Hugging Face's logo

jadechoghari
/
pi05-vi-lib

Safetensors
Model card Files
xet
 Community
jadechoghari commited on
Commit
8de25a6
·
verified ·
1 Parent(s): 3d3ac62

Upload folder using huggingface_hub

Browse files
Files changed (7) hide show
  1. config.json +112 -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 +98 -0
  6. policy_preprocessor_step_2_normalizer_processor.safetensors +3 -0
  7. train_config.json +251 -0
config.json ADDED
@@ -0,0 +1,112 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "type": "pi05_video",
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": "jade_choghari/pi05-video-libero",
57
+ "private": null,
58
+ "tags": null,
59
+ "license": null,
60
+ "pretrained_path": "/fsx/jade_choghari/models/pi05-video",
61
+ "paligemma_variant": "gemma_2b",
62
+ "action_expert_variant": "gemma_300m",
63
+ "dtype": "bfloat16",
64
+ "chunk_size": 10,
65
+ "n_action_steps": 10,
66
+ "use_video_encoder": true,
67
+ "video_num_frames": 16,
68
+ "videoprism_model_name": "MHRDYN7/videoprism-base-f16r288",
69
+ "videoprism_image_size": 288,
70
+ "freeze_video_encoder": true,
71
+ "video_padding_mode": "repeat",
72
+ "video_encoder_camera_key": null,
73
+ "video_num_latents": 256,
74
+ "video_resampler_num_heads": 8,
75
+ "max_state_dim": 32,
76
+ "max_action_dim": 32,
77
+ "num_inference_steps": 10,
78
+ "time_sampling_beta_alpha": 1.5,
79
+ "time_sampling_beta_beta": 1.0,
80
+ "time_sampling_scale": 0.999,
81
+ "time_sampling_offset": 0.001,
82
+ "min_period": 0.004,
83
+ "max_period": 4.0,
84
+ "rtc_config": null,
85
+ "image_resolution": [
86
+ 224,
87
+ 224
88
+ ],
89
+ "empty_cameras": 1,
90
+ "tokenizer_max_length": 200,
91
+ "normalization_mapping": {
92
+ "VISUAL": "IDENTITY",
93
+ "STATE": "QUANTILES",
94
+ "ACTION": "QUANTILES"
95
+ },
96
+ "gradient_checkpointing": true,
97
+ "compile_model": false,
98
+ "compile_mode": "max-autotune",
99
+ "freeze_vision_encoder": false,
100
+ "train_expert_only": false,
101
+ "optimizer_lr": 2.5e-05,
102
+ "optimizer_betas": [
103
+ 0.9,
104
+ 0.95
105
+ ],
106
+ "optimizer_eps": 1e-08,
107
+ "optimizer_weight_decay": 0.01,
108
+ "optimizer_grad_clip_norm": 1.0,
109
+ "scheduler_warmup_steps": 4000,
110
+ "scheduler_decay_steps": 100000,
111
+ "scheduler_decay_lr": 1e-05
112
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47bbaddbbcbdea721641851a59f887ad7caa02b8b03ceaa44728f1d222ffe97c
3
+ size 7718413728
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": "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:a002c0df7f79c5b169c5a899ad151d4ea1bed246c7d82bd93ed1556558d517a9
3
+ size 7668
policy_preprocessor.json ADDED
@@ -0,0 +1,98 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "QUANTILES",
70
+ "ACTION": "QUANTILES"
71
+ }
72
+ },
73
+ "state_file": "policy_preprocessor_step_2_normalizer_processor.safetensors"
74
+ },
75
+ {
76
+ "registry_name": "pi05_prepare_state_tokenizer_processor_step",
77
+ "config": {}
78
+ },
79
+ {
80
+ "registry_name": "tokenizer_processor",
81
+ "config": {
82
+ "max_length": 200,
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": "device_processor",
92
+ "config": {
93
+ "device": "cuda",
94
+ "float_dtype": null
95
+ }
96
+ }
97
+ ]
98
+ }
policy_preprocessor_step_2_normalizer_processor.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a002c0df7f79c5b169c5a899ad151d4ea1bed246c7d82bd93ed1556558d517a9
3
+ size 7668
train_config.json ADDED
@@ -0,0 +1,251 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset": {
3
+ "repo_id": "local",
4
+ "root": "/fsx/jade_choghari/data/libero",
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_video",
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": "jade_choghari/pi05-video-libero",
139
+ "private": null,
140
+ "tags": null,
141
+ "license": null,
142
+ "pretrained_path": "/fsx/jade_choghari/models/pi05-video",
143
+ "paligemma_variant": "gemma_2b",
144
+ "action_expert_variant": "gemma_300m",
145
+ "dtype": "bfloat16",
146
+ "chunk_size": 10,
147
+ "n_action_steps": 10,
148
+ "use_video_encoder": true,
149
+ "video_num_frames": 16,
150
+ "videoprism_model_name": "MHRDYN7/videoprism-base-f16r288",
151
+ "videoprism_image_size": 288,
152
+ "freeze_video_encoder": true,
153
+ "video_padding_mode": "repeat",
154
+ "video_encoder_camera_key": null,
155
+ "video_num_latents": 256,
156
+ "video_resampler_num_heads": 8,
157
+ "max_state_dim": 32,
158
+ "max_action_dim": 32,
159
+ "num_inference_steps": 10,
160
+ "time_sampling_beta_alpha": 1.5,
161
+ "time_sampling_beta_beta": 1.0,
162
+ "time_sampling_scale": 0.999,
163
+ "time_sampling_offset": 0.001,
164
+ "min_period": 0.004,
165
+ "max_period": 4.0,
166
+ "rtc_config": null,
167
+ "image_resolution": [
168
+ 224,
169
+ 224
170
+ ],
171
+ "empty_cameras": 1,
172
+ "tokenizer_max_length": 200,
173
+ "normalization_mapping": {
174
+ "VISUAL": "IDENTITY",
175
+ "STATE": "QUANTILES",
176
+ "ACTION": "QUANTILES"
177
+ },
178
+ "gradient_checkpointing": true,
179
+ "compile_model": false,
180
+ "compile_mode": "max-autotune",
181
+ "freeze_vision_encoder": false,
182
+ "train_expert_only": false,
183
+ "optimizer_lr": 2.5e-05,
184
+ "optimizer_betas": [
185
+ 0.9,
186
+ 0.95
187
+ ],
188
+ "optimizer_eps": 1e-08,
189
+ "optimizer_weight_decay": 0.01,
190
+ "optimizer_grad_clip_norm": 1.0,
191
+ "scheduler_warmup_steps": 4000,
192
+ "scheduler_decay_steps": 100000,
193
+ "scheduler_decay_lr": 1e-05
194
+ },
195
+ "output_dir": "/fsx/jade_choghari/outputs/libero_training_pi05_video",
196
+ "job_name": "libero_training_pi05_video",
197
+ "resume": false,
198
+ "seed": 1000,
199
+ "num_workers": 4,
200
+ "batch_size": 4,
201
+ "steps": 100000,
202
+ "eval_freq": 20000,
203
+ "log_freq": 200,
204
+ "tolerance_s": 0.0001,
205
+ "save_checkpoint": true,
206
+ "save_freq": 20000,
207
+ "use_policy_training_preset": true,
208
+ "optimizer": {
209
+ "type": "adamw",
210
+ "lr": 2.5e-05,
211
+ "weight_decay": 0.01,
212
+ "grad_clip_norm": 1.0,
213
+ "betas": [
214
+ 0.9,
215
+ 0.95
216
+ ],
217
+ "eps": 1e-08
218
+ },
219
+ "scheduler": {
220
+ "type": "cosine_decay_with_warmup",
221
+ "num_warmup_steps": 4000,
222
+ "num_decay_steps": 100000,
223
+ "peak_lr": 2.5e-05,
224
+ "decay_lr": 1e-05
225
+ },
226
+ "eval": {
227
+ "n_episodes": 50,
228
+ "batch_size": 50,
229
+ "use_async_envs": false
230
+ },
231
+ "wandb": {
232
+ "enable": true,
233
+ "disable_artifact": true,
234
+ "project": "pi05-video-libero-training",
235
+ "entity": null,
236
+ "notes": null,
237
+ "run_id": "hltndrsg",
238
+ "mode": null
239
+ },
240
+ "peft": null,
241
+ "use_rabc": false,
242
+ "rabc_progress_path": null,
243
+ "rabc_kappa": 0.01,
244
+ "rabc_epsilon": 1e-06,
245
+ "rabc_head_mode": "sparse",
246
+ "rename_map": {
247
+ "observation.images.image": "observation.images.base_0_rgb",
248
+ "observation.images.image2": "observation.images.left_wrist_0_rgb"
249
+ },
250
+ "checkpoint_path": null
251
+ }