<!-- 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-wnli-target-glue-qqp
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: 0.4204
- Accuracy: 0.7892
- F1: 0.7460
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 | Accuracy | F1 |
|---|---|---|---|---|---|
| 0.5839 | 0.04 | 500 | 0.5193 | 0.7299 | 0.6543 |
| 0.5179 | 0.09 | 1000 | 0.4861 | 0.7508 | 0.6874 |
| 0.5047 | 0.13 | 1500 | 0.4916 | 0.7406 | 0.7097 |
| 0.4871 | 0.18 | 2000 | 0.4647 | 0.7584 | 0.7182 |
| 0.4789 | 0.22 | 2500 | 0.4564 | 0.7637 | 0.7240 |
| 0.4622 | 0.26 | 3000 | 0.4496 | 0.7668 | 0.7296 |
| 0.4617 | 0.31 | 3500 | 0.4468 | 0.7678 | 0.7343 |
| 0.454 | 0.35 | 4000 | 0.4415 | 0.7718 | 0.7376 |
| 0.4553 | 0.4 | 4500 | 0.4371 | 0.7755 | 0.7415 |
| 0.4438 | 0.44 | 5000 | 0.4204 | 0.7892 | 0.7460 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu116
- Datasets 2.8.1.dev0
- Tokenizers 0.13.2
