distilbert_sa_GLUE_Experiment_logit_kd_qnli_96
This model is a fine-tuned version of distilbert-base-uncased on the GLUE QNLI dataset. It achieves the following results on the evaluation set:
- Loss: 0.3932
- Accuracy: 0.5808
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: 5e-05
- train_batch_size: 256
- eval_batch_size: 256
- seed: 10
- distributed_type: multi-GPU
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 50
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.4105 | 1.0 | 410 | 0.3976 | 0.5762 |
| 0.3966 | 2.0 | 820 | 0.3932 | 0.5808 |
| 0.3883 | 3.0 | 1230 | 0.3934 | 0.5841 |
| 0.3816 | 4.0 | 1640 | 0.3970 | 0.5772 |
| 0.376 | 5.0 | 2050 | 0.4003 | 0.5834 |
| 0.3713 | 6.0 | 2460 | 0.4040 | 0.5817 |
| 0.3672 | 7.0 | 2870 | 0.4088 | 0.5797 |
Framework versions
- Transformers 4.26.0
- Pytorch 1.14.0a0+410ce96
- Datasets 2.9.0
- Tokenizers 0.13.2