N_roberta_twitterfin_padding0model
This model is a fine-tuned version of roberta-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.8899
- Accuracy: 0.9054
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: 20
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.5034 | 1.0 | 597 | 0.3089 | 0.8861 |
| 0.2809 | 2.0 | 1194 | 0.2518 | 0.9062 |
| 0.2265 | 3.0 | 1791 | 0.3194 | 0.8995 |
| 0.1758 | 4.0 | 2388 | 0.5205 | 0.8987 |
| 0.1577 | 5.0 | 2985 | 0.5400 | 0.8932 |
| 0.0711 | 6.0 | 3582 | 0.6033 | 0.8991 |
| 0.0708 | 7.0 | 4179 | 0.6740 | 0.8970 |
| 0.0566 | 8.0 | 4776 | 0.6367 | 0.8987 |
| 0.0541 | 9.0 | 5373 | 0.8236 | 0.8857 |
| 0.0393 | 10.0 | 5970 | 0.7245 | 0.8974 |
| 0.028 | 11.0 | 6567 | 0.7695 | 0.8999 |
| 0.032 | 12.0 | 7164 | 0.7127 | 0.9037 |
| 0.0234 | 13.0 | 7761 | 0.8016 | 0.8961 |
| 0.016 | 14.0 | 8358 | 0.8060 | 0.9083 |
| 0.0109 | 15.0 | 8955 | 0.8555 | 0.8987 |
| 0.0119 | 16.0 | 9552 | 0.8472 | 0.9049 |
| 0.0075 | 17.0 | 10149 | 0.8454 | 0.9062 |
| 0.0038 | 18.0 | 10746 | 0.8613 | 0.9079 |
| 0.0069 | 19.0 | 11343 | 0.8795 | 0.9075 |
| 0.0072 | 20.0 | 11940 | 0.8899 | 0.9054 |
Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu117
- Datasets 2.14.5
- Tokenizers 0.13.3