<!-- 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_data_aug_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: 0.4463
- Accuracy: 0.5576
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 |
---|---|---|---|---|
0.338 | 1.0 | 16604 | 0.4463 | 0.5576 |
0.2791 | 2.0 | 33208 | 0.4560 | 0.5711 |
0.256 | 3.0 | 49812 | 0.4603 | 0.5691 |
0.2446 | 4.0 | 66416 | 0.4620 | 0.5709 |
0.2379 | 5.0 | 83020 | 0.4547 | 0.5958 |
0.2334 | 6.0 | 99624 | 0.4581 | 0.5863 |
Framework versions
- Transformers 4.26.0
- Pytorch 1.14.0a0+410ce96
- Datasets 2.9.0
- Tokenizers 0.13.2