bert-small-finetuned-finetuned-finer-longer10
This model is a fine-tuned version of muhtasham/bert-small-finetuned-finer on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.3791
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: 128
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 7
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.5687 | 1.0 | 2433 | 1.5357 |
| 1.5081 | 2.0 | 4866 | 1.4759 |
| 1.4813 | 3.0 | 7299 | 1.4337 |
| 1.4453 | 4.0 | 9732 | 1.4084 |
| 1.4257 | 5.0 | 12165 | 1.3913 |
| 1.4155 | 6.0 | 14598 | 1.3855 |
| 1.4057 | 7.0 | 17031 | 1.3791 |
Framework versions
- Transformers 4.21.2
- Pytorch 1.12.1+cu113
- Datasets 2.4.0
- Tokenizers 0.12.1