<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
hBERTv2_new_pretrain_48_ver2_qnli
This model is a fine-tuned version of gokuls/bert_12_layer_model_v2_complete_training_new_48 on the GLUE QNLI dataset. It achieves the following results on the evaluation set:
- Loss: 0.6731
- Accuracy: 0.5839
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: 4e-05
- train_batch_size: 64
- eval_batch_size: 64
- seed: 10
- distributed_type: multi-GPU
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 15
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.6905 | 1.0 | 1637 | 0.6830 | 0.5724 |
| 0.6788 | 2.0 | 3274 | 0.6778 | 0.5812 |
| 0.6699 | 3.0 | 4911 | 0.6731 | 0.5839 |
| 0.6711 | 4.0 | 6548 | 0.6835 | 0.5678 |
| 0.6723 | 5.0 | 8185 | 0.6852 | 0.5546 |
| 0.674 | 6.0 | 9822 | 0.6818 | 0.5678 |
| 0.6679 | 7.0 | 11459 | 0.6759 | 0.5737 |
| 0.6681 | 8.0 | 13096 | 0.6932 | 0.5329 |
Framework versions
- Transformers 4.34.0
- Pytorch 1.14.0a0+410ce96
- Datasets 2.14.5
- Tokenizers 0.14.1
