mobilebert_sa_GLUE_Experiment_data_aug_stsb_256
This model is a fine-tuned version of google/mobilebert-uncased on the GLUE STSB dataset. It achieves the following results on the evaluation set:
- Loss: 2.7922
- Pearson: 0.1559
- Spearmanr: 0.1663
- Combined Score: 0.1611
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: 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 |
|---|---|---|---|---|---|---|
| 1.0735 | 1.0 | 2518 | 2.8241 | 0.1664 | 0.1853 | 0.1759 |
| 0.6303 | 2.0 | 5036 | 2.7922 | 0.1559 | 0.1663 | 0.1611 |
| 0.501 | 3.0 | 7554 | 3.0939 | 0.1590 | 0.1630 | 0.1610 |
| 0.3527 | 4.0 | 10072 | 3.2284 | 0.1662 | 0.1715 | 0.1689 |
| 0.255 | 5.0 | 12590 | 2.9106 | 0.1775 | 0.1835 | 0.1805 |
| 0.194 | 6.0 | 15108 | 3.1703 | 0.1550 | 0.1626 | 0.1588 |
| 0.1563 | 7.0 | 17626 | 2.9109 | 0.1632 | 0.1691 | 0.1661 |
Framework versions
- Transformers 4.26.0
- Pytorch 1.14.0a0+410ce96
- Datasets 2.9.0
- Tokenizers 0.13.2