Hugging Face's logo

Orellius
/
so101_matchbox_fpv_reward_model

Robotics
LeRobot
Safetensors
cnn
reward_classifier
Model card Files
xet
Community
so101_matchbox_fpv_reward_model
File size: 3,402 Bytes
a7d5f81
 
7e1433c
a7d5f81
 
 
1ac09bd
a7d5f81
 
 
1ac09bd
a7d5f81
 
 
1ac09bd
 
 
 
a7d5f81
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7e1433c
 
a7d5f81
 
 
 
 
7e1433c
a7d5f81
 
 
 
 
04b60b9
a7d5f81
1ac09bd
a7d5f81
04b60b9
1ac09bd
a7d5f81
d7d9e13
a7d5f81
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7e1433c
a7d5f81
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
 
{
    "dataset": {
        "repo_id": "hubnemo/so101_matchbox_reward_fpv_less_bias",
        "root": null,
        "episodes": null,
        "image_transforms": {
            "enable": true,
            "max_num_transforms": 3,
            "random_order": false,
            "tfs": {
                "color_jitter": {
                    "weight": 1.0,
                    "type": "ColorJitter",
                    "kwargs": {
                        "brightness": 0.2,
                        "contrast": 0.2,
                        "saturation": 0.2,
                        "hue": 0.1
                    }
                }
            }
        },
        "revision": null,
        "use_imagenet_stats": true,
        "video_backend": "torchcodec"
    },
    "env": null,
    "policy": {
        "type": "reward_classifier",
        "n_obs_steps": 1,
        "normalization_mapping": {
            "VISUAL": "IDENTITY",
            "STATE": "MEAN_STD",
            "ACTION": "MEAN_STD"
        },
        "input_features": {
            "observation.state": {
                "type": "STATE",
                "shape": [
                    6
                ]
            },
            "observation.image.front": {
                "type": "VISUAL",
                "shape": [
                    3,
                    480,
                    640
                ]
            }
        },
        "output_features": {
            "action": {
                "type": "ACTION",
                "shape": [
                    6
                ]
            }
        },
        "device": "mps",
        "use_amp": false,
        "use_peft": false,
        "push_to_hub": true,
        "repo_id": "orellius/so101_matchbox_fpv_reward_model",
        "private": null,
        "tags": null,
        "license": null,
        "name": "reward_classifier",
        "num_classes": 2,
        "hidden_dim": 256,
        "latent_dim": 256,
        "image_embedding_pooling_dim": 8,
        "dropout_rate": 0.1,
        "model_name": "helper2424/resnet10",
        "model_type": "cnn",
        "num_cameras": 1,
        "learning_rate": 0.0003,
        "weight_decay": 0.01,
        "grad_clip_norm": 1.0
    },
    "output_dir": "outputs/train/2025-09-12/18-52-09_reward-classifier",
    "job_name": "reward-classifier",
    "resume": false,
    "seed": 2,
    "num_workers": 4,
    "batch_size": 16,
    "steps": 3000,
    "eval_freq": 1000,
    "log_freq": 100,
    "save_checkpoint": true,
    "save_freq": 10000,
    "use_validation": true,
    "val_split": 0.05,
    "val_freq": 500,
    "val_batch_size": 16,
    "use_policy_training_preset": true,
    "optimizer": {
        "type": "adamw",
        "lr": 0.0003,
        "weight_decay": 0.01,
        "grad_clip_norm": 1.0,
        "betas": [
            0.9,
            0.999
        ],
        "eps": 1e-08
    },
    "scheduler": null,
    "eval": {
        "n_episodes": 50,
        "batch_size": 50,
        "use_async_envs": false
    },
    "wandb": {
        "enable": true,
        "disable_artifact": false,
        "project": "reward-classifier",
        "entity": null,
        "notes": null,
        "run_id": "c62unon8",
        "mode": null
    },
    "use_peft": false,
    "peft": {
        "target_modules": null,
        "modules_to_save": null,
        "method_type": "LORA",
        "init_type": null,
        "r": 16
    }
}