tiny-bert-sst2-distilled
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: 1.2916
- Accuracy: 0.8039
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: 6.478952479475704e-05
- train_batch_size: 128
- eval_batch_size: 128
- seed: 33
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.8025 | 1.0 | 527 | 1.3940 | 0.7901 |
| 1.1308 | 2.0 | 1054 | 1.2916 | 0.8039 |
Framework versions
- Transformers 4.34.1
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1
- Downloads last month
- 40
Model tree for lindeberg/tiny-bert-sst2-distilled
Base model
google/bert_uncased_L-2_H-128_A-2Dataset used to train lindeberg/tiny-bert-sst2-distilled
Evaluation results
- Accuracy on gluevalidation set self-reported0.804