Upload folder using huggingface_hub

config.json

@@ -73,7 +73,8 @@
         "grouped_depth": 2,
         "norm": "layer"
     },
-    "vqvae_name_or_path": "MINT-tokenizer-libero/ms_vqvae.pth",
+    "vqvae_name_or_path": "/inspire/hdd/project/robot-decision/huangrenming-253108120148/project/lerobot/pretrained/multi-scale-vqvae.pth",
+    "rtc_config": null,
     "image_resolution": [
         224,
         224

policy_postprocessor_step_0_unnormalizer_processor.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a002c0df7f79c5b169c5a899ad151d4ea1bed246c7d82bd93ed1556558d517a9
+size 7668

policy_preprocessor_step_2_normalizer_processor.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a002c0df7f79c5b169c5a899ad151d4ea1bed246c7d82bd93ed1556558d517a9
+size 7668

train_config.json

@@ -0,0 +1,238 @@
+{
+    "dataset": {
+        "repo_id": "/root/.cache/huggingface/lerobot/HuggingFaceVLA/libero/",
+        "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": "btm",
+        "n_obs_steps": 1,
+        "input_features": {
+            "observation.images.image": {
+                "type": "VISUAL",
+                "shape": [
+                    3,
+                    256,
+                    256
+                ]
+            },
+            "observation.images.image2": {
+                "type": "VISUAL",
+                "shape": [
+                    3,
+                    256,
+                    256
+                ]
+            },
+            "observation.state": {
+                "type": "STATE",
+                "shape": [
+                    8
+                ]
+            }
+        },
+        "output_features": {
+            "action": {
+                "type": "ACTION",
+                "shape": [
+                    7
+                ]
+            }
+        },
+        "device": "cuda",
+        "use_amp": false,
+        "push_to_hub": true,
+        "repo_id": "btm",
+        "private": null,
+        "tags": null,
+        "license": null,
+        "pretrained_path": "lerobot/pi05_base",
+        "paligemma_variant": "gemma_2b",
+        "action_expert_variant": "gemma_300m",
+        "train_expert_only": false,
+        "dtype": "bfloat16",
+        "chunk_size": 16,
+        "n_action_steps": 1,
+        "label_smooth": 0.0,
+        "max_state_dim": 32,
+        "max_action_dim": 7,
+        "codebook_size": 512,
+        "codebook_dim": 32,
+        "ch": 48,
+        "ch_mult": [
+            2,
+            4,
+            8
+        ],
+        "patch_nums": [
+            1,
+            2,
+            4
+        ],
+        "znorm": true,
+        "quant_conv_ks": 3,
+        "quant_resi": 0.5,
+        "share_quant_resi": 0,
+        "patchwise": {
+            "enable": true,
+            "d_embed": 8,
+            "grouped_depth": 2,
+            "norm": "layer"
+        },
+        "vqvae_name_or_path": "/inspire/hdd/project/robot-decision/huangrenming-253108120148/project/lerobot/pretrained/multi-scale-vqvae.pth",
+        "rtc_config": null,
+        "image_resolution": [
+            224,
+            224
+        ],
+        "empty_cameras": 0,
+        "tokenizer_max_length": 200,
+        "normalization_mapping": {
+            "VISUAL": "IDENTITY",
+            "STATE": "QUANTILES",
+            "ACTION": "IDENTITY"
+        },
+        "gradient_checkpointing": true,
+        "compile_model": false,
+        "compile_mode": "max-autotune",
+        "optimizer_lr": 0.00025,
+        "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-05
+    },
+    "output_dir": "outputs/btm_training_full_bs64",
+    "job_name": "btm_training",
+    "resume": false,
+    "seed": 1000,
+    "num_workers": 4,
+    "batch_size": 64,
+    "steps": 30000,
+    "eval_freq": 20000,
+    "log_freq": 500,
+    "tolerance_s": 0.0001,
+    "save_checkpoint": true,
+    "save_freq": 3000,
+    "use_policy_training_preset": true,
+    "optimizer": {
+        "type": "adamw",
+        "lr": 0.00025,
+        "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": 0.00025,
+        "decay_lr": 2.5e-05
+    },
+    "eval": {
+        "n_episodes": 50,
+        "batch_size": 50,
+        "use_async_envs": false
+    },
+    "wandb": {
+        "enable": false,
+        "disable_artifact": false,
+        "project": "lerobot-btm",
+        "entity": null,
+        "notes": null,
+        "run_id": null,
+        "mode": 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
+}