tanganke
/

convnext-base-224_resisc45_sgd_batch-size-64_lr-0.01_steps-4000

Image Classification

Model card Files Files and versions

Metrics Training metrics Community

convnext-base-224_resisc45_sgd_batch-size-64_lr-0.01_steps-4000 / cli.log

tanganke's picture

Upload folder using huggingface_hub

aa79212 verified 9 months ago

History Blame Contribute Delete

1.42 kB

	[2026-01-05 22:18:56,613][fusion_bench.programs.fusion_program][INFO] - Running the model fusion program.
	[2026-01-05 22:18:56,616][fusion_bench.programs.fusion_program][INFO] - loading model pool
	[2026-01-05 22:18:59,043][fusion_bench.programs.fusion_program][INFO] - loading method
	[2026-01-05 22:18:59,108][fusion_bench.method.classification.image_classification_finetune][INFO] - Training interval: step
	[2026-01-05 22:18:59,109][fusion_bench.method.classification.image_classification_finetune][INFO] - Max epochs: -1, max steps: 4000
	[2026-01-05 22:18:59,110][fusion_bench.programs.fusion_program][INFO] - loading task pool
	[2026-01-05 22:19:01,585][fusion_bench.method.classification.image_classification_finetune][INFO] - Number of classes for dataset resisc45: 45
	[2026-01-05 22:19:05,201][fusion_bench.method.classification.image_classification_finetune][INFO] - Training dataset size: 18900
	[2026-01-05 22:19:07,683][fusion_bench.method.classification.image_classification_finetune][INFO] - optimizer:
	SGD (
	Parameter Group 0
	dampening: 0
	differentiable: False
	foreach: None
	fused: None
	lr: 0.01
	maximize: False
	momentum: 0.9
	nesterov: False
	weight_decay: 0.0001
	)
	[2026-01-05 22:58:09,348][fusion_bench.method.classification.image_classification_finetune][INFO] - Saving the final model to outputs/convnext-base-224/resisc45/batch_size=64,lr=0.01/raw_checkpoints/final