tiny-mlm-glue-wnli-target-glue-cola
This model is a fine-tuned version of muhtasham/tiny-mlm-glue-wnli on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.7631
- Matthews Correlation: 0.0785
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: 3e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant
- training_steps: 5000
Training results
| Training Loss | Epoch | Step | Validation Loss | Matthews Correlation |
|---|---|---|---|---|
| 0.6111 | 1.87 | 500 | 0.6217 | 0.0 |
| 0.6032 | 3.73 | 1000 | 0.6187 | 0.0464 |
| 0.5916 | 5.6 | 1500 | 0.6211 | 0.0174 |
| 0.5626 | 7.46 | 2000 | 0.6501 | 0.0583 |
| 0.5246 | 9.33 | 2500 | 0.6752 | 0.0908 |
| 0.5001 | 11.19 | 3000 | 0.7081 | 0.0629 |
| 0.4744 | 13.06 | 3500 | 0.7299 | 0.0593 |
| 0.4539 | 14.93 | 4000 | 0.7631 | 0.0785 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu116
- Datasets 2.8.1.dev0
- Tokenizers 0.13.2