tiny-mlm-snli-target-glue-sst2
This model is a fine-tuned version of muhtasham/tiny-mlm-snli on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.4415
- Accuracy: 0.8234
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 |
|---|---|---|---|---|
| 0.5925 | 0.24 | 500 | 0.4955 | 0.7741 |
| 0.4461 | 0.48 | 1000 | 0.4719 | 0.7856 |
| 0.3964 | 0.71 | 1500 | 0.4450 | 0.8016 |
| 0.375 | 0.95 | 2000 | 0.4547 | 0.7970 |
| 0.3361 | 1.19 | 2500 | 0.4403 | 0.8050 |
| 0.3163 | 1.43 | 3000 | 0.4422 | 0.8028 |
| 0.2995 | 1.66 | 3500 | 0.4388 | 0.8073 |
| 0.2931 | 1.9 | 4000 | 0.4413 | 0.8096 |
| 0.2741 | 2.14 | 4500 | 0.4884 | 0.8028 |
| 0.2555 | 2.38 | 5000 | 0.4415 | 0.8234 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu116
- Datasets 2.8.1.dev0
- Tokenizers 0.13.2