mobilebert_sa_GLUE_Experiment_logit_kd_sst2_256
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: 0.8734
- Accuracy: 0.7592
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 |
|---|---|---|---|---|
| 1.0863 | 1.0 | 527 | 0.8734 | 0.7592 |
| 0.5116 | 2.0 | 1054 | 1.1742 | 0.7489 |
| 0.3952 | 3.0 | 1581 | 0.9197 | 0.7787 |
| 0.3401 | 4.0 | 2108 | 1.0557 | 0.7695 |
| 0.3113 | 5.0 | 2635 | 0.9003 | 0.7924 |
| 0.2862 | 6.0 | 3162 | 0.8923 | 0.8016 |
Framework versions
- Transformers 4.26.0
- Pytorch 1.14.0a0+410ce96
- Datasets 2.9.0
- Tokenizers 0.13.2