<!-- 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-stsb
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: 0.5419
- Pearson: 0.8754
- Spearmanr: 0.8723
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 | Pearson | Spearmanr |
|---|---|---|---|---|---|
| 0.8054 | 2.78 | 500 | 0.6118 | 0.8682 | 0.8680 |
| 0.2875 | 5.56 | 1000 | 0.5788 | 0.8693 | 0.8682 |
| 0.1718 | 8.33 | 1500 | 0.6133 | 0.8673 | 0.8639 |
| 0.1251 | 11.11 | 2000 | 0.6103 | 0.8716 | 0.8681 |
| 0.0999 | 13.89 | 2500 | 0.5665 | 0.8734 | 0.8707 |
| 0.0825 | 16.67 | 3000 | 0.6035 | 0.8736 | 0.8700 |
| 0.07 | 19.44 | 3500 | 0.5605 | 0.8752 | 0.8716 |
| 0.0611 | 22.22 | 4000 | 0.5661 | 0.8768 | 0.8730 |
| 0.0565 | 25.0 | 4500 | 0.5557 | 0.8739 | 0.8705 |
| 0.0523 | 27.78 | 5000 | 0.5419 | 0.8754 | 0.8723 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu116
- Datasets 2.8.1.dev0
- Tokenizers 0.13.2
