naamapadam-bengali-stage1-full

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

• Loss: nan
• Precision: 0.0
• Recall: 0.0
• F1: 0.0
• Accuracy: 0.8213

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: 0.0005
• 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: 1
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
0.0	0.4990	240	nan	0.0	0.0	0.0	0.8213
0.0	0.9979	480	nan	0.0	0.0	0.0	0.8213

Framework versions

• PEFT 0.17.1
• Transformers 4.56.1
• Pytorch 2.8.0+cu126
• Datasets 2.14.7
• Tokenizers 0.22.0