roberta-base-finetuned-cola
This model is a fine-tuned version of roberta-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.6185
- Matthews Correlation: 0.0
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: 5e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Matthews Correlation |
|---|---|---|---|---|
| 0.6126 | 1.0 | 535 | 0.6185 | 0.0 |
| 0.6158 | 2.0 | 1070 | 0.6204 | 0.0 |
| 0.6119 | 3.0 | 1605 | 0.6201 | 0.0 |
| 0.6133 | 4.0 | 2140 | 0.6336 | 0.0 |
| 0.6107 | 5.0 | 2675 | 0.6216 | 0.0 |
| 0.6057 | 6.0 | 3210 | 0.6185 | 0.0 |
| 0.6099 | 7.0 | 3745 | 0.6188 | 0.0 |
| 0.6132 | 8.0 | 4280 | 0.6183 | 0.0 |
| 0.6084 | 9.0 | 4815 | 0.6187 | 0.0 |
| 0.6059 | 10.0 | 5350 | 0.6188 | 0.0 |
Framework versions
- Transformers 4.56.1
- Pytorch 2.8.0+cu126
- Datasets 4.0.0
- Tokenizers 0.22.0