<!-- 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. -->
distilbert_sa_GLUE_Experiment_stsb
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: 2.3709
- Pearson: 0.1628
- Spearmanr: 0.1610
- Combined Score: 0.1619
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 |
|---|---|---|---|---|---|---|
| 3.4997 | 1.0 | 23 | 2.5067 | 0.0558 | 0.0619 | 0.0588 |
| 2.0151 | 2.0 | 46 | 2.4888 | 0.1092 | 0.0973 | 0.1033 |
| 1.8234 | 3.0 | 69 | 2.3709 | 0.1628 | 0.1610 | 0.1619 |
| 1.5482 | 4.0 | 92 | 3.0640 | 0.1571 | 0.1632 | 0.1602 |
| 1.33 | 5.0 | 115 | 3.1306 | 0.1649 | 0.1896 | 0.1772 |
| 1.1586 | 6.0 | 138 | 2.9752 | 0.1454 | 0.1567 | 0.1511 |
| 1.0473 | 7.0 | 161 | 3.1783 | 0.1490 | 0.1670 | 0.1580 |
| 0.9198 | 8.0 | 184 | 3.0440 | 0.1632 | 0.1734 | 0.1683 |
Framework versions
- Transformers 4.26.0
- Pytorch 1.14.0a0+410ce96
- Datasets 2.8.0
- Tokenizers 0.13.2
