<!-- 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. -->
distilbert-base-cased-finetuned-paper2
This model is a fine-tuned version of distilbert-base-cased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1849
- Precision: 0.6124
- Recall: 0.6695
- F1: 0.6397
- Accuracy: 0.9714
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: 30
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
No log | 1.0 | 68 | 0.1941 | 0.2474 | 0.2034 | 0.2233 | 0.9438 |
No log | 2.0 | 136 | 0.1462 | 0.3680 | 0.3602 | 0.3640 | 0.9593 |
No log | 3.0 | 204 | 0.1154 | 0.4921 | 0.5254 | 0.5082 | 0.9667 |
No log | 4.0 | 272 | 0.1121 | 0.5420 | 0.6017 | 0.5703 | 0.9675 |
No log | 5.0 | 340 | 0.1291 | 0.5714 | 0.6102 | 0.5902 | 0.9676 |
No log | 6.0 | 408 | 0.1355 | 0.5152 | 0.6483 | 0.5741 | 0.9649 |
No log | 7.0 | 476 | 0.1396 | 0.5694 | 0.6949 | 0.6260 | 0.9671 |
0.1425 | 8.0 | 544 | 0.1459 | 0.5484 | 0.6483 | 0.5942 | 0.9675 |
0.1425 | 9.0 | 612 | 0.1623 | 0.5290 | 0.6186 | 0.5703 | 0.9661 |
0.1425 | 10.0 | 680 | 0.1545 | 0.5938 | 0.6441 | 0.6179 | 0.9705 |
0.1425 | 11.0 | 748 | 0.1540 | 0.6171 | 0.7034 | 0.6574 | 0.9709 |
0.1425 | 12.0 | 816 | 0.1621 | 0.5985 | 0.6822 | 0.6376 | 0.9696 |
0.1425 | 13.0 | 884 | 0.1672 | 0.5664 | 0.6864 | 0.6207 | 0.9699 |
0.1425 | 14.0 | 952 | 0.1828 | 0.5563 | 0.7119 | 0.6245 | 0.9675 |
0.0068 | 15.0 | 1020 | 0.1751 | 0.6216 | 0.6822 | 0.6505 | 0.9714 |
0.0068 | 16.0 | 1088 | 0.1738 | 0.5933 | 0.6737 | 0.6310 | 0.9703 |
0.0068 | 17.0 | 1156 | 0.1740 | 0.6345 | 0.6695 | 0.6515 | 0.9717 |
0.0068 | 18.0 | 1224 | 0.1850 | 0.6062 | 0.6653 | 0.6343 | 0.9707 |
0.0068 | 19.0 | 1292 | 0.1856 | 0.6216 | 0.6822 | 0.6505 | 0.9714 |
0.0068 | 20.0 | 1360 | 0.1936 | 0.6015 | 0.6653 | 0.6318 | 0.9718 |
0.0068 | 21.0 | 1428 | 0.1844 | 0.6367 | 0.6907 | 0.6626 | 0.9724 |
0.0068 | 22.0 | 1496 | 0.1882 | 0.6092 | 0.6737 | 0.6398 | 0.9709 |
0.0021 | 23.0 | 1564 | 0.1887 | 0.6423 | 0.6695 | 0.6556 | 0.9721 |
0.0021 | 24.0 | 1632 | 0.1874 | 0.5985 | 0.6568 | 0.6263 | 0.9710 |
0.0021 | 25.0 | 1700 | 0.1861 | 0.5874 | 0.6695 | 0.6257 | 0.9707 |
0.0021 | 26.0 | 1768 | 0.1868 | 0.5918 | 0.6695 | 0.6282 | 0.9709 |
0.0021 | 27.0 | 1836 | 0.1858 | 0.5970 | 0.6780 | 0.6349 | 0.9714 |
0.0021 | 28.0 | 1904 | 0.1842 | 0.6 | 0.6737 | 0.6347 | 0.9713 |
0.0021 | 29.0 | 1972 | 0.1847 | 0.6124 | 0.6695 | 0.6397 | 0.9714 |
0.0012 | 30.0 | 2040 | 0.1849 | 0.6124 | 0.6695 | 0.6397 | 0.9714 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu116
- Datasets 2.10.1
- Tokenizers 0.13.2