Hugging Face's logo

YHRG
/
pi0.5-bi-s1-mixed-pick-place-cube-fixed-5pos

Safetensors
Model card Files
xet
 Community
wyb5210 commited on
Commit
938adf0
·
verified ·
1 Parent(s): 268d319

Upload folder using huggingface_hub

Browse files
Files changed (7) hide show
  1. config.json +95 -0
  2. model.safetensors +3 -0
  3. policy_postprocessor.json +32 -0
  4. policy_postprocessor_step_0_unnormalizer_processor.safetensors +3 -0
  5. policy_preprocessor.json +87 -0
  6. policy_preprocessor_step_2_normalizer_processor.safetensors +3 -0
  7. train_config.json +256 -0
config.json ADDED
@@ -0,0 +1,95 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "type": "pi05",
3
+ "n_obs_steps": 1,
4
+ "input_features": {
5
+ "observation.state": {
6
+ "type": "STATE",
7
+ "shape": [
8
+ 14
9
+ ]
10
+ },
11
+ "observation.images.left": {
12
+ "type": "VISUAL",
13
+ "shape": [
14
+ 3,
15
+ 480,
16
+ 640
17
+ ]
18
+ },
19
+ "observation.images.right": {
20
+ "type": "VISUAL",
21
+ "shape": [
22
+ 3,
23
+ 480,
24
+ 640
25
+ ]
26
+ },
27
+ "observation.images.middle": {
28
+ "type": "VISUAL",
29
+ "shape": [
30
+ 3,
31
+ 480,
32
+ 640
33
+ ]
34
+ }
35
+ },
36
+ "output_features": {
37
+ "action": {
38
+ "type": "ACTION",
39
+ "shape": [
40
+ 14
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
+ "rtc_config": null,
68
+ "image_resolution": [
69
+ 224,
70
+ 224
71
+ ],
72
+ "empty_cameras": 0,
73
+ "tokenizer_max_length": 200,
74
+ "normalization_mapping": {
75
+ "VISUAL": "IDENTITY",
76
+ "STATE": "QUANTILES",
77
+ "ACTION": "QUANTILES"
78
+ },
79
+ "gradient_checkpointing": true,
80
+ "compile_model": true,
81
+ "compile_mode": "max-autotune",
82
+ "freeze_vision_encoder": false,
83
+ "train_expert_only": false,
84
+ "optimizer_lr": 2.5e-05,
85
+ "optimizer_betas": [
86
+ 0.9,
87
+ 0.95
88
+ ],
89
+ "optimizer_eps": 1e-08,
90
+ "optimizer_weight_decay": 0.01,
91
+ "optimizer_grad_clip_norm": 1.0,
92
+ "scheduler_warmup_steps": 1000,
93
+ "scheduler_decay_steps": 30000,
94
+ "scheduler_decay_lr": 2.5e-06
95
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7dda33bb4e11e85513095c4574ed209d7567b3fe796126444877e5a98546b15
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
+ 14
13
+ ]
14
+ }
15
+ },
16
+ "norm_map": {
17
+ "VISUAL": "IDENTITY",
18
+ "STATE": "QUANTILES",
19
+ "ACTION": "QUANTILES"
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 sha256:4da7407d16cb6217e0046c66ac4a2ad644b0a45c64ccfd61a9a51d32236d1db8
3
+ size 12652
policy_preprocessor.json ADDED
@@ -0,0 +1,87 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "name": "policy_preprocessor",
3
+ "steps": [
4
+ {
5
+ "registry_name": "rename_observations_processor",
6
+ "config": {
7
+ "rename_map": {}
8
+ }
9
+ },
10
+ {
11
+ "registry_name": "to_batch_processor",
12
+ "config": {}
13
+ },
14
+ {
15
+ "registry_name": "normalizer_processor",
16
+ "config": {
17
+ "eps": 1e-08,
18
+ "features": {
19
+ "observation.state": {
20
+ "type": "STATE",
21
+ "shape": [
22
+ 14
23
+ ]
24
+ },
25
+ "observation.images.left": {
26
+ "type": "VISUAL",
27
+ "shape": [
28
+ 3,
29
+ 480,
30
+ 640
31
+ ]
32
+ },
33
+ "observation.images.right": {
34
+ "type": "VISUAL",
35
+ "shape": [
36
+ 3,
37
+ 480,
38
+ 640
39
+ ]
40
+ },
41
+ "observation.images.middle": {
42
+ "type": "VISUAL",
43
+ "shape": [
44
+ 3,
45
+ 480,
46
+ 640
47
+ ]
48
+ },
49
+ "action": {
50
+ "type": "ACTION",
51
+ "shape": [
52
+ 14
53
+ ]
54
+ }
55
+ },
56
+ "norm_map": {
57
+ "VISUAL": "IDENTITY",
58
+ "STATE": "QUANTILES",
59
+ "ACTION": "QUANTILES"
60
+ }
61
+ },
62
+ "state_file": "policy_preprocessor_step_2_normalizer_processor.safetensors"
63
+ },
64
+ {
65
+ "registry_name": "pi05_prepare_state_tokenizer_processor_step",
66
+ "config": {}
67
+ },
68
+ {
69
+ "registry_name": "tokenizer_processor",
70
+ "config": {
71
+ "max_length": 200,
72
+ "task_key": "task",
73
+ "padding_side": "right",
74
+ "padding": "max_length",
75
+ "truncation": true,
76
+ "tokenizer_name": "google/paligemma-3b-pt-224"
77
+ }
78
+ },
79
+ {
80
+ "registry_name": "device_processor",
81
+ "config": {
82
+ "device": "cuda",
83
+ "float_dtype": null
84
+ }
85
+ }
86
+ ]
87
+ }
policy_preprocessor_step_2_normalizer_processor.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4da7407d16cb6217e0046c66ac4a2ad644b0a45c64ccfd61a9a51d32236d1db8
3
+ size 12652
train_config.json ADDED
@@ -0,0 +1,256 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset": {
3
+ "repo_id": "local/bi_s1_mix_pick_place_cube_fix_5",
4
+ "root": "/home/sl/wyb-workspace/dataset/bi_s1_mix_pick_place_cube_fix_5",
5
+ "episodes": null,
6
+ "image_transforms": {
7
+ "enable": false,
8
+ "max_num_transforms": 3,
9
+ "random_order": false,
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
+ "return_uint8": false,
81
+ "streaming": false
82
+ },
83
+ "env": null,
84
+ "policy": {
85
+ "type": "pi05",
86
+ "n_obs_steps": 1,
87
+ "input_features": {
88
+ "observation.state": {
89
+ "type": "STATE",
90
+ "shape": [
91
+ 14
92
+ ]
93
+ },
94
+ "observation.images.left": {
95
+ "type": "VISUAL",
96
+ "shape": [
97
+ 3,
98
+ 480,
99
+ 640
100
+ ]
101
+ },
102
+ "observation.images.right": {
103
+ "type": "VISUAL",
104
+ "shape": [
105
+ 3,
106
+ 480,
107
+ 640
108
+ ]
109
+ },
110
+ "observation.images.middle": {
111
+ "type": "VISUAL",
112
+ "shape": [
113
+ 3,
114
+ 480,
115
+ 640
116
+ ]
117
+ }
118
+ },
119
+ "output_features": {
120
+ "action": {
121
+ "type": "ACTION",
122
+ "shape": [
123
+ 14
124
+ ]
125
+ }
126
+ },
127
+ "device": "cuda",
128
+ "use_amp": false,
129
+ "use_peft": false,
130
+ "push_to_hub": false,
131
+ "repo_id": null,
132
+ "private": null,
133
+ "tags": null,
134
+ "license": null,
135
+ "pretrained_path": "lerobot/pi05_base",
136
+ "paligemma_variant": "gemma_2b",
137
+ "action_expert_variant": "gemma_300m",
138
+ "dtype": "bfloat16",
139
+ "chunk_size": 50,
140
+ "n_action_steps": 50,
141
+ "max_state_dim": 32,
142
+ "max_action_dim": 32,
143
+ "num_inference_steps": 10,
144
+ "time_sampling_beta_alpha": 1.5,
145
+ "time_sampling_beta_beta": 1.0,
146
+ "time_sampling_scale": 0.999,
147
+ "time_sampling_offset": 0.001,
148
+ "min_period": 0.004,
149
+ "max_period": 4.0,
150
+ "use_relative_actions": false,
151
+ "relative_exclude_joints": [
152
+ "gripper"
153
+ ],
154
+ "action_feature_names": [
155
+ "left_joint_1.pos",
156
+ "left_joint_2.pos",
157
+ "left_joint_3.pos",
158
+ "left_joint_4.pos",
159
+ "left_joint_5.pos",
160
+ "left_joint_6.pos",
161
+ "left_gripper.pos",
162
+ "right_joint_1.pos",
163
+ "right_joint_2.pos",
164
+ "right_joint_3.pos",
165
+ "right_joint_4.pos",
166
+ "right_joint_5.pos",
167
+ "right_joint_6.pos",
168
+ "right_gripper.pos"
169
+ ],
170
+ "rtc_config": null,
171
+ "image_resolution": [
172
+ 224,
173
+ 224
174
+ ],
175
+ "empty_cameras": 0,
176
+ "tokenizer_max_length": 200,
177
+ "normalization_mapping": {
178
+ "VISUAL": "IDENTITY",
179
+ "STATE": "QUANTILES",
180
+ "ACTION": "QUANTILES"
181
+ },
182
+ "gradient_checkpointing": true,
183
+ "compile_model": true,
184
+ "compile_mode": "max-autotune",
185
+ "freeze_vision_encoder": false,
186
+ "train_expert_only": false,
187
+ "optimizer_lr": 2.5e-05,
188
+ "optimizer_betas": [
189
+ 0.9,
190
+ 0.95
191
+ ],
192
+ "optimizer_eps": 1e-08,
193
+ "optimizer_weight_decay": 0.01,
194
+ "optimizer_grad_clip_norm": 1.0,
195
+ "scheduler_warmup_steps": 1000,
196
+ "scheduler_decay_steps": 30000,
197
+ "scheduler_decay_lr": 2.5e-06
198
+ },
199
+ "output_dir": "outputs/pi05_training",
200
+ "job_name": "pi05_training",
201
+ "resume": false,
202
+ "seed": 1000,
203
+ "cudnn_deterministic": false,
204
+ "num_workers": 4,
205
+ "batch_size": 16,
206
+ "prefetch_factor": 4,
207
+ "persistent_workers": true,
208
+ "steps": 200000,
209
+ "eval_freq": 20000,
210
+ "log_freq": 200,
211
+ "tolerance_s": 0.0001,
212
+ "save_checkpoint": true,
213
+ "save_freq": 5000,
214
+ "use_policy_training_preset": true,
215
+ "optimizer": {
216
+ "type": "adamw",
217
+ "lr": 2.5e-05,
218
+ "weight_decay": 0.01,
219
+ "grad_clip_norm": 1.0,
220
+ "betas": [
221
+ 0.9,
222
+ 0.95
223
+ ],
224
+ "eps": 1e-08
225
+ },
226
+ "scheduler": {
227
+ "type": "cosine_decay_with_warmup",
228
+ "num_warmup_steps": 1000,
229
+ "num_decay_steps": 30000,
230
+ "peak_lr": 2.5e-05,
231
+ "decay_lr": 2.5e-06
232
+ },
233
+ "eval": {
234
+ "n_episodes": 50,
235
+ "batch_size": 22,
236
+ "use_async_envs": true
237
+ },
238
+ "wandb": {
239
+ "enable": false,
240
+ "disable_artifact": false,
241
+ "project": "lerobot",
242
+ "entity": null,
243
+ "notes": null,
244
+ "run_id": null,
245
+ "mode": null,
246
+ "add_tags": true
247
+ },
248
+ "peft": null,
249
+ "use_rabc": false,
250
+ "rabc_progress_path": null,
251
+ "rabc_kappa": 0.01,
252
+ "rabc_epsilon": 1e-06,
253
+ "rabc_head_mode": "sparse",
254
+ "rename_map": {},
255
+ "checkpoint_path": null
256
+ }