<!-- 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-emotion
This model is a fine-tuned version of distilbert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.0202
- Accuracy: 0.8235
- F1: 0.8223
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: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 40
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 0.7099 | 1.0 | 17 | 0.6695 | 0.5294 | 0.3665 |
| 0.686 | 2.0 | 34 | 0.6288 | 0.5294 | 0.3665 |
| 0.5945 | 3.0 | 51 | 0.4339 | 0.8824 | 0.8824 |
| 0.3718 | 4.0 | 68 | 0.3600 | 0.8235 | 0.8235 |
| 0.1248 | 5.0 | 85 | 0.5730 | 0.8235 | 0.8223 |
| 0.0984 | 6.0 | 102 | 0.7659 | 0.7647 | 0.7647 |
| 0.0138 | 7.0 | 119 | 0.8271 | 0.8235 | 0.8223 |
| 0.0121 | 8.0 | 136 | 0.8223 | 0.8235 | 0.8223 |
| 0.0062 | 9.0 | 153 | 0.7349 | 0.8235 | 0.8223 |
| 0.0045 | 10.0 | 170 | 0.8381 | 0.7647 | 0.7597 |
| 0.0037 | 11.0 | 187 | 0.8636 | 0.7647 | 0.7597 |
| 0.0031 | 12.0 | 204 | 0.8603 | 0.8235 | 0.8223 |
| 0.0025 | 13.0 | 221 | 0.8714 | 0.8235 | 0.8223 |
| 0.0021 | 14.0 | 238 | 0.8864 | 0.8235 | 0.8223 |
| 0.002 | 15.0 | 255 | 0.9114 | 0.8235 | 0.8223 |
| 0.0017 | 16.0 | 272 | 0.9295 | 0.8235 | 0.8223 |
| 0.0014 | 17.0 | 289 | 0.9360 | 0.8235 | 0.8223 |
| 0.0013 | 18.0 | 306 | 0.9378 | 0.8235 | 0.8223 |
| 0.0012 | 19.0 | 323 | 0.9429 | 0.8235 | 0.8223 |
| 0.0012 | 20.0 | 340 | 0.9528 | 0.8235 | 0.8223 |
| 0.0011 | 21.0 | 357 | 0.9609 | 0.8235 | 0.8223 |
| 0.001 | 22.0 | 374 | 0.9667 | 0.8235 | 0.8223 |
| 0.001 | 23.0 | 391 | 0.9738 | 0.8235 | 0.8223 |
| 0.001 | 24.0 | 408 | 0.9804 | 0.8235 | 0.8223 |
| 0.0009 | 25.0 | 425 | 0.9827 | 0.8235 | 0.8223 |
| 0.0009 | 26.0 | 442 | 0.9863 | 0.8235 | 0.8223 |
| 0.0008 | 27.0 | 459 | 0.9910 | 0.8235 | 0.8223 |
| 0.0008 | 28.0 | 476 | 0.9949 | 0.8235 | 0.8223 |
| 0.0007 | 29.0 | 493 | 1.0002 | 0.8235 | 0.8223 |
| 0.0008 | 30.0 | 510 | 1.0042 | 0.8235 | 0.8223 |
| 0.0007 | 31.0 | 527 | 1.0058 | 0.8235 | 0.8223 |
| 0.0007 | 32.0 | 544 | 1.0091 | 0.8235 | 0.8223 |
| 0.0006 | 33.0 | 561 | 1.0118 | 0.8235 | 0.8223 |
| 0.0006 | 34.0 | 578 | 1.0148 | 0.8235 | 0.8223 |
| 0.0007 | 35.0 | 595 | 1.0163 | 0.8235 | 0.8223 |
| 0.0006 | 36.0 | 612 | 1.0174 | 0.8235 | 0.8223 |
| 0.0006 | 37.0 | 629 | 1.0185 | 0.8235 | 0.8223 |
| 0.0006 | 38.0 | 646 | 1.0194 | 0.8235 | 0.8223 |
| 0.0006 | 39.0 | 663 | 1.0200 | 0.8235 | 0.8223 |
| 0.0006 | 40.0 | 680 | 1.0202 | 0.8235 | 0.8223 |
Framework versions
- Transformers 4.22.2
- Pytorch 1.10.2
- Datasets 2.5.2
- Tokenizers 0.12.1
