tiny-bert-sst2-1_mobilebert_2_bert-only-distillation
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: 1.5399
- Accuracy: 0.8291
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: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.2068 | 1.0 | 4210 | 1.5399 | 0.8291 |
| 0.22 | 2.0 | 8420 | 1.5395 | 0.8234 |
| 0.2171 | 3.0 | 12630 | 1.6631 | 0.8200 |
| 0.2434 | 4.0 | 16840 | 1.6152 | 0.8234 |
Framework versions
- Transformers 4.21.1
- Pytorch 1.12.1+cu113
- Datasets 2.4.0
- Tokenizers 0.12.1
- Downloads last month
- 3
Dataset used to train gokuls/tiny-bert-sst2-1_mobilebert_2_bert-only-distillation
Evaluation results
- Accuracy on glueself-reported0.829