<!-- 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
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: 0.9220
- Matthews Correlation: 0.5769
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: 8.45110449379687e-06
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 8
Training results
| Training Loss | Epoch | Step | Validation Loss | Matthews Correlation |
|---|---|---|---|---|
| 0.5408 | 1.0 | 855 | 0.4675 | 0.4474 |
| 0.351 | 2.0 | 1710 | 0.6087 | 0.5354 |
| 0.2601 | 3.0 | 2565 | 0.7320 | 0.5580 |
| 0.1919 | 4.0 | 3420 | 0.8818 | 0.5595 |
| 0.1437 | 5.0 | 4275 | 0.9220 | 0.5769 |
| 0.1071 | 6.0 | 5130 | 1.0528 | 0.5629 |
| 0.0734 | 7.0 | 5985 | 1.0573 | 0.5577 |
| 0.0635 | 8.0 | 6840 | 1.0774 | 0.5580 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3
