<!-- 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-mrpc-target-glue-cola
This model is a fine-tuned version of muhtasham/tiny-mlm-glue-mrpc on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.7869
- Matthews Correlation: 0.1551
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 |
|---|---|---|---|---|
| 0.6097 | 1.87 | 500 | 0.6213 | 0.0 |
| 0.6008 | 3.73 | 1000 | 0.6170 | 0.0 |
| 0.5827 | 5.6 | 1500 | 0.6185 | 0.0615 |
| 0.5534 | 7.46 | 2000 | 0.6389 | 0.1043 |
| 0.5246 | 9.33 | 2500 | 0.6589 | 0.1507 |
| 0.5102 | 11.19 | 3000 | 0.6608 | 0.1476 |
| 0.4873 | 13.06 | 3500 | 0.6693 | 0.1282 |
| 0.4681 | 14.93 | 4000 | 0.7066 | 0.1577 |
| 0.448 | 16.79 | 4500 | 0.7266 | 0.1613 |
| 0.4302 | 18.66 | 5000 | 0.7454 | 0.1446 |
| 0.4108 | 20.52 | 5500 | 0.7858 | 0.1595 |
| 0.4023 | 22.39 | 6000 | 0.7869 | 0.1551 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu116
- Datasets 2.8.1.dev0
- Tokenizers 0.13.2
