bert-large-cased-finetuned-mrpc
This model is a fine-tuned version of bert-large-cased on the glue dataset. It achieves the following results on the evaluation set:
- Loss: 0.4358
- Accuracy: 0.8775
- F1: 0.9135
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: 32
- eval_batch_size: 32
- seed: 26
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| No log | 1.0 | 115 | 0.4797 | 0.7966 | 0.8614 |
| No log | 2.0 | 230 | 0.4097 | 0.8358 | 0.8822 |
| No log | 3.0 | 345 | 0.3815 | 0.8529 | 0.8976 |
| No log | 4.0 | 460 | 0.3961 | 0.8652 | 0.9050 |
| 0.3944 | 5.0 | 575 | 0.4358 | 0.8775 | 0.9135 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.13.3