\n\u001b[1;32m 822\u001b[0m position_ids\u001b[38;5;241m=\u001b[39mposition_ids,\n\u001b[1;32m 823\u001b[0m past_key_values\u001b[38;5;241m=\u001b[39mpast_key_values,\n\u001b[1;32m 824\u001b[0m inputs_embeds\u001b[38;5;241m=\u001b[39minputs_embeds,\n\u001b[1;32m 825\u001b[0m use_cache\u001b[38;5;241m=\u001b[39muse_cache,\n\u001b[1;32m 826\u001b[0m output_attentions\u001b[38;5;241m=\u001b[39moutput_attentions,\n\u001b[1;32m 827\u001b[0m output_hidden_states\u001b[38;5;241m=\u001b[39moutput_hidden_states,\n\u001b[1;32m 828\u001b[0m return_dict\u001b[38;5;241m=\u001b[39mreturn_dict,\n\u001b[1;32m 829\u001b[0m )\n\u001b[1;32m 831\u001b[0m hidden_states \u001b[38;5;241m=\u001b[39m outputs[\u001b[38;5;241m0\u001b[39m]\n\u001b[1;32m 832\u001b[0m logits \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mlm_head(hidden_states)\u001b[38;5;241m.\u001b[39mfloat()\n", + "File \u001b[0;32m/opt/miniconda/lib/python3.11/site-packages/torch/nn/modules/module.py:1511\u001b[0m, in \u001b[0;36mModule._wrapped_call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m 1509\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_compiled_call_impl(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs) \u001b[38;5;66;03m# type: ignore[misc]\u001b[39;00m\n\u001b[1;32m 1510\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m-> 1511\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_call_impl(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n", + "File \u001b[0;32m/opt/miniconda/lib/python3.11/site-packages/torch/nn/modules/module.py:1520\u001b[0m, in \u001b[0;36mModule._call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m 1515\u001b[0m \u001b[38;5;66;03m# If we don't have any hooks, we want to skip the rest of the logic in\u001b[39;00m\n\u001b[1;32m 1516\u001b[0m \u001b[38;5;66;03m# this function, and just call forward.\u001b[39;00m\n\u001b[1;32m 1517\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m (\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_pre_hooks\n\u001b[1;32m 1518\u001b[0m \u001b[38;5;129;01mor\u001b[39;00m _global_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_backward_hooks\n\u001b[1;32m 1519\u001b[0m \u001b[38;5;129;01mor\u001b[39;00m _global_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_forward_pre_hooks):\n\u001b[0;32m-> 1520\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m forward_call(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n\u001b[1;32m 1522\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m 1523\u001b[0m result \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n", + "File \u001b[0;32m/opt/miniconda/lib/python3.11/site-packages/accelerate/hooks.py:166\u001b[0m, in \u001b[0;36madd_hook_to_module..new_forward\u001b[0;34m(module, *args, **kwargs)\u001b[0m\n\u001b[1;32m 164\u001b[0m output \u001b[38;5;241m=\u001b[39m module\u001b[38;5;241m.\u001b[39m_old_forward(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n\u001b[1;32m 165\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m--> 166\u001b[0m output \u001b[38;5;241m=\u001b[39m module\u001b[38;5;241m.\u001b[39m_old_forward(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n\u001b[1;32m 167\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m module\u001b[38;5;241m.\u001b[39m_hf_hook\u001b[38;5;241m.\u001b[39mpost_forward(module, output)\n", + "File \u001b[0;32m~/.cache/huggingface/modules/transformers_modules/stabilityai/stablelm-zephyr-3b/e20b0d644459c889294d51be537c7d15971f9fb1/modeling_stablelm_epoch.py:716\u001b[0m, in \u001b[0;36mStableLMEpochModel.forward\u001b[0;34m(self, input_ids, attention_mask, position_ids, past_key_values, inputs_embeds, use_cache, output_attentions, output_hidden_states, return_dict)\u001b[0m\n\u001b[1;32m 712\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m module(\u001b[38;5;241m*\u001b[39minputs, past_key_value, output_attentions)\n\u001b[1;32m 714\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m custom_forward\n\u001b[0;32m--> 716\u001b[0m layer_outputs \u001b[38;5;241m=\u001b[39m torch\u001b[38;5;241m.\u001b[39mutils\u001b[38;5;241m.\u001b[39mcheckpoint\u001b[38;5;241m.\u001b[39mcheckpoint(\n\u001b[1;32m 717\u001b[0m create_custom_forward(decoder_layer),\n\u001b[1;32m 718\u001b[0m hidden_states,\n\u001b[1;32m 719\u001b[0m attention_mask,\n\u001b[1;32m 720\u001b[0m position_ids,\n\u001b[1;32m 721\u001b[0m )\n\u001b[1;32m 722\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m 723\u001b[0m layer_outputs \u001b[38;5;241m=\u001b[39m decoder_layer(\n\u001b[1;32m 724\u001b[0m hidden_states,\n\u001b[1;32m 725\u001b[0m attention_mask\u001b[38;5;241m=\u001b[39mattention_mask,\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 729\u001b[0m use_cache\u001b[38;5;241m=\u001b[39muse_cache,\n\u001b[1;32m 730\u001b[0m )\n", + "File \u001b[0;32m/opt/miniconda/lib/python3.11/site-packages/torch/_compile.py:24\u001b[0m, in \u001b[0;36m_disable_dynamo..inner\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m 20\u001b[0m \u001b[38;5;129m@functools\u001b[39m\u001b[38;5;241m.\u001b[39mwraps(fn)\n\u001b[1;32m 21\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21minner\u001b[39m(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs):\n\u001b[1;32m 22\u001b[0m \u001b[38;5;28;01mimport\u001b[39;00m \u001b[38;5;21;01mtorch\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01m_dynamo\u001b[39;00m\n\u001b[0;32m---> 24\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m torch\u001b[38;5;241m.\u001b[39m_dynamo\u001b[38;5;241m.\u001b[39mdisable(fn, recursive)(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n", + "File \u001b[0;32m/opt/miniconda/lib/python3.11/site-packages/torch/_dynamo/eval_frame.py:489\u001b[0m, in \u001b[0;36m_TorchDynamoContext.__call__.._fn\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m 487\u001b[0m dynamo_config_ctx\u001b[38;5;241m.\u001b[39m\u001b[38;5;21m__enter__\u001b[39m()\n\u001b[1;32m 488\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m--> 489\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m fn(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n\u001b[1;32m 490\u001b[0m \u001b[38;5;28;01mfinally\u001b[39;00m:\n\u001b[1;32m 491\u001b[0m set_eval_frame(prior)\n", + "File \u001b[0;32m/opt/miniconda/lib/python3.11/site-packages/torch/_dynamo/external_utils.py:17\u001b[0m, in \u001b[0;36mwrap_inline..inner\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m 15\u001b[0m \u001b[38;5;129m@functools\u001b[39m\u001b[38;5;241m.\u001b[39mwraps(fn)\n\u001b[1;32m 16\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21minner\u001b[39m(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs):\n\u001b[0;32m---> 17\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m fn(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n", + "File \u001b[0;32m/opt/miniconda/lib/python3.11/site-packages/torch/utils/checkpoint.py:482\u001b[0m, in \u001b[0;36mcheckpoint\u001b[0;34m(function, use_reentrant, context_fn, determinism_check, debug, *args, **kwargs)\u001b[0m\n\u001b[1;32m 477\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m context_fn \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m noop_context_fn \u001b[38;5;129;01mor\u001b[39;00m debug \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mFalse\u001b[39;00m:\n\u001b[1;32m 478\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mValueError\u001b[39;00m(\n\u001b[1;32m 479\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mPassing `context_fn` or `debug` is only supported when \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 480\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124muse_reentrant=False.\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 481\u001b[0m )\n\u001b[0;32m--> 482\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m CheckpointFunction\u001b[38;5;241m.\u001b[39mapply(function, preserve, \u001b[38;5;241m*\u001b[39margs)\n\u001b[1;32m 483\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m 484\u001b[0m gen \u001b[38;5;241m=\u001b[39m _checkpoint_without_reentrant_generator(\n\u001b[1;32m 485\u001b[0m function, preserve, context_fn, determinism_check, debug, \u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs\n\u001b[1;32m 486\u001b[0m )\n", + "File \u001b[0;32m/opt/miniconda/lib/python3.11/site-packages/torch/autograd/function.py:553\u001b[0m, in \u001b[0;36mFunction.apply\u001b[0;34m(cls, *args, **kwargs)\u001b[0m\n\u001b[1;32m 550\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m torch\u001b[38;5;241m.\u001b[39m_C\u001b[38;5;241m.\u001b[39m_are_functorch_transforms_active():\n\u001b[1;32m 551\u001b[0m \u001b[38;5;66;03m# See NOTE: [functorch vjp and autograd interaction]\u001b[39;00m\n\u001b[1;32m 552\u001b[0m args \u001b[38;5;241m=\u001b[39m _functorch\u001b[38;5;241m.\u001b[39mutils\u001b[38;5;241m.\u001b[39munwrap_dead_wrappers(args)\n\u001b[0;32m--> 553\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28msuper\u001b[39m()\u001b[38;5;241m.\u001b[39mapply(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs) \u001b[38;5;66;03m# type: ignore[misc]\u001b[39;00m\n\u001b[1;32m 555\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m is_setup_ctx_defined:\n\u001b[1;32m 556\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mRuntimeError\u001b[39;00m(\n\u001b[1;32m 557\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mIn order to use an autograd.Function with functorch transforms \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 558\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m(vmap, grad, jvp, jacrev, ...), it must override the setup_context \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 559\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mstaticmethod. For more details, please see \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 560\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mhttps://pytorch.org/docs/master/notes/extending.func.html\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 561\u001b[0m )\n", + "File \u001b[0;32m/opt/miniconda/lib/python3.11/site-packages/torch/utils/checkpoint.py:261\u001b[0m, in \u001b[0;36mCheckpointFunction.forward\u001b[0;34m(ctx, run_function, preserve_rng_state, *args)\u001b[0m\n\u001b[1;32m 258\u001b[0m ctx\u001b[38;5;241m.\u001b[39msave_for_backward(\u001b[38;5;241m*\u001b[39mtensor_inputs)\n\u001b[1;32m 260\u001b[0m \u001b[38;5;28;01mwith\u001b[39;00m torch\u001b[38;5;241m.\u001b[39mno_grad():\n\u001b[0;32m--> 261\u001b[0m outputs \u001b[38;5;241m=\u001b[39m run_function(\u001b[38;5;241m*\u001b[39margs)\n\u001b[1;32m 262\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m outputs\n", + "File \u001b[0;32m~/.cache/huggingface/modules/transformers_modules/stabilityai/stablelm-zephyr-3b/e20b0d644459c889294d51be537c7d15971f9fb1/modeling_stablelm_epoch.py:712\u001b[0m, in \u001b[0;36mStableLMEpochModel.forward..create_custom_forward..custom_forward\u001b[0;34m(*inputs)\u001b[0m\n\u001b[1;32m 710\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mcustom_forward\u001b[39m(\u001b[38;5;241m*\u001b[39minputs):\n\u001b[1;32m 711\u001b[0m \u001b[38;5;66;03m# None for past_key_value\u001b[39;00m\n\u001b[0;32m--> 712\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m module(\u001b[38;5;241m*\u001b[39minputs, past_key_value, output_attentions)\n", + "File \u001b[0;32m/opt/miniconda/lib/python3.11/site-packages/torch/nn/modules/module.py:1511\u001b[0m, in \u001b[0;36mModule._wrapped_call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m 1509\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_compiled_call_impl(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs) \u001b[38;5;66;03m# type: ignore[misc]\u001b[39;00m\n\u001b[1;32m 1510\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m-> 1511\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_call_impl(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n", + "File \u001b[0;32m/opt/miniconda/lib/python3.11/site-packages/torch/nn/modules/module.py:1520\u001b[0m, in \u001b[0;36mModule._call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m 1515\u001b[0m \u001b[38;5;66;03m# If we don't have any hooks, we want to skip the rest of the logic in\u001b[39;00m\n\u001b[1;32m 1516\u001b[0m \u001b[38;5;66;03m# this function, and just call forward.\u001b[39;00m\n\u001b[1;32m 1517\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m (\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_pre_hooks\n\u001b[1;32m 1518\u001b[0m \u001b[38;5;129;01mor\u001b[39;00m _global_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_backward_hooks\n\u001b[1;32m 1519\u001b[0m \u001b[38;5;129;01mor\u001b[39;00m _global_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_forward_pre_hooks):\n\u001b[0;32m-> 1520\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m forward_call(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n\u001b[1;32m 1522\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m 1523\u001b[0m result \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n", + "File \u001b[0;32m/opt/miniconda/lib/python3.11/site-packages/accelerate/hooks.py:166\u001b[0m, in \u001b[0;36madd_hook_to_module..new_forward\u001b[0;34m(module, *args, **kwargs)\u001b[0m\n\u001b[1;32m 164\u001b[0m output \u001b[38;5;241m=\u001b[39m module\u001b[38;5;241m.\u001b[39m_old_forward(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n\u001b[1;32m 165\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m--> 166\u001b[0m output \u001b[38;5;241m=\u001b[39m module\u001b[38;5;241m.\u001b[39m_old_forward(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n\u001b[1;32m 167\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m module\u001b[38;5;241m.\u001b[39m_hf_hook\u001b[38;5;241m.\u001b[39mpost_forward(module, output)\n", + "File \u001b[0;32m~/.cache/huggingface/modules/transformers_modules/stabilityai/stablelm-zephyr-3b/e20b0d644459c889294d51be537c7d15971f9fb1/modeling_stablelm_epoch.py:514\u001b[0m, in \u001b[0;36mDecoderLayer.forward\u001b[0;34m(self, hidden_states, attention_mask, position_ids, past_key_value, output_attentions, use_cache)\u001b[0m\n\u001b[1;32m 511\u001b[0m hidden_states \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39minput_layernorm(hidden_states)\n\u001b[1;32m 513\u001b[0m \u001b[38;5;66;03m# Self Attention\u001b[39;00m\n\u001b[0;32m--> 514\u001b[0m hidden_states, self_attn_weights, present_key_value \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mself_attn(\n\u001b[1;32m 515\u001b[0m hidden_states\u001b[38;5;241m=\u001b[39mhidden_states,\n\u001b[1;32m 516\u001b[0m attention_mask\u001b[38;5;241m=\u001b[39mattention_mask,\n\u001b[1;32m 517\u001b[0m position_ids\u001b[38;5;241m=\u001b[39mposition_ids,\n\u001b[1;32m 518\u001b[0m past_key_value\u001b[38;5;241m=\u001b[39mpast_key_value,\n\u001b[1;32m 519\u001b[0m output_attentions\u001b[38;5;241m=\u001b[39moutput_attentions,\n\u001b[1;32m 520\u001b[0m use_cache\u001b[38;5;241m=\u001b[39muse_cache,\n\u001b[1;32m 521\u001b[0m )\n\u001b[1;32m 522\u001b[0m hidden_states \u001b[38;5;241m=\u001b[39m residual \u001b[38;5;241m+\u001b[39m hidden_states\n\u001b[1;32m 524\u001b[0m \u001b[38;5;66;03m# Fully Connected\u001b[39;00m\n", + "File \u001b[0;32m/opt/miniconda/lib/python3.11/site-packages/torch/nn/modules/module.py:1511\u001b[0m, in \u001b[0;36mModule._wrapped_call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m 1509\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_compiled_call_impl(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs) \u001b[38;5;66;03m# type: ignore[misc]\u001b[39;00m\n\u001b[1;32m 1510\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m-> 1511\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_call_impl(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n", + "File \u001b[0;32m/opt/miniconda/lib/python3.11/site-packages/torch/nn/modules/module.py:1520\u001b[0m, in \u001b[0;36mModule._call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m 1515\u001b[0m \u001b[38;5;66;03m# If we don't have any hooks, we want to skip the rest of the logic in\u001b[39;00m\n\u001b[1;32m 1516\u001b[0m \u001b[38;5;66;03m# this function, and just call forward.\u001b[39;00m\n\u001b[1;32m 1517\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m (\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_pre_hooks\n\u001b[1;32m 1518\u001b[0m \u001b[38;5;129;01mor\u001b[39;00m _global_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_backward_hooks\n\u001b[1;32m 1519\u001b[0m \u001b[38;5;129;01mor\u001b[39;00m _global_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_forward_pre_hooks):\n\u001b[0;32m-> 1520\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m forward_call(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n\u001b[1;32m 1522\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m 1523\u001b[0m result \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n", + "File \u001b[0;32m/opt/miniconda/lib/python3.11/site-packages/accelerate/hooks.py:166\u001b[0m, in \u001b[0;36madd_hook_to_module..new_forward\u001b[0;34m(module, *args, **kwargs)\u001b[0m\n\u001b[1;32m 164\u001b[0m output \u001b[38;5;241m=\u001b[39m module\u001b[38;5;241m.\u001b[39m_old_forward(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n\u001b[1;32m 165\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m--> 166\u001b[0m output \u001b[38;5;241m=\u001b[39m module\u001b[38;5;241m.\u001b[39m_old_forward(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n\u001b[1;32m 167\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m module\u001b[38;5;241m.\u001b[39m_hf_hook\u001b[38;5;241m.\u001b[39mpost_forward(module, output)\n", + "File \u001b[0;32m~/.cache/huggingface/modules/transformers_modules/stabilityai/stablelm-zephyr-3b/e20b0d644459c889294d51be537c7d15971f9fb1/modeling_stablelm_epoch.py:227\u001b[0m, in \u001b[0;36mAttention.forward\u001b[0;34m(self, hidden_states, attention_mask, position_ids, past_key_value, output_attentions, use_cache)\u001b[0m\n\u001b[1;32m 216\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mforward\u001b[39m(\n\u001b[1;32m 217\u001b[0m \u001b[38;5;28mself\u001b[39m,\n\u001b[1;32m 218\u001b[0m hidden_states: torch\u001b[38;5;241m.\u001b[39mFloatTensor,\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 223\u001b[0m use_cache: Optional[\u001b[38;5;28mbool\u001b[39m] \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mFalse\u001b[39;00m,\n\u001b[1;32m 224\u001b[0m ) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m Tuple[torch\u001b[38;5;241m.\u001b[39mTensor, Optional[torch\u001b[38;5;241m.\u001b[39mTensor], Optional[Tuple[torch\u001b[38;5;241m.\u001b[39mTensor]]]:\n\u001b[1;32m 225\u001b[0m bsz, q_len, _ \u001b[38;5;241m=\u001b[39m hidden_states\u001b[38;5;241m.\u001b[39msize()\n\u001b[0;32m--> 227\u001b[0m query_states \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mq_proj(hidden_states)\n\u001b[1;32m 228\u001b[0m key_states \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mk_proj(hidden_states)\n\u001b[1;32m 229\u001b[0m value_states \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mv_proj(hidden_states)\n", + "File \u001b[0;32m/opt/miniconda/lib/python3.11/site-packages/torch/nn/modules/module.py:1511\u001b[0m, in \u001b[0;36mModule._wrapped_call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m 1509\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_compiled_call_impl(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs) \u001b[38;5;66;03m# type: ignore[misc]\u001b[39;00m\n\u001b[1;32m 1510\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m-> 1511\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_call_impl(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n", + "File \u001b[0;32m/opt/miniconda/lib/python3.11/site-packages/torch/nn/modules/module.py:1520\u001b[0m, in \u001b[0;36mModule._call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m 1515\u001b[0m \u001b[38;5;66;03m# If we don't have any hooks, we want to skip the rest of the logic in\u001b[39;00m\n\u001b[1;32m 1516\u001b[0m \u001b[38;5;66;03m# this function, and just call forward.\u001b[39;00m\n\u001b[1;32m 1517\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m (\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_pre_hooks\n\u001b[1;32m 1518\u001b[0m \u001b[38;5;129;01mor\u001b[39;00m _global_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_backward_hooks\n\u001b[1;32m 1519\u001b[0m \u001b[38;5;129;01mor\u001b[39;00m _global_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_forward_pre_hooks):\n\u001b[0;32m-> 1520\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m forward_call(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n\u001b[1;32m 1522\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m 1523\u001b[0m result \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n", + "File \u001b[0;32m/opt/miniconda/lib/python3.11/site-packages/peft/tuners/lora/bnb.py:311\u001b[0m, in \u001b[0;36mLinear4bit.forward\u001b[0;34m(self, x, *args, **kwargs)\u001b[0m\n\u001b[1;32m 309\u001b[0m result \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mbase_layer(x, \u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n\u001b[1;32m 310\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m--> 311\u001b[0m result \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mbase_layer(x, \u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n\u001b[1;32m 312\u001b[0m \u001b[38;5;66;03m# As per Tim Dettmers, for 4bit, we need to defensively clone here.\u001b[39;00m\n\u001b[1;32m 313\u001b[0m \u001b[38;5;66;03m# The reason is that in some cases, an error can occur that backprop\u001b[39;00m\n\u001b[1;32m 314\u001b[0m \u001b[38;5;66;03m# does not work on a manipulated view. This issue may be solved with\u001b[39;00m\n\u001b[1;32m 315\u001b[0m \u001b[38;5;66;03m# newer PyTorch versions but this would need extensive testing to be\u001b[39;00m\n\u001b[1;32m 316\u001b[0m \u001b[38;5;66;03m# sure.\u001b[39;00m\n\u001b[1;32m 317\u001b[0m result \u001b[38;5;241m=\u001b[39m result\u001b[38;5;241m.\u001b[39mclone()\n", + "File \u001b[0;32m/opt/miniconda/lib/python3.11/site-packages/torch/nn/modules/module.py:1511\u001b[0m, in \u001b[0;36mModule._wrapped_call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m 1509\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_compiled_call_impl(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs) \u001b[38;5;66;03m# type: ignore[misc]\u001b[39;00m\n\u001b[1;32m 1510\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m-> 1511\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_call_impl(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n", + "File \u001b[0;32m/opt/miniconda/lib/python3.11/site-packages/torch/nn/modules/module.py:1520\u001b[0m, in \u001b[0;36mModule._call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m 1515\u001b[0m \u001b[38;5;66;03m# If we don't have any hooks, we want to skip the rest of the logic in\u001b[39;00m\n\u001b[1;32m 1516\u001b[0m \u001b[38;5;66;03m# this function, and just call forward.\u001b[39;00m\n\u001b[1;32m 1517\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m (\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_pre_hooks\n\u001b[1;32m 1518\u001b[0m \u001b[38;5;129;01mor\u001b[39;00m _global_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_backward_hooks\n\u001b[1;32m 1519\u001b[0m \u001b[38;5;129;01mor\u001b[39;00m _global_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_forward_pre_hooks):\n\u001b[0;32m-> 1520\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m forward_call(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n\u001b[1;32m 1522\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m 1523\u001b[0m result \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n", + "File \u001b[0;32m/opt/miniconda/lib/python3.11/site-packages/accelerate/hooks.py:166\u001b[0m, in \u001b[0;36madd_hook_to_module..new_forward\u001b[0;34m(module, *args, **kwargs)\u001b[0m\n\u001b[1;32m 164\u001b[0m output \u001b[38;5;241m=\u001b[39m module\u001b[38;5;241m.\u001b[39m_old_forward(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n\u001b[1;32m 165\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m--> 166\u001b[0m output \u001b[38;5;241m=\u001b[39m module\u001b[38;5;241m.\u001b[39m_old_forward(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n\u001b[1;32m 167\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m module\u001b[38;5;241m.\u001b[39m_hf_hook\u001b[38;5;241m.\u001b[39mpost_forward(module, output)\n", + "File \u001b[0;32m/opt/miniconda/lib/python3.11/site-packages/bitsandbytes/nn/modules.py:248\u001b[0m, in \u001b[0;36mLinear4bit.forward\u001b[0;34m(self, x)\u001b[0m\n\u001b[1;32m 245\u001b[0m x \u001b[38;5;241m=\u001b[39m x\u001b[38;5;241m.\u001b[39mto(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mcompute_dtype)\n\u001b[1;32m 247\u001b[0m bias \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mbias \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;28;01melse\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mbias\u001b[38;5;241m.\u001b[39mto(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mcompute_dtype)\n\u001b[0;32m--> 248\u001b[0m out \u001b[38;5;241m=\u001b[39m bnb\u001b[38;5;241m.\u001b[39mmatmul_4bit(x, \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mweight\u001b[38;5;241m.\u001b[39mt(), bias\u001b[38;5;241m=\u001b[39mbias, quant_state\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mweight\u001b[38;5;241m.\u001b[39mquant_state)\n\u001b[1;32m 250\u001b[0m out \u001b[38;5;241m=\u001b[39m out\u001b[38;5;241m.\u001b[39mto(inp_dtype)\n\u001b[1;32m 252\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m out\n", + "File \u001b[0;32m/opt/miniconda/lib/python3.11/site-packages/bitsandbytes/autograd/_functions.py:579\u001b[0m, in \u001b[0;36mmatmul_4bit\u001b[0;34m(A, B, quant_state, out, bias)\u001b[0m\n\u001b[1;32m 577\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m out\n\u001b[1;32m 578\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m--> 579\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m MatMul4Bit\u001b[38;5;241m.\u001b[39mapply(A, B, out, bias, quant_state)\n", + "File \u001b[0;32m/opt/miniconda/lib/python3.11/site-packages/torch/autograd/function.py:553\u001b[0m, in \u001b[0;36mFunction.apply\u001b[0;34m(cls, *args, **kwargs)\u001b[0m\n\u001b[1;32m 550\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m torch\u001b[38;5;241m.\u001b[39m_C\u001b[38;5;241m.\u001b[39m_are_functorch_transforms_active():\n\u001b[1;32m 551\u001b[0m \u001b[38;5;66;03m# See NOTE: [functorch vjp and autograd interaction]\u001b[39;00m\n\u001b[1;32m 552\u001b[0m args \u001b[38;5;241m=\u001b[39m _functorch\u001b[38;5;241m.\u001b[39mutils\u001b[38;5;241m.\u001b[39munwrap_dead_wrappers(args)\n\u001b[0;32m--> 553\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28msuper\u001b[39m()\u001b[38;5;241m.\u001b[39mapply(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs) \u001b[38;5;66;03m# type: ignore[misc]\u001b[39;00m\n\u001b[1;32m 555\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m is_setup_ctx_defined:\n\u001b[1;32m 556\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mRuntimeError\u001b[39;00m(\n\u001b[1;32m 557\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mIn order to use an autograd.Function with functorch transforms \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 558\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m(vmap, grad, jvp, jacrev, ...), it must override the setup_context \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 559\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mstaticmethod. For more details, please see \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 560\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mhttps://pytorch.org/docs/master/notes/extending.func.html\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 561\u001b[0m )\n", + "File \u001b[0;32m/opt/miniconda/lib/python3.11/site-packages/bitsandbytes/autograd/_functions.py:516\u001b[0m, in \u001b[0;36mMatMul4Bit.forward\u001b[0;34m(ctx, A, B, out, bias, state)\u001b[0m\n\u001b[1;32m 511\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m torch\u001b[38;5;241m.\u001b[39mempty(A\u001b[38;5;241m.\u001b[39mshape[:\u001b[38;5;241m-\u001b[39m\u001b[38;5;241m1\u001b[39m] \u001b[38;5;241m+\u001b[39m B_shape[:\u001b[38;5;241m1\u001b[39m], dtype\u001b[38;5;241m=\u001b[39mA\u001b[38;5;241m.\u001b[39mdtype, device\u001b[38;5;241m=\u001b[39mA\u001b[38;5;241m.\u001b[39mdevice)\n\u001b[1;32m 514\u001b[0m \u001b[38;5;66;03m# 1. Dequantize\u001b[39;00m\n\u001b[1;32m 515\u001b[0m \u001b[38;5;66;03m# 2. MatmulnN\u001b[39;00m\n\u001b[0;32m--> 516\u001b[0m output \u001b[38;5;241m=\u001b[39m torch\u001b[38;5;241m.\u001b[39mnn\u001b[38;5;241m.\u001b[39mfunctional\u001b[38;5;241m.\u001b[39mlinear(A, F\u001b[38;5;241m.\u001b[39mdequantize_4bit(B, state)\u001b[38;5;241m.\u001b[39mto(A\u001b[38;5;241m.\u001b[39mdtype)\u001b[38;5;241m.\u001b[39mt(), bias)\n\u001b[1;32m 518\u001b[0m \u001b[38;5;66;03m# 3. Save state\u001b[39;00m\n\u001b[1;32m 519\u001b[0m ctx\u001b[38;5;241m.\u001b[39mstate \u001b[38;5;241m=\u001b[39m state\n", + "\u001b[0;31mRuntimeError\u001b[0m: CUDA error: CUBLAS_STATUS_NOT_INITIALIZED when calling `cublasCreate(handle)`" + ] + } + ], + "source": [ + "def train(model, tokenizer, dataset, output_dir):\n", + " model.gradient_checkpointing_enable()\n", + "\n", + " model = prepare_model_for_kbit_training(model)\n", + " modules = find_all_linear_names(model)\n", + "\n", + " peft_config = create_peft_config(modules)\n", + " model = get_peft_model(model, peft_config)\n", + "\n", + " print_trainable_parameters(model)\n", + "\n", + " trainer = Trainer(\n", + " model=model,\n", + " train_dataset=dataset,\n", + " eval_dataset=dataset_subset,\n", + " args=TrainingArguments(\n", + " per_device_train_batch_size=1,\n", + " gradient_accumulation_steps=10,\n", + " warmup_steps=10,\n", + " max_steps=20,\n", + " learning_rate=2.5e-5,\n", + " fp16=True,\n", + " logging_steps=2,\n", + " eval_steps=10,\n", + " do_eval=True,\n", + " output_dir=\"outputs\",\n", + " optim=\"paged_adamw_8bit\",\n", + " report_to=\"wandb\"\n", + " ),\n", + " data_collator=DataCollatorForLanguageModeling(tokenizer, mlm=False)\n", + " )\n", + "\n", + " model.config.use_cache = False \n", + "\n", + "\n", + " dtypes = {}\n", + " for _, p in model.named_parameters():\n", + " dtype = p.dtype\n", + " if dtype not in dtypes: dtypes[dtype] = 0\n", + " dtypes[dtype] += p.numel()\n", + " total = 0\n", + " for k, v in dtypes.items(): total+= v\n", + " for k, v in dtypes.items():\n", + " print(k, v, v/total)\n", + "\n", + " do_train = True\n", + "\n", + " # Launch training\n", + " print(\"Training...\")\n", + "\n", + " if do_train:\n", + " train_result = trainer.train()\n", + " metrics = train_result.metrics\n", + " trainer.log_metrics(\"train\", metrics)\n", + " trainer.save_metrics(\"train\", metrics)\n", + " trainer.save_state()\n", + " print(metrics)\n", + "\n", + " ###\n", + "\n", + " # Saving model\n", + " print(\"Saving last checkpoint of the model...\")\n", + " os.makedirs(output_dir, exist_ok=True)\n", + " trainer.model.save_pretrained(output_dir)\n", + "\n", + " # Free memory for merging weights\n", + " del model\n", + " del trainer\n", + " torch.cuda.empty_cache()\n", + "namespace = \"results\"\n", + "repo_name = \"stableai\"\n", + "output_dir = f\"{namespace}/{repo_name}\"\n", + "train(model, tokenizer2, dataset, output_dir)" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "3XCfOCLzmDcR" + }, + "source": [ + "**Merge weights**" + ] + }, + { + "cell_type": "code", + "execution_count": 69, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 49, + "referenced_widgets": [ + "0213bde523d843a69e34b32aad8ce8c0", + "4e4ee24a2da7418d8f41aa50dfe13c48", + "221160933ee84438bf9191a0183bd727", + "96c01f8404264611b18167586f114a67", + "de87494d800e40cc9139807cedb5378b", + "8f8bd8aa9c1141a09a4becad4aa80418", + "6d93880e03644c59bb2aa97a6524d246", + "3d5ea8d8acba467d85704a73a223c6af", + "cf20581b6f3d498dbd25711e626d6f15", + "d590bf4d7b6a4aea8db3b8a800ee343f", + "f8991a7f787d427ca9215135ce2c3c77" + ] + }, + "id": "sMveKsptXIuc", + "outputId": "1e53fb9c-1480-4ab8-9808-88afeaecd853" + }, + "outputs": [], + "source": [ + "\n", + "model = AutoPeftModelForCausalLM.from_pretrained(output_dir, device_map=\"auto\", torch_dtype=torch.bfloat16, trust_remote_code=True)\n", + "model = model.merge_and_unload()" + ] + }, + { + "cell_type": "code", + "execution_count": 70, + "metadata": { + "id": "Wkr8Li03lh6K" + }, + "outputs": [], + "source": [ + "output_merged_dir = \"results/stableai/final_merged_checkpoint\"\n", + "os.makedirs(output_merged_dir, exist_ok=True)\n" + ] + }, + { + "cell_type": "code", + "execution_count": 71, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "dCDXHUx0x9YD", + "outputId": "0616744e-ab43-40da-f8a0-f090d1a86d01" + }, + "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.\n" + ] + }, + { + "data": { + "text/plain": [ + "('results/stableai/final_merged_checkpoint/tokenizer_config.json',\n", + " 'results/stableai/final_merged_checkpoint/special_tokens_map.json',\n", + " 'results/stableai/final_merged_checkpoint/tokenizer.json')" + ] + }, + "execution_count": 71, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# save tokenizer for easy inference\n", + "tokenizer = AutoTokenizer.from_pretrained(model_name)\n", + "\n", + "tokenizer.save_pretrained(output_merged_dir)" + ] + }, + { + "cell_type": "code", + "execution_count": 72, + "metadata": { + "id": "q4kzB6rzooG_" + }, + "outputs": [], + "source": [ + "#model.save_pretrained(output_merged_dir, safe_serialization=True)\n" + ] + }, + { + "cell_type": "code", + "execution_count": 67, + "metadata": {}, + "outputs": [], + "source": [ + "def create_prompt_formats_for_test(sample):\n", + " \"\"\"\n", + " Formats a sample dictionary into a prompt suitable for fine-tuning Mistral for ad classification.\n", + "\n", + " Args:\n", + " sample: A dictionary containing 'text' and 'label' fields.\n", + "\n", + " Returns:\n", + " The modified sample dictionary with the formatted prompt.\n", + " \"\"\"\n", + " INTRO_BLURB = \"You are tasked with classifying messages as either advertisements (Ad) or non-advertisements (Not Ad) based on a comprehensive analysis of various factors.\"\n", + "\n", + " INSTRUCTION_KEY = \"### Text:\"\n", + "\n", + " blurb = f\"{INTRO_BLURB}\\n\\n\"\n", + " text = f\"{INSTRUCTION_KEY}\\n{sample['text']}\\n\\n\"\n", + "\n", + " formatted_prompt = blurb + text\n", + " sample[\"text\"] = formatted_prompt\n", + "\n", + " return sample\n" + ] + }, + { + "cell_type": "code", + "execution_count": 68, + "metadata": { + "id": "lFGmUSKMCYul" + }, + "outputs": [], + "source": [ + "prompts = []\n", + "for prompt in dataset_subset:\n", + " prompts.append(create_prompt_formats_for_test(prompt)['text'])" + ] + }, + { + "cell_type": "code", + "execution_count": 69, + "metadata": { + "id": "4bNAmwZdp_-Z" + }, + "outputs": [], + "source": [ + "import time" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "kZL3HRc9nWCC" + }, + "source": [ + "**Inference using Instruction or Question Only**\n" + ] + }, + { + "cell_type": "code", + "execution_count": 70, + "metadata": { + "id": "q_kyOVVodUfR" + }, + "outputs": [], + "source": [ + "input_texts = []\n", + "for prompt in prompts:\n", + " input_texts.append(f\"Instruction: {prompt}\")" + ] + }, + { + "cell_type": "code", + "execution_count": 71, + "metadata": {}, + "outputs": [], + "source": [ + "ad = input_texts[83]" + ] + }, + { + "cell_type": "code", + "execution_count": 72, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "'Instruction: You are tasked with classifying messages as either advertisements (Ad) or non-advertisements (Not Ad) based on a comprehensive analysis of various factors.\\n\\n### Text:\\nቻይና የሚገኙ ተማሪዎችን ወደ ኢትዮጵያ ለማምጣት ግብረኃይል ተቋቋመ! በኮሮና ቫይረስ ስጋት ውስጥ እንደሆኑ የተነገረላቸው ተማሪዎችን ለማስመጣት ግብረኃይል መቋቋሙን የውጭ ጉዳይ ሚኒስቴር ዛሬ አርብ የካቲት 6/2012 በወቅታዊ ጉዳይ በሰጠው ጋዜጣዊ መግለጫ ላይ አስታወቀ፡፡ በቻይና ለሚገኙ ኢትዮጵያውያን ተማሪዎች መንግስት የገንዘብ ድጋፍ መላኩን የገለጹት የሚኒስቴሩ ቃል አቀባይ ነብያት ጌታቸው ተማሪዎቹ በቫይረስ እንዳይጠቁ ክትትል እየተደረገ ነው ብለዋል። Via Addis Maleda @YeneTube @FikerAssefa\\n\\n'" + ] + }, + "execution_count": 72, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "not_ad = input_texts[777]\n", + "not_ad" + ] + }, + { + "cell_type": "code", + "execution_count": 73, + "metadata": {}, + "outputs": [], + "source": [ + "def format_input(sample):\n", + " \"\"\"\n", + " Formats a sample dictionary into a prompt suitable for fine-tuning Mistral for ad classification.\n", + "\n", + " Args:\n", + " sample: A dictionary containing 'text' and 'label' fields.\n", + "\n", + " Returns:\n", + " The modified sample dictionary with the formatted prompt.\n", + " \"\"\"\n", + " INTRO_BLURB = \"You are tasked with classifying messages as either advertisements (Ad) or non-advertisements (Not Ad) based on a comprehensive analysis of various factors.\"\n", + "\n", + " INSTRUCTION_KEY = \"### Text:\"\n", + "\n", + " blurb = f\"{INTRO_BLURB}\\n\\n\"\n", + " text = f\"{INSTRUCTION_KEY}\\n{sample}\\n\\n\"\n", + "\n", + " formatted_prompt = blurb + text\n", + "\n", + " return formatted_prompt\n" + ] + }, + { + "cell_type": "code", + "execution_count": 74, + "metadata": { + "id": "ePVbmJyqt1UI" + }, + "outputs": [ + { + "ename": "NameError", + "evalue": "name 'tokenizer' is not defined", + "output_type": "error", + "traceback": [ + "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m", + "\u001b[0;31mNameError\u001b[0m Traceback (most recent call last)", + "Cell \u001b[0;32mIn[74], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m input_ids \u001b[38;5;241m=\u001b[39m tokenizer\u001b[38;5;241m.\u001b[39mencode(not_ad, return_tensors\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mpt\u001b[39m\u001b[38;5;124m\"\u001b[39m, truncation\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mTrue\u001b[39;00m)\u001b[38;5;241m.\u001b[39mto(model\u001b[38;5;241m.\u001b[39mdevice)\n\u001b[1;32m 3\u001b[0m start_time \u001b[38;5;241m=\u001b[39m time\u001b[38;5;241m.\u001b[39mtime()\n\u001b[1;32m 5\u001b[0m output \u001b[38;5;241m=\u001b[39m model\u001b[38;5;241m.\u001b[39mgenerate(input_ids, max_length\u001b[38;5;241m=\u001b[39mmax_length, temperature\u001b[38;5;241m=\u001b[39m\u001b[38;5;241m1.0\u001b[39m, top_k\u001b[38;5;241m=\u001b[39m\u001b[38;5;241m50\u001b[39m, top_p\u001b[38;5;241m=\u001b[39m\u001b[38;5;241m0.95\u001b[39m, num_return_sequences\u001b[38;5;241m=\u001b[39m\u001b[38;5;241m1\u001b[39m)\n", + "\u001b[0;31mNameError\u001b[0m: name 'tokenizer' is not defined" + ] + } + ], + "source": [ + "input_ids = tokenizer.encode(not_ad, return_tensors=\"pt\", truncation=True).to(model.device)\n", + "\n", + "start_time = time.time()\n", + "\n", + "output = model.generate(input_ids, max_length=max_length, temperature=1.0, top_k=50, top_p=0.95, num_return_sequences=1)\n", + "generated_output = tokenizer.decode(output[0], skip_special_tokens=True)\n", + "\n", + "end_time = time.time()\n", + "\n", + "# Calculate and print the inference time\n", + "inference_time = end_time - start_time\n" + ] + }, + { + "cell_type": "code", + "execution_count": 81, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "TEST \n", + "\n", + "Generated Output:\n", + "======================\n", + "Instruction: You are tasked with classifying messages as either advertisements (Ad) or non-advertisements (Not Ad) based on a comprehensive analysis of various factors.\n", + "\n", + "### Text:\n", + "ቻይና የሚገኙ ተማሪዎችን ወደ ኢትዮጵያ ለማምጣት ግብረኃይል ተቋቋመ! በኮሮና ቫይረስ ስጋት ውስጥ እንደሆኑ የተነገረላቸው ተማሪዎችን ለማስመጣት ግብረኃይል መቋቋሙን የውጭ ጉዳይ ሚኒስቴር ዛሬ አርብ የካቲት 6/2012 በወቅታዊ ጉዳይ በሰጠው ጋዜጣዊ መግለጫ ላይ አስታወቀ፡፡ በቻይና ለሚገኙ ኢትዮጵያውያን ተማሪዎች መንግስት የገንዘብ ድጋፍ መላኩን የገለጹት የሚኒስቴሩ ቃል አቀባይ ነብያት ጌታቸው ተማሪዎቹ በቫይረስ እንዳይጠቁ ክትትል እየተደረገ ነው ብለዋል። Via Addis Maleda @YeneTube @FikerAssefa\n", + "\n", + "\n", + "### Explanation:\n", + "The message is an advertisement for a product called \"ሚገኙ ተማሪዎችን ወደ ኢትዮጵያ ለማምጣት ግብረኃይል ተቋቋመ!\" which translates to \"Get rid of bad credit with ease!\" The message also mentions that the product has helped many people to improve their credit score. The message ends with a call to action to buy the product through a specific website. This message is an advertisement for a product that promises to help people improve their credit score. The message uses a call to action to encourage people to buy the product.\n", + "\n", + "Inference Time:5.075511693954468 seconds\n", + "==========================================\n" + ] + } + ], + "source": [ + "# Print the formatted input\n", + "print(f\"TEST \\n\")\n", + "print(f\"Generated Output:\\n======================\\n{generated_output}\\n\")\n", + "print(f\"Inference Time:{inference_time} seconds\\n==========================================\")" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [] + } + ], + "metadata": { + "accelerator": "GPU", + "colab": { + "gpuType": "A100", + "machine_shape": "hm", + "provenance": [] + }, + "kernelspec": { + "display_name": "Python 3 (ipykernel)", + "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": "3.11.5" + }, + "widgets": { + "application/vnd.jupyter.widget-state+json": { + "004123701b5c4085b7bbaf6024a1c6a0": { + "model_module": "@jupyter-widgets/base", + "model_module_version": "1.2.0", + "model_name": "LayoutModel", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "0213bde523d843a69e34b32aad8ce8c0": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "HBoxModel", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HBoxModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HBoxView", + "box_style": "", + "children": [ + "IPY_MODEL_4e4ee24a2da7418d8f41aa50dfe13c48", + "IPY_MODEL_221160933ee84438bf9191a0183bd727", + "IPY_MODEL_96c01f8404264611b18167586f114a67" + ], + "layout": "IPY_MODEL_de87494d800e40cc9139807cedb5378b" + } + }, + "02c0da9b2dd24f2186e0b80eba63728b": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "HTMLModel", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HTMLModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_6b7c3bd8a0aa422cbfe29eba10281783", + "placeholder": "​", + "style": "IPY_MODEL_3cde60fe9c314ab1890c56b3e22982fb", + "value": "tokenizer.model: 100%" + } + }, + "0531d921ee994496bc356b165f843918": { + "model_module": "@jupyter-widgets/base", + "model_module_version": "1.2.0", + "model_name": "LayoutModel", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "0539d23c4c064f4a90296fe22a8a84b3": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "DescriptionStyleModel", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "DescriptionStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "description_width": "" + } + }, + "055187fe1d204467892336b850a986c5": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "HBoxModel", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HBoxModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HBoxView", + "box_style": "", + "children": [ + "IPY_MODEL_c47945ffea92487ab3b5f0184fcd4aac", + "IPY_MODEL_c2473c5645dc47f585d63c11536b097a", + "IPY_MODEL_0e51aad4b7e844f69f5c81f97d3673a7" + ], + "layout": "IPY_MODEL_31e1bb79a79e48f4aaefbd145a6ccb0e" + } + }, + "07c82a6818454130be13570faf77d1a7": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "FloatProgressModel", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "FloatProgressModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "ProgressView", + "bar_style": "success", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_a3e05d1e704f46f7bfdca2cefc04a610", + "max": 609, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_60a679a1d13b475c835785c765012444", + "value": 609 + } + }, + "081c408abd914a29b48faf34ee12a6cd": { + "model_module": "@jupyter-widgets/base", + "model_module_version": "1.2.0", + "model_name": "LayoutModel", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "089965f75c0840b2a668241d75e6ed92": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "FloatProgressModel", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "FloatProgressModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "ProgressView", + "bar_style": "", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_929e7cc6c8c6468b98ac4b9f9ed37947", + "max": 18404, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_2408301332bf46028f478451e29e27d0", + "value": 18404 + } + }, + "0a0e8f6c7a2645bfbd2df9509a21909d": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "HBoxModel", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HBoxModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HBoxView", + "box_style": "", + "children": [ + "IPY_MODEL_afaa2c18a1eb47dc955ae934c4968a01", + "IPY_MODEL_b36b878e0b7347e59fe87bb0de806cfb", + "IPY_MODEL_87570f6d2e644c318196678a46bcf922" + ], + "layout": "IPY_MODEL_db589f37bf4c419284f21c6267d6f408" + } + }, + "0dd65cecc4f84cfc9cf58ecd5d610c01": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "DescriptionStyleModel", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "DescriptionStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "description_width": "" + } + }, + "0e51aad4b7e844f69f5c81f97d3673a7": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "HTMLModel", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HTMLModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_f642eeb766eb4c33b6e42e43d2108d5a", + "placeholder": "​", + "style": "IPY_MODEL_52b4491a79564237829ab02c8500e089", + "value": " 3.50G/3.50G [00:13<00:00, 239MB/s]" + } + }, + "0fe7a638601c4d62ab15a1edaab7f5e1": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "HTMLModel", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HTMLModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_b2f36e79b411454b9c648f07a7053bf7", + "placeholder": "​", + "style": "IPY_MODEL_e7091d8f4455432795782b522d5ee9b6", + "value": " 2/2 [00:59<00:00, 26.83s/it]" + } + }, + "1057a900755a44ee973109682bd1a285": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "DescriptionStyleModel", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "DescriptionStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "description_width": "" + } + }, + "10a27dc44b1f43ba9c774564169c617f": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "DescriptionStyleModel", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "DescriptionStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "description_width": "" + } + }, + "1142fcef536a4f0a914322bbce538054": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "HTMLModel", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HTMLModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_353889488fb941ab9de818997d64d6b7", + "placeholder": "​", + "style": "IPY_MODEL_64f4d807b9d04a89b7abe9792236dc4a", + "value": "Downloading shards: 100%" + } + }, + "12fc2f4a906e4806b50fcd145f7726e1": { + "model_module": "@jupyter-widgets/base", + "model_module_version": "1.2.0", + "model_name": "LayoutModel", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "14206e17bdf14c9f8a81ed30bea678cf": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "FloatProgressModel", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "FloatProgressModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "ProgressView", + "bar_style": "success", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_fcc9664580b6482dbe8ad7f4c2fabb09", + "max": 1842767, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_a94f5ffc1e864be6b95a7372c471d9bf", + "value": 1842767 + } + }, + "17de6afe24e94ff2960760c0bbbb7146": { + "model_module": "@jupyter-widgets/base", + "model_module_version": "1.2.0", + "model_name": "LayoutModel", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "18454784ad24444ca34b726f83ce8248": { + "model_module": "@jupyter-widgets/base", + "model_module_version": "1.2.0", + "model_name": "LayoutModel", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": "hidden", + "width": null + } + }, + "1af6d6ba6365401a96a6a4e6d2b39b87": { + "model_module": "@jupyter-widgets/base", + "model_module_version": "1.2.0", + "model_name": "LayoutModel", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "1dac838ad78c4f89844d34309ff71013": { + "model_module": "@jupyter-widgets/base", + "model_module_version": "1.2.0", + "model_name": "LayoutModel", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "1fe6f1ef4e924bc9b08495077671c39d": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "DescriptionStyleModel", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "DescriptionStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "description_width": "" + } + }, + "215483dd3721466ebdb9a383eac7580a": { + "model_module": "@jupyter-widgets/base", + "model_module_version": "1.2.0", + "model_name": "LayoutModel", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "221160933ee84438bf9191a0183bd727": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "FloatProgressModel", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "FloatProgressModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "ProgressView", + "bar_style": "success", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_3d5ea8d8acba467d85704a73a223c6af", + "max": 2, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_cf20581b6f3d498dbd25711e626d6f15", + "value": 2 + } + }, + "226b0ff5917b49a5bbdd6ec45fa307d9": { + "model_module": "@jupyter-widgets/base", + "model_module_version": "1.2.0", + "model_name": "LayoutModel", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "2408301332bf46028f478451e29e27d0": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "ProgressStyleModel", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "ProgressStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "bar_color": null, + "description_width": "" + } + }, + "28bb7249f8e54cdfa8ea222ccb5482c6": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "HBoxModel", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HBoxModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HBoxView", + "box_style": "", + "children": [ + "IPY_MODEL_684a973060d9456a86d444fbbeaa2133", + "IPY_MODEL_089965f75c0840b2a668241d75e6ed92", + "IPY_MODEL_a7712b27e6c94e45aa2a060ab49f0e04" + ], + "layout": "IPY_MODEL_bb1f598f9aea44f1a7fe4da9b3d869fb" + } + }, + "2acdb638a06d4764b2479c861605b266": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "DescriptionStyleModel", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "DescriptionStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "description_width": "" + } + }, + "2d1801b723f74ee6ade584e95f23696e": { + "model_module": "@jupyter-widgets/base", + "model_module_version": "1.2.0", + "model_name": "LayoutModel", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "2df80d3d454b442388a2e3127e736e3e": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "HTMLModel", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HTMLModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_900a336dc6a744cf8f6221bc63aaa633", + "placeholder": "​", + "style": "IPY_MODEL_0539d23c4c064f4a90296fe22a8a84b3", + "value": " 609/609 [00:00<00:00, 53.7kB/s]" + } + }, + "2e11546d6bab47b9917cd7751651e04e": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "FloatProgressModel", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "FloatProgressModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "ProgressView", + "bar_style": "success", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_b91fa9edc65a4093a13931160210d5e5", + "max": 499723, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_adbc64a4b9f245ab86258cbffa805241", + "value": 499723 + } + }, + "2ee7f2e534c24c8ba888f01db059bdbb": { + "model_module": "@jupyter-widgets/base", + "model_module_version": "1.2.0", + "model_name": "LayoutModel", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "31e1bb79a79e48f4aaefbd145a6ccb0e": { + "model_module": "@jupyter-widgets/base", + "model_module_version": "1.2.0", + "model_name": "LayoutModel", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "353889488fb941ab9de818997d64d6b7": { + "model_module": "@jupyter-widgets/base", + "model_module_version": "1.2.0", + "model_name": "LayoutModel", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "379912692baf4f0a8e629d9273071984": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "HBoxModel", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HBoxModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HBoxView", + "box_style": "", + "children": [ + "IPY_MODEL_02c0da9b2dd24f2186e0b80eba63728b", + "IPY_MODEL_2e11546d6bab47b9917cd7751651e04e", + "IPY_MODEL_d0327ceb4e9a4e8f93624c522450f8f6" + ], + "layout": "IPY_MODEL_2d1801b723f74ee6ade584e95f23696e" + } + }, + "393f451ec81940b181e259c5fbb62e84": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "DescriptionStyleModel", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "DescriptionStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "description_width": "" + } + }, + "3ade97e55b8247c2a2f440db4b56bced": { + "model_module": "@jupyter-widgets/base", + "model_module_version": "1.2.0", + "model_name": "LayoutModel", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "3cde60fe9c314ab1890c56b3e22982fb": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "DescriptionStyleModel", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "DescriptionStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "description_width": "" + } + }, + "3d5ea8d8acba467d85704a73a223c6af": { + "model_module": "@jupyter-widgets/base", + "model_module_version": "1.2.0", + "model_name": "LayoutModel", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "3eb3fd49d093408a8dff8097bad6c2f6": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "DescriptionStyleModel", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "DescriptionStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "description_width": "" + } + }, + "3f7c91d894b2499591501e8b70b51dc9": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "HTMLModel", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HTMLModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_98f1e2e0824f40ab92048e9f5a2ed067", + "placeholder": "​", + "style": "IPY_MODEL_3eb3fd49d093408a8dff8097bad6c2f6", + "value": "model-00001-of-00002.safetensors: 100%" + } + }, + "407f7d85e7964983a1ec685b6db14f1c": { + "model_module": "@jupyter-widgets/base", + "model_module_version": "1.2.0", + "model_name": "LayoutModel", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "4105500f56514764856fdd104feb4a63": { + "model_module": "@jupyter-widgets/base", + "model_module_version": "1.2.0", + "model_name": "LayoutModel", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "43ef1a6f9cef4e08bc9237b3ec7856e5": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "HTMLModel", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HTMLModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_7435a21f09ea4131bd61284634db5b7a", + "placeholder": "​", + "style": "IPY_MODEL_7a714cab0fa24fa3b11f5eb626d51efd", + "value": "Map: 100%" + } + }, + "46be584dddd84634b539117fcecdc4b7": { + "model_module": "@jupyter-widgets/base", + "model_module_version": "1.2.0", + "model_name": "LayoutModel", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "48c4888d267e46a69fbd7648250b5a93": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "DescriptionStyleModel", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "DescriptionStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "description_width": "" + } + }, + "48d300a81ab544708d44ac7049a0bd3a": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "ProgressStyleModel", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "ProgressStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "bar_color": null, + "description_width": "" + } + }, + "4a5bbd81ea2b424c953ddabce0633d90": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "ProgressStyleModel", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "ProgressStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "bar_color": null, + "description_width": "" + } + }, + "4b78213b465e416d9f7fd547d11059af": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "HTMLModel", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HTMLModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_215483dd3721466ebdb9a383eac7580a", + "placeholder": "​", + "style": "IPY_MODEL_7f2597d2478a4320bc191e878697d5a7", + "value": " 9.98G/9.98G [00:44<00:00, 174MB/s]" + } + }, + "4e4ee24a2da7418d8f41aa50dfe13c48": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "HTMLModel", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HTMLModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_8f8bd8aa9c1141a09a4becad4aa80418", + "placeholder": "​", + "style": "IPY_MODEL_6d93880e03644c59bb2aa97a6524d246", + "value": "Loading checkpoint shards: 100%" + } + }, + "51985bec0a1947fead86dabe1b605193": { + "model_module": "@jupyter-widgets/base", + "model_module_version": "1.2.0", + "model_name": "LayoutModel", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "52b4491a79564237829ab02c8500e089": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "DescriptionStyleModel", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "DescriptionStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "description_width": "" + } + }, + "54de021924594864b79016c42242f9e9": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "DescriptionStyleModel", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "DescriptionStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "description_width": "" + } + }, + "5c1f9ab6c1594871b8b5afdf51e19726": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "HBoxModel", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HBoxModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HBoxView", + "box_style": "", + "children": [ + "IPY_MODEL_3f7c91d894b2499591501e8b70b51dc9", + "IPY_MODEL_92a8a3349bf942fe8a91fb36efad1e60", + "IPY_MODEL_4b78213b465e416d9f7fd547d11059af" + ], + "layout": "IPY_MODEL_77b5a275d26e4f4ba826f2c9198e0d65" + } + }, + "5fc5433f4f9f48e59dac63c0c3bd156a": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "DescriptionStyleModel", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "DescriptionStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "description_width": "" + } + }, + "60a679a1d13b475c835785c765012444": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "ProgressStyleModel", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "ProgressStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "bar_color": null, + "description_width": "" + } + }, + "64133685cf1043149c999e654c5e247f": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "HTMLModel", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HTMLModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_fef86b2372094c71b7f75ac7dd0caabd", + "placeholder": "​", + "style": "IPY_MODEL_1057a900755a44ee973109682bd1a285", + "value": "special_tokens_map.json: 100%" + } + }, + "64f4d807b9d04a89b7abe9792236dc4a": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "DescriptionStyleModel", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "DescriptionStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "description_width": "" + } + }, + "66febca78ca84452b72499635a8b259b": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "HTMLModel", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HTMLModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_87efe32842c741918e411eb68a3fe69f", + "placeholder": "​", + "style": "IPY_MODEL_0dd65cecc4f84cfc9cf58ecd5d610c01", + "value": " 414/414 [00:00<00:00, 39.6kB/s]" + } + }, + "6733d61830d143af9dcdfea0a1200e60": { + "model_module": "@jupyter-widgets/base", + "model_module_version": "1.2.0", + "model_name": "LayoutModel", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "6776efc6b05a43149515f8a9ab8c4102": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "ProgressStyleModel", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "ProgressStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "bar_color": null, + "description_width": "" + } + }, + "684a973060d9456a86d444fbbeaa2133": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "HTMLModel", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HTMLModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_f3b6da9b49f547c7ad92d1b86af2fa78", + "placeholder": "​", + "style": "IPY_MODEL_77dc8fce07a04fc1988737496ef09c09", + "value": "Filter: 100%" + } + }, + "68a2dd2fbcdf45f4b96ac5ab1d33c32b": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "HBoxModel", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HBoxModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HBoxView", + "box_style": "", + "children": [ + "IPY_MODEL_64133685cf1043149c999e654c5e247f", + "IPY_MODEL_86090b230d71463989f09b6860f8d2c6", + "IPY_MODEL_66febca78ca84452b72499635a8b259b" + ], + "layout": "IPY_MODEL_226b0ff5917b49a5bbdd6ec45fa307d9" + } + }, + "6a00fd4fd52d4f87a7d1df2e86ce25d6": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "HBoxModel", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HBoxModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HBoxView", + "box_style": "", + "children": [ + "IPY_MODEL_7928cbeebc5c48ee826531612770ad7f", + "IPY_MODEL_8d3330dcb56242cf881ed948978d8dc5", + "IPY_MODEL_6eb867a7932a482c8095054be7a62f0c" + ], + "layout": "IPY_MODEL_7e3cdef7cafb48d6a11549b90cbd14a4" + } + }, + "6b7c3bd8a0aa422cbfe29eba10281783": { + "model_module": "@jupyter-widgets/base", + "model_module_version": "1.2.0", + "model_name": "LayoutModel", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "6c64e8c244134d07a92a76bd5903c519": { + "model_module": "@jupyter-widgets/base", + "model_module_version": "1.2.0", + "model_name": "LayoutModel", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "6c87c5570fac4712a1a77c9e78aa9105": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "HTMLModel", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HTMLModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_004123701b5c4085b7bbaf6024a1c6a0", + "placeholder": "​", + "style": "IPY_MODEL_b994b8fcf9d64f46bce1ededbd2d0042", + "value": " 188/188 [00:00<00:00, 17.6kB/s]" + } + }, + "6d93880e03644c59bb2aa97a6524d246": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "DescriptionStyleModel", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "DescriptionStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "description_width": "" + } + }, + "6e6dfc7b5e7c4393b32440417c759a0f": { + "model_module": "@jupyter-widgets/base", + "model_module_version": "1.2.0", + "model_name": "LayoutModel", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "6eb867a7932a482c8095054be7a62f0c": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "HTMLModel", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HTMLModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_cf84406cd1be464ca9caf07b3ab7cecf", + "placeholder": "​", + "style": "IPY_MODEL_cd21e232645e41d4834badc1fb0a860d", + "value": " 776/776 [00:00<00:00, 72.7kB/s]" + } + }, + "70918a1c19a443b380bed9b87978cf51": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "HBoxModel", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HBoxModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HBoxView", + "box_style": "", + "children": [ + "IPY_MODEL_43ef1a6f9cef4e08bc9237b3ec7856e5", + "IPY_MODEL_aad494542dc1422abe803ecdb6c77e76", + "IPY_MODEL_a05250531071414585d29876f1f05319" + ], + "layout": "IPY_MODEL_7bb63bb641034fe7b0f3f422eec3b9d4" + } + }, + "70b33dfa18db4e768458fa6930d00a4a": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "DescriptionStyleModel", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "DescriptionStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "description_width": "" + } + }, + "719ee4a0fe29440c8185eaec857cbc0d": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "HTMLModel", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HTMLModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_d63611b41599470a84357222964933e7", + "placeholder": "​", + "style": "IPY_MODEL_54de021924594864b79016c42242f9e9", + "value": "Map: 100%" + } + }, + "74233ec9e4b94e64ba5ed3bfc544cab1": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "HBoxModel", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HBoxModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HBoxView", + "box_style": "", + "children": [ + "IPY_MODEL_1142fcef536a4f0a914322bbce538054", + "IPY_MODEL_9ab388c3b879402a899fc953e650a117", + "IPY_MODEL_0fe7a638601c4d62ab15a1edaab7f5e1" + ], + "layout": "IPY_MODEL_51985bec0a1947fead86dabe1b605193" + } + }, + "7435a21f09ea4131bd61284634db5b7a": { + "model_module": "@jupyter-widgets/base", + "model_module_version": "1.2.0", + "model_name": "LayoutModel", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "7650d6d7fd5f490d9901f0bf8b970eff": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "ProgressStyleModel", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "ProgressStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "bar_color": null, + "description_width": "" + } + }, + "7651d0f306884b53848bd64bc56df500": { + "model_module": "@jupyter-widgets/base", + "model_module_version": "1.2.0", + "model_name": "LayoutModel", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "77b5a275d26e4f4ba826f2c9198e0d65": { + "model_module": "@jupyter-widgets/base", + "model_module_version": "1.2.0", + "model_name": "LayoutModel", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "77dc8fce07a04fc1988737496ef09c09": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "DescriptionStyleModel", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "DescriptionStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "description_width": "" + } + }, + "7928cbeebc5c48ee826531612770ad7f": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "HTMLModel", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HTMLModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_0531d921ee994496bc356b165f843918", + "placeholder": "​", + "style": "IPY_MODEL_10a27dc44b1f43ba9c774564169c617f", + "value": "tokenizer_config.json: 100%" + } + }, + "7a714cab0fa24fa3b11f5eb626d51efd": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "DescriptionStyleModel", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "DescriptionStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "description_width": "" + } + }, + "7bb63bb641034fe7b0f3f422eec3b9d4": { + "model_module": "@jupyter-widgets/base", + "model_module_version": "1.2.0", + "model_name": "LayoutModel", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": "hidden", + "width": null + } + }, + "7c1fc07ce3b64a23835ec167bd9e11a7": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "ProgressStyleModel", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "ProgressStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "bar_color": null, + "description_width": "" + } + }, + "7c50fd8a551846c4a1c3d1244f6f9f46": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "ProgressStyleModel", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "ProgressStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "bar_color": null, + "description_width": "" + } + }, + "7e3cdef7cafb48d6a11549b90cbd14a4": { + "model_module": "@jupyter-widgets/base", + "model_module_version": "1.2.0", + "model_name": "LayoutModel", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "7f2597d2478a4320bc191e878697d5a7": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "DescriptionStyleModel", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "DescriptionStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "description_width": "" + } + }, + "7f7ef54bc5b14f709279b53311b48524": { + "model_module": "@jupyter-widgets/base", + "model_module_version": "1.2.0", + "model_name": "LayoutModel", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "86090b230d71463989f09b6860f8d2c6": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "FloatProgressModel", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "FloatProgressModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "ProgressView", + "bar_style": "success", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_2ee7f2e534c24c8ba888f01db059bdbb", + "max": 414, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_7c50fd8a551846c4a1c3d1244f6f9f46", + "value": 414 + } + }, + "87570f6d2e644c318196678a46bcf922": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "HTMLModel", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HTMLModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_a37699cadc064618bcc850ba37b01145", + "placeholder": "​", + "style": "IPY_MODEL_5fc5433f4f9f48e59dac63c0c3bd156a", + "value": " 26.8k/26.8k [00:00<00:00, 2.05MB/s]" + } + }, + "87efe32842c741918e411eb68a3fe69f": { + "model_module": "@jupyter-widgets/base", + "model_module_version": "1.2.0", + "model_name": "LayoutModel", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "89a6f68b747f4a7f9708081dd205e995": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "HBoxModel", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HBoxModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HBoxView", + "box_style": "", + "children": [ + "IPY_MODEL_ba98a5af142a46ac979d43f45c7f1bc2", + "IPY_MODEL_ceb1be11f57d4c57893ad22ef99b6653", + "IPY_MODEL_6c87c5570fac4712a1a77c9e78aa9105" + ], + "layout": "IPY_MODEL_4105500f56514764856fdd104feb4a63" + } + }, + "8a0340af2ed54f47a3b7e585ea80cb43": { + "model_module": "@jupyter-widgets/base", + "model_module_version": "1.2.0", + "model_name": "LayoutModel", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "8d3330dcb56242cf881ed948978d8dc5": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "FloatProgressModel", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "FloatProgressModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "ProgressView", + "bar_style": "success", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_6733d61830d143af9dcdfea0a1200e60", + "max": 776, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_94a3ee09029a46cf8a62f2ea03a8bc62", + "value": 776 + } + }, + "8f8bd8aa9c1141a09a4becad4aa80418": { + "model_module": "@jupyter-widgets/base", + "model_module_version": "1.2.0", + "model_name": "LayoutModel", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "900a336dc6a744cf8f6221bc63aaa633": { + "model_module": "@jupyter-widgets/base", + "model_module_version": "1.2.0", + "model_name": "LayoutModel", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "929e7cc6c8c6468b98ac4b9f9ed37947": { + "model_module": "@jupyter-widgets/base", + "model_module_version": "1.2.0", + "model_name": "LayoutModel", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "92a8a3349bf942fe8a91fb36efad1e60": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "FloatProgressModel", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "FloatProgressModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "ProgressView", + "bar_style": "success", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_bc482a1b71e846008d64347303e8da53", + "max": 9976578928, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_4a5bbd81ea2b424c953ddabce0633d90", + "value": 9976578928 + } + }, + "94a3ee09029a46cf8a62f2ea03a8bc62": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "ProgressStyleModel", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "ProgressStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "bar_color": null, + "description_width": "" + } + }, + "9576b1746f414e0890747c5113880148": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "HTMLModel", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HTMLModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_081c408abd914a29b48faf34ee12a6cd", + "placeholder": "​", + "style": "IPY_MODEL_ca09604bb55249b7913c84e681c348dc", + "value": "tokenizer.json: 100%" + } + }, + "96c01f8404264611b18167586f114a67": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "HTMLModel", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HTMLModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_d590bf4d7b6a4aea8db3b8a800ee343f", + "placeholder": "​", + "style": "IPY_MODEL_f8991a7f787d427ca9215135ce2c3c77", + "value": " 2/2 [00:07<00:00, 3.49s/it]" + } + }, + "97cb7a52ca3543a1be62650e0bf026f1": { + "model_module": "@jupyter-widgets/base", + "model_module_version": "1.2.0", + "model_name": "LayoutModel", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "98f1e2e0824f40ab92048e9f5a2ed067": { + "model_module": "@jupyter-widgets/base", + "model_module_version": "1.2.0", + "model_name": "LayoutModel", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "9ab388c3b879402a899fc953e650a117": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "FloatProgressModel", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "FloatProgressModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "ProgressView", + "bar_style": "success", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_6c64e8c244134d07a92a76bd5903c519", + "max": 2, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_db11269c0c2143e79c8e1be2a3fe29a0", + "value": 2 + } + }, + "9b81c580bd7a4b24b9aeadc891f8bb41": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "FloatProgressModel", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "FloatProgressModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "ProgressView", + "bar_style": "success", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_ac51732e189445098e1a60011e4aebd5", + "max": 2, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_7650d6d7fd5f490d9901f0bf8b970eff", + "value": 2 + } + }, + "9d34c0676891432e8fbcb20a1dda07c0": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "DescriptionStyleModel", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "DescriptionStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "description_width": "" + } + }, + "9e4adea806be46d49b7f37e92748a338": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "HBoxModel", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HBoxModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HBoxView", + "box_style": "", + "children": [ + "IPY_MODEL_9f27bdce93994bc0bc5655c97879d637", + "IPY_MODEL_07c82a6818454130be13570faf77d1a7", + "IPY_MODEL_2df80d3d454b442388a2e3127e736e3e" + ], + "layout": "IPY_MODEL_7651d0f306884b53848bd64bc56df500" + } + }, + "9f27bdce93994bc0bc5655c97879d637": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "HTMLModel", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HTMLModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_17de6afe24e94ff2960760c0bbbb7146", + "placeholder": "​", + "style": "IPY_MODEL_70b33dfa18db4e768458fa6930d00a4a", + "value": "config.json: 100%" + } + }, + "a05250531071414585d29876f1f05319": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "HTMLModel", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HTMLModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_97cb7a52ca3543a1be62650e0bf026f1", + "placeholder": "​", + "style": "IPY_MODEL_d875bfc9ce5b4bc4a8e2329bf24987fb", + "value": " 18404/18404 [00:07<00:00, 1973.14 examples/s]" + } + }, + "a2d7c8e9d87d43389e8b70cfe59a1232": { + "model_module": "@jupyter-widgets/base", + "model_module_version": "1.2.0", + "model_name": "LayoutModel", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "a37699cadc064618bcc850ba37b01145": { + "model_module": "@jupyter-widgets/base", + "model_module_version": "1.2.0", + "model_name": "LayoutModel", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "a3e05d1e704f46f7bfdca2cefc04a610": { + "model_module": "@jupyter-widgets/base", + "model_module_version": "1.2.0", + "model_name": "LayoutModel", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "a55ac6497b434d328caaccd03833459a": { + "model_module": "@jupyter-widgets/base", + "model_module_version": "1.2.0", + "model_name": "LayoutModel", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "a7712b27e6c94e45aa2a060ab49f0e04": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "HTMLModel", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HTMLModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_8a0340af2ed54f47a3b7e585ea80cb43", + "placeholder": "​", + "style": "IPY_MODEL_c419f2587cc74ae6b0dde962caec6159", + "value": " 18404/18404 [00:16<00:00, 934.01 examples/s]" + } + }, + "a94f5ffc1e864be6b95a7372c471d9bf": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "ProgressStyleModel", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "ProgressStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "bar_color": null, + "description_width": "" + } + }, + "aad494542dc1422abe803ecdb6c77e76": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "FloatProgressModel", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "FloatProgressModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "ProgressView", + "bar_style": "", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_ea67d69c64fd4420bb8986c3887eb7e9", + "max": 18404, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_c4292de9659d416c8b08c44faf1bb5cf", + "value": 18404 + } + }, + "ac51732e189445098e1a60011e4aebd5": { + "model_module": "@jupyter-widgets/base", + "model_module_version": "1.2.0", + "model_name": "LayoutModel", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "adbc64a4b9f245ab86258cbffa805241": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "ProgressStyleModel", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "ProgressStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "bar_color": null, + "description_width": "" + } + }, + "afaa2c18a1eb47dc955ae934c4968a01": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "HTMLModel", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HTMLModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_407f7d85e7964983a1ec685b6db14f1c", + "placeholder": "​", + "style": "IPY_MODEL_c6ed5de47d194f56899a01f4795274ce", + "value": "model.safetensors.index.json: 100%" + } + }, + "b2f36e79b411454b9c648f07a7053bf7": { + "model_module": "@jupyter-widgets/base", + "model_module_version": "1.2.0", + "model_name": "LayoutModel", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "b36b878e0b7347e59fe87bb0de806cfb": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "FloatProgressModel", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "FloatProgressModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "ProgressView", + "bar_style": "success", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_46be584dddd84634b539117fcecdc4b7", + "max": 26788, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_c71a37bd40a448d1aa9bd760fd8692ee", + "value": 26788 + } + }, + "b42bae80865e46478356dfe1658db451": { + "model_module": "@jupyter-widgets/base", + "model_module_version": "1.2.0", + "model_name": "LayoutModel", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "b65badf0c84c4bfdb720944a7206df18": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "HBoxModel", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HBoxModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HBoxView", + "box_style": "", + "children": [ + "IPY_MODEL_9576b1746f414e0890747c5113880148", + "IPY_MODEL_14206e17bdf14c9f8a81ed30bea678cf", + "IPY_MODEL_cfe5eb2326654c4a92ef520bf059d7e1" + ], + "layout": "IPY_MODEL_a55ac6497b434d328caaccd03833459a" + } + }, + "b91fa9edc65a4093a13931160210d5e5": { + "model_module": "@jupyter-widgets/base", + "model_module_version": "1.2.0", + "model_name": "LayoutModel", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "b994b8fcf9d64f46bce1ededbd2d0042": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "DescriptionStyleModel", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "DescriptionStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "description_width": "" + } + }, + "b9c70871f78b41aaa579b26621dd79a7": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "HTMLModel", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HTMLModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_7f7ef54bc5b14f709279b53311b48524", + "placeholder": "​", + "style": "IPY_MODEL_1fe6f1ef4e924bc9b08495077671c39d", + "value": "Loading checkpoint shards: 100%" + } + }, + "ba98a5af142a46ac979d43f45c7f1bc2": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "HTMLModel", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HTMLModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_3ade97e55b8247c2a2f440db4b56bced", + "placeholder": "​", + "style": "IPY_MODEL_e7296da44e6d4f1ab1708f5c1d344f44", + "value": "generation_config.json: 100%" + } + }, + "baafa594d8814e3a9584dc3f2c42bf45": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "HBoxModel", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HBoxModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HBoxView", + "box_style": "", + "children": [ + "IPY_MODEL_719ee4a0fe29440c8185eaec857cbc0d", + "IPY_MODEL_d045cc3593b74209b7bf149dbf9b2e61", + "IPY_MODEL_bdb4f2de960d4529810d1ad3eefea59c" + ], + "layout": "IPY_MODEL_18454784ad24444ca34b726f83ce8248" + } + }, + "bb1f598f9aea44f1a7fe4da9b3d869fb": { + "model_module": "@jupyter-widgets/base", + "model_module_version": "1.2.0", + "model_name": "LayoutModel", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": "hidden", + "width": null + } + }, + "bc482a1b71e846008d64347303e8da53": { + "model_module": "@jupyter-widgets/base", + "model_module_version": "1.2.0", + "model_name": "LayoutModel", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "bdb4f2de960d4529810d1ad3eefea59c": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "HTMLModel", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HTMLModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_ff6e5ac3180c47d69aa7630246c71e6f", + "placeholder": "​", + "style": "IPY_MODEL_c2f438f50dee4f23904602a7c2c7f41b", + "value": " 18404/18404 [00:00<00:00, 18850.44 examples/s]" + } + }, + "c2473c5645dc47f585d63c11536b097a": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "FloatProgressModel", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "FloatProgressModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "ProgressView", + "bar_style": "success", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_1af6d6ba6365401a96a6a4e6d2b39b87", + "max": 3500297344, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_6776efc6b05a43149515f8a9ab8c4102", + "value": 3500297344 + } + }, + "c2f438f50dee4f23904602a7c2c7f41b": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "DescriptionStyleModel", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "DescriptionStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "description_width": "" + } + }, + "c419f2587cc74ae6b0dde962caec6159": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "DescriptionStyleModel", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "DescriptionStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "description_width": "" + } + }, + "c4292de9659d416c8b08c44faf1bb5cf": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "ProgressStyleModel", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "ProgressStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "bar_color": null, + "description_width": "" + } + }, + "c47945ffea92487ab3b5f0184fcd4aac": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "HTMLModel", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HTMLModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_ffa4f33221a64507bf53a25574e8a4e3", + "placeholder": "​", + "style": "IPY_MODEL_393f451ec81940b181e259c5fbb62e84", + "value": "model-00002-of-00002.safetensors: 100%" + } + }, + "c6ed5de47d194f56899a01f4795274ce": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "DescriptionStyleModel", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "DescriptionStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "description_width": "" + } + }, + "c71a37bd40a448d1aa9bd760fd8692ee": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "ProgressStyleModel", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "ProgressStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "bar_color": null, + "description_width": "" + } + }, + "ca09604bb55249b7913c84e681c348dc": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "DescriptionStyleModel", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "DescriptionStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "description_width": "" + } + }, + "cd21e232645e41d4834badc1fb0a860d": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "DescriptionStyleModel", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "DescriptionStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "description_width": "" + } + }, + "ceb1be11f57d4c57893ad22ef99b6653": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "FloatProgressModel", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "FloatProgressModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "ProgressView", + "bar_style": "success", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_1dac838ad78c4f89844d34309ff71013", + "max": 188, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_7c1fc07ce3b64a23835ec167bd9e11a7", + "value": 188 + } + }, + "cf20581b6f3d498dbd25711e626d6f15": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "ProgressStyleModel", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "ProgressStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "bar_color": null, + "description_width": "" + } + }, + "cf84406cd1be464ca9caf07b3ab7cecf": { + "model_module": "@jupyter-widgets/base", + "model_module_version": "1.2.0", + "model_name": "LayoutModel", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "cfe5eb2326654c4a92ef520bf059d7e1": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "HTMLModel", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HTMLModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_a2d7c8e9d87d43389e8b70cfe59a1232", + "placeholder": "​", + "style": "IPY_MODEL_2acdb638a06d4764b2479c861605b266", + "value": " 1.84M/1.84M [00:01<00:00, 1.50MB/s]" + } + }, + "d0327ceb4e9a4e8f93624c522450f8f6": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "HTMLModel", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HTMLModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_6e6dfc7b5e7c4393b32440417c759a0f", + "placeholder": "​", + "style": "IPY_MODEL_48c4888d267e46a69fbd7648250b5a93", + "value": " 500k/500k [00:00<00:00, 40.6MB/s]" + } + }, + "d045cc3593b74209b7bf149dbf9b2e61": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "FloatProgressModel", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "FloatProgressModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "ProgressView", + "bar_style": "", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_d5e7af0cff5c411d96b89ba43d6979fb", + "max": 18404, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_48d300a81ab544708d44ac7049a0bd3a", + "value": 18404 + } + }, + "d590bf4d7b6a4aea8db3b8a800ee343f": { + "model_module": "@jupyter-widgets/base", + "model_module_version": "1.2.0", + "model_name": "LayoutModel", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "d5e7af0cff5c411d96b89ba43d6979fb": { + "model_module": "@jupyter-widgets/base", + "model_module_version": "1.2.0", + "model_name": "LayoutModel", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "d63611b41599470a84357222964933e7": { + "model_module": "@jupyter-widgets/base", + "model_module_version": "1.2.0", + "model_name": "LayoutModel", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "d875bfc9ce5b4bc4a8e2329bf24987fb": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "DescriptionStyleModel", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "DescriptionStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "description_width": "" + } + }, + "db11269c0c2143e79c8e1be2a3fe29a0": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "ProgressStyleModel", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "ProgressStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "bar_color": null, + "description_width": "" + } + }, + "db589f37bf4c419284f21c6267d6f408": { + "model_module": "@jupyter-widgets/base", + "model_module_version": "1.2.0", + "model_name": "LayoutModel", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "de87494d800e40cc9139807cedb5378b": { + "model_module": "@jupyter-widgets/base", + "model_module_version": "1.2.0", + "model_name": "LayoutModel", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "deae19c5a56e4ec58e33701f22872455": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "HBoxModel", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HBoxModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HBoxView", + "box_style": "", + "children": [ + "IPY_MODEL_b9c70871f78b41aaa579b26621dd79a7", + "IPY_MODEL_9b81c580bd7a4b24b9aeadc891f8bb41", + "IPY_MODEL_edad5b919b974aa3bbb6af0ebf988bee" + ], + "layout": "IPY_MODEL_b42bae80865e46478356dfe1658db451" + } + }, + "e7091d8f4455432795782b522d5ee9b6": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "DescriptionStyleModel", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "DescriptionStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "description_width": "" + } + }, + "e7296da44e6d4f1ab1708f5c1d344f44": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "DescriptionStyleModel", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "DescriptionStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "description_width": "" + } + }, + "ea67d69c64fd4420bb8986c3887eb7e9": { + "model_module": "@jupyter-widgets/base", + "model_module_version": "1.2.0", + "model_name": "LayoutModel", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "edad5b919b974aa3bbb6af0ebf988bee": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "HTMLModel", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HTMLModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_12fc2f4a906e4806b50fcd145f7726e1", + "placeholder": "​", + "style": "IPY_MODEL_9d34c0676891432e8fbcb20a1dda07c0", + "value": " 2/2 [00:04<00:00, 2.21s/it]" + } + }, + "f3b6da9b49f547c7ad92d1b86af2fa78": { + "model_module": "@jupyter-widgets/base", + "model_module_version": "1.2.0", + "model_name": "LayoutModel", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "f642eeb766eb4c33b6e42e43d2108d5a": { + "model_module": "@jupyter-widgets/base", + "model_module_version": "1.2.0", + "model_name": "LayoutModel", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "f8991a7f787d427ca9215135ce2c3c77": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "DescriptionStyleModel", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "DescriptionStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "description_width": "" + } + }, + "fcc9664580b6482dbe8ad7f4c2fabb09": { + "model_module": "@jupyter-widgets/base", + "model_module_version": "1.2.0", + "model_name": "LayoutModel", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "fef86b2372094c71b7f75ac7dd0caabd": { + "model_module": "@jupyter-widgets/base", + "model_module_version": "1.2.0", + "model_name": "LayoutModel", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "ff6e5ac3180c47d69aa7630246c71e6f": { + "model_module": "@jupyter-widgets/base", + "model_module_version": "1.2.0", + "model_name": "LayoutModel", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "ffa4f33221a64507bf53a25574e8a4e3": { + "model_module": "@jupyter-widgets/base", + "model_module_version": "1.2.0", + "model_name": "LayoutModel", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + } + } + } + }, + "nbformat": 4, + "nbformat_minor": 4 +}