{
  "global_step": 20000,
  "effective_global_batch": 32,
  "pretrained_model": "robotics-diffusion-transformer/rdt-1b",
  "model_report": {
    "trainable": 1223595136,
    "total": 1251662976,
    "percentage": 97.75755610430392,
    "finetune_mode": "full",
    "qwen_fusion": "fastthinkact_state_kv",
    "rdt_state_dim": 128,
    "state_adaptor_frozen": true,
    "condition_adaptors_frozen": true,
    "native_state_encoder": true,
    "native_action_encoder": true,
    "action_adaptor_trainable": false,
    "lora_target_count": 0,
    "pretrained": {
      "copied_tensors": 617,
      "partially_copied_tensors": 1,
      "skipped_shape": 0,
      "state_adaptor_copied_tensors": 6,
      "state_adaptor_target_tensors": 6,
      "missing_after_partial_load": 0,
      "unexpected_after_partial_load": 0
    },
    "base_artifact": null
  },
  "horizon_loss_weights": null,
  "mask_noisy_gripper_input": false,
  "training_objective": {
    "horizon_loss_weights": null,
    "mask_noisy_gripper_input": false,
    "gripper_bce_weight": 0.0,
    "gripper_bce_logit_scale": 1.0,
    "rotation_geodesic_weight": 0.0
  },
  "config": {
    "seed": 42,
    "rdt_repo": "/home/ubuntu/RoboticsDiffusionTransformer",
    "pretrained_model": "robotics-diffusion-transformer/rdt-1b",
    "output_dir": "/home/ubuntu/ThinkFlow-RDT-1B/output_2",
    "model": {
      "action_dim": 128,
      "state_dim": 128,
      "pred_horizon": 64,
      "qwen_hidden_size": 2560,
      "qwen_kv_dim": 2048,
      "lang_token_dim": 4096,
      "img_token_dim": 1152,
      "max_lang_tokens": 128,
      "image_tokens": 4374,
      "hidden_size": 2048,
      "depth": 28,
      "num_heads": 32,
      "dtype": "bfloat16",
      "lang_adaptor": "mlp2x_gelu",
      "img_adaptor": "mlp2x_gelu",
      "state_adaptor": "mlp3x_gelu",
      "copy_pretrained_final_fc1": true,
      "gradient_checkpointing": false,
      "finetune_mode": "full",
      "qwen_fusion": "fastthinkact_state_kv",
      "rdt_state_dim": 128,
      "freeze_state_adaptor": true,
      "freeze_condition_adaptors": true,
      "state_encoder_layout": "rdt_native_128",
      "action_encoder_layout": "rdt_native_128",
      "convert_cached_gripper_closed_to_open": false,
      "allow_random_frozen_state_adaptor": false,
      "pretrained_copy_mode": "compatible",
      "cache_state_dim": 7,
      "cache_action_dim": 7
    },
    "lora": {
      "rank": 32,
      "alpha": 64,
      "dropout": 0.05,
      "target_self_attention": true,
      "target_cross_attention": true,
      "target_ffn": true,
      "train_final_layer": true
    },
    "noise_scheduler": {
      "num_train_timesteps": 1000,
      "num_inference_timesteps": 5,
      "beta_schedule": "squaredcos_cap_v2",
      "prediction_type": "sample",
      "clip_sample": false
    },
    "data": {
      "train_manifest": "/home/ubuntu/ThinkFlow-RDT-1B/output_2/manifests/train_manifest.jsonl",
      "val_manifest": "/home/ubuntu/ThinkFlow-RDT-1B/output_2/manifests/val_manifest.jsonl",
      "num_workers": 4,
      "pin_memory": true,
      "persistent_workers": true,
      "excluded_dataset_ids": [],
      "episode_aware_shuffle": true,
      "shuffle_validation": false,
      "stratified_validation": true,
      "action_stats_paths": {
        "bc_z": "dataset/mock_dataset/bc_z_dataset/audit.json",
        "bridge": "dataset/mock_dataset/bridge_dataset/audit.json",
        "droid": "dataset/mock_dataset/droid_dataset/audit.json",
        "fractal": "dataset/mock_dataset/fractal_dataset/audit.json",
        "kuka": "dataset/mock_dataset/kuka_dataset/audit.json"
      }
    },
    "training": {
      "max_steps": 20000,
      "micro_batch_size": 8,
      "gradient_accumulation_steps": 4,
      "learning_rate_lora": 0.0001,
      "learning_rate_interfaces": 0.0001,
      "weight_decay_interfaces": 0.01,
      "warmup_steps": 500,
      "max_grad_norm": 1.0,
      "log_every": 10,
      "validate_every": 500,
      "save_every": 1000,
      "validation_batches": 256,
      "sample_validation_batches": 1,
      "mixed_precision": "bf16",
      "report_to": "wandb",
      "global_batch_size": 32,
      "learning_rate": 0.0001,
      "wandb_project": "ThinkLite B0 OXE",
      "wandb_run_name": "oxe-rdt1b-native128-fastthinkact-full",
      "validation_seed": 12345,
      "validation_samples": 256,
      "skip_nonfinite_updates": true,
      "max_consecutive_nonfinite_updates": 10,
      "log_gradient_stats": true,
      "qualitative_validation_examples": 2
    }
  }
}