distilbert_sa_GLUE_Experiment_data_aug_sst2_96
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: 0.4855
- Accuracy: 0.8005
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 |
|---|---|---|---|---|
| 0.3811 | 1.0 | 4374 | 0.4855 | 0.8005 |
| 0.2999 | 2.0 | 8748 | 0.5732 | 0.7890 |
| 0.2675 | 3.0 | 13122 | 0.6208 | 0.7787 |
| 0.2408 | 4.0 | 17496 | 0.6883 | 0.7798 |
| 0.2194 | 5.0 | 21870 | 0.7810 | 0.7798 |
| 0.2022 | 6.0 | 26244 | 0.7588 | 0.7592 |
Framework versions
- Transformers 4.26.0
- Pytorch 1.14.0a0+410ce96
- Datasets 2.9.0
- Tokenizers 0.13.2