{ "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/llm-finetuning\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/llm-finetuning/.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',\n", " True,\n", " None,\n", " None,\n", " 2048,\n", " 6,\n", " None,\n", " 'datasets/mac/mac.tsv',\n", " 'results/mac-results_lf-r2.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": [ "Fri Jul 5 20:43:31 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 Off | N/A |\n", "| N/A 53C P8 3W / 150W | 0MiB / 12282MiB | 0% 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": [ "Python 3.11.9\n", "\u001b[33mWARNING: Package(s) not found: flash-attn\u001b[0m\u001b[33m\n", "\u001b[0mCPU times: user 9.63 ms, sys: 584 μs, total: 10.2 ms\n", "Wall time: 561 ms\n" ] } ], "source": [ "%%time\n", "!python --version\n", "!pip show flash-attn" ] }, { "cell_type": "code", "execution_count": 7, "metadata": {}, "outputs": [], "source": [ "def evaluate_model_all_epochs(model_name, num_train_epochs, adapter_path_base, load_in_4bit=True):\n", " os.environ[\"MODEL_NAME\"] = model_name \n", " os.environ[\"LOAD_IN_4BIT\"] = \"true\" if load_in_4bit else \"false\"\n", " for i in range(num_train_epochs + 1):\n", " print(f\"Epoch {i}\")\n", " if i == 0:\n", " os.unsetenv(\"ADAPTER_NAME_OR_PATH\")\n", " else:\n", " adapter_path = f\"{adapter_path_base}/checkpoint-{560 * i}\"\n", " os.environ[\"ADAPTER_NAME_OR_PATH\"] = adapter_path\n", " \n", " !python llm_toolkit/eval_lf.py" ] }, { "cell_type": "code", "execution_count": 8, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Epoch 0\n", "loading env vars from: /home/inflaton/code/projects/courses/llm-finetuning/.env\n", "Adding /home/inflaton/code/projects/courses/llm-finetuning to sys.path\n", "loading /home/inflaton/code/projects/courses/llm-finetuning/llm_toolkit/translation_utils.py\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", "Qwen/Qwen2-0.5B-Instruct None False datasets/mac/mac.tsv results/mac-results_lf-r2.csv\n", "(1) GPU = NVIDIA GeForce RTX 4080 Laptop GPU. Max memory = 11.994 GB.\n", "0.0 GB of memory reserved.\n", "loading model: Qwen/Qwen2-0.5B-Instruct\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", "0.648 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 model: Qwen/Qwen2-0.5B-Instruct\n", " 0%| | 0/1133 [00:00\n", "--------\n", "step 2: Old Ge lifted his gun and lowered his eyes as he fired a round at the muzzle of his revolver. A clatter echoed as the bullet landed on the ground, a thunderclap sound as the metal bullets flew through the air like tiny raindrops. The clangs were so loud that it was almost deafening.\n", "--------\n", "step 3: Old Ge lifted his gun and lowered his eyes as he fired a round at the muzzle of his revolver. A clatter echoed as the bullet landed on the ground, a thunderclap sound as the metal bullets flew through the air like tiny raindrops. The clangs were so loud that it was almost deafening.\n", "100%|█████████████████████████████████████| 1133/1133 [1:12:38<00:00, 3.85s/it]\n", "(3) GPU = NVIDIA GeForce RTX 4080 Laptop GPU. Max memory = 11.994 GB.\n", "42.221 GB of memory reserved.\n", " chinese ... Qwen/Qwen2-0.5B-Instruct\n", "0 老耿端起枪，眯缝起一只三角眼，一搂扳机响了枪，冰雹般的金麻雀劈哩啪啦往下落，铁砂子在柳枝间飞... ... Old Ge lifted his gun and lowered his eyes as ...\n", "\n", "[1 rows x 3 columns]\n", "{'accuracy': 0.00088261253309797, 'correct_ids': [659], 'meteor': 0.26081317536040693, 'bleu_scores': {'bleu': 0.04524849442288909, 'precisions': [0.29694860978538656, 0.07063552833078102, 0.022536982493298476, 0.008867807795421737], 'brevity_penalty': 1.0, 'length_ratio': 1.0757535607817157, 'translation_length': 32477, 'reference_length': 30190}, 'rouge_scores': {'rouge1': 0.30875100352153667, 'rouge2': 0.0888448776296162, 'rougeL': 0.25554192339577875, 'rougeLsum': 0.25541634440613653}}\n", "Epoch 1\n", "loading env vars from: /home/inflaton/code/projects/courses/llm-finetuning/.env\n", "Adding /home/inflaton/code/projects/courses/llm-finetuning to sys.path\n", "loading /home/inflaton/code/projects/courses/llm-finetuning/llm_toolkit/translation_utils.py\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", "Qwen/Qwen2-0.5B-Instruct llama-factory/saves/qwen2-0.5b-bf16/lora/sft/checkpoint-560 False datasets/mac/mac.tsv results/mac-results_lf-r2.csv\n", "(1) GPU = NVIDIA GeForce RTX 4080 Laptop GPU. Max memory = 11.994 GB.\n", "0.0 GB of memory reserved.\n", "loading model: Qwen/Qwen2-0.5B-Instruct\n", "[INFO|tokenization_utils_base.py:2161] 2024-07-05 21:57:32,624 >> loading file vocab.json from cache at /home/inflaton/.cache/huggingface/hub/models--Qwen--Qwen2-0.5B-Instruct/snapshots/c291d6fce4804a1d39305f388dd32897d1f7acc4/vocab.json\n", "[INFO|tokenization_utils_base.py:2161] 2024-07-05 21:57:32,624 >> loading file merges.txt from cache at /home/inflaton/.cache/huggingface/hub/models--Qwen--Qwen2-0.5B-Instruct/snapshots/c291d6fce4804a1d39305f388dd32897d1f7acc4/merges.txt\n", "[INFO|tokenization_utils_base.py:2161] 2024-07-05 21:57:32,624 >> loading file tokenizer.json from cache at /home/inflaton/.cache/huggingface/hub/models--Qwen--Qwen2-0.5B-Instruct/snapshots/c291d6fce4804a1d39305f388dd32897d1f7acc4/tokenizer.json\n", "[INFO|tokenization_utils_base.py:2161] 2024-07-05 21:57:32,624 >> loading file added_tokens.json from cache at None\n", "[INFO|tokenization_utils_base.py:2161] 2024-07-05 21:57:32,624 >> loading file special_tokens_map.json from cache at None\n", "[INFO|tokenization_utils_base.py:2161] 2024-07-05 21:57:32,624 >> loading file tokenizer_config.json from cache at /home/inflaton/.cache/huggingface/hub/models--Qwen--Qwen2-0.5B-Instruct/snapshots/c291d6fce4804a1d39305f388dd32897d1f7acc4/tokenizer_config.json\n", "[WARNING|logging.py:313] 2024-07-05 21:57:32,754 >> Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.\n", "07/05/2024 21:57:32 - INFO - llamafactory.data.template - Replace eos token: <|im_end|>\n", "07/05/2024 21:57:32 - INFO - llamafactory.data.template - Add <|im_start|> to stop words.\n", "[INFO|configuration_utils.py:733] 2024-07-05 21:57:33,154 >> loading configuration file config.json from cache at /home/inflaton/.cache/huggingface/hub/models--Qwen--Qwen2-0.5B-Instruct/snapshots/c291d6fce4804a1d39305f388dd32897d1f7acc4/config.json\n", "[INFO|configuration_utils.py:800] 2024-07-05 21:57:33,155 >> Model config Qwen2Config {\n", " \"_name_or_path\": \"Qwen/Qwen2-0.5B-Instruct\",\n", " \"architectures\": [\n", " \"Qwen2ForCausalLM\"\n", " ],\n", " \"attention_dropout\": 0.0,\n", " \"bos_token_id\": 151643,\n", " \"eos_token_id\": 151645,\n", " \"hidden_act\": \"silu\",\n", " \"hidden_size\": 896,\n", " \"initializer_range\": 0.02,\n", " \"intermediate_size\": 4864,\n", " \"max_position_embeddings\": 32768,\n", " \"max_window_layers\": 24,\n", " \"model_type\": \"qwen2\",\n", " \"num_attention_heads\": 14,\n", " \"num_hidden_layers\": 24,\n", " \"num_key_value_heads\": 2,\n", " \"rms_norm_eps\": 1e-06,\n", " \"rope_theta\": 1000000.0,\n", " \"sliding_window\": 32768,\n", " \"tie_word_embeddings\": true,\n", " \"torch_dtype\": \"bfloat16\",\n", " \"transformers_version\": \"4.42.3\",\n", " \"use_cache\": true,\n", " \"use_sliding_window\": false,\n", " \"vocab_size\": 151936\n", "}\n", "\n", "07/05/2024 21:57:33 - INFO - llamafactory.model.model_utils.quantization - Quantizing model to 4 bit with bitsandbytes.\n", "07/05/2024 21:57:33 - INFO - llamafactory.model.patcher - Using KV cache for faster generation.\n", "[INFO|modeling_utils.py:3556] 2024-07-05 21:57:33,197 >> loading weights file model.safetensors from cache at /home/inflaton/.cache/huggingface/hub/models--Qwen--Qwen2-0.5B-Instruct/snapshots/c291d6fce4804a1d39305f388dd32897d1f7acc4/model.safetensors\n", "[INFO|modeling_utils.py:1531] 2024-07-05 21:57:34,819 >> Instantiating Qwen2ForCausalLM model under default dtype torch.bfloat16.\n", "[INFO|configuration_utils.py:1000] 2024-07-05 21:57:34,821 >> Generate config GenerationConfig {\n", " \"bos_token_id\": 151643,\n", " \"eos_token_id\": 151645\n", "}\n", "\n", "[INFO|modeling_utils.py:4364] 2024-07-05 21:58:53,028 >> All model checkpoint weights were used when initializing Qwen2ForCausalLM.\n", "\n", "[INFO|modeling_utils.py:4372] 2024-07-05 21:58:53,029 >> All the weights of Qwen2ForCausalLM were initialized from the model checkpoint at Qwen/Qwen2-0.5B-Instruct.\n", "If your task is similar to the task the model of the checkpoint was trained on, you can already use Qwen2ForCausalLM for predictions without further training.\n", "[INFO|configuration_utils.py:955] 2024-07-05 21:58:53,351 >> loading configuration file generation_config.json from cache at /home/inflaton/.cache/huggingface/hub/models--Qwen--Qwen2-0.5B-Instruct/snapshots/c291d6fce4804a1d39305f388dd32897d1f7acc4/generation_config.json\n", "[INFO|configuration_utils.py:1000] 2024-07-05 21:58:53,352 >> Generate config GenerationConfig {\n", " \"bos_token_id\": 151643,\n", " \"do_sample\": true,\n", " \"eos_token_id\": [\n", " 151645,\n", " 151643\n", " ],\n", " \"pad_token_id\": 151643,\n", " \"repetition_penalty\": 1.1,\n", " \"temperature\": 0.7,\n", " \"top_k\": 20,\n", " \"top_p\": 0.8\n", "}\n", "\n", "07/05/2024 21:58:53 - INFO - llamafactory.model.model_utils.attention - Using torch SDPA for faster training and inference.\n", "07/05/2024 21:58:54 - INFO - llamafactory.model.adapter - Loaded adapter(s): llama-factory/saves/qwen2-0.5b-bf16/lora/sft/checkpoint-560\n", "07/05/2024 21:58:54 - INFO - llamafactory.model.loader - all params: 498,431,872\n", "(2) GPU = NVIDIA GeForce RTX 4080 Laptop GPU. Max memory = 11.994 GB.\n", "0.658 GB of memory reserved.\n", "loading train/test data files\n", "Map: 100%|████████████████████████| 4528/4528 [00:00<00:00, 13341.90 examples/s]\n", "Map: 100%|█████████████████████████| 1133/1133 [00:00<00:00, 4246.31 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 model: Qwen/Qwen2-0.5B-Instruct\n", " 0%| | 0/1133 [00:00\n", "--------\n", "step 2: Old Goong cocked his gun and lowered his eyes as he pulled the trigger. The hammer clinked, and a hail of metal balls fell like ice from the sky. The sound of a crackling pine was heard above him.\n", "--------\n", "step 3: Old Goong cocked his gun and lowered his eyes as he pulled the trigger. The hammer clinked, and a hail of metal balls fell like ice from the sky. The sound of a crackling pine was heard above him.\n", "100%|█████████████████████████████████████| 1133/1133 [2:01:28<00:00, 6.43s/it]\n", "(3) GPU = NVIDIA GeForce RTX 4080 Laptop GPU. Max memory = 11.994 GB.\n", "42.279 GB of memory reserved.\n", " chinese ... Qwen/Qwen2-0.5B-Instruct_checkpoint-560\n", "0 老耿端起枪，眯缝起一只三角眼，一搂扳机响了枪，冰雹般的金麻雀劈哩啪啦往下落，铁砂子在柳枝间飞... ... Old Goong cocked his gun and lowered his eyes ...\n", "\n", "[1 rows x 4 columns]\n", "{'accuracy': 0.0, 'correct_ids': [], 'meteor': 0.29049497377443884, 'bleu_scores': {'bleu': 0.04774897884656905, 'precisions': [0.3009629887457942, 0.07359865638964701, 0.024153239576542175, 0.009716234476545911], 'brevity_penalty': 1.0, 'length_ratio': 1.1419675389201722, 'translation_length': 34476, 'reference_length': 30190}, 'rouge_scores': {'rouge1': 0.3246452473704004, 'rouge2': 0.09593992376129423, 'rougeL': 0.26493434905174373, 'rougeLsum': 0.26501903150454154}}\n", "Epoch 2\n", "loading env vars from: /home/inflaton/code/projects/courses/llm-finetuning/.env\n", "Adding /home/inflaton/code/projects/courses/llm-finetuning to sys.path\n", "loading /home/inflaton/code/projects/courses/llm-finetuning/llm_toolkit/translation_utils.py\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", "Qwen/Qwen2-0.5B-Instruct llama-factory/saves/qwen2-0.5b-bf16/lora/sft/checkpoint-1120 False datasets/mac/mac.tsv results/mac-results_lf-r2.csv\n", "(1) GPU = NVIDIA GeForce RTX 4080 Laptop GPU. Max memory = 11.994 GB.\n", "0.0 GB of memory reserved.\n", "loading model: Qwen/Qwen2-0.5B-Instruct\n", "[INFO|tokenization_utils_base.py:2161] 2024-07-06 00:00:55,837 >> loading file vocab.json from cache at /home/inflaton/.cache/huggingface/hub/models--Qwen--Qwen2-0.5B-Instruct/snapshots/c291d6fce4804a1d39305f388dd32897d1f7acc4/vocab.json\n", "[INFO|tokenization_utils_base.py:2161] 2024-07-06 00:00:55,837 >> loading file merges.txt from cache at /home/inflaton/.cache/huggingface/hub/models--Qwen--Qwen2-0.5B-Instruct/snapshots/c291d6fce4804a1d39305f388dd32897d1f7acc4/merges.txt\n", "[INFO|tokenization_utils_base.py:2161] 2024-07-06 00:00:55,837 >> loading file tokenizer.json from cache at /home/inflaton/.cache/huggingface/hub/models--Qwen--Qwen2-0.5B-Instruct/snapshots/c291d6fce4804a1d39305f388dd32897d1f7acc4/tokenizer.json\n", "[INFO|tokenization_utils_base.py:2161] 2024-07-06 00:00:55,837 >> loading file added_tokens.json from cache at None\n", "[INFO|tokenization_utils_base.py:2161] 2024-07-06 00:00:55,837 >> loading file special_tokens_map.json from cache at None\n", "[INFO|tokenization_utils_base.py:2161] 2024-07-06 00:00:55,838 >> loading file tokenizer_config.json from cache at /home/inflaton/.cache/huggingface/hub/models--Qwen--Qwen2-0.5B-Instruct/snapshots/c291d6fce4804a1d39305f388dd32897d1f7acc4/tokenizer_config.json\n", "[WARNING|logging.py:313] 2024-07-06 00:00:55,965 >> Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.\n", "07/06/2024 00:00:55 - INFO - llamafactory.data.template - Replace eos token: <|im_end|>\n", "07/06/2024 00:00:55 - INFO - llamafactory.data.template - Add <|im_start|> to stop words.\n", "[INFO|configuration_utils.py:733] 2024-07-06 00:00:56,623 >> loading configuration file config.json from cache at /home/inflaton/.cache/huggingface/hub/models--Qwen--Qwen2-0.5B-Instruct/snapshots/c291d6fce4804a1d39305f388dd32897d1f7acc4/config.json\n", "[INFO|configuration_utils.py:800] 2024-07-06 00:00:56,623 >> Model config Qwen2Config {\n", " \"_name_or_path\": \"Qwen/Qwen2-0.5B-Instruct\",\n", " \"architectures\": [\n", " \"Qwen2ForCausalLM\"\n", " ],\n", " \"attention_dropout\": 0.0,\n", " \"bos_token_id\": 151643,\n", " \"eos_token_id\": 151645,\n", " \"hidden_act\": \"silu\",\n", " \"hidden_size\": 896,\n", " \"initializer_range\": 0.02,\n", " \"intermediate_size\": 4864,\n", " \"max_position_embeddings\": 32768,\n", " \"max_window_layers\": 24,\n", " \"model_type\": \"qwen2\",\n", " \"num_attention_heads\": 14,\n", " \"num_hidden_layers\": 24,\n", " \"num_key_value_heads\": 2,\n", " \"rms_norm_eps\": 1e-06,\n", " \"rope_theta\": 1000000.0,\n", " \"sliding_window\": 32768,\n", " \"tie_word_embeddings\": true,\n", " \"torch_dtype\": \"bfloat16\",\n", " \"transformers_version\": \"4.42.3\",\n", " \"use_cache\": true,\n", " \"use_sliding_window\": false,\n", " \"vocab_size\": 151936\n", "}\n", "\n", "07/06/2024 00:00:56 - INFO - llamafactory.model.model_utils.quantization - Quantizing model to 4 bit with bitsandbytes.\n", "07/06/2024 00:00:56 - INFO - llamafactory.model.patcher - Using KV cache for faster generation.\n", "[INFO|modeling_utils.py:3556] 2024-07-06 00:00:56,669 >> loading weights file model.safetensors from cache at /home/inflaton/.cache/huggingface/hub/models--Qwen--Qwen2-0.5B-Instruct/snapshots/c291d6fce4804a1d39305f388dd32897d1f7acc4/model.safetensors\n", "[INFO|modeling_utils.py:1531] 2024-07-06 00:00:57,733 >> Instantiating Qwen2ForCausalLM model under default dtype torch.bfloat16.\n", "[INFO|configuration_utils.py:1000] 2024-07-06 00:00:57,736 >> Generate config GenerationConfig {\n", " \"bos_token_id\": 151643,\n", " \"eos_token_id\": 151645\n", "}\n", "\n", "[INFO|modeling_utils.py:4364] 2024-07-06 00:01:23,016 >> All model checkpoint weights were used when initializing Qwen2ForCausalLM.\n", "\n", "[INFO|modeling_utils.py:4372] 2024-07-06 00:01:23,016 >> All the weights of Qwen2ForCausalLM were initialized from the model checkpoint at Qwen/Qwen2-0.5B-Instruct.\n", "If your task is similar to the task the model of the checkpoint was trained on, you can already use Qwen2ForCausalLM for predictions without further training.\n", "[INFO|configuration_utils.py:955] 2024-07-06 00:01:23,305 >> loading configuration file generation_config.json from cache at /home/inflaton/.cache/huggingface/hub/models--Qwen--Qwen2-0.5B-Instruct/snapshots/c291d6fce4804a1d39305f388dd32897d1f7acc4/generation_config.json\n", "[INFO|configuration_utils.py:1000] 2024-07-06 00:01:23,305 >> Generate config GenerationConfig {\n", " \"bos_token_id\": 151643,\n", " \"do_sample\": true,\n", " \"eos_token_id\": [\n", " 151645,\n", " 151643\n", " ],\n", " \"pad_token_id\": 151643,\n", " \"repetition_penalty\": 1.1,\n", " \"temperature\": 0.7,\n", " \"top_k\": 20,\n", " \"top_p\": 0.8\n", "}\n", "\n", "07/06/2024 00:01:23 - INFO - llamafactory.model.model_utils.attention - Using torch SDPA for faster training and inference.\n", "07/06/2024 00:01:23 - INFO - llamafactory.model.adapter - Loaded adapter(s): llama-factory/saves/qwen2-0.5b-bf16/lora/sft/checkpoint-1120\n", "07/06/2024 00:01:23 - INFO - llamafactory.model.loader - all params: 498,431,872\n", "(2) GPU = NVIDIA GeForce RTX 4080 Laptop GPU. Max memory = 11.994 GB.\n", "0.658 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 model: Qwen/Qwen2-0.5B-Instruct\n", " 0%| | 0/1133 [00:00\n", "--------\n", "step 2: Old Geng held his gun up, his eyes narrowed. The trigger crackled and a shower of gold feathers fell from his fingers as he fired his pistol. Crisp thundering sounds rang out, like a clatter of metal against stone.\n", "--------\n", "step 3: Old Geng held his gun up, his eyes narrowed. The trigger crackled and a shower of gold feathers fell from his fingers as he fired his pistol. Crisp thundering sounds rang out, like a clatter of metal against stone.\n", "100%|███████████████████████████████████████| 1133/1133 [29:02<00:00, 1.54s/it]\n", "(3) GPU = NVIDIA GeForce RTX 4080 Laptop GPU. Max memory = 11.994 GB.\n", "6.992 GB of memory reserved.\n", " chinese ... Qwen/Qwen2-0.5B-Instruct_checkpoint-1120\n", "0 老耿端起枪，眯缝起一只三角眼，一搂扳机响了枪，冰雹般的金麻雀劈哩啪啦往下落，铁砂子在柳枝间飞... ... Old Geng held his gun up, his eyes narrowed. T...\n", "\n", "[1 rows x 5 columns]\n", "{'accuracy': 0.00088261253309797, 'correct_ids': [659], 'meteor': 0.31049607994218004, 'bleu_scores': {'bleu': 0.06668675115525585, 'precisions': [0.3681131155533886, 0.1027518944200718, 0.037731568998109644, 0.017020772450833267], 'brevity_penalty': 0.9498953137120124, 'length_ratio': 0.9511096389532958, 'translation_length': 28714, 'reference_length': 30190}, 'rouge_scores': {'rouge1': 0.3479658441183239, 'rouge2': 0.11472239367740286, 'rougeL': 0.2868370512147882, 'rougeLsum': 0.2867332633148184}}\n", "Epoch 3\n", "loading env vars from: /home/inflaton/code/projects/courses/llm-finetuning/.env\n", "Adding /home/inflaton/code/projects/courses/llm-finetuning to sys.path\n", "loading /home/inflaton/code/projects/courses/llm-finetuning/llm_toolkit/translation_utils.py\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", "Qwen/Qwen2-0.5B-Instruct llama-factory/saves/qwen2-0.5b-bf16/lora/sft/checkpoint-1680 False datasets/mac/mac.tsv results/mac-results_lf-r2.csv\n", "(1) GPU = NVIDIA GeForce RTX 4080 Laptop GPU. Max memory = 11.994 GB.\n", "0.0 GB of memory reserved.\n", "loading model: Qwen/Qwen2-0.5B-Instruct\n", "[INFO|tokenization_utils_base.py:2161] 2024-07-06 00:30:45,885 >> loading file vocab.json from cache at /home/inflaton/.cache/huggingface/hub/models--Qwen--Qwen2-0.5B-Instruct/snapshots/c291d6fce4804a1d39305f388dd32897d1f7acc4/vocab.json\n", "[INFO|tokenization_utils_base.py:2161] 2024-07-06 00:30:45,885 >> loading file merges.txt from cache at /home/inflaton/.cache/huggingface/hub/models--Qwen--Qwen2-0.5B-Instruct/snapshots/c291d6fce4804a1d39305f388dd32897d1f7acc4/merges.txt\n", "[INFO|tokenization_utils_base.py:2161] 2024-07-06 00:30:45,885 >> loading file tokenizer.json from cache at /home/inflaton/.cache/huggingface/hub/models--Qwen--Qwen2-0.5B-Instruct/snapshots/c291d6fce4804a1d39305f388dd32897d1f7acc4/tokenizer.json\n", "[INFO|tokenization_utils_base.py:2161] 2024-07-06 00:30:45,885 >> loading file added_tokens.json from cache at None\n", "[INFO|tokenization_utils_base.py:2161] 2024-07-06 00:30:45,885 >> loading file special_tokens_map.json from cache at None\n", "[INFO|tokenization_utils_base.py:2161] 2024-07-06 00:30:45,885 >> loading file tokenizer_config.json from cache at /home/inflaton/.cache/huggingface/hub/models--Qwen--Qwen2-0.5B-Instruct/snapshots/c291d6fce4804a1d39305f388dd32897d1f7acc4/tokenizer_config.json\n", "[WARNING|logging.py:313] 2024-07-06 00:30:46,030 >> Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.\n", "07/06/2024 00:30:46 - INFO - llamafactory.data.template - Replace eos token: <|im_end|>\n", "07/06/2024 00:30:46 - INFO - llamafactory.data.template - Add <|im_start|> to stop words.\n", "[INFO|configuration_utils.py:733] 2024-07-06 00:30:46,401 >> loading configuration file config.json from cache at /home/inflaton/.cache/huggingface/hub/models--Qwen--Qwen2-0.5B-Instruct/snapshots/c291d6fce4804a1d39305f388dd32897d1f7acc4/config.json\n", "[INFO|configuration_utils.py:800] 2024-07-06 00:30:46,402 >> Model config Qwen2Config {\n", " \"_name_or_path\": \"Qwen/Qwen2-0.5B-Instruct\",\n", " \"architectures\": [\n", " \"Qwen2ForCausalLM\"\n", " ],\n", " \"attention_dropout\": 0.0,\n", " \"bos_token_id\": 151643,\n", " \"eos_token_id\": 151645,\n", " \"hidden_act\": \"silu\",\n", " \"hidden_size\": 896,\n", " \"initializer_range\": 0.02,\n", " \"intermediate_size\": 4864,\n", " \"max_position_embeddings\": 32768,\n", " \"max_window_layers\": 24,\n", " \"model_type\": \"qwen2\",\n", " \"num_attention_heads\": 14,\n", " \"num_hidden_layers\": 24,\n", " \"num_key_value_heads\": 2,\n", " \"rms_norm_eps\": 1e-06,\n", " \"rope_theta\": 1000000.0,\n", " \"sliding_window\": 32768,\n", " \"tie_word_embeddings\": true,\n", " \"torch_dtype\": \"bfloat16\",\n", " \"transformers_version\": \"4.42.3\",\n", " \"use_cache\": true,\n", " \"use_sliding_window\": false,\n", " \"vocab_size\": 151936\n", "}\n", "\n", "07/06/2024 00:30:46 - INFO - llamafactory.model.model_utils.quantization - Quantizing model to 4 bit with bitsandbytes.\n", "07/06/2024 00:30:46 - INFO - llamafactory.model.patcher - Using KV cache for faster generation.\n", "[INFO|modeling_utils.py:3556] 2024-07-06 00:30:46,448 >> loading weights file model.safetensors from cache at /home/inflaton/.cache/huggingface/hub/models--Qwen--Qwen2-0.5B-Instruct/snapshots/c291d6fce4804a1d39305f388dd32897d1f7acc4/model.safetensors\n", "[INFO|modeling_utils.py:1531] 2024-07-06 00:30:47,453 >> Instantiating Qwen2ForCausalLM model under default dtype torch.bfloat16.\n", "[INFO|configuration_utils.py:1000] 2024-07-06 00:30:47,456 >> Generate config GenerationConfig {\n", " \"bos_token_id\": 151643,\n", " \"eos_token_id\": 151645\n", "}\n", "\n", "[INFO|modeling_utils.py:4364] 2024-07-06 00:31:12,438 >> All model checkpoint weights were used when initializing Qwen2ForCausalLM.\n", "\n", "[INFO|modeling_utils.py:4372] 2024-07-06 00:31:12,439 >> All the weights of Qwen2ForCausalLM were initialized from the model checkpoint at Qwen/Qwen2-0.5B-Instruct.\n", "If your task is similar to the task the model of the checkpoint was trained on, you can already use Qwen2ForCausalLM for predictions without further training.\n", "[INFO|configuration_utils.py:955] 2024-07-06 00:31:12,728 >> loading configuration file generation_config.json from cache at /home/inflaton/.cache/huggingface/hub/models--Qwen--Qwen2-0.5B-Instruct/snapshots/c291d6fce4804a1d39305f388dd32897d1f7acc4/generation_config.json\n", "[INFO|configuration_utils.py:1000] 2024-07-06 00:31:12,729 >> Generate config GenerationConfig {\n", " \"bos_token_id\": 151643,\n", " \"do_sample\": true,\n", " \"eos_token_id\": [\n", " 151645,\n", " 151643\n", " ],\n", " \"pad_token_id\": 151643,\n", " \"repetition_penalty\": 1.1,\n", " \"temperature\": 0.7,\n", " \"top_k\": 20,\n", " \"top_p\": 0.8\n", "}\n", "\n", "07/06/2024 00:31:12 - INFO - llamafactory.model.model_utils.attention - Using torch SDPA for faster training and inference.\n", "07/06/2024 00:31:13 - INFO - llamafactory.model.adapter - Loaded adapter(s): llama-factory/saves/qwen2-0.5b-bf16/lora/sft/checkpoint-1680\n", "07/06/2024 00:31:13 - INFO - llamafactory.model.loader - all params: 498,431,872\n", "(2) GPU = NVIDIA GeForce RTX 4080 Laptop GPU. Max memory = 11.994 GB.\n", "0.658 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 model: Qwen/Qwen2-0.5B-Instruct\n", " 0%| | 0/1133 [00:00\n", "--------\n", "step 2: Old Geng took his pistol from his holster and raised a pair of triangular eyes. The barrel started firing, and the hammer clicked. A shower of gold sparrows fell down like hailstones on the ground, cracking and clattering as though they were being thrown by wind.\n", "--------\n", "step 3: Old Geng took his pistol from his holster and raised a pair of triangular eyes. The barrel started firing, and the hammer clicked. A shower of gold sparrows fell down like hailstones on the ground, cracking and clattering as though they were being thrown by wind.\n", "100%|███████████████████████████████████████| 1133/1133 [31:24<00:00, 1.66s/it]\n", "(3) GPU = NVIDIA GeForce RTX 4080 Laptop GPU. Max memory = 11.994 GB.\n", "5.885 GB of memory reserved.\n", " chinese ... Qwen/Qwen2-0.5B-Instruct_checkpoint-1680\n", "0 老耿端起枪，眯缝起一只三角眼，一搂扳机响了枪，冰雹般的金麻雀劈哩啪啦往下落，铁砂子在柳枝间飞... ... Old Geng took his pistol from his holster and ...\n", "\n", "[1 rows x 6 columns]\n", "{'accuracy': 0.0, 'correct_ids': [], 'meteor': 0.3229970135854747, 'bleu_scores': {'bleu': 0.06974645118974397, 'precisions': [0.3523769402767426, 0.10115723608961852, 0.038224802406099184, 0.017367558711086837], 'brevity_penalty': 1.0, 'length_ratio': 1.0221596555150712, 'translation_length': 30859, 'reference_length': 30190}, 'rouge_scores': {'rouge1': 0.35019397498390753, 'rouge2': 0.1213649003504492, 'rougeL': 0.2888414547712551, 'rougeLsum': 0.28908710512654723}}\n", "Epoch 4\n", "loading env vars from: /home/inflaton/code/projects/courses/llm-finetuning/.env\n", "Adding /home/inflaton/code/projects/courses/llm-finetuning to sys.path\n", "loading /home/inflaton/code/projects/courses/llm-finetuning/llm_toolkit/translation_utils.py\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", "Qwen/Qwen2-0.5B-Instruct llama-factory/saves/qwen2-0.5b-bf16/lora/sft/checkpoint-2240 False datasets/mac/mac.tsv results/mac-results_lf-r2.csv\n", "(1) GPU = NVIDIA GeForce RTX 4080 Laptop GPU. Max memory = 11.994 GB.\n", "0.0 GB of memory reserved.\n", "loading model: Qwen/Qwen2-0.5B-Instruct\n", "[INFO|tokenization_utils_base.py:2161] 2024-07-06 01:02:58,401 >> loading file vocab.json from cache at /home/inflaton/.cache/huggingface/hub/models--Qwen--Qwen2-0.5B-Instruct/snapshots/c291d6fce4804a1d39305f388dd32897d1f7acc4/vocab.json\n", "[INFO|tokenization_utils_base.py:2161] 2024-07-06 01:02:58,401 >> loading file merges.txt from cache at /home/inflaton/.cache/huggingface/hub/models--Qwen--Qwen2-0.5B-Instruct/snapshots/c291d6fce4804a1d39305f388dd32897d1f7acc4/merges.txt\n", "[INFO|tokenization_utils_base.py:2161] 2024-07-06 01:02:58,401 >> loading file tokenizer.json from cache at /home/inflaton/.cache/huggingface/hub/models--Qwen--Qwen2-0.5B-Instruct/snapshots/c291d6fce4804a1d39305f388dd32897d1f7acc4/tokenizer.json\n", "[INFO|tokenization_utils_base.py:2161] 2024-07-06 01:02:58,401 >> loading file added_tokens.json from cache at None\n", "[INFO|tokenization_utils_base.py:2161] 2024-07-06 01:02:58,401 >> loading file special_tokens_map.json from cache at None\n", "[INFO|tokenization_utils_base.py:2161] 2024-07-06 01:02:58,401 >> loading file tokenizer_config.json from cache at /home/inflaton/.cache/huggingface/hub/models--Qwen--Qwen2-0.5B-Instruct/snapshots/c291d6fce4804a1d39305f388dd32897d1f7acc4/tokenizer_config.json\n", "[WARNING|logging.py:313] 2024-07-06 01:02:58,564 >> Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.\n", "07/06/2024 01:02:58 - INFO - llamafactory.data.template - Replace eos token: <|im_end|>\n", "07/06/2024 01:02:58 - INFO - llamafactory.data.template - Add <|im_start|> to stop words.\n", "[INFO|configuration_utils.py:733] 2024-07-06 01:02:58,870 >> loading configuration file config.json from cache at /home/inflaton/.cache/huggingface/hub/models--Qwen--Qwen2-0.5B-Instruct/snapshots/c291d6fce4804a1d39305f388dd32897d1f7acc4/config.json\n", "[INFO|configuration_utils.py:800] 2024-07-06 01:02:58,871 >> Model config Qwen2Config {\n", " \"_name_or_path\": \"Qwen/Qwen2-0.5B-Instruct\",\n", " \"architectures\": [\n", " \"Qwen2ForCausalLM\"\n", " ],\n", " \"attention_dropout\": 0.0,\n", " \"bos_token_id\": 151643,\n", " \"eos_token_id\": 151645,\n", " \"hidden_act\": \"silu\",\n", " \"hidden_size\": 896,\n", " \"initializer_range\": 0.02,\n", " \"intermediate_size\": 4864,\n", " \"max_position_embeddings\": 32768,\n", " \"max_window_layers\": 24,\n", " \"model_type\": \"qwen2\",\n", " \"num_attention_heads\": 14,\n", " \"num_hidden_layers\": 24,\n", " \"num_key_value_heads\": 2,\n", " \"rms_norm_eps\": 1e-06,\n", " \"rope_theta\": 1000000.0,\n", " \"sliding_window\": 32768,\n", " \"tie_word_embeddings\": true,\n", " \"torch_dtype\": \"bfloat16\",\n", " \"transformers_version\": \"4.42.3\",\n", " \"use_cache\": true,\n", " \"use_sliding_window\": false,\n", " \"vocab_size\": 151936\n", "}\n", "\n", "07/06/2024 01:02:58 - INFO - llamafactory.model.model_utils.quantization - Quantizing model to 4 bit with bitsandbytes.\n", "07/06/2024 01:02:58 - INFO - llamafactory.model.patcher - Using KV cache for faster generation.\n", "[INFO|modeling_utils.py:3556] 2024-07-06 01:02:58,913 >> loading weights file model.safetensors from cache at /home/inflaton/.cache/huggingface/hub/models--Qwen--Qwen2-0.5B-Instruct/snapshots/c291d6fce4804a1d39305f388dd32897d1f7acc4/model.safetensors\n", "[INFO|modeling_utils.py:1531] 2024-07-06 01:02:59,768 >> Instantiating Qwen2ForCausalLM model under default dtype torch.bfloat16.\n", "[INFO|configuration_utils.py:1000] 2024-07-06 01:02:59,771 >> Generate config GenerationConfig {\n", " \"bos_token_id\": 151643,\n", " \"eos_token_id\": 151645\n", "}\n", "\n", "[INFO|modeling_utils.py:4364] 2024-07-06 01:03:25,366 >> All model checkpoint weights were used when initializing Qwen2ForCausalLM.\n", "\n", "[INFO|modeling_utils.py:4372] 2024-07-06 01:03:25,366 >> All the weights of Qwen2ForCausalLM were initialized from the model checkpoint at Qwen/Qwen2-0.5B-Instruct.\n", "If your task is similar to the task the model of the checkpoint was trained on, you can already use Qwen2ForCausalLM for predictions without further training.\n", "[INFO|configuration_utils.py:955] 2024-07-06 01:03:25,684 >> loading configuration file generation_config.json from cache at /home/inflaton/.cache/huggingface/hub/models--Qwen--Qwen2-0.5B-Instruct/snapshots/c291d6fce4804a1d39305f388dd32897d1f7acc4/generation_config.json\n", "[INFO|configuration_utils.py:1000] 2024-07-06 01:03:25,684 >> Generate config GenerationConfig {\n", " \"bos_token_id\": 151643,\n", " \"do_sample\": true,\n", " \"eos_token_id\": [\n", " 151645,\n", " 151643\n", " ],\n", " \"pad_token_id\": 151643,\n", " \"repetition_penalty\": 1.1,\n", " \"temperature\": 0.7,\n", " \"top_k\": 20,\n", " \"top_p\": 0.8\n", "}\n", "\n", "07/06/2024 01:03:25 - INFO - llamafactory.model.model_utils.attention - Using torch SDPA for faster training and inference.\n", "07/06/2024 01:03:26 - INFO - llamafactory.model.adapter - Loaded adapter(s): llama-factory/saves/qwen2-0.5b-bf16/lora/sft/checkpoint-2240\n", "07/06/2024 01:03:26 - INFO - llamafactory.model.loader - all params: 498,431,872\n", "(2) GPU = NVIDIA GeForce RTX 4080 Laptop GPU. Max memory = 11.994 GB.\n", "0.658 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 model: Qwen/Qwen2-0.5B-Instruct\n", " 0%| | 0/1133 [00:00\n", "--------\n", "step 2: Old Geng raised his rifle, narrowed his eyes, and fired. A shot rang out as the bullet flew down from a distant windowpane, hammering the golden sparrows of ice and snow, cracking the leaves on the ground like a hailstorm.\n", "--------\n", "step 3: Old Geng raised his rifle, narrowed his eyes, and fired. A shot rang out as the bullet flew down from a distant windowpane, hammering the golden sparrows of ice and snow, cracking the leaves on the ground like a hailstorm.\n", "100%|███████████████████████████████████████| 1133/1133 [30:51<00:00, 1.63s/it]\n", "(3) GPU = NVIDIA GeForce RTX 4080 Laptop GPU. Max memory = 11.994 GB.\n", "7.842 GB of memory reserved.\n", " chinese ... Qwen/Qwen2-0.5B-Instruct_checkpoint-2240\n", "0 老耿端起枪，眯缝起一只三角眼，一搂扳机响了枪，冰雹般的金麻雀劈哩啪啦往下落，铁砂子在柳枝间飞... ... Old Geng raised his rifle, narrowed his eyes, ...\n", "\n", "[1 rows x 7 columns]\n", "{'accuracy': 0.00176522506619594, 'correct_ids': [147, 555], 'meteor': 0.3162958975982396, 'bleu_scores': {'bleu': 0.07169822392654703, 'precisions': [0.3574799511567275, 0.10412095447065277, 0.03987872302479044, 0.017803382270953353], 'brevity_penalty': 1.0, 'length_ratio': 1.0036767141437561, 'translation_length': 30301, 'reference_length': 30190}, 'rouge_scores': {'rouge1': 0.34455286773137617, 'rouge2': 0.12246702123907623, 'rougeL': 0.28572160041791167, 'rougeLsum': 0.28540154083752656}}\n", "Epoch 5\n", "loading env vars from: /home/inflaton/code/projects/courses/llm-finetuning/.env\n", "Adding /home/inflaton/code/projects/courses/llm-finetuning to sys.path\n", "loading /home/inflaton/code/projects/courses/llm-finetuning/llm_toolkit/translation_utils.py\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", "Qwen/Qwen2-0.5B-Instruct llama-factory/saves/qwen2-0.5b-bf16/lora/sft/checkpoint-2800 False datasets/mac/mac.tsv results/mac-results_lf-r2.csv\n", "(1) GPU = NVIDIA GeForce RTX 4080 Laptop GPU. Max memory = 11.994 GB.\n", "0.0 GB of memory reserved.\n", "loading model: Qwen/Qwen2-0.5B-Instruct\n", "[INFO|tokenization_utils_base.py:2161] 2024-07-06 01:34:37,013 >> loading file vocab.json from cache at /home/inflaton/.cache/huggingface/hub/models--Qwen--Qwen2-0.5B-Instruct/snapshots/c291d6fce4804a1d39305f388dd32897d1f7acc4/vocab.json\n", "[INFO|tokenization_utils_base.py:2161] 2024-07-06 01:34:37,013 >> loading file merges.txt from cache at /home/inflaton/.cache/huggingface/hub/models--Qwen--Qwen2-0.5B-Instruct/snapshots/c291d6fce4804a1d39305f388dd32897d1f7acc4/merges.txt\n", "[INFO|tokenization_utils_base.py:2161] 2024-07-06 01:34:37,013 >> loading file tokenizer.json from cache at /home/inflaton/.cache/huggingface/hub/models--Qwen--Qwen2-0.5B-Instruct/snapshots/c291d6fce4804a1d39305f388dd32897d1f7acc4/tokenizer.json\n", "[INFO|tokenization_utils_base.py:2161] 2024-07-06 01:34:37,013 >> loading file added_tokens.json from cache at None\n", "[INFO|tokenization_utils_base.py:2161] 2024-07-06 01:34:37,013 >> loading file special_tokens_map.json from cache at None\n", "[INFO|tokenization_utils_base.py:2161] 2024-07-06 01:34:37,013 >> loading file tokenizer_config.json from cache at /home/inflaton/.cache/huggingface/hub/models--Qwen--Qwen2-0.5B-Instruct/snapshots/c291d6fce4804a1d39305f388dd32897d1f7acc4/tokenizer_config.json\n", "[WARNING|logging.py:313] 2024-07-06 01:34:37,140 >> Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.\n", "07/06/2024 01:34:37 - INFO - llamafactory.data.template - Replace eos token: <|im_end|>\n", "07/06/2024 01:34:37 - INFO - llamafactory.data.template - Add <|im_start|> to stop words.\n", "[INFO|configuration_utils.py:733] 2024-07-06 01:34:37,533 >> loading configuration file config.json from cache at /home/inflaton/.cache/huggingface/hub/models--Qwen--Qwen2-0.5B-Instruct/snapshots/c291d6fce4804a1d39305f388dd32897d1f7acc4/config.json\n", "[INFO|configuration_utils.py:800] 2024-07-06 01:34:37,534 >> Model config Qwen2Config {\n", " \"_name_or_path\": \"Qwen/Qwen2-0.5B-Instruct\",\n", " \"architectures\": [\n", " \"Qwen2ForCausalLM\"\n", " ],\n", " \"attention_dropout\": 0.0,\n", " \"bos_token_id\": 151643,\n", " \"eos_token_id\": 151645,\n", " \"hidden_act\": \"silu\",\n", " \"hidden_size\": 896,\n", " \"initializer_range\": 0.02,\n", " \"intermediate_size\": 4864,\n", " \"max_position_embeddings\": 32768,\n", " \"max_window_layers\": 24,\n", " \"model_type\": \"qwen2\",\n", " \"num_attention_heads\": 14,\n", " \"num_hidden_layers\": 24,\n", " \"num_key_value_heads\": 2,\n", " \"rms_norm_eps\": 1e-06,\n", " \"rope_theta\": 1000000.0,\n", " \"sliding_window\": 32768,\n", " \"tie_word_embeddings\": true,\n", " \"torch_dtype\": \"bfloat16\",\n", " \"transformers_version\": \"4.42.3\",\n", " \"use_cache\": true,\n", " \"use_sliding_window\": false,\n", " \"vocab_size\": 151936\n", "}\n", "\n", "07/06/2024 01:34:37 - INFO - llamafactory.model.model_utils.quantization - Quantizing model to 4 bit with bitsandbytes.\n", "07/06/2024 01:34:37 - INFO - llamafactory.model.patcher - Using KV cache for faster generation.\n", "[INFO|modeling_utils.py:3556] 2024-07-06 01:34:37,582 >> loading weights file model.safetensors from cache at /home/inflaton/.cache/huggingface/hub/models--Qwen--Qwen2-0.5B-Instruct/snapshots/c291d6fce4804a1d39305f388dd32897d1f7acc4/model.safetensors\n", "[INFO|modeling_utils.py:1531] 2024-07-06 01:34:38,570 >> Instantiating Qwen2ForCausalLM model under default dtype torch.bfloat16.\n", "[INFO|configuration_utils.py:1000] 2024-07-06 01:34:38,572 >> Generate config GenerationConfig {\n", " \"bos_token_id\": 151643,\n", " \"eos_token_id\": 151645\n", "}\n", "\n", "[INFO|modeling_utils.py:4364] 2024-07-06 01:35:04,788 >> All model checkpoint weights were used when initializing Qwen2ForCausalLM.\n", "\n", "[INFO|modeling_utils.py:4372] 2024-07-06 01:35:04,788 >> All the weights of Qwen2ForCausalLM were initialized from the model checkpoint at Qwen/Qwen2-0.5B-Instruct.\n", "If your task is similar to the task the model of the checkpoint was trained on, you can already use Qwen2ForCausalLM for predictions without further training.\n", "[INFO|configuration_utils.py:955] 2024-07-06 01:35:05,254 >> loading configuration file generation_config.json from cache at /home/inflaton/.cache/huggingface/hub/models--Qwen--Qwen2-0.5B-Instruct/snapshots/c291d6fce4804a1d39305f388dd32897d1f7acc4/generation_config.json\n", "[INFO|configuration_utils.py:1000] 2024-07-06 01:35:05,254 >> Generate config GenerationConfig {\n", " \"bos_token_id\": 151643,\n", " \"do_sample\": true,\n", " \"eos_token_id\": [\n", " 151645,\n", " 151643\n", " ],\n", " \"pad_token_id\": 151643,\n", " \"repetition_penalty\": 1.1,\n", " \"temperature\": 0.7,\n", " \"top_k\": 20,\n", " \"top_p\": 0.8\n", "}\n", "\n", "07/06/2024 01:35:05 - INFO - llamafactory.model.model_utils.attention - Using torch SDPA for faster training and inference.\n", "07/06/2024 01:35:05 - INFO - llamafactory.model.adapter - Loaded adapter(s): llama-factory/saves/qwen2-0.5b-bf16/lora/sft/checkpoint-2800\n", "07/06/2024 01:35:05 - INFO - llamafactory.model.loader - all params: 498,431,872\n", "(2) GPU = NVIDIA GeForce RTX 4080 Laptop GPU. Max memory = 11.994 GB.\n", "0.658 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 model: Qwen/Qwen2-0.5B-Instruct\n", " 0%| | 0/1133 [00:00\n", "--------\n", "step 2: Old Geng raised his rifle,眯着眼睛，the trigger clicked, a hail of bullets flying down from his fingertips like ice martins screeching with delight. Then came the sound of sand flying, crunching as it flew through the air.\n", "--------\n", "step 3: Old Geng raised his rifle,眯着眼睛，the trigger clicked, a hail of bullets flying down from his fingertips like ice martins screeching with delight. Then came the sound of sand flying, crunching as it flew through the air.\n", "100%|█████████████████████████████████████| 1133/1133 [1:14:52<00:00, 3.97s/it]\n", "(3) GPU = NVIDIA GeForce RTX 4080 Laptop GPU. Max memory = 11.994 GB.\n", "42.277 GB of memory reserved.\n", " chinese ... Qwen/Qwen2-0.5B-Instruct_checkpoint-2800\n", "0 老耿端起枪，眯缝起一只三角眼，一搂扳机响了枪，冰雹般的金麻雀劈哩啪啦往下落，铁砂子在柳枝间飞... ... Old Geng raised his rifle,眯着眼睛，the trigger cli...\n", "\n", "[1 rows x 8 columns]\n", "{'accuracy': 0.00176522506619594, 'correct_ids': [147, 364], 'meteor': 0.31283536857877553, 'bleu_scores': {'bleu': 0.060313705990244354, 'precisions': [0.3079815657779411, 0.08660474354480664, 0.03277549540840986, 0.01513729905548258], 'brevity_penalty': 1.0, 'length_ratio': 1.1715468698244451, 'translation_length': 35369, 'reference_length': 30190}, 'rouge_scores': {'rouge1': 0.34381816601376697, 'rouge2': 0.11947696823377901, 'rougeL': 0.28276793110866827, 'rougeLsum': 0.2825445910163455}}\n", "Epoch 6\n", "loading env vars from: /home/inflaton/code/projects/courses/llm-finetuning/.env\n", "Adding /home/inflaton/code/projects/courses/llm-finetuning to sys.path\n", "loading /home/inflaton/code/projects/courses/llm-finetuning/llm_toolkit/translation_utils.py\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", "Qwen/Qwen2-0.5B-Instruct llama-factory/saves/qwen2-0.5b-bf16/lora/sft/checkpoint-3360 False datasets/mac/mac.tsv results/mac-results_lf-r2.csv\n", "(1) GPU = NVIDIA GeForce RTX 4080 Laptop GPU. Max memory = 11.994 GB.\n", "0.0 GB of memory reserved.\n", "loading model: Qwen/Qwen2-0.5B-Instruct\n", "[INFO|tokenization_utils_base.py:2161] 2024-07-06 02:50:21,290 >> loading file vocab.json from cache at /home/inflaton/.cache/huggingface/hub/models--Qwen--Qwen2-0.5B-Instruct/snapshots/c291d6fce4804a1d39305f388dd32897d1f7acc4/vocab.json\n", "[INFO|tokenization_utils_base.py:2161] 2024-07-06 02:50:21,290 >> loading file merges.txt from cache at /home/inflaton/.cache/huggingface/hub/models--Qwen--Qwen2-0.5B-Instruct/snapshots/c291d6fce4804a1d39305f388dd32897d1f7acc4/merges.txt\n", "[INFO|tokenization_utils_base.py:2161] 2024-07-06 02:50:21,290 >> loading file tokenizer.json from cache at /home/inflaton/.cache/huggingface/hub/models--Qwen--Qwen2-0.5B-Instruct/snapshots/c291d6fce4804a1d39305f388dd32897d1f7acc4/tokenizer.json\n", "[INFO|tokenization_utils_base.py:2161] 2024-07-06 02:50:21,290 >> loading file added_tokens.json from cache at None\n", "[INFO|tokenization_utils_base.py:2161] 2024-07-06 02:50:21,290 >> loading file special_tokens_map.json from cache at None\n", "[INFO|tokenization_utils_base.py:2161] 2024-07-06 02:50:21,290 >> loading file tokenizer_config.json from cache at /home/inflaton/.cache/huggingface/hub/models--Qwen--Qwen2-0.5B-Instruct/snapshots/c291d6fce4804a1d39305f388dd32897d1f7acc4/tokenizer_config.json\n", "[WARNING|logging.py:313] 2024-07-06 02:50:21,413 >> Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.\n", "07/06/2024 02:50:21 - INFO - llamafactory.data.template - Replace eos token: <|im_end|>\n", "07/06/2024 02:50:21 - INFO - llamafactory.data.template - Add <|im_start|> to stop words.\n", "[INFO|configuration_utils.py:733] 2024-07-06 02:50:21,722 >> loading configuration file config.json from cache at /home/inflaton/.cache/huggingface/hub/models--Qwen--Qwen2-0.5B-Instruct/snapshots/c291d6fce4804a1d39305f388dd32897d1f7acc4/config.json\n", "[INFO|configuration_utils.py:800] 2024-07-06 02:50:21,723 >> Model config Qwen2Config {\n", " \"_name_or_path\": \"Qwen/Qwen2-0.5B-Instruct\",\n", " \"architectures\": [\n", " \"Qwen2ForCausalLM\"\n", " ],\n", " \"attention_dropout\": 0.0,\n", " \"bos_token_id\": 151643,\n", " \"eos_token_id\": 151645,\n", " \"hidden_act\": \"silu\",\n", " \"hidden_size\": 896,\n", " \"initializer_range\": 0.02,\n", " \"intermediate_size\": 4864,\n", " \"max_position_embeddings\": 32768,\n", " \"max_window_layers\": 24,\n", " \"model_type\": \"qwen2\",\n", " \"num_attention_heads\": 14,\n", " \"num_hidden_layers\": 24,\n", " \"num_key_value_heads\": 2,\n", " \"rms_norm_eps\": 1e-06,\n", " \"rope_theta\": 1000000.0,\n", " \"sliding_window\": 32768,\n", " \"tie_word_embeddings\": true,\n", " \"torch_dtype\": \"bfloat16\",\n", " \"transformers_version\": \"4.42.3\",\n", " \"use_cache\": true,\n", " \"use_sliding_window\": false,\n", " \"vocab_size\": 151936\n", "}\n", "\n", "07/06/2024 02:50:21 - INFO - llamafactory.model.model_utils.quantization - Quantizing model to 4 bit with bitsandbytes.\n", "07/06/2024 02:50:21 - INFO - llamafactory.model.patcher - Using KV cache for faster generation.\n", "[INFO|modeling_utils.py:3556] 2024-07-06 02:50:21,766 >> loading weights file model.safetensors from cache at /home/inflaton/.cache/huggingface/hub/models--Qwen--Qwen2-0.5B-Instruct/snapshots/c291d6fce4804a1d39305f388dd32897d1f7acc4/model.safetensors\n", "[INFO|modeling_utils.py:1531] 2024-07-06 02:50:22,690 >> Instantiating Qwen2ForCausalLM model under default dtype torch.bfloat16.\n", "[INFO|configuration_utils.py:1000] 2024-07-06 02:50:22,693 >> Generate config GenerationConfig {\n", " \"bos_token_id\": 151643,\n", " \"eos_token_id\": 151645\n", "}\n", "\n", "[INFO|modeling_utils.py:4364] 2024-07-06 02:50:46,315 >> All model checkpoint weights were used when initializing Qwen2ForCausalLM.\n", "\n", "[INFO|modeling_utils.py:4372] 2024-07-06 02:50:46,315 >> All the weights of Qwen2ForCausalLM were initialized from the model checkpoint at Qwen/Qwen2-0.5B-Instruct.\n", "If your task is similar to the task the model of the checkpoint was trained on, you can already use Qwen2ForCausalLM for predictions without further training.\n", "[INFO|configuration_utils.py:955] 2024-07-06 02:50:46,596 >> loading configuration file generation_config.json from cache at /home/inflaton/.cache/huggingface/hub/models--Qwen--Qwen2-0.5B-Instruct/snapshots/c291d6fce4804a1d39305f388dd32897d1f7acc4/generation_config.json\n", "[INFO|configuration_utils.py:1000] 2024-07-06 02:50:46,597 >> Generate config GenerationConfig {\n", " \"bos_token_id\": 151643,\n", " \"do_sample\": true,\n", " \"eos_token_id\": [\n", " 151645,\n", " 151643\n", " ],\n", " \"pad_token_id\": 151643,\n", " \"repetition_penalty\": 1.1,\n", " \"temperature\": 0.7,\n", " \"top_k\": 20,\n", " \"top_p\": 0.8\n", "}\n", "\n", "07/06/2024 02:50:46 - INFO - llamafactory.model.model_utils.attention - Using torch SDPA for faster training and inference.\n", "07/06/2024 02:50:47 - INFO - llamafactory.model.adapter - Loaded adapter(s): llama-factory/saves/qwen2-0.5b-bf16/lora/sft/checkpoint-3360\n", "07/06/2024 02:50:47 - INFO - llamafactory.model.loader - all params: 498,431,872\n", "(2) GPU = NVIDIA GeForce RTX 4080 Laptop GPU. Max memory = 11.994 GB.\n", "0.658 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 model: Qwen/Qwen2-0.5B-Instruct\n", " 0%| | 0/1133 [00:00\n", "--------\n", "step 2: Old Geng held his gun at someone's head, his eyes a bit crooked as he cocked it. The shotgun fired, a deafening bang! followed by ricochet after ricochet of gold-winged sparrows raining down ice pellets on leaves, cracking, cracking. The sandalstick of bullets snapping through the air like a clattering metal drum.\n", "--------\n", "step 3: Old Geng held his gun at someone's head, his eyes a bit crooked as he cocked it. The shotgun fired, a deafening bang! followed by ricochet after ricochet of gold-winged sparrows raining down ice pellets on leaves, cracking, cracking. The sandalstick of bullets snapping through the air like a clattering metal drum.\n", "100%|█████████████████████████████████████| 1133/1133 [1:09:23<00:00, 3.67s/it]\n", "(3) GPU = NVIDIA GeForce RTX 4080 Laptop GPU. Max memory = 11.994 GB.\n", "42.277 GB of memory reserved.\n", " chinese ... Qwen/Qwen2-0.5B-Instruct_checkpoint-3360\n", "0 老耿端起枪，眯缝起一只三角眼，一搂扳机响了枪，冰雹般的金麻雀劈哩啪啦往下落，铁砂子在柳枝间飞... ... Old Geng held his gun at someone's head, his e...\n", "\n", "[1 rows x 9 columns]\n", "{'accuracy': 0.00176522506619594, 'correct_ids': [147, 364], 'meteor': 0.31152790941615477, 'bleu_scores': {'bleu': 0.061326135354300634, 'precisions': [0.31536558706782486, 0.08687895816608687, 0.03332205162918064, 0.015492508766337265], 'brevity_penalty': 1.0, 'length_ratio': 1.1515733686651208, 'translation_length': 34766, 'reference_length': 30190}, 'rouge_scores': {'rouge1': 0.34370850889188637, 'rouge2': 0.11732037461970812, 'rougeL': 0.28244417413163836, 'rougeLsum': 0.2820705045841321}}\n", "CPU times: user 7min 17s, sys: 2min 39s, total: 9min 57s\n", "Wall time: 7h 16min 45s\n" ] } ], "source": [ "%%time\n", "\n", "evaluate_model_all_epochs(\"Qwen/Qwen2-0.5B-Instruct\", num_train_epochs, \"llama-factory/saves/qwen2-0.5b-bf16/lora/sft\", load_in_4bit=False)" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "%%time\n", "\n", "evaluate_model_all_epochs(\"unsloth/qwen2-0.5b-instruct-bnb-4bit\" , num_train_epochs, \"llama-factory/saves/qwen2-0.5b/lora/sft\")" ] }, { "cell_type": "code", "execution_count": 9, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Epoch 0\n", "loading env vars from: /home/inflaton/code/projects/courses/llm-finetuning/.env\n", "Adding /home/inflaton/code/projects/courses/llm-finetuning to sys.path\n", "loading /home/inflaton/code/projects/courses/llm-finetuning/llm_toolkit/translation_utils.py\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", "Qwen/Qwen2-1.5B-Instruct None False datasets/mac/mac.tsv results/mac-results_lf-r2.csv\n", "(1) GPU = NVIDIA GeForce RTX 4080 Laptop GPU. Max memory = 11.994 GB.\n", "0.0 GB of memory reserved.\n", "loading model: Qwen/Qwen2-1.5B-Instruct\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", "1.697 GB of memory reserved.\n", "loading train/test data files\n", "Map: 100%|████████████████████████| 4528/4528 [00:00<00:00, 12597.96 examples/s]\n", "Map: 100%|████████████████████████| 1133/1133 [00:00<00:00, 13985.25 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 model: Qwen/Qwen2-1.5B-Instruct\n", " 0%| | 0/1133 [00:00\n", "--------\n", "step 2: Old耿端起枪，眯缝起一只三角眼，一搂扳机响了枪，冰雹般的金麻雀劈哩啪啦往下落，铁砂子在柳枝间飞迸着，嚓嚓有声。\n", "--------\n", "step 3: Old耿端起枪，眯缝起一只三角眼，一搂扳机响了枪，冰雹般的金麻雀劈哩啪啦往下落，铁砂子在柳枝间飞迸着，嚓嚓有声。\n", "100%|███████████████████████████████████████| 1133/1133 [44:18<00:00, 2.35s/it]\n", "(3) GPU = NVIDIA GeForce RTX 4080 Laptop GPU. Max memory = 11.994 GB.\n", "8.055 GB of memory reserved.\n", " chinese ... Qwen/Qwen2-1.5B-Instruct\n", "0 老耿端起枪，眯缝起一只三角眼，一搂扳机响了枪，冰雹般的金麻雀劈哩啪啦往下落，铁砂子在柳枝间飞... ... Old耿端起枪，眯缝起一只三角眼，一搂扳机响了枪，冰雹般的金麻雀劈哩啪啦往下落，铁砂子在柳枝...\n", "\n", "[1 rows x 10 columns]\n", "{'accuracy': 0.0, 'correct_ids': [], 'meteor': 0.31463018790549185, 'bleu_scores': {'bleu': 0.07617500476658332, 'precisions': [0.4025838638817529, 0.12186115214180207, 0.04992072848489776, 0.022578171594104114], 'brevity_penalty': 0.8833639224944743, 'length_ratio': 0.8896654521364691, 'translation_length': 26859, 'reference_length': 30190}, 'rouge_scores': {'rouge1': 0.37119834139701413, 'rouge2': 0.13281280032592238, 'rougeL': 0.3150444223537181, 'rougeLsum': 0.31529082897505967}}\n", "Epoch 1\n", "loading env vars from: /home/inflaton/code/projects/courses/llm-finetuning/.env\n", "Adding /home/inflaton/code/projects/courses/llm-finetuning to sys.path\n", "loading /home/inflaton/code/projects/courses/llm-finetuning/llm_toolkit/translation_utils.py\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", "Qwen/Qwen2-1.5B-Instruct llama-factory/saves/qwen2-1.5b-bf16/lora/sft/checkpoint-560 False datasets/mac/mac.tsv results/mac-results_lf-r2.csv\n", "(1) GPU = NVIDIA GeForce RTX 4080 Laptop GPU. Max memory = 11.994 GB.\n", "0.0 GB of memory reserved.\n", "loading model: Qwen/Qwen2-1.5B-Instruct\n", "[INFO|tokenization_utils_base.py:2161] 2024-07-06 04:46:07,209 >> loading file vocab.json from cache at /home/inflaton/.cache/huggingface/hub/models--Qwen--Qwen2-1.5B-Instruct/snapshots/ba1cf1846d7df0a0591d6c00649f57e798519da8/vocab.json\n", "[INFO|tokenization_utils_base.py:2161] 2024-07-06 04:46:07,209 >> loading file merges.txt from cache at /home/inflaton/.cache/huggingface/hub/models--Qwen--Qwen2-1.5B-Instruct/snapshots/ba1cf1846d7df0a0591d6c00649f57e798519da8/merges.txt\n", "[INFO|tokenization_utils_base.py:2161] 2024-07-06 04:46:07,209 >> loading file tokenizer.json from cache at /home/inflaton/.cache/huggingface/hub/models--Qwen--Qwen2-1.5B-Instruct/snapshots/ba1cf1846d7df0a0591d6c00649f57e798519da8/tokenizer.json\n", "[INFO|tokenization_utils_base.py:2161] 2024-07-06 04:46:07,209 >> loading file added_tokens.json from cache at None\n", "[INFO|tokenization_utils_base.py:2161] 2024-07-06 04:46:07,209 >> loading file special_tokens_map.json from cache at None\n", "[INFO|tokenization_utils_base.py:2161] 2024-07-06 04:46:07,209 >> loading file tokenizer_config.json from cache at /home/inflaton/.cache/huggingface/hub/models--Qwen--Qwen2-1.5B-Instruct/snapshots/ba1cf1846d7df0a0591d6c00649f57e798519da8/tokenizer_config.json\n", "[WARNING|logging.py:313] 2024-07-06 04:46:07,379 >> Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.\n", "07/06/2024 04:46:07 - INFO - llamafactory.data.template - Replace eos token: <|im_end|>\n", "07/06/2024 04:46:07 - INFO - llamafactory.data.template - Add <|im_start|> to stop words.\n", "[INFO|configuration_utils.py:733] 2024-07-06 04:46:07,705 >> loading configuration file config.json from cache at /home/inflaton/.cache/huggingface/hub/models--Qwen--Qwen2-1.5B-Instruct/snapshots/ba1cf1846d7df0a0591d6c00649f57e798519da8/config.json\n", "[INFO|configuration_utils.py:800] 2024-07-06 04:46:07,706 >> Model config Qwen2Config {\n", " \"_name_or_path\": \"Qwen/Qwen2-1.5B-Instruct\",\n", " \"architectures\": [\n", " \"Qwen2ForCausalLM\"\n", " ],\n", " \"attention_dropout\": 0.0,\n", " \"bos_token_id\": 151643,\n", " \"eos_token_id\": 151645,\n", " \"hidden_act\": \"silu\",\n", " \"hidden_size\": 1536,\n", " \"initializer_range\": 0.02,\n", " \"intermediate_size\": 8960,\n", " \"max_position_embeddings\": 32768,\n", " \"max_window_layers\": 28,\n", " \"model_type\": \"qwen2\",\n", " \"num_attention_heads\": 12,\n", " \"num_hidden_layers\": 28,\n", " \"num_key_value_heads\": 2,\n", " \"rms_norm_eps\": 1e-06,\n", " \"rope_theta\": 1000000.0,\n", " \"sliding_window\": 32768,\n", " \"tie_word_embeddings\": true,\n", " \"torch_dtype\": \"bfloat16\",\n", " \"transformers_version\": \"4.42.3\",\n", " \"use_cache\": true,\n", " \"use_sliding_window\": false,\n", " \"vocab_size\": 151936\n", "}\n", "\n", "07/06/2024 04:46:07 - INFO - llamafactory.model.model_utils.quantization - Quantizing model to 4 bit with bitsandbytes.\n", "07/06/2024 04:46:07 - INFO - llamafactory.model.patcher - Using KV cache for faster generation.\n", "[INFO|modeling_utils.py:3556] 2024-07-06 04:46:07,824 >> loading weights file model.safetensors from cache at /home/inflaton/.cache/huggingface/hub/models--Qwen--Qwen2-1.5B-Instruct/snapshots/ba1cf1846d7df0a0591d6c00649f57e798519da8/model.safetensors\n", "[INFO|modeling_utils.py:1531] 2024-07-06 04:46:10,135 >> Instantiating Qwen2ForCausalLM model under default dtype torch.bfloat16.\n", "[INFO|configuration_utils.py:1000] 2024-07-06 04:46:10,139 >> Generate config GenerationConfig {\n", " \"bos_token_id\": 151643,\n", " \"eos_token_id\": 151645\n", "}\n", "\n", "[INFO|modeling_utils.py:4364] 2024-07-06 04:47:37,722 >> All model checkpoint weights were used when initializing Qwen2ForCausalLM.\n", "\n", "[INFO|modeling_utils.py:4372] 2024-07-06 04:47:37,722 >> All the weights of Qwen2ForCausalLM were initialized from the model checkpoint at Qwen/Qwen2-1.5B-Instruct.\n", "If your task is similar to the task the model of the checkpoint was trained on, you can already use Qwen2ForCausalLM for predictions without further training.\n", "[INFO|configuration_utils.py:955] 2024-07-06 04:47:37,994 >> loading configuration file generation_config.json from cache at /home/inflaton/.cache/huggingface/hub/models--Qwen--Qwen2-1.5B-Instruct/snapshots/ba1cf1846d7df0a0591d6c00649f57e798519da8/generation_config.json\n", "[INFO|configuration_utils.py:1000] 2024-07-06 04:47:37,994 >> Generate config GenerationConfig {\n", " \"bos_token_id\": 151643,\n", " \"do_sample\": true,\n", " \"eos_token_id\": [\n", " 151645,\n", " 151643\n", " ],\n", " \"pad_token_id\": 151643,\n", " \"repetition_penalty\": 1.1,\n", " \"temperature\": 0.7,\n", " \"top_k\": 20,\n", " \"top_p\": 0.8\n", "}\n", "\n", "07/06/2024 04:47:38 - INFO - llamafactory.model.model_utils.attention - Using torch SDPA for faster training and inference.\n", "07/06/2024 04:47:38 - INFO - llamafactory.model.adapter - Loaded adapter(s): llama-factory/saves/qwen2-1.5b-bf16/lora/sft/checkpoint-560\n", "07/06/2024 04:47:38 - INFO - llamafactory.model.loader - all params: 1,552,946,688\n", "(2) GPU = NVIDIA GeForce RTX 4080 Laptop GPU. Max memory = 11.994 GB.\n", "1.689 GB of memory reserved.\n", "loading train/test data files\n", "Map: 100%|████████████████████████| 4528/4528 [00:00<00:00, 28781.97 examples/s]\n", "Map: 100%|█████████████████████████| 1133/1133 [00:00<00:00, 3422.61 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 model: Qwen/Qwen2-1.5B-Instruct\n", " 0%| | 0/1133 [00:00\n", "--------\n", "step 2: Old Geng took up his rifle and squinted through the raindrops with one eye. He squeezed the trigger and a hail of gold sparrows came down from the sky, striking the birches. The sand flew through the air, making a sound like popping popcorn.\n", "--------\n", "step 3: Old Geng took up his rifle and squinted through the raindrops with one eye. He squeezed the trigger and a hail of gold sparrows came down from the sky, striking the birches. The sand flew through the air, making a sound like popping popcorn.\n", "100%|███████████████████████████████████████| 1133/1133 [41:14<00:00, 2.18s/it]\n", "(3) GPU = NVIDIA GeForce RTX 4080 Laptop GPU. Max memory = 11.994 GB.\n", "8.17 GB of memory reserved.\n", " chinese ... Qwen/Qwen2-1.5B-Instruct_checkpoint-560\n", "0 老耿端起枪，眯缝起一只三角眼，一搂扳机响了枪，冰雹般的金麻雀劈哩啪啦往下落，铁砂子在柳枝间飞... ... Old Geng took up his rifle and squinted throug...\n", "\n", "[1 rows x 11 columns]\n", "{'accuracy': 0.00176522506619594, 'correct_ids': [77, 419], 'meteor': 0.3601984358327376, 'bleu_scores': {'bleu': 0.09136211453920208, 'precisions': [0.4177844546982867, 0.13815985684461676, 0.058223709815521135, 0.02853537409427664], 'brevity_penalty': 0.9232339020413112, 'length_ratio': 0.9260351109638953, 'translation_length': 27957, 'reference_length': 30190}, 'rouge_scores': {'rouge1': 0.39835530538706004, 'rouge2': 0.153852117821579, 'rougeL': 0.3364598612963231, 'rougeLsum': 0.3364542798589155}}\n", "Epoch 2\n", "loading env vars from: /home/inflaton/code/projects/courses/llm-finetuning/.env\n", "Adding /home/inflaton/code/projects/courses/llm-finetuning to sys.path\n", "loading /home/inflaton/code/projects/courses/llm-finetuning/llm_toolkit/translation_utils.py\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", "Qwen/Qwen2-1.5B-Instruct llama-factory/saves/qwen2-1.5b-bf16/lora/sft/checkpoint-1120 False datasets/mac/mac.tsv results/mac-results_lf-r2.csv\n", "(1) GPU = NVIDIA GeForce RTX 4080 Laptop GPU. Max memory = 11.994 GB.\n", "0.0 GB of memory reserved.\n", "loading model: Qwen/Qwen2-1.5B-Instruct\n", "[INFO|tokenization_utils_base.py:2161] 2024-07-06 05:29:13,243 >> loading file vocab.json from cache at /home/inflaton/.cache/huggingface/hub/models--Qwen--Qwen2-1.5B-Instruct/snapshots/ba1cf1846d7df0a0591d6c00649f57e798519da8/vocab.json\n", "[INFO|tokenization_utils_base.py:2161] 2024-07-06 05:29:13,243 >> loading file merges.txt from cache at /home/inflaton/.cache/huggingface/hub/models--Qwen--Qwen2-1.5B-Instruct/snapshots/ba1cf1846d7df0a0591d6c00649f57e798519da8/merges.txt\n", "[INFO|tokenization_utils_base.py:2161] 2024-07-06 05:29:13,243 >> loading file tokenizer.json from cache at /home/inflaton/.cache/huggingface/hub/models--Qwen--Qwen2-1.5B-Instruct/snapshots/ba1cf1846d7df0a0591d6c00649f57e798519da8/tokenizer.json\n", "[INFO|tokenization_utils_base.py:2161] 2024-07-06 05:29:13,243 >> loading file added_tokens.json from cache at None\n", "[INFO|tokenization_utils_base.py:2161] 2024-07-06 05:29:13,243 >> loading file special_tokens_map.json from cache at None\n", "[INFO|tokenization_utils_base.py:2161] 2024-07-06 05:29:13,243 >> loading file tokenizer_config.json from cache at /home/inflaton/.cache/huggingface/hub/models--Qwen--Qwen2-1.5B-Instruct/snapshots/ba1cf1846d7df0a0591d6c00649f57e798519da8/tokenizer_config.json\n", "[WARNING|logging.py:313] 2024-07-06 05:29:13,391 >> Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.\n", "07/06/2024 05:29:13 - INFO - llamafactory.data.template - Replace eos token: <|im_end|>\n", "07/06/2024 05:29:13 - INFO - llamafactory.data.template - Add <|im_start|> to stop words.\n", "[INFO|configuration_utils.py:733] 2024-07-06 05:29:13,932 >> loading configuration file config.json from cache at /home/inflaton/.cache/huggingface/hub/models--Qwen--Qwen2-1.5B-Instruct/snapshots/ba1cf1846d7df0a0591d6c00649f57e798519da8/config.json\n", "[INFO|configuration_utils.py:800] 2024-07-06 05:29:13,932 >> Model config Qwen2Config {\n", " \"_name_or_path\": \"Qwen/Qwen2-1.5B-Instruct\",\n", " \"architectures\": [\n", " \"Qwen2ForCausalLM\"\n", " ],\n", " \"attention_dropout\": 0.0,\n", " \"bos_token_id\": 151643,\n", " \"eos_token_id\": 151645,\n", " \"hidden_act\": \"silu\",\n", " \"hidden_size\": 1536,\n", " \"initializer_range\": 0.02,\n", " \"intermediate_size\": 8960,\n", " \"max_position_embeddings\": 32768,\n", " \"max_window_layers\": 28,\n", " \"model_type\": \"qwen2\",\n", " \"num_attention_heads\": 12,\n", " \"num_hidden_layers\": 28,\n", " \"num_key_value_heads\": 2,\n", " \"rms_norm_eps\": 1e-06,\n", " \"rope_theta\": 1000000.0,\n", " \"sliding_window\": 32768,\n", " \"tie_word_embeddings\": true,\n", " \"torch_dtype\": \"bfloat16\",\n", " \"transformers_version\": \"4.42.3\",\n", " \"use_cache\": true,\n", " \"use_sliding_window\": false,\n", " \"vocab_size\": 151936\n", "}\n", "\n", "07/06/2024 05:29:13 - INFO - llamafactory.model.model_utils.quantization - Quantizing model to 4 bit with bitsandbytes.\n", "07/06/2024 05:29:13 - INFO - llamafactory.model.patcher - Using KV cache for faster generation.\n", "[INFO|modeling_utils.py:3556] 2024-07-06 05:29:13,983 >> loading weights file model.safetensors from cache at /home/inflaton/.cache/huggingface/hub/models--Qwen--Qwen2-1.5B-Instruct/snapshots/ba1cf1846d7df0a0591d6c00649f57e798519da8/model.safetensors\n", "[INFO|modeling_utils.py:1531] 2024-07-06 05:29:15,487 >> Instantiating Qwen2ForCausalLM model under default dtype torch.bfloat16.\n", "[INFO|configuration_utils.py:1000] 2024-07-06 05:29:15,490 >> Generate config GenerationConfig {\n", " \"bos_token_id\": 151643,\n", " \"eos_token_id\": 151645\n", "}\n", "\n", "[INFO|modeling_utils.py:4364] 2024-07-06 05:30:36,733 >> All model checkpoint weights were used when initializing Qwen2ForCausalLM.\n", "\n", "[INFO|modeling_utils.py:4372] 2024-07-06 05:30:36,733 >> All the weights of Qwen2ForCausalLM were initialized from the model checkpoint at Qwen/Qwen2-1.5B-Instruct.\n", "If your task is similar to the task the model of the checkpoint was trained on, you can already use Qwen2ForCausalLM for predictions without further training.\n", "[INFO|configuration_utils.py:955] 2024-07-06 05:30:37,009 >> loading configuration file generation_config.json from cache at /home/inflaton/.cache/huggingface/hub/models--Qwen--Qwen2-1.5B-Instruct/snapshots/ba1cf1846d7df0a0591d6c00649f57e798519da8/generation_config.json\n", "[INFO|configuration_utils.py:1000] 2024-07-06 05:30:37,009 >> Generate config GenerationConfig {\n", " \"bos_token_id\": 151643,\n", " \"do_sample\": true,\n", " \"eos_token_id\": [\n", " 151645,\n", " 151643\n", " ],\n", " \"pad_token_id\": 151643,\n", " \"repetition_penalty\": 1.1,\n", " \"temperature\": 0.7,\n", " \"top_k\": 20,\n", " \"top_p\": 0.8\n", "}\n", "\n", "07/06/2024 05:30:37 - INFO - llamafactory.model.model_utils.attention - Using torch SDPA for faster training and inference.\n", "07/06/2024 05:30:37 - INFO - llamafactory.model.adapter - Loaded adapter(s): llama-factory/saves/qwen2-1.5b-bf16/lora/sft/checkpoint-1120\n", "07/06/2024 05:30:37 - INFO - llamafactory.model.loader - all params: 1,552,946,688\n", "(2) GPU = NVIDIA GeForce RTX 4080 Laptop GPU. Max memory = 11.994 GB.\n", "1.689 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 model: Qwen/Qwen2-1.5B-Instruct\n", " 0%| | 0/1133 [00:00\n", "--------\n", "step 2: Old Geng raised his gun, squinted at it through the rain, cocked it, fired, and a hail of golden sparrows fell down on the ground, iron sand whizzing between the branches of the willow trees, making a sound like broken glass.\n", "--------\n", "step 3: Old Geng raised his gun, squinted at it through the rain, cocked it, fired, and a hail of golden sparrows fell down on the ground, iron sand whizzing between the branches of the willow trees, making a sound like broken glass.\n", "100%|███████████████████████████████████████| 1133/1133 [42:38<00:00, 2.26s/it]\n", "(3) GPU = NVIDIA GeForce RTX 4080 Laptop GPU. Max memory = 11.994 GB.\n", "6.896 GB of memory reserved.\n", " chinese ... Qwen/Qwen2-1.5B-Instruct_checkpoint-1120\n", "0 老耿端起枪，眯缝起一只三角眼，一搂扳机响了枪，冰雹般的金麻雀劈哩啪啦往下落，铁砂子在柳枝间飞... ... Old Geng raised his gun, squinted at it throug...\n", "\n", "[1 rows x 12 columns]\n", "{'accuracy': 0.00353045013239188, 'correct_ids': [77, 170, 240, 738], 'meteor': 0.3715145486123948, 'bleu_scores': {'bleu': 0.09990739895468834, 'precisions': [0.41975395678381333, 0.14803935967102363, 0.06454702164336334, 0.0321108263933376], 'brevity_penalty': 0.9378269974960846, 'length_ratio': 0.9396820139118913, 'translation_length': 28369, 'reference_length': 30190}, 'rouge_scores': {'rouge1': 0.407656988217189, 'rouge2': 0.16985073716420096, 'rougeL': 0.34850770823763794, 'rougeLsum': 0.34839716484833966}}\n", "Epoch 3\n", "loading env vars from: /home/inflaton/code/projects/courses/llm-finetuning/.env\n", "Adding /home/inflaton/code/projects/courses/llm-finetuning to sys.path\n", "loading /home/inflaton/code/projects/courses/llm-finetuning/llm_toolkit/translation_utils.py\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", "Qwen/Qwen2-1.5B-Instruct llama-factory/saves/qwen2-1.5b-bf16/lora/sft/checkpoint-1680 False datasets/mac/mac.tsv results/mac-results_lf-r2.csv\n", "(1) GPU = NVIDIA GeForce RTX 4080 Laptop GPU. Max memory = 11.994 GB.\n", "0.0 GB of memory reserved.\n", "loading model: Qwen/Qwen2-1.5B-Instruct\n", "[INFO|tokenization_utils_base.py:2161] 2024-07-06 06:13:37,150 >> loading file vocab.json from cache at /home/inflaton/.cache/huggingface/hub/models--Qwen--Qwen2-1.5B-Instruct/snapshots/ba1cf1846d7df0a0591d6c00649f57e798519da8/vocab.json\n", "[INFO|tokenization_utils_base.py:2161] 2024-07-06 06:13:37,150 >> loading file merges.txt from cache at /home/inflaton/.cache/huggingface/hub/models--Qwen--Qwen2-1.5B-Instruct/snapshots/ba1cf1846d7df0a0591d6c00649f57e798519da8/merges.txt\n", "[INFO|tokenization_utils_base.py:2161] 2024-07-06 06:13:37,150 >> loading file tokenizer.json from cache at /home/inflaton/.cache/huggingface/hub/models--Qwen--Qwen2-1.5B-Instruct/snapshots/ba1cf1846d7df0a0591d6c00649f57e798519da8/tokenizer.json\n", "[INFO|tokenization_utils_base.py:2161] 2024-07-06 06:13:37,150 >> loading file added_tokens.json from cache at None\n", "[INFO|tokenization_utils_base.py:2161] 2024-07-06 06:13:37,150 >> loading file special_tokens_map.json from cache at None\n", "[INFO|tokenization_utils_base.py:2161] 2024-07-06 06:13:37,150 >> loading file tokenizer_config.json from cache at /home/inflaton/.cache/huggingface/hub/models--Qwen--Qwen2-1.5B-Instruct/snapshots/ba1cf1846d7df0a0591d6c00649f57e798519da8/tokenizer_config.json\n", "[WARNING|logging.py:313] 2024-07-06 06:13:37,283 >> Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.\n", "07/06/2024 06:13:37 - INFO - llamafactory.data.template - Replace eos token: <|im_end|>\n", "07/06/2024 06:13:37 - INFO - llamafactory.data.template - Add <|im_start|> to stop words.\n", "[INFO|configuration_utils.py:733] 2024-07-06 06:13:37,654 >> loading configuration file config.json from cache at /home/inflaton/.cache/huggingface/hub/models--Qwen--Qwen2-1.5B-Instruct/snapshots/ba1cf1846d7df0a0591d6c00649f57e798519da8/config.json\n", "[INFO|configuration_utils.py:800] 2024-07-06 06:13:37,655 >> Model config Qwen2Config {\n", " \"_name_or_path\": \"Qwen/Qwen2-1.5B-Instruct\",\n", " \"architectures\": [\n", " \"Qwen2ForCausalLM\"\n", " ],\n", " \"attention_dropout\": 0.0,\n", " \"bos_token_id\": 151643,\n", " \"eos_token_id\": 151645,\n", " \"hidden_act\": \"silu\",\n", " \"hidden_size\": 1536,\n", " \"initializer_range\": 0.02,\n", " \"intermediate_size\": 8960,\n", " \"max_position_embeddings\": 32768,\n", " \"max_window_layers\": 28,\n", " \"model_type\": \"qwen2\",\n", " \"num_attention_heads\": 12,\n", " \"num_hidden_layers\": 28,\n", " \"num_key_value_heads\": 2,\n", " \"rms_norm_eps\": 1e-06,\n", " \"rope_theta\": 1000000.0,\n", " \"sliding_window\": 32768,\n", " \"tie_word_embeddings\": true,\n", " \"torch_dtype\": \"bfloat16\",\n", " \"transformers_version\": \"4.42.3\",\n", " \"use_cache\": true,\n", " \"use_sliding_window\": false,\n", " \"vocab_size\": 151936\n", "}\n", "\n", "07/06/2024 06:13:37 - INFO - llamafactory.model.model_utils.quantization - Quantizing model to 4 bit with bitsandbytes.\n", "07/06/2024 06:13:37 - INFO - llamafactory.model.patcher - Using KV cache for faster generation.\n", "[INFO|modeling_utils.py:3556] 2024-07-06 06:13:37,796 >> loading weights file model.safetensors from cache at /home/inflaton/.cache/huggingface/hub/models--Qwen--Qwen2-1.5B-Instruct/snapshots/ba1cf1846d7df0a0591d6c00649f57e798519da8/model.safetensors\n", "[INFO|modeling_utils.py:1531] 2024-07-06 06:13:39,400 >> Instantiating Qwen2ForCausalLM model under default dtype torch.bfloat16.\n", "[INFO|configuration_utils.py:1000] 2024-07-06 06:13:39,403 >> Generate config GenerationConfig {\n", " \"bos_token_id\": 151643,\n", " \"eos_token_id\": 151645\n", "}\n", "\n", "[INFO|modeling_utils.py:4364] 2024-07-06 06:14:58,257 >> All model checkpoint weights were used when initializing Qwen2ForCausalLM.\n", "\n", "[INFO|modeling_utils.py:4372] 2024-07-06 06:14:58,257 >> All the weights of Qwen2ForCausalLM were initialized from the model checkpoint at Qwen/Qwen2-1.5B-Instruct.\n", "If your task is similar to the task the model of the checkpoint was trained on, you can already use Qwen2ForCausalLM for predictions without further training.\n", "[INFO|configuration_utils.py:955] 2024-07-06 06:14:58,530 >> loading configuration file generation_config.json from cache at /home/inflaton/.cache/huggingface/hub/models--Qwen--Qwen2-1.5B-Instruct/snapshots/ba1cf1846d7df0a0591d6c00649f57e798519da8/generation_config.json\n", "[INFO|configuration_utils.py:1000] 2024-07-06 06:14:58,530 >> Generate config GenerationConfig {\n", " \"bos_token_id\": 151643,\n", " \"do_sample\": true,\n", " \"eos_token_id\": [\n", " 151645,\n", " 151643\n", " ],\n", " \"pad_token_id\": 151643,\n", " \"repetition_penalty\": 1.1,\n", " \"temperature\": 0.7,\n", " \"top_k\": 20,\n", " \"top_p\": 0.8\n", "}\n", "\n", "07/06/2024 06:14:58 - INFO - llamafactory.model.model_utils.attention - Using torch SDPA for faster training and inference.\n", "07/06/2024 06:14:59 - INFO - llamafactory.model.adapter - Loaded adapter(s): llama-factory/saves/qwen2-1.5b-bf16/lora/sft/checkpoint-1680\n", "07/06/2024 06:14:59 - INFO - llamafactory.model.loader - all params: 1,552,946,688\n", "(2) GPU = NVIDIA GeForce RTX 4080 Laptop GPU. Max memory = 11.994 GB.\n", "1.689 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 model: Qwen/Qwen2-1.5B-Instruct\n", " 0%| | 0/1133 [00:00\n", "--------\n", "step 2: Old Geng took a step forward with his gun raised and fired; a hail of golden sparrows rained down on the ground, while iron pellets flew through the treetops, crackling as they went.\n", "--------\n", "step 3: Old Geng took a step forward with his gun raised and fired; a hail of golden sparrows rained down on the ground, while iron pellets flew through the treetops, crackling as they went.\n", "100%|█████████████████████████████████████| 1133/1133 [4:04:10<00:00, 12.93s/it]\n", "(3) GPU = NVIDIA GeForce RTX 4080 Laptop GPU. Max memory = 11.994 GB.\n", "42.271 GB of memory reserved.\n", " chinese ... Qwen/Qwen2-1.5B-Instruct_checkpoint-1680\n", "0 老耿端起枪，眯缝起一只三角眼，一搂扳机响了枪，冰雹般的金麻雀劈哩啪啦往下落，铁砂子在柳枝间飞... ... Old Geng took a step forward with his gun rais...\n", "\n", "[1 rows x 13 columns]\n", "{'accuracy': 0.00176522506619594, 'correct_ids': [147, 381], 'meteor': 0.3720444789500285, 'bleu_scores': {'bleu': 0.09123009255208808, 'precisions': [0.3641282748922381, 0.1247070745455697, 0.05514681731590357, 0.027662187052322804], 'brevity_penalty': 1.0, 'length_ratio': 1.083504471679364, 'translation_length': 32711, 'reference_length': 30190}, 'rouge_scores': {'rouge1': 0.40494632360158267, 'rouge2': 0.16629962834305784, 'rougeL': 0.3426174581521877, 'rougeLsum': 0.34263145168084297}}\n", "Epoch 4\n", "loading env vars from: /home/inflaton/code/projects/courses/llm-finetuning/.env\n", "Adding /home/inflaton/code/projects/courses/llm-finetuning to sys.path\n", "loading /home/inflaton/code/projects/courses/llm-finetuning/llm_toolkit/translation_utils.py\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", "Qwen/Qwen2-1.5B-Instruct llama-factory/saves/qwen2-1.5b-bf16/lora/sft/checkpoint-2240 False datasets/mac/mac.tsv results/mac-results_lf-r2.csv\n", "(1) GPU = NVIDIA GeForce RTX 4080 Laptop GPU. Max memory = 11.994 GB.\n", "0.0 GB of memory reserved.\n", "loading model: Qwen/Qwen2-1.5B-Instruct\n", "[INFO|tokenization_utils_base.py:2161] 2024-07-06 10:19:42,798 >> loading file vocab.json from cache at /home/inflaton/.cache/huggingface/hub/models--Qwen--Qwen2-1.5B-Instruct/snapshots/ba1cf1846d7df0a0591d6c00649f57e798519da8/vocab.json\n", "[INFO|tokenization_utils_base.py:2161] 2024-07-06 10:19:42,798 >> loading file merges.txt from cache at /home/inflaton/.cache/huggingface/hub/models--Qwen--Qwen2-1.5B-Instruct/snapshots/ba1cf1846d7df0a0591d6c00649f57e798519da8/merges.txt\n", "[INFO|tokenization_utils_base.py:2161] 2024-07-06 10:19:42,798 >> loading file tokenizer.json from cache at /home/inflaton/.cache/huggingface/hub/models--Qwen--Qwen2-1.5B-Instruct/snapshots/ba1cf1846d7df0a0591d6c00649f57e798519da8/tokenizer.json\n", "[INFO|tokenization_utils_base.py:2161] 2024-07-06 10:19:42,798 >> loading file added_tokens.json from cache at None\n", "[INFO|tokenization_utils_base.py:2161] 2024-07-06 10:19:42,798 >> loading file special_tokens_map.json from cache at None\n", "[INFO|tokenization_utils_base.py:2161] 2024-07-06 10:19:42,798 >> loading file tokenizer_config.json from cache at /home/inflaton/.cache/huggingface/hub/models--Qwen--Qwen2-1.5B-Instruct/snapshots/ba1cf1846d7df0a0591d6c00649f57e798519da8/tokenizer_config.json\n", "[WARNING|logging.py:313] 2024-07-06 10:19:42,959 >> Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.\n", "07/06/2024 10:19:42 - INFO - llamafactory.data.template - Replace eos token: <|im_end|>\n", "07/06/2024 10:19:42 - INFO - llamafactory.data.template - Add <|im_start|> to stop words.\n", "[INFO|configuration_utils.py:733] 2024-07-06 10:19:43,246 >> loading configuration file config.json from cache at /home/inflaton/.cache/huggingface/hub/models--Qwen--Qwen2-1.5B-Instruct/snapshots/ba1cf1846d7df0a0591d6c00649f57e798519da8/config.json\n", "[INFO|configuration_utils.py:800] 2024-07-06 10:19:43,246 >> Model config Qwen2Config {\n", " \"_name_or_path\": \"Qwen/Qwen2-1.5B-Instruct\",\n", " \"architectures\": [\n", " \"Qwen2ForCausalLM\"\n", " ],\n", " \"attention_dropout\": 0.0,\n", " \"bos_token_id\": 151643,\n", " \"eos_token_id\": 151645,\n", " \"hidden_act\": \"silu\",\n", " \"hidden_size\": 1536,\n", " \"initializer_range\": 0.02,\n", " \"intermediate_size\": 8960,\n", " \"max_position_embeddings\": 32768,\n", " \"max_window_layers\": 28,\n", " \"model_type\": \"qwen2\",\n", " \"num_attention_heads\": 12,\n", " \"num_hidden_layers\": 28,\n", " \"num_key_value_heads\": 2,\n", " \"rms_norm_eps\": 1e-06,\n", " \"rope_theta\": 1000000.0,\n", " \"sliding_window\": 32768,\n", " \"tie_word_embeddings\": true,\n", " \"torch_dtype\": \"bfloat16\",\n", " \"transformers_version\": \"4.42.3\",\n", " \"use_cache\": true,\n", " \"use_sliding_window\": false,\n", " \"vocab_size\": 151936\n", "}\n", "\n", "07/06/2024 10:19:43 - INFO - llamafactory.model.model_utils.quantization - Quantizing model to 4 bit with bitsandbytes.\n", "07/06/2024 10:19:43 - INFO - llamafactory.model.patcher - Using KV cache for faster generation.\n", "[INFO|modeling_utils.py:3556] 2024-07-06 10:19:43,306 >> loading weights file model.safetensors from cache at /home/inflaton/.cache/huggingface/hub/models--Qwen--Qwen2-1.5B-Instruct/snapshots/ba1cf1846d7df0a0591d6c00649f57e798519da8/model.safetensors\n", "[INFO|modeling_utils.py:1531] 2024-07-06 10:19:44,980 >> Instantiating Qwen2ForCausalLM model under default dtype torch.bfloat16.\n", "[INFO|configuration_utils.py:1000] 2024-07-06 10:19:44,983 >> Generate config GenerationConfig {\n", " \"bos_token_id\": 151643,\n", " \"eos_token_id\": 151645\n", "}\n", "\n", "[INFO|modeling_utils.py:4364] 2024-07-06 10:21:08,496 >> All model checkpoint weights were used when initializing Qwen2ForCausalLM.\n", "\n", "[INFO|modeling_utils.py:4372] 2024-07-06 10:21:08,496 >> All the weights of Qwen2ForCausalLM were initialized from the model checkpoint at Qwen/Qwen2-1.5B-Instruct.\n", "If your task is similar to the task the model of the checkpoint was trained on, you can already use Qwen2ForCausalLM for predictions without further training.\n", "[INFO|configuration_utils.py:955] 2024-07-06 10:21:08,782 >> loading configuration file generation_config.json from cache at /home/inflaton/.cache/huggingface/hub/models--Qwen--Qwen2-1.5B-Instruct/snapshots/ba1cf1846d7df0a0591d6c00649f57e798519da8/generation_config.json\n", "[INFO|configuration_utils.py:1000] 2024-07-06 10:21:08,782 >> Generate config GenerationConfig {\n", " \"bos_token_id\": 151643,\n", " \"do_sample\": true,\n", " \"eos_token_id\": [\n", " 151645,\n", " 151643\n", " ],\n", " \"pad_token_id\": 151643,\n", " \"repetition_penalty\": 1.1,\n", " \"temperature\": 0.7,\n", " \"top_k\": 20,\n", " \"top_p\": 0.8\n", "}\n", "\n", "07/06/2024 10:21:09 - INFO - llamafactory.model.model_utils.attention - Using torch SDPA for faster training and inference.\n", "07/06/2024 10:21:09 - INFO - llamafactory.model.adapter - Loaded adapter(s): llama-factory/saves/qwen2-1.5b-bf16/lora/sft/checkpoint-2240\n", "07/06/2024 10:21:09 - INFO - llamafactory.model.loader - all params: 1,552,946,688\n", "(2) GPU = NVIDIA GeForce RTX 4080 Laptop GPU. Max memory = 11.994 GB.\n", "1.689 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 model: Qwen/Qwen2-1.5B-Instruct\n", " 0%| | 0/1133 [00:00\n", "--------\n", "step 2: Old Geng took up his weapon with a squinted look, raised the butt of the rifle to his lips, squeezed the trigger, and it went off like a bolt from the blue sky: hailstones of lead rain down in all directions, striking branches and scattering sparks.\n", "--------\n", "step 3: Old Geng took up his weapon with a squinted look, raised the butt of the rifle to his lips, squeezed the trigger, and it went off like a bolt from the blue sky: hailstones of lead rain down in all directions, striking branches and scattering sparks.\n", "100%|███████████████████████████████████████| 1133/1133 [45:00<00:00, 2.38s/it]\n", "(3) GPU = NVIDIA GeForce RTX 4080 Laptop GPU. Max memory = 11.994 GB.\n", "7.518 GB of memory reserved.\n", " chinese ... Qwen/Qwen2-1.5B-Instruct_checkpoint-2240\n", "0 老耿端起枪，眯缝起一只三角眼，一搂扳机响了枪，冰雹般的金麻雀劈哩啪啦往下落，铁砂子在柳枝间飞... ... Old Geng took up his weapon with a squinted lo...\n", "\n", "[1 rows x 14 columns]\n", "{'accuracy': 0.00088261253309797, 'correct_ids': [147], 'meteor': 0.36344098311977724, 'bleu_scores': {'bleu': 0.09957396873764404, 'precisions': [0.4061541642259054, 0.13941480206540446, 0.06297652862909255, 0.03238771608069614], 'brevity_penalty': 0.9605193264852147, 'length_ratio': 0.9612785690626036, 'translation_length': 29021, 'reference_length': 30190}, 'rouge_scores': {'rouge1': 0.3947630372166354, 'rouge2': 0.1607957226567645, 'rougeL': 0.33285208707455316, 'rougeLsum': 0.33265174295694383}}\n", "Epoch 5\n", "loading env vars from: /home/inflaton/code/projects/courses/llm-finetuning/.env\n", "Adding /home/inflaton/code/projects/courses/llm-finetuning to sys.path\n", "loading /home/inflaton/code/projects/courses/llm-finetuning/llm_toolkit/translation_utils.py\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", "Qwen/Qwen2-1.5B-Instruct llama-factory/saves/qwen2-1.5b-bf16/lora/sft/checkpoint-2800 False datasets/mac/mac.tsv results/mac-results_lf-r2.csv\n", "(1) GPU = NVIDIA GeForce RTX 4080 Laptop GPU. Max memory = 11.994 GB.\n", "0.0 GB of memory reserved.\n", "loading model: Qwen/Qwen2-1.5B-Instruct\n", "[INFO|tokenization_utils_base.py:2161] 2024-07-06 11:06:31,391 >> loading file vocab.json from cache at /home/inflaton/.cache/huggingface/hub/models--Qwen--Qwen2-1.5B-Instruct/snapshots/ba1cf1846d7df0a0591d6c00649f57e798519da8/vocab.json\n", "[INFO|tokenization_utils_base.py:2161] 2024-07-06 11:06:31,391 >> loading file merges.txt from cache at /home/inflaton/.cache/huggingface/hub/models--Qwen--Qwen2-1.5B-Instruct/snapshots/ba1cf1846d7df0a0591d6c00649f57e798519da8/merges.txt\n", "[INFO|tokenization_utils_base.py:2161] 2024-07-06 11:06:31,391 >> loading file tokenizer.json from cache at /home/inflaton/.cache/huggingface/hub/models--Qwen--Qwen2-1.5B-Instruct/snapshots/ba1cf1846d7df0a0591d6c00649f57e798519da8/tokenizer.json\n", "[INFO|tokenization_utils_base.py:2161] 2024-07-06 11:06:31,391 >> loading file added_tokens.json from cache at None\n", "[INFO|tokenization_utils_base.py:2161] 2024-07-06 11:06:31,391 >> loading file special_tokens_map.json from cache at None\n", "[INFO|tokenization_utils_base.py:2161] 2024-07-06 11:06:31,391 >> loading file tokenizer_config.json from cache at /home/inflaton/.cache/huggingface/hub/models--Qwen--Qwen2-1.5B-Instruct/snapshots/ba1cf1846d7df0a0591d6c00649f57e798519da8/tokenizer_config.json\n", "[WARNING|logging.py:313] 2024-07-06 11:06:31,614 >> Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.\n", "07/06/2024 11:06:31 - INFO - llamafactory.data.template - Replace eos token: <|im_end|>\n", "07/06/2024 11:06:31 - INFO - llamafactory.data.template - Add <|im_start|> to stop words.\n", "[INFO|configuration_utils.py:733] 2024-07-06 11:06:31,925 >> loading configuration file config.json from cache at /home/inflaton/.cache/huggingface/hub/models--Qwen--Qwen2-1.5B-Instruct/snapshots/ba1cf1846d7df0a0591d6c00649f57e798519da8/config.json\n", "[INFO|configuration_utils.py:800] 2024-07-06 11:06:31,925 >> Model config Qwen2Config {\n", " \"_name_or_path\": \"Qwen/Qwen2-1.5B-Instruct\",\n", " \"architectures\": [\n", " \"Qwen2ForCausalLM\"\n", " ],\n", " \"attention_dropout\": 0.0,\n", " \"bos_token_id\": 151643,\n", " \"eos_token_id\": 151645,\n", " \"hidden_act\": \"silu\",\n", " \"hidden_size\": 1536,\n", " \"initializer_range\": 0.02,\n", " \"intermediate_size\": 8960,\n", " \"max_position_embeddings\": 32768,\n", " \"max_window_layers\": 28,\n", " \"model_type\": \"qwen2\",\n", " \"num_attention_heads\": 12,\n", " \"num_hidden_layers\": 28,\n", " \"num_key_value_heads\": 2,\n", " \"rms_norm_eps\": 1e-06,\n", " \"rope_theta\": 1000000.0,\n", " \"sliding_window\": 32768,\n", " \"tie_word_embeddings\": true,\n", " \"torch_dtype\": \"bfloat16\",\n", " \"transformers_version\": \"4.42.3\",\n", " \"use_cache\": true,\n", " \"use_sliding_window\": false,\n", " \"vocab_size\": 151936\n", "}\n", "\n", "07/06/2024 11:06:31 - INFO - llamafactory.model.model_utils.quantization - Quantizing model to 4 bit with bitsandbytes.\n", "07/06/2024 11:06:31 - INFO - llamafactory.model.patcher - Using KV cache for faster generation.\n", "[INFO|modeling_utils.py:3556] 2024-07-06 11:06:31,974 >> loading weights file model.safetensors from cache at /home/inflaton/.cache/huggingface/hub/models--Qwen--Qwen2-1.5B-Instruct/snapshots/ba1cf1846d7df0a0591d6c00649f57e798519da8/model.safetensors\n", "[INFO|modeling_utils.py:1531] 2024-07-06 11:06:33,333 >> Instantiating Qwen2ForCausalLM model under default dtype torch.bfloat16.\n", "[INFO|configuration_utils.py:1000] 2024-07-06 11:06:33,337 >> Generate config GenerationConfig {\n", " \"bos_token_id\": 151643,\n", " \"eos_token_id\": 151645\n", "}\n", "\n", "[INFO|modeling_utils.py:4364] 2024-07-06 11:07:51,767 >> All model checkpoint weights were used when initializing Qwen2ForCausalLM.\n", "\n", "[INFO|modeling_utils.py:4372] 2024-07-06 11:07:51,767 >> All the weights of Qwen2ForCausalLM were initialized from the model checkpoint at Qwen/Qwen2-1.5B-Instruct.\n", "If your task is similar to the task the model of the checkpoint was trained on, you can already use Qwen2ForCausalLM for predictions without further training.\n", "[INFO|configuration_utils.py:955] 2024-07-06 11:07:52,244 >> loading configuration file generation_config.json from cache at /home/inflaton/.cache/huggingface/hub/models--Qwen--Qwen2-1.5B-Instruct/snapshots/ba1cf1846d7df0a0591d6c00649f57e798519da8/generation_config.json\n", "[INFO|configuration_utils.py:1000] 2024-07-06 11:07:52,244 >> Generate config GenerationConfig {\n", " \"bos_token_id\": 151643,\n", " \"do_sample\": true,\n", " \"eos_token_id\": [\n", " 151645,\n", " 151643\n", " ],\n", " \"pad_token_id\": 151643,\n", " \"repetition_penalty\": 1.1,\n", " \"temperature\": 0.7,\n", " \"top_k\": 20,\n", " \"top_p\": 0.8\n", "}\n", "\n", "07/06/2024 11:07:52 - INFO - llamafactory.model.model_utils.attention - Using torch SDPA for faster training and inference.\n", "07/06/2024 11:07:53 - INFO - llamafactory.model.adapter - Loaded adapter(s): llama-factory/saves/qwen2-1.5b-bf16/lora/sft/checkpoint-2800\n", "07/06/2024 11:07:53 - INFO - llamafactory.model.loader - all params: 1,552,946,688\n", "(2) GPU = NVIDIA GeForce RTX 4080 Laptop GPU. Max memory = 11.994 GB.\n", "1.689 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 model: Qwen/Qwen2-1.5B-Instruct\n", " 0%| | 0/1133 [00:00\n", "--------\n", "step 2: Old Geng took a step forward, raised his pistol, and squeezed the trigger. The bullets flew like hailstones; tin pellets whistled through the air as they exploded among the willow twigs.\n", "--------\n", "step 3: Old Geng took a step forward, raised his pistol, and squeezed the trigger. The bullets flew like hailstones; tin pellets whistled through the air as they exploded among the willow twigs.\n", "100%|███████████████████████████████████████| 1133/1133 [44:57<00:00, 2.38s/it]\n", "(3) GPU = NVIDIA GeForce RTX 4080 Laptop GPU. Max memory = 11.994 GB.\n", "8.508 GB of memory reserved.\n", " chinese ... Qwen/Qwen2-1.5B-Instruct_checkpoint-2800\n", "0 老耿端起枪，眯缝起一只三角眼，一搂扳机响了枪，冰雹般的金麻雀劈哩啪啦往下落，铁砂子在柳枝间飞... ... Old Geng took a step forward, raised his pisto...\n", "\n", "[1 rows x 15 columns]\n", "{'accuracy': 0.00088261253309797, 'correct_ids': [147], 'meteor': 0.3590942297170212, 'bleu_scores': {'bleu': 0.09721160968740532, 'precisions': [0.3943767957312902, 0.13539479770842971, 0.06072964555835682, 0.031379377055523315], 'brevity_penalty': 0.9678956444152034, 'length_ratio': 0.9684001324942034, 'translation_length': 29236, 'reference_length': 30190}, 'rouge_scores': {'rouge1': 0.3854727479634057, 'rouge2': 0.1555832972124876, 'rougeL': 0.3279226642764544, 'rougeLsum': 0.32816076982382436}}\n", "Epoch 6\n", "loading env vars from: /home/inflaton/code/projects/courses/llm-finetuning/.env\n", "Adding /home/inflaton/code/projects/courses/llm-finetuning to sys.path\n", "loading /home/inflaton/code/projects/courses/llm-finetuning/llm_toolkit/translation_utils.py\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", "Qwen/Qwen2-1.5B-Instruct llama-factory/saves/qwen2-1.5b-bf16/lora/sft/checkpoint-3360 False datasets/mac/mac.tsv results/mac-results_lf-r2.csv\n", "(1) GPU = NVIDIA GeForce RTX 4080 Laptop GPU. Max memory = 11.994 GB.\n", "0.0 GB of memory reserved.\n", "loading model: Qwen/Qwen2-1.5B-Instruct\n", "[INFO|tokenization_utils_base.py:2161] 2024-07-06 11:53:12,406 >> loading file vocab.json from cache at /home/inflaton/.cache/huggingface/hub/models--Qwen--Qwen2-1.5B-Instruct/snapshots/ba1cf1846d7df0a0591d6c00649f57e798519da8/vocab.json\n", "[INFO|tokenization_utils_base.py:2161] 2024-07-06 11:53:12,406 >> loading file merges.txt from cache at /home/inflaton/.cache/huggingface/hub/models--Qwen--Qwen2-1.5B-Instruct/snapshots/ba1cf1846d7df0a0591d6c00649f57e798519da8/merges.txt\n", "[INFO|tokenization_utils_base.py:2161] 2024-07-06 11:53:12,406 >> loading file tokenizer.json from cache at /home/inflaton/.cache/huggingface/hub/models--Qwen--Qwen2-1.5B-Instruct/snapshots/ba1cf1846d7df0a0591d6c00649f57e798519da8/tokenizer.json\n", "[INFO|tokenization_utils_base.py:2161] 2024-07-06 11:53:12,406 >> loading file added_tokens.json from cache at None\n", "[INFO|tokenization_utils_base.py:2161] 2024-07-06 11:53:12,406 >> loading file special_tokens_map.json from cache at None\n", "[INFO|tokenization_utils_base.py:2161] 2024-07-06 11:53:12,406 >> loading file tokenizer_config.json from cache at /home/inflaton/.cache/huggingface/hub/models--Qwen--Qwen2-1.5B-Instruct/snapshots/ba1cf1846d7df0a0591d6c00649f57e798519da8/tokenizer_config.json\n", "[WARNING|logging.py:313] 2024-07-06 11:53:12,531 >> Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.\n", "07/06/2024 11:53:12 - INFO - llamafactory.data.template - Replace eos token: <|im_end|>\n", "07/06/2024 11:53:12 - INFO - llamafactory.data.template - Add <|im_start|> to stop words.\n", "[INFO|configuration_utils.py:733] 2024-07-06 11:53:12,846 >> loading configuration file config.json from cache at /home/inflaton/.cache/huggingface/hub/models--Qwen--Qwen2-1.5B-Instruct/snapshots/ba1cf1846d7df0a0591d6c00649f57e798519da8/config.json\n", "[INFO|configuration_utils.py:800] 2024-07-06 11:53:12,847 >> Model config Qwen2Config {\n", " \"_name_or_path\": \"Qwen/Qwen2-1.5B-Instruct\",\n", " \"architectures\": [\n", " \"Qwen2ForCausalLM\"\n", " ],\n", " \"attention_dropout\": 0.0,\n", " \"bos_token_id\": 151643,\n", " \"eos_token_id\": 151645,\n", " \"hidden_act\": \"silu\",\n", " \"hidden_size\": 1536,\n", " \"initializer_range\": 0.02,\n", " \"intermediate_size\": 8960,\n", " \"max_position_embeddings\": 32768,\n", " \"max_window_layers\": 28,\n", " \"model_type\": \"qwen2\",\n", " \"num_attention_heads\": 12,\n", " \"num_hidden_layers\": 28,\n", " \"num_key_value_heads\": 2,\n", " \"rms_norm_eps\": 1e-06,\n", " \"rope_theta\": 1000000.0,\n", " \"sliding_window\": 32768,\n", " \"tie_word_embeddings\": true,\n", " \"torch_dtype\": \"bfloat16\",\n", " \"transformers_version\": \"4.42.3\",\n", " \"use_cache\": true,\n", " \"use_sliding_window\": false,\n", " \"vocab_size\": 151936\n", "}\n", "\n", "07/06/2024 11:53:12 - INFO - llamafactory.model.model_utils.quantization - Quantizing model to 4 bit with bitsandbytes.\n", "07/06/2024 11:53:12 - INFO - llamafactory.model.patcher - Using KV cache for faster generation.\n", "[INFO|modeling_utils.py:3556] 2024-07-06 11:53:12,906 >> loading weights file model.safetensors from cache at /home/inflaton/.cache/huggingface/hub/models--Qwen--Qwen2-1.5B-Instruct/snapshots/ba1cf1846d7df0a0591d6c00649f57e798519da8/model.safetensors\n", "[INFO|modeling_utils.py:1531] 2024-07-06 11:53:13,748 >> Instantiating Qwen2ForCausalLM model under default dtype torch.bfloat16.\n", "[INFO|configuration_utils.py:1000] 2024-07-06 11:53:13,752 >> Generate config GenerationConfig {\n", " \"bos_token_id\": 151643,\n", " \"eos_token_id\": 151645\n", "}\n", "\n", "[INFO|modeling_utils.py:4364] 2024-07-06 11:54:39,244 >> All model checkpoint weights were used when initializing Qwen2ForCausalLM.\n", "\n", "[INFO|modeling_utils.py:4372] 2024-07-06 11:54:39,244 >> All the weights of Qwen2ForCausalLM were initialized from the model checkpoint at Qwen/Qwen2-1.5B-Instruct.\n", "If your task is similar to the task the model of the checkpoint was trained on, you can already use Qwen2ForCausalLM for predictions without further training.\n", "[INFO|configuration_utils.py:955] 2024-07-06 11:54:39,612 >> loading configuration file generation_config.json from cache at /home/inflaton/.cache/huggingface/hub/models--Qwen--Qwen2-1.5B-Instruct/snapshots/ba1cf1846d7df0a0591d6c00649f57e798519da8/generation_config.json\n", "[INFO|configuration_utils.py:1000] 2024-07-06 11:54:39,612 >> Generate config GenerationConfig {\n", " \"bos_token_id\": 151643,\n", " \"do_sample\": true,\n", " \"eos_token_id\": [\n", " 151645,\n", " 151643\n", " ],\n", " \"pad_token_id\": 151643,\n", " \"repetition_penalty\": 1.1,\n", " \"temperature\": 0.7,\n", " \"top_k\": 20,\n", " \"top_p\": 0.8\n", "}\n", "\n", "07/06/2024 11:54:40 - INFO - llamafactory.model.model_utils.attention - Using torch SDPA for faster training and inference.\n", "07/06/2024 11:54:40 - INFO - llamafactory.model.adapter - Loaded adapter(s): llama-factory/saves/qwen2-1.5b-bf16/lora/sft/checkpoint-3360\n", "07/06/2024 11:54:40 - INFO - llamafactory.model.loader - all params: 1,552,946,688\n", "(2) GPU = NVIDIA GeForce RTX 4080 Laptop GPU. Max memory = 11.994 GB.\n", "1.689 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 model: Qwen/Qwen2-1.5B-Instruct\n", " 0%| | 0/1133 [00:00\n", "--------\n", "step 2: Old Geng took a step forward, lifted his pistol, and squeezed the trigger. A shower of gold-bird pellets flew from the barrel, along with a dozen or so pieces of metal-shrapnel that exploded among the willows.\n", "--------\n", "step 3: Old Geng took a step forward, lifted his pistol, and squeezed the trigger. A shower of gold-bird pellets flew from the barrel, along with a dozen or so pieces of metal-shrapnel that exploded among the willows.\n", "100%|███████████████████████████████████████| 1133/1133 [46:06<00:00, 2.44s/it]\n", "(3) GPU = NVIDIA GeForce RTX 4080 Laptop GPU. Max memory = 11.994 GB.\n", "7.359 GB of memory reserved.\n", " chinese ... Qwen/Qwen2-1.5B-Instruct_checkpoint-3360\n", "0 老耿端起枪，眯缝起一只三角眼，一搂扳机响了枪，冰雹般的金麻雀劈哩啪啦往下落，铁砂子在柳枝间飞... ... Old Geng took a step forward, lifted his pisto...\n", "\n", "[1 rows x 16 columns]\n", "{'accuracy': 0.00088261253309797, 'correct_ids': [199], 'meteor': 0.3486547719340687, 'bleu_scores': {'bleu': 0.0936397309436105, 'precisions': [0.3901145886779545, 0.12895879296847199, 0.05791835069895065, 0.03006965944272446], 'brevity_penalty': 0.9678614572628684, 'length_ratio': 0.9683670089433587, 'translation_length': 29235, 'reference_length': 30190}, 'rouge_scores': {'rouge1': 0.3811393635601209, 'rouge2': 0.1492043203557439, 'rougeL': 0.3217330341685408, 'rougeLsum': 0.32214344841265247}}\n", "CPU times: user 8min 37s, sys: 2min 58s, total: 11min 35s\n", "Wall time: 8h 40min 35s\n" ] } ], "source": [ "%%time\n", "\n", "evaluate_model_all_epochs(\"Qwen/Qwen2-1.5B-Instruct\", num_train_epochs, \"llama-factory/saves/qwen2-1.5b-bf16/lora/sft\", load_in_4bit=False)" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "%%time\n", "\n", "evaluate_model_all_epochs(\"unsloth/qwen2-1.5b-instruct-bnb-4bit\" , num_train_epochs, \"llama-factory/saves/qwen2-1.5b/lora/sft\")" ] } ], "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": "3.11.9" }, "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 }