hiera-finetuned-busi

This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.1380
• Accuracy: 0.9679
• F1: 0.9678
• Precision: 0.9678
• Recall: 0.9679

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: 8
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 64
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine_with_restarts
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 48
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision	Recall
0.2276	10.0	100	0.1666	0.9615	0.9611	0.9640	0.9615
0.1447	20.0	200	0.1826	0.9359	0.9352	0.9426	0.9359
0.0882	30.0	300	0.1612	0.9615	0.9612	0.9613	0.9615
0.0606	40.0	400	0.1380	0.9679	0.9678	0.9678	0.9679

Framework versions

• Transformers 4.53.1
• Pytorch 2.7.1+cu126
• Datasets 3.6.0
• Tokenizers 0.21.2