<!-- 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. -->
hBERTv1_no_pretrain_wnli
This model is a fine-tuned version of on the GLUE WNLI dataset. It achieves the following results on the evaluation set:
- Loss: 0.6862
- Accuracy: 0.5634
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: 96
- eval_batch_size: 96
- seed: 10
- distributed_type: multi-GPU
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 50
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.8468 | 1.0 | 7 | 0.6988 | 0.5634 |
| 0.733 | 2.0 | 14 | 0.8370 | 0.4366 |
| 0.7422 | 3.0 | 21 | 0.7440 | 0.4366 |
| 0.7016 | 4.0 | 28 | 0.7514 | 0.4366 |
| 0.7085 | 5.0 | 35 | 0.7207 | 0.4366 |
| 0.7291 | 6.0 | 42 | 0.6975 | 0.5634 |
| 0.7123 | 7.0 | 49 | 0.6938 | 0.4366 |
| 0.703 | 8.0 | 56 | 0.7073 | 0.4366 |
| 0.714 | 9.0 | 63 | 0.7375 | 0.4366 |
| 0.7049 | 10.0 | 70 | 0.7098 | 0.4366 |
| 0.7036 | 11.0 | 77 | 0.6951 | 0.4366 |
| 0.7061 | 12.0 | 84 | 0.6862 | 0.5634 |
| 0.7034 | 13.0 | 91 | 0.7034 | 0.4366 |
| 0.7052 | 14.0 | 98 | 0.6955 | 0.4366 |
| 0.7028 | 15.0 | 105 | 0.7138 | 0.4366 |
| 0.7064 | 16.0 | 112 | 0.6864 | 0.5634 |
| 0.6953 | 17.0 | 119 | 0.6956 | 0.4507 |
Framework versions
- Transformers 4.30.2
- Pytorch 1.14.0a0+410ce96
- Datasets 2.12.0
- Tokenizers 0.13.3
