bert_base_train_book_rte
This model is a fine-tuned version of gokulsrinivasagan/bert_base_train_book on the GLUE RTE dataset. It achieves the following results on the evaluation set:
- Loss: 0.6893
- Accuracy: 0.5162
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
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 50
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.7152 | 1.0 | 10 | 0.6896 | 0.5343 |
| 0.679 | 2.0 | 20 | 0.6893 | 0.5162 |
| 0.6414 | 3.0 | 30 | 0.6979 | 0.5523 |
| 0.5501 | 4.0 | 40 | 0.7464 | 0.5451 |
| 0.415 | 5.0 | 50 | 0.9704 | 0.5632 |
| 0.3696 | 6.0 | 60 | 1.0318 | 0.5415 |
| 0.2357 | 7.0 | 70 | 1.0713 | 0.5776 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.2.1+cu118
- Datasets 2.17.0
- Tokenizers 0.20.3