srvmishra832/SQuAD-extractive_QA-bert-base-cased

SQuAD-extractive_QA-bert-base-cased

This model is a fine-tuned version of bert-base-cased on the SQuAD dataset.

Model description

bert-base-cased

Intended uses & limitations

Extractive QA

Training and evaluation data

SQuAD dataset. Can be accessed using the load_dataset() method.

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• —learning_rate: 2e-05
• —trainbatchsize: 64
• —evalbatchsize: 64
• —seed: 42
• —optimizer: Use OptimizerNames.ADAMWTORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizerargs=No additional optimizer arguments
• —lrschedulertype: linear
• —num_epochs: 3
• —mixedprecisiontraining: Native AMP

Training results

After training, exact_match: 80.246, and f1: 87.665

Framework versions

• —Transformers 4.50.0
• —Pytorch 2.6.0+cu124
• —Datasets 3.5.0
• —Tokenizers 0.21.1