distilbert-base-uncased-finetuned-glue_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: 0.5604
- Accuracy: 0.7958
- F1: 0.7879
- Matthews Correlation: 0.4977
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
- lr_scheduler_warmup_steps: 500
- num_epochs: 3
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Matthews Correlation |
---|---|---|---|---|---|---|
0.5632 | 1.0 | 535 | 0.4971 | 0.7603 | 0.7576 | 0.4273 |
0.4157 | 2.0 | 1070 | 0.4898 | 0.8015 | 0.7870 | 0.5051 |
0.2571 | 3.0 | 1605 | 0.5604 | 0.7958 | 0.7879 | 0.4977 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0
- Downloads last month
- 0
Finetuned from
Dataset used to train markuscolab/distilbert-base-uncased-finetuned-glue_cola
Evaluation results
- Accuracy on gluevalidation set self-reported0.796
- F1 on gluevalidation set self-reported0.788
- Matthews Correlation on gluevalidation set self-reported0.498