Hugging Face's logo

mtzig
/
v2_mistral_lora

PEFT
Safetensors
Generated from Trainer
Model card Files Community
v2_mistral_lora / README.md
mtzig's picture
mtzig
Model save
4525ba5 verified
preview code
|
raw
history blame contribute delete
33.3 kB
metadata
library_name: peft
base_model: peiyi9979/math-shepherd-mistral-7b-prm
tags:
  - generated_from_trainer
metrics:
  - accuracy
  - precision
  - recall
  - f1
model-index:
  - name: v2_mistral_lora
    results: []

v2_mistral_lora

This model is a fine-tuned version of peiyi9979/math-shepherd-mistral-7b-prm on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.0549
  • Accuracy: 0.9783
  • Precision: 0.9799
  • Recall: 0.9466
  • F1: 0.9630

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: 2e-05
  • train_batch_size: 8
  • eval_batch_size: 8
  • seed: 765837
  • distributed_type: multi-GPU
  • num_devices: 4
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 64
  • total_eval_batch_size: 32
  • optimizer: Use OptimizerNames.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: 0.1
  • num_epochs: 1

Training results

Training Loss Epoch Step Validation Loss Accuracy Precision Recall F1
No log 0 0 0.4624 0.8307 0.9495 0.4563 0.6164
0.6147 0.0030 20 0.4628 0.8292 0.9314 0.4612 0.6169
0.5341 0.0059 40 0.4612 0.8278 0.9394 0.4515 0.6098
0.5857 0.0089 60 0.4569 0.8278 0.9485 0.4466 0.6073
0.5562 0.0118 80 0.4473 0.8365 0.9429 0.4806 0.6367
0.5169 0.0148 100 0.4302 0.8596 0.9658 0.5485 0.6997
0.4474 0.0177 120 0.3985 0.8712 0.9209 0.6214 0.7420
0.4423 0.0207 140 0.3567 0.8929 0.9024 0.7184 0.8
0.3734 0.0236 160 0.2948 0.9117 0.9143 0.7767 0.8399
0.3324 0.0266 180 0.2196 0.9363 0.9219 0.8592 0.8894
0.2337 0.0295 200 0.1744 0.9522 0.9391 0.8981 0.9181
0.1528 0.0325 220 0.1573 0.9522 0.9303 0.9078 0.9189
0.3151 0.0354 240 0.1498 0.9551 0.9310 0.9175 0.9242
0.1388 0.0384 260 0.1408 0.9566 0.9314 0.9223 0.9268
0.1405 0.0413 280 0.1342 0.9566 0.9444 0.9078 0.9257
0.093 0.0443 300 0.1380 0.9580 0.9492 0.9078 0.9280
0.1395 0.0472 320 0.1359 0.9580 0.9492 0.9078 0.9280
0.1686 0.0502 340 0.1316 0.9638 0.9689 0.9078 0.9373
0.0542 0.0531 360 0.1270 0.9595 0.9541 0.9078 0.9303
0.131 0.0561 380 0.1170 0.9638 0.9689 0.9078 0.9373
0.1276 0.0590 400 0.1199 0.9624 0.95 0.9223 0.9360
0.0377 0.0620 420 0.1211 0.9609 0.9453 0.9223 0.9337
0.1356 0.0649 440 0.1265 0.9609 0.9497 0.9175 0.9333
0.1409 0.0679 460 0.1059 0.9638 0.9689 0.9078 0.9373
0.0815 0.0708 480 0.1212 0.9624 0.9455 0.9272 0.9363
0.0143 0.0738 500 0.1042 0.9638 0.9641 0.9126 0.9377
0.0877 0.0767 520 0.0976 0.9667 0.9645 0.9223 0.9429
0.1308 0.0797 540 0.1042 0.9624 0.9545 0.9175 0.9356
0.0673 0.0826 560 0.1021 0.9653 0.9740 0.9078 0.9397
0.0763 0.0856 580 0.0967 0.9682 0.9842 0.9078 0.9444
0.0827 0.0885 600 0.0953 0.9711 0.9844 0.9175 0.9497
0.0838 0.0915 620 0.0923 0.9711 0.9794 0.9223 0.95
0.0797 0.0944 640 0.0986 0.9682 0.9510 0.9417 0.9463
0.084 0.0974 660 0.0877 0.9682 0.9792 0.9126 0.9447
0.0091 0.1003 680 0.0856 0.9682 0.9742 0.9175 0.945
0.0832 0.1033 700 0.0913 0.9682 0.9792 0.9126 0.9447
0.0599 0.1062 720 0.0872 0.9696 0.9793 0.9175 0.9474
0.1185 0.1092 740 0.0871 0.9638 0.9788 0.8981 0.9367
0.059 0.1121 760 0.0878 0.9653 0.9740 0.9078 0.9397
0.1429 0.1151 780 0.0868 0.9696 0.9648 0.9320 0.9481
0.0583 0.1180 800 0.0858 0.9696 0.9648 0.9320 0.9481
0.0792 0.1210 820 0.0833 0.9682 0.9694 0.9223 0.9453
0.0746 0.1239 840 0.0772 0.9725 0.9947 0.9126 0.9519
0.0463 0.1269 860 0.0733 0.9725 0.9795 0.9272 0.9526
0.1658 0.1298 880 0.0861 0.9696 0.9894 0.9078 0.9468
0.1177 0.1328 900 0.0815 0.9711 0.9604 0.9417 0.9510
0.0709 0.1357 920 0.0773 0.9696 0.9793 0.9175 0.9474
0.0801 0.1387 940 0.0726 0.9740 0.9845 0.9272 0.955
0.0609 0.1416 960 0.0709 0.9754 0.9797 0.9369 0.9578
0.0865 0.1446 980 0.0696 0.9754 0.9846 0.9320 0.9576
0.0347 0.1475 1000 0.0722 0.9725 0.9698 0.9369 0.9531
0.1003 0.1505 1020 0.0817 0.9653 0.9505 0.9320 0.9412
0.0152 0.1534 1040 0.0774 0.9725 0.9947 0.9126 0.9519
0.0965 0.1564 1060 0.0752 0.9754 0.9896 0.9272 0.9574
0.1153 0.1594 1080 0.0771 0.9740 0.9947 0.9175 0.9545
0.0918 0.1623 1100 0.0798 0.9711 0.9947 0.9078 0.9492
0.0745 0.1653 1120 0.0739 0.9740 0.9796 0.9320 0.9552
0.0426 0.1682 1140 0.0782 0.9725 0.9895 0.9175 0.9521
0.0373 0.1712 1160 0.0795 0.9740 0.9796 0.9320 0.9552
0.0635 0.1741 1180 0.0754 0.9754 0.9846 0.9320 0.9576
0.0733 0.1771 1200 0.0744 0.9768 0.9847 0.9369 0.9602
0.0914 0.1800 1220 0.0765 0.9740 0.9845 0.9272 0.955
0.1249 0.1830 1240 0.0765 0.9725 0.9845 0.9223 0.9524
0.0829 0.1859 1260 0.0715 0.9725 0.9795 0.9272 0.9526
0.1013 0.1889 1280 0.0927 0.9711 0.9947 0.9078 0.9492
0.0697 0.1918 1300 0.0805 0.9725 0.9895 0.9175 0.9521
0.0905 0.1948 1320 0.0773 0.9740 0.9796 0.9320 0.9552
0.0417 0.1977 1340 0.0790 0.9711 0.9844 0.9175 0.9497
0.0541 0.2007 1360 0.0759 0.9740 0.9845 0.9272 0.955
0.0333 0.2036 1380 0.0932 0.9682 0.9946 0.8981 0.9439
0.0933 0.2066 1400 0.0744 0.9740 0.9896 0.9223 0.9548
0.0679 0.2095 1420 0.0702 0.9754 0.9896 0.9272 0.9574
0.0482 0.2125 1440 0.0707 0.9754 0.9846 0.9320 0.9576
0.0408 0.2154 1460 0.0740 0.9768 0.9897 0.9320 0.96
0.0819 0.2184 1480 0.0675 0.9797 0.9898 0.9417 0.9652
0.0622 0.2213 1500 0.0701 0.9754 0.9846 0.9320 0.9576
0.0211 0.2243 1520 0.0649 0.9754 0.9749 0.9417 0.9580
0.0753 0.2272 1540 0.0686 0.9740 0.9747 0.9369 0.9554
0.0839 0.2302 1560 0.0785 0.9754 0.9948 0.9223 0.9572
0.0861 0.2331 1580 0.0811 0.9754 0.9948 0.9223 0.9572
0.0657 0.2361 1600 0.0680 0.9754 0.9846 0.9320 0.9576
0.0693 0.2390 1620 0.0741 0.9740 0.9947 0.9175 0.9545
0.0547 0.2420 1640 0.0713 0.9754 0.9896 0.9272 0.9574
0.0983 0.2449 1660 0.0711 0.9740 0.9896 0.9223 0.9548
0.0599 0.2479 1680 0.0660 0.9740 0.9845 0.9272 0.955
0.1337 0.2508 1700 0.0652 0.9797 0.9848 0.9466 0.9653
0.0401 0.2538 1720 0.0818 0.9754 0.9948 0.9223 0.9572
0.0215 0.2567 1740 0.0677 0.9754 0.9948 0.9223 0.9572
0.1742 0.2597 1760 0.0675 0.9740 0.9947 0.9175 0.9545
0.0445 0.2626 1780 0.0656 0.9754 0.9896 0.9272 0.9574
0.0557 0.2656 1800 0.0699 0.9783 0.9799 0.9466 0.9630
0.0079 0.2685 1820 0.0733 0.9740 0.9947 0.9175 0.9545
0.056 0.2715 1840 0.0709 0.9740 0.9796 0.9320 0.9552
0.0923 0.2744 1860 0.0676 0.9740 0.97 0.9417 0.9557
0.0769 0.2774 1880 0.0715 0.9754 0.9948 0.9223 0.9572
0.1452 0.2803 1900 0.0687 0.9754 0.9896 0.9272 0.9574
0.0938 0.2833 1920 0.0676 0.9754 0.9846 0.9320 0.9576
0.0583 0.2862 1940 0.0698 0.9740 0.9845 0.9272 0.955
0.0937 0.2892 1960 0.0672 0.9768 0.9847 0.9369 0.9602
0.0391 0.2921 1980 0.0675 0.9768 0.9897 0.9320 0.96
0.0536 0.2951 2000 0.0699 0.9725 0.9895 0.9175 0.9521
0.0647 0.2980 2020 0.0723 0.9740 0.9896 0.9223 0.9548
0.0637 0.3010 2040 0.0699 0.9754 0.9655 0.9515 0.9584
0.07 0.3039 2060 0.0656 0.9740 0.9796 0.9320 0.9552
0.0264 0.3069 2080 0.0672 0.9711 0.9895 0.9126 0.9495
0.1048 0.3098 2100 0.0656 0.9783 0.9799 0.9466 0.9630
0.136 0.3128 2120 0.0685 0.9725 0.9947 0.9126 0.9519
0.0833 0.3158 2140 0.0660 0.9768 0.9798 0.9417 0.9604
0.0643 0.3187 2160 0.0696 0.9754 0.9948 0.9223 0.9572
0.032 0.3217 2180 0.0672 0.9754 0.9701 0.9466 0.9582
0.0613 0.3246 2200 0.0658 0.9768 0.975 0.9466 0.9606
0.0755 0.3276 2220 0.0692 0.9783 0.9848 0.9417 0.9628
0.0122 0.3305 2240 0.0724 0.9725 0.9652 0.9417 0.9533
0.0472 0.3335 2260 0.0754 0.9711 0.9947 0.9078 0.9492
0.0404 0.3364 2280 0.0664 0.9768 0.9798 0.9417 0.9604
0.0952 0.3394 2300 0.0807 0.9696 0.9947 0.9029 0.9466
0.0435 0.3423 2320 0.0642 0.9783 0.9799 0.9466 0.9630
0.027 0.3453 2340 0.0664 0.9768 0.9798 0.9417 0.9604
0.075 0.3482 2360 0.0663 0.9754 0.9655 0.9515 0.9584
0.071 0.3512 2380 0.0694 0.9740 0.9845 0.9272 0.955
0.0724 0.3541 2400 0.0716 0.9754 0.9846 0.9320 0.9576
0.0126 0.3571 2420 0.0800 0.9740 0.9947 0.9175 0.9545
0.0611 0.3600 2440 0.0661 0.9797 0.9848 0.9466 0.9653
0.0067 0.3630 2460 0.0671 0.9725 0.9845 0.9223 0.9524
0.0804 0.3659 2480 0.0652 0.9783 0.9799 0.9466 0.9630
0.057 0.3689 2500 0.0716 0.9725 0.9895 0.9175 0.9521
0.0518 0.3718 2520 0.0707 0.9754 0.9846 0.9320 0.9576
0.0533 0.3748 2540 0.0778 0.9711 0.9895 0.9126 0.9495
0.0371 0.3777 2560 0.0714 0.9740 0.9796 0.9320 0.9552
0.1052 0.3807 2580 0.0677 0.9754 0.9896 0.9272 0.9574
0.0384 0.3836 2600 0.0641 0.9783 0.9799 0.9466 0.9630
0.0482 0.3866 2620 0.0643 0.9783 0.9799 0.9466 0.9630
0.0892 0.3895 2640 0.0676 0.9754 0.9896 0.9272 0.9574
0.0999 0.3925 2660 0.0669 0.9768 0.9897 0.9320 0.96
0.055 0.3954 2680 0.0658 0.9754 0.9846 0.9320 0.9576
0.0561 0.3984 2700 0.0656 0.9783 0.9848 0.9417 0.9628
0.0701 0.4013 2720 0.0693 0.9754 0.9948 0.9223 0.9572
0.0307 0.4043 2740 0.0637 0.9754 0.9749 0.9417 0.9580
0.029 0.4072 2760 0.0688 0.9768 0.9847 0.9369 0.9602
0.0687 0.4102 2780 0.0662 0.9754 0.9797 0.9369 0.9578
0.0577 0.4131 2800 0.0669 0.9725 0.9895 0.9175 0.9521
0.0286 0.4161 2820 0.0624 0.9754 0.9749 0.9417 0.9580
0.1144 0.4190 2840 0.0647 0.9783 0.9897 0.9369 0.9626
0.0424 0.4220 2860 0.0620 0.9783 0.9751 0.9515 0.9631
0.1575 0.4249 2880 0.0651 0.9768 0.9897 0.9320 0.96
0.0651 0.4279 2900 0.0620 0.9768 0.9798 0.9417 0.9604
0.1524 0.4308 2920 0.0596 0.9783 0.9799 0.9466 0.9630
0.0547 0.4338 2940 0.0597 0.9783 0.9799 0.9466 0.9630
0.0064 0.4367 2960 0.0604 0.9768 0.9847 0.9369 0.9602
0.075 0.4397 2980 0.0591 0.9754 0.9701 0.9466 0.9582
0.0542 0.4426 3000 0.0661 0.9711 0.9745 0.9272 0.9502
0.0455 0.4456 3020 0.0632 0.9754 0.9749 0.9417 0.9580
0.0152 0.4485 3040 0.0605 0.9797 0.9752 0.9563 0.9657
0.0467 0.4515 3060 0.0646 0.9768 0.9897 0.9320 0.96
0.0418 0.4544 3080 0.0597 0.9754 0.9896 0.9272 0.9574
0.0556 0.4574 3100 0.0622 0.9740 0.9896 0.9223 0.9548
0.0675 0.4603 3120 0.0642 0.9740 0.9608 0.9515 0.9561
0.0227 0.4633 3140 0.0619 0.9740 0.9796 0.9320 0.9552
0.0502 0.4662 3160 0.0622 0.9725 0.9746 0.9320 0.9529
0.0478 0.4692 3180 0.0605 0.9754 0.9749 0.9417 0.9580
0.1021 0.4722 3200 0.0630 0.9768 0.9847 0.9369 0.9602
0.0418 0.4751 3220 0.0615 0.9754 0.9701 0.9466 0.9582
0.0354 0.4781 3240 0.0615 0.9768 0.9798 0.9417 0.9604
0.0575 0.4810 3260 0.0593 0.9768 0.975 0.9466 0.9606
0.0901 0.4840 3280 0.0630 0.9754 0.9846 0.9320 0.9576
0.0166 0.4869 3300 0.0616 0.9783 0.9799 0.9466 0.9630
0.0942 0.4899 3320 0.0612 0.9754 0.9701 0.9466 0.9582
0.1136 0.4928 3340 0.0661 0.9711 0.9697 0.9320 0.9505
0.0865 0.4958 3360 0.0666 0.9696 0.9602 0.9369 0.9484
0.0684 0.4987 3380 0.0617 0.9682 0.9554 0.9369 0.9461
0.0556 0.5017 3400 0.0649 0.9682 0.9554 0.9369 0.9461
0.079 0.5046 3420 0.0640 0.9711 0.9559 0.9466 0.9512
0.0976 0.5076 3440 0.0632 0.9696 0.9602 0.9369 0.9484
0.0756 0.5105 3460 0.0646 0.9711 0.9604 0.9417 0.9510
0.0786 0.5135 3480 0.0651 0.9682 0.9646 0.9272 0.9455
0.0663 0.5164 3500 0.0588 0.9711 0.9559 0.9466 0.9512
0.1079 0.5194 3520 0.0598 0.9754 0.9749 0.9417 0.9580
0.0547 0.5223 3540 0.0573 0.9740 0.9653 0.9466 0.9559
0.0204 0.5253 3560 0.0594 0.9754 0.9701 0.9466 0.9582
0.0595 0.5282 3580 0.0602 0.9754 0.9797 0.9369 0.9578
0.0574 0.5312 3600 0.0604 0.9711 0.9559 0.9466 0.9512
0.0249 0.5341 3620 0.0654 0.9740 0.9796 0.9320 0.9552
0.131 0.5371 3640 0.0596 0.9740 0.9608 0.9515 0.9561
0.0454 0.5400 3660 0.0638 0.9754 0.9846 0.9320 0.9576
0.0219 0.5430 3680 0.0636 0.9768 0.9897 0.9320 0.96
0.0547 0.5459 3700 0.0609 0.9754 0.9701 0.9466 0.9582
0.077 0.5489 3720 0.0585 0.9754 0.9797 0.9369 0.9578
0.0403 0.5518 3740 0.0552 0.9783 0.9799 0.9466 0.9630
0.0228 0.5548 3760 0.0541 0.9797 0.9848 0.9466 0.9653
0.0321 0.5577 3780 0.0533 0.9797 0.9898 0.9417 0.9652
0.0698 0.5607 3800 0.0525 0.9797 0.98 0.9515 0.9655
0.0555 0.5636 3820 0.0535 0.9768 0.9703 0.9515 0.9608
0.0853 0.5666 3840 0.0534 0.9783 0.9799 0.9466 0.9630
0.0385 0.5695 3860 0.0581 0.9783 0.9897 0.9369 0.9626
0.0516 0.5725 3880 0.0552 0.9754 0.9701 0.9466 0.9582
0.0248 0.5754 3900 0.0562 0.9768 0.975 0.9466 0.9606
0.0351 0.5784 3920 0.0617 0.9754 0.9846 0.9320 0.9576
0.0629 0.5813 3940 0.0587 0.9740 0.9747 0.9369 0.9554
0.0564 0.5843 3960 0.0587 0.9740 0.9653 0.9466 0.9559
0.0364 0.5872 3980 0.0596 0.9754 0.9846 0.9320 0.9576
0.0995 0.5902 4000 0.0603 0.9768 0.9897 0.9320 0.96
0.0686 0.5931 4020 0.0582 0.9754 0.9749 0.9417 0.9580
0.0269 0.5961 4040 0.0625 0.9768 0.9897 0.9320 0.96
0.0478 0.5990 4060 0.0588 0.9754 0.9701 0.9466 0.9582
0.0405 0.6020 4080 0.0578 0.9768 0.975 0.9466 0.9606
0.0824 0.6049 4100 0.0560 0.9783 0.9751 0.9515 0.9631
0.008 0.6079 4120 0.0564 0.9797 0.9898 0.9417 0.9652
0.0488 0.6108 4140 0.0543 0.9783 0.9799 0.9466 0.9630
0.0837 0.6138 4160 0.0557 0.9783 0.9799 0.9466 0.9630
0.021 0.6167 4180 0.0585 0.9768 0.975 0.9466 0.9606
0.0661 0.6197 4200 0.0600 0.9754 0.9749 0.9417 0.9580
0.0784 0.6226 4220 0.0593 0.9768 0.9798 0.9417 0.9604
0.0598 0.6256 4240 0.0613 0.9754 0.9749 0.9417 0.9580
0.0856 0.6286 4260 0.0615 0.9783 0.9848 0.9417 0.9628
0.0634 0.6315 4280 0.0583 0.9797 0.98 0.9515 0.9655
0.0396 0.6345 4300 0.0583 0.9783 0.9799 0.9466 0.9630
0.0307 0.6374 4320 0.0595 0.9797 0.9898 0.9417 0.9652
0.0549 0.6404 4340 0.0577 0.9812 0.9898 0.9466 0.9677
0.0647 0.6433 4360 0.0596 0.9783 0.9897 0.9369 0.9626
0.0181 0.6463 4380 0.0586 0.9783 0.9897 0.9369 0.9626
0.0798 0.6492 4400 0.0562 0.9783 0.9799 0.9466 0.9630
0.0386 0.6522 4420 0.0578 0.9797 0.9848 0.9466 0.9653
0.0986 0.6551 4440 0.0601 0.9768 0.9847 0.9369 0.9602
0.0731 0.6581 4460 0.0596 0.9754 0.9846 0.9320 0.9576
0.0269 0.6610 4480 0.0573 0.9754 0.9749 0.9417 0.9580
0.0509 0.6640 4500 0.0589 0.9783 0.9897 0.9369 0.9626
0.0554 0.6669 4520 0.0568 0.9768 0.9798 0.9417 0.9604
0.0536 0.6699 4540 0.0555 0.9783 0.9799 0.9466 0.9630
0.0681 0.6728 4560 0.0562 0.9768 0.9847 0.9369 0.9602
0.0446 0.6758 4580 0.0570 0.9797 0.9848 0.9466 0.9653
0.0238 0.6787 4600 0.0559 0.9797 0.9848 0.9466 0.9653
0.0653 0.6817 4620 0.0548 0.9797 0.9848 0.9466 0.9653
0.05 0.6846 4640 0.0546 0.9812 0.9849 0.9515 0.9679
0.048 0.6876 4660 0.0541 0.9812 0.9849 0.9515 0.9679
0.0746 0.6905 4680 0.0560 0.9797 0.9848 0.9466 0.9653
0.036 0.6935 4700 0.0551 0.9812 0.9849 0.9515 0.9679
0.0498 0.6964 4720 0.0555 0.9812 0.9849 0.9515 0.9679
0.0327 0.6994 4740 0.0603 0.9783 0.9848 0.9417 0.9628
0.0637 0.7023 4760 0.0553 0.9797 0.98 0.9515 0.9655
0.0089 0.7053 4780 0.0611 0.9768 0.9847 0.9369 0.9602
0.0219 0.7082 4800 0.0577 0.9797 0.98 0.9515 0.9655
0.0171 0.7112 4820 0.0562 0.9812 0.9849 0.9515 0.9679
0.0388 0.7141 4840 0.0559 0.9812 0.9849 0.9515 0.9679
0.0057 0.7171 4860 0.0586 0.9768 0.9847 0.9369 0.9602
0.0507 0.7200 4880 0.0592 0.9754 0.9846 0.9320 0.9576
0.0478 0.7230 4900 0.0566 0.9812 0.9849 0.9515 0.9679
0.0949 0.7259 4920 0.0550 0.9812 0.9849 0.9515 0.9679
0.0567 0.7289 4940 0.0558 0.9783 0.9799 0.9466 0.9630
0.025 0.7318 4960 0.0580 0.9768 0.9798 0.9417 0.9604
0.0488 0.7348 4980 0.0612 0.9768 0.9897 0.9320 0.96
0.0313 0.7377 5000 0.0559 0.9797 0.98 0.9515 0.9655
0.0552 0.7407 5020 0.0589 0.9768 0.9847 0.9369 0.9602
0.0579 0.7436 5040 0.0556 0.9826 0.9899 0.9515 0.9703
0.0704 0.7466 5060 0.0551 0.9812 0.9898 0.9466 0.9677
0.0537 0.7495 5080 0.0575 0.9783 0.9897 0.9369 0.9626
0.038 0.7525 5100 0.0577 0.9783 0.9897 0.9369 0.9626
0.1133 0.7554 5120 0.0593 0.9783 0.9897 0.9369 0.9626
0.072 0.7584 5140 0.0575 0.9783 0.9897 0.9369 0.9626
0.0663 0.7613 5160 0.0559 0.9797 0.9898 0.9417 0.9652
0.0416 0.7643 5180 0.0563 0.9783 0.9848 0.9417 0.9628
0.0462 0.7672 5200 0.0577 0.9797 0.9898 0.9417 0.9652
0.0268 0.7702 5220 0.0585 0.9797 0.9898 0.9417 0.9652
0.0406 0.7731 5240 0.0560 0.9768 0.9798 0.9417 0.9604
0.0304 0.7761 5260 0.0592 0.9783 0.9897 0.9369 0.9626
0.0758 0.7790 5280 0.0580 0.9768 0.9847 0.9369 0.9602
0.0623 0.7820 5300 0.0582 0.9768 0.9847 0.9369 0.9602
0.0472 0.7850 5320 0.0586 0.9797 0.9898 0.9417 0.9652
0.0349 0.7879 5340 0.0558 0.9783 0.9848 0.9417 0.9628
0.0311 0.7909 5360 0.0561 0.9812 0.9898 0.9466 0.9677
0.0943 0.7938 5380 0.0580 0.9783 0.9897 0.9369 0.9626
0.0458 0.7968 5400 0.0579 0.9783 0.9848 0.9417 0.9628
0.0744 0.7997 5420 0.0576 0.9797 0.9898 0.9417 0.9652
0.1293 0.8027 5440 0.0562 0.9797 0.9848 0.9466 0.9653
0.0526 0.8056 5460 0.0557 0.9812 0.9898 0.9466 0.9677
0.0609 0.8086 5480 0.0571 0.9812 0.9898 0.9466 0.9677
0.0684 0.8115 5500 0.0583 0.9768 0.9847 0.9369 0.9602
0.0579 0.8145 5520 0.0594 0.9768 0.9847 0.9369 0.9602
0.0728 0.8174 5540 0.0592 0.9783 0.9897 0.9369 0.9626
0.0304 0.8204 5560 0.0592 0.9754 0.9797 0.9369 0.9578
0.0519 0.8233 5580 0.0575 0.9783 0.9799 0.9466 0.9630
0.0091 0.8263 5600 0.0568 0.9797 0.9848 0.9466 0.9653
0.0306 0.8292 5620 0.0574 0.9783 0.9799 0.9466 0.9630
0.0112 0.8322 5640 0.0587 0.9783 0.9897 0.9369 0.9626
0.0214 0.8351 5660 0.0576 0.9797 0.9898 0.9417 0.9652
0.02 0.8381 5680 0.0564 0.9812 0.9898 0.9466 0.9677
0.0866 0.8410 5700 0.0559 0.9797 0.9848 0.9466 0.9653
0.0269 0.8440 5720 0.0576 0.9797 0.9898 0.9417 0.9652
0.0441 0.8469 5740 0.0572 0.9812 0.9898 0.9466 0.9677
0.0413 0.8499 5760 0.0545 0.9797 0.9848 0.9466 0.9653
0.061 0.8528 5780 0.0542 0.9783 0.9799 0.9466 0.9630
0.0699 0.8558 5800 0.0544 0.9783 0.9799 0.9466 0.9630
0.0674 0.8587 5820 0.0548 0.9783 0.9799 0.9466 0.9630
0.0402 0.8617 5840 0.0571 0.9797 0.9848 0.9466 0.9653
0.0226 0.8646 5860 0.0577 0.9783 0.9848 0.9417 0.9628
0.0419 0.8676 5880 0.0577 0.9783 0.9848 0.9417 0.9628
0.089 0.8705 5900 0.0567 0.9797 0.9848 0.9466 0.9653
0.1096 0.8735 5920 0.0562 0.9783 0.9799 0.9466 0.9630
0.0933 0.8764 5940 0.0551 0.9783 0.9799 0.9466 0.9630
0.0482 0.8794 5960 0.0552 0.9783 0.9799 0.9466 0.9630
0.1723 0.8823 5980 0.0557 0.9783 0.9799 0.9466 0.9630
0.0259 0.8853 6000 0.0557 0.9783 0.9799 0.9466 0.9630
0.0291 0.8882 6020 0.0557 0.9783 0.9799 0.9466 0.9630
0.0872 0.8912 6040 0.0560 0.9783 0.9799 0.9466 0.9630
0.0819 0.8941 6060 0.0557 0.9783 0.9799 0.9466 0.9630
0.0912 0.8971 6080 0.0558 0.9783 0.9799 0.9466 0.9630
0.0307 0.9000 6100 0.0563 0.9783 0.9799 0.9466 0.9630
0.0271 0.9030 6120 0.0554 0.9783 0.9799 0.9466 0.9630
0.0405 0.9059 6140 0.0555 0.9783 0.9799 0.9466 0.9630
0.0175 0.9089 6160 0.0550 0.9783 0.9799 0.9466 0.9630
0.0459 0.9118 6180 0.0549 0.9783 0.9799 0.9466 0.9630
0.0631 0.9148 6200 0.0554 0.9783 0.9799 0.9466 0.9630
0.0737 0.9177 6220 0.0552 0.9797 0.9848 0.9466 0.9653
0.042 0.9207 6240 0.0559 0.9783 0.9799 0.9466 0.9630
0.0505 0.9236 6260 0.0557 0.9783 0.9799 0.9466 0.9630
0.0424 0.9266 6280 0.0552 0.9797 0.9848 0.9466 0.9653
0.0506 0.9295 6300 0.0560 0.9783 0.9799 0.9466 0.9630
0.0238 0.9325 6320 0.0557 0.9783 0.9799 0.9466 0.9630
0.0703 0.9354 6340 0.0550 0.9783 0.9799 0.9466 0.9630
0.0772 0.9384 6360 0.0556 0.9783 0.9799 0.9466 0.9630
0.0697 0.9414 6380 0.0557 0.9783 0.9799 0.9466 0.9630
0.0446 0.9443 6400 0.0558 0.9783 0.9799 0.9466 0.9630
0.0323 0.9473 6420 0.0550 0.9783 0.9799 0.9466 0.9630
0.0496 0.9502 6440 0.0553 0.9783 0.9799 0.9466 0.9630
0.0809 0.9532 6460 0.0553 0.9783 0.9799 0.9466 0.9630
0.0706 0.9561 6480 0.0549 0.9797 0.9848 0.9466 0.9653
0.0716 0.9591 6500 0.0555 0.9783 0.9799 0.9466 0.9630
0.067 0.9620 6520 0.0552 0.9797 0.9848 0.9466 0.9653
0.0626 0.9650 6540 0.0551 0.9783 0.9799 0.9466 0.9630
0.0275 0.9679 6560 0.0553 0.9783 0.9799 0.9466 0.9630
0.0196 0.9709 6580 0.0551 0.9783 0.9799 0.9466 0.9630
0.0986 0.9738 6600 0.0555 0.9783 0.9799 0.9466 0.9630
0.0275 0.9768 6620 0.0559 0.9797 0.9848 0.9466 0.9653
0.0358 0.9797 6640 0.0552 0.9783 0.9799 0.9466 0.9630
0.0266 0.9827 6660 0.0550 0.9783 0.9799 0.9466 0.9630
0.0759 0.9856 6680 0.0559 0.9783 0.9799 0.9466 0.9630
0.0396 0.9886 6700 0.0549 0.9797 0.9848 0.9466 0.9653
0.0172 0.9915 6720 0.0554 0.9783 0.9799 0.9466 0.9630
0.0444 0.9945 6740 0.0552 0.9783 0.9799 0.9466 0.9630
0.0481 0.9974 6760 0.0549 0.9783 0.9799 0.9466 0.9630

Framework versions

  • PEFT 0.13.2
  • Transformers 4.46.0
  • Pytorch 2.5.1+cu124
  • Datasets 3.1.0
  • Tokenizers 0.20.3