Hugging Face's logo

pr0tos
/
smolvla_stack_rb

Safetensors
Model card Files
xet
Community
pr0tos commited on
Commit
3296630
·
verified ·
1 Parent(s): 7b97b26

Upload folder using huggingface_hub

Browse files
Files changed (7) hide show
  1. config.json +105 -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_5_normalizer_processor.safetensors +3 -0
  7. train_config.json +237 -0
config.json ADDED
@@ -0,0 +1,105 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "type": "smolvla",
3
+ "n_obs_steps": 1,
4
+ "input_features": {
5
+ "observation.state": {
6
+ "type": "STATE",
7
+ "shape": [
8
+ 6
9
+ ]
10
+ },
11
+ "observation.images.camera1": {
12
+ "type": "VISUAL",
13
+ "shape": [
14
+ 3,
15
+ 256,
16
+ 256
17
+ ]
18
+ },
19
+ "observation.images.camera2": {
20
+ "type": "VISUAL",
21
+ "shape": [
22
+ 3,
23
+ 256,
24
+ 256
25
+ ]
26
+ },
27
+ "observation.images.camera3": {
28
+ "type": "VISUAL",
29
+ "shape": [
30
+ 3,
31
+ 256,
32
+ 256
33
+ ]
34
+ },
35
+ "observation.images.empty_camera_0": {
36
+ "type": "VISUAL",
37
+ "shape": [
38
+ 3,
39
+ 480,
40
+ 640
41
+ ]
42
+ }
43
+ },
44
+ "output_features": {
45
+ "action": {
46
+ "type": "ACTION",
47
+ "shape": [
48
+ 6
49
+ ]
50
+ }
51
+ },
52
+ "device": "cuda",
53
+ "use_amp": false,
54
+ "push_to_hub": true,
55
+ "repo_id": "pr0tos/my_smolvla",
56
+ "private": null,
57
+ "tags": null,
58
+ "license": null,
59
+ "pretrained_path": "lerobot/smolvla_base",
60
+ "chunk_size": 50,
61
+ "n_action_steps": 50,
62
+ "normalization_mapping": {
63
+ "VISUAL": "IDENTITY",
64
+ "STATE": "MEAN_STD",
65
+ "ACTION": "MEAN_STD"
66
+ },
67
+ "max_state_dim": 32,
68
+ "max_action_dim": 32,
69
+ "resize_imgs_with_padding": [
70
+ 512,
71
+ 512
72
+ ],
73
+ "empty_cameras": 1,
74
+ "adapt_to_pi_aloha": false,
75
+ "use_delta_joint_actions_aloha": false,
76
+ "tokenizer_max_length": 48,
77
+ "num_steps": 10,
78
+ "use_cache": true,
79
+ "freeze_vision_encoder": true,
80
+ "train_expert_only": true,
81
+ "train_state_proj": true,
82
+ "optimizer_lr": 0.0001,
83
+ "optimizer_betas": [
84
+ 0.9,
85
+ 0.95
86
+ ],
87
+ "optimizer_eps": 1e-08,
88
+ "optimizer_weight_decay": 1e-10,
89
+ "optimizer_grad_clip_norm": 10.0,
90
+ "scheduler_warmup_steps": 1000,
91
+ "scheduler_decay_steps": 30000,
92
+ "scheduler_decay_lr": 2.5e-06,
93
+ "vlm_model_name": "HuggingFaceTB/SmolVLM2-500M-Video-Instruct",
94
+ "load_vlm_weights": true,
95
+ "add_image_special_tokens": false,
96
+ "attention_mode": "cross_attn",
97
+ "prefix_length": 0,
98
+ "pad_language_to": "max_length",
99
+ "num_expert_layers": 0,
100
+ "num_vlm_layers": 16,
101
+ "self_attn_every_n_layers": 2,
102
+ "expert_width_multiplier": 0.75,
103
+ "min_period": 0.004,
104
+ "max_period": 4.0
105
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:629a913db80f2219cbf924ab654d4dbfb193adb91f0e80e84483894658819130
3
+ size 906712520
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
+ "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": "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:dca7ae30ceaa4a0ef4b51702d165ba2eeeb05162d4ae29aef4f29fd1f0720941
3
+ size 7520
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.wrist": "observation.images.camera1",
9
+ "observation.images.front": "observation.images.camera2"
10
+ }
11
+ }
12
+ },
13
+ {
14
+ "registry_name": "to_batch_processor",
15
+ "config": {}
16
+ },
17
+ {
18
+ "registry_name": "smolvla_new_line_processor",
19
+ "config": {}
20
+ },
21
+ {
22
+ "registry_name": "tokenizer_processor",
23
+ "config": {
24
+ "max_length": 48,
25
+ "task_key": "task",
26
+ "padding_side": "right",
27
+ "padding": "max_length",
28
+ "truncation": true,
29
+ "tokenizer_name": "HuggingFaceTB/SmolVLM2-500M-Video-Instruct"
30
+ }
31
+ },
32
+ {
33
+ "registry_name": "device_processor",
34
+ "config": {
35
+ "device": "cuda",
36
+ "float_dtype": null
37
+ }
38
+ },
39
+ {
40
+ "registry_name": "normalizer_processor",
41
+ "config": {
42
+ "eps": 1e-08,
43
+ "features": {
44
+ "observation.state": {
45
+ "type": "STATE",
46
+ "shape": [
47
+ 6
48
+ ]
49
+ },
50
+ "observation.images.camera1": {
51
+ "type": "VISUAL",
52
+ "shape": [
53
+ 3,
54
+ 256,
55
+ 256
56
+ ]
57
+ },
58
+ "observation.images.camera2": {
59
+ "type": "VISUAL",
60
+ "shape": [
61
+ 3,
62
+ 256,
63
+ 256
64
+ ]
65
+ },
66
+ "observation.images.camera3": {
67
+ "type": "VISUAL",
68
+ "shape": [
69
+ 3,
70
+ 256,
71
+ 256
72
+ ]
73
+ },
74
+ "observation.images.empty_camera_0": {
75
+ "type": "VISUAL",
76
+ "shape": [
77
+ 3,
78
+ 480,
79
+ 640
80
+ ]
81
+ },
82
+ "action": {
83
+ "type": "ACTION",
84
+ "shape": [
85
+ 6
86
+ ]
87
+ }
88
+ },
89
+ "norm_map": {
90
+ "VISUAL": "IDENTITY",
91
+ "STATE": "MEAN_STD",
92
+ "ACTION": "MEAN_STD"
93
+ }
94
+ },
95
+ "state_file": "policy_preprocessor_step_5_normalizer_processor.safetensors"
96
+ }
97
+ ]
98
+ }
policy_preprocessor_step_5_normalizer_processor.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dca7ae30ceaa4a0ef4b51702d165ba2eeeb05162d4ae29aef4f29fd1f0720941
3
+ size 7520
train_config.json ADDED
@@ -0,0 +1,237 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset": {
3
+ "repo_id": "pr0tos/merged_vla_long_task",
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
+ "streaming": false
81
+ },
82
+ "env": null,
83
+ "policy": {
84
+ "type": "smolvla",
85
+ "n_obs_steps": 1,
86
+ "input_features": {
87
+ "observation.state": {
88
+ "type": "STATE",
89
+ "shape": [
90
+ 6
91
+ ]
92
+ },
93
+ "observation.images.camera1": {
94
+ "type": "VISUAL",
95
+ "shape": [
96
+ 3,
97
+ 256,
98
+ 256
99
+ ]
100
+ },
101
+ "observation.images.camera2": {
102
+ "type": "VISUAL",
103
+ "shape": [
104
+ 3,
105
+ 256,
106
+ 256
107
+ ]
108
+ },
109
+ "observation.images.camera3": {
110
+ "type": "VISUAL",
111
+ "shape": [
112
+ 3,
113
+ 256,
114
+ 256
115
+ ]
116
+ },
117
+ "observation.images.empty_camera_0": {
118
+ "type": "VISUAL",
119
+ "shape": [
120
+ 3,
121
+ 480,
122
+ 640
123
+ ]
124
+ }
125
+ },
126
+ "output_features": {
127
+ "action": {
128
+ "type": "ACTION",
129
+ "shape": [
130
+ 6
131
+ ]
132
+ }
133
+ },
134
+ "device": "cuda",
135
+ "use_amp": false,
136
+ "push_to_hub": true,
137
+ "repo_id": "pr0tos/my_smolvla",
138
+ "private": null,
139
+ "tags": null,
140
+ "license": null,
141
+ "pretrained_path": "lerobot/smolvla_base",
142
+ "chunk_size": 50,
143
+ "n_action_steps": 50,
144
+ "normalization_mapping": {
145
+ "VISUAL": "IDENTITY",
146
+ "STATE": "MEAN_STD",
147
+ "ACTION": "MEAN_STD"
148
+ },
149
+ "max_state_dim": 32,
150
+ "max_action_dim": 32,
151
+ "resize_imgs_with_padding": [
152
+ 512,
153
+ 512
154
+ ],
155
+ "empty_cameras": 1,
156
+ "adapt_to_pi_aloha": false,
157
+ "use_delta_joint_actions_aloha": false,
158
+ "tokenizer_max_length": 48,
159
+ "num_steps": 10,
160
+ "use_cache": true,
161
+ "freeze_vision_encoder": true,
162
+ "train_expert_only": true,
163
+ "train_state_proj": true,
164
+ "optimizer_lr": 0.0001,
165
+ "optimizer_betas": [
166
+ 0.9,
167
+ 0.95
168
+ ],
169
+ "optimizer_eps": 1e-08,
170
+ "optimizer_weight_decay": 1e-10,
171
+ "optimizer_grad_clip_norm": 10.0,
172
+ "scheduler_warmup_steps": 1000,
173
+ "scheduler_decay_steps": 30000,
174
+ "scheduler_decay_lr": 2.5e-06,
175
+ "vlm_model_name": "HuggingFaceTB/SmolVLM2-500M-Video-Instruct",
176
+ "load_vlm_weights": true,
177
+ "add_image_special_tokens": false,
178
+ "attention_mode": "cross_attn",
179
+ "prefix_length": 0,
180
+ "pad_language_to": "max_length",
181
+ "num_expert_layers": 0,
182
+ "num_vlm_layers": 16,
183
+ "self_attn_every_n_layers": 2,
184
+ "expert_width_multiplier": 0.75,
185
+ "min_period": 0.004,
186
+ "max_period": 4.0
187
+ },
188
+ "output_dir": "outputs/train/my_smolvla_2",
189
+ "job_name": "my_smolvla_training",
190
+ "resume": false,
191
+ "seed": 1000,
192
+ "num_workers": 4,
193
+ "batch_size": 64,
194
+ "steps": 100000,
195
+ "eval_freq": 20000,
196
+ "log_freq": 200,
197
+ "save_checkpoint": true,
198
+ "save_freq": 20000,
199
+ "use_policy_training_preset": true,
200
+ "optimizer": {
201
+ "type": "adamw",
202
+ "lr": 0.0001,
203
+ "weight_decay": 1e-10,
204
+ "grad_clip_norm": 10.0,
205
+ "betas": [
206
+ 0.9,
207
+ 0.95
208
+ ],
209
+ "eps": 1e-08
210
+ },
211
+ "scheduler": {
212
+ "type": "cosine_decay_with_warmup",
213
+ "num_warmup_steps": 1000,
214
+ "num_decay_steps": 30000,
215
+ "peak_lr": 0.0001,
216
+ "decay_lr": 2.5e-06
217
+ },
218
+ "eval": {
219
+ "n_episodes": 50,
220
+ "batch_size": 50,
221
+ "use_async_envs": false
222
+ },
223
+ "wandb": {
224
+ "enable": false,
225
+ "disable_artifact": false,
226
+ "project": "lerobot",
227
+ "entity": null,
228
+ "notes": null,
229
+ "run_id": null,
230
+ "mode": null
231
+ },
232
+ "checkpoint_path": null,
233
+ "rename_map": {
234
+ "observation.images.wrist": "observation.images.camera1",
235
+ "observation.images.front": "observation.images.camera2"
236
+ }
237
+ }