distilbert_sst2_padding40model
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: 0.8990
- Accuracy: 0.8984
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 | 0.2807 | 0.8918 |
| 0.352 | 2.0 | 866 | 0.2839 | 0.8984 |
| 0.1741 | 3.0 | 1299 | 0.4073 | 0.8979 |
| 0.0814 | 4.0 | 1732 | 0.5104 | 0.9039 |
| 0.0415 | 5.0 | 2165 | 0.8648 | 0.8693 |
| 0.0268 | 6.0 | 2598 | 0.6747 | 0.8957 |
| 0.0204 | 7.0 | 3031 | 0.7511 | 0.8940 |
| 0.0204 | 8.0 | 3464 | 0.6485 | 0.9017 |
| 0.0195 | 9.0 | 3897 | 0.8488 | 0.8929 |
| 0.0042 | 10.0 | 4330 | 0.8213 | 0.9001 |
| 0.0097 | 11.0 | 4763 | 0.8371 | 0.8979 |
| 0.0069 | 12.0 | 5196 | 0.9002 | 0.8935 |
| 0.0108 | 13.0 | 5629 | 0.8321 | 0.8973 |
| 0.0072 | 14.0 | 6062 | 0.9234 | 0.8885 |
| 0.0072 | 15.0 | 6495 | 0.8939 | 0.8962 |
| 0.0068 | 16.0 | 6928 | 0.9207 | 0.8940 |
| 0.0045 | 17.0 | 7361 | 0.8769 | 0.8968 |
| 0.004 | 18.0 | 7794 | 0.9354 | 0.8946 |
| 0.0024 | 19.0 | 8227 | 0.9192 | 0.8968 |
| 0.0012 | 20.0 | 8660 | 0.8990 | 0.8984 |
Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu117
- Datasets 2.14.5
- Tokenizers 0.13.3