mobilebert_sa_GLUE_Experiment_data_aug_rte_128
This model is a fine-tuned version of google/mobilebert-uncased on the GLUE RTE dataset. It achieves the following results on the evaluation set:
- Loss: 2.4009
- Accuracy: 0.4693
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 |
|---|---|---|---|---|
| 0.2565 | 1.0 | 1136 | 2.4009 | 0.4693 |
| 0.0479 | 2.0 | 2272 | 4.5560 | 0.4801 |
| 0.0277 | 3.0 | 3408 | 3.9412 | 0.4946 |
| 0.0162 | 4.0 | 4544 | 5.7917 | 0.4910 |
| 0.0107 | 5.0 | 5680 | 5.5483 | 0.4946 |
| 0.0089 | 6.0 | 6816 | 9.5227 | 0.4946 |
Framework versions
- Transformers 4.26.0
- Pytorch 1.14.0a0+410ce96
- Datasets 2.9.0
- Tokenizers 0.13.2
- Downloads last month
- 4
Dataset used to train gokuls/mobilebert_sa_GLUE_Experiment_data_aug_rte_128
Evaluation results
- Accuracy on GLUE RTEself-reported0.469