Hugging Face's logo

Mimic-Robotics
/
smol_augusto_red_x_10k

Safetensors
Model card Files
xet
 Community
M3thRocks commited on
Commit
6bde3a5
·
verified ·
1 Parent(s): afe7dc8

Upload folder using huggingface_hub

Browse files
Files changed (7) hide show
  1. config.json +99 -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 +87 -0
  6. policy_preprocessor_step_5_normalizer_processor.safetensors +3 -0
  7. train_config.json +271 -0
config.json ADDED
@@ -0,0 +1,99 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "type": "smolvla",
3
+ "n_obs_steps": 1,
4
+ "input_features": {
5
+ "observation.images.top": {
6
+ "type": "VISUAL",
7
+ "shape": [
8
+ 3,
9
+ 224,
10
+ 224
11
+ ]
12
+ },
13
+ "observation.images.left_wrist": {
14
+ "type": "VISUAL",
15
+ "shape": [
16
+ 3,
17
+ 224,
18
+ 224
19
+ ]
20
+ },
21
+ "observation.images.right_wrist": {
22
+ "type": "VISUAL",
23
+ "shape": [
24
+ 3,
25
+ 224,
26
+ 224
27
+ ]
28
+ },
29
+ "observation.state": {
30
+ "type": "STATE",
31
+ "shape": [
32
+ 15
33
+ ]
34
+ }
35
+ },
36
+ "output_features": {
37
+ "action": {
38
+ "type": "ACTION",
39
+ "shape": [
40
+ 15
41
+ ]
42
+ }
43
+ },
44
+ "device": "cuda",
45
+ "use_amp": false,
46
+ "use_peft": false,
47
+ "push_to_hub": true,
48
+ "repo_id": "Mimic-Robotics/smolvla_augusto-linux_red_x_handover_and_place_tictactoe",
49
+ "private": null,
50
+ "tags": null,
51
+ "license": null,
52
+ "pretrained_path": "lerobot/smolvla_base",
53
+ "chunk_size": 50,
54
+ "n_action_steps": 50,
55
+ "normalization_mapping": {
56
+ "VISUAL": "IDENTITY",
57
+ "STATE": "MEAN_STD",
58
+ "ACTION": "MEAN_STD"
59
+ },
60
+ "max_state_dim": 32,
61
+ "max_action_dim": 32,
62
+ "resize_imgs_with_padding": [
63
+ 512,
64
+ 512
65
+ ],
66
+ "empty_cameras": 0,
67
+ "adapt_to_pi_aloha": false,
68
+ "use_delta_joint_actions_aloha": false,
69
+ "tokenizer_max_length": 48,
70
+ "num_steps": 10,
71
+ "use_cache": true,
72
+ "freeze_vision_encoder": true,
73
+ "train_expert_only": true,
74
+ "train_state_proj": true,
75
+ "optimizer_lr": 0.0001,
76
+ "optimizer_betas": [
77
+ 0.9,
78
+ 0.95
79
+ ],
80
+ "optimizer_eps": 1e-08,
81
+ "optimizer_weight_decay": 1e-10,
82
+ "optimizer_grad_clip_norm": 10,
83
+ "scheduler_warmup_steps": 1000,
84
+ "scheduler_decay_steps": 30000,
85
+ "scheduler_decay_lr": 2.5e-06,
86
+ "vlm_model_name": "HuggingFaceTB/SmolVLM2-500M-Video-Instruct",
87
+ "load_vlm_weights": false,
88
+ "add_image_special_tokens": false,
89
+ "attention_mode": "cross_attn",
90
+ "prefix_length": -1,
91
+ "pad_language_to": "longest",
92
+ "num_expert_layers": -1,
93
+ "num_vlm_layers": 16,
94
+ "self_attn_every_n_layers": 2,
95
+ "expert_width_multiplier": 0.75,
96
+ "min_period": 0.004,
97
+ "max_period": 4.0,
98
+ "rtc_config": null
99
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03820496bc4c2952fda933ef225439a97230f60e53933a1b6ffae971f5901421
3
+ size 1197789224
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
+ 15
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:bef68475e643607621867318232998ae155b647a3af98277393e69b0d864cfbf
3
+ size 10376
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": "smolvla_new_line_processor",
16
+ "config": {}
17
+ },
18
+ {
19
+ "registry_name": "tokenizer_processor",
20
+ "config": {
21
+ "max_length": 48,
22
+ "task_key": "task",
23
+ "padding_side": "right",
24
+ "padding": "max_length",
25
+ "truncation": true,
26
+ "tokenizer_name": "HuggingFaceTB/SmolVLM2-500M-Video-Instruct"
27
+ }
28
+ },
29
+ {
30
+ "registry_name": "device_processor",
31
+ "config": {
32
+ "device": "cuda",
33
+ "float_dtype": null
34
+ }
35
+ },
36
+ {
37
+ "registry_name": "normalizer_processor",
38
+ "config": {
39
+ "eps": 1e-08,
40
+ "features": {
41
+ "observation.images.top": {
42
+ "type": "VISUAL",
43
+ "shape": [
44
+ 3,
45
+ 224,
46
+ 224
47
+ ]
48
+ },
49
+ "observation.images.left_wrist": {
50
+ "type": "VISUAL",
51
+ "shape": [
52
+ 3,
53
+ 224,
54
+ 224
55
+ ]
56
+ },
57
+ "observation.images.right_wrist": {
58
+ "type": "VISUAL",
59
+ "shape": [
60
+ 3,
61
+ 224,
62
+ 224
63
+ ]
64
+ },
65
+ "observation.state": {
66
+ "type": "STATE",
67
+ "shape": [
68
+ 15
69
+ ]
70
+ },
71
+ "action": {
72
+ "type": "ACTION",
73
+ "shape": [
74
+ 15
75
+ ]
76
+ }
77
+ },
78
+ "norm_map": {
79
+ "VISUAL": "IDENTITY",
80
+ "STATE": "MEAN_STD",
81
+ "ACTION": "MEAN_STD"
82
+ }
83
+ },
84
+ "state_file": "policy_preprocessor_step_5_normalizer_processor.safetensors"
85
+ }
86
+ ]
87
+ }
policy_preprocessor_step_5_normalizer_processor.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bef68475e643607621867318232998ae155b647a3af98277393e69b0d864cfbf
3
+ size 10376
train_config.json ADDED
@@ -0,0 +1,271 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset": {
3
+ "repo_id": [
4
+ "Mimic-Robotics/mimic_tictactoe_pick_red_x_handover_place_mm_v2",
5
+ "Mimic-Robotics/mimic_tictactoe_pick_red_x_handover_place_mm_v3",
6
+ "Mimic-Robotics/mimic_tictactoe_pick_red_x_handover_place_mm_v4",
7
+ "Mimic-Robotics/mimic_tictactoe_pick_red_x_handover_place_mm_v5",
8
+ "Mimic-Robotics/mimic_tictactoe_pick_red_x_handover_place_mm_v6",
9
+ "Mimic-Robotics/mimic_tictactoe_pick_red_x_handover_place_mm_v8",
10
+ "Mimic-Robotics/mimic_tictactoe_pick_red_x_handover_place_mm_v9",
11
+ "Mimic-Robotics/mimic_tictactoe_pick_red_x_handover_place_mm_v11",
12
+ "Mimic-Robotics/mimic_tictactoe_pick_red_x_handover_place_mm_v12",
13
+ "Mimic-Robotics/mimic_tictactoe_pick_red_x_handover_place_mm_v13",
14
+ "Mimic-Robotics/mimic_tictactoe_pick_red_x_handover_place_mm_v14",
15
+ "Mimic-Robotics/mimic_tictactoe_pick_red_x_handover_place_mm_v15",
16
+ "Mimic-Robotics/mimic_tictactoe_pick_red_x_handover_place_mm_v16",
17
+ "Mimic-Robotics/mimic_tictactoe_red_x_handover_topleft_v1",
18
+ "Mimic-Robotics/mimic_tictactoe_red_x_handover_topleft_v2",
19
+ "Mimic-Robotics/mimic_tictactoe_red_x_handover_toprght_v1",
20
+ "Mimic-Robotics/mimic_tictactoe_red_x_handover_toprght_v2",
21
+ "Mimic-Robotics/mimic_tictactoe_red_x_handover_toprght_v3",
22
+ "Mimic-Robotics/mimic_tictactoe_red_x_handover_toprght_v4",
23
+ "Mimic-Robotics/mimic_tictactoe_red_x_handover_bottomleft_v1",
24
+ "Mimic-Robotics/mimic_tictactoe_red_x_handover_bottomleft_v2",
25
+ "Mimic-Robotics/mimic_tictactoe_red_x_handover_bottomright_v1",
26
+ "Mimic-Robotics/mimic_tictactoe_red_x_handover_bottomright_v2",
27
+ "Mimic-Robotics/mimic_tictactoe_red_x_handover_topmiddle_v1",
28
+ "Mimic-Robotics/mimic_tictactoe_red_x_handover_topMiddle_v3",
29
+ "Mimic-Robotics/mimic_tictactoe_red_x_handover_topMiddle_v4",
30
+ "Mimic-Robotics/mimic_tictactoe_red_x_handover_middleLeft_v1",
31
+ "Mimic-Robotics/mimic_tictactoe_red_x_handover_middleLeft_v2",
32
+ "Mimic-Robotics/mimic_tictactoe_red_x_handover_middleLeft_v3",
33
+ "Mimic-Robotics/mimic_tictactoe_red_x_handover_middleLeft_v4",
34
+ "Mimic-Robotics/mimic_tictactoe_red_x_handover_middleRight_v1",
35
+ "Mimic-Robotics/mimic_tictactoe_red_x_handover_middleRight_v2",
36
+ "Mimic-Robotics/mimic_tictactoe_red_x_handover_bottom_middle_v1",
37
+ "Mimic-Robotics/mimic_tictactoe_red_x_handover_bottom_middle_v2",
38
+ "Mimic-Robotics/mimic_tictactoe_red_x_handover_center_slow_v1"
39
+ ],
40
+ "root": null,
41
+ "episodes": null,
42
+ "image_transforms": {
43
+ "enable": false,
44
+ "max_num_transforms": 3,
45
+ "random_order": false,
46
+ "tfs": {
47
+ "brightness": {
48
+ "weight": 1.0,
49
+ "type": "ColorJitter",
50
+ "kwargs": {
51
+ "brightness": [
52
+ 0.8,
53
+ 1.2
54
+ ]
55
+ }
56
+ },
57
+ "contrast": {
58
+ "weight": 1.0,
59
+ "type": "ColorJitter",
60
+ "kwargs": {
61
+ "contrast": [
62
+ 0.8,
63
+ 1.2
64
+ ]
65
+ }
66
+ },
67
+ "saturation": {
68
+ "weight": 1.0,
69
+ "type": "ColorJitter",
70
+ "kwargs": {
71
+ "saturation": [
72
+ 0.5,
73
+ 1.5
74
+ ]
75
+ }
76
+ },
77
+ "hue": {
78
+ "weight": 1.0,
79
+ "type": "ColorJitter",
80
+ "kwargs": {
81
+ "hue": [
82
+ -0.05,
83
+ 0.05
84
+ ]
85
+ }
86
+ },
87
+ "sharpness": {
88
+ "weight": 1.0,
89
+ "type": "SharpnessJitter",
90
+ "kwargs": {
91
+ "sharpness": [
92
+ 0.5,
93
+ 1.5
94
+ ]
95
+ }
96
+ },
97
+ "affine": {
98
+ "weight": 1.0,
99
+ "type": "RandomAffine",
100
+ "kwargs": {
101
+ "degrees": [
102
+ -5.0,
103
+ 5.0
104
+ ],
105
+ "translate": [
106
+ 0.05,
107
+ 0.05
108
+ ]
109
+ }
110
+ }
111
+ }
112
+ },
113
+ "revision": null,
114
+ "use_imagenet_stats": true,
115
+ "video_backend": "pyav",
116
+ "streaming": false
117
+ },
118
+ "env": null,
119
+ "policy": {
120
+ "type": "smolvla",
121
+ "n_obs_steps": 1,
122
+ "input_features": {
123
+ "observation.images.top": {
124
+ "type": "VISUAL",
125
+ "shape": [
126
+ 3,
127
+ 224,
128
+ 224
129
+ ]
130
+ },
131
+ "observation.images.left_wrist": {
132
+ "type": "VISUAL",
133
+ "shape": [
134
+ 3,
135
+ 224,
136
+ 224
137
+ ]
138
+ },
139
+ "observation.images.right_wrist": {
140
+ "type": "VISUAL",
141
+ "shape": [
142
+ 3,
143
+ 224,
144
+ 224
145
+ ]
146
+ },
147
+ "observation.state": {
148
+ "type": "STATE",
149
+ "shape": [
150
+ 15
151
+ ]
152
+ }
153
+ },
154
+ "output_features": {
155
+ "action": {
156
+ "type": "ACTION",
157
+ "shape": [
158
+ 15
159
+ ]
160
+ }
161
+ },
162
+ "device": "cuda",
163
+ "use_amp": false,
164
+ "use_peft": false,
165
+ "push_to_hub": true,
166
+ "repo_id": "Mimic-Robotics/smolvla_augusto-linux_red_x_handover_and_place_tictactoe",
167
+ "private": null,
168
+ "tags": null,
169
+ "license": null,
170
+ "pretrained_path": "lerobot/smolvla_base",
171
+ "chunk_size": 50,
172
+ "n_action_steps": 50,
173
+ "normalization_mapping": {
174
+ "VISUAL": "IDENTITY",
175
+ "STATE": "MEAN_STD",
176
+ "ACTION": "MEAN_STD"
177
+ },
178
+ "max_state_dim": 32,
179
+ "max_action_dim": 32,
180
+ "resize_imgs_with_padding": [
181
+ 512,
182
+ 512
183
+ ],
184
+ "empty_cameras": 0,
185
+ "adapt_to_pi_aloha": false,
186
+ "use_delta_joint_actions_aloha": false,
187
+ "tokenizer_max_length": 48,
188
+ "num_steps": 10,
189
+ "use_cache": true,
190
+ "freeze_vision_encoder": true,
191
+ "train_expert_only": true,
192
+ "train_state_proj": true,
193
+ "optimizer_lr": 0.0001,
194
+ "optimizer_betas": [
195
+ 0.9,
196
+ 0.95
197
+ ],
198
+ "optimizer_eps": 1e-08,
199
+ "optimizer_weight_decay": 1e-10,
200
+ "optimizer_grad_clip_norm": 10,
201
+ "scheduler_warmup_steps": 1000,
202
+ "scheduler_decay_steps": 30000,
203
+ "scheduler_decay_lr": 2.5e-06,
204
+ "vlm_model_name": "HuggingFaceTB/SmolVLM2-500M-Video-Instruct",
205
+ "load_vlm_weights": false,
206
+ "add_image_special_tokens": false,
207
+ "attention_mode": "cross_attn",
208
+ "prefix_length": -1,
209
+ "pad_language_to": "longest",
210
+ "num_expert_layers": -1,
211
+ "num_vlm_layers": 16,
212
+ "self_attn_every_n_layers": 2,
213
+ "expert_width_multiplier": 0.75,
214
+ "min_period": 0.004,
215
+ "max_period": 4.0,
216
+ "rtc_config": null
217
+ },
218
+ "output_dir": "/home/mat/mimic-lerobot/outputs/train/smolvla_augusto-linux_red_x_handover_and_place_tictactoe_20260211_1503",
219
+ "job_name": "smolvla_augusto-linux_red_x_handover_and_place_tictactoe_20260211_1503",
220
+ "resume": false,
221
+ "seed": 1000,
222
+ "num_workers": 4,
223
+ "batch_size": 70,
224
+ "steps": 50000,
225
+ "eval_freq": 20000,
226
+ "log_freq": 200,
227
+ "tolerance_s": 0.0001,
228
+ "save_checkpoint": true,
229
+ "save_freq": 5000,
230
+ "use_policy_training_preset": true,
231
+ "optimizer": {
232
+ "type": "adamw",
233
+ "lr": 0.0001,
234
+ "weight_decay": 1e-10,
235
+ "grad_clip_norm": 10,
236
+ "betas": [
237
+ 0.9,
238
+ 0.95
239
+ ],
240
+ "eps": 1e-08
241
+ },
242
+ "scheduler": {
243
+ "type": "cosine_decay_with_warmup",
244
+ "num_warmup_steps": 1000,
245
+ "num_decay_steps": 30000,
246
+ "peak_lr": 0.0001,
247
+ "decay_lr": 2.5e-06
248
+ },
249
+ "eval": {
250
+ "n_episodes": 50,
251
+ "batch_size": 50,
252
+ "use_async_envs": false
253
+ },
254
+ "wandb": {
255
+ "enable": true,
256
+ "disable_artifact": false,
257
+ "project": "lerobot",
258
+ "entity": null,
259
+ "notes": null,
260
+ "run_id": "sx1bekux",
261
+ "mode": null
262
+ },
263
+ "peft": null,
264
+ "use_rabc": false,
265
+ "rabc_progress_path": null,
266
+ "rabc_kappa": 0.01,
267
+ "rabc_epsilon": 1e-06,
268
+ "rabc_head_mode": "sparse",
269
+ "rename_map": {},
270
+ "checkpoint_path": null
271
+ }