<!-- 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_new_pretrain_48_KD_w_init_stsb
This model is a fine-tuned version of gokuls/bert_12_layer_model_v1_complete_training_new_48_KD_wt_init on the GLUE STSB dataset. It achieves the following results on the evaluation set:
- Loss: 2.3593
- Pearson: 0.1283
- Spearmanr: 0.1100
- Combined Score: 0.1192
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: 128
- eval_batch_size: 128
- 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 |
|---|---|---|---|---|---|---|
| 2.3304 | 1.0 | 45 | 2.3593 | 0.1283 | 0.1100 | 0.1192 |
| 1.9951 | 2.0 | 90 | 2.5865 | 0.1746 | 0.1639 | 0.1692 |
| 1.8698 | 3.0 | 135 | 2.4068 | 0.1900 | 0.1928 | 0.1914 |
| 1.535 | 4.0 | 180 | 2.4625 | 0.2815 | 0.2884 | 0.2849 |
| 1.1788 | 5.0 | 225 | 2.6830 | 0.3003 | 0.2981 | 0.2992 |
| 0.8586 | 6.0 | 270 | 2.5719 | 0.3295 | 0.3452 | 0.3373 |
Framework versions
- Transformers 4.30.2
- Pytorch 1.14.0a0+410ce96
- Datasets 2.13.0
- Tokenizers 0.13.3
