[2026-01-07 17:52:59,419][fusion_bench.programs.fusion_program][INFO] - Running the model fusion program.
[2026-01-07 17:52:59,422][fusion_bench.programs.fusion_program][INFO] - loading model pool
[2026-01-07 17:53:01,536][fusion_bench.programs.fusion_program][INFO] - loading method
[2026-01-07 17:53:01,591][fusion_bench.method.classification.image_classification_finetune][INFO] - Training interval: step
[2026-01-07 17:53:01,592][fusion_bench.method.classification.image_classification_finetune][INFO] - Max epochs: -1, max steps: 4000
[2026-01-07 17:53:01,593][fusion_bench.programs.fusion_program][INFO] - loading task pool
[2026-01-07 17:53:03,190][fusion_bench.method.classification.image_classification_finetune][INFO] - Number of classes for dataset mnist: 10
[2026-01-07 17:53:03,203][datasets.load][WARNING] - Using the latest cached version of the dataset since mnist couldn't be found on the Hugging Face Hub (offline mode is enabled).
[2026-01-07 17:53:03,211][datasets.packaged_modules.cache.cache][WARNING] - Found the latest cached dataset configuration 'mnist' at /data/dataset/datasets/mnist/mnist/0.0.0/77f3279092a1c1579b2250db8eafed0ad422088c (last modified on Mon Jan  5 04:21:12 2026).
[2026-01-07 17:53:03,516][fusion_bench.method.classification.image_classification_finetune][INFO] - Training dataset size: 60000
[2026-01-07 17:53:03,540][datasets.load][WARNING] - Using the latest cached version of the dataset since mnist couldn't be found on the Hugging Face Hub (offline mode is enabled).
[2026-01-07 17:53:03,547][datasets.packaged_modules.cache.cache][WARNING] - Found the latest cached dataset configuration 'mnist' at /data/dataset/datasets/mnist/mnist/0.0.0/77f3279092a1c1579b2250db8eafed0ad422088c (last modified on Mon Jan  5 04:21:12 2026).
[2026-01-07 17:53:03,615][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
)
[2026-01-07 18:31:07,790][fusion_bench.method.classification.image_classification_finetune][INFO] - Saving the final model to outputs/convnext-base-224/mnist/batch_size=64,lr=0.01/raw_checkpoints/final