<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
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: 0.8744
- Matthews Correlation: 0.3549
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: 1.705152204400204e-05
- train_batch_size: 8
- eval_batch_size: 16
- seed: 39
- 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 |
---|---|---|---|---|
No log | 1.0 | 107 | 0.5696 | 0.1474 |
No log | 2.0 | 214 | 0.5700 | 0.2981 |
No log | 3.0 | 321 | 0.6856 | 0.3437 |
No log | 4.0 | 428 | 0.8744 | 0.3549 |
0.3495 | 5.0 | 535 | 0.9641 | 0.3295 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu116
- Datasets 2.10.1
- Tokenizers 0.13.2