distilbert_add_GLUE_Experiment_logit_kd_stsb_256
This model is a fine-tuned version of distilbert-base-uncased on the GLUE STSB dataset. It achieves the following results on the evaluation set:
- Loss: 1.1575
- Pearson: nan
- Spearmanr: nan
- Combined Score: nan
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
- distributed_type: multi-GPU
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 50
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Pearson | Spearmanr | Combined Score |
|---|---|---|---|---|---|---|
| 2.8046 | 1.0 | 23 | 1.5779 | nan | nan | nan |
| 1.6122 | 2.0 | 46 | 1.1810 | nan | nan | nan |
| 1.1799 | 3.0 | 69 | 1.1666 | nan | nan | nan |
| 1.0869 | 4.0 | 92 | 1.1575 | nan | nan | nan |
| 1.0853 | 5.0 | 115 | 1.1872 | nan | nan | nan |
| 1.0773 | 6.0 | 138 | 1.1803 | 0.0712 | 0.0571 | 0.0642 |
| 1.0751 | 7.0 | 161 | 1.1795 | 0.0815 | 0.0739 | 0.0777 |
| 1.0607 | 8.0 | 184 | 1.1821 | 0.0734 | 0.0794 | 0.0764 |
| 0.9479 | 9.0 | 207 | 1.3706 | 0.0583 | 0.0830 | 0.0706 |
Framework versions
- Transformers 4.26.0
- Pytorch 1.14.0a0+410ce96
- Datasets 2.9.0
- Tokenizers 0.13.2