BxSD-finetuned-Real_RGBCROP_Aug16F-8B16F-GACWDlr

This model is a fine-tuned version of TanAlexanderlz/BxSD_RGBCROP_Aug16F-8B16F-GACWDlr on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.6475
• Accuracy: 0.7810

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: 1e-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 with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• training_steps: 3520

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.4829	0.025	88	0.7656	0.67
0.3096	1.025	176	0.6833	0.69
0.1399	2.025	264	0.8448	0.72
0.0227	3.025	352	1.3403	0.71
0.0054	4.025	440	1.4998	0.7133
0.0007	5.025	528	1.7194	0.6967
0.0004	6.025	616	1.7670	0.71
0.0002	7.025	704	1.8450	0.7033

Framework versions

• Transformers 4.51.3
• Pytorch 2.6.0+cu124
• Datasets 3.6.0
• Tokenizers 0.21.1