left_padding50model
This model is a fine-tuned version of distilbert-base-uncased on the imdb dataset. It achieves the following results on the evaluation set:
- Accuracy: 0.9330
- Loss: 0.6731
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: 10
Training results
Training Loss | Epoch | Step | Accuracy | Validation Loss |
---|---|---|---|---|
0.0717 | 1.0 | 1563 | 0.9253 | 0.4438 |
0.0129 | 2.0 | 3126 | 0.9311 | 0.4835 |
0.04 | 3.0 | 4689 | 0.9292 | 0.4372 |
0.022 | 4.0 | 6252 | 0.9285 | 0.5136 |
0.0146 | 5.0 | 7815 | 0.9232 | 0.6244 |
0.03 | 6.0 | 9378 | 0.9278 | 0.5806 |
0.0031 | 7.0 | 10941 | 0.9293 | 0.6286 |
0.0082 | 8.0 | 12504 | 0.9286 | 0.6613 |
0.0 | 9.0 | 14067 | 0.9309 | 0.6665 |
0.0 | 10.0 | 15630 | 0.9330 | 0.6731 |
Framework versions
- Transformers 4.35.0
- Pytorch 2.0.0+cu117
- Datasets 2.14.6
- Tokenizers 0.14.1
- Downloads last month
- 0