mobilebert_sa_GLUE_Experiment_data_aug_mnli
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: 0.9046
- Accuracy: 0.6099
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 |
|---|---|---|---|---|
| 0.8429 | 1.0 | 62880 | 0.8755 | 0.6185 |
| 0.6713 | 2.0 | 125760 | 0.9512 | 0.6039 |
| 0.5387 | 3.0 | 188640 | 1.0796 | 0.5978 |
| 0.4297 | 4.0 | 251520 | 1.1877 | 0.5961 |
| 0.3405 | 5.0 | 314400 | 1.3154 | 0.5895 |
| 0.2693 | 6.0 | 377280 | 1.4320 | 0.5798 |
Framework versions
- Transformers 4.26.0
- Pytorch 1.14.0a0+410ce96
- Datasets 2.9.0
- Tokenizers 0.13.2
- Downloads last month
- 2
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.