MiniLMv2-L6-H384-distilled-from-BERT-Base-finetuned-qqp
This model is a fine-tuned version of jim12345/MiniLMv2-L6-H384-distilled-from-BERT-Base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2846
- Accuracy: 0.9012
- F1: 0.8673
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 0.2557 | 1.0 | 22741 | 0.2670 | 0.8885 | 0.8498 |
| 0.2382 | 2.0 | 45482 | 0.2613 | 0.8929 | 0.8602 |
| 0.2041 | 3.0 | 68223 | 0.2712 | 0.8976 | 0.8632 |
| 0.1779 | 4.0 | 90964 | 0.2846 | 0.9012 | 0.8673 |
| 0.1704 | 5.0 | 113705 | 0.3077 | 0.9010 | 0.8669 |
Framework versions
- Transformers 4.52.4
- Pytorch 2.6.0+cu124
- Datasets 3.6.0
- Tokenizers 0.21.1