small-mlm-snli-target-glue-sst2
This model is a fine-tuned version of muhtasham/small-mlm-snli on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3698
- Accuracy: 0.8842
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 |
|---|---|---|---|---|
| 0.3914 | 0.24 | 500 | 0.3591 | 0.8406 |
| 0.3025 | 0.48 | 1000 | 0.3262 | 0.8567 |
| 0.2576 | 0.71 | 1500 | 0.3541 | 0.8601 |
| 0.2378 | 0.95 | 2000 | 0.3003 | 0.8853 |
| 0.1826 | 1.19 | 2500 | 0.3614 | 0.8716 |
| 0.1691 | 1.43 | 3000 | 0.3817 | 0.8704 |
| 0.1671 | 1.66 | 3500 | 0.3698 | 0.8842 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu116
- Datasets 2.8.1.dev0
- Tokenizers 0.13.2