Bert Base Uncased Finetuned Squad

🚀 bert-base-uncased-finetuned-squad

This model is a fine - tuned version of [bert - base - uncased](https://huggingface.co/bert - base - uncased) on the SQuAD1.1 dataset. It addresses the question - answering problem and provides accurate answers to questions based on given contexts. It was trained through Transformers' example Colab notebook on Question Answering, available here. It achieves a loss of 1.0780 on the evaluation set.

🚀 Quick Start

This model is a fine - tuned version of [bert - base - uncased](https://huggingface.co/bert - base - uncased) on the SQuAD1.1 dataset. It was trained using the example Colab notebook on Question Answering from Transformers, which you can access here.

📄 License

The model is licensed under the Apache 2.0 license.

🔧 Technical Details

Training Hyperparameters

The following hyperparameters were used during training. They are equal to the ones used to fine - tune [distilbert - base - uncased](https://huggingface.co/distilbert - base - uncased) for QA:

• 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: 3

Training Results

Validation Results

Framework Versions

• Transformers 4.9.2
• Pytorch 1.9.0+cu102
• Datasets 1.11.0
• Tokenizers 0.10.3

📋 Model Information