--- license: apache-2.0 base_model: bert-base-uncased tags: - generated_from_trainer datasets: - squad model-index: - name: bert-base-uncased-finetuned-squad results: [] --- # bert-base-uncased-finetuned-squad This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the squad dataset. It achieves the following results on the evaluation set: - Loss: 1.3657 - EM: 79.5837 - F1: 87.5227 ## 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 | |:-------------:|:-----:|:-----:|:---------------:| | 1.0671 | 1.0 | 5533 | 1.0278 | | 0.8197 | 2.0 | 11066 | 1.0359 | | 0.5664 | 3.0 | 16599 | 1.1494 | | 0.4077 | 4.0 | 22132 | 1.2497 | | 0.3299 | 5.0 | 27665 | 1.3657 | ### Framework versions - Transformers 4.34.0 - Pytorch 1.12.1 - Datasets 2.14.5 - Tokenizers 0.14.1