Hugging Face's logo

tthhanh
/
legal_mistral

PEFT
Safetensors
Generated from Trainer
Model card Files Community
legal_mistral / README.md
tthhanh's picture
tthhanh
End of training
bef4cb7 verified
preview code
|
raw
history blame contribute delete
43.7 kB
metadata
base_model: mistralai/Mistral-7B-v0.3
library_name: peft
license: apache-2.0
tags:
  - generated_from_trainer
model-index:
  - name: legal_mistral
    results: []

legal_mistral

This model is a fine-tuned version of mistralai/Mistral-7B-v0.3 on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.7130
  • Law Precision: 0.7976
  • Law Recall: 0.9054
  • Law F1: 0.8481
  • Law Number: 74
  • Violated by Precision: 0.7442
  • Violated by Recall: 0.8767
  • Violated by F1: 0.8050
  • Violated by Number: 73
  • Violated on Precision: 0.4079
  • Violated on Recall: 0.5636
  • Violated on F1: 0.4733
  • Violated on Number: 55
  • Violation Precision: 0.4756
  • Violation Recall: 0.6007
  • Violation F1: 0.5309
  • Violation Number: 601
  • Overall Precision: 0.5204
  • Overall Recall: 0.6513
  • Overall F1: 0.5785
  • Overall Accuracy: 0.9392

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: 0.0001
  • train_batch_size: 16
  • eval_batch_size: 16
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 100

Training results

Training Loss Epoch Step Validation Loss Law Precision Law Recall Law F1 Law Number Violated by Precision Violated by Recall Violated by F1 Violated by Number Violated on Precision Violated on Recall Violated on F1 Violated on Number Violation Precision Violation Recall Violation F1 Violation Number Overall Precision Overall Recall Overall F1 Overall Accuracy
No log 1.0 45 0.3496 0.2927 0.1622 0.2087 74 0.0 0.0 0.0 73 0.0 0.0 0.0 55 0.1594 0.2912 0.2060 601 0.1637 0.2329 0.1923 0.8818
No log 2.0 90 0.2786 0.2857 0.5946 0.3860 74 0.3684 0.6712 0.4757 73 0.1370 0.1818 0.1562 55 0.3021 0.4459 0.3602 601 0.2975 0.4620 0.3620 0.9131
No log 3.0 135 0.2256 0.7356 0.8649 0.7950 74 0.5472 0.7945 0.6480 73 0.2442 0.3818 0.2979 55 0.3269 0.4775 0.3881 601 0.3717 0.5355 0.4388 0.9301
No log 4.0 180 0.2840 0.7794 0.7162 0.7465 74 0.5663 0.6438 0.6026 73 0.2632 0.0909 0.1351 55 0.3212 0.4709 0.3819 601 0.3692 0.4832 0.4186 0.9264
No log 5.0 225 0.3785 0.7273 0.8649 0.7901 74 0.5743 0.7945 0.6667 73 0.3099 0.4 0.3492 55 0.2723 0.4359 0.3353 601 0.3322 0.5056 0.4010 0.9185
No log 6.0 270 0.3050 0.8 0.8649 0.8312 74 0.5943 0.8630 0.7039 73 0.3651 0.4182 0.3898 55 0.3945 0.5973 0.4752 601 0.4392 0.6339 0.5189 0.9356
No log 7.0 315 0.3576 0.75 0.8514 0.7975 74 0.5614 0.8767 0.6845 73 0.2755 0.4909 0.3529 55 0.3720 0.5341 0.4385 601 0.4098 0.5915 0.4842 0.9321
No log 8.0 360 0.4070 0.7949 0.8378 0.8158 74 0.4961 0.8767 0.6337 73 0.2990 0.5273 0.3816 55 0.4488 0.6273 0.5232 601 0.4650 0.6625 0.5465 0.9338
No log 9.0 405 0.4427 0.6535 0.8919 0.7543 74 0.5161 0.8767 0.6497 73 0.2091 0.4182 0.2788 55 0.4059 0.5957 0.4828 601 0.4199 0.6364 0.5059 0.9349
No log 10.0 450 0.5291 0.8148 0.8919 0.8516 74 0.7342 0.7945 0.7632 73 0.4242 0.5091 0.4628 55 0.3529 0.4892 0.4100 601 0.4212 0.5554 0.4791 0.9275
No log 11.0 495 0.3658 0.7927 0.8784 0.8333 74 0.6778 0.8356 0.7485 73 0.4561 0.4727 0.4643 55 0.4259 0.5641 0.4853 601 0.4790 0.6115 0.5372 0.9387
0.2535 12.0 540 0.5794 0.7738 0.8784 0.8228 74 0.6630 0.8356 0.7394 73 0.4242 0.5091 0.4628 55 0.3261 0.4759 0.3870 601 0.3932 0.5479 0.4579 0.9239
0.2535 13.0 585 0.4110 0.7021 0.8919 0.7857 74 0.5727 0.8630 0.6885 73 0.4727 0.4727 0.4727 55 0.4014 0.5923 0.4785 601 0.4459 0.6364 0.5244 0.9349
0.2535 14.0 630 0.5910 0.68 0.9189 0.7816 74 0.6854 0.8356 0.7531 73 0.4079 0.5636 0.4733 55 0.3767 0.5391 0.4435 601 0.4302 0.6027 0.5021 0.9314
0.2535 15.0 675 0.5236 0.7143 0.8784 0.7879 74 0.5909 0.8904 0.7104 73 0.4375 0.5091 0.4706 55 0.4388 0.6323 0.5181 601 0.4757 0.6700 0.5564 0.9382
0.2535 16.0 720 0.4704 0.7391 0.9189 0.8193 74 0.6 0.8630 0.7079 73 0.4429 0.5636 0.4960 55 0.4175 0.5641 0.4798 601 0.4643 0.6239 0.5324 0.9363
0.2535 17.0 765 0.4735 0.7444 0.9054 0.8171 74 0.6139 0.8493 0.7126 73 0.5 0.5455 0.5217 55 0.4302 0.6356 0.5131 601 0.4750 0.6737 0.5572 0.9376
0.2535 18.0 810 0.5859 0.7333 0.8919 0.8049 74 0.5773 0.7671 0.6588 73 0.4815 0.4727 0.4771 55 0.4431 0.5890 0.5057 601 0.4827 0.6252 0.5448 0.9381
0.2535 19.0 855 0.5776 0.7444 0.9054 0.8171 74 0.6552 0.7808 0.7125 73 0.4324 0.5818 0.4961 55 0.4475 0.6240 0.5212 601 0.4876 0.6613 0.5613 0.9398
0.2535 20.0 900 0.5639 0.7711 0.8649 0.8153 74 0.6471 0.7534 0.6962 73 0.4444 0.5091 0.4746 55 0.4185 0.5857 0.4882 601 0.4655 0.6214 0.5323 0.9363
0.2535 21.0 945 0.5959 0.6875 0.8919 0.7765 74 0.6042 0.7945 0.6864 73 0.4127 0.4727 0.4407 55 0.4450 0.6123 0.5154 601 0.4787 0.6451 0.5496 0.9386
0.2535 22.0 990 0.5469 0.8 0.8649 0.8312 74 0.6264 0.7808 0.6951 73 0.4821 0.4909 0.4865 55 0.4362 0.5973 0.5042 601 0.4829 0.6314 0.5472 0.9381
0.0058 23.0 1035 0.4742 0.7901 0.8649 0.8258 74 0.6628 0.7808 0.7170 73 0.2963 0.4364 0.3529 55 0.4322 0.5940 0.5004 601 0.4674 0.6252 0.5349 0.9377
0.0058 24.0 1080 0.4809 0.7363 0.9054 0.8121 74 0.6522 0.8219 0.7273 73 0.4348 0.5455 0.4839 55 0.4330 0.6023 0.5038 601 0.4770 0.6463 0.5489 0.9387
0.0058 25.0 1125 0.5530 0.8049 0.8919 0.8462 74 0.6941 0.8082 0.7468 73 0.3636 0.5091 0.4242 55 0.4596 0.6339 0.5329 601 0.4977 0.6650 0.5693 0.9399
0.0058 26.0 1170 0.5184 0.7952 0.8919 0.8408 74 0.6556 0.8082 0.7239 73 0.4286 0.5455 0.4800 55 0.4561 0.6223 0.5264 601 0.4976 0.6588 0.5670 0.9406
0.0058 27.0 1215 0.5380 0.8049 0.8919 0.8462 74 0.6484 0.8082 0.7195 73 0.4571 0.5818 0.512 55 0.4515 0.6123 0.5198 601 0.4962 0.6538 0.5642 0.9396
0.0058 28.0 1260 0.5645 0.7857 0.8919 0.8354 74 0.6484 0.8082 0.7195 73 0.4348 0.5455 0.4839 55 0.4581 0.6273 0.5295 601 0.4986 0.6625 0.5690 0.9402
0.0058 29.0 1305 0.5867 0.7586 0.8919 0.8199 74 0.6629 0.8082 0.7284 73 0.4493 0.5636 0.5000 55 0.4571 0.6206 0.5265 601 0.4986 0.6588 0.5676 0.9395
0.0058 30.0 1350 0.5698 0.7711 0.8649 0.8153 74 0.7176 0.8356 0.7722 73 0.4179 0.5091 0.4590 55 0.4514 0.5874 0.5105 601 0.4975 0.6301 0.5560 0.9385
0.0058 31.0 1395 0.5533 0.75 0.8919 0.8148 74 0.7126 0.8493 0.7750 73 0.4167 0.5455 0.4724 55 0.4223 0.5790 0.4884 601 0.4725 0.6301 0.5400 0.9367
0.0058 32.0 1440 0.5650 0.8025 0.8784 0.8387 74 0.7241 0.8630 0.7875 73 0.4412 0.5455 0.4878 55 0.4435 0.6140 0.5150 601 0.4934 0.6563 0.5633 0.9388
0.0058 33.0 1485 0.5849 0.75 0.8919 0.8148 74 0.6889 0.8493 0.7607 73 0.4167 0.5455 0.4724 55 0.4355 0.6123 0.5090 601 0.4804 0.6550 0.5543 0.9381
0.0065 34.0 1530 0.6040 0.8784 0.8784 0.8784 74 0.7195 0.8082 0.7613 73 0.4429 0.5636 0.4960 55 0.4728 0.6223 0.5374 601 0.5202 0.6588 0.5813 0.9416
0.0065 35.0 1575 0.6334 0.8333 0.8784 0.8553 74 0.6941 0.8082 0.7468 73 0.4444 0.5818 0.5039 55 0.4707 0.6273 0.5378 601 0.5145 0.6638 0.5797 0.9409
0.0065 36.0 1620 0.6558 0.8442 0.8784 0.8609 74 0.6941 0.8082 0.7468 73 0.4189 0.5636 0.4806 55 0.4795 0.6240 0.5423 601 0.5206 0.6600 0.5821 0.9412
0.0065 37.0 1665 0.6929 0.7473 0.9189 0.8242 74 0.6263 0.8493 0.7209 73 0.3488 0.5455 0.4255 55 0.4421 0.6223 0.5169 601 0.4759 0.6650 0.5548 0.9399
0.0065 38.0 1710 0.7065 0.8228 0.8784 0.8497 74 0.6705 0.8082 0.7329 73 0.4590 0.5091 0.4828 55 0.4432 0.5973 0.5089 601 0.4923 0.6364 0.5551 0.9392
0.0065 39.0 1755 0.5583 0.6947 0.8919 0.7811 74 0.6444 0.7945 0.7117 73 0.4143 0.5273 0.464 55 0.4501 0.6156 0.5200 601 0.4856 0.6513 0.5564 0.9387
0.0065 40.0 1800 0.5268 0.8072 0.9054 0.8535 74 0.6705 0.8082 0.7329 73 0.3889 0.5091 0.4409 55 0.4231 0.6223 0.5037 601 0.4685 0.6575 0.5472 0.9377
0.0065 41.0 1845 0.4682 0.7471 0.8784 0.8075 74 0.5 0.6986 0.5829 73 0.3810 0.5818 0.4604 55 0.3989 0.5874 0.4751 601 0.4326 0.6239 0.5110 0.9361
0.0065 42.0 1890 0.4727 0.7976 0.9054 0.8481 74 0.6526 0.8493 0.7381 73 0.4531 0.5273 0.4874 55 0.4304 0.6173 0.5072 601 0.4787 0.6588 0.5545 0.9400
0.0065 43.0 1935 0.4891 0.8171 0.9054 0.8590 74 0.6061 0.8219 0.6977 73 0.3537 0.5273 0.4234 55 0.4163 0.6040 0.4929 601 0.4573 0.6463 0.5356 0.9373
0.0065 44.0 1980 0.6090 0.8571 0.8919 0.8742 74 0.6344 0.8082 0.7108 73 0.4444 0.5091 0.4746 55 0.4462 0.6007 0.5121 601 0.4933 0.6401 0.5572 0.9344
0.0031 45.0 2025 0.5379 0.8095 0.9189 0.8608 74 0.6019 0.8493 0.7045 73 0.4 0.5455 0.4615 55 0.4463 0.6290 0.5221 601 0.4851 0.6700 0.5628 0.9393
0.0031 46.0 2070 0.6277 0.7701 0.9054 0.8323 74 0.6316 0.8219 0.7143 73 0.4583 0.6 0.5197 55 0.4736 0.6423 0.5452 601 0.5108 0.6800 0.5833 0.9399
0.0031 47.0 2115 0.6039 0.7556 0.9189 0.8293 74 0.6277 0.8082 0.7066 73 0.4154 0.4909 0.45 55 0.4342 0.6206 0.5110 601 0.4756 0.6563 0.5515 0.9380
0.0031 48.0 2160 0.5597 0.7363 0.9054 0.8121 74 0.6941 0.8082 0.7468 73 0.4412 0.5455 0.4878 55 0.4806 0.6406 0.5492 601 0.5177 0.6737 0.5855 0.9417
0.0031 49.0 2205 0.6343 0.8333 0.8784 0.8553 74 0.7654 0.8493 0.8052 73 0.4286 0.5455 0.4800 55 0.4816 0.6323 0.5468 601 0.5275 0.6687 0.5898 0.9420
0.0031 50.0 2250 0.6156 0.7312 0.9189 0.8144 74 0.6593 0.8219 0.7317 73 0.4576 0.4909 0.4737 55 0.4605 0.6306 0.5323 601 0.5009 0.6650 0.5714 0.9394
0.0031 51.0 2295 0.5474 0.8784 0.8784 0.8784 74 0.7143 0.8219 0.7643 73 0.5161 0.5818 0.5470 55 0.4663 0.6323 0.5367 601 0.5188 0.6687 0.5843 0.9403
0.0031 52.0 2340 0.6359 0.7416 0.8919 0.8098 74 0.6139 0.8493 0.7126 73 0.4051 0.5818 0.4776 55 0.4392 0.5707 0.4964 601 0.4790 0.6264 0.5429 0.9377
0.0031 53.0 2385 0.7374 0.8025 0.8784 0.8387 74 0.7176 0.8356 0.7722 73 0.4603 0.5273 0.4915 55 0.4928 0.6306 0.5533 601 0.5351 0.6650 0.5930 0.9420
0.0031 54.0 2430 0.7585 0.75 0.8919 0.8148 74 0.6275 0.8767 0.7314 73 0.4328 0.5273 0.4754 55 0.4859 0.6290 0.5482 601 0.5188 0.6687 0.5843 0.9417
0.0031 55.0 2475 0.7661 0.7614 0.9054 0.8272 74 0.6495 0.8630 0.7412 73 0.4545 0.5455 0.4959 55 0.4890 0.6306 0.5509 601 0.5253 0.6712 0.5894 0.9423
0.0047 56.0 2520 0.7124 0.8354 0.8919 0.8627 74 0.6933 0.7123 0.7027 73 0.4918 0.5455 0.5172 55 0.4885 0.6373 0.5531 601 0.5315 0.6613 0.5893 0.9413
0.0047 57.0 2565 0.7115 0.7791 0.9054 0.8375 74 0.6860 0.8082 0.7421 73 0.4286 0.5455 0.4800 55 0.4800 0.6406 0.5488 601 0.5182 0.6737 0.5858 0.9414
0.0047 58.0 2610 0.7209 0.7791 0.9054 0.8375 74 0.6860 0.8082 0.7421 73 0.4143 0.5273 0.464 55 0.4807 0.6423 0.5499 601 0.5177 0.6737 0.5855 0.9414
0.0047 59.0 2655 0.7296 0.7791 0.9054 0.8375 74 0.6860 0.8082 0.7421 73 0.4493 0.5636 0.5000 55 0.4843 0.6423 0.5522 601 0.5231 0.6762 0.5899 0.9416
0.0047 60.0 2700 0.7469 0.7791 0.9054 0.8375 74 0.6860 0.8082 0.7421 73 0.4559 0.5636 0.5041 55 0.4855 0.6406 0.5524 601 0.5247 0.6750 0.5904 0.9415
0.0047 61.0 2745 0.7983 0.8049 0.8919 0.8462 74 0.7662 0.8082 0.7867 73 0.4839 0.5455 0.5128 55 0.4930 0.6406 0.5572 601 0.5389 0.6725 0.5983 0.9405
0.0047 62.0 2790 0.7982 0.7976 0.9054 0.8481 74 0.7561 0.8493 0.8000 73 0.5 0.6182 0.5528 55 0.4924 0.6456 0.5587 601 0.5391 0.6862 0.6038 0.9405
0.0047 63.0 2835 0.8038 0.8072 0.9054 0.8535 74 0.7561 0.8493 0.8000 73 0.4853 0.6 0.5366 55 0.4917 0.6423 0.5570 601 0.5383 0.6824 0.6019 0.9407
0.0047 64.0 2880 0.7946 0.8072 0.9054 0.8535 74 0.7561 0.8493 0.8000 73 0.4559 0.5636 0.5041 55 0.4898 0.6406 0.5552 601 0.5348 0.6787 0.5982 0.9412
0.0047 65.0 2925 0.7979 0.8072 0.9054 0.8535 74 0.7561 0.8493 0.8000 73 0.4848 0.5818 0.5289 55 0.4911 0.6423 0.5566 601 0.5379 0.6812 0.6011 0.9410
0.0047 66.0 2970 0.8016 0.8072 0.9054 0.8535 74 0.7561 0.8493 0.8000 73 0.4412 0.5455 0.4878 55 0.4848 0.6373 0.5507 601 0.5298 0.6750 0.5936 0.9409
0.0004 67.0 3015 0.8049 0.7976 0.9054 0.8481 74 0.7561 0.8493 0.8000 73 0.4627 0.5636 0.5082 55 0.4848 0.6373 0.5507 601 0.5308 0.6762 0.5947 0.9408
0.0004 68.0 3060 0.8076 0.8072 0.9054 0.8535 74 0.7561 0.8493 0.8000 73 0.4627 0.5636 0.5082 55 0.4842 0.6356 0.5496 601 0.5309 0.6750 0.5943 0.9409
0.0004 69.0 3105 0.8572 0.7952 0.8919 0.8408 74 0.7229 0.8219 0.7692 73 0.4091 0.4909 0.4463 55 0.4624 0.5724 0.5115 601 0.5092 0.6189 0.5587 0.9368
0.0004 70.0 3150 0.8463 0.7444 0.9054 0.8171 74 0.7442 0.8767 0.8050 73 0.4429 0.5636 0.4960 55 0.4893 0.6489 0.5579 601 0.5292 0.6874 0.5980 0.9394
0.0004 71.0 3195 0.8223 0.7528 0.9054 0.8221 74 0.6813 0.8493 0.7561 73 0.4110 0.5455 0.4688 55 0.4446 0.5740 0.5011 601 0.4898 0.6276 0.5502 0.9349
0.0004 72.0 3240 0.7763 0.7528 0.9054 0.8221 74 0.7222 0.8904 0.7975 73 0.4722 0.6182 0.5354 55 0.4834 0.6556 0.5565 601 0.5253 0.6974 0.5993 0.9388
0.0004 73.0 3285 0.7803 0.7363 0.9054 0.8121 74 0.7442 0.8767 0.8050 73 0.4324 0.5818 0.4961 55 0.4875 0.6473 0.5561 601 0.5262 0.6874 0.5961 0.9397
0.0004 74.0 3330 0.7861 0.7363 0.9054 0.8121 74 0.7442 0.8767 0.8050 73 0.4189 0.5636 0.4806 55 0.4887 0.6473 0.5569 601 0.5263 0.6862 0.5957 0.9399
0.0004 75.0 3375 0.7918 0.7528 0.9054 0.8221 74 0.7126 0.8493 0.7750 73 0.4189 0.5636 0.4806 55 0.4905 0.6473 0.5581 601 0.5264 0.6837 0.5948 0.9402
0.0004 76.0 3420 0.8002 0.7444 0.9054 0.8171 74 0.7412 0.8630 0.7975 73 0.4133 0.5636 0.4769 55 0.4899 0.6456 0.5571 601 0.5269 0.6837 0.5951 0.9404
0.0004 77.0 3465 0.8039 0.7444 0.9054 0.8171 74 0.7209 0.8493 0.7799 73 0.4133 0.5636 0.4769 55 0.4924 0.6473 0.5593 601 0.5274 0.6837 0.5954 0.9406
0.0029 78.0 3510 0.8081 0.7528 0.9054 0.8221 74 0.7209 0.8493 0.7799 73 0.4189 0.5636 0.4806 55 0.4887 0.6456 0.5563 601 0.5254 0.6824 0.5937 0.9405
0.0029 79.0 3555 0.8118 0.7363 0.9054 0.8121 74 0.7209 0.8493 0.7799 73 0.4384 0.5818 0.5 55 0.4911 0.6456 0.5579 601 0.5279 0.6837 0.5958 0.9405
0.0029 80.0 3600 0.8164 0.7528 0.9054 0.8221 74 0.7294 0.8493 0.7848 73 0.4110 0.5455 0.4688 55 0.4898 0.6406 0.5552 601 0.5266 0.6775 0.5926 0.9407
0.0029 81.0 3645 0.8433 0.7738 0.8784 0.8228 74 0.7381 0.8493 0.7898 73 0.4091 0.4909 0.4463 55 0.5027 0.6123 0.5521 601 0.5404 0.6501 0.5902 0.9412
0.0029 82.0 3690 0.8455 0.7738 0.8784 0.8228 74 0.7381 0.8493 0.7898 73 0.4308 0.5091 0.4667 55 0.5 0.6106 0.5498 601 0.5398 0.6501 0.5898 0.9412
0.0029 83.0 3735 0.8470 0.7647 0.8784 0.8176 74 0.7381 0.8493 0.7898 73 0.4091 0.4909 0.4463 55 0.4993 0.6123 0.5501 601 0.5370 0.6501 0.5882 0.9413
0.0029 84.0 3780 0.8478 0.7738 0.8784 0.8228 74 0.7381 0.8493 0.7898 73 0.4462 0.5273 0.4833 55 0.5007 0.6123 0.5509 601 0.5413 0.6526 0.5918 0.9414
0.0029 85.0 3825 0.8493 0.7558 0.8784 0.8125 74 0.7381 0.8493 0.7898 73 0.4091 0.4909 0.4463 55 0.5007 0.6123 0.5509 601 0.5376 0.6501 0.5885 0.9413
0.0029 86.0 3870 0.8384 0.7386 0.8784 0.8025 74 0.7381 0.8493 0.7898 73 0.4328 0.5273 0.4754 55 0.4966 0.6156 0.5498 601 0.5346 0.6550 0.5887 0.9412
0.0029 87.0 3915 0.7411 0.7444 0.9054 0.8171 74 0.7273 0.8767 0.7950 73 0.4789 0.6182 0.5397 55 0.4864 0.6240 0.5466 601 0.5294 0.6725 0.5924 0.9420
0.0029 88.0 3960 0.7434 0.7975 0.8514 0.8235 74 0.7209 0.8493 0.7799 73 0.4167 0.5455 0.4724 55 0.4872 0.6007 0.5380 601 0.5276 0.6426 0.5794 0.9391
0.0021 89.0 4005 0.7456 0.8 0.8649 0.8312 74 0.6932 0.8356 0.7578 73 0.4028 0.5273 0.4567 55 0.4885 0.6023 0.5395 601 0.5260 0.6426 0.5785 0.9392
0.0021 90.0 4050 0.7476 0.8025 0.8784 0.8387 74 0.6932 0.8356 0.7578 73 0.4110 0.5455 0.4688 55 0.4872 0.6023 0.5387 601 0.5259 0.6451 0.5794 0.9393
0.0021 91.0 4095 0.7483 0.7831 0.8784 0.8280 74 0.7126 0.8493 0.7750 73 0.4247 0.5636 0.4844 55 0.4885 0.6023 0.5395 601 0.5285 0.6476 0.5820 0.9393
0.0021 92.0 4140 0.7495 0.7857 0.8919 0.8354 74 0.7045 0.8493 0.7702 73 0.4189 0.5636 0.4806 55 0.4912 0.6040 0.5418 601 0.5299 0.6501 0.5839 0.9394
0.0021 93.0 4185 0.7514 0.7857 0.8919 0.8354 74 0.7045 0.8493 0.7702 73 0.4189 0.5636 0.4806 55 0.4959 0.6057 0.5453 601 0.5337 0.6513 0.5867 0.9395
0.0021 94.0 4230 0.7520 0.7857 0.8919 0.8354 74 0.7126 0.8493 0.7750 73 0.4247 0.5636 0.4844 55 0.4912 0.6040 0.5418 601 0.5310 0.6501 0.5845 0.9394
0.0021 95.0 4275 0.7500 0.7952 0.8919 0.8408 74 0.7126 0.8493 0.7750 73 0.4247 0.5636 0.4844 55 0.4639 0.5774 0.5145 601 0.5106 0.6301 0.5641 0.9367
0.0021 96.0 4320 0.7505 0.7952 0.8919 0.8408 74 0.7126 0.8493 0.7750 73 0.4247 0.5636 0.4844 55 0.4601 0.5757 0.5115 601 0.5075 0.6289 0.5617 0.9369
0.0021 97.0 4365 0.7136 0.7976 0.9054 0.8481 74 0.7241 0.8630 0.7875 73 0.4079 0.5636 0.4733 55 0.4756 0.5990 0.5302 601 0.5189 0.6488 0.5766 0.9390
0.0021 98.0 4410 0.7125 0.7976 0.9054 0.8481 74 0.7273 0.8767 0.7950 73 0.4079 0.5636 0.4733 55 0.4749 0.5990 0.5298 601 0.5189 0.6501 0.5771 0.9393
0.0021 99.0 4455 0.7130 0.7976 0.9054 0.8481 74 0.7273 0.8767 0.7950 73 0.4079 0.5636 0.4733 55 0.4763 0.6007 0.5313 601 0.5199 0.6513 0.5782 0.9393
0.0015 100.0 4500 0.7130 0.7976 0.9054 0.8481 74 0.7442 0.8767 0.8050 73 0.4079 0.5636 0.4733 55 0.4756 0.6007 0.5309 601 0.5204 0.6513 0.5785 0.9392

Framework versions

  • PEFT 0.12.0
  • Transformers 4.44.0
  • Pytorch 2.4.0+cu121
  • Datasets 2.20.0
  • Tokenizers 0.19.1