mobilebert_sa_GLUE_Experiment_mnli_256
This model is a fine-tuned version of google/mobilebert-uncased on the GLUE MNLI dataset. It achieves the following results on the evaluation set:
- Loss: 0.8790
- Accuracy: 0.6030
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 |
|---|---|---|---|---|
| 1.0008 | 1.0 | 3068 | 0.9490 | 0.5405 |
| 0.9205 | 2.0 | 6136 | 0.9166 | 0.5675 |
| 0.8928 | 3.0 | 9204 | 0.9022 | 0.5786 |
| 0.872 | 4.0 | 12272 | 0.8843 | 0.5967 |
| 0.8531 | 5.0 | 15340 | 0.8807 | 0.5959 |
| 0.8359 | 6.0 | 18408 | 0.8763 | 0.5999 |
| 0.8197 | 7.0 | 21476 | 0.8815 | 0.6009 |
| 0.8028 | 8.0 | 24544 | 0.9012 | 0.5934 |
| 0.786 | 9.0 | 27612 | 0.8633 | 0.6191 |
| 0.769 | 10.0 | 30680 | 0.8734 | 0.6098 |
| 0.752 | 11.0 | 33748 | 0.8682 | 0.6220 |
| 0.736 | 12.0 | 36816 | 0.8741 | 0.6175 |
| 0.7204 | 13.0 | 39884 | 0.8994 | 0.6048 |
| 0.7038 | 14.0 | 42952 | 0.8940 | 0.6079 |
Framework versions
- Transformers 4.26.0
- Pytorch 1.14.0a0+410ce96
- Datasets 2.8.0
- Tokenizers 0.13.2
- Downloads last month
- 1