--- license: apache-2.0 tags: - generated_from_trainer datasets: - glue metrics: - accuracy model-index: - name: distilbert-base-uncased-finetuned-mnli results: - task: name: Text Classification type: text-classification dataset: name: glue type: glue config: mnli split: validation_matched args: mnli metrics: - name: Accuracy type: accuracy value: 0.8188487009679063 --- # distilbert-base-uncased-finetuned-mnli This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the glue dataset. It achieves the following results on the evaluation set: - Loss: 0.5546 - Accuracy: 0.8188 ## 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 | |:-------------:|:-----:|:------:|:---------------:|:--------:| | 0.5153 | 1.0 | 24544 | 0.4999 | 0.8029 | | 0.4194 | 2.0 | 49088 | 0.4788 | 0.8138 | | 0.3065 | 3.0 | 73632 | 0.5546 | 0.8188 | | 0.2172 | 4.0 | 98176 | 0.7237 | 0.8142 | | 0.1784 | 5.0 | 122720 | 0.8463 | 0.8165 | ### Framework versions - Transformers 4.29.2 - Pytorch 2.0.1+cu118 - Datasets 2.12.0 - Tokenizers 0.13.3