distilbert_sa_GLUE_Experiment_qnli_192
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: 0.6554
- Accuracy: 0.6050
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 |
|---|---|---|---|---|
| 0.6802 | 1.0 | 410 | 0.6614 | 0.5988 |
| 0.6514 | 2.0 | 820 | 0.6554 | 0.6050 |
| 0.6306 | 3.0 | 1230 | 0.6610 | 0.5938 |
| 0.6105 | 4.0 | 1640 | 0.6700 | 0.5942 |
| 0.5925 | 5.0 | 2050 | 0.6833 | 0.5891 |
| 0.5725 | 6.0 | 2460 | 0.7225 | 0.5898 |
| 0.5537 | 7.0 | 2870 | 0.7806 | 0.5810 |
Framework versions
- Transformers 4.26.0
- Pytorch 1.14.0a0+410ce96
- Datasets 2.8.0
- Tokenizers 0.13.2