{ "dataset": { "repo_id": "maximellerbach/omx_multicubes", "repo_type": "dataset", "root": null, "episodes": null, "exclude_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": "dm05-relative-chunk50", "use_imagenet_stats": true, "video_backend": "pyav", "return_uint8": false, "depth_output_unit": "mm", "streaming": false, "eval_split": 0.0 }, "env": null, "policy": { "type": "dm05", "n_obs_steps": 1, "input_features": { "observation.state": { "type": "STATE", "shape": [ 6 ] }, "observation.images.wrist": { "type": "VISUAL", "shape": [ 3, 480, 640 ] }, "observation.images.top": { "type": "VISUAL", "shape": [ 3, 480, 640 ] } }, "output_features": { "action": { "type": "ACTION", "shape": [ 6 ] } }, "device": "cuda:0", "use_amp": false, "use_peft": false, "push_to_hub": true, "repo_id": "maximellerbach/dm05_omx_multicubes_rel", "private": null, "tags": null, "license": "gemma", "pretrained_path": "Dexmal/DM05-Lerobot", "pretrained_revision": null, "core_config": { "vlm_gradient_checkpointing": true, "ae_gradient_checkpointing": true, "ae_gradient_checkpointing_layers": 1, "freeze_vlm_embedding": false, "llm_attn_implementation": "eager", "vision_attn_implementation": "sdpa", "action_attn_implementation": "sdpa", "transformers_version": "5.5.4", "architectures": [ "DM05ForConditionalGeneration" ], "output_hidden_states": false, "return_dict": true, "dtype": "bfloat16", "chunk_size_feed_forward": 0, "is_encoder_decoder": false, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "problem_type": null, "vlm_config": { "architectures": [ "Gemma3ForConditionalGeneration" ], "output_hidden_states": false, "return_dict": true, "dtype": "bfloat16", "chunk_size_feed_forward": 0, "is_encoder_decoder": false, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "problem_type": null, "text_config": { "architectures": null, "output_hidden_states": false, "return_dict": true, "dtype": "bfloat16", "chunk_size_feed_forward": 0, "is_encoder_decoder": false, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "problem_type": null, "vocab_size": 262208, "hidden_size": 2560, "intermediate_size": 10240, "num_hidden_layers": 34, "num_attention_heads": 8, "num_key_value_heads": 4, "head_dim": 256, "hidden_activation": "gelu_pytorch_tanh", "max_position_embeddings": 131072, "initializer_range": 0.02, "rms_norm_eps": 1e-06, "use_cache": true, "pad_token_id": 0, "eos_token_id": 1, "bos_token_id": 2, "tie_word_embeddings": true, "rope_parameters": { "full_attention": { "factor": 8.0, "rope_theta": 1000000.0, "rope_type": "linear" }, "sliding_attention": { "rope_theta": 10000.0, "rope_type": "default" } }, "attention_bias": false, "attention_dropout": 0.0, "query_pre_attn_scalar": 256, "sliding_window": 4096, "layer_types": [ "sliding_attention", "sliding_attention", "sliding_attention", "sliding_attention", "sliding_attention", "full_attention", "sliding_attention", "sliding_attention", "sliding_attention", "sliding_attention", "sliding_attention", "full_attention", "sliding_attention", "sliding_attention", "sliding_attention", "sliding_attention", "sliding_attention", "full_attention", "sliding_attention", "sliding_attention", "sliding_attention", "sliding_attention", "sliding_attention", "full_attention", "sliding_attention", "sliding_attention", "sliding_attention", "sliding_attention", "sliding_attention", "full_attention", "sliding_attention", "sliding_attention", "sliding_attention", "sliding_attention" ], "final_logit_softcapping": null, "attn_logit_softcapping": null, "use_bidirectional_attention": false, "_sliding_window_pattern": 6, "_name_or_path": "", "model_type": "gemma3_text", "attn_implementation": "eager", "output_attentions": false }, "vision_config": { "architectures": null, "output_hidden_states": false, "return_dict": true, "dtype": "bfloat16", "chunk_size_feed_forward": 0, "is_encoder_decoder": false, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "problem_type": null, "hidden_size": 1152, "intermediate_size": 4304, "num_hidden_layers": 27, "num_attention_heads": 16, "num_channels": 3, "image_size": 448, "patch_size": 14, "hidden_act": "gelu_pytorch_tanh", "layer_norm_eps": 1e-06, "attention_dropout": 0.0, "_name_or_path": "", "model_type": "siglip_vision_model", "vision_use_head": false, "attn_implementation": "sdpa", "output_attentions": false }, "mm_tokens_per_image": 256, "boi_token_index": 255999, "eoi_token_index": 256000, "image_token_index": 262144, "initializer_range": 0.02, "tie_word_embeddings": true, "_name_or_path": "", "eos_token_id": [ 1, 106 ], "model_type": "gemma3", "attn_implementation": { "": "eager", "text_config": "eager", "vision_config": "sdpa" }, "output_attentions": false }, "action_config": { "architectures": null, "output_hidden_states": false, "return_dict": true, "dtype": null, "chunk_size_feed_forward": 0, "is_encoder_decoder": false, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "problem_type": null, "vocab_size": 262208, "hidden_size": 1024, "intermediate_size": 4096, "num_hidden_layers": 34, "num_attention_heads": 8, "num_key_value_heads": 4, "head_dim": 256, "hidden_activation": "gelu_pytorch_tanh", "max_position_embeddings": 131072, "initializer_range": 0.02, "rms_norm_eps": 1e-06, "use_cache": true, "pad_token_id": 0, "eos_token_id": 1, "bos_token_id": 2, "tie_word_embeddings": true, "rope_parameters": { "full_attention": { "factor": 8.0, "rope_theta": 1000000.0, "rope_type": "linear" }, "sliding_attention": { "rope_theta": 10000.0, "rope_type": "default" } }, "attention_bias": false, "attention_dropout": 0.0, "query_pre_attn_scalar": 256, "sliding_window": 4096, "layer_types": [ "sliding_attention", "sliding_attention", "sliding_attention", "sliding_attention", "sliding_attention", "full_attention", "sliding_attention", "sliding_attention", "sliding_attention", "sliding_attention", "sliding_attention", "full_attention", "sliding_attention", "sliding_attention", "sliding_attention", "sliding_attention", "sliding_attention", "full_attention", "sliding_attention", "sliding_attention", "sliding_attention", "sliding_attention", "sliding_attention", "full_attention", "sliding_attention", "sliding_attention", "sliding_attention", "sliding_attention", "sliding_attention", "full_attention", "sliding_attention", "sliding_attention", "sliding_attention", "sliding_attention" ], "final_logit_softcapping": null, "attn_logit_softcapping": null, "use_bidirectional_attention": false, "_sliding_window_pattern": 6, "_name_or_path": "", "model_type": "gemma3_text", "attn_implementation": "sdpa", "action_attn_implementation": "sdpa", "ae_gradient_checkpointing_layers": 1, "output_attentions": false }, "processor_config": null, "action_dim": 32, "chunk_size": 50, "bf16": true, "_name_or_path": ".", "bos_token_id": 2, "eos_token_id": 1, "model_type": "dexbotic_dm05", "pad_token_id": 0, "tie_word_embeddings": true, "gradient_checkpointing": true, "output_attentions": false }, "chunk_size": 50, "n_action_steps": 50, "drop_n_last_frames": 1, "max_state_dim": 32, "max_action_dim": 32, "image_resolution": [ 448, 448 ], "empty_cameras": 0, "add_state": true, "pretrained_name_or_path": ".", "processor_name_or_path": null, "image_keys": null, "n_bins": 256, "tokenizer_max_length": 1024, "diffusion_steps": 10, "compile_model": false, "compile_suffix_pad_length": 1024, "llm_attn_implementation": "eager", "vision_attn_implementation": "sdpa", "action_attn_implementation": "sdpa", "use_liger_kernel": false, "dtype": "bfloat16", "vlm_gradient_checkpointing": true, "ae_gradient_checkpointing": true, "ae_gradient_checkpointing_layers": 1, "freeze_vlm_embedding": true, "use_relative_actions": true, "relative_exclude_joints": [ "gripper" ], "action_feature_names": [ "shoulder_pan.pos", "shoulder_lift.pos", "elbow_flex.pos", "wrist_flex.pos", "wrist_roll.pos", "gripper.pos" ], "norm_clip": true, "normalization_mapping": { "VISUAL": "IDENTITY", "STATE": "QUANTILES", "ACTION": "QUANTILES" }, "optimizer_lr": 2.5e-05, "optimizer_betas": [ 0.9, 0.95 ], "optimizer_eps": 1e-08, "optimizer_weight_decay": 1e-10, "optimizer_grad_clip_norm": 1.0, "scheduler_warmup_steps": 500, "scheduler_decay_steps": 10000, "scheduler_decay_lr": 2.5e-06 }, "reward_model": null, "output_dir": "/tmp/train/dm05_omx_multicubes_rel", "job_name": "dm05_omx_multicubes_rel", "resume": false, "seed": 1000, "cudnn_deterministic": false, "num_workers": 8, "batch_size": 4, "prefetch_factor": 4, "persistent_workers": true, "dataloader_multiprocessing_context": "spawn", "steps": 10000, "env_eval_freq": 20000, "log_freq": 25, "eval_steps": 0, "max_eval_samples": 0, "tolerance_s": 0.0001, "save_checkpoint": true, "save_freq": 5000, "checkpoint_format": "safetensors", "use_policy_training_preset": true, "optimizer": { "type": "adamw", "lr": 2.5e-05, "weight_decay": 1e-10, "grad_clip_norm": 1.0, "betas": [ 0.9, 0.95 ], "eps": 1e-08 }, "scheduler": { "type": "cosine_decay_with_warmup", "num_warmup_steps": 500, "num_decay_steps": 10000, "peak_lr": 2.5e-05, "decay_lr": 2.5e-06 }, "parallelism": { "dp_replicate": 1, "dp_shard": 1, "context_parallel": { "ring_degree": 1, "ulysses_degree": 1 }, "cfg_parallel": 1 }, "accelerator": { "mixed_precision": "no", "gradient_accumulation": { "steps": 1 }, "fsdp": { "reshard_after_forward": true, "wrap_modules": null, "min_num_params": null, "cpu_offload": false, "ignored_modules": null }, "ddp": { "find_unused_parameters": true, "gradient_as_bucket_view": false, "static_graph": false }, "compile": { "enabled": false, "backend": "inductor", "mode": null, "regional": true }, "activation_checkpointing": { "mode": "none" } }, "eval": { "n_episodes": 50, "batch_size": 50, "use_async_envs": true, "recording": false, "recording_repo_id": null, "recording_private": false }, "ema": { "enable": false, "decay": null, "update_after_step": 0, "inv_gamma": 1.0, "power": 0.75, "min_decay": 0.0, "max_decay": 0.9999, "use_for_eval": true }, "wandb": { "enable": true, "disable_artifact": true, "project": "lerobot", "entity": null, "notes": null, "run_id": "qcwvqsuq", "mode": null, "add_tags": true }, "peft": null, "job": { "target": null, "image": "huggingface/lerobot-gpu:latest", "timeout": "2d", "detach": false, "tags": [] }, "save_checkpoint_to_hub": true, "sample_weighting": null, "rename_map": {}, "checkpoint_path": null }