bert-base-uncased-finetuned-mrpc
This model is a fine-tuned version of bert-base-uncased on the glue dataset. It achieves the following results on the evaluation set:
- Loss: 0.4213
- Accuracy: 0.8652
- F1: 0.9047
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: 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: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| No log | 1.0 | 230 | 0.4085 | 0.8480 | 0.8927 |
| No log | 2.0 | 460 | 0.3720 | 0.8554 | 0.8995 |
| 0.4310 | 3.0 | 690 | 0.4213 | 0.8652 | 0.9047 |
Framework versions
- Transformers 5.20.1
- Pytorch 2.11.0+cu130
- Datasets 5.1.0
- Tokenizers 0.23.2