hBERTv1_no_pretrain_stsb
This model is a fine-tuned version of on the GLUE STSB dataset. It achieves the following results on the evaluation set:
- Loss: 2.1733
- Pearson: 0.2374
- Spearmanr: 0.2137
- Combined Score: 0.2256
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 | Pearson | Spearmanr | Combined Score |
|---|---|---|---|---|---|---|
| 2.3601 | 1.0 | 60 | 2.6639 | 0.1059 | 0.1080 | 0.1069 |
| 1.9983 | 2.0 | 120 | 2.1733 | 0.2374 | 0.2137 | 0.2256 |
| 1.7079 | 3.0 | 180 | 2.5000 | 0.1872 | 0.1967 | 0.1920 |
| 1.3775 | 4.0 | 240 | 3.1203 | 0.2177 | 0.2251 | 0.2214 |
| 1.1218 | 5.0 | 300 | 2.8260 | 0.2609 | 0.2598 | 0.2603 |
| 0.8882 | 6.0 | 360 | 2.5413 | 0.3099 | 0.3062 | 0.3081 |
| 0.728 | 7.0 | 420 | 2.4024 | 0.3429 | 0.3468 | 0.3448 |
Framework versions
- Transformers 4.30.2
- Pytorch 1.14.0a0+410ce96
- Datasets 2.12.0
- Tokenizers 0.13.3