<!-- 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-3e-05
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: 1.0201
- Matthews Correlation: 0.5881
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: 3e-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 |
---|---|---|---|---|
0.4873 | 1.0 | 535 | 0.6048 | 0.4571 |
0.2844 | 2.0 | 1070 | 0.5333 | 0.5521 |
0.1893 | 3.0 | 1605 | 0.7435 | 0.5574 |
0.1362 | 4.0 | 2140 | 0.7142 | 0.5825 |
0.0924 | 5.0 | 2675 | 0.8334 | 0.5625 |
0.0596 | 6.0 | 3210 | 1.0201 | 0.5881 |
0.0496 | 7.0 | 3745 | 1.0777 | 0.5686 |
0.03 | 8.0 | 4280 | 1.2245 | 0.5630 |
0.0122 | 9.0 | 4815 | 1.3665 | 0.5701 |
0.0111 | 10.0 | 5350 | 1.4043 | 0.5778 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3