mobilebert-uncased-finetuned-mrpc
This model is a fine-tuned version of google/mobilebert-uncased on the glue dataset. It achieves the following results on the evaluation set:
- Loss: 0.5753
- Accuracy: 0.7132
- F1: 0.8208
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: 2e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 70
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| No log | 1.0 | 115 | 0.9696 | 0.6863 | 0.8134 |
| No log | 2.0 | 230 | 1.3255 | 0.6740 | 0.8053 |
| No log | 3.0 | 345 | 0.5753 | 0.7132 | 0.8208 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3