tiny-mlm-glue-qqp-target-glue-qnli
This model is a fine-tuned version of muhtasham/tiny-mlm-glue-qqp on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.4653
- Accuracy: 0.7820
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 | Accuracy |
|---|---|---|---|---|
| 0.6087 | 0.15 | 500 | 0.5449 | 0.7311 |
| 0.5432 | 0.31 | 1000 | 0.5312 | 0.7390 |
| 0.521 | 0.46 | 1500 | 0.4937 | 0.7648 |
| 0.5144 | 0.61 | 2000 | 0.5254 | 0.7465 |
| 0.5128 | 0.76 | 2500 | 0.4786 | 0.7769 |
| 0.5037 | 0.92 | 3000 | 0.4670 | 0.7849 |
| 0.4915 | 1.07 | 3500 | 0.4569 | 0.7899 |
| 0.4804 | 1.22 | 4000 | 0.4689 | 0.7800 |
| 0.4676 | 1.37 | 4500 | 0.4725 | 0.7769 |
| 0.4738 | 1.53 | 5000 | 0.4653 | 0.7820 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu116
- Datasets 2.8.1.dev0
- Tokenizers 0.13.2