distilbert_sa_GLUE_Experiment_data_aug_sst2_256
This model is a fine-tuned version of distilbert-base-uncased on the GLUE SST2 dataset. It achieves the following results on the evaluation set:
- Loss: 0.5204
- Accuracy: 0.7913
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 | Accuracy | Validation Loss |
|---|---|---|---|---|
| 0.3537 | 1.0 | 4374 | 0.7913 | 0.5204 |
| 0.2638 | 2.0 | 8748 | 0.6801 | 0.7649 |
| 0.2156 | 3.0 | 13122 | 0.6808 | 0.7752 |
| 0.1812 | 4.0 | 17496 | 0.7841 | 0.7718 |
| 0.1563 | 5.0 | 21870 | 0.8941 | 0.7683 |
| 0.1369 | 6.0 | 26244 | 1.0494 | 0.7569 |
Framework versions
- Transformers 4.26.0
- Pytorch 1.14.0a0+410ce96
- Datasets 2.9.0
- Tokenizers 0.13.2