deberta-v3-base-finetuned-cola
This model is a fine-tuned version of microsoft/deberta-v3-base on the glue dataset. It achieves the following results on the evaluation set:
- Loss: 0.6510
- Matthews Correlation: 0.6933
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 |
|---|---|---|---|---|
| 0.3853 | 1.0 | 535 | 0.3907 | 0.6307 |
| 0.2186 | 2.0 | 1070 | 0.5065 | 0.6603 |
| 0.1481 | 3.0 | 1605 | 0.5638 | 0.6740 |
| 0.1002 | 4.0 | 2140 | 0.6510 | 0.6933 |
| 0.0656 | 5.0 | 2675 | 0.7462 | 0.6877 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.1
- Tokenizers 0.13.3
- Downloads last month
- 5
Model tree for manyet1k/deberta-v3-base-finetuned-cola
Base model
microsoft/deberta-v3-baseDataset used to train manyet1k/deberta-v3-base-finetuned-cola
Evaluation results
- Matthews Correlation on gluevalidation set self-reported0.693