small-mlm-snli-target-glue-cola
This model is a fine-tuned version of muhtasham/small-mlm-snli on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.4489
- Matthews Correlation: 0.4133
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 |
|---|---|---|---|---|
| 0.5418 | 1.87 | 500 | 0.6051 | 0.2796 |
| 0.3572 | 3.73 | 1000 | 0.6915 | 0.3452 |
| 0.2288 | 5.6 | 1500 | 0.7982 | 0.3466 |
| 0.1649 | 7.46 | 2000 | 0.9558 | 0.3574 |
| 0.1272 | 9.33 | 2500 | 1.0736 | 0.3918 |
| 0.1059 | 11.19 | 3000 | 1.2405 | 0.3573 |
| 0.0953 | 13.06 | 3500 | 1.3135 | 0.3521 |
| 0.0772 | 14.93 | 4000 | 1.3722 | 0.3965 |
| 0.0658 | 16.79 | 4500 | 1.4417 | 0.3609 |
| 0.0608 | 18.66 | 5000 | 1.4489 | 0.4133 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu116
- Datasets 2.8.1.dev0
- Tokenizers 0.13.2