<!-- 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-finetuned2-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: 0.5176
- Matthews Correlation: 0.5650
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: 2.6781109393881056e-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: 8
Training results
| Training Loss | Epoch | Step | Validation Loss | Matthews Correlation |
|---|---|---|---|---|
| 0.5726 | 1.0 | 535 | 0.5090 | 0.3912 |
| 0.4467 | 2.0 | 1070 | 0.4536 | 0.5024 |
| 0.3891 | 3.0 | 1605 | 0.5093 | 0.4943 |
| 0.3387 | 4.0 | 2140 | 0.4927 | 0.5365 |
| 0.3177 | 5.0 | 2675 | 0.4897 | 0.5624 |
| 0.2853 | 6.0 | 3210 | 0.5176 | 0.5650 |
| 0.2718 | 7.0 | 3745 | 0.5440 | 0.5524 |
| 0.2532 | 8.0 | 4280 | 0.5431 | 0.5602 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3
