<!-- 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-sst2
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: 0.4379
- Accuracy: 0.8245
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 |
|---|---|---|---|---|
| 0.5813 | 0.24 | 500 | 0.4900 | 0.7649 |
| 0.4434 | 0.48 | 1000 | 0.4701 | 0.7810 |
| 0.3931 | 0.71 | 1500 | 0.4431 | 0.7924 |
| 0.3729 | 0.95 | 2000 | 0.4576 | 0.7890 |
| 0.3315 | 1.19 | 2500 | 0.4439 | 0.8062 |
| 0.3141 | 1.43 | 3000 | 0.4594 | 0.8050 |
| 0.2976 | 1.66 | 3500 | 0.4395 | 0.8142 |
| 0.2905 | 1.9 | 4000 | 0.4367 | 0.8154 |
| 0.2724 | 2.14 | 4500 | 0.4948 | 0.8062 |
| 0.2524 | 2.38 | 5000 | 0.4379 | 0.8245 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu116
- Datasets 2.8.1.dev0
- Tokenizers 0.13.2
