bert-base-multilingual-cased-finetuned-deduplicate_PersianQuAD – AI Model by Z-Jafari | AlphaNeural AI

You can deploy this model and start earning money today!

Z-Jafari/
bert-base-multilingual-cased-finetuned-deduplicate_PersianQuAD

like

0

question-answering

generated_from_trainer

Z-Jafari/deduplicated_PersianQuAD

google-bert/bert-base-multilingual-cased

endpoints_compatible

Views

No views yet

bert-base-multilingual-cased-finetuned-deduplicate_PersianQuAD

This model is a fine-tuned version of google-bert/bert-base-multilingual-cased on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.9458
{'exact_match': 77.3319959879639, 'f1': 81.2248342580515}

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: 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: 3
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.9088	1.0	1557	0.9219
0.6251	2.0	3114	0.9514
0.4192	3.0	4671	0.9458

Framework versions

Transformers 4.57.3
Pytorch 2.9.0+cu126
Datasets 4.0.0
Tokenizers 0.22.1