<!-- 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. -->
small-mlm-glue-cola-custom-tokenizer-expand-vocab-target-glue-cola
This model is a fine-tuned version of muhtasham/small-mlm-glue-cola-custom-tokenizer-expand-vocab on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.7483
- Matthews Correlation: 0.2042
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 |
|---|---|---|---|---|
| 0.59 | 1.87 | 500 | 0.6270 | 0.0559 |
| 0.4698 | 3.73 | 1000 | 0.7320 | 0.1675 |
| 0.3335 | 5.6 | 1500 | 0.8527 | 0.1941 |
| 0.236 | 7.46 | 2000 | 1.0732 | 0.1998 |
| 0.1844 | 9.33 | 2500 | 1.2259 | 0.1681 |
| 0.1475 | 11.19 | 3000 | 1.3607 | 0.2085 |
| 0.1225 | 13.06 | 3500 | 1.5803 | 0.1746 |
| 0.1105 | 14.93 | 4000 | 1.5546 | 0.1717 |
| 0.0922 | 16.79 | 4500 | 1.7483 | 0.2042 |
Framework versions
- Transformers 4.27.0.dev0
- Pytorch 1.13.1+cu116
- Datasets 2.9.1.dev0
- Tokenizers 0.13.2
