<!-- 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. -->
tiny-mlm-glue-sst2-target-glue-cola
This model is a fine-tuned version of muhtasham/tiny-mlm-glue-sst2 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.7448
- Matthews Correlation: 0.0872
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
- num_epochs: 200
Training results
| Training Loss | Epoch | Step | Validation Loss | Matthews Correlation |
|---|---|---|---|---|
| 0.6095 | 1.87 | 500 | 0.6220 | 0.0 |
| 0.6011 | 3.73 | 1000 | 0.6197 | 0.0464 |
| 0.5864 | 5.6 | 1500 | 0.6206 | 0.0452 |
| 0.5615 | 7.46 | 2000 | 0.6423 | 0.0789 |
| 0.5349 | 9.33 | 2500 | 0.6603 | 0.0765 |
| 0.518 | 11.19 | 3000 | 0.6809 | 0.0882 |
| 0.4938 | 13.06 | 3500 | 0.6936 | 0.0864 |
| 0.4755 | 14.93 | 4000 | 0.7229 | 0.0848 |
| 0.4509 | 16.79 | 4500 | 0.7448 | 0.0872 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu116
- Datasets 2.8.1.dev0
- Tokenizers 0.13.2
