multi-wiki-qa-multilingual-bert-gn-base-cased

WARNING: This model is no recommended.
For a best model, please use:
mmaguero/multi-wiki-qa-gn-xlm-v-base

This model is a fine-tuned version of mmaguero/multilingual-bert-gn-base-cased on alexandrainst/multi-wiki-qa dataset.

Test set (20%):

• exact_match: 0.7992007992007992
• f1: 3.0641271162419117

Model description

More information needed

Intended uses & limitations

Question Answering in Guarani.

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 3e-05
• train_batch_size: 16
• eval_batch_size: 16
• 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: 20
• mixed_precision_training: Native AMP

Training results

Validation set (10%):

• exact_match: 0.3992015968063872
• f1: 3.02416407545123

Framework versions

• Transformers 4.57.1
• Pytorch 2.8.0+cu126
• Datasets 4.0.0
• Tokenizers 0.22.1