Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer/tokenizer.json filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,110 @@
+{
+    "type": "pi05",
+    "n_obs_steps": 1,
+    "input_features": {
+        "observation.images.base_0_rgb": {
+            "type": "VISUAL",
+            "shape": [
+                3,
+                224,
+                224
+            ]
+        },
+        "observation.images.left_wrist_0_rgb": {
+            "type": "VISUAL",
+            "shape": [
+                3,
+                224,
+                224
+            ]
+        },
+        "observation.images.right_wrist_0_rgb": {
+            "type": "VISUAL",
+            "shape": [
+                3,
+                224,
+                224
+            ]
+        },
+        "observation.state": {
+            "type": "STATE",
+            "shape": [
+                32
+            ]
+        }
+    },
+    "output_features": {
+        "action": {
+            "type": "ACTION",
+            "shape": [
+                8
+            ]
+        }
+    },
+    "device": "cuda",
+    "use_amp": false,
+    "use_peft": false,
+    "push_to_hub": false,
+    "repo_id": null,
+    "private": null,
+    "tags": null,
+    "license": null,
+    "pretrained_path": "/workspace/yangtong/gq/WorkSpace/EBiM/outputs/pi05_continue_0814/checkpoints/020000/pretrained_model",
+    "pretrained_revision": null,
+    "paligemma_variant": "gemma_2b",
+    "action_expert_variant": "gemma_300m",
+    "dtype": "bfloat16",
+    "chunk_size": 50,
+    "n_action_steps": 50,
+    "max_state_dim": 32,
+    "max_action_dim": 32,
+    "num_inference_steps": 10,
+    "time_sampling_beta_alpha": 1.5,
+    "time_sampling_beta_beta": 1.0,
+    "time_sampling_scale": 0.999,
+    "time_sampling_offset": 0.001,
+    "min_period": 0.004,
+    "max_period": 4.0,
+    "use_relative_actions": false,
+    "relative_exclude_joints": [
+        "gripper"
+    ],
+    "action_feature_names": [
+        "right_fr3v2_joint1.target",
+        "right_fr3v2_joint2.target",
+        "right_fr3v2_joint3.target",
+        "right_fr3v2_joint4.target",
+        "right_fr3v2_joint5.target",
+        "right_fr3v2_joint6.target",
+        "right_fr3v2_joint7.target",
+        "right_gripper.open_fraction.target"
+    ],
+    "rtc_config": null,
+    "image_resolution": [
+        224,
+        224
+    ],
+    "empty_cameras": 0,
+    "tokenizer_max_length": 200,
+    "normalization_mapping": {
+        "VISUAL": "IDENTITY",
+        "STATE": "QUANTILES",
+        "ACTION": "QUANTILES"
+    },
+    "gradient_checkpointing": true,
+    "compile_model": false,
+    "compile_mode": "max-autotune",
+    "freeze_vision_encoder": false,
+    "train_expert_only": false,
+    "optimizer_lr": 2.5e-05,
+    "optimizer_betas": [
+        0.9,
+        0.95
+    ],
+    "optimizer_eps": 1e-08,
+    "optimizer_weight_decay": 0.01,
+    "optimizer_grad_clip_norm": 1.0,
+    "scheduler_warmup_steps": 1000,
+    "scheduler_decay_steps": 30000,
+    "scheduler_decay_lr": 2.5e-06
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad2502cb2268613c18b6e3846f69916a0841f5f9f54c3c12efec011a9c163b5d
+size 9354050784

policy_postprocessor.json

@@ -0,0 +1,32 @@
+{
+  "name": "policy_postprocessor",
+  "steps": [
+    {
+      "registry_name": "unnormalizer_processor",
+      "config": {
+        "eps": 1e-08,
+        "features": {
+          "action": {
+            "type": "ACTION",
+            "shape": [
+              8
+            ]
+          }
+        },
+        "norm_map": {
+          "VISUAL": "IDENTITY",
+          "STATE": "QUANTILES",
+          "ACTION": "QUANTILES"
+        }
+      },
+      "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 sha256:36af12a2a2efe972a9ac3fa9dfc444bdc30db5963af95a812d47646dd9b70f2b
+size 7752

policy_preprocessor.json

@@ -0,0 +1,93 @@
+{
+  "name": "policy_preprocessor",
+  "steps": [
+    {
+      "registry_name": "rename_observations_processor",
+      "config": {
+        "rename_map": {
+          "observation.images.head": "observation.images.base_0_rgb",
+          "observation.images.wrist_right": "observation.images.right_wrist_0_rgb"
+        }
+      }
+    },
+    {
+      "registry_name": "to_batch_processor",
+      "config": {}
+    },
+    {
+      "registry_name": "normalizer_processor",
+      "config": {
+        "eps": 1e-08,
+        "features": {
+          "observation.images.base_0_rgb": {
+            "type": "VISUAL",
+            "shape": [
+              3,
+              224,
+              224
+            ]
+          },
+          "observation.images.left_wrist_0_rgb": {
+            "type": "VISUAL",
+            "shape": [
+              3,
+              224,
+              224
+            ]
+          },
+          "observation.images.right_wrist_0_rgb": {
+            "type": "VISUAL",
+            "shape": [
+              3,
+              224,
+              224
+            ]
+          },
+          "observation.state": {
+            "type": "STATE",
+            "shape": [
+              32
+            ]
+          },
+          "action": {
+            "type": "ACTION",
+            "shape": [
+              8
+            ]
+          }
+        },
+        "norm_map": {
+          "VISUAL": "IDENTITY",
+          "STATE": "QUANTILES",
+          "ACTION": "QUANTILES"
+        }
+      },
+      "state_file": "policy_preprocessor_step_2_normalizer_processor.safetensors"
+    },
+    {
+      "registry_name": "pi05_prepare_state_tokenizer_processor_step",
+      "config": {}
+    },
+    {
+      "registry_name": "tokenizer_processor",
+      "config": {
+        "max_length": 200,
+        "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
+      }
+    }
+  ]
+}

policy_preprocessor_step_2_normalizer_processor.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36af12a2a2efe972a9ac3fa9dfc444bdc30db5963af95a812d47646dd9b70f2b
+size 7752

tokenizer/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a29a78a3c72f7e3cc1e44e0b1ba6ae8921f8eff3e7b6b3f112cde67e1b01898c
+size 34383052

tokenizer/tokenizer_config.json

@@ -0,0 +1,27 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<bos>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<eos>",
+  "extra_special_tokens": [
+    "<image>"
+  ],
+  "is_local": true,
+  "mask_token": "<mask>",
+  "max_length": 200,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "processor_class": "PaliGemmaProcessor",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "stride": 0,
+  "tokenizer_class": "GemmaTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false,
+  "vocab_file": "/workspace/yangtong/gq/models/google_paligemma_3b_pt_224/tokenizer.model"
+}

train_config.json

@@ -0,0 +1,316 @@
+{
+    "dataset": {
+        "repo_id": "sev/pi_final_data",
+        "repo_type": "dataset",
+        "root": "/workspace/yangtong/gq/WorkSpace/EBiM/data/pi_final_data",
+        "episodes": null,
+        "exclude_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": "pyav",
+        "return_uint8": false,
+        "depth_output_unit": "mm",
+        "streaming": false,
+        "eval_split": 0.0
+    },
+    "env": null,
+    "policy": {
+        "type": "pi05",
+        "n_obs_steps": 1,
+        "input_features": {
+            "observation.images.base_0_rgb": {
+                "type": "VISUAL",
+                "shape": [
+                    3,
+                    224,
+                    224
+                ]
+            },
+            "observation.images.left_wrist_0_rgb": {
+                "type": "VISUAL",
+                "shape": [
+                    3,
+                    224,
+                    224
+                ]
+            },
+            "observation.images.right_wrist_0_rgb": {
+                "type": "VISUAL",
+                "shape": [
+                    3,
+                    224,
+                    224
+                ]
+            },
+            "observation.state": {
+                "type": "STATE",
+                "shape": [
+                    32
+                ]
+            }
+        },
+        "output_features": {
+            "action": {
+                "type": "ACTION",
+                "shape": [
+                    8
+                ]
+            }
+        },
+        "device": "cuda",
+        "use_amp": false,
+        "use_peft": false,
+        "push_to_hub": false,
+        "repo_id": null,
+        "private": null,
+        "tags": null,
+        "license": null,
+        "pretrained_path": "/workspace/yangtong/gq/WorkSpace/EBiM/outputs/pi05_continue_0814/checkpoints/020000/pretrained_model",
+        "pretrained_revision": null,
+        "paligemma_variant": "gemma_2b",
+        "action_expert_variant": "gemma_300m",
+        "dtype": "bfloat16",
+        "chunk_size": 50,
+        "n_action_steps": 50,
+        "max_state_dim": 32,
+        "max_action_dim": 32,
+        "num_inference_steps": 10,
+        "time_sampling_beta_alpha": 1.5,
+        "time_sampling_beta_beta": 1.0,
+        "time_sampling_scale": 0.999,
+        "time_sampling_offset": 0.001,
+        "min_period": 0.004,
+        "max_period": 4.0,
+        "use_relative_actions": false,
+        "relative_exclude_joints": [
+            "gripper"
+        ],
+        "action_feature_names": [
+            "right_fr3v2_joint1.target",
+            "right_fr3v2_joint2.target",
+            "right_fr3v2_joint3.target",
+            "right_fr3v2_joint4.target",
+            "right_fr3v2_joint5.target",
+            "right_fr3v2_joint6.target",
+            "right_fr3v2_joint7.target",
+            "right_gripper.open_fraction.target"
+        ],
+        "rtc_config": null,
+        "image_resolution": [
+            224,
+            224
+        ],
+        "empty_cameras": 0,
+        "tokenizer_max_length": 200,
+        "normalization_mapping": {
+            "VISUAL": "IDENTITY",
+            "STATE": "QUANTILES",
+            "ACTION": "QUANTILES"
+        },
+        "gradient_checkpointing": true,
+        "compile_model": false,
+        "compile_mode": "max-autotune",
+        "freeze_vision_encoder": false,
+        "train_expert_only": false,
+        "optimizer_lr": 2.5e-05,
+        "optimizer_betas": [
+            0.9,
+            0.95
+        ],
+        "optimizer_eps": 1e-08,
+        "optimizer_weight_decay": 0.01,
+        "optimizer_grad_clip_norm": 1.0,
+        "scheduler_warmup_steps": 1000,
+        "scheduler_decay_steps": 30000,
+        "scheduler_decay_lr": 2.5e-06
+    },
+    "reward_model": null,
+    "output_dir": "/workspace/yangtong/gq/WorkSpace/EBiM/outputs/pi05_final_0815",
+    "job_name": "pi05_final_0815",
+    "resume": false,
+    "seed": 1000,
+    "cudnn_deterministic": false,
+    "num_workers": 8,
+    "batch_size": 32,
+    "prefetch_factor": 4,
+    "persistent_workers": true,
+    "dataloader_multiprocessing_context": "spawn",
+    "steps": 15000,
+    "env_eval_freq": 0,
+    "log_freq": 100,
+    "eval_steps": 0,
+    "max_eval_samples": 0,
+    "tolerance_s": 0.0001,
+    "save_checkpoint": true,
+    "save_freq": 3000,
+    "checkpoint_format": "safetensors",
+    "use_policy_training_preset": true,
+    "optimizer": {
+        "type": "adamw",
+        "lr": 2.5e-05,
+        "weight_decay": 0.01,
+        "grad_clip_norm": 1.0,
+        "betas": [
+            0.9,
+            0.95
+        ],
+        "eps": 1e-08
+    },
+    "scheduler": {
+        "type": "cosine_decay_with_warmup",
+        "num_warmup_steps": 1000,
+        "num_decay_steps": 30000,
+        "peak_lr": 2.5e-05,
+        "decay_lr": 2.5e-06
+    },
+    "parallelism": {
+        "dp_replicate": 56,
+        "dp_shard": 1,
+        "context_parallel": {
+            "ring_degree": 1,
+            "ulysses_degree": 1
+        },
+        "cfg_parallel": 1
+    },
+    "accelerator": {
+        "mixed_precision": "no",
+        "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": true,
+        "decay": 0.99,
+        "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": false,
+        "disable_artifact": false,
+        "project": "lerobot",
+        "entity": null,
+        "notes": null,
+        "run_id": null,
+        "mode": null,
+        "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": {
+        "observation.images.head": "observation.images.base_0_rgb",
+        "observation.images.wrist_right": "observation.images.right_wrist_0_rgb"
+    },
+    "checkpoint_path": null
+}