--- license: apache-2.0 base_model: distilbert-base-uncased tags: - generated_from_trainer metrics: - accuracy model-index: - name: distilbert_EPU results: [] --- # distilbert_EPU This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 1.0592 - Accuracy: 0.7291 ## 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: 1e-05 - train_batch_size: 6 - eval_batch_size: 6 - seed: 42 - gradient_accumulation_steps: 2 - total_train_batch_size: 12 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 8 - mixed_precision_training: Native AMP ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | |:-------------:|:-----:|:----:|:---------------:|:--------:| | 0.4904 | 1.0 | 699 | 0.5631 | 0.7077 | | 0.5241 | 2.0 | 1398 | 0.5150 | 0.7458 | | 0.3692 | 3.0 | 2097 | 0.5419 | 0.7501 | | 0.3366 | 4.0 | 2796 | 0.6243 | 0.7430 | | 0.2657 | 5.0 | 3495 | 0.7257 | 0.7358 | | 0.2303 | 6.0 | 4194 | 0.8840 | 0.7349 | | 0.0503 | 7.0 | 4893 | 1.0307 | 0.7291 | | 0.0732 | 8.0 | 5592 | 1.0592 | 0.7291 | ### Framework versions - Transformers 4.41.2 - Pytorch 2.3.0+cu121 - Datasets 2.20.0 - Tokenizers 0.19.1