Spaces:
Build error
Build error
File size: 60,083 Bytes
b83b354 |
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 |
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {
"executionInfo": {
"elapsed": 476,
"status": "ok",
"timestamp": 1720679526275,
"user": {
"displayName": "HUANG DONGHAO _",
"userId": "00977795705617022768"
},
"user_tz": -480
},
"id": "uWKRSV6eZsCn"
},
"outputs": [],
"source": [
"%load_ext autoreload\n",
"%autoreload 2"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {
"application/vnd.databricks.v1+cell": {
"cellMetadata": {
"byteLimit": 2048000,
"rowLimit": 10000
},
"inputWidgets": {},
"nuid": "6d394937-6c99-4a7c-9d32-7600a280032f",
"showTitle": false,
"title": ""
},
"colab": {
"base_uri": "https://localhost:8080/"
},
"executionInfo": {
"elapsed": 5,
"status": "ok",
"timestamp": 1720679529345,
"user": {
"displayName": "HUANG DONGHAO _",
"userId": "00977795705617022768"
},
"user_tz": -480
},
"id": "G5pNu3zgZBrL",
"outputId": "160a554f-fb08-4aa0-bc00-0422fb7c1fac"
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"workding dir: d:\\code\\projects\\rapget-translation\n"
]
}
],
"source": [
"import os\n",
"import sys\n",
"from pathlib import Path\n",
"\n",
"# check if workding_dir is in local variables\n",
"if \"workding_dir\" not in locals():\n",
" workding_dir = str(Path.cwd().parent)\n",
"\n",
"os.chdir(workding_dir)\n",
"sys.path.append(workding_dir)\n",
"print(\"workding dir:\", workding_dir)"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {
"application/vnd.databricks.v1+cell": {
"cellMetadata": {
"byteLimit": 2048000,
"rowLimit": 10000
},
"inputWidgets": {},
"nuid": "9f67ec60-2f24-411c-84eb-0dd664b44775",
"showTitle": false,
"title": ""
},
"colab": {
"base_uri": "https://localhost:8080/"
},
"executionInfo": {
"elapsed": 3,
"status": "ok",
"timestamp": 1720679529345,
"user": {
"displayName": "HUANG DONGHAO _",
"userId": "00977795705617022768"
},
"user_tz": -480
},
"id": "hPCC-6m7ZBrM",
"outputId": "c7aa2c96-5e99-440a-c148-201d79465ff9"
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"loading env vars from: d:\\code\\projects\\rapget-translation\\.env\n"
]
},
{
"data": {
"text/plain": [
"True"
]
},
"execution_count": 3,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"from dotenv import find_dotenv, load_dotenv\n",
"\n",
"found_dotenv = find_dotenv(\".env\")\n",
"\n",
"if len(found_dotenv) == 0:\n",
" found_dotenv = find_dotenv(\".env.example\")\n",
"print(f\"loading env vars from: {found_dotenv}\")\n",
"load_dotenv(found_dotenv, override=True)"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {
"application/vnd.databricks.v1+cell": {
"cellMetadata": {
"byteLimit": 2048000,
"rowLimit": 10000
},
"inputWidgets": {},
"nuid": "f1597656-8042-4878-9d3b-9ebfb8dd86dc",
"showTitle": false,
"title": ""
},
"colab": {
"base_uri": "https://localhost:8080/"
},
"executionInfo": {
"elapsed": 3,
"status": "ok",
"timestamp": 1720679529345,
"user": {
"displayName": "HUANG DONGHAO _",
"userId": "00977795705617022768"
},
"user_tz": -480
},
"id": "1M3IraVtZBrM",
"outputId": "29ab35f6-2970-4ade-d85d-3174acf8cda0"
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"01-ai/Yi-1.5-9B-Chat None True datasets/mac/mac.tsv results/mac-results_few_shots_4bit.csv False 300\n"
]
}
],
"source": [
"import os\n",
"\n",
"model_name = os.getenv(\"MODEL_NAME\")\n",
"adapter_name_or_path = os.getenv(\"ADAPTER_NAME_OR_PATH\")\n",
"load_in_4bit = os.getenv(\"LOAD_IN_4BIT\") == \"true\"\n",
"data_path = os.getenv(\"DATA_PATH\")\n",
"results_path = os.getenv(\"RESULTS_PATH\")\n",
"use_english_datasets = os.getenv(\"USE_ENGLISH_DATASETS\") == \"true\"\n",
"max_new_tokens = int(os.getenv(\"MAX_NEW_TOKENS\", 2048))\n",
"\n",
"print(\n",
" model_name,\n",
" adapter_name_or_path,\n",
" load_in_4bit,\n",
" data_path,\n",
" results_path,\n",
" use_english_datasets,\n",
" max_new_tokens,\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {
"application/vnd.databricks.v1+cell": {
"cellMetadata": {
"byteLimit": 2048000,
"rowLimit": 10000
},
"inputWidgets": {},
"nuid": "b2a43943-9324-4839-9a47-cfa72de2244b",
"showTitle": false,
"title": ""
},
"colab": {
"base_uri": "https://localhost:8080/"
},
"executionInfo": {
"elapsed": 564,
"status": "ok",
"timestamp": 1720679529907,
"user": {
"displayName": "HUANG DONGHAO _",
"userId": "00977795705617022768"
},
"user_tz": -480
},
"id": "UgMvt6dIZBrM",
"outputId": "ce37581c-fd26-46c2-ad87-d933d99f68f7"
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Python 3.11.9\n",
"Name: torch\n",
"Version: 2.4.0+cu124\n",
"Summary: Tensors and Dynamic neural networks in Python with strong GPU acceleration\n",
"Home-page: https://pytorch.org/\n",
"Author: PyTorch Team\n",
"Author-email: packages@pytorch.org\n",
"License: BSD-3\n",
"Location: C:\\Users\\dongh\\.conda\\envs\\rapget\\Lib\\site-packages\n",
"Requires: filelock, fsspec, jinja2, networkx, sympy, typing-extensions\n",
"Required-by: accelerate, bitsandbytes, peft, torchaudio, torchvision\n",
"---\n",
"Name: transformers\n",
"Version: 4.43.3\n",
"Summary: State-of-the-art Machine Learning for JAX, PyTorch and TensorFlow\n",
"Home-page: https://github.com/huggingface/transformers\n",
"Author: The Hugging Face team (past and future) with the help of all our contributors (https://github.com/huggingface/transformers/graphs/contributors)\n",
"Author-email: transformers@huggingface.co\n",
"License: Apache 2.0 License\n",
"Location: C:\\Users\\dongh\\.conda\\envs\\rapget\\Lib\\site-packages\n",
"Requires: filelock, huggingface-hub, numpy, packaging, pyyaml, regex, requests, safetensors, tokenizers, tqdm\n",
"Required-by: peft\n",
"CPU times: total: 0 ns\n",
"Wall time: 6.94 s\n"
]
}
],
"source": [
"%%time\n",
"os.environ[\"TOKENIZERS_PARALLELISM\"] = \"true\"\n",
"\n",
"!python --version\n",
"!pip show torch transformers"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"executionInfo": {
"elapsed": 1685,
"status": "ok",
"timestamp": 1720679531591,
"user": {
"displayName": "HUANG DONGHAO _",
"userId": "00977795705617022768"
},
"user_tz": -480
},
"id": "ZuS_FsLyZBrN",
"outputId": "2cba0105-c505-4395-afbd-2f2fee6581d0"
},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"c:\\Users\\dongh\\.conda\\envs\\rapget\\Lib\\site-packages\\threadpoolctl.py:1214: RuntimeWarning: \n",
"Found Intel OpenMP ('libiomp') and LLVM OpenMP ('libomp') loaded at\n",
"the same time. Both libraries are known to be incompatible and this\n",
"can cause random crashes or deadlocks on Linux when loaded in the\n",
"same Python program.\n",
"Using threadpoolctl may cause crashes or deadlocks. For more\n",
"information and possible workarounds, please see\n",
" https://github.com/joblib/threadpoolctl/blob/master/multiple_openmp.md\n",
"\n",
" warnings.warn(msg, RuntimeWarning)\n",
"[nltk_data] Downloading package wordnet to\n",
"[nltk_data] C:\\Users\\dongh\\AppData\\Roaming\\nltk_data...\n",
"[nltk_data] Package wordnet is already up-to-date!\n",
"[nltk_data] Downloading package punkt to\n",
"[nltk_data] C:\\Users\\dongh\\AppData\\Roaming\\nltk_data...\n",
"[nltk_data] Package punkt is already up-to-date!\n",
"[nltk_data] Downloading package omw-1.4 to\n",
"[nltk_data] C:\\Users\\dongh\\AppData\\Roaming\\nltk_data...\n",
"[nltk_data] Package omw-1.4 is already up-to-date!\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"loading: d:\\code\\projects\\rapget-translation\\eval_modules\\calc_repetitions.py\n",
"loading d:\\code\\projects\\rapget-translation\\llm_toolkit\\translation_utils.py\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"[nltk_data] Downloading package wordnet to\n",
"[nltk_data] C:\\Users\\dongh\\AppData\\Roaming\\nltk_data...\n",
"[nltk_data] Package wordnet is already up-to-date!\n",
"[nltk_data] Downloading package punkt to\n",
"[nltk_data] C:\\Users\\dongh\\AppData\\Roaming\\nltk_data...\n",
"[nltk_data] Package punkt is already up-to-date!\n",
"[nltk_data] Downloading package omw-1.4 to\n",
"[nltk_data] C:\\Users\\dongh\\AppData\\Roaming\\nltk_data...\n",
"[nltk_data] Package omw-1.4 is already up-to-date!\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"CUDA is available, we have found 1 GPU(s)\n",
"NVIDIA GeForce RTX 4080 Laptop GPU\n",
"CUDA version: 12.4\n"
]
}
],
"source": [
"from llm_toolkit.llm_utils import *\n",
"from llm_toolkit.translation_utils import *\n",
"\n",
"device = check_gpu()"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"loading model: 01-ai/Yi-1.5-9B-Chat with adapter: None\n"
]
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "16faabb1083d4662b639c035b54844de",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"tokenizer_config.json: 0%| | 0.00/1.67k [00:00<?, ?B/s]"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"c:\\Users\\dongh\\.conda\\envs\\rapget\\Lib\\site-packages\\huggingface_hub\\file_download.py:159: UserWarning: `huggingface_hub` cache-system uses symlinks by default to efficiently store duplicated files but your machine does not support them in C:\\Users\\dongh\\.cache\\huggingface\\hub\\models--01-ai--Yi-1.5-9B-Chat. Caching files will still work but in a degraded version that might require more space on your disk. This warning can be disabled by setting the `HF_HUB_DISABLE_SYMLINKS_WARNING` environment variable. For more details, see https://huggingface.co/docs/huggingface_hub/how-to-cache#limitations.\n",
"To support symlinks on Windows, you either need to activate Developer Mode or to run Python as an administrator. In order to see activate developer mode, see this article: https://docs.microsoft.com/en-us/windows/apps/get-started/enable-your-device-for-development\n",
" warnings.warn(message)\n"
]
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "3316d03bf00d49c59537caf4fa45d683",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"tokenizer.model: 0%| | 0.00/1.03M [00:00<?, ?B/s]"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "8ad82b2bf7224459a56668b0b34660f6",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"tokenizer.json: 0%| | 0.00/3.60M [00:00<?, ?B/s]"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "654d3c4a90fe4011bee581af81770e36",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"special_tokens_map.json: 0%| | 0.00/567 [00:00<?, ?B/s]"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "bdb46ebad4fe48e3b17e44b372f4c33b",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"config.json: 0%| | 0.00/661 [00:00<?, ?B/s]"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "f5bf514086a34a99a3e83d8e3f6bf99e",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"model.safetensors.index.json: 0%| | 0.00/35.8k [00:00<?, ?B/s]"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "2c63583627a14301949f4696a0777dbd",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"Downloading shards: 0%| | 0/4 [00:00<?, ?it/s]"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "8c56c07a67ac477194351791eddc8069",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"model-00001-of-00004.safetensors: 0%| | 0.00/4.93G [00:00<?, ?B/s]"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "cccfaf200fe340628649245e87205e5a",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"model-00002-of-00004.safetensors: 0%| | 0.00/4.98G [00:00<?, ?B/s]"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "780839610e2245a99a2044f7108dce4a",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"model-00003-of-00004.safetensors: 0%| | 0.00/4.97G [00:00<?, ?B/s]"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "12df1cda8a4c445cb7c96ccbe8c34921",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"model-00004-of-00004.safetensors: 0%| | 0.00/2.78G [00:00<?, ?B/s]"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "a37aa5117f044c49806ae9cac830d440",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"Loading checkpoint shards: 0%| | 0/4 [00:00<?, ?it/s]"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "61ea7704789942ce9ef72ec3f6f1d9be",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"generation_config.json: 0%| | 0.00/132 [00:00<?, ?B/s]"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"Some parameters are on the meta device device because they were offloaded to the cpu.\n"
]
}
],
"source": [
"model, tokenizer = load_model(model_name)"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"loading d:\\code\\projects\\rapget-translation\\llm_toolkit\\translation_utils.py\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"[nltk_data] Downloading package wordnet to\n",
"[nltk_data] C:\\Users\\dongh\\AppData\\Roaming\\nltk_data...\n",
"[nltk_data] Package wordnet is already up-to-date!\n",
"[nltk_data] Downloading package punkt to\n",
"[nltk_data] C:\\Users\\dongh\\AppData\\Roaming\\nltk_data...\n",
"[nltk_data] Package punkt is already up-to-date!\n",
"[nltk_data] Downloading package omw-1.4 to\n",
"[nltk_data] C:\\Users\\dongh\\AppData\\Roaming\\nltk_data...\n",
"[nltk_data] Package omw-1.4 is already up-to-date!\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"loading train/test data files\n"
]
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "f37f3ccde5c541f5a5c9eeb2df64613c",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"Map: 0%| | 0/4528 [00:00<?, ? examples/s]"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "d0cd7340999e45179a7ead59e426b7f7",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"Map: 0%| | 0/1133 [00:00<?, ? examples/s]"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"DatasetDict({\n",
" train: Dataset({\n",
" features: ['chinese', 'english', 'text', 'prompt'],\n",
" num_rows: 4528\n",
" })\n",
" test: Dataset({\n",
" features: ['chinese', 'english', 'text', 'prompt'],\n",
" num_rows: 1133\n",
" })\n",
"})\n"
]
}
],
"source": [
"dataset = load_translation_dataset(data_path, tokenizer=tokenizer, num_shots=5)"
]
},
{
"cell_type": "code",
"execution_count": 11,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"('那刘姥姥先听见告艰苦，只当是没想头了， 又听见给他二十两银子，喜的眉开眼笑道：“我们也知道艰难的，但只俗语说的：‘瘦死的骆驼比马还大’呢。',\n",
" '后来她不挣扎了，对我说，混蛋，你要把我怎么办。')"
]
},
"execution_count": 11,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"dataset[\"test\"][\"chinese\"][260], dataset[\"test\"][\"chinese\"][908]"
]
},
{
"cell_type": "code",
"execution_count": 12,
"metadata": {},
"outputs": [],
"source": [
"eval_dataset = dataset[\"test\"].select([260, 908])"
]
},
{
"cell_type": "code",
"execution_count": 13,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"--------------------------------------------------\n",
"chinese: 那刘姥姥先听见告艰苦，只当是没想头了， 又听见给他二十两银子，喜的眉开眼笑道：“我们也知道艰难的，但只俗语说的：‘瘦死的骆驼比马还大’呢。\n",
"--------------------------------------------------\n",
"english: When Grannie Liu heard Xi-feng talk about 'difficulties' she concluded that there was no hope. Her delight and the way in which her face lit up with pleasure when she heard that she was, after all, to be given twenty taels of silver can be imagined. 'We knew you had your troubles,' she said, 'but as the saying goes, 'A starved camel is bigger than a fat horse.'\n",
"--------------------------------------------------\n",
"text: You are a helpful assistant that translates Chinese to English.<|im_start|>user\n",
"You will be given a Chinese sentence to translate. If it is an incomplete sentence, or if you are unsure about the meaning, simply copy the input text as your output. Do not output any additional sentence such as explanation or reasoning.\n",
"\n",
"Example Translations:\n",
"Chinese: 全仗着狐仙搭救。\n",
"English: Because I was protected by a fox fairy.\n",
"Chinese: 过后，表哥告诉她俩，这人是导演，在外国留过学的，还会编剧，今天拍的这戏，就是他自编自导的。\n",
"English: He was the director, the cousin later told them. He had studied abroad and was also a screenwriter; in fact he had written and directed the scene they had earlier seen being filmed.\n",
"Chinese: 这凤姐忽然想起一件事来，便向窗外叫：“蓉儿回来！”\n",
"English: Xi-feng suddenly seemed to remember something, and called to him through the window, 'Rong, come back!'\n",
"Chinese: 三个老红卫兵走到叶文洁面前，面对着她站成了一排——当年，她们也是这样面对叶哲泰的——试图再现那早已忘却的尊严，但她们当年那魔鬼般的精神力量显然已荡然无存。\n",
"English: The three old Red Guards stood in front of Ye in a row—just like they had stood against Ye Zhetai—trying to recapture their long-forgotten dignity. But the demonic spiritual energy that had once propelled them was gone.\n",
"Chinese: 程先生照单全收，都是一个“谢”字，然后问王琦瑶有什么话说。\n",
"English: Mr. Cheng accepted their toast with equanimity and a 'thank you.' Then, turning to Wang Qiyao, he asked if she had anything to say.\n",
"\n",
"Chinese: 那刘姥姥先听见告艰苦，只当是没想头了， 又听见给他二十两银子，喜的眉开眼笑道：“我们也知道艰难的，但只俗语说的：‘瘦死的骆驼比马还大’呢。\n",
"English:<|im_end|>\n",
"<|im_start|>assistant\n",
"When Grannie Liu heard Xi-feng talk about 'difficulties' she concluded that there was no hope. Her delight and the way in which her face lit up with pleasure when she heard that she was, after all, to be given twenty taels of silver can be imagined. 'We knew you had your troubles,' she said, 'but as the saying goes, 'A starved camel is bigger than a fat horse.'<|im_end|>\n",
"--------------------------------------------------\n",
"prompt: You are a helpful assistant that translates Chinese to English.<|im_start|>user\n",
"You will be given a Chinese sentence to translate. If it is an incomplete sentence, or if you are unsure about the meaning, simply copy the input text as your output. Do not output any additional sentence such as explanation or reasoning.\n",
"\n",
"Example Translations:\n",
"Chinese: 全仗着狐仙搭救。\n",
"English: Because I was protected by a fox fairy.\n",
"Chinese: 过后，表哥告诉她俩，这人是导演，在外国留过学的，还会编剧，今天拍的这戏，就是他自编自导的。\n",
"English: He was the director, the cousin later told them. He had studied abroad and was also a screenwriter; in fact he had written and directed the scene they had earlier seen being filmed.\n",
"Chinese: 这凤姐忽然想起一件事来，便向窗外叫：“蓉儿回来！”\n",
"English: Xi-feng suddenly seemed to remember something, and called to him through the window, 'Rong, come back!'\n",
"Chinese: 三个老红卫兵走到叶文洁面前，面对着她站成了一排——当年，她们也是这样面对叶哲泰的——试图再现那早已忘却的尊严，但她们当年那魔鬼般的精神力量显然已荡然无存。\n",
"English: The three old Red Guards stood in front of Ye in a row—just like they had stood against Ye Zhetai—trying to recapture their long-forgotten dignity. But the demonic spiritual energy that had once propelled them was gone.\n",
"Chinese: 程先生照单全收，都是一个“谢”字，然后问王琦瑶有什么话说。\n",
"English: Mr. Cheng accepted their toast with equanimity and a 'thank you.' Then, turning to Wang Qiyao, he asked if she had anything to say.\n",
"\n",
"Chinese: 那刘姥姥先听见告艰苦，只当是没想头了， 又听见给他二十两银子，喜的眉开眼笑道：“我们也知道艰难的，但只俗语说的：‘瘦死的骆驼比马还大’呢。\n",
"English:<|im_end|>\n",
"<|im_start|>assistant\n",
"\n",
"--------------------------------------------------\n",
"chinese: 后来她不挣扎了，对我说，混蛋，你要把我怎么办。\n",
"--------------------------------------------------\n",
"english: After a while, she no longer struggled and said, You bastard! What are you going to do with me?\n",
"--------------------------------------------------\n",
"text: You are a helpful assistant that translates Chinese to English.<|im_start|>user\n",
"You will be given a Chinese sentence to translate. If it is an incomplete sentence, or if you are unsure about the meaning, simply copy the input text as your output. Do not output any additional sentence such as explanation or reasoning.\n",
"\n",
"Example Translations:\n",
"Chinese: 全仗着狐仙搭救。\n",
"English: Because I was protected by a fox fairy.\n",
"Chinese: 过后，表哥告诉她俩，这人是导演，在外国留过学的，还会编剧，今天拍的这戏，就是他自编自导的。\n",
"English: He was the director, the cousin later told them. He had studied abroad and was also a screenwriter; in fact he had written and directed the scene they had earlier seen being filmed.\n",
"Chinese: 这凤姐忽然想起一件事来，便向窗外叫：“蓉儿回来！”\n",
"English: Xi-feng suddenly seemed to remember something, and called to him through the window, 'Rong, come back!'\n",
"Chinese: 三个老红卫兵走到叶文洁面前，面对着她站成了一排——当年，她们也是这样面对叶哲泰的——试图再现那早已忘却的尊严，但她们当年那魔鬼般的精神力量显然已荡然无存。\n",
"English: The three old Red Guards stood in front of Ye in a row—just like they had stood against Ye Zhetai—trying to recapture their long-forgotten dignity. But the demonic spiritual energy that had once propelled them was gone.\n",
"Chinese: 程先生照单全收，都是一个“谢”字，然后问王琦瑶有什么话说。\n",
"English: Mr. Cheng accepted their toast with equanimity and a 'thank you.' Then, turning to Wang Qiyao, he asked if she had anything to say.\n",
"\n",
"Chinese: 后来她不挣扎了，对我说，混蛋，你要把我怎么办。\n",
"English:<|im_end|>\n",
"<|im_start|>assistant\n",
"After a while, she no longer struggled and said, You bastard! What are you going to do with me?<|im_end|>\n",
"--------------------------------------------------\n",
"prompt: You are a helpful assistant that translates Chinese to English.<|im_start|>user\n",
"You will be given a Chinese sentence to translate. If it is an incomplete sentence, or if you are unsure about the meaning, simply copy the input text as your output. Do not output any additional sentence such as explanation or reasoning.\n",
"\n",
"Example Translations:\n",
"Chinese: 全仗着狐仙搭救。\n",
"English: Because I was protected by a fox fairy.\n",
"Chinese: 过后，表哥告诉她俩，这人是导演，在外国留过学的，还会编剧，今天拍的这戏，就是他自编自导的。\n",
"English: He was the director, the cousin later told them. He had studied abroad and was also a screenwriter; in fact he had written and directed the scene they had earlier seen being filmed.\n",
"Chinese: 这凤姐忽然想起一件事来，便向窗外叫：“蓉儿回来！”\n",
"English: Xi-feng suddenly seemed to remember something, and called to him through the window, 'Rong, come back!'\n",
"Chinese: 三个老红卫兵走到叶文洁面前，面对着她站成了一排——当年，她们也是这样面对叶哲泰的——试图再现那早已忘却的尊严，但她们当年那魔鬼般的精神力量显然已荡然无存。\n",
"English: The three old Red Guards stood in front of Ye in a row—just like they had stood against Ye Zhetai—trying to recapture their long-forgotten dignity. But the demonic spiritual energy that had once propelled them was gone.\n",
"Chinese: 程先生照单全收，都是一个“谢”字，然后问王琦瑶有什么话说。\n",
"English: Mr. Cheng accepted their toast with equanimity and a 'thank you.' Then, turning to Wang Qiyao, he asked if she had anything to say.\n",
"\n",
"Chinese: 后来她不挣扎了，对我说，混蛋，你要把我怎么办。\n",
"English:<|im_end|>\n",
"<|im_start|>assistant\n",
"\n"
]
}
],
"source": [
"print_row_details(eval_dataset.to_pandas(), range(len(eval_dataset)))"
]
},
{
"cell_type": "code",
"execution_count": 14,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
" 0%| | 0/2 [00:00<?, ?it/s]c:\\Users\\dongh\\.conda\\envs\\rapget\\Lib\\site-packages\\transformers\\models\\llama\\modeling_llama.py:603: UserWarning: 1Torch was not compiled with flash attention. (Triggered internally at C:\\actions-runner\\_work\\pytorch\\pytorch\\builder\\windows\\pytorch\\aten\\src\\ATen\\native\\transformers\\cuda\\sdp_utils.cpp:555.)\n",
" attn_output = torch.nn.functional.scaled_dot_product_attention(\n",
" 50%|█████ | 1/2 [12:18<12:18, 738.30s/it]"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"Batch output: ['The task is to translate a given Chinese sentence into English. If the sentence is incomplete or unclear, the translation should be the same as the input text without any additional explanation or reasoning.\\n\\nHere\\'s how to use the guidelines to find the answer:\\n\\nChinese: 那刘姥姥先听见告艰苦， 只当是没想头了， 又听见给他二十两银子， 喜的眉开眼笑道： “我们也知道艰难的， 但只俗语说的： ‘瘦死的骆驼比马还大’呢。\\n\\n1. Read the Chinese sentence carefully.\\n2. Identify any incomplete or unclear parts of the sentence.\\n3. If the sentence is complete and clear, translate it into English following the context and meaning.\\n4. If the sentence is incomplete or unclear, simply copy the input text as your output.\\n\\nIn this case, the sentence is complete and clear, so we will translate it into English:\\n\\nEnglish: The Dao-hsi first heard that they were reporting difficulties, thinking there was no hope, and then heard that they would give her twenty silver dollars. She was overjoyed, smiling broadly and saying, \"We know the difficulties, but as the saying goes, \\'A camel that\\'s lost its fat is still bigger than a horse.\\'\"']\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"100%|██████████| 2/2 [24:19<00:00, 729.62s/it]\n"
]
}
],
"source": [
"predictions = eval_model(\n",
" model, tokenizer, eval_dataset, device=device, max_new_tokens=max_new_tokens\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 15,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"loading d:\\code\\projects\\rapget-translation\\llm_toolkit\\translation_utils.py\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"[nltk_data] Downloading package wordnet to\n",
"[nltk_data] C:\\Users\\dongh\\AppData\\Roaming\\nltk_data...\n",
"[nltk_data] Package wordnet is already up-to-date!\n",
"[nltk_data] Downloading package punkt to\n",
"[nltk_data] C:\\Users\\dongh\\AppData\\Roaming\\nltk_data...\n",
"[nltk_data] Package punkt is already up-to-date!\n",
"[nltk_data] Downloading package omw-1.4 to\n",
"[nltk_data] C:\\Users\\dongh\\AppData\\Roaming\\nltk_data...\n",
"[nltk_data] Package omw-1.4 is already up-to-date!\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"['The task is to translate a given Chinese sentence into English. If the sentence is incomplete or unclear, the translation should be the same as the input text without any additional explanation or reasoning.\\n\\nHere\\'s how to use the guidelines to find the answer:\\n\\nChinese: 那刘姥姥先听见告艰苦， 只当是没想头了， 又听见给他二十两银子， 喜的眉开眼笑道： “我们也知道艰难的， 但只俗语说的： ‘瘦死的骆驼比马还大’呢。\\n\\n1. Read the Chinese sentence carefully.\\n2. Identify any incomplete or unclear parts of the sentence.\\n3. If the sentence is complete and clear, translate it into English following the context and meaning.\\n4. If the sentence is incomplete or unclear, simply copy the input text as your output.\\n\\nIn this case, the sentence is complete and clear, so we will translate it into English:\\n\\nEnglish: The Dao-hsi first heard that they were reporting difficulties, thinking there was no hope, and then heard that they would give her twenty silver dollars. She was overjoyed, smiling broadly and saying, \"We know the difficulties, but as the saying goes, \\'A camel that\\'s lost its fat is still bigger than a horse.\\'\"', 'Later, she stopped struggling and asked me, \"Asshole, what are you going to do with me?\"']\n"
]
}
],
"source": [
"print(predictions)"
]
},
{
"cell_type": "code",
"execution_count": 16,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"loading d:\\code\\projects\\rapget-translation\\llm_toolkit\\translation_utils_v1.py\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"[nltk_data] Downloading package wordnet to\n",
"[nltk_data] C:\\Users\\dongh\\AppData\\Roaming\\nltk_data...\n",
"[nltk_data] Package wordnet is already up-to-date!\n",
"[nltk_data] Downloading package punkt to\n",
"[nltk_data] C:\\Users\\dongh\\AppData\\Roaming\\nltk_data...\n",
"[nltk_data] Package punkt is already up-to-date!\n",
"[nltk_data] Downloading package omw-1.4 to\n",
"[nltk_data] C:\\Users\\dongh\\AppData\\Roaming\\nltk_data...\n",
"[nltk_data] Package omw-1.4 is already up-to-date!\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"loading train/test data files\n"
]
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "9b93dc2e072345bab26e7dc4b1170e13",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"Map: 0%| | 0/4528 [00:00<?, ? examples/s]"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "a9adb136bd474eba99a718a6bef0b953",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"Map: 0%| | 0/1133 [00:00<?, ? examples/s]"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"DatasetDict({\n",
" train: Dataset({\n",
" features: ['chinese', 'english', 'text', 'prompt'],\n",
" num_rows: 4528\n",
" })\n",
" test: Dataset({\n",
" features: ['chinese', 'english', 'text', 'prompt'],\n",
" num_rows: 1133\n",
" })\n",
"})\n"
]
}
],
"source": [
"from llm_toolkit.translation_utils_v1 import (\n",
" load_translation_dataset as load_translation_dataset_v1,\n",
")\n",
"\n",
"dataset_v1 = load_translation_dataset_v1(data_path, tokenizer=tokenizer)"
]
},
{
"cell_type": "code",
"execution_count": 17,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"--------------------------------------------------\n",
"chinese: 老耿端起枪，眯缝起一只三角眼，一搂扳机响了枪，冰雹般的金麻雀劈哩啪啦往下落，铁砂子在柳枝间飞迸着，嚓嚓有声。\n",
"--------------------------------------------------\n",
"english: Old Geng picked up his shotgun, squinted, and pulled the trigger. Two sparrows crashed to the ground like hailstones as shotgun pellets tore noisily through the branches.\n",
"--------------------------------------------------\n",
"text: You are an expert in translating Chinese to English.<|im_start|>user\n",
"Please translate the following Chinese text into English and provide only the translated content, nothing else.\n",
"老耿端起枪，眯缝起一只三角眼，一搂扳机响了枪，冰雹般的金麻雀劈哩啪啦往下落，铁砂子在柳枝间飞迸着，嚓嚓有声。<|im_end|>\n",
"<|im_start|>assistant\n",
"Old Geng picked up his shotgun, squinted, and pulled the trigger. Two sparrows crashed to the ground like hailstones as shotgun pellets tore noisily through the branches.<|im_end|>\n",
"--------------------------------------------------\n",
"prompt: You are an expert in translating Chinese to English.<|im_start|>user\n",
"Please translate the following Chinese text into English and provide only the translated content, nothing else.\n",
"老耿端起枪，眯缝起一只三角眼，一搂扳机响了枪，冰雹般的金麻雀劈哩啪啦往下落，铁砂子在柳枝间飞迸着，嚓嚓有声。<|im_end|>\n",
"<|im_start|>assistant\n",
"\n"
]
}
],
"source": [
"print_row_details(dataset_v1[\"test\"].to_pandas())"
]
},
{
"cell_type": "code",
"execution_count": 25,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{'meteor': 0.5158944459316517,\n",
" 'bleu_scores': {'bleu': 0.08754836694338668,\n",
" 'precisions': [0.23318385650224216,\n",
" 0.09502262443438914,\n",
" 0.0639269406392694,\n",
" 0.041474654377880185],\n",
" 'brevity_penalty': 1.0,\n",
" 'length_ratio': 2.207920792079208,\n",
" 'translation_length': 223,\n",
" 'reference_length': 101},\n",
" 'rouge_scores': {'rouge1': 0.4382566585956416,\n",
" 'rouge2': 0.2634032634032634,\n",
" 'rougeL': 0.387409200968523,\n",
" 'rougeLsum': 0.4170702179176755},\n",
" 'accuracy': 0.0}"
]
},
"execution_count": 25,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"calc_metrics(eval_dataset[\"english\"], predictions)"
]
},
{
"cell_type": "code",
"execution_count": 18,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
" 50%|█████ | 1/2 [11:04<11:04, 664.47s/it]"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"Batch output: ['First, I\\'ll identify the key phrases and words in the Chinese text:\\n\\n1. 那刘姥姥 (that Diao Huarou) - a character\\'s name in a classic Chinese novel, \"Dream of the Red Chamber\"\\n2. 先听见告艰苦 (first heard of the hardship)\\n3. 只当是没想头了 (just thought it was nonsense)\\n4. 又听见给他二十两银子 (then heard that he received twenty silver pieces)\\n5. 喜的眉开眼笑 (very happy, smiling broadly)\\n6. “我们也知道艰难的 (we also know the difficulties)\\n7. 但只俗语说的 (but as the saying goes)\\n8. ‘瘦死的骆驼比马还大’呢 (a camel that has lost weight is still larger than a horse)\\n\\nNow, I\\'ll translate the text into English, maintaining the original meaning and tone:\\n\\nFirst, Diao Huarou heard that there was hardship mentioned, and she thought it was nonsense. Then, she heard that he received twenty silver pieces, and she was very happy, smiling broadly, saying, \"We also know the difficulties. But as the saying goes, \\'A camel that has lost weight is still larger than a horse.\\'\"']\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"100%|██████████| 2/2 [22:04<00:00, 662.38s/it]\n"
]
},
{
"data": {
"text/plain": [
"['First, I\\'ll identify the key phrases and words in the Chinese text:\\n\\n1. 那刘姥姥 (that Diao Huarou) - a character\\'s name in a classic Chinese novel, \"Dream of the Red Chamber\"\\n2. 先听见告艰苦 (first heard of the hardship)\\n3. 只当是没想头了 (just thought it was nonsense)\\n4. 又听见给他二十两银子 (then heard that he received twenty silver pieces)\\n5. 喜的眉开眼笑 (very happy, smiling broadly)\\n6. “我们也知道艰难的 (we also know the difficulties)\\n7. 但只俗语说的 (but as the saying goes)\\n8. ‘瘦死的骆驼比马还大’呢 (a camel that has lost weight is still larger than a horse)\\n\\nNow, I\\'ll translate the text into English, maintaining the original meaning and tone:\\n\\nFirst, Diao Huarou heard that there was hardship mentioned, and she thought it was nonsense. Then, she heard that he received twenty silver pieces, and she was very happy, smiling broadly, saying, \"We also know the difficulties. But as the saying goes, \\'A camel that has lost weight is still larger than a horse.\\'\"',\n",
" 'Later, she stopped struggling and said to me, \"Son of a bitch, what are you going to do with me?\"']"
]
},
"execution_count": 18,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"eval_dataset_v1 = dataset_v1[\"test\"].select([260, 908])\n",
"predictions_v1 = eval_model(\n",
" model, tokenizer, eval_dataset_v1, device=device, max_new_tokens=max_new_tokens\n",
")\n",
"predictions_v1"
]
},
{
"cell_type": "code",
"execution_count": 19,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"['First, I\\'ll identify the key phrases and words in the Chinese text:\\n\\n1. 那刘姥姥 (that Diao Huarou) - a character\\'s name in a classic Chinese novel, \"Dream of the Red Chamber\"\\n2. 先听见告艰苦 (first heard of the hardship)\\n3. 只当是没想头了 (just thought it was nonsense)\\n4. 又听见给他二十两银子 (then heard that he received twenty silver pieces)\\n5. 喜的眉开眼笑 (very happy, smiling broadly)\\n6. “我们也知道艰难的 (we also know the difficulties)\\n7. 但只俗语说的 (but as the saying goes)\\n8. ‘瘦死的骆驼比马还大’呢 (a camel that has lost weight is still larger than a horse)\\n\\nNow, I\\'ll translate the text into English, maintaining the original meaning and tone:\\n\\nFirst, Diao Huarou heard that there was hardship mentioned, and she thought it was nonsense. Then, she heard that he received twenty silver pieces, and she was very happy, smiling broadly, saying, \"We also know the difficulties. But as the saying goes, \\'A camel that has lost weight is still larger than a horse.\\'\"', 'Later, she stopped struggling and said to me, \"Son of a bitch, what are you going to do with me?\"']\n"
]
}
],
"source": [
"print(predictions_v1)"
]
},
{
"cell_type": "code",
"execution_count": 20,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"--------------------------------------------------\n",
"chinese: 那刘姥姥先听见告艰苦，只当是没想头了， 又听见给他二十两银子，喜的眉开眼笑道：“我们也知道艰难的，但只俗语说的：‘瘦死的骆驼比马还大’呢。\n",
"--------------------------------------------------\n",
"english: When Grannie Liu heard Xi-feng talk about 'difficulties' she concluded that there was no hope. Her delight and the way in which her face lit up with pleasure when she heard that she was, after all, to be given twenty taels of silver can be imagined. 'We knew you had your troubles,' she said, 'but as the saying goes, 'A starved camel is bigger than a fat horse.'\n",
"--------------------------------------------------\n",
"text: You are an expert in translating Chinese to English.<|im_start|>user\n",
"Please translate the following Chinese text into English and provide only the translated content, nothing else.\n",
"那刘姥姥先听见告艰苦，只当是没想头了， 又听见给他二十两银子，喜的眉开眼笑道：“我们也知道艰难的，但只俗语说的：‘瘦死的骆驼比马还大’呢。<|im_end|>\n",
"<|im_start|>assistant\n",
"When Grannie Liu heard Xi-feng talk about 'difficulties' she concluded that there was no hope. Her delight and the way in which her face lit up with pleasure when she heard that she was, after all, to be given twenty taels of silver can be imagined. 'We knew you had your troubles,' she said, 'but as the saying goes, 'A starved camel is bigger than a fat horse.'<|im_end|>\n",
"--------------------------------------------------\n",
"prompt: You are an expert in translating Chinese to English.<|im_start|>user\n",
"Please translate the following Chinese text into English and provide only the translated content, nothing else.\n",
"那刘姥姥先听见告艰苦，只当是没想头了， 又听见给他二十两银子，喜的眉开眼笑道：“我们也知道艰难的，但只俗语说的：‘瘦死的骆驼比马还大’呢。<|im_end|>\n",
"<|im_start|>assistant\n",
"\n",
"--------------------------------------------------\n",
"chinese: 后来她不挣扎了，对我说，混蛋，你要把我怎么办。\n",
"--------------------------------------------------\n",
"english: After a while, she no longer struggled and said, You bastard! What are you going to do with me?\n",
"--------------------------------------------------\n",
"text: You are an expert in translating Chinese to English.<|im_start|>user\n",
"Please translate the following Chinese text into English and provide only the translated content, nothing else.\n",
"后来她不挣扎了，对我说，混蛋，你要把我怎么办。<|im_end|>\n",
"<|im_start|>assistant\n",
"After a while, she no longer struggled and said, You bastard! What are you going to do with me?<|im_end|>\n",
"--------------------------------------------------\n",
"prompt: You are an expert in translating Chinese to English.<|im_start|>user\n",
"Please translate the following Chinese text into English and provide only the translated content, nothing else.\n",
"后来她不挣扎了，对我说，混蛋，你要把我怎么办。<|im_end|>\n",
"<|im_start|>assistant\n",
"\n"
]
}
],
"source": [
"print_row_details(eval_dataset_v1.to_pandas(), range(len(eval_dataset_v1)))"
]
},
{
"cell_type": "code",
"execution_count": 26,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{'meteor': 0.5153317672515252,\n",
" 'bleu_scores': {'bleu': 0.08097031799100003,\n",
" 'precisions': [0.21397379912663755,\n",
" 0.09691629955947137,\n",
" 0.057777777777777775,\n",
" 0.03587443946188341],\n",
" 'brevity_penalty': 1.0,\n",
" 'length_ratio': 2.267326732673267,\n",
" 'translation_length': 229,\n",
" 'reference_length': 101},\n",
" 'rouge_scores': {'rouge1': 0.4401123990165086,\n",
" 'rouge2': 0.26690746045584757,\n",
" 'rougeL': 0.38707411310151035,\n",
" 'rougeLsum': 0.40533895328415875},\n",
" 'accuracy': 0.0}"
]
},
"execution_count": 26,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"calc_metrics(eval_dataset_v1[\"english\"], predictions_v1)"
]
},
{
"cell_type": "code",
"execution_count": 21,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"loading train/test data files\n"
]
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "22e0eed1c971459497f30cf1141317f2",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"Map: 0%| | 0/4528 [00:00<?, ? examples/s]"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "3925ff53b4c34183a8427d900f2f51f3",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"Map: 0%| | 0/1133 [00:00<?, ? examples/s]"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"DatasetDict({\n",
" train: Dataset({\n",
" features: ['chinese', 'english', 'text', 'prompt'],\n",
" num_rows: 4528\n",
" })\n",
" test: Dataset({\n",
" features: ['chinese', 'english', 'text', 'prompt'],\n",
" num_rows: 1133\n",
" })\n",
"})\n"
]
}
],
"source": [
"dataset_v2 = load_translation_dataset(data_path, tokenizer=tokenizer, num_shots=0)"
]
},
{
"cell_type": "code",
"execution_count": 22,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
" 50%|█████ | 1/2 [11:33<11:33, 693.07s/it]"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"Batch output: ['That Dukai first heard about the hardship, thinking it was pointless, but then heard that he received twenty silver pieces, and was so happy that his eyebrows and eyes opened wide as he said, \"We know the difficulties, but as the saying goes, \\'Even a lean camel is bigger than a horse.\\'\"']\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"100%|██████████| 2/2 [22:34<00:00, 677.33s/it]\n"
]
},
{
"data": {
"text/plain": [
"['That Dukai first heard about the hardship, thinking it was pointless, but then heard that he received twenty silver pieces, and was so happy that his eyebrows and eyes opened wide as he said, \"We know the difficulties, but as the saying goes, \\'Even a lean camel is bigger than a horse.\\'\"',\n",
" '后来她不挣扎了， 对我说， 混蛋， 你要把我怎么办。\\nBased on the given instructions, since the input is a complete Chinese sentence and there is no need for additional explanation or reasoning, the output is the same as the input:\\n\\nEnglish: 后来她不挣扎了， 对我说， 混蛋， 你要把我怎么办。']"
]
},
"execution_count": 22,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"eval_dataset_v2 = dataset_v2[\"test\"].select([260, 908])\n",
"predictions_v2 = eval_model(\n",
" model, tokenizer, eval_dataset_v2, device=device, max_new_tokens=max_new_tokens\n",
")\n",
"predictions_v2"
]
},
{
"cell_type": "code",
"execution_count": 23,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"['That Dukai first heard about the hardship, thinking it was pointless, but then heard that he received twenty silver pieces, and was so happy that his eyebrows and eyes opened wide as he said, \"We know the difficulties, but as the saying goes, \\'Even a lean camel is bigger than a horse.\\'\"', '后来她不挣扎了， 对我说， 混蛋， 你要把我怎么办。\\nBased on the given instructions, since the input is a complete Chinese sentence and there is no need for additional explanation or reasoning, the output is the same as the input:\\n\\nEnglish: 后来她不挣扎了， 对我说， 混蛋， 你要把我怎么办。']\n"
]
}
],
"source": [
"print(predictions_v2)"
]
},
{
"cell_type": "code",
"execution_count": 24,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"--------------------------------------------------\n",
"chinese: 那刘姥姥先听见告艰苦，只当是没想头了， 又听见给他二十两银子，喜的眉开眼笑道：“我们也知道艰难的，但只俗语说的：‘瘦死的骆驼比马还大’呢。\n",
"--------------------------------------------------\n",
"english: When Grannie Liu heard Xi-feng talk about 'difficulties' she concluded that there was no hope. Her delight and the way in which her face lit up with pleasure when she heard that she was, after all, to be given twenty taels of silver can be imagined. 'We knew you had your troubles,' she said, 'but as the saying goes, 'A starved camel is bigger than a fat horse.'\n",
"--------------------------------------------------\n",
"text: You are a helpful assistant that translates Chinese to English.<|im_start|>user\n",
"You will be given a Chinese sentence to translate. If it is an incomplete sentence, or if you are unsure about the meaning, simply copy the input text as your output. Do not output any additional sentence such as explanation or reasoning.\n",
"\n",
"Chinese: 那刘姥姥先听见告艰苦，只当是没想头了， 又听见给他二十两银子，喜的眉开眼笑道：“我们也知道艰难的，但只俗语说的：‘瘦死的骆驼比马还大’呢。\n",
"English:<|im_end|>\n",
"<|im_start|>assistant\n",
"When Grannie Liu heard Xi-feng talk about 'difficulties' she concluded that there was no hope. Her delight and the way in which her face lit up with pleasure when she heard that she was, after all, to be given twenty taels of silver can be imagined. 'We knew you had your troubles,' she said, 'but as the saying goes, 'A starved camel is bigger than a fat horse.'<|im_end|>\n",
"--------------------------------------------------\n",
"prompt: You are a helpful assistant that translates Chinese to English.<|im_start|>user\n",
"You will be given a Chinese sentence to translate. If it is an incomplete sentence, or if you are unsure about the meaning, simply copy the input text as your output. Do not output any additional sentence such as explanation or reasoning.\n",
"\n",
"Chinese: 那刘姥姥先听见告艰苦，只当是没想头了， 又听见给他二十两银子，喜的眉开眼笑道：“我们也知道艰难的，但只俗语说的：‘瘦死的骆驼比马还大’呢。\n",
"English:<|im_end|>\n",
"<|im_start|>assistant\n",
"\n",
"--------------------------------------------------\n",
"chinese: 后来她不挣扎了，对我说，混蛋，你要把我怎么办。\n",
"--------------------------------------------------\n",
"english: After a while, she no longer struggled and said, You bastard! What are you going to do with me?\n",
"--------------------------------------------------\n",
"text: You are a helpful assistant that translates Chinese to English.<|im_start|>user\n",
"You will be given a Chinese sentence to translate. If it is an incomplete sentence, or if you are unsure about the meaning, simply copy the input text as your output. Do not output any additional sentence such as explanation or reasoning.\n",
"\n",
"Chinese: 后来她不挣扎了，对我说，混蛋，你要把我怎么办。\n",
"English:<|im_end|>\n",
"<|im_start|>assistant\n",
"After a while, she no longer struggled and said, You bastard! What are you going to do with me?<|im_end|>\n",
"--------------------------------------------------\n",
"prompt: You are a helpful assistant that translates Chinese to English.<|im_start|>user\n",
"You will be given a Chinese sentence to translate. If it is an incomplete sentence, or if you are unsure about the meaning, simply copy the input text as your output. Do not output any additional sentence such as explanation or reasoning.\n",
"\n",
"Chinese: 后来她不挣扎了，对我说，混蛋，你要把我怎么办。\n",
"English:<|im_end|>\n",
"<|im_start|>assistant\n",
"\n"
]
}
],
"source": [
"print_row_details(eval_dataset_v2.to_pandas(), range(len(eval_dataset_v2)))"
]
},
{
"cell_type": "code",
"execution_count": 27,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{'meteor': 0.21319948962320656,\n",
" 'bleu_scores': {'bleu': 0.10039676162391267,\n",
" 'precisions': [0.32075471698113206,\n",
" 0.11538461538461539,\n",
" 0.06862745098039216,\n",
" 0.04],\n",
" 'brevity_penalty': 1.0,\n",
" 'length_ratio': 1.0495049504950495,\n",
" 'translation_length': 106,\n",
" 'reference_length': 101},\n",
" 'rouge_scores': {'rouge1': 0.27369956246961596,\n",
" 'rouge2': 0.07563025210084033,\n",
" 'rougeL': 0.20450494247285692,\n",
" 'rougeLsum': 0.20450494247285692},\n",
" 'accuracy': 0.0}"
]
},
"execution_count": 27,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"calc_metrics(eval_dataset_v2[\"english\"], predictions_v2)"
]
}
],
"metadata": {
"accelerator": "GPU",
"application/vnd.databricks.v1+notebook": {
"dashboards": [],
"environmentMetadata": null,
"language": "python",
"notebookMetadata": {
"mostRecentlyExecutedCommandWithImplicitDF": {
"commandId": -1,
"dataframes": [
"_sqldf"
]
},
"pythonIndentUnit": 4
},
"notebookName": "10_eval-lf-medium-py3.11",
"widgets": {}
},
"colab": {
"gpuType": "L4",
"provenance": []
},
"kernelspec": {
"display_name": "Python 3",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.11.9"
}
},
"nbformat": 4,
"nbformat_minor": 0
}
|