<!-- 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-rte-target-glue-cola
This model is a fine-tuned version of muhtasham/small-mlm-glue-rte on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.6486
- Matthews Correlation: 0.3544
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 |
|---|---|---|---|---|
| 0.5424 | 1.87 | 500 | 0.6619 | 0.2317 |
| 0.3542 | 3.73 | 1000 | 0.6861 | 0.3364 |
| 0.2241 | 5.6 | 1500 | 0.8315 | 0.3491 |
| 0.1605 | 7.46 | 2000 | 0.9669 | 0.3670 |
| 0.1217 | 9.33 | 2500 | 1.1338 | 0.3751 |
| 0.1016 | 11.19 | 3000 | 1.2180 | 0.3804 |
| 0.0889 | 13.06 | 3500 | 1.4956 | 0.3073 |
| 0.0739 | 14.93 | 4000 | 1.3699 | 0.3777 |
| 0.066 | 16.79 | 4500 | 1.6486 | 0.3544 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu116
- Datasets 2.8.1.dev0
- Tokenizers 0.13.2
