Upload default pretrained model from checkpoint 003000

README.md

@@ -1,38 +1,24 @@
----
-library_name: lerobot
-tags:
-- robotics
-- lerobot
-- smolvla
-- so101
----
+# eval3_sanitycheck
 
-# eval3_sanity
+SmolVLA sanity-check overfit policy for Eval 3 coke-can placement.
 
-All numbered SmolVLA overfit-20 checkpoints for Eval 3 sanity checking.
+- Base VLM: `HuggingFaceTB/SmolVLM2-500M-Video-Instruct`
+- Policy type: `smolvla`
+- Dataset: `robot-learning-group47/eval3_overfit20`
+- Local dataset root: `/data/lerobot_datasets/robot-learning-group47/eval3_overfit20`
+- Source episodes: `0,1,6,7,12,13,18,19,24,25,30,31,36,37,42,43,48,49,54,55`
+- Steps: `3000`
+- Batch size: `8`
+- Image augmentation: disabled
+- Trainable params: expert/state/action heads only, vision/VLM frozen
+- Final training loss: approximately `0.182`
 
-Dataset: `robot-learning-group47/eval3_overfit20`
+Important inference settings are stored in `config.json`:
 
-Checkpoints:
-
-- `checkpoints/000500`
-- `checkpoints/001000`
-- `checkpoints/001500`
-- `checkpoints/002000`
-- `checkpoints/002500`
-- `checkpoints/003000`
-
-The `003000/pretrained_model` checkpoint is also uploaded at repo root as the default loadable policy.
-
-Key inference settings are stored in each checkpoint config:
-
-- policy type: `smolvla`
-- fps: `15`
-- camera key: `observation.images.front`
-- image size: `240x320`, resized internally with padding to `512x512`
 - `chunk_size=50`
 - `n_action_steps=50`
 - `num_steps=10`
 - `attention_mode=self_attn`
 - `num_vlm_layers=8`
 - `num_expert_layers=4`
+- `resize_imgs_with_padding=[512,512]`

config.json

@@ -0,0 +1,85 @@
+{
+    "type": "smolvla",
+    "n_obs_steps": 1,
+    "input_features": {
+        "observation.state": {
+            "type": "STATE",
+            "shape": [
+                6
+            ]
+        },
+        "observation.images.front": {
+            "type": "VISUAL",
+            "shape": [
+                3,
+                240,
+                320
+            ]
+        }
+    },
+    "output_features": {
+        "action": {
+            "type": "ACTION",
+            "shape": [
+                6
+            ]
+        }
+    },
+    "device": "cuda",
+    "use_amp": false,
+    "use_peft": false,
+    "push_to_hub": false,
+    "repo_id": null,
+    "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"
+    },
+    "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,
+    "scheduler_warmup_steps": 100,
+    "scheduler_decay_steps": 3000,
+    "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": "self_attn",
+    "prefix_length": -1,
+    "pad_language_to": "longest",
+    "num_expert_layers": 4,
+    "num_vlm_layers": 8,
+    "self_attn_every_n_layers": 2,
+    "expert_width_multiplier": 0.75,
+    "min_period": 0.004,
+    "max_period": 4.0,
+    "rtc_config": null,
+    "compile_model": false,
+    "compile_mode": "max-autotune"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6de6bca545855eeae75b82f4b6728fbfdcfbaf85e6e5e3e30fe6ab9f5549d05f
+size 599749280

policy_postprocessor.json

@@ -0,0 +1,32 @@
+{
+  "name": "policy_postprocessor",
+  "steps": [
+    {
+      "registry_name": "unnormalizer_processor",
+      "config": {
+        "eps": 1e-08,
+        "features": {
+          "action": {
+            "type": "ACTION",
+            "shape": [
+              6
+            ]
+          }
+        },
+        "norm_map": {
+          "VISUAL": "IDENTITY",
+          "STATE": "MEAN_STD",
+          "ACTION": "MEAN_STD"
+        }
+      },
+      "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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ec4f3742a63af18f8893f65f386129c63790c57351b91cc402cdb2d8a79ab44
+size 6560

policy_preprocessor.json

@@ -0,0 +1,71 @@
+{
+  "name": "policy_preprocessor",
+  "steps": [
+    {
+      "registry_name": "rename_observations_processor",
+      "config": {
+        "rename_map": {}
+      }
+    },
+    {
+      "registry_name": "to_batch_processor",
+      "config": {}
+    },
+    {
+      "registry_name": "smolvla_new_line_processor",
+      "config": {}
+    },
+    {
+      "registry_name": "tokenizer_processor",
+      "config": {
+        "max_length": 48,
+        "task_key": "task",
+        "padding_side": "right",
+        "padding": "longest",
+        "truncation": true,
+        "tokenizer_name": "HuggingFaceTB/SmolVLM2-500M-Video-Instruct"
+      }
+    },
+    {
+      "registry_name": "device_processor",
+      "config": {
+        "device": "cuda",
+        "float_dtype": null
+      }
+    },
+    {
+      "registry_name": "normalizer_processor",
+      "config": {
+        "eps": 1e-08,
+        "features": {
+          "observation.state": {
+            "type": "STATE",
+            "shape": [
+              6
+            ]
+          },
+          "observation.images.front": {
+            "type": "VISUAL",
+            "shape": [
+              3,
+              240,
+              320
+            ]
+          },
+          "action": {
+            "type": "ACTION",
+            "shape": [
+              6
+            ]
+          }
+        },
+        "norm_map": {
+          "VISUAL": "IDENTITY",
+          "STATE": "MEAN_STD",
+          "ACTION": "MEAN_STD"
+        }
+      },
+      "state_file": "policy_preprocessor_step_5_normalizer_processor.safetensors"
+    }
+  ]
+}

policy_preprocessor_step_5_normalizer_processor.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac69b9e1f1c0cbbf0ab09343f6c139fab56b46b3e1395e4bec4d218e0a955059
+size 6568

train_config.json

@@ -0,0 +1,223 @@
+{
+    "dataset": {
+        "repo_id": "robot-learning-group47/eval3_overfit20",
+        "root": "/data/lerobot_datasets/robot-learning-group47/eval3_overfit20",
+        "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",
+        "return_uint8": false,
+        "streaming": false
+    },
+    "env": null,
+    "policy": {
+        "type": "smolvla",
+        "n_obs_steps": 1,
+        "input_features": {
+            "observation.state": {
+                "type": "STATE",
+                "shape": [
+                    6
+                ]
+            },
+            "observation.images.front": {
+                "type": "VISUAL",
+                "shape": [
+                    3,
+                    240,
+                    320
+                ]
+            }
+        },
+        "output_features": {
+            "action": {
+                "type": "ACTION",
+                "shape": [
+                    6
+                ]
+            }
+        },
+        "device": "cuda",
+        "use_amp": false,
+        "use_peft": false,
+        "push_to_hub": false,
+        "repo_id": null,
+        "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"
+        },
+        "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,
+        "scheduler_warmup_steps": 100,
+        "scheduler_decay_steps": 3000,
+        "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": "self_attn",
+        "prefix_length": -1,
+        "pad_language_to": "longest",
+        "num_expert_layers": 4,
+        "num_vlm_layers": 8,
+        "self_attn_every_n_layers": 2,
+        "expert_width_multiplier": 0.75,
+        "min_period": 0.004,
+        "max_period": 4.0,
+        "rtc_config": null,
+        "compile_model": false,
+        "compile_mode": "max-autotune"
+    },
+    "reward_model": null,
+    "output_dir": "outputs/train/2026-05-20/20-23-02_smolvla",
+    "job_name": "smolvla",
+    "resume": false,
+    "seed": 1000,
+    "cudnn_deterministic": false,
+    "num_workers": 4,
+    "batch_size": 8,
+    "prefetch_factor": 4,
+    "persistent_workers": true,
+    "steps": 3000,
+    "eval_freq": 20000,
+    "log_freq": 50,
+    "tolerance_s": 0.0001,
+    "save_checkpoint": true,
+    "save_freq": 500,
+    "use_policy_training_preset": true,
+    "optimizer": {
+        "type": "adamw",
+        "lr": 0.0001,
+        "weight_decay": 1e-10,
+        "grad_clip_norm": 10,
+        "betas": [
+            0.9,
+            0.95
+        ],
+        "eps": 1e-08
+    },
+    "scheduler": {
+        "type": "cosine_decay_with_warmup",
+        "num_warmup_steps": 100,
+        "num_decay_steps": 3000,
+        "peak_lr": 0.0001,
+        "decay_lr": 2.5e-06
+    },
+    "eval": {
+        "n_episodes": 50,
+        "batch_size": 11,
+        "use_async_envs": true
+    },
+    "wandb": {
+        "enable": false,
+        "disable_artifact": false,
+        "project": "lerobot",
+        "entity": null,
+        "notes": null,
+        "run_id": null,
+        "mode": null,
+        "add_tags": true
+    },
+    "peft": null,
+    "sample_weighting": null,
+    "rename_map": {},
+    "checkpoint_path": null
+}