<!-- 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-stsb-target-glue-stsb
This model is a fine-tuned version of muhtasham/small-mlm-glue-stsb on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.5861
- Pearson: 0.8714
- Spearmanr: 0.8681
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 |
|---|---|---|---|---|---|
| 0.8465 | 2.78 | 500 | 0.6096 | 0.8646 | 0.8643 |
| 0.3031 | 5.56 | 1000 | 0.6011 | 0.8684 | 0.8662 |
| 0.1834 | 8.33 | 1500 | 0.6142 | 0.8660 | 0.8633 |
| 0.1322 | 11.11 | 2000 | 0.6086 | 0.8683 | 0.8645 |
| 0.1064 | 13.89 | 2500 | 0.5933 | 0.8693 | 0.8665 |
| 0.0865 | 16.67 | 3000 | 0.6259 | 0.8661 | 0.8626 |
| 0.0721 | 19.44 | 3500 | 0.5735 | 0.8704 | 0.8672 |
| 0.0633 | 22.22 | 4000 | 0.5747 | 0.8730 | 0.8699 |
| 0.0589 | 25.0 | 4500 | 0.5596 | 0.8733 | 0.8700 |
| 0.0532 | 27.78 | 5000 | 0.5861 | 0.8714 | 0.8681 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu116
- Datasets 2.8.1.dev0
- Tokenizers 0.13.2
