imdb_distilbert-base-uncased
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: 0.2911
- Accuracy: 0.8774
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: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 3.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.6487 | 0.2 | 78 | 0.4402 | 0.8117 |
| 0.402 | 0.4 | 156 | 0.3563 | 0.8416 |
| 0.3528 | 0.6 | 234 | 0.3522 | 0.8434 |
| 0.3362 | 0.8 | 312 | 0.3099 | 0.8652 |
| 0.3184 | 1.0 | 390 | 0.3028 | 0.8700 |
| 0.265 | 1.2 | 468 | 0.3052 | 0.8738 |
| 0.2593 | 1.4 | 546 | 0.2983 | 0.8735 |
| 0.2537 | 1.6 | 624 | 0.2977 | 0.8754 |
| 0.2558 | 1.8 | 702 | 0.2911 | 0.8774 |
| 0.2476 | 1.99 | 780 | 0.2907 | 0.8751 |
| 0.1941 | 2.19 | 858 | 0.3151 | 0.8774 |
| 0.1873 | 2.39 | 936 | 0.3104 | 0.8764 |
| 0.1869 | 2.59 | 1014 | 0.3181 | 0.8771 |
| 0.1807 | 2.79 | 1092 | 0.3148 | 0.8764 |
| 0.1967 | 2.99 | 1170 | 0.3141 | 0.8766 |
Framework versions
- Transformers 4.35.0.dev0
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1