legal_qwen / README.md
tthhanh's picture
End of training
0de9c53 verified
metadata
base_model: Qwen/Qwen2-7B
library_name: peft
license: apache-2.0
tags:
  - generated_from_trainer
model-index:
  - name: legal_qwen
    results: []

legal_qwen

This model is a fine-tuned version of Qwen/Qwen2-7B on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 1.0383
  • Law Precision: 0.62
  • Law Recall: 0.8378
  • Law F1: 0.7126
  • Law Number: 74
  • Violated by Precision: 0.5253
  • Violated by Recall: 0.7222
  • Violated by F1: 0.6082
  • Violated by Number: 72
  • Violated on Precision: 0.35
  • Violated on Recall: 0.4286
  • Violated on F1: 0.3853
  • Violated on Number: 49
  • Violation Precision: 0.3881
  • Violation Recall: 0.5386
  • Violation F1: 0.4512
  • Violation Number: 596
  • Overall Precision: 0.4199
  • Overall Recall: 0.5765
  • Overall F1: 0.4859
  • Overall Accuracy: 0.9180

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 0.6704 0.0323 0.0135 0.0190 74 0.0 0.0 0.0 72 0.0 0.0 0.0 49 0.0108 0.0319 0.0161 596 0.0110 0.0253 0.0153 0.7892
No log 2.0 90 0.4076 0.1795 0.1892 0.1842 74 0.2041 0.1389 0.1653 72 0.0 0.0 0.0 49 0.0865 0.1544 0.1109 596 0.0971 0.1466 0.1168 0.8655
No log 3.0 135 0.3604 0.2936 0.4324 0.3497 74 0.2887 0.3889 0.3314 72 0.1139 0.1837 0.1406 49 0.2060 0.3691 0.2644 596 0.2136 0.3654 0.2696 0.8854
No log 4.0 180 0.3332 0.3279 0.2703 0.2963 74 0.4648 0.4583 0.4615 72 0.1149 0.2041 0.1471 49 0.2134 0.3356 0.2609 596 0.2275 0.3325 0.2702 0.8958
No log 5.0 225 0.3371 0.4216 0.5811 0.4886 74 0.4190 0.6111 0.4972 72 0.1558 0.2449 0.1905 49 0.2816 0.4144 0.3354 596 0.2980 0.4374 0.3545 0.9058
No log 6.0 270 0.4870 0.4690 0.7162 0.5668 74 0.2806 0.5417 0.3697 72 0.1182 0.2653 0.1635 49 0.3350 0.5503 0.4165 596 0.3229 0.5474 0.4062 0.8931
No log 7.0 315 0.4646 0.4898 0.6486 0.5581 74 0.4190 0.6111 0.4972 72 0.1831 0.2653 0.2167 49 0.3071 0.4195 0.3546 596 0.3263 0.4488 0.3779 0.9071
No log 8.0 360 0.4911 0.5327 0.7703 0.6298 74 0.4231 0.6111 0.5 72 0.1616 0.3265 0.2162 49 0.3518 0.5218 0.4203 596 0.3585 0.5411 0.4312 0.9072
No log 9.0 405 0.5094 0.5179 0.7838 0.6237 74 0.3721 0.6667 0.4776 72 0.2632 0.4082 0.32 49 0.3204 0.4849 0.3858 596 0.3404 0.5247 0.4129 0.9064
No log 10.0 450 0.4695 0.6180 0.7432 0.6748 74 0.5172 0.625 0.5660 72 0.2090 0.2857 0.2414 49 0.2876 0.4295 0.3445 596 0.3266 0.4678 0.3846 0.9103
No log 11.0 495 0.5086 0.6042 0.7838 0.6824 74 0.5 0.6528 0.5663 72 0.2537 0.3469 0.2931 49 0.3303 0.4866 0.3935 596 0.3630 0.5209 0.4278 0.9135
0.3466 12.0 540 0.5226 0.6629 0.7973 0.7239 74 0.4667 0.6806 0.5537 72 0.1379 0.2449 0.1765 49 0.3281 0.4916 0.3936 596 0.3518 0.5221 0.4204 0.9140
0.3466 13.0 585 0.5519 0.5490 0.7568 0.6364 74 0.4122 0.75 0.5320 72 0.2424 0.3265 0.2783 49 0.3381 0.5168 0.4088 596 0.3587 0.5487 0.4338 0.9110
0.3466 14.0 630 0.6075 0.4957 0.7703 0.6032 74 0.4215 0.7083 0.5285 72 0.2346 0.3878 0.2923 49 0.3681 0.5453 0.4395 596 0.3767 0.5714 0.4540 0.9142
0.3466 15.0 675 0.6533 0.6905 0.7838 0.7342 74 0.4659 0.5694 0.5125 72 0.24 0.2449 0.2424 49 0.3459 0.4614 0.3954 596 0.3795 0.4880 0.4270 0.9123
0.3466 16.0 720 0.6310 0.5534 0.7703 0.6441 74 0.5096 0.7361 0.6023 72 0.2024 0.3469 0.2556 49 0.3502 0.5117 0.4158 596 0.3718 0.5461 0.4424 0.9171
0.3466 17.0 765 0.7060 0.5234 0.7568 0.6188 74 0.4561 0.7222 0.5591 72 0.2308 0.3673 0.2835 49 0.3566 0.5487 0.4323 596 0.3725 0.5727 0.4514 0.9102
0.3466 18.0 810 0.6275 0.5514 0.7973 0.6519 74 0.5306 0.7222 0.6118 72 0.2537 0.3469 0.2931 49 0.3589 0.5017 0.4185 596 0.3864 0.5398 0.4504 0.9158
0.3466 19.0 855 0.6179 0.5514 0.7973 0.6519 74 0.4757 0.6806 0.56 72 0.1967 0.2449 0.2182 49 0.3341 0.5201 0.4068 596 0.3586 0.5436 0.4322 0.9144
0.3466 20.0 900 0.7150 0.5514 0.7973 0.6519 74 0.4694 0.6389 0.5412 72 0.2727 0.3673 0.3130 49 0.3102 0.4581 0.3699 596 0.3440 0.5006 0.4078 0.9132
0.3466 21.0 945 0.7231 0.5673 0.7973 0.6629 74 0.4421 0.5833 0.5030 72 0.2759 0.3265 0.2991 49 0.3344 0.5352 0.4116 596 0.3600 0.5512 0.4356 0.9121
0.3466 22.0 990 0.7431 0.5126 0.8243 0.6321 74 0.4274 0.7361 0.5408 72 0.2073 0.3469 0.2595 49 0.3268 0.4782 0.3883 596 0.3475 0.5259 0.4185 0.9109
0.0235 23.0 1035 0.7899 0.6667 0.8378 0.7425 74 0.5169 0.6389 0.5714 72 0.2419 0.3061 0.2703 49 0.3252 0.4933 0.392 596 0.3632 0.5272 0.4301 0.9134
0.0235 24.0 1080 0.7823 0.5575 0.8514 0.6738 74 0.4609 0.7361 0.5668 72 0.2361 0.3469 0.2810 49 0.3421 0.5034 0.4073 596 0.3679 0.5474 0.4400 0.9152
0.0235 25.0 1125 0.8200 0.4593 0.8378 0.5933 74 0.4472 0.7639 0.5641 72 0.1980 0.4082 0.2667 49 0.3596 0.5503 0.4350 596 0.3659 0.5879 0.4510 0.9115
0.0235 26.0 1170 0.7593 0.5619 0.7973 0.6592 74 0.4522 0.7222 0.5561 72 0.2432 0.3673 0.2927 49 0.3409 0.5268 0.4140 596 0.3646 0.5601 0.4417 0.9134
0.0235 27.0 1215 0.7955 0.5755 0.8243 0.6778 74 0.4742 0.6389 0.5444 72 0.2308 0.3061 0.2632 49 0.3247 0.4849 0.3890 596 0.3549 0.5196 0.4218 0.9160
0.0235 28.0 1260 0.8286 0.6180 0.7432 0.6748 74 0.5060 0.5833 0.5419 72 0.28 0.2857 0.2828 49 0.2911 0.4128 0.3414 596 0.3346 0.4513 0.3843 0.9106
0.0235 29.0 1305 0.8632 0.5524 0.7838 0.6480 74 0.4237 0.6944 0.5263 72 0.2778 0.4082 0.3306 49 0.3497 0.5134 0.4160 596 0.3709 0.5487 0.4426 0.9109
0.0235 30.0 1350 0.7689 0.5673 0.7973 0.6629 74 0.4722 0.7083 0.5667 72 0.2647 0.3673 0.3077 49 0.3094 0.4480 0.3660 596 0.3456 0.4994 0.4085 0.9105
0.0235 31.0 1395 0.7931 0.5268 0.7973 0.6344 74 0.4811 0.7083 0.5730 72 0.2368 0.3673 0.288 49 0.3047 0.4530 0.3644 596 0.3373 0.5032 0.4039 0.9106
0.0235 32.0 1440 0.7861 0.5169 0.8243 0.6354 74 0.4796 0.6528 0.5529 72 0.2683 0.4490 0.3359 49 0.3359 0.5084 0.4045 596 0.3608 0.5474 0.4350 0.9135
0.0235 33.0 1485 0.8035 0.5221 0.7973 0.6310 74 0.3846 0.6944 0.4950 72 0.2714 0.3878 0.3193 49 0.3410 0.5252 0.4135 596 0.3582 0.5575 0.4362 0.9137
0.0103 34.0 1530 0.8581 0.5 0.8108 0.6186 74 0.4359 0.7083 0.5397 72 0.2703 0.4082 0.3252 49 0.3303 0.4799 0.3912 596 0.3543 0.5272 0.4238 0.9125
0.0103 35.0 1575 0.8677 0.5085 0.8108 0.6250 74 0.4138 0.6667 0.5106 72 0.2258 0.4286 0.2958 49 0.3240 0.4832 0.3879 596 0.3429 0.5272 0.4155 0.9122
0.0103 36.0 1620 0.9150 0.5514 0.7973 0.6519 74 0.4519 0.6528 0.5341 72 0.2647 0.3673 0.3077 49 0.3399 0.4933 0.4025 596 0.3654 0.5284 0.4320 0.9146
0.0103 37.0 1665 0.9198 0.5405 0.8108 0.6486 74 0.4528 0.6667 0.5393 72 0.3143 0.4490 0.3697 49 0.3287 0.4799 0.3902 596 0.3596 0.5259 0.4271 0.9144
0.0103 38.0 1710 0.9436 0.5210 0.8378 0.6425 74 0.4752 0.6667 0.5549 72 0.2857 0.4082 0.3361 49 0.3392 0.4832 0.3986 596 0.3670 0.5284 0.4332 0.9157
0.0103 39.0 1755 0.9250 0.6061 0.8108 0.6936 74 0.5341 0.6528 0.5875 72 0.3167 0.3878 0.3486 49 0.3562 0.4883 0.4119 596 0.3919 0.5272 0.4496 0.9159
0.0103 40.0 1800 0.8905 0.5905 0.8378 0.6927 74 0.4667 0.6806 0.5537 72 0.2857 0.4082 0.3361 49 0.3521 0.5134 0.4177 596 0.3803 0.5525 0.4505 0.9164
0.0103 41.0 1845 0.9588 0.6354 0.8243 0.7176 74 0.4842 0.6389 0.5509 72 0.2969 0.3878 0.3363 49 0.3418 0.4765 0.3980 596 0.3775 0.5183 0.4369 0.9153
0.0103 42.0 1890 0.9381 0.5636 0.8378 0.6739 74 0.4505 0.6944 0.5464 72 0.2958 0.4286 0.3500 49 0.3559 0.5117 0.4198 596 0.3812 0.5537 0.4515 0.9168
0.0103 43.0 1935 0.9576 0.5625 0.8514 0.6774 74 0.4762 0.6944 0.5650 72 0.3134 0.4286 0.3621 49 0.3433 0.5017 0.4076 596 0.3749 0.5474 0.4450 0.9156
0.0103 44.0 1980 0.9541 0.5556 0.8108 0.6593 74 0.4274 0.6944 0.5291 72 0.2899 0.4082 0.3390 49 0.3438 0.4765 0.3994 596 0.3696 0.5234 0.4333 0.9143
0.0031 45.0 2025 0.9564 0.6139 0.8378 0.7086 74 0.4615 0.6667 0.5455 72 0.2951 0.3673 0.3273 49 0.3491 0.5084 0.4139 596 0.3801 0.5449 0.4478 0.9158
0.0031 46.0 2070 0.9680 0.5755 0.8243 0.6778 74 0.4717 0.6944 0.5618 72 0.2923 0.3878 0.3333 49 0.36 0.5436 0.4332 596 0.3857 0.5740 0.4614 0.9144
0.0031 47.0 2115 0.8938 0.5636 0.8378 0.6739 74 0.4673 0.6944 0.5587 72 0.2703 0.4082 0.3252 49 0.3488 0.4916 0.4081 596 0.3758 0.5373 0.4422 0.9145
0.0031 48.0 2160 0.9492 0.5607 0.8108 0.6630 74 0.5 0.6667 0.5714 72 0.3448 0.4082 0.3738 49 0.3457 0.5 0.4088 596 0.3793 0.5386 0.4451 0.9161
0.0031 49.0 2205 0.9510 0.5607 0.8108 0.6630 74 0.5052 0.6806 0.5799 72 0.3231 0.4286 0.3684 49 0.3523 0.5101 0.4167 596 0.3834 0.5487 0.4514 0.9158
0.0031 50.0 2250 0.9416 0.5636 0.8378 0.6739 74 0.5 0.6528 0.5663 72 0.3088 0.4286 0.3590 49 0.3556 0.5084 0.4185 596 0.3852 0.5474 0.4522 0.9159
0.0031 51.0 2295 0.9471 0.5357 0.8108 0.6452 74 0.4948 0.6667 0.5680 72 0.2857 0.4082 0.3361 49 0.3732 0.5235 0.4358 596 0.3946 0.5563 0.4617 0.9168
0.0031 52.0 2340 0.9231 0.5876 0.7703 0.6667 74 0.5281 0.6528 0.5839 72 0.3443 0.4286 0.3818 49 0.3325 0.4564 0.3847 596 0.3728 0.5019 0.4278 0.9137
0.0031 53.0 2385 0.8841 0.5825 0.8108 0.6780 74 0.5312 0.7083 0.6071 72 0.3284 0.4490 0.3793 49 0.3687 0.5369 0.4372 596 0.3995 0.5727 0.4706 0.9172
0.0031 54.0 2430 0.9170 0.5934 0.7297 0.6545 74 0.5676 0.5833 0.5753 72 0.3125 0.4082 0.3540 49 0.3525 0.4832 0.4076 596 0.3862 0.5107 0.4398 0.9165
0.0031 55.0 2475 0.9097 0.6105 0.7838 0.6864 74 0.5422 0.625 0.5806 72 0.3016 0.3878 0.3393 49 0.3568 0.5185 0.4227 596 0.3893 0.5449 0.4542 0.9182
0.0085 56.0 2520 0.8692 0.5701 0.8243 0.6740 74 0.4464 0.6944 0.5435 72 0.2769 0.3673 0.3158 49 0.3475 0.4950 0.4083 596 0.3742 0.5360 0.4407 0.9161
0.0085 57.0 2565 0.8842 0.61 0.8243 0.7011 74 0.5281 0.6528 0.5839 72 0.3226 0.4082 0.3604 49 0.3726 0.5151 0.4324 596 0.4047 0.5499 0.4662 0.9183
0.0085 58.0 2610 0.9079 0.5304 0.8243 0.6455 74 0.4474 0.7083 0.5484 72 0.3065 0.3878 0.3423 49 0.3520 0.4966 0.4120 596 0.3772 0.5398 0.4441 0.9158
0.0085 59.0 2655 0.9612 0.5648 0.8243 0.6703 74 0.4623 0.6806 0.5506 72 0.3103 0.3673 0.3364 49 0.3733 0.5067 0.4299 596 0.3978 0.5436 0.4594 0.9152
0.0085 60.0 2700 0.9343 0.5905 0.8378 0.6927 74 0.4537 0.6806 0.5444 72 0.2386 0.4286 0.3066 49 0.3618 0.5050 0.4216 596 0.3822 0.5474 0.4501 0.9161
0.0085 61.0 2745 0.8683 0.5263 0.8108 0.6383 74 0.4766 0.7083 0.5698 72 0.2545 0.2857 0.2692 49 0.3411 0.5134 0.4099 596 0.3674 0.5449 0.4389 0.9134
0.0085 62.0 2790 0.9314 0.5439 0.8378 0.6596 74 0.4944 0.6111 0.5466 72 0.2985 0.4082 0.3448 49 0.3564 0.5185 0.4224 596 0.3826 0.5499 0.4512 0.9153
0.0085 63.0 2835 0.9549 0.5676 0.8514 0.6811 74 0.4842 0.6389 0.5509 72 0.2836 0.3878 0.3276 49 0.3543 0.5201 0.4215 596 0.3815 0.5537 0.4518 0.9148
0.0085 64.0 2880 0.9605 0.6458 0.8378 0.7294 74 0.5106 0.6667 0.5783 72 0.2951 0.3673 0.3273 49 0.3569 0.5084 0.4194 596 0.3918 0.5449 0.4558 0.9151
0.0085 65.0 2925 0.9836 0.6139 0.8378 0.7086 74 0.5 0.6528 0.5663 72 0.2951 0.3673 0.3273 49 0.3589 0.5101 0.4213 596 0.3908 0.5449 0.4551 0.9148
0.0085 66.0 2970 0.9778 0.6139 0.8378 0.7086 74 0.5051 0.6944 0.5848 72 0.3016 0.3878 0.3393 49 0.3544 0.5084 0.4176 596 0.3882 0.5487 0.4547 0.9151
0.0025 67.0 3015 0.9872 0.6078 0.8378 0.7045 74 0.5051 0.6944 0.5848 72 0.2969 0.3878 0.3363 49 0.3591 0.5151 0.4232 596 0.3911 0.5537 0.4584 0.9153
0.0025 68.0 3060 0.9874 0.6139 0.8378 0.7086 74 0.5051 0.6944 0.5848 72 0.2836 0.3878 0.3276 49 0.3611 0.5168 0.4251 596 0.3920 0.5550 0.4594 0.9152
0.0025 69.0 3105 1.0168 0.6458 0.8378 0.7294 74 0.5158 0.6806 0.5868 72 0.3 0.3673 0.3303 49 0.3762 0.5403 0.4435 596 0.4074 0.5702 0.4752 0.9169
0.0025 70.0 3150 0.9922 0.5727 0.8514 0.6848 74 0.4538 0.75 0.5654 72 0.2778 0.4082 0.3306 49 0.3577 0.5168 0.4228 596 0.3830 0.5626 0.4557 0.9155
0.0025 71.0 3195 0.9906 0.5755 0.8243 0.6778 74 0.5208 0.6944 0.5952 72 0.3065 0.3878 0.3423 49 0.3675 0.5050 0.4254 596 0.3980 0.5449 0.4600 0.9152
0.0025 72.0 3240 0.9563 0.5833 0.8514 0.6923 74 0.5435 0.6944 0.6098 72 0.3115 0.3878 0.3455 49 0.3718 0.5134 0.4313 596 0.4041 0.5537 0.4672 0.9162
0.0025 73.0 3285 0.9835 0.5794 0.8378 0.6851 74 0.5312 0.7083 0.6071 72 0.3226 0.4082 0.3604 49 0.3715 0.5168 0.4323 596 0.4031 0.5575 0.4679 0.9161
0.0025 74.0 3330 0.9978 0.5888 0.8514 0.6961 74 0.5 0.6806 0.5765 72 0.3125 0.4082 0.3540 49 0.3678 0.5134 0.4286 596 0.3978 0.5537 0.4630 0.9161
0.0025 75.0 3375 1.0115 0.5943 0.8514 0.7000 74 0.5312 0.7083 0.6071 72 0.3077 0.4082 0.3509 49 0.3648 0.5117 0.4260 596 0.3980 0.5550 0.4636 0.9159
0.0025 76.0 3420 1.0282 0.5849 0.8378 0.6889 74 0.5204 0.7083 0.6000 72 0.3077 0.4082 0.3509 49 0.3645 0.5101 0.4252 596 0.3962 0.5525 0.4615 0.9154
0.0025 77.0 3465 1.0204 0.5905 0.8378 0.6927 74 0.5368 0.7083 0.6108 72 0.3125 0.4082 0.3540 49 0.3705 0.5134 0.4304 596 0.4028 0.5550 0.4668 0.9158
0.0038 78.0 3510 1.0008 0.5922 0.8243 0.6893 74 0.56 0.5833 0.5714 72 0.3051 0.3673 0.3333 49 0.3538 0.5034 0.4155 596 0.3880 0.5322 0.4488 0.9168
0.0038 79.0 3555 0.9657 0.5701 0.8243 0.6740 74 0.5532 0.7222 0.6265 72 0.2969 0.3878 0.3363 49 0.3582 0.5067 0.4197 596 0.3917 0.5487 0.4571 0.9160
0.0038 80.0 3600 0.9676 0.5701 0.8243 0.6740 74 0.5426 0.7083 0.6145 72 0.3333 0.4082 0.3670 49 0.3593 0.5101 0.4216 596 0.3939 0.5512 0.4594 0.9163
0.0038 81.0 3645 0.9830 0.5882 0.8108 0.6818 74 0.5426 0.7083 0.6145 72 0.3226 0.4082 0.3604 49 0.3769 0.5369 0.4429 596 0.4074 0.5702 0.4752 0.9172
0.0038 82.0 3690 0.9940 0.5810 0.8243 0.6816 74 0.5667 0.7083 0.6296 72 0.3279 0.4082 0.3636 49 0.3692 0.5302 0.4353 596 0.4029 0.5664 0.4708 0.9174
0.0038 83.0 3735 0.9963 0.5741 0.8378 0.6813 74 0.4825 0.7639 0.5914 72 0.2838 0.4286 0.3415 49 0.3579 0.5134 0.4218 596 0.3858 0.5613 0.4573 0.9161
0.0038 84.0 3780 1.0159 0.5849 0.8378 0.6889 74 0.4911 0.7639 0.5978 72 0.2941 0.4082 0.3419 49 0.3657 0.5117 0.4266 596 0.3946 0.5588 0.4626 0.9162
0.0038 85.0 3825 1.0231 0.5810 0.8243 0.6816 74 0.4952 0.7222 0.5876 72 0.3077 0.4082 0.3509 49 0.3670 0.5117 0.4275 596 0.3960 0.5537 0.4618 0.9164
0.0038 86.0 3870 1.0280 0.6078 0.8378 0.7045 74 0.52 0.7222 0.6047 72 0.3016 0.3878 0.3393 49 0.3668 0.5084 0.4262 596 0.3996 0.5512 0.4633 0.9167
0.0038 87.0 3915 1.0225 0.5922 0.8243 0.6893 74 0.5258 0.7083 0.6036 72 0.3065 0.3878 0.3423 49 0.3614 0.4966 0.4184 596 0.3950 0.5398 0.4562 0.9165
0.0038 88.0 3960 1.0069 0.5905 0.8378 0.6927 74 0.5361 0.7222 0.6154 72 0.3279 0.4082 0.3636 49 0.3763 0.5336 0.4414 596 0.4079 0.5714 0.4760 0.9180
0.0031 89.0 4005 1.0139 0.62 0.8378 0.7126 74 0.52 0.7222 0.6047 72 0.3226 0.4082 0.3604 49 0.3744 0.5252 0.4372 596 0.4071 0.5651 0.4733 0.9182
0.0031 90.0 4050 1.0159 0.6078 0.8378 0.7045 74 0.5253 0.7222 0.6082 72 0.3333 0.4082 0.3670 49 0.3705 0.5185 0.4322 596 0.4046 0.5601 0.4698 0.9176
0.0031 91.0 4095 1.0399 0.6526 0.8378 0.7337 74 0.5484 0.7083 0.6182 72 0.3016 0.3878 0.3393 49 0.3759 0.5185 0.4358 596 0.4110 0.5575 0.4732 0.9175
0.0031 92.0 4140 1.0673 0.62 0.8378 0.7126 74 0.5263 0.6944 0.5988 72 0.2951 0.3673 0.3273 49 0.375 0.4983 0.4280 596 0.4074 0.5398 0.4644 0.9167
0.0031 93.0 4185 1.0578 0.6078 0.8378 0.7045 74 0.5102 0.6944 0.5882 72 0.2951 0.3673 0.3273 49 0.3788 0.5034 0.4323 596 0.4084 0.5436 0.4664 0.9172
0.0031 94.0 4230 1.0467 0.6078 0.8378 0.7045 74 0.5155 0.6944 0.5917 72 0.3279 0.4082 0.3636 49 0.3787 0.5134 0.4359 596 0.4101 0.5537 0.4712 0.9175
0.0031 95.0 4275 1.0454 0.5905 0.8378 0.6927 74 0.5152 0.7083 0.5965 72 0.3175 0.4082 0.3571 49 0.3792 0.5084 0.4344 596 0.4090 0.5512 0.4696 0.9174
0.0031 96.0 4320 1.0367 0.5962 0.8378 0.6966 74 0.5049 0.7222 0.5943 72 0.3443 0.4286 0.3818 49 0.3812 0.5168 0.4387 596 0.4117 0.5601 0.4746 0.9176
0.0031 97.0 4365 1.0343 0.5962 0.8378 0.6966 74 0.5049 0.7222 0.5943 72 0.3443 0.4286 0.3818 49 0.3869 0.5336 0.4485 596 0.4156 0.5727 0.4817 0.9180
0.0031 98.0 4410 1.0340 0.6078 0.8378 0.7045 74 0.5098 0.7222 0.5977 72 0.3333 0.4286 0.375 49 0.3886 0.5352 0.4502 596 0.4173 0.5740 0.4832 0.9179
0.0031 99.0 4455 1.0366 0.6040 0.8243 0.6971 74 0.51 0.7083 0.5930 72 0.35 0.4286 0.3853 49 0.3878 0.5336 0.4492 596 0.4172 0.5702 0.4818 0.9181
0.0028 100.0 4500 1.0383 0.62 0.8378 0.7126 74 0.5253 0.7222 0.6082 72 0.35 0.4286 0.3853 49 0.3881 0.5386 0.4512 596 0.4199 0.5765 0.4859 0.9180

Framework versions

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