tinybert_train_book_ent_15p_inv_qnli
This model is a fine-tuned version of gokulsrinivasagan/tinybert_train_book_ent_15p_inv on the GLUE QNLI dataset. It achieves the following results on the evaluation set:
- Loss: 0.6088
- Accuracy: 0.6562
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 |
|---|---|---|---|---|
| 0.6601 | 1.0 | 410 | 0.6325 | 0.6377 |
| 0.6169 | 2.0 | 820 | 0.6088 | 0.6562 |
| 0.5593 | 3.0 | 1230 | 0.6206 | 0.6480 |
| 0.4876 | 4.0 | 1640 | 0.6570 | 0.6529 |
| 0.4172 | 5.0 | 2050 | 0.7083 | 0.6579 |
| 0.3519 | 6.0 | 2460 | 0.8199 | 0.6449 |
| 0.2969 | 7.0 | 2870 | 0.9762 | 0.6443 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.2.1+cu118
- Datasets 3.1.0
- Tokenizers 0.20.3