Upload reward model weights, train config and readme

README.md

@@ -0,0 +1,57 @@
+---
+datasets: lilkm/stackblocks_recap_all_for_vf_v3
+library_name: lerobot
+license: apache-2.0
+model_name: temporal_siglip_value_function
+pipeline_tag: robotics
+tags:
+- lerobot
+- reward-model
+- robotics
+- temporal_siglip_value_function
+---
+
+# Reward Model Card for temporal_siglip_value_function
+
+<!-- Provide a quick summary of what the reward model is/does. -->
+
+
+_Reward model type not recognized — please update this template._
+
+
+This reward model 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 Reward Model
+
+### Train from scratch
+
+```bash
+lerobot-train \
+  --dataset.repo_id=${HF_USER}/<dataset> \
+  --reward_model.type=temporal_siglip_value_function \
+  --output_dir=outputs/train/<desired_reward_model_repo_id> \
+  --job_name=lerobot_reward_training \
+  --reward_model.device=cuda \
+  --reward_model.repo_id=${HF_USER}/<desired_reward_model_repo_id> \
+  --wandb.enable=true
+```
+
+_Writes checkpoints to `outputs/train/<desired_reward_model_repo_id>/checkpoints/`._
+
+### Load the reward model in Python
+
+```python
+from lerobot.rewards import make_reward_model
+
+reward_model = make_reward_model(pretrained_path="<hf_user>/<reward_model_repo_id>")
+reward = reward_model.compute_reward(batch)
+```
+
+---
+
+## Model Details
+
+- **License:** apache-2.0

config.json

@@ -0,0 +1,60 @@
+{
+    "type": "temporal_siglip_value_function",
+    "input_features": {
+        "observation.state": {
+            "type": "STATE",
+            "shape": [
+                6
+            ]
+        },
+        "observation.images.top": {
+            "type": "VISUAL",
+            "shape": [
+                3,
+                480,
+                640
+            ]
+        },
+        "observation.images.wrist": {
+            "type": "VISUAL",
+            "shape": [
+                3,
+                480,
+                640
+            ]
+        }
+    },
+    "output_features": {},
+    "device": "cuda",
+    "pretrained_path": null,
+    "pretrained_revision": null,
+    "push_to_hub": true,
+    "repo_id": "lilkm/vf_stackblocks_temporal_siglip_v2_fixed",
+    "license": null,
+    "tags": null,
+    "private": null,
+    "siglip_path": "google/siglip2-so400m-patch14-384",
+    "image_resolution": [
+        384,
+        384
+    ],
+    "tokenizer_max_length": 64,
+    "history_steps": 6,
+    "frame_gap": 30,
+    "state_key": "observation.state",
+    "state_dim": 32,
+    "hidden_size": 512,
+    "num_layers": 4,
+    "num_heads": 8,
+    "dropout": 0.1,
+    "num_value_bins": 201,
+    "value_support_min": -1.0,
+    "value_support_max": 0.0,
+    "hl_gauss_sigma_ratio": 0.75,
+    "target_method": "dirac_delta",
+    "use_one_hot_terminal": true,
+    "normalization_mapping": {
+        "VISUAL": "IDENTITY",
+        "STATE": "MEAN_STD"
+    }
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:260ae1b15a3ab26018a1bfa8540ac9778fd10fe9ca69128bce1ff8c67834b54c
+size 4604352476

train_config.json

@@ -0,0 +1,213 @@
+{
+    "dataset": {
+        "repo_id": "lilkm/stackblocks_recap_all_for_vf_v3",
+        "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": "pyav",
+        "return_uint8": false,
+        "depth_output_unit": "mm",
+        "streaming": false,
+        "eval_split": 0.1
+    },
+    "env": null,
+    "policy": null,
+    "reward_model": {
+        "type": "temporal_siglip_value_function",
+        "input_features": {
+            "observation.state": {
+                "type": "STATE",
+                "shape": [
+                    6
+                ]
+            },
+            "observation.images.top": {
+                "type": "VISUAL",
+                "shape": [
+                    3,
+                    480,
+                    640
+                ]
+            },
+            "observation.images.wrist": {
+                "type": "VISUAL",
+                "shape": [
+                    3,
+                    480,
+                    640
+                ]
+            }
+        },
+        "output_features": {},
+        "device": "cuda",
+        "pretrained_path": null,
+        "pretrained_revision": null,
+        "push_to_hub": true,
+        "repo_id": "lilkm/vf_stackblocks_temporal_siglip_v2_fixed",
+        "license": null,
+        "tags": null,
+        "private": null,
+        "siglip_path": "google/siglip2-so400m-patch14-384",
+        "image_resolution": [
+            384,
+            384
+        ],
+        "tokenizer_max_length": 64,
+        "history_steps": 6,
+        "frame_gap": 30,
+        "state_key": "observation.state",
+        "state_dim": 32,
+        "hidden_size": 512,
+        "num_layers": 4,
+        "num_heads": 8,
+        "dropout": 0.1,
+        "num_value_bins": 201,
+        "value_support_min": -1.0,
+        "value_support_max": 0.0,
+        "hl_gauss_sigma_ratio": 0.75,
+        "target_method": "dirac_delta",
+        "use_one_hot_terminal": true,
+        "normalization_mapping": {
+            "VISUAL": "IDENTITY",
+            "STATE": "MEAN_STD"
+        }
+    },
+    "output_dir": "outputs/vf_stackblocks_temporal_siglip_v2_fixed",
+    "job_name": "vf_stackblocks_temporal_siglip_v2_fixed",
+    "resume": false,
+    "seed": 1000,
+    "cudnn_deterministic": false,
+    "num_workers": 4,
+    "batch_size": 4,
+    "prefetch_factor": 4,
+    "persistent_workers": true,
+    "steps": 2000,
+    "env_eval_freq": -1,
+    "log_freq": 50,
+    "eval_steps": 250,
+    "max_eval_samples": 2000,
+    "tolerance_s": 0.0001,
+    "save_checkpoint": true,
+    "save_freq": 1000,
+    "use_policy_training_preset": true,
+    "optimizer": {
+        "type": "adamw",
+        "lr": 0.0001,
+        "weight_decay": 0.0001,
+        "grad_clip_norm": 1.0,
+        "betas": [
+            0.9,
+            0.999
+        ],
+        "eps": 1e-08
+    },
+    "scheduler": {
+        "type": "cosine_decay_with_warmup",
+        "num_warmup_steps": 500,
+        "num_decay_steps": 40000,
+        "peak_lr": 0.0001,
+        "decay_lr": 1e-06
+    },
+    "eval": {
+        "n_episodes": 50,
+        "batch_size": 50,
+        "use_async_envs": true,
+        "recording": false,
+        "recording_repo_id": null,
+        "recording_private": false
+    },
+    "wandb": {
+        "enable": true,
+        "disable_artifact": true,
+        "project": "recap-vf",
+        "entity": null,
+        "notes": null,
+        "run_id": "75pq8d77",
+        "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": {},
+    "checkpoint_path": null
+}