bert-tiny-sst2-KD-distilBERT
This model is a fine-tuned version of google/bert_uncased_L-2_H-128_A-2 on the glue dataset. It achieves the following results on the evaluation set:
- Loss: 1.1035
- Accuracy: 0.8326
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: 16
- eval_batch_size: 16
- seed: 33
- 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 |
|---|---|---|---|---|
| 1.2008 | 1.0 | 4210 | 1.1319 | 0.8177 |
| 0.6821 | 2.0 | 8420 | 1.1035 | 0.8326 |
| 0.5315 | 3.0 | 12630 | 1.2271 | 0.8245 |
| 0.4486 | 4.0 | 16840 | 1.4426 | 0.8177 |
| 0.3857 | 5.0 | 21050 | 1.4309 | 0.8303 |
Framework versions
- Transformers 4.22.1
- Pytorch 1.12.1+cu113
- Datasets 2.5.1
- Tokenizers 0.12.1