Hugging Face's logo

mddoai
/
pi05_openarm_vision

Robotics
LeRobot
Safetensors
pi05
Model card Files
xet
 Community
mddoai commited on
Commit
0170d42
·
verified ·
1 Parent(s): 7cd8f75

Upload folder using huggingface_hub

Browse files
Files changed (7) hide show
  1. checkpoints/040000/pretrained_model/config.json +117 -0
  2. checkpoints/040000/pretrained_model/model.safetensors +3 -0
  3. checkpoints/040000/pretrained_model/policy_postprocessor.json +32 -0
  4. checkpoints/040000/pretrained_model/policy_postprocessor_step_0_unnormalizer_processor.safetensors +3 -0
  5. checkpoints/040000/pretrained_model/policy_preprocessor.json +87 -0
  6. checkpoints/040000/pretrained_model/policy_preprocessor_step_2_normalizer_processor.safetensors +3 -0
  7. checkpoints/040000/pretrained_model/train_config.json +255 -0
checkpoints/040000/pretrained_model/config.json ADDED
@@ -0,0 +1,117 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "type": "pi05",
3
+ "n_obs_steps": 1,
4
+ "input_features": {
5
+ "observation.state": {
6
+ "type": "STATE",
7
+ "shape": [
8
+ 16
9
+ ]
10
+ },
11
+ "observation.images.base": {
12
+ "type": "VISUAL",
13
+ "shape": [
14
+ 3,
15
+ 480,
16
+ 640
17
+ ]
18
+ },
19
+ "observation.images.right_wrist": {
20
+ "type": "VISUAL",
21
+ "shape": [
22
+ 3,
23
+ 480,
24
+ 640
25
+ ]
26
+ },
27
+ "observation.images.left_wrist": {
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
+ 16
41
+ ]
42
+ }
43
+ },
44
+ "device": "cuda",
45
+ "use_amp": false,
46
+ "use_peft": false,
47
+ "push_to_hub": true,
48
+ "repo_id": "mddoai/pi05_openarm_vision",
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
+ "openarm_left_joint1",
73
+ "openarm_left_joint2",
74
+ "openarm_left_joint3",
75
+ "openarm_left_joint4",
76
+ "openarm_left_joint5",
77
+ "openarm_left_joint6",
78
+ "openarm_left_joint7",
79
+ "openarm_left_gripper",
80
+ "openarm_right_joint1",
81
+ "openarm_right_joint2",
82
+ "openarm_right_joint3",
83
+ "openarm_right_joint4",
84
+ "openarm_right_joint5",
85
+ "openarm_right_joint6",
86
+ "openarm_right_joint7",
87
+ "openarm_right_gripper"
88
+ ],
89
+ "rtc_config": null,
90
+ "image_resolution": [
91
+ 224,
92
+ 224
93
+ ],
94
+ "empty_cameras": 0,
95
+ "tokenizer_max_length": 200,
96
+ "normalization_mapping": {
97
+ "VISUAL": "IDENTITY",
98
+ "STATE": "QUANTILES",
99
+ "ACTION": "QUANTILES"
100
+ },
101
+ "gradient_checkpointing": true,
102
+ "compile_model": true,
103
+ "compile_mode": "max-autotune",
104
+ "freeze_vision_encoder": false,
105
+ "train_expert_only": false,
106
+ "optimizer_lr": 2.5e-05,
107
+ "optimizer_betas": [
108
+ 0.9,
109
+ 0.95
110
+ ],
111
+ "optimizer_eps": 1e-08,
112
+ "optimizer_weight_decay": 0.01,
113
+ "optimizer_grad_clip_norm": 1.0,
114
+ "scheduler_warmup_steps": 1000,
115
+ "scheduler_decay_steps": 30000,
116
+ "scheduler_decay_lr": 2.5e-06
117
+ }
checkpoints/040000/pretrained_model/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59d1327714fc13f98b42a201742d0be0ff7f7c2343e9241ea3a3fa7207a029a4
3
+ size 9354050752
checkpoints/040000/pretrained_model/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
+ 16
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
+ }
checkpoints/040000/pretrained_model/policy_postprocessor_step_0_unnormalizer_processor.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7d269bc7c6e5602cc97a16f73dec2a2b0920553a6c334c79bd08ab1eeaf3eb0
3
+ size 9456
checkpoints/040000/pretrained_model/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
+ 16
23
+ ]
24
+ },
25
+ "observation.images.base": {
26
+ "type": "VISUAL",
27
+ "shape": [
28
+ 3,
29
+ 480,
30
+ 640
31
+ ]
32
+ },
33
+ "observation.images.right_wrist": {
34
+ "type": "VISUAL",
35
+ "shape": [
36
+ 3,
37
+ 480,
38
+ 640
39
+ ]
40
+ },
41
+ "observation.images.left_wrist": {
42
+ "type": "VISUAL",
43
+ "shape": [
44
+ 3,
45
+ 480,
46
+ 640
47
+ ]
48
+ },
49
+ "action": {
50
+ "type": "ACTION",
51
+ "shape": [
52
+ 16
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
+ }
checkpoints/040000/pretrained_model/policy_preprocessor_step_2_normalizer_processor.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26e6bf8e62ca86eabdbbba7960bf0055ea4218bb1bc21b70f60aeec9303c438d
3
+ size 9464
checkpoints/040000/pretrained_model/train_config.json ADDED
@@ -0,0 +1,255 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset": {
3
+ "repo_id": "mddoai/openarm_2026-05-14_clean",
4
+ "root": null,
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
+ 16
92
+ ]
93
+ },
94
+ "observation.images.base": {
95
+ "type": "VISUAL",
96
+ "shape": [
97
+ 3,
98
+ 480,
99
+ 640
100
+ ]
101
+ },
102
+ "observation.images.right_wrist": {
103
+ "type": "VISUAL",
104
+ "shape": [
105
+ 3,
106
+ 480,
107
+ 640
108
+ ]
109
+ },
110
+ "observation.images.left_wrist": {
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
+ 16
124
+ ]
125
+ }
126
+ },
127
+ "device": "cuda",
128
+ "use_amp": false,
129
+ "use_peft": false,
130
+ "push_to_hub": true,
131
+ "repo_id": "mddoai/pi05_openarm_vision",
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
+ "openarm_left_joint1",
156
+ "openarm_left_joint2",
157
+ "openarm_left_joint3",
158
+ "openarm_left_joint4",
159
+ "openarm_left_joint5",
160
+ "openarm_left_joint6",
161
+ "openarm_left_joint7",
162
+ "openarm_left_gripper",
163
+ "openarm_right_joint1",
164
+ "openarm_right_joint2",
165
+ "openarm_right_joint3",
166
+ "openarm_right_joint4",
167
+ "openarm_right_joint5",
168
+ "openarm_right_joint6",
169
+ "openarm_right_joint7",
170
+ "openarm_right_gripper"
171
+ ],
172
+ "rtc_config": null,
173
+ "image_resolution": [
174
+ 224,
175
+ 224
176
+ ],
177
+ "empty_cameras": 0,
178
+ "tokenizer_max_length": 200,
179
+ "normalization_mapping": {
180
+ "VISUAL": "IDENTITY",
181
+ "STATE": "QUANTILES",
182
+ "ACTION": "QUANTILES"
183
+ },
184
+ "gradient_checkpointing": true,
185
+ "compile_model": true,
186
+ "compile_mode": "max-autotune",
187
+ "freeze_vision_encoder": false,
188
+ "train_expert_only": false,
189
+ "optimizer_lr": 2.5e-05,
190
+ "optimizer_betas": [
191
+ 0.9,
192
+ 0.95
193
+ ],
194
+ "optimizer_eps": 1e-08,
195
+ "optimizer_weight_decay": 0.01,
196
+ "optimizer_grad_clip_norm": 1.0,
197
+ "scheduler_warmup_steps": 1000,
198
+ "scheduler_decay_steps": 30000,
199
+ "scheduler_decay_lr": 2.5e-06
200
+ },
201
+ "reward_model": null,
202
+ "output_dir": "/workspace/outputs/pi05_openarm_vision",
203
+ "job_name": "pi05_openarm_vision",
204
+ "resume": false,
205
+ "seed": 1000,
206
+ "cudnn_deterministic": false,
207
+ "num_workers": 4,
208
+ "batch_size": 16,
209
+ "prefetch_factor": 4,
210
+ "persistent_workers": true,
211
+ "steps": 40000,
212
+ "eval_freq": 20000,
213
+ "log_freq": 200,
214
+ "tolerance_s": 0.0001,
215
+ "save_checkpoint": true,
216
+ "save_freq": 5000,
217
+ "use_policy_training_preset": true,
218
+ "optimizer": {
219
+ "type": "adamw",
220
+ "lr": 2.5e-05,
221
+ "weight_decay": 0.01,
222
+ "grad_clip_norm": 1.0,
223
+ "betas": [
224
+ 0.9,
225
+ 0.95
226
+ ],
227
+ "eps": 1e-08
228
+ },
229
+ "scheduler": {
230
+ "type": "cosine_decay_with_warmup",
231
+ "num_warmup_steps": 1000,
232
+ "num_decay_steps": 30000,
233
+ "peak_lr": 2.5e-05,
234
+ "decay_lr": 2.5e-06
235
+ },
236
+ "eval": {
237
+ "n_episodes": 50,
238
+ "batch_size": 50,
239
+ "use_async_envs": true
240
+ },
241
+ "wandb": {
242
+ "enable": true,
243
+ "disable_artifact": true,
244
+ "project": "lerobot",
245
+ "entity": null,
246
+ "notes": null,
247
+ "run_id": "q4eucuk7",
248
+ "mode": null,
249
+ "add_tags": true
250
+ },
251
+ "peft": null,
252
+ "sample_weighting": null,
253
+ "rename_map": {},
254
+ "checkpoint_path": null
255
+ }