{
  "batch_size": 256,
  "dataset": {
    "episodes": null,
    "image_transforms": {
      "enable": false,
      "max_num_transforms": 3,
      "random_order": false,
      "tfs": {
        "brightness": {
          "kwargs": {
            "brightness": [
              0.8,
              1.2
            ]
          },
          "type": "ColorJitter",
          "weight": 1.0
        },
        "contrast": {
          "kwargs": {
            "contrast": [
              0.8,
              1.2
            ]
          },
          "type": "ColorJitter",
          "weight": 1.0
        },
        "hue": {
          "kwargs": {
            "hue": [
              -0.05,
              0.05
            ]
          },
          "type": "ColorJitter",
          "weight": 1.0
        },
        "saturation": {
          "kwargs": {
            "saturation": [
              0.5,
              1.5
            ]
          },
          "type": "ColorJitter",
          "weight": 1.0
        },
        "sharpness": {
          "kwargs": {
            "sharpness": [
              0.5,
              1.5
            ]
          },
          "type": "SharpnessJitter",
          "weight": 1.0
        }
      }
    },
    "repo_id": "imstevenpmwork/thanos_picking_power_gem_1749731584242992",
    "revision": null,
    "root": null,
    "use_imagenet_stats": true,
    "video_backend": "torchcodec"
  },
  "device": "cuda",
  "job_name": "nanovla_main",
  "log_freq": 20,
  "policy": {
    "adapt_to_pi_aloha": false,
    "add_image_special_tokens": false,
    "attention_mode": "cross_attn",
    "chunk_size": 50,
    "device": "cuda",
    "empty_cameras": 0,
    "expert_width_multiplier": 0.75,
    "freeze_vision_encoder": true,
    "input_features": {},
    "license": null,
    "load_vlm_weights": false,
    "max_action_dim": 32,
    "max_period": 4.0,
    "max_state_dim": 32,
    "min_period": 0.004,
    "n_action_steps": 50,
    "n_obs_steps": 1,
    "normalization_mapping": {
      "ACTION": "MEAN_STD",
      "STATE": "MEAN_STD",
      "VISUAL": "IDENTITY"
    },
    "num_expert_layers": -1,
    "num_steps": 10,
    "num_vlm_layers": 16,
    "optimizer_betas": [
      0.9,
      0.95
    ],
    "optimizer_eps": 1e-08,
    "optimizer_grad_clip_norm": 10,
    "optimizer_lr": 0.0001,
    "optimizer_weight_decay": 1e-10,
    "output_features": {},
    "pad_language_to": "longest",
    "prefix_length": -1,
    "private": null,
    "push_to_hub": true,
    "repo_id": "smol_vla_special",
    "resize_imgs_with_padding": [
      512,
      512
    ],
    "scheduler_decay_lr": 2.5e-06,
    "scheduler_decay_steps": 30000,
    "scheduler_warmup_steps": 1000,
    "self_attn_every_n_layers": 2,
    "tags": null,
    "tokenizer_max_length": 48,
    "train_expert_only": true,
    "train_state_proj": true,
    "use_amp": false,
    "use_cache": true,
    "use_delta_joint_actions_aloha": false,
    "vlm_model_name": "HuggingFaceTB/SmolVLM2-500M-Video-Instruct"
  },
  "steps": 100,
  "torch_compile": false,
  "wandb": {
    "disable_artifact": false,
    "enable": true,
    "entity": null,
    "mode": null,
    "notes": null,
    "project": "lerobot",
    "run_id": null
  }
}