Hugging Face's logo

DorianAtSchool
/
smolvla_autoscript_executor_base

Safetensors
Model card Files
xet
 Community
DorianAtSchool commited on
Commit
a3b5c6c
·
verified ·
1 Parent(s): 7241c17

Upload checkpoint folder

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 +91 -0
  6. policy_preprocessor_step_5_normalizer_processor.safetensors +3 -0
  7. train_config.json +239 -0
config.json ADDED
@@ -0,0 +1,99 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ 7
41
+ ]
42
+ }
43
+ },
44
+ "device": "cuda",
45
+ "use_amp": false,
46
+ "use_peft": false,
47
+ "push_to_hub": true,
48
+ "repo_id": "DorianAtSchool/smolvla_autoscript_executor_base",
49
+ "private": null,
50
+ "tags": null,
51
+ "license": null,
52
+ "pretrained_path": "DorianAtSchool/smolvla-combined-finetune-automated-scripted",
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
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48ed9d02a9a7eb4e96b25784bc6cab980848a6131a1be44a7c3db84042190d8c
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
+ 7
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:d7ac87977089840c9d1db00fc855c719449503c89910c0d5dad5712ea88cfb07
3
+ size 8660
policy_preprocessor.json ADDED
@@ -0,0 +1,91 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "name": "policy_preprocessor",
3
+ "steps": [
4
+ {
5
+ "registry_name": "rename_observations_processor",
6
+ "config": {
7
+ "rename_map": {
8
+ "observation.images.top": "observation.images.camera1",
9
+ "observation.images.wrist": "observation.images.camera2",
10
+ "observation.images.side": "observation.images.camera3"
11
+ }
12
+ }
13
+ },
14
+ {
15
+ "registry_name": "to_batch_processor",
16
+ "config": {}
17
+ },
18
+ {
19
+ "registry_name": "smolvla_new_line_processor",
20
+ "config": {}
21
+ },
22
+ {
23
+ "registry_name": "tokenizer_processor",
24
+ "config": {
25
+ "max_length": 48,
26
+ "task_key": "task",
27
+ "padding_side": "right",
28
+ "padding": "max_length",
29
+ "truncation": true,
30
+ "tokenizer_name": "HuggingFaceTB/SmolVLM2-500M-Video-Instruct"
31
+ }
32
+ },
33
+ {
34
+ "registry_name": "device_processor",
35
+ "config": {
36
+ "device": "cuda",
37
+ "float_dtype": null
38
+ }
39
+ },
40
+ {
41
+ "registry_name": "normalizer_processor",
42
+ "config": {
43
+ "eps": 1e-08,
44
+ "features": {
45
+ "observation.state": {
46
+ "type": "STATE",
47
+ "shape": [
48
+ 6
49
+ ]
50
+ },
51
+ "observation.images.camera1": {
52
+ "type": "VISUAL",
53
+ "shape": [
54
+ 3,
55
+ 256,
56
+ 256
57
+ ]
58
+ },
59
+ "observation.images.camera2": {
60
+ "type": "VISUAL",
61
+ "shape": [
62
+ 3,
63
+ 256,
64
+ 256
65
+ ]
66
+ },
67
+ "observation.images.camera3": {
68
+ "type": "VISUAL",
69
+ "shape": [
70
+ 3,
71
+ 256,
72
+ 256
73
+ ]
74
+ },
75
+ "action": {
76
+ "type": "ACTION",
77
+ "shape": [
78
+ 7
79
+ ]
80
+ }
81
+ },
82
+ "norm_map": {
83
+ "VISUAL": "IDENTITY",
84
+ "STATE": "MEAN_STD",
85
+ "ACTION": "MEAN_STD"
86
+ }
87
+ },
88
+ "state_file": "policy_preprocessor_step_5_normalizer_processor.safetensors"
89
+ }
90
+ ]
91
+ }
policy_preprocessor_step_5_normalizer_processor.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7ac87977089840c9d1db00fc855c719449503c89910c0d5dad5712ea88cfb07
3
+ size 8660
train_config.json ADDED
@@ -0,0 +1,239 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset": {
3
+ "repo_id": "DorianAtSchool/color_relay_dagger_single_1000",
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
+ 7
123
+ ]
124
+ }
125
+ },
126
+ "device": "cuda",
127
+ "use_amp": false,
128
+ "use_peft": false,
129
+ "push_to_hub": true,
130
+ "repo_id": "DorianAtSchool/smolvla_autoscript_executor_base",
131
+ "private": null,
132
+ "tags": null,
133
+ "license": null,
134
+ "pretrained_path": "DorianAtSchool/smolvla-combined-finetune-automated-scripted",
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
+ },
182
+ "output_dir": "outputs/finetune/smolvla_autoscript_executor_base",
183
+ "job_name": "smolvla_autoscript_executor_base_ncsa",
184
+ "resume": false,
185
+ "seed": 1000,
186
+ "num_workers": 4,
187
+ "batch_size": 64,
188
+ "steps": 50000,
189
+ "eval_freq": 20000,
190
+ "log_freq": 200,
191
+ "tolerance_s": 0.0001,
192
+ "save_checkpoint": true,
193
+ "save_freq": 20000,
194
+ "use_policy_training_preset": true,
195
+ "optimizer": {
196
+ "type": "adamw",
197
+ "lr": 0.0001,
198
+ "weight_decay": 1e-10,
199
+ "grad_clip_norm": 10.0,
200
+ "betas": [
201
+ 0.9,
202
+ 0.95
203
+ ],
204
+ "eps": 1e-08
205
+ },
206
+ "scheduler": {
207
+ "type": "cosine_decay_with_warmup",
208
+ "num_warmup_steps": 1000,
209
+ "num_decay_steps": 30000,
210
+ "peak_lr": 0.0001,
211
+ "decay_lr": 2.5e-06
212
+ },
213
+ "eval": {
214
+ "n_episodes": 50,
215
+ "batch_size": 50,
216
+ "use_async_envs": false
217
+ },
218
+ "wandb": {
219
+ "enable": false,
220
+ "disable_artifact": false,
221
+ "project": "lerobot",
222
+ "entity": null,
223
+ "notes": null,
224
+ "run_id": null,
225
+ "mode": null
226
+ },
227
+ "peft": null,
228
+ "use_rabc": false,
229
+ "rabc_progress_path": null,
230
+ "rabc_kappa": 0.01,
231
+ "rabc_epsilon": 1e-06,
232
+ "rabc_head_mode": "sparse",
233
+ "rename_map": {
234
+ "observation.images.top": "observation.images.camera1",
235
+ "observation.images.wrist": "observation.images.camera2",
236
+ "observation.images.side": "observation.images.camera3"
237
+ },
238
+ "checkpoint_path": null
239
+ }