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: 0.5931
- Matthews Correlation: 0.5598
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: 2e-05
- train_batch_size: 16
- eval_batch_size: 128
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Matthews Correlation |
|---|---|---|---|---|
| 0.5206 | 1.0 | 535 | 0.4503 | 0.4984 |
| 0.347 | 2.0 | 1070 | 0.4558 | 0.5816 |
| 0.2461 | 3.0 | 1605 | 0.5931 | 0.5598 |
Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1
- Datasets 2.14.5
- Tokenizers 0.13.3
- Downloads last month
- 2
Model tree for tombm/bert-base-uncased-finetuned-cola
Base model
google-bert/bert-base-uncased