cpus_per_task: 16
eval_name: image_classification_frozen
folder: /your_folder/evals/vitl/in1k
mem_per_gpu: 220G
nodes: 8
resume_checkpoint: true
tag: in1k-vitl16-384-18f
tasks_per_node: 8
experiment:
  classifier:
    num_heads: 16
    num_probe_blocks: 4
  data:
    dataset_name: ImageNet
    num_classes: 1000
    root_path: /your_data_path/ImageNet_FullSize/240712/061417/
    resolution: 256
  optimization:
    batch_size: 16
    multihead_kwargs:
    - final_lr: 0.0
      final_weight_decay: 0.0
      lr: 0.001
      start_lr: 0.001
      warmup: 0.0
      weight_decay: 0.001
    - final_lr: 0.0
      final_weight_decay: 0.008
      lr: 0.0005
      start_lr: 0.0002
      warmup: 5
      weight_decay: 0.008
    - final_lr: 0.0
      final_weight_decay: 0.004
      lr: 0.0005
      start_lr: 0.0002
      warmup: 5
      weight_decay: 0.004
    - final_lr: 0.0
      final_weight_decay: 0.002
      lr: 0.0005
      start_lr: 0.0002
      warmup: 5
      weight_decay: 0.002
    - final_lr: 0.0
      final_weight_decay: 0.001
      lr: 0.0005
      start_lr: 0.0002
      warmup: 5
      weight_decay: 0.001
    - final_lr: 0.0
      final_weight_decay: 0.0005
      lr: 0.0005
      start_lr: 0.0002
      warmup: 5
      weight_decay: 0.0005
    - final_lr: 0.0
      final_weight_decay: 0.008
      lr: 0.001
      start_lr: 0.0002
      warmup: 5
      weight_decay: 0.008
    - final_lr: 0.0
      final_weight_decay: 0.004
      lr: 0.001
      start_lr: 0.0002
      warmup: 5
      weight_decay: 0.004
    - final_lr: 0.0
      final_weight_decay: 0.002
      lr: 0.001
      start_lr: 0.0002
      warmup: 5
      weight_decay: 0.002
    - final_lr: 0.0
      final_weight_decay: 0.001
      lr: 0.001
      start_lr: 0.0002
      warmup: 5
      weight_decay: 0.001
    - final_lr: 0.0
      final_weight_decay: 0.0005
      lr: 0.001
      start_lr: 0.0002
      warmup: 5
      weight_decay: 0.0005
    - final_lr: 0.0
      final_weight_decay: 0.008
      lr: 0.0015
      start_lr: 0.0002
      warmup: 5
      weight_decay: 0.008
    - final_lr: 0.0
      final_weight_decay: 0.004
      lr: 0.0015
      start_lr: 0.0002
      warmup: 5
      weight_decay: 0.004
    - final_lr: 0.0
      final_weight_decay: 0.002
      lr: 0.0015
      start_lr: 0.0002
      warmup: 5
      weight_decay: 0.002
    - final_lr: 0.0
      final_weight_decay: 0.001
      lr: 0.0015
      start_lr: 0.0002
      warmup: 5
      weight_decay: 0.001
    - final_lr: 0.0
      final_weight_decay: 0.0005
      lr: 0.0015
      start_lr: 0.0002
      warmup: 5
      weight_decay: 0.0005
    - final_lr: 0.0
      final_weight_decay: 0.008
      lr: 0.002
      start_lr: 0.0002
      warmup: 5
      weight_decay: 0.008
    - final_lr: 0.0
      final_weight_decay: 0.004
      lr: 0.002
      start_lr: 0.0002
      warmup: 5
      weight_decay: 0.004
    - final_lr: 0.0
      final_weight_decay: 0.002
      lr: 0.002
      start_lr: 0.0002
      warmup: 5
      weight_decay: 0.002
    - final_lr: 0.0
      final_weight_decay: 0.001
      lr: 0.002
      start_lr: 0.0002
      warmup: 5
      weight_decay: 0.001
    - final_lr: 0.0
      final_weight_decay: 0.0005
      lr: 0.002
      start_lr: 0.0002
      warmup: 5
      weight_decay: 0.0005
    num_epochs: 20
    use_bfloat16: true
model_kwargs:
  checkpoint: /your_vjepa2_checkpoints/vitl.pt
  module_name: evals.image_classification_frozen.modelcustom.vit_encoder
  pretrain_kwargs:
    encoder:
      checkpoint_key: target_encoder
      img_temporal_dim_size: null
      model_name: vit_large
      patch_size: 16
      tubelet_size: 2
      uniform_power: true
      use_rope: true
  wrapper_kwargs:
    img_as_video_nframes: 16