CR_DistilBERT_5E
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: 0.3663
- Accuracy: 0.9
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: 1e-05
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.6345 | 0.33 | 50 | 0.5656 | 0.66 |
| 0.4704 | 0.66 | 100 | 0.3705 | 0.82 |
| 0.3428 | 0.99 | 150 | 0.3186 | 0.8867 |
| 0.2272 | 1.32 | 200 | 0.2871 | 0.9 |
| 0.259 | 1.66 | 250 | 0.2975 | 0.8867 |
| 0.2583 | 1.99 | 300 | 0.3125 | 0.8867 |
| 0.1713 | 2.32 | 350 | 0.3146 | 0.8867 |
| 0.181 | 2.65 | 400 | 0.3602 | 0.8867 |
| 0.1868 | 2.98 | 450 | 0.3319 | 0.8933 |
| 0.1521 | 3.31 | 500 | 0.3413 | 0.8867 |
| 0.1153 | 3.64 | 550 | 0.3868 | 0.88 |
| 0.1238 | 3.97 | 600 | 0.3686 | 0.8867 |
| 0.1104 | 4.3 | 650 | 0.3674 | 0.8867 |
| 0.0881 | 4.64 | 700 | 0.3750 | 0.8867 |
| 0.1247 | 4.97 | 750 | 0.3663 | 0.9 |
Framework versions
- Transformers 4.24.0
- Pytorch 1.13.0
- Datasets 2.3.2
- Tokenizers 0.13.1