| { |
| "dataset": { |
| "repo_id": "RoboDojo-Benchmark/RoboDojo", |
| "root": "/lustre/fsw/portfolios/nvr/projects/nvr_elm_llm/users/zekail/data/RoboDojo/data/RoboDojo_lerobot_v30_video", |
| "episodes": null, |
| "image_transforms": { |
| "enable": false, |
| "max_num_transforms": 3, |
| "random_order": false, |
| "tfs": { |
| "brightness": { |
| "weight": 1.0, |
| "type": "ColorJitter", |
| "kwargs": { |
| "brightness": [ |
| 0.8, |
| 1.2 |
| ] |
| } |
| }, |
| "contrast": { |
| "weight": 1.0, |
| "type": "ColorJitter", |
| "kwargs": { |
| "contrast": [ |
| 0.8, |
| 1.2 |
| ] |
| } |
| }, |
| "saturation": { |
| "weight": 1.0, |
| "type": "ColorJitter", |
| "kwargs": { |
| "saturation": [ |
| 0.5, |
| 1.5 |
| ] |
| } |
| }, |
| "hue": { |
| "weight": 1.0, |
| "type": "ColorJitter", |
| "kwargs": { |
| "hue": [ |
| -0.05, |
| 0.05 |
| ] |
| } |
| }, |
| "sharpness": { |
| "weight": 1.0, |
| "type": "SharpnessJitter", |
| "kwargs": { |
| "sharpness": [ |
| 0.5, |
| 1.5 |
| ] |
| } |
| }, |
| "affine": { |
| "weight": 1.0, |
| "type": "RandomAffine", |
| "kwargs": { |
| "degrees": [ |
| -5.0, |
| 5.0 |
| ], |
| "translate": [ |
| 0.05, |
| 0.05 |
| ] |
| } |
| } |
| } |
| }, |
| "revision": null, |
| "use_imagenet_stats": true, |
| "video_backend": "torchcodec", |
| "streaming": false |
| }, |
| "env": null, |
| "policy": { |
| "type": "pi05", |
| "n_obs_steps": 1, |
| "input_features": { |
| "observation.state": { |
| "type": "STATE", |
| "shape": [ |
| 14 |
| ] |
| }, |
| "observation.images.cam_high": { |
| "type": "VISUAL", |
| "shape": [ |
| 3, |
| 480, |
| 640 |
| ] |
| }, |
| "observation.images.cam_left_wrist": { |
| "type": "VISUAL", |
| "shape": [ |
| 3, |
| 480, |
| 640 |
| ] |
| }, |
| "observation.images.cam_right_wrist": { |
| "type": "VISUAL", |
| "shape": [ |
| 3, |
| 480, |
| 640 |
| ] |
| } |
| }, |
| "output_features": { |
| "action": { |
| "type": "ACTION", |
| "shape": [ |
| 14 |
| ] |
| } |
| }, |
| "device": "cuda", |
| "use_amp": false, |
| "use_peft": false, |
| "push_to_hub": false, |
| "repo_id": null, |
| "private": null, |
| "tags": null, |
| "license": null, |
| "pretrained_path": "/lustre/fsw/portfolios/nvr/projects/nvr_elm_llm/users/zekail/outputs/pi05_robodojo_baseline_50k_gc_fresh/checkpoints/last/pretrained_model", |
| "paligemma_variant": "gemma_2b", |
| "action_expert_variant": "gemma_300m", |
| "dtype": "bfloat16", |
| "chunk_size": 50, |
| "n_action_steps": 16, |
| "max_state_dim": 32, |
| "max_action_dim": 32, |
| "state_cond": false, |
| "num_inference_steps": 10, |
| "time_sampling_beta_alpha": 1.5, |
| "time_sampling_beta_beta": 1.0, |
| "time_sampling_scale": 0.999, |
| "time_sampling_offset": 0.001, |
| "min_period": 0.004, |
| "max_period": 4.0, |
| "image_resolution": [ |
| 224, |
| 224 |
| ], |
| "empty_cameras": 0, |
| "num_frames_per_view": 1, |
| "tokenizer_max_length": 200, |
| "normalization_mapping": { |
| "VISUAL": "IDENTITY", |
| "STATE": "QUANTILES", |
| "ACTION": "QUANTILES" |
| }, |
| "attention_backend": "sdpa", |
| "gradient_checkpointing": true, |
| "freeze_vision_encoder": false, |
| "compile_model": false, |
| "compile_mode": "max-autotune", |
| "fuse_qkv": false, |
| "fuse_gate_up": false, |
| "optimizer_lr": 2.5e-05, |
| "optimizer_betas": [ |
| 0.9, |
| 0.95 |
| ], |
| "optimizer_eps": 1e-08, |
| "optimizer_weight_decay": 0.01, |
| "optimizer_grad_clip_norm": 1.0, |
| "scheduler_warmup_steps": 1000, |
| "scheduler_decay_steps": 30000, |
| "scheduler_decay_lr": 2.5e-06, |
| "vlm_config": {}, |
| "action_expert_config": {} |
| }, |
| "output_dir": "/lustre/fsw/portfolios/nvr/projects/nvr_elm_llm/users/zekail/outputs/pi05_robodojo_baseline_50k_gc_fresh", |
| "job_name": "pi05_robodojo_baseline_50k_gc_fresh", |
| "resume": true, |
| "seed": 1000, |
| "cudnn_deterministic": false, |
| "num_workers": 8, |
| "batch_size": 16, |
| "steps": 50000, |
| "eval_freq": 20000, |
| "log_freq": 50, |
| "tolerance_s": 0.0001, |
| "save_checkpoint": true, |
| "save_freq": 500, |
| "use_policy_training_preset": false, |
| "optimizer": { |
| "type": "adamw", |
| "lr": 1e-05, |
| "weight_decay": 0.01, |
| "grad_clip_norm": 1.0, |
| "betas": [ |
| 0.9, |
| 0.95 |
| ], |
| "eps": 1e-08 |
| }, |
| "scheduler": { |
| "type": "cosine_decay_with_warmup", |
| "num_warmup_steps": 1000, |
| "num_decay_steps": 50000, |
| "peak_lr": 1e-05, |
| "decay_lr": 1e-05 |
| }, |
| "eval": { |
| "n_episodes": 50, |
| "batch_size": 50, |
| "use_async_envs": false |
| }, |
| "wandb": { |
| "enable": true, |
| "disable_artifact": true, |
| "project": "flashvla-robodojo", |
| "entity": null, |
| "notes": null, |
| "run_id": "bbbzwr5x", |
| "mode": null, |
| "add_tags": true |
| }, |
| "peft": null, |
| "use_rabc": false, |
| "rabc_progress_path": null, |
| "rabc_kappa": 0.01, |
| "rabc_epsilon": 1e-06, |
| "rabc_head_mode": "sparse", |
| "rename_map": {}, |
| "checkpoint_path": "/lustre/fsw/portfolios/nvr/projects/nvr_elm_llm/users/zekail/outputs/pi05_robodojo_baseline_50k_gc_fresh/checkpoints/last", |
| "grad_accum_steps": 2, |
| "fsdp": { |
| "enable": true, |
| "mixed_precision": "bf16", |
| "reduce_dtype": "float32", |
| "reshard_after_forward": true, |
| "cpu_offload": false, |
| "state_dict_type": "SHARDED_STATE_DICT", |
| "save_pretrained_max_shard_size": "50GB" |
| }, |
| "robotwin_multitask": { |
| "enable": false, |
| "roots": [], |
| "root": "", |
| "config_subdir": "aloha-agilex_randomized_500", |
| "config_subdirs": [], |
| "tasks": [], |
| "stats_path": "" |
| }, |
| "flashvla_init": { |
| "mode": "default", |
| "include_final_norm": true, |
| "reset_time_mlp": true, |
| "time_mlp_init": "random", |
| "action_expert_norm_init": "zero" |
| }, |
| "checkpoint_keep_last": 3, |
| "checkpoint_keep_every_n_steps": 0 |
| } |
