distilbert_sa_GLUE_Experiment_data_aug_stsb_384
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: 2.8610
- Pearson: 0.1867
- Spearmanr: 0.1905
- Combined Score: 0.1886
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 |
|---|---|---|---|---|---|---|
| 0.9512 | 1.0 | 1259 | 2.8610 | 0.1867 | 0.1905 | 0.1886 |
| 0.3073 | 2.0 | 2518 | 3.0669 | 0.1520 | 0.1508 | 0.1514 |
| 0.1587 | 3.0 | 3777 | 3.1954 | 0.1595 | 0.1627 | 0.1611 |
| 0.1014 | 4.0 | 5036 | 2.9135 | 0.1600 | 0.1591 | 0.1596 |
| 0.0713 | 5.0 | 6295 | 3.2956 | 0.1514 | 0.1464 | 0.1489 |
| 0.0551 | 6.0 | 7554 | 3.1588 | 0.1712 | 0.1642 | 0.1677 |
Framework versions
- Transformers 4.26.0
- Pytorch 1.14.0a0+410ce96
- Datasets 2.9.0
- Tokenizers 0.13.2