muril-base-part1
This model is a fine-tuned version of google/muril-base-cased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0166
- F1: 0.9836
- Precision: 0.9836
- Recall: 0.9836
- Fpr: 0.0175
- Fnr: 0.0164
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: 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: 4
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 | Precision | Recall | Fpr | Fnr |
|---|---|---|---|---|---|---|---|---|
| No log | 1.0 | 207 | 0.0255 | 0.9741 | 0.9787 | 0.9696 | 0.0225 | 0.0304 |
| No log | 2.0 | 414 | 0.0161 | 0.9836 | 0.9836 | 0.9836 | 0.0175 | 0.0164 |
| 0.0382 | 3.0 | 621 | 0.0159 | 0.9847 | 0.9905 | 0.9789 | 0.01 | 0.0211 |
| 0.0382 | 4.0 | 828 | 0.0166 | 0.9836 | 0.9836 | 0.9836 | 0.0175 | 0.0164 |
Framework versions
- Transformers 5.12.0
- Pytorch 2.11.0+cu128
- Datasets 4.0.0
- Tokenizers 0.22.2