<!-- 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-cola-custom-tokenizer-target-glue-stsb
This model is a fine-tuned version of muhtasham/tiny-mlm-glue-cola-custom-tokenizer on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.3195
- Pearson: 0.6745
- Spearmanr: 0.6765
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 | Pearson | Spearmanr |
|---|---|---|---|---|---|
| 3.3068 | 2.78 | 500 | 1.9896 | 0.3651 | 0.3938 |
| 1.4915 | 5.56 | 1000 | 1.3053 | 0.6677 | 0.6745 |
| 1.2119 | 8.33 | 1500 | 1.2683 | 0.6873 | 0.6896 |
| 1.0589 | 11.11 | 2000 | 1.1930 | 0.6929 | 0.6911 |
| 0.9145 | 13.89 | 2500 | 1.2757 | 0.6787 | 0.6807 |
| 0.8423 | 16.67 | 3000 | 1.3657 | 0.6751 | 0.6800 |
| 0.7599 | 19.44 | 3500 | 1.3195 | 0.6745 | 0.6765 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu116
- Datasets 2.8.1.dev0
- Tokenizers 0.13.2
