mobilebert_sa_GLUE_Experiment_logit_kd_data_aug_wnli_256
This model is a fine-tuned version of google/mobilebert-uncased on the GLUE WNLI dataset. It achieves the following results on the evaluation set:
- Loss: 0.5755
- Accuracy: 0.1268
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 |
|---|---|---|---|---|
| 0.337 | 1.0 | 435 | 0.5755 | 0.1268 |
| 0.3007 | 2.0 | 870 | 0.5814 | 0.1127 |
| 0.2921 | 3.0 | 1305 | 0.6514 | 0.1127 |
| 0.2857 | 4.0 | 1740 | 0.6644 | 0.0704 |
| 0.2804 | 5.0 | 2175 | 0.6380 | 0.0986 |
| 0.2751 | 6.0 | 2610 | 0.6571 | 0.0986 |
Framework versions
- Transformers 4.26.0
- Pytorch 1.14.0a0+410ce96
- Datasets 2.9.0
- Tokenizers 0.13.2