distilbert-base-uncased-cola
This model is a fine-tuned version of distilbert-base-uncased on the glue dataset. It achieves the following results on the evaluation set:
- Loss: 0.748253
- Matthews Correlation: 0.551796
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: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
Training Loss | Epoch | Validation Loss | Matthews Correlation |
---|---|---|---|
0.373500 | 6 | 0.700206 | 0.509989 |
0.373500 | 7 | 0.715856 | 0.524198 |
0.129300 | 8 | 0.707939 | 0.552374 |
0.129300 | 9 | 0.745391 | 0.549192 |
0.129300 | 10 | 0.748253 | 0.551739 |