<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
bert-base-uncased-finetuned-cola-dropout-0.1
This model is a fine-tuned version of bert-base-uncased on the glue dataset. It achieves the following results on the evaluation set:
- Loss: 1.1127
- Matthews Correlation: 0.5932
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Matthews Correlation |
|---|---|---|---|---|
| 0.49 | 1.0 | 535 | 0.5310 | 0.4914 |
| 0.3003 | 2.0 | 1070 | 0.5391 | 0.5572 |
| 0.2033 | 3.0 | 1605 | 0.6975 | 0.5473 |
| 0.1427 | 4.0 | 2140 | 0.8513 | 0.5612 |
| 0.0998 | 5.0 | 2675 | 0.8598 | 0.5829 |
| 0.0783 | 6.0 | 3210 | 1.1127 | 0.5932 |
| 0.0456 | 7.0 | 3745 | 1.0697 | 0.5890 |
| 0.0395 | 8.0 | 4280 | 1.1813 | 0.5782 |
| 0.0277 | 9.0 | 4815 | 1.2958 | 0.5727 |
| 0.0205 | 10.0 | 5350 | 1.3045 | 0.5832 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3
