bert_twitterfin_padding40model
This model is a fine-tuned version of bert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.1063
- Accuracy: 0.8819
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 |
|---|---|---|---|---|
| 0.7718 | 1.0 | 597 | 0.4637 | 0.8208 |
| 0.4046 | 2.0 | 1194 | 0.3366 | 0.8765 |
| 0.2833 | 3.0 | 1791 | 0.3967 | 0.8836 |
| 0.1856 | 4.0 | 2388 | 0.5273 | 0.8790 |
| 0.1388 | 5.0 | 2985 | 0.6270 | 0.8786 |
| 0.0609 | 6.0 | 3582 | 0.7756 | 0.8585 |
| 0.0517 | 7.0 | 4179 | 0.7692 | 0.8773 |
| 0.0324 | 8.0 | 4776 | 0.7837 | 0.8798 |
| 0.031 | 9.0 | 5373 | 0.8253 | 0.8773 |
| 0.0253 | 10.0 | 5970 | 0.8893 | 0.8823 |
| 0.0133 | 11.0 | 6567 | 0.9943 | 0.8802 |
| 0.0119 | 12.0 | 7164 | 0.9277 | 0.8786 |
| 0.0148 | 13.0 | 7761 | 1.0189 | 0.8836 |
| 0.0051 | 14.0 | 8358 | 1.0542 | 0.8790 |
| 0.005 | 15.0 | 8955 | 1.0600 | 0.8802 |
| 0.0055 | 16.0 | 9552 | 1.0521 | 0.8794 |
| 0.0052 | 17.0 | 10149 | 1.0653 | 0.8777 |
| 0.0021 | 18.0 | 10746 | 1.0891 | 0.8832 |
| 0.002 | 19.0 | 11343 | 1.1045 | 0.8811 |
| 0.0039 | 20.0 | 11940 | 1.1063 | 0.8819 |
Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu117
- Datasets 2.14.5
- Tokenizers 0.13.3