distilbert-base-uncased-finetuned-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: 0.8549
- Matthews Correlation: 0.5332
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
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
Training Loss | Epoch | Step | Validation Loss | Matthews Correlation |
---|---|---|---|---|
0.5213 | 1.0 | 535 | 0.5163 | 0.4183 |
0.3479 | 2.0 | 1070 | 0.5351 | 0.5182 |
0.231 | 3.0 | 1605 | 0.6271 | 0.5291 |
0.166 | 4.0 | 2140 | 0.7531 | 0.5279 |
0.1313 | 5.0 | 2675 | 0.8549 | 0.5332 |
Framework versions
- Transformers 4.10.0.dev0
- Pytorch 1.8.1
- Datasets 1.11.0
- Tokenizers 0.10.3
- Downloads last month
- 22