distilbert_imdb_padding60model
This model is a fine-tuned version of distilbert-base-uncased on the imdb dataset. It achieves the following results on the evaluation set:
- Loss: 0.7595
- Accuracy: 0.9334
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 |
---|---|---|---|---|
0.2373 | 1.0 | 1563 | 0.2252 | 0.9165 |
0.1765 | 2.0 | 3126 | 0.2079 | 0.9274 |
0.1139 | 3.0 | 4689 | 0.2956 | 0.9302 |
0.0677 | 4.0 | 6252 | 0.3145 | 0.9261 |
0.0337 | 5.0 | 7815 | 0.4048 | 0.9280 |
0.0359 | 6.0 | 9378 | 0.4836 | 0.9296 |
0.0229 | 7.0 | 10941 | 0.5211 | 0.9228 |
0.0203 | 8.0 | 12504 | 0.5524 | 0.9280 |
0.015 | 9.0 | 14067 | 0.5274 | 0.9291 |
0.0214 | 10.0 | 15630 | 0.5787 | 0.9266 |
0.0134 | 11.0 | 17193 | 0.5935 | 0.9299 |
0.0075 | 12.0 | 18756 | 0.6236 | 0.9306 |
0.0054 | 13.0 | 20319 | 0.6758 | 0.9279 |
0.0057 | 14.0 | 21882 | 0.6801 | 0.9301 |
0.0066 | 15.0 | 23445 | 0.7197 | 0.929 |
0.0021 | 16.0 | 25008 | 0.7070 | 0.9321 |
0.0014 | 17.0 | 26571 | 0.6949 | 0.9320 |
0.0001 | 18.0 | 28134 | 0.7482 | 0.9319 |
0.0014 | 19.0 | 29697 | 0.7587 | 0.9334 |
0.0004 | 20.0 | 31260 | 0.7595 | 0.9334 |
Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu117
- Datasets 2.14.5
- Tokenizers 0.13.3
- Downloads last month
- 0