Edit model card

t5-small-finetuned-cve-reason

This model is a fine-tuned version of t5-small on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.3518
  • Rouge1: 85.938
  • Rouge2: 80.3378
  • Rougel: 85.3453
  • Rougelsum: 85.2428
  • Gen Len: 7.4651

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: 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: 200
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Rouge1 Rouge2 Rougel Rougelsum Gen Len
No log 1.0 8 1.2647 37.882 27.7984 37.5181 37.7119 12.9302
No log 2.0 16 1.1581 48.2163 39.0458 48.2989 48.2259 10.2791
No log 3.0 24 1.0603 68.5508 57.1908 67.9871 68.2547 7.3023
No log 4.0 32 0.9842 69.4934 59.4592 69.0929 69.1346 6.8372
No log 5.0 40 0.9316 70.4653 60.9745 70.0948 70.2304 6.7209
No log 6.0 48 0.9035 70.1471 60.9745 69.6743 69.8902 6.6047
No log 7.0 56 0.8794 71.6694 62.6726 71.1348 71.2078 6.6977
No log 8.0 64 0.8623 72.3055 63.3924 71.714 71.9726 6.7907
No log 9.0 72 0.8441 72.9096 63.9073 72.3081 72.4054 6.814
No log 10.0 80 0.8223 73.2144 64.9539 72.6362 72.758 6.814
No log 11.0 88 0.8032 73.2144 64.9539 72.6362 72.758 6.814
No log 12.0 96 0.7756 73.2144 64.9539 72.6362 72.758 6.7674
No log 13.0 104 0.7530 73.5734 65.4559 73.0007 73.0639 6.7442
No log 14.0 112 0.7348 73.6227 64.8117 73.1084 73.1018 6.7442
No log 15.0 120 0.7176 73.6227 64.8117 73.1084 73.1018 6.7442
No log 16.0 128 0.6972 73.6227 64.8117 73.1084 73.1018 6.7442
No log 17.0 136 0.6767 73.6323 64.8283 73.173 73.1477 6.6977
No log 18.0 144 0.6563 73.6227 64.8117 73.1084 73.1018 6.7442
No log 19.0 152 0.6352 73.6227 64.8117 73.1084 73.1018 6.7442
No log 20.0 160 0.6193 73.6227 64.8117 73.1084 73.1018 6.7442
No log 21.0 168 0.6022 73.6227 64.8117 73.1084 73.1018 6.7442
No log 22.0 176 0.5876 73.6227 64.8117 73.1084 73.1018 6.7442
No log 23.0 184 0.5720 78.5982 69.6235 78.024 77.9477 6.7907
No log 24.0 192 0.5574 78.5982 69.6235 78.024 77.9477 6.7907
No log 25.0 200 0.5473 78.5583 69.5146 78.0858 77.9665 6.7442
No log 26.0 208 0.5370 78.5583 69.5146 78.0858 77.9665 6.7442
No log 27.0 216 0.5258 78.5583 69.5146 78.0858 77.9665 6.7442
No log 28.0 224 0.5205 78.5583 69.5146 78.0858 77.9665 6.7442
No log 29.0 232 0.5129 78.5583 69.5146 78.0858 77.9665 6.7442
No log 30.0 240 0.5063 78.5583 69.5146 78.0858 77.9665 6.7442
No log 31.0 248 0.5008 78.5583 69.5146 78.0858 77.9665 6.7442
No log 32.0 256 0.4922 78.5982 69.6235 78.024 77.9477 6.7907
No log 33.0 264 0.4837 79.5649 71.0373 79.0703 79.0146 6.814
No log 34.0 272 0.4730 81.8866 74.33 81.3878 81.2901 6.8605
No log 35.0 280 0.4671 81.9657 74.2303 81.3391 81.2906 6.814
No log 36.0 288 0.4650 81.4937 74.6705 80.5426 80.5935 6.9302
No log 37.0 296 0.4686 81.3135 74.2368 80.3014 80.4175 6.8837
No log 38.0 304 0.4677 81.3135 74.2368 80.3014 80.4175 6.8837
No log 39.0 312 0.4632 81.3135 74.2368 80.3014 80.4175 6.8837
No log 40.0 320 0.4574 82.1781 74.853 81.2534 81.3743 6.907
No log 41.0 328 0.4522 82.1781 74.853 81.2534 81.3743 6.907
No log 42.0 336 0.4448 82.4366 75.3043 81.4852 81.5497 6.9535
No log 43.0 344 0.4449 82.1781 74.853 81.2534 81.3743 6.907
No log 44.0 352 0.4388 82.4366 75.3043 81.4852 81.5497 6.9535
No log 45.0 360 0.4328 82.4366 75.3043 81.4852 81.5497 6.9535
No log 46.0 368 0.4321 82.4366 75.3043 81.4852 81.5497 6.9535
No log 47.0 376 0.4304 82.4366 75.3043 81.4852 81.5497 6.9535
No log 48.0 384 0.4285 82.4366 75.3043 81.4852 81.5497 6.9535
No log 49.0 392 0.4255 82.1999 74.4808 81.2765 81.3433 6.9767
No log 50.0 400 0.4228 82.1999 74.4808 81.2765 81.3433 6.9767
No log 51.0 408 0.4185 82.4366 75.3043 81.4852 81.5497 6.9535
No log 52.0 416 0.4174 82.1781 74.853 81.2534 81.3743 6.907
No log 53.0 424 0.4186 82.1781 74.853 81.2534 81.3743 6.907
No log 54.0 432 0.4164 82.1781 74.853 81.2534 81.3743 6.907
No log 55.0 440 0.4085 82.1781 74.853 81.2534 81.3743 6.907
No log 56.0 448 0.4002 82.1781 74.853 81.2534 81.3743 6.907
No log 57.0 456 0.3916 82.1781 74.853 81.2534 81.3743 6.907
No log 58.0 464 0.3871 82.4366 75.3043 81.4852 81.5497 6.9535
No log 59.0 472 0.3876 82.1781 74.853 81.2534 81.3743 6.907
No log 60.0 480 0.3916 82.1781 74.853 81.2534 81.3743 6.907
No log 61.0 488 0.3896 82.1781 74.853 81.2534 81.3743 6.907
No log 62.0 496 0.3852 82.1781 74.853 81.2534 81.3743 6.907
0.6237 63.0 504 0.3812 82.1781 74.853 81.2534 81.3743 6.907
0.6237 64.0 512 0.3748 82.1781 74.853 81.2534 81.3743 6.907
0.6237 65.0 520 0.3733 82.1781 74.853 81.2534 81.3743 6.907
0.6237 66.0 528 0.3704 82.1781 74.853 81.2534 81.3743 6.907
0.6237 67.0 536 0.3661 82.4366 75.3043 81.4852 81.5497 6.9535
0.6237 68.0 544 0.3625 83.2845 76.4905 82.4072 82.4264 6.9767
0.6237 69.0 552 0.3615 83.2845 76.4905 82.4072 82.4264 6.9767
0.6237 70.0 560 0.3601 82.4366 75.3043 81.4852 81.5497 6.9535
0.6237 71.0 568 0.3636 82.4366 75.3043 81.4852 81.5497 6.9535
0.6237 72.0 576 0.3625 82.1999 74.4808 81.2765 81.3433 6.9767
0.6237 73.0 584 0.3607 82.1999 74.4808 81.2765 81.3433 6.9767
0.6237 74.0 592 0.3617 82.8601 75.3335 81.8967 82.0105 7.0233
0.6237 75.0 600 0.3617 82.5965 74.9638 81.6483 81.7381 6.9767
0.6237 76.0 608 0.3625 82.8185 75.5535 81.8975 81.9123 6.9535
0.6237 77.0 616 0.3603 82.8185 75.5535 81.8975 81.9123 6.9535
0.6237 78.0 624 0.3585 82.8185 75.5535 81.8975 81.9123 6.9535
0.6237 79.0 632 0.3567 82.8185 75.5535 81.8975 81.9123 6.9535
0.6237 80.0 640 0.3567 81.9612 74.1954 81.0613 81.213 7.1163
0.6237 81.0 648 0.3561 82.146 74.6038 81.291 81.4392 7.1628
0.6237 82.0 656 0.3556 82.2466 74.9846 81.3774 81.5195 7.3023
0.6237 83.0 664 0.3611 82.2466 74.9846 81.3774 81.5195 7.3023
0.6237 84.0 672 0.3654 82.2342 75.2389 81.3411 81.5126 7.2326
0.6237 85.0 680 0.3650 82.2342 75.2389 81.3411 81.5126 7.2326
0.6237 86.0 688 0.3623 82.0317 74.5029 81.1031 81.2565 7.2558
0.6237 87.0 696 0.3642 82.0317 74.5029 81.1031 81.2565 7.2558
0.6237 88.0 704 0.3679 82.0317 74.5029 81.1031 81.2565 7.2558
0.6237 89.0 712 0.3659 82.2466 74.9846 81.3774 81.5195 7.3023
0.6237 90.0 720 0.3629 82.609 76.312 81.7346 81.837 7.3256
0.6237 91.0 728 0.3617 82.609 76.312 81.7346 81.837 7.3256
0.6237 92.0 736 0.3623 82.0317 74.5029 81.1031 81.2565 7.2558
0.6237 93.0 744 0.3610 82.0317 74.5029 81.1031 81.2565 7.2558
0.6237 94.0 752 0.3622 82.4928 76.6636 81.8006 81.8182 7.2558
0.6237 95.0 760 0.3613 82.4928 76.6636 81.8006 81.8182 7.2558
0.6237 96.0 768 0.3618 82.4928 76.6636 81.8006 81.8182 7.2558
0.6237 97.0 776 0.3609 81.3106 75.0954 80.5458 80.7024 7.3488
0.6237 98.0 784 0.3622 81.3106 75.0954 80.5458 80.7024 7.3488
0.6237 99.0 792 0.3622 81.3106 75.0954 80.5458 80.7024 7.3488
0.6237 100.0 800 0.3610 81.3106 75.0954 80.5458 80.7024 7.3488
0.6237 101.0 808 0.3599 81.3106 75.0954 80.5458 80.7024 7.3488
0.6237 102.0 816 0.3591 81.3106 75.0954 80.5458 80.7024 7.3488
0.6237 103.0 824 0.3609 81.1102 74.3423 80.3961 80.4803 7.3721
0.6237 104.0 832 0.3622 81.1102 74.3423 80.3961 80.4803 7.3721
0.6237 105.0 840 0.3614 81.3106 75.0954 80.5458 80.7024 7.3488
0.6237 106.0 848 0.3597 81.3106 75.0954 80.5458 80.7024 7.3488
0.6237 107.0 856 0.3578 81.1102 74.3423 80.3961 80.4803 7.3721
0.6237 108.0 864 0.3556 81.1102 74.3423 80.3961 80.4803 7.3721
0.6237 109.0 872 0.3554 81.3106 75.0954 80.5458 80.7024 7.3488
0.6237 110.0 880 0.3577 81.3106 75.0954 80.5458 80.7024 7.3488
0.6237 111.0 888 0.3577 81.3106 75.0954 80.5458 80.7024 7.3488
0.6237 112.0 896 0.3576 83.3677 76.9088 82.9137 82.8636 7.3023
0.6237 113.0 904 0.3565 83.3677 76.9088 82.9137 82.8636 7.3023
0.6237 114.0 912 0.3572 83.3677 76.9088 82.9137 82.8636 7.3023
0.6237 115.0 920 0.3559 83.3677 76.9088 82.9137 82.8636 7.3023
0.6237 116.0 928 0.3522 83.3677 76.9088 82.9137 82.8636 7.3023
0.6237 117.0 936 0.3508 83.3677 76.9088 82.9137 82.8636 7.3023
0.6237 118.0 944 0.3496 81.1102 74.3423 80.3961 80.4803 7.3721
0.6237 119.0 952 0.3466 81.3044 74.734 80.6017 80.7189 7.4186
0.6237 120.0 960 0.3469 81.3044 74.734 80.6017 80.7189 7.4186
0.6237 121.0 968 0.3487 81.3044 74.734 80.6017 80.7189 7.4186
0.6237 122.0 976 0.3489 81.3044 74.734 80.6017 80.7189 7.4186
0.6237 123.0 984 0.3487 81.3044 74.734 80.6017 80.7189 7.4186
0.6237 124.0 992 0.3474 81.3044 74.734 80.6017 80.7189 7.4186
0.2099 125.0 1000 0.3464 83.152 76.3453 82.6781 82.6273 7.3721
0.2099 126.0 1008 0.3440 83.152 76.3453 82.6781 82.6273 7.3721
0.2099 127.0 1016 0.3439 83.152 76.3453 82.6781 82.6273 7.3721
0.2099 128.0 1024 0.3441 83.152 76.3453 82.6781 82.6273 7.3721
0.2099 129.0 1032 0.3436 83.152 76.3453 82.6781 82.6273 7.3721
0.2099 130.0 1040 0.3423 83.152 76.3453 82.6781 82.6273 7.3721
0.2099 131.0 1048 0.3417 83.152 76.3453 82.6781 82.6273 7.4651
0.2099 132.0 1056 0.3432 83.152 76.3453 82.6781 82.6273 7.4651
0.2099 133.0 1064 0.3445 83.152 76.3453 82.6781 82.6273 7.4651
0.2099 134.0 1072 0.3457 83.152 76.3453 82.6781 82.6273 7.4651
0.2099 135.0 1080 0.3470 83.152 76.3453 82.6781 82.6273 7.4651
0.2099 136.0 1088 0.3472 83.152 76.3453 82.6781 82.6273 7.3721
0.2099 137.0 1096 0.3473 83.152 76.3453 82.6781 82.6273 7.3721
0.2099 138.0 1104 0.3447 83.152 76.3453 82.6781 82.6273 7.3721
0.2099 139.0 1112 0.3429 83.152 76.3453 82.6781 82.6273 7.3721
0.2099 140.0 1120 0.3427 83.152 76.3453 82.6781 82.6273 7.3721
0.2099 141.0 1128 0.3413 83.152 76.3453 82.6781 82.6273 7.3721
0.2099 142.0 1136 0.3387 84.4252 77.8292 83.8648 83.9203 7.4651
0.2099 143.0 1144 0.3393 84.4252 77.8292 83.8648 83.9203 7.4651
0.2099 144.0 1152 0.3419 84.4252 77.8292 83.8648 83.9203 7.4651
0.2099 145.0 1160 0.3440 84.5823 78.8495 84.0725 84.1992 7.4884
0.2099 146.0 1168 0.3427 84.5823 78.8495 84.0725 84.1992 7.4884
0.2099 147.0 1176 0.3417 84.5823 78.8495 84.0725 84.1992 7.4884
0.2099 148.0 1184 0.3399 85.8694 80.4664 85.2862 85.3235 7.5116
0.2099 149.0 1192 0.3399 85.8694 80.4664 85.2862 85.3235 7.5116
0.2099 150.0 1200 0.3413 85.938 80.3378 85.3453 85.2428 7.4651
0.2099 151.0 1208 0.3417 85.938 80.3378 85.3453 85.2428 7.4651
0.2099 152.0 1216 0.3418 86.202 81.91 85.6626 85.5681 7.4884
0.2099 153.0 1224 0.3420 85.938 80.3378 85.3453 85.2428 7.4651
0.2099 154.0 1232 0.3432 85.8694 80.4664 85.2862 85.3235 7.5116
0.2099 155.0 1240 0.3441 85.8694 80.4664 85.2862 85.3235 7.5116
0.2099 156.0 1248 0.3436 85.938 80.3378 85.3453 85.2428 7.4651
0.2099 157.0 1256 0.3424 85.938 80.3378 85.3453 85.2428 7.4651
0.2099 158.0 1264 0.3420 85.938 80.3378 85.3453 85.2428 7.4651
0.2099 159.0 1272 0.3424 85.8694 80.4664 85.2862 85.3235 7.5116
0.2099 160.0 1280 0.3440 85.938 80.3378 85.3453 85.2428 7.4651
0.2099 161.0 1288 0.3475 85.938 80.3378 85.3453 85.2428 7.4651
0.2099 162.0 1296 0.3501 85.938 80.3378 85.3453 85.2428 7.4651
0.2099 163.0 1304 0.3516 85.938 80.3378 85.3453 85.2428 7.4651
0.2099 164.0 1312 0.3524 85.938 80.3378 85.3453 85.2428 7.4651
0.2099 165.0 1320 0.3516 85.938 80.3378 85.3453 85.2428 7.4651
0.2099 166.0 1328 0.3505 85.938 80.3378 85.3453 85.2428 7.4651
0.2099 167.0 1336 0.3500 85.938 80.3378 85.3453 85.2428 7.4651
0.2099 168.0 1344 0.3493 85.938 80.3378 85.3453 85.2428 7.4651
0.2099 169.0 1352 0.3495 85.938 80.3378 85.3453 85.2428 7.4651
0.2099 170.0 1360 0.3503 85.938 80.3378 85.3453 85.2428 7.4651
0.2099 171.0 1368 0.3505 85.938 80.3378 85.3453 85.2428 7.4651
0.2099 172.0 1376 0.3508 85.938 80.3378 85.3453 85.2428 7.4651
0.2099 173.0 1384 0.3506 85.938 80.3378 85.3453 85.2428 7.4651
0.2099 174.0 1392 0.3501 85.938 80.3378 85.3453 85.2428 7.4651
0.2099 175.0 1400 0.3504 85.938 80.3378 85.3453 85.2428 7.4651
0.2099 176.0 1408 0.3498 85.938 80.3378 85.3453 85.2428 7.4651
0.2099 177.0 1416 0.3494 85.938 80.3378 85.3453 85.2428 7.4651
0.2099 178.0 1424 0.3491 85.938 80.3378 85.3453 85.2428 7.4651
0.2099 179.0 1432 0.3491 85.938 80.3378 85.3453 85.2428 7.4651
0.2099 180.0 1440 0.3488 85.938 80.3378 85.3453 85.2428 7.4651
0.2099 181.0 1448 0.3485 85.938 80.3378 85.3453 85.2428 7.4651
0.2099 182.0 1456 0.3490 85.938 80.3378 85.3453 85.2428 7.4651
0.2099 183.0 1464 0.3503 85.938 80.3378 85.3453 85.2428 7.4651
0.2099 184.0 1472 0.3508 85.938 80.3378 85.3453 85.2428 7.4651
0.2099 185.0 1480 0.3513 85.938 80.3378 85.3453 85.2428 7.4651
0.2099 186.0 1488 0.3518 85.938 80.3378 85.3453 85.2428 7.4651
0.2099 187.0 1496 0.3522 85.938 80.3378 85.3453 85.2428 7.4651
0.137 188.0 1504 0.3525 85.938 80.3378 85.3453 85.2428 7.4651
0.137 189.0 1512 0.3525 85.938 80.3378 85.3453 85.2428 7.4651
0.137 190.0 1520 0.3526 85.938 80.3378 85.3453 85.2428 7.4651
0.137 191.0 1528 0.3526 85.938 80.3378 85.3453 85.2428 7.4651
0.137 192.0 1536 0.3523 85.938 80.3378 85.3453 85.2428 7.4651
0.137 193.0 1544 0.3520 85.938 80.3378 85.3453 85.2428 7.4651
0.137 194.0 1552 0.3520 85.938 80.3378 85.3453 85.2428 7.4651
0.137 195.0 1560 0.3521 85.938 80.3378 85.3453 85.2428 7.4651
0.137 196.0 1568 0.3519 85.938 80.3378 85.3453 85.2428 7.4651
0.137 197.0 1576 0.3519 85.938 80.3378 85.3453 85.2428 7.4651
0.137 198.0 1584 0.3518 85.938 80.3378 85.3453 85.2428 7.4651
0.137 199.0 1592 0.3518 85.938 80.3378 85.3453 85.2428 7.4651
0.137 200.0 1600 0.3518 85.938 80.3378 85.3453 85.2428 7.4651

Framework versions

  • Transformers 4.42.3
  • Pytorch 2.3.0+cu121
  • Datasets 2.20.0
  • Tokenizers 0.19.1
Downloads last month
6
Safetensors
Model size
60.5M params
Tensor type
F32
·
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Finetuned from