mobilebert_sa_GLUE_Experiment_logit_kd_pretrain_cola
This model is a fine-tuned version of gokuls/mobilebert_sa_pre-training-complete on the GLUE COLA dataset. It achieves the following results on the evaluation set:
- Loss: 0.3784
- Matthews Correlation: 0.5440
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 | Matthews Correlation |
|---|---|---|---|---|
| 0.6286 | 1.0 | 67 | 0.4351 | 0.4469 |
| 0.3982 | 2.0 | 134 | 0.4004 | 0.4858 |
| 0.2722 | 3.0 | 201 | 0.3867 | 0.5372 |
| 0.2056 | 4.0 | 268 | 0.3784 | 0.5440 |
| 0.1649 | 5.0 | 335 | 0.4274 | 0.5624 |
| 0.135 | 6.0 | 402 | 0.4440 | 0.5261 |
| 0.1174 | 7.0 | 469 | 0.4543 | 0.5495 |
| 0.108 | 8.0 | 536 | 0.3885 | 0.5506 |
| 0.1002 | 9.0 | 603 | 0.4125 | 0.5423 |
Framework versions
- Transformers 4.26.0
- Pytorch 1.14.0a0+410ce96
- Datasets 2.9.0
- Tokenizers 0.13.2