v11_bert-base-uncased-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: 1.7029
- Accuracy: 0.7868
- F1: 0.8571
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: 63
- 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 |
|---|---|---|---|---|---|
| 0.4168 | 1.0 | 867 | 0.7619 | 0.7745 | 0.8502 |
| 0.0597 | 2.0 | 1734 | 1.1606 | 0.8088 | 0.8691 |
| 0.0175 | 3.0 | 2601 | 1.4812 | 0.7696 | 0.8433 |
| 0.0079 | 4.0 | 3468 | 1.6528 | 0.7819 | 0.8543 |
| 0.0038 | 5.0 | 4335 | 1.7029 | 0.7868 | 0.8571 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.13.3