<!-- 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-mnli-target-glue-sst2
This model is a fine-tuned version of muhtasham/tiny-mlm-glue-mnli on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.5014
- Accuracy: 0.7993
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 |
|---|---|---|---|---|
| 0.5929 | 0.24 | 500 | 0.4966 | 0.7752 |
| 0.4445 | 0.48 | 1000 | 0.4688 | 0.7833 |
| 0.3937 | 0.71 | 1500 | 0.4462 | 0.8005 |
| 0.372 | 0.95 | 2000 | 0.4629 | 0.7913 |
| 0.3341 | 1.19 | 2500 | 0.4480 | 0.7993 |
| 0.3159 | 1.43 | 3000 | 0.4481 | 0.8085 |
| 0.2978 | 1.66 | 3500 | 0.4441 | 0.8073 |
| 0.2923 | 1.9 | 4000 | 0.4464 | 0.8085 |
| 0.273 | 2.14 | 4500 | 0.5014 | 0.7993 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu116
- Datasets 2.8.1.dev0
- Tokenizers 0.13.2
