<!-- 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. -->
small-mlm-glue-stsb-target-glue-mnli
This model is a fine-tuned version of muhtasham/small-mlm-glue-stsb on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.6513
- Accuracy: 0.7268
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 |
|---|---|---|---|---|
| 0.9101 | 0.04 | 500 | 0.8299 | 0.6385 |
| 0.8131 | 0.08 | 1000 | 0.7844 | 0.6635 |
| 0.7743 | 0.12 | 1500 | 0.7392 | 0.6780 |
| 0.7491 | 0.16 | 2000 | 0.7260 | 0.6899 |
| 0.7444 | 0.2 | 2500 | 0.7143 | 0.6923 |
| 0.7326 | 0.24 | 3000 | 0.7026 | 0.7013 |
| 0.7134 | 0.29 | 3500 | 0.6841 | 0.7124 |
| 0.7018 | 0.33 | 4000 | 0.6710 | 0.7230 |
| 0.679 | 0.37 | 4500 | 0.6698 | 0.7227 |
| 0.6818 | 0.41 | 5000 | 0.6513 | 0.7268 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu116
- Datasets 2.8.1.dev0
- Tokenizers 0.13.2
