distilbert_sa_GLUE_Experiment_sst2_192
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: 0.4491
- Accuracy: 0.7982
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 |
|---|---|---|---|---|
| 0.5372 | 1.0 | 264 | 0.4524 | 0.8005 |
| 0.3132 | 2.0 | 528 | 0.4632 | 0.7913 |
| 0.2501 | 3.0 | 792 | 0.4491 | 0.7982 |
| 0.2176 | 4.0 | 1056 | 0.4819 | 0.7924 |
| 0.1963 | 5.0 | 1320 | 0.4784 | 0.7878 |
| 0.1793 | 6.0 | 1584 | 0.5427 | 0.7947 |
| 0.1651 | 7.0 | 1848 | 0.5849 | 0.7867 |
| 0.1515 | 8.0 | 2112 | 0.6103 | 0.7787 |
Framework versions
- Transformers 4.26.0
- Pytorch 1.14.0a0+410ce96
- Datasets 2.8.0
- Tokenizers 0.13.2