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: 0.7569
- Matthews Correlation: 0.5403
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 |
|---|---|---|---|---|
| 0.5304 | 1.0 | 535 | 0.4711 | 0.4796 |
| 0.3578 | 2.0 | 1070 | 0.5249 | 0.5209 |
| 0.2374 | 3.0 | 1605 | 0.6196 | 0.5212 |
| 0.1808 | 4.0 | 2140 | 0.7569 | 0.5403 |
| 0.136 | 5.0 | 2675 | 0.8015 | 0.5328 |
Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1
- Downloads last month
- 2
Model tree for kibru/distilbert-base-uncased-finetuned-cola
Base model
distilbert/distilbert-base-uncasedDataset used to train kibru/distilbert-base-uncased-finetuned-cola
Evaluation results
- Matthews Correlation on gluevalidation set self-reported0.540