mobilebert_sa_GLUE_Experiment_data_aug_sst2_128
This model is a fine-tuned version of google/mobilebert-uncased on the GLUE SST2 dataset. It achieves the following results on the evaluation set:
- Loss: 0.4922
- Accuracy: 0.7936
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 |
|---|---|---|---|---|
| 0.3587 | 1.0 | 8748 | 0.4922 | 0.7936 |
| 0.2861 | 2.0 | 17496 | 0.5522 | 0.7878 |
| 0.2387 | 3.0 | 26244 | 0.7233 | 0.7775 |
| 0.2089 | 4.0 | 34992 | 0.6891 | 0.7890 |
| 0.1882 | 5.0 | 43740 | 0.8317 | 0.7913 |
| 0.1726 | 6.0 | 52488 | 0.8467 | 0.7706 |
Framework versions
- Transformers 4.26.0
- Pytorch 1.14.0a0+410ce96
- Datasets 2.9.0
- Tokenizers 0.13.2