distilbert_add_GLUE_Experiment_logit_kd_mrpc_256
This model is a fine-tuned version of distilbert-base-uncased on the GLUE MRPC dataset. It achieves the following results on the evaluation set:
- Loss: 0.5290
- Accuracy: 0.3162
- F1: 0.0
- Combined Score: 0.1581
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: 256
- eval_batch_size: 256
- 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
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Combined Score |
|---|---|---|---|---|---|---|
| 0.533 | 1.0 | 15 | 0.5291 | 0.3162 | 0.0 | 0.1581 |
| 0.5292 | 2.0 | 30 | 0.5293 | 0.3162 | 0.0 | 0.1581 |
| 0.5306 | 3.0 | 45 | 0.5302 | 0.3162 | 0.0 | 0.1581 |
| 0.5293 | 4.0 | 60 | 0.5296 | 0.3162 | 0.0 | 0.1581 |
| 0.5285 | 5.0 | 75 | 0.5291 | 0.3162 | 0.0 | 0.1581 |
| 0.5291 | 6.0 | 90 | 0.5293 | 0.3162 | 0.0 | 0.1581 |
| 0.5274 | 7.0 | 105 | 0.5290 | 0.3162 | 0.0 | 0.1581 |
| 0.5286 | 8.0 | 120 | 0.5293 | 0.3162 | 0.0 | 0.1581 |
| 0.5282 | 9.0 | 135 | 0.5292 | 0.3162 | 0.0 | 0.1581 |
| 0.5286 | 10.0 | 150 | 0.5294 | 0.3162 | 0.0 | 0.1581 |
| 0.5282 | 11.0 | 165 | 0.5291 | 0.3162 | 0.0 | 0.1581 |
| 0.5284 | 12.0 | 180 | 0.5294 | 0.3162 | 0.0 | 0.1581 |
Framework versions
- Transformers 4.26.0
- Pytorch 1.14.0a0+410ce96
- Datasets 2.9.0
- Tokenizers 0.13.2