Hugging Face's logo

Lakesenberg
/
TTRTC_smolvla

Safetensors
Model card Files
xet
Community
Lakesenberg commited on
Commit
a85a072
·
verified ·
1 Parent(s): 18f97e1

Upload folder using huggingface_hub

Browse files
Files changed (7) hide show
  1. config.json +106 -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 +242 -0
config.json ADDED
@@ -0,0 +1,106 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ },
44
+ "device": "cuda",
45
+ "use_amp": false,
46
+ "use_peft": false,
47
+ "push_to_hub": true,
48
+ "repo_id": "Lakesenberg/smolvla_rtc_red_cube_retry",
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": 10.0,
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": true,
88
+ "add_image_special_tokens": false,
89
+ "attention_mode": "cross_attn",
90
+ "prefix_length": 0,
91
+ "pad_language_to": "max_length",
92
+ "num_expert_layers": 0,
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
+ "rtc_training_config": {
100
+ "enabled": true,
101
+ "min_delay": 0,
102
+ "max_delay": 6,
103
+ "delay_distribution": "UNIFORM",
104
+ "exp_decay": 1.0
105
+ }
106
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:173e73b4bc9cd386a43fb2f125e8fb1d17511e90c8c8ce77bb179999e376c9bd
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:c5fd61eeb7fe632531e99f5787e18b108f1b34a2e29560470800f6d266ef49e8
3
+ size 7592
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.state": {
42
+ "type": "STATE",
43
+ "shape": [
44
+ 6
45
+ ]
46
+ },
47
+ "observation.images.camera1": {
48
+ "type": "VISUAL",
49
+ "shape": [
50
+ 3,
51
+ 256,
52
+ 256
53
+ ]
54
+ },
55
+ "observation.images.camera2": {
56
+ "type": "VISUAL",
57
+ "shape": [
58
+ 3,
59
+ 256,
60
+ 256
61
+ ]
62
+ },
63
+ "observation.images.camera3": {
64
+ "type": "VISUAL",
65
+ "shape": [
66
+ 3,
67
+ 256,
68
+ 256
69
+ ]
70
+ },
71
+ "action": {
72
+ "type": "ACTION",
73
+ "shape": [
74
+ 6
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:c5fd61eeb7fe632531e99f5787e18b108f1b34a2e29560470800f6d266ef49e8
3
+ size 7592
train_config.json ADDED
@@ -0,0 +1,242 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset": {
3
+ "repo_id": "Lakesenberg/RTC_red_cube_on_blue_cube_retry",
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": "pyav",
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
+ },
126
+ "device": "cuda",
127
+ "use_amp": false,
128
+ "use_peft": false,
129
+ "push_to_hub": true,
130
+ "repo_id": "Lakesenberg/smolvla_rtc_red_cube_retry",
131
+ "private": null,
132
+ "tags": null,
133
+ "license": null,
134
+ "pretrained_path": "lerobot/smolvla_base",
135
+ "chunk_size": 50,
136
+ "n_action_steps": 50,
137
+ "normalization_mapping": {
138
+ "VISUAL": "IDENTITY",
139
+ "STATE": "MEAN_STD",
140
+ "ACTION": "MEAN_STD"
141
+ },
142
+ "max_state_dim": 32,
143
+ "max_action_dim": 32,
144
+ "resize_imgs_with_padding": [
145
+ 512,
146
+ 512
147
+ ],
148
+ "empty_cameras": 0,
149
+ "adapt_to_pi_aloha": false,
150
+ "use_delta_joint_actions_aloha": false,
151
+ "tokenizer_max_length": 48,
152
+ "num_steps": 10,
153
+ "use_cache": true,
154
+ "freeze_vision_encoder": true,
155
+ "train_expert_only": true,
156
+ "train_state_proj": true,
157
+ "optimizer_lr": 0.0001,
158
+ "optimizer_betas": [
159
+ 0.9,
160
+ 0.95
161
+ ],
162
+ "optimizer_eps": 1e-08,
163
+ "optimizer_weight_decay": 1e-10,
164
+ "optimizer_grad_clip_norm": 10.0,
165
+ "scheduler_warmup_steps": 1000,
166
+ "scheduler_decay_steps": 30000,
167
+ "scheduler_decay_lr": 2.5e-06,
168
+ "vlm_model_name": "HuggingFaceTB/SmolVLM2-500M-Video-Instruct",
169
+ "load_vlm_weights": true,
170
+ "add_image_special_tokens": false,
171
+ "attention_mode": "cross_attn",
172
+ "prefix_length": 0,
173
+ "pad_language_to": "max_length",
174
+ "num_expert_layers": 0,
175
+ "num_vlm_layers": 16,
176
+ "self_attn_every_n_layers": 2,
177
+ "expert_width_multiplier": 0.75,
178
+ "min_period": 0.004,
179
+ "max_period": 4.0,
180
+ "rtc_config": null,
181
+ "rtc_training_config": {
182
+ "enabled": true,
183
+ "min_delay": 0,
184
+ "max_delay": 6,
185
+ "delay_distribution": "UNIFORM",
186
+ "exp_decay": 1.0
187
+ }
188
+ },
189
+ "output_dir": "outputs/output_2",
190
+ "job_name": "smolvla_rtc_red_cube_retry",
191
+ "resume": false,
192
+ "seed": 1000,
193
+ "num_workers": 4,
194
+ "batch_size": 64,
195
+ "steps": 50000,
196
+ "eval_freq": 20000,
197
+ "log_freq": 200,
198
+ "tolerance_s": 0.0001,
199
+ "save_checkpoint": true,
200
+ "save_freq": 20000,
201
+ "use_policy_training_preset": true,
202
+ "optimizer": {
203
+ "type": "adamw",
204
+ "lr": 0.0001,
205
+ "weight_decay": 1e-10,
206
+ "grad_clip_norm": 10.0,
207
+ "betas": [
208
+ 0.9,
209
+ 0.95
210
+ ],
211
+ "eps": 1e-08
212
+ },
213
+ "scheduler": {
214
+ "type": "cosine_decay_with_warmup",
215
+ "num_warmup_steps": 1000,
216
+ "num_decay_steps": 30000,
217
+ "peak_lr": 0.0001,
218
+ "decay_lr": 2.5e-06
219
+ },
220
+ "eval": {
221
+ "n_episodes": 50,
222
+ "batch_size": 50,
223
+ "use_async_envs": false
224
+ },
225
+ "wandb": {
226
+ "enable": true,
227
+ "disable_artifact": false,
228
+ "project": "smolvla_rtc_red_cube",
229
+ "entity": null,
230
+ "notes": null,
231
+ "run_id": "l49fzclf",
232
+ "mode": null
233
+ },
234
+ "peft": null,
235
+ "use_rabc": false,
236
+ "rabc_progress_path": null,
237
+ "rabc_kappa": 0.01,
238
+ "rabc_epsilon": 1e-06,
239
+ "rabc_head_mode": "sparse",
240
+ "rename_map": {},
241
+ "checkpoint_path": null
242
+ }