token_bert
This model is a fine-tuned version of distilbert/distilbert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0020
- Precision: 0.9986
- Recall: 0.9986
- F1: 0.9986
- Accuracy: 0.9995
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: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.0081 | 1.0 | 2250 | 0.0039 | 0.9982 | 0.9976 | 0.9979 | 0.9991 |
| 0.0040 | 2.0 | 4500 | 0.0031 | 0.9983 | 0.9970 | 0.9977 | 0.9992 |
| 0.0016 | 3.0 | 6750 | 0.0020 | 0.9986 | 0.9986 | 0.9986 | 0.9995 |
Framework versions
- Transformers 5.14.1
- Pytorch 2.13.0+cu130
- Datasets 5.0.0
- Tokenizers 0.22.2