distilbert_sa_GLUE_Experiment_data_aug_qqp_96
This model is a fine-tuned version of distilbert-base-uncased on the GLUE QQP dataset. It achieves the following results on the evaluation set:
- Loss: 0.4833
- Accuracy: 0.7735
- F1: 0.7060
- Combined Score: 0.7397
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 |
|---|---|---|---|---|---|---|
| 0.4535 | 1.0 | 29671 | 0.4833 | 0.7735 | 0.7060 | 0.7397 |
| 0.3495 | 2.0 | 59342 | 0.5018 | 0.7825 | 0.7161 | 0.7493 |
| 0.289 | 3.0 | 89013 | 0.5229 | 0.7909 | 0.7268 | 0.7589 |
| 0.2484 | 4.0 | 118684 | 0.5749 | 0.7844 | 0.7255 | 0.7550 |
| 0.2181 | 5.0 | 148355 | 0.6016 | 0.7907 | 0.7309 | 0.7608 |
| 0.1951 | 6.0 | 178026 | 0.6304 | 0.7916 | 0.7274 | 0.7595 |
Framework versions
- Transformers 4.26.0
- Pytorch 1.14.0a0+410ce96
- Datasets 2.9.0
- Tokenizers 0.13.2