Spaces:
Build error
Build error
File size: 121,987 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 |
{
"cells": [
{
"cell_type": "code",
"execution_count": 33,
"metadata": {
"executionInfo": {
"elapsed": 476,
"status": "ok",
"timestamp": 1720679526275,
"user": {
"displayName": "HUANG DONGHAO _",
"userId": "00977795705617022768"
},
"user_tz": -480
},
"id": "uWKRSV6eZsCn"
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"The autoreload extension is already loaded. To reload it, use:\n",
" %reload_ext autoreload\n"
]
}
],
"source": [
"%load_ext autoreload\n",
"%autoreload 2"
]
},
{
"cell_type": "code",
"execution_count": 34,
"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: /Users/inflaton/code/engd/papers/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": 35,
"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: /Users/inflaton/code/engd/papers/rapget-translation/.env\n"
]
},
{
"data": {
"text/plain": [
"True"
]
},
"execution_count": 35,
"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": 36,
"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": [
"Qwen/Qwen2-7B-Instruct None False datasets/mac/mac.tsv results/mac-results.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": 37,
"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\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: /Users/inflaton/anaconda3/envs/rapget/lib/python3.11/site-packages\n",
"Requires: filelock, fsspec, jinja2, networkx, sympy, typing-extensions\n",
"Required-by: accelerate, peft, torchaudio, torchvision, trl\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: /Users/inflaton/anaconda3/envs/rapget/lib/python3.11/site-packages\n",
"Requires: filelock, huggingface-hub, numpy, packaging, pyyaml, regex, requests, safetensors, tokenizers, tqdm\n",
"Required-by: llamafactory, peft, trl\n",
"CPU times: user 8.97 ms, sys: 13.7 ms, total: 22.7 ms\n",
"Wall time: 1.91 s\n"
]
}
],
"source": [
"%%time\n",
"os.environ[\"TOKENIZERS_PARALLELISM\"] = \"true\"\n",
"\n",
"!python --version\n",
"!pip show torch transformers"
]
},
{
"cell_type": "code",
"execution_count": 38,
"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": "stdout",
"output_type": "stream",
"text": [
"MPS is available\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": 39,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"loading existing data from: logs/openai-training-sample.jsonl\n"
]
},
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>messages</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>[{'role': 'system', 'content': 'Marv is a fact...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>[{'role': 'system', 'content': 'Marv is a fact...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>[{'role': 'system', 'content': 'Marv is a fact...</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" messages\n",
"0 [{'role': 'system', 'content': 'Marv is a fact...\n",
"1 [{'role': 'system', 'content': 'Marv is a fact...\n",
"2 [{'role': 'system', 'content': 'Marv is a fact..."
]
},
"execution_count": 39,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df_openai = load_openai_training_data(\n",
" data_path, openai_data_path=\"logs/openai-training-sample.jsonl\"\n",
")\n",
"df_openai"
]
},
{
"cell_type": "code",
"execution_count": 40,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"--------------------------------------------------\n",
"messages: [{'role': 'system', 'content': 'Marv is a factual chatbot that is also sarcastic.'}, {'role': 'user', 'content': \"What's the capital of France?\"}, {'role': 'assistant', 'content': \"Paris, as if everyone doesn't know that already.\"}]\n",
"--------------------------------------------------\n",
"messages: [{'role': 'system', 'content': 'Marv is a factual chatbot that is also sarcastic.'}, {'role': 'user', 'content': \"Who wrote 'Romeo and Juliet'?\"}, {'role': 'assistant', 'content': 'Oh, just some guy named William Shakespeare. Ever heard of him?'}]\n",
"--------------------------------------------------\n",
"messages: [{'role': 'system', 'content': 'Marv is a factual chatbot that is also sarcastic.'}, {'role': 'user', 'content': 'How far is the Moon from Earth?'}, {'role': 'assistant', 'content': 'Around 384,400 kilometers. Give or take a few, like that really matters.'}]\n"
]
}
],
"source": [
"print_row_details(df_openai, range(len(df_openai)))"
]
},
{
"cell_type": "code",
"execution_count": 41,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"loading existing data from: datasets/mac/openai-training.jsonl\n",
"--------------------------------------------------\n",
"messages: [{'role': 'system', 'content': 'You are a helpful assistant that translates Chinese to English.'}, {'role': 'user', 'content': '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\\nChinese: 全仗着狐仙搭救。\\nEnglish:'}, {'role': 'assistant', 'content': 'Because I was protected by a fox fairy.'}]\n"
]
}
],
"source": [
"df_openai = load_openai_training_data(data_path)\n",
"print_row_details(df_openai)"
]
},
{
"cell_type": "code",
"execution_count": 42,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"FileObject(id='file-IokPHn4YWcniXL4wGnK4xVmn', bytes=3413094, created_at=1723269681, filename='openai-training.jsonl', object='file', purpose='fine-tune', status='processed', status_details=None)"
]
},
"execution_count": 42,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"from openai import OpenAI\n",
"\n",
"client = OpenAI()\n",
"\n",
"client.files.create(\n",
" file=open(\"datasets/mac/openai-training.jsonl\", \"rb\"), purpose=\"fine-tune\"\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 50,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"FineTuningJob(id='ftjob-TcCo4KtDd3Gp5cnOVky2Rxhh', created_at=1723270136, error=Error(code=None, message=None, param=None), fine_tuned_model=None, finished_at=None, hyperparameters=Hyperparameters(n_epochs=6, batch_size='auto', learning_rate_multiplier='auto'), model='gpt-4o-mini-2024-07-18', object='fine_tuning.job', organization_id='org-RXHVnD8cqPvqTPdXgZ5rQdl3', result_files=[], seed=1046194933, status='validating_files', trained_tokens=None, training_file='file-IokPHn4YWcniXL4wGnK4xVmn', validation_file=None, estimated_finish=None, integrations=[], user_provided_suffix=None)"
]
},
"execution_count": 50,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"from openai import OpenAI\n",
"\n",
"client = OpenAI()\n",
"\n",
"client.fine_tuning.jobs.create(\n",
" training_file=\"file-IokPHn4YWcniXL4wGnK4xVmn\",\n",
" model=\"gpt-4o-mini-2024-07-18\",\n",
" hyperparameters={\"n_epochs\": 6},\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 52,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"FineTuningJob(id='ftjob-TcCo4KtDd3Gp5cnOVky2Rxhh', created_at=1723270136, error=Error(code=None, message=None, param=None), fine_tuned_model='ft:gpt-4o-mini-2024-07-18:mastercard::9uaCEFTs', finished_at=1723272532, hyperparameters=Hyperparameters(n_epochs=6, batch_size=18, learning_rate_multiplier=1.8), model='gpt-4o-mini-2024-07-18', object='fine_tuning.job', organization_id='org-RXHVnD8cqPvqTPdXgZ5rQdl3', result_files=['file-aCppW0GWhhytwe4yKwymNUZl'], seed=1046194933, status='succeeded', trained_tokens=3640956, training_file='file-IokPHn4YWcniXL4wGnK4xVmn', validation_file=None, estimated_finish=None, integrations=[], user_provided_suffix=None)"
]
},
"execution_count": 52,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"from openai import OpenAI\n",
"\n",
"client = OpenAI()\n",
"\n",
"client.fine_tuning.jobs.retrieve(\"ftjob-TcCo4KtDd3Gp5cnOVky2Rxhh\")"
]
},
{
"cell_type": "code",
"execution_count": 56,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"loading /Users/inflaton/code/engd/papers/rapget-translation/llm_toolkit/translation_utils.py\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"[nltk_data] Downloading package wordnet to\n",
"[nltk_data] /Users/inflaton/nltk_data...\n",
"[nltk_data] Package wordnet is already up-to-date!\n",
"[nltk_data] Downloading package punkt to /Users/inflaton/nltk_data...\n",
"[nltk_data] Package punkt is already up-to-date!\n",
"[nltk_data] Downloading package omw-1.4 to\n",
"[nltk_data] /Users/inflaton/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": "1a87da44759e427f8aeba2beb4fad0ec",
"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": "fff4afca226843d89ba56ec8c0d305f7",
"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",
"--------------------------------------------------\n",
"chinese: 然后他们到一间为游客开的通宵酒吧中去坐了两个多小时，沙瑞山一杯接着一杯地灌啤酒，变得更加健谈，而汪淼却早已心神不定，脑子里不断地浮现出那条绿色直线。\n",
"--------------------------------------------------\n",
"english: Then they went to an all-night bar for tourists and sat for two hours. As Sha finished one beer after another, his tongue loosened even more. But Wang became anxious, and his mind kept returning to that green line on the terminal in Sha's office.\n",
"--------------------------------------------------\n",
"text: [{'content': 'You are a helpful assistant that translates Chinese to English.', 'role': 'system'}\n",
" {'content': '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\\nChinese: 然后他们到一间为游客开的通宵酒吧中去坐了两个多小时，沙瑞山一杯接着一杯地灌啤酒，变得更加健谈，而汪淼却早已心神不定，脑子里不断地浮现出那条绿色直线。\\nEnglish:', 'role': 'user'}\n",
" {'content': \"Then they went to an all-night bar for tourists and sat for two hours. As Sha finished one beer after another, his tongue loosened even more. But Wang became anxious, and his mind kept returning to that green line on the terminal in Sha's office.\", 'role': 'assistant'}]\n",
"--------------------------------------------------\n",
"prompt: [{'content': 'You are a helpful assistant that translates Chinese to English.', 'role': 'system'}\n",
" {'content': '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\\nChinese: 然后他们到一间为游客开的通宵酒吧中去坐了两个多小时，沙瑞山一杯接着一杯地灌啤酒，变得更加健谈，而汪淼却早已心神不定，脑子里不断地浮现出那条绿色直线。\\nEnglish:', 'role': 'user'}]\n"
]
}
],
"source": [
"datasets = load_translation_dataset(data_path, for_openai=True)\n",
"df_test = datasets[\"test\"].to_pandas()\n",
"print_row_details(df_test, [100])"
]
},
{
"cell_type": "code",
"execution_count": 57,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"ChatCompletionMessage(content=\"After that, they sat for more than two hours in an all-night bar open to hotel guests. Sha drank one cup of beer after another, becoming even more talkative. On the other hand, Wang's mind was no longer there. The green line floated constantly in his mind.\", role='assistant', function_call=None, tool_calls=None, refusal=None)\n"
]
}
],
"source": [
"from openai import OpenAI\n",
"\n",
"client = OpenAI()\n",
"\n",
"completion = client.chat.completions.create(\n",
" model=\"ft:gpt-4o-mini-2024-07-18:mastercard::9uaCEFTs\",\n",
" messages=df_test.iloc[100].prompt,\n",
")\n",
"print(completion.choices[0].message)"
]
},
{
"cell_type": "code",
"execution_count": 60,
"metadata": {},
"outputs": [
{
"ename": "RateLimitError",
"evalue": "Error code: 429 - {'error': {'message': \"This fine-tune request has been rate-limited. Your organization has reached the maximum of 3 active requests (2 running, 1 pending) for the model 'gpt-4o-mini-2024-07-18'.\", 'type': 'invalid_request_error', 'param': None, 'code': 'rate_limit_exceeded'}}",
"output_type": "error",
"traceback": [
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[0;31mRateLimitError\u001b[0m Traceback (most recent call last)",
"Cell \u001b[0;32mIn[60], line 7\u001b[0m\n\u001b[1;32m 5\u001b[0m jobs \u001b[38;5;241m=\u001b[39m []\n\u001b[1;32m 6\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m epoch \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28mrange\u001b[39m(\u001b[38;5;241m1\u001b[39m, \u001b[38;5;241m6\u001b[39m):\n\u001b[0;32m----> 7\u001b[0m job \u001b[38;5;241m=\u001b[39m \u001b[43mclient\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mfine_tuning\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mjobs\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mcreate\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 8\u001b[0m \u001b[43m \u001b[49m\u001b[43mtraining_file\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mfile-IokPHn4YWcniXL4wGnK4xVmn\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[1;32m 9\u001b[0m \u001b[43m \u001b[49m\u001b[43mmodel\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mgpt-4o-mini-2024-07-18\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[1;32m 10\u001b[0m \u001b[43m \u001b[49m\u001b[43mseed\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;241;43m1046194933\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[1;32m 11\u001b[0m \u001b[43m \u001b[49m\u001b[43mhyperparameters\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43m{\u001b[49m\n\u001b[1;32m 12\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mn_epochs\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mepoch\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 13\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mbatch_size\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m18\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[1;32m 14\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mlearning_rate_multiplier\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m1.8\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[1;32m 15\u001b[0m \u001b[43m \u001b[49m\u001b[43m}\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 16\u001b[0m \u001b[43m \u001b[49m\u001b[43mintegrations\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43m[\u001b[49m\n\u001b[1;32m 17\u001b[0m \u001b[43m \u001b[49m\u001b[43m{\u001b[49m\n\u001b[1;32m 18\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mtype\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mwandb\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[1;32m 19\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mwandb\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43m{\u001b[49m\n\u001b[1;32m 20\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mproject\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mOpenAI\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[1;32m 21\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mname\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;124;43mf\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mgpt-4o-mini-2024-07-18-\u001b[39;49m\u001b[38;5;132;43;01m{\u001b[39;49;00m\u001b[43mepoch\u001b[49m\u001b[38;5;132;43;01m}\u001b[39;49;00m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[1;32m 22\u001b[0m \u001b[43m \u001b[49m\u001b[43m}\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 23\u001b[0m \u001b[43m \u001b[49m\u001b[43m}\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 24\u001b[0m \u001b[43m \u001b[49m\u001b[43m]\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 25\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 26\u001b[0m jobs\u001b[38;5;241m.\u001b[39mappend(job)\n\u001b[1;32m 28\u001b[0m jobs\n",
"File \u001b[0;32m~/anaconda3/envs/rapget/lib/python3.11/site-packages/openai/resources/fine_tuning/jobs/jobs.py:133\u001b[0m, in \u001b[0;36mJobs.create\u001b[0;34m(self, model, training_file, hyperparameters, integrations, seed, suffix, validation_file, extra_headers, extra_query, extra_body, timeout)\u001b[0m\n\u001b[1;32m 52\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mcreate\u001b[39m(\n\u001b[1;32m 53\u001b[0m \u001b[38;5;28mself\u001b[39m,\n\u001b[1;32m 54\u001b[0m \u001b[38;5;241m*\u001b[39m,\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 67\u001b[0m timeout: \u001b[38;5;28mfloat\u001b[39m \u001b[38;5;241m|\u001b[39m httpx\u001b[38;5;241m.\u001b[39mTimeout \u001b[38;5;241m|\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;241m|\u001b[39m NotGiven \u001b[38;5;241m=\u001b[39m NOT_GIVEN,\n\u001b[1;32m 68\u001b[0m ) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m FineTuningJob:\n\u001b[1;32m 69\u001b[0m \u001b[38;5;250m \u001b[39m\u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[1;32m 70\u001b[0m \u001b[38;5;124;03m Creates a fine-tuning job which begins the process of creating a new model from\u001b[39;00m\n\u001b[1;32m 71\u001b[0m \u001b[38;5;124;03m a given dataset.\u001b[39;00m\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 131\u001b[0m \u001b[38;5;124;03m timeout: Override the client-level default timeout for this request, in seconds\u001b[39;00m\n\u001b[1;32m 132\u001b[0m \u001b[38;5;124;03m \"\"\"\u001b[39;00m\n\u001b[0;32m--> 133\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_post\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 134\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43m/fine_tuning/jobs\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[1;32m 135\u001b[0m \u001b[43m \u001b[49m\u001b[43mbody\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mmaybe_transform\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 136\u001b[0m \u001b[43m \u001b[49m\u001b[43m{\u001b[49m\n\u001b[1;32m 137\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mmodel\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mmodel\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 138\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mtraining_file\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mtraining_file\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 139\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mhyperparameters\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mhyperparameters\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 140\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mintegrations\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mintegrations\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 141\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mseed\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mseed\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 142\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43msuffix\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43msuffix\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 143\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mvalidation_file\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mvalidation_file\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 144\u001b[0m \u001b[43m \u001b[49m\u001b[43m}\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 145\u001b[0m \u001b[43m \u001b[49m\u001b[43mjob_create_params\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mJobCreateParams\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 146\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 147\u001b[0m \u001b[43m \u001b[49m\u001b[43moptions\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mmake_request_options\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 148\u001b[0m \u001b[43m \u001b[49m\u001b[43mextra_headers\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mextra_headers\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mextra_query\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mextra_query\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mextra_body\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mextra_body\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mtimeout\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mtimeout\u001b[49m\n\u001b[1;32m 149\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 150\u001b[0m \u001b[43m \u001b[49m\u001b[43mcast_to\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mFineTuningJob\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 151\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n",
"File \u001b[0;32m~/anaconda3/envs/rapget/lib/python3.11/site-packages/openai/_base_client.py:1266\u001b[0m, in \u001b[0;36mSyncAPIClient.post\u001b[0;34m(self, path, cast_to, body, options, files, stream, stream_cls)\u001b[0m\n\u001b[1;32m 1252\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mpost\u001b[39m(\n\u001b[1;32m 1253\u001b[0m \u001b[38;5;28mself\u001b[39m,\n\u001b[1;32m 1254\u001b[0m path: \u001b[38;5;28mstr\u001b[39m,\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 1261\u001b[0m stream_cls: \u001b[38;5;28mtype\u001b[39m[_StreamT] \u001b[38;5;241m|\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m,\n\u001b[1;32m 1262\u001b[0m ) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m ResponseT \u001b[38;5;241m|\u001b[39m _StreamT:\n\u001b[1;32m 1263\u001b[0m opts \u001b[38;5;241m=\u001b[39m FinalRequestOptions\u001b[38;5;241m.\u001b[39mconstruct(\n\u001b[1;32m 1264\u001b[0m method\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mpost\u001b[39m\u001b[38;5;124m\"\u001b[39m, url\u001b[38;5;241m=\u001b[39mpath, json_data\u001b[38;5;241m=\u001b[39mbody, files\u001b[38;5;241m=\u001b[39mto_httpx_files(files), \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39moptions\n\u001b[1;32m 1265\u001b[0m )\n\u001b[0;32m-> 1266\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m cast(ResponseT, \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mrequest\u001b[49m\u001b[43m(\u001b[49m\u001b[43mcast_to\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mopts\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mstream\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstream\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mstream_cls\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstream_cls\u001b[49m\u001b[43m)\u001b[49m)\n",
"File \u001b[0;32m~/anaconda3/envs/rapget/lib/python3.11/site-packages/openai/_base_client.py:942\u001b[0m, in \u001b[0;36mSyncAPIClient.request\u001b[0;34m(self, cast_to, options, remaining_retries, stream, stream_cls)\u001b[0m\n\u001b[1;32m 933\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mrequest\u001b[39m(\n\u001b[1;32m 934\u001b[0m \u001b[38;5;28mself\u001b[39m,\n\u001b[1;32m 935\u001b[0m cast_to: Type[ResponseT],\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 940\u001b[0m stream_cls: \u001b[38;5;28mtype\u001b[39m[_StreamT] \u001b[38;5;241m|\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m,\n\u001b[1;32m 941\u001b[0m ) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m ResponseT \u001b[38;5;241m|\u001b[39m _StreamT:\n\u001b[0;32m--> 942\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_request\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 943\u001b[0m \u001b[43m \u001b[49m\u001b[43mcast_to\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcast_to\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 944\u001b[0m \u001b[43m \u001b[49m\u001b[43moptions\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43moptions\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 945\u001b[0m \u001b[43m \u001b[49m\u001b[43mstream\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstream\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 946\u001b[0m \u001b[43m \u001b[49m\u001b[43mstream_cls\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstream_cls\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 947\u001b[0m \u001b[43m \u001b[49m\u001b[43mremaining_retries\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mremaining_retries\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 948\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n",
"File \u001b[0;32m~/anaconda3/envs/rapget/lib/python3.11/site-packages/openai/_base_client.py:1031\u001b[0m, in \u001b[0;36mSyncAPIClient._request\u001b[0;34m(self, cast_to, options, remaining_retries, stream, stream_cls)\u001b[0m\n\u001b[1;32m 1029\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m retries \u001b[38;5;241m>\u001b[39m \u001b[38;5;241m0\u001b[39m \u001b[38;5;129;01mand\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_should_retry(err\u001b[38;5;241m.\u001b[39mresponse):\n\u001b[1;32m 1030\u001b[0m err\u001b[38;5;241m.\u001b[39mresponse\u001b[38;5;241m.\u001b[39mclose()\n\u001b[0;32m-> 1031\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_retry_request\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 1032\u001b[0m \u001b[43m \u001b[49m\u001b[43minput_options\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1033\u001b[0m \u001b[43m \u001b[49m\u001b[43mcast_to\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1034\u001b[0m \u001b[43m \u001b[49m\u001b[43mretries\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1035\u001b[0m \u001b[43m \u001b[49m\u001b[43merr\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mresponse\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mheaders\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1036\u001b[0m \u001b[43m \u001b[49m\u001b[43mstream\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstream\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1037\u001b[0m \u001b[43m \u001b[49m\u001b[43mstream_cls\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstream_cls\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1038\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 1040\u001b[0m \u001b[38;5;66;03m# If the response is streamed then we need to explicitly read the response\u001b[39;00m\n\u001b[1;32m 1041\u001b[0m \u001b[38;5;66;03m# to completion before attempting to access the response text.\u001b[39;00m\n\u001b[1;32m 1042\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m err\u001b[38;5;241m.\u001b[39mresponse\u001b[38;5;241m.\u001b[39mis_closed:\n",
"File \u001b[0;32m~/anaconda3/envs/rapget/lib/python3.11/site-packages/openai/_base_client.py:1079\u001b[0m, in \u001b[0;36mSyncAPIClient._retry_request\u001b[0;34m(self, options, cast_to, remaining_retries, response_headers, stream, stream_cls)\u001b[0m\n\u001b[1;32m 1075\u001b[0m \u001b[38;5;66;03m# In a synchronous context we are blocking the entire thread. Up to the library user to run the client in a\u001b[39;00m\n\u001b[1;32m 1076\u001b[0m \u001b[38;5;66;03m# different thread if necessary.\u001b[39;00m\n\u001b[1;32m 1077\u001b[0m time\u001b[38;5;241m.\u001b[39msleep(timeout)\n\u001b[0;32m-> 1079\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_request\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 1080\u001b[0m \u001b[43m \u001b[49m\u001b[43moptions\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43moptions\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1081\u001b[0m \u001b[43m \u001b[49m\u001b[43mcast_to\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcast_to\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1082\u001b[0m \u001b[43m \u001b[49m\u001b[43mremaining_retries\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mremaining\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1083\u001b[0m \u001b[43m \u001b[49m\u001b[43mstream\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstream\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1084\u001b[0m \u001b[43m \u001b[49m\u001b[43mstream_cls\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstream_cls\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1085\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n",
"File \u001b[0;32m~/anaconda3/envs/rapget/lib/python3.11/site-packages/openai/_base_client.py:1031\u001b[0m, in \u001b[0;36mSyncAPIClient._request\u001b[0;34m(self, cast_to, options, remaining_retries, stream, stream_cls)\u001b[0m\n\u001b[1;32m 1029\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m retries \u001b[38;5;241m>\u001b[39m \u001b[38;5;241m0\u001b[39m \u001b[38;5;129;01mand\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_should_retry(err\u001b[38;5;241m.\u001b[39mresponse):\n\u001b[1;32m 1030\u001b[0m err\u001b[38;5;241m.\u001b[39mresponse\u001b[38;5;241m.\u001b[39mclose()\n\u001b[0;32m-> 1031\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_retry_request\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 1032\u001b[0m \u001b[43m \u001b[49m\u001b[43minput_options\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1033\u001b[0m \u001b[43m \u001b[49m\u001b[43mcast_to\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1034\u001b[0m \u001b[43m \u001b[49m\u001b[43mretries\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1035\u001b[0m \u001b[43m \u001b[49m\u001b[43merr\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mresponse\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mheaders\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1036\u001b[0m \u001b[43m \u001b[49m\u001b[43mstream\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstream\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1037\u001b[0m \u001b[43m \u001b[49m\u001b[43mstream_cls\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstream_cls\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1038\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 1040\u001b[0m \u001b[38;5;66;03m# If the response is streamed then we need to explicitly read the response\u001b[39;00m\n\u001b[1;32m 1041\u001b[0m \u001b[38;5;66;03m# to completion before attempting to access the response text.\u001b[39;00m\n\u001b[1;32m 1042\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m err\u001b[38;5;241m.\u001b[39mresponse\u001b[38;5;241m.\u001b[39mis_closed:\n",
"File \u001b[0;32m~/anaconda3/envs/rapget/lib/python3.11/site-packages/openai/_base_client.py:1079\u001b[0m, in \u001b[0;36mSyncAPIClient._retry_request\u001b[0;34m(self, options, cast_to, remaining_retries, response_headers, stream, stream_cls)\u001b[0m\n\u001b[1;32m 1075\u001b[0m \u001b[38;5;66;03m# In a synchronous context we are blocking the entire thread. Up to the library user to run the client in a\u001b[39;00m\n\u001b[1;32m 1076\u001b[0m \u001b[38;5;66;03m# different thread if necessary.\u001b[39;00m\n\u001b[1;32m 1077\u001b[0m time\u001b[38;5;241m.\u001b[39msleep(timeout)\n\u001b[0;32m-> 1079\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_request\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 1080\u001b[0m \u001b[43m \u001b[49m\u001b[43moptions\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43moptions\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1081\u001b[0m \u001b[43m \u001b[49m\u001b[43mcast_to\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcast_to\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1082\u001b[0m \u001b[43m \u001b[49m\u001b[43mremaining_retries\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mremaining\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1083\u001b[0m \u001b[43m \u001b[49m\u001b[43mstream\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstream\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1084\u001b[0m \u001b[43m \u001b[49m\u001b[43mstream_cls\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstream_cls\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1085\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n",
"File \u001b[0;32m~/anaconda3/envs/rapget/lib/python3.11/site-packages/openai/_base_client.py:1046\u001b[0m, in \u001b[0;36mSyncAPIClient._request\u001b[0;34m(self, cast_to, options, remaining_retries, stream, stream_cls)\u001b[0m\n\u001b[1;32m 1043\u001b[0m err\u001b[38;5;241m.\u001b[39mresponse\u001b[38;5;241m.\u001b[39mread()\n\u001b[1;32m 1045\u001b[0m log\u001b[38;5;241m.\u001b[39mdebug(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mRe-raising status error\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[0;32m-> 1046\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_make_status_error_from_response(err\u001b[38;5;241m.\u001b[39mresponse) \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[1;32m 1048\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_process_response(\n\u001b[1;32m 1049\u001b[0m cast_to\u001b[38;5;241m=\u001b[39mcast_to,\n\u001b[1;32m 1050\u001b[0m options\u001b[38;5;241m=\u001b[39moptions,\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 1053\u001b[0m stream_cls\u001b[38;5;241m=\u001b[39mstream_cls,\n\u001b[1;32m 1054\u001b[0m )\n",
"\u001b[0;31mRateLimitError\u001b[0m: Error code: 429 - {'error': {'message': \"This fine-tune request has been rate-limited. Your organization has reached the maximum of 3 active requests (2 running, 1 pending) for the model 'gpt-4o-mini-2024-07-18'.\", 'type': 'invalid_request_error', 'param': None, 'code': 'rate_limit_exceeded'}}"
]
}
],
"source": [
"from openai import OpenAI\n",
"\n",
"client = OpenAI()\n",
"\n",
"jobs = []\n",
"for epoch in range(1, 6):\n",
" job = client.fine_tuning.jobs.create(\n",
" training_file=\"file-IokPHn4YWcniXL4wGnK4xVmn\",\n",
" model=\"gpt-4o-mini-2024-07-18\",\n",
" seed=1046194933,\n",
" hyperparameters={\n",
" \"n_epochs\": epoch,\n",
" \"batch_size\": 18,\n",
" \"learning_rate_multiplier\": 1.8,\n",
" },\n",
" integrations=[\n",
" {\n",
" \"type\": \"wandb\",\n",
" \"wandb\": {\n",
" \"project\": \"OpenAI\",\n",
" \"name\": f\"gpt-4o-mini-2024-07-18-{epoch}\",\n",
" },\n",
" },\n",
" ],\n",
" )\n",
" jobs.append(job)\n",
"\n",
"jobs"
]
},
{
"cell_type": "code",
"execution_count": 61,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"[FineTuningJob(id='ftjob-LtXA4cTshuV3CVogO2jmRkMb', created_at=1723294897, error=Error(code=None, message=None, param=None), fine_tuned_model=None, finished_at=None, hyperparameters=Hyperparameters(n_epochs=4, batch_size=18, learning_rate_multiplier=1.8), model='gpt-4o-mini-2024-07-18', object='fine_tuning.job', organization_id='org-RXHVnD8cqPvqTPdXgZ5rQdl3', result_files=[], seed=1046194933, status='validating_files', trained_tokens=None, training_file='file-IokPHn4YWcniXL4wGnK4xVmn', validation_file=None, estimated_finish=None, integrations=[FineTuningJobWandbIntegrationObject(type='wandb', wandb=FineTuningJobWandbIntegration(project='OpenAI', entity=None, name=None, tags=None, run_id='ftjob-LtXA4cTshuV3CVogO2jmRkMb'))], user_provided_suffix=None),\n",
" FineTuningJob(id='ftjob-ryBXC4G96hIWQ0M2csfwx42J', created_at=1723294900, error=Error(code=None, message=None, param=None), fine_tuned_model=None, finished_at=None, hyperparameters=Hyperparameters(n_epochs=5, batch_size=18, learning_rate_multiplier=1.8), model='gpt-4o-mini-2024-07-18', object='fine_tuning.job', organization_id='org-RXHVnD8cqPvqTPdXgZ5rQdl3', result_files=[], seed=1046194933, status='validating_files', trained_tokens=None, training_file='file-IokPHn4YWcniXL4wGnK4xVmn', validation_file=None, estimated_finish=None, integrations=[FineTuningJobWandbIntegrationObject(type='wandb', wandb=FineTuningJobWandbIntegration(project='OpenAI', entity=None, name=None, tags=None, run_id='ftjob-ryBXC4G96hIWQ0M2csfwx42J'))], user_provided_suffix=None)]"
]
},
"execution_count": 61,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"from openai import OpenAI\n",
"\n",
"client = OpenAI()\n",
"\n",
"jobs = []\n",
"for epoch in range(4, 6):\n",
" job = client.fine_tuning.jobs.create(\n",
" training_file=\"file-IokPHn4YWcniXL4wGnK4xVmn\",\n",
" model=\"gpt-4o-mini-2024-07-18\",\n",
" seed=1046194933,\n",
" hyperparameters={\n",
" \"n_epochs\": epoch,\n",
" \"batch_size\": 18,\n",
" \"learning_rate_multiplier\": 1.8,\n",
" },\n",
" integrations=[\n",
" {\n",
" \"type\": \"wandb\",\n",
" \"wandb\": {\n",
" \"project\": \"OpenAI\",\n",
" \"name\": f\"gpt-4o-mini-2024-07-18-{epoch}\",\n",
" },\n",
" },\n",
" ],\n",
" )\n",
" jobs.append(job)\n",
"\n",
"jobs"
]
},
{
"cell_type": "code",
"execution_count": 67,
"metadata": {},
"outputs": [],
"source": [
"fine_tuned_models = [\n",
" \"ft:gpt-4o-mini-2024-07-18:mastercard::9ufuULvy\",\n",
" \"ft:gpt-4o-mini-2024-07-18:mastercard::9ug0Gt3w\",\n",
" \"ft:gpt-4o-mini-2024-07-18:mastercard::9ug5PhpZ\",\n",
" \"ft:gpt-4o-mini-2024-07-18:mastercard::9ugPThQI\",\n",
" \"ft:gpt-4o-mini-2024-07-18:mastercard::9ugVLmcB\",\n",
" \"ft:gpt-4o-mini-2024-07-18:mastercard::9uaCEFTs\",\n",
"]"
]
},
{
"cell_type": "code",
"execution_count": 68,
"metadata": {},
"outputs": [],
"source": [
"from llm_toolkit.eval_openai import evaluate_model_with_num_shots"
]
},
{
"cell_type": "code",
"execution_count": 69,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Evaluating model: ft:gpt-4o-mini-2024-07-18:mastercard::9ufuULvy\n",
"loading train/test data files\n",
"DatasetDict({\n",
" train: Dataset({\n",
" features: ['chinese', 'english'],\n",
" num_rows: 4528\n",
" })\n",
" test: Dataset({\n",
" features: ['chinese', 'english'],\n",
" num_rows: 1133\n",
" })\n",
"})\n",
"--------------------------------------------------\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",
"*** Evaluating with num_shots: 0\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"100%|██████████| 1133/1133 [16:48<00:00, 1.12it/s]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"gpt-4o-mini/epochs-01 metrics: {'meteor': 0.3785370331806402, 'sacrebleu': {'score': 12.052844230027103, 'counts': [12818, 4623, 2153, 1081], 'totals': [29097, 27964, 26850, 25740], 'precisions': [44.05265147609719, 16.53196967529681, 8.018621973929237, 4.1996891996892], 'bp': 0.9631327655852462, 'sys_len': 29097, 'ref_len': 30190}, 'bleu_scores': {'bleu': 0.12052844230027103, 'precisions': [0.44052651476097193, 0.1653196967529681, 0.08018621973929237, 0.041996891996891994], 'brevity_penalty': 0.9631327655852462, 'length_ratio': 0.9637959589267969, 'translation_length': 29097, 'reference_length': 30190}, 'rouge_scores': {'rouge1': 0.4244007719128182, 'rouge2': 0.17601540674784633, 'rougeL': 0.3693615986543504, 'rougeLsum': 0.3696442718692141}, 'accuracy': 0.00088261253309797, 'correct_ids': [77]}\n",
"Evaluating model: ft:gpt-4o-mini-2024-07-18:mastercard::9ug0Gt3w\n",
"loading train/test data files\n",
"DatasetDict({\n",
" train: Dataset({\n",
" features: ['chinese', 'english'],\n",
" num_rows: 4528\n",
" })\n",
" test: Dataset({\n",
" features: ['chinese', 'english'],\n",
" num_rows: 1133\n",
" })\n",
"})\n",
"--------------------------------------------------\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",
"*** Evaluating with num_shots: 0\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"100%|██████████| 1133/1133 [17:56<00:00, 1.05it/s]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"gpt-4o-mini/epochs-02 metrics: {'meteor': 0.3785921332515917, 'sacrebleu': {'score': 12.033706874864837, 'counts': [12801, 4628, 2150, 1076], 'totals': [29076, 27943, 26830, 25722], 'precisions': [44.02600082542303, 16.562287513867517, 8.013417815877748, 4.183189487598165], 'bp': 0.9624112877781842, 'sys_len': 29076, 'ref_len': 30190}, 'bleu_scores': {'bleu': 0.12033706874864836, 'precisions': [0.4402600082542303, 0.16562287513867516, 0.08013417815877749, 0.04183189487598165], 'brevity_penalty': 0.9624112877781842, 'length_ratio': 0.9631003643590593, 'translation_length': 29076, 'reference_length': 30190}, 'rouge_scores': {'rouge1': 0.4235104923203792, 'rouge2': 0.1758318317686482, 'rougeL': 0.36922125683186846, 'rougeLsum': 0.3693808162149962}, 'accuracy': 0.00088261253309797, 'correct_ids': [77]}\n",
"Evaluating model: ft:gpt-4o-mini-2024-07-18:mastercard::9ug5PhpZ\n",
"loading train/test data files\n",
"DatasetDict({\n",
" train: Dataset({\n",
" features: ['chinese', 'english'],\n",
" num_rows: 4528\n",
" })\n",
" test: Dataset({\n",
" features: ['chinese', 'english'],\n",
" num_rows: 1133\n",
" })\n",
"})\n",
"--------------------------------------------------\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",
"*** Evaluating with num_shots: 0\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"100%|██████████| 1133/1133 [17:02<00:00, 1.11it/s]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"gpt-4o-mini/epochs-03 metrics: {'meteor': 0.37736228106121694, 'sacrebleu': {'score': 11.933111335430906, 'counts': [12779, 4601, 2124, 1061], 'totals': [29096, 27963, 26848, 25737], 'precisions': [43.920126477866376, 16.453885491542394, 7.911203814064362, 4.122469596301046], 'bp': 0.9630984208616785, 'sys_len': 29096, 'ref_len': 30190}, 'bleu_scores': {'bleu': 0.11933111335430906, 'precisions': [0.4392012647786637, 0.16453885491542394, 0.07911203814064362, 0.041224695963010455], 'brevity_penalty': 0.9630984208616785, 'length_ratio': 0.9637628353759523, 'translation_length': 29096, 'reference_length': 30190}, 'rouge_scores': {'rouge1': 0.4235319934194407, 'rouge2': 0.17493309683581332, 'rougeL': 0.3685697120399035, 'rougeLsum': 0.3689298428303013}, 'accuracy': 0.00088261253309797, 'correct_ids': [77]}\n",
"Evaluating model: ft:gpt-4o-mini-2024-07-18:mastercard::9ugPThQI\n",
"loading train/test data files\n",
"DatasetDict({\n",
" train: Dataset({\n",
" features: ['chinese', 'english'],\n",
" num_rows: 4528\n",
" })\n",
" test: Dataset({\n",
" features: ['chinese', 'english'],\n",
" num_rows: 1133\n",
" })\n",
"})\n",
"--------------------------------------------------\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",
"*** Evaluating with num_shots: 0\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"100%|██████████| 1133/1133 [18:35<00:00, 1.02it/s]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"gpt-4o-mini/epochs-04 metrics: {'meteor': 0.37818535038887346, 'sacrebleu': {'score': 11.933285526593995, 'counts': [12797, 4601, 2121, 1061], 'totals': [29110, 27977, 26861, 25749], 'precisions': [43.960838199931295, 16.445651785395146, 7.896206395889952, 4.120548370810517], 'bp': 0.9635791436286372, 'sys_len': 29110, 'ref_len': 30190}, 'bleu_scores': {'bleu': 0.11933285526593994, 'precisions': [0.43960838199931296, 0.16445651785395146, 0.07896206395889951, 0.041205483708105166], 'brevity_penalty': 0.9635791436286371, 'length_ratio': 0.9642265650877774, 'translation_length': 29110, 'reference_length': 30190}, 'rouge_scores': {'rouge1': 0.42372801674771476, 'rouge2': 0.17487358435014705, 'rougeL': 0.36931437347367646, 'rougeLsum': 0.36934766241132383}, 'accuracy': 0.00088261253309797, 'correct_ids': [77]}\n",
"Evaluating model: ft:gpt-4o-mini-2024-07-18:mastercard::9ugVLmcB\n",
"loading train/test data files\n",
"DatasetDict({\n",
" train: Dataset({\n",
" features: ['chinese', 'english'],\n",
" num_rows: 4528\n",
" })\n",
" test: Dataset({\n",
" features: ['chinese', 'english'],\n",
" num_rows: 1133\n",
" })\n",
"})\n",
"--------------------------------------------------\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",
"*** Evaluating with num_shots: 0\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
" 7%|▋ | 82/1133 [5:27:15<69:54:29, 239.46s/it]\n"
]
},
{
"ename": "KeyboardInterrupt",
"evalue": "",
"output_type": "error",
"traceback": [
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[0;31mKeyboardInterrupt\u001b[0m Traceback (most recent call last)",
"Cell \u001b[0;32mIn[69], line 3\u001b[0m\n\u001b[1;32m 1\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m i, model \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28menumerate\u001b[39m(fine_tuned_models):\n\u001b[1;32m 2\u001b[0m epoch \u001b[38;5;241m=\u001b[39m i \u001b[38;5;241m+\u001b[39m \u001b[38;5;241m1\u001b[39m\n\u001b[0;32m----> 3\u001b[0m \u001b[43mevaluate_model_with_num_shots\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 4\u001b[0m \u001b[43m \u001b[49m\u001b[43mmodel\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 5\u001b[0m \u001b[43m \u001b[49m\u001b[43mdata_path\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 6\u001b[0m \u001b[43m \u001b[49m\u001b[43mresults_path\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mresults/mac-results_few_shots_openai.csv\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[1;32m 7\u001b[0m \u001b[43m \u001b[49m\u001b[43mrange_num_shots\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43m[\u001b[49m\u001b[38;5;241;43m0\u001b[39;49m\u001b[43m]\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 8\u001b[0m \u001b[43m \u001b[49m\u001b[43mmax_new_tokens\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mmax_new_tokens\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 9\u001b[0m \u001b[43m \u001b[49m\u001b[43mresult_column_name\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;124;43mf\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mgpt-4o-mini/epochs-\u001b[39;49m\u001b[38;5;132;43;01m{\u001b[39;49;00m\u001b[43mepoch\u001b[49m\u001b[38;5;132;43;01m:\u001b[39;49;00m\u001b[38;5;124;43m02d\u001b[39;49m\u001b[38;5;132;43;01m}\u001b[39;49;00m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[1;32m 10\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n",
"File \u001b[0;32m~/code/engd/papers/rapget-translation/llm_toolkit/eval_openai.py:60\u001b[0m, in \u001b[0;36mevaluate_model_with_num_shots\u001b[0;34m(model_name, data_path, results_path, range_num_shots, max_new_tokens, result_column_name)\u001b[0m\n\u001b[1;32m 57\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m num_shots \u001b[38;5;129;01min\u001b[39;00m range_num_shots:\n\u001b[1;32m 58\u001b[0m \u001b[38;5;28mprint\u001b[39m(\u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m*** Evaluating with num_shots: \u001b[39m\u001b[38;5;132;01m{\u001b[39;00mnum_shots\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m\"\u001b[39m)\n\u001b[0;32m---> 60\u001b[0m predictions \u001b[38;5;241m=\u001b[39m \u001b[43meval_openai\u001b[49m\u001b[43m(\u001b[49m\u001b[43mnum_shots\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mdatasets\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mmax_new_tokens\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mmax_new_tokens\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 61\u001b[0m model_name_with_shorts \u001b[38;5;241m=\u001b[39m (\n\u001b[1;32m 62\u001b[0m result_column_name\n\u001b[1;32m 63\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m result_column_name\n\u001b[1;32m 64\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;132;01m{\u001b[39;00mmodel_name\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m/shots-\u001b[39m\u001b[38;5;132;01m{\u001b[39;00mnum_shots\u001b[38;5;132;01m:\u001b[39;00m\u001b[38;5;124m02d\u001b[39m\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 65\u001b[0m )\n\u001b[1;32m 67\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n",
"File \u001b[0;32m~/code/engd/papers/rapget-translation/llm_toolkit/translation_utils.py:505\u001b[0m, in \u001b[0;36meval_openai\u001b[0;34m(num_shots, datasets, model, max_new_tokens)\u001b[0m\n\u001b[1;32m 502\u001b[0m predictions \u001b[38;5;241m=\u001b[39m []\n\u001b[1;32m 504\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m i \u001b[38;5;129;01min\u001b[39;00m tqdm(\u001b[38;5;28mrange\u001b[39m(total)):\n\u001b[0;32m--> 505\u001b[0m output \u001b[38;5;241m=\u001b[39m \u001b[43mtranslate_via_openai\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 506\u001b[0m \u001b[43m \u001b[49m\u001b[43meval_dataset\u001b[49m\u001b[43m[\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mchinese\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m]\u001b[49m\u001b[43m[\u001b[49m\u001b[43mi\u001b[49m\u001b[43m]\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 507\u001b[0m \u001b[43m \u001b[49m\u001b[43mtranslation_prompt\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 508\u001b[0m \u001b[43m \u001b[49m\u001b[43mmodel\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mmodel\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 509\u001b[0m \u001b[43m \u001b[49m\u001b[43mmax_tokens\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mmax_new_tokens\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 510\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 511\u001b[0m predictions\u001b[38;5;241m.\u001b[39mappend(output)\n\u001b[1;32m 513\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m predictions\n",
"File \u001b[0;32m~/code/engd/papers/rapget-translation/llm_toolkit/translation_utils.py:489\u001b[0m, in \u001b[0;36mtranslate_via_openai\u001b[0;34m(text, translation_prompt, max_tokens, model, base_url)\u001b[0m\n\u001b[1;32m 475\u001b[0m prompt \u001b[38;5;241m=\u001b[39m ChatPromptTemplate\u001b[38;5;241m.\u001b[39mfrom_messages(\n\u001b[1;32m 476\u001b[0m [\n\u001b[1;32m 477\u001b[0m (\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 485\u001b[0m ]\n\u001b[1;32m 486\u001b[0m )\n\u001b[1;32m 488\u001b[0m chain \u001b[38;5;241m=\u001b[39m prompt \u001b[38;5;241m|\u001b[39m llm\n\u001b[0;32m--> 489\u001b[0m response \u001b[38;5;241m=\u001b[39m \u001b[43mchain\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43minvoke\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 490\u001b[0m \u001b[43m \u001b[49m\u001b[43m{\u001b[49m\n\u001b[1;32m 491\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43minput\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mtext\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 492\u001b[0m \u001b[43m \u001b[49m\u001b[43m}\u001b[49m\n\u001b[1;32m 493\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 495\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m response\u001b[38;5;241m.\u001b[39mcontent\n",
"File \u001b[0;32m~/anaconda3/envs/rapget/lib/python3.11/site-packages/langchain_core/runnables/base.py:2875\u001b[0m, in \u001b[0;36mRunnableSequence.invoke\u001b[0;34m(self, input, config, **kwargs)\u001b[0m\n\u001b[1;32m 2873\u001b[0m \u001b[38;5;28minput\u001b[39m \u001b[38;5;241m=\u001b[39m step\u001b[38;5;241m.\u001b[39minvoke(\u001b[38;5;28minput\u001b[39m, config, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n\u001b[1;32m 2874\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m-> 2875\u001b[0m \u001b[38;5;28minput\u001b[39m \u001b[38;5;241m=\u001b[39m \u001b[43mstep\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43minvoke\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;28;43minput\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mconfig\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 2876\u001b[0m \u001b[38;5;66;03m# finish the root run\u001b[39;00m\n\u001b[1;32m 2877\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mBaseException\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m e:\n",
"File \u001b[0;32m~/anaconda3/envs/rapget/lib/python3.11/site-packages/langchain_core/language_models/chat_models.py:274\u001b[0m, in \u001b[0;36mBaseChatModel.invoke\u001b[0;34m(self, input, config, stop, **kwargs)\u001b[0m\n\u001b[1;32m 263\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21minvoke\u001b[39m(\n\u001b[1;32m 264\u001b[0m \u001b[38;5;28mself\u001b[39m,\n\u001b[1;32m 265\u001b[0m \u001b[38;5;28minput\u001b[39m: LanguageModelInput,\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 269\u001b[0m \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs: Any,\n\u001b[1;32m 270\u001b[0m ) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m BaseMessage:\n\u001b[1;32m 271\u001b[0m config \u001b[38;5;241m=\u001b[39m ensure_config(config)\n\u001b[1;32m 272\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m cast(\n\u001b[1;32m 273\u001b[0m ChatGeneration,\n\u001b[0;32m--> 274\u001b[0m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mgenerate_prompt\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 275\u001b[0m \u001b[43m \u001b[49m\u001b[43m[\u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_convert_input\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;28;43minput\u001b[39;49m\u001b[43m)\u001b[49m\u001b[43m]\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 276\u001b[0m \u001b[43m \u001b[49m\u001b[43mstop\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstop\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 277\u001b[0m \u001b[43m \u001b[49m\u001b[43mcallbacks\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mconfig\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mget\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mcallbacks\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 278\u001b[0m \u001b[43m \u001b[49m\u001b[43mtags\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mconfig\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mget\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mtags\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 279\u001b[0m \u001b[43m \u001b[49m\u001b[43mmetadata\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mconfig\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mget\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mmetadata\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 280\u001b[0m \u001b[43m \u001b[49m\u001b[43mrun_name\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mconfig\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mget\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mrun_name\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 281\u001b[0m \u001b[43m \u001b[49m\u001b[43mrun_id\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mconfig\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mpop\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mrun_id\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mNone\u001b[39;49;00m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 282\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 283\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\u001b[38;5;241m.\u001b[39mgenerations[\u001b[38;5;241m0\u001b[39m][\u001b[38;5;241m0\u001b[39m],\n\u001b[1;32m 284\u001b[0m )\u001b[38;5;241m.\u001b[39mmessage\n",
"File \u001b[0;32m~/anaconda3/envs/rapget/lib/python3.11/site-packages/langchain_core/language_models/chat_models.py:714\u001b[0m, in \u001b[0;36mBaseChatModel.generate_prompt\u001b[0;34m(self, prompts, stop, callbacks, **kwargs)\u001b[0m\n\u001b[1;32m 706\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mgenerate_prompt\u001b[39m(\n\u001b[1;32m 707\u001b[0m \u001b[38;5;28mself\u001b[39m,\n\u001b[1;32m 708\u001b[0m prompts: List[PromptValue],\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 711\u001b[0m \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs: Any,\n\u001b[1;32m 712\u001b[0m ) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m LLMResult:\n\u001b[1;32m 713\u001b[0m prompt_messages \u001b[38;5;241m=\u001b[39m [p\u001b[38;5;241m.\u001b[39mto_messages() \u001b[38;5;28;01mfor\u001b[39;00m p \u001b[38;5;129;01min\u001b[39;00m prompts]\n\u001b[0;32m--> 714\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mgenerate\u001b[49m\u001b[43m(\u001b[49m\u001b[43mprompt_messages\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mstop\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstop\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mcallbacks\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcallbacks\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n",
"File \u001b[0;32m~/anaconda3/envs/rapget/lib/python3.11/site-packages/langchain_core/language_models/chat_models.py:571\u001b[0m, in \u001b[0;36mBaseChatModel.generate\u001b[0;34m(self, messages, stop, callbacks, tags, metadata, run_name, run_id, **kwargs)\u001b[0m\n\u001b[1;32m 569\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m run_managers:\n\u001b[1;32m 570\u001b[0m run_managers[i]\u001b[38;5;241m.\u001b[39mon_llm_error(e, response\u001b[38;5;241m=\u001b[39mLLMResult(generations\u001b[38;5;241m=\u001b[39m[]))\n\u001b[0;32m--> 571\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m e\n\u001b[1;32m 572\u001b[0m flattened_outputs \u001b[38;5;241m=\u001b[39m [\n\u001b[1;32m 573\u001b[0m LLMResult(generations\u001b[38;5;241m=\u001b[39m[res\u001b[38;5;241m.\u001b[39mgenerations], llm_output\u001b[38;5;241m=\u001b[39mres\u001b[38;5;241m.\u001b[39mllm_output) \u001b[38;5;66;03m# type: ignore[list-item]\u001b[39;00m\n\u001b[1;32m 574\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m res \u001b[38;5;129;01min\u001b[39;00m results\n\u001b[1;32m 575\u001b[0m ]\n\u001b[1;32m 576\u001b[0m llm_output \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_combine_llm_outputs([res\u001b[38;5;241m.\u001b[39mllm_output \u001b[38;5;28;01mfor\u001b[39;00m res \u001b[38;5;129;01min\u001b[39;00m results])\n",
"File \u001b[0;32m~/anaconda3/envs/rapget/lib/python3.11/site-packages/langchain_core/language_models/chat_models.py:561\u001b[0m, in \u001b[0;36mBaseChatModel.generate\u001b[0;34m(self, messages, stop, callbacks, tags, metadata, run_name, run_id, **kwargs)\u001b[0m\n\u001b[1;32m 558\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m i, m \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28menumerate\u001b[39m(messages):\n\u001b[1;32m 559\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m 560\u001b[0m results\u001b[38;5;241m.\u001b[39mappend(\n\u001b[0;32m--> 561\u001b[0m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_generate_with_cache\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 562\u001b[0m \u001b[43m \u001b[49m\u001b[43mm\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 563\u001b[0m \u001b[43m \u001b[49m\u001b[43mstop\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstop\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 564\u001b[0m \u001b[43m \u001b[49m\u001b[43mrun_manager\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mrun_managers\u001b[49m\u001b[43m[\u001b[49m\u001b[43mi\u001b[49m\u001b[43m]\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mif\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mrun_managers\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01melse\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mNone\u001b[39;49;00m\u001b[43m,\u001b[49m\n\u001b[1;32m 565\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 566\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 567\u001b[0m )\n\u001b[1;32m 568\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mBaseException\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[1;32m 569\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m run_managers:\n",
"File \u001b[0;32m~/anaconda3/envs/rapget/lib/python3.11/site-packages/langchain_core/language_models/chat_models.py:793\u001b[0m, in \u001b[0;36mBaseChatModel._generate_with_cache\u001b[0;34m(self, messages, stop, run_manager, **kwargs)\u001b[0m\n\u001b[1;32m 791\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m 792\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m inspect\u001b[38;5;241m.\u001b[39msignature(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_generate)\u001b[38;5;241m.\u001b[39mparameters\u001b[38;5;241m.\u001b[39mget(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mrun_manager\u001b[39m\u001b[38;5;124m\"\u001b[39m):\n\u001b[0;32m--> 793\u001b[0m result \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_generate\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 794\u001b[0m \u001b[43m \u001b[49m\u001b[43mmessages\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mstop\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstop\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mrun_manager\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mrun_manager\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\n\u001b[1;32m 795\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 796\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m 797\u001b[0m result \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_generate(messages, stop\u001b[38;5;241m=\u001b[39mstop, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n",
"File \u001b[0;32m~/anaconda3/envs/rapget/lib/python3.11/site-packages/langchain_openai/chat_models/base.py:549\u001b[0m, in \u001b[0;36mBaseChatOpenAI._generate\u001b[0;34m(self, messages, stop, run_manager, **kwargs)\u001b[0m\n\u001b[1;32m 547\u001b[0m message_dicts, params \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_create_message_dicts(messages, stop)\n\u001b[1;32m 548\u001b[0m params \u001b[38;5;241m=\u001b[39m {\u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mparams, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs}\n\u001b[0;32m--> 549\u001b[0m response \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mclient\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mcreate\u001b[49m\u001b[43m(\u001b[49m\u001b[43mmessages\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mmessage_dicts\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mparams\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 550\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_create_chat_result(response)\n",
"File \u001b[0;32m~/anaconda3/envs/rapget/lib/python3.11/site-packages/openai/_utils/_utils.py:277\u001b[0m, in \u001b[0;36mrequired_args.<locals>.inner.<locals>.wrapper\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m 275\u001b[0m msg \u001b[38;5;241m=\u001b[39m \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mMissing required argument: \u001b[39m\u001b[38;5;132;01m{\u001b[39;00mquote(missing[\u001b[38;5;241m0\u001b[39m])\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 276\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mTypeError\u001b[39;00m(msg)\n\u001b[0;32m--> 277\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mfunc\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n",
"File \u001b[0;32m~/anaconda3/envs/rapget/lib/python3.11/site-packages/openai/resources/chat/completions.py:646\u001b[0m, in \u001b[0;36mCompletions.create\u001b[0;34m(self, messages, model, frequency_penalty, function_call, functions, logit_bias, logprobs, max_tokens, n, parallel_tool_calls, presence_penalty, response_format, seed, service_tier, stop, stream, stream_options, temperature, tool_choice, tools, top_logprobs, top_p, user, extra_headers, extra_query, extra_body, timeout)\u001b[0m\n\u001b[1;32m 612\u001b[0m \u001b[38;5;129m@required_args\u001b[39m([\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mmessages\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mmodel\u001b[39m\u001b[38;5;124m\"\u001b[39m], [\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mmessages\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mmodel\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mstream\u001b[39m\u001b[38;5;124m\"\u001b[39m])\n\u001b[1;32m 613\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mcreate\u001b[39m(\n\u001b[1;32m 614\u001b[0m \u001b[38;5;28mself\u001b[39m,\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 644\u001b[0m timeout: \u001b[38;5;28mfloat\u001b[39m \u001b[38;5;241m|\u001b[39m httpx\u001b[38;5;241m.\u001b[39mTimeout \u001b[38;5;241m|\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;241m|\u001b[39m NotGiven \u001b[38;5;241m=\u001b[39m NOT_GIVEN,\n\u001b[1;32m 645\u001b[0m ) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m ChatCompletion \u001b[38;5;241m|\u001b[39m Stream[ChatCompletionChunk]:\n\u001b[0;32m--> 646\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_post\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 647\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43m/chat/completions\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[1;32m 648\u001b[0m \u001b[43m \u001b[49m\u001b[43mbody\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mmaybe_transform\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 649\u001b[0m \u001b[43m \u001b[49m\u001b[43m{\u001b[49m\n\u001b[1;32m 650\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mmessages\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mmessages\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 651\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mmodel\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mmodel\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 652\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mfrequency_penalty\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mfrequency_penalty\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 653\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mfunction_call\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mfunction_call\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 654\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mfunctions\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mfunctions\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 655\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mlogit_bias\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mlogit_bias\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 656\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mlogprobs\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mlogprobs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 657\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mmax_tokens\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mmax_tokens\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 658\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mn\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mn\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 659\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mparallel_tool_calls\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mparallel_tool_calls\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 660\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mpresence_penalty\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mpresence_penalty\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 661\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mresponse_format\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mresponse_format\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 662\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mseed\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mseed\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 663\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mservice_tier\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mservice_tier\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 664\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mstop\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mstop\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 665\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mstream\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mstream\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 666\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mstream_options\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mstream_options\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 667\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mtemperature\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mtemperature\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 668\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mtool_choice\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mtool_choice\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 669\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mtools\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mtools\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 670\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mtop_logprobs\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mtop_logprobs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 671\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mtop_p\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mtop_p\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 672\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43muser\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43muser\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 673\u001b[0m \u001b[43m \u001b[49m\u001b[43m}\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 674\u001b[0m \u001b[43m \u001b[49m\u001b[43mcompletion_create_params\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mCompletionCreateParams\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 675\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 676\u001b[0m \u001b[43m \u001b[49m\u001b[43moptions\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mmake_request_options\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 677\u001b[0m \u001b[43m \u001b[49m\u001b[43mextra_headers\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mextra_headers\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mextra_query\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mextra_query\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mextra_body\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mextra_body\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mtimeout\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mtimeout\u001b[49m\n\u001b[1;32m 678\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 679\u001b[0m \u001b[43m \u001b[49m\u001b[43mcast_to\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mChatCompletion\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 680\u001b[0m \u001b[43m \u001b[49m\u001b[43mstream\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstream\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;129;43;01mor\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mFalse\u001b[39;49;00m\u001b[43m,\u001b[49m\n\u001b[1;32m 681\u001b[0m \u001b[43m \u001b[49m\u001b[43mstream_cls\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mStream\u001b[49m\u001b[43m[\u001b[49m\u001b[43mChatCompletionChunk\u001b[49m\u001b[43m]\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 682\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n",
"File \u001b[0;32m~/anaconda3/envs/rapget/lib/python3.11/site-packages/openai/_base_client.py:1266\u001b[0m, in \u001b[0;36mSyncAPIClient.post\u001b[0;34m(self, path, cast_to, body, options, files, stream, stream_cls)\u001b[0m\n\u001b[1;32m 1252\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mpost\u001b[39m(\n\u001b[1;32m 1253\u001b[0m \u001b[38;5;28mself\u001b[39m,\n\u001b[1;32m 1254\u001b[0m path: \u001b[38;5;28mstr\u001b[39m,\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 1261\u001b[0m stream_cls: \u001b[38;5;28mtype\u001b[39m[_StreamT] \u001b[38;5;241m|\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m,\n\u001b[1;32m 1262\u001b[0m ) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m ResponseT \u001b[38;5;241m|\u001b[39m _StreamT:\n\u001b[1;32m 1263\u001b[0m opts \u001b[38;5;241m=\u001b[39m FinalRequestOptions\u001b[38;5;241m.\u001b[39mconstruct(\n\u001b[1;32m 1264\u001b[0m method\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mpost\u001b[39m\u001b[38;5;124m\"\u001b[39m, url\u001b[38;5;241m=\u001b[39mpath, json_data\u001b[38;5;241m=\u001b[39mbody, files\u001b[38;5;241m=\u001b[39mto_httpx_files(files), \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39moptions\n\u001b[1;32m 1265\u001b[0m )\n\u001b[0;32m-> 1266\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m cast(ResponseT, \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mrequest\u001b[49m\u001b[43m(\u001b[49m\u001b[43mcast_to\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mopts\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mstream\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstream\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mstream_cls\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstream_cls\u001b[49m\u001b[43m)\u001b[49m)\n",
"File \u001b[0;32m~/anaconda3/envs/rapget/lib/python3.11/site-packages/openai/_base_client.py:942\u001b[0m, in \u001b[0;36mSyncAPIClient.request\u001b[0;34m(self, cast_to, options, remaining_retries, stream, stream_cls)\u001b[0m\n\u001b[1;32m 933\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mrequest\u001b[39m(\n\u001b[1;32m 934\u001b[0m \u001b[38;5;28mself\u001b[39m,\n\u001b[1;32m 935\u001b[0m cast_to: Type[ResponseT],\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 940\u001b[0m stream_cls: \u001b[38;5;28mtype\u001b[39m[_StreamT] \u001b[38;5;241m|\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m,\n\u001b[1;32m 941\u001b[0m ) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m ResponseT \u001b[38;5;241m|\u001b[39m _StreamT:\n\u001b[0;32m--> 942\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_request\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 943\u001b[0m \u001b[43m \u001b[49m\u001b[43mcast_to\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcast_to\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 944\u001b[0m \u001b[43m \u001b[49m\u001b[43moptions\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43moptions\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 945\u001b[0m \u001b[43m \u001b[49m\u001b[43mstream\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstream\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 946\u001b[0m \u001b[43m \u001b[49m\u001b[43mstream_cls\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstream_cls\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 947\u001b[0m \u001b[43m \u001b[49m\u001b[43mremaining_retries\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mremaining_retries\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 948\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n",
"File \u001b[0;32m~/anaconda3/envs/rapget/lib/python3.11/site-packages/openai/_base_client.py:978\u001b[0m, in \u001b[0;36mSyncAPIClient._request\u001b[0;34m(self, cast_to, options, remaining_retries, stream, stream_cls)\u001b[0m\n\u001b[1;32m 975\u001b[0m log\u001b[38;5;241m.\u001b[39mdebug(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mSending HTTP Request: \u001b[39m\u001b[38;5;132;01m%s\u001b[39;00m\u001b[38;5;124m \u001b[39m\u001b[38;5;132;01m%s\u001b[39;00m\u001b[38;5;124m\"\u001b[39m, request\u001b[38;5;241m.\u001b[39mmethod, request\u001b[38;5;241m.\u001b[39murl)\n\u001b[1;32m 977\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m--> 978\u001b[0m response \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_client\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43msend\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 979\u001b[0m \u001b[43m \u001b[49m\u001b[43mrequest\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 980\u001b[0m \u001b[43m \u001b[49m\u001b[43mstream\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstream\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;129;43;01mor\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_should_stream_response_body\u001b[49m\u001b[43m(\u001b[49m\u001b[43mrequest\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mrequest\u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 981\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 982\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 983\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m httpx\u001b[38;5;241m.\u001b[39mTimeoutException \u001b[38;5;28;01mas\u001b[39;00m err:\n\u001b[1;32m 984\u001b[0m log\u001b[38;5;241m.\u001b[39mdebug(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mEncountered httpx.TimeoutException\u001b[39m\u001b[38;5;124m\"\u001b[39m, exc_info\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mTrue\u001b[39;00m)\n",
"File \u001b[0;32m~/anaconda3/envs/rapget/lib/python3.11/site-packages/httpx/_client.py:914\u001b[0m, in \u001b[0;36mClient.send\u001b[0;34m(self, request, stream, auth, follow_redirects)\u001b[0m\n\u001b[1;32m 906\u001b[0m follow_redirects \u001b[38;5;241m=\u001b[39m (\n\u001b[1;32m 907\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mfollow_redirects\n\u001b[1;32m 908\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(follow_redirects, UseClientDefault)\n\u001b[1;32m 909\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m follow_redirects\n\u001b[1;32m 910\u001b[0m )\n\u001b[1;32m 912\u001b[0m auth \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_build_request_auth(request, auth)\n\u001b[0;32m--> 914\u001b[0m response \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_send_handling_auth\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 915\u001b[0m \u001b[43m \u001b[49m\u001b[43mrequest\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 916\u001b[0m \u001b[43m \u001b[49m\u001b[43mauth\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mauth\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 917\u001b[0m \u001b[43m \u001b[49m\u001b[43mfollow_redirects\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mfollow_redirects\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 918\u001b[0m \u001b[43m \u001b[49m\u001b[43mhistory\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43m[\u001b[49m\u001b[43m]\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 919\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 920\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m 921\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m stream:\n",
"File \u001b[0;32m~/anaconda3/envs/rapget/lib/python3.11/site-packages/httpx/_client.py:942\u001b[0m, in \u001b[0;36mClient._send_handling_auth\u001b[0;34m(self, request, auth, follow_redirects, history)\u001b[0m\n\u001b[1;32m 939\u001b[0m request \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mnext\u001b[39m(auth_flow)\n\u001b[1;32m 941\u001b[0m \u001b[38;5;28;01mwhile\u001b[39;00m \u001b[38;5;28;01mTrue\u001b[39;00m:\n\u001b[0;32m--> 942\u001b[0m response \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_send_handling_redirects\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 943\u001b[0m \u001b[43m \u001b[49m\u001b[43mrequest\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 944\u001b[0m \u001b[43m \u001b[49m\u001b[43mfollow_redirects\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mfollow_redirects\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 945\u001b[0m \u001b[43m \u001b[49m\u001b[43mhistory\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mhistory\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 946\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 947\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m 948\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n",
"File \u001b[0;32m~/anaconda3/envs/rapget/lib/python3.11/site-packages/httpx/_client.py:979\u001b[0m, in \u001b[0;36mClient._send_handling_redirects\u001b[0;34m(self, request, follow_redirects, history)\u001b[0m\n\u001b[1;32m 976\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m hook \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_event_hooks[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mrequest\u001b[39m\u001b[38;5;124m\"\u001b[39m]:\n\u001b[1;32m 977\u001b[0m hook(request)\n\u001b[0;32m--> 979\u001b[0m response \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_send_single_request\u001b[49m\u001b[43m(\u001b[49m\u001b[43mrequest\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 980\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m 981\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m hook \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_event_hooks[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mresponse\u001b[39m\u001b[38;5;124m\"\u001b[39m]:\n",
"File \u001b[0;32m~/anaconda3/envs/rapget/lib/python3.11/site-packages/httpx/_client.py:1015\u001b[0m, in \u001b[0;36mClient._send_single_request\u001b[0;34m(self, request)\u001b[0m\n\u001b[1;32m 1010\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mRuntimeError\u001b[39;00m(\n\u001b[1;32m 1011\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mAttempted to send an async request with a sync Client instance.\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 1012\u001b[0m )\n\u001b[1;32m 1014\u001b[0m \u001b[38;5;28;01mwith\u001b[39;00m request_context(request\u001b[38;5;241m=\u001b[39mrequest):\n\u001b[0;32m-> 1015\u001b[0m response \u001b[38;5;241m=\u001b[39m \u001b[43mtransport\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mhandle_request\u001b[49m\u001b[43m(\u001b[49m\u001b[43mrequest\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 1017\u001b[0m \u001b[38;5;28;01massert\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(response\u001b[38;5;241m.\u001b[39mstream, SyncByteStream)\n\u001b[1;32m 1019\u001b[0m response\u001b[38;5;241m.\u001b[39mrequest \u001b[38;5;241m=\u001b[39m request\n",
"File \u001b[0;32m~/anaconda3/envs/rapget/lib/python3.11/site-packages/httpx/_transports/default.py:233\u001b[0m, in \u001b[0;36mHTTPTransport.handle_request\u001b[0;34m(self, request)\u001b[0m\n\u001b[1;32m 220\u001b[0m req \u001b[38;5;241m=\u001b[39m httpcore\u001b[38;5;241m.\u001b[39mRequest(\n\u001b[1;32m 221\u001b[0m method\u001b[38;5;241m=\u001b[39mrequest\u001b[38;5;241m.\u001b[39mmethod,\n\u001b[1;32m 222\u001b[0m url\u001b[38;5;241m=\u001b[39mhttpcore\u001b[38;5;241m.\u001b[39mURL(\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 230\u001b[0m extensions\u001b[38;5;241m=\u001b[39mrequest\u001b[38;5;241m.\u001b[39mextensions,\n\u001b[1;32m 231\u001b[0m )\n\u001b[1;32m 232\u001b[0m \u001b[38;5;28;01mwith\u001b[39;00m map_httpcore_exceptions():\n\u001b[0;32m--> 233\u001b[0m resp \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_pool\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mhandle_request\u001b[49m\u001b[43m(\u001b[49m\u001b[43mreq\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 235\u001b[0m \u001b[38;5;28;01massert\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(resp\u001b[38;5;241m.\u001b[39mstream, typing\u001b[38;5;241m.\u001b[39mIterable)\n\u001b[1;32m 237\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m Response(\n\u001b[1;32m 238\u001b[0m status_code\u001b[38;5;241m=\u001b[39mresp\u001b[38;5;241m.\u001b[39mstatus,\n\u001b[1;32m 239\u001b[0m headers\u001b[38;5;241m=\u001b[39mresp\u001b[38;5;241m.\u001b[39mheaders,\n\u001b[1;32m 240\u001b[0m stream\u001b[38;5;241m=\u001b[39mResponseStream(resp\u001b[38;5;241m.\u001b[39mstream),\n\u001b[1;32m 241\u001b[0m extensions\u001b[38;5;241m=\u001b[39mresp\u001b[38;5;241m.\u001b[39mextensions,\n\u001b[1;32m 242\u001b[0m )\n",
"File \u001b[0;32m~/anaconda3/envs/rapget/lib/python3.11/site-packages/httpcore/_sync/connection_pool.py:216\u001b[0m, in \u001b[0;36mConnectionPool.handle_request\u001b[0;34m(self, request)\u001b[0m\n\u001b[1;32m 213\u001b[0m closing \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_assign_requests_to_connections()\n\u001b[1;32m 215\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_close_connections(closing)\n\u001b[0;32m--> 216\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m exc \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[1;32m 218\u001b[0m \u001b[38;5;66;03m# Return the response. Note that in this case we still have to manage\u001b[39;00m\n\u001b[1;32m 219\u001b[0m \u001b[38;5;66;03m# the point at which the response is closed.\u001b[39;00m\n\u001b[1;32m 220\u001b[0m \u001b[38;5;28;01massert\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(response\u001b[38;5;241m.\u001b[39mstream, Iterable)\n",
"File \u001b[0;32m~/anaconda3/envs/rapget/lib/python3.11/site-packages/httpcore/_sync/connection_pool.py:196\u001b[0m, in \u001b[0;36mConnectionPool.handle_request\u001b[0;34m(self, request)\u001b[0m\n\u001b[1;32m 192\u001b[0m connection \u001b[38;5;241m=\u001b[39m pool_request\u001b[38;5;241m.\u001b[39mwait_for_connection(timeout\u001b[38;5;241m=\u001b[39mtimeout)\n\u001b[1;32m 194\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m 195\u001b[0m \u001b[38;5;66;03m# Send the request on the assigned connection.\u001b[39;00m\n\u001b[0;32m--> 196\u001b[0m response \u001b[38;5;241m=\u001b[39m \u001b[43mconnection\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mhandle_request\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 197\u001b[0m \u001b[43m \u001b[49m\u001b[43mpool_request\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mrequest\u001b[49m\n\u001b[1;32m 198\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 199\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m ConnectionNotAvailable:\n\u001b[1;32m 200\u001b[0m \u001b[38;5;66;03m# In some cases a connection may initially be available to\u001b[39;00m\n\u001b[1;32m 201\u001b[0m \u001b[38;5;66;03m# handle a request, but then become unavailable.\u001b[39;00m\n\u001b[1;32m 202\u001b[0m \u001b[38;5;66;03m#\u001b[39;00m\n\u001b[1;32m 203\u001b[0m \u001b[38;5;66;03m# In this case we clear the connection and try again.\u001b[39;00m\n\u001b[1;32m 204\u001b[0m pool_request\u001b[38;5;241m.\u001b[39mclear_connection()\n",
"File \u001b[0;32m~/anaconda3/envs/rapget/lib/python3.11/site-packages/httpcore/_sync/connection.py:101\u001b[0m, in \u001b[0;36mHTTPConnection.handle_request\u001b[0;34m(self, request)\u001b[0m\n\u001b[1;32m 98\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_connect_failed \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mTrue\u001b[39;00m\n\u001b[1;32m 99\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m exc\n\u001b[0;32m--> 101\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_connection\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mhandle_request\u001b[49m\u001b[43m(\u001b[49m\u001b[43mrequest\u001b[49m\u001b[43m)\u001b[49m\n",
"File \u001b[0;32m~/anaconda3/envs/rapget/lib/python3.11/site-packages/httpcore/_sync/http11.py:143\u001b[0m, in \u001b[0;36mHTTP11Connection.handle_request\u001b[0;34m(self, request)\u001b[0m\n\u001b[1;32m 141\u001b[0m \u001b[38;5;28;01mwith\u001b[39;00m Trace(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mresponse_closed\u001b[39m\u001b[38;5;124m\"\u001b[39m, logger, request) \u001b[38;5;28;01mas\u001b[39;00m trace:\n\u001b[1;32m 142\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_response_closed()\n\u001b[0;32m--> 143\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m exc\n",
"File \u001b[0;32m~/anaconda3/envs/rapget/lib/python3.11/site-packages/httpcore/_sync/http11.py:113\u001b[0m, in \u001b[0;36mHTTP11Connection.handle_request\u001b[0;34m(self, request)\u001b[0m\n\u001b[1;32m 102\u001b[0m \u001b[38;5;28;01mpass\u001b[39;00m\n\u001b[1;32m 104\u001b[0m \u001b[38;5;28;01mwith\u001b[39;00m Trace(\n\u001b[1;32m 105\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mreceive_response_headers\u001b[39m\u001b[38;5;124m\"\u001b[39m, logger, request, kwargs\n\u001b[1;32m 106\u001b[0m ) \u001b[38;5;28;01mas\u001b[39;00m trace:\n\u001b[1;32m 107\u001b[0m (\n\u001b[1;32m 108\u001b[0m http_version,\n\u001b[1;32m 109\u001b[0m status,\n\u001b[1;32m 110\u001b[0m reason_phrase,\n\u001b[1;32m 111\u001b[0m headers,\n\u001b[1;32m 112\u001b[0m trailing_data,\n\u001b[0;32m--> 113\u001b[0m ) \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_receive_response_headers\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 114\u001b[0m trace\u001b[38;5;241m.\u001b[39mreturn_value \u001b[38;5;241m=\u001b[39m (\n\u001b[1;32m 115\u001b[0m http_version,\n\u001b[1;32m 116\u001b[0m status,\n\u001b[1;32m 117\u001b[0m reason_phrase,\n\u001b[1;32m 118\u001b[0m headers,\n\u001b[1;32m 119\u001b[0m )\n\u001b[1;32m 121\u001b[0m network_stream \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_network_stream\n",
"File \u001b[0;32m~/anaconda3/envs/rapget/lib/python3.11/site-packages/httpcore/_sync/http11.py:186\u001b[0m, in \u001b[0;36mHTTP11Connection._receive_response_headers\u001b[0;34m(self, request)\u001b[0m\n\u001b[1;32m 183\u001b[0m timeout \u001b[38;5;241m=\u001b[39m timeouts\u001b[38;5;241m.\u001b[39mget(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mread\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;28;01mNone\u001b[39;00m)\n\u001b[1;32m 185\u001b[0m \u001b[38;5;28;01mwhile\u001b[39;00m \u001b[38;5;28;01mTrue\u001b[39;00m:\n\u001b[0;32m--> 186\u001b[0m event \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_receive_event\u001b[49m\u001b[43m(\u001b[49m\u001b[43mtimeout\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mtimeout\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 187\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(event, h11\u001b[38;5;241m.\u001b[39mResponse):\n\u001b[1;32m 188\u001b[0m \u001b[38;5;28;01mbreak\u001b[39;00m\n",
"File \u001b[0;32m~/anaconda3/envs/rapget/lib/python3.11/site-packages/httpcore/_sync/http11.py:224\u001b[0m, in \u001b[0;36mHTTP11Connection._receive_event\u001b[0;34m(self, timeout)\u001b[0m\n\u001b[1;32m 221\u001b[0m event \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_h11_state\u001b[38;5;241m.\u001b[39mnext_event()\n\u001b[1;32m 223\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m event \u001b[38;5;129;01mis\u001b[39;00m h11\u001b[38;5;241m.\u001b[39mNEED_DATA:\n\u001b[0;32m--> 224\u001b[0m data \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_network_stream\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mread\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 225\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mREAD_NUM_BYTES\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mtimeout\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mtimeout\u001b[49m\n\u001b[1;32m 226\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 228\u001b[0m \u001b[38;5;66;03m# If we feed this case through h11 we'll raise an exception like:\u001b[39;00m\n\u001b[1;32m 229\u001b[0m \u001b[38;5;66;03m#\u001b[39;00m\n\u001b[1;32m 230\u001b[0m \u001b[38;5;66;03m# httpcore.RemoteProtocolError: can't handle event type\u001b[39;00m\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 234\u001b[0m \u001b[38;5;66;03m# perspective. Instead we handle this case distinctly and treat\u001b[39;00m\n\u001b[1;32m 235\u001b[0m \u001b[38;5;66;03m# it as a ConnectError.\u001b[39;00m\n\u001b[1;32m 236\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m data \u001b[38;5;241m==\u001b[39m \u001b[38;5;124mb\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m\"\u001b[39m \u001b[38;5;129;01mand\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_h11_state\u001b[38;5;241m.\u001b[39mtheir_state \u001b[38;5;241m==\u001b[39m h11\u001b[38;5;241m.\u001b[39mSEND_RESPONSE:\n",
"File \u001b[0;32m~/anaconda3/envs/rapget/lib/python3.11/site-packages/httpcore/_backends/sync.py:126\u001b[0m, in \u001b[0;36mSyncStream.read\u001b[0;34m(self, max_bytes, timeout)\u001b[0m\n\u001b[1;32m 124\u001b[0m \u001b[38;5;28;01mwith\u001b[39;00m map_exceptions(exc_map):\n\u001b[1;32m 125\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_sock\u001b[38;5;241m.\u001b[39msettimeout(timeout)\n\u001b[0;32m--> 126\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_sock\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mrecv\u001b[49m\u001b[43m(\u001b[49m\u001b[43mmax_bytes\u001b[49m\u001b[43m)\u001b[49m\n",
"File \u001b[0;32m~/anaconda3/envs/rapget/lib/python3.11/ssl.py:1295\u001b[0m, in \u001b[0;36mSSLSocket.recv\u001b[0;34m(self, buflen, flags)\u001b[0m\n\u001b[1;32m 1291\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m flags \u001b[38;5;241m!=\u001b[39m \u001b[38;5;241m0\u001b[39m:\n\u001b[1;32m 1292\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mValueError\u001b[39;00m(\n\u001b[1;32m 1293\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mnon-zero flags not allowed in calls to recv() on \u001b[39m\u001b[38;5;132;01m%s\u001b[39;00m\u001b[38;5;124m\"\u001b[39m \u001b[38;5;241m%\u001b[39m\n\u001b[1;32m 1294\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m\u001b[38;5;18m__class__\u001b[39m)\n\u001b[0;32m-> 1295\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mread\u001b[49m\u001b[43m(\u001b[49m\u001b[43mbuflen\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 1296\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m 1297\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28msuper\u001b[39m()\u001b[38;5;241m.\u001b[39mrecv(buflen, flags)\n",
"File \u001b[0;32m~/anaconda3/envs/rapget/lib/python3.11/ssl.py:1168\u001b[0m, in \u001b[0;36mSSLSocket.read\u001b[0;34m(self, len, buffer)\u001b[0m\n\u001b[1;32m 1166\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_sslobj\u001b[38;5;241m.\u001b[39mread(\u001b[38;5;28mlen\u001b[39m, buffer)\n\u001b[1;32m 1167\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m-> 1168\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_sslobj\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mread\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;28;43mlen\u001b[39;49m\u001b[43m)\u001b[49m\n\u001b[1;32m 1169\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m SSLError \u001b[38;5;28;01mas\u001b[39;00m x:\n\u001b[1;32m 1170\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m x\u001b[38;5;241m.\u001b[39margs[\u001b[38;5;241m0\u001b[39m] \u001b[38;5;241m==\u001b[39m SSL_ERROR_EOF \u001b[38;5;129;01mand\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39msuppress_ragged_eofs:\n",
"\u001b[0;31mKeyboardInterrupt\u001b[0m: "
]
}
],
"source": [
"for i, model in enumerate(fine_tuned_models):\n",
" epoch = i + 1\n",
" evaluate_model_with_num_shots(\n",
" model,\n",
" data_path,\n",
" results_path=\"results/mac-results_few_shots_openai.csv\",\n",
" range_num_shots=[0],\n",
" max_new_tokens=max_new_tokens,\n",
" result_column_name=f\"gpt-4o-mini/epochs-{epoch:02d}\",\n",
" )"
]
},
{
"cell_type": "code",
"execution_count": 70,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Evaluating model: ft:gpt-4o-mini-2024-07-18:mastercard::9ugVLmcB\n",
"loading train/test data files\n",
"DatasetDict({\n",
" train: Dataset({\n",
" features: ['chinese', 'english'],\n",
" num_rows: 4528\n",
" })\n",
" test: Dataset({\n",
" features: ['chinese', 'english'],\n",
" num_rows: 1133\n",
" })\n",
"})\n",
"--------------------------------------------------\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",
"*** Evaluating with num_shots: 0\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"100%|██████████| 1133/1133 [15:47<00:00, 1.20it/s]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"gpt-4o-mini/epochs-05 metrics: {'meteor': 0.3790673551140706, 'sacrebleu': {'score': 11.955698498650582, 'counts': [12808, 4609, 2126, 1064], 'totals': [29209, 28076, 26959, 25846], 'precisions': [43.849498442260945, 16.416156147599374, 7.88604918580066, 4.116691170780778], 'bp': 0.9669721941455759, 'sys_len': 29209, 'ref_len': 30190}, 'bleu_scores': {'bleu': 0.11955698498650584, 'precisions': [0.4384949844226095, 0.16416156147599373, 0.0788604918580066, 0.041166911707807785], 'brevity_penalty': 0.9669721941455759, 'length_ratio': 0.9675057966213978, 'translation_length': 29209, 'reference_length': 30190}, 'rouge_scores': {'rouge1': 0.42476082012412075, 'rouge2': 0.17559955520032905, 'rougeL': 0.3700113513462385, 'rougeLsum': 0.37012014201963733}, 'accuracy': 0.00088261253309797, 'correct_ids': [77]}\n",
"Evaluating model: ft:gpt-4o-mini-2024-07-18:mastercard::9uaCEFTs\n",
"loading train/test data files\n",
"DatasetDict({\n",
" train: Dataset({\n",
" features: ['chinese', 'english'],\n",
" num_rows: 4528\n",
" })\n",
" test: Dataset({\n",
" features: ['chinese', 'english'],\n",
" num_rows: 1133\n",
" })\n",
"})\n",
"--------------------------------------------------\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",
"*** Evaluating with num_shots: 0\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"100%|██████████| 1133/1133 [15:43<00:00, 1.20it/s]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"gpt-4o-mini/epochs-06 metrics: {'meteor': 0.3792226866395673, 'sacrebleu': {'score': 11.982811850915233, 'counts': [12810, 4617, 2137, 1066], 'totals': [29116, 27983, 26868, 25757], 'precisions': [43.996428080780326, 16.499303148340065, 7.95369956825964, 4.138680746981403], 'bp': 0.9637850995333245, 'sys_len': 29116, 'ref_len': 30190}, 'bleu_scores': {'bleu': 0.11982811850915229, 'precisions': [0.43996428080780325, 0.16499303148340064, 0.0795369956825964, 0.04138680746981403], 'brevity_penalty': 0.9637850995333245, 'length_ratio': 0.9644253063928453, 'translation_length': 29116, 'reference_length': 30190}, 'rouge_scores': {'rouge1': 0.4251187202203103, 'rouge2': 0.17553224521896635, 'rougeL': 0.37003282393672954, 'rougeLsum': 0.370114181474168}, 'accuracy': 0.00088261253309797, 'correct_ids': [77]}\n"
]
}
],
"source": [
"for i, model in enumerate(fine_tuned_models):\n",
" epoch = i + 1\n",
" if epoch < 5:\n",
" continue\n",
"\n",
" evaluate_model_with_num_shots(\n",
" model,\n",
" data_path,\n",
" results_path=\"results/mac-results_few_shots_openai.csv\",\n",
" range_num_shots=[0],\n",
" max_new_tokens=max_new_tokens,\n",
" result_column_name=f\"gpt-4o-mini/epochs-{epoch:02d}\",\n",
" )"
]
}
],
"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
}
|