distilbert_sa_GLUE_Experiment_logit_kd_data_aug_cola_192
This model is a fine-tuned version of distilbert-base-uncased on the GLUE COLA dataset. It achieves the following results on the evaluation set:
- Loss: 0.6917
- Matthews Correlation: 0.0937
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 | Matthews Correlation |
|---|---|---|---|---|
| 0.647 | 1.0 | 835 | 0.6917 | 0.0937 |
| 0.5356 | 2.0 | 1670 | 0.7312 | 0.1294 |
| 0.4736 | 3.0 | 2505 | 0.7512 | 0.1372 |
| 0.4318 | 4.0 | 3340 | 0.7576 | 0.1259 |
| 0.3993 | 5.0 | 4175 | 0.7826 | 0.1277 |
| 0.3736 | 6.0 | 5010 | 0.8138 | 0.1028 |
Framework versions
- Transformers 4.26.0
- Pytorch 1.14.0a0+410ce96
- Datasets 2.9.0
- Tokenizers 0.13.2