<!-- 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-mnli
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: 0.8534
- Accuracy: 0.6159
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 |
|---|---|---|---|---|
| 1.0812 | 0.04 | 500 | 1.0475 | 0.4698 |
| 1.0185 | 0.08 | 1000 | 0.9640 | 0.5484 |
| 0.9627 | 0.12 | 1500 | 0.9279 | 0.5657 |
| 0.9401 | 0.16 | 2000 | 0.9181 | 0.5779 |
| 0.9307 | 0.2 | 2500 | 0.8954 | 0.5926 |
| 0.9249 | 0.24 | 3000 | 0.8846 | 0.5998 |
| 0.9083 | 0.29 | 3500 | 0.8752 | 0.6028 |
| 0.9022 | 0.33 | 4000 | 0.8636 | 0.6108 |
| 0.8841 | 0.37 | 4500 | 0.8628 | 0.6095 |
| 0.8857 | 0.41 | 5000 | 0.8534 | 0.6159 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu116
- Datasets 2.8.1.dev0
- Tokenizers 0.13.2
