Hugging Face's logo

jadechoghari
/
pi-full-lib-80k

Safetensors
Model card Files
xet
 Community
jadechoghari commited on
Commit
064d8ca
·
verified ·
1 Parent(s): 42af76a

Upload folder using huggingface_hub

Browse files
Files changed (7) hide show
  1. config.json +109 -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 +106 -0
  6. policy_preprocessor_step_2_normalizer_processor.safetensors +3 -0
  7. train_config.json +248 -0
config.json ADDED
@@ -0,0 +1,109 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "type": "pi05_full",
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
+ "observation.images.empty_camera_0": {
36
+ "type": "VISUAL",
37
+ "shape": [
38
+ 3,
39
+ 224,
40
+ 224
41
+ ]
42
+ }
43
+ },
44
+ "output_features": {
45
+ "action": {
46
+ "type": "ACTION",
47
+ "shape": [
48
+ 7
49
+ ]
50
+ }
51
+ },
52
+ "device": "cuda",
53
+ "use_amp": false,
54
+ "use_peft": false,
55
+ "push_to_hub": true,
56
+ "repo_id": "jadechoghari/pi05-libero-10",
57
+ "private": null,
58
+ "tags": null,
59
+ "license": null,
60
+ "pretrained_path": "/fsx/jade_choghari/models/pi05-base",
61
+ "paligemma_variant": "gemma_2b",
62
+ "action_expert_variant": "gemma_300m",
63
+ "dtype": "bfloat16",
64
+ "chunk_size": 10,
65
+ "n_action_steps": 10,
66
+ "max_state_dim": 32,
67
+ "max_action_dim": 32,
68
+ "num_inference_steps": 10,
69
+ "time_sampling_beta_alpha": 1.5,
70
+ "time_sampling_beta_beta": 1.0,
71
+ "time_sampling_scale": 0.999,
72
+ "time_sampling_offset": 0.001,
73
+ "min_period": 0.004,
74
+ "max_period": 4.0,
75
+ "rtc_config": null,
76
+ "image_resolution": [
77
+ 224,
78
+ 224
79
+ ],
80
+ "empty_cameras": 1,
81
+ "normalization_mapping": {
82
+ "VISUAL": "IDENTITY",
83
+ "STATE": "MEAN_STD",
84
+ "ACTION": "MEAN_STD"
85
+ },
86
+ "action_tokenizer_name": "physical-intelligence/fast",
87
+ "text_tokenizer_name": "google/paligemma-3b-pt-224",
88
+ "max_action_tokens": 256,
89
+ "fast_skip_tokens": 128,
90
+ "max_decoding_steps": 200,
91
+ "temperature": 0.0,
92
+ "gradient_checkpointing": true,
93
+ "compile_model": true,
94
+ "compile_mode": "max-autotune",
95
+ "freeze_vision_encoder": false,
96
+ "train_expert_only": false,
97
+ "optimizer_lr": 2.5e-05,
98
+ "optimizer_betas": [
99
+ 0.9,
100
+ 0.95
101
+ ],
102
+ "optimizer_eps": 1e-08,
103
+ "optimizer_weight_decay": 0.01,
104
+ "optimizer_grad_clip_norm": 1.0,
105
+ "scheduler_warmup_steps": 4000,
106
+ "scheduler_decay_steps": 100000,
107
+ "scheduler_decay_lr": 1e-05,
108
+ "tokenizer_max_length": 48
109
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c52220a70efa318939f227438b0e55fadb5fb48361194d11a16d613d7448300
3
+ size 7473096344
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
+ 7
13
+ ]
14
+ }
15
+ },
16
+ "norm_map": {
17
+ "VISUAL": "IDENTITY",
18
+ "STATE": "MEAN_STD",
19
+ "ACTION": "MEAN_STD"
20
+ }
21
+ },
22
+ "state_file": "policy_postprocessor_step_0_unnormalizer_processor.safetensors"
23
+ },
24
+ {
25
+ "registry_name": "device_processor",
26
+ "config": {
27
+ "device": "cuda",
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 sha256:362bec11490a5dcbe22158ca42260c64ed67ca7090e6f1ba887338e8794a3024
3
+ size 3836
policy_preprocessor.json ADDED
@@ -0,0 +1,106 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "name": "policy_preprocessor",
3
+ "steps": [
4
+ {
5
+ "registry_name": "rename_observations_processor",
6
+ "config": {
7
+ "rename_map": {
8
+ "observation.images.image": "observation.images.base_0_rgb",
9
+ "observation.images.image2": "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
+ "observation.images.empty_camera_0": {
53
+ "type": "VISUAL",
54
+ "shape": [
55
+ 3,
56
+ 224,
57
+ 224
58
+ ]
59
+ },
60
+ "action": {
61
+ "type": "ACTION",
62
+ "shape": [
63
+ 7
64
+ ]
65
+ }
66
+ },
67
+ "norm_map": {
68
+ "VISUAL": "IDENTITY",
69
+ "STATE": "MEAN_STD",
70
+ "ACTION": "MEAN_STD"
71
+ }
72
+ },
73
+ "state_file": "policy_preprocessor_step_2_normalizer_processor.safetensors"
74
+ },
75
+ {
76
+ "registry_name": "pi05_full_prepare_state_tokenizer_processor_step",
77
+ "config": {}
78
+ },
79
+ {
80
+ "registry_name": "tokenizer_processor",
81
+ "config": {
82
+ "max_length": 48,
83
+ "task_key": "task",
84
+ "padding_side": "right",
85
+ "padding": "max_length",
86
+ "truncation": true,
87
+ "tokenizer_name": "google/paligemma-3b-pt-224"
88
+ }
89
+ },
90
+ {
91
+ "registry_name": "action_tokenizer_processor",
92
+ "config": {
93
+ "trust_remote_code": true,
94
+ "max_action_tokens": 256,
95
+ "action_tokenizer_name": "physical-intelligence/fast"
96
+ }
97
+ },
98
+ {
99
+ "registry_name": "device_processor",
100
+ "config": {
101
+ "device": "cuda",
102
+ "float_dtype": null
103
+ }
104
+ }
105
+ ]
106
+ }
policy_preprocessor_step_2_normalizer_processor.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:362bec11490a5dcbe22158ca42260c64ed67ca7090e6f1ba887338e8794a3024
3
+ size 3836
train_config.json ADDED
@@ -0,0 +1,248 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset": {
3
+ "repo_id": "local",
4
+ "root": "/fsx/jade_choghari/outputs/libero-10-annotate",
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
+ "streaming": false
81
+ },
82
+ "env": null,
83
+ "policy": {
84
+ "type": "pi05_full",
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
+ "observation.images.empty_camera_0": {
118
+ "type": "VISUAL",
119
+ "shape": [
120
+ 3,
121
+ 224,
122
+ 224
123
+ ]
124
+ }
125
+ },
126
+ "output_features": {
127
+ "action": {
128
+ "type": "ACTION",
129
+ "shape": [
130
+ 7
131
+ ]
132
+ }
133
+ },
134
+ "device": "cuda",
135
+ "use_amp": false,
136
+ "use_peft": false,
137
+ "push_to_hub": true,
138
+ "repo_id": "jadechoghari/pi05-libero-10",
139
+ "private": null,
140
+ "tags": null,
141
+ "license": null,
142
+ "pretrained_path": "/fsx/jade_choghari/models/pi05-base",
143
+ "paligemma_variant": "gemma_2b",
144
+ "action_expert_variant": "gemma_300m",
145
+ "dtype": "bfloat16",
146
+ "chunk_size": 10,
147
+ "n_action_steps": 10,
148
+ "max_state_dim": 32,
149
+ "max_action_dim": 32,
150
+ "num_inference_steps": 10,
151
+ "time_sampling_beta_alpha": 1.5,
152
+ "time_sampling_beta_beta": 1.0,
153
+ "time_sampling_scale": 0.999,
154
+ "time_sampling_offset": 0.001,
155
+ "min_period": 0.004,
156
+ "max_period": 4.0,
157
+ "rtc_config": null,
158
+ "image_resolution": [
159
+ 224,
160
+ 224
161
+ ],
162
+ "empty_cameras": 1,
163
+ "normalization_mapping": {
164
+ "VISUAL": "IDENTITY",
165
+ "STATE": "MEAN_STD",
166
+ "ACTION": "MEAN_STD"
167
+ },
168
+ "action_tokenizer_name": "physical-intelligence/fast",
169
+ "text_tokenizer_name": "google/paligemma-3b-pt-224",
170
+ "max_action_tokens": 256,
171
+ "fast_skip_tokens": 128,
172
+ "max_decoding_steps": 200,
173
+ "temperature": 0.0,
174
+ "gradient_checkpointing": true,
175
+ "compile_model": true,
176
+ "compile_mode": "max-autotune",
177
+ "freeze_vision_encoder": false,
178
+ "train_expert_only": false,
179
+ "optimizer_lr": 2.5e-05,
180
+ "optimizer_betas": [
181
+ 0.9,
182
+ 0.95
183
+ ],
184
+ "optimizer_eps": 1e-08,
185
+ "optimizer_weight_decay": 0.01,
186
+ "optimizer_grad_clip_norm": 1.0,
187
+ "scheduler_warmup_steps": 4000,
188
+ "scheduler_decay_steps": 100000,
189
+ "scheduler_decay_lr": 1e-05,
190
+ "tokenizer_max_length": 48
191
+ },
192
+ "output_dir": "/fsx/jade_choghari/outputs/pi05_libero_10_training",
193
+ "job_name": "pi05_libero_10",
194
+ "resume": false,
195
+ "seed": 1000,
196
+ "num_workers": 4,
197
+ "batch_size": 16,
198
+ "steps": 100000,
199
+ "eval_freq": 20000,
200
+ "log_freq": 200,
201
+ "tolerance_s": 0.0001,
202
+ "save_checkpoint": true,
203
+ "save_freq": 20000,
204
+ "use_policy_training_preset": true,
205
+ "optimizer": {
206
+ "type": "adamw",
207
+ "lr": 2.5e-05,
208
+ "weight_decay": 0.01,
209
+ "grad_clip_norm": 1.0,
210
+ "betas": [
211
+ 0.9,
212
+ 0.95
213
+ ],
214
+ "eps": 1e-08
215
+ },
216
+ "scheduler": {
217
+ "type": "cosine_decay_with_warmup",
218
+ "num_warmup_steps": 4000,
219
+ "num_decay_steps": 100000,
220
+ "peak_lr": 2.5e-05,
221
+ "decay_lr": 1e-05
222
+ },
223
+ "eval": {
224
+ "n_episodes": 50,
225
+ "batch_size": 50,
226
+ "use_async_envs": false
227
+ },
228
+ "wandb": {
229
+ "enable": true,
230
+ "disable_artifact": true,
231
+ "project": "pi05-full",
232
+ "entity": null,
233
+ "notes": null,
234
+ "run_id": "ynqa3nxj",
235
+ "mode": null
236
+ },
237
+ "peft": null,
238
+ "use_rabc": false,
239
+ "rabc_progress_path": null,
240
+ "rabc_kappa": 0.01,
241
+ "rabc_epsilon": 1e-06,
242
+ "rabc_head_mode": "sparse",
243
+ "rename_map": {
244
+ "observation.images.image": "observation.images.base_0_rgb",
245
+ "observation.images.image2": "observation.images.left_wrist_0_rgb"
246
+ },
247
+ "checkpoint_path": null
248
+ }