<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
bart-cnn-pubmed-arxiv-pubmed-v3-e100
This model is a fine-tuned version of theojolliffe/bart-cnn-pubmed-arxiv-pubmed on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.1806
- Rouge1: 59.4159
- Rouge2: 48.867
- Rougel: 51.9013
- Rougelsum: 58.3382
- Gen Len: 142.0
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: 1
- eval_batch_size: 1
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 100
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
---|---|---|---|---|---|---|---|---|
1.2541 | 1.0 | 795 | 0.9350 | 52.5594 | 32.6314 | 35.2302 | 50.1767 | 142.0 |
0.7018 | 2.0 | 1590 | 0.8022 | 53.4804 | 35.4649 | 37.1673 | 51.2428 | 142.0 |
0.5266 | 3.0 | 2385 | 0.7752 | 52.9462 | 34.3697 | 36.611 | 50.6922 | 142.0 |
0.3475 | 4.0 | 3180 | 0.7771 | 53.4605 | 35.4738 | 38.5714 | 51.3798 | 142.0 |
0.2691 | 5.0 | 3975 | 0.7424 | 54.1132 | 35.7289 | 39.2653 | 51.6822 | 141.4259 |
0.182 | 6.0 | 4770 | 0.8037 | 53.7969 | 35.7324 | 38.4764 | 51.4929 | 141.7778 |
0.1446 | 7.0 | 5565 | 0.7686 | 55.0274 | 38.7813 | 42.6251 | 52.9847 | 142.0 |
0.1191 | 8.0 | 6360 | 0.7807 | 55.4651 | 38.6537 | 41.2746 | 53.578 | 141.8704 |
0.0976 | 9.0 | 7155 | 0.8045 | 55.2843 | 40.2358 | 42.8464 | 54.0957 | 142.0 |
0.0882 | 10.0 | 7950 | 0.8533 | 56.8288 | 41.6714 | 44.3961 | 54.9406 | 142.0 |
0.0721 | 11.0 | 8745 | 0.8962 | 55.3187 | 40.1599 | 43.2103 | 54.1964 | 142.0 |
0.0597 | 12.0 | 9540 | 0.8653 | 55.5706 | 40.2321 | 44.0075 | 53.9883 | 142.0 |
0.054 | 13.0 | 10335 | 0.8566 | 55.6622 | 40.0252 | 42.6907 | 54.0548 | 142.0 |
0.0476 | 14.0 | 11130 | 0.8900 | 57.5046 | 43.6309 | 46.449 | 55.9909 | 142.0 |
0.0432 | 15.0 | 11925 | 0.9149 | 55.604 | 39.9591 | 43.1729 | 54.3703 | 142.0 |
0.0403 | 16.0 | 12720 | 0.9258 | 55.1275 | 39.6566 | 42.3852 | 53.7656 | 142.0 |
0.0351 | 17.0 | 13515 | 0.9184 | 58.2352 | 44.6109 | 47.3863 | 56.9529 | 142.0 |
0.032 | 18.0 | 14310 | 0.9275 | 55.9687 | 41.2482 | 44.0076 | 54.0707 | 142.0 |
0.0313 | 19.0 | 15105 | 0.9635 | 56.3574 | 41.2113 | 44.8358 | 54.6279 | 142.0 |
0.0258 | 20.0 | 15900 | 0.9478 | 57.8445 | 44.297 | 46.8836 | 56.2003 | 142.0 |
0.0277 | 21.0 | 16695 | 0.9363 | 58.4823 | 46.0943 | 48.7817 | 57.5883 | 141.6667 |
0.0219 | 22.0 | 17490 | 0.9705 | 57.6022 | 43.9147 | 47.3054 | 56.3866 | 142.0 |
0.0231 | 23.0 | 18285 | 0.9857 | 56.5809 | 42.9124 | 46.789 | 55.3897 | 142.0 |
0.021 | 24.0 | 19080 | 1.0155 | 56.9745 | 43.8859 | 46.6109 | 55.708 | 142.0 |
0.02 | 25.0 | 19875 | 1.0095 | 57.9702 | 45.1809 | 48.2856 | 56.6941 | 142.0 |
0.0175 | 26.0 | 20670 | 0.9634 | 57.7023 | 45.1577 | 48.2398 | 56.5282 | 142.0 |
0.0161 | 27.0 | 21465 | 1.0197 | 58.739 | 46.3307 | 49.2328 | 57.5778 | 142.0 |
0.0186 | 28.0 | 22260 | 0.9790 | 56.1661 | 42.9731 | 45.8654 | 54.4365 | 142.0 |
0.0145 | 29.0 | 23055 | 0.9883 | 55.8554 | 41.7405 | 45.177 | 54.478 | 142.0 |
0.013 | 30.0 | 23850 | 0.9977 | 55.5831 | 41.2429 | 44.8063 | 53.886 | 142.0 |
0.0131 | 31.0 | 24645 | 0.9765 | 57.4478 | 44.8905 | 48.1376 | 56.102 | 141.463 |
0.0118 | 32.0 | 25440 | 1.0000 | 58.4282 | 46.6557 | 49.4122 | 57.1979 | 142.0 |
0.0117 | 33.0 | 26235 | 0.9924 | 57.1995 | 44.4177 | 47.6248 | 56.0251 | 141.2407 |
0.011 | 34.0 | 27030 | 1.0698 | 57.8918 | 45.925 | 49.0505 | 56.9352 | 142.0 |
0.0093 | 35.0 | 27825 | 1.0297 | 57.7003 | 45.4556 | 47.9919 | 56.5134 | 141.8148 |
0.0112 | 36.0 | 28620 | 1.0429 | 58.4039 | 46.6401 | 49.3897 | 57.4753 | 142.0 |
0.0101 | 37.0 | 29415 | 1.0761 | 59.2768 | 47.5384 | 50.2152 | 57.9493 | 142.0 |
0.0095 | 38.0 | 30210 | 1.0254 | 58.6205 | 47.246 | 50.87 | 57.7829 | 142.0 |
0.0087 | 39.0 | 31005 | 1.0216 | 57.7667 | 44.7762 | 48.067 | 56.6006 | 142.0 |
0.0082 | 40.0 | 31800 | 1.0587 | 58.4703 | 45.8371 | 48.5321 | 57.2036 | 142.0 |
0.0075 | 41.0 | 32595 | 1.0621 | 58.5629 | 46.8885 | 49.5943 | 57.4579 | 142.0 |
0.0079 | 42.0 | 33390 | 1.0845 | 57.664 | 45.5954 | 48.408 | 56.661 | 141.9815 |
0.0076 | 43.0 | 34185 | 1.0705 | 58.1776 | 46.0435 | 49.3126 | 57.138 | 142.0 |
0.0074 | 44.0 | 34980 | 1.0636 | 58.1022 | 46.4877 | 48.7985 | 56.9073 | 142.0 |
0.007 | 45.0 | 35775 | 1.0810 | 57.8251 | 44.8767 | 47.8991 | 56.5977 | 142.0 |
0.0057 | 46.0 | 36570 | 1.0560 | 58.5086 | 46.3448 | 49.2576 | 57.4386 | 142.0 |
0.0062 | 47.0 | 37365 | 1.0903 | 58.8772 | 47.2886 | 49.9502 | 57.611 | 142.0 |
0.0058 | 48.0 | 38160 | 1.0847 | 59.4672 | 48.3847 | 51.602 | 58.4588 | 142.0 |
0.0061 | 49.0 | 38955 | 1.0798 | 59.5308 | 48.0396 | 50.8641 | 58.5016 | 142.0 |
0.0062 | 50.0 | 39750 | 1.0795 | 59.5026 | 48.5319 | 51.7426 | 58.7111 | 142.0 |
0.0051 | 51.0 | 40545 | 1.0842 | 57.7941 | 46.1198 | 48.7341 | 56.7164 | 142.0 |
0.0057 | 52.0 | 41340 | 1.0777 | 58.6131 | 46.3924 | 49.0787 | 57.1278 | 142.0 |
0.0039 | 53.0 | 42135 | 1.1133 | 57.6447 | 45.6699 | 48.5207 | 56.6447 | 142.0 |
0.0038 | 54.0 | 42930 | 1.0714 | 58.1462 | 46.4616 | 49.273 | 57.2771 | 142.0 |
0.004 | 55.0 | 43725 | 1.0852 | 58.6577 | 47.2095 | 50.4702 | 57.7724 | 142.0 |
0.0044 | 56.0 | 44520 | 1.1152 | 59.0564 | 47.1621 | 50.2807 | 58.3122 | 142.0 |
0.0042 | 57.0 | 45315 | 1.0831 | 58.1767 | 46.8127 | 49.9166 | 57.1833 | 142.0 |
0.0038 | 58.0 | 46110 | 1.1156 | 57.8515 | 46.3229 | 48.6843 | 56.7218 | 142.0 |
0.0038 | 59.0 | 46905 | 1.1105 | 57.9332 | 45.8354 | 49.27 | 57.1209 | 142.0 |
0.0034 | 60.0 | 47700 | 1.1104 | 60.0207 | 49.2067 | 51.8751 | 58.9484 | 142.0 |
0.0028 | 61.0 | 48495 | 1.1533 | 58.3432 | 46.8835 | 50.2868 | 57.5427 | 141.6111 |
0.0026 | 62.0 | 49290 | 1.1441 | 58.6838 | 46.9472 | 49.9524 | 57.5287 | 142.0 |
0.0028 | 63.0 | 50085 | 1.1232 | 58.0202 | 45.5855 | 48.6554 | 56.8368 | 141.9444 |
0.0037 | 64.0 | 50880 | 1.1520 | 58.3905 | 47.0348 | 49.8478 | 57.3665 | 142.0 |
0.0029 | 65.0 | 51675 | 1.1358 | 59.231 | 48.7251 | 51.6138 | 58.5718 | 142.0 |
0.0026 | 66.0 | 52470 | 1.1559 | 58.9482 | 47.2137 | 49.4299 | 57.7235 | 142.0 |
0.0025 | 67.0 | 53265 | 1.1272 | 59.3333 | 47.7419 | 50.7018 | 58.326 | 142.0 |
0.0026 | 68.0 | 54060 | 1.1613 | 58.6404 | 47.3218 | 50.255 | 57.4646 | 142.0 |
0.0015 | 69.0 | 54855 | 1.1575 | 58.7927 | 47.7018 | 50.695 | 57.796 | 142.0 |
0.0018 | 70.0 | 55650 | 1.1463 | 58.9455 | 47.2691 | 50.176 | 57.9997 | 142.0 |
0.0023 | 71.0 | 56445 | 1.1622 | 58.5943 | 46.9325 | 49.4159 | 57.2131 | 142.0 |
0.0024 | 72.0 | 57240 | 1.1258 | 58.2779 | 47.4119 | 49.9836 | 57.4867 | 142.0 |
0.0019 | 73.0 | 58035 | 1.1333 | 58.9185 | 47.5755 | 50.0765 | 57.8661 | 142.0 |
0.0017 | 74.0 | 58830 | 1.1469 | 60.5037 | 49.4508 | 52.2863 | 59.6675 | 141.963 |
0.0017 | 75.0 | 59625 | 1.1349 | 59.4264 | 47.4554 | 50.0383 | 58.3103 | 142.0 |
0.0025 | 76.0 | 60420 | 1.1215 | 58.2795 | 46.9852 | 49.5787 | 57.4501 | 142.0 |
0.0012 | 77.0 | 61215 | 1.1272 | 58.2248 | 47.0914 | 50.2569 | 57.1888 | 142.0 |
0.001 | 78.0 | 62010 | 1.1648 | 59.3808 | 48.4901 | 51.118 | 58.6251 | 142.0 |
0.0011 | 79.0 | 62805 | 1.1433 | 58.8697 | 47.6232 | 50.0226 | 57.6299 | 142.0 |
0.001 | 80.0 | 63600 | 1.1486 | 59.0608 | 47.1931 | 50.1354 | 57.8687 | 142.0 |
0.0011 | 81.0 | 64395 | 1.1695 | 58.341 | 47.0306 | 49.9269 | 57.339 | 142.0 |
0.001 | 82.0 | 65190 | 1.1589 | 58.9283 | 48.4586 | 51.2319 | 57.9485 | 142.0 |
0.0009 | 83.0 | 65985 | 1.1868 | 59.1377 | 48.2469 | 50.8486 | 58.1111 | 142.0 |
0.001 | 84.0 | 66780 | 1.1664 | 58.7706 | 47.5868 | 50.5937 | 57.7824 | 142.0 |
0.0009 | 85.0 | 67575 | 1.1719 | 57.8121 | 45.5997 | 48.2442 | 56.5272 | 142.0 |
0.0006 | 86.0 | 68370 | 1.1662 | 58.5204 | 47.5947 | 50.1839 | 57.6431 | 142.0 |
0.0007 | 87.0 | 69165 | 1.1668 | 59.2416 | 48.2985 | 51.0347 | 58.2794 | 142.0 |
0.0007 | 88.0 | 69960 | 1.1619 | 58.6933 | 47.5716 | 50.6785 | 57.5726 | 142.0 |
0.0003 | 89.0 | 70755 | 1.1765 | 59.2853 | 48.6451 | 51.3017 | 58.2603 | 142.0 |
0.0005 | 90.0 | 71550 | 1.1766 | 59.248 | 48.5642 | 50.9843 | 58.1706 | 142.0 |
0.0005 | 91.0 | 72345 | 1.1983 | 59.0009 | 48.311 | 51.0192 | 57.9822 | 142.0 |
0.0006 | 92.0 | 73140 | 1.1721 | 59.1248 | 49.0902 | 51.9937 | 58.2288 | 142.0 |
0.0003 | 93.0 | 73935 | 1.1799 | 58.2448 | 47.4011 | 49.987 | 57.515 | 142.0 |
0.0005 | 94.0 | 74730 | 1.1900 | 59.931 | 49.6663 | 52.3233 | 58.962 | 142.0 |
0.0004 | 95.0 | 75525 | 1.1868 | 59.5898 | 49.0004 | 51.4835 | 58.6463 | 142.0 |
0.0093 | 96.0 | 76320 | 1.1831 | 59.9405 | 49.83 | 52.4355 | 59.0702 | 142.0 |
0.0004 | 97.0 | 77115 | 1.1841 | 59.7379 | 49.5435 | 52.5255 | 58.8526 | 142.0 |
0.0004 | 98.0 | 77910 | 1.1790 | 59.5515 | 49.0724 | 51.9888 | 58.5488 | 142.0 |
0.0003 | 99.0 | 78705 | 1.1786 | 59.7712 | 49.0557 | 51.8137 | 58.7144 | 142.0 |
0.0002 | 100.0 | 79500 | 1.1806 | 59.4159 | 48.867 | 51.9013 | 58.3382 | 142.0 |
Framework versions
- Transformers 4.19.2
- Pytorch 1.11.0+cu113
- Datasets 2.2.2
- Tokenizers 0.12.1