bert-tiny-finetuned-glue-rte
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: 0.6673
- Accuracy: 0.6318
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: 2.4294744851376705e-05
- train_batch_size: 64
- eval_batch_size: 16
- seed: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 156 | 0.6852 | 0.5776 |
| No log | 2.0 | 312 | 0.6800 | 0.5993 |
| No log | 3.0 | 468 | 0.6737 | 0.6173 |
| 0.6845 | 4.0 | 624 | 0.6690 | 0.6101 |
| 0.6845 | 5.0 | 780 | 0.6673 | 0.6318 |
Framework versions
- Transformers 4.21.0
- Pytorch 1.12.0+cu113
- Datasets 2.4.0
- Tokenizers 0.12.1