<!-- 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-sst2-target-glue-cola
This model is a fine-tuned version of muhtasham/small-mlm-glue-sst2 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.5598
- Matthews Correlation: 0.3885
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 |
|---|---|---|---|---|
| 0.5397 | 1.87 | 500 | 0.6364 | 0.2396 |
| 0.3514 | 3.73 | 1000 | 0.7722 | 0.3110 |
| 0.2254 | 5.6 | 1500 | 0.8466 | 0.3528 |
| 0.1675 | 7.46 | 2000 | 0.9693 | 0.3824 |
| 0.1238 | 9.33 | 2500 | 1.1907 | 0.3798 |
| 0.1043 | 11.19 | 3000 | 1.2831 | 0.4028 |
| 0.0934 | 13.06 | 3500 | 1.3186 | 0.3478 |
| 0.0807 | 14.93 | 4000 | 1.3018 | 0.4120 |
| 0.0616 | 16.79 | 4500 | 1.4735 | 0.3913 |
| 0.0626 | 18.66 | 5000 | 1.5598 | 0.3885 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu116
- Datasets 2.8.1.dev0
- Tokenizers 0.13.2
