distilbert_sst2_padding90model
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: 0.8603
- Accuracy: 0.9077
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 | 0.2769 | 0.8858 |
| 0.361 | 2.0 | 866 | 0.3695 | 0.8935 |
| 0.1858 | 3.0 | 1299 | 0.4577 | 0.8929 |
| 0.0971 | 4.0 | 1732 | 0.5781 | 0.8896 |
| 0.0575 | 5.0 | 2165 | 0.6172 | 0.8940 |
| 0.0255 | 6.0 | 2598 | 0.6606 | 0.8951 |
| 0.0211 | 7.0 | 3031 | 0.7161 | 0.8990 |
| 0.0211 | 8.0 | 3464 | 0.6963 | 0.9083 |
| 0.0221 | 9.0 | 3897 | 0.6817 | 0.9044 |
| 0.0176 | 10.0 | 4330 | 0.7174 | 0.9077 |
| 0.0092 | 11.0 | 4763 | 0.7863 | 0.9001 |
| 0.0126 | 12.0 | 5196 | 0.8451 | 0.8968 |
| 0.0057 | 13.0 | 5629 | 0.7709 | 0.9066 |
| 0.0043 | 14.0 | 6062 | 0.8267 | 0.9061 |
| 0.0043 | 15.0 | 6495 | 0.8121 | 0.9050 |
| 0.0029 | 16.0 | 6928 | 0.9722 | 0.8940 |
| 0.0048 | 17.0 | 7361 | 0.8179 | 0.9116 |
| 0.0031 | 18.0 | 7794 | 0.8398 | 0.9105 |
| 0.0025 | 19.0 | 8227 | 0.8607 | 0.9072 |
| 0.001 | 20.0 | 8660 | 0.8603 | 0.9077 |
Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu117
- Datasets 2.14.5
- Tokenizers 0.13.3