v12_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: 1.7151
- Accuracy: 0.7623
- F1: 0.8418
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 |
|---|---|---|---|---|---|
| 0.4064 | 1.0 | 719 | 0.6134 | 0.8015 | 0.8643 |
| 0.1426 | 2.0 | 1438 | 1.2114 | 0.7696 | 0.8479 |
| 0.0209 | 3.0 | 2157 | 1.4115 | 0.7819 | 0.8514 |
| 0.0136 | 4.0 | 2876 | 1.5548 | 0.7672 | 0.8403 |
| 0.0041 | 5.0 | 3595 | 1.7151 | 0.7623 | 0.8418 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.1.0+cu118
- Datasets 2.14.7
- Tokenizers 0.13.3