Upload policy weights, train config and readme

README.md

@@ -0,0 +1,62 @@
+---
+datasets: naavox/tidy_up
+library_name: lerobot
+license: apache-2.0
+model_name: multi_task_dit
+pipeline_tag: robotics
+tags:
+- robotics
+- lerobot
+- multi_task_dit
+---
+
+# Model Card for multi_task_dit
+
+<!-- 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

@@ -0,0 +1,105 @@
+{
+    "type": "multi_task_dit",
+    "n_obs_steps": 2,
+    "input_features": {
+        "observation.state": {
+            "type": "STATE",
+            "shape": [
+                43
+            ]
+        },
+        "observation.images.gripper_camera": {
+            "type": "VISUAL",
+            "shape": [
+                3,
+                384,
+                384
+            ]
+        },
+        "observation.images.overhead_camera": {
+            "type": "VISUAL",
+            "shape": [
+                3,
+                384,
+                384
+            ]
+        }
+    },
+    "output_features": {
+        "action": {
+            "type": "ACTION",
+            "shape": [
+                5
+            ]
+        }
+    },
+    "device": "cuda",
+    "use_amp": false,
+    "use_peft": false,
+    "push_to_hub": true,
+    "repo_id": "naavox/multitask-dit-4",
+    "private": null,
+    "tags": null,
+    "license": null,
+    "pretrained_path": null,
+    "horizon": 64,
+    "n_action_steps": 32,
+    "objective": "flow_matching",
+    "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": null,
+    "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": 512,
+    "num_layers": 6,
+    "num_heads": 8,
+    "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": 2e-05,
+    "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": 31
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86b0bd203fc81cb40dc6abc05fd8e5c6bae41ac5a3569113299884aca14d7549
+size 1000945892

train_config.json

@@ -0,0 +1,241 @@
+{
+    "dataset": {
+        "repo_id": "naavox/tidy_up",
+        "root": "/data_volume/tidy_up",
+        "episodes": null,
+        "image_transforms": {
+            "enable": true,
+            "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": "multi_task_dit",
+        "n_obs_steps": 2,
+        "input_features": {
+            "observation.state": {
+                "type": "STATE",
+                "shape": [
+                    43
+                ]
+            },
+            "observation.images.gripper_camera": {
+                "type": "VISUAL",
+                "shape": [
+                    3,
+                    384,
+                    384
+                ]
+            },
+            "observation.images.overhead_camera": {
+                "type": "VISUAL",
+                "shape": [
+                    3,
+                    384,
+                    384
+                ]
+            }
+        },
+        "output_features": {
+            "action": {
+                "type": "ACTION",
+                "shape": [
+                    5
+                ]
+            }
+        },
+        "device": "cuda",
+        "use_amp": false,
+        "use_peft": false,
+        "push_to_hub": true,
+        "repo_id": "naavox/multitask-dit-4",
+        "private": null,
+        "tags": null,
+        "license": null,
+        "pretrained_path": null,
+        "horizon": 64,
+        "n_action_steps": 32,
+        "objective": "flow_matching",
+        "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": null,
+        "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": 512,
+        "num_layers": 6,
+        "num_heads": 8,
+        "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": 2e-05,
+        "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": 31
+    },
+    "output_dir": "/data_volume/tidy_modal_1",
+    "job_name": "multi_task_dit",
+    "resume": false,
+    "seed": 1000,
+    "cudnn_deterministic": false,
+    "num_workers": 10,
+    "batch_size": 8,
+    "steps": 30000,
+    "eval_freq": 20000,
+    "log_freq": 200,
+    "tolerance_s": 0.001,
+    "save_checkpoint": true,
+    "save_freq": 20000,
+    "use_policy_training_preset": true,
+    "optimizer": {
+        "type": "adam",
+        "lr": 2e-05,
+        "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"
+    },
+    "eval": {
+        "n_episodes": 50,
+        "batch_size": 50,
+        "use_async_envs": false
+    },
+    "wandb": {
+        "enable": false,
+        "disable_artifact": false,
+        "project": "lerobot",
+        "entity": null,
+        "notes": null,
+        "run_id": null,
+        "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": null
+}