Upload policy weights, train config and readme

Browse files

Files changed (5) hide show

README.md +62 -0
config.json +93 -0
groot_model_config.json +56 -0
model.safetensors +3 -0
train_config.json +206 -0

README.md ADDED Viewed

	@@ -0,0 +1,62 @@

+---
+datasets: aractingi/bimanual-so100-handover-cube-224
+library_name: lerobot
+license: apache-2.0
+model_name: groot
+pipeline_tag: robotics
+tags:
+- lerobot
+- robotics
+- groot
+---
+# Model Card for groot
+<!-- Provide a quick summary of what the model is/does. -->
+_Model type not recognized — please update this template._
+This policy has been trained and pushed to the Hub using [LeRobot](https://github.com/huggingface/lerobot).
+See the full documentation at [LeRobot Docs](https://huggingface.co/docs/lerobot/index).
+---
+## How to Get Started with the Model
+For a complete walkthrough, see the [training guide](https://huggingface.co/docs/lerobot/il_robots#train-a-policy).
+Below is the short version on how to train and run inference/eval:
+### Train from scratch
+```bash
+lerobot-train \
+  --dataset.repo_id=${HF_USER}/<dataset> \
+  --policy.type=act \
+  --output_dir=outputs/train/<desired_policy_repo_id> \
+  --job_name=lerobot_training \
+  --policy.device=cuda \
+  --policy.repo_id=${HF_USER}/<desired_policy_repo_id>
+  --wandb.enable=true
+```
+_Writes checkpoints to `outputs/train/<desired_policy_repo_id>/checkpoints/`._
+### Evaluate the policy/run inference
+```bash
+lerobot-record \
+  --robot.type=so100_follower \
+  --dataset.repo_id=<hf_user>/eval_<dataset> \
+  --policy.path=<hf_user>/<desired_policy_repo_id> \
+  --episodes=10
+```
+Prefix the dataset repo with **eval\_** and supply `--policy.path` pointing to a local or hub checkpoint.
+---
+## Model Details
+- **License:** apache-2.0

config.json ADDED Viewed

	@@ -0,0 +1,93 @@

+{
+    "type": "groot",
+    "n_obs_steps": 1,
+    "input_features": {
+        "observation.state": {
+            "type": "STATE",
+            "shape": [
+                12
+            ]
+        },
+        "observation.images.left": {
+            "type": "VISUAL",
+            "shape": [
+                3,
+                224,
+                224
+            ]
+        },
+        "observation.images.top": {
+            "type": "VISUAL",
+            "shape": [
+                3,
+                224,
+                224
+            ]
+        },
+        "observation.images.right": {
+            "type": "VISUAL",
+            "shape": [
+                3,
+                224,
+                224
+            ]
+        }
+    },
+    "output_features": {
+        "action": {
+            "type": "ACTION",
+            "shape": [
+                12
+            ]
+        }
+    },
+    "device": "cuda",
+    "use_amp": false,
+    "push_to_hub": true,
+    "repo_id": "aractingi/groot-bimanual-224",
+    "private": null,
+    "tags": null,
+    "license": null,
+    "pretrained_path": null,
+    "chunk_size": 50,
+    "n_action_steps": 50,
+    "normalization_mapping": {
+        "VISUAL": "IDENTITY",
+        "STATE": "MEAN_STD",
+        "ACTION": "MEAN_STD"
+    },
+    "image_size": [
+        224,
+        224
+    ],
+    "base_model_path": "nvidia/GR00T-N1.5-3B",
+    "embodiment_tag": "new_embodiment",
+    "tune_llm": false,
+    "tune_visual": false,
+    "tune_projector": true,
+    "tune_diffusion_model": false,
+    "lora_rank": 0,
+    "lora_alpha": 16,
+    "lora_dropout": 0.1,
+    "lora_full_model": false,
+    "optimizer_lr": 0.0001,
+    "optimizer_betas": [
+        0.95,
+        0.999
+    ],
+    "optimizer_eps": 1e-08,
+    "optimizer_weight_decay": 1e-05,
+    "warmup_ratio": 0.05,
+    "use_bf16": true,
+    "video_backend": "decord",
+    "balance_dataset_weights": true,
+    "balance_trajectory_weights": true,
+    "dataset_paths": null,
+    "output_dir": "./tmp/gr00t",
+    "save_steps": 1000,
+    "max_steps": 10000,
+    "batch_size": 32,
+    "dataloader_num_workers": 8,
+    "report_to": "wandb",
+    "resume": false
+}

groot_model_config.json ADDED Viewed

	@@ -0,0 +1,56 @@

+{
+  "backbone_cfg": {
+    "eagle_path": "NVEagle/eagle_er-qwen3_1_7B-Siglip2_400M_stage1_5_128gpu_er_v7_1mlp_nops",
+    "load_bf16": false,
+    "project_to_dim": null,
+    "reproject_vision": false,
+    "select_layer": 12,
+    "tune_llm": false,
+    "tune_visual": true,
+    "use_flash_attention": true
+  },
+  "action_head_cfg": {
+    "action_dim": 32,
+    "action_horizon": 16,
+    "add_pos_embed": true,
+    "backbone_embedding_dim": 2048,
+    "diffusion_model_cfg": {
+      "attention_head_dim": 48,
+      "cross_attention_dim": 2048,
+      "dropout": 0.2,
+      "final_dropout": true,
+      "interleave_self_attention": true,
+      "norm_type": "ada_norm",
+      "num_attention_heads": 32,
+      "num_layers": 16,
+      "output_dim": 1024,
+      "positional_embeddings": null
+    },
+    "hidden_size": 1024,
+    "input_embedding_dim": 1536,
+    "max_action_dim": 32,
+    "max_state_dim": 64,
+    "model_dtype": "float32",
+    "noise_beta_alpha": 1.5,
+    "noise_beta_beta": 1.0,
+    "noise_s": 0.999,
+    "num_inference_timesteps": 4,
+    "num_target_vision_tokens": 32,
+    "num_timestep_buckets": 1000,
+    "tune_diffusion_model": true,
+    "tune_projector": true,
+    "use_vlln": true,
+    "vl_self_attention_cfg": {
+      "attention_head_dim": 64,
+      "dropout": 0.2,
+      "final_dropout": true,
+      "num_attention_heads": 32,
+      "num_layers": 4,
+      "positional_embeddings": null
+    }
+  },
+  "action_horizon": 16,
+  "action_dim": 32,
+  "compute_dtype": "bfloat16",
+  "model_type": "gr00t_n1_5"
+}

model.safetensors ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:99e926960795197db6d0671a89672fa63716174883cbb3fe88eeb5a48ebab13b
+size 7586084224

train_config.json ADDED Viewed

	@@ -0,0 +1,206 @@

+{
+    "dataset": {
+        "repo_id": "aractingi/bimanual-so100-handover-cube-224",
+        "root": null,
+        "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
+                        ]
+                    }
+                }
+            }
+        },
+        "revision": null,
+        "use_imagenet_stats": true,
+        "video_backend": "torchcodec",
+        "streaming": false
+    },
+    "env": null,
+    "policy": {
+        "type": "groot",
+        "n_obs_steps": 1,
+        "input_features": {
+            "observation.state": {
+                "type": "STATE",
+                "shape": [
+                    12
+                ]
+            },
+            "observation.images.left": {
+                "type": "VISUAL",
+                "shape": [
+                    3,
+                    224,
+                    224
+                ]
+            },
+            "observation.images.top": {
+                "type": "VISUAL",
+                "shape": [
+                    3,
+                    224,
+                    224
+                ]
+            },
+            "observation.images.right": {
+                "type": "VISUAL",
+                "shape": [
+                    3,
+                    224,
+                    224
+                ]
+            }
+        },
+        "output_features": {
+            "action": {
+                "type": "ACTION",
+                "shape": [
+                    12
+                ]
+            }
+        },
+        "device": "cuda",
+        "use_amp": false,
+        "push_to_hub": true,
+        "repo_id": "aractingi/groot-bimanual-224",
+        "private": null,
+        "tags": null,
+        "license": null,
+        "pretrained_path": null,
+        "chunk_size": 50,
+        "n_action_steps": 50,
+        "normalization_mapping": {
+            "VISUAL": "IDENTITY",
+            "STATE": "MEAN_STD",
+            "ACTION": "MEAN_STD"
+        },
+        "image_size": [
+            224,
+            224
+        ],
+        "base_model_path": "nvidia/GR00T-N1.5-3B",
+        "embodiment_tag": "new_embodiment",
+        "tune_llm": false,
+        "tune_visual": false,
+        "tune_projector": true,
+        "tune_diffusion_model": false,
+        "lora_rank": 0,
+        "lora_alpha": 16,
+        "lora_dropout": 0.1,
+        "lora_full_model": false,
+        "optimizer_lr": 0.0001,
+        "optimizer_betas": [
+            0.95,
+            0.999
+        ],
+        "optimizer_eps": 1e-08,
+        "optimizer_weight_decay": 1e-05,
+        "warmup_ratio": 0.05,
+        "use_bf16": true,
+        "video_backend": "decord",
+        "balance_dataset_weights": true,
+        "balance_trajectory_weights": true,
+        "dataset_paths": null,
+        "output_dir": "./tmp/gr00t",
+        "save_steps": 1000,
+        "max_steps": 10000,
+        "batch_size": 32,
+        "dataloader_num_workers": 8,
+        "report_to": "wandb",
+        "resume": false
+    },
+    "output_dir": "/fsx/michel_aractingi/outputs/real/groot-bimanual-224",
+    "job_name": "groot-bimanual-224",
+    "resume": false,
+    "seed": 1000,
+    "num_workers": 4,
+    "batch_size": 32,
+    "steps": 100000,
+    "eval_freq": 20000,
+    "log_freq": 50,
+    "save_checkpoint": true,
+    "save_freq": 10000,
+    "use_policy_training_preset": true,
+    "optimizer": {
+        "type": "adamw",
+        "lr": 0.0001,
+        "weight_decay": 1e-05,
+        "grad_clip_norm": 10.0,
+        "betas": [
+            0.95,
+            0.999
+        ],
+        "eps": 1e-08
+    },
+    "scheduler": {
+        "type": "cosine_decay_with_warmup",
+        "num_warmup_steps": 500,
+        "num_decay_steps": 10000,
+        "peak_lr": 0.0001,
+        "decay_lr": 1e-05
+    },
+    "eval": {
+        "n_episodes": 50,
+        "batch_size": 50,
+        "use_async_envs": false
+    },
+    "wandb": {
+        "enable": true,
+        "disable_artifact": true,
+        "project": "groot",
+        "entity": null,
+        "notes": null,
+        "run_id": "p6shvxvk",
+        "mode": null
+    }
+}