distilbert-base-uncased-finetuned-cola
This model is a fine-tuned version of distilbert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.6308
- Matthews Correlation: 0.5238
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: 9.98401844382555e-06
- train_batch_size: 16
- eval_batch_size: 16
- seed: 4
- 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: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Matthews Correlation |
|---|---|---|---|---|
| 0.5331 | 1.0 | 535 | 0.5294 | 0.3920 |
| 0.3986 | 2.0 | 1070 | 0.5129 | 0.4782 |
| 0.3061 | 3.0 | 1605 | 0.5229 | 0.5281 |
| 0.2428 | 4.0 | 2140 | 0.5733 | 0.5253 |
| 0.2055 | 5.0 | 2675 | 0.6308 | 0.5238 |
Framework versions
- Transformers 4.55.4
- Pytorch 2.8.0+cu126
- Datasets 2.21.0
- Tokenizers 0.21.4
- Downloads last month
- 4
Model tree for queueingnctu/distilbert-base-uncased-finetuned-cola
Base model
distilbert/distilbert-base-uncased