<!-- 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-rte-from-scratch-custom-tokenizer-target-glue-stsb
This model is a fine-tuned version of muhtasham/tiny-mlm-glue-rte-from-scratch-custom-tokenizer on the None dataset. It achieves the following results on the evaluation set:
- Loss: 3.1300
- Pearson: 0.1749
- Spearmanr: 0.1759
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 |
|---|---|---|---|---|---|
| 3.5119 | 2.78 | 500 | 2.3604 | 0.0421 | 0.0353 |
| 2.0241 | 5.56 | 1000 | 2.4688 | 0.0923 | 0.0872 |
| 1.7799 | 8.33 | 1500 | 2.6317 | 0.1353 | 0.1453 |
| 1.3798 | 11.11 | 2000 | 2.7682 | 0.1647 | 0.1754 |
| 1.093 | 13.89 | 2500 | 2.8072 | 0.1788 | 0.1810 |
| 0.8918 | 16.67 | 3000 | 3.1068 | 0.1724 | 0.1745 |
| 0.7578 | 19.44 | 3500 | 3.1069 | 0.1719 | 0.1741 |
| 0.668 | 22.22 | 4000 | 3.1300 | 0.1749 | 0.1759 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu116
- Datasets 2.8.1.dev0
- Tokenizers 0.13.2
