small-mlm-snli-target-glue-qnli
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: 0.3455
- Accuracy: 0.8578
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 |
|---|---|---|---|---|
| 0.4923 | 0.15 | 500 | 0.3923 | 0.8263 |
| 0.4458 | 0.31 | 1000 | 0.3827 | 0.8334 |
| 0.4233 | 0.46 | 1500 | 0.3632 | 0.8418 |
| 0.4157 | 0.61 | 2000 | 0.3732 | 0.8396 |
| 0.4152 | 0.76 | 2500 | 0.3416 | 0.8515 |
| 0.3942 | 0.92 | 3000 | 0.3320 | 0.8559 |
| 0.3572 | 1.07 | 3500 | 0.3458 | 0.8552 |
| 0.32 | 1.22 | 4000 | 0.3571 | 0.8611 |
| 0.3163 | 1.37 | 4500 | 0.3556 | 0.8539 |
| 0.3233 | 1.53 | 5000 | 0.3455 | 0.8578 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu116
- Datasets 2.8.1.dev0
- Tokenizers 0.13.2