classifier-chapter4
This model is a fine-tuned version of bert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2539
- Accuracy: 0.9137
- F1: 0.9137
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: 5e-05
- train_batch_size: 32
- eval_batch_size: 32
- 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: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 0.3815 | 1.0 | 313 | 0.2819 | 0.9054 | 0.9053 |
| 0.196 | 2.0 | 626 | 0.2539 | 0.9137 | 0.9137 |
| 0.1181 | 3.0 | 939 | 0.3078 | 0.9128 | 0.9126 |
| 0.0592 | 4.0 | 1252 | 0.3739 | 0.9164 | 0.9164 |
| 0.032 | 5.0 | 1565 | 0.4194 | 0.9234 | 0.9234 |
Framework versions
- Transformers 4.56.1
- Pytorch 2.8.0+cu126
- Datasets 4.0.0
- Tokenizers 0.22.0