distilbert_sa_GLUE_Experiment_sst2
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: 0.4455
- Accuracy: 0.8073
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 |
|---|---|---|---|---|
| 0.4404 | 1.0 | 264 | 0.5503 | 0.7477 |
| 0.2565 | 2.0 | 528 | 0.6115 | 0.7580 |
| 0.2067 | 3.0 | 792 | 0.4455 | 0.8073 |
| 0.1714 | 4.0 | 1056 | 0.5150 | 0.7947 |
| 0.1438 | 5.0 | 1320 | 0.5712 | 0.7867 |
| 0.1162 | 6.0 | 1584 | 0.6657 | 0.7878 |
| 0.0992 | 7.0 | 1848 | 0.6404 | 0.7821 |
| 0.08 | 8.0 | 2112 | 0.7414 | 0.7924 |
Framework versions
- Transformers 4.26.0
- Pytorch 1.14.0a0+410ce96
- Datasets 2.8.0
- Tokenizers 0.13.2