Edit model card

bart-base-finetuned-cve-reason

This model is a fine-tuned version of facebook/bart-base on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.7242
  • Rouge1: 86.7292
  • Rouge2: 80.2129
  • Rougel: 86.5386
  • Rougelsum: 86.4657
  • Gen Len: 8.7209

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 1.3243 67.339 50.8361 67.3741 67.1699 8.3488
No log 2.0 16 0.7632 70.9083 55.4762 71.0228 70.8892 7.9767
No log 3.0 24 0.6163 71.7595 63.6825 72.1485 71.7123 8.2326
No log 4.0 32 0.4829 78.0511 70.5341 78.2173 77.9653 8.3488
No log 5.0 40 0.4423 74.1714 64.3602 74.4255 74.3167 8.2326
No log 6.0 48 0.4247 77.0949 70.6073 77.3638 77.1752 8.5349
No log 7.0 56 0.4081 76.4213 69.5743 76.6255 76.5681 8.3721
No log 8.0 64 0.3481 77.489 70.4674 77.5236 77.5534 8.5814
No log 9.0 72 0.3723 81.5975 74.4863 81.5031 81.2898 8.5814
No log 10.0 80 0.3301 79.2387 73.8951 79.4667 79.3255 8.4884
No log 11.0 88 0.3287 84.7464 78.9188 84.5119 84.6171 8.5581
No log 12.0 96 0.3494 84.9055 79.7423 84.874 84.6678 8.6047
No log 13.0 104 0.3771 84.4005 78.2226 84.4101 84.1687 8.6744
No log 14.0 112 0.4061 82.8304 76.3376 82.564 82.4215 8.6744
No log 15.0 120 0.3681 81.9693 75.0607 81.6464 81.527 8.6047
No log 16.0 128 0.3653 86.3552 81.2234 86.1172 86.135 8.7209
No log 17.0 136 0.3889 86.7927 79.6688 86.9133 86.9376 8.5116
No log 18.0 144 0.4115 86.8485 81.1308 86.6876 86.5896 8.6977
No log 19.0 152 0.4514 84.0645 76.0789 83.9224 84.1115 8.6047
No log 20.0 160 0.4032 86.1873 80.1299 86.0015 85.9981 8.7209
No log 21.0 168 0.4335 86.1909 78.3663 86.0234 85.8704 8.6047
No log 22.0 176 0.4705 86.8725 81.7095 87.1232 87.0863 8.7209
No log 23.0 184 0.4362 86.572 79.0652 86.4234 86.3894 8.6977
No log 24.0 192 0.4482 86.4459 78.7065 86.3177 86.1807 8.6744
No log 25.0 200 0.4093 85.5143 78.6253 85.5057 85.279 8.6279
No log 26.0 208 0.4383 85.8655 76.9002 85.8011 85.5836 8.5116
No log 27.0 216 0.4653 86.7114 80.053 86.6863 86.5543 8.7442
No log 28.0 224 0.4791 86.7114 80.053 86.6863 86.5543 8.7442
No log 29.0 232 0.4420 88.888 82.0477 88.6613 88.5852 8.6279
No log 30.0 240 0.4261 85.5644 78.7677 85.5776 85.471 8.6977
No log 31.0 248 0.4487 86.656 79.0557 86.4973 86.3996 8.6279
No log 32.0 256 0.4345 87.0087 80.5341 86.8669 86.6288 8.6279
No log 33.0 264 0.4985 84.8791 76.91 84.8426 84.8187 8.6279
No log 34.0 272 0.4905 85.1913 77.3222 85.204 85.1211 8.6744
No log 35.0 280 0.5040 86.7292 80.2129 86.5386 86.4657 8.7209
No log 36.0 288 0.5368 84.7912 76.6981 84.9436 84.829 8.5814
No log 37.0 296 0.4997 85.9598 80.2323 85.915 85.8587 8.7209
No log 38.0 304 0.5739 84.8791 76.91 84.8426 84.8187 8.6279
No log 39.0 312 0.5641 86.7292 80.2129 86.5386 86.4657 8.8372
No log 40.0 320 0.5013 86.8485 81.1308 86.6876 86.5896 8.6977
No log 41.0 328 0.5565 83.8836 75.9866 83.6564 83.7678 8.6279
No log 42.0 336 0.5493 84.423 77.1673 84.3614 84.3597 8.5116
No log 43.0 344 0.5627 85.4816 78.7135 85.542 85.4334 8.7209
No log 44.0 352 0.5944 83.1265 75.08 82.7267 82.7311 8.6977
No log 45.0 360 0.6430 83.4545 76.4388 83.1878 83.1047 8.7209
No log 46.0 368 0.6313 85.4816 78.7135 85.542 85.4334 8.7209
No log 47.0 376 0.6261 85.1913 77.3222 85.204 85.1211 8.6744
No log 48.0 384 0.6148 85.3464 77.6256 85.3989 85.3622 8.6512
No log 49.0 392 0.5997 86.8635 80.523 86.7244 86.6763 8.7209
No log 50.0 400 0.6140 84.8791 76.91 84.8426 84.8187 8.6279
No log 51.0 408 0.6374 85.1913 77.3222 85.204 85.1211 8.6744
No log 52.0 416 0.6330 85.1863 78.3341 85.2485 85.1526 8.6512
No log 53.0 424 0.6294 85.1863 78.3341 85.2485 85.1526 8.6512
No log 54.0 432 0.6408 86.3792 78.753 86.1622 86.1327 8.6977
No log 55.0 440 0.6459 86.3792 78.753 86.1622 86.1327 8.6977
No log 56.0 448 0.6387 86.8635 80.523 86.7244 86.6763 8.6977
No log 57.0 456 0.6526 85.5596 78.6894 85.5393 85.5324 8.6512
No log 58.0 464 0.6774 85.4816 78.7135 85.542 85.4334 8.6977
No log 59.0 472 0.6622 85.4816 78.7135 85.542 85.4334 8.7209
No log 60.0 480 0.6590 86.3792 78.753 86.1622 86.1327 8.6977
No log 61.0 488 0.6507 84.4274 76.8061 84.0639 83.9789 8.6977
No log 62.0 496 0.6544 84.4274 76.8061 84.0639 83.9789 8.6977
0.1969 63.0 504 0.6443 86.8635 80.523 86.7244 86.6763 8.7209
0.1969 64.0 512 0.6707 86.3792 78.753 86.1622 86.1327 8.6977
0.1969 65.0 520 0.6775 86.3792 78.753 86.1622 86.1327 8.6977
0.1969 66.0 528 0.6602 85.4816 78.7135 85.542 85.4334 8.7209
0.1969 67.0 536 0.6927 85.4816 78.7135 85.542 85.4334 8.6977
0.1969 68.0 544 0.6795 85.1913 77.3222 85.204 85.1211 8.6744
0.1969 69.0 552 0.6403 86.7292 80.2129 86.5386 86.4657 8.7209
0.1969 70.0 560 0.6402 86.3792 78.753 86.1622 86.1327 8.6977
0.1969 71.0 568 0.6455 86.3792 78.753 86.1622 86.1327 8.6977
0.1969 72.0 576 0.6463 86.3792 78.753 86.1622 86.1327 8.6977
0.1969 73.0 584 0.6078 86.7292 80.2129 86.5386 86.4657 8.7209
0.1969 74.0 592 0.6162 86.7292 80.2129 86.5386 86.4657 8.7209
0.1969 75.0 600 0.6122 86.7292 80.2129 86.5386 86.4657 8.7209
0.1969 76.0 608 0.6286 85.1913 77.3222 85.204 85.1211 8.6744
0.1969 77.0 616 0.6875 85.1913 77.3222 85.204 85.1211 8.6744
0.1969 78.0 624 0.7017 85.1913 77.3222 85.204 85.1211 8.6744
0.1969 79.0 632 0.6846 85.4816 78.7135 85.542 85.4334 8.6977
0.1969 80.0 640 0.6958 85.6288 79.5153 85.7781 85.5754 8.7209
0.1969 81.0 648 0.6940 85.3796 78.0439 85.4614 85.3101 8.6977
0.1969 82.0 656 0.6704 85.3796 78.0439 85.4614 85.3101 8.6977
0.1969 83.0 664 0.6569 85.6288 79.5153 85.7781 85.5754 8.7209
0.1969 84.0 672 0.6674 86.5778 79.4872 86.3955 86.3363 8.7209
0.1969 85.0 680 0.6802 86.9008 80.8494 86.7579 86.7091 8.7442
0.1969 86.0 688 0.6868 85.4816 78.7135 85.542 85.4334 8.6977
0.1969 87.0 696 0.7054 85.4816 78.7135 85.542 85.4334 8.6977
0.1969 88.0 704 0.6566 86.7292 80.2129 86.5386 86.4657 8.7209
0.1969 89.0 712 0.6318 86.3792 78.753 86.1622 86.1327 8.6977
0.1969 90.0 720 0.6005 86.9008 80.8494 86.7579 86.7091 8.7442
0.1969 91.0 728 0.6527 86.3792 78.753 86.1622 86.1327 8.6977
0.1969 92.0 736 0.6642 85.4816 78.7135 85.542 85.4334 8.6977
0.1969 93.0 744 0.6576 85.4816 78.7135 85.542 85.4334 8.6977
0.1969 94.0 752 0.6502 85.4816 78.7135 85.542 85.4334 8.6977
0.1969 95.0 760 0.6275 85.4816 78.7135 85.542 85.4334 8.7209
0.1969 96.0 768 0.6249 86.3792 78.753 86.1622 86.1327 8.6977
0.1969 97.0 776 0.6263 86.7292 80.2129 86.5386 86.4657 8.7209
0.1969 98.0 784 0.6513 86.7292 80.2129 86.5386 86.4657 8.7209
0.1969 99.0 792 0.6712 85.9196 79.2535 85.5727 85.611 8.7674
0.1969 100.0 800 0.6755 86.9008 80.8494 86.7579 86.7091 8.7442
0.1969 101.0 808 0.6849 86.3792 78.753 86.1622 86.1327 8.6977
0.1969 102.0 816 0.6921 86.3792 78.753 86.1622 86.1327 8.6977
0.1969 103.0 824 0.6931 86.7292 80.2129 86.5386 86.4657 8.7209
0.1969 104.0 832 0.6942 86.3792 78.753 86.1622 86.1327 8.6977
0.1969 105.0 840 0.6830 86.7292 80.2129 86.5386 86.4657 8.7209
0.1969 106.0 848 0.6595 86.7292 80.2129 86.5386 86.4657 8.7209
0.1969 107.0 856 0.6437 86.7292 80.2129 86.5386 86.4657 8.7209
0.1969 108.0 864 0.6410 86.3792 78.753 86.1622 86.1327 8.6977
0.1969 109.0 872 0.6662 85.1913 77.3222 85.204 85.1211 8.6744
0.1969 110.0 880 0.6716 85.4816 78.7135 85.542 85.4334 8.6977
0.1969 111.0 888 0.6613 85.4816 78.7135 85.542 85.4334 8.6977
0.1969 112.0 896 0.6648 86.3792 78.753 86.1622 86.1327 8.6977
0.1969 113.0 904 0.6755 85.1913 77.3222 85.204 85.1211 8.6744
0.1969 114.0 912 0.6874 85.1913 77.3222 85.204 85.1211 8.6744
0.1969 115.0 920 0.7020 85.4816 78.7135 85.542 85.4334 8.6977
0.1969 116.0 928 0.7019 85.4816 78.7135 85.542 85.4334 8.6977
0.1969 117.0 936 0.6939 86.7292 80.2129 86.5386 86.4657 8.7209
0.1969 118.0 944 0.6893 86.3792 78.753 86.1622 86.1327 8.6977
0.1969 119.0 952 0.6771 86.3792 78.753 86.1622 86.1327 8.6977
0.1969 120.0 960 0.6921 86.7292 80.2129 86.5386 86.4657 8.7209
0.1969 121.0 968 0.7286 86.7292 80.2129 86.5386 86.4657 8.7209
0.1969 122.0 976 0.7536 86.7292 80.2129 86.5386 86.4657 8.7209
0.1969 123.0 984 0.7721 86.3792 78.753 86.1622 86.1327 8.6977
0.1969 124.0 992 0.7338 85.4816 78.7135 85.542 85.4334 8.6977
0.0164 125.0 1000 0.6910 86.7292 80.2129 86.5386 86.4657 8.7209
0.0164 126.0 1008 0.6750 86.7292 80.2129 86.5386 86.4657 8.7209
0.0164 127.0 1016 0.6828 86.3792 78.753 86.1622 86.1327 8.6977
0.0164 128.0 1024 0.6808 86.3792 78.753 86.1622 86.1327 8.6977
0.0164 129.0 1032 0.6858 86.3792 78.753 86.1622 86.1327 8.6977
0.0164 130.0 1040 0.7016 86.3792 78.753 86.1622 86.1327 8.6977
0.0164 131.0 1048 0.7247 86.7292 80.2129 86.5386 86.4657 8.7209
0.0164 132.0 1056 0.7364 86.7292 80.2129 86.5386 86.4657 8.7209
0.0164 133.0 1064 0.7304 86.3792 78.753 86.1622 86.1327 8.6977
0.0164 134.0 1072 0.7239 86.7292 80.2129 86.5386 86.4657 8.7209
0.0164 135.0 1080 0.7285 85.6288 79.5153 85.7781 85.5754 8.7209
0.0164 136.0 1088 0.7250 85.4816 78.7135 85.542 85.4334 8.6977
0.0164 137.0 1096 0.7271 85.6288 79.5153 85.7781 85.5754 8.7209
0.0164 138.0 1104 0.7249 85.1913 77.3222 85.204 85.1211 8.6744
0.0164 139.0 1112 0.7249 85.4816 78.7135 85.542 85.4334 8.6977
0.0164 140.0 1120 0.7417 85.3796 78.0439 85.4614 85.3101 8.6977
0.0164 141.0 1128 0.7366 85.4816 78.7135 85.542 85.4334 8.6977
0.0164 142.0 1136 0.7390 85.1913 77.3222 85.204 85.1211 8.6744
0.0164 143.0 1144 0.7423 85.3796 78.0439 85.4614 85.3101 8.6977
0.0164 144.0 1152 0.7355 86.7292 80.2129 86.5386 86.4657 8.7209
0.0164 145.0 1160 0.7249 86.7292 80.2129 86.5386 86.4657 8.7209
0.0164 146.0 1168 0.7205 86.3792 78.753 86.1622 86.1327 8.6977
0.0164 147.0 1176 0.7211 86.3792 78.753 86.1622 86.1327 8.6977
0.0164 148.0 1184 0.7169 86.7292 80.2129 86.5386 86.4657 8.7209
0.0164 149.0 1192 0.7123 86.7292 80.2129 86.5386 86.4657 8.7209
0.0164 150.0 1200 0.7140 86.7292 80.2129 86.5386 86.4657 8.7209
0.0164 151.0 1208 0.7136 86.7292 80.2129 86.5386 86.4657 8.7209
0.0164 152.0 1216 0.7127 86.7292 80.2129 86.5386 86.4657 8.7209
0.0164 153.0 1224 0.7169 86.7292 80.2129 86.5386 86.4657 8.7209
0.0164 154.0 1232 0.7168 86.7292 80.2129 86.5386 86.4657 8.7209
0.0164 155.0 1240 0.7109 86.7292 80.2129 86.5386 86.4657 8.7209
0.0164 156.0 1248 0.7081 86.7292 80.2129 86.5386 86.4657 8.7209
0.0164 157.0 1256 0.7081 86.3792 78.753 86.1622 86.1327 8.6977
0.0164 158.0 1264 0.7053 86.7292 80.2129 86.5386 86.4657 8.7209
0.0164 159.0 1272 0.6957 86.7292 80.2129 86.5386 86.4657 8.7209
0.0164 160.0 1280 0.7018 86.7292 80.2129 86.5386 86.4657 8.7209
0.0164 161.0 1288 0.7043 86.7292 80.2129 86.5386 86.4657 8.7209
0.0164 162.0 1296 0.7012 86.7292 80.2129 86.5386 86.4657 8.7209
0.0164 163.0 1304 0.6963 86.7292 80.2129 86.5386 86.4657 8.7209
0.0164 164.0 1312 0.6959 86.7292 80.2129 86.5386 86.4657 8.7209
0.0164 165.0 1320 0.7010 86.3792 78.753 86.1622 86.1327 8.6977
0.0164 166.0 1328 0.7021 86.3792 78.753 86.1622 86.1327 8.6977
0.0164 167.0 1336 0.7009 86.7292 80.2129 86.5386 86.4657 8.7209
0.0164 168.0 1344 0.7028 86.7292 80.2129 86.5386 86.4657 8.7209
0.0164 169.0 1352 0.7019 86.7292 80.2129 86.5386 86.4657 8.7209
0.0164 170.0 1360 0.7036 86.7292 80.2129 86.5386 86.4657 8.7209
0.0164 171.0 1368 0.7060 86.7292 80.2129 86.5386 86.4657 8.7209
0.0164 172.0 1376 0.7101 86.7292 80.2129 86.5386 86.4657 8.7209
0.0164 173.0 1384 0.7090 86.7292 80.2129 86.5386 86.4657 8.7209
0.0164 174.0 1392 0.7092 86.7292 80.2129 86.5386 86.4657 8.7209
0.0164 175.0 1400 0.7089 86.7292 80.2129 86.5386 86.4657 8.7209
0.0164 176.0 1408 0.7080 86.7292 80.2129 86.5386 86.4657 8.7209
0.0164 177.0 1416 0.7104 86.7292 80.2129 86.5386 86.4657 8.7209
0.0164 178.0 1424 0.7127 86.7292 80.2129 86.5386 86.4657 8.7209
0.0164 179.0 1432 0.7149 86.7292 80.2129 86.5386 86.4657 8.7209
0.0164 180.0 1440 0.7156 86.7292 80.2129 86.5386 86.4657 8.7209
0.0164 181.0 1448 0.7173 86.3792 78.753 86.1622 86.1327 8.6977
0.0164 182.0 1456 0.7164 86.7292 80.2129 86.5386 86.4657 8.7209
0.0164 183.0 1464 0.7185 86.3792 78.753 86.1622 86.1327 8.6977
0.0164 184.0 1472 0.7173 86.7292 80.2129 86.5386 86.4657 8.7209
0.0164 185.0 1480 0.7204 86.7292 80.2129 86.5386 86.4657 8.7209
0.0164 186.0 1488 0.7241 86.7292 80.2129 86.5386 86.4657 8.7209
0.0164 187.0 1496 0.7255 86.7292 80.2129 86.5386 86.4657 8.7209
0.0124 188.0 1504 0.7257 86.7292 80.2129 86.5386 86.4657 8.7209
0.0124 189.0 1512 0.7248 86.7292 80.2129 86.5386 86.4657 8.7209
0.0124 190.0 1520 0.7251 86.7292 80.2129 86.5386 86.4657 8.7209
0.0124 191.0 1528 0.7258 86.7292 80.2129 86.5386 86.4657 8.7209
0.0124 192.0 1536 0.7268 86.7292 80.2129 86.5386 86.4657 8.7209
0.0124 193.0 1544 0.7255 86.7292 80.2129 86.5386 86.4657 8.7209
0.0124 194.0 1552 0.7243 86.7292 80.2129 86.5386 86.4657 8.7209
0.0124 195.0 1560 0.7244 86.7292 80.2129 86.5386 86.4657 8.7209
0.0124 196.0 1568 0.7237 86.7292 80.2129 86.5386 86.4657 8.7209
0.0124 197.0 1576 0.7238 86.7292 80.2129 86.5386 86.4657 8.7209
0.0124 198.0 1584 0.7240 86.7292 80.2129 86.5386 86.4657 8.7209
0.0124 199.0 1592 0.7241 86.7292 80.2129 86.5386 86.4657 8.7209
0.0124 200.0 1600 0.7242 86.7292 80.2129 86.5386 86.4657 8.7209

Framework versions

  • Transformers 4.42.3
  • Pytorch 2.3.0+cu121
  • Datasets 2.20.0
  • Tokenizers 0.19.1
Downloads last month
3
Safetensors
Model size
139M params
Tensor type
F32
·
Inference API
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.

Model tree for mgkamalesh7/bart-base-finetuned-cve-reason

Base model

facebook/bart-base
Finetuned
this model