distilbert_sst2_padding10model
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: 0.8972
- Accuracy: 0.9017
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 |
|---|---|---|---|---|
| No log | 1.0 | 433 | 0.2551 | 0.9023 |
| 0.3447 | 2.0 | 866 | 0.3196 | 0.8979 |
| 0.1734 | 3.0 | 1299 | 0.3882 | 0.9001 |
| 0.0877 | 4.0 | 1732 | 0.4801 | 0.9050 |
| 0.0444 | 5.0 | 2165 | 0.6567 | 0.8918 |
| 0.0206 | 6.0 | 2598 | 0.6090 | 0.9023 |
| 0.0145 | 7.0 | 3031 | 0.6415 | 0.9028 |
| 0.0145 | 8.0 | 3464 | 0.7532 | 0.9023 |
| 0.0083 | 9.0 | 3897 | 0.6840 | 0.9116 |
| 0.0073 | 10.0 | 4330 | 0.8115 | 0.9001 |
| 0.0131 | 11.0 | 4763 | 0.7755 | 0.9017 |
| 0.0083 | 12.0 | 5196 | 0.7370 | 0.9083 |
| 0.0045 | 13.0 | 5629 | 0.8288 | 0.9066 |
| 0.0072 | 14.0 | 6062 | 0.8585 | 0.9017 |
| 0.0072 | 15.0 | 6495 | 0.8054 | 0.9028 |
| 0.0064 | 16.0 | 6928 | 0.8080 | 0.9039 |
| 0.0059 | 17.0 | 7361 | 0.8245 | 0.9050 |
| 0.0019 | 18.0 | 7794 | 0.9924 | 0.8940 |
| 0.001 | 19.0 | 8227 | 0.9138 | 0.8984 |
| 0.0016 | 20.0 | 8660 | 0.8972 | 0.9017 |
Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu117
- Datasets 2.14.5
- Tokenizers 0.13.3