<!-- 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-uncased-finetuned-sprint-meds
This model is a fine-tuned version of distilbert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.8121
- Accuracy: 0.8843
- F1: 0.8655
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: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 50
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 0.4894 | 1.0 | 21 | 0.9107 | 0.8612 | 0.8354 |
| 0.4471 | 2.0 | 42 | 0.8964 | 0.8630 | 0.8363 |
| 0.4086 | 3.0 | 63 | 0.8796 | 0.8612 | 0.8348 |
| 0.3651 | 4.0 | 84 | 0.8581 | 0.8665 | 0.8415 |
| 0.3365 | 5.0 | 105 | 0.8546 | 0.8683 | 0.8429 |
| 0.3241 | 6.0 | 126 | 0.8448 | 0.8701 | 0.8467 |
| 0.299 | 7.0 | 147 | 0.8372 | 0.8683 | 0.8461 |
| 0.2498 | 8.0 | 168 | 0.8340 | 0.8737 | 0.8500 |
| 0.2579 | 9.0 | 189 | 0.8199 | 0.8737 | 0.8498 |
| 0.2526 | 10.0 | 210 | 0.8191 | 0.8772 | 0.8549 |
| 0.2243 | 11.0 | 231 | 0.8227 | 0.8719 | 0.8476 |
| 0.1888 | 12.0 | 252 | 0.8254 | 0.8719 | 0.8489 |
| 0.2159 | 13.0 | 273 | 0.8163 | 0.8772 | 0.8541 |
| 0.1845 | 14.0 | 294 | 0.8117 | 0.8754 | 0.8533 |
| 0.1774 | 15.0 | 315 | 0.8107 | 0.8772 | 0.8529 |
| 0.1503 | 16.0 | 336 | 0.8109 | 0.8790 | 0.8589 |
| 0.1565 | 17.0 | 357 | 0.8141 | 0.8772 | 0.8533 |
| 0.1539 | 18.0 | 378 | 0.8174 | 0.8772 | 0.8556 |
| 0.1393 | 19.0 | 399 | 0.8132 | 0.8790 | 0.8587 |
| 0.1279 | 20.0 | 420 | 0.8171 | 0.8826 | 0.8602 |
| 0.1231 | 21.0 | 441 | 0.8134 | 0.8808 | 0.8603 |
| 0.119 | 22.0 | 462 | 0.8132 | 0.8843 | 0.8628 |
| 0.1058 | 23.0 | 483 | 0.8043 | 0.8826 | 0.8631 |
| 0.1106 | 24.0 | 504 | 0.8159 | 0.8808 | 0.8596 |
| 0.1036 | 25.0 | 525 | 0.8090 | 0.8826 | 0.8612 |
| 0.0895 | 26.0 | 546 | 0.8093 | 0.8879 | 0.8666 |
| 0.1001 | 27.0 | 567 | 0.8121 | 0.8843 | 0.8636 |
| 0.0956 | 28.0 | 588 | 0.8113 | 0.8808 | 0.8609 |
| 0.0954 | 29.0 | 609 | 0.8099 | 0.8790 | 0.8581 |
| 0.0856 | 30.0 | 630 | 0.8169 | 0.8826 | 0.8616 |
| 0.0819 | 31.0 | 651 | 0.8204 | 0.8790 | 0.8590 |
| 0.0888 | 32.0 | 672 | 0.8125 | 0.8826 | 0.8644 |
| 0.0806 | 33.0 | 693 | 0.8144 | 0.8826 | 0.8628 |
| 0.0836 | 34.0 | 714 | 0.8153 | 0.8790 | 0.8583 |
| 0.0832 | 35.0 | 735 | 0.8139 | 0.8843 | 0.8644 |
| 0.0719 | 36.0 | 756 | 0.8134 | 0.8826 | 0.8623 |
| 0.0843 | 37.0 | 777 | 0.8141 | 0.8826 | 0.8637 |
| 0.0768 | 38.0 | 798 | 0.8157 | 0.8826 | 0.8616 |
| 0.0765 | 39.0 | 819 | 0.8183 | 0.8808 | 0.8621 |
| 0.0685 | 40.0 | 840 | 0.8139 | 0.8808 | 0.8628 |
| 0.0696 | 41.0 | 861 | 0.8149 | 0.8808 | 0.8631 |
| 0.0747 | 42.0 | 882 | 0.8144 | 0.8843 | 0.8655 |
| 0.0709 | 43.0 | 903 | 0.8136 | 0.8843 | 0.8655 |
| 0.0666 | 44.0 | 924 | 0.8140 | 0.8843 | 0.8661 |
| 0.071 | 45.0 | 945 | 0.8123 | 0.8808 | 0.8634 |
| 0.0682 | 46.0 | 966 | 0.8137 | 0.8843 | 0.8661 |
| 0.0743 | 47.0 | 987 | 0.8119 | 0.8843 | 0.8661 |
| 0.069 | 48.0 | 1008 | 0.8113 | 0.8843 | 0.8661 |
| 0.0624 | 49.0 | 1029 | 0.8119 | 0.8843 | 0.8655 |
| 0.0713 | 50.0 | 1050 | 0.8121 | 0.8843 | 0.8655 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.3
