distilbert_sa_GLUE_Experiment_data_aug_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: 2.9014
- Pearson: 0.1788
- Spearmanr: 0.1804
- Combined Score: 0.1796
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 | Combined Score | Validation Loss | Pearson | Spearmanr |
|---|---|---|---|---|---|---|
| 1.1748 | 1.0 | 1259 | 0.1811 | 3.0220 | 0.1788 | 0.1834 |
| 0.4365 | 2.0 | 2518 | 0.1777 | 2.9725 | 0.1774 | 0.1779 |
| 0.2502 | 3.0 | 3777 | 0.1796 | 2.9014 | 0.1788 | 0.1804 |
| 0.1669 | 4.0 | 5036 | 3.1989 | 0.1510 | 0.1571 | 0.1540 |
| 0.1237 | 5.0 | 6295 | 2.9701 | 0.1717 | 0.1765 | 0.1741 |
| 0.0969 | 6.0 | 7554 | 3.1938 | 0.1479 | 0.1523 | 0.1501 |
| 0.0802 | 7.0 | 8813 | 3.2793 | 0.1350 | 0.1440 | 0.1395 |
| 0.0669 | 8.0 | 10072 | 3.1238 | 0.1564 | 0.1640 | 0.1602 |
Framework versions
- Transformers 4.26.0
- Pytorch 1.14.0a0+410ce96
- Datasets 2.9.0
- Tokenizers 0.13.2