mobilebert_sa_GLUE_Experiment_logit_kd_data_aug_qnli
This model is a fine-tuned version of google/mobilebert-uncased on the GLUE QNLI dataset. It achieves the following results on the evaluation set:
- Loss: 1.1420
- Accuracy: 0.5923
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 | Accuracy |
|---|---|---|---|---|
| 0.6899 | 1.0 | 33208 | 1.1420 | 0.5923 |
| 0.498 | 2.0 | 66416 | 1.2196 | 0.5944 |
| 0.4209 | 3.0 | 99624 | 1.2370 | 0.5977 |
| 0.3746 | 4.0 | 132832 | 1.2784 | 0.5973 |
| 0.3449 | 5.0 | 166040 | 1.2649 | 0.5938 |
| 0.3238 | 6.0 | 199248 | 1.1662 | 0.6114 |
Framework versions
- Transformers 4.26.0
- Pytorch 1.14.0a0+410ce96
- Datasets 2.9.0
- Tokenizers 0.13.2
- Downloads last month
- 3
Dataset used to train gokuls/mobilebert_sa_GLUE_Experiment_logit_kd_data_aug_qnli
Evaluation results
- Accuracy on GLUE QNLIself-reported0.592