--- base_model: Qwen/Qwen2.5-0.5B-Instruct library_name: peft license: apache-2.0 tags: - trl - sft - generated_from_trainer model-index: - name: quen_2.5_qlora results: [] --- # quen_2.5_qlora This model is a fine-tuned version of [Qwen/Qwen2.5-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-0.5B-Instruct) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 0.7671 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-06 - train_batch_size: 8 - eval_batch_size: 8 - seed: 0 - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments - lr_scheduler_type: cosine - lr_scheduler_warmup_ratio: 0.01 - num_epochs: 40 ### Training results | Training Loss | Epoch | Step | Validation Loss | |:-------------:|:-------:|:----:|:---------------:| | 3.1118 | 0.0811 | 3 | 3.2024 | | 3.0902 | 0.1622 | 6 | 3.2023 | | 2.9193 | 0.2432 | 9 | 3.1908 | | 3.0231 | 0.3243 | 12 | 3.1700 | | 3.0429 | 0.4054 | 15 | 3.1323 | | 2.9739 | 0.4865 | 18 | 3.0926 | | 2.9118 | 0.5676 | 21 | 3.0477 | | 2.8564 | 0.6486 | 24 | 2.9984 | | 2.9689 | 0.7297 | 27 | 2.9489 | | 2.8155 | 0.8108 | 30 | 2.8946 | | 2.8495 | 0.8919 | 33 | 2.8411 | | 2.7311 | 0.9730 | 36 | 2.7843 | | 2.6327 | 1.0541 | 39 | 2.7375 | | 2.6728 | 1.1351 | 42 | 2.6747 | | 2.5236 | 1.2162 | 45 | 2.6151 | | 2.5009 | 1.2973 | 48 | 2.5595 | | 2.4129 | 1.3784 | 51 | 2.5030 | | 2.3506 | 1.4595 | 54 | 2.4369 | | 2.3542 | 1.5405 | 57 | 2.3803 | | 2.237 | 1.6216 | 60 | 2.3189 | | 2.3302 | 1.7027 | 63 | 2.2589 | | 2.1679 | 1.7838 | 66 | 2.2005 | | 2.1406 | 1.8649 | 69 | 2.1355 | | 2.0373 | 1.9459 | 72 | 2.0689 | | 1.9979 | 2.0270 | 75 | 2.0098 | | 2.0711 | 2.1081 | 78 | 1.9351 | | 1.8819 | 2.1892 | 81 | 1.8753 | | 1.7832 | 2.2703 | 84 | 1.8243 | | 1.7165 | 2.3514 | 87 | 1.7668 | | 1.6765 | 2.4324 | 90 | 1.7111 | | 1.6243 | 2.5135 | 93 | 1.6613 | | 1.6819 | 2.5946 | 96 | 1.6154 | | 1.6006 | 2.6757 | 99 | 1.5679 | | 1.4845 | 2.7568 | 102 | 1.5229 | | 1.4014 | 2.8378 | 105 | 1.4728 | | 1.452 | 2.9189 | 108 | 1.4313 | | 1.3642 | 3.0 | 111 | 1.3985 | | 1.3571 | 3.0811 | 114 | 1.3647 | | 1.4434 | 3.1622 | 117 | 1.3416 | | 1.3829 | 3.2432 | 120 | 1.3206 | | 1.3319 | 3.3243 | 123 | 1.3000 | | 1.2262 | 3.4054 | 126 | 1.2851 | | 1.2693 | 3.4865 | 129 | 1.2711 | | 1.264 | 3.5676 | 132 | 1.2588 | | 1.1851 | 3.6486 | 135 | 1.2470 | | 1.2656 | 3.7297 | 138 | 1.2380 | | 1.205 | 3.8108 | 141 | 1.2244 | | 1.2115 | 3.8919 | 144 | 1.2109 | | 1.1366 | 3.9730 | 147 | 1.1997 | | 1.1794 | 4.0541 | 150 | 1.1929 | | 1.171 | 4.1351 | 153 | 1.1805 | | 1.0875 | 4.2162 | 156 | 1.1714 | | 1.1192 | 4.2973 | 159 | 1.1619 | | 1.1082 | 4.3784 | 162 | 1.1548 | | 1.0923 | 4.4595 | 165 | 1.1465 | | 1.1731 | 4.5405 | 168 | 1.1397 | | 1.2138 | 4.6216 | 171 | 1.1315 | | 1.2322 | 4.7027 | 174 | 1.1223 | | 1.0893 | 4.7838 | 177 | 1.1179 | | 1.1414 | 4.8649 | 180 | 1.1116 | | 1.0242 | 4.9459 | 183 | 1.1058 | | 1.0929 | 5.0270 | 186 | 1.0982 | | 1.0967 | 5.1081 | 189 | 1.0916 | | 1.0666 | 5.1892 | 192 | 1.0866 | | 1.1382 | 5.2703 | 195 | 1.0851 | | 1.0709 | 5.3514 | 198 | 1.0781 | | 1.0904 | 5.4324 | 201 | 1.0742 | | 1.0521 | 5.5135 | 204 | 1.0699 | | 0.9745 | 5.5946 | 207 | 1.0641 | | 1.1268 | 5.6757 | 210 | 1.0624 | | 1.0437 | 5.7568 | 213 | 1.0588 | | 1.0124 | 5.8378 | 216 | 1.0578 | | 1.0217 | 5.9189 | 219 | 1.0511 | | 1.0656 | 6.0 | 222 | 1.0475 | | 1.0841 | 6.0811 | 225 | 1.0454 | | 1.1352 | 6.1622 | 228 | 1.0440 | | 1.0402 | 6.2432 | 231 | 1.0407 | | 1.0042 | 6.3243 | 234 | 1.0326 | | 0.9738 | 6.4054 | 237 | 1.0295 | | 0.9671 | 6.4865 | 240 | 1.0292 | | 1.0515 | 6.5676 | 243 | 1.0282 | | 0.9551 | 6.6486 | 246 | 1.0246 | | 1.0084 | 6.7297 | 249 | 1.0210 | | 0.9964 | 6.8108 | 252 | 1.0188 | | 0.966 | 6.8919 | 255 | 1.0146 | | 1.0284 | 6.9730 | 258 | 1.0113 | | 1.0367 | 7.0541 | 261 | 1.0103 | | 0.9015 | 7.1351 | 264 | 1.0056 | | 0.9097 | 7.2162 | 267 | 1.0043 | | 0.9598 | 7.2973 | 270 | 0.9998 | | 1.1724 | 7.3784 | 273 | 0.9980 | | 0.9607 | 7.4595 | 276 | 0.9947 | | 0.9749 | 7.5405 | 279 | 0.9960 | | 0.9704 | 7.6216 | 282 | 0.9924 | | 0.9855 | 7.7027 | 285 | 0.9899 | | 0.9368 | 7.7838 | 288 | 0.9853 | | 0.9812 | 7.8649 | 291 | 0.9856 | | 0.9809 | 7.9459 | 294 | 0.9809 | | 0.9337 | 8.0270 | 297 | 0.9824 | | 0.8848 | 8.1081 | 300 | 0.9759 | | 0.876 | 8.1892 | 303 | 0.9751 | | 0.97 | 8.2703 | 306 | 0.9734 | | 1.1309 | 8.3514 | 309 | 0.9726 | | 0.9012 | 8.4324 | 312 | 0.9709 | | 1.0355 | 8.5135 | 315 | 0.9681 | | 0.9047 | 8.5946 | 318 | 0.9663 | | 0.9417 | 8.6757 | 321 | 0.9622 | | 0.9266 | 8.7568 | 324 | 0.9613 | | 0.8873 | 8.8378 | 327 | 0.9625 | | 0.9364 | 8.9189 | 330 | 0.9598 | | 0.9885 | 9.0 | 333 | 0.9539 | | 0.91 | 9.0811 | 336 | 0.9538 | | 1.0834 | 9.1622 | 339 | 0.9522 | | 0.8694 | 9.2432 | 342 | 0.9502 | | 1.0554 | 9.3243 | 345 | 0.9498 | | 0.9123 | 9.4054 | 348 | 0.9484 | | 0.9542 | 9.4865 | 351 | 0.9449 | | 0.9287 | 9.5676 | 354 | 0.9417 | | 0.8435 | 9.6486 | 357 | 0.9406 | | 0.8419 | 9.7297 | 360 | 0.9374 | | 0.8265 | 9.8108 | 363 | 0.9351 | | 0.8677 | 9.8919 | 366 | 0.9343 | | 0.9989 | 9.9730 | 369 | 0.9341 | | 0.8331 | 10.0541 | 372 | 0.9329 | | 0.8823 | 10.1351 | 375 | 0.9312 | | 0.9312 | 10.2162 | 378 | 0.9299 | | 0.8736 | 10.2973 | 381 | 0.9279 | | 1.0039 | 10.3784 | 384 | 0.9259 | | 0.8728 | 10.4595 | 387 | 0.9249 | | 0.9946 | 10.5405 | 390 | 0.9216 | | 0.8747 | 10.6216 | 393 | 0.9196 | | 0.9043 | 10.7027 | 396 | 0.9183 | | 0.8777 | 10.7838 | 399 | 0.9163 | | 0.8023 | 10.8649 | 402 | 0.9160 | | 0.9002 | 10.9459 | 405 | 0.9128 | | 0.8568 | 11.0270 | 408 | 0.9146 | | 0.9145 | 11.1081 | 411 | 0.9124 | | 0.896 | 11.1892 | 414 | 0.9101 | | 0.8151 | 11.2703 | 417 | 0.9067 | | 0.8352 | 11.3514 | 420 | 0.9060 | | 1.0484 | 11.4324 | 423 | 0.9044 | | 0.8623 | 11.5135 | 426 | 0.9041 | | 0.8942 | 11.5946 | 429 | 0.9022 | | 0.8789 | 11.6757 | 432 | 0.9008 | | 0.9077 | 11.7568 | 435 | 0.9000 | | 0.8 | 11.8378 | 438 | 0.8999 | | 0.8116 | 11.9189 | 441 | 0.8985 | | 0.8382 | 12.0 | 444 | 0.8970 | | 0.8267 | 12.0811 | 447 | 0.8962 | | 0.9168 | 12.1622 | 450 | 0.8947 | | 0.7878 | 12.2432 | 453 | 0.8949 | | 0.8829 | 12.3243 | 456 | 0.8926 | | 0.8465 | 12.4054 | 459 | 0.8935 | | 0.882 | 12.4865 | 462 | 0.8914 | | 0.8265 | 12.5676 | 465 | 0.8896 | | 0.8846 | 12.6486 | 468 | 0.8891 | | 0.7943 | 12.7297 | 471 | 0.8899 | | 0.8846 | 12.8108 | 474 | 0.8883 | | 0.8177 | 12.8919 | 477 | 0.8852 | | 0.8807 | 12.9730 | 480 | 0.8840 | | 0.893 | 13.0541 | 483 | 0.8822 | | 0.7497 | 13.1351 | 486 | 0.8799 | | 0.8803 | 13.2162 | 489 | 0.8785 | | 0.917 | 13.2973 | 492 | 0.8797 | | 0.8162 | 13.3784 | 495 | 0.8783 | | 0.9659 | 13.4595 | 498 | 0.8799 | | 0.8163 | 13.5405 | 501 | 0.8790 | | 0.8139 | 13.6216 | 504 | 0.8753 | | 0.7451 | 13.7027 | 507 | 0.8737 | | 0.7726 | 13.7838 | 510 | 0.8738 | | 0.821 | 13.8649 | 513 | 0.8714 | | 0.8782 | 13.9459 | 516 | 0.8689 | | 0.8563 | 14.0270 | 519 | 0.8700 | | 0.8645 | 14.1081 | 522 | 0.8671 | | 0.9223 | 14.1892 | 525 | 0.8676 | | 0.8396 | 14.2703 | 528 | 0.8682 | | 0.8224 | 14.3514 | 531 | 0.8679 | | 0.7793 | 14.4324 | 534 | 0.8690 | | 0.7911 | 14.5135 | 537 | 0.8650 | | 0.7706 | 14.5946 | 540 | 0.8634 | | 0.7983 | 14.6757 | 543 | 0.8606 | | 0.7409 | 14.7568 | 546 | 0.8611 | | 0.8634 | 14.8378 | 549 | 0.8594 | | 0.8631 | 14.9189 | 552 | 0.8594 | | 0.7624 | 15.0 | 555 | 0.8582 | | 0.8568 | 15.0811 | 558 | 0.8568 | | 0.8833 | 15.1622 | 561 | 0.8542 | | 0.7804 | 15.2432 | 564 | 0.8514 | | 0.9113 | 15.3243 | 567 | 0.8526 | | 0.72 | 15.4054 | 570 | 0.8511 | | 0.8631 | 15.4865 | 573 | 0.8498 | | 0.6486 | 15.5676 | 576 | 0.8507 | | 0.7745 | 15.6486 | 579 | 0.8507 | | 0.8591 | 15.7297 | 582 | 0.8519 | | 0.8479 | 15.8108 | 585 | 0.8515 | | 0.7879 | 15.8919 | 588 | 0.8486 | | 0.7829 | 15.9730 | 591 | 0.8483 | | 0.7271 | 16.0541 | 594 | 0.8451 | | 0.7425 | 16.1351 | 597 | 0.8464 | | 0.7692 | 16.2162 | 600 | 0.8436 | | 0.7492 | 16.2973 | 603 | 0.8459 | | 0.7085 | 16.3784 | 606 | 0.8440 | | 0.7351 | 16.4595 | 609 | 0.8429 | | 0.8593 | 16.5405 | 612 | 0.8412 | | 0.8999 | 16.6216 | 615 | 0.8400 | | 0.8136 | 16.7027 | 618 | 0.8417 | | 0.8415 | 16.7838 | 621 | 0.8393 | | 0.849 | 16.8649 | 624 | 0.8400 | | 0.798 | 16.9459 | 627 | 0.8409 | | 0.7581 | 17.0270 | 630 | 0.8393 | | 0.7244 | 17.1081 | 633 | 0.8376 | | 0.7221 | 17.1892 | 636 | 0.8379 | | 0.8085 | 17.2703 | 639 | 0.8363 | | 0.7364 | 17.3514 | 642 | 0.8357 | | 0.7684 | 17.4324 | 645 | 0.8385 | | 0.7323 | 17.5135 | 648 | 0.8330 | | 0.8999 | 17.5946 | 651 | 0.8334 | | 0.7243 | 17.6757 | 654 | 0.8323 | | 0.741 | 17.7568 | 657 | 0.8300 | | 0.7529 | 17.8378 | 660 | 0.8290 | | 0.9129 | 17.9189 | 663 | 0.8313 | | 0.8043 | 18.0 | 666 | 0.8282 | | 0.838 | 18.0811 | 669 | 0.8294 | | 0.8133 | 18.1622 | 672 | 0.8294 | | 0.708 | 18.2432 | 675 | 0.8283 | | 0.8017 | 18.3243 | 678 | 0.8289 | | 0.9087 | 18.4054 | 681 | 0.8256 | | 0.6983 | 18.4865 | 684 | 0.8260 | | 0.7684 | 18.5676 | 687 | 0.8251 | | 0.6372 | 18.6486 | 690 | 0.8241 | | 0.7369 | 18.7297 | 693 | 0.8261 | | 0.819 | 18.8108 | 696 | 0.8231 | | 0.6806 | 18.8919 | 699 | 0.8244 | | 0.8233 | 18.9730 | 702 | 0.8237 | | 0.7614 | 19.0541 | 705 | 0.8234 | | 0.7862 | 19.1351 | 708 | 0.8212 | | 0.6605 | 19.2162 | 711 | 0.8195 | | 0.8229 | 19.2973 | 714 | 0.8194 | | 0.731 | 19.3784 | 717 | 0.8193 | | 0.783 | 19.4595 | 720 | 0.8187 | | 0.6495 | 19.5405 | 723 | 0.8185 | | 0.8034 | 19.6216 | 726 | 0.8173 | | 0.7064 | 19.7027 | 729 | 0.8177 | | 0.7276 | 19.7838 | 732 | 0.8156 | | 0.8778 | 19.8649 | 735 | 0.8143 | | 0.7399 | 19.9459 | 738 | 0.8126 | | 0.7399 | 20.0270 | 741 | 0.8139 | | 0.7912 | 20.1081 | 744 | 0.8153 | | 0.8063 | 20.1892 | 747 | 0.8120 | | 0.671 | 20.2703 | 750 | 0.8105 | | 0.6342 | 20.3514 | 753 | 0.8113 | | 0.8271 | 20.4324 | 756 | 0.8097 | | 0.6755 | 20.5135 | 759 | 0.8099 | | 0.762 | 20.5946 | 762 | 0.8084 | | 0.9197 | 20.6757 | 765 | 0.8079 | | 0.7844 | 20.7568 | 768 | 0.8094 | | 0.6502 | 20.8378 | 771 | 0.8096 | | 0.6877 | 20.9189 | 774 | 0.8078 | | 0.7705 | 21.0 | 777 | 0.8074 | | 0.6842 | 21.0811 | 780 | 0.8067 | | 0.6799 | 21.1622 | 783 | 0.8066 | | 0.7344 | 21.2432 | 786 | 0.8039 | | 0.6554 | 21.3243 | 789 | 0.8051 | | 0.7007 | 21.4054 | 792 | 0.8051 | | 0.6292 | 21.4865 | 795 | 0.8040 | | 0.7404 | 21.5676 | 798 | 0.8031 | | 0.7976 | 21.6486 | 801 | 0.8030 | | 1.0023 | 21.7297 | 804 | 0.8045 | | 0.6626 | 21.8108 | 807 | 0.8042 | | 0.8212 | 21.8919 | 810 | 0.8019 | | 0.6982 | 21.9730 | 813 | 0.8029 | | 0.7221 | 22.0541 | 816 | 0.8007 | | 0.8042 | 22.1351 | 819 | 0.8013 | | 0.775 | 22.2162 | 822 | 0.7999 | | 0.7614 | 22.2973 | 825 | 0.7971 | | 0.7132 | 22.3784 | 828 | 0.7972 | | 0.647 | 22.4595 | 831 | 0.8001 | | 0.692 | 22.5405 | 834 | 0.7968 | | 0.7775 | 22.6216 | 837 | 0.7976 | | 0.7764 | 22.7027 | 840 | 0.7980 | | 0.6962 | 22.7838 | 843 | 0.7990 | | 0.649 | 22.8649 | 846 | 0.7941 | | 0.7853 | 22.9459 | 849 | 0.7940 | | 0.6808 | 23.0270 | 852 | 0.7959 | | 0.7018 | 23.1081 | 855 | 0.7948 | | 0.6743 | 23.1892 | 858 | 0.7949 | | 0.7512 | 23.2703 | 861 | 0.7926 | | 0.7136 | 23.3514 | 864 | 0.7922 | | 0.6847 | 23.4324 | 867 | 0.7943 | | 0.7309 | 23.5135 | 870 | 0.7910 | | 0.9269 | 23.5946 | 873 | 0.7903 | | 0.7629 | 23.6757 | 876 | 0.7923 | | 0.6551 | 23.7568 | 879 | 0.7896 | | 0.7346 | 23.8378 | 882 | 0.7920 | | 0.7469 | 23.9189 | 885 | 0.7921 | | 0.6343 | 24.0 | 888 | 0.7925 | | 0.7232 | 24.0811 | 891 | 0.7905 | | 0.714 | 24.1622 | 894 | 0.7885 | | 0.6603 | 24.2432 | 897 | 0.7885 | | 0.6798 | 24.3243 | 900 | 0.7892 | | 0.7163 | 24.4054 | 903 | 0.7889 | | 0.8428 | 24.4865 | 906 | 0.7871 | | 0.8125 | 24.5676 | 909 | 0.7875 | | 0.7566 | 24.6486 | 912 | 0.7895 | | 0.7167 | 24.7297 | 915 | 0.7874 | | 0.65 | 24.8108 | 918 | 0.7861 | | 0.6817 | 24.8919 | 921 | 0.7860 | | 0.6185 | 24.9730 | 924 | 0.7879 | | 0.7745 | 25.0541 | 927 | 0.7900 | | 0.8923 | 25.1351 | 930 | 0.7871 | | 0.7395 | 25.2162 | 933 | 0.7834 | | 0.7361 | 25.2973 | 936 | 0.7842 | | 0.676 | 25.3784 | 939 | 0.7835 | | 0.7359 | 25.4595 | 942 | 0.7846 | | 0.6533 | 25.5405 | 945 | 0.7829 | | 0.6989 | 25.6216 | 948 | 0.7848 | | 0.8168 | 25.7027 | 951 | 0.7837 | | 0.6519 | 25.7838 | 954 | 0.7826 | | 0.6951 | 25.8649 | 957 | 0.7840 | | 0.5833 | 25.9459 | 960 | 0.7823 | | 0.617 | 26.0270 | 963 | 0.7812 | | 0.6778 | 26.1081 | 966 | 0.7829 | | 0.6571 | 26.1892 | 969 | 0.7818 | | 0.7921 | 26.2703 | 972 | 0.7811 | | 0.6962 | 26.3514 | 975 | 0.7807 | | 0.8437 | 26.4324 | 978 | 0.7814 | | 0.6147 | 26.5135 | 981 | 0.7813 | | 0.7263 | 26.5946 | 984 | 0.7803 | | 0.6618 | 26.6757 | 987 | 0.7809 | | 0.7502 | 26.7568 | 990 | 0.7835 | | 0.6094 | 26.8378 | 993 | 0.7813 | | 0.6506 | 26.9189 | 996 | 0.7800 | | 0.7927 | 27.0 | 999 | 0.7807 | | 0.8217 | 27.0811 | 1002 | 0.7816 | | 0.5989 | 27.1622 | 1005 | 0.7786 | | 0.7204 | 27.2432 | 1008 | 0.7782 | | 0.6906 | 27.3243 | 1011 | 0.7785 | | 0.7592 | 27.4054 | 1014 | 0.7777 | | 0.8692 | 27.4865 | 1017 | 0.7778 | | 0.587 | 27.5676 | 1020 | 0.7781 | | 0.7139 | 27.6486 | 1023 | 0.7781 | | 0.6367 | 27.7297 | 1026 | 0.7774 | | 0.6502 | 27.8108 | 1029 | 0.7779 | | 0.6956 | 27.8919 | 1032 | 0.7770 | | 0.7137 | 27.9730 | 1035 | 0.7784 | | 0.7062 | 28.0541 | 1038 | 0.7775 | | 0.6568 | 28.1351 | 1041 | 0.7782 | | 0.7612 | 28.2162 | 1044 | 0.7766 | | 0.7177 | 28.2973 | 1047 | 0.7765 | | 0.6537 | 28.3784 | 1050 | 0.7776 | | 0.6742 | 28.4595 | 1053 | 0.7773 | | 0.724 | 28.5405 | 1056 | 0.7778 | | 0.8277 | 28.6216 | 1059 | 0.7763 | | 0.609 | 28.7027 | 1062 | 0.7767 | | 0.5459 | 28.7838 | 1065 | 0.7781 | | 0.8179 | 28.8649 | 1068 | 0.7769 | | 0.6419 | 28.9459 | 1071 | 0.7754 | | 0.6947 | 29.0270 | 1074 | 0.7745 | | 0.71 | 29.1081 | 1077 | 0.7751 | | 0.5664 | 29.1892 | 1080 | 0.7747 | | 0.7678 | 29.2703 | 1083 | 0.7741 | | 0.7829 | 29.3514 | 1086 | 0.7732 | | 0.7294 | 29.4324 | 1089 | 0.7729 | | 0.679 | 29.5135 | 1092 | 0.7752 | | 0.6838 | 29.5946 | 1095 | 0.7739 | | 0.6918 | 29.6757 | 1098 | 0.7731 | | 0.6563 | 29.7568 | 1101 | 0.7727 | | 0.6946 | 29.8378 | 1104 | 0.7742 | | 0.6884 | 29.9189 | 1107 | 0.7729 | | 0.6851 | 30.0 | 1110 | 0.7744 | | 0.5865 | 30.0811 | 1113 | 0.7744 | | 0.6906 | 30.1622 | 1116 | 0.7746 | | 0.6716 | 30.2432 | 1119 | 0.7751 | | 0.7492 | 30.3243 | 1122 | 0.7736 | | 0.6608 | 30.4054 | 1125 | 0.7709 | | 0.6577 | 30.4865 | 1128 | 0.7710 | | 0.7475 | 30.5676 | 1131 | 0.7722 | | 0.7643 | 30.6486 | 1134 | 0.7694 | | 0.8186 | 30.7297 | 1137 | 0.7711 | | 0.7465 | 30.8108 | 1140 | 0.7724 | | 0.6621 | 30.8919 | 1143 | 0.7728 | | 0.579 | 30.9730 | 1146 | 0.7713 | | 0.6014 | 31.0541 | 1149 | 0.7707 | | 0.7663 | 31.1351 | 1152 | 0.7697 | | 0.6609 | 31.2162 | 1155 | 0.7719 | | 0.7984 | 31.2973 | 1158 | 0.7715 | | 0.7166 | 31.3784 | 1161 | 0.7715 | | 0.7276 | 31.4595 | 1164 | 0.7712 | | 0.6179 | 31.5405 | 1167 | 0.7681 | | 0.621 | 31.6216 | 1170 | 0.7707 | | 0.743 | 31.7027 | 1173 | 0.7711 | | 0.6733 | 31.7838 | 1176 | 0.7706 | | 0.6066 | 31.8649 | 1179 | 0.7716 | | 0.6787 | 31.9459 | 1182 | 0.7713 | | 0.812 | 32.0270 | 1185 | 0.7708 | | 0.7022 | 32.1081 | 1188 | 0.7695 | | 0.6709 | 32.1892 | 1191 | 0.7721 | | 0.5536 | 32.2703 | 1194 | 0.7716 | | 0.7462 | 32.3514 | 1197 | 0.7693 | | 0.7817 | 32.4324 | 1200 | 0.7686 | | 0.7624 | 32.5135 | 1203 | 0.7719 | | 0.6346 | 32.5946 | 1206 | 0.7696 | | 0.6284 | 32.6757 | 1209 | 0.7717 | | 0.654 | 32.7568 | 1212 | 0.7708 | | 0.6406 | 32.8378 | 1215 | 0.7707 | | 0.752 | 32.9189 | 1218 | 0.7690 | | 0.5956 | 33.0 | 1221 | 0.7713 | | 0.6772 | 33.0811 | 1224 | 0.7701 | | 0.5034 | 33.1622 | 1227 | 0.7693 | | 0.6292 | 33.2432 | 1230 | 0.7687 | | 0.7374 | 33.3243 | 1233 | 0.7693 | | 0.5385 | 33.4054 | 1236 | 0.7678 | | 0.7198 | 33.4865 | 1239 | 0.7686 | | 0.7642 | 33.5676 | 1242 | 0.7695 | | 0.6984 | 33.6486 | 1245 | 0.7682 | | 0.776 | 33.7297 | 1248 | 0.7694 | | 0.7073 | 33.8108 | 1251 | 0.7700 | | 0.8016 | 33.8919 | 1254 | 0.7683 | | 0.7812 | 33.9730 | 1257 | 0.7662 | | 0.578 | 34.0541 | 1260 | 0.7681 | | 0.7074 | 34.1351 | 1263 | 0.7679 | | 0.6142 | 34.2162 | 1266 | 0.7669 | | 0.6469 | 34.2973 | 1269 | 0.7675 | | 0.7334 | 34.3784 | 1272 | 0.7669 | | 0.7086 | 34.4595 | 1275 | 0.7675 | | 0.6302 | 34.5405 | 1278 | 0.7684 | | 0.6576 | 34.6216 | 1281 | 0.7687 | | 0.7496 | 34.7027 | 1284 | 0.7667 | | 0.7836 | 34.7838 | 1287 | 0.7671 | | 0.6405 | 34.8649 | 1290 | 0.7679 | | 0.6088 | 34.9459 | 1293 | 0.7681 | | 0.7511 | 35.0270 | 1296 | 0.7697 | | 0.7591 | 35.1081 | 1299 | 0.7680 | | 0.6207 | 35.1892 | 1302 | 0.7689 | | 0.651 | 35.2703 | 1305 | 0.7660 | | 0.6758 | 35.3514 | 1308 | 0.7694 | | 0.7277 | 35.4324 | 1311 | 0.7680 | | 0.7118 | 35.5135 | 1314 | 0.7663 | | 0.706 | 35.5946 | 1317 | 0.7669 | | 0.6595 | 35.6757 | 1320 | 0.7678 | | 0.7253 | 35.7568 | 1323 | 0.7688 | | 0.582 | 35.8378 | 1326 | 0.7694 | | 0.7094 | 35.9189 | 1329 | 0.7684 | | 0.7042 | 36.0 | 1332 | 0.7686 | | 0.6486 | 36.0811 | 1335 | 0.7664 | | 0.6691 | 36.1622 | 1338 | 0.7678 | | 0.7937 | 36.2432 | 1341 | 0.7672 | | 0.6343 | 36.3243 | 1344 | 0.7670 | | 0.76 | 36.4054 | 1347 | 0.7674 | | 0.5929 | 36.4865 | 1350 | 0.7690 | | 0.6485 | 36.5676 | 1353 | 0.7674 | | 0.7451 | 36.6486 | 1356 | 0.7663 | | 0.6367 | 36.7297 | 1359 | 0.7691 | | 0.6192 | 36.8108 | 1362 | 0.7656 | | 0.7042 | 36.8919 | 1365 | 0.7682 | | 0.6886 | 36.9730 | 1368 | 0.7682 | | 0.8111 | 37.0541 | 1371 | 0.7690 | | 0.6443 | 37.1351 | 1374 | 0.7690 | | 0.6387 | 37.2162 | 1377 | 0.7679 | | 0.7861 | 37.2973 | 1380 | 0.7668 | | 0.6397 | 37.3784 | 1383 | 0.7670 | | 0.6467 | 37.4595 | 1386 | 0.7688 | | 0.6977 | 37.5405 | 1389 | 0.7699 | | 0.7833 | 37.6216 | 1392 | 0.7672 | | 0.6164 | 37.7027 | 1395 | 0.7675 | | 0.7457 | 37.7838 | 1398 | 0.7690 | | 0.6477 | 37.8649 | 1401 | 0.7681 | | 0.7251 | 37.9459 | 1404 | 0.7674 | | 0.5642 | 38.0270 | 1407 | 0.7672 | | 0.786 | 38.1081 | 1410 | 0.7660 | | 0.7014 | 38.1892 | 1413 | 0.7683 | | 0.7747 | 38.2703 | 1416 | 0.7659 | | 0.631 | 38.3514 | 1419 | 0.7675 | | 0.6787 | 38.4324 | 1422 | 0.7671 | | 0.6388 | 38.5135 | 1425 | 0.7684 | | 0.5745 | 38.5946 | 1428 | 0.7666 | | 0.6253 | 38.6757 | 1431 | 0.7668 | | 0.6611 | 38.7568 | 1434 | 0.7688 | | 0.6129 | 38.8378 | 1437 | 0.7666 | | 0.7588 | 38.9189 | 1440 | 0.7670 | | 0.7615 | 39.0 | 1443 | 0.7664 | | 0.7449 | 39.0811 | 1446 | 0.7674 | | 0.7012 | 39.1622 | 1449 | 0.7666 | | 0.788 | 39.2432 | 1452 | 0.7676 | | 0.5958 | 39.3243 | 1455 | 0.7666 | | 0.675 | 39.4054 | 1458 | 0.7670 | | 0.6761 | 39.4865 | 1461 | 0.7676 | | 0.7046 | 39.5676 | 1464 | 0.7669 | | 0.6198 | 39.6486 | 1467 | 0.7673 | | 0.6646 | 39.7297 | 1470 | 0.7670 | | 0.6161 | 39.8108 | 1473 | 0.7677 | | 0.7152 | 39.8919 | 1476 | 0.7676 | | 0.7365 | 39.9730 | 1479 | 0.7671 | ### Framework versions - PEFT 0.13.2 - Transformers 4.46.0 - Pytorch 2.4.0 - Datasets 3.0.1 - Tokenizers 0.20.0