bert-finetuned-mrpc
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: 0.5500
- Accuracy: 0.8456
- F1: 0.8901
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: 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 | Accuracy | F1 |
|---|---|---|---|---|---|
| 0.6079 | 0.2174 | 50 | 0.5599 | 0.7451 | 0.8243 |
| 0.4837 | 0.4348 | 100 | 0.4716 | 0.7721 | 0.8540 |
| 0.4432 | 0.6522 | 150 | 0.4644 | 0.7745 | 0.8553 |
| 0.3663 | 0.8696 | 200 | 0.3423 | 0.8603 | 0.9005 |
| 0.2180 | 1.0870 | 250 | 0.3931 | 0.8382 | 0.8834 |
| 0.1974 | 1.3043 | 300 | 0.3961 | 0.8578 | 0.9014 |
| 0.2518 | 1.5217 | 350 | 0.3656 | 0.8382 | 0.8838 |
| 0.1819 | 1.7391 | 400 | 0.4897 | 0.8603 | 0.9026 |
| 0.3046 | 1.9565 | 450 | 0.3743 | 0.8578 | 0.8945 |
| 0.1691 | 2.1739 | 500 | 0.4821 | 0.8652 | 0.9047 |
| 0.0965 | 2.3913 | 550 | 0.5304 | 0.8456 | 0.8912 |
| 0.1347 | 2.6087 | 600 | 0.5437 | 0.8407 | 0.8870 |
| 0.1246 | 2.8261 | 650 | 0.5505 | 0.8431 | 0.8881 |
| 0.1031 | 3.0 | 690 | 0.5500 | 0.8456 | 0.8901 |
Framework versions
- Transformers 5.13.1
- Pytorch 2.11.0+cu128
- Datasets 5.0.1
- Tokenizers 0.22.2