NLPGroupProject-Finetune-DistilBert
This model is a fine-tuned version of distilbert/distilbert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.1391
- Accuracy: 0.723
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: 5e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 0.25 | 250 | 0.9720 | 0.69 |
| 0.9562 | 0.5 | 500 | 0.8417 | 0.707 |
| 0.9562 | 0.75 | 750 | 0.7335 | 0.73 |
| 0.8908 | 1.0 | 1000 | 0.7306 | 0.739 |
| 0.8908 | 1.25 | 1250 | 0.7490 | 0.721 |
| 0.646 | 1.5 | 1500 | 0.7560 | 0.738 |
| 0.646 | 1.75 | 1750 | 0.7759 | 0.73 |
| 0.6244 | 2.0 | 2000 | 0.8180 | 0.723 |
| 0.6244 | 2.25 | 2250 | 1.0023 | 0.722 |
| 0.359 | 2.5 | 2500 | 1.0590 | 0.728 |
| 0.359 | 2.75 | 2750 | 1.0733 | 0.723 |
| 0.3716 | 3.0 | 3000 | 1.1391 | 0.723 |
Framework versions
- Transformers 4.40.0
- Pytorch 2.2.2+cu118
- Datasets 2.19.0
- Tokenizers 0.19.1