Upload policy weights, train config and readme

README.md

@@ -1,14 +1,14 @@
 ---
 base_model: lerobot/smolvla_base
-datasets: ISdept/piper_arm
+datasets: ISdept/piper-pick-place-depth
 library_name: lerobot
 license: apache-2.0
 model_name: smolvla
 pipeline_tag: robotics
 tags:
 - robotics
-- lerobot
 - smolvla
+- lerobot
 ---
 
 # Model Card for smolvla

config.json

@@ -1,6 +1,6 @@
 {
     "type": "smolvla",
-    "n_obs_steps": 2,
+    "n_obs_steps": 1,
     "input_features": {
         "observation.state": {
             "type": "STATE",
@@ -23,6 +23,14 @@
                 400,
                 640
             ]
+        },
+        "observation.images.camera3": {
+            "type": "VISUAL",
+            "shape": [
+                3,
+                256,
+                256
+            ]
         }
     },
     "output_features": {
@@ -36,13 +44,13 @@
     "device": "cuda",
     "use_amp": false,
     "push_to_hub": true,
-    "repo_id": null,
+    "repo_id": "ISdept/smolvla-piper",
     "private": null,
     "tags": null,
     "license": null,
-    "pretrained_path": null,
-    "chunk_size": 24,
-    "n_action_steps": 24,
+    "pretrained_path": "lerobot/smolvla_base",
+    "chunk_size": 50,
+    "n_action_steps": 50,
     "normalization_mapping": {
         "VISUAL": "IDENTITY",
         "STATE": "MEAN_STD",

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a2e7c035eb3c8620ed644cc5b96a4035925f5817307670c9490fdf72e08c1bb
+oid sha256:1a039cd06220642dd5812b17037afd0870515f61a47794c02ea9b301977a5659
 size 906712520

train_config.json

@@ -0,0 +1,230 @@
+{
+    "dataset": {
+        "repo_id": "ISdept/piper-pick-place-depth",
+        "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
+                        ]
+                    }
+                },
+                "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": "smolvla",
+        "n_obs_steps": 1,
+        "input_features": {
+            "observation.state": {
+                "type": "STATE",
+                "shape": [
+                    7
+                ]
+            },
+            "observation.images.camera1": {
+                "type": "VISUAL",
+                "shape": [
+                    3,
+                    400,
+                    640
+                ]
+            },
+            "observation.images.camera2": {
+                "type": "VISUAL",
+                "shape": [
+                    3,
+                    400,
+                    640
+                ]
+            },
+            "observation.images.camera3": {
+                "type": "VISUAL",
+                "shape": [
+                    3,
+                    256,
+                    256
+                ]
+            }
+        },
+        "output_features": {
+            "action": {
+                "type": "ACTION",
+                "shape": [
+                    7
+                ]
+            }
+        },
+        "device": "cuda",
+        "use_amp": false,
+        "push_to_hub": true,
+        "repo_id": "ISdept/smolvla-piper",
+        "private": null,
+        "tags": null,
+        "license": null,
+        "pretrained_path": "lerobot/smolvla_base",
+        "chunk_size": 50,
+        "n_action_steps": 50,
+        "normalization_mapping": {
+            "VISUAL": "IDENTITY",
+            "STATE": "MEAN_STD",
+            "ACTION": "MEAN_STD"
+        },
+        "max_state_dim": 32,
+        "max_action_dim": 32,
+        "resize_imgs_with_padding": [
+            512,
+            512
+        ],
+        "empty_cameras": 0,
+        "adapt_to_pi_aloha": false,
+        "use_delta_joint_actions_aloha": false,
+        "tokenizer_max_length": 48,
+        "num_steps": 10,
+        "use_cache": true,
+        "freeze_vision_encoder": true,
+        "train_expert_only": true,
+        "train_state_proj": true,
+        "optimizer_lr": 0.0001,
+        "optimizer_betas": [
+            0.9,
+            0.95
+        ],
+        "optimizer_eps": 1e-08,
+        "optimizer_weight_decay": 1e-10,
+        "optimizer_grad_clip_norm": 10.0,
+        "scheduler_warmup_steps": 1000,
+        "scheduler_decay_steps": 30000,
+        "scheduler_decay_lr": 2.5e-06,
+        "vlm_model_name": "HuggingFaceTB/SmolVLM2-500M-Video-Instruct",
+        "load_vlm_weights": true,
+        "add_image_special_tokens": false,
+        "attention_mode": "cross_attn",
+        "prefix_length": 0,
+        "pad_language_to": "max_length",
+        "num_expert_layers": 0,
+        "num_vlm_layers": 16,
+        "self_attn_every_n_layers": 2,
+        "expert_width_multiplier": 0.75,
+        "min_period": 0.004,
+        "max_period": 4.0,
+        "rtc_config": null
+    },
+    "output_dir": "outputs/train/output_smolvla_7dof",
+    "job_name": "smolvla",
+    "resume": false,
+    "seed": 1000,
+    "num_workers": 4,
+    "batch_size": 16,
+    "steps": 20000,
+    "eval_freq": 20000,
+    "log_freq": 200,
+    "save_checkpoint": true,
+    "save_freq": 1000,
+    "use_policy_training_preset": true,
+    "optimizer": {
+        "type": "adamw",
+        "lr": 0.0001,
+        "weight_decay": 1e-10,
+        "grad_clip_norm": 10.0,
+        "betas": [
+            0.9,
+            0.95
+        ],
+        "eps": 1e-08
+    },
+    "scheduler": {
+        "type": "cosine_decay_with_warmup",
+        "num_warmup_steps": 1000,
+        "num_decay_steps": 30000,
+        "peak_lr": 0.0001,
+        "decay_lr": 2.5e-06
+    },
+    "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
+    },
+    "checkpoint_path": null,
+    "rename_map": {
+        "observation.images.depth": "observation.images.camera1",
+        "observation.images.gripper": "observation.images.camera2"
+    }
+}