<!-- 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-base-uncased-layerdrop
This model is a fine-tuned version of distilbert-base-uncased on the glue dataset. It achieves the following results on the evaluation set:
- Loss: 0.5821
- Accuracy: 0.7826
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: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
0.642 | 1.0 | 24544 | 0.6169 | 0.7460 |
0.5793 | 2.0 | 49088 | 0.5678 | 0.7692 |
0.4914 | 3.0 | 73632 | 0.5669 | 0.7744 |
0.429 | 4.0 | 98176 | 0.5764 | 0.7868 |
0.4359 | 5.0 | 122720 | 0.5821 | 0.7826 |
Framework versions
- Transformers 4.27.2
- Pytorch 1.13.1+cu116
- Datasets 2.10.1
- Tokenizers 0.13.2