<!-- 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-stsb-target-glue-cola
This model is a fine-tuned version of muhtasham/tiny-mlm-glue-stsb on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.6987
- Matthews Correlation: 0.0881
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 |
---|---|---|---|---|
0.6101 | 1.87 | 500 | 0.6217 | 0.0 |
0.601 | 3.73 | 1000 | 0.6177 | 0.0 |
0.5849 | 5.6 | 1500 | 0.6187 | 0.0799 |
0.5588 | 7.46 | 2000 | 0.6384 | 0.1120 |
0.5308 | 9.33 | 2500 | 0.6528 | 0.0912 |
0.5142 | 11.19 | 3000 | 0.6690 | 0.0939 |
0.4865 | 13.06 | 3500 | 0.6987 | 0.0881 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu116
- Datasets 2.8.1.dev0
- Tokenizers 0.13.2