da_distilbert
This model is a fine-tuned version of distilbert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.7151
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 | Validation Loss |
---|---|---|---|
No log | 1.0 | 130 | 2.1034 |
No log | 2.0 | 260 | 1.9547 |
No log | 3.0 | 390 | 1.8459 |
2.1418 | 4.0 | 520 | 1.8499 |
2.1418 | 5.0 | 650 | 1.7874 |
2.1418 | 6.0 | 780 | 1.7771 |
2.1418 | 7.0 | 910 | 1.7605 |
1.8295 | 8.0 | 1040 | 1.7202 |
1.8295 | 9.0 | 1170 | 1.6926 |
1.8295 | 10.0 | 1300 | 1.7350 |
Framework versions
- Transformers 4.40.1
- Pytorch 2.4.0.dev20240502
- Datasets 2.19.0
- Tokenizers 0.19.1
- Downloads last month
- 85