<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
distilbert_sa_GLUE_Experiment_data_aug_qnli
This model is a fine-tuned version of distilbert-base-uncased on the GLUE QNLI dataset. It achieves the following results on the evaluation set:
- Loss: 1.2699
- Accuracy: 0.5997
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 |
|---|---|---|---|---|
| 0.3057 | 1.0 | 16604 | 1.2699 | 0.5997 |
| 0.0735 | 2.0 | 33208 | 1.7786 | 0.5953 |
| 0.0313 | 3.0 | 49812 | 1.9603 | 0.5801 |
| 0.0188 | 4.0 | 66416 | 2.2529 | 0.5927 |
| 0.0134 | 5.0 | 83020 | 2.4498 | 0.5913 |
| 0.0106 | 6.0 | 99624 | 2.5181 | 0.6031 |
Framework versions
- Transformers 4.26.0
- Pytorch 1.14.0a0+410ce96
- Datasets 2.9.0
- Tokenizers 0.13.2
