multi-task DiT trained 50k steps on RoboTwin

Browse files

Files changed (9) hide show

config.json +114 -0
model.safetensors +3 -0
policy_postprocessor.json +32 -0
policy_postprocessor_step_0_unnormalizer_processor.safetensors +3 -0
policy_preprocessor.json +86 -0
policy_preprocessor_step_4_normalizer_processor.safetensors +3 -0
tokenizer/tokenizer.json +0 -0
tokenizer/tokenizer_config.json +20 -0
train_config.json +295 -0

config.json ADDED Viewed

	@@ -0,0 +1,114 @@

+{
+    "type": "multi_task_dit",
+    "n_obs_steps": 2,
+    "input_features": {
+        "observation.state": {
+            "type": "STATE",
+            "shape": [
+                14
+            ]
+        },
+        "observation.images.cam_high": {
+            "type": "VISUAL",
+            "shape": [
+                480,
+                640,
+                3
+            ]
+        },
+        "observation.images.cam_left_wrist": {
+            "type": "VISUAL",
+            "shape": [
+                480,
+                640,
+                3
+            ]
+        },
+        "observation.images.cam_right_wrist": {
+            "type": "VISUAL",
+            "shape": [
+                480,
+                640,
+                3
+            ]
+        }
+    },
+    "output_features": {
+        "action": {
+            "type": "ACTION",
+            "shape": [
+                14
+            ]
+        }
+    },
+    "device": "cuda",
+    "use_amp": true,
+    "use_peft": false,
+    "push_to_hub": true,
+    "repo_id": "unitzero-ai/dit_robotwin_2026-09-29_15-41-09",
+    "private": true,
+    "tags": null,
+    "license": null,
+    "pretrained_path": "outputs/train/2026-09-30/09-34-48_dit_robotwin_2026-09-29_15-41-09/checkpoints/012000/pretrained_model",
+    "pretrained_revision": null,
+    "horizon": 32,
+    "n_action_steps": 24,
+    "objective": "diffusion",
+    "noise_scheduler_type": "DDPM",
+    "num_train_timesteps": 100,
+    "beta_schedule": "squaredcos_cap_v2",
+    "beta_start": 0.0001,
+    "beta_end": 0.02,
+    "prediction_type": "epsilon",
+    "clip_sample": true,
+    "clip_sample_range": 1.0,
+    "num_inference_steps": 10,
+    "sigma_min": 0.0,
+    "num_integration_steps": 100,
+    "integration_method": "euler",
+    "timestep_sampling_strategy": "beta",
+    "timestep_sampling_s": 0.999,
+    "timestep_sampling_alpha": 1.5,
+    "timestep_sampling_beta": 1.0,
+    "hidden_dim": 768,
+    "num_layers": 8,
+    "num_heads": 12,
+    "dropout": 0.1,
+    "use_positional_encoding": false,
+    "timestep_embed_dim": 256,
+    "use_rope": true,
+    "rope_base": 10000.0,
+    "vision_encoder_name": "openai/clip-vit-base-patch16",
+    "use_separate_rgb_encoder_per_camera": false,
+    "vision_encoder_lr_multiplier": 0.1,
+    "image_resize_shape": [
+        256,
+        256
+    ],
+    "image_crop_shape": [
+        224,
+        224
+    ],
+    "image_crop_is_random": true,
+    "text_encoder_name": "openai/clip-vit-base-patch16",
+    "tokenizer_max_length": 77,
+    "tokenizer_padding": "max_length",
+    "tokenizer_padding_side": "right",
+    "tokenizer_truncation": true,
+    "normalization_mapping": {
+        "VISUAL": "MEAN_STD",
+        "STATE": "MIN_MAX",
+        "ACTION": "MIN_MAX"
+    },
+    "optimizer_lr": 0.0003,
+    "optimizer_betas": [
+        0.95,
+        0.999
+    ],
+    "optimizer_eps": 1e-08,
+    "optimizer_weight_decay": 0.0,
+    "scheduler_name": "cosine",
+    "scheduler_warmup_steps": 0,
+    "do_mask_loss_for_padding": false,
+    "drop_n_last_frames": 7
+}

model.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:f55caf7f62ccf3b88521bcf39276c96512a4c441792fa7d4f2edf942c55a9a3b
+size 1773362776

policy_postprocessor.json ADDED Viewed

	@@ -0,0 +1,32 @@

+{
+  "name": "policy_postprocessor",
+  "steps": [
+    {
+      "registry_name": "unnormalizer_processor",
+      "config": {
+        "eps": 1e-08,
+        "features": {
+          "action": {
+            "type": "ACTION",
+            "shape": [
+              14
+            ]
+          }
+        },
+        "norm_map": {
+          "VISUAL": "MEAN_STD",
+          "STATE": "MIN_MAX",
+          "ACTION": "MIN_MAX"
+        }
+      },
+      "state_file": "policy_postprocessor_step_0_unnormalizer_processor.safetensors"
+    },
+    {
+      "registry_name": "device_processor",
+      "config": {
+        "device": "cpu",
+        "float_dtype": null
+      }
+    }
+  ]
+}

policy_postprocessor_step_0_unnormalizer_processor.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:03f5dcff1c71f45d35caa328581a195754a95b8a176ab91760ed7fed3e1e9b4e
+size 4624

policy_preprocessor.json ADDED Viewed

	@@ -0,0 +1,86 @@

+{
+  "name": "policy_preprocessor",
+  "steps": [
+    {
+      "registry_name": "rename_observations_processor",
+      "config": {
+        "rename_map": {}
+      }
+    },
+    {
+      "registry_name": "to_batch_processor",
+      "config": {}
+    },
+    {
+      "registry_name": "tokenizer_processor",
+      "config": {
+        "max_length": 77,
+        "task_key": "task",
+        "padding_side": "right",
+        "padding": "max_length",
+        "truncation": true,
+        "tokenizer_name": "tokenizer"
+      },
+      "artifacts": {
+        "tokenizer_name": "tokenizer"
+      }
+    },
+    {
+      "registry_name": "device_processor",
+      "config": {
+        "device": "cuda",
+        "float_dtype": null
+      }
+    },
+    {
+      "registry_name": "normalizer_processor",
+      "config": {
+        "eps": 1e-08,
+        "features": {
+          "observation.state": {
+            "type": "STATE",
+            "shape": [
+              14
+            ]
+          },
+          "observation.images.cam_high": {
+            "type": "VISUAL",
+            "shape": [
+              480,
+              640,
+              3
+            ]
+          },
+          "observation.images.cam_left_wrist": {
+            "type": "VISUAL",
+            "shape": [
+              480,
+              640,
+              3
+            ]
+          },
+          "observation.images.cam_right_wrist": {
+            "type": "VISUAL",
+            "shape": [
+              480,
+              640,
+              3
+            ]
+          },
+          "action": {
+            "type": "ACTION",
+            "shape": [
+              14
+            ]
+          }
+        },
+        "norm_map": {
+          "VISUAL": "MEAN_STD",
+          "STATE": "MIN_MAX",
+          "ACTION": "MIN_MAX"
+        }
+      },
+      "state_file": "policy_preprocessor_step_4_normalizer_processor.safetensors"
+    }
+  ]
+}

policy_preprocessor_step_4_normalizer_processor.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:8b3713d7915d5865e4872131d358c28300a1ba19430c8639cde984f0cd0f0088
+size 4600

tokenizer/tokenizer.json ADDED Viewed

The diff for this file is too large to render. See raw diff

tokenizer/tokenizer_config.json ADDED Viewed

	@@ -0,0 +1,20 @@

+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": "<|startoftext|>",
+  "do_lower_case": true,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "is_local": true,
+  "max_length": 77,
+  "model_max_length": 77,
+  "pad_to_multiple_of": null,
+  "pad_token": "<|endoftext|>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "stride": 0,
+  "tokenizer_class": "CLIPTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<|endoftext|>"
+}

train_config.json ADDED Viewed

	@@ -0,0 +1,295 @@

+{
+    "dataset": {
+        "repo_id": "lerobot/robotwin_unified",
+        "repo_type": "dataset",
+        "root": null,
+        "episodes": null,
+        "exclude_episodes": null,
+        "image_transforms": {
+            "enable": true,
+            "max_num_transforms": 4,
+            "random_order": false,
+            "tfs": {
+                "brightness": {
+                    "weight": 1.0,
+                    "type": "ColorJitter",
+                    "kwargs": {
+                        "brightness": [
+                            0.75,
+                            1.25
+                        ]
+                    }
+                },
+                "contrast": {
+                    "weight": 1.0,
+                    "type": "ColorJitter",
+                    "kwargs": {
+                        "contrast": [
+                            0.6,
+                            1.4
+                        ]
+                    }
+                },
+                "saturation": {
+                    "weight": 1.0,
+                    "type": "ColorJitter",
+                    "kwargs": {
+                        "saturation": [
+                            0.8,
+                            1.2
+                        ]
+                    }
+                },
+                "hue": {
+                    "weight": 1.0,
+                    "type": "ColorJitter",
+                    "kwargs": {
+                        "hue": [
+                            -0.05,
+                            0.05
+                        ]
+                    }
+                }
+            }
+        },
+        "revision": "main",
+        "use_imagenet_stats": true,
+        "video_backend": "torchcodec",
+        "return_uint8": false,
+        "depth_output_unit": "mm",
+        "streaming": false,
+        "eval_split": 0.0
+    },
+    "env": null,
+    "policy": {
+        "type": "multi_task_dit",
+        "n_obs_steps": 2,
+        "input_features": {
+            "observation.state": {
+                "type": "STATE",
+                "shape": [
+                    14
+                ]
+            },
+            "observation.images.cam_high": {
+                "type": "VISUAL",
+                "shape": [
+                    480,
+                    640,
+                    3
+                ]
+            },
+            "observation.images.cam_left_wrist": {
+                "type": "VISUAL",
+                "shape": [
+                    480,
+                    640,
+                    3
+                ]
+            },
+            "observation.images.cam_right_wrist": {
+                "type": "VISUAL",
+                "shape": [
+                    480,
+                    640,
+                    3
+                ]
+            }
+        },
+        "output_features": {
+            "action": {
+                "type": "ACTION",
+                "shape": [
+                    14
+                ]
+            }
+        },
+        "device": "cuda",
+        "use_amp": true,
+        "use_peft": false,
+        "push_to_hub": true,
+        "repo_id": "unitzero-ai/dit_robotwin_2026-09-29_15-41-09",
+        "private": true,
+        "tags": null,
+        "license": null,
+        "pretrained_path": "outputs/train/2026-09-30/09-34-48_dit_robotwin_2026-09-29_15-41-09/checkpoints/012000/pretrained_model",
+        "pretrained_revision": null,
+        "horizon": 32,
+        "n_action_steps": 24,
+        "objective": "diffusion",
+        "noise_scheduler_type": "DDPM",
+        "num_train_timesteps": 100,
+        "beta_schedule": "squaredcos_cap_v2",
+        "beta_start": 0.0001,
+        "beta_end": 0.02,
+        "prediction_type": "epsilon",
+        "clip_sample": true,
+        "clip_sample_range": 1.0,
+        "num_inference_steps": 10,
+        "sigma_min": 0.0,
+        "num_integration_steps": 100,
+        "integration_method": "euler",
+        "timestep_sampling_strategy": "beta",
+        "timestep_sampling_s": 0.999,
+        "timestep_sampling_alpha": 1.5,
+        "timestep_sampling_beta": 1.0,
+        "hidden_dim": 768,
+        "num_layers": 8,
+        "num_heads": 12,
+        "dropout": 0.1,
+        "use_positional_encoding": false,
+        "timestep_embed_dim": 256,
+        "use_rope": true,
+        "rope_base": 10000.0,
+        "vision_encoder_name": "openai/clip-vit-base-patch16",
+        "use_separate_rgb_encoder_per_camera": false,
+        "vision_encoder_lr_multiplier": 0.1,
+        "image_resize_shape": [
+            256,
+            256
+        ],
+        "image_crop_shape": [
+            224,
+            224
+        ],
+        "image_crop_is_random": true,
+        "text_encoder_name": "openai/clip-vit-base-patch16",
+        "tokenizer_max_length": 77,
+        "tokenizer_padding": "max_length",
+        "tokenizer_padding_side": "right",
+        "tokenizer_truncation": true,
+        "normalization_mapping": {
+            "VISUAL": "MEAN_STD",
+            "STATE": "MIN_MAX",
+            "ACTION": "MIN_MAX"
+        },
+        "optimizer_lr": 0.0003,
+        "optimizer_betas": [
+            0.95,
+            0.999
+        ],
+        "optimizer_eps": 1e-08,
+        "optimizer_weight_decay": 0.0,
+        "scheduler_name": "cosine",
+        "scheduler_warmup_steps": 0,
+        "do_mask_loss_for_padding": false,
+        "drop_n_last_frames": 7
+    },
+    "reward_model": null,
+    "output_dir": "outputs/train/2026-09-30/09-34-48_dit_robotwin_2026-09-29_15-41-09",
+    "job_name": "dit_robotwin",
+    "resume": true,
+    "seed": 123,
+    "cudnn_deterministic": false,
+    "num_workers": 8,
+    "batch_size": 64,
+    "prefetch_factor": 4,
+    "persistent_workers": true,
+    "dataloader_multiprocessing_context": "spawn",
+    "steps": 50000,
+    "env_eval_freq": 0,
+    "log_freq": 100,
+    "eval_steps": 0,
+    "max_eval_samples": 0,
+    "tolerance_s": 0.0001,
+    "save_checkpoint": true,
+    "save_freq": 4000,
+    "checkpoint_format": "safetensors",
+    "use_policy_training_preset": true,
+    "optimizer": {
+        "type": "adam",
+        "lr": 0.0003,
+        "weight_decay": 0.0,
+        "grad_clip_norm": 10.0,
+        "betas": [
+            0.95,
+            0.999
+        ],
+        "eps": 1e-08
+    },
+    "scheduler": {
+        "type": "diffuser",
+        "num_warmup_steps": 0,
+        "name": "cosine"
+    },
+    "parallelism": {
+        "dp_replicate": 8,
+        "dp_shard": 1,
+        "context_parallel": {
+            "ring_degree": 1,
+            "ulysses_degree": 1
+        },
+        "cfg_parallel": 1
+    },
+    "accelerator": {
+        "mixed_precision": "bf16",
+        "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": false,
+        "project": "dit_robotwin",
+        "entity": "unitzero-ai",
+        "notes": null,
+        "run_id": "qhy4lauf",
+        "resume": null,
+        "mode": null,
+        "console": "wrap",
+        "console_multipart": false,
+        "console_chunk_max_seconds": 0,
+        "add_tags": true
+    },
+    "peft": null,
+    "job": {
+        "target": null,
+        "image": "huggingface/lerobot-gpu:latest",
+        "timeout": "2d",
+        "detach": false,
+        "tags": []
+    },
+    "save_checkpoint_to_hub": false,
+    "sample_weighting": null,
+    "rename_map": {},
+    "checkpoint_path": "outputs/train/2026-09-30/09-34-48_dit_robotwin_2026-09-29_15-41-09/checkpoints/012000"
+}