<!-- 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-0.5
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: 0.4578
- Matthews Correlation: 0.5960
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 |
|---|---|---|---|---|
| 0.5124 | 1.0 | 535 | 0.5110 | 0.4947 |
| 0.3144 | 2.0 | 1070 | 0.4578 | 0.5960 |
| 0.198 | 3.0 | 1605 | 0.7233 | 0.5393 |
| 0.1458 | 4.0 | 2140 | 0.7943 | 0.5554 |
| 0.0968 | 5.0 | 2675 | 1.0669 | 0.5393 |
| 0.069 | 6.0 | 3210 | 1.0982 | 0.5689 |
| 0.0484 | 7.0 | 3745 | 1.2170 | 0.5446 |
| 0.0394 | 8.0 | 4280 | 1.2429 | 0.5831 |
| 0.0292 | 9.0 | 4815 | 1.3490 | 0.5684 |
| 0.0175 | 10.0 | 5350 | 1.3534 | 0.5743 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3
