sa_BERT_24_cola
This model is a fine-tuned version of gokuls/bert_base_24 on the GLUE COLA dataset. It achieves the following results on the evaluation set:
- Loss: 0.6120
- Matthews Correlation: 0.0
- Accuracy: 0.6913
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: 4e-05
- train_batch_size: 96
- eval_batch_size: 96
- seed: 10
- distributed_type: multi-GPU
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 50
Training results
| Training Loss | Epoch | Step | Validation Loss | Matthews Correlation | Accuracy |
|---|---|---|---|---|---|
| 0.6138 | 1.0 | 90 | 0.6120 | 0.0 | 0.6913 |
| 0.5898 | 2.0 | 180 | 0.6242 | 0.0656 | 0.6932 |
| 0.5491 | 3.0 | 270 | 0.6798 | 0.0733 | 0.6405 |
| 0.5027 | 4.0 | 360 | 0.6873 | 0.0667 | 0.6328 |
| 0.4549 | 5.0 | 450 | 0.7841 | 0.1025 | 0.6299 |
| 0.4177 | 6.0 | 540 | 0.8221 | 0.0827 | 0.5849 |
Framework versions
- Transformers 4.30.2
- Pytorch 1.14.0a0+410ce96
- Datasets 2.13.0
- Tokenizers 0.13.3