tiny-mlm-glue-wnli-target-glue-stsb
This model is a fine-tuned version of muhtasham/tiny-mlm-glue-wnli on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.8784
- Pearson: 0.7929
- Spearmanr: 0.7891
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 |
|---|---|---|---|---|---|
| 3.3443 | 2.78 | 500 | 1.5642 | 0.5784 | 0.6011 |
| 1.2259 | 5.56 | 1000 | 1.0907 | 0.7358 | 0.7382 |
| 0.8948 | 8.33 | 1500 | 0.9367 | 0.7750 | 0.7751 |
| 0.7357 | 11.11 | 2000 | 0.8525 | 0.7934 | 0.7905 |
| 0.6119 | 13.89 | 2500 | 0.8436 | 0.7977 | 0.7944 |
| 0.5301 | 16.67 | 3000 | 0.8999 | 0.7947 | 0.7928 |
| 0.4657 | 19.44 | 3500 | 0.8341 | 0.7989 | 0.7943 |
| 0.4104 | 22.22 | 4000 | 0.8818 | 0.7972 | 0.7930 |
| 0.3686 | 25.0 | 4500 | 0.8811 | 0.7973 | 0.7929 |
| 0.3348 | 27.78 | 5000 | 0.8784 | 0.7929 | 0.7891 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu116
- Datasets 2.8.1.dev0
- Tokenizers 0.13.2