<!-- 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-finetuned-mnli
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: 2.4896
- Accuracy: 0.6812
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: 10
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
0.3128 | 1.0 | 625 | 1.1219 | 0.6772 |
0.1801 | 2.0 | 1250 | 1.4366 | 0.6716 |
0.1304 | 3.0 | 1875 | 1.8460 | 0.6777 |
0.1377 | 4.0 | 2500 | 1.9691 | 0.6702 |
0.0949 | 5.0 | 3125 | 2.1351 | 0.6792 |
0.0693 | 6.0 | 3750 | 2.3718 | 0.6797 |
0.0581 | 7.0 | 4375 | 2.4629 | 0.6801 |
0.0333 | 8.0 | 5000 | 2.4896 | 0.6812 |
0.0239 | 9.0 | 5625 | 2.5793 | 0.6783 |
0.0148 | 10.0 | 6250 | 2.5962 | 0.6791 |
Framework versions
- Transformers 4.22.2
- Pytorch 1.12.1+cu113
- Datasets 2.5.1
- Tokenizers 0.12.1