diff --git a/week07_LLM_v1/README.md b/week07_LLM_v1/README.md new file mode 100644 index 0000000..59aab47 --- /dev/null +++ b/week07_LLM_v1/README.md @@ -0,0 +1 @@ +Slides: https://docs.google.com/presentation/d/1zYp365BEJrcO80chc1S-EoJn3VI6hQ7Ry3cr9Yzgkto/edit?usp=sharing \ No newline at end of file diff --git a/week08_LLM_v2/README.md b/week08_LLM_v2/README.md new file mode 100644 index 0000000..3518f5f --- /dev/null +++ b/week08_LLM_v2/README.md @@ -0,0 +1 @@ +Slides: https://docs.google.com/presentation/d/1wu2izZPZ_uLBRhkodshVQqknsRqGF9ta1rcMLFYKJFQ/edit?usp=sharing \ No newline at end of file diff --git a/week09_Advanced_techniques_LLM_v1/.ipynb_checkpoints/README-checkpoint.md b/week09_Advanced_techniques_LLM_v1/.ipynb_checkpoints/README-checkpoint.md new file mode 100644 index 0000000..e69de29 diff --git a/week09_Advanced_techniques_LLM_v1/PEFT.ipynb b/week09_Advanced_techniques_LLM_v1/PEFT.ipynb new file mode 100644 index 0000000..eb20e27 --- /dev/null +++ b/week09_Advanced_techniques_LLM_v1/PEFT.ipynb @@ -0,0 +1,6902 @@ +{ + "cells": [ + { + "cell_type": "markdown", + "metadata": { + "id": "aSWEcS2XKgzi" + }, + "source": [ + "# Методы дообучения Больших Языковых Моделей.\n", + "\n", + "\n", + "**Credits: Данный ноутбук основан на наработках курса NLP от ШАД Яндекса** [yandexdataschool/nlp_course](https://github.com/yandexdataschool/nlp_course)" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "7xeRF_hSKgzs", + "colab": { + "base_uri": "https://localhost:8080/" + }, + "outputId": "f6a61edb-0d7b-4e7a-c61f-e03ff1a4d0fd" + }, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "Requirement already satisfied: transformers in /usr/local/lib/python3.10/dist-packages (4.44.2)\n", + "Requirement already satisfied: accelerate in /usr/local/lib/python3.10/dist-packages (0.34.2)\n", + "Requirement already satisfied: sentencepiece in /usr/local/lib/python3.10/dist-packages (0.2.0)\n", + "Requirement already satisfied: optimum in /usr/local/lib/python3.10/dist-packages (1.22.0)\n", + "Requirement already satisfied: peft in /usr/local/lib/python3.10/dist-packages (0.12.0)\n", + "Requirement already satisfied: bitsandbytes in /usr/local/lib/python3.10/dist-packages (0.43.3)\n", + "Requirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from transformers) (3.16.0)\n", + "Requirement already satisfied: huggingface-hub<1.0,>=0.23.2 in /usr/local/lib/python3.10/dist-packages (from transformers) (0.24.6)\n", + "Requirement already satisfied: numpy>=1.17 in /usr/local/lib/python3.10/dist-packages (from transformers) (1.26.4)\n", + "Requirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.10/dist-packages (from transformers) (24.1)\n", + "Requirement already satisfied: pyyaml>=5.1 in /usr/local/lib/python3.10/dist-packages (from transformers) (6.0.2)\n", + "Requirement already satisfied: regex!=2019.12.17 in /usr/local/lib/python3.10/dist-packages (from transformers) (2024.5.15)\n", + "Requirement already satisfied: requests in /usr/local/lib/python3.10/dist-packages (from transformers) (2.32.3)\n", + "Requirement already satisfied: safetensors>=0.4.1 in /usr/local/lib/python3.10/dist-packages (from transformers) (0.4.5)\n", + "Requirement already satisfied: tokenizers<0.20,>=0.19 in /usr/local/lib/python3.10/dist-packages (from transformers) (0.19.1)\n", + "Requirement already satisfied: tqdm>=4.27 in /usr/local/lib/python3.10/dist-packages (from transformers) (4.66.5)\n", + "Requirement already satisfied: psutil in /usr/local/lib/python3.10/dist-packages (from accelerate) (5.9.5)\n", + "Requirement already satisfied: torch>=1.10.0 in /usr/local/lib/python3.10/dist-packages (from accelerate) (2.4.0+cu121)\n", + "Requirement already satisfied: coloredlogs in /usr/local/lib/python3.10/dist-packages (from optimum) (15.0.1)\n", + "Requirement already satisfied: sympy in /usr/local/lib/python3.10/dist-packages (from optimum) (1.13.2)\n", + "Requirement already satisfied: datasets in /usr/local/lib/python3.10/dist-packages (from optimum) (3.0.0)\n", + "Requirement already satisfied: fsspec>=2023.5.0 in /usr/local/lib/python3.10/dist-packages (from huggingface-hub<1.0,>=0.23.2->transformers) (2024.6.1)\n", + "Requirement already satisfied: typing-extensions>=3.7.4.3 in /usr/local/lib/python3.10/dist-packages (from huggingface-hub<1.0,>=0.23.2->transformers) (4.12.2)\n", + "Requirement already satisfied: networkx in /usr/local/lib/python3.10/dist-packages (from torch>=1.10.0->accelerate) (3.3)\n", + "Requirement already satisfied: jinja2 in /usr/local/lib/python3.10/dist-packages (from torch>=1.10.0->accelerate) (3.1.4)\n", + "Requirement already satisfied: protobuf in /usr/local/lib/python3.10/dist-packages (from transformers[sentencepiece]<4.45.0,>=4.29->optimum) (3.20.3)\n", + "Requirement already satisfied: humanfriendly>=9.1 in /usr/local/lib/python3.10/dist-packages (from coloredlogs->optimum) (10.0)\n", + "Requirement already satisfied: pyarrow>=15.0.0 in /usr/local/lib/python3.10/dist-packages (from datasets->optimum) (17.0.0)\n", + "Requirement already satisfied: dill<0.3.9,>=0.3.0 in /usr/local/lib/python3.10/dist-packages (from datasets->optimum) (0.3.8)\n", + "Requirement already satisfied: pandas in /usr/local/lib/python3.10/dist-packages (from datasets->optimum) (2.1.4)\n", + "Requirement already satisfied: xxhash in /usr/local/lib/python3.10/dist-packages (from datasets->optimum) (3.5.0)\n", + "Requirement already satisfied: multiprocess in /usr/local/lib/python3.10/dist-packages (from datasets->optimum) (0.70.16)\n", + "Requirement already satisfied: aiohttp in /usr/local/lib/python3.10/dist-packages (from datasets->optimum) (3.10.5)\n", + "Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/dist-packages (from requests->transformers) (3.3.2)\n", + "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests->transformers) (3.8)\n", + "Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests->transformers) (2.0.7)\n", + "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests->transformers) (2024.8.30)\n", + "Requirement already satisfied: mpmath<1.4,>=1.1.0 in /usr/local/lib/python3.10/dist-packages (from sympy->optimum) (1.3.0)\n", + "Requirement already satisfied: aiohappyeyeballs>=2.3.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets->optimum) (2.4.0)\n", + "Requirement already satisfied: aiosignal>=1.1.2 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets->optimum) (1.3.1)\n", + "Requirement already satisfied: attrs>=17.3.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets->optimum) (24.2.0)\n", + "Requirement already satisfied: frozenlist>=1.1.1 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets->optimum) (1.4.1)\n", + "Requirement already satisfied: multidict<7.0,>=4.5 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets->optimum) (6.0.5)\n", + "Requirement already satisfied: yarl<2.0,>=1.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets->optimum) (1.11.1)\n", + "Requirement already satisfied: async-timeout<5.0,>=4.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets->optimum) (4.0.3)\n", + "Requirement already satisfied: MarkupSafe>=2.0 in /usr/local/lib/python3.10/dist-packages (from jinja2->torch>=1.10.0->accelerate) (2.1.5)\n", + "Requirement already satisfied: python-dateutil>=2.8.2 in /usr/local/lib/python3.10/dist-packages (from pandas->datasets->optimum) (2.8.2)\n", + "Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.10/dist-packages (from pandas->datasets->optimum) (2024.1)\n", + "Requirement already satisfied: tzdata>=2022.1 in /usr/local/lib/python3.10/dist-packages (from pandas->datasets->optimum) (2024.1)\n", + "Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.10/dist-packages (from python-dateutil>=2.8.2->pandas->datasets->optimum) (1.16.0)\n" + ] + } + ], + "source": [ + "%pip install --upgrade transformers accelerate sentencepiece optimum peft bitsandbytes\n", + "\n", + "import torch\n", + "import torch.nn as nn\n", + "import torch.nn.functional as F\n", + "\n", + "import transformers\n", + "from tqdm.auto import tqdm, trange\n", + "\n", + "assert torch.cuda.is_available(), \"you need cuda for this part\"\n", + "device = torch.device(\"cuda\" if torch.cuda.is_available() else \"cpu\")" + ] + }, + { + "cell_type": "code", + "source": [ + "import torch\n", + "from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline\n", + "\n", + "torch.random.manual_seed(0)\n", + "\n", + "model = AutoModelForCausalLM.from_pretrained(\n", + " \"microsoft/Phi-3.5-mini-instruct\",\n", + " device_map=\"cuda\",\n", + " torch_dtype=\"auto\",\n", + " trust_remote_code=True,\n", + ")\n", + "tokenizer = AutoTokenizer.from_pretrained(\"microsoft/Phi-3.5-mini-instruct\")\n", + "\n", + "messages = [\n", + " {\"role\": \"system\", \"content\": \"You are a helpful AI assistant.\"},\n", + " {\"role\": \"user\", \"content\": \"Can you provide ways to eat combinations of bananas and dragonfruits?\"},\n", + " {\"role\": \"assistant\", \"content\": \"Sure! Here are some ways to eat bananas and dragonfruits together: 1. Banana and dragonfruit smoothie: Blend bananas and dragonfruits together with some milk and honey. 2. Banana and dragonfruit salad: Mix sliced bananas and dragonfruits together with some lemon juice and honey.\"},\n", + " {\"role\": \"user\", \"content\": \"What about solving an 2x + 3 = 7 equation?\"},\n", + "]\n", + "\n", + "pipe = pipeline(\n", + " \"text-generation\",\n", + " model=model,\n", + " tokenizer=tokenizer,\n", + ")\n", + "\n", + "generation_args = {\n", + " \"max_new_tokens\": 500,\n", + " \"return_full_text\": False,\n", + " \"temperature\": 0.0,\n", + " \"do_sample\": False,\n", + "}\n", + "\n", + "output = pipe(messages, **generation_args)\n", + "print(output[0]['generated_text'])\n" + ], + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 641, + "referenced_widgets": [ + "aa44911037784664a62eb9f03de76b90", + "b3b060782d434b43a8d807b5b24204e8", + "1c387f8c51c8406da4a31f415fd1aedf", + "372375fd32bd49dda8c2d160cf76e494", + "b4e8c62c961443aeabc53d7ae63adc94", + "0705c1df630f4a658c767b6b5db9d5b5", + "47908a88c9c942f3a9cc5692fa746fa9", + "6df30859057e4ad38dd719e973259eaa", + "b09b9ad7b56845178fa553fa9510af5b", + "8d4ca550a6ef4e8794f4c9ef51e68337", + "e885cf6a6ff34972af62ac79b3029821", + "9d70f17cf7ce444194d8505dd4d5ba40", + "6d753205d6204b518181db6d48b5ca04", + "71caa6cde3ed4534b20f9aeceb6a6825", + "0bc2135a2cb04e85be41dfd4be4d0cf4", + "c1001011ec1d4bac80949b5acdfb3740", + "301598e43eda49189505df7ec71d4680", + "bf1bf67ad63347a4969d44ef48c2e8d0", + "d7edca6998fd469bbb0da2449580c5e8", + "5b21de81dc8847edb6a795109682e702", + "6326bd94c4a244d586454a6ed75e0e33", + "afd9ef6838ac4d8f9adcca82df0f4b7e", + "5861525268574fc9941500f9e0885ab7", + "e242fe8690384927ac08cb6cefc951f0", + "38c50a52882e4df88600def974336eca", + "d3395b221f9c453aa5a08d5f186ede4c", + "270ddfca364749a1ab5626586c9b26a0", + "f7334d70f1b44cf6bb3675960a7234fa", + "34e1107c8e07495bb5700a3357333b9c", + "f65e1abe249e42569513a68fe9e25454", + "8dfaf0e7da6a4c41bbf7d75436e05f56", + "1ceeba93c14240208acf65bcaafb749c", + "8a298dcdc74a4e2d802cbf2b903714cc", + "90b7c9102a7b499c87b2e83f2a881f70", + "46cec79f77644a2ca9968f08320fbe1e", + "487dd0246e2345eb9cb1e682a926dfe4", + "0c4561867a8e486cb780099d71a7cb74", + "fb2707fdb16744abb57a2cdd206d652d", + "5cfbc5c3f4bf4309b6987e0e4b06ac6c", + "13574814004e42698a0b96192504bc11", + "73969e68faff4548a40a7244e2c92a94", + "88eb6b8ad47840d788f61f11a4065ed7", + "4b4c9324b364478f92e4b1d81eaced10", + "1bca7143149d44118fdc46dce30d9bac", + "ef160425b2924f34981e26037b4882c8", + "aad453caddfd4d1a8a041de187ba1c5b", + "5120a53a9a9c4486b769093ce154c908", + "3e5179b2c8024377bfd0888199d593ca", + "9da5bd672b2d4f028b19ee1f35fd0b0c", + "1a402c1091af4fd39c05d08dfb0a9e7b", + "4b380725519a4f7b81193c03e1eb8027", + "f8803131486d499a8253f6ae20429af4", + "2c8803e4c52840c6a5b2261bcb6ce2d3", + "e11d969b5e3e4d0887917ca6d2aa6d12", + "10cd824052c5443885dbf11375c34b09", + "78a2e1479f5743f1938a012073079728", + "b3a2da8bd47b4c8eb9995068cc967bde", + "345c094bc03941c98ec7bdd59060eb05", + "0fdf7237b90f4e58a9656c3d009ef3ee", + "e70069519f92475e9df45e2a59dc9ad7", + "6116ae88fa2c4b2791f7b059c2e834b5", + "5444556ddc3f4d218967d489b3e21c48", + "dcc46b94429e42468cb830c03524b518", + "1c2f3d1d5b5a4eb8bc15722259e2c592", + "0147f1325a8a44c988c86622a8733a0e", + "43356817fc2b4a01bfdf6f4ed23a0af9", + "5397a8cb15ec43f39a8468adf6a7c9de", + "4915641943824ae2b66a4a3b8631f265", + "6369531e1f764ee5b28944fb4ad4195d", + "a78f0bf1d95f4925bf5f8da2d6287cbb", + "f6c7c1de1a454e5baa8b56729c67e9d8", + "ca3d804bf103468b9b8b3e11e9414a44", + "cc0c819dd8c14666b92f41ed033c82fa", + "077b35dbbd694baeaa24e3751275c092", + "418d8920bf3d45568d04f4c04cd47285", + "a925b7c55d3e492e988bed78fbaebb41", + "b2d3186602304f76bf1e513085012d0c" + ] + }, + "id": "x2W45V4lUT8A", + "outputId": "7b8b7f68-cd0a-4567-b515-b1ef54a7471d" + }, + "execution_count": null, + "outputs": [ + { + "output_type": "stream", + "name": "stderr", + "text": [ + "/usr/local/lib/python3.10/dist-packages/huggingface_hub/utils/_token.py:89: UserWarning: \n", + "The secret `HF_TOKEN` does not exist in your Colab secrets.\n", + "To authenticate with the Hugging Face Hub, create a token in your settings tab (https://huggingface.co/settings/tokens), set it as secret in your Google Colab and restart your session.\n", + "You will be able to reuse this secret in all of your notebooks.\n", + "Please note that authentication is recommended but still optional to access public models or datasets.\n", + " warnings.warn(\n", + "WARNING:transformers_modules.microsoft.Phi-3.5-mini-instruct.ccf028fc8e1b3ab750a7c55b22792f57ba69f216.modeling_phi3:`flash-attention` package not found, consider installing for better performance: No module named 'flash_attn'.\n", + "WARNING:transformers_modules.microsoft.Phi-3.5-mini-instruct.ccf028fc8e1b3ab750a7c55b22792f57ba69f216.modeling_phi3:Current `flash-attention` does not support `window_size`. Either upgrade or use `attn_implementation='eager'`.\n" + ] + }, + { + "output_type": "display_data", + "data": { + "text/plain": [ + "Loading checkpoint shards: 0%| | 0/2 [00:00)\n" + ] + } + ], + "source": [ + "the_truth = \"A quick brown fox did not jump over the lazy dog. Besides, that dog deserved it anyway!\"\n", + "batch = tokenizer(the_truth, return_tensors=\"pt\", return_token_type_ids=False).to(\n", + " device\n", + ")\n", + "outputs = model(**batch)\n", + "\n", + "next_word_logits = outputs.logits[:, :-1]\n", + "true_next_tokens = batch[\"input_ids\"][:, 1:]\n", + "loss = F.cross_entropy(next_word_logits.flatten(0, 1), true_next_tokens.flatten(0, 1))\n", + "\n", + "print(\"Loss:\", loss)" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "amvNufS8WXa0" + }, + "source": [ + "Воспользуемся механизмом prompt-tuning чтобы модель отвечала \"no dog was jumped over today\" на запросы. Статья о [prompt tuning](https://arxiv.org/abs/2104.08691).\n", + "\n", + "![img](https://i.imgur.com/VwNNKnb.png)\n" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "73ZOCFRZWR98" + }, + "outputs": [], + "source": [ + "class WordEmbeddingsWithLearnedPrompts(nn.Module):\n", + " \"\"\"\n", + " To perform prompt tuning, you will need to replace model's original word embeddings with a layer - THIS layer\n", + " - that inserts trainable prompts instead of the first N token embeddings.\"\"\"\n", + "\n", + " def __init__(self, word_embeddings: nn.Embedding, num_prompts: int):\n", + " super().__init__()\n", + " self.original_word_embeddings = word_embeddings\n", + " self.num_prompts = num_prompts\n", + " self.learnable_prompts = nn.Parameter(\n", + " torch.randn(1, num_prompts, word_embeddings.embedding_dim),\n", + " requires_grad=True,\n", + " )\n", + "\n", + " def forward(self, input_ids: torch.LongTensor):\n", + " # input_ids shape: [batch_size, seq length]\n", + " assert input_ids.dtype == torch.int64\n", + " assert input_ids.shape[1] > self.num_prompts\n", + " assert torch.all(\n", + " input_ids[:, : self.num_prompts] == tokenizer.pad_token_id\n", + " ).item(), \"don't forget to prepend several BOS tokens to input_ids\"\n", + "\n", + " # Your task: embed input_ids, but replace the first :num_prompts: tokens with self.learnable_prompts\n", + " # This is because we will prepend :num_prompts: padding tokens at the beginning\n", + "\n", + " # After you are done, you must produce a word embedding vector for each token in input_ids,\n", + " # except that the first :num_prompts: vectors should equal learnable_prompts;\n", + " # any additional vectors after first :num_prompts: ones should be embedded as usual\n", + " # Note: since you're dealing with trainable params, please torch.cat instead of item assignment\n", + "\n", + " # \n", + " output = torch.cat(\n", + " [\n", + " self.learnable_prompts,\n", + " self.original_word_embeddings(input_ids[:, self.num_prompts :]),\n", + " ],\n", + " dim=1,\n", + " )\n", + "\n", + " return output # your_outputs_with_prompts_as_per_instructions_above" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "kxUyUU2uT2f1", + "outputId": "0fe94275-acfd-481e-c42b-653283515ca0" + }, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "Looks legit!\n" + ] + }, + { + "output_type": "stream", + "name": "stderr", + "text": [ + ":17: FutureWarning: `torch.cuda.amp.autocast(args...)` is deprecated. Please use `torch.amp.autocast('cuda', args...)` instead.\n", + " with torch.cuda.amp.autocast():\n" + ] + } + ], + "source": [ + "num_prompts = 16\n", + "test_emb_layer = WordEmbeddingsWithLearnedPrompts(\n", + " model.model.embed_tokens, num_prompts=num_prompts\n", + ").to(device)\n", + "test_input_ids = tokenizer(\"a cat say on a may\", return_tensors=\"pt\")[\"input_ids\"].to(\n", + " device\n", + ")\n", + "\n", + "space_for_prompts = torch.full(\n", + " [len(test_input_ids), num_prompts],\n", + " fill_value=tokenizer.pad_token_id,\n", + " dtype=torch.int64,\n", + " device=device,\n", + ")\n", + "test_inputs_with_prompts = torch.cat([space_for_prompts, test_input_ids], dim=1)\n", + "\n", + "with torch.cuda.amp.autocast():\n", + " test_prompt_embeddings = test_emb_layer(test_inputs_with_prompts)\n", + "\n", + "assert test_prompt_embeddings.shape[:2] == test_inputs_with_prompts.shape\n", + "assert test_prompt_embeddings.shape[-1] == model.config.hidden_size\n", + "assert torch.allclose(\n", + " test_prompt_embeddings[:, :num_prompts], test_emb_layer.learnable_prompts.float()\n", + ")\n", + "assert torch.allclose(\n", + " test_prompt_embeddings[:, num_prompts:],\n", + " model.model.embed_tokens(test_input_ids).float(),\n", + ")\n", + "print(\"Looks legit!\")" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "FbKPgfT-crqW" + }, + "source": [ + "__Работает!__ Давайте посмотрим на результаты." + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "QRe0lpREV49G" + }, + "outputs": [], + "source": [ + "assert isinstance(\n", + " model.model.embed_tokens, nn.Embedding\n", + "), \"you have already replaced the embedding layer. If the replacement is broken, please reload the model\"\n", + "\n", + "model.model.embed_tokens = WordEmbeddingsWithLearnedPrompts(\n", + " model.model.embed_tokens, num_prompts=num_prompts\n", + ").to(device)\n", + "\n", + "opt = torch.optim.Adam([model.model.embed_tokens.learnable_prompts], lr=0.01)" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "xt-mk4HjudKM" + }, + "outputs": [], + "source": [ + "from tqdm.auto import tqdm as tqdma" + ] + }, + { + "cell_type": "code", + "source": [ + "# checking if the model can learn. Change max_steps for proper training\n", + "import datasets\n", + "\n", + "data = datasets.load_dataset(\"Abirate/english_quotes\", split=\"train[:32]\") # 32 lines\n", + "data = data.map(lambda samples: tokenizer(samples[\"quote\"]), batched=True)\n", + "model._hf_peft_config_loaded = True # silence a warning from HF trainer" + ], + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 69, + "referenced_widgets": [ + "228bd4b13ca8471bbe603f6c16996ce9", + "3a3e89622bc8475ab776224a94451304", + "e208dc30c2eb4459bcfb8bded9389f44", + "afd789c0715446bfbca1253ac4b1d7b5", + "594f6dbb7b5b40e5b5fc422077d9f058", + "040c1447189b43a6ac14b68392166e51", + "5d06f93935c5483b8b8d1f49efc7784f", + "16392b2f676d4819a26b57e8cc1607ff", + "d01672815e14428f85403ad1aab0a1f5", + "714028864ef047749950f9e6e25af9d9", + "f40d46b078c54d36821e80bb507e6d43" + ] + }, + "id": "NXDWOo9EXGW8", + "outputId": "5bb789e3-e363-4efe-c936-bd6df827cf7e" + }, + "execution_count": null, + "outputs": [ + { + "output_type": "display_data", + "data": { + "text/plain": [ + "Map: 0%| | 0/32 [00:00)\n", + "Loss: tensor(6.9157, device='cuda:0', grad_fn=)\n", + "Loss: tensor(6.3019, device='cuda:0', grad_fn=)\n", + "Loss: tensor(5.8188, device='cuda:0', grad_fn=)\n", + "Loss: tensor(5.5013, device='cuda:0', grad_fn=)\n", + "Loss: tensor(5.2245, device='cuda:0', grad_fn=)\n", + "Loss: tensor(4.9599, device='cuda:0', grad_fn=)\n", + "Loss: tensor(4.7094, device='cuda:0', grad_fn=)\n", + "Loss: tensor(4.4785, device='cuda:0', grad_fn=)\n", + "Loss: tensor(4.2659, device='cuda:0', grad_fn=)\n", + "Loss: tensor(4.0657, device='cuda:0', grad_fn=)\n", + "Loss: tensor(3.8725, device='cuda:0', grad_fn=)\n", + "Loss: tensor(3.6835, device='cuda:0', grad_fn=)\n", + "Loss: tensor(3.4982, device='cuda:0', grad_fn=)\n", + "Loss: tensor(3.3176, device='cuda:0', grad_fn=)\n", + "Loss: tensor(3.1430, device='cuda:0', grad_fn=)\n", + "Loss: tensor(2.9759, device='cuda:0', grad_fn=)\n", + "Loss: tensor(2.8178, device='cuda:0', grad_fn=)\n", + "Loss: tensor(2.6687, device='cuda:0', grad_fn=)\n", + "Loss: tensor(2.5253, device='cuda:0', grad_fn=)\n", + "Loss: tensor(2.3808, device='cuda:0', grad_fn=)\n", + "Loss: tensor(2.2306, device='cuda:0', grad_fn=)\n", + "Loss: tensor(2.0768, device='cuda:0', grad_fn=)\n", + "Loss: tensor(1.9246, device='cuda:0', grad_fn=)\n", + "Loss: tensor(1.7783, device='cuda:0', grad_fn=)\n", + "Loss: tensor(1.6400, device='cuda:0', grad_fn=)\n", + "Loss: tensor(1.5097, device='cuda:0', grad_fn=)\n", + "Loss: tensor(1.3861, device='cuda:0', grad_fn=)\n", + "Loss: tensor(1.2681, device='cuda:0', grad_fn=)\n", + "Loss: tensor(1.1549, device='cuda:0', grad_fn=)\n", + "Loss: tensor(1.0474, device='cuda:0', grad_fn=)\n", + "Loss: tensor(0.9465, device='cuda:0', grad_fn=)\n", + "Loss: tensor(0.8530, device='cuda:0', grad_fn=)\n", + "Loss: tensor(0.7670, device='cuda:0', grad_fn=)\n", + "Loss: tensor(0.6882, device='cuda:0', grad_fn=)\n", + "Loss: tensor(0.6165, device='cuda:0', grad_fn=)\n", + "Loss: tensor(0.5516, device='cuda:0', grad_fn=)\n", + "Loss: tensor(0.4931, device='cuda:0', grad_fn=)\n", + "Loss: tensor(0.4400, device='cuda:0', grad_fn=)\n", + "Loss: tensor(0.3915, device='cuda:0', grad_fn=)\n", + "Loss: tensor(0.3471, device='cuda:0', grad_fn=)\n", + "Loss: tensor(0.3069, device='cuda:0', grad_fn=)\n", + "Loss: tensor(0.2711, device='cuda:0', grad_fn=)\n", + "Loss: tensor(0.2399, device='cuda:0', grad_fn=)\n", + "Loss: tensor(0.2128, device='cuda:0', grad_fn=)\n", + "Loss: tensor(0.1897, device='cuda:0', grad_fn=)\n", + "Loss: tensor(0.1700, device='cuda:0', grad_fn=)\n", + "Loss: tensor(0.1532, device='cuda:0', grad_fn=)\n", + "Loss: tensor(0.1387, device='cuda:0', grad_fn=)\n", + "Loss: tensor(0.1260, device='cuda:0', grad_fn=)\n", + "Loss: tensor(0.1148, device='cuda:0', grad_fn=)\n", + "Loss: tensor(0.1047, device='cuda:0', grad_fn=)\n", + "Loss: tensor(0.0956, device='cuda:0', grad_fn=)\n", + "Good job!\n" + ] + } + ], + "source": [ + "the_truth = \"A quick brown fox did not jump over the lazy dog. Besides, that dog deserved it anyway!\"\n", + "batch = tokenizer(the_truth, return_tensors=\"pt\", return_token_type_ids=False).to(\n", + " device\n", + ")\n", + "space_for_prompts = torch.full(\n", + " [len(test_input_ids), num_prompts],\n", + " fill_value=tokenizer.pad_token_id,\n", + " dtype=torch.int64,\n", + " device=device,\n", + ")\n", + "batch[\"input_ids\"] = torch.cat([space_for_prompts, batch[\"input_ids\"]], dim=1)\n", + "batch[\"attention_mask\"] = torch.cat(\n", + " [torch.ones_like(space_for_prompts), batch[\"attention_mask\"]], dim=1\n", + ")\n", + "\n", + "for _ in tqdma(range(100)):\n", + " outputs = model(**batch)\n", + " next_word_logits = outputs.logits[:, num_prompts:-1, :]\n", + " true_next_tokens = batch[\"input_ids\"][:, num_prompts + 1 :]\n", + " loss = F.cross_entropy(\n", + " next_word_logits.flatten(0, 1), true_next_tokens.flatten(0, 1)\n", + " )\n", + " print(\"Loss:\", loss)\n", + " loss.backward()\n", + " opt.step()\n", + " opt.zero_grad()\n", + "\n", + " if loss.item() <= 0.1:\n", + " break\n", + "# raise NotImplemented(\"Your task: iteratively train the model to reduce loss using prompt optimizer (opt)\")\n", + "\n", + "\n", + "assert loss.item() <= 0.1\n", + "print(\"Good job!\")" + ] + }, + { + "cell_type": "code", + "source": [ + "# Output: A quick brown fox did not jump over the lazy dog. Besides, that dog deserved it\n" + ], + "metadata": { + "id": "bS7wmrypMf0-" + }, + "execution_count": null, + "outputs": [] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "F7DkWHD-r1Xo", + "outputId": "2303a5f3-d009-41b5-cbc1-03c31e81fa1a" + }, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "\n", + "Output: A quick brown fox did not jump over the lazy dog. Besides, that dog deserved it\n" + ] + } + ], + "source": [ + "prompt = \"A quick brown fox\"\n", + "batch = tokenizer(prompt, return_tensors=\"pt\", return_token_type_ids=False).to(device)\n", + "batch[\"input_ids\"] = torch.cat([space_for_prompts, batch[\"input_ids\"]], dim=1)\n", + "batch[\"attention_mask\"] = torch.cat(\n", + " [torch.ones_like(space_for_prompts), batch[\"attention_mask\"]], dim=1\n", + ")\n", + "\n", + "\n", + "for i in range(15):\n", + " next_token = model(**batch).logits[0, -1].argmax(-1).reshape(1, 1)\n", + " batch[\"input_ids\"] = torch.cat([batch[\"input_ids\"], next_token], dim=-1)\n", + " batch[\"attention_mask\"] = torch.cat(\n", + " [batch[\"attention_mask\"], torch.ones_like(next_token)], dim=-1\n", + " )\n", + "\n", + "print(\n", + " \"\\nOutput:\",\n", + " tokenizer.decode(batch[\"input_ids\"][0, num_prompts:].cpu().numpy().tolist()),\n", + ")\n", + "\n", + "# if you did everything right, the model will deny that the fox jumped over the lazy dog" + ] + }, + { + "cell_type": "code", + "source": [ + "# 1. Invert the words order" + ], + "metadata": { + "id": "phuX4JxVOf2F" + }, + "execution_count": null, + "outputs": [] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "sEkoFNdlshv_" + }, + "source": [ + "### Шаг 1.1 (опциональный): HuggingFace PEFT\n", + "\n", + "HuggingFace также предоставил широко применимый инструмент для дообучения: [`peft`](https://huggingface.co/docs/peft/index). Многие современные техники: prompt-tuning, LoRA и другие.\n", + "\n" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "mqEEpZm2Q4UC" + }, + "outputs": [], + "source": [ + "import peft\n", + "\n", + "assert isinstance(model.model.embed_tokens, nn.Embedding), \"please reload the model\"\n", + "\n", + "peft_config = peft.PromptTuningConfig(\n", + " task_type=peft.TaskType.CAUSAL_LM, num_virtual_tokens=16\n", + ")\n", + "model = peft.get_peft_model(\n", + " model, peft_config\n", + ") # note: for most peft methods, this line also modifies model in-place\n", + "print(\n", + " \"Trainable parameters:\",\n", + " sum(p.numel() for p in model.parameters() if p.requires_grad),\n", + ")\n", + "print(\n", + " \"Total parameters (excluding quantization):\",\n", + " sum(p.numel() for p in model.parameters()),\n", + ")" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "UW54GnzCwVpp" + }, + "outputs": [], + "source": [ + "# Your task: optimize the PEFT-wrapped model to achieve next token prediction loss < 0.1, but this time using PEFT\n", + "# Please note: you no longer need to prepend PAD tokens, but you still need to skip :num_virtual_tokens: first logits.\n", + "# Finally, generate the sentence to make sure that the model learned the truth." + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "71vJ9Mq7w67f" + }, + "outputs": [], + "source": [ + "# Feel free to structure your code as you see fit - as long as it's legible :)" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "uCkpKYjWxfhk" + }, + "source": [ + "### Шаг 2: LoRA\n", + "\n", + "При дообучении для более серьезных задач можно обратиться к линейной алгебре и вспомнить о __ранге матрицы__. Низкоранговые адаптеры на основе матричного разложения описаны в [статье о LoRA](https://arxiv.org/pdf/2106.09685.pdf).\n", + "\n", + "Основная идея заключается в добавлении низкоранговых адаптеров параллельно с существующими линейными слоями:\n", + "
\n", + "\n", + "В оригинальной статье по LoRA адаптеры добавлялись только к матрицам внимания. Тем не менее, [новые работы](https://arxiv.org/abs/2305.14314) показывают, что также полезно применять их и к полносвязным частям.\n", + "\n", + "Для начала реализуем базовый слой LoRA." + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 86, + "referenced_widgets": [ + "ea39322bcc0848f4a1c2d901c9830f20", + "b52e9d8330844d55bfac3f4972d30bf6", + "56c41973b7914eccad4a94c55af1b05d", + "f573f939c02d4e42901abea84496b169", + "be2e5e683e08423093da7dcfd7f90411", + "9638b8a54936477693056621d3f9f3c5", + "cb6958905eef4479a7fe6ed170a27ad6", + "e8492250f4924ec3b01bb7dcad72554a", + "681c7c8a482b470eb460fdfbdfe13d4c", + "398012a6b4ff46f09920684c63eaa4f1", + "c6922c429afa4b73a33a4270eadd36b6" + ] + }, + "id": "8zundaSzx90r", + "outputId": "f51dd070-892d-4054-c312-613a5f82973d" + }, + "outputs": [ + { + "output_type": "stream", + "name": "stderr", + "text": [ + "The `load_in_4bit` and `load_in_8bit` arguments are deprecated and will be removed in the future versions. Please, pass a `BitsAndBytesConfig` object in `quantization_config` argument instead.\n" + ] + }, + { + "output_type": "display_data", + "data": { + "text/plain": [ + "Loading checkpoint shards: 0%| | 0/33 [00:00\n", + " return self.module(input) + torch.matmul(\n", + " torch.matmul(input, self.adapter_A), self.adapter_B\n", + " )" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "tTzOs65JydcS", + "outputId": "591920b4-e018-474a-ea17-8ffb5ea331d7" + }, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "All tests passed!\n" + ] + } + ], + "source": [ + "# test your implementation\n", + "test_linear = nn.Linear(128, 128)\n", + "test_linear.weight.data[...] = torch.eye(128)\n", + "test_adapter = LoRALayer(test_linear, rank=8)\n", + "\n", + "assert torch.allclose(\n", + " test_adapter(torch.ones(1, 1, 128)), test_linear.bias + 1\n", + "), \"please check your forward pass\"\n", + "\n", + "test_adapter.adapter_A.data[...] = torch.linspace(0.1, -0.5, 128 * 8).view(128, 8)\n", + "test_adapter.adapter_B.data[...] = torch.linspace(0.5, -0.1, 128 * 8).view(8, 128)\n", + "test_linear.bias.data[...] = torch.linspace(1.0, -1.0, 128)\n", + "\n", + "dummy_loss = F.mse_loss(\n", + " test_adapter(torch.ones(1, 128) / 128).squeeze(), torch.linspace(-1, 1, 128)\n", + ")\n", + "assert torch.allclose(dummy_loss, torch.tensor(1.3711389), rtol=0, atol=1e-4)\n", + "dummy_loss.backward()\n", + "assert all(\n", + " w.grad is not None for w in [test_adapter.adapter_A, test_adapter.adapter_B]\n", + "), \"some adapter weights have no grad\"\n", + "assert torch.allclose(\n", + " test_adapter.adapter_A.grad.sum(), torch.tensor(-0.60158), rtol=0, atol=1e-4\n", + "), \"bad grad w.r.t. A\"\n", + "assert torch.allclose(\n", + " test_adapter.adapter_B.grad.sum(), torch.tensor(0.9931), rtol=0, atol=1e-4\n", + "), \"bad grad w.r.t. B\"\n", + "# note: bad grad means that your code is different from LoRA paper OR that your code is not autograd-friendly (e.g. no_grad)\n", + "del dummy_loss, test_linear, test_adapter\n", + "print(\"All tests passed!\")" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "tajVTsvLulB6" + }, + "source": [ + "Ниже приведен код, который применяет адаптер LoRA к линейным слоям Q/K/V внимания модели. Модифицировать можно и другие слои:\n", + "* self_attn.o_proj\n", + "* mlp.up_proj, mlp.gate_proj, mlp.down_proj\n", + "* lm_head" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "davyUVEwulB6" + }, + "outputs": [], + "source": [ + "lora_rank = 8\n", + "\n", + "for name, module in model.model.layers.named_modules():\n", + " if \"LlamaDecoderLayer\" in repr(type(module)):\n", + " module.self_attn.q_proj = LoRALayer(module.self_attn.q_proj, rank=lora_rank).to(\n", + " device\n", + " )\n", + " module.self_attn.k_proj = LoRALayer(module.self_attn.k_proj, rank=lora_rank).to(\n", + " device\n", + " )\n", + " module.self_attn.v_proj = LoRALayer(module.self_attn.v_proj, rank=lora_rank).to(\n", + " device\n", + " )\n", + "\n", + "assert (\n", + " sum(isinstance(module, LoRALayer) for module in model.modules()) == 96\n", + ") # for Llama-7B" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "AWzfvc0EulB6", + "outputId": "ab0f3c2d-002b-4176-cdd1-fd81c6f6a546", + "tags": [] + }, + "outputs": [ + { + "output_type": "stream", + "name": "stderr", + "text": [ + ":7: FutureWarning: `torch.cuda.amp.autocast(args...)` is deprecated. Please use `torch.amp.autocast('cuda', args...)` instead.\n", + " with torch.cuda.amp.autocast(dtype=torch.float32):\n" + ] + }, + { + "output_type": "stream", + "name": "stdout", + "text": [ + "Grad check successful, well done!\n" + ] + } + ], + "source": [ + "batch = tokenizer(\n", + " \"This model wants to share its greatest secret:\",\n", + " return_tensors=\"pt\",\n", + " return_token_type_ids=False,\n", + ")\n", + "# test a single training step, make sure we get meaningful gradients\n", + "with torch.cuda.amp.autocast(dtype=torch.float32):\n", + " out = model.forward(**batch)\n", + " (out.logits.norm() / 100).backward()\n", + "\n", + "for i, module in enumerate(model.modules()):\n", + " if isinstance(module, LoRALayer):\n", + " assert module.adapter_B.grad is not None\n", + " assert module.adapter_B.grad.norm().item() > 0\n", + "\n", + "model.zero_grad(set_to_none=True)\n", + "print(\"Grad check successful, well done!\")" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "rjIJ1vkUulB7" + }, + "source": [ + "Приведенный ниже пример показывает, как обучить адаптеры LoRA на небольшом наборе данных." + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 166, + "referenced_widgets": [ + "2565c3d24f524f2ca4c1a3bd40eec3d6", + "e18d8533c7c24b259ea31ee42c439012", + "a8f5353d0a2549609d488f818fda04ce", + "1c632ec373284565af94703bca5f87d8", + "cc114568a65840fa8c92c6da33c31d95", + "0e1b1d6328b448ed9b6f45eaf9cd512d", + "2f4ce07967344f12af5d8576e8048cbc", + "a8f8713bfb3f4bd8947de56cd73759b6", + "6478cee1f71b478c8d970370e1965847", + "6540cb7c618b41ec9c81af7833540112", + "107ed2ed6b4f41b98cbf0a2cd4ed8939", + "dd8167994e5d4d51ab86bef80f7fc866", + "7a256aa44e364199b13ffc9eb27f5706", + "b2c019db47f348f082f725ef87589b6c", + "46b41a1e94674444aa8c3c871f384374", + "164593bc8f9048cabfd3447a40819b05", + "a93a881bd8ec4bac998c650ec6861e64", + "524c2277dd664099bb69085e4953202b", + "ed325721bcad4ecd9022909912ad3f38", + "1106eed2a35c4c268d4c6edf5f85c643", + "4274987d777349c8b1a98cd0b2c8a321", + "90a0d2b5e86141aca5bc64a012085dd0", + "1b9b8035f6c64ba6a80aa2105902cf0f", + "c4c3bfddeee34c93a5ac77f58ad3826c", + "50fdb22658034563b0d02dd6b6d9cad7", + "7c82aabb5ecb460096e461e993085245", + "a86bd2750d044cedacdb710983c49c41", + "59ef4e355eb548c69af3fa43c5cbdee0", + "289364699b0c4117a50b4e23cc8af0a0", + "6c982241db824e3ba20e806269b680b3", + "16ddad2721954475bcbad000f44369cb", + "a5dbe34fea0d41a6b54d777803345929", + "1c69bd5349814dd08fe112a00383b0ce", + "9c4d0b83744d42ffab6d2f74ebfc65e8", + "d286eff453034dc8a15f5e9cb908480a", + "fd88fbd8bfdf438ba3b6b32fdd1b8202", + "aaa976169d564f40b2b1471696c06a15", + "0ccfaf92f4684a219ebb34a6a9108e1d", + "094993c5be3d46a690fbc75e4f217adc", + "fa5420a0d29a4b90bb293be5d205a0da", + "3f91a33f821045639c0b590d749e86f2", + "5849e2fb31d84d2fa9af5457c2b4297d", + "6653eb0b9dfd4f47ac7886eeb7a4fabd", + "960e0f1ee6e6413d8895b3d93ba0d2d4" + ] + }, + "id": "r9mIpntHulB8", + "outputId": "306393cb-86cf-452d-b820-ab46c2065fdc" + }, + "outputs": [ + { + "output_type": "display_data", + "data": { + "text/plain": [ + "README.md: 0%| | 0.00/5.55k [00:00" + ], + "text/html": [ + "\n", + "
\n", + " \n", + " \n", + " [100/100 02:36, Epoch 6.25/7]\n", + "
\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
StepTraining Loss
11.271400
20.377600
31.469400
41.427200
50.851300
61.648700
71.840600
81.271200
90.560300
101.285800
110.391900
120.814100
131.208200
140.620100
151.630200
161.288100
171.077000
180.807400
190.261700
201.101300
211.034600
221.307400
230.340700
241.251600
250.752800
260.354700
270.846100
280.852200
290.975800
300.226400
311.091300
320.916700
331.108600
340.576800
350.768400
360.782500
370.283200
380.310500
390.500100
400.426300
410.636600
420.149300
430.596200
440.758400
450.429600
460.150800
470.405400
480.293400
490.342900
500.565300
510.263700
520.315700
530.260700
540.677900
550.164400
560.498000
570.314000
580.474100
590.568200
600.571300
610.265100
620.075500
630.091500
640.526500
650.063700
660.274400
670.348100
680.351900
690.301400
700.476700
710.329200
720.132300
730.358100
740.195500
750.112500
760.144400
770.307200
780.414900
790.378800
800.362500
810.208600
820.237900
830.064700
840.168300
850.157000
860.145700
870.362700
880.312000
890.159000
900.041800
910.253700
920.109400
930.275400
940.258000
950.236400
960.463600
970.363200
980.031800
990.089100

" + ] + }, + "metadata": {} + }, + { + "output_type": "stream", + "name": "stderr", + "text": [ + "/usr/local/lib/python3.10/dist-packages/transformers/integrations/peft.py:397: FutureWarning: The `active_adapter` method is deprecated and will be removed in a future version.\n", + " warnings.warn(\n" + ] + }, + { + "output_type": "error", + "ename": "UnboundLocalError", + "evalue": "local variable 'active_adapters' referenced before assignment", + "traceback": [ + "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m", + "\u001b[0;31mUnboundLocalError\u001b[0m Traceback (most recent call last)", + "\u001b[0;32m\u001b[0m in \u001b[0;36m\u001b[0;34m()\u001b[0m\n\u001b[1;32m 18\u001b[0m \u001b[0;31m# if you see cache warnings, set `model.config.use_cache = False` to silence them. Please re-enable for inference!\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 19\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 20\u001b[0;31m \u001b[0mtrainer\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mtrain\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 21\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 22\u001b[0m \u001b[0;31m# NOTE: this is just an example! you do not have to wait for this progressbar to finish :)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/transformers/trainer.py\u001b[0m in \u001b[0;36mtrain\u001b[0;34m(self, resume_from_checkpoint, trial, ignore_keys_for_eval, **kwargs)\u001b[0m\n\u001b[1;32m 1936\u001b[0m \u001b[0mhf_hub_utils\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0menable_progress_bars\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1937\u001b[0m \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1938\u001b[0;31m return inner_training_loop(\n\u001b[0m\u001b[1;32m 1939\u001b[0m \u001b[0margs\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1940\u001b[0m \u001b[0mresume_from_checkpoint\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mresume_from_checkpoint\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/transformers/trainer.py\u001b[0m in \u001b[0;36m_inner_training_loop\u001b[0;34m(self, batch_size, args, resume_from_checkpoint, trial, ignore_keys_for_eval)\u001b[0m\n\u001b[1;32m 2354\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcontrol\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcallback_handler\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mon_step_end\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mstate\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcontrol\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 2355\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 2356\u001b[0;31m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_maybe_log_save_evaluate\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mtr_loss\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mgrad_norm\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mmodel\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mtrial\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mepoch\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mignore_keys_for_eval\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 2357\u001b[0m \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 2358\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcontrol\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcallback_handler\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mon_substep_end\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mstate\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcontrol\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/transformers/trainer.py\u001b[0m in \u001b[0;36m_maybe_log_save_evaluate\u001b[0;34m(self, tr_loss, grad_norm, model, trial, epoch, ignore_keys_for_eval)\u001b[0m\n\u001b[1;32m 2805\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 2806\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcontrol\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mshould_save\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 2807\u001b[0;31m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_save_checkpoint\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mmodel\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mtrial\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mmetrics\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mmetrics\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 2808\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcontrol\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcallback_handler\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mon_save\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mstate\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcontrol\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 2809\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/transformers/trainer.py\u001b[0m in \u001b[0;36m_save_checkpoint\u001b[0;34m(self, model, trial, metrics)\u001b[0m\n\u001b[1;32m 2884\u001b[0m \u001b[0mrun_dir\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_get_output_dir\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mtrial\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mtrial\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 2885\u001b[0m \u001b[0moutput_dir\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mos\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mpath\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mjoin\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mrun_dir\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mcheckpoint_folder\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 2886\u001b[0;31m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msave_model\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0moutput_dir\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0m_internal_call\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mTrue\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 2887\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 2888\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msave_only_model\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/transformers/trainer.py\u001b[0m in \u001b[0;36msave_model\u001b[0;34m(self, output_dir, _internal_call)\u001b[0m\n\u001b[1;32m 3452\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 3453\u001b[0m \u001b[0;32melif\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mshould_save\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 3454\u001b[0;31m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_save\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0moutput_dir\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 3455\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 3456\u001b[0m \u001b[0;31m# Push to the Hub when `save_model` is called by the user.\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/transformers/trainer.py\u001b[0m in \u001b[0;36m_save\u001b[0;34m(self, output_dir, state_dict)\u001b[0m\n\u001b[1;32m 3523\u001b[0m \u001b[0mtorch\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msave\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mstate_dict\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mos\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mpath\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mjoin\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0moutput_dir\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mWEIGHTS_NAME\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 3524\u001b[0m \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 3525\u001b[0;31m self.model.save_pretrained(\n\u001b[0m\u001b[1;32m 3526\u001b[0m \u001b[0moutput_dir\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mstate_dict\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mstate_dict\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0msafe_serialization\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msave_safetensors\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 3527\u001b[0m )\n", + "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/transformers/modeling_utils.py\u001b[0m in \u001b[0;36msave_pretrained\u001b[0;34m(self, save_directory, is_main_process, state_dict, save_function, push_to_hub, max_shard_size, safe_serialization, variant, token, save_peft_format, **kwargs)\u001b[0m\n\u001b[1;32m 2597\u001b[0m \u001b[0;34m\"Detected adapters on the model, saving the model in the PEFT format, only adapter weights will be saved.\"\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 2598\u001b[0m )\n\u001b[0;32m-> 2599\u001b[0;31m \u001b[0mstate_dict\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mmodel_to_save\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mget_adapter_state_dict\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 2600\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 2601\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0msave_peft_format\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/transformers/integrations/peft.py\u001b[0m in \u001b[0;36mget_adapter_state_dict\u001b[0;34m(self, adapter_name)\u001b[0m\n\u001b[1;32m 421\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 422\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0madapter_name\u001b[0m \u001b[0;32mis\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 423\u001b[0;31m \u001b[0madapter_name\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mactive_adapter\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 424\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 425\u001b[0m \u001b[0madapter_state_dict\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mget_peft_model_state_dict\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0madapter_name\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0madapter_name\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/transformers/integrations/peft.py\u001b[0m in \u001b[0;36mactive_adapter\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m 399\u001b[0m )\n\u001b[1;32m 400\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 401\u001b[0;31m \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mactive_adapters\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;36m0\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 402\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 403\u001b[0m \u001b[0;32mdef\u001b[0m \u001b[0mget_adapter_state_dict\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0madapter_name\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0mOptional\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mstr\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;34m->\u001b[0m \u001b[0mdict\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/transformers/integrations/peft.py\u001b[0m in \u001b[0;36mactive_adapters\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m 389\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 390\u001b[0m \u001b[0;31m# For previous PEFT versions\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 391\u001b[0;31m \u001b[0;32mif\u001b[0m \u001b[0misinstance\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mactive_adapters\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mstr\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 392\u001b[0m \u001b[0mactive_adapters\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m[\u001b[0m\u001b[0mactive_adapters\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 393\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;31mUnboundLocalError\u001b[0m: local variable 'active_adapters' referenced before assignment" + ] + } + ] + }, + { + "cell_type": "code", + "source": [ + "prompt = \"Если где-то тебе не рады в рваных носках \"\n", + "batch = tokenizer(prompt, return_tensors=\"pt\", return_token_type_ids=False).to(device)\n", + "for i in range(15):\n", + " next_token = model(**batch).logits[0, -1].argmax(-1).reshape(1, 1)\n", + " batch[\"input_ids\"] = torch.cat([batch[\"input_ids\"], next_token], dim=-1)\n", + " batch[\"attention_mask\"] = torch.cat(\n", + " [batch[\"attention_mask\"], torch.ones_like(next_token)], dim=-1\n", + " )\n", + "\n", + "print(\n", + " \"\\nOutput:\",\n", + " tokenizer.decode(batch[\"input_ids\"][0, :].cpu().numpy().tolist()),\n", + ")\n", + "\n", + "# if you did everything right, the model will deny that the fox jumped over the lazy dog" + ], + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "GIHTQGdZR1sD", + "outputId": "fbf03009-c047-486d-f543-11f0f7861fd0" + }, + "execution_count": null, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "\n", + "Output: Если где-то тебе не рады в рваных носках ходить, то в этом году нашлось новое облепие\n" + ] + } + ] + }, + { + "cell_type": "code", + "source": [ + "1. Развернуть фразу на входе (на уровне слов) с помощью p-tune\n", + "2. Сделать то же самое с помощью библиотеки peft от HF\n", + "3. Дообучить с помощью LoRA одну из моделей (лучше gemma:2b или phi3.5, т.к. они небольшие) делать что-то прикольное на ваш выбор\n" + ], + "metadata": { + "id": "lbELN_ofSsOJ" + }, + "execution_count": null, + "outputs": [] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "DQUlqoEAulB8" + }, + "source": [ + "## Шаг 3: Дополнительное задание, *фактическое* обучение модели\n", + "\n", + "Ваша задача - дообучить модель для _генерации кода на Python_. Пожалуйста, используйте вышеприведенные примеры в качестве вдохновения. Например:\n", + "\n", + "* dataset: используйте [codeparrot-clean](https://huggingface.co/datasets/codeparrot/codeparrot-clean) или любые другие данные, содержащие код на Python. Так как вам не нужно много данных для этого упражнения, достаточно использовать только более короткий набор данных для валидации codeparrots.\n", + "* предобработка: выберите код на Python на основе расширений файлов (.py) (можно пропустить в случае codeparrot - 100% этого датасета – Python)\n", + "* короткие строки: используйте первые 512 символов каждой строки\n", + "* тип адаптера: используйте LoRA, плюс как минимум один из:\n", + " - дополнительный адаптер на lm_head\n", + " - дополнительный адаптер на компоненты MLP (mlp.*)\n", + " - обучаемые входные эмбеддинги (требуется настройка использования памяти)\n", + "\n", + "* обучение: вам не обязательно обучать до сходимости. Если все пройдет хорошо, ваша модель должна начать генерировать код после 500 шагов. Пожалуйста, используйте batch size не менее 4 (4 x 1 x 512 токенов) с использованием gradient_accumulation_steps=4.\n", + "\n", + "Примечание: в библиотеке peft также есть реализация LoRA. Однако мы просим вас показать хотя бы один полный запуск обучения с вашим собственным кодом LoRA для этого задания.\n", + "\n", + "Альтернативное задание: Вместо написания кода на Python, вы можете заменить задачу любым другим набором данных, например, вашим любимым исполнителем или подкастом, при условии, что это этично. Если вы выберете собственную задачу, пожалуйста, покажите примеры того, что ваша модель выучила - или не выучила, аналогично приведенным ниже примерам кода." + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "_LfFWSYhulB8" + }, + "outputs": [], + "source": [ + "prompts = [\n", + " \"\",\n", + " \"import\",\n", + " \"from\",\n", + " \"while\",\n", + " \"try\",\n", + " \"if\",\n", + " \"for\",\n", + " \"torch\",\n", + "] # feel free to add a few more that are not 100% assiciated with Python\n", + "\n", + "# \n", + "# generate baseline samples with the selected prompts before finetuning\n", + "# please feel free to use transformers.Trainer (as above) or your custom training code\n", + "# after the training concludes, please show examples of text generated by your model. It is expected to look like Python code fragments\n", + "# print the generation examples nicely (suggestion: use pandas or HTML) for easier comparison\n", + "# note: your LoRA-enhanced model can run generation the same way as the non-trained model (above)" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "SSucUeB4ulB9" + }, + "outputs": [], + "source": [ + "# This template helps to compare generated code samples in pretty table form\n", + "# feel free to present your work in other forms\n", + "\n", + "from IPython.display import HTML, display\n", + "\n", + "table_template = \"\"\"\n", + " \n", + " \n", + " \n", + " \n", + " \n", + "{}\n", + "
PROMPTBEFOREAFTER
\"\"\"\n", + "\n", + "row_template = \"\"\" \n", + " 

`{}`
\n", + " 
{}
\n", + " 
{}
\n", + " \"\"\"\n", + "\n", + "rows = []\n", + "\n", + "for prompt in prompts:\n", + " # replace placeholders in the format() arguments\n", + " rows.append(\n", + " row_template.format(\n", + " prompt, \"BEFORE FINETUNING\", \"TO BE GENERATED AFTER FINETUNING\"\n", + " )\n", + " )\n", + "\n", + "display(HTML(table_template.format(\"\\n\".join(rows))))" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "hrKidv5KulB9" + }, + "source": [ + "### Доп. материалы:\n", + "\n", + "* How post-training quantization works: https://arxiv.org/abs/2208.07339\n", + "* An overview of running large models: https://huggingface.co/docs/accelerate/package_reference/big_modeling\n", + "* A general library for different adapter types: https://adapterhub.ml/\n", + "\n", + "\n", + "### P.s.\n", + "Приведенный выше код можно достаточно легко адаптировать ко многим современным и не очень моделям: [Falcon-7B](https://huggingface.co/tiiuae/falcon-7b), [OPT-6.7B](https://huggingface.co/facebook/opt-6.7b) or [BLOOM-7.1B](https://huggingface.co/bigscience/bloom-7b1).\n", + "\n", + "Но вам может понадобиться изменить некоторые переменные:\n", + "1. Название модели для `AutoModelForCausalLM.from_pretrained()` и `AutoTokenizer`\n", + "2. Для prompt-tuning обратите внимание на `model.model.embed_tokens`.\n", + "3. Доработайте код для добавления LoRA. Сам адаптер не требует изменений." + ] + } + ], + "metadata": { + "accelerator": "GPU", + "colab": { + "gpuType": "T4", + "provenance": [] + }, + "kernelspec": { + "display_name": "Python 3 (ipykernel)", + "language": "python", + "name": "python3" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 3 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython3", + "version": "3.9.15" + }, + "widgets": { + "application/vnd.jupyter.widget-state+json": { + "aa44911037784664a62eb9f03de76b90": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HBoxModel", + "model_module_version": "1.5.0", + "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_b3b060782d434b43a8d807b5b24204e8", + "IPY_MODEL_1c387f8c51c8406da4a31f415fd1aedf", + "IPY_MODEL_372375fd32bd49dda8c2d160cf76e494" + ], + "layout": "IPY_MODEL_b4e8c62c961443aeabc53d7ae63adc94" + } + }, + "b3b060782d434b43a8d807b5b24204e8": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HTMLModel", + "model_module_version": "1.5.0", + "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_0705c1df630f4a658c767b6b5db9d5b5", + "placeholder": "​", + "style": "IPY_MODEL_47908a88c9c942f3a9cc5692fa746fa9", + "value": "Loading checkpoint shards: 100%" + } + }, + "1c387f8c51c8406da4a31f415fd1aedf": { + "model_module": "@jupyter-widgets/controls", + "model_name": "FloatProgressModel", + "model_module_version": "1.5.0", + "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_6df30859057e4ad38dd719e973259eaa", + "max": 2, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_b09b9ad7b56845178fa553fa9510af5b", + "value": 2 + } + }, + "372375fd32bd49dda8c2d160cf76e494": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HTMLModel", + "model_module_version": "1.5.0", + "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_8d4ca550a6ef4e8794f4c9ef51e68337", + "placeholder": "​", + "style": "IPY_MODEL_e885cf6a6ff34972af62ac79b3029821", + "value": " 2/2 [00:22<00:00, 11.69s/it]" + } + }, + "b4e8c62c961443aeabc53d7ae63adc94": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "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 + } + }, + "0705c1df630f4a658c767b6b5db9d5b5": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "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 + } + }, + "47908a88c9c942f3a9cc5692fa746fa9": { + "model_module": "@jupyter-widgets/controls", + "model_name": "DescriptionStyleModel", + "model_module_version": "1.5.0", + "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": "" + } + }, + "6df30859057e4ad38dd719e973259eaa": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "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 + } + }, + "b09b9ad7b56845178fa553fa9510af5b": { + "model_module": "@jupyter-widgets/controls", + "model_name": "ProgressStyleModel", + "model_module_version": "1.5.0", + "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": "" + } + }, + "8d4ca550a6ef4e8794f4c9ef51e68337": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "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 + } + }, + "e885cf6a6ff34972af62ac79b3029821": { + "model_module": "@jupyter-widgets/controls", + "model_name": "DescriptionStyleModel", + "model_module_version": "1.5.0", + "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": "" + } + }, + "9d70f17cf7ce444194d8505dd4d5ba40": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HBoxModel", + "model_module_version": "1.5.0", + "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_6d753205d6204b518181db6d48b5ca04", + "IPY_MODEL_71caa6cde3ed4534b20f9aeceb6a6825", + "IPY_MODEL_0bc2135a2cb04e85be41dfd4be4d0cf4" + ], + "layout": "IPY_MODEL_c1001011ec1d4bac80949b5acdfb3740" + } + }, + "6d753205d6204b518181db6d48b5ca04": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HTMLModel", + "model_module_version": "1.5.0", + "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_301598e43eda49189505df7ec71d4680", + "placeholder": "​", + "style": "IPY_MODEL_bf1bf67ad63347a4969d44ef48c2e8d0", + "value": "generation_config.json: 100%" + } + }, + "71caa6cde3ed4534b20f9aeceb6a6825": { + "model_module": "@jupyter-widgets/controls", + "model_name": "FloatProgressModel", + "model_module_version": "1.5.0", + "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_d7edca6998fd469bbb0da2449580c5e8", + "max": 195, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_5b21de81dc8847edb6a795109682e702", + "value": 195 + } + }, + "0bc2135a2cb04e85be41dfd4be4d0cf4": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HTMLModel", + "model_module_version": "1.5.0", + "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_6326bd94c4a244d586454a6ed75e0e33", + "placeholder": "​", + "style": "IPY_MODEL_afd9ef6838ac4d8f9adcca82df0f4b7e", + "value": " 195/195 [00:00<00:00, 10.9kB/s]" + } + }, + "c1001011ec1d4bac80949b5acdfb3740": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "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 + } + }, + "301598e43eda49189505df7ec71d4680": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "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 + } + }, + "bf1bf67ad63347a4969d44ef48c2e8d0": { + "model_module": "@jupyter-widgets/controls", + "model_name": "DescriptionStyleModel", + "model_module_version": "1.5.0", + "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": "" + } + }, + "d7edca6998fd469bbb0da2449580c5e8": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "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 + } + }, + "5b21de81dc8847edb6a795109682e702": { + "model_module": "@jupyter-widgets/controls", + "model_name": "ProgressStyleModel", + "model_module_version": "1.5.0", + "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": "" + } + }, + "6326bd94c4a244d586454a6ed75e0e33": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "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 + } + }, + "afd9ef6838ac4d8f9adcca82df0f4b7e": { + "model_module": "@jupyter-widgets/controls", + "model_name": "DescriptionStyleModel", + "model_module_version": "1.5.0", + "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": "" + } + }, + "5861525268574fc9941500f9e0885ab7": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HBoxModel", + "model_module_version": "1.5.0", + "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_e242fe8690384927ac08cb6cefc951f0", + "IPY_MODEL_38c50a52882e4df88600def974336eca", + "IPY_MODEL_d3395b221f9c453aa5a08d5f186ede4c" + ], + "layout": "IPY_MODEL_270ddfca364749a1ab5626586c9b26a0" + } + }, + "e242fe8690384927ac08cb6cefc951f0": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HTMLModel", + "model_module_version": "1.5.0", + "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_f7334d70f1b44cf6bb3675960a7234fa", + "placeholder": "​", + "style": "IPY_MODEL_34e1107c8e07495bb5700a3357333b9c", + "value": "tokenizer_config.json: 100%" + } + }, + "38c50a52882e4df88600def974336eca": { + "model_module": "@jupyter-widgets/controls", + "model_name": "FloatProgressModel", + "model_module_version": "1.5.0", + "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_f65e1abe249e42569513a68fe9e25454", + "max": 3984, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_8dfaf0e7da6a4c41bbf7d75436e05f56", + "value": 3984 + } + }, + "d3395b221f9c453aa5a08d5f186ede4c": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HTMLModel", + "model_module_version": "1.5.0", + "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_1ceeba93c14240208acf65bcaafb749c", + "placeholder": "​", + "style": "IPY_MODEL_8a298dcdc74a4e2d802cbf2b903714cc", + "value": " 3.98k/3.98k [00:00<00:00, 251kB/s]" + } + }, + "270ddfca364749a1ab5626586c9b26a0": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "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 + } + }, + "f7334d70f1b44cf6bb3675960a7234fa": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "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 + } + }, + "34e1107c8e07495bb5700a3357333b9c": { + "model_module": "@jupyter-widgets/controls", + "model_name": "DescriptionStyleModel", + "model_module_version": "1.5.0", + "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": "" + } + }, + "f65e1abe249e42569513a68fe9e25454": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "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 + } + }, + "8dfaf0e7da6a4c41bbf7d75436e05f56": { + "model_module": "@jupyter-widgets/controls", + "model_name": "ProgressStyleModel", + "model_module_version": "1.5.0", + "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": "" + } + }, + "1ceeba93c14240208acf65bcaafb749c": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "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 + } + }, + "8a298dcdc74a4e2d802cbf2b903714cc": { + "model_module": "@jupyter-widgets/controls", + "model_name": "DescriptionStyleModel", + "model_module_version": "1.5.0", + "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": "" + } + }, + "90b7c9102a7b499c87b2e83f2a881f70": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HBoxModel", + "model_module_version": "1.5.0", + "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_46cec79f77644a2ca9968f08320fbe1e", + "IPY_MODEL_487dd0246e2345eb9cb1e682a926dfe4", + "IPY_MODEL_0c4561867a8e486cb780099d71a7cb74" + ], + "layout": "IPY_MODEL_fb2707fdb16744abb57a2cdd206d652d" + } + }, + "46cec79f77644a2ca9968f08320fbe1e": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HTMLModel", + "model_module_version": "1.5.0", + "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_5cfbc5c3f4bf4309b6987e0e4b06ac6c", + "placeholder": "​", + "style": "IPY_MODEL_13574814004e42698a0b96192504bc11", + "value": "tokenizer.model: 100%" + } + }, + "487dd0246e2345eb9cb1e682a926dfe4": { + "model_module": "@jupyter-widgets/controls", + "model_name": "FloatProgressModel", + "model_module_version": "1.5.0", + "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_73969e68faff4548a40a7244e2c92a94", + "max": 499723, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_88eb6b8ad47840d788f61f11a4065ed7", + "value": 499723 + } + }, + "0c4561867a8e486cb780099d71a7cb74": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HTMLModel", + "model_module_version": "1.5.0", + "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_4b4c9324b364478f92e4b1d81eaced10", + "placeholder": "​", + "style": "IPY_MODEL_1bca7143149d44118fdc46dce30d9bac", + "value": " 500k/500k [00:00<00:00, 4.14MB/s]" + } + }, + "fb2707fdb16744abb57a2cdd206d652d": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "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 + } + }, + "5cfbc5c3f4bf4309b6987e0e4b06ac6c": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "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 + } + }, + "13574814004e42698a0b96192504bc11": { + "model_module": "@jupyter-widgets/controls", + "model_name": "DescriptionStyleModel", + "model_module_version": "1.5.0", + "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": "" + } + }, + "73969e68faff4548a40a7244e2c92a94": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "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 + } + }, + "88eb6b8ad47840d788f61f11a4065ed7": { + "model_module": "@jupyter-widgets/controls", + "model_name": "ProgressStyleModel", + "model_module_version": "1.5.0", + "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": "" + } + }, + "4b4c9324b364478f92e4b1d81eaced10": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "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 + } + }, + "1bca7143149d44118fdc46dce30d9bac": { + "model_module": "@jupyter-widgets/controls", + "model_name": "DescriptionStyleModel", + "model_module_version": "1.5.0", + "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": "" + } + }, + "ef160425b2924f34981e26037b4882c8": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HBoxModel", + "model_module_version": "1.5.0", + "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_aad453caddfd4d1a8a041de187ba1c5b", + "IPY_MODEL_5120a53a9a9c4486b769093ce154c908", + "IPY_MODEL_3e5179b2c8024377bfd0888199d593ca" + ], + "layout": "IPY_MODEL_9da5bd672b2d4f028b19ee1f35fd0b0c" + } + }, + "aad453caddfd4d1a8a041de187ba1c5b": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HTMLModel", + "model_module_version": "1.5.0", + "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_1a402c1091af4fd39c05d08dfb0a9e7b", + "placeholder": "​", + "style": "IPY_MODEL_4b380725519a4f7b81193c03e1eb8027", + "value": "tokenizer.json: 100%" + } + }, + "5120a53a9a9c4486b769093ce154c908": { + "model_module": "@jupyter-widgets/controls", + "model_name": "FloatProgressModel", + "model_module_version": "1.5.0", + "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_f8803131486d499a8253f6ae20429af4", + "max": 1844408, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_2c8803e4c52840c6a5b2261bcb6ce2d3", + "value": 1844408 + } + }, + "3e5179b2c8024377bfd0888199d593ca": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HTMLModel", + "model_module_version": "1.5.0", + "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_e11d969b5e3e4d0887917ca6d2aa6d12", + "placeholder": "​", + "style": "IPY_MODEL_10cd824052c5443885dbf11375c34b09", + "value": " 1.84M/1.84M [00:00<00:00, 13.7MB/s]" + } + }, + "9da5bd672b2d4f028b19ee1f35fd0b0c": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "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 + } + }, + "1a402c1091af4fd39c05d08dfb0a9e7b": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "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 + } + }, + "4b380725519a4f7b81193c03e1eb8027": { + "model_module": "@jupyter-widgets/controls", + "model_name": "DescriptionStyleModel", + "model_module_version": "1.5.0", + "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": "" + } + }, + "f8803131486d499a8253f6ae20429af4": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "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 + } + }, + "2c8803e4c52840c6a5b2261bcb6ce2d3": { + "model_module": "@jupyter-widgets/controls", + "model_name": "ProgressStyleModel", + "model_module_version": "1.5.0", + "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": "" + } + }, + "e11d969b5e3e4d0887917ca6d2aa6d12": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "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 + } + }, + "10cd824052c5443885dbf11375c34b09": { + "model_module": "@jupyter-widgets/controls", + "model_name": "DescriptionStyleModel", + "model_module_version": "1.5.0", + "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": "" + } + }, + "78a2e1479f5743f1938a012073079728": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HBoxModel", + "model_module_version": "1.5.0", + "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_b3a2da8bd47b4c8eb9995068cc967bde", + "IPY_MODEL_345c094bc03941c98ec7bdd59060eb05", + "IPY_MODEL_0fdf7237b90f4e58a9656c3d009ef3ee" + ], + "layout": "IPY_MODEL_e70069519f92475e9df45e2a59dc9ad7" + } + }, + "b3a2da8bd47b4c8eb9995068cc967bde": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HTMLModel", + "model_module_version": "1.5.0", + "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_6116ae88fa2c4b2791f7b059c2e834b5", + "placeholder": "​", + "style": "IPY_MODEL_5444556ddc3f4d218967d489b3e21c48", + "value": "added_tokens.json: 100%" + } + }, + "345c094bc03941c98ec7bdd59060eb05": { + "model_module": "@jupyter-widgets/controls", + "model_name": "FloatProgressModel", + "model_module_version": "1.5.0", + "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_dcc46b94429e42468cb830c03524b518", + "max": 306, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_1c2f3d1d5b5a4eb8bc15722259e2c592", + "value": 306 + } + }, + "0fdf7237b90f4e58a9656c3d009ef3ee": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HTMLModel", + "model_module_version": "1.5.0", + "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_0147f1325a8a44c988c86622a8733a0e", + "placeholder": "​", + "style": "IPY_MODEL_43356817fc2b4a01bfdf6f4ed23a0af9", + "value": " 306/306 [00:00<00:00, 19.9kB/s]" + } + }, + "e70069519f92475e9df45e2a59dc9ad7": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "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 + } + }, + "6116ae88fa2c4b2791f7b059c2e834b5": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "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 + } + }, + "5444556ddc3f4d218967d489b3e21c48": { + "model_module": "@jupyter-widgets/controls", + "model_name": "DescriptionStyleModel", + "model_module_version": "1.5.0", + "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": "" + } + }, + "dcc46b94429e42468cb830c03524b518": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "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 + } + }, + "1c2f3d1d5b5a4eb8bc15722259e2c592": { + "model_module": "@jupyter-widgets/controls", + "model_name": "ProgressStyleModel", + "model_module_version": "1.5.0", + "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": "" + } + }, + "0147f1325a8a44c988c86622a8733a0e": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "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 + } + }, + "43356817fc2b4a01bfdf6f4ed23a0af9": { + "model_module": "@jupyter-widgets/controls", + "model_name": "DescriptionStyleModel", + "model_module_version": "1.5.0", + "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": "" + } + }, + "5397a8cb15ec43f39a8468adf6a7c9de": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HBoxModel", + "model_module_version": "1.5.0", + "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_4915641943824ae2b66a4a3b8631f265", + "IPY_MODEL_6369531e1f764ee5b28944fb4ad4195d", + "IPY_MODEL_a78f0bf1d95f4925bf5f8da2d6287cbb" + ], + "layout": "IPY_MODEL_f6c7c1de1a454e5baa8b56729c67e9d8" + } + }, + "4915641943824ae2b66a4a3b8631f265": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HTMLModel", + "model_module_version": "1.5.0", + "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_ca3d804bf103468b9b8b3e11e9414a44", + "placeholder": "​", + "style": "IPY_MODEL_cc0c819dd8c14666b92f41ed033c82fa", + "value": "special_tokens_map.json: 100%" + } + }, + "6369531e1f764ee5b28944fb4ad4195d": { + "model_module": "@jupyter-widgets/controls", + "model_name": "FloatProgressModel", + "model_module_version": "1.5.0", + "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_077b35dbbd694baeaa24e3751275c092", + "max": 665, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_418d8920bf3d45568d04f4c04cd47285", + "value": 665 + } + }, + "a78f0bf1d95f4925bf5f8da2d6287cbb": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HTMLModel", + "model_module_version": "1.5.0", + "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_a925b7c55d3e492e988bed78fbaebb41", + "placeholder": "​", + "style": "IPY_MODEL_b2d3186602304f76bf1e513085012d0c", + "value": " 665/665 [00:00<00:00, 45.4kB/s]" + } + }, + "f6c7c1de1a454e5baa8b56729c67e9d8": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "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 + } + }, + "ca3d804bf103468b9b8b3e11e9414a44": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "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 + } + }, + "cc0c819dd8c14666b92f41ed033c82fa": { + "model_module": "@jupyter-widgets/controls", + "model_name": "DescriptionStyleModel", + "model_module_version": "1.5.0", + "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": "" + } + }, + "077b35dbbd694baeaa24e3751275c092": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "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 + } + }, + "418d8920bf3d45568d04f4c04cd47285": { + "model_module": "@jupyter-widgets/controls", + "model_name": "ProgressStyleModel", + "model_module_version": "1.5.0", + "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": "" + } + }, + "a925b7c55d3e492e988bed78fbaebb41": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "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 + } + }, + "b2d3186602304f76bf1e513085012d0c": { + "model_module": "@jupyter-widgets/controls", + "model_name": "DescriptionStyleModel", + "model_module_version": "1.5.0", + "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": "" + } + }, + "228bd4b13ca8471bbe603f6c16996ce9": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HBoxModel", + "model_module_version": "1.5.0", + "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_3a3e89622bc8475ab776224a94451304", + "IPY_MODEL_e208dc30c2eb4459bcfb8bded9389f44", + "IPY_MODEL_afd789c0715446bfbca1253ac4b1d7b5" + ], + "layout": "IPY_MODEL_594f6dbb7b5b40e5b5fc422077d9f058" + } + }, + "3a3e89622bc8475ab776224a94451304": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HTMLModel", + "model_module_version": "1.5.0", + "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_040c1447189b43a6ac14b68392166e51", + "placeholder": "​", + "style": "IPY_MODEL_5d06f93935c5483b8b8d1f49efc7784f", + "value": "Map: 100%" + } + }, + "e208dc30c2eb4459bcfb8bded9389f44": { + "model_module": "@jupyter-widgets/controls", + "model_name": "FloatProgressModel", + "model_module_version": "1.5.0", + "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_16392b2f676d4819a26b57e8cc1607ff", + "max": 32, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_d01672815e14428f85403ad1aab0a1f5", + "value": 32 + } + }, + "afd789c0715446bfbca1253ac4b1d7b5": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HTMLModel", + "model_module_version": "1.5.0", + "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_714028864ef047749950f9e6e25af9d9", + "placeholder": "​", + "style": "IPY_MODEL_f40d46b078c54d36821e80bb507e6d43", + "value": " 32/32 [00:00<00:00, 307.33 examples/s]" + } + }, + "594f6dbb7b5b40e5b5fc422077d9f058": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "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 + } + }, + "040c1447189b43a6ac14b68392166e51": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "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 + } + }, + "5d06f93935c5483b8b8d1f49efc7784f": { + "model_module": "@jupyter-widgets/controls", + "model_name": "DescriptionStyleModel", + "model_module_version": "1.5.0", + "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": "" + } + }, + "16392b2f676d4819a26b57e8cc1607ff": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "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 + } + }, + "d01672815e14428f85403ad1aab0a1f5": { + "model_module": "@jupyter-widgets/controls", + "model_name": "ProgressStyleModel", + "model_module_version": "1.5.0", + "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": "" + } + }, + "714028864ef047749950f9e6e25af9d9": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "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 + } + }, + "f40d46b078c54d36821e80bb507e6d43": { + "model_module": "@jupyter-widgets/controls", + "model_name": "DescriptionStyleModel", + "model_module_version": "1.5.0", + "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": "" + } + }, + "1152c259aaa24ad2a6216ce1c886071f": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HBoxModel", + "model_module_version": "1.5.0", + "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_080a36264994477a8097b9476fc7137d", + "IPY_MODEL_842681298e074cea8b9543895c4e6c0b", + "IPY_MODEL_8df6073abd0449809d55fae71c738706" + ], + "layout": "IPY_MODEL_8c2304a491d043e096f8b4c53c0d8bc0" + } + }, + "080a36264994477a8097b9476fc7137d": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HTMLModel", + "model_module_version": "1.5.0", + "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_d21d9cfe900047108fd4d151c9aa6e22", + "placeholder": "​", + "style": "IPY_MODEL_57c81ba2b3f5432f82176c5cce144774", + "value": " 52%" + } + }, + "842681298e074cea8b9543895c4e6c0b": { + "model_module": "@jupyter-widgets/controls", + "model_name": "FloatProgressModel", + "model_module_version": "1.5.0", + "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": "danger", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_86567f37d1a84a0a97ded8c42748580f", + "max": 100, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_58902d6a3ba84ca7a627c85ac0d606e2", + "value": 52 + } + }, + "8df6073abd0449809d55fae71c738706": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HTMLModel", + "model_module_version": "1.5.0", + "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_4c328d2554e74a45ae2bd134277bd7d9", + "placeholder": "​", + "style": "IPY_MODEL_96d456f2ba134806ba1782a13ae4d456", + "value": " 52/100 [00:50<00:44,  1.08it/s]" + } + }, + "8c2304a491d043e096f8b4c53c0d8bc0": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "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 + } + }, + "d21d9cfe900047108fd4d151c9aa6e22": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "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 + } + }, + "57c81ba2b3f5432f82176c5cce144774": { + "model_module": "@jupyter-widgets/controls", + "model_name": "DescriptionStyleModel", + "model_module_version": "1.5.0", + "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": "" + } + }, + "86567f37d1a84a0a97ded8c42748580f": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "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 + } + }, + "58902d6a3ba84ca7a627c85ac0d606e2": { + "model_module": "@jupyter-widgets/controls", + "model_name": "ProgressStyleModel", + "model_module_version": "1.5.0", + "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": "" + } + }, + "4c328d2554e74a45ae2bd134277bd7d9": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "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 + } + }, + "96d456f2ba134806ba1782a13ae4d456": { + "model_module": "@jupyter-widgets/controls", + "model_name": "DescriptionStyleModel", + "model_module_version": "1.5.0", + "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": "" + } + }, + "ea39322bcc0848f4a1c2d901c9830f20": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HBoxModel", + "model_module_version": "1.5.0", + "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_b52e9d8330844d55bfac3f4972d30bf6", + "IPY_MODEL_56c41973b7914eccad4a94c55af1b05d", + "IPY_MODEL_f573f939c02d4e42901abea84496b169" + ], + "layout": "IPY_MODEL_be2e5e683e08423093da7dcfd7f90411" + } + }, + "b52e9d8330844d55bfac3f4972d30bf6": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HTMLModel", + "model_module_version": "1.5.0", + "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_9638b8a54936477693056621d3f9f3c5", + "placeholder": "​", + "style": "IPY_MODEL_cb6958905eef4479a7fe6ed170a27ad6", + "value": "Loading checkpoint shards: 100%" + } + }, + "56c41973b7914eccad4a94c55af1b05d": { + "model_module": "@jupyter-widgets/controls", + "model_name": "FloatProgressModel", + "model_module_version": "1.5.0", + "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_e8492250f4924ec3b01bb7dcad72554a", + "max": 33, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_681c7c8a482b470eb460fdfbdfe13d4c", + "value": 33 + } + }, + "f573f939c02d4e42901abea84496b169": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HTMLModel", + "model_module_version": "1.5.0", + "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_398012a6b4ff46f09920684c63eaa4f1", + "placeholder": "​", + "style": "IPY_MODEL_c6922c429afa4b73a33a4270eadd36b6", + "value": " 33/33 [01:24<00:00,  2.66s/it]" + } + }, + "be2e5e683e08423093da7dcfd7f90411": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "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 + } + }, + "9638b8a54936477693056621d3f9f3c5": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "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 + } + }, + "cb6958905eef4479a7fe6ed170a27ad6": { + "model_module": "@jupyter-widgets/controls", + "model_name": "DescriptionStyleModel", + "model_module_version": "1.5.0", + "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": "" + } + }, + "e8492250f4924ec3b01bb7dcad72554a": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "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 + } + }, + "681c7c8a482b470eb460fdfbdfe13d4c": { + "model_module": "@jupyter-widgets/controls", + "model_name": "ProgressStyleModel", + "model_module_version": "1.5.0", + "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": "" + } + }, + "398012a6b4ff46f09920684c63eaa4f1": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "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 + } + }, + "c6922c429afa4b73a33a4270eadd36b6": { + "model_module": "@jupyter-widgets/controls", + "model_name": "DescriptionStyleModel", + "model_module_version": "1.5.0", + "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": "" + } + }, + "2565c3d24f524f2ca4c1a3bd40eec3d6": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HBoxModel", + "model_module_version": "1.5.0", + "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_e18d8533c7c24b259ea31ee42c439012", + "IPY_MODEL_a8f5353d0a2549609d488f818fda04ce", + "IPY_MODEL_1c632ec373284565af94703bca5f87d8" + ], + "layout": "IPY_MODEL_cc114568a65840fa8c92c6da33c31d95" + } + }, + "e18d8533c7c24b259ea31ee42c439012": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HTMLModel", + "model_module_version": "1.5.0", + "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_0e1b1d6328b448ed9b6f45eaf9cd512d", + "placeholder": "​", + "style": "IPY_MODEL_2f4ce07967344f12af5d8576e8048cbc", + "value": "README.md: 100%" + } + }, + "a8f5353d0a2549609d488f818fda04ce": { + "model_module": "@jupyter-widgets/controls", + "model_name": "FloatProgressModel", + "model_module_version": "1.5.0", + "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_a8f8713bfb3f4bd8947de56cd73759b6", + "max": 5554, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_6478cee1f71b478c8d970370e1965847", + "value": 5554 + } + }, + "1c632ec373284565af94703bca5f87d8": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HTMLModel", + "model_module_version": "1.5.0", + "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_6540cb7c618b41ec9c81af7833540112", + "placeholder": "​", + "style": "IPY_MODEL_107ed2ed6b4f41b98cbf0a2cd4ed8939", + "value": " 5.55k/5.55k [00:00<00:00, 126kB/s]" + } + }, + "cc114568a65840fa8c92c6da33c31d95": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "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 + } + }, + "0e1b1d6328b448ed9b6f45eaf9cd512d": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "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 + } + }, + "2f4ce07967344f12af5d8576e8048cbc": { + "model_module": "@jupyter-widgets/controls", + "model_name": "DescriptionStyleModel", + "model_module_version": "1.5.0", + "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": "" + } + }, + "a8f8713bfb3f4bd8947de56cd73759b6": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "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 + } + }, + "6478cee1f71b478c8d970370e1965847": { + "model_module": "@jupyter-widgets/controls", + "model_name": "ProgressStyleModel", + "model_module_version": "1.5.0", + "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": "" + } + }, + "6540cb7c618b41ec9c81af7833540112": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "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 + } + }, + "107ed2ed6b4f41b98cbf0a2cd4ed8939": { + "model_module": "@jupyter-widgets/controls", + "model_name": "DescriptionStyleModel", + "model_module_version": "1.5.0", + "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": "" + } + }, + "dd8167994e5d4d51ab86bef80f7fc866": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HBoxModel", + "model_module_version": "1.5.0", + "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_7a256aa44e364199b13ffc9eb27f5706", + "IPY_MODEL_b2c019db47f348f082f725ef87589b6c", + "IPY_MODEL_46b41a1e94674444aa8c3c871f384374" + ], + "layout": "IPY_MODEL_164593bc8f9048cabfd3447a40819b05" + } + }, + "7a256aa44e364199b13ffc9eb27f5706": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HTMLModel", + "model_module_version": "1.5.0", + "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_a93a881bd8ec4bac998c650ec6861e64", + "placeholder": "​", + "style": "IPY_MODEL_524c2277dd664099bb69085e4953202b", + "value": "quotes.jsonl: 100%" + } + }, + "b2c019db47f348f082f725ef87589b6c": { + "model_module": "@jupyter-widgets/controls", + "model_name": "FloatProgressModel", + "model_module_version": "1.5.0", + "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_ed325721bcad4ecd9022909912ad3f38", + "max": 646739, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_1106eed2a35c4c268d4c6edf5f85c643", + "value": 646739 + } + }, + "46b41a1e94674444aa8c3c871f384374": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HTMLModel", + "model_module_version": "1.5.0", + "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_4274987d777349c8b1a98cd0b2c8a321", + "placeholder": "​", + "style": "IPY_MODEL_90a0d2b5e86141aca5bc64a012085dd0", + "value": " 647k/647k [00:00<00:00, 5.01MB/s]" + } + }, + "164593bc8f9048cabfd3447a40819b05": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "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 + } + }, + "a93a881bd8ec4bac998c650ec6861e64": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "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 + } + }, + "524c2277dd664099bb69085e4953202b": { + "model_module": "@jupyter-widgets/controls", + "model_name": "DescriptionStyleModel", + "model_module_version": "1.5.0", + "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": "" + } + }, + "ed325721bcad4ecd9022909912ad3f38": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "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 + } + }, + "1106eed2a35c4c268d4c6edf5f85c643": { + "model_module": "@jupyter-widgets/controls", + "model_name": "ProgressStyleModel", + "model_module_version": "1.5.0", + "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": "" + } + }, + "4274987d777349c8b1a98cd0b2c8a321": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "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 + } + }, + "90a0d2b5e86141aca5bc64a012085dd0": { + "model_module": "@jupyter-widgets/controls", + "model_name": "DescriptionStyleModel", + "model_module_version": "1.5.0", + "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": "" + } + }, + "1b9b8035f6c64ba6a80aa2105902cf0f": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HBoxModel", + "model_module_version": "1.5.0", + "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_c4c3bfddeee34c93a5ac77f58ad3826c", + "IPY_MODEL_50fdb22658034563b0d02dd6b6d9cad7", + "IPY_MODEL_7c82aabb5ecb460096e461e993085245" + ], + "layout": "IPY_MODEL_a86bd2750d044cedacdb710983c49c41" + } + }, + "c4c3bfddeee34c93a5ac77f58ad3826c": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HTMLModel", + "model_module_version": "1.5.0", + "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_59ef4e355eb548c69af3fa43c5cbdee0", + "placeholder": "​", + "style": "IPY_MODEL_289364699b0c4117a50b4e23cc8af0a0", + "value": "Generating train split: 100%" + } + }, + "50fdb22658034563b0d02dd6b6d9cad7": { + "model_module": "@jupyter-widgets/controls", + "model_name": "FloatProgressModel", + "model_module_version": "1.5.0", + "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_6c982241db824e3ba20e806269b680b3", + "max": 2508, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_16ddad2721954475bcbad000f44369cb", + "value": 2508 + } + }, + "7c82aabb5ecb460096e461e993085245": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HTMLModel", + "model_module_version": "1.5.0", + "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_a5dbe34fea0d41a6b54d777803345929", + "placeholder": "​", + "style": "IPY_MODEL_1c69bd5349814dd08fe112a00383b0ce", + "value": " 2508/2508 [00:00<00:00, 14879.92 examples/s]" + } + }, + "a86bd2750d044cedacdb710983c49c41": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "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 + } + }, + "59ef4e355eb548c69af3fa43c5cbdee0": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "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 + } + }, + "289364699b0c4117a50b4e23cc8af0a0": { + "model_module": "@jupyter-widgets/controls", + "model_name": "DescriptionStyleModel", + "model_module_version": "1.5.0", + "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": "" + } + }, + "6c982241db824e3ba20e806269b680b3": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "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 + } + }, + "16ddad2721954475bcbad000f44369cb": { + "model_module": "@jupyter-widgets/controls", + "model_name": "ProgressStyleModel", + "model_module_version": "1.5.0", + "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": "" + } + }, + "a5dbe34fea0d41a6b54d777803345929": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "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 + } + }, + "1c69bd5349814dd08fe112a00383b0ce": { + "model_module": "@jupyter-widgets/controls", + "model_name": "DescriptionStyleModel", + "model_module_version": "1.5.0", + "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": "" + } + }, + "9c4d0b83744d42ffab6d2f74ebfc65e8": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HBoxModel", + "model_module_version": "1.5.0", + "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_d286eff453034dc8a15f5e9cb908480a", + "IPY_MODEL_fd88fbd8bfdf438ba3b6b32fdd1b8202", + "IPY_MODEL_aaa976169d564f40b2b1471696c06a15" + ], + "layout": "IPY_MODEL_0ccfaf92f4684a219ebb34a6a9108e1d" + } + }, + "d286eff453034dc8a15f5e9cb908480a": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HTMLModel", + "model_module_version": "1.5.0", + "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_094993c5be3d46a690fbc75e4f217adc", + "placeholder": "​", + "style": "IPY_MODEL_fa5420a0d29a4b90bb293be5d205a0da", + "value": "Map: 100%" + } + }, + "fd88fbd8bfdf438ba3b6b32fdd1b8202": { + "model_module": "@jupyter-widgets/controls", + "model_name": "FloatProgressModel", + "model_module_version": "1.5.0", + "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_3f91a33f821045639c0b590d749e86f2", + "max": 32, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_5849e2fb31d84d2fa9af5457c2b4297d", + "value": 32 + } + }, + "aaa976169d564f40b2b1471696c06a15": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HTMLModel", + "model_module_version": "1.5.0", + "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_6653eb0b9dfd4f47ac7886eeb7a4fabd", + "placeholder": "​", + "style": "IPY_MODEL_960e0f1ee6e6413d8895b3d93ba0d2d4", + "value": " 32/32 [00:00<00:00, 326.03 examples/s]" + } + }, + "0ccfaf92f4684a219ebb34a6a9108e1d": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "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 + } + }, + "094993c5be3d46a690fbc75e4f217adc": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "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 + } + }, + "fa5420a0d29a4b90bb293be5d205a0da": { + "model_module": "@jupyter-widgets/controls", + "model_name": "DescriptionStyleModel", + "model_module_version": "1.5.0", + "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": "" + } + }, + "3f91a33f821045639c0b590d749e86f2": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "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 + } + }, + "5849e2fb31d84d2fa9af5457c2b4297d": { + "model_module": "@jupyter-widgets/controls", + "model_name": "ProgressStyleModel", + "model_module_version": "1.5.0", + "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": "" + } + }, + "6653eb0b9dfd4f47ac7886eeb7a4fabd": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "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 + } + }, + "960e0f1ee6e6413d8895b3d93ba0d2d4": { + "model_module": "@jupyter-widgets/controls", + "model_name": "DescriptionStyleModel", + "model_module_version": "1.5.0", + "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": "" + } + } + } + } + }, + "nbformat": 4, + "nbformat_minor": 0 +} \ No newline at end of file diff --git a/week09_Advanced_techniques_LLM_v1/README.md b/week09_Advanced_techniques_LLM_v1/README.md new file mode 100644 index 0000000..b996cd8 --- /dev/null +++ b/week09_Advanced_techniques_LLM_v1/README.md @@ -0,0 +1 @@ +Slides: https://docs.google.com/presentation/d/1YBmIaALEsse5tYsA_7qFJ3aoQfBekxToxwQ6W6N8t_8/edit?usp=sharing \ No newline at end of file diff --git a/week_10_Advanced_techniques_LLM_v2/.ipynb_checkpoints/README-checkpoint.md b/week_10_Advanced_techniques_LLM_v2/.ipynb_checkpoints/README-checkpoint.md new file mode 100644 index 0000000..e69de29 diff --git a/week_10_Advanced_techniques_LLM_v2/README.md b/week_10_Advanced_techniques_LLM_v2/README.md new file mode 100644 index 0000000..6a0030e --- /dev/null +++ b/week_10_Advanced_techniques_LLM_v2/README.md @@ -0,0 +1 @@ +Slides: https://docs.google.com/presentation/d/1nBSgryVHpls1PgPZIQEqsw9h5dXKeym68sp-q-uh_7w/edit?usp=sharing \ No newline at end of file