Hugging Face's logo

samithva
/
task_e_smolvla_merged

Safetensors
Model card Files
xet
 Community
samithva commited on
Commit
ce208fd
·
verified ·
1 Parent(s): 676123d

Upload folder using huggingface_hub

Browse files
Files changed (7) hide show
  1. config.json +102 -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 +90 -0
  6. policy_preprocessor_step_5_normalizer_processor.safetensors +3 -0
  7. train_config.json +243 -0
config.json ADDED
@@ -0,0 +1,102 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ 8
41
+ ]
42
+ }
43
+ },
44
+ "device": "cuda",
45
+ "use_amp": false,
46
+ "use_peft": false,
47
+ "push_to_hub": false,
48
+ "repo_id": null,
49
+ "private": null,
50
+ "tags": null,
51
+ "license": null,
52
+ "pretrained_path": "lerobot/smolvla_base",
53
+ "pretrained_revision": null,
54
+ "chunk_size": 50,
55
+ "n_action_steps": 50,
56
+ "normalization_mapping": {
57
+ "VISUAL": "IDENTITY",
58
+ "STATE": "MEAN_STD",
59
+ "ACTION": "MEAN_STD"
60
+ },
61
+ "max_state_dim": 32,
62
+ "max_action_dim": 32,
63
+ "resize_imgs_with_padding": [
64
+ 512,
65
+ 512
66
+ ],
67
+ "empty_cameras": 0,
68
+ "adapt_to_pi_aloha": false,
69
+ "use_delta_joint_actions_aloha": false,
70
+ "tokenizer_max_length": 48,
71
+ "num_steps": 10,
72
+ "use_cache": true,
73
+ "freeze_vision_encoder": true,
74
+ "train_expert_only": true,
75
+ "train_state_proj": true,
76
+ "optimizer_lr": 0.0001,
77
+ "optimizer_betas": [
78
+ 0.9,
79
+ 0.95
80
+ ],
81
+ "optimizer_eps": 1e-08,
82
+ "optimizer_weight_decay": 1e-10,
83
+ "optimizer_grad_clip_norm": 10.0,
84
+ "scheduler_warmup_steps": 1000,
85
+ "scheduler_decay_steps": 30000,
86
+ "scheduler_decay_lr": 2.5e-06,
87
+ "vlm_model_name": "HuggingFaceTB/SmolVLM2-500M-Video-Instruct",
88
+ "load_vlm_weights": true,
89
+ "add_image_special_tokens": false,
90
+ "attention_mode": "cross_attn",
91
+ "prefix_length": 0,
92
+ "pad_language_to": "max_length",
93
+ "num_expert_layers": 0,
94
+ "num_vlm_layers": 16,
95
+ "self_attn_every_n_layers": 2,
96
+ "expert_width_multiplier": 0.75,
97
+ "min_period": 0.004,
98
+ "max_period": 4.0,
99
+ "rtc_config": null,
100
+ "compile_model": false,
101
+ "compile_mode": "max-autotune"
102
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32677637a38e2b1a65e2379cc5c0cdd64c671fbc3873368fdf09c7b42953a405
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
+ 8
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 sha256:084067d00de0d9d417f7b705fd491e99f0e1151de756e19a5b070de11c0b668a
3
+ size 7704
policy_preprocessor.json ADDED
@@ -0,0 +1,90 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "name": "policy_preprocessor",
3
+ "steps": [
4
+ {
5
+ "registry_name": "rename_observations_processor",
6
+ "config": {
7
+ "rename_map": {
8
+ "observation.images.external": "observation.images.camera1",
9
+ "observation.images.ee": "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
+ 8
78
+ ]
79
+ }
80
+ },
81
+ "norm_map": {
82
+ "VISUAL": "IDENTITY",
83
+ "STATE": "MEAN_STD",
84
+ "ACTION": "MEAN_STD"
85
+ }
86
+ },
87
+ "state_file": "policy_preprocessor_step_5_normalizer_processor.safetensors"
88
+ }
89
+ ]
90
+ }
policy_preprocessor_step_5_normalizer_processor.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:084067d00de0d9d417f7b705fd491e99f0e1151de756e19a5b070de11c0b668a
3
+ size 7704
train_config.json ADDED
@@ -0,0 +1,243 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset": {
3
+ "repo_id": "samithva/teleop_task_e_merged",
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
+ "return_uint8": false,
81
+ "streaming": false
82
+ },
83
+ "env": null,
84
+ "policy": {
85
+ "type": "smolvla",
86
+ "n_obs_steps": 1,
87
+ "input_features": {
88
+ "observation.state": {
89
+ "type": "STATE",
90
+ "shape": [
91
+ 6
92
+ ]
93
+ },
94
+ "observation.images.camera1": {
95
+ "type": "VISUAL",
96
+ "shape": [
97
+ 3,
98
+ 256,
99
+ 256
100
+ ]
101
+ },
102
+ "observation.images.camera2": {
103
+ "type": "VISUAL",
104
+ "shape": [
105
+ 3,
106
+ 256,
107
+ 256
108
+ ]
109
+ },
110
+ "observation.images.camera3": {
111
+ "type": "VISUAL",
112
+ "shape": [
113
+ 3,
114
+ 256,
115
+ 256
116
+ ]
117
+ }
118
+ },
119
+ "output_features": {
120
+ "action": {
121
+ "type": "ACTION",
122
+ "shape": [
123
+ 8
124
+ ]
125
+ }
126
+ },
127
+ "device": "cuda",
128
+ "use_amp": false,
129
+ "use_peft": false,
130
+ "push_to_hub": false,
131
+ "repo_id": null,
132
+ "private": null,
133
+ "tags": null,
134
+ "license": null,
135
+ "pretrained_path": "lerobot/smolvla_base",
136
+ "pretrained_revision": null,
137
+ "chunk_size": 50,
138
+ "n_action_steps": 50,
139
+ "normalization_mapping": {
140
+ "VISUAL": "IDENTITY",
141
+ "STATE": "MEAN_STD",
142
+ "ACTION": "MEAN_STD"
143
+ },
144
+ "max_state_dim": 32,
145
+ "max_action_dim": 32,
146
+ "resize_imgs_with_padding": [
147
+ 512,
148
+ 512
149
+ ],
150
+ "empty_cameras": 0,
151
+ "adapt_to_pi_aloha": false,
152
+ "use_delta_joint_actions_aloha": false,
153
+ "tokenizer_max_length": 48,
154
+ "num_steps": 10,
155
+ "use_cache": true,
156
+ "freeze_vision_encoder": true,
157
+ "train_expert_only": true,
158
+ "train_state_proj": true,
159
+ "optimizer_lr": 0.0001,
160
+ "optimizer_betas": [
161
+ 0.9,
162
+ 0.95
163
+ ],
164
+ "optimizer_eps": 1e-08,
165
+ "optimizer_weight_decay": 1e-10,
166
+ "optimizer_grad_clip_norm": 10.0,
167
+ "scheduler_warmup_steps": 1000,
168
+ "scheduler_decay_steps": 30000,
169
+ "scheduler_decay_lr": 2.5e-06,
170
+ "vlm_model_name": "HuggingFaceTB/SmolVLM2-500M-Video-Instruct",
171
+ "load_vlm_weights": true,
172
+ "add_image_special_tokens": false,
173
+ "attention_mode": "cross_attn",
174
+ "prefix_length": 0,
175
+ "pad_language_to": "max_length",
176
+ "num_expert_layers": 0,
177
+ "num_vlm_layers": 16,
178
+ "self_attn_every_n_layers": 2,
179
+ "expert_width_multiplier": 0.75,
180
+ "min_period": 0.004,
181
+ "max_period": 4.0,
182
+ "rtc_config": null,
183
+ "compile_model": false,
184
+ "compile_mode": "max-autotune"
185
+ },
186
+ "reward_model": null,
187
+ "output_dir": "outputs/train/smolvla_task_e_merged",
188
+ "job_name": "smolvla_task_e_merged",
189
+ "resume": false,
190
+ "seed": 1000,
191
+ "cudnn_deterministic": false,
192
+ "num_workers": 16,
193
+ "batch_size": 8,
194
+ "prefetch_factor": 4,
195
+ "persistent_workers": true,
196
+ "steps": 100000,
197
+ "eval_freq": 20000,
198
+ "log_freq": 200,
199
+ "tolerance_s": 0.0001,
200
+ "save_checkpoint": true,
201
+ "save_freq": 10000,
202
+ "use_policy_training_preset": true,
203
+ "optimizer": {
204
+ "type": "adamw",
205
+ "lr": 0.0001,
206
+ "weight_decay": 1e-10,
207
+ "grad_clip_norm": 10.0,
208
+ "betas": [
209
+ 0.9,
210
+ 0.95
211
+ ],
212
+ "eps": 1e-08
213
+ },
214
+ "scheduler": {
215
+ "type": "cosine_decay_with_warmup",
216
+ "num_warmup_steps": 1000,
217
+ "num_decay_steps": 30000,
218
+ "peak_lr": 0.0001,
219
+ "decay_lr": 2.5e-06
220
+ },
221
+ "eval": {
222
+ "n_episodes": 50,
223
+ "batch_size": 50,
224
+ "use_async_envs": true
225
+ },
226
+ "wandb": {
227
+ "enable": true,
228
+ "disable_artifact": false,
229
+ "project": "lerobot",
230
+ "entity": null,
231
+ "notes": null,
232
+ "run_id": "le86959x",
233
+ "mode": null,
234
+ "add_tags": true
235
+ },
236
+ "peft": null,
237
+ "sample_weighting": null,
238
+ "rename_map": {
239
+ "observation.images.external": "observation.images.camera1",
240
+ "observation.images.ee": "observation.images.camera2"
241
+ },
242
+ "checkpoint_path": null
243
+ }