signet

This model is a fine-tuned version of on the imagefolder dataset. It achieves the following results on the evaluation set:

• Loss: 0.4517
• Accuracy: 0.7854
• F1: 0.8643

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: 0.0002
• train_batch_size: 128
• eval_batch_size: 256
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 512
• 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: 0.05
• num_epochs: 12
• mixed_precision_training: Native AMP
• label_smoothing_factor: 0.05

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
No log	1.0	37	0.5892	0.7383	0.8479
No log	2.0	74	0.5829	0.7372	0.8464
2.4270	3.0	111	0.5547	0.7419	0.8504
2.4270	4.0	148	0.5311	0.7344	0.8415
2.4270	5.0	185	0.5291	0.7404	0.8472
2.1988	6.0	222	0.5170	0.7432	0.8496
2.1988	7.0	259	0.4517	0.7854	0.8643
2.1988	8.0	296	0.4865	0.7653	0.8406
1.9616	9.0	333	0.4380	0.7875	0.8614
1.9616	10.0	370	0.4546	0.7698	0.8367
1.7220	11.0	407	0.4355	0.7901	0.8552
1.7220	12.0	444	0.4334	0.7963	0.8622

Framework versions

• Transformers 5.0.0
• Pytorch 2.9.0+cu128
• Datasets 4.0.0
• Tokenizers 0.22.2