nodes: 8
tasks_per_node: 8
cpus_per_task: 12
tag: ek100-vitl16
eval_name: action_anticipation_frozen
folder: /your_folder/evals/vitl/ek100
resume_checkpoint: true
val_only: true
experiment:
  classifier:
    num_probe_blocks: 4
    num_heads: 16
  data:
    anticipation_time_sec:
    - 1.0
    - 1.0
    auto_augment: true
    file_format: 0
    dataset: EK100
    base_path: /your_ek100_root_dir/
    dataset_train: /your_data/EPIC_100_train.csv
    dataset_val: /your_data/EPIC_100_validation.csv
    frames_per_clip: 32
    frames_per_second: 8
    motion_shift: false
    num_workers: 2
    pin_memory: true
    random_resize_scale:
    - 0.08
    - 1.0
    reprob: 0.25
    resolution: 256
    train_anticipation_point:
    - 0.0
    - 0.25
    train_anticipation_time_sec:
    - 0.25
    - 1.75
  optimization:
    num_epochs: 20
    batch_size: 2
    use_bfloat16: true
    use_focal_loss: true
    multihead_kwargs:
      - weight_decay: 0.0
        final_weight_decay: 0.0
        lr: 0.0
        start_lr: 0.0
        final_lr: 0.0
        warmup: 0.0
model_kwargs:
  checkpoint: /your_vjepa2_checkpoints/vitl.pt
  module_name: evals.action_anticipation_frozen.modelcustom.vit_encoder_predictor_concat_ar
  wrapper_kwargs:
    no_predictor: false
    num_output_frames: 2
    num_steps: 1
  pretrain_kwargs:
    encoder:
      model_name: vit_large
      checkpoint_key: target_encoder
      tubelet_size: 2
      patch_size: 16
      uniform_power: true
      use_rope: true
    predictor:
      model_name: vit_predictor
      checkpoint_key: predictor
      num_frames: 64
      depth: 12
      num_heads: 12
      predictor_embed_dim: 384
      num_mask_tokens: 10
      uniform_power: true
      use_mask_tokens: true
      use_sdpa: true
      use_silu: false
      wide_silu: false
      use_rope: true