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: 0.6416
- Matthews Correlation: 0.5265
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 |
|---|---|---|---|---|
| 0.5174 | 1.0 | 535 | 0.4669 | 0.4667 |
| 0.341 | 2.0 | 1070 | 0.4695 | 0.5051 |
| 0.2332 | 3.0 | 1605 | 0.6416 | 0.5265 |
| 0.1767 | 4.0 | 2140 | 0.7472 | 0.5242 |
| 0.1286 | 5.0 | 2675 | 0.8278 | 0.5249 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Datasets 1.18.2
- Tokenizers 0.19.1
- Downloads last month
- 6
Model tree for FredaSun/distilbert-base-uncased-finetuned-cola
Base model
distilbert/distilbert-base-uncasedDataset used to train FredaSun/distilbert-base-uncased-finetuned-cola
Evaluation results
- Matthews Correlation on gluevalidation set self-reported0.526