mdeberta-fiqhqa-qa-tuned

This model is a fine-tuned version of micsrosoft/mdeberta-v3-base on the FiqhQA dataset. It achieves the following results on the evaluation set:

• Loss: 0.8749
• Exact Match: 25.1799
• F1: 52.6026

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: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Exact Match	F1
1.0508	1.0	666	0.8893	22.3022	49.2989
0.8132	2.0	1332	0.8286	24.4604	55.0689
0.6724	3.0	1998	0.8749	25.1799	52.6026

Framework versions

• Transformers 4.57.1
• Pytorch 2.9.1+cu128
• Datasets 4.4.1
• Tokenizers 0.22.1