File size: 23,140 Bytes
2e0c701 07eb0e9 2e0c701 07eb0e9 d0702fa 2e0c701 07eb0e9 2e0c701 07eb0e9 2e0c701 07eb0e9 2e0c701 07eb0e9 2e0c701 07eb0e9 d0702fa 07eb0e9 2e0c701 d0702fa 07eb0e9 d0702fa 2e0c701 07eb0e9 2e0c701 07eb0e9 2e0c701 d0702fa 2e0c701 d0702fa 2e0c701 d0702fa 2e0c701 d0702fa ed39e1a 2e0c701 d0702fa 2e0c701 d0702fa 2e0c701 d0702fa 2e0c701 07eb0e9 2e0c701 07eb0e9 2e0c701 07eb0e9 2e0c701 07eb0e9 d0702fa 2e0c701 07eb0e9 2e0c701 07eb0e9 2e0c701 07eb0e9 2e0c701 07eb0e9 2e0c701 07eb0e9 2e0c701 07eb0e9 2e0c701 07eb0e9 2e0c701 07eb0e9 2e0c701 d0702fa 2e0c701 d0702fa 2e0c701 d0702fa 2e0c701 07eb0e9 2e0c701 07eb0e9 2e0c701 07eb0e9 2e0c701 ed39e1a 2e0c701 ed39e1a 2e0c701 ed39e1a 2e0c701 ed39e1a 2e0c701 d0702fa 2e0c701 d0702fa 07eb0e9 2e0c701 07eb0e9 2e0c701 07eb0e9 2e0c701 db53170 07eb0e9 db53170 2e0c701 db53170 2e0c701 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 |
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"import os; os.chdir('..')"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"/home/ubuntu/SentenceStructureComparision/venv/lib/python3.10/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",
" from .autonotebook import tqdm as notebook_tqdm\n"
]
}
],
"source": [
"import pandas as pd\n",
"\n",
"from datasets import Dataset, load_dataset"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>category</th>\n",
" <th>label</th>\n",
" <th>label_id</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>3982</th>\n",
" <td>Citation context relevance assessment platforms</td>\n",
" <td>Reference</td>\n",
" <td>12</td>\n",
" </tr>\n",
" <tr>\n",
" <th>24651</th>\n",
" <td>Geology fieldwork</td>\n",
" <td>Science</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>28113</th>\n",
" <td>Password management for individuals</td>\n",
" <td>Computers_and_Electronics</td>\n",
" <td>7</td>\n",
" </tr>\n",
" <tr>\n",
" <th>10999</th>\n",
" <td>Real estate market statistics</td>\n",
" <td>Real Estate</td>\n",
" <td>24</td>\n",
" </tr>\n",
" <tr>\n",
" <th>17096</th>\n",
" <td>Running gear for women</td>\n",
" <td>Beauty_and_Fitness</td>\n",
" <td>9</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2374</th>\n",
" <td>Sports Team Fan Pride</td>\n",
" <td>Sports</td>\n",
" <td>26</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9932</th>\n",
" <td>Wine and food events</td>\n",
" <td>Food_and_Drink</td>\n",
" <td>15</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2953</th>\n",
" <td>College admissions for aspiring dancers</td>\n",
" <td>Jobs_and_Education</td>\n",
" <td>21</td>\n",
" </tr>\n",
" <tr>\n",
" <th>25038</th>\n",
" <td>Software development best practices forums</td>\n",
" <td>Online Communities</td>\n",
" <td>8</td>\n",
" </tr>\n",
" <tr>\n",
" <th>29703</th>\n",
" <td>Quantum physics theories</td>\n",
" <td>Science</td>\n",
" <td>2</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" category \\\n",
"3982 Citation context relevance assessment platforms \n",
"24651 Geology fieldwork \n",
"28113 Password management for individuals \n",
"10999 Real estate market statistics \n",
"17096 Running gear for women \n",
"2374 Sports Team Fan Pride \n",
"9932 Wine and food events \n",
"2953 College admissions for aspiring dancers \n",
"25038 Software development best practices forums \n",
"29703 Quantum physics theories \n",
"\n",
" label label_id \n",
"3982 Reference 12 \n",
"24651 Science 2 \n",
"28113 Computers_and_Electronics 7 \n",
"10999 Real Estate 24 \n",
"17096 Beauty_and_Fitness 9 \n",
"2374 Sports 26 \n",
"9932 Food_and_Drink 15 \n",
"2953 Jobs_and_Education 21 \n",
"25038 Online Communities 8 \n",
"29703 Science 2 "
]
},
"execution_count": 3,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df= pd.read_csv('data_categories/Final_Category_Data_With_Labels.csv')\n",
"\n",
"\n",
"df.sample(10)"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>category</th>\n",
" <th>label_id</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Internet usage monitoring</td>\n",
" <td>25</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>Food safety guidelines and regulations</td>\n",
" <td>15</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>Internet protocols and edge computing in finance</td>\n",
" <td>25</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>Online grocery shopping</td>\n",
" <td>15</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>Writing retreats for poets and novelists</td>\n",
" <td>17</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" category label_id\n",
"0 Internet usage monitoring 25\n",
"1 Food safety guidelines and regulations 15\n",
"2 Internet protocols and edge computing in finance 25\n",
"3 Online grocery shopping 15\n",
"4 Writing retreats for poets and novelists 17"
]
},
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df_new= df[['category', 'label_id']]\n",
"df_new.head()"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"False 22474\n",
"True 11138\n",
"Name: count, dtype: int64"
]
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df_new.duplicated().value_counts() # 10837 duplicate values"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"/tmp/ipykernel_139501/984288843.py:1: SettingWithCopyWarning: \n",
"A value is trying to be set on a copy of a slice from a DataFrame\n",
"\n",
"See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
" df_new.rename(\n"
]
},
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>text</th>\n",
" <th>label</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>2925</th>\n",
" <td>Kids' toy stores online</td>\n",
" <td>13</td>\n",
" </tr>\n",
" <tr>\n",
" <th>31108</th>\n",
" <td>Birdwatching apps for bird behavior</td>\n",
" <td>5</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6817</th>\n",
" <td>Legal developments</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>20037</th>\n",
" <td>Citation context relevance assessment tools</td>\n",
" <td>12</td>\n",
" </tr>\n",
" <tr>\n",
" <th>18928</th>\n",
" <td>Orchid care guide</td>\n",
" <td>20</td>\n",
" </tr>\n",
" <tr>\n",
" <th>33358</th>\n",
" <td>Scientific publications and journals</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>16499</th>\n",
" <td>Service dog etiquette</td>\n",
" <td>5</td>\n",
" </tr>\n",
" <tr>\n",
" <th>26484</th>\n",
" <td>Social media trends analysis</td>\n",
" <td>25</td>\n",
" </tr>\n",
" <tr>\n",
" <th>15543</th>\n",
" <td>Troubleshooting computer issues</td>\n",
" <td>7</td>\n",
" </tr>\n",
" <tr>\n",
" <th>15854</th>\n",
" <td>large</td>\n",
" <td>23</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" text label\n",
"2925 Kids' toy stores online 13\n",
"31108 Birdwatching apps for bird behavior 5\n",
"6817 Legal developments 1\n",
"20037 Citation context relevance assessment tools 12\n",
"18928 Orchid care guide 20\n",
"33358 Scientific publications and journals 2\n",
"16499 Service dog etiquette 5\n",
"26484 Social media trends analysis 25\n",
"15543 Troubleshooting computer issues 7\n",
"15854 large 23"
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df_new.rename(\n",
" columns={\n",
" \"category\": \"text\", \n",
" \"label_id\": \"label\"\n",
"}, \n",
" inplace=True\n",
")\n",
"\n",
"df_new.sample(10)"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"/home/ubuntu/SentenceStructureComparision/venv/lib/python3.10/site-packages/pyarrow/pandas_compat.py:373: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.\n",
" if _pandas_api.is_sparse(col):\n"
]
},
{
"data": {
"text/plain": [
"Dataset({\n",
" features: ['text', 'label'],\n",
" num_rows: 33612\n",
"})"
]
},
"execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"dataset_df= Dataset.from_pandas(df_new)\n",
"dataset_df"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"DatasetDict({\n",
" train: Dataset({\n",
" features: ['text', 'label'],\n",
" num_rows: 26889\n",
" })\n",
" test: Dataset({\n",
" features: ['text', 'label'],\n",
" num_rows: 6723\n",
" })\n",
"})"
]
},
"execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"new_data= dataset_df.train_test_split(test_size=0.2)\n",
"new_data"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {},
"outputs": [],
"source": [
"from transformers import AutoTokenizer\n",
"\n",
"tokenizer = AutoTokenizer.from_pretrained(\"distilbert-base-uncased\")"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {},
"outputs": [],
"source": [
"def preprocess_function(examples):\n",
" return tokenizer(examples[\"text\"], truncation=True)"
]
},
{
"cell_type": "code",
"execution_count": 11,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"Map: 48%|βββββ | 13000/26889 [00:00<00:00, 32226.42 examples/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"Map: 100%|ββββββββββ| 26889/26889 [00:00<00:00, 34388.34 examples/s]\n",
"Map: 100%|ββββββββββ| 6723/6723 [00:00<00:00, 41978.69 examples/s]\n"
]
}
],
"source": [
"tokenized_df = new_data.map(preprocess_function, batched=True)"
]
},
{
"cell_type": "code",
"execution_count": 12,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"2023-10-13 10:29:49.212220: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.\n",
"To enable the following instructions: AVX2 FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.\n",
"2023-10-13 10:29:50.573292: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT\n"
]
}
],
"source": [
"# from transformers import DataCollatorWithPadding\n",
"\n",
"# data_collator = DataCollatorWithPadding(tokenizer=tokenizer, return_tensors=\"tf\")\n",
"\n",
"\n",
"\n",
"\n",
"from transformers import DataCollatorWithPadding\n",
"\n",
"data_collator = DataCollatorWithPadding(tokenizer=tokenizer)"
]
},
{
"cell_type": "code",
"execution_count": 13,
"metadata": {},
"outputs": [],
"source": [
"import evaluate\n",
"\n",
"accuracy = evaluate.load(\"accuracy\")"
]
},
{
"cell_type": "code",
"execution_count": 14,
"metadata": {},
"outputs": [],
"source": [
"import numpy as np\n",
"\n",
"\n",
"def compute_metrics(eval_pred):\n",
" predictions, labels = eval_pred\n",
" predictions = np.argmax(predictions, axis=1)\n",
" return accuracy.compute(predictions=predictions, references=labels)"
]
},
{
"cell_type": "code",
"execution_count": 15,
"metadata": {},
"outputs": [],
"source": [
"import json\n"
]
},
{
"cell_type": "code",
"execution_count": 16,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{'Hobbies_and_Leisure': 0,\n",
" 'News': 1,\n",
" 'Science': 2,\n",
" 'Autos_and_Vehicles': 3,\n",
" 'Health': 4,\n",
" 'Pets_and_Animals': 5,\n",
" 'Adult': 6,\n",
" 'Computers_and_Electronics': 7,\n",
" 'Online Communities': 8,\n",
" 'Beauty_and_Fitness': 9,\n",
" 'People_and_Society': 10,\n",
" 'Business_and_Industrial': 11,\n",
" 'Reference': 12,\n",
" 'Shopping': 13,\n",
" 'Travel_and_Transportation': 14,\n",
" 'Food_and_Drink': 15,\n",
" 'Law_and_Government': 16,\n",
" 'Books_and_Literature': 17,\n",
" 'Finance': 18,\n",
" 'Games': 19,\n",
" 'Home_and_Garden': 20,\n",
" 'Jobs_and_Education': 21,\n",
" 'Arts_and_Entertainment': 22,\n",
" 'Sensitive Subjects': 23,\n",
" 'Real Estate': 24,\n",
" 'Internet_and_Telecom': 25,\n",
" 'Sports': 26}"
]
},
"execution_count": 16,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"label2id= json.load(\n",
" open('data/categories_refined.json', 'r')\n",
")\n",
"label2id"
]
},
{
"cell_type": "code",
"execution_count": 17,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{0: 'Hobbies_and_Leisure',\n",
" 1: 'News',\n",
" 2: 'Science',\n",
" 3: 'Autos_and_Vehicles',\n",
" 4: 'Health',\n",
" 5: 'Pets_and_Animals',\n",
" 6: 'Adult',\n",
" 7: 'Computers_and_Electronics',\n",
" 8: 'Online Communities',\n",
" 9: 'Beauty_and_Fitness',\n",
" 10: 'People_and_Society',\n",
" 11: 'Business_and_Industrial',\n",
" 12: 'Reference',\n",
" 13: 'Shopping',\n",
" 14: 'Travel_and_Transportation',\n",
" 15: 'Food_and_Drink',\n",
" 16: 'Law_and_Government',\n",
" 17: 'Books_and_Literature',\n",
" 18: 'Finance',\n",
" 19: 'Games',\n",
" 20: 'Home_and_Garden',\n",
" 21: 'Jobs_and_Education',\n",
" 22: 'Arts_and_Entertainment',\n",
" 23: 'Sensitive Subjects',\n",
" 24: 'Real Estate',\n",
" 25: 'Internet_and_Telecom',\n",
" 26: 'Sports'}"
]
},
"execution_count": 17,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"id2label= {}\n",
"for key in label2id.keys():\n",
" id2label[label2id[key]] = key\n",
" \n",
"id2label"
]
},
{
"cell_type": "code",
"execution_count": 18,
"metadata": {},
"outputs": [],
"source": [
"from transformers import AutoModelForSequenceClassification, TrainingArguments, Trainer\n",
"\n",
"model = AutoModelForSequenceClassification.from_pretrained(\n",
" \"finetuned_entity_categorical_classification/checkpoint-3346\", num_labels=27, id2label=id2label, label2id=label2id\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 19,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"You're using a DistilBertTokenizerFast tokenizer. Please note that with a fast tokenizer, using the `__call__` method is faster than using a method to encode the text followed by a call to the `pad` method to get a padded encoding.\n"
]
},
{
"data": {
"text/html": [
"\n",
" <div>\n",
" \n",
" <progress value='3362' max='3362' style='width:300px; height:20px; vertical-align: middle;'></progress>\n",
" [3362/3362 01:52, Epoch 2/2]\n",
" </div>\n",
" <table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: left;\">\n",
" <th>Epoch</th>\n",
" <th>Training Loss</th>\n",
" <th>Validation Loss</th>\n",
" <th>Accuracy</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <td>1</td>\n",
" <td>0.102300</td>\n",
" <td>0.077652</td>\n",
" <td>0.975309</td>\n",
" </tr>\n",
" <tr>\n",
" <td>2</td>\n",
" <td>0.083400</td>\n",
" <td>0.086291</td>\n",
" <td>0.974714</td>\n",
" </tr>\n",
" </tbody>\n",
"</table><p>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/plain": [
"TrainOutput(global_step=3362, training_loss=0.08880683540376008, metrics={'train_runtime': 113.5357, 'train_samples_per_second': 473.666, 'train_steps_per_second': 29.612, 'total_flos': 213673546900476.0, 'train_loss': 0.08880683540376008, 'epoch': 2.0})"
]
},
"execution_count": 19,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"training_args = TrainingArguments(\n",
" output_dir=\"finetuned_entity_categorical_classification\",\n",
" learning_rate=2e-5,\n",
" per_device_train_batch_size=16,\n",
" per_device_eval_batch_size=16,\n",
" num_train_epochs=2,\n",
" weight_decay=0.01,\n",
" evaluation_strategy=\"epoch\",\n",
" save_strategy=\"epoch\",\n",
" load_best_model_at_end=True,\n",
" # push_to_hub=True,\n",
")\n",
"\n",
"trainer = Trainer(\n",
" model=model,\n",
" args=training_args,\n",
" train_dataset=tokenized_df[\"train\"],\n",
" eval_dataset=tokenized_df[\"test\"],\n",
" tokenizer=tokenizer,\n",
" data_collator=data_collator,\n",
" compute_metrics=compute_metrics,\n",
")\n",
"\n",
"trainer.train()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "venv",
"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": "3.10.12"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
|