bengali-sentiment-bert

This model is a fine-tuned version of google-bert/bert-base-multilingual-cased on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.1376
• F1 Macro: 0.9055
• F1 Micro: 0.9187
• Precision Macro: 0.9295
• Recall Macro: 0.8850
• Exact Match Accuracy: 0.8166

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: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 16
• 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
• lr_scheduler_warmup_steps: 130
• num_epochs: 5

Training results

Framework versions

• Transformers 5.22.2
• Pytorch 2.15.0+cu132
• Datasets 5.2.0
• Tokenizers 0.23.3