<!-- 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-learning_rate-8e-06
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: 0.8389
- Matthews Correlation: 0.5753
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: 8e-06
- 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 |
|---|---|---|---|---|
| 0.5241 | 1.0 | 535 | 0.4659 | 0.5046 |
| 0.3755 | 2.0 | 1070 | 0.4412 | 0.5650 |
| 0.2782 | 3.0 | 1605 | 0.5524 | 0.5395 |
| 0.2154 | 4.0 | 2140 | 0.6437 | 0.5651 |
| 0.1669 | 5.0 | 2675 | 0.7709 | 0.5650 |
| 0.1503 | 6.0 | 3210 | 0.8389 | 0.5753 |
| 0.1151 | 7.0 | 3745 | 0.8964 | 0.5681 |
| 0.1082 | 8.0 | 4280 | 0.9767 | 0.5548 |
| 0.0816 | 9.0 | 4815 | 0.9978 | 0.5498 |
| 0.0809 | 10.0 | 5350 | 1.0170 | 0.5576 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3
