<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
mobilebert_add_GLUE_Experiment_sst2
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: 0.4671
- Accuracy: 0.7970
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 |
|---|---|---|---|---|
| 0.6635 | 1.0 | 527 | 0.6994 | 0.5390 |
| 0.5959 | 2.0 | 1054 | 0.6921 | 0.5665 |
| 0.5684 | 3.0 | 1581 | 0.7082 | 0.5516 |
| 0.5544 | 4.0 | 2108 | 0.6883 | 0.5619 |
| 0.5471 | 5.0 | 2635 | 0.6938 | 0.5940 |
| 0.5414 | 6.0 | 3162 | 0.7045 | 0.5803 |
| 0.5381 | 7.0 | 3689 | 0.7354 | 0.5654 |
| 0.5338 | 8.0 | 4216 | 0.7316 | 0.5826 |
| 0.3529 | 9.0 | 4743 | 0.4671 | 0.7970 |
| 0.2415 | 10.0 | 5270 | 0.4722 | 0.7982 |
| 0.2075 | 11.0 | 5797 | 0.4797 | 0.8062 |
| 0.1862 | 12.0 | 6324 | 0.5134 | 0.7993 |
| 0.1724 | 13.0 | 6851 | 0.5256 | 0.7993 |
| 0.1662 | 14.0 | 7378 | 0.5706 | 0.8028 |
Framework versions
- Transformers 4.26.0
- Pytorch 1.14.0a0+410ce96
- Datasets 2.8.0
- Tokenizers 0.13.2
