bert-large-uncased_fold_2
This model is a fine-tuned version of bert-large-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0351
- Accuracy: 0.9935
- F1: 0.9879
- Precision: 0.9980
- Recall: 0.9780
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: 15
- eval_batch_size: 15
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|---|---|---|---|---|---|---|---|
| 0.0678 | 1.0 | 10089 | 0.0491 | 0.9918 | 0.9846 | 0.9953 | 0.9742 |
| 0.0697 | 2.0 | 20178 | 0.0394 | 0.9917 | 0.9846 | 0.9924 | 0.9769 |
| 0.0345 | 3.0 | 30267 | 0.0351 | 0.9935 | 0.9879 | 0.9980 | 0.9780 |
Framework versions
- Transformers 4.57.6
- Pytorch 2.11.0+cu128
- Datasets 4.8.4
- Tokenizers 0.22.2