BarinkDev/LargeLanguageModels
0
1{2 "cells": [3 {4 "cell_type": "code",5 "execution_count": 1,6 "id": "60dd57c5-0e8d-4f88-ab6c-c6ebc7e3fbd6",7 "metadata": {},8 "outputs": [9 {10 "name": "stderr",11 "output_type": "stream",12 "text": [13 "/mnt/f/wkspc-linux/tf-gpu/.venv/lib/python3.9/site-packages/tqdm/auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",14 " from .autonotebook import tqdm as notebook_tqdm\n",15 "2023-12-09 12:45:03.725545: I tensorflow/core/util/port.cc:111] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.\n",16 "2023-12-09 12:45:08.420633: E tensorflow/compiler/xla/stream_executor/cuda/cuda_dnn.cc:9342] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered\n",17 "2023-12-09 12:45:08.420679: E tensorflow/compiler/xla/stream_executor/cuda/cuda_fft.cc:609] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered\n",18 "2023-12-09 12:45:08.437126: E tensorflow/compiler/xla/stream_executor/cuda/cuda_blas.cc:1518] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered\n",19 "2023-12-09 12:45:10.370641: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.\n",20 "To enable the following instructions: AVX2 AVX_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.\n",21 "2023-12-09 12:45:29.973250: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT\n"22 ]23 }24 ],25 "source": [26 "import transformers\n",27 "from transformers import AutoTokenizer \n",28 "from datasets import load_dataset\n",29 "from datasets import ClassLabel \n",30 "import random\n",31 "import pandas as pd\n",32 "from IPython.display import display, HTML\n",33 "from transformers import AutoConfig, AutoModelForCausalLM\n",34 "from transformers import Trainer, TrainingArguments"35 ]36 },37 {38 "cell_type": "code",39 "execution_count": 2,40 "id": "80ec706a-641c-4b2f-86a5-5a30a92aa78d",41 "metadata": {},42 "outputs": [],43 "source": [44 "datasets = load_dataset('wikitext', 'wikitext-2-raw-v1')"45 ]46 },47 {48 "cell_type": "code",49 "execution_count": 3,50 "id": "58159522-5c39-48ab-a868-27634d9d058a",51 "metadata": {},52 "outputs": [53 {54 "data": {55 "text/plain": [56 "{'text': ' The game \\'s battle system , the BliTZ system , is carried over directly from Valkyira Chronicles . During missions , players select each unit using a top @-@ down perspective of the battlefield map : once a character is selected , the player moves the character around the battlefield in third @-@ person . A character can only act once per @-@ turn , but characters can be granted multiple turns at the expense of other characters \\' turns . Each character has a field and distance of movement limited by their Action Gauge . Up to nine characters can be assigned to a single mission . During gameplay , characters will call out if something happens to them , such as their health points ( HP ) getting low or being knocked out by enemy attacks . Each character has specific \" Potentials \" , skills unique to each character . They are divided into \" Personal Potential \" , which are innate skills that remain unaltered unless otherwise dictated by the story and can either help or impede a character , and \" Battle Potentials \" , which are grown throughout the game and always grant boons to a character . To learn Battle Potentials , each character has a unique \" Masters Table \" , a grid @-@ based skill table that can be used to acquire and link different skills . Characters also have Special Abilities that grant them temporary boosts on the battlefield : Kurt can activate \" Direct Command \" and move around the battlefield without depleting his Action Point gauge , the character Reila can shift into her \" Valkyria Form \" and become invincible , while Imca can target multiple enemy units with her heavy weapon . \\n'}"57 ]58 },59 "execution_count": 3,60 "metadata": {},61 "output_type": "execute_result"62 }63 ],64 "source": [65 "datasets[\"train\"][10]"66 ]67 },68 {69 "cell_type": "code",70 "execution_count": 4,71 "id": "b456c51b-200a-4ee1-affe-078c32216011",72 "metadata": {},73 "outputs": [],74 "source": [75 "def show_random_elements(dataset, num_examples=10):\n",76 " assert num_examples <= len(dataset), \"Dataset too small\"\n",77 " picks = []\n",78 " for _ in range(num_examples):\n",79 " pick = random.randint(0, len(dataset) -1 )\n",80 " while pick in picks:\n",81 " pick = random.randint(0, len(dataset) -1)\n",82 " picks.append(pick)\n",83 "\n",84 " df = pd.DataFrame(dataset[picks])\n",85 " for column, typ in dataset.features.items():\n",86 " if isinstance(typ, ClassLabel):\n",87 " df[column] = df[column].transform(lambda i : typ.names[i])\n",88 " display(HTML(df.to_html()))\n",89 " "90 ]91 },92 {93 "cell_type": "code",94 "execution_count": 5,95 "id": "b0d20dd1-b905-4941-ae84-2443425a4cab",96 "metadata": {},97 "outputs": [98 {99 "data": {100 "text/html": [101 "<table border=\"1\" class=\"dataframe\">\n",102 " <thead>\n",103 " <tr style=\"text-align: right;\">\n",104 " <th></th>\n",105 " <th>text</th>\n",106 " </tr>\n",107 " </thead>\n",108 " <tbody>\n",109 " <tr>\n",110 " <th>0</th>\n",111 " <td>= = Description and career as Fingal = = \\n</td>\n",112 " </tr>\n",113 " <tr>\n",114 " <th>1</th>\n",115 " <td>Despite these efforts , on 21 February it became clear just how fundamentally opposed the groups were . Philip Nye , one of the dissenting brethren , asserted in a speech that a presbytery set over local congregations would become as powerful as the state and was dangerous to the commonwealth , provoking vigorous opposition from presbyterians . The next day , the Assembly finally began to establish a prescription for presbyterian government . Owing to a strong belief in the unity of the church , the Assembly continued to try to find ways to reconcile the dissenting brethren with the majority throughout 1644 , including the establishment of a special committee for that purpose in March . However , on 15 November , the dissenting brethren presented their reasons for disagreement with the rest of the Assembly to Parliament , and on 11 December the majority submitted a draft of a presbyterian form of government . \\n</td>\n",116 " </tr>\n",117 " <tr>\n",118 " <th>2</th>\n",119 " <td></td>\n",120 " </tr>\n",121 " <tr>\n",122 " <th>3</th>\n",123 " <td>Reines had prepared for the possibility of measuring the distant events of a supernova explosion . Supernova explosions are rare , but Reines thought he might be lucky enough to see one in his lifetime , and be able to catch the neutrinos streaming from it in his specially @-@ designed detectors . During his wait for a supernova to explode , he put signs on some of his large neutrino detectors , calling them \" Supernova Early Warning Systems \" . In 1987 , neutrinos emitted from Supernova SN1987A were detected by the Irvine – Michigan – Brookhaven ( IMB ) Collaboration , which used an 8 @,@ 000 ton Cherenkov detector located in a salt mine near Cleveland . Normally , the detectors recorded only a few background events each day . The supernova registered 19 events in just ten seconds . This discovery is regarded as inaugurating the field of neutrino astronomy . \\n</td>\n",124 " </tr>\n",125 " <tr>\n",126 " <th>4</th>\n",127 " <td></td>\n",128 " </tr>\n",129 " <tr>\n",130 " <th>5</th>\n",131 " <td>Manager of the Month : July / August 2011 , October 2011 , March 2013 \\n</td>\n",132 " </tr>\n",133 " <tr>\n",134 " <th>6</th>\n",135 " <td>In June , Federer announced that after the end of his third term , he would resign as President of the ATP Players Council , a position he had held since 2008 . At the Halle Open , Federer reached both the singles and the doubles finals and won his seventh Halle singles title , beating Alejandro Falla in the final . At Wimbledon , Federer reached a record ninth final , but he defeated by Djokovic in an epic five @-@ set match . \\n</td>\n",136 " </tr>\n",137 " <tr>\n",138 " <th>7</th>\n",139 " <td>As part of the second wave , the 2nd Brigade had been landing since 05 : 30 ; the 5th , 6th and 8th Battalions were supposed to cross 400 Plateau and head to Hill 971 , while the 7th Battalion on the left were to climb Plugge 's Plateau then make for Hill 971 . One 7th Battalion company , Jackson 's , landed beside the Fisherman 's Hut in the north and was almost wiped out ; only forty men survived the landing . At 06 : 00 Major Ivie Blezard 's 7th Battalion company , and part of another , were sent onto 400 Plateau by Maclagen to strengthen the defence . When the 7th Battalion commander Lieutenant @-@ Colonel Harold Elliott landed he realised events were not going to plan , and he headed to the 3rd Brigade headquarters to find out what was happening . Maclagen ordered him to gather his battalion at the south of the beachhead , as the 2nd Brigade would now form the division 's right flank , not left . When the 2nd Brigade commander Colonel James McCay arrived Maclagen convinced him to move his brigade to the south , swapping responsibility with the 3rd Brigade . Eventually agreeing , he established his headquarters on the seaward slope of 400 Plateau ( McCay 's Hill ) . Heading onto the plateau , McCay realised the ridge to his right , Bolton 's Ridge , would be a key point in their defence . He located the Brigade @-@ Major , Walter Cass , and ordered him to gather what men he could to defend the ridge . Looking around , he saw the 8th Battalion , commanded by Colonel William Bolton , moving forward , so Cass directed them to Bolton 's Ridge . As such , it was the only ANZAC battalion that remained together during the day . Eventually , around 07 : 00 , the rest of the brigade started arriving . As each company and battalion appeared they were pushed forward into the front line , but with no defined orders other than to support the 3rd Brigade . At 10 : 30 the six guns of the 26th Jacobs Mountain Battery arrived , positioning three guns each side of White 's Valley . At noon they opened fire on the Turks on Gun Ridge . \\n</td>\n",140 " </tr>\n",141 " <tr>\n",142 " <th>8</th>\n",143 " <td>Laurence Kerr Olivier , Baron Olivier , OM ( / ˈlɒrəns kɜːr ɒˈlɪvieɪ / ; 22 May 1907 – 11 July 1989 ) was an English actor who , along with his contemporaries Ralph Richardson and John Gielgud , dominated the British stage of the mid @-@ 20th century . He also worked in films throughout his career , playing more than fifty cinema roles . Late in his career , he had considerable success in television roles . \\n</td>\n",144 " </tr>\n",145 " <tr>\n",146 " <th>9</th>\n",147 " <td>\" Mothers of the Disappeared \" was created and mixed at guitarist the Edge 's newly @-@ bought home , Melbeach , which U2 used as a recording studio . Bono wrote the song on his mother @-@ in @-@ law 's Spanish guitar , and drummer Larry Mullen , Jr. created a drum loop that was sampled by producer Brian Eno . The melody came from a song that Bono wrote in Ethiopia in 1985 to teach children about basic methods of hygiene . Producer Daniel Lanois was the principal mixer of the song . Bono , likening the studio itself to an instrument , described Lanois 's mix as a \" performance \" . \\n</td>\n",148 " </tr>\n",149 " </tbody>\n",150 "</table>"151 ],152 "text/plain": [153 "<IPython.core.display.HTML object>"154 ]155 },156 "metadata": {},157 "output_type": "display_data"158 }159 ],160 "source": [161 "show_random_elements(datasets[\"train\"])"162 ]163 },164 {165 "cell_type": "code",166 "execution_count": 6,167 "id": "9ff2781a-b961-4656-baed-0b6a40cb9e61",168 "metadata": {},169 "outputs": [],170 "source": [171 "model_checkpoint = \"gpt2\" \n",172 "tokenizer_checkpoint = \"sgugger/gpt2-like-tokenizer\""173 ]174 },175 {176 "cell_type": "code",177 "execution_count": 7,178 "id": "1e2c8eb4-a512-4bb5-a6d4-5cfd3b51dbe2",179 "metadata": {},180 "outputs": [],181 "source": [182 "tokenizer = AutoTokenizer.from_pretrained(tokenizer_checkpoint)"183 ]184 },185 {186 "cell_type": "code",187 "execution_count": 8,188 "id": "782406ce-f242-4cf1-87a3-2fec9f1a6de5",189 "metadata": {},190 "outputs": [],191 "source": [192 "def tokize_function(examples):\n",193 " return tokenizer(examples[\"text\"])\n",194 " "195 ]196 },197 {198 "cell_type": "code",199 "execution_count": 9,200 "id": "5d9e36bd-0542-40a0-ae91-4c05c68db9f8",201 "metadata": {},202 "outputs": [],203 "source": [204 "tokenized_datasets = datasets.map(tokize_function, batched=True, num_proc=6, remove_columns=[\"text\"])"205 ]206 },207 {208 "cell_type": "code",209 "execution_count": 10,210 "id": "cca06086-9653-452f-969d-7bb4b0aaf549",211 "metadata": {},212 "outputs": [213 {214 "data": {215 "text/plain": [216 "{'input_ids': [238, 8576, 9441, 2987, 238, 252],\n",217 " 'attention_mask': [1, 1, 1, 1, 1, 1]}"218 ]219 },220 "execution_count": 10,221 "metadata": {},222 "output_type": "execute_result"223 }224 ],225 "source": [226 "tokenized_datasets[\"train\"][1]"227 ]228 },229 {230 "cell_type": "code",231 "execution_count": 11,232 "id": "83c749af-fc04-4123-8f79-529a2637f841",233 "metadata": {},234 "outputs": [],235 "source": [236 "block_size = 128"237 ]238 },239 {240 "cell_type": "code",241 "execution_count": 12,242 "id": "404c5e33-38ce-431f-9f10-bb114b1e03e2",243 "metadata": {},244 "outputs": [],245 "source": [246 "def group_texts(examples):\n",247 " concated_examples = {k: sum(examples[k], []) for k in examples.keys()}\n",248 " total_length = len(concated_examples[list(examples.keys())[0]])\n",249 " total_length = (total_length // block_size) * block_size\n",250 " result = { \n",251 " k: [t[i: i + block_size] for i in range(0, total_length, block_size)]\n",252 " for k, t in concated_examples.items()\n",253 " }\n",254 " result[\"labels\"] = result[\"input_ids\"].copy()\n",255 " return result"256 ]257 },258 {259 "cell_type": "code",260 "execution_count": 13,261 "id": "6d2bd0d5-1394-47d9-950b-951ea04af951",262 "metadata": {},263 "outputs": [],264 "source": [265 "lm_datasets = tokenized_datasets.map(group_texts, batched=True, batch_size=1000, num_proc=6)"266 ]267 },268 {269 "cell_type": "code",270 "execution_count": 14,271 "id": "f0e79ec7-dc48-4497-9a4c-255bc8383897",272 "metadata": {},273 "outputs": [274 {275 "data": {276 "text/plain": [277 "' the \" Nameless \", a penal military unit serving the nation of Gallia during the Second Europan War who perform secret black operations and are pitted against the Imperial unit \" Calamaty Raven \". \\n The game began development in 2010, carrying over a large portion of the work done on Valkyria Chronicles II. While it retained the standard features of the series, it also underwent multiple adjustments, such as making the game more forgiving for series newcomers. Character designer Raita Honjou and composer Hitoshi Sakimoto both returned from previous entries, along with Valkyria Chronicles II director Takeshi Ozawa. A large'"278 ]279 },280 "execution_count": 14,281 "metadata": {},282 "output_type": "execute_result"283 }284 ],285 "source": [286 "tokenizer.decode(lm_datasets[\"train\"][1][\"input_ids\"])"287 ]288 },289 {290 "cell_type": "code",291 "execution_count": 15,292 "id": "04b6e31a-78a7-418a-b360-c0a873af1235",293 "metadata": {},294 "outputs": [],295 "source": [296 "config = AutoConfig.from_pretrained(model_checkpoint)\n",297 "model = AutoModelForCausalLM.from_config(config)"298 ]299 },300 {301 "cell_type": "code",302 "execution_count": 16,303 "id": "b917d7ee-281b-41ff-8c90-2505730019cb",304 "metadata": {},305 "outputs": [],306 "source": [307 "training_args = TrainingArguments(\n",308 " f\"{model_checkpoint}-wikitext2\",\n",309 " evaluation_strategy = \"epoch\",\n",310 " learning_rate = 2e-5,\n",311 " weight_decay = 0.01,\n",312 " push_to_hub=False)"313 ]314 },315 {316 "cell_type": "code",317 "execution_count": 17,318 "id": "deca2a1b-9cc3-4021-8b17-62abf8929099",319 "metadata": {},320 "outputs": [],321 "source": [322 "trainer = Trainer(model=model, args=training_args, train_dataset=lm_datasets[\"train\"], eval_dataset=lm_datasets[\"validation\"],)"323 ]324 },325 {326 "cell_type": "code",327 "execution_count": 18,328 "id": "86b3b2fe-01a4-4b04-86c0-8f667943286c",329 "metadata": {},330 "outputs": [331 {332 "data": {333 "text/html": [334 "\n",335 " <div>\n",336 " \n",337 " <progress value='6750' max='6750' style='width:300px; height:20px; vertical-align: middle;'></progress>\n",338 " [6750/6750 27:40, Epoch 3/3]\n",339 " </div>\n",340 " <table border=\"1\" class=\"dataframe\">\n",341 " <thead>\n",342 " <tr style=\"text-align: left;\">\n",343 " <th>Epoch</th>\n",344 " <th>Training Loss</th>\n",345 " <th>Validation Loss</th>\n",346 " </tr>\n",347 " </thead>\n",348 " <tbody>\n",349 " <tr>\n",350 " <td>1</td>\n",351 " <td>6.551200</td>\n",352 " <td>6.481327</td>\n",353 " </tr>\n",354 " <tr>\n",355 " <td>2</td>\n",356 " <td>6.162500</td>\n",357 " <td>6.209187</td>\n",358 " </tr>\n",359 " <tr>\n",360 " <td>3</td>\n",361 " <td>6.018400</td>\n",362 " <td>6.120646</td>\n",363 " </tr>\n",364 " </tbody>\n",365 "</table><p>"366 ],367 "text/plain": [368 "<IPython.core.display.HTML object>"369 ]370 },371 "metadata": {},372 "output_type": "display_data"373 },374 {375 "data": {376 "text/plain": [377 "TrainOutput(global_step=6750, training_loss=6.3967724609375, metrics={'train_runtime': 1664.8174, 'train_samples_per_second': 32.423, 'train_steps_per_second': 4.054, 'total_flos': 3526070648832000.0, 'train_loss': 6.3967724609375, 'epoch': 3.0})"378 ]379 },380 "execution_count": 18,381 "metadata": {},382 "output_type": "execute_result"383 }384 ],385 "source": [386 "trainer.train()"387 ]388 },389 {390 "cell_type": "code",391 "execution_count": 19,392 "id": "00275113-02e6-471c-bd87-c6d7c9013e05",393 "metadata": {},394 "outputs": [395 {396 "data": {397 "text/plain": [398 "transformers.models.gpt2.modeling_gpt2.GPT2LMHeadModel"399 ]400 },401 "execution_count": 19,402 "metadata": {},403 "output_type": "execute_result"404 }405 ],406 "source": [407 "type(model)"408 ]409 },410 {411 "cell_type": "markdown",412 "id": "c7762346-cf1d-4526-875b-0d3c872b3d2e",413 "metadata": {},414 "source": [415 "help(model)"416 ]417 },418 {419 "cell_type": "code",420 "execution_count": 39,421 "id": "a2eed72e-51bf-4355-90dd-f7b89f07c235",422 "metadata": {},423 "outputs": [],424 "source": [425 "def prompt(text : str ) -> str:\n",426 " input = tokenizer(text, return_tensors=\"pt\").to('cuda')\n",427 " output = model.generate(**input, max_new_tokens=60, return_dict_in_generate=True, output_scores=True)\n",428 " generated_tokens_ids = output.sequences[0]\n",429 " return tokenizer.decode(generated_tokens_ids)"430 ]431 },432 {433 "cell_type": "code",434 "execution_count": 41,435 "id": "ef3562aa-d929-4242-b2a3-195d02084da0",436 "metadata": {},437 "outputs": [438 {439 "name": "stderr",440 "output_type": "stream",441 "text": [442 "Setting `pad_token_id` to `eos_token_id`:50256 for open-end generation.\n"443 ]444 },445 {446 "data": {447 "text/plain": [448 "'Netherlands, and the first time of the first time, and the first time of the first time. The first time, the first time was the first time of the first time, and the first time was the first time. \\n = = = = = = \\n The first time was the first time in'"449 ]450 },451 "execution_count": 41,452 "metadata": {},453 "output_type": "execute_result"454 }455 ],456 "source": [457 "prompt(\"Netherlands\")"458 ]459 },460 {461 "cell_type": "code",462 "execution_count": 42,463 "id": "fd2fc360-a4b5-4f70-8262-8dca7dbe2928",464 "metadata": {},465 "outputs": [466 {467 "name": "stderr",468 "output_type": "stream",469 "text": [470 "Setting `pad_token_id` to `eos_token_id`:50256 for open-end generation.\n"471 ]472 },473 {474 "data": {475 "text/plain": [476 "'Nvidia, and the first time of the first time, and the first time of the first time. The first time, the first time was the first time of the first time, and the first time was the first time. \\n = = = = = \\n The first time of the first season was the'"477 ]478 },479 "execution_count": 42,480 "metadata": {},481 "output_type": "execute_result"482 }483 ],484 "source": [485 "prompt(\"Nvidia\")"486 ]487 },488 {489 "cell_type": "code",490 "execution_count": 43,491 "id": "20572ca7-b109-4ab2-9e68-ad7c8e888708",492 "metadata": {},493 "outputs": [494 {495 "data": {496 "text/html": [497 "<table border=\"1\" class=\"dataframe\">\n",498 " <thead>\n",499 " <tr style=\"text-align: right;\">\n",500 " <th></th>\n",501 " <th>text</th>\n",502 " </tr>\n",503 " </thead>\n",504 " <tbody>\n",505 " <tr>\n",506 " <th>0</th>\n",507 " <td>Politically , Ireland is divided between the Republic of Ireland ( officially named Ireland ) , which covers five @-@ sixths of the island , and Northern Ireland , which is part of the United Kingdom , in the northeast of the island . In 2011 the population of Ireland was about 6 @.@ 4 million , ranking it the second @-@ most populous island in Europe after Great Britain . Just under 4 @.@ 6 million live in the Republic of Ireland and just over 1 @.@ 8 million live in Northern Ireland . \\n</td>\n",508 " </tr>\n",509 " <tr>\n",510 " <th>1</th>\n",511 " <td>The Great Coastal hurricane of 1806 was first noted far east of the Lesser Antilles on 17 August . Weather historian David M. Ludlum followed the disturbance 's track to the Bahamas by 19 August ; intense winds persisted until 21 August , however , approximately 150 mi ( 240 km ) east of the Bahamian island of Eleuthera . Steering currents brought the storm northward , and it approached Charleston , South Carolina on 22 August , where a generally easterly flow preceded the storm indicated its passage far east of the city . The hurricane made landfall at the mouth of the Cape Fear River in North Carolina later that day , though the earliest impacts from the storm started several days earlier , with gusts initially toward the northeast but later curving southwestward . Reports of similar wind shifts throughout the region suggested that the gale persisted , stationary , for several hours . It eventually moved back out to sea while south of Norfolk , Virginia , departing the region on 24 August . The hurricane maintained 1 @-@ minute maximum sustained winds of 110 mph ( 175 km / h ) while offshore , equivalent to a Category 2 system on the Saffir – Simpson hurricane wind scale . While offshore New England , the gale featured a swath of winds 90 mi ( 150 km ) wide , and was last observed just south of Nova Scotia on 25 August slightly weaker , with sustained winds of 75 mph ( 120 km / h ) . \\n</td>\n",512 " </tr>\n",513 " <tr>\n",514 " <th>2</th>\n",515 " <td></td>\n",516 " </tr>\n",517 " <tr>\n",518 " <th>3</th>\n",519 " <td></td>\n",520 " </tr>\n",521 " <tr>\n",522 " <th>4</th>\n",523 " <td></td>\n",524 " </tr>\n",525 " <tr>\n",526 " <th>5</th>\n",527 " <td>= = Service history = = \\n</td>\n",528 " </tr>\n",529 " <tr>\n",530 " <th>6</th>\n",531 " <td></td>\n",532 " </tr>\n",533 " <tr>\n",534 " <th>7</th>\n",535 " <td>= = Life = = \\n</td>\n",536 " </tr>\n",537 " <tr>\n",538 " <th>8</th>\n",539 " <td>= = Music video and live performances = = \\n</td>\n",540 " </tr>\n",541 " <tr>\n",542 " <th>9</th>\n",543 " <td>There were many reports of tropical storm @-@ force winds from ships in the north Atlantic . One ship , with the call sign GBSA , encountered Tanya 's winds twice and reported the strongest winds from any ship , 71 mph ( 112 km / h ) . \\n</td>\n",544 " </tr>\n",545 " </tbody>\n",546 "</table>"547 ],548 "text/plain": [549 "<IPython.core.display.HTML object>"550 ]551 },552 "metadata": {},553 "output_type": "display_data"554 }555 ],556 "source": [557 "show_random_elements(datasets[\"train\"])"558 ]559 },560 {561 "cell_type": "code",562 "execution_count": 44,563 "id": "b915acdd-0ebe-4e54-8c31-4417bf296368",564 "metadata": {},565 "outputs": [566 {567 "name": "stderr",568 "output_type": "stream",569 "text": [570 "Setting `pad_token_id` to `eos_token_id`:50256 for open-end generation.\n"571 ]572 },573 {574 "data": {575 "text/plain": [576 "\"The Great Coastal hurricane of 1806 was first noted far east of the Lesser Antilles on 17 August. Weather historian David M. Ludlum followed the disturbance's track to the Bahamas by 19 August ; the first time, the first time was the first time of the first time. \\n = = = = = \\n The first time of the first time was the first time of the first time, and was the first time of the first time of the first time. The first time, the first time\""577 ]578 },579 "execution_count": 44,580 "metadata": {},581 "output_type": "execute_result"582 }583 ],584 "source": [585 "prompt(\"The Great Coastal hurricane of 1806 was first noted far east of the Lesser Antilles on 17 August . Weather historian David M. Ludlum followed the disturbance 's track to the Bahamas by 19 August ;\")"586 ]587 },588 {589 "cell_type": "markdown",590 "id": "57564b2f-4b88-439d-900d-ddde71297f1c",591 "metadata": {},592 "source": [593 "# Mistral model"594 ]595 },596 {597 "cell_type": "code",598 "execution_count": null,599 "id": "5f5127fe-bf7a-419b-8a04-3858790cc5dd",600 "metadata": {601 "scrolled": true602 },603 "outputs": [604 {605 "name": "stderr",606 "output_type": "stream",607 "text": [608 "tokenizer_config.json: 100%|████████████████████████████████████████████████████████████| 967/967 [00:00<00:00, 433kB/s]\n",609 "tokenizer.model: 100%|███████████████████████████████████████████████████████████████| 493k/493k [00:00<00:00, 9.54MB/s]\n",610 "tokenizer.json: 100%|██████████████████████████████████████████████████████████████| 1.80M/1.80M [00:00<00:00, 5.80MB/s]\n",611 "special_tokens_map.json: 100%|███████████████████████████████████████████████████████| 72.0/72.0 [00:00<00:00, 72.7kB/s]\n",612 "config.json: 100%|██████████████████████████████████████████████████████████████████████| 571/571 [00:00<00:00, 200kB/s]\n",613 "pytorch_model.bin.index.json: 100%|████████████████████████████████████████████████| 23.9k/23.9k [00:00<00:00, 24.9MB/s]\n",614 "Downloading shards: 0%| | 0/2 [00:00<?, ?it/s]\n",615 "pytorch_model-00001-of-00002.bin: 0%| | 0.00/9.94G [00:00<?, ?B/s]\u001b[A\n",616 "pytorch_model-00001-of-00002.bin: 0%| | 10.5M/9.94G [00:00<15:06, 11.0MB/s]\u001b[A\n",617 "pytorch_model-00001-of-00002.bin: 0%| | 21.0M/9.94G [00:01<14:49, 11.2MB/s]\u001b[A\n",618 "pytorch_model-00001-of-00002.bin: 0%|▏ | 31.5M/9.94G [00:02<15:04, 11.0MB/s]\u001b[A\n",619 "pytorch_model-00001-of-00002.bin: 0%|▏ | 41.9M/9.94G [00:03<14:46, 11.2MB/s]\u001b[A\n",620 "pytorch_model-00001-of-00002.bin: 1%|▏ | 52.4M/9.94G [00:04<15:14, 10.8MB/s]\u001b[A\n",621 "pytorch_model-00001-of-00002.bin: 1%|▎ | 62.9M/9.94G [00:05<14:56, 11.0MB/s]\u001b[A\n",622 "pytorch_model-00001-of-00002.bin: 1%|▎ | 73.4M/9.94G [00:06<14:44, 11.2MB/s]\u001b[A\n",623 "pytorch_model-00001-of-00002.bin: 1%|▎ | 83.9M/9.94G [00:07<15:15, 10.8MB/s]\u001b[A\n",624 "pytorch_model-00001-of-00002.bin: 1%|▍ | 94.4M/9.94G [00:08<15:16, 10.7MB/s]\u001b[A\n",625 "pytorch_model-00001-of-00002.bin: 1%|▍ | 105M/9.94G [00:09<14:56, 11.0MB/s]\u001b[A\n",626 "pytorch_model-00001-of-00002.bin: 1%|▌ | 115M/9.94G [00:10<14:46, 11.1MB/s]\u001b[A\n",627 "pytorch_model-00001-of-00002.bin: 1%|▌ | 126M/9.94G [00:11<14:37, 11.2MB/s]\u001b[A\n",628 "pytorch_model-00001-of-00002.bin: 1%|▌ | 136M/9.94G [00:12<14:39, 11.1MB/s]\u001b[A\n",629 "pytorch_model-00001-of-00002.bin: 1%|▋ | 147M/9.94G [00:13<14:31, 11.2MB/s]\u001b[A\n",630 "pytorch_model-00001-of-00002.bin: 2%|▋ | 157M/9.94G [00:14<14:25, 11.3MB/s]\u001b[A\n",631 "pytorch_model-00001-of-00002.bin: 2%|▊ | 168M/9.94G [00:15<15:40, 10.4MB/s]\u001b[A\n",632 "pytorch_model-00001-of-00002.bin: 2%|▊ | 178M/9.94G [00:16<15:29, 10.5MB/s]\u001b[A\n",633 "pytorch_model-00001-of-00002.bin: 2%|▊ | 189M/9.94G [00:17<15:35, 10.4MB/s]\u001b[A\n",634 "pytorch_model-00001-of-00002.bin: 2%|▉ | 199M/9.94G [00:18<15:08, 10.7MB/s]\u001b[A\n",635 "pytorch_model-00001-of-00002.bin: 2%|▉ | 210M/9.94G [00:19<15:20, 10.6MB/s]\u001b[A\n",636 "pytorch_model-00001-of-00002.bin: 2%|▉ | 220M/9.94G [00:20<14:56, 10.8MB/s]\u001b[A\n",637 "pytorch_model-00001-of-00002.bin: 2%|█ | 231M/9.94G [00:21<14:43, 11.0MB/s]\u001b[A\n",638 "pytorch_model-00001-of-00002.bin: 2%|█ | 241M/9.94G [00:22<14:30, 11.1MB/s]\u001b[A\n",639 "pytorch_model-00001-of-00002.bin: 3%|█▏ | 252M/9.94G [00:23<14:33, 11.1MB/s]\u001b[A\n",640 "pytorch_model-00001-of-00002.bin: 3%|█▏ | 262M/9.94G [00:23<14:25, 11.2MB/s]\u001b[A\n",641 "pytorch_model-00001-of-00002.bin: 3%|█▏ | 273M/9.94G [00:24<14:19, 11.2MB/s]\u001b[A\n",642 "pytorch_model-00001-of-00002.bin: 3%|█▎ | 283M/9.94G [00:25<14:19, 11.2MB/s]\u001b[A\n",643 "pytorch_model-00001-of-00002.bin: 3%|█▎ | 294M/9.94G [00:26<14:14, 11.3MB/s]\u001b[A\n",644 "pytorch_model-00001-of-00002.bin: 3%|█▍ | 304M/9.94G [00:27<14:11, 11.3MB/s]\u001b[A\n",645 "pytorch_model-00001-of-00002.bin: 3%|█▍ | 315M/9.94G [00:28<14:16, 11.2MB/s]\u001b[A\n",646 "pytorch_model-00001-of-00002.bin: 3%|█▍ | 325M/9.94G [00:29<15:01, 10.7MB/s]\u001b[A\n",647 "pytorch_model-00001-of-00002.bin: 3%|█▌ | 336M/9.94G [00:30<14:46, 10.8MB/s]\u001b[A\n",648 "pytorch_model-00001-of-00002.bin: 3%|█▌ | 346M/9.94G [00:31<14:51, 10.8MB/s]\u001b[A\n",649 "pytorch_model-00001-of-00002.bin: 4%|█▌ | 357M/9.94G [00:32<15:16, 10.5MB/s]\u001b[A\n",650 "pytorch_model-00001-of-00002.bin: 4%|█▋ | 367M/9.94G [00:33<15:05, 10.6MB/s]\u001b[A\n",651 "pytorch_model-00001-of-00002.bin: 4%|█▋ | 377M/9.94G [00:34<14:54, 10.7MB/s]\u001b[A\n",652 "pytorch_model-00001-of-00002.bin: 4%|█▊ | 388M/9.94G [00:35<14:50, 10.7MB/s]\u001b[A\n",653 "pytorch_model-00001-of-00002.bin: 4%|█▊ | 398M/9.94G [00:36<14:32, 10.9MB/s]\u001b[A\n",654 "pytorch_model-00001-of-00002.bin: 4%|█▊ | 409M/9.94G [00:37<14:21, 11.1MB/s]\u001b[A\n",655 "pytorch_model-00001-of-00002.bin: 4%|█▉ | 419M/9.94G [00:38<14:12, 11.2MB/s]\u001b[A\n",656 "pytorch_model-00001-of-00002.bin: 4%|█▉ | 430M/9.94G [00:39<14:06, 11.2MB/s]\u001b[A\n",657 "pytorch_model-00001-of-00002.bin: 4%|█▉ | 440M/9.94G [00:40<14:02, 11.3MB/s]\u001b[A\n",658 "pytorch_model-00001-of-00002.bin: 5%|██ | 451M/9.94G [00:41<13:56, 11.3MB/s]\u001b[A\n",659 "pytorch_model-00001-of-00002.bin: 5%|██ | 461M/9.94G [00:41<13:53, 11.4MB/s]\u001b[A\n",660 "pytorch_model-00001-of-00002.bin: 5%|██▏ | 472M/9.94G [00:42<13:50, 11.4MB/s]\u001b[A\n",661 "pytorch_model-00001-of-00002.bin: 5%|██▏ | 482M/9.94G [00:43<13:47, 11.4MB/s]\u001b[A\n",662 "pytorch_model-00001-of-00002.bin: 5%|██▏ | 493M/9.94G [00:44<14:42, 10.7MB/s]\u001b[A\n",663 "pytorch_model-00001-of-00002.bin: 5%|██▎ | 503M/9.94G [00:45<14:19, 11.0MB/s]\u001b[A\n",664 "pytorch_model-00001-of-00002.bin: 5%|██▎ | 514M/9.94G [00:46<14:07, 11.1MB/s]\u001b[A\n",665 "pytorch_model-00001-of-00002.bin: 5%|██▎ | 524M/9.94G [00:47<13:59, 11.2MB/s]\u001b[A\n",666 "pytorch_model-00001-of-00002.bin: 5%|██▍ | 535M/9.94G [00:48<13:52, 11.3MB/s]\u001b[A\n",667 "pytorch_model-00001-of-00002.bin: 5%|██▍ | 545M/9.94G [00:49<13:48, 11.3MB/s]\u001b[A\n",668 "pytorch_model-00001-of-00002.bin: 6%|██▌ | 556M/9.94G [00:50<13:45, 11.4MB/s]\u001b[A\n",669 "pytorch_model-00001-of-00002.bin: 6%|██▌ | 566M/9.94G [00:51<13:42, 11.4MB/s]\u001b[A\n",670 "pytorch_model-00001-of-00002.bin: 6%|██▌ | 577M/9.94G [00:52<13:38, 11.4MB/s]\u001b[A\n",671 "pytorch_model-00001-of-00002.bin: 6%|██▋ | 587M/9.94G [00:53<13:37, 11.4MB/s]\u001b[A\n",672 "pytorch_model-00001-of-00002.bin: 6%|██▋ | 598M/9.94G [00:54<13:37, 11.4MB/s]\u001b[A\n",673 "pytorch_model-00001-of-00002.bin: 6%|██▊ | 608M/9.94G [00:55<14:26, 10.8MB/s]\u001b[A\n",674 "pytorch_model-00001-of-00002.bin: 6%|██▊ | 619M/9.94G [00:56<14:11, 11.0MB/s]\u001b[A\n",675 "pytorch_model-00001-of-00002.bin: 6%|██▊ | 629M/9.94G [00:56<13:57, 11.1MB/s]\u001b[A\n",676 "pytorch_model-00001-of-00002.bin: 6%|██▉ | 640M/9.94G [00:57<13:49, 11.2MB/s]\u001b[A\n",677 "pytorch_model-00001-of-00002.bin: 7%|██▉ | 650M/9.94G [00:58<13:45, 11.3MB/s]\u001b[A\n",678 "pytorch_model-00001-of-00002.bin: 7%|██▉ | 661M/9.94G [00:59<13:37, 11.4MB/s]\u001b[A\n",679 "pytorch_model-00001-of-00002.bin: 7%|███ | 671M/9.94G [01:00<13:36, 11.4MB/s]\u001b[A\n",680 "pytorch_model-00001-of-00002.bin: 7%|███ | 682M/9.94G [01:01<13:42, 11.3MB/s]\u001b[A\n",681 "pytorch_model-00001-of-00002.bin: 7%|███▏ | 692M/9.94G [01:02<13:47, 11.2MB/s]\u001b[A\n",682 "pytorch_model-00001-of-00002.bin: 7%|███▏ | 703M/9.94G [01:03<13:41, 11.2MB/s]\u001b[A\n",683 "pytorch_model-00001-of-00002.bin: 7%|███▏ | 713M/9.94G [01:04<13:36, 11.3MB/s]\u001b[A\n",684 "pytorch_model-00001-of-00002.bin: 7%|███▎ | 724M/9.94G [01:05<13:32, 11.4MB/s]\u001b[A\n",685 "pytorch_model-00001-of-00002.bin: 7%|███▎ | 734M/9.94G [01:06<13:29, 11.4MB/s]\u001b[A\n",686 "pytorch_model-00001-of-00002.bin: 7%|███▎ | 744M/9.94G [01:07<13:25, 11.4MB/s]\u001b[A\n",687 "pytorch_model-00001-of-00002.bin: 8%|███▍ | 755M/9.94G [01:08<13:24, 11.4MB/s]\u001b[A\n",688 "pytorch_model-00001-of-00002.bin: 8%|███▍ | 765M/9.94G [01:08<13:21, 11.5MB/s]\u001b[A\n",689 "pytorch_model-00001-of-00002.bin: 8%|███▌ | 776M/9.94G [01:10<14:08, 10.8MB/s]\u001b[A\n",690 "pytorch_model-00001-of-00002.bin: 8%|███▌ | 786M/9.94G [01:10<13:54, 11.0MB/s]\u001b[A\n",691 "pytorch_model-00001-of-00002.bin: 8%|███▌ | 797M/9.94G [01:11<13:40, 11.1MB/s]\u001b[A\n",692 "pytorch_model-00001-of-00002.bin: 8%|███▋ | 807M/9.94G [01:12<13:35, 11.2MB/s]\u001b[A\n",693 "pytorch_model-00001-of-00002.bin: 8%|███▋ | 818M/9.94G [01:13<13:26, 11.3MB/s]\u001b[A\n",694 "pytorch_model-00001-of-00002.bin: 8%|███▋ | 828M/9.94G [01:14<13:24, 11.3MB/s]\u001b[A\n",695 "pytorch_model-00001-of-00002.bin: 8%|███▊ | 839M/9.94G [01:15<13:20, 11.4MB/s]\u001b[A\n",696 "pytorch_model-00001-of-00002.bin: 9%|███▊ | 849M/9.94G [01:16<13:56, 10.9MB/s]\u001b[A\n",697 "pytorch_model-00001-of-00002.bin: 9%|███▉ | 860M/9.94G [01:17<13:52, 10.9MB/s]\u001b[A\n",698 "pytorch_model-00001-of-00002.bin: 9%|███▉ | 870M/9.94G [01:18<13:41, 11.0MB/s]\u001b[A\n",699 "pytorch_model-00001-of-00002.bin: 9%|███▉ | 881M/9.94G [01:19<13:58, 10.8MB/s]\u001b[A\n",700 "pytorch_model-00001-of-00002.bin: 9%|████ | 891M/9.94G [01:20<13:51, 10.9MB/s]\u001b[A\n",701 "pytorch_model-00001-of-00002.bin: 9%|████ | 902M/9.94G [01:21<13:38, 11.0MB/s]\u001b[A\n",702 "pytorch_model-00001-of-00002.bin: 9%|████▏ | 912M/9.94G [01:22<13:56, 10.8MB/s]\u001b[A\n",703 "pytorch_model-00001-of-00002.bin: 9%|████▏ | 923M/9.94G [01:23<13:51, 10.9MB/s]\u001b[A\n",704 "pytorch_model-00001-of-00002.bin: 9%|████▏ | 933M/9.94G [01:24<13:36, 11.0MB/s]\u001b[A\n",705 "pytorch_model-00001-of-00002.bin: 9%|████▎ | 944M/9.94G [01:25<13:25, 11.2MB/s]\u001b[A\n",706 "pytorch_model-00001-of-00002.bin: 10%|████▎ | 954M/9.94G [01:26<13:17, 11.3MB/s]\u001b[A\n",707 "pytorch_model-00001-of-00002.bin: 10%|████▎ | 965M/9.94G [01:27<14:02, 10.7MB/s]\u001b[A\n",708 "pytorch_model-00001-of-00002.bin: 10%|████▍ | 975M/9.94G [01:28<14:12, 10.5MB/s]\u001b[A\n",709 "pytorch_model-00001-of-00002.bin: 10%|████▍ | 986M/9.94G [01:29<13:49, 10.8MB/s]\u001b[A\n",710 "pytorch_model-00001-of-00002.bin: 10%|████▌ | 996M/9.94G [01:30<14:10, 10.5MB/s]\u001b[A\n",711 "pytorch_model-00001-of-00002.bin: 10%|████▍ | 1.01G/9.94G [01:31<15:15, 9.76MB/s]\u001b[A\n",712 "pytorch_model-00001-of-00002.bin: 10%|████▌ | 1.02G/9.94G [01:32<15:37, 9.52MB/s]\u001b[A\n",713 "pytorch_model-00001-of-00002.bin: 10%|████▌ | 1.03G/9.94G [01:33<14:49, 10.0MB/s]\u001b[A\n",714 "pytorch_model-00001-of-00002.bin: 10%|████▌ | 1.04G/9.94G [01:34<14:20, 10.4MB/s]\u001b[A\n",715 "pytorch_model-00001-of-00002.bin: 11%|████▋ | 1.05G/9.94G [01:35<13:59, 10.6MB/s]\u001b[A\n",716 "pytorch_model-00001-of-00002.bin: 11%|████▋ | 1.06G/9.94G [01:36<13:38, 10.9MB/s]\u001b[A\n",717 "pytorch_model-00001-of-00002.bin: 11%|████▋ | 1.07G/9.94G [01:37<13:23, 11.0MB/s]\u001b[A\n",718 "pytorch_model-00001-of-00002.bin: 11%|████▊ | 1.08G/9.94G [01:38<13:43, 10.8MB/s]\u001b[A\n",719 "pytorch_model-00001-of-00002.bin: 11%|████▊ | 1.09G/9.94G [01:39<13:35, 10.9MB/s]\u001b[A\n",720 "pytorch_model-00001-of-00002.bin: 11%|████▊ | 1.10G/9.94G [01:40<13:46, 10.7MB/s]\u001b[A\n",721 "pytorch_model-00001-of-00002.bin: 11%|████▉ | 1.11G/9.94G [01:41<13:35, 10.8MB/s]\u001b[A\n",722 "pytorch_model-00001-of-00002.bin: 11%|████▉ | 1.12G/9.94G [01:42<13:29, 10.9MB/s]\u001b[A\n",723 "pytorch_model-00001-of-00002.bin: 11%|█████ | 1.13G/9.94G [01:43<13:44, 10.7MB/s]\u001b[A\n",724 "pytorch_model-00001-of-00002.bin: 11%|█████ | 1.14G/9.94G [01:44<13:25, 10.9MB/s]\u001b[A\n",725 "pytorch_model-00001-of-00002.bin: 12%|█████ | 1.15G/9.94G [01:44<13:11, 11.1MB/s]\u001b[A\n",726 "pytorch_model-00001-of-00002.bin: 12%|█████▏ | 1.16G/9.94G [01:45<13:05, 11.2MB/s]\u001b[A\n",727 "pytorch_model-00001-of-00002.bin: 12%|█████▏ | 1.17G/9.94G [01:46<12:56, 11.3MB/s]\u001b[A\n",728 "pytorch_model-00001-of-00002.bin: 12%|█████▏ | 1.18G/9.94G [01:47<12:55, 11.3MB/s]\u001b[A\n",729 "pytorch_model-00001-of-00002.bin: 12%|█████▎ | 1.20G/9.94G [01:48<12:57, 11.2MB/s]\u001b[A\n",730 "pytorch_model-00001-of-00002.bin: 12%|█████▎ | 1.21G/9.94G [01:49<13:06, 11.1MB/s]\u001b[A\n",731 "pytorch_model-00001-of-00002.bin: 12%|█████▍ | 1.22G/9.94G [01:50<13:47, 10.5MB/s]\u001b[A\n",732 "pytorch_model-00001-of-00002.bin: 12%|█████▍ | 1.23G/9.94G [01:51<13:25, 10.8MB/s]\u001b[A\n",733 "pytorch_model-00001-of-00002.bin: 12%|█████▍ | 1.24G/9.94G [01:52<13:11, 11.0MB/s]\u001b[A\n",734 "pytorch_model-00001-of-00002.bin: 13%|█████▌ | 1.25G/9.94G [01:53<13:00, 11.1MB/s]\u001b[A\n",735 "pytorch_model-00001-of-00002.bin: 13%|█████▌ | 1.26G/9.94G [01:54<12:52, 11.2MB/s]\u001b[A\n",736 "pytorch_model-00001-of-00002.bin: 13%|█████▌ | 1.27G/9.94G [01:55<12:47, 11.3MB/s]\u001b[A\n",737 "pytorch_model-00001-of-00002.bin: 13%|█████▋ | 1.28G/9.94G [01:56<13:31, 10.7MB/s]\u001b[A\n",738 "pytorch_model-00001-of-00002.bin: 13%|█████▋ | 1.29G/9.94G [01:57<13:13, 10.9MB/s]\u001b[A\n",739 "pytorch_model-00001-of-00002.bin: 13%|█████▊ | 1.30G/9.94G [01:58<13:00, 11.1MB/s]\u001b[A\n",740 "pytorch_model-00001-of-00002.bin: 13%|█████▊ | 1.31G/9.94G [01:59<13:00, 11.1MB/s]\u001b[A\n",741 "pytorch_model-00001-of-00002.bin: 13%|█████▊ | 1.32G/9.94G [02:00<12:51, 11.2MB/s]\u001b[A\n",742 "pytorch_model-00001-of-00002.bin: 13%|█████▉ | 1.33G/9.94G [02:01<13:16, 10.8MB/s]\u001b[A\n",743 "pytorch_model-00001-of-00002.bin: 13%|█████▉ | 1.34G/9.94G [02:02<12:57, 11.1MB/s]\u001b[A\n",744 "pytorch_model-00001-of-00002.bin: 14%|█████▉ | 1.35G/9.94G [02:03<13:32, 10.6MB/s]\u001b[A\n",745 "pytorch_model-00001-of-00002.bin: 14%|██████ | 1.36G/9.94G [02:04<13:14, 10.8MB/s]\u001b[A\n",746 "pytorch_model-00001-of-00002.bin: 14%|██████ | 1.37G/9.94G [02:04<12:59, 11.0MB/s]\u001b[A\n",747 "pytorch_model-00001-of-00002.bin: 14%|██████▏ | 1.38G/9.94G [02:05<12:51, 11.1MB/s]\u001b[A\n",748 "pytorch_model-00001-of-00002.bin: 14%|██████▏ | 1.39G/9.94G [02:06<13:25, 10.6MB/s]\u001b[A\n",749 "pytorch_model-00001-of-00002.bin: 14%|██████▏ | 1.41G/9.94G [02:07<13:06, 10.9MB/s]\u001b[A\n",750 "pytorch_model-00001-of-00002.bin: 14%|██████▎ | 1.42G/9.94G [02:09<13:46, 10.3MB/s]\u001b[A\n",751 "pytorch_model-00001-of-00002.bin: 14%|██████▎ | 1.43G/9.94G [02:10<13:32, 10.5MB/s]\u001b[A\n",752 "pytorch_model-00001-of-00002.bin: 14%|██████▎ | 1.44G/9.94G [02:11<13:37, 10.4MB/s]\u001b[A\n",753 "pytorch_model-00001-of-00002.bin: 15%|██████▍ | 1.45G/9.94G [02:11<13:18, 10.6MB/s]\u001b[A\n",754 "pytorch_model-00001-of-00002.bin: 15%|██████▍ | 1.46G/9.94G [02:12<13:06, 10.8MB/s]\u001b[A\n",755 "pytorch_model-00001-of-00002.bin: 15%|██████▍ | 1.47G/9.94G [02:13<12:51, 11.0MB/s]\u001b[A\n",756 "pytorch_model-00001-of-00002.bin: 15%|██████▌ | 1.48G/9.94G [02:14<12:50, 11.0MB/s]\u001b[A\n",757 "pytorch_model-00001-of-00002.bin: 15%|██████▌ | 1.49G/9.94G [02:15<12:49, 11.0MB/s]\u001b[A\n",758 "pytorch_model-00001-of-00002.bin: 15%|██████▋ | 1.50G/9.94G [02:16<13:37, 10.3MB/s]\u001b[A\n",759 "pytorch_model-00001-of-00002.bin: 15%|██████▋ | 1.51G/9.94G [02:17<13:12, 10.6MB/s]\u001b[A\n",760 "pytorch_model-00001-of-00002.bin: 15%|██████▋ | 1.52G/9.94G [02:18<13:04, 10.7MB/s]\u001b[A\n",761 "pytorch_model-00001-of-00002.bin: 15%|██████▊ | 1.53G/9.94G [02:19<13:32, 10.4MB/s]\u001b[A\n",762 "pytorch_model-00001-of-00002.bin: 16%|██████▊ | 1.54G/9.94G [02:20<13:07, 10.7MB/s]\u001b[A\n",763 "pytorch_model-00001-of-00002.bin: 16%|██████▊ | 1.55G/9.94G [02:21<12:49, 10.9MB/s]\u001b[A\n",764 "pytorch_model-00001-of-00002.bin: 16%|██████▉ | 1.56G/9.94G [02:22<12:47, 10.9MB/s]\u001b[A\n",765 "pytorch_model-00001-of-00002.bin: 16%|██████▉ | 1.57G/9.94G [02:23<12:31, 11.1MB/s]\u001b[A\n",766 "pytorch_model-00001-of-00002.bin: 16%|███████ | 1.58G/9.94G [02:24<12:36, 11.1MB/s]\u001b[A\n",767 "pytorch_model-00001-of-00002.bin: 16%|███████ | 1.59G/9.94G [02:25<12:40, 11.0MB/s]\u001b[A\n",768 "pytorch_model-00001-of-00002.bin: 16%|███████ | 1.60G/9.94G [02:26<12:32, 11.1MB/s]\u001b[A\n",769 "pytorch_model-00001-of-00002.bin: 16%|███████▏ | 1.61G/9.94G [02:27<12:43, 10.9MB/s]\u001b[A\n",770 "pytorch_model-00001-of-00002.bin: 16%|███████▏ | 1.63G/9.94G [02:28<12:38, 11.0MB/s]\u001b[A\n",771 "pytorch_model-00001-of-00002.bin: 16%|███████▏ | 1.64G/9.94G [02:29<12:35, 11.0MB/s]\u001b[A\n",772 "pytorch_model-00001-of-00002.bin: 17%|███████▎ | 1.65G/9.94G [02:30<12:24, 11.1MB/s]\u001b[A\n",773 "pytorch_model-00001-of-00002.bin: 17%|███████▎ | 1.66G/9.94G [02:31<12:17, 11.2MB/s]\u001b[A\n",774 "pytorch_model-00001-of-00002.bin: 17%|███████▍ | 1.67G/9.94G [02:32<12:11, 11.3MB/s]\u001b[A\n",775 "pytorch_model-00001-of-00002.bin: 17%|███████▍ | 1.68G/9.94G [02:32<12:14, 11.2MB/s]\u001b[A\n",776 "pytorch_model-00001-of-00002.bin: 17%|███████▍ | 1.69G/9.94G [02:33<12:09, 11.3MB/s]\u001b[A\n",777 "pytorch_model-00001-of-00002.bin: 17%|███████▌ | 1.70G/9.94G [02:34<12:16, 11.2MB/s]\u001b[A\n",778 "pytorch_model-00001-of-00002.bin: 17%|███████▌ | 1.71G/9.94G [02:35<12:08, 11.3MB/s]\u001b[A\n",779 "pytorch_model-00001-of-00002.bin: 17%|███████▌ | 1.72G/9.94G [02:36<12:11, 11.2MB/s]\u001b[A\n",780 "pytorch_model-00001-of-00002.bin: 17%|███████▋ | 1.73G/9.94G [02:37<12:08, 11.3MB/s]\u001b[A\n",781 "pytorch_model-00001-of-00002.bin: 18%|███████▋ | 1.74G/9.94G [02:38<12:04, 11.3MB/s]\u001b[A\n",782 "pytorch_model-00001-of-00002.bin: 18%|███████▋ | 1.75G/9.94G [02:39<12:01, 11.4MB/s]\u001b[A\n",783 "pytorch_model-00001-of-00002.bin: 18%|███████▊ | 1.76G/9.94G [02:40<12:06, 11.3MB/s]\u001b[A\n",784 "pytorch_model-00001-of-00002.bin: 18%|███████▊ | 1.77G/9.94G [02:41<12:11, 11.2MB/s]\u001b[A\n",785 "pytorch_model-00001-of-00002.bin: 18%|███████▉ | 1.78G/9.94G [02:42<12:05, 11.2MB/s]\u001b[A\n",786 "pytorch_model-00001-of-00002.bin: 18%|███████▉ | 1.79G/9.94G [02:43<12:01, 11.3MB/s]\u001b[A\n",787 "pytorch_model-00001-of-00002.bin: 18%|███████▉ | 1.80G/9.94G [02:44<11:56, 11.4MB/s]\u001b[A\n",788 "pytorch_model-00001-of-00002.bin: 18%|████████ | 1.81G/9.94G [02:45<12:46, 10.6MB/s]\u001b[A\n",789 "pytorch_model-00001-of-00002.bin: 18%|████████ | 1.82G/9.94G [02:46<12:25, 10.9MB/s]\u001b[A\n",790 "pytorch_model-00001-of-00002.bin: 18%|████████ | 1.84G/9.94G [02:47<12:15, 11.0MB/s]\u001b[A\n",791 "pytorch_model-00001-of-00002.bin: 19%|████████▏ | 1.85G/9.94G [02:47<12:08, 11.1MB/s]\u001b[A\n",792 "pytorch_model-00001-of-00002.bin: 19%|████████▏ | 1.86G/9.94G [02:48<11:57, 11.3MB/s]\u001b[A\n",793 "pytorch_model-00001-of-00002.bin: 19%|████████▎ | 1.87G/9.94G [02:49<11:54, 11.3MB/s]\u001b[A\n",794 "pytorch_model-00001-of-00002.bin: 19%|████████▎ | 1.88G/9.94G [02:50<11:50, 11.3MB/s]\u001b[A\n",795 "pytorch_model-00001-of-00002.bin: 19%|████████▎ | 1.89G/9.94G [02:51<11:46, 11.4MB/s]\u001b[A\n",796 "pytorch_model-00001-of-00002.bin: 19%|████████▍ | 1.90G/9.94G [02:52<11:45, 11.4MB/s]\u001b[A\n",797 "pytorch_model-00001-of-00002.bin: 19%|████████▍ | 1.91G/9.94G [02:53<11:45, 11.4MB/s]\u001b[A\n",798 "pytorch_model-00001-of-00002.bin: 19%|████████▍ | 1.92G/9.94G [02:54<11:44, 11.4MB/s]\u001b[A\n",799 "pytorch_model-00001-of-00002.bin: 19%|████████▌ | 1.93G/9.94G [02:55<12:29, 10.7MB/s]\u001b[A\n",800 "pytorch_model-00001-of-00002.bin: 20%|████████▌ | 1.94G/9.94G [02:56<12:14, 10.9MB/s]\u001b[A\n",801 "pytorch_model-00001-of-00002.bin: 20%|████████▋ | 1.95G/9.94G [02:57<12:04, 11.0MB/s]\u001b[A\n",802 "pytorch_model-00001-of-00002.bin: 20%|████████▋ | 1.96G/9.94G [02:58<11:55, 11.1MB/s]\u001b[A\n",803 "pytorch_model-00001-of-00002.bin: 20%|████████▋ | 1.97G/9.94G [02:59<11:51, 11.2MB/s]\u001b[A\n",804 "pytorch_model-00001-of-00002.bin: 20%|████████▊ | 1.98G/9.94G [03:00<11:43, 11.3MB/s]\u001b[A\n",805 "pytorch_model-00001-of-00002.bin: 20%|████████▊ | 1.99G/9.94G [03:01<11:39, 11.4MB/s]\u001b[A\n",806 "pytorch_model-00001-of-00002.bin: 20%|████████▊ | 2.00G/9.94G [03:01<11:37, 11.4MB/s]\u001b[A\n",807 "pytorch_model-00001-of-00002.bin: 20%|████████▉ | 2.01G/9.94G [03:02<11:35, 11.4MB/s]\u001b[A\n",808 "pytorch_model-00001-of-00002.bin: 20%|████████▉ | 2.02G/9.94G [03:03<11:33, 11.4MB/s]\u001b[A\n",809 "pytorch_model-00001-of-00002.bin: 20%|█████████ | 2.03G/9.94G [03:04<11:29, 11.5MB/s]\u001b[A\n",810 "pytorch_model-00001-of-00002.bin: 21%|█████████ | 2.04G/9.94G [03:05<12:11, 10.8MB/s]\u001b[A\n",811 "pytorch_model-00001-of-00002.bin: 21%|█████████ | 2.06G/9.94G [03:06<11:56, 11.0MB/s]\u001b[A\n",812 "pytorch_model-00001-of-00002.bin: 21%|█████████▏ | 2.07G/9.94G [03:07<11:49, 11.1MB/s]\u001b[A\n",813 "pytorch_model-00001-of-00002.bin: 21%|█████████▏ | 2.08G/9.94G [03:08<11:44, 11.2MB/s]\u001b[A\n",814 "pytorch_model-00001-of-00002.bin: 21%|█████████▏ | 2.09G/9.94G [03:09<11:37, 11.3MB/s]\u001b[A\n",815 "pytorch_model-00001-of-00002.bin: 21%|█████████▎ | 2.10G/9.94G [03:10<11:30, 11.4MB/s]\u001b[A\n",816 "pytorch_model-00001-of-00002.bin: 21%|█████████▎ | 2.11G/9.94G [03:11<11:31, 11.3MB/s]\u001b[A\n",817 "pytorch_model-00001-of-00002.bin: 21%|█████████▎ | 2.12G/9.94G [03:12<11:27, 11.4MB/s]\u001b[A\n",818 "pytorch_model-00001-of-00002.bin: 21%|█████████▍ | 2.13G/9.94G [03:13<11:25, 11.4MB/s]\u001b[A\n",819 "pytorch_model-00001-of-00002.bin: 22%|█████████▍ | 2.14G/9.94G [03:14<11:24, 11.4MB/s]\u001b[A\n",820 "pytorch_model-00001-of-00002.bin: 22%|█████████▌ | 2.15G/9.94G [03:14<11:21, 11.4MB/s]\u001b[A\n",821 "pytorch_model-00001-of-00002.bin: 22%|█████████▌ | 2.16G/9.94G [03:16<12:02, 10.8MB/s]\u001b[A\n",822 "pytorch_model-00001-of-00002.bin: 22%|█████████▌ | 2.17G/9.94G [03:16<11:48, 11.0MB/s]\u001b[A\n",823 "pytorch_model-00001-of-00002.bin: 22%|█████████▋ | 2.18G/9.94G [03:17<11:38, 11.1MB/s]\u001b[A\n",824 "pytorch_model-00001-of-00002.bin: 22%|█████████▋ | 2.19G/9.94G [03:18<11:32, 11.2MB/s]\u001b[A\n",825 "pytorch_model-00001-of-00002.bin: 22%|█████████▋ | 2.20G/9.94G [03:19<11:25, 11.3MB/s]\u001b[A\n",826 "pytorch_model-00001-of-00002.bin: 22%|█████████▊ | 2.21G/9.94G [03:20<11:24, 11.3MB/s]\u001b[A\n",827 "pytorch_model-00001-of-00002.bin: 22%|█████████▊ | 2.22G/9.94G [03:21<11:17, 11.4MB/s]\u001b[A\n",828 "pytorch_model-00001-of-00002.bin: 22%|█████████▉ | 2.23G/9.94G [03:22<11:15, 11.4MB/s]\u001b[A\n",829 "pytorch_model-00001-of-00002.bin: 23%|█████████▉ | 2.24G/9.94G [03:23<11:14, 11.4MB/s]\u001b[A\n",830 "pytorch_model-00001-of-00002.bin: 23%|█████████▉ | 2.25G/9.94G [03:24<11:12, 11.4MB/s]\u001b[A\n",831 "pytorch_model-00001-of-00002.bin: 23%|██████████ | 2.26G/9.94G [03:25<11:10, 11.4MB/s]\u001b[A\n",832 "pytorch_model-00001-of-00002.bin: 23%|██████████ | 2.28G/9.94G [03:26<11:50, 10.8MB/s]\u001b[A\n",833 "pytorch_model-00001-of-00002.bin: 23%|██████████ | 2.29G/9.94G [03:27<11:36, 11.0MB/s]\u001b[A\n",834 "pytorch_model-00001-of-00002.bin: 23%|██████████▏ | 2.30G/9.94G [03:28<11:26, 11.1MB/s]\u001b[A\n",835 "pytorch_model-00001-of-00002.bin: 23%|██████████▏ | 2.31G/9.94G [03:29<11:19, 11.2MB/s]\u001b[A\n",836 "pytorch_model-00001-of-00002.bin: 23%|██████████▎ | 2.32G/9.94G [03:29<11:14, 11.3MB/s]\u001b[A\n",837 "pytorch_model-00001-of-00002.bin: 23%|██████████▎ | 2.33G/9.94G [03:30<11:15, 11.3MB/s]\u001b[A\n",838 "pytorch_model-00001-of-00002.bin: 24%|██████████▎ | 2.34G/9.94G [03:31<11:14, 11.3MB/s]\u001b[A\n",839 "pytorch_model-00001-of-00002.bin: 24%|██████████▍ | 2.35G/9.94G [03:32<11:09, 11.3MB/s]\u001b[A\n",840 "pytorch_model-00001-of-00002.bin: 24%|██████████▍ | 2.36G/9.94G [03:33<11:05, 11.4MB/s]\u001b[A\n",841 "pytorch_model-00001-of-00002.bin: 24%|██████████▍ | 2.37G/9.94G [03:34<12:22, 10.2MB/s]\u001b[A\n",842 "pytorch_model-00001-of-00002.bin: 24%|██████████▌ | 2.38G/9.94G [03:35<12:25, 10.1MB/s]\u001b[A\n",843 "pytorch_model-00001-of-00002.bin: 24%|██████████▌ | 2.39G/9.94G [03:36<12:07, 10.4MB/s]\u001b[A\n",844 "pytorch_model-00001-of-00002.bin: 24%|██████████▋ | 2.40G/9.94G [03:37<11:54, 10.6MB/s]\u001b[A\n",845 "pytorch_model-00001-of-00002.bin: 24%|██████████▋ | 2.41G/9.94G [03:38<11:36, 10.8MB/s]\u001b[A\n",846 "pytorch_model-00001-of-00002.bin: 24%|██████████▋ | 2.42G/9.94G [03:39<11:40, 10.7MB/s]\u001b[A\n",847 "pytorch_model-00001-of-00002.bin: 24%|██████████▊ | 2.43G/9.94G [03:40<11:52, 10.5MB/s]\u001b[A\n",848 "pytorch_model-00001-of-00002.bin: 25%|██████████▊ | 2.44G/9.94G [03:41<11:30, 10.9MB/s]\u001b[A\n",849 "pytorch_model-00001-of-00002.bin: 25%|██████████▊ | 2.45G/9.94G [03:42<11:20, 11.0MB/s]\u001b[A\n",850 "pytorch_model-00001-of-00002.bin: 25%|██████████▉ | 2.46G/9.94G [03:43<11:28, 10.9MB/s]\u001b[A\n",851 "pytorch_model-00001-of-00002.bin: 25%|██████████▉ | 2.47G/9.94G [03:44<11:27, 10.9MB/s]\u001b[A\n",852 "pytorch_model-00001-of-00002.bin: 25%|██████████▉ | 2.49G/9.94G [03:45<12:20, 10.1MB/s]\u001b[A\n",853 "pytorch_model-00001-of-00002.bin: 25%|███████████ | 2.50G/9.94G [03:46<12:08, 10.2MB/s]\u001b[A\n",854 "pytorch_model-00001-of-00002.bin: 25%|███████████ | 2.51G/9.94G [03:47<11:59, 10.3MB/s]\u001b[A\n",855 "pytorch_model-00001-of-00002.bin: 25%|███████████▏ | 2.52G/9.94G [03:48<11:46, 10.5MB/s]\u001b[A\n",856 "pytorch_model-00001-of-00002.bin: 25%|███████████▏ | 2.53G/9.94G [03:49<11:27, 10.8MB/s]\u001b[A\n",857 "pytorch_model-00001-of-00002.bin: 26%|███████████▏ | 2.54G/9.94G [03:50<11:13, 11.0MB/s]\u001b[A\n",858 "pytorch_model-00001-of-00002.bin: 26%|███████████▎ | 2.55G/9.94G [03:51<11:02, 11.2MB/s]\u001b[A\n",859 "pytorch_model-00001-of-00002.bin: 26%|███████████▎ | 2.56G/9.94G [03:52<10:56, 11.3MB/s]\u001b[A\n",860 "pytorch_model-00001-of-00002.bin: 26%|███████████▎ | 2.57G/9.94G [03:53<11:21, 10.8MB/s]\u001b[A\n",861 "pytorch_model-00001-of-00002.bin: 26%|███████████▍ | 2.58G/9.94G [03:54<11:08, 11.0MB/s]\u001b[A\n",862 "pytorch_model-00001-of-00002.bin: 26%|███████████▍ | 2.59G/9.94G [03:55<11:00, 11.1MB/s]\u001b[A\n",863 "pytorch_model-00001-of-00002.bin: 26%|███████████▌ | 2.60G/9.94G [03:56<10:52, 11.2MB/s]\u001b[A\n",864 "pytorch_model-00001-of-00002.bin: 26%|███████████▌ | 2.61G/9.94G [03:57<11:27, 10.7MB/s]\u001b[A\n",865 "pytorch_model-00001-of-00002.bin: 26%|███████████▌ | 2.62G/9.94G [03:58<11:10, 10.9MB/s]\u001b[A\n",866 "pytorch_model-00001-of-00002.bin: 26%|███████████▋ | 2.63G/9.94G [03:59<11:03, 11.0MB/s]\u001b[A\n",867 "pytorch_model-00001-of-00002.bin: 27%|███████████▋ | 2.64G/9.94G [04:00<10:53, 11.2MB/s]\u001b[A\n",868 "pytorch_model-00001-of-00002.bin: 27%|███████████▋ | 2.65G/9.94G [04:00<10:46, 11.3MB/s]\u001b[A\n",869 "pytorch_model-00001-of-00002.bin: 27%|███████████▊ | 2.66G/9.94G [04:01<10:42, 11.3MB/s]\u001b[A\n",870 "pytorch_model-00001-of-00002.bin: 27%|███████████▊ | 2.67G/9.94G [04:02<11:14, 10.8MB/s]\u001b[A\n",871 "pytorch_model-00001-of-00002.bin: 27%|███████████▉ | 2.68G/9.94G [04:04<11:31, 10.5MB/s]\u001b[A\n",872 "pytorch_model-00001-of-00002.bin: 27%|███████████▉ | 2.69G/9.94G [04:05<11:30, 10.5MB/s]\u001b[A\n",873 "pytorch_model-00001-of-00002.bin: 27%|███████████▉ | 2.71G/9.94G [04:05<11:12, 10.8MB/s]\u001b[A\n",874 "pytorch_model-00001-of-00002.bin: 27%|████████████ | 2.72G/9.94G [04:06<10:59, 11.0MB/s]\u001b[A\n",875 "pytorch_model-00001-of-00002.bin: 27%|████████████ | 2.73G/9.94G [04:07<10:51, 11.1MB/s]\u001b[A\n",876 "pytorch_model-00001-of-00002.bin: 28%|████████████ | 2.74G/9.94G [04:08<10:49, 11.1MB/s]\u001b[A\n",877 "pytorch_model-00001-of-00002.bin: 28%|████████████▏ | 2.75G/9.94G [04:09<10:50, 11.1MB/s]\u001b[A\n",878 "pytorch_model-00001-of-00002.bin: 28%|████████████▏ | 2.76G/9.94G [04:10<10:44, 11.1MB/s]\u001b[A\n",879 "pytorch_model-00001-of-00002.bin: 28%|████████████▎ | 2.77G/9.94G [04:11<10:35, 11.3MB/s]\u001b[A\n",880 "pytorch_model-00001-of-00002.bin: 28%|████████████▎ | 2.78G/9.94G [04:12<10:51, 11.0MB/s]\u001b[A\n",881 "pytorch_model-00001-of-00002.bin: 28%|████████████▎ | 2.79G/9.94G [04:13<11:20, 10.5MB/s]\u001b[A\n",882 "pytorch_model-00001-of-00002.bin: 28%|████████████▍ | 2.80G/9.94G [04:14<10:58, 10.8MB/s]\u001b[A\n",883 "pytorch_model-00001-of-00002.bin: 28%|████████████▍ | 2.81G/9.94G [04:15<10:44, 11.1MB/s]\u001b[A\n",884 "pytorch_model-00001-of-00002.bin: 28%|████████████▍ | 2.82G/9.94G [04:16<10:33, 11.2MB/s]\u001b[A\n",885 "pytorch_model-00001-of-00002.bin: 28%|████████████▌ | 2.83G/9.94G [04:17<10:27, 11.3MB/s]\u001b[A\n",886 "pytorch_model-00001-of-00002.bin: 29%|████████████▌ | 2.84G/9.94G [04:18<10:20, 11.5MB/s]\u001b[A\n",887 "pytorch_model-00001-of-00002.bin: 29%|████████████▌ | 2.85G/9.94G [04:19<10:20, 11.4MB/s]\u001b[A\n",888 "pytorch_model-00001-of-00002.bin: 29%|████████████▋ | 2.86G/9.94G [04:19<10:17, 11.5MB/s]\u001b[A\n",889 "pytorch_model-00001-of-00002.bin: 29%|████████████▋ | 2.87G/9.94G [04:20<10:14, 11.5MB/s]\u001b[A\n",890 "pytorch_model-00001-of-00002.bin: 29%|████████████▊ | 2.88G/9.94G [04:21<10:12, 11.5MB/s]\u001b[A\n",891 "pytorch_model-00001-of-00002.bin: 29%|████████████▊ | 2.89G/9.94G [04:22<10:11, 11.5MB/s]\u001b[A\n",892 "pytorch_model-00001-of-00002.bin: 29%|████████████▊ | 2.90G/9.94G [04:23<10:08, 11.6MB/s]\u001b[A\n",893 "pytorch_model-00001-of-00002.bin: 29%|████████████▉ | 2.92G/9.94G [04:24<10:06, 11.6MB/s]\u001b[A\n",894 "pytorch_model-00001-of-00002.bin: 29%|████████████▉ | 2.93G/9.94G [04:25<10:04, 11.6MB/s]\u001b[A\n",895 "pytorch_model-00001-of-00002.bin: 30%|████████████▉ | 2.94G/9.94G [04:26<10:18, 11.3MB/s]\u001b[A\n",896 "pytorch_model-00001-of-00002.bin: 30%|█████████████ | 2.95G/9.94G [04:27<10:41, 10.9MB/s]\u001b[A\n",897 "pytorch_model-00001-of-00002.bin: 30%|█████████████ | 2.96G/9.94G [04:28<10:43, 10.8MB/s]\u001b[A\n",898 "pytorch_model-00001-of-00002.bin: 30%|█████████████▏ | 2.97G/9.94G [04:29<10:37, 10.9MB/s]\u001b[A\n",899 "pytorch_model-00001-of-00002.bin: 30%|█████████████▏ | 2.98G/9.94G [04:30<10:30, 11.1MB/s]\u001b[A\n",900 "pytorch_model-00001-of-00002.bin: 30%|█████████████▏ | 2.99G/9.94G [04:31<10:19, 11.2MB/s]\u001b[A\n",901 "pytorch_model-00001-of-00002.bin: 30%|█████████████▎ | 3.00G/9.94G [04:32<10:21, 11.2MB/s]\u001b[A\n",902 "pytorch_model-00001-of-00002.bin: 30%|█████████████▎ | 3.01G/9.94G [04:33<11:42, 9.86MB/s]\u001b[A\n",903 "pytorch_model-00001-of-00002.bin: 30%|█████████████▎ | 3.02G/9.94G [04:34<11:37, 9.93MB/s]\u001b[A\n",904 "pytorch_model-00001-of-00002.bin: 30%|█████████████▍ | 3.03G/9.94G [04:35<11:34, 9.95MB/s]\u001b[A\n",905 "pytorch_model-00001-of-00002.bin: 31%|█████████████▍ | 3.04G/9.94G [04:36<11:11, 10.3MB/s]\u001b[A\n",906 "pytorch_model-00001-of-00002.bin: 31%|█████████████▌ | 3.05G/9.94G [04:37<10:47, 10.6MB/s]\u001b[A\n",907 "pytorch_model-00001-of-00002.bin: 31%|█████████████▌ | 3.06G/9.94G [04:38<10:31, 10.9MB/s]\u001b[A\n",908 "pytorch_model-00001-of-00002.bin: 31%|█████████████▌ | 3.07G/9.94G [04:39<10:21, 11.1MB/s]\u001b[A\n",909 "pytorch_model-00001-of-00002.bin: 31%|█████████████▋ | 3.08G/9.94G [04:40<10:11, 11.2MB/s]\u001b[A\n",910 "pytorch_model-00001-of-00002.bin: 31%|█████████████▋ | 3.09G/9.94G [04:41<10:11, 11.2MB/s]\u001b[A\n",911 "pytorch_model-00001-of-00002.bin: 31%|█████████████▋ | 3.10G/9.94G [04:41<10:02, 11.3MB/s]\u001b[A\n",912 "pytorch_model-00001-of-00002.bin: 31%|█████████████▊ | 3.11G/9.94G [04:42<09:56, 11.4MB/s]\u001b[A\n",913 "pytorch_model-00001-of-00002.bin: 31%|█████████████▊ | 3.12G/9.94G [04:43<10:29, 10.8MB/s]\u001b[A\n",914 "pytorch_model-00001-of-00002.bin: 32%|█████████████▊ | 3.14G/9.94G [04:44<10:23, 10.9MB/s]\u001b[A\n",915 "pytorch_model-00001-of-00002.bin: 32%|█████████████▉ | 3.15G/9.94G [04:45<10:10, 11.1MB/s]\u001b[A\n",916 "pytorch_model-00001-of-00002.bin: 32%|█████████████▉ | 3.16G/9.94G [04:46<10:03, 11.2MB/s]\u001b[A\n",917 "pytorch_model-00001-of-00002.bin: 32%|██████████████ | 3.17G/9.94G [04:47<09:56, 11.4MB/s]\u001b[A\n",918 "pytorch_model-00001-of-00002.bin: 32%|██████████████ | 3.18G/9.94G [04:48<09:49, 11.5MB/s]\u001b[A\n",919 "pytorch_model-00001-of-00002.bin: 32%|██████████████ | 3.19G/9.94G [04:49<09:52, 11.4MB/s]\u001b[A\n",920 "pytorch_model-00001-of-00002.bin: 32%|██████████████▏ | 3.20G/9.94G [04:50<09:48, 11.5MB/s]\u001b[A\n",921 "pytorch_model-00001-of-00002.bin: 32%|██████████████▏ | 3.21G/9.94G [04:51<09:46, 11.5MB/s]\u001b[A\n",922 "pytorch_model-00001-of-00002.bin: 32%|██████████████▏ | 3.22G/9.94G [04:52<09:43, 11.5MB/s]\u001b[A\n",923 "pytorch_model-00001-of-00002.bin: 32%|██████████████▎ | 3.23G/9.94G [04:53<09:45, 11.5MB/s]\u001b[A\n",924 "pytorch_model-00001-of-00002.bin: 33%|██████████████▎ | 3.24G/9.94G [04:53<09:43, 11.5MB/s]\u001b[A\n",925 "pytorch_model-00001-of-00002.bin: 33%|██████████████▍ | 3.25G/9.94G [04:54<09:40, 11.5MB/s]\u001b[A\n",926 "pytorch_model-00001-of-00002.bin: 33%|██████████████▍ | 3.26G/9.94G [04:55<09:37, 11.6MB/s]\u001b[A\n",927 "pytorch_model-00001-of-00002.bin: 33%|██████████████▍ | 3.27G/9.94G [04:56<09:49, 11.3MB/s]\u001b[A\n",928 "pytorch_model-00001-of-00002.bin: 33%|██████████████▌ | 3.28G/9.94G [04:57<10:03, 11.0MB/s]\u001b[A\n",929 "pytorch_model-00001-of-00002.bin: 33%|██████████████▌ | 3.29G/9.94G [04:58<09:55, 11.2MB/s]\u001b[A\n",930 "pytorch_model-00001-of-00002.bin: 33%|██████████████▌ | 3.30G/9.94G [04:59<09:48, 11.3MB/s]\u001b[A\n",931 "pytorch_model-00001-of-00002.bin: 33%|██████████████▋ | 3.31G/9.94G [05:00<09:42, 11.4MB/s]\u001b[A\n",932 "pytorch_model-00001-of-00002.bin: 33%|██████████████▋ | 3.32G/9.94G [05:01<09:38, 11.4MB/s]\u001b[A\n",933 "pytorch_model-00001-of-00002.bin: 34%|██████████████▊ | 3.33G/9.94G [05:02<09:33, 11.5MB/s]\u001b[A\n",934 "pytorch_model-00001-of-00002.bin: 34%|██████████████▊ | 3.34G/9.94G [05:03<09:32, 11.5MB/s]\u001b[A\n",935 "pytorch_model-00001-of-00002.bin: 34%|██████████████▊ | 3.36G/9.94G [05:04<09:30, 11.5MB/s]\u001b[A\n",936 "pytorch_model-00001-of-00002.bin: 34%|██████████████▉ | 3.37G/9.94G [05:04<09:26, 11.6MB/s]\u001b[A\n",937 "pytorch_model-00001-of-00002.bin: 34%|██████████████▉ | 3.38G/9.94G [05:05<09:27, 11.6MB/s]\u001b[A\n",938 "pytorch_model-00001-of-00002.bin: 34%|██████████████▉ | 3.39G/9.94G [05:06<09:24, 11.6MB/s]\u001b[A\n",939 "pytorch_model-00001-of-00002.bin: 34%|███████████████ | 3.40G/9.94G [05:07<10:00, 10.9MB/s]\u001b[A\n",940 "pytorch_model-00001-of-00002.bin: 34%|███████████████ | 3.41G/9.94G [05:08<09:47, 11.1MB/s]\u001b[A\n",941 "pytorch_model-00001-of-00002.bin: 34%|███████████████▏ | 3.42G/9.94G [05:09<10:03, 10.8MB/s]\u001b[A\n",942 "pytorch_model-00001-of-00002.bin: 34%|███████████████▏ | 3.43G/9.94G [05:10<09:49, 11.1MB/s]\u001b[A\n",943 "pytorch_model-00001-of-00002.bin: 35%|███████████████▏ | 3.44G/9.94G [05:11<09:40, 11.2MB/s]\u001b[A\n",944 "pytorch_model-00001-of-00002.bin: 35%|███████████████▎ | 3.45G/9.94G [05:12<09:33, 11.3MB/s]\u001b[A\n",945 "pytorch_model-00001-of-00002.bin: 35%|███████████████▎ | 3.46G/9.94G [05:13<09:35, 11.3MB/s]\u001b[A\n",946 "pytorch_model-00001-of-00002.bin: 35%|███████████████▎ | 3.47G/9.94G [05:14<09:26, 11.4MB/s]\u001b[A\n",947 "pytorch_model-00001-of-00002.bin: 35%|███████████████▍ | 3.48G/9.94G [05:15<09:43, 11.1MB/s]\u001b[A\n",948 "pytorch_model-00001-of-00002.bin: 35%|███████████████▍ | 3.49G/9.94G [05:16<09:33, 11.2MB/s]\u001b[A\n",949 "pytorch_model-00001-of-00002.bin: 35%|███████████████▍ | 3.50G/9.94G [05:17<09:44, 11.0MB/s]\u001b[A\n",950 "pytorch_model-00001-of-00002.bin: 35%|███████████████▌ | 3.51G/9.94G [05:18<09:34, 11.2MB/s]\u001b[A\n",951 "pytorch_model-00001-of-00002.bin: 35%|███████████████▌ | 3.52G/9.94G [05:19<09:31, 11.2MB/s]\u001b[A\n",952 "pytorch_model-00001-of-00002.bin: 36%|███████████████▋ | 3.53G/9.94G [05:19<09:22, 11.4MB/s]\u001b[A\n",953 "pytorch_model-00001-of-00002.bin: 36%|███████████████▋ | 3.54G/9.94G [05:20<09:25, 11.3MB/s]\u001b[A\n",954 "pytorch_model-00001-of-00002.bin: 36%|███████████████▋ | 3.55G/9.94G [05:21<09:19, 11.4MB/s]\u001b[A\n",955 "pytorch_model-00001-of-00002.bin: 36%|███████████████▊ | 3.57G/9.94G [05:22<09:22, 11.3MB/s]\u001b[A\n",956 "pytorch_model-00001-of-00002.bin: 36%|███████████████▊ | 3.58G/9.94G [05:23<09:17, 11.4MB/s]\u001b[A\n",957 "pytorch_model-00001-of-00002.bin: 36%|███████████████▊ | 3.59G/9.94G [05:24<09:13, 11.5MB/s]\u001b[A\n",958 "pytorch_model-00001-of-00002.bin: 36%|███████████████▉ | 3.60G/9.94G [05:25<09:14, 11.5MB/s]\u001b[A\n",959 "pytorch_model-00001-of-00002.bin: 36%|███████████████▉ | 3.61G/9.94G [05:26<09:10, 11.5MB/s]\u001b[A\n",960 "pytorch_model-00001-of-00002.bin: 36%|████████████████ | 3.62G/9.94G [05:27<09:22, 11.2MB/s]\u001b[A\n",961 "pytorch_model-00001-of-00002.bin: 36%|████████████████ | 3.63G/9.94G [05:28<09:16, 11.3MB/s]\u001b[A\n",962 "pytorch_model-00001-of-00002.bin: 37%|████████████████ | 3.64G/9.94G [05:29<09:19, 11.3MB/s]\u001b[A\n",963 "pytorch_model-00001-of-00002.bin: 37%|████████████████▏ | 3.65G/9.94G [05:30<09:14, 11.3MB/s]\u001b[A\n",964 "pytorch_model-00001-of-00002.bin: 37%|████████████████▏ | 3.66G/9.94G [05:30<09:09, 11.4MB/s]\u001b[A\n",965 "pytorch_model-00001-of-00002.bin: 37%|████████████████▏ | 3.67G/9.94G [05:31<09:07, 11.5MB/s]\u001b[A\n",966 "pytorch_model-00001-of-00002.bin: 37%|████████████████▎ | 3.68G/9.94G [05:32<09:10, 11.4MB/s]\u001b[A\n",967 "pytorch_model-00001-of-00002.bin: 37%|████████████████▎ | 3.69G/9.94G [05:33<09:05, 11.5MB/s]\u001b[A\n",968 "pytorch_model-00001-of-00002.bin: 37%|████████████████▍ | 3.70G/9.94G [05:34<09:01, 11.5MB/s]\u001b[A\n",969 "pytorch_model-00001-of-00002.bin: 37%|████████████████▍ | 3.71G/9.94G [05:35<09:04, 11.4MB/s]\u001b[A\n",970 "pytorch_model-00001-of-00002.bin: 37%|████████████████▍ | 3.72G/9.94G [05:36<08:58, 11.5MB/s]\u001b[A\n",971 "pytorch_model-00001-of-00002.bin: 38%|████████████████▌ | 3.73G/9.94G [05:37<09:46, 10.6MB/s]\u001b[A\n",972 "pytorch_model-00001-of-00002.bin: 38%|████████████████▌ | 3.74G/9.94G [05:38<09:58, 10.4MB/s]\u001b[A\n",973 "pytorch_model-00001-of-00002.bin: 38%|████████████████▌ | 3.75G/9.94G [05:39<10:11, 10.1MB/s]\u001b[A\n",974 "pytorch_model-00001-of-00002.bin: 38%|████████████████▋ | 3.76G/9.94G [05:40<10:30, 9.80MB/s]\u001b[A\n",975 "pytorch_model-00001-of-00002.bin: 38%|████████████████▋ | 3.77G/9.94G [05:41<10:17, 9.99MB/s]\u001b[A\n",976 "pytorch_model-00001-of-00002.bin: 38%|████████████████▊ | 3.79G/9.94G [05:43<10:25, 9.84MB/s]\u001b[A\n",977 "pytorch_model-00001-of-00002.bin: 38%|████████████████▊ | 3.80G/9.94G [05:44<10:18, 9.93MB/s]\u001b[A\n",978 "pytorch_model-00001-of-00002.bin: 38%|████████████████▊ | 3.81G/9.94G [05:45<10:06, 10.1MB/s]\u001b[A\n",979 "pytorch_model-00001-of-00002.bin: 38%|████████████████▉ | 3.82G/9.94G [05:46<10:06, 10.1MB/s]\u001b[A\n",980 "pytorch_model-00001-of-00002.bin: 38%|████████████████▉ | 3.83G/9.94G [05:47<09:47, 10.4MB/s]\u001b[A\n",981 "pytorch_model-00001-of-00002.bin: 39%|████████████████▉ | 3.84G/9.94G [05:47<09:28, 10.7MB/s]\u001b[A\n",982 "pytorch_model-00001-of-00002.bin: 39%|█████████████████ | 3.85G/9.94G [05:48<09:38, 10.5MB/s]\u001b[A\n",983 "pytorch_model-00001-of-00002.bin: 39%|█████████████████ | 3.86G/9.94G [05:50<09:53, 10.3MB/s]\u001b[A\n",984 "pytorch_model-00001-of-00002.bin: 39%|█████████████████ | 3.87G/9.94G [05:51<10:03, 10.1MB/s]\u001b[A\n",985 "pytorch_model-00001-of-00002.bin: 39%|█████████████████▏ | 3.88G/9.94G [05:52<09:53, 10.2MB/s]\u001b[A\n",986 "pytorch_model-00001-of-00002.bin: 39%|█████████████████▏ | 3.89G/9.94G [05:53<09:47, 10.3MB/s]\u001b[A\n",987 "pytorch_model-00001-of-00002.bin: 39%|█████████████████▎ | 3.90G/9.94G [05:54<09:56, 10.1MB/s]\u001b[A\n",988 "pytorch_model-00001-of-00002.bin: 39%|█████████████████▎ | 3.91G/9.94G [05:55<09:39, 10.4MB/s]\u001b[A\n",989 "pytorch_model-00001-of-00002.bin: 39%|█████████████████▎ | 3.92G/9.94G [05:56<09:22, 10.7MB/s]\u001b[A\n",990 "pytorch_model-00001-of-00002.bin: 40%|█████████████████▍ | 3.93G/9.94G [05:56<09:06, 11.0MB/s]\u001b[A\n",991 "pytorch_model-00001-of-00002.bin: 40%|█████████████████▍ | 3.94G/9.94G [05:57<09:06, 11.0MB/s]\u001b[A\n",992 "pytorch_model-00001-of-00002.bin: 40%|█████████████████▍ | 3.95G/9.94G [05:58<09:21, 10.7MB/s]\u001b[A\n",993 "pytorch_model-00001-of-00002.bin: 40%|█████████████████▌ | 3.96G/9.94G [05:59<09:05, 11.0MB/s]\u001b[A\n",994 "pytorch_model-00001-of-00002.bin: 40%|█████████████████▌ | 3.97G/9.94G [06:00<09:00, 11.0MB/s]\u001b[A\n",995 "pytorch_model-00001-of-00002.bin: 40%|█████████████████▋ | 3.98G/9.94G [06:01<08:55, 11.1MB/s]\u001b[A\n",996 "pytorch_model-00001-of-00002.bin: 40%|█████████████████▋ | 4.00G/9.94G [06:02<08:51, 11.2MB/s]\u001b[A\n",997 "pytorch_model-00001-of-00002.bin: 40%|█████████████████▋ | 4.01G/9.94G [06:03<09:32, 10.4MB/s]\u001b[A\n",998 "pytorch_model-00001-of-00002.bin: 40%|█████████████████▊ | 4.02G/9.94G [06:04<09:24, 10.5MB/s]\u001b[A\n",999 "pytorch_model-00001-of-00002.bin: 40%|█████████████████▊ | 4.03G/9.94G [06:05<09:13, 10.7MB/s]\u001b[A\n",1000 "pytorch_model-00001-of-00002.bin: 41%|█████████████████▊ | 4.04G/9.94G [06:06<09:02, 10.9MB/s]\u001b[A\n",1001 "pytorch_model-00001-of-00002.bin: 41%|█████████████████▉ | 4.05G/9.94G [06:07<08:51, 11.1MB/s]\u001b[A\n",1002 "pytorch_model-00001-of-00002.bin: 41%|█████████████████▉ | 4.06G/9.94G [06:08<09:01, 10.9MB/s]\u001b[A\n",1003 "pytorch_model-00001-of-00002.bin: 41%|██████████████████ | 4.07G/9.94G [06:09<09:01, 10.9MB/s]\u001b[A\n",1004 "pytorch_model-00001-of-00002.bin: 41%|██████████████████ | 4.08G/9.94G [06:10<08:51, 11.0MB/s]\u001b[A\n",1005 "pytorch_model-00001-of-00002.bin: 41%|██████████████████ | 4.09G/9.94G [06:11<09:03, 10.8MB/s]\u001b[A\n",1006 "pytorch_model-00001-of-00002.bin: 41%|██████████████████▏ | 4.10G/9.94G [06:12<08:50, 11.0MB/s]\u001b[A\n",1007 "pytorch_model-00001-of-00002.bin: 41%|██████████████████▏ | 4.11G/9.94G [06:13<09:09, 10.6MB/s]\u001b[A\n",1008 "pytorch_model-00001-of-00002.bin: 41%|██████████████████▏ | 4.12G/9.94G [06:14<08:57, 10.8MB/s]\u001b[A\n",1009 "pytorch_model-00001-of-00002.bin: 42%|██████████████████▎ | 4.13G/9.94G [06:15<08:54, 10.9MB/s]\u001b[A\n",1010 "pytorch_model-00001-of-00002.bin: 42%|██████████████████▎ | 4.14G/9.94G [06:16<08:42, 11.1MB/s]\u001b[A\n",1011 "pytorch_model-00001-of-00002.bin: 42%|██████████████████▍ | 4.15G/9.94G [06:17<08:42, 11.1MB/s]\u001b[A\n",1012 "pytorch_model-00001-of-00002.bin: 42%|██████████████████▍ | 4.16G/9.94G [06:18<08:36, 11.2MB/s]\u001b[A\n",1013 "pytorch_model-00001-of-00002.bin: 42%|██████████████████▍ | 4.17G/9.94G [06:19<08:55, 10.8MB/s]\u001b[A\n",1014 "pytorch_model-00001-of-00002.bin: 42%|██████████████████▌ | 4.18G/9.94G [06:20<08:44, 11.0MB/s]\u001b[A\n",1015 "pytorch_model-00001-of-00002.bin: 42%|██████████████████▌ | 4.19G/9.94G [06:21<08:56, 10.7MB/s]\u001b[A\n",1016 "pytorch_model-00001-of-00002.bin: 42%|██████████████████▌ | 4.20G/9.94G [06:22<08:44, 10.9MB/s]\u001b[A\n",1017 "pytorch_model-00001-of-00002.bin: 42%|██████████████████▋ | 4.22G/9.94G [06:22<08:40, 11.0MB/s]\u001b[A\n",1018 "pytorch_model-00001-of-00002.bin: 42%|██████████████████▋ | 4.23G/9.94G [06:24<09:10, 10.4MB/s]\u001b[A\n",1019 "pytorch_model-00001-of-00002.bin: 43%|██████████████████▋ | 4.24G/9.94G [06:25<09:08, 10.4MB/s]\u001b[A\n",1020 "pytorch_model-00001-of-00002.bin: 43%|██████████████████▊ | 4.25G/9.94G [06:26<08:52, 10.7MB/s]\u001b[A\n",1021 "pytorch_model-00001-of-00002.bin: 43%|██████████████████▊ | 4.26G/9.94G [06:26<08:46, 10.8MB/s]\u001b[A\n",1022 "pytorch_model-00001-of-00002.bin: 43%|██████████████████▉ | 4.27G/9.94G [06:27<08:41, 10.9MB/s]\u001b[A\n",1023 "pytorch_model-00001-of-00002.bin: 43%|██████████████████▉ | 4.28G/9.94G [06:28<08:53, 10.6MB/s]\u001b[A\n",1024 "pytorch_model-00001-of-00002.bin: 43%|██████████████████▉ | 4.29G/9.94G [06:29<08:53, 10.6MB/s]\u001b[A\n",1025 "pytorch_model-00001-of-00002.bin: 43%|███████████████████ | 4.30G/9.94G [06:31<09:20, 10.1MB/s]\u001b[A\n",1026 "pytorch_model-00001-of-00002.bin: 43%|███████████████████ | 4.31G/9.94G [06:32<09:30, 9.88MB/s]\u001b[A\n",1027 "pytorch_model-00001-of-00002.bin: 43%|███████████████████ | 4.32G/9.94G [06:33<09:25, 9.95MB/s]\u001b[A\n",1028 "pytorch_model-00001-of-00002.bin: 44%|███████████████████▏ | 4.33G/9.94G [06:34<09:21, 10.0MB/s]\u001b[A\n",1029 "pytorch_model-00001-of-00002.bin: 44%|███████████████████▏ | 4.34G/9.94G [06:35<08:55, 10.5MB/s]\u001b[A\n",1030 "pytorch_model-00001-of-00002.bin: 44%|███████████████████▎ | 4.35G/9.94G [06:36<08:38, 10.8MB/s]\u001b[A\n",1031 "pytorch_model-00001-of-00002.bin: 44%|███████████████████▎ | 4.36G/9.94G [06:37<08:29, 11.0MB/s]\u001b[A\n",1032 "pytorch_model-00001-of-00002.bin: 44%|███████████████████▎ | 4.37G/9.94G [06:37<08:18, 11.2MB/s]\u001b[A\n",1033 "pytorch_model-00001-of-00002.bin: 44%|███████████████████▍ | 4.38G/9.94G [06:38<08:38, 10.7MB/s]\u001b[A\n",1034 "pytorch_model-00001-of-00002.bin: 44%|███████████████████▍ | 4.39G/9.94G [06:39<08:25, 11.0MB/s]\u001b[A\n",1035 "pytorch_model-00001-of-00002.bin: 44%|███████████████████▍ | 4.40G/9.94G [06:40<08:16, 11.1MB/s]\u001b[A\n",1036 "pytorch_model-00001-of-00002.bin: 44%|███████████████████▌ | 4.41G/9.94G [06:41<08:09, 11.3MB/s]\u001b[A\n",1037 "pytorch_model-00001-of-00002.bin: 45%|███████████████████▌ | 4.42G/9.94G [06:42<08:04, 11.4MB/s]\u001b[A\n",1038 "pytorch_model-00001-of-00002.bin: 45%|███████████████████▋ | 4.44G/9.94G [06:43<08:12, 11.2MB/s]\u001b[A\n",1039 "pytorch_model-00001-of-00002.bin: 45%|███████████████████▋ | 4.45G/9.94G [06:44<08:46, 10.4MB/s]\u001b[A\n",1040 "pytorch_model-00001-of-00002.bin: 45%|███████████████████▋ | 4.46G/9.94G [06:45<08:29, 10.8MB/s]\u001b[A\n",1041 "pytorch_model-00001-of-00002.bin: 45%|███████████████████▊ | 4.47G/9.94G [06:46<08:16, 11.0MB/s]\u001b[A\n",1042 "pytorch_model-00001-of-00002.bin: 45%|███████████████████▊ | 4.48G/9.94G [06:47<08:09, 11.2MB/s]\u001b[A\n",1043 "pytorch_model-00001-of-00002.bin: 45%|███████████████████▊ | 4.49G/9.94G [06:48<08:11, 11.1MB/s]\u001b[A\n",1044 "pytorch_model-00001-of-00002.bin: 45%|███████████████████▉ | 4.50G/9.94G [06:49<08:21, 10.9MB/s]\u001b[A\n",1045 "pytorch_model-00001-of-00002.bin: 45%|███████████████████▉ | 4.51G/9.94G [06:50<08:15, 11.0MB/s]\u001b[A\n",1046 "pytorch_model-00001-of-00002.bin: 45%|███████████████████▉ | 4.52G/9.94G [06:51<08:04, 11.2MB/s]\u001b[A\n",1047 "pytorch_model-00001-of-00002.bin: 46%|████████████████████ | 4.53G/9.94G [06:52<08:03, 11.2MB/s]\u001b[A\n",1048 "pytorch_model-00001-of-00002.bin: 46%|████████████████████ | 4.54G/9.94G [06:53<07:59, 11.3MB/s]\u001b[A\n",1049 "pytorch_model-00001-of-00002.bin: 46%|████████████████████▏ | 4.55G/9.94G [06:54<08:22, 10.7MB/s]\u001b[A\n",1050 "pytorch_model-00001-of-00002.bin: 46%|████████████████████▏ | 4.56G/9.94G [06:55<08:10, 11.0MB/s]\u001b[A\n",1051 "pytorch_model-00001-of-00002.bin: 46%|████████████████████▏ | 4.57G/9.94G [06:56<08:12, 10.9MB/s]\u001b[A\n",1052 "pytorch_model-00001-of-00002.bin: 46%|████████████████████▎ | 4.58G/9.94G [06:56<08:05, 11.1MB/s]\u001b[A\n",1053 "pytorch_model-00001-of-00002.bin: 46%|████████████████████▎ | 4.59G/9.94G [06:57<07:58, 11.2MB/s]\u001b[A\n",1054 "pytorch_model-00001-of-00002.bin: 46%|████████████████████▎ | 4.60G/9.94G [06:59<08:47, 10.1MB/s]\u001b[A\n",1055 "pytorch_model-00001-of-00002.bin: 46%|████████████████████▍ | 4.61G/9.94G [07:00<08:30, 10.4MB/s]\u001b[A\n",1056 "pytorch_model-00001-of-00002.bin: 47%|████████████████████▍ | 4.62G/9.94G [07:01<08:16, 10.7MB/s]\u001b[A\n",1057 "pytorch_model-00001-of-00002.bin: 47%|████████████████████▌ | 4.63G/9.94G [07:01<08:04, 11.0MB/s]\u001b[A\n",1058 "pytorch_model-00001-of-00002.bin: 47%|████████████████████▌ | 4.65G/9.94G [07:02<07:57, 11.1MB/s]\u001b[A\n",1059 "pytorch_model-00001-of-00002.bin: 47%|████████████████████▌ | 4.66G/9.94G [07:03<08:14, 10.7MB/s]\u001b[A\n",1060 "pytorch_model-00001-of-00002.bin: 47%|████████████████████▋ | 4.67G/9.94G [07:04<08:04, 10.9MB/s]\u001b[A\n",1061 "pytorch_model-00001-of-00002.bin: 47%|████████████████████▋ | 4.68G/9.94G [07:05<07:54, 11.1MB/s]\u001b[A\n",1062 "pytorch_model-00001-of-00002.bin: 47%|████████████████████▋ | 4.69G/9.94G [07:06<07:50, 11.2MB/s]\u001b[A\n",1063 "pytorch_model-00001-of-00002.bin: 47%|████████████████████▊ | 4.70G/9.94G [07:07<07:46, 11.2MB/s]\u001b[A\n",1064 "pytorch_model-00001-of-00002.bin: 47%|████████████████████▊ | 4.71G/9.94G [07:08<07:51, 11.1MB/s]\u001b[A\n",1065 "pytorch_model-00001-of-00002.bin: 47%|████████████████████▉ | 4.72G/9.94G [07:09<07:53, 11.0MB/s]\u001b[A\n",1066 "pytorch_model-00001-of-00002.bin: 48%|████████████████████▉ | 4.73G/9.94G [07:10<07:49, 11.1MB/s]\u001b[A\n",1067 "pytorch_model-00001-of-00002.bin: 48%|████████████████████▉ | 4.74G/9.94G [07:11<07:47, 11.1MB/s]\u001b[A\n",1068 "pytorch_model-00001-of-00002.bin: 48%|█████████████████████ | 4.75G/9.94G [07:12<08:00, 10.8MB/s]\u001b[A\n",1069 "pytorch_model-00001-of-00002.bin: 48%|█████████████████████ | 4.76G/9.94G [07:13<07:57, 10.9MB/s]\u001b[A\n",1070 "pytorch_model-00001-of-00002.bin: 48%|█████████████████████ | 4.77G/9.94G [07:14<08:03, 10.7MB/s]\u001b[A\n",1071 "pytorch_model-00001-of-00002.bin: 48%|█████████████████████▏ | 4.78G/9.94G [07:15<07:53, 10.9MB/s]\u001b[A\n",1072 "pytorch_model-00001-of-00002.bin: 48%|█████████████████████▏ | 4.79G/9.94G [07:16<07:44, 11.1MB/s]\u001b[A\n",1073 "pytorch_model-00001-of-00002.bin: 48%|█████████████████████▎ | 4.80G/9.94G [07:17<07:39, 11.2MB/s]\u001b[A\n",1074 "pytorch_model-00001-of-00002.bin: 48%|█████████████████████▎ | 4.81G/9.94G [07:18<07:35, 11.3MB/s]\u001b[A\n",1075 "pytorch_model-00001-of-00002.bin: 49%|█████████████████████▎ | 4.82G/9.94G [07:19<08:25, 10.1MB/s]\u001b[A\n",1076 "pytorch_model-00001-of-00002.bin: 49%|█████████████████████▍ | 4.83G/9.94G [07:20<08:09, 10.4MB/s]\u001b[A\n",1077 "pytorch_model-00001-of-00002.bin: 49%|█████████████████████▍ | 4.84G/9.94G [07:21<07:51, 10.8MB/s]\u001b[A\n",1078 "pytorch_model-00001-of-00002.bin: 49%|█████████████████████▍ | 4.85G/9.94G [07:22<07:44, 10.9MB/s]\u001b[A\n",1079 "pytorch_model-00001-of-00002.bin: 49%|█████████████████████▌ | 4.87G/9.94G [07:22<07:37, 11.1MB/s]\u001b[A\n",1080 "pytorch_model-00001-of-00002.bin: 49%|█████████████████████▌ | 4.88G/9.94G [07:24<07:56, 10.6MB/s]\u001b[A\n",1081 "pytorch_model-00001-of-00002.bin: 49%|█████████████████████▌ | 4.89G/9.94G [07:24<07:43, 10.9MB/s]\u001b[A\n",1082 "pytorch_model-00001-of-00002.bin: 49%|█████████████████████▋ | 4.90G/9.94G [07:25<07:37, 11.0MB/s]\u001b[A\n",1083 "pytorch_model-00001-of-00002.bin: 49%|█████████████████████▋ | 4.91G/9.94G [07:26<07:31, 11.1MB/s]\u001b[A\n",1084 "pytorch_model-00001-of-00002.bin: 49%|█████████████████████▊ | 4.92G/9.94G [07:27<07:26, 11.2MB/s]\u001b[A\n",1085 "pytorch_model-00001-of-00002.bin: 50%|█████████████████████▊ | 4.93G/9.94G [07:28<07:37, 11.0MB/s]\u001b[A\n",1086 "pytorch_model-00001-of-00002.bin: 50%|█████████████████████▊ | 4.94G/9.94G [07:29<07:36, 11.0MB/s]\u001b[A\n",1087 "pytorch_model-00001-of-00002.bin: 50%|█████████████████████▉ | 4.95G/9.94G [07:30<07:39, 10.9MB/s]\u001b[A\n",1088 "pytorch_model-00001-of-00002.bin: 50%|█████████████████████▉ | 4.96G/9.94G [07:31<07:48, 10.6MB/s]\u001b[A\n",1089 "pytorch_model-00001-of-00002.bin: 50%|█████████████████████▉ | 4.97G/9.94G [07:32<07:43, 10.7MB/s]\u001b[A\n",1090 "pytorch_model-00001-of-00002.bin: 50%|██████████████████████ | 4.98G/9.94G [07:33<08:01, 10.3MB/s]\u001b[A\n",1091 "pytorch_model-00001-of-00002.bin: 50%|██████████████████████ | 4.99G/9.94G [07:34<07:55, 10.4MB/s]\u001b[A\n",1092 "pytorch_model-00001-of-00002.bin: 50%|██████████████████████▏ | 5.00G/9.94G [07:35<07:41, 10.7MB/s]\u001b[A\n",1093 "pytorch_model-00001-of-00002.bin: 50%|██████████████████████▏ | 5.01G/9.94G [07:36<07:38, 10.7MB/s]\u001b[A\n",1094 "pytorch_model-00001-of-00002.bin: 51%|██████████████████████▏ | 5.02G/9.94G [07:37<07:40, 10.7MB/s]\u001b[A\n",1095 "pytorch_model-00001-of-00002.bin: 51%|██████████████████████▎ | 5.03G/9.94G [07:38<07:46, 10.5MB/s]\u001b[A\n",1096 "pytorch_model-00001-of-00002.bin: 51%|██████████████████████▎ | 5.04G/9.94G [07:39<07:47, 10.5MB/s]\u001b[A\n",1097 "pytorch_model-00001-of-00002.bin: 51%|██████████████████████▎ | 5.05G/9.94G [07:40<07:35, 10.7MB/s]\u001b[A\n",1098 "pytorch_model-00001-of-00002.bin: 51%|██████████████████████▍ | 5.06G/9.94G [07:41<07:25, 11.0MB/s]\u001b[A\n",1099 "pytorch_model-00001-of-00002.bin: 51%|██████████████████████▍ | 5.08G/9.94G [07:42<07:17, 11.1MB/s]\u001b[A\n",1100 "pytorch_model-00001-of-00002.bin: 51%|██████████████████████▌ | 5.09G/9.94G [07:43<07:22, 11.0MB/s]\u001b[A\n",1101 "pytorch_model-00001-of-00002.bin: 51%|██████████████████████▌ | 5.10G/9.94G [07:44<07:54, 10.2MB/s]\u001b[A\n",1102 "pytorch_model-00001-of-00002.bin: 51%|██████████████████████▌ | 5.11G/9.94G [07:45<07:36, 10.6MB/s]\u001b[A\n",1103 "pytorch_model-00001-of-00002.bin: 51%|██████████████████████▋ | 5.12G/9.94G [07:46<07:26, 10.8MB/s]\u001b[A\n",1104 "pytorch_model-00001-of-00002.bin: 52%|██████████████████████▋ | 5.13G/9.94G [07:47<07:21, 10.9MB/s]\u001b[A\n",1105 "pytorch_model-00001-of-00002.bin: 52%|██████████████████████▋ | 5.14G/9.94G [07:48<07:15, 11.0MB/s]\u001b[A\n",1106 "pytorch_model-00001-of-00002.bin: 52%|██████████████████████▊ | 5.15G/9.94G [07:49<07:08, 11.2MB/s]\u001b[A\n",1107 "pytorch_model-00001-of-00002.bin: 52%|██████████████████████▊ | 5.16G/9.94G [07:50<07:06, 11.2MB/s]\u001b[A\n",1108 "pytorch_model-00001-of-00002.bin: 52%|██████████████████████▉ | 5.17G/9.94G [07:51<07:06, 11.2MB/s]\u001b[A\n",1109 "pytorch_model-00001-of-00002.bin: 52%|██████████████████████▉ | 5.18G/9.94G [07:51<07:03, 11.2MB/s]\u001b[A\n",1110 "pytorch_model-00001-of-00002.bin: 52%|██████████████████████▉ | 5.19G/9.94G [07:52<07:07, 11.1MB/s]\u001b[A\n",1111 "pytorch_model-00001-of-00002.bin: 52%|███████████████████████ | 5.20G/9.94G [07:54<07:47, 10.1MB/s]\u001b[A\n",1112 "pytorch_model-00001-of-00002.bin: 52%|███████████████████████ | 5.21G/9.94G [07:55<07:40, 10.3MB/s]\u001b[A\n",1113 "pytorch_model-00001-of-00002.bin: 53%|███████████████████████ | 5.22G/9.94G [07:56<07:26, 10.6MB/s]\u001b[A\n",1114 "pytorch_model-00001-of-00002.bin: 53%|███████████████████████▏ | 5.23G/9.94G [07:57<07:15, 10.8MB/s]\u001b[A\n",1115 "pytorch_model-00001-of-00002.bin: 53%|███████████████████████▏ | 5.24G/9.94G [07:57<07:06, 11.0MB/s]\u001b[A\n",1116 "pytorch_model-00001-of-00002.bin: 53%|███████████████████████▏ | 5.25G/9.94G [07:59<07:20, 10.6MB/s]\u001b[A\n",1117 "pytorch_model-00001-of-00002.bin: 53%|███████████████████████▎ | 5.26G/9.94G [07:59<07:20, 10.6MB/s]\u001b[A\n",1118 "pytorch_model-00001-of-00002.bin: 53%|███████████████████████▎ | 5.27G/9.94G [08:00<07:09, 10.9MB/s]\u001b[A\n",1119 "pytorch_model-00001-of-00002.bin: 53%|███████████████████████▍ | 5.28G/9.94G [08:01<07:01, 11.0MB/s]\u001b[A\n",1120 "pytorch_model-00001-of-00002.bin: 53%|███████████████████████▍ | 5.30G/9.94G [08:02<07:22, 10.5MB/s]\u001b[A\n",1121 "pytorch_model-00001-of-00002.bin: 53%|███████████████████████▍ | 5.31G/9.94G [08:04<07:53, 9.79MB/s]\u001b[A\n",1122 "pytorch_model-00001-of-00002.bin: 53%|███████████████████████▌ | 5.32G/9.94G [08:05<07:38, 10.1MB/s]\u001b[A\n",1123 "pytorch_model-00001-of-00002.bin: 54%|███████████████████████▌ | 5.33G/9.94G [08:06<07:20, 10.5MB/s]\u001b[A\n",1124 "pytorch_model-00001-of-00002.bin: 54%|███████████████████████▌ | 5.34G/9.94G [08:06<07:09, 10.7MB/s]\u001b[A\n",1125 "pytorch_model-00001-of-00002.bin: 54%|███████████████████████▋ | 5.35G/9.94G [08:07<06:59, 10.9MB/s]\u001b[A\n",1126 "pytorch_model-00001-of-00002.bin: 54%|███████████████████████▋ | 5.36G/9.94G [08:09<07:20, 10.4MB/s]\u001b[A\n",1127 "pytorch_model-00001-of-00002.bin: 54%|███████████████████████▊ | 5.37G/9.94G [08:09<07:06, 10.7MB/s]\u001b[A\n",1128 "pytorch_model-00001-of-00002.bin: 54%|███████████████████████▊ | 5.38G/9.94G [08:10<06:58, 10.9MB/s]\u001b[A\n",1129 "pytorch_model-00001-of-00002.bin: 54%|███████████████████████▊ | 5.39G/9.94G [08:11<06:51, 11.1MB/s]\u001b[A\n",1130 "pytorch_model-00001-of-00002.bin: 54%|███████████████████████▉ | 5.40G/9.94G [08:12<06:45, 11.2MB/s]\u001b[A\n",1131 "pytorch_model-00001-of-00002.bin: 54%|███████████████████████▉ | 5.41G/9.94G [08:13<06:41, 11.3MB/s]\u001b[A\n",1132 "pytorch_model-00001-of-00002.bin: 55%|███████████████████████▉ | 5.42G/9.94G [08:14<06:39, 11.3MB/s]\u001b[A\n",1133 "pytorch_model-00001-of-00002.bin: 55%|████████████████████████ | 5.43G/9.94G [08:15<06:37, 11.3MB/s]\u001b[A\n",1134 "pytorch_model-00001-of-00002.bin: 55%|████████████████████████ | 5.44G/9.94G [08:16<06:33, 11.4MB/s]\u001b[A\n",1135 "pytorch_model-00001-of-00002.bin: 55%|████████████████████████▏ | 5.45G/9.94G [08:17<06:34, 11.4MB/s]\u001b[A\n",1136 "pytorch_model-00001-of-00002.bin: 55%|████████████████████████▏ | 5.46G/9.94G [08:18<06:32, 11.4MB/s]\u001b[A\n",1137 "pytorch_model-00001-of-00002.bin: 55%|████████████████████████▏ | 5.47G/9.94G [08:19<06:32, 11.4MB/s]\u001b[A\n",1138 "pytorch_model-00001-of-00002.bin: 55%|████████████████████████▎ | 5.48G/9.94G [08:20<06:31, 11.4MB/s]\u001b[A\n",1139 "pytorch_model-00001-of-00002.bin: 55%|████████████████████████▎ | 5.49G/9.94G [08:20<06:31, 11.4MB/s]\u001b[A\n",1140 "pytorch_model-00001-of-00002.bin: 55%|████████████████████████▎ | 5.51G/9.94G [08:21<06:31, 11.3MB/s]\u001b[A\n",1141 "pytorch_model-00001-of-00002.bin: 55%|████████████████████████▍ | 5.52G/9.94G [08:23<07:00, 10.5MB/s]\u001b[A\n",1142 "pytorch_model-00001-of-00002.bin: 56%|████████████████████████▍ | 5.53G/9.94G [08:24<06:59, 10.5MB/s]\u001b[A\n",1143 "pytorch_model-00001-of-00002.bin: 56%|████████████████████████▌ | 5.54G/9.94G [08:24<06:48, 10.8MB/s]\u001b[A\n",1144 "pytorch_model-00001-of-00002.bin: 56%|████████████████████████▌ | 5.55G/9.94G [08:25<06:40, 11.0MB/s]\u001b[A\n",1145 "pytorch_model-00001-of-00002.bin: 56%|████████████████████████▌ | 5.56G/9.94G [08:26<06:37, 11.0MB/s]\u001b[A\n",1146 "pytorch_model-00001-of-00002.bin: 56%|████████████████████████▋ | 5.57G/9.94G [08:27<06:47, 10.7MB/s]\u001b[A\n",1147 "pytorch_model-00001-of-00002.bin: 56%|████████████████████████▋ | 5.58G/9.94G [08:28<06:45, 10.8MB/s]\u001b[A\n",1148 "pytorch_model-00001-of-00002.bin: 56%|████████████████████████▋ | 5.59G/9.94G [08:29<06:39, 10.9MB/s]\u001b[A\n",1149 "pytorch_model-00001-of-00002.bin: 56%|████████████████████████▊ | 5.60G/9.94G [08:30<06:45, 10.7MB/s]\u001b[A\n",1150 "pytorch_model-00001-of-00002.bin: 56%|████████████████████████▊ | 5.61G/9.94G [08:31<06:45, 10.7MB/s]\u001b[A\n",1151 "pytorch_model-00001-of-00002.bin: 57%|████████████████████████▊ | 5.62G/9.94G [08:32<06:54, 10.4MB/s]\u001b[A\n",1152 "pytorch_model-00001-of-00002.bin: 57%|████████████████████████▉ | 5.63G/9.94G [08:33<06:51, 10.5MB/s]\u001b[A\n",1153 "pytorch_model-00001-of-00002.bin: 57%|████████████████████████▉ | 5.64G/9.94G [08:34<06:50, 10.5MB/s]\u001b[A\n",1154 "pytorch_model-00001-of-00002.bin: 57%|█████████████████████████ | 5.65G/9.94G [08:35<06:38, 10.8MB/s]\u001b[A\n",1155 "pytorch_model-00001-of-00002.bin: 57%|█████████████████████████ | 5.66G/9.94G [08:36<06:32, 10.9MB/s]\u001b[A\n",1156 "pytorch_model-00001-of-00002.bin: 57%|█████████████████████████ | 5.67G/9.94G [08:37<06:25, 11.1MB/s]\u001b[A\n",1157 "pytorch_model-00001-of-00002.bin: 57%|█████████████████████████▏ | 5.68G/9.94G [08:38<06:21, 11.2MB/s]\u001b[A\n",1158 "pytorch_model-00001-of-00002.bin: 57%|█████████████████████████▏ | 5.69G/9.94G [08:39<06:19, 11.2MB/s]\u001b[A\n",1159 "pytorch_model-00001-of-00002.bin: 57%|█████████████████████████▏ | 5.70G/9.94G [08:40<06:16, 11.3MB/s]\u001b[A\n",1160 "pytorch_model-00001-of-00002.bin: 57%|█████████████████████████▎ | 5.71G/9.94G [08:41<06:14, 11.3MB/s]\u001b[A\n",1161 "pytorch_model-00001-of-00002.bin: 58%|█████████████████████████▎ | 5.73G/9.94G [08:42<06:10, 11.4MB/s]\u001b[A\n",1162 "pytorch_model-00001-of-00002.bin: 58%|█████████████████████████▍ | 5.74G/9.94G [08:43<06:15, 11.2MB/s]\u001b[A\n",1163 "pytorch_model-00001-of-00002.bin: 58%|█████████████████████████▍ | 5.75G/9.94G [08:44<07:01, 9.97MB/s]\u001b[A\n",1164 "pytorch_model-00001-of-00002.bin: 58%|█████████████████████████▍ | 5.76G/9.94G [08:45<06:44, 10.3MB/s]\u001b[A\n",1165 "pytorch_model-00001-of-00002.bin: 58%|█████████████████████████▌ | 5.77G/9.94G [08:46<06:32, 10.6MB/s]\u001b[A\n",1166 "pytorch_model-00001-of-00002.bin: 58%|█████████████████████████▌ | 5.78G/9.94G [08:47<06:25, 10.8MB/s]\u001b[A\n",1167 "pytorch_model-00001-of-00002.bin: 58%|█████████████████████████▌ | 5.79G/9.94G [08:48<06:16, 11.0MB/s]\u001b[A\n",1168 "pytorch_model-00001-of-00002.bin: 58%|█████████████████████████▋ | 5.80G/9.94G [08:49<06:09, 11.2MB/s]\u001b[A\n",1169 "pytorch_model-00001-of-00002.bin: 58%|█████████████████████████▋ | 5.81G/9.94G [08:49<06:08, 11.2MB/s]\u001b[A\n",1170 "pytorch_model-00001-of-00002.bin: 59%|█████████████████████████▊ | 5.82G/9.94G [08:50<06:06, 11.3MB/s]\u001b[A\n",1171 "pytorch_model-00001-of-00002.bin: 59%|█████████████████████████▊ | 5.83G/9.94G [08:51<06:03, 11.3MB/s]\u001b[A\n",1172 "pytorch_model-00001-of-00002.bin: 59%|█████████████████████████▊ | 5.84G/9.94G [08:52<06:04, 11.3MB/s]\u001b[A\n",1173 "pytorch_model-00001-of-00002.bin: 59%|█████████████████████████▉ | 5.85G/9.94G [08:53<06:17, 10.8MB/s]\u001b[A\n",1174 "pytorch_model-00001-of-00002.bin: 59%|█████████████████████████▉ | 5.86G/9.94G [08:54<06:16, 10.8MB/s]\u001b[A\n",1175 "pytorch_model-00001-of-00002.bin: 59%|█████████████████████████▉ | 5.87G/9.94G [08:55<06:08, 11.0MB/s]\u001b[A\n",1176 "pytorch_model-00001-of-00002.bin: 59%|██████████████████████████ | 5.88G/9.94G [08:56<06:02, 11.2MB/s]\u001b[A\n",1177 "pytorch_model-00001-of-00002.bin: 59%|██████████████████████████ | 5.89G/9.94G [08:57<06:00, 11.2MB/s]\u001b[A\n",1178 "pytorch_model-00001-of-00002.bin: 59%|██████████████████████████ | 5.90G/9.94G [08:58<05:57, 11.3MB/s]\u001b[A\n",1179 "pytorch_model-00001-of-00002.bin: 59%|██████████████████████████▏ | 5.91G/9.94G [08:59<05:56, 11.3MB/s]\u001b[A\n",1180 "pytorch_model-00001-of-00002.bin: 60%|██████████████████████████▏ | 5.92G/9.94G [09:00<05:53, 11.4MB/s]\u001b[A\n",1181 "pytorch_model-00001-of-00002.bin: 60%|██████████████████████████▎ | 5.93G/9.94G [09:01<05:52, 11.4MB/s]\u001b[A\n",1182 "pytorch_model-00001-of-00002.bin: 60%|██████████████████████████▎ | 5.95G/9.94G [09:02<05:49, 11.4MB/s]\u001b[A\n",1183 "pytorch_model-00001-of-00002.bin: 60%|██████████████████████████▎ | 5.96G/9.94G [09:02<05:49, 11.4MB/s]\u001b[A\n",1184 "pytorch_model-00001-of-00002.bin: 60%|██████████████████████████▍ | 5.97G/9.94G [09:03<05:47, 11.4MB/s]\u001b[A\n",1185 "pytorch_model-00001-of-00002.bin: 60%|██████████████████████████▍ | 5.98G/9.94G [09:05<06:08, 10.8MB/s]\u001b[A\n",1186 "pytorch_model-00001-of-00002.bin: 60%|██████████████████████████▍ | 5.99G/9.94G [09:05<05:59, 11.0MB/s]\u001b[A\n",1187 "pytorch_model-00001-of-00002.bin: 60%|██████████████████████████▌ | 6.00G/9.94G [09:06<05:55, 11.1MB/s]\u001b[A\n",1188 "pytorch_model-00001-of-00002.bin: 60%|██████████████████████████▌ | 6.01G/9.94G [09:07<06:01, 10.9MB/s]\u001b[A\n",1189 "pytorch_model-00001-of-00002.bin: 61%|██████████████████████████▋ | 6.02G/9.94G [09:08<05:58, 10.9MB/s]\u001b[A\n",1190 "pytorch_model-00001-of-00002.bin: 61%|██████████████████████████▋ | 6.03G/9.94G [09:09<05:53, 11.1MB/s]\u001b[A\n",1191 "pytorch_model-00001-of-00002.bin: 61%|██████████████████████████▋ | 6.04G/9.94G [09:10<05:50, 11.1MB/s]\u001b[A\n",1192 "pytorch_model-00001-of-00002.bin: 61%|██████████████████████████▊ | 6.05G/9.94G [09:11<05:45, 11.3MB/s]\u001b[A\n",1193 "pytorch_model-00001-of-00002.bin: 61%|██████████████████████████▊ | 6.06G/9.94G [09:12<05:45, 11.2MB/s]\u001b[A\n",1194 "pytorch_model-00001-of-00002.bin: 61%|██████████████████████████▊ | 6.07G/9.94G [09:13<05:40, 11.4MB/s]\u001b[A\n",1195 "pytorch_model-00001-of-00002.bin: 61%|██████████████████████████▉ | 6.08G/9.94G [09:14<05:58, 10.8MB/s]\u001b[A\n",1196 "pytorch_model-00001-of-00002.bin: 61%|██████████████████████████▉ | 6.09G/9.94G [09:15<05:54, 10.9MB/s]\u001b[A\n",1197 "pytorch_model-00001-of-00002.bin: 61%|███████████████████████████ | 6.10G/9.94G [09:16<05:52, 10.9MB/s]\u001b[A\n",1198 "pytorch_model-00001-of-00002.bin: 61%|███████████████████████████ | 6.11G/9.94G [09:17<05:46, 11.1MB/s]\u001b[A\n",1199 "pytorch_model-00001-of-00002.bin: 62%|███████████████████████████ | 6.12G/9.94G [09:18<05:49, 10.9MB/s]\u001b[A\n",1200 "pytorch_model-00001-of-00002.bin: 62%|███████████████████████████▏ | 6.13G/9.94G [09:19<05:40, 11.2MB/s]\u001b[A\n",