Hugging Face's logo

Cache-SCA
/
smol_CaP_pnp_10fps

Safetensors
Model card Files
xet
 Community
HyeonseokE commited on
Commit
8b82dc4
·
verified ·
1 Parent(s): a6e61a0

Upload folder using huggingface_hub

Browse files
Files changed (7) hide show
  1. config.json +107 -0
  2. model.safetensors +3 -0
  3. policy_postprocessor.json +38 -0
  4. policy_postprocessor_step_0_unnormalizer_processor.safetensors +3 -0
  5. policy_preprocessor.json +96 -0
  6. policy_preprocessor_step_5_normalizer_processor.safetensors +3 -0
  7. train_config.json +249 -0
config.json ADDED
@@ -0,0 +1,107 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ },
36
+ "output_features": {
37
+ "action": {
38
+ "type": "ACTION",
39
+ "shape": [
40
+ 6
41
+ ]
42
+ },
43
+ "action.radian_urdf0": {
44
+ "type": "ACTION",
45
+ "shape": [
46
+ 6
47
+ ]
48
+ }
49
+ },
50
+ "device": "cuda",
51
+ "use_amp": false,
52
+ "use_peft": false,
53
+ "push_to_hub": false,
54
+ "repo_id": null,
55
+ "private": null,
56
+ "tags": null,
57
+ "license": null,
58
+ "pretrained_path": "lerobot/smolvla_base",
59
+ "chunk_size": 50,
60
+ "n_action_steps": 50,
61
+ "normalization_mapping": {
62
+ "VISUAL": "IDENTITY",
63
+ "STATE": "MEAN_STD",
64
+ "ACTION": "MEAN_STD"
65
+ },
66
+ "max_state_dim": 32,
67
+ "max_action_dim": 32,
68
+ "resize_imgs_with_padding": [
69
+ 512,
70
+ 512
71
+ ],
72
+ "empty_cameras": 0,
73
+ "adapt_to_pi_aloha": false,
74
+ "use_delta_joint_actions_aloha": false,
75
+ "tokenizer_max_length": 48,
76
+ "num_steps": 50,
77
+ "use_cache": true,
78
+ "freeze_vision_encoder": true,
79
+ "train_expert_only": true,
80
+ "train_state_proj": true,
81
+ "optimizer_lr": 0.0001,
82
+ "optimizer_betas": [
83
+ 0.9,
84
+ 0.95
85
+ ],
86
+ "optimizer_eps": 1e-08,
87
+ "optimizer_weight_decay": 1e-10,
88
+ "optimizer_grad_clip_norm": 10.0,
89
+ "scheduler_warmup_steps": 1000,
90
+ "scheduler_decay_steps": 30000,
91
+ "scheduler_decay_lr": 2.5e-06,
92
+ "vlm_model_name": "HuggingFaceTB/SmolVLM2-500M-Video-Instruct",
93
+ "load_vlm_weights": true,
94
+ "add_image_special_tokens": false,
95
+ "attention_mode": "cross_attn",
96
+ "prefix_length": 0,
97
+ "pad_language_to": "max_length",
98
+ "num_expert_layers": 0,
99
+ "num_vlm_layers": 16,
100
+ "self_attn_every_n_layers": 2,
101
+ "expert_width_multiplier": 0.75,
102
+ "min_period": 0.004,
103
+ "max_period": 4.0,
104
+ "rtc_config": null,
105
+ "compile_model": false,
106
+ "compile_mode": "max-autotune"
107
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:751a8b0f59fcb48b4aed42d3939b7cf12f967c171483d5c5b4a7bf24c8033e1c
3
+ size 906712520
policy_postprocessor.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "action.radian_urdf0": {
16
+ "type": "ACTION",
17
+ "shape": [
18
+ 6
19
+ ]
20
+ }
21
+ },
22
+ "norm_map": {
23
+ "VISUAL": "IDENTITY",
24
+ "STATE": "MEAN_STD",
25
+ "ACTION": "MEAN_STD"
26
+ }
27
+ },
28
+ "state_file": "policy_postprocessor_step_0_unnormalizer_processor.safetensors"
29
+ },
30
+ {
31
+ "registry_name": "device_processor",
32
+ "config": {
33
+ "device": "cpu",
34
+ "float_dtype": null
35
+ }
36
+ }
37
+ ]
38
+ }
policy_postprocessor_step_0_unnormalizer_processor.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4877a42c59e375ee6c0ddfcc75e05185cac831a038ce0122e5c1cea516c84407
3
+ size 16796
policy_preprocessor.json ADDED
@@ -0,0 +1,96 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "name": "policy_preprocessor",
3
+ "steps": [
4
+ {
5
+ "registry_name": "rename_observations_processor",
6
+ "config": {
7
+ "rename_map": {
8
+ "observation.images.left_wrist": "observation.images.camera1",
9
+ "observation.images.top": "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
+ "action": {
75
+ "type": "ACTION",
76
+ "shape": [
77
+ 6
78
+ ]
79
+ },
80
+ "action.radian_urdf0": {
81
+ "type": "ACTION",
82
+ "shape": [
83
+ 6
84
+ ]
85
+ }
86
+ },
87
+ "norm_map": {
88
+ "VISUAL": "IDENTITY",
89
+ "STATE": "MEAN_STD",
90
+ "ACTION": "MEAN_STD"
91
+ }
92
+ },
93
+ "state_file": "policy_preprocessor_step_5_normalizer_processor.safetensors"
94
+ }
95
+ ]
96
+ }
policy_preprocessor_step_5_normalizer_processor.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4877a42c59e375ee6c0ddfcc75e05185cac831a038ce0122e5c1cea516c84407
3
+ size 16796
train_config.json ADDED
@@ -0,0 +1,249 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset": {
3
+ "repo_id": "CoRL2026-CSI/SO101-cap_pnp_100ep_baseline_10fps",
4
+ "root": null,
5
+ "episodes": null,
6
+ "image_transforms": {
7
+ "enable": true,
8
+ "max_num_transforms": 3,
9
+ "random_order": true,
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
+ },
118
+ "output_features": {
119
+ "action": {
120
+ "type": "ACTION",
121
+ "shape": [
122
+ 6
123
+ ]
124
+ },
125
+ "action.radian_urdf0": {
126
+ "type": "ACTION",
127
+ "shape": [
128
+ 6
129
+ ]
130
+ }
131
+ },
132
+ "device": "cuda",
133
+ "use_amp": false,
134
+ "use_peft": false,
135
+ "push_to_hub": false,
136
+ "repo_id": null,
137
+ "private": null,
138
+ "tags": null,
139
+ "license": null,
140
+ "pretrained_path": "lerobot/smolvla_base",
141
+ "chunk_size": 50,
142
+ "n_action_steps": 50,
143
+ "normalization_mapping": {
144
+ "VISUAL": "IDENTITY",
145
+ "STATE": "MEAN_STD",
146
+ "ACTION": "MEAN_STD"
147
+ },
148
+ "max_state_dim": 32,
149
+ "max_action_dim": 32,
150
+ "resize_imgs_with_padding": [
151
+ 512,
152
+ 512
153
+ ],
154
+ "empty_cameras": 0,
155
+ "adapt_to_pi_aloha": false,
156
+ "use_delta_joint_actions_aloha": false,
157
+ "tokenizer_max_length": 48,
158
+ "num_steps": 50,
159
+ "use_cache": true,
160
+ "freeze_vision_encoder": true,
161
+ "train_expert_only": true,
162
+ "train_state_proj": true,
163
+ "optimizer_lr": 0.0001,
164
+ "optimizer_betas": [
165
+ 0.9,
166
+ 0.95
167
+ ],
168
+ "optimizer_eps": 1e-08,
169
+ "optimizer_weight_decay": 1e-10,
170
+ "optimizer_grad_clip_norm": 10.0,
171
+ "scheduler_warmup_steps": 1000,
172
+ "scheduler_decay_steps": 30000,
173
+ "scheduler_decay_lr": 2.5e-06,
174
+ "vlm_model_name": "HuggingFaceTB/SmolVLM2-500M-Video-Instruct",
175
+ "load_vlm_weights": true,
176
+ "add_image_special_tokens": false,
177
+ "attention_mode": "cross_attn",
178
+ "prefix_length": 0,
179
+ "pad_language_to": "max_length",
180
+ "num_expert_layers": 0,
181
+ "num_vlm_layers": 16,
182
+ "self_attn_every_n_layers": 2,
183
+ "expert_width_multiplier": 0.75,
184
+ "min_period": 0.004,
185
+ "max_period": 4.0,
186
+ "rtc_config": null,
187
+ "compile_model": false,
188
+ "compile_mode": "max-autotune"
189
+ },
190
+ "output_dir": "/home/csiwoo/CORL2026/lerobot/outputs/train/smolvla_cap_pnp_100ep_baseline_10fps",
191
+ "job_name": "smolvla_cap_pnp_100ep_baseline_10fps",
192
+ "resume": false,
193
+ "seed": 1000,
194
+ "cudnn_deterministic": false,
195
+ "num_workers": 24,
196
+ "persistent_workers": true,
197
+ "batch_size": 128,
198
+ "steps": 3000,
199
+ "eval_freq": 0,
200
+ "log_freq": 100,
201
+ "tolerance_s": 0.0001,
202
+ "save_checkpoint": true,
203
+ "save_freq": 3000,
204
+ "use_policy_training_preset": true,
205
+ "optimizer": {
206
+ "type": "adamw",
207
+ "lr": 0.0001,
208
+ "weight_decay": 1e-10,
209
+ "grad_clip_norm": 10.0,
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": 1000,
219
+ "num_decay_steps": 30000,
220
+ "peak_lr": 0.0001,
221
+ "decay_lr": 2.5e-06
222
+ },
223
+ "eval": {
224
+ "n_episodes": 50,
225
+ "batch_size": 50,
226
+ "use_async_envs": true
227
+ },
228
+ "wandb": {
229
+ "enable": true,
230
+ "disable_artifact": false,
231
+ "project": "lerobot-smolvla",
232
+ "entity": null,
233
+ "notes": null,
234
+ "run_id": "zyohf53j",
235
+ "mode": null,
236
+ "add_tags": true
237
+ },
238
+ "peft": null,
239
+ "use_rabc": false,
240
+ "rabc_progress_path": null,
241
+ "rabc_kappa": 0.01,
242
+ "rabc_epsilon": 1e-06,
243
+ "rabc_head_mode": "sparse",
244
+ "rename_map": {
245
+ "observation.images.left_wrist": "observation.images.camera1",
246
+ "observation.images.top": "observation.images.camera2"
247
+ },
248
+ "checkpoint_path": null
249
+ }