Spaces:
Runtime error
Runtime error
File size: 79,563 Bytes
91a9511 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 |
{
"cells": [
{
"cell_type": "markdown",
"metadata": {
"id": "X4cRE8IbIrIV"
},
"source": [
"If you're opening this Notebook on colab, you will probably need to install 🤗 Transformers and 🤗 Datasets. Uncomment the following cell and run it."
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 1000
},
"id": "MOsHUjgdIrIW",
"outputId": "f84a093e-147f-470e-aad9-80fb51193c8e"
},
"outputs": [],
"source": [
"#! pip install transformers\n",
"#! pip install datasets\n",
"#! pip install huggingface_hub"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"If you're opening this notebook locally, make sure your environment has an install from the latest version of those libraries.\n",
"\n",
"To be able to share your model with the community and generate results like the one shown in the picture below via the inference API, there are a few more steps to follow.\n",
"\n",
"First you have to store your authentication token from the Hugging Face website (sign up [here](https://huggingface.co/join) if you haven't already!) then run the following cell and input your token:"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "9dbff25b935149db8796a354c89fdcc3",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"VBox(children=(HTML(value='<center>\\n<img src=https://huggingface.co/front/assets/huggingface_logo-noborder.sv…"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"from huggingface_hub import notebook_login\n",
"\n",
"notebook_login()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Then you need to install Git-LFS and setup Git if you haven't already. Uncomment the following instructions and adapt with your name and email:"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# !apt install git-lfs\n",
"# !git config --global user.email \"you@example.com\"\n",
"# !git config --global user.name \"Your Name\""
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Make sure your version of Transformers is at least 4.16.0 since some of the functionality we use was only introduced in that version."
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"4.18.0\n"
]
}
],
"source": [
"import transformers\n",
"\n",
"print(transformers.__version__)"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "HFASsisvIrIb"
},
"source": [
"You can find a script version of this notebook to fine-tune your model in a distributed fashion using multiple GPUs or TPUs [here](https://github.com/huggingface/transformers/tree/master/examples/language-modeling)."
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "a3KD3WXU3l-O"
},
"source": [
"# Fine-tuning a language model"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "JAscNNUD3l-P"
},
"source": [
"In this notebook, we'll see how to fine-tune one of the [🤗 Transformers](https://github.com/huggingface/transformers) model on a language modeling task. We will cover two types of language modeling tasks which are:\n",
"\n",
"- Causal language modeling: the model has to predict the next token in the sentence (so the labels are the same as the inputs shifted to the right). To make sure the model does not cheat, its attention computations are masked so that tokens cannot attend to tokens to their right, as this would result in label leakage.\n",
"\n",
"\n",
"\n",
"- Masked language modeling: the model has to predict some tokens that are masked in the input. It still has access to the whole sentence, so it can use the tokens before and after the masked tokens to predict their value.\n",
"\n",
"\n",
"\n",
"We will see how to easily load and preprocess the dataset for each one of those tasks, and how to use Keras to fine-tune a model on it.\n",
"\n",
"A script version of this notebook you can directly run on a distributed environment or on TPU is available in our [examples folder](https://github.com/huggingface/transformers/tree/master/examples)."
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "1r_n9OWV3l-Q"
},
"source": [
"## Preparing the dataset"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "kswRMhPc3l-Q"
},
"source": [
"For each of those tasks, we will use the [Wikitext 2]() dataset as an example. You can load it very easily with the 🤗 Datasets library."
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {
"id": "n2ZRs1cL3l-R",
"outputId": "11151c56-be90-4d11-e7df-db85e745ca5c"
},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"Reusing dataset wikitext (/Users/ArjunPatel/.cache/huggingface/datasets/wikitext/wikitext-2-raw-v1/1.0.0/a241db52902eaf2c6aa732210bead40c090019a499ceb13bcbfa3f8ab646a126)\n"
]
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "c4380fbf717e4b7aa0c6a7512335950c",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
" 0%| | 0/3 [00:00<?, ?it/s]"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"from datasets import load_dataset\n",
"\n",
"datasets = load_dataset(\"wikitext\", \"wikitext-2-raw-v1\")"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "f1-9jepM3l-W"
},
"source": [
"You can replace the dataset above with any dataset hosted on [the hub](https://huggingface.co/datasets) or use your own files. Just uncomment the following cell and replace the paths with your own input files:"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {
"id": "uxSaGa_l3l-W"
},
"outputs": [],
"source": [
"# datasets = load_dataset(\"text\", data_files={\"train\": path_to_train.txt, \"validation\": path_to_validation.txt}"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "jY1SwIrY3l-a"
},
"source": [
"You can also load datasets from a csv or a JSON file, see the [full documentation](https://huggingface.co/docs/datasets/loading_datasets.html#from-local-files) for more information."
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "u3EtYfeHIrIz"
},
"source": [
"To access an actual element, you need to select a split first, then give an index:"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {
"id": "X6HrpprwIrIz",
"outputId": "d7670bc0-42e4-4c09-8a6a-5c018ded7d95"
},
"outputs": [
{
"data": {
"text/plain": [
"{'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'}"
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"datasets[\"train\"][10]"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "WHUmphG3IrI3"
},
"source": [
"To get a sense of what the data looks like, the following function will show some examples picked randomly in the dataset."
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {
"id": "ur5sNUcZ3l-g"
},
"outputs": [],
"source": [
"from datasets import ClassLabel\n",
"import random\n",
"import pandas as pd\n",
"from IPython.display import display, HTML\n",
"\n",
"\n",
"def show_random_elements(dataset, num_examples=10):\n",
" assert num_examples <= len(\n",
" dataset\n",
" ), \"Can't pick more elements than there are in the dataset.\"\n",
" picks = []\n",
" for _ in range(num_examples):\n",
" pick = random.randint(0, len(dataset) - 1)\n",
" while pick in picks:\n",
" pick = random.randint(0, len(dataset) - 1)\n",
" picks.append(pick)\n",
"\n",
" df = pd.DataFrame(dataset[picks])\n",
" for column, typ in dataset.features.items():\n",
" if isinstance(typ, ClassLabel):\n",
" df[column] = df[column].transform(lambda i: typ.names[i])\n",
" display(HTML(df.to_html()))"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {
"id": "1Uk8NROQ3l-k",
"outputId": "a822dcec-51e3-4dba-c73c-dba9e0301726"
},
"outputs": [
{
"data": {
"text/html": [
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>text</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Today , Lady Rosebery is a mere footnote in the long history of her husband 's family , rather as Consuelo Vanderbilt is regarded in the Spencer @-@ Churchill family . Her husband , once one of the \" most celebrated figures in Britain , \" is a minor figure in British history . Thus , Hannah , Countess of Rosebery , in her day celebrated in the worlds of politics , philanthropy , and high society , is largely unknown and forgotten . \\n</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>Agujaceratops - ( Texas , USA ) \\n</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>The city of Galveston is situated on Galveston Island , a barrier island off the Texas Gulf coast near the mainland coast . Made up of mostly sand @-@ sized particles and smaller amounts of finer mud sediments and larger gravel @-@ sized sediments , the island is unstable , affected by water and weather , and can shift its boundaries through erosion . \\n</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>Although ceratopsians are generally considered herbivorous , a few paleontologists , such as Darren Naish and Mark Witton , have speculated online that at least some ceratopsians may have been opportunistically omnivorous . \\n</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td></td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td></td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>= = = Menu , coup and North Vietnamese offensive = = = \\n</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
" <td>It was for his leadership and bravery during these actions that Andrew was awarded the Victoria Cross ( VC ) at the age of 20 . The citation read as follows : \\n</td>\n",
" </tr>\n",
" <tr>\n",
" <th>8</th>\n",
" <td>= = Death of Clement XIII = = \\n</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9</th>\n",
" <td>= = = In the media = = = \\n</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"show_random_elements(datasets[\"train\"])"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "CKerdF353l-o"
},
"source": [
"As we can see, some of the texts are a full paragraph of a Wikipedia article while others are just titles or empty lines."
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "JEA1ju653l-p"
},
"source": [
"## Causal Language modeling"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "v5GTGKZS3l-q"
},
"source": [
"For causal language modeling (CLM) we are going to take all the texts in our dataset, tokenize them and concatenate them. Then we will split them into examples of a fixed sequence length. This way the model will receive chunks of contiguous text that may look like:\n",
"```\n",
"part of text 1\n",
"```\n",
"or \n",
"```\n",
"end of text 1 [BOS_TOKEN] beginning of text 2\n",
"```\n",
"depending on whether they span multiple original texts or not. The labels will be the same as the inputs, shifted to the right.\n",
"\n",
"We will use the [`distilgpt2`](https://huggingface.co/distilgpt2) model for this example. You can pick any of the checkpoints listed [here](https://huggingface.co/models?filter=causal-lm) instead:"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {
"id": "-WGBCO343l-q"
},
"outputs": [],
"source": [
"model_checkpoint = \"distilgpt2\"\n"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "5io6fY_d3l-u"
},
"source": [
"To tokenize all our texts with the same vocabulary that was used when training the model, we have to download a pretrained tokenizer. This is all done by the `AutoTokenizer` class:"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {
"id": "iAYlS40Z3l-v"
},
"outputs": [],
"source": [
"from transformers import AutoTokenizer\n",
"\n",
"tokenizer = AutoTokenizer.from_pretrained(model_checkpoint)"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "rpOiBrJ13l-y"
},
"source": [
"We can now call the tokenizer on all our texts. This is very simple, using the [`map`](https://huggingface.co/docs/datasets/package_reference/main_classes.html#datasets.Dataset.map) method from the Datasets library. First we define a function that calls the tokenizer on our texts:"
]
},
{
"cell_type": "code",
"execution_count": 11,
"metadata": {
"id": "lS2m25YM3l-z"
},
"outputs": [],
"source": [
"def tokenize_function(examples):\n",
" return tokenizer(examples[\"text\"])"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "M9xVAa3s3l-2"
},
"source": [
"Then we apply it to all the splits in our `datasets` object, using `batched=True` and 4 processes to speed up the preprocessing. We won't need the `text` column afterward, so we discard it."
]
},
{
"cell_type": "code",
"execution_count": 12,
"metadata": {
"id": "NVAO0H8u3l-3",
"outputId": "30d88b8a-e353-4e13-f709-8e5e06ef747b"
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
" "
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"Loading cached processed dataset at /Users/ArjunPatel/.cache/huggingface/datasets/wikitext/wikitext-2-raw-v1/1.0.0/a241db52902eaf2c6aa732210bead40c090019a499ceb13bcbfa3f8ab646a126/cache-61391423a2766fc9.arrow\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
" "
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"Loading cached processed dataset at /Users/ArjunPatel/.cache/huggingface/datasets/wikitext/wikitext-2-raw-v1/1.0.0/a241db52902eaf2c6aa732210bead40c090019a499ceb13bcbfa3f8ab646a126/cache-5ceac15e651919d2.arrow\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
" "
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"Loading cached processed dataset at /Users/ArjunPatel/.cache/huggingface/datasets/wikitext/wikitext-2-raw-v1/1.0.0/a241db52902eaf2c6aa732210bead40c090019a499ceb13bcbfa3f8ab646a126/cache-b81e39451b6b2f7e.arrow\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
" "
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"Loading cached processed dataset at /Users/ArjunPatel/.cache/huggingface/datasets/wikitext/wikitext-2-raw-v1/1.0.0/a241db52902eaf2c6aa732210bead40c090019a499ceb13bcbfa3f8ab646a126/cache-1bcda98ae382df67.arrow\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
" "
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"Loading cached processed dataset at /Users/ArjunPatel/.cache/huggingface/datasets/wikitext/wikitext-2-raw-v1/1.0.0/a241db52902eaf2c6aa732210bead40c090019a499ceb13bcbfa3f8ab646a126/cache-fa4442bf92b4768b.arrow\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
" "
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"Loading cached processed dataset at /Users/ArjunPatel/.cache/huggingface/datasets/wikitext/wikitext-2-raw-v1/1.0.0/a241db52902eaf2c6aa732210bead40c090019a499ceb13bcbfa3f8ab646a126/cache-aa2a4366053b507c.arrow\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
" "
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"Loading cached processed dataset at /Users/ArjunPatel/.cache/huggingface/datasets/wikitext/wikitext-2-raw-v1/1.0.0/a241db52902eaf2c6aa732210bead40c090019a499ceb13bcbfa3f8ab646a126/cache-962e11e2efef61ea.arrow\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
" "
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"Loading cached processed dataset at /Users/ArjunPatel/.cache/huggingface/datasets/wikitext/wikitext-2-raw-v1/1.0.0/a241db52902eaf2c6aa732210bead40c090019a499ceb13bcbfa3f8ab646a126/cache-9a86568f88be8e85.arrow\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
" "
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"Loading cached processed dataset at /Users/ArjunPatel/.cache/huggingface/datasets/wikitext/wikitext-2-raw-v1/1.0.0/a241db52902eaf2c6aa732210bead40c090019a499ceb13bcbfa3f8ab646a126/cache-9f392100036d7e36.arrow\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
" "
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"Loading cached processed dataset at /Users/ArjunPatel/.cache/huggingface/datasets/wikitext/wikitext-2-raw-v1/1.0.0/a241db52902eaf2c6aa732210bead40c090019a499ceb13bcbfa3f8ab646a126/cache-bcce0e8f19f73037.arrow\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
" "
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"Loading cached processed dataset at /Users/ArjunPatel/.cache/huggingface/datasets/wikitext/wikitext-2-raw-v1/1.0.0/a241db52902eaf2c6aa732210bead40c090019a499ceb13bcbfa3f8ab646a126/cache-9776e9836e6e1ee0.arrow\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
" "
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"Loading cached processed dataset at /Users/ArjunPatel/.cache/huggingface/datasets/wikitext/wikitext-2-raw-v1/1.0.0/a241db52902eaf2c6aa732210bead40c090019a499ceb13bcbfa3f8ab646a126/cache-55693ec29a40f3cb.arrow\n"
]
}
],
"source": [
"tokenized_datasets = datasets.map(\n",
" tokenize_function, batched=True, num_proc=4, remove_columns=[\"text\"]\n",
")"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "8qik3J_C3l-7"
},
"source": [
"If we now look at an element of our datasets, we will see the text have been replaced by the `input_ids` the model will need:"
]
},
{
"cell_type": "code",
"execution_count": 13,
"metadata": {
"id": "nYv_mcKk3l-7",
"outputId": "8334734c-0f86-4e18-ec17-4216a2d5dd18"
},
"outputs": [
{
"data": {
"text/plain": [
"{'input_ids': [796, 569, 18354, 7496, 17740, 6711, 796, 220, 198],\n",
" 'attention_mask': [1, 1, 1, 1, 1, 1, 1, 1, 1]}"
]
},
"execution_count": 13,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"tokenized_datasets[\"train\"][1]"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "obvgcXda3l--"
},
"source": [
"Now for the harder part: We need to concatenate all our texts together, and then split the result into chunks of a fixed size, which we will call `block_size`. To do this, we will use the `map` method again, with the option `batched=True`. When we use `batched=True`, the function we pass to `map()` will be passed multiple inputs at once, allowing us to group them into more or fewer examples than we had in the input. This allows us to create our new fixed-length samples.\n",
"\n",
"We can use any `block_size` up to the the maximum length our model was pretrained with, which for models in the `gpt2` family is usually something in the range 512-1024. This might be a bit too big to fit in your GPU RAM, though, so let's use something a bit smaller: 128."
]
},
{
"cell_type": "code",
"execution_count": 14,
"metadata": {
"id": "DVHs5aCA3l-_"
},
"outputs": [],
"source": [
"# block_size = tokenizer.model_max_length\n",
"block_size = 128"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "RpNfGiMw3l_A"
},
"source": [
"Then we write the preprocessing function that will group our texts:"
]
},
{
"cell_type": "code",
"execution_count": 15,
"metadata": {
"id": "iaAJy5Hu3l_B"
},
"outputs": [],
"source": [
"def group_texts(examples):\n",
" # Concatenate all texts.\n",
" concatenated_examples = {k: sum(examples[k], []) for k in examples.keys()}\n",
" total_length = len(concatenated_examples[list(examples.keys())[0]])\n",
" # We drop the small remainder, though you could add padding instead if the model supports it\n",
" # In this, as in all things, we advise you to follow your heart\n",
" total_length = (total_length // block_size) * block_size\n",
" # Split by chunks of max_len.\n",
" result = {\n",
" k: [t[i : i + block_size] for i in range(0, total_length, block_size)]\n",
" for k, t in concatenated_examples.items()\n",
" }\n",
" result[\"labels\"] = result[\"input_ids\"].copy()\n",
" return result"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "LGJWXtNv3l_C"
},
"source": [
"Note that we duplicate the inputs for our labels, without shifting them, even though we told you the labels need to be shifted! This is because CausalLM models in the 🤗 Transformers library automatically apply right-shifting to the inputs, so we don't need to do it manually.\n",
"\n",
"Also note that by default, the `map` method will send a batch of 1,000 examples to be treated by the preprocessing function. So here, we will drop the remainder to make the concatenated tokenized texts a multiple of `block_size` every 1,000 examples. You can adjust this behavior by passing a higher batch size (which will also be processed slower). You can also speed-up the preprocessing by using multiprocessing:"
]
},
{
"cell_type": "code",
"execution_count": 16,
"metadata": {
"id": "gXUSfBrq3l_C",
"outputId": "34e55885-3d8f-4f05-cbdb-706ce56a25f8"
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
" "
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"Loading cached processed dataset at /Users/ArjunPatel/.cache/huggingface/datasets/wikitext/wikitext-2-raw-v1/1.0.0/a241db52902eaf2c6aa732210bead40c090019a499ceb13bcbfa3f8ab646a126/cache-7b71dd2271728f79.arrow\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
" "
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"Loading cached processed dataset at /Users/ArjunPatel/.cache/huggingface/datasets/wikitext/wikitext-2-raw-v1/1.0.0/a241db52902eaf2c6aa732210bead40c090019a499ceb13bcbfa3f8ab646a126/cache-cee53a8f6793ac14.arrow\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
" "
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"Loading cached processed dataset at /Users/ArjunPatel/.cache/huggingface/datasets/wikitext/wikitext-2-raw-v1/1.0.0/a241db52902eaf2c6aa732210bead40c090019a499ceb13bcbfa3f8ab646a126/cache-03de660721d6e90f.arrow\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
" "
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"Loading cached processed dataset at /Users/ArjunPatel/.cache/huggingface/datasets/wikitext/wikitext-2-raw-v1/1.0.0/a241db52902eaf2c6aa732210bead40c090019a499ceb13bcbfa3f8ab646a126/cache-1aa9f24edffd33bf.arrow\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
" "
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"Loading cached processed dataset at /Users/ArjunPatel/.cache/huggingface/datasets/wikitext/wikitext-2-raw-v1/1.0.0/a241db52902eaf2c6aa732210bead40c090019a499ceb13bcbfa3f8ab646a126/cache-be9266f35a58e0d1.arrow\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
" "
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"Loading cached processed dataset at /Users/ArjunPatel/.cache/huggingface/datasets/wikitext/wikitext-2-raw-v1/1.0.0/a241db52902eaf2c6aa732210bead40c090019a499ceb13bcbfa3f8ab646a126/cache-a6201b62855b0506.arrow\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
" "
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"Loading cached processed dataset at /Users/ArjunPatel/.cache/huggingface/datasets/wikitext/wikitext-2-raw-v1/1.0.0/a241db52902eaf2c6aa732210bead40c090019a499ceb13bcbfa3f8ab646a126/cache-f208c1a35aa5450a.arrow\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
" "
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"Loading cached processed dataset at /Users/ArjunPatel/.cache/huggingface/datasets/wikitext/wikitext-2-raw-v1/1.0.0/a241db52902eaf2c6aa732210bead40c090019a499ceb13bcbfa3f8ab646a126/cache-233fc6217e931151.arrow\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
" "
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"Loading cached processed dataset at /Users/ArjunPatel/.cache/huggingface/datasets/wikitext/wikitext-2-raw-v1/1.0.0/a241db52902eaf2c6aa732210bead40c090019a499ceb13bcbfa3f8ab646a126/cache-865d7a7e5760a6af.arrow\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
" "
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"Loading cached processed dataset at /Users/ArjunPatel/.cache/huggingface/datasets/wikitext/wikitext-2-raw-v1/1.0.0/a241db52902eaf2c6aa732210bead40c090019a499ceb13bcbfa3f8ab646a126/cache-996d57e28a0c3daa.arrow\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
" "
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"Loading cached processed dataset at /Users/ArjunPatel/.cache/huggingface/datasets/wikitext/wikitext-2-raw-v1/1.0.0/a241db52902eaf2c6aa732210bead40c090019a499ceb13bcbfa3f8ab646a126/cache-2b587ab7ed92bd6d.arrow\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
" "
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"Loading cached processed dataset at /Users/ArjunPatel/.cache/huggingface/datasets/wikitext/wikitext-2-raw-v1/1.0.0/a241db52902eaf2c6aa732210bead40c090019a499ceb13bcbfa3f8ab646a126/cache-81447c56f742f510.arrow\n"
]
}
],
"source": [
"lm_datasets = tokenized_datasets.map(\n",
" group_texts,\n",
" batched=True,\n",
" batch_size=1000,\n",
" num_proc=4,\n",
")"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "6n84V8Gc3l_G"
},
"source": [
"And we can check our datasets have changed: now the samples contain chunks of `block_size` contiguous tokens, potentially spanning several of our original texts."
]
},
{
"cell_type": "code",
"execution_count": 17,
"metadata": {
"id": "hTeGCLl_3l_G",
"outputId": "ab381a07-f92e-4b14-f7b6-e4af5513d7c4"
},
"outputs": [
{
"data": {
"text/plain": [
"' game and follows 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 Oz'"
]
},
"execution_count": 17,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"tokenizer.decode(lm_datasets[\"train\"][1][\"input_ids\"])"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "iEmeQ7Xm3l_H"
},
"source": [
"Now that the data has been cleaned, we're ready to initialize our model:"
]
},
{
"cell_type": "code",
"execution_count": 18,
"metadata": {
"id": "sPqQA3TT3l_I"
},
"outputs": [
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "ff73baa0c0764c60846c0dd310506dfc",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"Downloading: 0%| | 0.00/313M [00:00<?, ?B/s]"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"2022-05-09 20:46:18.219552: I tensorflow/core/platform/cpu_feature_guard.cc:151] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations: AVX2 FMA\n",
"To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.\n",
"2022-05-09 20:46:18.230340: W tensorflow/python/util/util.cc:368] Sets are not currently considered sequences, but this may change in the future, so consider avoiding using them.\n",
"All model checkpoint layers were used when initializing TFGPT2LMHeadModel.\n",
"\n",
"All the layers of TFGPT2LMHeadModel were initialized from the model checkpoint at distilgpt2.\n",
"If your task is similar to the task the model of the checkpoint was trained on, you can already use TFGPT2LMHeadModel for predictions without further training.\n"
]
}
],
"source": [
"from transformers import TFAutoModelForCausalLM\n",
"\n",
"model = TFAutoModelForCausalLM.from_pretrained(model_checkpoint)"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "VyPQTOF_3l_J"
},
"source": [
"Once we've done that, it's time for our optimizer! We can initialize our `AdamWeightDecay` optimizer directly, or we can use the `create_optimizer` function to generate an `AdamWeightDecay` optimizer with a learning rate schedule. In this case, we'll just stick with a constant learning rate for simplicity, so let's just use `AdamWeightDecay`."
]
},
{
"cell_type": "code",
"execution_count": 19,
"metadata": {
"id": "jElf8LJ33l_K"
},
"outputs": [],
"source": [
"from transformers import create_optimizer, AdamWeightDecay"
]
},
{
"cell_type": "code",
"execution_count": 20,
"metadata": {
"id": "YbSwEhQ63l_L"
},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"/Users/ArjunPatel/.local/lib/python3.7/site-packages/keras/optimizer_v2/adam.py:105: UserWarning: The `lr` argument is deprecated, use `learning_rate` instead.\n",
" super(Adam, self).__init__(name, **kwargs)\n"
]
}
],
"source": [
"optimizer = AdamWeightDecay(lr=2e-5, weight_decay_rate=0.01)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Note that most models on the Hub compute loss internally, so we actually don't have to specify anything there! Leaving the loss field blank will cause the model to read the `loss` head as its loss value.\n",
"\n",
"This is an unusual quirk of TensorFlow models in 🤗 Transformers, so it's worth elaborating on in a little more detail. All 🤗 Transformers models are capable of computing an appropriate loss for their task internally (for example, a CausalLM model will use a cross-entropy loss). To do this, the labels must be provided in the input dict (or equivalently, in the `columns` argument to `to_tf_dataset()`), so that they are visible to the model during the forward pass.\n",
"\n",
"This is quite different from the standard Keras way of handling losses, where labels are passed separately and not visible to the main body of the model, and loss is handled by a function that the user passes to `compile()`, which uses the model outputs and the label to compute a loss value.\n",
"\n",
"The approach we take is that if the user does not pass a loss to `compile()`, the model will assume you want the **internal** loss. If you are doing this, you should make sure that the labels column(s) are included in the **input dict** or in the `columns` argument to `to_tf_dataset`.\n",
"\n",
"If you want to use your own loss, that is of course possible too! If you do this, you should make sure your labels column(s) are passed like normal labels, either as the **second argument** to `model.fit()`, or in the `label_cols` argument to `to_tf_dataset`. "
]
},
{
"cell_type": "code",
"execution_count": 22,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"No loss specified in compile() - the model's internal loss computation will be used as the loss. Don't panic - this is a common way to train TensorFlow models in Transformers! To disable this behaviour, please pass a loss argument, or explicitly pass `loss=None` if you do not want your model to compute a loss.\n"
]
}
],
"source": [
"import tensorflow as tf\n",
"\n",
"model.compile(optimizer=optimizer)"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "sZRbT9ui3l_N"
},
"source": [
"Next, we convert our datasets to `tf.data.Dataset`, which Keras understands natively. `Dataset` objects have a built-in method for this. Because all our inputs are the same length, no padding is required, so we can use the DefaultDataCollator. Note that our data collators are designed to work for multiple frameworks, so ensure you set the `return_tensors='tf'` argument to get Tensorflow tensors out - you don't want to accidentally get a load of `torch.Tensor` objects in the middle of your nice TF code!"
]
},
{
"cell_type": "code",
"execution_count": 23,
"metadata": {
"id": "OEuqwIra3l_N"
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"WARNING:tensorflow:AutoGraph could not transform <function TensorflowDatasetMixin.to_tf_dataset.<locals>.fetch_function at 0x7fd6e30aa830> and will run it as-is.\n",
"Please report this to the TensorFlow team. When filing the bug, set the verbosity to 10 (on Linux, `export AUTOGRAPH_VERBOSITY=10`) and attach the full output.\n",
"Cause: module 'gast' has no attribute 'Constant'\n",
"To silence this warning, decorate the function with @tf.autograph.experimental.do_not_convert\n",
"WARNING: AutoGraph could not transform <function TensorflowDatasetMixin.to_tf_dataset.<locals>.fetch_function at 0x7fd6e30aa830> and will run it as-is.\n",
"Please report this to the TensorFlow team. When filing the bug, set the verbosity to 10 (on Linux, `export AUTOGRAPH_VERBOSITY=10`) and attach the full output.\n",
"Cause: module 'gast' has no attribute 'Constant'\n",
"To silence this warning, decorate the function with @tf.autograph.experimental.do_not_convert\n",
"WARNING:tensorflow:AutoGraph could not transform <function TensorflowDatasetMixin.to_tf_dataset.<locals>.ensure_shapes at 0x7fd6f2d50f80> and will run it as-is.\n",
"Please report this to the TensorFlow team. When filing the bug, set the verbosity to 10 (on Linux, `export AUTOGRAPH_VERBOSITY=10`) and attach the full output.\n",
"Cause: module 'gast' has no attribute 'Constant'\n",
"To silence this warning, decorate the function with @tf.autograph.experimental.do_not_convert\n",
"WARNING: AutoGraph could not transform <function TensorflowDatasetMixin.to_tf_dataset.<locals>.ensure_shapes at 0x7fd6f2d50f80> and will run it as-is.\n",
"Please report this to the TensorFlow team. When filing the bug, set the verbosity to 10 (on Linux, `export AUTOGRAPH_VERBOSITY=10`) and attach the full output.\n",
"Cause: module 'gast' has no attribute 'Constant'\n",
"To silence this warning, decorate the function with @tf.autograph.experimental.do_not_convert\n",
"WARNING:tensorflow:AutoGraph could not transform <function TensorflowDatasetMixin.to_tf_dataset.<locals>.fetch_function at 0x7fd6e30ddd40> and will run it as-is.\n",
"Please report this to the TensorFlow team. When filing the bug, set the verbosity to 10 (on Linux, `export AUTOGRAPH_VERBOSITY=10`) and attach the full output.\n",
"Cause: module 'gast' has no attribute 'Constant'\n",
"To silence this warning, decorate the function with @tf.autograph.experimental.do_not_convert\n",
"WARNING: AutoGraph could not transform <function TensorflowDatasetMixin.to_tf_dataset.<locals>.fetch_function at 0x7fd6e30ddd40> and will run it as-is.\n",
"Please report this to the TensorFlow team. When filing the bug, set the verbosity to 10 (on Linux, `export AUTOGRAPH_VERBOSITY=10`) and attach the full output.\n",
"Cause: module 'gast' has no attribute 'Constant'\n",
"To silence this warning, decorate the function with @tf.autograph.experimental.do_not_convert\n",
"WARNING:tensorflow:AutoGraph could not transform <function TensorflowDatasetMixin.to_tf_dataset.<locals>.ensure_shapes at 0x7fd6e2b88050> and will run it as-is.\n",
"Please report this to the TensorFlow team. When filing the bug, set the verbosity to 10 (on Linux, `export AUTOGRAPH_VERBOSITY=10`) and attach the full output.\n",
"Cause: module 'gast' has no attribute 'Constant'\n",
"To silence this warning, decorate the function with @tf.autograph.experimental.do_not_convert\n",
"WARNING: AutoGraph could not transform <function TensorflowDatasetMixin.to_tf_dataset.<locals>.ensure_shapes at 0x7fd6e2b88050> and will run it as-is.\n",
"Please report this to the TensorFlow team. When filing the bug, set the verbosity to 10 (on Linux, `export AUTOGRAPH_VERBOSITY=10`) and attach the full output.\n",
"Cause: module 'gast' has no attribute 'Constant'\n",
"To silence this warning, decorate the function with @tf.autograph.experimental.do_not_convert\n"
]
}
],
"source": [
"from transformers import DefaultDataCollator\n",
"\n",
"data_collator = DefaultDataCollator(return_tensors=\"tf\")\n",
"\n",
"train_set = lm_datasets[\"train\"].to_tf_dataset(\n",
" columns=[\"attention_mask\", \"input_ids\", \"labels\"],\n",
" shuffle=True,\n",
" batch_size=16,\n",
" collate_fn=data_collator,\n",
")\n",
"validation_set = lm_datasets[\"validation\"].to_tf_dataset(\n",
" columns=[\"attention_mask\", \"input_ids\", \"labels\"],\n",
" shuffle=False,\n",
" batch_size=16,\n",
" collate_fn=data_collator,\n",
")"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "6Vvz34Td3l_O"
},
"source": [
"Now we can train our model. We can also add a callback to sync up our model with the Hub - this allows us to resume training from other machines and even test the model's inference quality midway through training! If you don't want to do this, simply remove the callbacks argument in the call to `fit()`. "
]
},
{
"cell_type": "code",
"execution_count": 24,
"metadata": {
"id": "NyZvu_MF3l_P",
"outputId": "b69d0931-7f1f-4f2d-fdb8-09d37c7418bb"
},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"Cloning https://huggingface.co/arjunpatel/distilgpt2-finetuned-wikitext2 into local empty directory.\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"WARNING:tensorflow:AutoGraph could not transform <function Model.make_train_function.<locals>.train_function at 0x7fd6e30fb200> and will run it as-is.\n",
"Please report this to the TensorFlow team. When filing the bug, set the verbosity to 10 (on Linux, `export AUTOGRAPH_VERBOSITY=10`) and attach the full output.\n",
"Cause: 'arguments' object has no attribute 'posonlyargs'\n",
"To silence this warning, decorate the function with @tf.autograph.experimental.do_not_convert\n",
"WARNING: AutoGraph could not transform <function Model.make_train_function.<locals>.train_function at 0x7fd6e30fb200> and will run it as-is.\n",
"Please report this to the TensorFlow team. When filing the bug, set the verbosity to 10 (on Linux, `export AUTOGRAPH_VERBOSITY=10`) and attach the full output.\n",
"Cause: 'arguments' object has no attribute 'posonlyargs'\n",
"To silence this warning, decorate the function with @tf.autograph.experimental.do_not_convert\n",
"WARNING:tensorflow:AutoGraph could not transform <bound method TFGPT2LMHeadModel.call of <transformers.models.gpt2.modeling_tf_gpt2.TFGPT2LMHeadModel object at 0x7fd72024f990>> and will run it as-is.\n",
"Please report this to the TensorFlow team. When filing the bug, set the verbosity to 10 (on Linux, `export AUTOGRAPH_VERBOSITY=10`) and attach the full output.\n",
"Cause: module 'gast' has no attribute 'Constant'\n",
"To silence this warning, decorate the function with @tf.autograph.experimental.do_not_convert\n",
"WARNING: AutoGraph could not transform <bound method TFGPT2LMHeadModel.call of <transformers.models.gpt2.modeling_tf_gpt2.TFGPT2LMHeadModel object at 0x7fd72024f990>> and will run it as-is.\n",
"Please report this to the TensorFlow team. When filing the bug, set the verbosity to 10 (on Linux, `export AUTOGRAPH_VERBOSITY=10`) and attach the full output.\n",
"Cause: module 'gast' has no attribute 'Constant'\n",
"To silence this warning, decorate the function with @tf.autograph.experimental.do_not_convert\n",
"WARNING:tensorflow:AutoGraph could not transform <bound method TFGPT2MainLayer.call of <transformers.models.gpt2.modeling_tf_gpt2.TFGPT2MainLayer object at 0x7fd7203394d0>> and will run it as-is.\n",
"Please report this to the TensorFlow team. When filing the bug, set the verbosity to 10 (on Linux, `export AUTOGRAPH_VERBOSITY=10`) and attach the full output.\n",
"Cause: module 'gast' has no attribute 'Constant'\n",
"To silence this warning, decorate the function with @tf.autograph.experimental.do_not_convert\n",
"WARNING: AutoGraph could not transform <bound method TFGPT2MainLayer.call of <transformers.models.gpt2.modeling_tf_gpt2.TFGPT2MainLayer object at 0x7fd7203394d0>> and will run it as-is.\n",
"Please report this to the TensorFlow team. When filing the bug, set the verbosity to 10 (on Linux, `export AUTOGRAPH_VERBOSITY=10`) and attach the full output.\n",
"Cause: module 'gast' has no attribute 'Constant'\n",
"To silence this warning, decorate the function with @tf.autograph.experimental.do_not_convert\n",
"WARNING:tensorflow:AutoGraph could not transform <bound method TFSharedEmbeddings.call of <transformers.modeling_tf_utils.TFSharedEmbeddings object at 0x7fd720332e10>> and will run it as-is.\n",
"Please report this to the TensorFlow team. When filing the bug, set the verbosity to 10 (on Linux, `export AUTOGRAPH_VERBOSITY=10`) and attach the full output.\n",
"Cause: 'arguments' object has no attribute 'posonlyargs'\n",
"To silence this warning, decorate the function with @tf.autograph.experimental.do_not_convert\n",
"WARNING: AutoGraph could not transform <bound method TFSharedEmbeddings.call of <transformers.modeling_tf_utils.TFSharedEmbeddings object at 0x7fd720332e10>> and will run it as-is.\n",
"Please report this to the TensorFlow team. When filing the bug, set the verbosity to 10 (on Linux, `export AUTOGRAPH_VERBOSITY=10`) and attach the full output.\n",
"Cause: 'arguments' object has no attribute 'posonlyargs'\n",
"To silence this warning, decorate the function with @tf.autograph.experimental.do_not_convert\n",
"WARNING:tensorflow:AutoGraph could not transform <bound method TFBlock.call of <transformers.models.gpt2.modeling_tf_gpt2.TFBlock object at 0x7fd7203bd690>> and will run it as-is.\n",
"Please report this to the TensorFlow team. When filing the bug, set the verbosity to 10 (on Linux, `export AUTOGRAPH_VERBOSITY=10`) and attach the full output.\n",
"Cause: module 'gast' has no attribute 'Constant'\n",
"To silence this warning, decorate the function with @tf.autograph.experimental.do_not_convert\n",
"WARNING: AutoGraph could not transform <bound method TFBlock.call of <transformers.models.gpt2.modeling_tf_gpt2.TFBlock object at 0x7fd7203bd690>> and will run it as-is.\n",
"Please report this to the TensorFlow team. When filing the bug, set the verbosity to 10 (on Linux, `export AUTOGRAPH_VERBOSITY=10`) and attach the full output.\n",
"Cause: module 'gast' has no attribute 'Constant'\n",
"To silence this warning, decorate the function with @tf.autograph.experimental.do_not_convert\n",
"WARNING:tensorflow:AutoGraph could not transform <bound method TFAttention.call of <transformers.models.gpt2.modeling_tf_gpt2.TFAttention object at 0x7fd7203bd990>> and will run it as-is.\n",
"Please report this to the TensorFlow team. When filing the bug, set the verbosity to 10 (on Linux, `export AUTOGRAPH_VERBOSITY=10`) and attach the full output.\n",
"Cause: module 'gast' has no attribute 'Constant'\n",
"To silence this warning, decorate the function with @tf.autograph.experimental.do_not_convert\n",
"WARNING: AutoGraph could not transform <bound method TFAttention.call of <transformers.models.gpt2.modeling_tf_gpt2.TFAttention object at 0x7fd7203bd990>> and will run it as-is.\n",
"Please report this to the TensorFlow team. When filing the bug, set the verbosity to 10 (on Linux, `export AUTOGRAPH_VERBOSITY=10`) and attach the full output.\n",
"Cause: module 'gast' has no attribute 'Constant'\n",
"To silence this warning, decorate the function with @tf.autograph.experimental.do_not_convert\n",
"WARNING:tensorflow:AutoGraph could not transform <bound method TFConv1D.call of <transformers.modeling_tf_utils.TFConv1D object at 0x7fd7203bd6d0>> and will run it as-is.\n",
"Please report this to the TensorFlow team. When filing the bug, set the verbosity to 10 (on Linux, `export AUTOGRAPH_VERBOSITY=10`) and attach the full output.\n",
"Cause: 'arguments' object has no attribute 'posonlyargs'\n",
"To silence this warning, decorate the function with @tf.autograph.experimental.do_not_convert\n",
"WARNING: AutoGraph could not transform <bound method TFConv1D.call of <transformers.modeling_tf_utils.TFConv1D object at 0x7fd7203bd6d0>> and will run it as-is.\n",
"Please report this to the TensorFlow team. When filing the bug, set the verbosity to 10 (on Linux, `export AUTOGRAPH_VERBOSITY=10`) and attach the full output.\n",
"Cause: 'arguments' object has no attribute 'posonlyargs'\n",
"To silence this warning, decorate the function with @tf.autograph.experimental.do_not_convert\n",
"WARNING:tensorflow:AutoGraph could not transform <bound method TFMLP.call of <transformers.models.gpt2.modeling_tf_gpt2.TFMLP object at 0x7fd7204c2a10>> and will run it as-is.\n",
"Please report this to the TensorFlow team. When filing the bug, set the verbosity to 10 (on Linux, `export AUTOGRAPH_VERBOSITY=10`) and attach the full output.\n",
"Cause: 'arguments' object has no attribute 'posonlyargs'\n",
"To silence this warning, decorate the function with @tf.autograph.experimental.do_not_convert\n",
"WARNING: AutoGraph could not transform <bound method TFMLP.call of <transformers.models.gpt2.modeling_tf_gpt2.TFMLP object at 0x7fd7204c2a10>> and will run it as-is.\n",
"Please report this to the TensorFlow team. When filing the bug, set the verbosity to 10 (on Linux, `export AUTOGRAPH_VERBOSITY=10`) and attach the full output.\n",
"Cause: 'arguments' object has no attribute 'posonlyargs'\n",
"To silence this warning, decorate the function with @tf.autograph.experimental.do_not_convert\n",
"WARNING:tensorflow:AutoGraph could not transform <function dummy_loss at 0x7fd7202ce710> and will run it as-is.\n",
"Please report this to the TensorFlow team. When filing the bug, set the verbosity to 10 (on Linux, `export AUTOGRAPH_VERBOSITY=10`) and attach the full output.\n",
"Cause: 'arguments' object has no attribute 'posonlyargs'\n",
"To silence this warning, decorate the function with @tf.autograph.experimental.do_not_convert\n",
"WARNING: AutoGraph could not transform <function dummy_loss at 0x7fd7202ce710> and will run it as-is.\n",
"Please report this to the TensorFlow team. When filing the bug, set the verbosity to 10 (on Linux, `export AUTOGRAPH_VERBOSITY=10`) and attach the full output.\n",
"Cause: 'arguments' object has no attribute 'posonlyargs'\n",
"To silence this warning, decorate the function with @tf.autograph.experimental.do_not_convert\n",
" 7/1166 [..............................] - ETA: 1:24:49 - loss: 4.5316"
]
},
{
"ename": "KeyboardInterrupt",
"evalue": "",
"output_type": "error",
"traceback": [
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[0;31mKeyboardInterrupt\u001b[0m Traceback (most recent call last)",
"\u001b[0;32m/var/folders/vj/m14m1x1j47b8nvnmkfkf20ph0000gn/T/ipykernel_10410/3702115951.py\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[1;32m 15\u001b[0m \u001b[0mcallbacks\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m[\u001b[0m\u001b[0mtensorboard_callback\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mpush_to_hub_callback\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 16\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 17\u001b[0;31m \u001b[0mmodel\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mfit\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mtrain_set\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mvalidation_data\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mvalidation_set\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mepochs\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m1\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mcallbacks\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mcallbacks\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
"\u001b[0;32m~/.local/lib/python3.7/site-packages/keras/utils/traceback_utils.py\u001b[0m in \u001b[0;36merror_handler\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m 62\u001b[0m \u001b[0mfiltered_tb\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 63\u001b[0m \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 64\u001b[0;31m \u001b[0;32mreturn\u001b[0m \u001b[0mfn\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 65\u001b[0m \u001b[0;32mexcept\u001b[0m \u001b[0mException\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0me\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0;31m# pylint: disable=broad-except\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 66\u001b[0m \u001b[0mfiltered_tb\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0m_process_traceback_frames\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0me\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m__traceback__\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m~/.local/lib/python3.7/site-packages/keras/engine/training.py\u001b[0m in \u001b[0;36mfit\u001b[0;34m(self, x, y, batch_size, epochs, verbose, callbacks, validation_split, validation_data, shuffle, class_weight, sample_weight, initial_epoch, steps_per_epoch, validation_steps, validation_batch_size, validation_freq, max_queue_size, workers, use_multiprocessing)\u001b[0m\n\u001b[1;32m 1382\u001b[0m _r=1):\n\u001b[1;32m 1383\u001b[0m \u001b[0mcallbacks\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mon_train_batch_begin\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mstep\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1384\u001b[0;31m \u001b[0mtmp_logs\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mtrain_function\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0miterator\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 1385\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mdata_handler\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mshould_sync\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1386\u001b[0m \u001b[0mcontext\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0masync_wait\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m~/.local/lib/python3.7/site-packages/tensorflow/python/util/traceback_utils.py\u001b[0m in \u001b[0;36merror_handler\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m 148\u001b[0m \u001b[0mfiltered_tb\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 149\u001b[0m \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 150\u001b[0;31m \u001b[0;32mreturn\u001b[0m \u001b[0mfn\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 151\u001b[0m \u001b[0;32mexcept\u001b[0m \u001b[0mException\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0me\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 152\u001b[0m \u001b[0mfiltered_tb\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0m_process_traceback_frames\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0me\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m__traceback__\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m~/.local/lib/python3.7/site-packages/tensorflow/python/eager/def_function.py\u001b[0m in \u001b[0;36m__call__\u001b[0;34m(self, *args, **kwds)\u001b[0m\n\u001b[1;32m 913\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 914\u001b[0m \u001b[0;32mwith\u001b[0m \u001b[0mOptionalXlaContext\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_jit_compile\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 915\u001b[0;31m \u001b[0mresult\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_call\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwds\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 916\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 917\u001b[0m \u001b[0mnew_tracing_count\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mexperimental_get_tracing_count\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m~/.local/lib/python3.7/site-packages/tensorflow/python/eager/def_function.py\u001b[0m in \u001b[0;36m_call\u001b[0;34m(self, *args, **kwds)\u001b[0m\n\u001b[1;32m 945\u001b[0m \u001b[0;31m# In this case we have created variables on the first call, so we run the\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 946\u001b[0m \u001b[0;31m# defunned version which is guaranteed to never create variables.\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 947\u001b[0;31m \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_stateless_fn\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwds\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;31m# pylint: disable=not-callable\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 948\u001b[0m \u001b[0;32melif\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_stateful_fn\u001b[0m \u001b[0;32mis\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 949\u001b[0m \u001b[0;31m# Release the lock early so that multiple threads can perform the call\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m~/.local/lib/python3.7/site-packages/tensorflow/python/eager/function.py\u001b[0m in \u001b[0;36m__call__\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m 2955\u001b[0m filtered_flat_args) = self._maybe_define_function(args, kwargs)\n\u001b[1;32m 2956\u001b[0m return graph_function._call_flat(\n\u001b[0;32m-> 2957\u001b[0;31m filtered_flat_args, captured_inputs=graph_function.captured_inputs) # pylint: disable=protected-access\n\u001b[0m\u001b[1;32m 2958\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 2959\u001b[0m \u001b[0;34m@\u001b[0m\u001b[0mproperty\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m~/.local/lib/python3.7/site-packages/tensorflow/python/eager/function.py\u001b[0m in \u001b[0;36m_call_flat\u001b[0;34m(self, args, captured_inputs, cancellation_manager)\u001b[0m\n\u001b[1;32m 1852\u001b[0m \u001b[0;31m# No tape is watching; skip to running the function.\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1853\u001b[0m return self._build_call_outputs(self._inference_function.call(\n\u001b[0;32m-> 1854\u001b[0;31m ctx, args, cancellation_manager=cancellation_manager))\n\u001b[0m\u001b[1;32m 1855\u001b[0m forward_backward = self._select_forward_and_backward_functions(\n\u001b[1;32m 1856\u001b[0m \u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m~/.local/lib/python3.7/site-packages/tensorflow/python/eager/function.py\u001b[0m in \u001b[0;36mcall\u001b[0;34m(self, ctx, args, cancellation_manager)\u001b[0m\n\u001b[1;32m 502\u001b[0m \u001b[0minputs\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 503\u001b[0m \u001b[0mattrs\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mattrs\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 504\u001b[0;31m ctx=ctx)\n\u001b[0m\u001b[1;32m 505\u001b[0m \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 506\u001b[0m outputs = execute.execute_with_cancellation(\n",
"\u001b[0;32m~/.local/lib/python3.7/site-packages/tensorflow/python/eager/execute.py\u001b[0m in \u001b[0;36mquick_execute\u001b[0;34m(op_name, num_outputs, inputs, attrs, ctx, name)\u001b[0m\n\u001b[1;32m 53\u001b[0m \u001b[0mctx\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mensure_initialized\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 54\u001b[0m tensors = pywrap_tfe.TFE_Py_Execute(ctx._handle, device_name, op_name,\n\u001b[0;32m---> 55\u001b[0;31m inputs, attrs, num_outputs)\n\u001b[0m\u001b[1;32m 56\u001b[0m \u001b[0;32mexcept\u001b[0m \u001b[0mcore\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_NotOkStatusException\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0me\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 57\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mname\u001b[0m \u001b[0;32mis\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;31mKeyboardInterrupt\u001b[0m: "
]
}
],
"source": [
"from transformers.keras_callbacks import PushToHubCallback\n",
"from tensorflow.keras.callbacks import TensorBoard\n",
"\n",
"model_name = model_checkpoint.split(\"/\")[-1]\n",
"push_to_hub_model_id = f\"{model_name}-finetuned-wikitext2\"\n",
"\n",
"tensorboard_callback = TensorBoard(log_dir=\"./clm_model_save/logs\")\n",
"\n",
"push_to_hub_callback = PushToHubCallback(\n",
" output_dir=\"./clm_model_save\",\n",
" tokenizer=tokenizer,\n",
" hub_model_id=push_to_hub_model_id,\n",
")\n",
"\n",
"callbacks = [tensorboard_callback, push_to_hub_callback]\n",
"\n",
"model.fit(train_set, validation_data=validation_set, epochs=1, callbacks=callbacks)"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "3APq-vUc3l_R"
},
"source": [
"Once the training is completed, we can evaluate our model and get its cross-entropy loss on the validation set like this:"
]
},
{
"cell_type": "code",
"execution_count": 22,
"metadata": {
"id": "diKZnB1I3l_R",
"outputId": "9b3ac725-0117-4830-f380-a555ee57c8cf"
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"121/121 [==============================] - 4s 33ms/step - loss: 3.6752\n"
]
}
],
"source": [
"eval_loss = model.evaluate(validation_set)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"The quality of language models is often measured in 'perplexity' rather than cross-entropy. To convert to perplexity, we simply raise e to the power of the cross-entropy loss."
]
},
{
"cell_type": "code",
"execution_count": 23,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Perplexity: 39.46\n"
]
}
],
"source": [
"import math\n",
"\n",
"print(f\"Perplexity: {math.exp(eval_loss):.2f}\")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"If you saved the model with the callback, you can now share this model with all your friends, family, favorite pets: they can all load it with the identifier `\"your-username/the-name-you-picked\"` so for instance:\n",
"\n",
"```python\n",
"from transformers import AutoModelForCausalLM\n",
"\n",
"model = AutoModelForCausalLM.from_pretrained(\"sgugger/my-awesome-model\")\n",
"```"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "q-EIELH43l_T"
},
"source": [
"## Masked language modeling"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "LWk97-Ny3l_T"
},
"source": [
"For masked language modeling (MLM) we are going to use the same preprocessing as before for our dataset with one additional step: we will randomly mask some tokens (by replacing them by `[MASK]`) and the labels will be adjusted to only include the masked tokens (we don't have to predict the non-masked tokens).\n",
"\n",
"We will use the [`distilroberta-base`](https://huggingface.co/distilroberta-base) model for this example. You can pick any of the checkpoints listed [here](https://huggingface.co/models?filter=masked-lm) instead:"
]
},
{
"cell_type": "code",
"execution_count": 24,
"metadata": {
"id": "QRTpmyCc3l_T"
},
"outputs": [],
"source": [
"model_checkpoint = \"distilroberta-base\""
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "12F1ulgT3l_V"
},
"source": [
"We can apply the same tokenization function as before, we just need to update our tokenizer to use the checkpoint we just picked. Don't panic about the warnings about inputs being too long for the model - remember that we'll be breaking them into shorter chunks right afterwards!"
]
},
{
"cell_type": "code",
"execution_count": 25,
"metadata": {
"id": "h8RCYcvr3l_V",
"outputId": "a5ffeb0a-71da-4b27-e57a-c62f1927562e"
},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"Token indices sequence length is longer than the specified maximum sequence length for this model (544 > 512). Running this sequence through the model will result in indexing errors\n",
"Token indices sequence length is longer than the specified maximum sequence length for this model (560 > 512). Running this sequence through the model will result in indexing errors\n",
"Token indices sequence length is longer than the specified maximum sequence length for this model (528 > 512). Running this sequence through the model will result in indexing errors\n",
"Token indices sequence length is longer than the specified maximum sequence length for this model (638 > 512). Running this sequence through the model will result in indexing errors\n",
"Token indices sequence length is longer than the specified maximum sequence length for this model (522 > 512). Running this sequence through the model will result in indexing errors\n"
]
}
],
"source": [
"tokenizer = AutoTokenizer.from_pretrained(model_checkpoint)\n",
"tokenized_datasets = datasets.map(\n",
" tokenize_function, batched=True, num_proc=4, remove_columns=[\"text\"]\n",
")"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "MTuy8UUs3l_X"
},
"source": [
"And now, we group texts together and chunk them into samples of length `block_size`. You can skip this step if your dataset is composed of individual sentences."
]
},
{
"cell_type": "code",
"execution_count": 26,
"metadata": {
"id": "LVYPMwEs3l_X",
"outputId": "e71ed7f1-b182-4643-a8fb-3d731c70e40b"
},
"outputs": [],
"source": [
"lm_datasets = tokenized_datasets.map(\n",
" group_texts,\n",
" batched=True,\n",
" batch_size=1000,\n",
" num_proc=4,\n",
")"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "nFJ49iHJ3l_Z"
},
"source": [
"The rest is very similar to what we had, with two exceptions. First we use a model suitable for masked LM:"
]
},
{
"cell_type": "code",
"execution_count": 27,
"metadata": {
"id": "PM10A9Za3l_Z",
"outputId": "fff2d5bb-397d-4d5d-9aa9-933090cb6680"
},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"All model checkpoint layers were used when initializing TFRobertaForMaskedLM.\n",
"\n",
"All the layers of TFRobertaForMaskedLM were initialized from the model checkpoint at distilroberta-base.\n",
"If your task is similar to the task the model of the checkpoint was trained on, you can already use TFRobertaForMaskedLM for predictions without further training.\n"
]
}
],
"source": [
"from transformers import TFAutoModelForMaskedLM\n",
"\n",
"model = TFAutoModelForMaskedLM.from_pretrained(model_checkpoint)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"We redefine our `optimizer` as we did with the CLM model, and we compile the model. We're using the internal loss again, like we did before."
]
},
{
"cell_type": "code",
"execution_count": 28,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"/home/matt/miniconda3/envs/tensorflow28/lib/python3.10/site-packages/keras/optimizer_v2/adam.py:105: UserWarning: The `lr` argument is deprecated, use `learning_rate` instead.\n",
" super(Adam, self).__init__(name, **kwargs)\n",
"No loss specified in compile() - the model's internal loss computation will be used as the loss. Don't panic - this is a common way to train TensorFlow models in Transformers! Please ensure your labels are passed as keys in the input dict so that they are accessible to the model during the forward pass. To disable this behaviour, please pass a loss argument, or explicitly pass loss=None if you do not want your model to compute a loss.\n"
]
}
],
"source": [
"from transformers import create_optimizer, AdamWeightDecay\n",
"import tensorflow as tf\n",
"\n",
"optimizer = AdamWeightDecay(lr=2e-5, weight_decay_rate=0.01)\n",
"\n",
"model.compile(optimizer=optimizer)"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "z6uuUnvz3l_b"
},
"source": [
"Finally, we use a special `data_collator`. The `data_collator` is a function that is responsible for taking the samples and batching them in tensors. In the previous example, we had nothing special to do, so we just used the default for this argument. Here we want to randomly mask tokens. We could do it as a pre-processing step (like the tokenization) but then the tokens would always be masked the same way at each epoch. By doing this step inside the `data_collator`, we ensure this random masking is done in a new way each time we go over the data.\n",
"\n",
"To do this masking for us, the library provides a `DataCollatorForLanguageModeling`. We can adjust the probability of the masking. Note that our data collators are designed to work for multiple frameworks, so ensure you set the `return_tensors='tf'` argument to get Tensorflow tensors out - you don't want to accidentally get a load of `torch.Tensor` objects in the middle of your nice TF code!"
]
},
{
"cell_type": "code",
"execution_count": 29,
"metadata": {
"id": "nRZ-5v_P3l_b"
},
"outputs": [],
"source": [
"from transformers import DataCollatorForLanguageModeling\n",
"\n",
"data_collator = DataCollatorForLanguageModeling(\n",
" tokenizer=tokenizer, mlm_probability=0.15, return_tensors=\"tf\"\n",
")"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "bqHnWcYC3l_d"
},
"source": [
"Now we generate our datasets as before. Remember to pass the `data_collator` you just made to the `collate_fn` argument."
]
},
{
"cell_type": "code",
"execution_count": 30,
"metadata": {},
"outputs": [],
"source": [
"train_set = lm_datasets[\"train\"].to_tf_dataset(\n",
" columns=[\"attention_mask\", \"input_ids\", \"labels\"],\n",
" shuffle=True,\n",
" batch_size=16,\n",
" collate_fn=data_collator,\n",
")\n",
"\n",
"validation_set = lm_datasets[\"validation\"].to_tf_dataset(\n",
" columns=[\"attention_mask\", \"input_ids\", \"labels\"],\n",
" shuffle=False,\n",
" batch_size=16,\n",
" collate_fn=data_collator,\n",
")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"And now we fit our model! As before, we can use a callback to sync with the hub during training. You can remove this if you don't want to!"
]
},
{
"cell_type": "code",
"execution_count": 32,
"metadata": {
"id": "V-Y3gNqV3l_d"
},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"/home/matt/PycharmProjects/notebooks/examples/mlm_model_save is already a clone of https://huggingface.co/Rocketknight1/distilroberta-base-finetuned-wikitext2. Make sure you pull the latest changes with `repo.git_pull()`.\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"1202/1202 [==============================] - ETA: 0s - loss: 1.9043"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"Several commits (2) will be pushed upstream.\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"1202/1202 [==============================] - 138s 110ms/step - loss: 1.9043 - val_loss: 1.7174\n"
]
},
{
"data": {
"text/plain": [
"<keras.callbacks.History at 0x7f96e3be36a0>"
]
},
"execution_count": 32,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"from transformers.keras_callbacks import PushToHubCallback\n",
"\n",
"model_name = model_checkpoint.split(\"/\")[-1]\n",
"push_to_hub_model_id = f\"{model_name}-finetuned-wikitext2\"\n",
"\n",
"callback = PushToHubCallback(\n",
" output_dir=\"./mlm_model_save\",\n",
" tokenizer=tokenizer,\n",
" hub_model_id=push_to_hub_model_id,\n",
")\n",
"\n",
"model.fit(train_set, validation_data=validation_set, epochs=1, callbacks=[callback])"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "KDBi0reX3l_g"
},
"source": [
"Like before, we can evaluate our model on the validation set and compute perplexity. The perplexity is much lower than for the CLM objective because for the MLM objective, we only have to make predictions for the masked tokens (which represent 15% of the total here) while having access to the rest of the tokens. It's thus an easier task for the model."
]
},
{
"cell_type": "code",
"execution_count": 33,
"metadata": {
"id": "4hSaANqj3l_g",
"outputId": "eeeb8727-2e27-4aeb-ac71-c98123214661"
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"125/125 [==============================] - 4s 32ms/step - loss: 1.7101\n",
"Perplexity: 5.53\n"
]
}
],
"source": [
"import math\n",
"\n",
"eval_results = model.evaluate(validation_set)\n",
"print(f\"Perplexity: {math.exp(eval_results):.2f}\")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"If you used the callback, you can now share this model with all your friends, family or favorite pets: they can all load it with the identifier `\"your-username/the-name-you-picked\"` so for instance:\n",
"\n",
"```python\n",
"from transformers import AutoModelForMaskedLM\n",
"\n",
"model = AutoModelForMaskedLM.from_pretrained(\"your-username/my-awesome-model\")\n",
"```"
]
}
],
"metadata": {
"colab": {
"name": "Fine-tune a language model",
"provenance": []
},
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.7.13"
}
},
"nbformat": 4,
"nbformat_minor": 4
}
|