mobilebert_add_GLUE_Experiment_logit_kd_stsb
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: 1.1407
- Pearson: 0.0533
- Spearmanr: 0.0481
- Combined Score: 0.0507
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 |
|---|---|---|---|---|---|---|
| 1.7607 | 1.0 | 45 | 1.2881 | 0.0340 | 0.0258 | 0.0299 |
| 1.0763 | 2.0 | 90 | 1.1761 | 0.0478 | 0.0438 | 0.0458 |
| 1.0466 | 3.0 | 135 | 1.1550 | 0.0509 | 0.0390 | 0.0450 |
| 1.0685 | 4.0 | 180 | 1.1407 | 0.0533 | 0.0481 | 0.0507 |
| 1.0449 | 5.0 | 225 | 1.1527 | 0.0562 | 0.0478 | 0.0520 |
| 1.0303 | 6.0 | 270 | 1.2257 | 0.0580 | 0.0606 | 0.0593 |
| 1.0006 | 7.0 | 315 | 1.2018 | 0.0711 | 0.0736 | 0.0724 |
| 0.9661 | 8.0 | 360 | 1.2391 | 0.0716 | 0.0848 | 0.0782 |
| 0.9524 | 9.0 | 405 | 1.2005 | 0.0795 | 0.0749 | 0.0772 |
Framework versions
- Transformers 4.26.0
- Pytorch 1.14.0a0+410ce96
- Datasets 2.9.0
- Tokenizers 0.13.2