mobilebert_sa_GLUE_Experiment_cola
This model is a fine-tuned version of google/mobilebert-uncased on the GLUE COLA dataset. It achieves the following results on the evaluation set:
- Loss: 0.6153
- Matthews Correlation: 0.0
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
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Matthews Correlation |
|---|---|---|---|---|
| 0.6122 | 1.0 | 67 | 0.6184 | 0.0 |
| 0.6078 | 2.0 | 134 | 0.6180 | 0.0 |
| 0.607 | 3.0 | 201 | 0.6185 | 0.0 |
| 0.6052 | 4.0 | 268 | 0.6153 | 0.0 |
| 0.5822 | 5.0 | 335 | 0.6292 | 0.0506 |
| 0.5193 | 6.0 | 402 | 0.6422 | 0.0743 |
| 0.4783 | 7.0 | 469 | 0.7020 | 0.0629 |
| 0.4504 | 8.0 | 536 | 0.7422 | 0.0834 |
| 0.4315 | 9.0 | 603 | 0.6915 | 0.0812 |
Framework versions
- Transformers 4.26.0
- Pytorch 1.14.0a0+410ce96
- Datasets 2.8.0
- Tokenizers 0.13.2