diff --git "a/novel-translation/05_tune-small-with-flash-attn.ipynb" "b/novel-translation/05_tune-small-with-flash-attn.ipynb" new file mode 100644--- /dev/null +++ "b/novel-translation/05_tune-small-with-flash-attn.ipynb" @@ -0,0 +1,4665 @@ +{ + "cells": [ + { + "cell_type": "code", + "execution_count": 1, + "metadata": { + "application/vnd.databricks.v1+cell": { + "cellMetadata": {}, + "inputWidgets": {}, + "nuid": "0ea8b46b-839b-445b-8043-ccdf4e920ace", + "showTitle": false, + "title": "" + } + }, + "outputs": [], + "source": [ + "%load_ext autoreload\n", + "%autoreload 2" + ] + }, + { + "cell_type": "code", + "execution_count": 2, + "metadata": { + "application/vnd.databricks.v1+cell": { + "cellMetadata": {}, + "inputWidgets": {}, + "nuid": "6d394937-6c99-4a7c-9d32-7600a280032f", + "showTitle": false, + "title": "" + } + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "workding dir: /home/inflaton/code/projects/courses/novel-translation\n" + ] + } + ], + "source": [ + "import os\n", + "import sys\n", + "from pathlib import Path\n", + "\n", + "workding_dir = str(Path.cwd().parent)\n", + "os.chdir(workding_dir)\n", + "sys.path.append(workding_dir)\n", + "print(\"workding dir:\", workding_dir)" + ] + }, + { + "cell_type": "code", + "execution_count": 3, + "metadata": { + "application/vnd.databricks.v1+cell": { + "cellMetadata": {}, + "inputWidgets": {}, + "nuid": "9f67ec60-2f24-411c-84eb-0dd664b44775", + "showTitle": false, + "title": "" + } + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "loading env vars from: /home/inflaton/code/projects/courses/novel-translation/.env\n" + ] + }, + { + "data": { + "text/plain": [ + "True" + ] + }, + "execution_count": 3, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "from dotenv import find_dotenv, load_dotenv\n", + "\n", + "found_dotenv = find_dotenv(\".env\")\n", + "\n", + "if len(found_dotenv) == 0:\n", + " found_dotenv = find_dotenv(\".env.example\")\n", + "print(f\"loading env vars from: {found_dotenv}\")\n", + "load_dotenv(found_dotenv, override=True)" + ] + }, + { + "cell_type": "code", + "execution_count": 4, + "metadata": { + "application/vnd.databricks.v1+cell": { + "cellMetadata": {}, + "inputWidgets": {}, + "nuid": "f1597656-8042-4878-9d3b-9ebfb8dd86dc", + "showTitle": false, + "title": "" + } + }, + "outputs": [ + { + "data": { + "text/plain": [ + "('unsloth/Qwen2-0.5B-Instruct-bnb-4bit',\n", + " True,\n", + " None,\n", + " None,\n", + " 2048,\n", + " 10,\n", + " None,\n", + " 'datasets/mac/mac.tsv',\n", + " 'results/mac-results_v3.csv')" + ] + }, + "execution_count": 4, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "import os\n", + "\n", + "model_name = os.getenv(\"MODEL_NAME\")\n", + "token = os.getenv(\"HF_TOKEN\") or None\n", + "load_in_4bit = os.getenv(\"LOAD_IN_4BIT\") == \"true\"\n", + "local_model = os.getenv(\"LOCAL_MODEL\")\n", + "hub_model = os.getenv(\"HUB_MODEL\")\n", + "num_train_epochs = int(os.getenv(\"NUM_TRAIN_EPOCHS\") or 0)\n", + "data_path = os.getenv(\"DATA_PATH\")\n", + "results_path = os.getenv(\"RESULTS_PATH\")\n", + "\n", + "max_seq_length = 2048 # Choose any! We auto support RoPE Scaling internally!\n", + "dtype = (\n", + " None # None for auto detection. Float16 for Tesla T4, V100, Bfloat16 for Ampere+\n", + ")\n", + "\n", + "model_name, load_in_4bit, local_model, hub_model, max_seq_length, num_train_epochs, dtype, data_path, results_path" + ] + }, + { + "cell_type": "code", + "execution_count": 5, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Sun Jun 23 12:46:16 2024 \n", + "+---------------------------------------------------------------------------------------+\n", + "| NVIDIA-SMI 545.23.07 Driver Version: 546.12 CUDA Version: 12.3 |\n", + "|-----------------------------------------+----------------------+----------------------+\n", + "| GPU Name Persistence-M | Bus-Id Disp.A | Volatile Uncorr. ECC |\n", + "| Fan Temp Perf Pwr:Usage/Cap | Memory-Usage | GPU-Util Compute M. |\n", + "| | | MIG M. |\n", + "|=========================================+======================+======================|\n", + "| 0 NVIDIA GeForce RTX 4080 ... On | 00000000:01:00.0 On | N/A |\n", + "| N/A 53C P8 5W / 150W | 452MiB / 12282MiB | 11% Default |\n", + "| | | N/A |\n", + "+-----------------------------------------+----------------------+----------------------+\n", + " \n", + "+---------------------------------------------------------------------------------------+\n", + "| Processes: |\n", + "| GPU GI CI PID Type Process name GPU Memory |\n", + "| ID ID Usage |\n", + "|=======================================================================================|\n", + "| No running processes found |\n", + "+---------------------------------------------------------------------------------------+\n" + ] + } + ], + "source": [ + "!nvidia-smi" + ] + }, + { + "cell_type": "code", + "execution_count": 6, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "CPU times: user 3 ΞΌs, sys: 1 ΞΌs, total: 4 ΞΌs\n", + "Wall time: 6.91 ΞΌs\n" + ] + } + ], + "source": [ + "%%time\n", + "\n", + "# !pip install flash-attn --no-build-isolation" + ] + }, + { + "cell_type": "code", + "execution_count": 7, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Name: flash-attn\n", + "Version: 2.5.9.post1\n", + "Summary: Flash Attention: Fast and Memory-Efficient Exact Attention\n", + "Home-page: https://github.com/Dao-AILab/flash-attention\n", + "Author: Tri Dao\n", + "Author-email: trid@cs.stanford.edu\n", + "License: \n", + "Location: /home/inflaton/miniconda3/envs/unsloth_env/lib/python3.10/site-packages\n", + "Requires: einops, torch\n", + "Required-by: \n" + ] + } + ], + "source": [ + "!pip show flash-attn" + ] + }, + { + "cell_type": "code", + "execution_count": 8, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Current Directory:\n", + "/home/inflaton/code/projects/courses/novel-translation\n", + "Tuning unsloth/Qwen2-0.5B-Instruct-bnb-4bit\n", + "πŸ¦₯ Unsloth: Will patch your computer to enable 2x faster free finetuning.\n", + "[nltk_data] Downloading package wordnet to /home/inflaton/nltk_data...\n", + "[nltk_data] Package wordnet is already up-to-date!\n", + "[nltk_data] Downloading package punkt to /home/inflaton/nltk_data...\n", + "[nltk_data] Package punkt is already up-to-date!\n", + "[nltk_data] Downloading package omw-1.4 to /home/inflaton/nltk_data...\n", + "[nltk_data] Package omw-1.4 is already up-to-date!\n", + "loading /home/inflaton/code/projects/courses/novel-translation/translation_engine_v3.py\n", + "loading env vars from: /home/inflaton/code/projects/courses/novel-translation/.env\n", + "unsloth/Qwen2-0.5B-Instruct-bnb-4bit True 2048 10 None datasets/mac/mac.tsv results/mac-results_v3.csv True True True\n", + "(1) GPU = NVIDIA GeForce RTX 4080 Laptop GPU. Max memory = 11.994 GB.\n", + "0.0 GB of memory reserved.\n", + "loading model: unsloth/Qwen2-0.5B-Instruct-bnb-4bit\n", + "==((====))== Unsloth: Fast Qwen2 patching release 2024.6\n", + " \\\\ /| GPU: NVIDIA GeForce RTX 4080 Laptop GPU. Max memory: 11.994 GB. Platform = Linux.\n", + "O^O/ \\_/ \\ Pytorch: 2.3.0. CUDA = 8.9. CUDA Toolkit = 12.1.\n", + "\\ / Bfloat16 = TRUE. Xformers = 0.0.26.post1. FA = True.\n", + " \"-____-\" Free Apache license: http://github.com/unslothai/unsloth\n", + "Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.\n", + "Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.\n", + "(2) GPU = NVIDIA GeForce RTX 4080 Laptop GPU. Max memory = 11.994 GB.\n", + "0.633 GB of memory reserved.\n", + "loading train/test data files\n", + "DatasetDict({\n", + " train: Dataset({\n", + " features: ['chinese', 'english', 'text', 'prompt'],\n", + " num_rows: 4528\n", + " })\n", + " test: Dataset({\n", + " features: ['chinese', 'english', 'text', 'prompt'],\n", + " num_rows: 1133\n", + " })\n", + "})\n", + "Evaluating base model: unsloth/Qwen2-0.5B-Instruct-bnb-4bit\n", + " 0%| | 0/1133 [00:00\n", + "--------\n", + "step 2: Old Teng raised his gun, closing his eyes and gripping a triangular eye. A boom of bullets rang out as he fired one, like thunder crashing down. The hammering sound of steel stones echoed through the branches of the trees. \n", + "\n", + "The noise was so loud that it made my heart beat faster.\n", + "--------\n", + "step 3: Old Teng raised his gun, closing his eyes and gripping a triangular eye. A boom of bullets rang out as he fired one, like thunder crashing down. The hammering sound of steel stones echoed through the branches of the trees. \n", + "\n", + "The noise was so loud that it made my heart beat faster.\n", + "100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 1133/1133 [1:06:42<00:00, 3.53s/it]\n", + " chinese ... unsloth/Qwen2-0.5B-Instruct-bnb-4bit\n", + "0 老耿端衷ζžͺοΌŒηœ―ηΌθ΅·δΈ€εͺδΈ‰θ§’ηœΌοΌŒδΈ€ζ‚ζ‰³ζœΊε“δΊ†ζžͺοΌŒε†°ι›Ήθˆ¬ηš„ι‡‘ιΊ»ι›€εŠˆε“©ε•ͺε•¦εΎ€δΈ‹θ½οΌŒι“η ‚ε­εœ¨ζŸ³ζžι—΄ι£ž... ... Old Teng raised his gun, closing his eyes and ...\n", + "\n", + "[1 rows x 3 columns]\n", + "(3) GPU = NVIDIA GeForce RTX 4080 Laptop GPU. Max memory = 11.994 GB.\n", + "3.023 GB of memory reserved.\n", + "Unsloth 2024.6 patched 24 layers with 0 QKV layers, 24 O layers and 24 MLP layers.\n", + "(4) GPU = NVIDIA GeForce RTX 4080 Laptop GPU. Max memory = 11.994 GB.\n", + "3.023 GB of memory reserved.\n", + "==((====))== Unsloth - 2x faster free finetuning | Num GPUs = 1\n", + " \\\\ /| Num examples = 4,528 | Num Epochs = 10\n", + "O^O/ \\_/ \\ Batch size per device = 2 | Gradient Accumulation steps = 4\n", + "\\ / Total batch size = 8 | Total steps = 5,660\n", + " \"-____-\" Number of trainable parameters = 8,798,208\n", + "{'loss': 1.9401, 'grad_norm': 0.9639493823051453, 'learning_rate': 0.00019664014146772768, 'epoch': 0.18}\n", + "{'loss': 1.7762, 'grad_norm': 0.8060959577560425, 'learning_rate': 0.0001931034482758621, 'epoch': 0.35}\n", + "{'loss': 1.7146, 'grad_norm': 0.9296559691429138, 'learning_rate': 0.00018956675508399648, 'epoch': 0.53}\n", + "{'loss': 1.7155, 'grad_norm': 0.7544056177139282, 'learning_rate': 0.00018603006189213086, 'epoch': 0.71}\n", + "{'loss': 1.6861, 'grad_norm': 0.8301573395729065, 'learning_rate': 0.00018249336870026527, 'epoch': 0.88}\n", + "{'loss': 1.6078, 'grad_norm': 0.8045125007629395, 'learning_rate': 0.00017895667550839965, 'epoch': 1.06}\n", + "{'loss': 1.4921, 'grad_norm': 0.9031914472579956, 'learning_rate': 0.00017541998231653406, 'epoch': 1.24}\n", + "{'loss': 1.5401, 'grad_norm': 0.9808986186981201, 'learning_rate': 0.00017188328912466844, 'epoch': 1.41}\n", + "{'loss': 1.4721, 'grad_norm': 1.0783536434173584, 'learning_rate': 0.00016834659593280285, 'epoch': 1.59}\n", + "{'loss': 1.4686, 'grad_norm': 0.988545835018158, 'learning_rate': 0.00016480990274093723, 'epoch': 1.77}\n", + "{'loss': 1.5278, 'grad_norm': 1.0253351926803589, 'learning_rate': 0.00016127320954907164, 'epoch': 1.94}\n", + "{'loss': 1.3493, 'grad_norm': 1.1621149778366089, 'learning_rate': 0.000157736516357206, 'epoch': 2.12}\n", + "{'loss': 1.2156, 'grad_norm': 1.1786366701126099, 'learning_rate': 0.0001541998231653404, 'epoch': 2.3}\n", + "{'loss': 1.2572, 'grad_norm': 1.3017158508300781, 'learning_rate': 0.0001506631299734748, 'epoch': 2.47}\n", + "{'loss': 1.2552, 'grad_norm': 1.2804787158966064, 'learning_rate': 0.0001471264367816092, 'epoch': 2.65}\n", + "{'loss': 1.2664, 'grad_norm': 1.1679364442825317, 'learning_rate': 0.0001435897435897436, 'epoch': 2.83}\n", + "{'loss': 1.2346, 'grad_norm': 1.171284794807434, 'learning_rate': 0.000140053050397878, 'epoch': 3.0}\n", + "{'loss': 0.9801, 'grad_norm': 1.5025601387023926, 'learning_rate': 0.0001365163572060124, 'epoch': 3.18}\n", + "{'loss': 0.9924, 'grad_norm': 1.5331358909606934, 'learning_rate': 0.00013297966401414678, 'epoch': 3.36}\n", + "{'loss': 0.9986, 'grad_norm': 1.5144548416137695, 'learning_rate': 0.0001294429708222812, 'epoch': 3.53}\n", + "{'loss': 0.9813, 'grad_norm': 1.5257072448730469, 'learning_rate': 0.00012590627763041555, 'epoch': 3.71}\n", + "{'loss': 1.0233, 'grad_norm': 1.5738170146942139, 'learning_rate': 0.00012236958443854996, 'epoch': 3.89}\n", + "{'loss': 0.9316, 'grad_norm': 1.5346697568893433, 'learning_rate': 0.00011883289124668435, 'epoch': 4.06}\n", + "{'loss': 0.7391, 'grad_norm': 1.7242717742919922, 'learning_rate': 0.00011529619805481875, 'epoch': 4.24}\n", + "{'loss': 0.7396, 'grad_norm': 1.7575305700302124, 'learning_rate': 0.00011175950486295315, 'epoch': 4.42}\n", + "{'loss': 0.7765, 'grad_norm': 2.111323833465576, 'learning_rate': 0.00010822281167108754, 'epoch': 4.59}\n", + "{'loss': 0.7738, 'grad_norm': 2.2442333698272705, 'learning_rate': 0.00010468611847922194, 'epoch': 4.77}\n", + "{'loss': 0.7942, 'grad_norm': 2.135150909423828, 'learning_rate': 0.00010114942528735633, 'epoch': 4.95}\n", + "{'loss': 0.6302, 'grad_norm': 1.8503246307373047, 'learning_rate': 9.761273209549072e-05, 'epoch': 5.12}\n", + "{'loss': 0.5572, 'grad_norm': 1.59291410446167, 'learning_rate': 9.407603890362513e-05, 'epoch': 5.3}\n", + "{'loss': 0.5616, 'grad_norm': 1.7540444135665894, 'learning_rate': 9.053934571175951e-05, 'epoch': 5.48}\n", + "{'loss': 0.5898, 'grad_norm': 2.267761707305908, 'learning_rate': 8.70026525198939e-05, 'epoch': 5.65}\n", + "{'loss': 0.5818, 'grad_norm': 2.345642328262329, 'learning_rate': 8.34659593280283e-05, 'epoch': 5.83}\n", + "{'loss': 0.5804, 'grad_norm': 2.3560101985931396, 'learning_rate': 7.99292661361627e-05, 'epoch': 6.01}\n", + "{'loss': 0.3973, 'grad_norm': 3.8223047256469727, 'learning_rate': 7.639257294429708e-05, 'epoch': 6.18}\n", + "{'loss': 0.4132, 'grad_norm': 1.865454912185669, 'learning_rate': 7.285587975243147e-05, 'epoch': 6.36}\n", + "{'loss': 0.4299, 'grad_norm': 2.473954200744629, 'learning_rate': 6.931918656056587e-05, 'epoch': 6.54}\n", + "{'loss': 0.422, 'grad_norm': 1.6875197887420654, 'learning_rate': 6.578249336870027e-05, 'epoch': 6.71}\n", + "{'loss': 0.4284, 'grad_norm': 1.5689966678619385, 'learning_rate': 6.224580017683466e-05, 'epoch': 6.89}\n", + "{'loss': 0.3869, 'grad_norm': 1.6680887937545776, 'learning_rate': 5.870910698496905e-05, 'epoch': 7.07}\n", + "{'loss': 0.2934, 'grad_norm': 1.7025184631347656, 'learning_rate': 5.517241379310345e-05, 'epoch': 7.24}\n", + "{'loss': 0.3139, 'grad_norm': 1.5031529664993286, 'learning_rate': 5.163572060123785e-05, 'epoch': 7.42}\n", + "{'loss': 0.3133, 'grad_norm': 1.9866334199905396, 'learning_rate': 4.809902740937224e-05, 'epoch': 7.6}\n", + "{'loss': 0.306, 'grad_norm': 2.1866486072540283, 'learning_rate': 4.4562334217506634e-05, 'epoch': 7.77}\n", + "{'loss': 0.3183, 'grad_norm': 1.4326164722442627, 'learning_rate': 4.1025641025641023e-05, 'epoch': 7.95}\n", + "{'loss': 0.2477, 'grad_norm': 1.3497223854064941, 'learning_rate': 3.7488947833775426e-05, 'epoch': 8.13}\n", + "{'loss': 0.2262, 'grad_norm': 1.6162991523742676, 'learning_rate': 3.3952254641909815e-05, 'epoch': 8.3}\n", + "{'loss': 0.2302, 'grad_norm': 1.0059006214141846, 'learning_rate': 3.041556145004421e-05, 'epoch': 8.48}\n", + "{'loss': 0.236, 'grad_norm': 1.3581494092941284, 'learning_rate': 2.6878868258178604e-05, 'epoch': 8.66}\n", + "{'loss': 0.2366, 'grad_norm': 1.891054391860962, 'learning_rate': 2.3342175066313e-05, 'epoch': 8.83}\n", + "{'loss': 0.238, 'grad_norm': 1.0669790506362915, 'learning_rate': 1.9805481874447392e-05, 'epoch': 9.01}\n", + "{'loss': 0.1814, 'grad_norm': 1.2125357389450073, 'learning_rate': 1.6268788682581788e-05, 'epoch': 9.19}\n", + "{'loss': 0.1897, 'grad_norm': 1.044737696647644, 'learning_rate': 1.273209549071618e-05, 'epoch': 9.36}\n", + "{'loss': 0.1873, 'grad_norm': 1.1148860454559326, 'learning_rate': 9.195402298850575e-06, 'epoch': 9.54}\n", + "{'loss': 0.189, 'grad_norm': 1.8938679695129395, 'learning_rate': 5.658709106984969e-06, 'epoch': 9.72}\n", + "{'loss': 0.1892, 'grad_norm': 1.0202747583389282, 'learning_rate': 2.1220159151193635e-06, 'epoch': 9.89}\n", + "{'train_runtime': 13804.2064, 'train_samples_per_second': 3.28, 'train_steps_per_second': 0.41, 'train_loss': 0.7992495260474539, 'epoch': 10.0}\n", + "100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 5660/5660 [3:50:04<00:00, 2.44s/it]\n", + "(5) GPU = NVIDIA GeForce RTX 4080 Laptop GPU. Max memory = 11.994 GB.\n", + "13804.2064 seconds used for training.\n", + "230.07 minutes used for training.\n", + "Peak reserved memory = 3.023 GB.\n", + "Peak reserved memory for training = 0.0 GB.\n", + "Peak reserved memory % of max memory = 25.204 %.\n", + "Peak reserved memory for training % of max memory = 0.0 %.\n", + "Evaluating fine-tuned model: unsloth/Qwen2-0.5B-Instruct-bnb-4bit\n", + " 0%| | 0/1133 [00:00\n", + "--------\n", + "step 2: Old Geng raised his rifle, squinted his triangular eye, and fired – a gun, like a ladle, crackled as the shot fell down towards him.\n", + "--------\n", + "step 3: Old Geng raised his rifle, squinted his triangular eye, and fired – a gun, like a ladle, crackled as the shot fell down towards him.\n", + "100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 1133/1133 [1:39:47<00:00, 5.28s/it]\n", + " chinese ... unsloth/Qwen2-0.5B-Instruct-bnb-4bit(finetuned)\n", + "0 老耿端衷ζžͺοΌŒηœ―ηΌθ΅·δΈ€εͺδΈ‰θ§’ηœΌοΌŒδΈ€ζ‚ζ‰³ζœΊε“δΊ†ζžͺοΌŒοΏ½οΏ½οΏ½ι›Ήθˆ¬ηš„ι‡‘ιΊ»ι›€εŠˆε“©ε•ͺε•¦εΎ€δΈ‹θ½οΌŒι“η ‚ε­εœ¨ζŸ³ζžι—΄ι£ž... ... Old Geng raised his rifle, squinted his triang...\n", + "\n", + "[1 rows x 4 columns]\n", + "(6) GPU = NVIDIA GeForce RTX 4080 Laptop GPU. Max memory = 11.994 GB.\n", + "3.023 GB of memory reserved.\n", + "README.md: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 593/593 [00:00<00:00, 3.39MB/s]\n", + "model.safetensors: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 493M/493M [00:41<00:00, 11.9MB/s]\n", + "Saved model to https://huggingface.co/Qwen2-0.5B-Instruct-bnb-4bit-MAC-lora\n", + "README.md: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 599/599 [00:00<00:00, 2.91MB/s]\n", + "Unsloth: Saving tokenizer... Done.\n", + "Unsloth: Saving model... Done.\n", + "Unsloth: Saving LoRA adapters. Please wait...\n", + "401 Client Error: Unauthorized for url: https://huggingface.co/api/repos/create (Request ID: Root=1-667805f5-6581fe263332f4220001e82f;27494d10-63ec-4751-8bd3-059f4a0c16c7)\n", + "\n", + "Invalid username or password.\n", + "Tuning unsloth/Qwen2-1.5B-Instruct-bnb-4bit\n", + "πŸ¦₯ Unsloth: Will patch your computer to enable 2x faster free finetuning.\n", + "[nltk_data] Downloading package wordnet to /home/inflaton/nltk_data...\n", + "[nltk_data] Package wordnet is already up-to-date!\n", + "[nltk_data] Downloading package punkt to /home/inflaton/nltk_data...\n", + "[nltk_data] Package punkt is already up-to-date!\n", + "[nltk_data] Downloading package omw-1.4 to /home/inflaton/nltk_data...\n", + "[nltk_data] Package omw-1.4 is already up-to-date!\n", + "loading /home/inflaton/code/projects/courses/novel-translation/translation_engine_v3.py\n", + "loading env vars from: /home/inflaton/code/projects/courses/novel-translation/.env\n", + "unsloth/Qwen2-1.5B-Instruct-bnb-4bit True 2048 10 None datasets/mac/mac.tsv results/mac-results_v3.csv True True True\n", + "(1) GPU = NVIDIA GeForce RTX 4080 Laptop GPU. Max memory = 11.994 GB.\n", + "0.0 GB of memory reserved.\n", + "loading model: unsloth/Qwen2-1.5B-Instruct-bnb-4bit\n", + "==((====))== Unsloth: Fast Qwen2 patching release 2024.6\n", + " \\\\ /| GPU: NVIDIA GeForce RTX 4080 Laptop GPU. Max memory: 11.994 GB. Platform = Linux.\n", + "O^O/ \\_/ \\ Pytorch: 2.3.0. CUDA = 8.9. CUDA Toolkit = 12.1.\n", + "\\ / Bfloat16 = TRUE. Xformers = 0.0.26.post1. FA = True.\n", + " \"-____-\" Free Apache license: http://github.com/unslothai/unsloth\n", + "Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.\n", + "Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.\n", + "(2) GPU = NVIDIA GeForce RTX 4080 Laptop GPU. Max memory = 11.994 GB.\n", + "1.516 GB of memory reserved.\n", + "loading train/test data files\n", + "Map: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 4528/4528 [00:00<00:00, 6537.59 examples/s]\n", + "Map: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 1133/1133 [00:00<00:00, 7281.32 examples/s]\n", + "DatasetDict({\n", + " train: Dataset({\n", + " features: ['chinese', 'english', 'text', 'prompt'],\n", + " num_rows: 4528\n", + " })\n", + " test: Dataset({\n", + " features: ['chinese', 'english', 'text', 'prompt'],\n", + " num_rows: 1133\n", + " })\n", + "})\n", + "Evaluating base model: unsloth/Qwen2-1.5B-Instruct-bnb-4bit\n", + " 0%| | 0/1133 [00:00\n", + "--------\n", + "step 2: Old Geer lifted his gun, squinting one eye as he pulled the trigger. A hail of bullets rained down from his rifle. Golden sparrows plopped down from the trees, sandstones flying through the willows, making a clattering sound.\n", + "--------\n", + "step 3: Old Geer lifted his gun, squinting one eye as he pulled the trigger. A hail of bullets rained down from his rifle. Golden sparrows plopped down from the trees, sandstones flying through the willows, making a clattering sound.\n", + "100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 1133/1133 [1:33:33<00:00, 4.95s/it]\n", + " chinese ... unsloth/Qwen2-1.5B-Instruct-bnb-4bit\n", + "0 老耿端衷ζžͺοΌŒηœ―ηΌθ΅·δΈ€εͺδΈ‰θ§’ηœΌοΌŒδΈ€ζ‚οΏ½οΏ½οΏ½ζœΊε“δΊ†ζžͺοΌŒε†°ι›Ήθˆ¬ηš„ι‡‘ιΊ»ι›€εŠˆε“©ε•ͺε•¦εΎ€δΈ‹θ½οΌŒι“η ‚ε­εœ¨ζŸ³ζžι—΄ι£ž... ... Old Geer lifted his gun, squinting one eye as ...\n", + "\n", + "[1 rows x 5 columns]\n", + "(3) GPU = NVIDIA GeForce RTX 4080 Laptop GPU. Max memory = 11.994 GB.\n", + "3.945 GB of memory reserved.\n", + "Unsloth 2024.6 patched 28 layers with 0 QKV layers, 28 O layers and 28 MLP layers.\n", + "Map (num_proc=2): 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 4528/4528 [00:01<00:00, 2276.92 examples/s]\n", + "(4) GPU = NVIDIA GeForce RTX 4080 Laptop GPU. Max memory = 11.994 GB.\n", + "3.945 GB of memory reserved.\n", + "==((====))== Unsloth - 2x faster free finetuning | Num GPUs = 1\n", + " \\\\ /| Num examples = 4,528 | Num Epochs = 10\n", + "O^O/ \\_/ \\ Batch size per device = 2 | Gradient Accumulation steps = 4\n", + "\\ / Total batch size = 8 | Total steps = 5,660\n", + " \"-____-\" Number of trainable parameters = 18,464,768\n", + "{'loss': 1.7411, 'grad_norm': 0.658531665802002, 'learning_rate': 0.00019664014146772768, 'epoch': 0.18}\n", + "{'loss': 1.5679, 'grad_norm': 0.6339693665504456, 'learning_rate': 0.0001931034482758621, 'epoch': 0.35}\n", + "{'loss': 1.5154, 'grad_norm': 0.6460090279579163, 'learning_rate': 0.00018956675508399648, 'epoch': 0.53}\n", + "{'loss': 1.5171, 'grad_norm': 0.5758596658706665, 'learning_rate': 0.00018603006189213086, 'epoch': 0.71}\n", + "{'loss': 1.4961, 'grad_norm': 0.5699881315231323, 'learning_rate': 0.00018249336870026527, 'epoch': 0.88}\n", + "{'loss': 1.4185, 'grad_norm': 0.6029691100120544, 'learning_rate': 0.00017895667550839965, 'epoch': 1.06}\n", + "{'loss': 1.2981, 'grad_norm': 0.7669411301612854, 'learning_rate': 0.00017541998231653406, 'epoch': 1.24}\n", + "{'loss': 1.3393, 'grad_norm': 0.6863419413566589, 'learning_rate': 0.00017188328912466844, 'epoch': 1.41}\n", + "{'loss': 1.2785, 'grad_norm': 0.9242411255836487, 'learning_rate': 0.00016834659593280285, 'epoch': 1.59}\n", + "{'loss': 1.2799, 'grad_norm': 0.8570270538330078, 'learning_rate': 0.00016480990274093723, 'epoch': 1.77}\n", + "{'loss': 1.3319, 'grad_norm': 1.2672839164733887, 'learning_rate': 0.00016127320954907164, 'epoch': 1.94}\n", + "{'loss': 1.1278, 'grad_norm': 0.9834404587745667, 'learning_rate': 0.000157736516357206, 'epoch': 2.12}\n", + "{'loss': 0.9963, 'grad_norm': 1.082615852355957, 'learning_rate': 0.0001541998231653404, 'epoch': 2.3}\n", + "{'loss': 1.0299, 'grad_norm': 1.1531076431274414, 'learning_rate': 0.0001506631299734748, 'epoch': 2.47}\n", + "{'loss': 1.0355, 'grad_norm': 1.0619866847991943, 'learning_rate': 0.0001471264367816092, 'epoch': 2.65}\n", + "{'loss': 1.0358, 'grad_norm': 1.0393147468566895, 'learning_rate': 0.0001435897435897436, 'epoch': 2.83}\n", + "{'loss': 1.0088, 'grad_norm': 0.8888176679611206, 'learning_rate': 0.000140053050397878, 'epoch': 3.0}\n", + "{'loss': 0.6966, 'grad_norm': 1.2902939319610596, 'learning_rate': 0.0001365163572060124, 'epoch': 3.18}\n", + "{'loss': 0.7113, 'grad_norm': 1.3367533683776855, 'learning_rate': 0.00013297966401414678, 'epoch': 3.36}\n", + "{'loss': 0.7152, 'grad_norm': 1.3983240127563477, 'learning_rate': 0.0001294429708222812, 'epoch': 3.53}\n", + "{'loss': 0.7054, 'grad_norm': 1.503348469734192, 'learning_rate': 0.00012590627763041555, 'epoch': 3.71}\n", + "{'loss': 0.7441, 'grad_norm': 1.2397220134735107, 'learning_rate': 0.00012236958443854996, 'epoch': 3.89}\n", + "{'loss': 0.644, 'grad_norm': 1.1092045307159424, 'learning_rate': 0.00011883289124668435, 'epoch': 4.06}\n", + "{'loss': 0.46, 'grad_norm': 1.3230023384094238, 'learning_rate': 0.00011529619805481875, 'epoch': 4.24}\n", + "{'loss': 0.4453, 'grad_norm': 1.4391876459121704, 'learning_rate': 0.00011175950486295315, 'epoch': 4.42}\n", + "{'loss': 0.4831, 'grad_norm': 1.8462566137313843, 'learning_rate': 0.00010822281167108754, 'epoch': 4.59}\n", + "{'loss': 0.4777, 'grad_norm': 2.09181547164917, 'learning_rate': 0.00010468611847922194, 'epoch': 4.77}\n", + "{'loss': 0.4871, 'grad_norm': 1.7411134243011475, 'learning_rate': 0.00010114942528735633, 'epoch': 4.95}\n", + "{'loss': 0.3573, 'grad_norm': 1.5780448913574219, 'learning_rate': 9.761273209549072e-05, 'epoch': 5.12}\n", + "{'loss': 0.2919, 'grad_norm': 1.4988445043563843, 'learning_rate': 9.407603890362513e-05, 'epoch': 5.3}\n", + "{'loss': 0.2988, 'grad_norm': 0.9282442927360535, 'learning_rate': 9.053934571175951e-05, 'epoch': 5.48}\n", + "{'loss': 0.3139, 'grad_norm': 1.3400734663009644, 'learning_rate': 8.70026525198939e-05, 'epoch': 5.65}\n", + "{'loss': 0.3079, 'grad_norm': 1.5739268064498901, 'learning_rate': 8.34659593280283e-05, 'epoch': 5.83}\n", + "{'loss': 0.3078, 'grad_norm': 0.6474704742431641, 'learning_rate': 7.99292661361627e-05, 'epoch': 6.01}\n", + "{'loss': 0.194, 'grad_norm': 1.3646390438079834, 'learning_rate': 7.639257294429708e-05, 'epoch': 6.18}\n", + "{'loss': 0.2034, 'grad_norm': 1.275925636291504, 'learning_rate': 7.285587975243147e-05, 'epoch': 6.36}\n", + "{'loss': 0.2082, 'grad_norm': 1.2210203409194946, 'learning_rate': 6.931918656056587e-05, 'epoch': 6.54}\n", + "{'loss': 0.205, 'grad_norm': 0.8089584112167358, 'learning_rate': 6.578249336870027e-05, 'epoch': 6.71}\n", + "{'loss': 0.2143, 'grad_norm': 1.1388084888458252, 'learning_rate': 6.224580017683466e-05, 'epoch': 6.89}\n", + "{'loss': 0.195, 'grad_norm': 0.7365647554397583, 'learning_rate': 5.870910698496905e-05, 'epoch': 7.07}\n", + "{'loss': 0.148, 'grad_norm': 0.5169339179992676, 'learning_rate': 5.517241379310345e-05, 'epoch': 7.24}\n", + "{'loss': 0.1574, 'grad_norm': 0.9203131198883057, 'learning_rate': 5.163572060123785e-05, 'epoch': 7.42}\n", + "{'loss': 0.1573, 'grad_norm': 0.7963287830352783, 'learning_rate': 4.809902740937224e-05, 'epoch': 7.6}\n", + "{'loss': 0.1567, 'grad_norm': 0.6291562914848328, 'learning_rate': 4.4562334217506634e-05, 'epoch': 7.77}\n", + "{'loss': 0.1591, 'grad_norm': 1.3627387285232544, 'learning_rate': 4.1025641025641023e-05, 'epoch': 7.95}\n", + "{'loss': 0.1367, 'grad_norm': 0.6390063166618347, 'learning_rate': 3.7488947833775426e-05, 'epoch': 8.13}\n", + "{'loss': 0.1307, 'grad_norm': 0.6079268455505371, 'learning_rate': 3.3952254641909815e-05, 'epoch': 8.3}\n", + "{'loss': 0.1313, 'grad_norm': 0.47809019684791565, 'learning_rate': 3.041556145004421e-05, 'epoch': 8.48}\n", + "{'loss': 0.1333, 'grad_norm': 0.41499361395835876, 'learning_rate': 2.6878868258178604e-05, 'epoch': 8.66}\n", + "{'loss': 0.1335, 'grad_norm': 0.6223477125167847, 'learning_rate': 2.3342175066313e-05, 'epoch': 8.83}\n", + "{'loss': 0.1331, 'grad_norm': 0.4558337330818176, 'learning_rate': 1.9805481874447392e-05, 'epoch': 9.01}\n", + "{'loss': 0.118, 'grad_norm': 0.4607541561126709, 'learning_rate': 1.6268788682581788e-05, 'epoch': 9.19}\n", + "{'loss': 0.1186, 'grad_norm': 0.49737748503685, 'learning_rate': 1.273209549071618e-05, 'epoch': 9.36}\n", + "{'loss': 0.1197, 'grad_norm': 0.46176978945732117, 'learning_rate': 9.195402298850575e-06, 'epoch': 9.54}\n", + "{'loss': 0.1203, 'grad_norm': 0.48998674750328064, 'learning_rate': 5.658709106984969e-06, 'epoch': 9.72}\n", + "{'loss': 0.1231, 'grad_norm': 0.443093866109848, 'learning_rate': 2.1220159151193635e-06, 'epoch': 9.89}\n", + "{'train_runtime': 15713.8663, 'train_samples_per_second': 2.882, 'train_steps_per_second': 0.36, 'train_loss': 0.5995376785736624, 'epoch': 10.0}\n", + "100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 5660/5660 [4:21:53<00:00, 2.78s/it]\n", + "(5) GPU = NVIDIA GeForce RTX 4080 Laptop GPU. Max memory = 11.994 GB.\n", + "15713.8663 seconds used for training.\n", + "261.9 minutes used for training.\n", + "Peak reserved memory = 3.945 GB.\n", + "Peak reserved memory for training = 0.0 GB.\n", + "Peak reserved memory % of max memory = 32.891 %.\n", + "Peak reserved memory for training % of max memory = 0.0 %.\n", + "Evaluating fine-tuned model: unsloth/Qwen2-1.5B-Instruct-bnb-4bit\n", + " 0%| | 0/1133 [00:00\n", + "--------\n", + "step 2: Old Geng raised the pistol to his eye, squeezed the trigger, and some of the shot flew straight into the sky, like ice pellets, as spattered tin shells burst against the willows.\n", + "--------\n", + "step 3: Old Geng raised the pistol to his eye, squeezed the trigger, and some of the shot flew straight into the sky, like ice pellets, as spattered tin shells burst against the willows.\n", + "100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 1133/1133 [2:11:23<00:00, 6.96s/it]\n", + " chinese ... unsloth/Qwen2-1.5B-Instruct-bnb-4bit(finetuned)\n", + "0 老耿端衷ζžͺοΌŒηœ―ηΌθ΅·δΈ€εͺδΈ‰θ§’ηœΌοΌŒδΈ€ζ‚ζ‰³ζœΊε“δΊ†ζžͺοΌŒε†°ι›Ήθˆ¬ηš„ι‡‘ιΊ»ι›€εŠˆε“©ε•ͺε•¦εΎ€δΈ‹θ½οΌŒι“η ‚ε­εœ¨ζŸ³ζžι—΄ι£ž... ... Old Geng raised the pistol to his eye, squeeze...\n", + "\n", + "[1 rows x 6 columns]\n", + "(6) GPU = NVIDIA GeForce RTX 4080 Laptop GPU. Max memory = 11.994 GB.\n", + "5.33 GB of memory reserved.\n", + "README.md: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 593/593 [00:00<00:00, 3.08MB/s]\n", + "model.safetensors: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 1.22G/1.22G [02:18<00:00, 8.82MB/s]\n", + "Saved model to https://huggingface.co/Qwen2-1.5B-Instruct-bnb-4bit-MAC-lora\n", + "README.md: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆοΏ½οΏ½οΏ½β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 599/599 [00:00<00:00, 2.99MB/s]\n", + "Unsloth: Saving tokenizer... Done.\n", + "Unsloth: Saving model... Done.\n", + "Unsloth: Saving LoRA adapters. Please wait...\n", + "401 Client Error: Unauthorized for url: https://huggingface.co/api/repos/create (Request ID: Root=1-66787955-4b5759766262340722a532d6;dcdc16ae-e45d-406a-81c9-13d22426edcb)\n", + "\n", + "Invalid username or password.\n", + "CPU times: user 23min 32s, sys: 8min 51s, total: 32min 24s\n", + "Wall time: 14h 50min 41s\n" + ] + } + ], + "source": [ + "%%time\n", + "\n", + "!./tune-small.sh" + ] + }, + { + "cell_type": "code", + "execution_count": 9, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Current Directory:\n", + "/home/inflaton/code/projects/courses/novel-translation\n", + "Tuning unsloth/Qwen2-0.5B-Instruct\n", + "πŸ¦₯ Unsloth: Will patch your computer to enable 2x faster free finetuning.\n", + "[nltk_data] Downloading package wordnet to /home/inflaton/nltk_data...\n", + "[nltk_data] Package wordnet is already up-to-date!\n", + "[nltk_data] Downloading package punkt to /home/inflaton/nltk_data...\n", + "[nltk_data] Package punkt is already up-to-date!\n", + "[nltk_data] Downloading package omw-1.4 to /home/inflaton/nltk_data...\n", + "[nltk_data] Package omw-1.4 is already up-to-date!\n", + "loading /home/inflaton/code/projects/courses/novel-translation/translation_engine_v3.py\n", + "loading env vars from: /home/inflaton/code/projects/courses/novel-translation/.env\n", + "unsloth/Qwen2-0.5B-Instruct True 2048 10 None datasets/mac/mac.tsv results/mac-results_v3.csv True True True\n", + "(1) GPU = NVIDIA GeForce RTX 4080 Laptop GPU. Max memory = 11.994 GB.\n", + "0.0 GB of memory reserved.\n", + "loading model: unsloth/Qwen2-0.5B-Instruct\n", + "==((====))== Unsloth: Fast Qwen2 patching release 2024.6\n", + " \\\\ /| GPU: NVIDIA GeForce RTX 4080 Laptop GPU. Max memory: 11.994 GB. Platform = Linux.\n", + "O^O/ \\_/ \\ Pytorch: 2.3.0. CUDA = 8.9. CUDA Toolkit = 12.1.\n", + "\\ / Bfloat16 = TRUE. Xformers = 0.0.26.post1. FA = True.\n", + " \"-____-\" Free Apache license: http://github.com/unslothai/unsloth\n", + "Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.\n", + "Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.\n", + "(2) GPU = NVIDIA GeForce RTX 4080 Laptop GPU. Max memory = 11.994 GB.\n", + "0.633 GB of memory reserved.\n", + "loading train/test data files\n", + "DatasetDict({\n", + " train: Dataset({\n", + " features: ['chinese', 'english', 'text', 'prompt'],\n", + " num_rows: 4528\n", + " })\n", + " test: Dataset({\n", + " features: ['chinese', 'english', 'text', 'prompt'],\n", + " num_rows: 1133\n", + " })\n", + "})\n", + "Evaluating base model: unsloth/Qwen2-0.5B-Instruct\n", + " 0%| | 0/1133 [00:00\n", + "--------\n", + "step 2: Oldθ€ΏδΈΎθ΅·ζžͺοΌŒηœ―η€ηœΌη›οΌŒζžͺε£°θ½°ιΈ£οΌŒε­εΌΉη °η °η °εœ°θ½εœ¨εœ°δΈŠοΌŒδΈ€ι’—ι’—ε†°ι›Ήθˆ¬ηš„ε€§ιΈŸζ‰‘ζ£±ζ£±εœ°θ½εœ¨ζŸ³ζ ‘δΉ‹ι—΄οΌŒε’”εš“δΈ€ε£°γ€‚\n", + "--------\n", + "step 3: Oldθ€ΏδΈΎθ΅·ζžͺοΌŒηœ―η€ηœΌη›οΌŒζžͺε£°θ½°ιΈ£οΌŒε­εΌΉη °η °η °εœ°θ½εœ¨εœ°δΈŠοΌŒδΈ€ι’—ι’—ε†°ι›Ήθˆ¬ηš„ε€§ιΈŸζ‰‘ζ£±ζ£±εœ°θ½εœ¨ζŸ³ζ ‘δΉ‹ι—΄οΌŒε’”εš“δΈ€ε£°γ€‚\n", + "100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 1133/1133 [1:07:20<00:00, 3.57s/it]\n", + " chinese ... unsloth/Qwen2-0.5B-Instruct\n", + "0 老耿端衷ζžͺοΌŒηœ―ηΌθ΅·δΈ€εͺδΈ‰θ§’ηœΌοΌŒδΈ€ζ‚ζ‰³ζœΊε“δΊ†ζžͺοΌŒε†°ι›Ήθˆ¬ηš„ι‡‘ιΊ»ι›€εŠˆε“©ε•ͺε•¦εΎ€δΈ‹θ½οΌŒι“η ‚ε­εœ¨ζŸ³ζžι—΄ι£ž... ... Oldθ€ΏδΈΎθ΅·ζžͺοΌŒηœ―η€ηœΌη›οΌŒζžͺε£°θ½°ιΈ£οΌŒε­εΌΉη °η °η °εœ°θ½εœ¨εœ°δΈŠοΌŒδΈ€ι’—ι’—ε†°ι›Ήθˆ¬ηš„ε€§ιΈŸζ‰‘ζ£±ζ£±εœ°θ½εœ¨ζŸ³ζ ‘...\n", + "\n", + "[1 rows x 7 columns]\n", + "(3) GPU = NVIDIA GeForce RTX 4080 Laptop GPU. Max memory = 11.994 GB.\n", + "0.873 GB of memory reserved.\n", + "Unsloth 2024.6 patched 24 layers with 0 QKV layers, 24 O layers and 24 MLP layers.\n", + "(4) GPU = NVIDIA GeForce RTX 4080 Laptop GPU. Max memory = 11.994 GB.\n", + "0.873 GB of memory reserved.\n", + "==((====))== Unsloth - 2x faster free finetuning | Num GPUs = 1\n", + " \\\\ /| Num examples = 4,528 | Num Epochs = 10\n", + "O^O/ \\_/ \\ Batch size per device = 2 | Gradient Accumulation steps = 4\n", + "\\ / Total batch size = 8 | Total steps = 5,660\n", + " \"-____-\" Number of trainable parameters = 8,798,208\n", + "{'loss': 1.9401, 'grad_norm': 0.9639493823051453, 'learning_rate': 0.00019664014146772768, 'epoch': 0.18}\n", + "{'loss': 1.7763, 'grad_norm': 0.8041688799858093, 'learning_rate': 0.0001931034482758621, 'epoch': 0.35}\n", + "{'loss': 1.7147, 'grad_norm': 0.93106609582901, 'learning_rate': 0.00018956675508399648, 'epoch': 0.53}\n", + "{'loss': 1.7156, 'grad_norm': 0.753624677658081, 'learning_rate': 0.00018603006189213086, 'epoch': 0.71}\n", + "{'loss': 1.6862, 'grad_norm': 0.823365330696106, 'learning_rate': 0.00018249336870026527, 'epoch': 0.88}\n", + "{'loss': 1.6076, 'grad_norm': 0.807159423828125, 'learning_rate': 0.00017895667550839965, 'epoch': 1.06}\n", + "{'loss': 1.492, 'grad_norm': 0.9032222032546997, 'learning_rate': 0.00017541998231653406, 'epoch': 1.24}\n", + "{'loss': 1.5407, 'grad_norm': 0.9780230522155762, 'learning_rate': 0.00017188328912466844, 'epoch': 1.41}\n", + "{'loss': 1.4722, 'grad_norm': 1.0792107582092285, 'learning_rate': 0.00016834659593280285, 'epoch': 1.59}\n", + "{'loss': 1.4688, 'grad_norm': 0.9899805784225464, 'learning_rate': 0.00016480990274093723, 'epoch': 1.77}\n", + "{'loss': 1.5279, 'grad_norm': 1.0187550783157349, 'learning_rate': 0.00016127320954907164, 'epoch': 1.94}\n", + "{'loss': 1.3492, 'grad_norm': 1.1653039455413818, 'learning_rate': 0.000157736516357206, 'epoch': 2.12}\n", + "{'loss': 1.2155, 'grad_norm': 1.1759636402130127, 'learning_rate': 0.0001541998231653404, 'epoch': 2.3}\n", + "{'loss': 1.258, 'grad_norm': 1.3161606788635254, 'learning_rate': 0.0001506631299734748, 'epoch': 2.47}\n", + "{'loss': 1.2556, 'grad_norm': 1.345459222793579, 'learning_rate': 0.0001471264367816092, 'epoch': 2.65}\n", + "{'loss': 1.2664, 'grad_norm': 1.1774756908416748, 'learning_rate': 0.0001435897435897436, 'epoch': 2.83}\n", + "{'loss': 1.2348, 'grad_norm': 1.1240969896316528, 'learning_rate': 0.000140053050397878, 'epoch': 3.0}\n", + "{'loss': 0.9803, 'grad_norm': 1.504067301750183, 'learning_rate': 0.0001365163572060124, 'epoch': 3.18}\n", + "{'loss': 0.9925, 'grad_norm': 1.5067857503890991, 'learning_rate': 0.00013297966401414678, 'epoch': 3.36}\n", + "{'loss': 0.9989, 'grad_norm': 1.520134449005127, 'learning_rate': 0.0001294429708222812, 'epoch': 3.53}\n", + "{'loss': 0.9807, 'grad_norm': 1.5608190298080444, 'learning_rate': 0.00012590627763041555, 'epoch': 3.71}\n", + "{'loss': 1.0231, 'grad_norm': 1.6115481853485107, 'learning_rate': 0.00012236958443854996, 'epoch': 3.89}\n", + "{'loss': 0.9304, 'grad_norm': 1.5296086072921753, 'learning_rate': 0.00011883289124668435, 'epoch': 4.06}\n", + "{'loss': 0.7399, 'grad_norm': 1.6573024988174438, 'learning_rate': 0.00011529619805481875, 'epoch': 4.24}\n", + "{'loss': 0.7408, 'grad_norm': 1.7512829303741455, 'learning_rate': 0.00011175950486295315, 'epoch': 4.42}\n", + "{'loss': 0.7755, 'grad_norm': 2.100616216659546, 'learning_rate': 0.00010822281167108754, 'epoch': 4.59}\n", + "{'loss': 0.7736, 'grad_norm': 2.121138572692871, 'learning_rate': 0.00010468611847922194, 'epoch': 4.77}\n", + "{'loss': 0.7939, 'grad_norm': 2.1208739280700684, 'learning_rate': 0.00010114942528735633, 'epoch': 4.95}\n", + "{'loss': 0.6306, 'grad_norm': 1.7874706983566284, 'learning_rate': 9.761273209549072e-05, 'epoch': 5.12}\n", + "{'loss': 0.5555, 'grad_norm': 1.7197502851486206, 'learning_rate': 9.407603890362513e-05, 'epoch': 5.3}\n", + "{'loss': 0.5615, 'grad_norm': 1.6627233028411865, 'learning_rate': 9.053934571175951e-05, 'epoch': 5.48}\n", + "{'loss': 0.5916, 'grad_norm': 1.8348921537399292, 'learning_rate': 8.70026525198939e-05, 'epoch': 5.65}\n", + "{'loss': 0.5824, 'grad_norm': 2.2089450359344482, 'learning_rate': 8.34659593280283e-05, 'epoch': 5.83}\n", + "{'loss': 0.5792, 'grad_norm': 2.447774648666382, 'learning_rate': 7.99292661361627e-05, 'epoch': 6.01}\n", + "{'loss': 0.3998, 'grad_norm': 1.8090907335281372, 'learning_rate': 7.639257294429708e-05, 'epoch': 6.18}\n", + "{'loss': 0.4113, 'grad_norm': 1.8496599197387695, 'learning_rate': 7.285587975243147e-05, 'epoch': 6.36}\n", + "{'loss': 0.4296, 'grad_norm': 2.046454429626465, 'learning_rate': 6.931918656056587e-05, 'epoch': 6.54}\n", + "{'loss': 0.4214, 'grad_norm': 1.8460564613342285, 'learning_rate': 6.578249336870027e-05, 'epoch': 6.71}\n", + "{'loss': 0.4279, 'grad_norm': 1.7839864492416382, 'learning_rate': 6.224580017683466e-05, 'epoch': 6.89}\n", + "{'loss': 0.3849, 'grad_norm': 1.6806727647781372, 'learning_rate': 5.870910698496905e-05, 'epoch': 7.07}\n", + "{'loss': 0.2936, 'grad_norm': 1.7148785591125488, 'learning_rate': 5.517241379310345e-05, 'epoch': 7.24}\n", + "{'loss': 0.3127, 'grad_norm': 1.2444647550582886, 'learning_rate': 5.163572060123785e-05, 'epoch': 7.42}\n", + "{'loss': 0.3143, 'grad_norm': 2.0613274574279785, 'learning_rate': 4.809902740937224e-05, 'epoch': 7.6}\n", + "{'loss': 0.3047, 'grad_norm': 1.9974720478057861, 'learning_rate': 4.4562334217506634e-05, 'epoch': 7.77}\n", + "{'loss': 0.3181, 'grad_norm': 1.7139118909835815, 'learning_rate': 4.1025641025641023e-05, 'epoch': 7.95}\n", + "{'loss': 0.247, 'grad_norm': 1.3952387571334839, 'learning_rate': 3.7488947833775426e-05, 'epoch': 8.13}\n", + "{'loss': 0.226, 'grad_norm': 1.4544029235839844, 'learning_rate': 3.3952254641909815e-05, 'epoch': 8.3}\n", + "{'loss': 0.2295, 'grad_norm': 1.3040739297866821, 'learning_rate': 3.041556145004421e-05, 'epoch': 8.48}\n", + "{'loss': 0.2367, 'grad_norm': 1.0945595502853394, 'learning_rate': 2.6878868258178604e-05, 'epoch': 8.66}\n", + "{'loss': 0.236, 'grad_norm': 2.110018491744995, 'learning_rate': 2.3342175066313e-05, 'epoch': 8.83}\n", + "{'loss': 0.2384, 'grad_norm': 1.0737488269805908, 'learning_rate': 1.9805481874447392e-05, 'epoch': 9.01}\n", + "{'loss': 0.181, 'grad_norm': 1.0586763620376587, 'learning_rate': 1.6268788682581788e-05, 'epoch': 9.19}\n", + "{'loss': 0.19, 'grad_norm': 1.11255943775177, 'learning_rate': 1.273209549071618e-05, 'epoch': 9.36}\n", + "{'loss': 0.1869, 'grad_norm': 1.0752365589141846, 'learning_rate': 9.195402298850575e-06, 'epoch': 9.54}\n", + "{'loss': 0.1881, 'grad_norm': 1.592451810836792, 'learning_rate': 5.658709106984969e-06, 'epoch': 9.72}\n", + "{'loss': 0.1889, 'grad_norm': 1.070407748222351, 'learning_rate': 2.1220159151193635e-06, 'epoch': 9.89}\n", + "{'train_runtime': 13633.0365, 'train_samples_per_second': 3.321, 'train_steps_per_second': 0.415, 'train_loss': 0.7991274287759625, 'epoch': 10.0}\n", + "100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 5660/5660 [3:47:13<00:00, 2.41s/it]\n", + "(5) GPU = NVIDIA GeForce RTX 4080 Laptop GPU. Max memory = 11.994 GB.\n", + "13633.0365 seconds used for training.\n", + "227.22 minutes used for training.\n", + "Peak reserved memory = 1.369 GB.\n", + "Peak reserved memory for training = 0.496 GB.\n", + "Peak reserved memory % of max memory = 11.414 %.\n", + "Peak reserved memory for training % of max memory = 4.135 %.\n", + "Evaluating fine-tuned model: unsloth/Qwen2-0.5B-Instruct\n", + " 0%| | 0/1133 [00:00\n", + "--------\n", + "step 2: Old Geng raised his rifle and tilted his head, clasping the trigger, and a crash of iron shrapnel fell beside him, splashing over time boundaries and scattering like ice rain.\n", + "--------\n", + "step 3: Old Geng raised his rifle and tilted his head, clasping the trigger, and a crash of iron shrapnel fell beside him, splashing over time boundaries and scattering like ice rain.\n", + "100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 1133/1133 [1:36:22<00:00, 5.10s/it]\n", + " chinese ... unsloth/Qwen2-0.5B-Instruct(finetuned)\n", + "0 老耿端衷ζžͺοΌŒηœ―ηΌθ΅·δΈ€εͺδΈ‰θ§’ηœΌοΌŒδΈ€ζ‚ζ‰³ζœΊε“δΊ†ζžͺοΌŒε†°ι›Ήθˆ¬ηš„ι‡‘ιΊ»ι›€εŠˆε“©ε•ͺε•¦εΎ€δΈ‹θ½οΌŒι“η ‚ε­εœ¨ζŸ³ζžι—΄ι£ž... ... Old Geng raised his rifle and tilted his head,...\n", + "\n", + "[1 rows x 8 columns]\n", + "(6) GPU = NVIDIA GeForce RTX 4080 Laptop GPU. Max memory = 11.994 GB.\n", + "1.369 GB of memory reserved.\n", + "README.md: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 599/599 [00:00<00:00, 3.47MB/s]\n", + "model.safetensors: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 493M/493M [01:42<00:00, 4.83MB/s]\n", + "Saved model to https://huggingface.co/Qwen2-0.5B-Instruct-MAC-lora\n", + "Unsloth: Saving tokenizer... Done.\n", + "Unsloth: Saving model... Done.\n", + "Unsloth: Saving LoRA adapters. Please wait...\n", + "401 Client Error: Unauthorized for url: https://huggingface.co/api/repos/create (Request ID: Root=1-6678d5ab-7ebfba970b06941d330c774c;eef78700-1bc6-4a4b-82dc-3a0513f85a69)\n", + "\n", + "Invalid username or password.\n", + "Tuning unsloth/Qwen2-1.5B-Instruct\n", + "πŸ¦₯ Unsloth: Will patch your computer to enable 2x faster free finetuning.\n", + "[nltk_data] Downloading package wordnet to /home/inflaton/nltk_data...\n", + "[nltk_data] Package wordnet is already up-to-date!\n", + "[nltk_data] Downloading package punkt to /home/inflaton/nltk_data...\n", + "[nltk_data] Package punkt is already up-to-date!\n", + "[nltk_data] Downloading package omw-1.4 to /home/inflaton/nltk_data...\n", + "[nltk_data] Package omw-1.4 is already up-to-date!\n", + "loading /home/inflaton/code/projects/courses/novel-translation/translation_engine_v3.py\n", + "loading env vars from: /home/inflaton/code/projects/courses/novel-translation/.env\n", + "unsloth/Qwen2-1.5B-Instruct True 2048 10 None datasets/mac/mac.tsv results/mac-results_v3.csv True True True\n", + "(1) GPU = NVIDIA GeForce RTX 4080 Laptop GPU. Max memory = 11.994 GB.\n", + "0.0 GB of memory reserved.\n", + "loading model: unsloth/Qwen2-1.5B-Instruct\n", + "==((====))== Unsloth: Fast Qwen2 patching release 2024.6\n", + " \\\\ /| GPU: NVIDIA GeForce RTX 4080 Laptop GPU. Max memory: 11.994 GB. Platform = Linux.\n", + "O^O/ \\_/ \\ Pytorch: 2.3.0. CUDA = 8.9. CUDA Toolkit = 12.1.\n", + "\\ / Bfloat16 = TRUE. Xformers = 0.0.26.post1. FA = True.\n", + " \"-____-\" Free Apache license: http://github.com/unslothai/unsloth\n", + "Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.\n", + "Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.\n", + "(2) GPU = NVIDIA GeForce RTX 4080 Laptop GPU. Max memory = 11.994 GB.\n", + "1.516 GB of memory reserved.\n", + "loading train/test data files\n", + "Map: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 4528/4528 [00:00<00:00, 9716.63 examples/s]\n", + "Map: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 1133/1133 [00:00<00:00, 5762.27 examples/s]\n", + "DatasetDict({\n", + " train: Dataset({\n", + " features: ['chinese', 'english', 'text', 'prompt'],\n", + " num_rows: 4528\n", + " })\n", + " test: Dataset({\n", + " features: ['chinese', 'english', 'text', 'prompt'],\n", + " num_rows: 1133\n", + " })\n", + "})\n", + "Evaluating base model: unsloth/Qwen2-1.5B-Instruct\n", + " 0%| | 0/1133 [00:00\n", + "--------\n", + "step 2: Old Geer lifted his gun, squinted one of his eyes, clutched it, and fired off a shot like hail of golden sparrows, sand grains flying from the willows, making a sound.\n", + "--------\n", + "step 3: Old Geer lifted his gun, squinted one of his eyes, clutched it, and fired off a shot like hail of golden sparrows, sand grains flying from the willows, making a sound.\n", + "100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 1133/1133 [1:08:04<00:00, 3.61s/it]\n", + " chinese ... unsloth/Qwen2-1.5B-Instruct\n", + "0 老耿端衷ζžͺοΌŒηœ―ηΌθ΅·δΈ€εͺδΈ‰θ§’ηœΌοΌŒδΈ€ζ‚ζ‰³ζœΊε“δΊ†ζžͺοΌŒε†°ι›Ήθˆ¬ηš„ι‡‘ιΊ»ι›€εŠˆε“©ε•ͺε•¦εΎ€δΈ‹θ½οΌŒι“η ‚ε­εœ¨ζŸ³ζžι—΄ι£ž... ... Old Geer lifted his gun, squinted one of his e...\n", + "\n", + "[1 rows x 9 columns]\n", + "(3) GPU = NVIDIA GeForce RTX 4080 Laptop GPU. Max memory = 11.994 GB.\n", + "1.758 GB of memory reserved.\n", + "Unsloth 2024.6 patched 28 layers with 0 QKV layers, 28 O layers and 28 MLP layers.\n", + "Map (num_proc=2): 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 4528/4528 [00:02<00:00, 2227.71 examples/s]\n", + "(4) GPU = NVIDIA GeForce RTX 4080 Laptop GPU. Max memory = 11.994 GB.\n", + "1.758 GB of memory reserved.\n", + "==((====))== Unsloth - 2x faster free finetuning | Num GPUs = 1\n", + " \\\\ /| Num examples = 4,528 | Num Epochs = 10\n", + "O^O/ \\_/ \\ Batch size per device = 2 | Gradient Accumulation steps = 4\n", + "\\ / Total batch size = 8 | Total steps = 5,660\n", + " \"-____-\" Number of trainable parameters = 18,464,768\n", + "{'loss': 1.7417, 'grad_norm': 0.6435620188713074, 'learning_rate': 0.00019664014146772768, 'epoch': 0.18}\n", + "{'loss': 1.5681, 'grad_norm': 0.6191736459732056, 'learning_rate': 0.0001931034482758621, 'epoch': 0.35}\n", + "{'loss': 1.516, 'grad_norm': 0.6416980028152466, 'learning_rate': 0.00018956675508399648, 'epoch': 0.53}\n", + "{'loss': 1.5173, 'grad_norm': 0.5749340057373047, 'learning_rate': 0.00018603006189213086, 'epoch': 0.71}\n", + "{'loss': 1.4962, 'grad_norm': 0.5725200176239014, 'learning_rate': 0.00018249336870026527, 'epoch': 0.88}\n", + "{'loss': 1.4184, 'grad_norm': 0.6020503640174866, 'learning_rate': 0.00017895667550839965, 'epoch': 1.06}\n", + "{'loss': 1.2973, 'grad_norm': 0.7252504229545593, 'learning_rate': 0.00017541998231653406, 'epoch': 1.24}\n", + "{'loss': 1.3397, 'grad_norm': 0.6848253011703491, 'learning_rate': 0.00017188328912466844, 'epoch': 1.41}\n", + "{'loss': 1.2787, 'grad_norm': 0.9209019541740417, 'learning_rate': 0.00016834659593280285, 'epoch': 1.59}\n", + "{'loss': 1.2797, 'grad_norm': 0.8531824946403503, 'learning_rate': 0.00016480990274093723, 'epoch': 1.77}\n", + "{'loss': 1.3313, 'grad_norm': 0.8282666206359863, 'learning_rate': 0.00016127320954907164, 'epoch': 1.94}\n", + "{'loss': 1.1277, 'grad_norm': 0.9999461770057678, 'learning_rate': 0.000157736516357206, 'epoch': 2.12}\n", + "{'loss': 0.9964, 'grad_norm': 1.1321799755096436, 'learning_rate': 0.0001541998231653404, 'epoch': 2.3}\n", + "{'loss': 1.0302, 'grad_norm': 1.2508618831634521, 'learning_rate': 0.0001506631299734748, 'epoch': 2.47}\n", + "{'loss': 1.0345, 'grad_norm': 1.0669715404510498, 'learning_rate': 0.0001471264367816092, 'epoch': 2.65}\n", + "{'loss': 1.0366, 'grad_norm': 1.0575922727584839, 'learning_rate': 0.0001435897435897436, 'epoch': 2.83}\n", + "{'loss': 1.0088, 'grad_norm': 0.8964874148368835, 'learning_rate': 0.000140053050397878, 'epoch': 3.0}\n", + "{'loss': 0.697, 'grad_norm': 1.2907732725143433, 'learning_rate': 0.0001365163572060124, 'epoch': 3.18}\n", + "{'loss': 0.7093, 'grad_norm': 1.3694052696228027, 'learning_rate': 0.00013297966401414678, 'epoch': 3.36}\n", + "{'loss': 0.7154, 'grad_norm': 1.3360122442245483, 'learning_rate': 0.0001294429708222812, 'epoch': 3.53}\n", + "{'loss': 0.7039, 'grad_norm': 1.3949358463287354, 'learning_rate': 0.00012590627763041555, 'epoch': 3.71}\n", + "{'loss': 0.7428, 'grad_norm': 1.2718554735183716, 'learning_rate': 0.00012236958443854996, 'epoch': 3.89}\n", + "{'loss': 0.643, 'grad_norm': 1.135117769241333, 'learning_rate': 0.00011883289124668435, 'epoch': 4.06}\n", + "{'loss': 0.4595, 'grad_norm': 1.454145908355713, 'learning_rate': 0.00011529619805481875, 'epoch': 4.24}\n", + "{'loss': 0.444, 'grad_norm': 1.6696418523788452, 'learning_rate': 0.00011175950486295315, 'epoch': 4.42}\n", + "{'loss': 0.4826, 'grad_norm': 1.7666652202606201, 'learning_rate': 0.00010822281167108754, 'epoch': 4.59}\n", + "{'loss': 0.4795, 'grad_norm': 1.742395281791687, 'learning_rate': 0.00010468611847922194, 'epoch': 4.77}\n", + "{'loss': 0.4856, 'grad_norm': 1.5103402137756348, 'learning_rate': 0.00010114942528735633, 'epoch': 4.95}\n", + "{'loss': 0.3593, 'grad_norm': 1.3078151941299438, 'learning_rate': 9.761273209549072e-05, 'epoch': 5.12}\n", + "{'loss': 0.2904, 'grad_norm': 1.2514950037002563, 'learning_rate': 9.407603890362513e-05, 'epoch': 5.3}\n", + "{'loss': 0.2991, 'grad_norm': 1.658071756362915, 'learning_rate': 9.053934571175951e-05, 'epoch': 5.48}\n", + "{'loss': 0.3144, 'grad_norm': 1.6055220365524292, 'learning_rate': 8.70026525198939e-05, 'epoch': 5.65}\n", + "{'loss': 0.3093, 'grad_norm': 1.5153316259384155, 'learning_rate': 8.34659593280283e-05, 'epoch': 5.83}\n", + "{'loss': 0.3058, 'grad_norm': 0.9724624752998352, 'learning_rate': 7.99292661361627e-05, 'epoch': 6.01}\n", + "{'loss': 0.1934, 'grad_norm': 0.954325795173645, 'learning_rate': 7.639257294429708e-05, 'epoch': 6.18}\n", + "{'loss': 0.2036, 'grad_norm': 1.537642240524292, 'learning_rate': 7.285587975243147e-05, 'epoch': 6.36}\n", + "{'loss': 0.2079, 'grad_norm': 1.2404054403305054, 'learning_rate': 6.931918656056587e-05, 'epoch': 6.54}\n", + "{'loss': 0.2049, 'grad_norm': 1.0820835828781128, 'learning_rate': 6.578249336870027e-05, 'epoch': 6.71}\n", + "{'loss': 0.215, 'grad_norm': 1.32541024684906, 'learning_rate': 6.224580017683466e-05, 'epoch': 6.89}\n", + "{'loss': 0.1946, 'grad_norm': 0.7059425711631775, 'learning_rate': 5.870910698496905e-05, 'epoch': 7.07}\n", + "{'loss': 0.1489, 'grad_norm': 1.0154873132705688, 'learning_rate': 5.517241379310345e-05, 'epoch': 7.24}\n", + "{'loss': 0.1581, 'grad_norm': 0.7846829891204834, 'learning_rate': 5.163572060123785e-05, 'epoch': 7.42}\n", + "{'loss': 0.1593, 'grad_norm': 0.9743372201919556, 'learning_rate': 4.809902740937224e-05, 'epoch': 7.6}\n", + "{'loss': 0.1568, 'grad_norm': 0.8308056592941284, 'learning_rate': 4.4562334217506634e-05, 'epoch': 7.77}\n", + "{'loss': 0.1587, 'grad_norm': 0.8165437579154968, 'learning_rate': 4.1025641025641023e-05, 'epoch': 7.95}\n", + "{'loss': 0.137, 'grad_norm': 1.081515908241272, 'learning_rate': 3.7488947833775426e-05, 'epoch': 8.13}\n", + "{'loss': 0.1305, 'grad_norm': 0.6178275942802429, 'learning_rate': 3.3952254641909815e-05, 'epoch': 8.3}\n", + "{'loss': 0.1318, 'grad_norm': 0.4706704914569855, 'learning_rate': 3.041556145004421e-05, 'epoch': 8.48}\n", + "{'loss': 0.1331, 'grad_norm': 0.41128799319267273, 'learning_rate': 2.6878868258178604e-05, 'epoch': 8.66}\n", + "{'loss': 0.1349, 'grad_norm': 0.674155056476593, 'learning_rate': 2.3342175066313e-05, 'epoch': 8.83}\n", + "{'loss': 0.1327, 'grad_norm': 0.49978604912757874, 'learning_rate': 1.9805481874447392e-05, 'epoch': 9.01}\n", + "{'loss': 0.1177, 'grad_norm': 0.44771721959114075, 'learning_rate': 1.6268788682581788e-05, 'epoch': 9.19}\n", + "{'loss': 0.1187, 'grad_norm': 0.587639331817627, 'learning_rate': 1.273209549071618e-05, 'epoch': 9.36}\n", + "{'loss': 0.1198, 'grad_norm': 0.47292351722717285, 'learning_rate': 9.195402298850575e-06, 'epoch': 9.54}\n", + "{'loss': 0.1203, 'grad_norm': 0.5652945041656494, 'learning_rate': 5.658709106984969e-06, 'epoch': 9.72}\n", + "{'loss': 0.1232, 'grad_norm': 0.93674236536026, 'learning_rate': 2.1220159151193635e-06, 'epoch': 9.89}\n", + "{'train_runtime': 15791.9321, 'train_samples_per_second': 2.867, 'train_steps_per_second': 0.358, 'train_loss': 0.5995039068767966, 'epoch': 10.0}\n", + "100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 5660/5660 [4:23:11<00:00, 2.79s/it]\n", + "(5) GPU = NVIDIA GeForce RTX 4080 Laptop GPU. Max memory = 11.994 GB.\n", + "15791.9321 seconds used for training.\n", + "263.2 minutes used for training.\n", + "Peak reserved memory = 2.365 GB.\n", + "Peak reserved memory for training = 0.607 GB.\n", + "Peak reserved memory % of max memory = 19.718 %.\n", + "Peak reserved memory for training % of max memory = 5.061 %.\n", + "Evaluating fine-tuned model: unsloth/Qwen2-1.5B-Instruct\n", + " 0%| | 0/1133 [00:00\n", + "--------\n", + "step 2: Old Geng raised his gun, squinted, and emptied it. The cocoon of bullets split open as they flew, like ice pellets, until it was gone, sending chiseling sounds tumbling through the air as iron seeds smashed pruneflower stems.\n", + "--------\n", + "step 3: Old Geng raised his gun, squinted, and emptied it. The cocoon of bullets split open as they flew, like ice pellets, until it was gone, sending chiseling sounds tumbling through the air as iron seeds smashed pruneflower stems.\n", + "100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 1133/1133 [2:10:28<00:00, 6.91s/it]\n", + " chinese ... unsloth/Qwen2-1.5B-Instruct(finetuned)\n", + "0 老耿端衷ζžͺοΌŒηœ―ηΌθ΅·δΈ€εͺδΈ‰θ§’ηœΌοΌŒδΈ€ζ‚ζ‰³ζœΊε“δΊ†ζžͺοΌŒε†°ι›Ήθˆ¬ηš„ι‡‘ιΊ»ι›€εŠˆε“©ε•ͺε•¦εΎ€δΈ‹θ½οΌŒι“η ‚ε­εœ¨ζŸ³ζžι—΄ι£ž... ... Old Geng raised his gun, squinted, and emptied...\n", + "\n", + "[1 rows x 10 columns]\n", + "(6) GPU = NVIDIA GeForce RTX 4080 Laptop GPU. Max memory = 11.994 GB.\n", + "5.33 GB of memory reserved.\n", + "README.md: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 599/599 [00:00<00:00, 3.36MB/s]\n", + "model.safetensors: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 1.22G/1.22G [04:57<00:00, 4.09MB/s]\n", + "Saved model to https://huggingface.co/Qwen2-1.5B-Instruct-MAC-lora\n", + "Unsloth: Saving tokenizer... Done.\n", + "Unsloth: Saving model... Done.\n", + "Unsloth: Saving LoRA adapters. Please wait...\n", + "401 Client Error: Unauthorized for url: https://huggingface.co/api/repos/create (Request ID: Root=1-667943a2-3b0230ba1811ed550b585d53;2d0f1d17-f232-41f6-9eab-add0e87114f8)\n", + "\n", + "Invalid username or password.\n", + "CPU times: user 23min 30s, sys: 8min 24s, total: 31min 55s\n", + "Wall time: 14h 23min 14s\n" + ] + } + ], + "source": [ + "%%time\n", + "\n", + "!./tune-small-2.sh" + ] + } + ], + "metadata": { + "accelerator": "GPU", + "application/vnd.databricks.v1+notebook": { + "dashboards": [], + "environmentMetadata": null, + "language": "python", + "notebookMetadata": { + "pythonIndentUnit": 4 + }, + "notebookName": "07_MAC_+_Qwen2-7B-Instructi_Unsloth_train", + "widgets": {} + }, + "colab": { + "gpuType": "T4", + "provenance": [] + }, + "kernelspec": { + "display_name": "Python 3", + "name": "python3" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 3 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython3", + "version": "3.10.14" + }, + "widgets": { + "application/vnd.jupyter.widget-state+json": { + "036fc5746f43416db18c19ad8fd36677": { + "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": "" + } + }, + "06e806c82c7b4cbea31c5358dd9c3434": { + "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": "" + } + }, + "087b76a8b7514269b1f0ab29b062e444": { + "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_a069d2ab23824f29aa320ac256e2cfe9", + "placeholder": "​", + "style": "IPY_MODEL_06e806c82c7b4cbea31c5358dd9c3434", + "value": "Map (num_proc=2): 100%" + } + }, + "09b76013aa9e45efb6deb23a7a0d0925": { + "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_dea41c5260884aa6879b5e1d1697b14f", + "placeholder": "​", + "style": "IPY_MODEL_89965917796a4f81b899fdc7685f33df", + "value": "config.json: 100%" + } + }, + "0a92c56bfa134ef583220d7ef0b13e17": { + "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": "" + } + }, + "0c34be936c8145d3ab41282f30a70713": { + "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 + } + }, + "0f8b6bfe16894500838793f2491d403f": { + "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 + } + }, + "177c78fce95d4b4ab33057c5a048d693": { + "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": "" + } + }, + "1f44c9ce1adf470cbb19784493ed209f": { + "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_0c34be936c8145d3ab41282f30a70713", + "placeholder": "​", + "style": "IPY_MODEL_0a92c56bfa134ef583220d7ef0b13e17", + "value": "model.safetensors: 100%" + } + }, + "201b59ccd9f845e197029b57e424aefc": { + "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": "" + } + }, + "2157f01726d748f8a9ae4a00664430da": { + "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": "" + } + }, + "21db8a77b00d4a4e82fdfa608657531f": { + "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 + } + }, + "26e4202cca81496a90d15a0dd4ca9cf1": { + "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_ba90fdb8822d47dab7ba203bee297f37", + "IPY_MODEL_61560ff6a36b44f4a9dfdae5c52791d4", + "IPY_MODEL_95fbe66647904c06a20f640630d6dc0e" + ], + "layout": "IPY_MODEL_57182a263d324a3dbf1471c74290a0d5" + } + }, + "27155728b6b84cb199c91c940095d0a8": { + "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_6b91feeed5464877991ac2c207aebe7c", + "IPY_MODEL_cca8113c54c0495daedce1327bf9c68b", + "IPY_MODEL_2e63a29e2f7247bba5beede9a568c99f" + ], + "layout": "IPY_MODEL_5c9d781c28944f3eb86e2a6d44efdf18" + } + }, + "271ddaa553a042d09b6db7b450643d8f": { + "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": "" + } + }, + "2a58d04b428c46f4b3dbadd3bc6cd529": { + "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 + } + }, + "2d18ddf6482c4d97829ac0e5a7b9868f": { + "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_9f679ad3ec7f4fe8ad0510ffb57bc2ab", + "IPY_MODEL_f2df530d22c74977b249dd9fb5f4829b", + "IPY_MODEL_89b2ef0dbfea47ab8e6f8d659e3351d1" + ], + "layout": "IPY_MODEL_3056b148aa9f4e6e8aa3b61d26886255" + } + }, + "2e5087c76f98437cb5dc729230358cba": { + "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 + } + }, + "2e63a29e2f7247bba5beede9a568c99f": { + "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_b993eaec6b224440bf80c0958c6fb536", + "placeholder": "​", + "style": "IPY_MODEL_de868e26e7154f62aa86223a539ad421", + "value": " 464/464 [00:00<00:00, 27.1kB/s]" + } + }, + "2f6c70dd266c4816bfad3fd3d192929a": { + "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": "" + } + }, + "30307300bc4e4baf96560e30969a82b6": { + "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_e36a3f9eff0e4cf68834d66b0213ae96", + "placeholder": "​", + "style": "IPY_MODEL_a0037bdccf254159becde630bee3d1db", + "value": "generation_config.json: 100%" + } + }, + "3056b148aa9f4e6e8aa3b61d26886255": { + "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 + } + }, + "30cdc32298134cb0be4d41615b9e5774": { + "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 + } + }, + "3572201bd4d74a58b7a665f9bdfdcdba": { + "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": "" + } + }, + "35b0e8c26d6640e9bd0ed7b242a423d8": { + "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_2e5087c76f98437cb5dc729230358cba", + "max": 51760, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_036fc5746f43416db18c19ad8fd36677", + "value": 51760 + } + }, + "36166c7bcb854b34aca1f41a5d6ea50b": { + "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": "" + } + }, + "370692d819df41828b48c4ad446f977b": { + "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 + } + }, + "39b29a75374b45c0a22506010be2b84e": { + "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_30cdc32298134cb0be4d41615b9e5774", + "max": 1179, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_47928317548c454bba6358ab132e8dee", + "value": 1179 + } + }, + "3cf2dd993b5e4d3daecf61e4bab5a404": { + "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_087b76a8b7514269b1f0ab29b062e444", + "IPY_MODEL_35b0e8c26d6640e9bd0ed7b242a423d8", + "IPY_MODEL_54ad89e05fd74576b9b8b5b5a10eaf8d" + ], + "layout": "IPY_MODEL_a41dc44766444a998bec2d777f249d23" + } + }, + "43dec2ede91341f5af60eb522e18e984": { + "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 + } + }, + "4463edd481c1467f914c7dcd6c6e6ffc": { + "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 + } + }, + "47928317548c454bba6358ab132e8dee": { + "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": "" + } + }, + "49277aeeac16434a865a4d12308b1abc": { + "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 + } + }, + "4ae7e449e4ea4c729b5f34607c18ebae": { + "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 + } + }, + "4b2061b8a73c43ffb0c2f83daf0d0183": { + "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 + } + }, + "4c4c88d4c701450692fa0f6b0c5764b0": { + "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 + } + }, + "4c666f4ace3943f8b80ecd20e7503236": { + "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": "" + } + }, + "4ccedf0d93094e63b57a0f8a434fba06": { + "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_4463edd481c1467f914c7dcd6c6e6ffc", + "max": 44307561, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_6d3b9a05db0b4dadb638c686faa0c40a", + "value": 44307561 + } + }, + "4dcf6ff672d24983a1877a8431709aa9": { + "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_5807d5fb827d490fb3bc698f801ffff5", + "placeholder": "​", + "style": "IPY_MODEL_c4f2b06a82fd4987b8b659524a7b503b", + "value": "Generating train split: 100%" + } + }, + "4ea63adfce694725bdba878aef709dd3": { + "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 + } + }, + "5234566b1bfc4655b8d582ea5b46ed9f": { + "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": "" + } + }, + "54ad89e05fd74576b9b8b5b5a10eaf8d": { + "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_fdb1941405ed4e4aa06019933892deb3", + "placeholder": "​", + "style": "IPY_MODEL_668d5377ca56426a99753867e6e24862", + "value": " 51760/51760 [01:02<00:00, 1131.51 examples/s]" + } + }, + "56aee4853b7740e6a977254f5d1fa66d": { + "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": "" + } + }, + "57182a263d324a3dbf1471c74290a0d5": { + "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 + } + }, + "5807d5fb827d490fb3bc698f801ffff5": { + "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 + } + }, + "5c9d781c28944f3eb86e2a6d44efdf18": { + "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 + } + }, + "5f40db8173dd4d76b6ef5ed6d9ec8b6e": { + "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 + } + }, + "61560ff6a36b44f4a9dfdae5c52791d4": { + "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_db19fc8d37db4e45a5790a876836d8c4", + "max": 11610, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_36166c7bcb854b34aca1f41a5d6ea50b", + "value": 11610 + } + }, + "6578fd7acdb54c4c93528ea431fd0144": { + "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_370692d819df41828b48c4ad446f977b", + "placeholder": "​", + "style": "IPY_MODEL_a0bf9160eb2647409b3200270914b90f", + "value": " 50.6k/50.6k [00:00<00:00, 2.71MB/s]" + } + }, + "668d5377ca56426a99753867e6e24862": { + "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": "" + } + }, + "697f027529b54ee9956bae78a11e0611": { + "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": "" + } + }, + "69ac12aec0714318bf2c83d4f4e745f5": { + "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": "" + } + }, + "6b2012c3f88547af8884a9ea90e3164b": { + "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_938f45f1b3e24118b815d96ae34ba86a", + "placeholder": "​", + "style": "IPY_MODEL_9367047a800747f79c6b225d92397846", + "value": " 44.3M/44.3M [00:01<00:00, 31.0MB/s]" + } + }, + "6b91feeed5464877991ac2c207aebe7c": { + "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_4b2061b8a73c43ffb0c2f83daf0d0183", + "placeholder": "​", + "style": "IPY_MODEL_69ac12aec0714318bf2c83d4f4e745f5", + "value": "special_tokens_map.json: 100%" + } + }, + "6d3b9a05db0b4dadb638c686faa0c40a": { + "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": "" + } + }, + "6dbbedeca9314e66ae50e44ffa31a414": { + "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": "" + } + }, + "6e34619b45934040b6092e6fb01ea7fe": { + "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 + } + }, + "71ce208e20d6483abb9ed923510c86d7": { + "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_d69dc491b3ab44d7852b21873ed7bb7f", + "placeholder": "​", + "style": "IPY_MODEL_f401d53bf28e44eb906bce6c05412662", + "value": " 51760/51760 [00:01<00:00, 45512.81 examples/s]" + } + }, + "7358cdad832342c983e31efb8754ab78": { + "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 + } + }, + "73e352a3404f4c7dad0737f57d29e92f": { + "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_988a0e8c1f89446086858da0a891a79c", + "IPY_MODEL_4ccedf0d93094e63b57a0f8a434fba06", + "IPY_MODEL_6b2012c3f88547af8884a9ea90e3164b" + ], + "layout": "IPY_MODEL_7e29cb8dd4df4d5b94407cd8fd3f2011" + } + }, + "74501720ac7e4dbb911a4a99b3633bc6": { + "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": "" + } + }, + "78e5400bff924a92a4cc61c4ff18b182": { + "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_b9b313fd861948f5aba25b24b1518d30", + "placeholder": "​", + "style": "IPY_MODEL_4c666f4ace3943f8b80ecd20e7503236", + "value": " 1.18k/1.18k [00:00<00:00, 31.3kB/s]" + } + }, + "7975adbc2ec5489ea7fa0167e620d85c": { + "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_6e34619b45934040b6092e6fb01ea7fe", + "max": 51760, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_271ddaa553a042d09b6db7b450643d8f", + "value": 51760 + } + }, + "7e29cb8dd4df4d5b94407cd8fd3f2011": { + "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 + } + }, + "810ff6c0e17d4fa09a30fef27eacff90": { + "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": "" + } + }, + "89965917796a4f81b899fdc7685f33df": { + "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": "" + } + }, + "89b2ef0dbfea47ab8e6f8d659e3351d1": { + "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_b8908fa0df3743ecb9d12983a739104f", + "placeholder": "​", + "style": "IPY_MODEL_177c78fce95d4b4ab33057c5a048d693", + "value": " 9.09M/9.09M [00:00<00:00, 32.6MB/s]" + } + }, + "8b3505352a5a42bf910428c40ce40465": { + "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_49277aeeac16434a865a4d12308b1abc", + "placeholder": "​", + "style": "IPY_MODEL_2157f01726d748f8a9ae4a00664430da", + "value": " 5.70G/5.70G [01:02<00:00, 30.1MB/s]" + } + }, + "8fc142b628fb40568730234de1cafde2": { + "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_4ae7e449e4ea4c729b5f34607c18ebae", + "max": 172, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_3572201bd4d74a58b7a665f9bdfdcdba", + "value": 172 + } + }, + "9367047a800747f79c6b225d92397846": { + "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": "" + } + }, + "938f45f1b3e24118b815d96ae34ba86a": { + "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 + } + }, + "95fbe66647904c06a20f640630d6dc0e": { + "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_b0a370dc20654b279b9680692e34418e", + "placeholder": "​", + "style": "IPY_MODEL_cfeb365ddf7548d58b2557f22737fcf5", + "value": " 11.6k/11.6k [00:00<00:00, 716kB/s]" + } + }, + "988a0e8c1f89446086858da0a891a79c": { + "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_ad2be500fc164c0f86f33e914ef8e6a0", + "placeholder": "​", + "style": "IPY_MODEL_5234566b1bfc4655b8d582ea5b46ed9f", + "value": "Downloading data: 100%" + } + }, + "98c58f23f4d549518832cb2d18f796e8": { + "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_09b76013aa9e45efb6deb23a7a0d0925", + "IPY_MODEL_39b29a75374b45c0a22506010be2b84e", + "IPY_MODEL_78e5400bff924a92a4cc61c4ff18b182" + ], + "layout": "IPY_MODEL_2a58d04b428c46f4b3dbadd3bc6cd529" + } + }, + "99fdbb0300c14c139d1937c646f0cfe7": { + "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_7358cdad832342c983e31efb8754ab78", + "placeholder": "​", + "style": "IPY_MODEL_e9adf418296e436fb48bb9f78885598b", + "value": " 51760/51760 [00:01<00:00, 38665.95 examples/s]" + } + }, + "9f679ad3ec7f4fe8ad0510ffb57bc2ab": { + "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_4ea63adfce694725bdba878aef709dd3", + "placeholder": "​", + "style": "IPY_MODEL_74501720ac7e4dbb911a4a99b3633bc6", + "value": "tokenizer.json: 100%" + } + }, + "a0037bdccf254159becde630bee3d1db": { + "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": "" + } + }, + "a069d2ab23824f29aa320ac256e2cfe9": { + "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 + } + }, + "a0bf9160eb2647409b3200270914b90f": { + "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": "" + } + }, + "a41dc44766444a998bec2d777f249d23": { + "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 + } + }, + "a8464a4c711e4e00aafdfc919b60d07e": { + "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_fb995c740590427b882572c81d4e848c", + "placeholder": "​", + "style": "IPY_MODEL_201b59ccd9f845e197029b57e424aefc", + "value": " 172/172 [00:00<00:00, 12.0kB/s]" + } + }, + "a9f0cc51fc3d4d7b874c32dcf1c5bdf2": { + "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 + } + }, + "ad2be500fc164c0f86f33e914ef8e6a0": { + "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 + } + }, + "b0240cd9a4554b29ae11f8051984a1c6": { + "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_edaf890370314a218f138015faa0b05d", + "placeholder": "​", + "style": "IPY_MODEL_697f027529b54ee9956bae78a11e0611", + "value": "Map: 100%" + } + }, + "b0a370dc20654b279b9680692e34418e": { + "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 + } + }, + "b518dcee69074b87be73957cd810e7ed": { + "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_d891f8d0b1fc462f8008d02bb2a15692", + "placeholder": "​", + "style": "IPY_MODEL_cced8fd7e998472794f3f3e3018956a5", + "value": "tokenizer_config.json: 100%" + } + }, + "b8908fa0df3743ecb9d12983a739104f": { + "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 + } + }, + "b993eaec6b224440bf80c0958c6fb536": { + "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 + } + }, + "b9b313fd861948f5aba25b24b1518d30": { + "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 + } + }, + "ba90fdb8822d47dab7ba203bee297f37": { + "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_0f8b6bfe16894500838793f2491d403f", + "placeholder": "​", + "style": "IPY_MODEL_bb19f6c747754682a514373a3a0535ba", + "value": "Downloading readme: 100%" + } + }, + "bb19f6c747754682a514373a3a0535ba": { + "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": "" + } + }, + "bc883d4cf13e4f8b8a4fe5f410cb6efd": { + "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_e9159e03e61f4f56978ece9c3bca49b2", + "max": 51760, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_810ff6c0e17d4fa09a30fef27eacff90", + "value": 51760 + } + }, + "c161d94df0f04feba9542237e0856c22": { + "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 + } + }, + "c22f71b1f85843209d7e5321506b9cb9": { + "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_1f44c9ce1adf470cbb19784493ed209f", + "IPY_MODEL_f1addc4479d849879e743cf9089e6540", + "IPY_MODEL_8b3505352a5a42bf910428c40ce40465" + ], + "layout": "IPY_MODEL_4c4c88d4c701450692fa0f6b0c5764b0" + } + }, + "c4f2b06a82fd4987b8b659524a7b503b": { + "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": "" + } + }, + "cca8113c54c0495daedce1327bf9c68b": { + "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_e02f9b7849c64531835eb77b860d1c93", + "max": 464, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_56aee4853b7740e6a977254f5d1fa66d", + "value": 464 + } + }, + "cced8fd7e998472794f3f3e3018956a5": { + "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": "" + } + }, + "cf245afeb1c04f29a24d291608c3d157": { + "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_b518dcee69074b87be73957cd810e7ed", + "IPY_MODEL_e29104486d594b2992d7285e0ef77371", + "IPY_MODEL_6578fd7acdb54c4c93528ea431fd0144" + ], + "layout": "IPY_MODEL_d35db8148a354c56aaac56dbae22536f" + } + }, + "cfe8cae0e22b495bafa221a63d13b283": { + "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 + } + }, + "cfeb365ddf7548d58b2557f22737fcf5": { + "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": "" + } + }, + "d1b47d39450d4019ae85c9b2f943eeaf": { + "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_4dcf6ff672d24983a1877a8431709aa9", + "IPY_MODEL_7975adbc2ec5489ea7fa0167e620d85c", + "IPY_MODEL_71ce208e20d6483abb9ed923510c86d7" + ], + "layout": "IPY_MODEL_cfe8cae0e22b495bafa221a63d13b283" + } + }, + "d35db8148a354c56aaac56dbae22536f": { + "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 + } + }, + "d69dc491b3ab44d7852b21873ed7bb7f": { + "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 + } + }, + "d891f8d0b1fc462f8008d02bb2a15692": { + "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 + } + }, + "d8e5318cead340c4adbeaccc05d39225": { + "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": "" + } + }, + "daf4cd890b35422683d22fd30bc71e83": { + "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_b0240cd9a4554b29ae11f8051984a1c6", + "IPY_MODEL_bc883d4cf13e4f8b8a4fe5f410cb6efd", + "IPY_MODEL_99fdbb0300c14c139d1937c646f0cfe7" + ], + "layout": "IPY_MODEL_c161d94df0f04feba9542237e0856c22" + } + }, + "db19fc8d37db4e45a5790a876836d8c4": { + "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 + } + }, + "de868e26e7154f62aa86223a539ad421": { + "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": "" + } + }, + "dea41c5260884aa6879b5e1d1697b14f": { + "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 + } + }, + "e02f9b7849c64531835eb77b860d1c93": { + "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 + } + }, + "e29104486d594b2992d7285e0ef77371": { + "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_a9f0cc51fc3d4d7b874c32dcf1c5bdf2", + "max": 50641, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_2f6c70dd266c4816bfad3fd3d192929a", + "value": 50641 + } + }, + "e36a3f9eff0e4cf68834d66b0213ae96": { + "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 + } + }, + "e9159e03e61f4f56978ece9c3bca49b2": { + "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 + } + }, + "e9adf418296e436fb48bb9f78885598b": { + "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": "" + } + }, + "edaf890370314a218f138015faa0b05d": { + "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 + } + }, + "f1addc4479d849879e743cf9089e6540": { + "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_43dec2ede91341f5af60eb522e18e984", + "max": 5702746405, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_d8e5318cead340c4adbeaccc05d39225", + "value": 5702746405 + } + }, + "f2df530d22c74977b249dd9fb5f4829b": { + "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_21db8a77b00d4a4e82fdfa608657531f", + "max": 9085698, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_6dbbedeca9314e66ae50e44ffa31a414", + "value": 9085698 + } + }, + "f401d53bf28e44eb906bce6c05412662": { + "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": "" + } + }, + "fb995c740590427b882572c81d4e848c": { + "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 + } + }, + "fce7a61c25ec4390af43d92b7c473a45": { + "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_30307300bc4e4baf96560e30969a82b6", + "IPY_MODEL_8fc142b628fb40568730234de1cafde2", + "IPY_MODEL_a8464a4c711e4e00aafdfc919b60d07e" + ], + "layout": "IPY_MODEL_5f40db8173dd4d76b6ef5ed6d9ec8b6e" + } + }, + "fdb1941405ed4e4aa06019933892deb3": { + "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": 0 +}