Robotics
LeRobot
Safetensors
pi05
so101
imitation-learning
HyeonseokE commited on
Commit
62db93e
·
verified ·
1 Parent(s): 88fa461

Upload folder using huggingface_hub

Browse files
config.json ADDED
@@ -0,0 +1,107 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "type": "pi05",
3
+ "n_obs_steps": 1,
4
+ "input_features": {
5
+ "observation.images.base_0_rgb": {
6
+ "type": "VISUAL",
7
+ "shape": [
8
+ 3,
9
+ 224,
10
+ 224
11
+ ]
12
+ },
13
+ "observation.images.left_wrist_0_rgb": {
14
+ "type": "VISUAL",
15
+ "shape": [
16
+ 3,
17
+ 224,
18
+ 224
19
+ ]
20
+ },
21
+ "observation.images.right_wrist_0_rgb": {
22
+ "type": "VISUAL",
23
+ "shape": [
24
+ 3,
25
+ 224,
26
+ 224
27
+ ]
28
+ },
29
+ "observation.state": {
30
+ "type": "STATE",
31
+ "shape": [
32
+ 32
33
+ ]
34
+ }
35
+ },
36
+ "output_features": {
37
+ "action": {
38
+ "type": "ACTION",
39
+ "shape": [
40
+ 6
41
+ ]
42
+ }
43
+ },
44
+ "device": "cuda",
45
+ "use_amp": false,
46
+ "use_peft": false,
47
+ "push_to_hub": false,
48
+ "repo_id": null,
49
+ "private": null,
50
+ "tags": null,
51
+ "license": null,
52
+ "pretrained_path": "lerobot/pi05_base",
53
+ "paligemma_variant": "gemma_2b",
54
+ "action_expert_variant": "gemma_300m",
55
+ "dtype": "bfloat16",
56
+ "chunk_size": 50,
57
+ "n_action_steps": 50,
58
+ "max_state_dim": 32,
59
+ "max_action_dim": 32,
60
+ "num_inference_steps": 10,
61
+ "time_sampling_beta_alpha": 1.5,
62
+ "time_sampling_beta_beta": 1.0,
63
+ "time_sampling_scale": 0.999,
64
+ "time_sampling_offset": 0.001,
65
+ "min_period": 0.004,
66
+ "max_period": 4.0,
67
+ "use_relative_actions": false,
68
+ "relative_exclude_joints": [
69
+ "gripper"
70
+ ],
71
+ "action_feature_names": [
72
+ "shoulder_pan.pos",
73
+ "shoulder_lift.pos",
74
+ "elbow_flex.pos",
75
+ "wrist_flex.pos",
76
+ "wrist_roll.pos",
77
+ "gripper.pos"
78
+ ],
79
+ "rtc_config": null,
80
+ "image_resolution": [
81
+ 224,
82
+ 224
83
+ ],
84
+ "empty_cameras": 0,
85
+ "tokenizer_max_length": 200,
86
+ "normalization_mapping": {
87
+ "ACTION": "MEAN_STD",
88
+ "STATE": "MEAN_STD",
89
+ "VISUAL": "IDENTITY"
90
+ },
91
+ "gradient_checkpointing": true,
92
+ "compile_model": false,
93
+ "compile_mode": "max-autotune",
94
+ "freeze_vision_encoder": false,
95
+ "train_expert_only": false,
96
+ "optimizer_lr": 2.5e-05,
97
+ "optimizer_betas": [
98
+ 0.9,
99
+ 0.95
100
+ ],
101
+ "optimizer_eps": 1e-08,
102
+ "optimizer_weight_decay": 0.01,
103
+ "optimizer_grad_clip_norm": 1.0,
104
+ "scheduler_warmup_steps": 1000,
105
+ "scheduler_decay_steps": 30000,
106
+ "scheduler_decay_lr": 2.5e-06
107
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19fe305c4b378b51062578f415aebf8355ae79ecc63cf7a7011492d3a15ca287
3
+ size 9354050752
policy_postprocessor.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "name": "policy_postprocessor",
3
+ "steps": [
4
+ {
5
+ "registry_name": "unnormalizer_processor",
6
+ "config": {
7
+ "eps": 1e-08,
8
+ "features": {
9
+ "action": {
10
+ "type": "ACTION",
11
+ "shape": [
12
+ 6
13
+ ]
14
+ }
15
+ },
16
+ "norm_map": {
17
+ "ACTION": "MEAN_STD",
18
+ "STATE": "MEAN_STD",
19
+ "VISUAL": "IDENTITY"
20
+ }
21
+ },
22
+ "state_file": "policy_postprocessor_step_0_unnormalizer_processor.safetensors"
23
+ },
24
+ {
25
+ "registry_name": "device_processor",
26
+ "config": {
27
+ "device": "cpu",
28
+ "float_dtype": null
29
+ }
30
+ }
31
+ ]
32
+ }
policy_postprocessor_step_0_unnormalizer_processor.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4edf70fc850c264167fc5bf2d82dbe4aba5e590e6d4ea9e1bfe625dd7db8d02
3
+ size 7536
policy_preprocessor.json ADDED
@@ -0,0 +1,90 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "name": "policy_preprocessor",
3
+ "steps": [
4
+ {
5
+ "registry_name": "rename_observations_processor",
6
+ "config": {
7
+ "rename_map": {
8
+ "observation.images.top": "observation.images.base_0_rgb",
9
+ "observation.images.wrist": "observation.images.left_wrist_0_rgb"
10
+ }
11
+ }
12
+ },
13
+ {
14
+ "registry_name": "to_batch_processor",
15
+ "config": {}
16
+ },
17
+ {
18
+ "registry_name": "normalizer_processor",
19
+ "config": {
20
+ "eps": 1e-08,
21
+ "features": {
22
+ "observation.images.base_0_rgb": {
23
+ "type": "VISUAL",
24
+ "shape": [
25
+ 3,
26
+ 224,
27
+ 224
28
+ ]
29
+ },
30
+ "observation.images.left_wrist_0_rgb": {
31
+ "type": "VISUAL",
32
+ "shape": [
33
+ 3,
34
+ 224,
35
+ 224
36
+ ]
37
+ },
38
+ "observation.images.right_wrist_0_rgb": {
39
+ "type": "VISUAL",
40
+ "shape": [
41
+ 3,
42
+ 224,
43
+ 224
44
+ ]
45
+ },
46
+ "observation.state": {
47
+ "type": "STATE",
48
+ "shape": [
49
+ 32
50
+ ]
51
+ },
52
+ "action": {
53
+ "type": "ACTION",
54
+ "shape": [
55
+ 6
56
+ ]
57
+ }
58
+ },
59
+ "norm_map": {
60
+ "ACTION": "MEAN_STD",
61
+ "STATE": "MEAN_STD",
62
+ "VISUAL": "IDENTITY"
63
+ }
64
+ },
65
+ "state_file": "policy_preprocessor_step_2_normalizer_processor.safetensors"
66
+ },
67
+ {
68
+ "registry_name": "pi05_prepare_state_tokenizer_processor_step",
69
+ "config": {}
70
+ },
71
+ {
72
+ "registry_name": "tokenizer_processor",
73
+ "config": {
74
+ "max_length": 200,
75
+ "task_key": "task",
76
+ "padding_side": "right",
77
+ "padding": "max_length",
78
+ "truncation": true,
79
+ "tokenizer_name": "google/paligemma-3b-pt-224"
80
+ }
81
+ },
82
+ {
83
+ "registry_name": "device_processor",
84
+ "config": {
85
+ "device": "cuda",
86
+ "float_dtype": null
87
+ }
88
+ }
89
+ ]
90
+ }
policy_preprocessor_step_2_normalizer_processor.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4edf70fc850c264167fc5bf2d82dbe4aba5e590e6d4ea9e1bfe625dd7db8d02
3
+ size 7536
train_config.json ADDED
@@ -0,0 +1,250 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset": {
3
+ "repo_id": "CoRL2026-CSI/SO101-teleop_close_pot_lid_100epi",
4
+ "root": null,
5
+ "episodes": null,
6
+ "image_transforms": {
7
+ "enable": true,
8
+ "max_num_transforms": 3,
9
+ "random_order": true,
10
+ "tfs": {
11
+ "brightness": {
12
+ "weight": 1.0,
13
+ "type": "ColorJitter",
14
+ "kwargs": {
15
+ "brightness": [
16
+ 0.8,
17
+ 1.2
18
+ ]
19
+ }
20
+ },
21
+ "contrast": {
22
+ "weight": 1.0,
23
+ "type": "ColorJitter",
24
+ "kwargs": {
25
+ "contrast": [
26
+ 0.8,
27
+ 1.2
28
+ ]
29
+ }
30
+ },
31
+ "saturation": {
32
+ "weight": 1.0,
33
+ "type": "ColorJitter",
34
+ "kwargs": {
35
+ "saturation": [
36
+ 0.5,
37
+ 1.5
38
+ ]
39
+ }
40
+ },
41
+ "hue": {
42
+ "weight": 1.0,
43
+ "type": "ColorJitter",
44
+ "kwargs": {
45
+ "hue": [
46
+ -0.05,
47
+ 0.05
48
+ ]
49
+ }
50
+ },
51
+ "sharpness": {
52
+ "weight": 1.0,
53
+ "type": "SharpnessJitter",
54
+ "kwargs": {
55
+ "sharpness": [
56
+ 0.5,
57
+ 1.5
58
+ ]
59
+ }
60
+ },
61
+ "affine": {
62
+ "weight": 1.0,
63
+ "type": "RandomAffine",
64
+ "kwargs": {
65
+ "degrees": [
66
+ -5.0,
67
+ 5.0
68
+ ],
69
+ "translate": [
70
+ 0.05,
71
+ 0.05
72
+ ]
73
+ }
74
+ }
75
+ }
76
+ },
77
+ "revision": null,
78
+ "use_imagenet_stats": true,
79
+ "video_backend": "torchcodec",
80
+ "streaming": false
81
+ },
82
+ "env": null,
83
+ "policy": {
84
+ "type": "pi05",
85
+ "n_obs_steps": 1,
86
+ "input_features": {
87
+ "observation.images.base_0_rgb": {
88
+ "type": "VISUAL",
89
+ "shape": [
90
+ 3,
91
+ 224,
92
+ 224
93
+ ]
94
+ },
95
+ "observation.images.left_wrist_0_rgb": {
96
+ "type": "VISUAL",
97
+ "shape": [
98
+ 3,
99
+ 224,
100
+ 224
101
+ ]
102
+ },
103
+ "observation.images.right_wrist_0_rgb": {
104
+ "type": "VISUAL",
105
+ "shape": [
106
+ 3,
107
+ 224,
108
+ 224
109
+ ]
110
+ },
111
+ "observation.state": {
112
+ "type": "STATE",
113
+ "shape": [
114
+ 32
115
+ ]
116
+ }
117
+ },
118
+ "output_features": {
119
+ "action": {
120
+ "type": "ACTION",
121
+ "shape": [
122
+ 6
123
+ ]
124
+ }
125
+ },
126
+ "device": "cuda",
127
+ "use_amp": false,
128
+ "use_peft": false,
129
+ "push_to_hub": false,
130
+ "repo_id": null,
131
+ "private": null,
132
+ "tags": null,
133
+ "license": null,
134
+ "pretrained_path": "lerobot/pi05_base",
135
+ "paligemma_variant": "gemma_2b",
136
+ "action_expert_variant": "gemma_300m",
137
+ "dtype": "bfloat16",
138
+ "chunk_size": 50,
139
+ "n_action_steps": 50,
140
+ "max_state_dim": 32,
141
+ "max_action_dim": 32,
142
+ "num_inference_steps": 10,
143
+ "time_sampling_beta_alpha": 1.5,
144
+ "time_sampling_beta_beta": 1.0,
145
+ "time_sampling_scale": 0.999,
146
+ "time_sampling_offset": 0.001,
147
+ "min_period": 0.004,
148
+ "max_period": 4.0,
149
+ "use_relative_actions": false,
150
+ "relative_exclude_joints": [
151
+ "gripper"
152
+ ],
153
+ "action_feature_names": [
154
+ "shoulder_pan.pos",
155
+ "shoulder_lift.pos",
156
+ "elbow_flex.pos",
157
+ "wrist_flex.pos",
158
+ "wrist_roll.pos",
159
+ "gripper.pos"
160
+ ],
161
+ "rtc_config": null,
162
+ "image_resolution": [
163
+ 224,
164
+ 224
165
+ ],
166
+ "empty_cameras": 0,
167
+ "tokenizer_max_length": 200,
168
+ "normalization_mapping": {
169
+ "ACTION": "MEAN_STD",
170
+ "STATE": "MEAN_STD",
171
+ "VISUAL": "IDENTITY"
172
+ },
173
+ "gradient_checkpointing": true,
174
+ "compile_model": false,
175
+ "compile_mode": "max-autotune",
176
+ "freeze_vision_encoder": false,
177
+ "train_expert_only": false,
178
+ "optimizer_lr": 2.5e-05,
179
+ "optimizer_betas": [
180
+ 0.9,
181
+ 0.95
182
+ ],
183
+ "optimizer_eps": 1e-08,
184
+ "optimizer_weight_decay": 0.01,
185
+ "optimizer_grad_clip_norm": 1.0,
186
+ "scheduler_warmup_steps": 1000,
187
+ "scheduler_decay_steps": 30000,
188
+ "scheduler_decay_lr": 2.5e-06
189
+ },
190
+ "output_dir": "/home/csiwoo/CORL2026/lerobot/outputs/train/pi05_teleop_close_pot_lid",
191
+ "job_name": "pi05_teleop_close_pot_lid",
192
+ "resume": false,
193
+ "seed": 1000,
194
+ "cudnn_deterministic": false,
195
+ "num_workers": 20,
196
+ "persistent_workers": false,
197
+ "batch_size": 32,
198
+ "gradient_accumulation_steps": 2,
199
+ "steps": 11200,
200
+ "eval_freq": 0,
201
+ "log_freq": 100,
202
+ "tolerance_s": 0.0001,
203
+ "save_checkpoint": true,
204
+ "save_freq": 11200,
205
+ "use_policy_training_preset": true,
206
+ "optimizer": {
207
+ "type": "adamw",
208
+ "lr": 2.5e-05,
209
+ "weight_decay": 0.01,
210
+ "grad_clip_norm": 1.0,
211
+ "betas": [
212
+ 0.9,
213
+ 0.95
214
+ ],
215
+ "eps": 1e-08
216
+ },
217
+ "scheduler": {
218
+ "type": "cosine_decay_with_warmup",
219
+ "num_warmup_steps": 1000,
220
+ "num_decay_steps": 30000,
221
+ "peak_lr": 2.5e-05,
222
+ "decay_lr": 2.5e-06
223
+ },
224
+ "eval": {
225
+ "n_episodes": 50,
226
+ "batch_size": 50,
227
+ "use_async_envs": true
228
+ },
229
+ "wandb": {
230
+ "enable": true,
231
+ "disable_artifact": false,
232
+ "project": "lerobot-pi05",
233
+ "entity": null,
234
+ "notes": null,
235
+ "run_id": "9felqn7d",
236
+ "mode": null,
237
+ "add_tags": true
238
+ },
239
+ "peft": null,
240
+ "use_rabc": false,
241
+ "rabc_progress_path": null,
242
+ "rabc_kappa": 0.01,
243
+ "rabc_epsilon": 1e-06,
244
+ "rabc_head_mode": "sparse",
245
+ "rename_map": {
246
+ "observation.images.top": "observation.images.base_0_rgb",
247
+ "observation.images.wrist": "observation.images.left_wrist_0_rgb"
248
+ },
249
+ "checkpoint_path": null
250
+ }