roberta-finetuned-sem_eval-english
This model is a fine-tuned version of roberta-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2160
- Micro-f1: 0.1883
- F1: 0.1210
- Roc Auc: 0.5492
- Accuracy: 0.0368
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: 1e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 48
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 16
Training results
Training Loss | Epoch | Step | Validation Loss | Micro-f1 | F1 | Roc Auc | Accuracy |
---|---|---|---|---|---|---|---|
0.3771 | 1.0 | 184 | 0.2700 | 0.1436 | 0.0138 | 0.5011 | 0.0809 |
0.2888 | 2.0 | 368 | 0.2580 | 0.0941 | 0.0366 | 0.5122 | 0.0112 |
0.2747 | 3.0 | 552 | 0.2495 | 0.1052 | 0.0376 | 0.5123 | 0.0173 |
0.2606 | 4.0 | 736 | 0.2447 | 0.1664 | 0.0521 | 0.5238 | 0.0192 |
0.2467 | 5.0 | 920 | 0.2339 | 0.1512 | 0.0654 | 0.5251 | 0.0195 |
0.2326 | 6.0 | 1104 | 0.2268 | 0.1460 | 0.0780 | 0.5271 | 0.0243 |
0.2202 | 7.0 | 1288 | 0.2224 | 0.1565 | 0.0883 | 0.5334 | 0.0272 |
0.2069 | 8.0 | 1472 | 0.2207 | 0.1493 | 0.0886 | 0.5345 | 0.0253 |
0.1949 | 9.0 | 1656 | 0.2240 | 0.1808 | 0.1106 | 0.5422 | 0.0291 |
0.1853 | 10.0 | 1840 | 0.2224 | 0.1754 | 0.1103 | 0.5428 | 0.0323 |
0.1759 | 11.0 | 2024 | 0.2176 | 0.1659 | 0.1047 | 0.5389 | 0.0320 |
0.1674 | 12.0 | 2208 | 0.2148 | 0.1742 | 0.1083 | 0.5437 | 0.0317 |
0.1618 | 13.0 | 2392 | 0.2174 | 0.1857 | 0.1195 | 0.5489 | 0.0387 |
0.157 | 14.0 | 2576 | 0.2162 | 0.1860 | 0.1202 | 0.5483 | 0.0365 |
0.1531 | 15.0 | 2760 | 0.2160 | 0.1883 | 0.1210 | 0.5492 | 0.0368 |
Framework versions
- Transformers 4.40.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1
- Downloads last month
- 2