<!-- 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-last-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: 0.8731
- Matthews Correlation: 0.5892
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: 3.350326176009724e-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: 8
Training results
| Training Loss | Epoch | Step | Validation Loss | Matthews Correlation |
|---|---|---|---|---|
| 0.4834 | 1.0 | 535 | 0.4471 | 0.5024 |
| 0.287 | 2.0 | 1070 | 0.4596 | 0.5573 |
| 0.1848 | 3.0 | 1605 | 0.8394 | 0.5140 |
| 0.1257 | 4.0 | 2140 | 0.8731 | 0.5892 |
| 0.0719 | 5.0 | 2675 | 0.9607 | 0.5851 |
| 0.0467 | 6.0 | 3210 | 1.0737 | 0.5731 |
| 0.0339 | 7.0 | 3745 | 1.3356 | 0.5470 |
| 0.0216 | 8.0 | 4280 | 1.3521 | 0.5579 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3
