indobert-squad-id

This model is a fine-tuned version of indobenchmark/indobert-base-p1 on the squad_id dataset. It achieves the following results on the evaluation set:

• Loss: 1.3745
• Exact Match: 45.3610
• F1: 62.8420

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: cosine
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Exact Match	F1
1.606	1.0	8211	1.4018	40.7895	57.0764
1.3641	2.0	16422	1.3417	44.2645	61.5786
1.0025	3.0	24633	1.3745	45.3610	62.8420

Framework versions

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