File size: 91,370 Bytes
9091c0d |
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 |
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"id": "b3b92bc7-d105-405f-970d-804d298b9976",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Collecting accelerate\n",
" Downloading accelerate-0.26.1-py3-none-any.whl.metadata (18 kB)\n",
"Collecting transformers\n",
" Downloading transformers-4.37.2-py3-none-any.whl.metadata (129 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m129.4/129.4 kB\u001b[0m \u001b[31m893.7 kB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0ma \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hCollecting einops\n",
" Downloading einops-0.7.0-py3-none-any.whl.metadata (13 kB)\n",
"Collecting datasets\n",
" Downloading datasets-2.16.1-py3-none-any.whl.metadata (20 kB)\n",
"Collecting peft\n",
" Downloading peft-0.8.2-py3-none-any.whl.metadata (25 kB)\n",
"Collecting bitsandbytes\n",
" Downloading bitsandbytes-0.42.0-py3-none-any.whl.metadata (9.9 kB)\n",
"Requirement already satisfied: numpy>=1.17 in /usr/local/lib/python3.11/site-packages (from accelerate) (1.26.4)\n",
"Requirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.11/site-packages (from accelerate) (23.2)\n",
"Requirement already satisfied: psutil in /usr/local/lib/python3.11/site-packages (from accelerate) (5.9.8)\n",
"Requirement already satisfied: pyyaml in /usr/local/lib/python3.11/site-packages (from accelerate) (6.0.1)\n",
"Collecting torch>=1.10.0 (from accelerate)\n",
" Downloading torch-2.2.0-cp311-cp311-manylinux1_x86_64.whl.metadata (25 kB)\n",
"Collecting huggingface-hub (from accelerate)\n",
" Downloading huggingface_hub-0.20.3-py3-none-any.whl.metadata (12 kB)\n",
"Collecting safetensors>=0.3.1 (from accelerate)\n",
" Downloading safetensors-0.4.2-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (3.8 kB)\n",
"Collecting filelock (from transformers)\n",
" Downloading filelock-3.13.1-py3-none-any.whl.metadata (2.8 kB)\n",
"Collecting regex!=2019.12.17 (from transformers)\n",
" Downloading regex-2023.12.25-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (40 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m40.9/40.9 kB\u001b[0m \u001b[31m121.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hRequirement already satisfied: requests in /usr/local/lib/python3.11/site-packages (from transformers) (2.31.0)\n",
"Collecting tokenizers<0.19,>=0.14 (from transformers)\n",
" Downloading tokenizers-0.15.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (6.7 kB)\n",
"Collecting tqdm>=4.27 (from transformers)\n",
" Downloading tqdm-4.66.1-py3-none-any.whl.metadata (57 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m57.6/57.6 kB\u001b[0m \u001b[31m47.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hCollecting pyarrow>=8.0.0 (from datasets)\n",
" Downloading pyarrow-15.0.0-cp311-cp311-manylinux_2_28_x86_64.whl.metadata (3.0 kB)\n",
"Collecting pyarrow-hotfix (from datasets)\n",
" Downloading pyarrow_hotfix-0.6-py3-none-any.whl.metadata (3.6 kB)\n",
"Collecting dill<0.3.8,>=0.3.0 (from datasets)\n",
" Downloading dill-0.3.7-py3-none-any.whl.metadata (9.9 kB)\n",
"Collecting pandas (from datasets)\n",
" Downloading pandas-2.2.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (19 kB)\n",
"Collecting xxhash (from datasets)\n",
" Downloading xxhash-3.4.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (12 kB)\n",
"Collecting multiprocess (from datasets)\n",
" Downloading multiprocess-0.70.16-py311-none-any.whl.metadata (7.2 kB)\n",
"Collecting fsspec<=2023.10.0,>=2023.1.0 (from fsspec[http]<=2023.10.0,>=2023.1.0->datasets)\n",
" Downloading fsspec-2023.10.0-py3-none-any.whl.metadata (6.8 kB)\n",
"Requirement already satisfied: aiohttp in /usr/local/lib/python3.11/site-packages (from datasets) (3.8.3)\n",
"Collecting scipy (from bitsandbytes)\n",
" Downloading scipy-1.12.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (60 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m60.4/60.4 kB\u001b[0m \u001b[31m54.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hRequirement already satisfied: attrs>=17.3.0 in /usr/local/lib/python3.11/site-packages (from aiohttp->datasets) (23.2.0)\n",
"Requirement already satisfied: charset-normalizer<3.0,>=2.0 in /usr/local/lib/python3.11/site-packages (from aiohttp->datasets) (2.1.1)\n",
"Requirement already satisfied: multidict<7.0,>=4.5 in /usr/local/lib/python3.11/site-packages (from aiohttp->datasets) (6.0.5)\n",
"Requirement already satisfied: async-timeout<5.0,>=4.0.0a3 in /usr/local/lib/python3.11/site-packages (from aiohttp->datasets) (4.0.3)\n",
"Requirement already satisfied: yarl<2.0,>=1.0 in /usr/local/lib/python3.11/site-packages (from aiohttp->datasets) (1.9.4)\n",
"Requirement already satisfied: frozenlist>=1.1.1 in /usr/local/lib/python3.11/site-packages (from aiohttp->datasets) (1.4.1)\n",
"Requirement already satisfied: aiosignal>=1.1.2 in /usr/local/lib/python3.11/site-packages (from aiohttp->datasets) (1.3.1)\n",
"Requirement already satisfied: typing-extensions>=3.7.4.3 in /usr/local/lib/python3.11/site-packages (from huggingface-hub->accelerate) (4.9.0)\n",
"Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.11/site-packages (from requests->transformers) (3.6)\n",
"Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.11/site-packages (from requests->transformers) (2.2.0)\n",
"Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.11/site-packages (from requests->transformers) (2024.2.2)\n",
"Collecting sympy (from torch>=1.10.0->accelerate)\n",
" Downloading sympy-1.12-py3-none-any.whl (5.7 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m5.7/5.7 MB\u001b[0m \u001b[31m32.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0ma \u001b[36m0:00:01\u001b[0m\n",
"\u001b[?25hCollecting networkx (from torch>=1.10.0->accelerate)\n",
" Downloading networkx-3.2.1-py3-none-any.whl.metadata (5.2 kB)\n",
"Requirement already satisfied: jinja2 in /usr/local/lib/python3.11/site-packages (from torch>=1.10.0->accelerate) (3.1.3)\n",
"Collecting nvidia-cuda-nvrtc-cu12==12.1.105 (from torch>=1.10.0->accelerate)\n",
" Downloading nvidia_cuda_nvrtc_cu12-12.1.105-py3-none-manylinux1_x86_64.whl (23.7 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m23.7/23.7 MB\u001b[0m \u001b[31m61.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m00:01\u001b[0m00:01\u001b[0m\n",
"\u001b[?25hCollecting nvidia-cuda-runtime-cu12==12.1.105 (from torch>=1.10.0->accelerate)\n",
" Downloading nvidia_cuda_runtime_cu12-12.1.105-py3-none-manylinux1_x86_64.whl (823 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m823.6/823.6 kB\u001b[0m \u001b[31m93.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hCollecting nvidia-cuda-cupti-cu12==12.1.105 (from torch>=1.10.0->accelerate)\n",
" Downloading nvidia_cuda_cupti_cu12-12.1.105-py3-none-manylinux1_x86_64.whl (14.1 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m14.1/14.1 MB\u001b[0m \u001b[31m44.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0ma \u001b[36m0:00:01\u001b[0m\n",
"\u001b[?25hCollecting nvidia-cudnn-cu12==8.9.2.26 (from torch>=1.10.0->accelerate)\n",
" Downloading nvidia_cudnn_cu12-8.9.2.26-py3-none-manylinux1_x86_64.whl.metadata (1.6 kB)\n",
"Collecting nvidia-cublas-cu12==12.1.3.1 (from torch>=1.10.0->accelerate)\n",
" Downloading nvidia_cublas_cu12-12.1.3.1-py3-none-manylinux1_x86_64.whl (410.6 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m410.6/410.6 MB\u001b[0m \u001b[31m59.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m00:01\u001b[0m00:01\u001b[0m\n",
"\u001b[?25hCollecting nvidia-cufft-cu12==11.0.2.54 (from torch>=1.10.0->accelerate)\n",
" Downloading nvidia_cufft_cu12-11.0.2.54-py3-none-manylinux1_x86_64.whl (121.6 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m121.6/121.6 MB\u001b[0m \u001b[31m59.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m00:01\u001b[0m00:01\u001b[0m\n",
"\u001b[?25hCollecting nvidia-curand-cu12==10.3.2.106 (from torch>=1.10.0->accelerate)\n",
" Downloading nvidia_curand_cu12-10.3.2.106-py3-none-manylinux1_x86_64.whl (56.5 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m56.5/56.5 MB\u001b[0m \u001b[31m60.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m00:01\u001b[0m00:01\u001b[0m\n",
"\u001b[?25hCollecting nvidia-cusolver-cu12==11.4.5.107 (from torch>=1.10.0->accelerate)\n",
" Downloading nvidia_cusolver_cu12-11.4.5.107-py3-none-manylinux1_x86_64.whl (124.2 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m124.2/124.2 MB\u001b[0m \u001b[31m50.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m00:01\u001b[0m00:01\u001b[0m\n",
"\u001b[?25hCollecting nvidia-cusparse-cu12==12.1.0.106 (from torch>=1.10.0->accelerate)\n",
" Downloading nvidia_cusparse_cu12-12.1.0.106-py3-none-manylinux1_x86_64.whl (196.0 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m196.0/196.0 MB\u001b[0m \u001b[31m40.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m00:01\u001b[0m00:01\u001b[0m\n",
"\u001b[?25hCollecting nvidia-nccl-cu12==2.19.3 (from torch>=1.10.0->accelerate)\n",
" Downloading nvidia_nccl_cu12-2.19.3-py3-none-manylinux1_x86_64.whl.metadata (1.8 kB)\n",
"Collecting nvidia-nvtx-cu12==12.1.105 (from torch>=1.10.0->accelerate)\n",
" Downloading nvidia_nvtx_cu12-12.1.105-py3-none-manylinux1_x86_64.whl (99 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m99.1/99.1 kB\u001b[0m \u001b[31m60.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hCollecting triton==2.2.0 (from torch>=1.10.0->accelerate)\n",
" Downloading triton-2.2.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (1.4 kB)\n",
"Collecting nvidia-nvjitlink-cu12 (from nvidia-cusolver-cu12==11.4.5.107->torch>=1.10.0->accelerate)\n",
" Downloading nvidia_nvjitlink_cu12-12.3.101-py3-none-manylinux1_x86_64.whl.metadata (1.5 kB)\n",
"INFO: pip is looking at multiple versions of multiprocess to determine which version is compatible with other requirements. This could take a while.\n",
"Collecting multiprocess (from datasets)\n",
" Downloading multiprocess-0.70.15-py311-none-any.whl.metadata (7.2 kB)\n",
"Requirement already satisfied: python-dateutil>=2.8.2 in /usr/local/lib/python3.11/site-packages (from pandas->datasets) (2.8.2)\n",
"Collecting pytz>=2020.1 (from pandas->datasets)\n",
" Downloading pytz-2024.1-py2.py3-none-any.whl.metadata (22 kB)\n",
"Collecting tzdata>=2022.7 (from pandas->datasets)\n",
" Downloading tzdata-2023.4-py2.py3-none-any.whl.metadata (1.4 kB)\n",
"Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.11/site-packages (from python-dateutil>=2.8.2->pandas->datasets) (1.16.0)\n",
"Requirement already satisfied: MarkupSafe>=2.0 in /usr/local/lib/python3.11/site-packages (from jinja2->torch>=1.10.0->accelerate) (2.1.5)\n",
"Collecting mpmath>=0.19 (from sympy->torch>=1.10.0->accelerate)\n",
" Downloading mpmath-1.3.0-py3-none-any.whl (536 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m536.2/536.2 kB\u001b[0m \u001b[31m73.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading accelerate-0.26.1-py3-none-any.whl (270 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m270.9/270.9 kB\u001b[0m \u001b[31m105.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading transformers-4.37.2-py3-none-any.whl (8.4 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m8.4/8.4 MB\u001b[0m \u001b[31m41.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0ma \u001b[36m0:00:01\u001b[0m\n",
"\u001b[?25hDownloading einops-0.7.0-py3-none-any.whl (44 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m44.6/44.6 kB\u001b[0m \u001b[31m139.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading datasets-2.16.1-py3-none-any.whl (507 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m507.1/507.1 kB\u001b[0m \u001b[31m77.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading peft-0.8.2-py3-none-any.whl (183 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m183.4/183.4 kB\u001b[0m \u001b[31m101.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading bitsandbytes-0.42.0-py3-none-any.whl (105.0 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m105.0/105.0 MB\u001b[0m \u001b[31m33.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m00:01\u001b[0m00:01\u001b[0m\n",
"\u001b[?25hDownloading dill-0.3.7-py3-none-any.whl (115 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m115.3/115.3 kB\u001b[0m \u001b[31m97.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading fsspec-2023.10.0-py3-none-any.whl (166 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m166.4/166.4 kB\u001b[0m \u001b[31m197.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading huggingface_hub-0.20.3-py3-none-any.whl (330 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m330.1/330.1 kB\u001b[0m \u001b[31m52.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading pyarrow-15.0.0-cp311-cp311-manylinux_2_28_x86_64.whl (38.3 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m38.3/38.3 MB\u001b[0m \u001b[31m33.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m00:01\u001b[0m00:01\u001b[0m\n",
"\u001b[?25hDownloading regex-2023.12.25-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (785 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m785.1/785.1 kB\u001b[0m \u001b[31m50.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading safetensors-0.4.2-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (1.3 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.3/1.3 MB\u001b[0m \u001b[31m38.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading tokenizers-0.15.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (3.6 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m3.6/3.6 MB\u001b[0m \u001b[31m36.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0ma \u001b[36m0:00:01\u001b[0m\n",
"\u001b[?25hDownloading torch-2.2.0-cp311-cp311-manylinux1_x86_64.whl (755.5 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m755.5/755.5 MB\u001b[0m \u001b[31m10.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m00:01\u001b[0m0:03\u001b[0mm\n",
"\u001b[?25hDownloading nvidia_cudnn_cu12-8.9.2.26-py3-none-manylinux1_x86_64.whl (731.7 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m731.7/731.7 MB\u001b[0m \u001b[31m28.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m00:01\u001b[0m00:01\u001b[0m\n",
"\u001b[?25hDownloading nvidia_nccl_cu12-2.19.3-py3-none-manylinux1_x86_64.whl (166.0 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m166.0/166.0 MB\u001b[0m \u001b[31m33.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m00:01\u001b[0m00:01\u001b[0m\n",
"\u001b[?25hDownloading triton-2.2.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (167.9 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m167.9/167.9 MB\u001b[0m \u001b[31m26.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m00:01\u001b[0m00:01\u001b[0m\n",
"\u001b[?25hDownloading tqdm-4.66.1-py3-none-any.whl (78 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m78.3/78.3 kB\u001b[0m \u001b[31m77.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading filelock-3.13.1-py3-none-any.whl (11 kB)\n",
"Downloading multiprocess-0.70.15-py311-none-any.whl (135 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m135.4/135.4 kB\u001b[0m \u001b[31m77.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading pandas-2.2.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (13.0 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m13.0/13.0 MB\u001b[0m \u001b[31m28.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0ma \u001b[36m0:00:01\u001b[0m\n",
"\u001b[?25hDownloading pyarrow_hotfix-0.6-py3-none-any.whl (7.9 kB)\n",
"Downloading scipy-1.12.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (38.4 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m38.4/38.4 MB\u001b[0m \u001b[31m28.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m00:01\u001b[0m00:01\u001b[0m\n",
"\u001b[?25hDownloading xxhash-3.4.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (194 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m194.8/194.8 kB\u001b[0m \u001b[31m92.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading pytz-2024.1-py2.py3-none-any.whl (505 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m505.5/505.5 kB\u001b[0m \u001b[31m49.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading tzdata-2023.4-py2.py3-none-any.whl (346 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m346.6/346.6 kB\u001b[0m \u001b[31m100.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading networkx-3.2.1-py3-none-any.whl (1.6 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.6/1.6 MB\u001b[0m \u001b[31m34.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0ma \u001b[36m0:00:01\u001b[0m\n",
"\u001b[?25hDownloading nvidia_nvjitlink_cu12-12.3.101-py3-none-manylinux1_x86_64.whl (20.5 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m20.5/20.5 MB\u001b[0m \u001b[31m22.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m00:01\u001b[0m00:01\u001b[0m\n",
"\u001b[?25hInstalling collected packages: pytz, mpmath, xxhash, tzdata, tqdm, sympy, scipy, safetensors, regex, pyarrow-hotfix, pyarrow, nvidia-nvtx-cu12, nvidia-nvjitlink-cu12, nvidia-nccl-cu12, nvidia-curand-cu12, nvidia-cufft-cu12, nvidia-cuda-runtime-cu12, nvidia-cuda-nvrtc-cu12, nvidia-cuda-cupti-cu12, nvidia-cublas-cu12, networkx, fsspec, filelock, einops, dill, triton, pandas, nvidia-cusparse-cu12, nvidia-cudnn-cu12, multiprocess, huggingface-hub, bitsandbytes, tokenizers, nvidia-cusolver-cu12, transformers, torch, datasets, accelerate, peft\n",
"Successfully installed accelerate-0.26.1 bitsandbytes-0.42.0 datasets-2.16.1 dill-0.3.7 einops-0.7.0 filelock-3.13.1 fsspec-2023.10.0 huggingface-hub-0.20.3 mpmath-1.3.0 multiprocess-0.70.15 networkx-3.2.1 nvidia-cublas-cu12-12.1.3.1 nvidia-cuda-cupti-cu12-12.1.105 nvidia-cuda-nvrtc-cu12-12.1.105 nvidia-cuda-runtime-cu12-12.1.105 nvidia-cudnn-cu12-8.9.2.26 nvidia-cufft-cu12-11.0.2.54 nvidia-curand-cu12-10.3.2.106 nvidia-cusolver-cu12-11.4.5.107 nvidia-cusparse-cu12-12.1.0.106 nvidia-nccl-cu12-2.19.3 nvidia-nvjitlink-cu12-12.3.101 nvidia-nvtx-cu12-12.1.105 pandas-2.2.0 peft-0.8.2 pyarrow-15.0.0 pyarrow-hotfix-0.6 pytz-2024.1 regex-2023.12.25 safetensors-0.4.2 scipy-1.12.0 sympy-1.12 tokenizers-0.15.1 torch-2.2.0 tqdm-4.66.1 transformers-4.37.2 triton-2.2.0 tzdata-2023.4 xxhash-3.4.1\n"
]
}
],
"source": [
"!pip install accelerate transformers einops datasets peft bitsandbytes"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "46a53303-b585-4b02-956f-4af173410e25",
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"/usr/local/lib/python3.11/site-packages/tqdm/auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
" from .autonotebook import tqdm as notebook_tqdm\n"
]
}
],
"source": [
"import torch\n",
"from datasets import load_dataset, Dataset\n",
"from transformers import AutoModelForCausalLM, AutoTokenizer, TrainingArguments, Trainer, DataCollatorForLanguageModeling, BitsAndBytesConfig\n",
"from peft import LoraConfig, get_peft_model\n",
"import os"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "ffa3ee11-3929-4032-8758-322cda3a912e",
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"tokenizer_config.json: 100%|██████████| 7.34k/7.34k [00:00<00:00, 13.7MB/s]\n",
"vocab.json: 100%|██████████| 798k/798k [00:00<00:00, 17.5MB/s]\n",
"merges.txt: 100%|██████████| 456k/456k [00:00<00:00, 43.7MB/s]\n",
"tokenizer.json: 100%|██████████| 2.11M/2.11M [00:00<00:00, 16.5MB/s]\n",
"added_tokens.json: 100%|██████████| 1.08k/1.08k [00:00<00:00, 2.35MB/s]\n",
"special_tokens_map.json: 100%|██████████| 99.0/99.0 [00:00<00:00, 269kB/s]\n",
"Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.\n"
]
}
],
"source": [
"tokenizer = AutoTokenizer.from_pretrained(\"microsoft/phi-2\", trust_remote_code=True)\n",
"tokenizer.pad_token = tokenizer.eos_token"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "b17096e6-c633-4d88-8cfc-fb738c1e4ca0",
"metadata": {
"scrolled": true
},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"config.json: 100%|██████████| 863/863 [00:00<00:00, 2.00MB/s]\n",
"configuration_phi.py: 100%|██████████| 9.26k/9.26k [00:00<00:00, 11.4MB/s]\n",
"A new version of the following files was downloaded from https://huggingface.co/microsoft/phi-2:\n",
"- configuration_phi.py\n",
". Make sure to double-check they do not contain any added malicious code. To avoid downloading new versions of the code file, you can pin a revision.\n",
"modeling_phi.py: 100%|██████████| 62.7k/62.7k [00:00<00:00, 48.8MB/s]\n",
"A new version of the following files was downloaded from https://huggingface.co/microsoft/phi-2:\n",
"- modeling_phi.py\n",
". Make sure to double-check they do not contain any added malicious code. To avoid downloading new versions of the code file, you can pin a revision.\n",
"model.safetensors.index.json: 100%|██████████| 35.7k/35.7k [00:00<00:00, 33.7MB/s]\n",
"Downloading shards: 0%| | 0/2 [00:00<?, ?it/s]\n",
"model-00001-of-00002.safetensors: 0%| | 0.00/5.00G [00:00<?, ?B/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 0%| | 10.5M/5.00G [00:00<00:55, 90.4MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 1%| | 31.5M/5.00G [00:00<00:41, 119MB/s] \u001b[A\n",
"model-00001-of-00002.safetensors: 1%| | 52.4M/5.00G [00:00<00:37, 133MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 1%|▏ | 73.4M/5.00G [00:00<00:35, 140MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 2%|▏ | 94.4M/5.00G [00:00<00:34, 143MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 2%|▏ | 115M/5.00G [00:00<00:33, 146MB/s] \u001b[A\n",
"model-00001-of-00002.safetensors: 3%|▎ | 136M/5.00G [00:00<00:34, 142MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 3%|▎ | 157M/5.00G [00:01<00:35, 135MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 4%|▎ | 178M/5.00G [00:01<00:35, 136MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 4%|▍ | 199M/5.00G [00:01<00:35, 135MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 4%|▍ | 220M/5.00G [00:01<00:35, 136MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 5%|▍ | 241M/5.00G [00:01<00:34, 136MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 5%|▌ | 262M/5.00G [00:01<00:34, 135MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 6%|▌ | 283M/5.00G [00:02<00:37, 124MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 6%|▌ | 304M/5.00G [00:02<00:37, 127MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 7%|▋ | 325M/5.00G [00:02<00:36, 129MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 7%|▋ | 346M/5.00G [00:02<00:35, 133MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 7%|▋ | 367M/5.00G [00:02<00:34, 135MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 8%|▊ | 388M/5.00G [00:02<00:33, 139MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 8%|▊ | 409M/5.00G [00:03<00:32, 141MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 9%|▊ | 430M/5.00G [00:03<00:32, 139MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 9%|▉ | 451M/5.00G [00:03<00:32, 138MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 9%|▉ | 472M/5.00G [00:03<00:33, 136MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 10%|▉ | 493M/5.00G [00:03<00:32, 138MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 10%|█ | 514M/5.00G [00:03<00:31, 140MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 11%|█ | 535M/5.00G [00:03<00:31, 140MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 11%|█ | 556M/5.00G [00:04<00:31, 140MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 12%|█▏ | 577M/5.00G [00:04<00:31, 138MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 12%|█▏ | 598M/5.00G [00:04<00:31, 137MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 12%|█▏ | 619M/5.00G [00:04<00:31, 139MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 13%|█▎ | 640M/5.00G [00:04<00:32, 136MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 13%|█▎ | 661M/5.00G [00:04<00:31, 139MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 14%|█▎ | 682M/5.00G [00:05<00:31, 138MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 14%|█▍ | 703M/5.00G [00:05<00:32, 131MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 14%|█▍ | 724M/5.00G [00:05<00:32, 132MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 15%|█▍ | 744M/5.00G [00:05<00:31, 135MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 15%|█▌ | 765M/5.00G [00:05<00:31, 136MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 16%|█▌ | 786M/5.00G [00:05<00:31, 133MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 16%|█▌ | 807M/5.00G [00:05<00:31, 135MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 17%|█▋ | 828M/5.00G [00:06<00:30, 138MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 17%|█▋ | 849M/5.00G [00:06<00:31, 133MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 17%|█▋ | 870M/5.00G [00:06<00:30, 136MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 18%|█▊ | 891M/5.00G [00:06<00:29, 138MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 18%|█▊ | 912M/5.00G [00:06<00:29, 139MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 19%|█▊ | 933M/5.00G [00:06<00:28, 141MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 19%|█▉ | 954M/5.00G [00:07<00:28, 140MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 20%|█▉ | 975M/5.00G [00:07<00:29, 136MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 20%|█▉ | 996M/5.00G [00:07<00:29, 136MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 20%|██ | 1.02G/5.00G [00:07<00:28, 139MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 21%|██ | 1.04G/5.00G [00:07<00:29, 134MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 21%|██ | 1.06G/5.00G [00:07<00:29, 135MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 22%|██▏ | 1.08G/5.00G [00:07<00:29, 135MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 22%|██▏ | 1.10G/5.00G [00:08<00:29, 132MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 22%|██▏ | 1.12G/5.00G [00:08<00:30, 129MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 23%|██▎ | 1.14G/5.00G [00:08<00:29, 133MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 23%|██▎ | 1.16G/5.00G [00:08<00:29, 131MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 24%|██▎ | 1.18G/5.00G [00:08<00:28, 133MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 24%|██▍ | 1.21G/5.00G [00:08<00:27, 136MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 25%|██▍ | 1.23G/5.00G [00:09<00:27, 137MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 25%|██▍ | 1.25G/5.00G [00:09<00:27, 136MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 25%|██▌ | 1.27G/5.00G [00:09<00:27, 136MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 26%|██▌ | 1.29G/5.00G [00:09<00:26, 138MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 26%|██▌ | 1.31G/5.00G [00:09<00:27, 136MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 27%|██▋ | 1.33G/5.00G [00:09<00:26, 137MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 27%|██▋ | 1.35G/5.00G [00:09<00:26, 135MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 27%|██▋ | 1.37G/5.00G [00:10<00:26, 135MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 28%|██▊ | 1.39G/5.00G [00:10<00:29, 124MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 28%|██▊ | 1.42G/5.00G [00:10<00:28, 124MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 29%|██▉ | 1.44G/5.00G [00:10<00:27, 130MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 29%|██▉ | 1.46G/5.00G [00:10<00:26, 133MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 30%|██▉ | 1.48G/5.00G [00:10<00:26, 134MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 30%|███ | 1.50G/5.00G [00:11<00:25, 136MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 30%|███ | 1.52G/5.00G [00:11<00:25, 138MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 31%|███ | 1.54G/5.00G [00:11<00:25, 135MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 31%|███▏ | 1.56G/5.00G [00:11<00:25, 137MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 32%|███▏ | 1.58G/5.00G [00:11<00:24, 141MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 32%|███▏ | 1.60G/5.00G [00:11<00:23, 142MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 33%|███▎ | 1.63G/5.00G [00:11<00:23, 142MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 33%|███▎ | 1.65G/5.00G [00:12<00:34, 97.8MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 33%|███▎ | 1.67G/5.00G [00:12<00:31, 107MB/s] \u001b[A\n",
"model-00001-of-00002.safetensors: 34%|███▍ | 1.69G/5.00G [00:12<00:28, 114MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 34%|███▍ | 1.71G/5.00G [00:12<00:27, 120MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 35%|███▍ | 1.73G/5.00G [00:12<00:26, 124MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 35%|███▌ | 1.75G/5.00G [00:13<00:26, 125MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 35%|███▌ | 1.77G/5.00G [00:13<00:25, 127MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 36%|███▌ | 1.79G/5.00G [00:13<00:25, 126MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 36%|███▋ | 1.81G/5.00G [00:13<00:25, 124MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 37%|███▋ | 1.84G/5.00G [00:13<00:24, 128MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 37%|███▋ | 1.86G/5.00G [00:13<00:24, 129MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 38%|███▊ | 1.88G/5.00G [00:14<00:23, 132MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 38%|███▊ | 1.90G/5.00G [00:14<00:22, 135MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 38%|███▊ | 1.92G/5.00G [00:14<00:23, 134MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 39%|███▉ | 1.94G/5.00G [00:14<00:22, 135MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 39%|███▉ | 1.96G/5.00G [00:14<00:22, 136MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 40%|███▉ | 1.98G/5.00G [00:14<00:22, 132MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 40%|████ | 2.00G/5.00G [00:15<00:22, 134MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 41%|████ | 2.02G/5.00G [00:15<00:22, 132MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 41%|████ | 2.04G/5.00G [00:15<00:22, 133MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 41%|████▏ | 2.07G/5.00G [00:15<00:22, 133MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 42%|████▏ | 2.09G/5.00G [00:15<00:22, 130MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 42%|████▏ | 2.11G/5.00G [00:15<00:21, 132MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 43%|████▎ | 2.13G/5.00G [00:15<00:21, 135MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 43%|████▎ | 2.15G/5.00G [00:16<00:20, 136MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 43%|████▎ | 2.17G/5.00G [00:16<00:20, 138MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 44%|████▍ | 2.19G/5.00G [00:16<00:20, 137MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 44%|████▍ | 2.21G/5.00G [00:16<00:20, 134MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 45%|████▍ | 2.23G/5.00G [00:16<00:20, 135MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 45%|████▌ | 2.25G/5.00G [00:16<00:19, 138MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 46%|████▌ | 2.28G/5.00G [00:17<00:19, 139MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 46%|████▌ | 2.30G/5.00G [00:17<00:19, 139MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 46%|████▋ | 2.32G/5.00G [00:17<00:19, 137MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 47%|████▋ | 2.34G/5.00G [00:17<00:20, 131MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 47%|████▋ | 2.36G/5.00G [00:17<00:19, 134MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 48%|████▊ | 2.38G/5.00G [00:17<00:20, 130MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 48%|████▊ | 2.40G/5.00G [00:18<00:20, 128MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 48%|████▊ | 2.42G/5.00G [00:18<00:19, 129MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 49%|████▉ | 2.44G/5.00G [00:18<00:19, 128MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 49%|████▉ | 2.46G/5.00G [00:18<00:19, 131MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 50%|████▉ | 2.49G/5.00G [00:18<00:18, 133MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 50%|█████ | 2.51G/5.00G [00:18<00:18, 131MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 51%|█████ | 2.53G/5.00G [00:18<00:18, 135MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 51%|█████ | 2.55G/5.00G [00:19<00:17, 136MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 51%|█████▏ | 2.57G/5.00G [00:19<00:18, 134MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 52%|█████▏ | 2.59G/5.00G [00:19<00:17, 135MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 52%|█████▏ | 2.61G/5.00G [00:19<00:20, 116MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 53%|█████▎ | 2.63G/5.00G [00:19<00:20, 117MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 53%|█████▎ | 2.65G/5.00G [00:19<00:19, 122MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 54%|█████▎ | 2.67G/5.00G [00:20<00:18, 127MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 54%|█████▍ | 2.69G/5.00G [00:20<00:18, 126MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 54%|█████▍ | 2.72G/5.00G [00:20<00:17, 129MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 55%|█████▍ | 2.74G/5.00G [00:20<00:20, 109MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 55%|█████▌ | 2.76G/5.00G [00:20<00:19, 113MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 56%|█████▌ | 2.78G/5.00G [00:21<00:18, 120MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 56%|█████▌ | 2.80G/5.00G [00:21<00:17, 124MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 56%|█████▋ | 2.82G/5.00G [00:21<00:17, 128MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 57%|█████▋ | 2.84G/5.00G [00:21<00:16, 127MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 57%|█████▋ | 2.86G/5.00G [00:21<00:21, 97.7MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 58%|█████▊ | 2.88G/5.00G [00:22<00:19, 107MB/s] \u001b[A\n",
"model-00001-of-00002.safetensors: 58%|█████▊ | 2.90G/5.00G [00:22<00:18, 116MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 59%|█████▊ | 2.93G/5.00G [00:22<00:16, 122MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 59%|█████▉ | 2.95G/5.00G [00:22<00:16, 122MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 59%|█████▉ | 2.97G/5.00G [00:22<00:16, 120MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 60%|█████▉ | 2.99G/5.00G [00:22<00:16, 125MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 60%|██████ | 3.01G/5.00G [00:22<00:15, 126MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 61%|██████ | 3.03G/5.00G [00:23<00:15, 128MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 61%|██████ | 3.05G/5.00G [00:23<00:14, 130MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 62%|██████▏ | 3.07G/5.00G [00:23<00:14, 129MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 62%|██████▏ | 3.09G/5.00G [00:23<00:15, 126MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 62%|██████▏ | 3.11G/5.00G [00:23<00:14, 131MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 63%|██████▎ | 3.14G/5.00G [00:23<00:14, 125MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 63%|██████▎ | 3.16G/5.00G [00:24<00:14, 128MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 64%|██████▎ | 3.18G/5.00G [00:24<00:13, 131MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 64%|██████▍ | 3.20G/5.00G [00:24<00:13, 130MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 64%|██████▍ | 3.22G/5.00G [00:24<00:13, 130MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 65%|██████▍ | 3.24G/5.00G [00:24<00:13, 132MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 65%|██████▌ | 3.26G/5.00G [00:24<00:13, 129MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 66%|██████▌ | 3.28G/5.00G [00:25<00:12, 132MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 66%|██████▌ | 3.30G/5.00G [00:25<00:12, 133MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 67%|██████▋ | 3.32G/5.00G [00:25<00:12, 130MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 67%|██████▋ | 3.34G/5.00G [00:25<00:12, 130MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 67%|██████▋ | 3.37G/5.00G [00:25<00:12, 132MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 68%|██████▊ | 3.39G/5.00G [00:25<00:12, 130MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 68%|██████▊ | 3.41G/5.00G [00:26<00:12, 132MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 69%|██████▊ | 3.43G/5.00G [00:26<00:11, 133MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 69%|██████▉ | 3.45G/5.00G [00:26<00:11, 132MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 69%|██████▉ | 3.47G/5.00G [00:26<00:11, 132MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 70%|██████▉ | 3.49G/5.00G [00:26<00:11, 130MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 70%|███████ | 3.51G/5.00G [00:26<00:11, 129MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 71%|███████ | 3.53G/5.00G [00:26<00:11, 131MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 71%|███████ | 3.55G/5.00G [00:27<00:10, 135MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 72%|███████▏ | 3.58G/5.00G [00:27<00:10, 133MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 72%|███████▏ | 3.60G/5.00G [00:27<00:10, 132MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 72%|███████▏ | 3.62G/5.00G [00:27<00:10, 130MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 73%|███████▎ | 3.64G/5.00G [00:27<00:10, 124MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 73%|███████▎ | 3.66G/5.00G [00:27<00:11, 121MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 74%|███████▎ | 3.68G/5.00G [00:28<00:10, 125MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 74%|███████▍ | 3.70G/5.00G [00:28<00:09, 130MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 75%|███████▍ | 3.72G/5.00G [00:28<00:09, 133MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 75%|███████▍ | 3.74G/5.00G [00:28<00:10, 125MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 75%|███████▌ | 3.76G/5.00G [00:28<00:09, 125MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 76%|███████▌ | 3.79G/5.00G [00:28<00:09, 126MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 76%|███████▌ | 3.81G/5.00G [00:29<00:09, 122MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 77%|███████▋ | 3.83G/5.00G [00:29<00:09, 130MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 77%|███████▋ | 3.85G/5.00G [00:29<00:08, 132MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 77%|███████▋ | 3.87G/5.00G [00:29<00:12, 88.9MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 78%|███████▊ | 3.89G/5.00G [00:30<00:11, 98.1MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 78%|███████▊ | 3.91G/5.00G [00:30<00:10, 105MB/s] \u001b[A\n",
"model-00001-of-00002.safetensors: 79%|███████▊ | 3.93G/5.00G [00:30<00:09, 112MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 79%|███████▉ | 3.95G/5.00G [00:30<00:08, 119MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 80%|███████▉ | 3.97G/5.00G [00:30<00:08, 122MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 80%|███████▉ | 4.00G/5.00G [00:30<00:08, 115MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 80%|████████ | 4.02G/5.00G [00:31<00:08, 114MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 81%|████████ | 4.04G/5.00G [00:31<00:08, 116MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 81%|████████ | 4.06G/5.00G [00:31<00:08, 117MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 82%|████████▏ | 4.08G/5.00G [00:31<00:07, 120MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 82%|████████▏ | 4.10G/5.00G [00:31<00:07, 122MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 82%|████████▏ | 4.12G/5.00G [00:31<00:07, 118MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 83%|████████▎ | 4.14G/5.00G [00:32<00:07, 119MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 83%|████████▎ | 4.16G/5.00G [00:32<00:06, 120MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 84%|████████▍ | 4.18G/5.00G [00:32<00:06, 119MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 84%|████████▍ | 4.20G/5.00G [00:32<00:06, 121MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 85%|████████▍ | 4.23G/5.00G [00:32<00:06, 122MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 85%|████████▌ | 4.25G/5.00G [00:32<00:06, 123MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 85%|████████▌ | 4.27G/5.00G [00:33<00:05, 129MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 86%|████████▌ | 4.29G/5.00G [00:33<00:05, 132MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 86%|████████▋ | 4.31G/5.00G [00:33<00:05, 131MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 87%|████████▋ | 4.33G/5.00G [00:33<00:04, 135MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 87%|████████▋ | 4.35G/5.00G [00:33<00:04, 134MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 88%|████████▊ | 4.37G/5.00G [00:33<00:05, 125MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 88%|████████▊ | 4.39G/5.00G [00:34<00:04, 128MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 88%|████████▊ | 4.41G/5.00G [00:34<00:04, 130MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 89%|████████▉ | 4.44G/5.00G [00:34<00:04, 129MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 89%|████████▉ | 4.46G/5.00G [00:34<00:04, 132MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 90%|████████▉ | 4.48G/5.00G [00:34<00:03, 136MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 90%|█████████ | 4.50G/5.00G [00:34<00:03, 135MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 90%|█████████ | 4.52G/5.00G [00:34<00:03, 138MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 91%|█████████ | 4.54G/5.00G [00:35<00:03, 140MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 91%|█████████▏| 4.56G/5.00G [00:35<00:03, 136MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 92%|█████████▏| 4.58G/5.00G [00:35<00:03, 137MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 92%|█████████▏| 4.60G/5.00G [00:35<00:02, 138MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 93%|█████████▎| 4.62G/5.00G [00:35<00:02, 135MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 93%|█████████▎| 4.65G/5.00G [00:35<00:02, 137MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 93%|█████████▎| 4.67G/5.00G [00:36<00:02, 137MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 94%|█████████▍| 4.69G/5.00G [00:36<00:02, 135MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 94%|█████████▍| 4.71G/5.00G [00:36<00:02, 136MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 95%|█████████▍| 4.73G/5.00G [00:36<00:01, 134MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 95%|█████████▌| 4.75G/5.00G [00:36<00:01, 130MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 96%|█████████▌| 4.77G/5.00G [00:36<00:01, 131MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 96%|█████████▌| 4.79G/5.00G [00:37<00:01, 132MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 96%|█████████▋| 4.81G/5.00G [00:37<00:01, 132MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 97%|█████████▋| 4.83G/5.00G [00:37<00:01, 136MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 97%|█████████▋| 4.85G/5.00G [00:37<00:01, 138MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 98%|█████████▊| 4.88G/5.00G [00:37<00:00, 135MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 98%|█████████▊| 4.90G/5.00G [00:37<00:00, 138MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 98%|█████████▊| 4.92G/5.00G [00:37<00:00, 139MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 99%|█████████▉| 4.94G/5.00G [00:38<00:00, 140MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 99%|█████████▉| 4.96G/5.00G [00:38<00:00, 142MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 100%|█████████▉| 4.98G/5.00G [00:38<00:00, 137MB/s]\u001b[A\n",
"model-00001-of-00002.safetensors: 100%|██████████| 5.00G/5.00G [00:38<00:00, 130MB/s]\u001b[A\n",
"Downloading shards: 50%|█████ | 1/2 [00:38<00:38, 38.64s/it]\n",
"model-00002-of-00002.safetensors: 0%| | 0.00/564M [00:00<?, ?B/s]\u001b[A\n",
"model-00002-of-00002.safetensors: 4%|▎ | 21.0M/564M [00:00<00:03, 150MB/s]\u001b[A\n",
"model-00002-of-00002.safetensors: 7%|▋ | 41.9M/564M [00:00<00:03, 143MB/s]\u001b[A\n",
"model-00002-of-00002.safetensors: 11%|█ | 62.9M/564M [00:00<00:03, 126MB/s]\u001b[A\n",
"model-00002-of-00002.safetensors: 15%|█▍ | 83.9M/564M [00:00<00:03, 130MB/s]\u001b[A\n",
"model-00002-of-00002.safetensors: 19%|█▊ | 105M/564M [00:00<00:03, 129MB/s] \u001b[A\n",
"model-00002-of-00002.safetensors: 22%|██▏ | 126M/564M [00:00<00:03, 133MB/s]\u001b[A\n",
"model-00002-of-00002.safetensors: 26%|██▌ | 147M/564M [00:01<00:03, 134MB/s]\u001b[A\n",
"model-00002-of-00002.safetensors: 30%|██▉ | 168M/564M [00:01<00:02, 135MB/s]\u001b[A\n",
"model-00002-of-00002.safetensors: 33%|███▎ | 189M/564M [00:01<00:02, 128MB/s]\u001b[A\n",
"model-00002-of-00002.safetensors: 37%|███▋ | 210M/564M [00:01<00:02, 131MB/s]\u001b[A\n",
"model-00002-of-00002.safetensors: 41%|████ | 231M/564M [00:01<00:02, 131MB/s]\u001b[A\n",
"model-00002-of-00002.safetensors: 45%|████▍ | 252M/564M [00:01<00:02, 131MB/s]\u001b[A\n",
"model-00002-of-00002.safetensors: 48%|████▊ | 273M/564M [00:02<00:02, 133MB/s]\u001b[A\n",
"model-00002-of-00002.safetensors: 52%|█████▏ | 294M/564M [00:02<00:02, 133MB/s]\u001b[A\n",
"model-00002-of-00002.safetensors: 56%|█████▌ | 315M/564M [00:02<00:01, 136MB/s]\u001b[A\n",
"model-00002-of-00002.safetensors: 60%|█████▉ | 336M/564M [00:02<00:01, 135MB/s]\u001b[A\n",
"model-00002-of-00002.safetensors: 63%|██████▎ | 357M/564M [00:02<00:01, 134MB/s]\u001b[A\n",
"model-00002-of-00002.safetensors: 67%|██████▋ | 377M/564M [00:02<00:01, 134MB/s]\u001b[A\n",
"model-00002-of-00002.safetensors: 71%|███████ | 398M/564M [00:02<00:01, 137MB/s]\u001b[A\n",
"model-00002-of-00002.safetensors: 74%|███████▍ | 419M/564M [00:03<00:01, 136MB/s]\u001b[A\n",
"model-00002-of-00002.safetensors: 78%|███████▊ | 440M/564M [00:03<00:00, 136MB/s]\u001b[A\n",
"model-00002-of-00002.safetensors: 82%|████████▏ | 461M/564M [00:03<00:01, 95.4MB/s]\u001b[A\n",
"model-00002-of-00002.safetensors: 86%|████████▌ | 482M/564M [00:03<00:00, 103MB/s] \u001b[A\n",
"model-00002-of-00002.safetensors: 89%|████████▉ | 503M/564M [00:04<00:00, 109MB/s]\u001b[A\n",
"model-00002-of-00002.safetensors: 93%|█████████▎| 524M/564M [00:04<00:00, 116MB/s]\u001b[A\n",
"model-00002-of-00002.safetensors: 97%|█████████▋| 545M/564M [00:04<00:00, 120MB/s]\u001b[A\n",
"model-00002-of-00002.safetensors: 100%|██████████| 564M/564M [00:04<00:00, 126MB/s]\u001b[A\n",
"Downloading shards: 100%|██████████| 2/2 [00:43<00:00, 21.61s/it]\n",
"Loading checkpoint shards: 100%|██████████| 2/2 [00:08<00:00, 4.06s/it]\n",
"generation_config.json: 100%|██████████| 124/124 [00:00<00:00, 278kB/s]\n"
]
}
],
"source": [
"bnb_config = BitsAndBytesConfig(\n",
" load_in_4bit=True,\n",
" bnb_4bit_use_double_quant=True,\n",
" bnb_4bit_quant_type=\"nf4\",\n",
" bnb_4bit_compute_dtype=torch.float16\n",
")\n",
"\n",
"model = AutoModelForCausalLM.from_pretrained(\n",
" \"microsoft/phi-2\",\n",
" device_map={\"\":0},\n",
" trust_remote_code=True,\n",
" quantization_config=bnb_config\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "e15aa794-e17c-4b09-a64a-c60377259218",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"PhiForCausalLM(\n",
" (model): PhiModel(\n",
" (embed_tokens): Embedding(51200, 2560)\n",
" (embed_dropout): Dropout(p=0.0, inplace=False)\n",
" (layers): ModuleList(\n",
" (0-31): 32 x PhiDecoderLayer(\n",
" (self_attn): PhiAttention(\n",
" (q_proj): Linear4bit(in_features=2560, out_features=2560, bias=True)\n",
" (k_proj): Linear4bit(in_features=2560, out_features=2560, bias=True)\n",
" (v_proj): Linear4bit(in_features=2560, out_features=2560, bias=True)\n",
" (dense): Linear4bit(in_features=2560, out_features=2560, bias=True)\n",
" (rotary_emb): PhiRotaryEmbedding()\n",
" )\n",
" (mlp): PhiMLP(\n",
" (activation_fn): NewGELUActivation()\n",
" (fc1): Linear4bit(in_features=2560, out_features=10240, bias=True)\n",
" (fc2): Linear4bit(in_features=10240, out_features=2560, bias=True)\n",
" )\n",
" (input_layernorm): LayerNorm((2560,), eps=1e-05, elementwise_affine=True)\n",
" (resid_dropout): Dropout(p=0.1, inplace=False)\n",
" )\n",
" )\n",
" (final_layernorm): LayerNorm((2560,), eps=1e-05, elementwise_affine=True)\n",
" )\n",
" (lm_head): Linear(in_features=2560, out_features=51200, bias=True)\n",
")\n"
]
}
],
"source": [
"print(model)"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "18d5599f-992d-4d8e-a90c-4d43774be473",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"trainable params: 17,039,360 || all params: 2,796,723,200 || trainable%: 0.6092615815537269\n"
]
}
],
"source": [
"config = LoraConfig(\n",
" r=16,\n",
" lora_alpha=16,\n",
" target_modules=[\"dense\", \"fc2\",\"q_proj\",\"k_proj\",\"v_proj\"],\n",
" lora_dropout=0.05,\n",
" bias=\"none\",\n",
" task_type=\"CAUSAL_LM\"\n",
")\n",
"\n",
"model = get_peft_model(model, config)\n",
"model.print_trainable_parameters()"
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "baeee903-3dce-48b2-93c3-7a697d8c6daf",
"metadata": {},
"outputs": [],
"source": [
"def tokenize(sample):\n",
" model_inps = tokenizer(sample[\"text\"], padding=True, truncation=True, max_length=512)\n",
" return model_inps"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "28a9b24a-a822-4fcb-96b3-d77b7ea30a5f",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Collecting scikit-learn\n",
" Downloading scikit_learn-1.4.0-1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (11 kB)\n",
"Requirement already satisfied: numpy<2.0,>=1.19.5 in /usr/local/lib/python3.11/site-packages (from scikit-learn) (1.26.4)\n",
"Requirement already satisfied: scipy>=1.6.0 in /usr/local/lib/python3.11/site-packages (from scikit-learn) (1.12.0)\n",
"Collecting joblib>=1.2.0 (from scikit-learn)\n",
" Downloading joblib-1.3.2-py3-none-any.whl.metadata (5.4 kB)\n",
"Collecting threadpoolctl>=2.0.0 (from scikit-learn)\n",
" Downloading threadpoolctl-3.2.0-py3-none-any.whl.metadata (10.0 kB)\n",
"Downloading scikit_learn-1.4.0-1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (12.1 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m12.1/12.1 MB\u001b[0m \u001b[31m62.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0ma \u001b[36m0:00:01\u001b[0m\n",
"\u001b[?25hDownloading joblib-1.3.2-py3-none-any.whl (302 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m302.2/302.2 kB\u001b[0m \u001b[31m279.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading threadpoolctl-3.2.0-py3-none-any.whl (15 kB)\n",
"Installing collected packages: threadpoolctl, joblib, scikit-learn\n",
"Successfully installed joblib-1.3.2 scikit-learn-1.4.0 threadpoolctl-3.2.0\n"
]
}
],
"source": [
"!pip install scikit-learn"
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "1ee7fd2a-38e4-4f23-a978-0bdeeda64d8b",
"metadata": {},
"outputs": [],
"source": [
"import pandas as pd\n",
"\n",
"from sklearn.model_selection import train_test_split\n",
"dataset_name='data.csv'\n",
"df = pd.read_csv(dataset_name)\n",
"train, test = train_test_split(df, test_size=0.2)"
]
},
{
"cell_type": "code",
"execution_count": 10,
"id": "e84c29e2-843e-42c2-8c0f-324d392e671c",
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"Tokenizing data: 100%|██████████| 13129/13129 [00:04<00:00, 2739.65 examples/s]\n"
]
},
{
"data": {
"text/plain": [
"Dataset({\n",
" features: ['input_ids', 'attention_mask'],\n",
" num_rows: 13129\n",
"})"
]
},
"execution_count": 10,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"data_df = train\n",
"data_df[\"text\"] = data_df[[\"user\", \"assistant\"]].apply(lambda x: \"question: \" + str(x[\"user\"]) + \" answer: \" + str(x[\"assistant\"]), axis=1)\n",
"data = Dataset.from_pandas(data_df)\n",
"tokenized_data = data.map(tokenize, batched=True, desc=\"Tokenizing data\", remove_columns=data.column_names)\n",
"tokenized_data"
]
},
{
"cell_type": "code",
"execution_count": 16,
"id": "ac968254-5338-49df-950d-222b82647407",
"metadata": {},
"outputs": [],
"source": [
"training_arguments = TrainingArguments(\n",
" output_dir=\".\",\n",
" per_device_train_batch_size=4,\n",
" gradient_accumulation_steps=1,\n",
" learning_rate=2e-4,\n",
" lr_scheduler_type=\"cosine\",\n",
" save_strategy=\"epoch\",\n",
" logging_steps=100,\n",
" max_steps=1100,\n",
" num_train_epochs=2,\n",
" push_to_hub=True\n",
" )"
]
},
{
"cell_type": "code",
"execution_count": 12,
"id": "729df2d0-0890-4ac4-adf3-c167a6e9669d",
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...\n",
"To disable this warning, you can either:\n",
"\t- Avoid using `tokenizers` before the fork if possible\n",
"\t- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"Requirement already satisfied: huggingface_hub in /usr/local/lib/python3.11/site-packages (0.20.3)\n",
"Requirement already satisfied: filelock in /usr/local/lib/python3.11/site-packages (from huggingface_hub) (3.13.1)\n",
"Requirement already satisfied: fsspec>=2023.5.0 in /usr/local/lib/python3.11/site-packages (from huggingface_hub) (2023.10.0)\n",
"Requirement already satisfied: requests in /usr/local/lib/python3.11/site-packages (from huggingface_hub) (2.31.0)\n",
"Requirement already satisfied: tqdm>=4.42.1 in /usr/local/lib/python3.11/site-packages (from huggingface_hub) (4.66.1)\n",
"Requirement already satisfied: pyyaml>=5.1 in /usr/local/lib/python3.11/site-packages (from huggingface_hub) (6.0.1)\n",
"Requirement already satisfied: typing-extensions>=3.7.4.3 in /usr/local/lib/python3.11/site-packages (from huggingface_hub) (4.9.0)\n",
"Requirement already satisfied: packaging>=20.9 in /usr/local/lib/python3.11/site-packages (from huggingface_hub) (23.2)\n",
"Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.11/site-packages (from requests->huggingface_hub) (2.1.1)\n",
"Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.11/site-packages (from requests->huggingface_hub) (3.6)\n",
"Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.11/site-packages (from requests->huggingface_hub) (2.2.0)\n",
"Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.11/site-packages (from requests->huggingface_hub) (2024.2.2)\n"
]
}
],
"source": [
"!pip install huggingface_hub"
]
},
{
"cell_type": "code",
"execution_count": 13,
"id": "525f81a4-eb92-466e-bb9c-cd63122231ab",
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...\n",
"To disable this warning, you can either:\n",
"\t- Avoid using `tokenizers` before the fork if possible\n",
"\t- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"Requirement already satisfied: jupyterlab in /usr/local/lib/python3.11/site-packages (4.1.0)\n",
"Collecting jupyterlab-git\n",
" Downloading jupyterlab_git-0.50.0-py3-none-any.whl.metadata (31 kB)\n",
"Requirement already satisfied: async-lru>=1.0.0 in /usr/local/lib/python3.11/site-packages (from jupyterlab) (2.0.4)\n",
"Requirement already satisfied: httpx>=0.25.0 in /usr/local/lib/python3.11/site-packages (from jupyterlab) (0.26.0)\n",
"Requirement already satisfied: ipykernel in /usr/local/lib/python3.11/site-packages (from jupyterlab) (6.29.1)\n",
"Requirement already satisfied: jinja2>=3.0.3 in /usr/local/lib/python3.11/site-packages (from jupyterlab) (3.1.3)\n",
"Requirement already satisfied: jupyter-core in /usr/local/lib/python3.11/site-packages (from jupyterlab) (5.7.1)\n",
"Requirement already satisfied: jupyter-lsp>=2.0.0 in /usr/local/lib/python3.11/site-packages (from jupyterlab) (2.2.2)\n",
"Requirement already satisfied: jupyter-server<3,>=2.4.0 in /usr/local/lib/python3.11/site-packages (from jupyterlab) (2.12.5)\n",
"Requirement already satisfied: jupyterlab-server<3,>=2.19.0 in /usr/local/lib/python3.11/site-packages (from jupyterlab) (2.25.2)\n",
"Requirement already satisfied: notebook-shim>=0.2 in /usr/local/lib/python3.11/site-packages (from jupyterlab) (0.2.3)\n",
"Requirement already satisfied: packaging in /usr/local/lib/python3.11/site-packages (from jupyterlab) (23.2)\n",
"Requirement already satisfied: tornado>=6.2.0 in /usr/local/lib/python3.11/site-packages (from jupyterlab) (6.4)\n",
"Requirement already satisfied: traitlets in /usr/local/lib/python3.11/site-packages (from jupyterlab) (5.14.1)\n",
"Collecting nbdime~=4.0.1 (from jupyterlab-git)\n",
" Downloading nbdime-4.0.1-py3-none-any.whl.metadata (9.5 kB)\n",
"Requirement already satisfied: nbformat in /usr/local/lib/python3.11/site-packages (from jupyterlab-git) (5.9.2)\n",
"Requirement already satisfied: pexpect in /usr/local/lib/python3.11/site-packages (from jupyterlab-git) (4.9.0)\n",
"Requirement already satisfied: anyio in /usr/local/lib/python3.11/site-packages (from httpx>=0.25.0->jupyterlab) (4.2.0)\n",
"Requirement already satisfied: certifi in /usr/local/lib/python3.11/site-packages (from httpx>=0.25.0->jupyterlab) (2024.2.2)\n",
"Requirement already satisfied: httpcore==1.* in /usr/local/lib/python3.11/site-packages (from httpx>=0.25.0->jupyterlab) (1.0.2)\n",
"Requirement already satisfied: idna in /usr/local/lib/python3.11/site-packages (from httpx>=0.25.0->jupyterlab) (3.6)\n",
"Requirement already satisfied: sniffio in /usr/local/lib/python3.11/site-packages (from httpx>=0.25.0->jupyterlab) (1.3.0)\n",
"Requirement already satisfied: h11<0.15,>=0.13 in /usr/local/lib/python3.11/site-packages (from httpcore==1.*->httpx>=0.25.0->jupyterlab) (0.14.0)\n",
"Requirement already satisfied: MarkupSafe>=2.0 in /usr/local/lib/python3.11/site-packages (from jinja2>=3.0.3->jupyterlab) (2.1.5)\n",
"Requirement already satisfied: argon2-cffi in /usr/local/lib/python3.11/site-packages (from jupyter-server<3,>=2.4.0->jupyterlab) (23.1.0)\n",
"Requirement already satisfied: jupyter-client>=7.4.4 in /usr/local/lib/python3.11/site-packages (from jupyter-server<3,>=2.4.0->jupyterlab) (8.6.0)\n",
"Requirement already satisfied: jupyter-events>=0.9.0 in /usr/local/lib/python3.11/site-packages (from jupyter-server<3,>=2.4.0->jupyterlab) (0.9.0)\n",
"Requirement already satisfied: jupyter-server-terminals in /usr/local/lib/python3.11/site-packages (from jupyter-server<3,>=2.4.0->jupyterlab) (0.5.2)\n",
"Requirement already satisfied: nbconvert>=6.4.4 in /usr/local/lib/python3.11/site-packages (from jupyter-server<3,>=2.4.0->jupyterlab) (7.15.0)\n",
"Requirement already satisfied: overrides in /usr/local/lib/python3.11/site-packages (from jupyter-server<3,>=2.4.0->jupyterlab) (7.7.0)\n",
"Requirement already satisfied: prometheus-client in /usr/local/lib/python3.11/site-packages (from jupyter-server<3,>=2.4.0->jupyterlab) (0.19.0)\n",
"Requirement already satisfied: pyzmq>=24 in /usr/local/lib/python3.11/site-packages (from jupyter-server<3,>=2.4.0->jupyterlab) (25.1.2)\n",
"Requirement already satisfied: send2trash>=1.8.2 in /usr/local/lib/python3.11/site-packages (from jupyter-server<3,>=2.4.0->jupyterlab) (1.8.2)\n",
"Requirement already satisfied: terminado>=0.8.3 in /usr/local/lib/python3.11/site-packages (from jupyter-server<3,>=2.4.0->jupyterlab) (0.18.0)\n",
"Requirement already satisfied: websocket-client in /usr/local/lib/python3.11/site-packages (from jupyter-server<3,>=2.4.0->jupyterlab) (1.7.0)\n",
"Requirement already satisfied: platformdirs>=2.5 in /usr/local/lib/python3.11/site-packages (from jupyter-core->jupyterlab) (4.2.0)\n",
"Requirement already satisfied: babel>=2.10 in /usr/local/lib/python3.11/site-packages (from jupyterlab-server<3,>=2.19.0->jupyterlab) (2.14.0)\n",
"Requirement already satisfied: json5>=0.9.0 in /usr/local/lib/python3.11/site-packages (from jupyterlab-server<3,>=2.19.0->jupyterlab) (0.9.14)\n",
"Requirement already satisfied: jsonschema>=4.18.0 in /usr/local/lib/python3.11/site-packages (from jupyterlab-server<3,>=2.19.0->jupyterlab) (4.21.1)\n",
"Requirement already satisfied: requests>=2.31 in /usr/local/lib/python3.11/site-packages (from jupyterlab-server<3,>=2.19.0->jupyterlab) (2.31.0)\n",
"Collecting colorama (from nbdime~=4.0.1->jupyterlab-git)\n",
" Downloading colorama-0.4.6-py2.py3-none-any.whl (25 kB)\n",
"Collecting gitpython!=2.1.4,!=2.1.5,!=2.1.6 (from nbdime~=4.0.1->jupyterlab-git)\n",
" Downloading GitPython-3.1.41-py3-none-any.whl.metadata (14 kB)\n",
"Collecting jupyter-server-mathjax>=0.2.2 (from nbdime~=4.0.1->jupyterlab-git)\n",
" Downloading jupyter_server_mathjax-0.2.6-py3-none-any.whl (3.1 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m3.1/3.1 MB\u001b[0m \u001b[31m18.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0ma \u001b[36m0:00:01\u001b[0m\n",
"\u001b[?25hRequirement already satisfied: pygments in /usr/local/lib/python3.11/site-packages (from nbdime~=4.0.1->jupyterlab-git) (2.17.2)\n",
"Requirement already satisfied: fastjsonschema in /usr/local/lib/python3.11/site-packages (from nbformat->jupyterlab-git) (2.19.1)\n",
"Requirement already satisfied: comm>=0.1.1 in /usr/local/lib/python3.11/site-packages (from ipykernel->jupyterlab) (0.2.1)\n",
"Requirement already satisfied: debugpy>=1.6.5 in /usr/local/lib/python3.11/site-packages (from ipykernel->jupyterlab) (1.8.0)\n",
"Requirement already satisfied: ipython>=7.23.1 in /usr/local/lib/python3.11/site-packages (from ipykernel->jupyterlab) (8.21.0)\n",
"Requirement already satisfied: matplotlib-inline>=0.1 in /usr/local/lib/python3.11/site-packages (from ipykernel->jupyterlab) (0.1.6)\n",
"Requirement already satisfied: nest-asyncio in /usr/local/lib/python3.11/site-packages (from ipykernel->jupyterlab) (1.6.0)\n",
"Requirement already satisfied: psutil in /usr/local/lib/python3.11/site-packages (from ipykernel->jupyterlab) (5.9.8)\n",
"Requirement already satisfied: ptyprocess>=0.5 in /usr/local/lib/python3.11/site-packages (from pexpect->jupyterlab-git) (0.7.0)\n",
"Collecting gitdb<5,>=4.0.1 (from gitpython!=2.1.4,!=2.1.5,!=2.1.6->nbdime~=4.0.1->jupyterlab-git)\n",
" Downloading gitdb-4.0.11-py3-none-any.whl.metadata (1.2 kB)\n",
"Requirement already satisfied: decorator in /usr/local/lib/python3.11/site-packages (from ipython>=7.23.1->ipykernel->jupyterlab) (5.1.1)\n",
"Requirement already satisfied: jedi>=0.16 in /usr/local/lib/python3.11/site-packages (from ipython>=7.23.1->ipykernel->jupyterlab) (0.19.1)\n",
"Requirement already satisfied: prompt-toolkit<3.1.0,>=3.0.41 in /usr/local/lib/python3.11/site-packages (from ipython>=7.23.1->ipykernel->jupyterlab) (3.0.43)\n",
"Requirement already satisfied: stack-data in /usr/local/lib/python3.11/site-packages (from ipython>=7.23.1->ipykernel->jupyterlab) (0.6.3)\n",
"Requirement already satisfied: attrs>=22.2.0 in /usr/local/lib/python3.11/site-packages (from jsonschema>=4.18.0->jupyterlab-server<3,>=2.19.0->jupyterlab) (23.2.0)\n",
"Requirement already satisfied: jsonschema-specifications>=2023.03.6 in /usr/local/lib/python3.11/site-packages (from jsonschema>=4.18.0->jupyterlab-server<3,>=2.19.0->jupyterlab) (2023.12.1)\n",
"Requirement already satisfied: referencing>=0.28.4 in /usr/local/lib/python3.11/site-packages (from jsonschema>=4.18.0->jupyterlab-server<3,>=2.19.0->jupyterlab) (0.33.0)\n",
"Requirement already satisfied: rpds-py>=0.7.1 in /usr/local/lib/python3.11/site-packages (from jsonschema>=4.18.0->jupyterlab-server<3,>=2.19.0->jupyterlab) (0.17.1)\n",
"Requirement already satisfied: python-dateutil>=2.8.2 in /usr/local/lib/python3.11/site-packages (from jupyter-client>=7.4.4->jupyter-server<3,>=2.4.0->jupyterlab) (2.8.2)\n",
"Requirement already satisfied: python-json-logger>=2.0.4 in /usr/local/lib/python3.11/site-packages (from jupyter-events>=0.9.0->jupyter-server<3,>=2.4.0->jupyterlab) (2.0.7)\n",
"Requirement already satisfied: pyyaml>=5.3 in /usr/local/lib/python3.11/site-packages (from jupyter-events>=0.9.0->jupyter-server<3,>=2.4.0->jupyterlab) (6.0.1)\n",
"Requirement already satisfied: rfc3339-validator in /usr/local/lib/python3.11/site-packages (from jupyter-events>=0.9.0->jupyter-server<3,>=2.4.0->jupyterlab) (0.1.4)\n",
"Requirement already satisfied: rfc3986-validator>=0.1.1 in /usr/local/lib/python3.11/site-packages (from jupyter-events>=0.9.0->jupyter-server<3,>=2.4.0->jupyterlab) (0.1.1)\n",
"Requirement already satisfied: beautifulsoup4 in /usr/local/lib/python3.11/site-packages (from nbconvert>=6.4.4->jupyter-server<3,>=2.4.0->jupyterlab) (4.12.3)\n",
"Requirement already satisfied: bleach!=5.0.0 in /usr/local/lib/python3.11/site-packages (from nbconvert>=6.4.4->jupyter-server<3,>=2.4.0->jupyterlab) (6.1.0)\n",
"Requirement already satisfied: defusedxml in /usr/local/lib/python3.11/site-packages (from nbconvert>=6.4.4->jupyter-server<3,>=2.4.0->jupyterlab) (0.7.1)\n",
"Requirement already satisfied: jupyterlab-pygments in /usr/local/lib/python3.11/site-packages (from nbconvert>=6.4.4->jupyter-server<3,>=2.4.0->jupyterlab) (0.3.0)\n",
"Requirement already satisfied: mistune<4,>=2.0.3 in /usr/local/lib/python3.11/site-packages (from nbconvert>=6.4.4->jupyter-server<3,>=2.4.0->jupyterlab) (3.0.2)\n",
"Requirement already satisfied: nbclient>=0.5.0 in /usr/local/lib/python3.11/site-packages (from nbconvert>=6.4.4->jupyter-server<3,>=2.4.0->jupyterlab) (0.9.0)\n",
"Requirement already satisfied: pandocfilters>=1.4.1 in /usr/local/lib/python3.11/site-packages (from nbconvert>=6.4.4->jupyter-server<3,>=2.4.0->jupyterlab) (1.5.1)\n",
"Requirement already satisfied: tinycss2 in /usr/local/lib/python3.11/site-packages (from nbconvert>=6.4.4->jupyter-server<3,>=2.4.0->jupyterlab) (1.2.1)\n",
"Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.11/site-packages (from requests>=2.31->jupyterlab-server<3,>=2.19.0->jupyterlab) (2.1.1)\n",
"Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.11/site-packages (from requests>=2.31->jupyterlab-server<3,>=2.19.0->jupyterlab) (2.2.0)\n",
"Requirement already satisfied: argon2-cffi-bindings in /usr/local/lib/python3.11/site-packages (from argon2-cffi->jupyter-server<3,>=2.4.0->jupyterlab) (21.2.0)\n",
"Requirement already satisfied: six>=1.9.0 in /usr/local/lib/python3.11/site-packages (from bleach!=5.0.0->nbconvert>=6.4.4->jupyter-server<3,>=2.4.0->jupyterlab) (1.16.0)\n",
"Requirement already satisfied: webencodings in /usr/local/lib/python3.11/site-packages (from bleach!=5.0.0->nbconvert>=6.4.4->jupyter-server<3,>=2.4.0->jupyterlab) (0.5.1)\n",
"Collecting smmap<6,>=3.0.1 (from gitdb<5,>=4.0.1->gitpython!=2.1.4,!=2.1.5,!=2.1.6->nbdime~=4.0.1->jupyterlab-git)\n",
" Downloading smmap-5.0.1-py3-none-any.whl.metadata (4.3 kB)\n",
"Requirement already satisfied: parso<0.9.0,>=0.8.3 in /usr/local/lib/python3.11/site-packages (from jedi>=0.16->ipython>=7.23.1->ipykernel->jupyterlab) (0.8.3)\n",
"Requirement already satisfied: fqdn in /usr/local/lib/python3.11/site-packages (from jsonschema[format-nongpl]>=4.18.0->jupyter-events>=0.9.0->jupyter-server<3,>=2.4.0->jupyterlab) (1.5.1)\n",
"Requirement already satisfied: isoduration in /usr/local/lib/python3.11/site-packages (from jsonschema[format-nongpl]>=4.18.0->jupyter-events>=0.9.0->jupyter-server<3,>=2.4.0->jupyterlab) (20.11.0)\n",
"Requirement already satisfied: jsonpointer>1.13 in /usr/local/lib/python3.11/site-packages (from jsonschema[format-nongpl]>=4.18.0->jupyter-events>=0.9.0->jupyter-server<3,>=2.4.0->jupyterlab) (2.4)\n",
"Requirement already satisfied: uri-template in /usr/local/lib/python3.11/site-packages (from jsonschema[format-nongpl]>=4.18.0->jupyter-events>=0.9.0->jupyter-server<3,>=2.4.0->jupyterlab) (1.3.0)\n",
"Requirement already satisfied: webcolors>=1.11 in /usr/local/lib/python3.11/site-packages (from jsonschema[format-nongpl]>=4.18.0->jupyter-events>=0.9.0->jupyter-server<3,>=2.4.0->jupyterlab) (1.13)\n",
"Requirement already satisfied: wcwidth in /usr/local/lib/python3.11/site-packages (from prompt-toolkit<3.1.0,>=3.0.41->ipython>=7.23.1->ipykernel->jupyterlab) (0.2.13)\n",
"Requirement already satisfied: cffi>=1.0.1 in /usr/local/lib/python3.11/site-packages (from argon2-cffi-bindings->argon2-cffi->jupyter-server<3,>=2.4.0->jupyterlab) (1.16.0)\n",
"Requirement already satisfied: soupsieve>1.2 in /usr/local/lib/python3.11/site-packages (from beautifulsoup4->nbconvert>=6.4.4->jupyter-server<3,>=2.4.0->jupyterlab) (2.5)\n",
"Requirement already satisfied: executing>=1.2.0 in /usr/local/lib/python3.11/site-packages (from stack-data->ipython>=7.23.1->ipykernel->jupyterlab) (2.0.1)\n",
"Requirement already satisfied: asttokens>=2.1.0 in /usr/local/lib/python3.11/site-packages (from stack-data->ipython>=7.23.1->ipykernel->jupyterlab) (2.4.1)\n",
"Requirement already satisfied: pure-eval in /usr/local/lib/python3.11/site-packages (from stack-data->ipython>=7.23.1->ipykernel->jupyterlab) (0.2.2)\n",
"Requirement already satisfied: pycparser in /usr/local/lib/python3.11/site-packages (from cffi>=1.0.1->argon2-cffi-bindings->argon2-cffi->jupyter-server<3,>=2.4.0->jupyterlab) (2.21)\n",
"Requirement already satisfied: arrow>=0.15.0 in /usr/local/lib/python3.11/site-packages (from isoduration->jsonschema[format-nongpl]>=4.18.0->jupyter-events>=0.9.0->jupyter-server<3,>=2.4.0->jupyterlab) (1.3.0)\n",
"Requirement already satisfied: types-python-dateutil>=2.8.10 in /usr/local/lib/python3.11/site-packages (from arrow>=0.15.0->isoduration->jsonschema[format-nongpl]>=4.18.0->jupyter-events>=0.9.0->jupyter-server<3,>=2.4.0->jupyterlab) (2.8.19.20240106)\n",
"Downloading jupyterlab_git-0.50.0-py3-none-any.whl (1.2 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.2/1.2 MB\u001b[0m \u001b[31m80.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading nbdime-4.0.1-py3-none-any.whl (5.9 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m5.9/5.9 MB\u001b[0m \u001b[31m43.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0ma \u001b[36m0:00:01\u001b[0m\n",
"\u001b[?25hDownloading GitPython-3.1.41-py3-none-any.whl (196 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m196.4/196.4 kB\u001b[0m \u001b[31m43.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading gitdb-4.0.11-py3-none-any.whl (62 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m62.7/62.7 kB\u001b[0m \u001b[31m132.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading smmap-5.0.1-py3-none-any.whl (24 kB)\n",
"Installing collected packages: smmap, colorama, gitdb, gitpython, jupyter-server-mathjax, nbdime, jupyterlab-git\n",
"Successfully installed colorama-0.4.6 gitdb-4.0.11 gitpython-3.1.41 jupyter-server-mathjax-0.2.6 jupyterlab-git-0.50.0 nbdime-4.0.1 smmap-5.0.1\n",
"Note: you may need to restart the kernel to use updated packages.\n"
]
}
],
"source": [
"pip install --upgrade jupyterlab jupyterlab-git"
]
},
{
"cell_type": "code",
"execution_count": 17,
"id": "05d58512-a9e2-4319-88bf-9331c6a0584c",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
" _| _| _| _| _|_|_| _|_|_| _|_|_| _| _| _|_|_| _|_|_|_| _|_| _|_|_| _|_|_|_|\n",
" _| _| _| _| _| _| _| _|_| _| _| _| _| _| _| _|\n",
" _|_|_|_| _| _| _| _|_| _| _|_| _| _| _| _| _| _|_| _|_|_| _|_|_|_| _| _|_|_|\n",
" _| _| _| _| _| _| _| _| _| _| _|_| _| _| _| _| _| _| _|\n",
" _| _| _|_| _|_|_| _|_|_| _|_|_| _| _| _|_|_| _| _| _| _|_|_| _|_|_|_|\n",
"\n",
" A token is already saved on your machine. Run `huggingface-cli whoami` to get more information or `huggingface-cli logout` if you want to log out.\n",
" Setting a new token will erase the existing one.\n",
" To login, `huggingface_hub` requires a token generated from https://huggingface.co/settings/tokens .\n"
]
},
{
"name": "stdin",
"output_type": "stream",
"text": [
"Token: ········\n",
"Add token as git credential? (Y/n) n\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"Token is valid (permission: write).\n",
"Your token has been saved to /root/.cache/huggingface/token\n",
"Login successful\n"
]
}
],
"source": [
"from huggingface_hub import interpreter_login\n",
"interpreter_login()"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "3bf553b6-b26c-49c3-9407-74c8d53a395e",
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"Detected kernel version 4.4.0, which is below the recommended minimum of 5.5.0; this can cause the process to hang. It is recommended to upgrade the kernel to the minimum version or higher.\n"
]
},
{
"data": {
"text/html": [
"\n",
" <div>\n",
" \n",
" <progress value='865' max='1100' style='width:300px; height:20px; vertical-align: middle;'></progress>\n",
" [ 865/1100 06:23 < 01:44, 2.25 it/s, Epoch 0.26/1]\n",
" </div>\n",
" <table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: left;\">\n",
" <th>Step</th>\n",
" <th>Training Loss</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <td>100</td>\n",
" <td>1.304900</td>\n",
" </tr>\n",
" <tr>\n",
" <td>200</td>\n",
" <td>1.187200</td>\n",
" </tr>\n",
" <tr>\n",
" <td>300</td>\n",
" <td>1.169100</td>\n",
" </tr>\n",
" <tr>\n",
" <td>400</td>\n",
" <td>1.171700</td>\n",
" </tr>\n",
" <tr>\n",
" <td>500</td>\n",
" <td>1.143400</td>\n",
" </tr>\n",
" <tr>\n",
" <td>600</td>\n",
" <td>1.191400</td>\n",
" </tr>\n",
" <tr>\n",
" <td>700</td>\n",
" <td>1.144800</td>\n",
" </tr>\n",
" <tr>\n",
" <td>800</td>\n",
" <td>1.152100</td>\n",
" </tr>\n",
" </tbody>\n",
"</table><p>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"trainer = Trainer(\n",
" model=model,\n",
" train_dataset=tokenized_data,\n",
" args=training_arguments,\n",
" data_collator=DataCollatorForLanguageModeling(tokenizer, mlm=False)\n",
")\n",
"trainer.train()"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "263cc15e-8e9d-4bd8-9708-ec1638bc1165",
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.11.5"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
|