<!-- 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_logit_kd_qnli_384
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: 0.3912
- Accuracy: 0.5881
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 |
|---|---|---|---|---|
| 0.4059 | 1.0 | 410 | 0.3930 | 0.5733 |
| 0.3918 | 2.0 | 820 | 0.3919 | 0.5839 |
| 0.3807 | 3.0 | 1230 | 0.3912 | 0.5881 |
| 0.371 | 4.0 | 1640 | 0.3949 | 0.5843 |
| 0.3618 | 5.0 | 2050 | 0.3985 | 0.5815 |
| 0.352 | 6.0 | 2460 | 0.4136 | 0.5801 |
| 0.3416 | 7.0 | 2870 | 0.4222 | 0.5773 |
| 0.331 | 8.0 | 3280 | 0.4226 | 0.5742 |
Framework versions
- Transformers 4.26.0
- Pytorch 1.14.0a0+410ce96
- Datasets 2.9.0
- Tokenizers 0.13.2
