Hugging Face's logo

ducido
/
MW_litevla-ms

Safetensors
Model card Files
xet
Community
ducido commited on
Commit
b1ce9da
·
verified ·
1 Parent(s): ca9c97c

Initial commit

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. .gitattributes +1 -0
  2. checkpoints/030000/pretrained_model/config.json +83 -0
  3. checkpoints/030000/pretrained_model/model.safetensors +3 -0
  4. checkpoints/030000/pretrained_model/train_config.json +276 -0
  5. checkpoints/030000/training_state/optimizer_param_groups.json +529 -0
  6. checkpoints/030000/training_state/optimizer_state.safetensors +3 -0
  7. checkpoints/030000/training_state/rng_state.safetensors +3 -0
  8. checkpoints/030000/training_state/scheduler_state.json +15 -0
  9. checkpoints/030000/training_state/training_step.json +3 -0
  10. checkpoints/040000/pretrained_model/config.json +83 -0
  11. checkpoints/040000/pretrained_model/model.safetensors +3 -0
  12. checkpoints/040000/pretrained_model/train_config.json +276 -0
  13. checkpoints/040000/training_state/optimizer_param_groups.json +529 -0
  14. checkpoints/040000/training_state/optimizer_state.safetensors +3 -0
  15. checkpoints/040000/training_state/rng_state.safetensors +3 -0
  16. checkpoints/040000/training_state/scheduler_state.json +15 -0
  17. checkpoints/040000/training_state/training_step.json +3 -0
  18. checkpoints/050000/pretrained_model/config.json +83 -0
  19. checkpoints/050000/pretrained_model/model.safetensors +3 -0
  20. checkpoints/050000/pretrained_model/train_config.json +276 -0
  21. checkpoints/050000/training_state/optimizer_param_groups.json +529 -0
  22. checkpoints/050000/training_state/optimizer_state.safetensors +3 -0
  23. checkpoints/050000/training_state/rng_state.safetensors +3 -0
  24. checkpoints/050000/training_state/scheduler_state.json +15 -0
  25. checkpoints/050000/training_state/training_step.json +3 -0
  26. checkpoints/060000/pretrained_model/config.json +81 -0
  27. checkpoints/060000/pretrained_model/model.safetensors +3 -0
  28. checkpoints/060000/pretrained_model/train_config.json +276 -0
  29. checkpoints/060000/pretrained_model_migrated/README.md +63 -0
  30. checkpoints/060000/pretrained_model_migrated/config.json +88 -0
  31. checkpoints/060000/pretrained_model_migrated/model.safetensors +3 -0
  32. checkpoints/060000/pretrained_model_migrated/policy_postprocessor.json +32 -0
  33. checkpoints/060000/pretrained_model_migrated/policy_postprocessor_step_0_unnormalizer_processor.safetensors +3 -0
  34. checkpoints/060000/pretrained_model_migrated/policy_preprocessor.json +77 -0
  35. checkpoints/060000/pretrained_model_migrated/policy_preprocessor_step_5_normalizer_processor.safetensors +3 -0
  36. checkpoints/060000/training_state/optimizer_param_groups.json +529 -0
  37. checkpoints/060000/training_state/optimizer_state.safetensors +3 -0
  38. checkpoints/060000/training_state/rng_state.safetensors +3 -0
  39. checkpoints/060000/training_state/scheduler_state.json +15 -0
  40. checkpoints/060000/training_state/training_step.json +3 -0
  41. checkpoints/070000/pretrained_model/config.json +83 -0
  42. checkpoints/070000/pretrained_model/model.safetensors +3 -0
  43. checkpoints/070000/pretrained_model/train_config.json +276 -0
  44. checkpoints/070000/training_state/optimizer_param_groups.json +529 -0
  45. checkpoints/070000/training_state/optimizer_state.safetensors +3 -0
  46. checkpoints/070000/training_state/rng_state.safetensors +3 -0
  47. checkpoints/070000/training_state/scheduler_state.json +15 -0
  48. checkpoints/070000/training_state/training_step.json +3 -0
  49. checkpoints/080000/pretrained_model/config.json +81 -0
  50. checkpoints/080000/pretrained_model/model.safetensors +3 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ wandb/run-20260209_084451-csy2m2pr/run-csy2m2pr.wandb filter=lfs diff=lfs merge=lfs -text
checkpoints/030000/pretrained_model/config.json ADDED
@@ -0,0 +1,83 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "type": "litevla-ms",
3
+ "n_obs_steps": 1,
4
+ "normalization_mapping": {
5
+ "VISUAL": "IDENTITY",
6
+ "STATE": "MEAN_STD",
7
+ "ACTION": "MEAN_STD"
8
+ },
9
+ "input_features": {
10
+ "observation.state": {
11
+ "type": "STATE",
12
+ "shape": [
13
+ 4
14
+ ]
15
+ },
16
+ "observation.environment_state": {
17
+ "type": "ENV",
18
+ "shape": [
19
+ 39
20
+ ]
21
+ },
22
+ "observation.image": {
23
+ "type": "VISUAL",
24
+ "shape": [
25
+ 3,
26
+ 480,
27
+ 480
28
+ ]
29
+ }
30
+ },
31
+ "output_features": {
32
+ "action": {
33
+ "type": "ACTION",
34
+ "shape": [
35
+ 4
36
+ ]
37
+ }
38
+ },
39
+ "device": "cuda",
40
+ "use_amp": false,
41
+ "gradient_accumulation_steps": 1,
42
+ "chunk_size": 50,
43
+ "n_action_steps": 1,
44
+ "max_state_dim": 32,
45
+ "max_action_dim": 32,
46
+ "resize_imgs_with_padding": [
47
+ 512,
48
+ 512
49
+ ],
50
+ "empty_cameras": 0,
51
+ "adapt_to_pi_aloha": false,
52
+ "use_delta_joint_actions_aloha": false,
53
+ "tokenizer_max_length": 48,
54
+ "num_steps": 10,
55
+ "use_cache": true,
56
+ "freeze_vision_encoder": true,
57
+ "train_expert_only": false,
58
+ "train_state_proj": true,
59
+ "optimizer_lr": 0.0001,
60
+ "optimizer_betas": [
61
+ 0.9,
62
+ 0.95
63
+ ],
64
+ "optimizer_eps": 1e-08,
65
+ "optimizer_weight_decay": 1e-10,
66
+ "optimizer_grad_clip_norm": 10,
67
+ "scheduler_warmup_steps": 1000,
68
+ "scheduler_decay_steps": 100000,
69
+ "scheduler_decay_lr": 2.5e-06,
70
+ "vlm_model_name": "/pfss/mlde/workspaces/mlde_wsp_IAS_SAMMerge/VLA/duc/VLA-Humanoid-MW/SmolVLM2-500M-Video-Instruct",
71
+ "load_vlm_weights": true,
72
+ "add_image_special_tokens": false,
73
+ "attention_mode": "cross_attn",
74
+ "prefix_length": 0,
75
+ "pad_language_to": "max_length",
76
+ "num_expert_layers": 0,
77
+ "num_vlm_layers": 16,
78
+ "self_attn_every_n_layers": 2,
79
+ "expert_width_multiplier": 0.75,
80
+ "min_period": 0.004,
81
+ "max_period": 4.0,
82
+ "of_path": "/pfss/mlde/workspaces/mlde_wsp_IAS_SAMMerge/VLA/duc/VLA-Humanoid-MW/ori_mw_if/ori_mw_100%_of.h5"
83
+ }
checkpoints/030000/pretrained_model/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12f91688a2ff0eb5c524271c8ae10992a04914bcca77075bc3c35e4493ceb284
3
+ size 934390312
checkpoints/030000/pretrained_model/train_config.json ADDED
@@ -0,0 +1,276 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset": {
3
+ "repo_id": ".",
4
+ "root": "/pfss/mlde/workspaces/mlde_wsp_IAS_SAMMerge/VLA/duc/VLA-Humanoid-MW/metaworld_mt50",
5
+ "episodes": null,
6
+ "image_transforms": {
7
+ "enable": true,
8
+ "max_num_transforms": 3,
9
+ "random_order": false,
10
+ "image_tfs": {
11
+ "hue": {
12
+ "weight": 1.0,
13
+ "type": "ColorJitter",
14
+ "kwargs": {
15
+ "hue": [
16
+ -0.05,
17
+ 0.05
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
+ "sharpness": {
32
+ "weight": 1.0,
33
+ "type": "SharpnessJitter",
34
+ "kwargs": {
35
+ "sharpness": [
36
+ 0.5,
37
+ 1.5
38
+ ]
39
+ }
40
+ },
41
+ "brightness": {
42
+ "weight": 1.0,
43
+ "type": "ColorJitter",
44
+ "kwargs": {
45
+ "brightness": [
46
+ 0.8,
47
+ 1.2
48
+ ]
49
+ }
50
+ },
51
+ "saturation": {
52
+ "weight": 1.0,
53
+ "type": "ColorJitter",
54
+ "kwargs": {
55
+ "saturation": [
56
+ 0.5,
57
+ 1.5
58
+ ]
59
+ }
60
+ },
61
+ "crop_resize": {
62
+ "weight": 1.0,
63
+ "type": "RandomResizedCrop",
64
+ "kwargs": {
65
+ "size": [
66
+ 256,
67
+ 256
68
+ ],
69
+ "ratio": [
70
+ 1,
71
+ 1
72
+ ],
73
+ "scale": [
74
+ 0.9,
75
+ 0.95
76
+ ]
77
+ }
78
+ },
79
+ "rotate": {
80
+ "weight": 1.0,
81
+ "type": "RandomRotate",
82
+ "kwargs": {
83
+ "degrees": [
84
+ -5,
85
+ 5
86
+ ]
87
+ }
88
+ }
89
+ },
90
+ "wrist_tfs": {
91
+ "hue": {
92
+ "weight": 1.0,
93
+ "type": "ColorJitter",
94
+ "kwargs": {
95
+ "hue": [
96
+ -0.05,
97
+ 0.05
98
+ ]
99
+ }
100
+ },
101
+ "contrast": {
102
+ "weight": 1.0,
103
+ "type": "ColorJitter",
104
+ "kwargs": {
105
+ "contrast": [
106
+ 0.8,
107
+ 1.2
108
+ ]
109
+ }
110
+ },
111
+ "sharpness": {
112
+ "weight": 1.0,
113
+ "type": "SharpnessJitter",
114
+ "kwargs": {
115
+ "sharpness": [
116
+ 0.5,
117
+ 1.5
118
+ ]
119
+ }
120
+ },
121
+ "brightness": {
122
+ "weight": 1.0,
123
+ "type": "ColorJitter",
124
+ "kwargs": {
125
+ "brightness": [
126
+ 0.8,
127
+ 1.2
128
+ ]
129
+ }
130
+ },
131
+ "saturation": {
132
+ "weight": 1.0,
133
+ "type": "ColorJitter",
134
+ "kwargs": {
135
+ "saturation": [
136
+ 0.5,
137
+ 1.5
138
+ ]
139
+ }
140
+ }
141
+ }
142
+ },
143
+ "revision": null,
144
+ "use_imagenet_stats": true,
145
+ "video_backend": "torchcodec",
146
+ "vqa_data_path": null
147
+ },
148
+ "env": null,
149
+ "policy": {
150
+ "type": "litevla-ms",
151
+ "n_obs_steps": 1,
152
+ "normalization_mapping": {
153
+ "VISUAL": "IDENTITY",
154
+ "STATE": "MEAN_STD",
155
+ "ACTION": "MEAN_STD"
156
+ },
157
+ "input_features": {
158
+ "observation.state": {
159
+ "type": "STATE",
160
+ "shape": [
161
+ 4
162
+ ]
163
+ },
164
+ "observation.environment_state": {
165
+ "type": "ENV",
166
+ "shape": [
167
+ 39
168
+ ]
169
+ },
170
+ "observation.image": {
171
+ "type": "VISUAL",
172
+ "shape": [
173
+ 3,
174
+ 480,
175
+ 480
176
+ ]
177
+ }
178
+ },
179
+ "output_features": {
180
+ "action": {
181
+ "type": "ACTION",
182
+ "shape": [
183
+ 4
184
+ ]
185
+ }
186
+ },
187
+ "device": "cuda",
188
+ "use_amp": false,
189
+ "gradient_accumulation_steps": 1,
190
+ "chunk_size": 50,
191
+ "n_action_steps": 1,
192
+ "max_state_dim": 32,
193
+ "max_action_dim": 32,
194
+ "resize_imgs_with_padding": [
195
+ 512,
196
+ 512
197
+ ],
198
+ "empty_cameras": 0,
199
+ "adapt_to_pi_aloha": false,
200
+ "use_delta_joint_actions_aloha": false,
201
+ "tokenizer_max_length": 48,
202
+ "num_steps": 10,
203
+ "use_cache": true,
204
+ "freeze_vision_encoder": true,
205
+ "train_expert_only": false,
206
+ "train_state_proj": true,
207
+ "optimizer_lr": 0.0001,
208
+ "optimizer_betas": [
209
+ 0.9,
210
+ 0.95
211
+ ],
212
+ "optimizer_eps": 1e-08,
213
+ "optimizer_weight_decay": 1e-10,
214
+ "optimizer_grad_clip_norm": 10,
215
+ "scheduler_warmup_steps": 1000,
216
+ "scheduler_decay_steps": 100000,
217
+ "scheduler_decay_lr": 2.5e-06,
218
+ "vlm_model_name": "/pfss/mlde/workspaces/mlde_wsp_IAS_SAMMerge/VLA/duc/VLA-Humanoid-MW/SmolVLM2-500M-Video-Instruct",
219
+ "load_vlm_weights": true,
220
+ "add_image_special_tokens": false,
221
+ "attention_mode": "cross_attn",
222
+ "prefix_length": 0,
223
+ "pad_language_to": "max_length",
224
+ "num_expert_layers": 0,
225
+ "num_vlm_layers": 16,
226
+ "self_attn_every_n_layers": 2,
227
+ "expert_width_multiplier": 0.75,
228
+ "min_period": 0.004,
229
+ "max_period": 4.0,
230
+ "of_path": "/pfss/mlde/workspaces/mlde_wsp_IAS_SAMMerge/VLA/duc/VLA-Humanoid-MW/ori_mw_if/ori_mw_100%_of.h5"
231
+ },
232
+ "output_dir": "outputs/train/2026-02-09/08-44-30_MW_100%_scratch_litevla-ms_lastlayer",
233
+ "job_name": "MW_100%_scratch_litevla-ms_lastlayer",
234
+ "resume": false,
235
+ "seed": 42,
236
+ "num_workers": 8,
237
+ "batch_size": 64,
238
+ "steps": 100000,
239
+ "eval_freq": 20000,
240
+ "log_freq": 200,
241
+ "save_checkpoint": true,
242
+ "save_freq": 10000,
243
+ "use_policy_training_preset": true,
244
+ "optimizer": {
245
+ "type": "adamw",
246
+ "lr": 0.0001,
247
+ "weight_decay": 1e-10,
248
+ "grad_clip_norm": 10,
249
+ "betas": [
250
+ 0.9,
251
+ 0.95
252
+ ],
253
+ "eps": 1e-08
254
+ },
255
+ "scheduler": {
256
+ "type": "cosine_decay_with_warmup",
257
+ "num_warmup_steps": 1000,
258
+ "num_decay_steps": 100000,
259
+ "peak_lr": 0.0001,
260
+ "decay_lr": 2.5e-06
261
+ },
262
+ "eval": {
263
+ "n_episodes": 50,
264
+ "batch_size": 50,
265
+ "use_async_envs": false
266
+ },
267
+ "wandb": {
268
+ "enable": true,
269
+ "disable_artifact": true,
270
+ "project": "LiteVLA-MS",
271
+ "entity": "Robotics_VLA",
272
+ "notes": null,
273
+ "run_id": null,
274
+ "mode": "online"
275
+ }
276
+ }
checkpoints/030000/training_state/optimizer_param_groups.json ADDED
@@ -0,0 +1,529 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "lr": 7.990453104925807e-05,
4
+ "betas": [
5
+ 0.9,
6
+ 0.95
7
+ ],
8
+ "eps": 1e-08,
9
+ "weight_decay": 1e-10,
10
+ "amsgrad": false,
11
+ "maximize": false,
12
+ "foreach": null,
13
+ "capturable": false,
14
+ "differentiable": false,
15
+ "fused": null,
16
+ "decoupled_weight_decay": true,
17
+ "initial_lr": 0.0001,
18
+ "params": [
19
+ 0,
20
+ 1,
21
+ 2,
22
+ 3,
23
+ 4,
24
+ 5,
25
+ 6,
26
+ 7,
27
+ 8,
28
+ 9,
29
+ 10,
30
+ 11,
31
+ 12,
32
+ 13,
33
+ 14,
34
+ 15,
35
+ 16,
36
+ 17,
37
+ 18,
38
+ 19,
39
+ 20,
40
+ 21,
41
+ 22,
42
+ 23,
43
+ 24,
44
+ 25,
45
+ 26,
46
+ 27,
47
+ 28,
48
+ 29,
49
+ 30,
50
+ 31,
51
+ 32,
52
+ 33,
53
+ 34,
54
+ 35,
55
+ 36,
56
+ 37,
57
+ 38,
58
+ 39,
59
+ 40,
60
+ 41,
61
+ 42,
62
+ 43,
63
+ 44,
64
+ 45,
65
+ 46,
66
+ 47,
67
+ 48,
68
+ 49,
69
+ 50,
70
+ 51,
71
+ 52,
72
+ 53,
73
+ 54,
74
+ 55,
75
+ 56,
76
+ 57,
77
+ 58,
78
+ 59,
79
+ 60,
80
+ 61,
81
+ 62,
82
+ 63,
83
+ 64,
84
+ 65,
85
+ 66,
86
+ 67,
87
+ 68,
88
+ 69,
89
+ 70,
90
+ 71,
91
+ 72,
92
+ 73,
93
+ 74,
94
+ 75,
95
+ 76,
96
+ 77,
97
+ 78,
98
+ 79,
99
+ 80,
100
+ 81,
101
+ 82,
102
+ 83,
103
+ 84,
104
+ 85,
105
+ 86,
106
+ 87,
107
+ 88,
108
+ 89,
109
+ 90,
110
+ 91,
111
+ 92,
112
+ 93,
113
+ 94,
114
+ 95,
115
+ 96,
116
+ 97,
117
+ 98,
118
+ 99,
119
+ 100,
120
+ 101,
121
+ 102,
122
+ 103,
123
+ 104,
124
+ 105,
125
+ 106,
126
+ 107,
127
+ 108,
128
+ 109,
129
+ 110,
130
+ 111,
131
+ 112,
132
+ 113,
133
+ 114,
134
+ 115,
135
+ 116,
136
+ 117,
137
+ 118,
138
+ 119,
139
+ 120,
140
+ 121,
141
+ 122,
142
+ 123,
143
+ 124,
144
+ 125,
145
+ 126,
146
+ 127,
147
+ 128,
148
+ 129,
149
+ 130,
150
+ 131,
151
+ 132,
152
+ 133,
153
+ 134,
154
+ 135,
155
+ 136,
156
+ 137,
157
+ 138,
158
+ 139,
159
+ 140,
160
+ 141,
161
+ 142,
162
+ 143,
163
+ 144,
164
+ 145,
165
+ 146,
166
+ 147,
167
+ 148,
168
+ 149,
169
+ 150,
170
+ 151,
171
+ 152,
172
+ 153,
173
+ 154,
174
+ 155,
175
+ 156,
176
+ 157,
177
+ 158,
178
+ 159,
179
+ 160,
180
+ 161,
181
+ 162,
182
+ 163,
183
+ 164,
184
+ 165,
185
+ 166,
186
+ 167,
187
+ 168,
188
+ 169,
189
+ 170,
190
+ 171,
191
+ 172,
192
+ 173,
193
+ 174,
194
+ 175,
195
+ 176,
196
+ 177,
197
+ 178,
198
+ 179,
199
+ 180,
200
+ 181,
201
+ 182,
202
+ 183,
203
+ 184,
204
+ 185,
205
+ 186,
206
+ 187,
207
+ 188,
208
+ 189,
209
+ 190,
210
+ 191,
211
+ 192,
212
+ 193,
213
+ 194,
214
+ 195,
215
+ 196,
216
+ 197,
217
+ 198,
218
+ 199,
219
+ 200,
220
+ 201,
221
+ 202,
222
+ 203,
223
+ 204,
224
+ 205,
225
+ 206,
226
+ 207,
227
+ 208,
228
+ 209,
229
+ 210,
230
+ 211,
231
+ 212,
232
+ 213,
233
+ 214,
234
+ 215,
235
+ 216,
236
+ 217,
237
+ 218,
238
+ 219,
239
+ 220,
240
+ 221,
241
+ 222,
242
+ 223,
243
+ 224,
244
+ 225,
245
+ 226,
246
+ 227,
247
+ 228,
248
+ 229,
249
+ 230,
250
+ 231,
251
+ 232,
252
+ 233,
253
+ 234,
254
+ 235,
255
+ 236,
256
+ 237,
257
+ 238,
258
+ 239,
259
+ 240,
260
+ 241,
261
+ 242,
262
+ 243,
263
+ 244,
264
+ 245,
265
+ 246,
266
+ 247,
267
+ 248,
268
+ 249,
269
+ 250,
270
+ 251,
271
+ 252,
272
+ 253,
273
+ 254,
274
+ 255,
275
+ 256,
276
+ 257,
277
+ 258,
278
+ 259,
279
+ 260,
280
+ 261,
281
+ 262,
282
+ 263,
283
+ 264,
284
+ 265,
285
+ 266,
286
+ 267,
287
+ 268,
288
+ 269,
289
+ 270,
290
+ 271,
291
+ 272,
292
+ 273,
293
+ 274,
294
+ 275,
295
+ 276,
296
+ 277,
297
+ 278,
298
+ 279,
299
+ 280,
300
+ 281,
301
+ 282,
302
+ 283,
303
+ 284,
304
+ 285,
305
+ 286,
306
+ 287,
307
+ 288,
308
+ 289,
309
+ 290,
310
+ 291,
311
+ 292,
312
+ 293,
313
+ 294,
314
+ 295,
315
+ 296,
316
+ 297,
317
+ 298,
318
+ 299,
319
+ 300,
320
+ 301,
321
+ 302,
322
+ 303,
323
+ 304,
324
+ 305,
325
+ 306,
326
+ 307,
327
+ 308,
328
+ 309,
329
+ 310,
330
+ 311,
331
+ 312,
332
+ 313,
333
+ 314,
334
+ 315,
335
+ 316,
336
+ 317,
337
+ 318,
338
+ 319,
339
+ 320,
340
+ 321,
341
+ 322,
342
+ 323,
343
+ 324,
344
+ 325,
345
+ 326,
346
+ 327,
347
+ 328,
348
+ 329,
349
+ 330,
350
+ 331,
351
+ 332,
352
+ 333,
353
+ 334,
354
+ 335,
355
+ 336,
356
+ 337,
357
+ 338,
358
+ 339,
359
+ 340,
360
+ 341,
361
+ 342,
362
+ 343,
363
+ 344,
364
+ 345,
365
+ 346,
366
+ 347,
367
+ 348,
368
+ 349,
369
+ 350,
370
+ 351,
371
+ 352,
372
+ 353,
373
+ 354,
374
+ 355,
375
+ 356,
376
+ 357,
377
+ 358,
378
+ 359,
379
+ 360,
380
+ 361,
381
+ 362,
382
+ 363,
383
+ 364,
384
+ 365,
385
+ 366,
386
+ 367,
387
+ 368,
388
+ 369,
389
+ 370,
390
+ 371,
391
+ 372,
392
+ 373,
393
+ 374,
394
+ 375,
395
+ 376,
396
+ 377,
397
+ 378,
398
+ 379,
399
+ 380,
400
+ 381,
401
+ 382,
402
+ 383,
403
+ 384,
404
+ 385,
405
+ 386,
406
+ 387,
407
+ 388,
408
+ 389,
409
+ 390,
410
+ 391,
411
+ 392,
412
+ 393,
413
+ 394,
414
+ 395,
415
+ 396,
416
+ 397,
417
+ 398,
418
+ 399,
419
+ 400,
420
+ 401,
421
+ 402,
422
+ 403,
423
+ 404,
424
+ 405,
425
+ 406,
426
+ 407,
427
+ 408,
428
+ 409,
429
+ 410,
430
+ 411,
431
+ 412,
432
+ 413,
433
+ 414,
434
+ 415,
435
+ 416,
436
+ 417,
437
+ 418,
438
+ 419,
439
+ 420,
440
+ 421,
441
+ 422,
442
+ 423,
443
+ 424,
444
+ 425,
445
+ 426,
446
+ 427,
447
+ 428,
448
+ 429,
449
+ 430,
450
+ 431,
451
+ 432,
452
+ 433,
453
+ 434,
454
+ 435,
455
+ 436,
456
+ 437,
457
+ 438,
458
+ 439,
459
+ 440,
460
+ 441,
461
+ 442,
462
+ 443,
463
+ 444,
464
+ 445,
465
+ 446,
466
+ 447,
467
+ 448,
468
+ 449,
469
+ 450,
470
+ 451,
471
+ 452,
472
+ 453,
473
+ 454,
474
+ 455,
475
+ 456,
476
+ 457,
477
+ 458,
478
+ 459,
479
+ 460,
480
+ 461,
481
+ 462,
482
+ 463,
483
+ 464,
484
+ 465,
485
+ 466,
486
+ 467,
487
+ 468,
488
+ 469,
489
+ 470,
490
+ 471,
491
+ 472,
492
+ 473,
493
+ 474,
494
+ 475,
495
+ 476,
496
+ 477,
497
+ 478,
498
+ 479,
499
+ 480,
500
+ 481,
501
+ 482,
502
+ 483,
503
+ 484,
504
+ 485,
505
+ 486,
506
+ 487,
507
+ 488,
508
+ 489,
509
+ 490,
510
+ 491,
511
+ 492,
512
+ 493,
513
+ 494,
514
+ 495,
515
+ 496,
516
+ 497,
517
+ 498,
518
+ 499,
519
+ 500,
520
+ 501,
521
+ 502,
522
+ 503,
523
+ 504,
524
+ 505,
525
+ 506,
526
+ 507
527
+ ]
528
+ }
529
+ ]
checkpoints/030000/training_state/optimizer_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f2288b662f76ead05007385d3d39e8505be98724f91821386dcf328c1721840
3
+ size 1333741212
checkpoints/030000/training_state/rng_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be17f320562bccd54138b82f80538c13f80dc76f3843dc1eff13f5f6e7ea7a77
3
+ size 15708
checkpoints/030000/training_state/scheduler_state.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "base_lrs": [
3
+ 0.0001
4
+ ],
5
+ "last_epoch": 30000,
6
+ "_step_count": 30001,
7
+ "_is_initial": false,
8
+ "_get_lr_called_within_step": false,
9
+ "_last_lr": [
10
+ 7.990453104925807e-05
11
+ ],
12
+ "lr_lambdas": [
13
+ null
14
+ ]
15
+ }
checkpoints/030000/training_state/training_step.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "step": 30000
3
+ }
checkpoints/040000/pretrained_model/config.json ADDED
@@ -0,0 +1,83 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "type": "litevla-ms",
3
+ "n_obs_steps": 1,
4
+ "normalization_mapping": {
5
+ "VISUAL": "IDENTITY",
6
+ "STATE": "MEAN_STD",
7
+ "ACTION": "MEAN_STD"
8
+ },
9
+ "input_features": {
10
+ "observation.state": {
11
+ "type": "STATE",
12
+ "shape": [
13
+ 4
14
+ ]
15
+ },
16
+ "observation.environment_state": {
17
+ "type": "ENV",
18
+ "shape": [
19
+ 39
20
+ ]
21
+ },
22
+ "observation.image": {
23
+ "type": "VISUAL",
24
+ "shape": [
25
+ 3,
26
+ 480,
27
+ 480
28
+ ]
29
+ }
30
+ },
31
+ "output_features": {
32
+ "action": {
33
+ "type": "ACTION",
34
+ "shape": [
35
+ 4
36
+ ]
37
+ }
38
+ },
39
+ "device": "cuda",
40
+ "use_amp": false,
41
+ "gradient_accumulation_steps": 1,
42
+ "chunk_size": 50,
43
+ "n_action_steps": 1,
44
+ "max_state_dim": 32,
45
+ "max_action_dim": 32,
46
+ "resize_imgs_with_padding": [
47
+ 512,
48
+ 512
49
+ ],
50
+ "empty_cameras": 0,
51
+ "adapt_to_pi_aloha": false,
52
+ "use_delta_joint_actions_aloha": false,
53
+ "tokenizer_max_length": 48,
54
+ "num_steps": 10,
55
+ "use_cache": true,
56
+ "freeze_vision_encoder": true,
57
+ "train_expert_only": false,
58
+ "train_state_proj": true,
59
+ "optimizer_lr": 0.0001,
60
+ "optimizer_betas": [
61
+ 0.9,
62
+ 0.95
63
+ ],
64
+ "optimizer_eps": 1e-08,
65
+ "optimizer_weight_decay": 1e-10,
66
+ "optimizer_grad_clip_norm": 10,
67
+ "scheduler_warmup_steps": 1000,
68
+ "scheduler_decay_steps": 100000,
69
+ "scheduler_decay_lr": 2.5e-06,
70
+ "vlm_model_name": "/pfss/mlde/workspaces/mlde_wsp_IAS_SAMMerge/VLA/duc/VLA-Humanoid-MW/SmolVLM2-500M-Video-Instruct",
71
+ "load_vlm_weights": true,
72
+ "add_image_special_tokens": false,
73
+ "attention_mode": "cross_attn",
74
+ "prefix_length": 0,
75
+ "pad_language_to": "max_length",
76
+ "num_expert_layers": 0,
77
+ "num_vlm_layers": 16,
78
+ "self_attn_every_n_layers": 2,
79
+ "expert_width_multiplier": 0.75,
80
+ "min_period": 0.004,
81
+ "max_period": 4.0,
82
+ "of_path": "/pfss/mlde/workspaces/mlde_wsp_IAS_SAMMerge/VLA/duc/VLA-Humanoid-MW/ori_mw_if/ori_mw_100%_of.h5"
83
+ }
checkpoints/040000/pretrained_model/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b29d135d4b54bcba25a6f80c723924f2afc9ba6e12187f5d88245452b88540b
3
+ size 934390312
checkpoints/040000/pretrained_model/train_config.json ADDED
@@ -0,0 +1,276 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset": {
3
+ "repo_id": ".",
4
+ "root": "/pfss/mlde/workspaces/mlde_wsp_IAS_SAMMerge/VLA/duc/VLA-Humanoid-MW/metaworld_mt50",
5
+ "episodes": null,
6
+ "image_transforms": {
7
+ "enable": true,
8
+ "max_num_transforms": 3,
9
+ "random_order": false,
10
+ "image_tfs": {
11
+ "hue": {
12
+ "weight": 1.0,
13
+ "type": "ColorJitter",
14
+ "kwargs": {
15
+ "hue": [
16
+ -0.05,
17
+ 0.05
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
+ "sharpness": {
32
+ "weight": 1.0,
33
+ "type": "SharpnessJitter",
34
+ "kwargs": {
35
+ "sharpness": [
36
+ 0.5,
37
+ 1.5
38
+ ]
39
+ }
40
+ },
41
+ "brightness": {
42
+ "weight": 1.0,
43
+ "type": "ColorJitter",
44
+ "kwargs": {
45
+ "brightness": [
46
+ 0.8,
47
+ 1.2
48
+ ]
49
+ }
50
+ },
51
+ "saturation": {
52
+ "weight": 1.0,
53
+ "type": "ColorJitter",
54
+ "kwargs": {
55
+ "saturation": [
56
+ 0.5,
57
+ 1.5
58
+ ]
59
+ }
60
+ },
61
+ "crop_resize": {
62
+ "weight": 1.0,
63
+ "type": "RandomResizedCrop",
64
+ "kwargs": {
65
+ "size": [
66
+ 256,
67
+ 256
68
+ ],
69
+ "ratio": [
70
+ 1,
71
+ 1
72
+ ],
73
+ "scale": [
74
+ 0.9,
75
+ 0.95
76
+ ]
77
+ }
78
+ },
79
+ "rotate": {
80
+ "weight": 1.0,
81
+ "type": "RandomRotate",
82
+ "kwargs": {
83
+ "degrees": [
84
+ -5,
85
+ 5
86
+ ]
87
+ }
88
+ }
89
+ },
90
+ "wrist_tfs": {
91
+ "hue": {
92
+ "weight": 1.0,
93
+ "type": "ColorJitter",
94
+ "kwargs": {
95
+ "hue": [
96
+ -0.05,
97
+ 0.05
98
+ ]
99
+ }
100
+ },
101
+ "contrast": {
102
+ "weight": 1.0,
103
+ "type": "ColorJitter",
104
+ "kwargs": {
105
+ "contrast": [
106
+ 0.8,
107
+ 1.2
108
+ ]
109
+ }
110
+ },
111
+ "sharpness": {
112
+ "weight": 1.0,
113
+ "type": "SharpnessJitter",
114
+ "kwargs": {
115
+ "sharpness": [
116
+ 0.5,
117
+ 1.5
118
+ ]
119
+ }
120
+ },
121
+ "brightness": {
122
+ "weight": 1.0,
123
+ "type": "ColorJitter",
124
+ "kwargs": {
125
+ "brightness": [
126
+ 0.8,
127
+ 1.2
128
+ ]
129
+ }
130
+ },
131
+ "saturation": {
132
+ "weight": 1.0,
133
+ "type": "ColorJitter",
134
+ "kwargs": {
135
+ "saturation": [
136
+ 0.5,
137
+ 1.5
138
+ ]
139
+ }
140
+ }
141
+ }
142
+ },
143
+ "revision": null,
144
+ "use_imagenet_stats": true,
145
+ "video_backend": "torchcodec",
146
+ "vqa_data_path": null
147
+ },
148
+ "env": null,
149
+ "policy": {
150
+ "type": "litevla-ms",
151
+ "n_obs_steps": 1,
152
+ "normalization_mapping": {
153
+ "VISUAL": "IDENTITY",
154
+ "STATE": "MEAN_STD",
155
+ "ACTION": "MEAN_STD"
156
+ },
157
+ "input_features": {
158
+ "observation.state": {
159
+ "type": "STATE",
160
+ "shape": [
161
+ 4
162
+ ]
163
+ },
164
+ "observation.environment_state": {
165
+ "type": "ENV",
166
+ "shape": [
167
+ 39
168
+ ]
169
+ },
170
+ "observation.image": {
171
+ "type": "VISUAL",
172
+ "shape": [
173
+ 3,
174
+ 480,
175
+ 480
176
+ ]
177
+ }
178
+ },
179
+ "output_features": {
180
+ "action": {
181
+ "type": "ACTION",
182
+ "shape": [
183
+ 4
184
+ ]
185
+ }
186
+ },
187
+ "device": "cuda",
188
+ "use_amp": false,
189
+ "gradient_accumulation_steps": 1,
190
+ "chunk_size": 50,
191
+ "n_action_steps": 1,
192
+ "max_state_dim": 32,
193
+ "max_action_dim": 32,
194
+ "resize_imgs_with_padding": [
195
+ 512,
196
+ 512
197
+ ],
198
+ "empty_cameras": 0,
199
+ "adapt_to_pi_aloha": false,
200
+ "use_delta_joint_actions_aloha": false,
201
+ "tokenizer_max_length": 48,
202
+ "num_steps": 10,
203
+ "use_cache": true,
204
+ "freeze_vision_encoder": true,
205
+ "train_expert_only": false,
206
+ "train_state_proj": true,
207
+ "optimizer_lr": 0.0001,
208
+ "optimizer_betas": [
209
+ 0.9,
210
+ 0.95
211
+ ],
212
+ "optimizer_eps": 1e-08,
213
+ "optimizer_weight_decay": 1e-10,
214
+ "optimizer_grad_clip_norm": 10,
215
+ "scheduler_warmup_steps": 1000,
216
+ "scheduler_decay_steps": 100000,
217
+ "scheduler_decay_lr": 2.5e-06,
218
+ "vlm_model_name": "/pfss/mlde/workspaces/mlde_wsp_IAS_SAMMerge/VLA/duc/VLA-Humanoid-MW/SmolVLM2-500M-Video-Instruct",
219
+ "load_vlm_weights": true,
220
+ "add_image_special_tokens": false,
221
+ "attention_mode": "cross_attn",
222
+ "prefix_length": 0,
223
+ "pad_language_to": "max_length",
224
+ "num_expert_layers": 0,
225
+ "num_vlm_layers": 16,
226
+ "self_attn_every_n_layers": 2,
227
+ "expert_width_multiplier": 0.75,
228
+ "min_period": 0.004,
229
+ "max_period": 4.0,
230
+ "of_path": "/pfss/mlde/workspaces/mlde_wsp_IAS_SAMMerge/VLA/duc/VLA-Humanoid-MW/ori_mw_if/ori_mw_100%_of.h5"
231
+ },
232
+ "output_dir": "outputs/train/2026-02-09/08-44-30_MW_100%_scratch_litevla-ms_lastlayer",
233
+ "job_name": "MW_100%_scratch_litevla-ms_lastlayer",
234
+ "resume": false,
235
+ "seed": 42,
236
+ "num_workers": 8,
237
+ "batch_size": 64,
238
+ "steps": 100000,
239
+ "eval_freq": 20000,
240
+ "log_freq": 200,
241
+ "save_checkpoint": true,
242
+ "save_freq": 10000,
243
+ "use_policy_training_preset": true,
244
+ "optimizer": {
245
+ "type": "adamw",
246
+ "lr": 0.0001,
247
+ "weight_decay": 1e-10,
248
+ "grad_clip_norm": 10,
249
+ "betas": [
250
+ 0.9,
251
+ 0.95
252
+ ],
253
+ "eps": 1e-08
254
+ },
255
+ "scheduler": {
256
+ "type": "cosine_decay_with_warmup",
257
+ "num_warmup_steps": 1000,
258
+ "num_decay_steps": 100000,
259
+ "peak_lr": 0.0001,
260
+ "decay_lr": 2.5e-06
261
+ },
262
+ "eval": {
263
+ "n_episodes": 50,
264
+ "batch_size": 50,
265
+ "use_async_envs": false
266
+ },
267
+ "wandb": {
268
+ "enable": true,
269
+ "disable_artifact": true,
270
+ "project": "LiteVLA-MS",
271
+ "entity": "Robotics_VLA",
272
+ "notes": null,
273
+ "run_id": null,
274
+ "mode": "online"
275
+ }
276
+ }
checkpoints/040000/training_state/optimizer_param_groups.json ADDED
@@ -0,0 +1,529 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "lr": 6.631457847577869e-05,
4
+ "betas": [
5
+ 0.9,
6
+ 0.95
7
+ ],
8
+ "eps": 1e-08,
9
+ "weight_decay": 1e-10,
10
+ "amsgrad": false,
11
+ "maximize": false,
12
+ "foreach": null,
13
+ "capturable": false,
14
+ "differentiable": false,
15
+ "fused": null,
16
+ "decoupled_weight_decay": true,
17
+ "initial_lr": 0.0001,
18
+ "params": [
19
+ 0,
20
+ 1,
21
+ 2,
22
+ 3,
23
+ 4,
24
+ 5,
25
+ 6,
26
+ 7,
27
+ 8,
28
+ 9,
29
+ 10,
30
+ 11,
31
+ 12,
32
+ 13,
33
+ 14,
34
+ 15,
35
+ 16,
36
+ 17,
37
+ 18,
38
+ 19,
39
+ 20,
40
+ 21,
41
+ 22,
42
+ 23,
43
+ 24,
44
+ 25,
45
+ 26,
46
+ 27,
47
+ 28,
48
+ 29,
49
+ 30,
50
+ 31,
51
+ 32,
52
+ 33,
53
+ 34,
54
+ 35,
55
+ 36,
56
+ 37,
57
+ 38,
58
+ 39,
59
+ 40,
60
+ 41,
61
+ 42,
62
+ 43,
63
+ 44,
64
+ 45,
65
+ 46,
66
+ 47,
67
+ 48,
68
+ 49,
69
+ 50,
70
+ 51,
71
+ 52,
72
+ 53,
73
+ 54,
74
+ 55,
75
+ 56,
76
+ 57,
77
+ 58,
78
+ 59,
79
+ 60,
80
+ 61,
81
+ 62,
82
+ 63,
83
+ 64,
84
+ 65,
85
+ 66,
86
+ 67,
87
+ 68,
88
+ 69,
89
+ 70,
90
+ 71,
91
+ 72,
92
+ 73,
93
+ 74,
94
+ 75,
95
+ 76,
96
+ 77,
97
+ 78,
98
+ 79,
99
+ 80,
100
+ 81,
101
+ 82,
102
+ 83,
103
+ 84,
104
+ 85,
105
+ 86,
106
+ 87,
107
+ 88,
108
+ 89,
109
+ 90,
110
+ 91,
111
+ 92,
112
+ 93,
113
+ 94,
114
+ 95,
115
+ 96,
116
+ 97,
117
+ 98,
118
+ 99,
119
+ 100,
120
+ 101,
121
+ 102,
122
+ 103,
123
+ 104,
124
+ 105,
125
+ 106,
126
+ 107,
127
+ 108,
128
+ 109,
129
+ 110,
130
+ 111,
131
+ 112,
132
+ 113,
133
+ 114,
134
+ 115,
135
+ 116,
136
+ 117,
137
+ 118,
138
+ 119,
139
+ 120,
140
+ 121,
141
+ 122,
142
+ 123,
143
+ 124,
144
+ 125,
145
+ 126,
146
+ 127,
147
+ 128,
148
+ 129,
149
+ 130,
150
+ 131,
151
+ 132,
152
+ 133,
153
+ 134,
154
+ 135,
155
+ 136,
156
+ 137,
157
+ 138,
158
+ 139,
159
+ 140,
160
+ 141,
161
+ 142,
162
+ 143,
163
+ 144,
164
+ 145,
165
+ 146,
166
+ 147,
167
+ 148,
168
+ 149,
169
+ 150,
170
+ 151,
171
+ 152,
172
+ 153,
173
+ 154,
174
+ 155,
175
+ 156,
176
+ 157,
177
+ 158,
178
+ 159,
179
+ 160,
180
+ 161,
181
+ 162,
182
+ 163,
183
+ 164,
184
+ 165,
185
+ 166,
186
+ 167,
187
+ 168,
188
+ 169,
189
+ 170,
190
+ 171,
191
+ 172,
192
+ 173,
193
+ 174,
194
+ 175,
195
+ 176,
196
+ 177,
197
+ 178,
198
+ 179,
199
+ 180,
200
+ 181,
201
+ 182,
202
+ 183,
203
+ 184,
204
+ 185,
205
+ 186,
206
+ 187,
207
+ 188,
208
+ 189,
209
+ 190,
210
+ 191,
211
+ 192,
212
+ 193,
213
+ 194,
214
+ 195,
215
+ 196,
216
+ 197,
217
+ 198,
218
+ 199,
219
+ 200,
220
+ 201,
221
+ 202,
222
+ 203,
223
+ 204,
224
+ 205,
225
+ 206,
226
+ 207,
227
+ 208,
228
+ 209,
229
+ 210,
230
+ 211,
231
+ 212,
232
+ 213,
233
+ 214,
234
+ 215,
235
+ 216,
236
+ 217,
237
+ 218,
238
+ 219,
239
+ 220,
240
+ 221,
241
+ 222,
242
+ 223,
243
+ 224,
244
+ 225,
245
+ 226,
246
+ 227,
247
+ 228,
248
+ 229,
249
+ 230,
250
+ 231,
251
+ 232,
252
+ 233,
253
+ 234,
254
+ 235,
255
+ 236,
256
+ 237,
257
+ 238,
258
+ 239,
259
+ 240,
260
+ 241,
261
+ 242,
262
+ 243,
263
+ 244,
264
+ 245,
265
+ 246,
266
+ 247,
267
+ 248,
268
+ 249,
269
+ 250,
270
+ 251,
271
+ 252,
272
+ 253,
273
+ 254,
274
+ 255,
275
+ 256,
276
+ 257,
277
+ 258,
278
+ 259,
279
+ 260,
280
+ 261,
281
+ 262,
282
+ 263,
283
+ 264,
284
+ 265,
285
+ 266,
286
+ 267,
287
+ 268,
288
+ 269,
289
+ 270,
290
+ 271,
291
+ 272,
292
+ 273,
293
+ 274,
294
+ 275,
295
+ 276,
296
+ 277,
297
+ 278,
298
+ 279,
299
+ 280,
300
+ 281,
301
+ 282,
302
+ 283,
303
+ 284,
304
+ 285,
305
+ 286,
306
+ 287,
307
+ 288,
308
+ 289,
309
+ 290,
310
+ 291,
311
+ 292,
312
+ 293,
313
+ 294,
314
+ 295,
315
+ 296,
316
+ 297,
317
+ 298,
318
+ 299,
319
+ 300,
320
+ 301,
321
+ 302,
322
+ 303,
323
+ 304,
324
+ 305,
325
+ 306,
326
+ 307,
327
+ 308,
328
+ 309,
329
+ 310,
330
+ 311,
331
+ 312,
332
+ 313,
333
+ 314,
334
+ 315,
335
+ 316,
336
+ 317,
337
+ 318,
338
+ 319,
339
+ 320,
340
+ 321,
341
+ 322,
342
+ 323,
343
+ 324,
344
+ 325,
345
+ 326,
346
+ 327,
347
+ 328,
348
+ 329,
349
+ 330,
350
+ 331,
351
+ 332,
352
+ 333,
353
+ 334,
354
+ 335,
355
+ 336,
356
+ 337,
357
+ 338,
358
+ 339,
359
+ 340,
360
+ 341,
361
+ 342,
362
+ 343,
363
+ 344,
364
+ 345,
365
+ 346,
366
+ 347,
367
+ 348,
368
+ 349,
369
+ 350,
370
+ 351,
371
+ 352,
372
+ 353,
373
+ 354,
374
+ 355,
375
+ 356,
376
+ 357,
377
+ 358,
378
+ 359,
379
+ 360,
380
+ 361,
381
+ 362,
382
+ 363,
383
+ 364,
384
+ 365,
385
+ 366,
386
+ 367,
387
+ 368,
388
+ 369,
389
+ 370,
390
+ 371,
391
+ 372,
392
+ 373,
393
+ 374,
394
+ 375,
395
+ 376,
396
+ 377,
397
+ 378,
398
+ 379,
399
+ 380,
400
+ 381,
401
+ 382,
402
+ 383,
403
+ 384,
404
+ 385,
405
+ 386,
406
+ 387,
407
+ 388,
408
+ 389,
409
+ 390,
410
+ 391,
411
+ 392,
412
+ 393,
413
+ 394,
414
+ 395,
415
+ 396,
416
+ 397,
417
+ 398,
418
+ 399,
419
+ 400,
420
+ 401,
421
+ 402,
422
+ 403,
423
+ 404,
424
+ 405,
425
+ 406,
426
+ 407,
427
+ 408,
428
+ 409,
429
+ 410,
430
+ 411,
431
+ 412,
432
+ 413,
433
+ 414,
434
+ 415,
435
+ 416,
436
+ 417,
437
+ 418,
438
+ 419,
439
+ 420,
440
+ 421,
441
+ 422,
442
+ 423,
443
+ 424,
444
+ 425,
445
+ 426,
446
+ 427,
447
+ 428,
448
+ 429,
449
+ 430,
450
+ 431,
451
+ 432,
452
+ 433,
453
+ 434,
454
+ 435,
455
+ 436,
456
+ 437,
457
+ 438,
458
+ 439,
459
+ 440,
460
+ 441,
461
+ 442,
462
+ 443,
463
+ 444,
464
+ 445,
465
+ 446,
466
+ 447,
467
+ 448,
468
+ 449,
469
+ 450,
470
+ 451,
471
+ 452,
472
+ 453,
473
+ 454,
474
+ 455,
475
+ 456,
476
+ 457,
477
+ 458,
478
+ 459,
479
+ 460,
480
+ 461,
481
+ 462,
482
+ 463,
483
+ 464,
484
+ 465,
485
+ 466,
486
+ 467,
487
+ 468,
488
+ 469,
489
+ 470,
490
+ 471,
491
+ 472,
492
+ 473,
493
+ 474,
494
+ 475,
495
+ 476,
496
+ 477,
497
+ 478,
498
+ 479,
499
+ 480,
500
+ 481,
501
+ 482,
502
+ 483,
503
+ 484,
504
+ 485,
505
+ 486,
506
+ 487,
507
+ 488,
508
+ 489,
509
+ 490,
510
+ 491,
511
+ 492,
512
+ 493,
513
+ 494,
514
+ 495,
515
+ 496,
516
+ 497,
517
+ 498,
518
+ 499,
519
+ 500,
520
+ 501,
521
+ 502,
522
+ 503,
523
+ 504,
524
+ 505,
525
+ 506,
526
+ 507
527
+ ]
528
+ }
529
+ ]
checkpoints/040000/training_state/optimizer_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34ae446d6304d02f3a629b352c5aa2627167d065b87d84745aff47045ec1537b
3
+ size 1333741212
checkpoints/040000/training_state/rng_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf6487bf2426da7edc131a3d9fea3224ecb849d4291485f68a0b46c37faebbc6
3
+ size 15708
checkpoints/040000/training_state/scheduler_state.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "base_lrs": [
3
+ 0.0001
4
+ ],
5
+ "last_epoch": 40000,
6
+ "_step_count": 40001,
7
+ "_is_initial": false,
8
+ "_get_lr_called_within_step": false,
9
+ "_last_lr": [
10
+ 6.631457847577869e-05
11
+ ],
12
+ "lr_lambdas": [
13
+ null
14
+ ]
15
+ }
checkpoints/040000/training_state/training_step.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "step": 40000
3
+ }
checkpoints/050000/pretrained_model/config.json ADDED
@@ -0,0 +1,83 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "type": "litevla-ms",
3
+ "n_obs_steps": 1,
4
+ "normalization_mapping": {
5
+ "VISUAL": "IDENTITY",
6
+ "STATE": "MEAN_STD",
7
+ "ACTION": "MEAN_STD"
8
+ },
9
+ "input_features": {
10
+ "observation.state": {
11
+ "type": "STATE",
12
+ "shape": [
13
+ 4
14
+ ]
15
+ },
16
+ "observation.environment_state": {
17
+ "type": "ENV",
18
+ "shape": [
19
+ 39
20
+ ]
21
+ },
22
+ "observation.image": {
23
+ "type": "VISUAL",
24
+ "shape": [
25
+ 3,
26
+ 480,
27
+ 480
28
+ ]
29
+ }
30
+ },
31
+ "output_features": {
32
+ "action": {
33
+ "type": "ACTION",
34
+ "shape": [
35
+ 4
36
+ ]
37
+ }
38
+ },
39
+ "device": "cuda",
40
+ "use_amp": false,
41
+ "gradient_accumulation_steps": 1,
42
+ "chunk_size": 50,
43
+ "n_action_steps": 1,
44
+ "max_state_dim": 32,
45
+ "max_action_dim": 32,
46
+ "resize_imgs_with_padding": [
47
+ 512,
48
+ 512
49
+ ],
50
+ "empty_cameras": 0,
51
+ "adapt_to_pi_aloha": false,
52
+ "use_delta_joint_actions_aloha": false,
53
+ "tokenizer_max_length": 48,
54
+ "num_steps": 10,
55
+ "use_cache": true,
56
+ "freeze_vision_encoder": true,
57
+ "train_expert_only": false,
58
+ "train_state_proj": true,
59
+ "optimizer_lr": 0.0001,
60
+ "optimizer_betas": [
61
+ 0.9,
62
+ 0.95
63
+ ],
64
+ "optimizer_eps": 1e-08,
65
+ "optimizer_weight_decay": 1e-10,
66
+ "optimizer_grad_clip_norm": 10,
67
+ "scheduler_warmup_steps": 1000,
68
+ "scheduler_decay_steps": 100000,
69
+ "scheduler_decay_lr": 2.5e-06,
70
+ "vlm_model_name": "/pfss/mlde/workspaces/mlde_wsp_IAS_SAMMerge/VLA/duc/VLA-Humanoid-MW/SmolVLM2-500M-Video-Instruct",
71
+ "load_vlm_weights": true,
72
+ "add_image_special_tokens": false,
73
+ "attention_mode": "cross_attn",
74
+ "prefix_length": 0,
75
+ "pad_language_to": "max_length",
76
+ "num_expert_layers": 0,
77
+ "num_vlm_layers": 16,
78
+ "self_attn_every_n_layers": 2,
79
+ "expert_width_multiplier": 0.75,
80
+ "min_period": 0.004,
81
+ "max_period": 4.0,
82
+ "of_path": "/pfss/mlde/workspaces/mlde_wsp_IAS_SAMMerge/VLA/duc/VLA-Humanoid-MW/ori_mw_if/ori_mw_100%_of.h5"
83
+ }
checkpoints/050000/pretrained_model/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2814b340ce751353a290944bbcad5d698d8a5c75ef2a21f2cabeade7a4832fa4
3
+ size 934390312
checkpoints/050000/pretrained_model/train_config.json ADDED
@@ -0,0 +1,276 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset": {
3
+ "repo_id": ".",
4
+ "root": "/pfss/mlde/workspaces/mlde_wsp_IAS_SAMMerge/VLA/duc/VLA-Humanoid-MW/metaworld_mt50",
5
+ "episodes": null,
6
+ "image_transforms": {
7
+ "enable": true,
8
+ "max_num_transforms": 3,
9
+ "random_order": false,
10
+ "image_tfs": {
11
+ "hue": {
12
+ "weight": 1.0,
13
+ "type": "ColorJitter",
14
+ "kwargs": {
15
+ "hue": [
16
+ -0.05,
17
+ 0.05
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
+ "sharpness": {
32
+ "weight": 1.0,
33
+ "type": "SharpnessJitter",
34
+ "kwargs": {
35
+ "sharpness": [
36
+ 0.5,
37
+ 1.5
38
+ ]
39
+ }
40
+ },
41
+ "brightness": {
42
+ "weight": 1.0,
43
+ "type": "ColorJitter",
44
+ "kwargs": {
45
+ "brightness": [
46
+ 0.8,
47
+ 1.2
48
+ ]
49
+ }
50
+ },
51
+ "saturation": {
52
+ "weight": 1.0,
53
+ "type": "ColorJitter",
54
+ "kwargs": {
55
+ "saturation": [
56
+ 0.5,
57
+ 1.5
58
+ ]
59
+ }
60
+ },
61
+ "crop_resize": {
62
+ "weight": 1.0,
63
+ "type": "RandomResizedCrop",
64
+ "kwargs": {
65
+ "size": [
66
+ 256,
67
+ 256
68
+ ],
69
+ "ratio": [
70
+ 1,
71
+ 1
72
+ ],
73
+ "scale": [
74
+ 0.9,
75
+ 0.95
76
+ ]
77
+ }
78
+ },
79
+ "rotate": {
80
+ "weight": 1.0,
81
+ "type": "RandomRotate",
82
+ "kwargs": {
83
+ "degrees": [
84
+ -5,
85
+ 5
86
+ ]
87
+ }
88
+ }
89
+ },
90
+ "wrist_tfs": {
91
+ "hue": {
92
+ "weight": 1.0,
93
+ "type": "ColorJitter",
94
+ "kwargs": {
95
+ "hue": [
96
+ -0.05,
97
+ 0.05
98
+ ]
99
+ }
100
+ },
101
+ "contrast": {
102
+ "weight": 1.0,
103
+ "type": "ColorJitter",
104
+ "kwargs": {
105
+ "contrast": [
106
+ 0.8,
107
+ 1.2
108
+ ]
109
+ }
110
+ },
111
+ "sharpness": {
112
+ "weight": 1.0,
113
+ "type": "SharpnessJitter",
114
+ "kwargs": {
115
+ "sharpness": [
116
+ 0.5,
117
+ 1.5
118
+ ]
119
+ }
120
+ },
121
+ "brightness": {
122
+ "weight": 1.0,
123
+ "type": "ColorJitter",
124
+ "kwargs": {
125
+ "brightness": [
126
+ 0.8,
127
+ 1.2
128
+ ]
129
+ }
130
+ },
131
+ "saturation": {
132
+ "weight": 1.0,
133
+ "type": "ColorJitter",
134
+ "kwargs": {
135
+ "saturation": [
136
+ 0.5,
137
+ 1.5
138
+ ]
139
+ }
140
+ }
141
+ }
142
+ },
143
+ "revision": null,
144
+ "use_imagenet_stats": true,
145
+ "video_backend": "torchcodec",
146
+ "vqa_data_path": null
147
+ },
148
+ "env": null,
149
+ "policy": {
150
+ "type": "litevla-ms",
151
+ "n_obs_steps": 1,
152
+ "normalization_mapping": {
153
+ "VISUAL": "IDENTITY",
154
+ "STATE": "MEAN_STD",
155
+ "ACTION": "MEAN_STD"
156
+ },
157
+ "input_features": {
158
+ "observation.state": {
159
+ "type": "STATE",
160
+ "shape": [
161
+ 4
162
+ ]
163
+ },
164
+ "observation.environment_state": {
165
+ "type": "ENV",
166
+ "shape": [
167
+ 39
168
+ ]
169
+ },
170
+ "observation.image": {
171
+ "type": "VISUAL",
172
+ "shape": [
173
+ 3,
174
+ 480,
175
+ 480
176
+ ]
177
+ }
178
+ },
179
+ "output_features": {
180
+ "action": {
181
+ "type": "ACTION",
182
+ "shape": [
183
+ 4
184
+ ]
185
+ }
186
+ },
187
+ "device": "cuda",
188
+ "use_amp": false,
189
+ "gradient_accumulation_steps": 1,
190
+ "chunk_size": 50,
191
+ "n_action_steps": 1,
192
+ "max_state_dim": 32,
193
+ "max_action_dim": 32,
194
+ "resize_imgs_with_padding": [
195
+ 512,
196
+ 512
197
+ ],
198
+ "empty_cameras": 0,
199
+ "adapt_to_pi_aloha": false,
200
+ "use_delta_joint_actions_aloha": false,
201
+ "tokenizer_max_length": 48,
202
+ "num_steps": 10,
203
+ "use_cache": true,
204
+ "freeze_vision_encoder": true,
205
+ "train_expert_only": false,
206
+ "train_state_proj": true,
207
+ "optimizer_lr": 0.0001,
208
+ "optimizer_betas": [
209
+ 0.9,
210
+ 0.95
211
+ ],
212
+ "optimizer_eps": 1e-08,
213
+ "optimizer_weight_decay": 1e-10,
214
+ "optimizer_grad_clip_norm": 10,
215
+ "scheduler_warmup_steps": 1000,
216
+ "scheduler_decay_steps": 100000,
217
+ "scheduler_decay_lr": 2.5e-06,
218
+ "vlm_model_name": "/pfss/mlde/workspaces/mlde_wsp_IAS_SAMMerge/VLA/duc/VLA-Humanoid-MW/SmolVLM2-500M-Video-Instruct",
219
+ "load_vlm_weights": true,
220
+ "add_image_special_tokens": false,
221
+ "attention_mode": "cross_attn",
222
+ "prefix_length": 0,
223
+ "pad_language_to": "max_length",
224
+ "num_expert_layers": 0,
225
+ "num_vlm_layers": 16,
226
+ "self_attn_every_n_layers": 2,
227
+ "expert_width_multiplier": 0.75,
228
+ "min_period": 0.004,
229
+ "max_period": 4.0,
230
+ "of_path": "/pfss/mlde/workspaces/mlde_wsp_IAS_SAMMerge/VLA/duc/VLA-Humanoid-MW/ori_mw_if/ori_mw_100%_of.h5"
231
+ },
232
+ "output_dir": "outputs/train/2026-02-09/08-44-30_MW_100%_scratch_litevla-ms_lastlayer",
233
+ "job_name": "MW_100%_scratch_litevla-ms_lastlayer",
234
+ "resume": false,
235
+ "seed": 42,
236
+ "num_workers": 8,
237
+ "batch_size": 64,
238
+ "steps": 100000,
239
+ "eval_freq": 20000,
240
+ "log_freq": 200,
241
+ "save_checkpoint": true,
242
+ "save_freq": 10000,
243
+ "use_policy_training_preset": true,
244
+ "optimizer": {
245
+ "type": "adamw",
246
+ "lr": 0.0001,
247
+ "weight_decay": 1e-10,
248
+ "grad_clip_norm": 10,
249
+ "betas": [
250
+ 0.9,
251
+ 0.95
252
+ ],
253
+ "eps": 1e-08
254
+ },
255
+ "scheduler": {
256
+ "type": "cosine_decay_with_warmup",
257
+ "num_warmup_steps": 1000,
258
+ "num_decay_steps": 100000,
259
+ "peak_lr": 0.0001,
260
+ "decay_lr": 2.5e-06
261
+ },
262
+ "eval": {
263
+ "n_episodes": 50,
264
+ "batch_size": 50,
265
+ "use_async_envs": false
266
+ },
267
+ "wandb": {
268
+ "enable": true,
269
+ "disable_artifact": true,
270
+ "project": "LiteVLA-MS",
271
+ "entity": "Robotics_VLA",
272
+ "notes": null,
273
+ "run_id": null,
274
+ "mode": "online"
275
+ }
276
+ }
checkpoints/050000/training_state/optimizer_param_groups.json ADDED
@@ -0,0 +1,529 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "lr": 5.125e-05,
4
+ "betas": [
5
+ 0.9,
6
+ 0.95
7
+ ],
8
+ "eps": 1e-08,
9
+ "weight_decay": 1e-10,
10
+ "amsgrad": false,
11
+ "maximize": false,
12
+ "foreach": null,
13
+ "capturable": false,
14
+ "differentiable": false,
15
+ "fused": null,
16
+ "decoupled_weight_decay": true,
17
+ "initial_lr": 0.0001,
18
+ "params": [
19
+ 0,
20
+ 1,
21
+ 2,
22
+ 3,
23
+ 4,
24
+ 5,
25
+ 6,
26
+ 7,
27
+ 8,
28
+ 9,
29
+ 10,
30
+ 11,
31
+ 12,
32
+ 13,
33
+ 14,
34
+ 15,
35
+ 16,
36
+ 17,
37
+ 18,
38
+ 19,
39
+ 20,
40
+ 21,
41
+ 22,
42
+ 23,
43
+ 24,
44
+ 25,
45
+ 26,
46
+ 27,
47
+ 28,
48
+ 29,
49
+ 30,
50
+ 31,
51
+ 32,
52
+ 33,
53
+ 34,
54
+ 35,
55
+ 36,
56
+ 37,
57
+ 38,
58
+ 39,
59
+ 40,
60
+ 41,
61
+ 42,
62
+ 43,
63
+ 44,
64
+ 45,
65
+ 46,
66
+ 47,
67
+ 48,
68
+ 49,
69
+ 50,
70
+ 51,
71
+ 52,
72
+ 53,
73
+ 54,
74
+ 55,
75
+ 56,
76
+ 57,
77
+ 58,
78
+ 59,
79
+ 60,
80
+ 61,
81
+ 62,
82
+ 63,
83
+ 64,
84
+ 65,
85
+ 66,
86
+ 67,
87
+ 68,
88
+ 69,
89
+ 70,
90
+ 71,
91
+ 72,
92
+ 73,
93
+ 74,
94
+ 75,
95
+ 76,
96
+ 77,
97
+ 78,
98
+ 79,
99
+ 80,
100
+ 81,
101
+ 82,
102
+ 83,
103
+ 84,
104
+ 85,
105
+ 86,
106
+ 87,
107
+ 88,
108
+ 89,
109
+ 90,
110
+ 91,
111
+ 92,
112
+ 93,
113
+ 94,
114
+ 95,
115
+ 96,
116
+ 97,
117
+ 98,
118
+ 99,
119
+ 100,
120
+ 101,
121
+ 102,
122
+ 103,
123
+ 104,
124
+ 105,
125
+ 106,
126
+ 107,
127
+ 108,
128
+ 109,
129
+ 110,
130
+ 111,
131
+ 112,
132
+ 113,
133
+ 114,
134
+ 115,
135
+ 116,
136
+ 117,
137
+ 118,
138
+ 119,
139
+ 120,
140
+ 121,
141
+ 122,
142
+ 123,
143
+ 124,
144
+ 125,
145
+ 126,
146
+ 127,
147
+ 128,
148
+ 129,
149
+ 130,
150
+ 131,
151
+ 132,
152
+ 133,
153
+ 134,
154
+ 135,
155
+ 136,
156
+ 137,
157
+ 138,
158
+ 139,
159
+ 140,
160
+ 141,
161
+ 142,
162
+ 143,
163
+ 144,
164
+ 145,
165
+ 146,
166
+ 147,
167
+ 148,
168
+ 149,
169
+ 150,
170
+ 151,
171
+ 152,
172
+ 153,
173
+ 154,
174
+ 155,
175
+ 156,
176
+ 157,
177
+ 158,
178
+ 159,
179
+ 160,
180
+ 161,
181
+ 162,
182
+ 163,
183
+ 164,
184
+ 165,
185
+ 166,
186
+ 167,
187
+ 168,
188
+ 169,
189
+ 170,
190
+ 171,
191
+ 172,
192
+ 173,
193
+ 174,
194
+ 175,
195
+ 176,
196
+ 177,
197
+ 178,
198
+ 179,
199
+ 180,
200
+ 181,
201
+ 182,
202
+ 183,
203
+ 184,
204
+ 185,
205
+ 186,
206
+ 187,
207
+ 188,
208
+ 189,
209
+ 190,
210
+ 191,
211
+ 192,
212
+ 193,
213
+ 194,
214
+ 195,
215
+ 196,
216
+ 197,
217
+ 198,
218
+ 199,
219
+ 200,
220
+ 201,
221
+ 202,
222
+ 203,
223
+ 204,
224
+ 205,
225
+ 206,
226
+ 207,
227
+ 208,
228
+ 209,
229
+ 210,
230
+ 211,
231
+ 212,
232
+ 213,
233
+ 214,
234
+ 215,
235
+ 216,
236
+ 217,
237
+ 218,
238
+ 219,
239
+ 220,
240
+ 221,
241
+ 222,
242
+ 223,
243
+ 224,
244
+ 225,
245
+ 226,
246
+ 227,
247
+ 228,
248
+ 229,
249
+ 230,
250
+ 231,
251
+ 232,
252
+ 233,
253
+ 234,
254
+ 235,
255
+ 236,
256
+ 237,
257
+ 238,
258
+ 239,
259
+ 240,
260
+ 241,
261
+ 242,
262
+ 243,
263
+ 244,
264
+ 245,
265
+ 246,
266
+ 247,
267
+ 248,
268
+ 249,
269
+ 250,
270
+ 251,
271
+ 252,
272
+ 253,
273
+ 254,
274
+ 255,
275
+ 256,
276
+ 257,
277
+ 258,
278
+ 259,
279
+ 260,
280
+ 261,
281
+ 262,
282
+ 263,
283
+ 264,
284
+ 265,
285
+ 266,
286
+ 267,
287
+ 268,
288
+ 269,
289
+ 270,
290
+ 271,
291
+ 272,
292
+ 273,
293
+ 274,
294
+ 275,
295
+ 276,
296
+ 277,
297
+ 278,
298
+ 279,
299
+ 280,
300
+ 281,
301
+ 282,
302
+ 283,
303
+ 284,
304
+ 285,
305
+ 286,
306
+ 287,
307
+ 288,
308
+ 289,
309
+ 290,
310
+ 291,
311
+ 292,
312
+ 293,
313
+ 294,
314
+ 295,
315
+ 296,
316
+ 297,
317
+ 298,
318
+ 299,
319
+ 300,
320
+ 301,
321
+ 302,
322
+ 303,
323
+ 304,
324
+ 305,
325
+ 306,
326
+ 307,
327
+ 308,
328
+ 309,
329
+ 310,
330
+ 311,
331
+ 312,
332
+ 313,
333
+ 314,
334
+ 315,
335
+ 316,
336
+ 317,
337
+ 318,
338
+ 319,
339
+ 320,
340
+ 321,
341
+ 322,
342
+ 323,
343
+ 324,
344
+ 325,
345
+ 326,
346
+ 327,
347
+ 328,
348
+ 329,
349
+ 330,
350
+ 331,
351
+ 332,
352
+ 333,
353
+ 334,
354
+ 335,
355
+ 336,
356
+ 337,
357
+ 338,
358
+ 339,
359
+ 340,
360
+ 341,
361
+ 342,
362
+ 343,
363
+ 344,
364
+ 345,
365
+ 346,
366
+ 347,
367
+ 348,
368
+ 349,
369
+ 350,
370
+ 351,
371
+ 352,
372
+ 353,
373
+ 354,
374
+ 355,
375
+ 356,
376
+ 357,
377
+ 358,
378
+ 359,
379
+ 360,
380
+ 361,
381
+ 362,
382
+ 363,
383
+ 364,
384
+ 365,
385
+ 366,
386
+ 367,
387
+ 368,
388
+ 369,
389
+ 370,
390
+ 371,
391
+ 372,
392
+ 373,
393
+ 374,
394
+ 375,
395
+ 376,
396
+ 377,
397
+ 378,
398
+ 379,
399
+ 380,
400
+ 381,
401
+ 382,
402
+ 383,
403
+ 384,
404
+ 385,
405
+ 386,
406
+ 387,
407
+ 388,
408
+ 389,
409
+ 390,
410
+ 391,
411
+ 392,
412
+ 393,
413
+ 394,
414
+ 395,
415
+ 396,
416
+ 397,
417
+ 398,
418
+ 399,
419
+ 400,
420
+ 401,
421
+ 402,
422
+ 403,
423
+ 404,
424
+ 405,
425
+ 406,
426
+ 407,
427
+ 408,
428
+ 409,
429
+ 410,
430
+ 411,
431
+ 412,
432
+ 413,
433
+ 414,
434
+ 415,
435
+ 416,
436
+ 417,
437
+ 418,
438
+ 419,
439
+ 420,
440
+ 421,
441
+ 422,
442
+ 423,
443
+ 424,
444
+ 425,
445
+ 426,
446
+ 427,
447
+ 428,
448
+ 429,
449
+ 430,
450
+ 431,
451
+ 432,
452
+ 433,
453
+ 434,
454
+ 435,
455
+ 436,
456
+ 437,
457
+ 438,
458
+ 439,
459
+ 440,
460
+ 441,
461
+ 442,
462
+ 443,
463
+ 444,
464
+ 445,
465
+ 446,
466
+ 447,
467
+ 448,
468
+ 449,
469
+ 450,
470
+ 451,
471
+ 452,
472
+ 453,
473
+ 454,
474
+ 455,
475
+ 456,
476
+ 457,
477
+ 458,
478
+ 459,
479
+ 460,
480
+ 461,
481
+ 462,
482
+ 463,
483
+ 464,
484
+ 465,
485
+ 466,
486
+ 467,
487
+ 468,
488
+ 469,
489
+ 470,
490
+ 471,
491
+ 472,
492
+ 473,
493
+ 474,
494
+ 475,
495
+ 476,
496
+ 477,
497
+ 478,
498
+ 479,
499
+ 480,
500
+ 481,
501
+ 482,
502
+ 483,
503
+ 484,
504
+ 485,
505
+ 486,
506
+ 487,
507
+ 488,
508
+ 489,
509
+ 490,
510
+ 491,
511
+ 492,
512
+ 493,
513
+ 494,
514
+ 495,
515
+ 496,
516
+ 497,
517
+ 498,
518
+ 499,
519
+ 500,
520
+ 501,
521
+ 502,
522
+ 503,
523
+ 504,
524
+ 505,
525
+ 506,
526
+ 507
527
+ ]
528
+ }
529
+ ]
checkpoints/050000/training_state/optimizer_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ed1cac5afe1a074deda41156828ab2feffea6a08a03ce7a83daeadecec06e29
3
+ size 1333741212
checkpoints/050000/training_state/rng_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25533ed902cf4bf1581fbde3cc9df950eb5505d4e55fe12b1768c6fd0cd4675f
3
+ size 15708
checkpoints/050000/training_state/scheduler_state.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "base_lrs": [
3
+ 0.0001
4
+ ],
5
+ "last_epoch": 50000,
6
+ "_step_count": 50001,
7
+ "_is_initial": false,
8
+ "_get_lr_called_within_step": false,
9
+ "_last_lr": [
10
+ 5.125e-05
11
+ ],
12
+ "lr_lambdas": [
13
+ null
14
+ ]
15
+ }
checkpoints/050000/training_state/training_step.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "step": 50000
3
+ }
checkpoints/060000/pretrained_model/config.json ADDED
@@ -0,0 +1,81 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "type": "smolvla",
3
+ "n_obs_steps": 1,
4
+ "normalization_mapping": {
5
+ "VISUAL": "IDENTITY",
6
+ "STATE": "MEAN_STD",
7
+ "ACTION": "MEAN_STD"
8
+ },
9
+ "input_features": {
10
+ "observation.state": {
11
+ "type": "STATE",
12
+ "shape": [
13
+ 4
14
+ ]
15
+ },
16
+ "observation.environment_state": {
17
+ "type": "ENV",
18
+ "shape": [
19
+ 39
20
+ ]
21
+ },
22
+ "observation.image": {
23
+ "type": "VISUAL",
24
+ "shape": [
25
+ 3,
26
+ 480,
27
+ 480
28
+ ]
29
+ }
30
+ },
31
+ "output_features": {
32
+ "action": {
33
+ "type": "ACTION",
34
+ "shape": [
35
+ 4
36
+ ]
37
+ }
38
+ },
39
+ "device": "cuda",
40
+ "use_amp": false,
41
+ "chunk_size": 50,
42
+ "n_action_steps": 1,
43
+ "max_state_dim": 32,
44
+ "max_action_dim": 32,
45
+ "resize_imgs_with_padding": [
46
+ 512,
47
+ 512
48
+ ],
49
+ "empty_cameras": 0,
50
+ "adapt_to_pi_aloha": false,
51
+ "use_delta_joint_actions_aloha": false,
52
+ "tokenizer_max_length": 48,
53
+ "num_steps": 10,
54
+ "use_cache": true,
55
+ "freeze_vision_encoder": true,
56
+ "train_expert_only": false,
57
+ "train_state_proj": true,
58
+ "optimizer_lr": 0.0001,
59
+ "optimizer_betas": [
60
+ 0.9,
61
+ 0.95
62
+ ],
63
+ "optimizer_eps": 1e-08,
64
+ "optimizer_weight_decay": 1e-10,
65
+ "optimizer_grad_clip_norm": 10,
66
+ "scheduler_warmup_steps": 1000,
67
+ "scheduler_decay_steps": 100000,
68
+ "scheduler_decay_lr": 2.5e-06,
69
+ "vlm_model_name": "/pfss/mlde/workspaces/mlde_wsp_IAS_SAMMerge/VLA/duc/VLA-Humanoid-MW/SmolVLM2-500M-Video-Instruct",
70
+ "load_vlm_weights": true,
71
+ "add_image_special_tokens": false,
72
+ "attention_mode": "cross_attn",
73
+ "prefix_length": 0,
74
+ "pad_language_to": "max_length",
75
+ "num_expert_layers": 0,
76
+ "num_vlm_layers": 16,
77
+ "self_attn_every_n_layers": 2,
78
+ "expert_width_multiplier": 0.75,
79
+ "min_period": 0.004,
80
+ "max_period": 4.0
81
+ }
checkpoints/060000/pretrained_model/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:edd6b94a71f1b3793b6cc21242b198da46937c7e7a276736d252b8597eba0fa5
3
+ size 934390312
checkpoints/060000/pretrained_model/train_config.json ADDED
@@ -0,0 +1,276 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset": {
3
+ "repo_id": ".",
4
+ "root": "/pfss/mlde/workspaces/mlde_wsp_IAS_SAMMerge/VLA/duc/VLA-Humanoid-MW/metaworld_mt50",
5
+ "episodes": null,
6
+ "image_transforms": {
7
+ "enable": true,
8
+ "max_num_transforms": 3,
9
+ "random_order": false,
10
+ "image_tfs": {
11
+ "hue": {
12
+ "weight": 1.0,
13
+ "type": "ColorJitter",
14
+ "kwargs": {
15
+ "hue": [
16
+ -0.05,
17
+ 0.05
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
+ "sharpness": {
32
+ "weight": 1.0,
33
+ "type": "SharpnessJitter",
34
+ "kwargs": {
35
+ "sharpness": [
36
+ 0.5,
37
+ 1.5
38
+ ]
39
+ }
40
+ },
41
+ "brightness": {
42
+ "weight": 1.0,
43
+ "type": "ColorJitter",
44
+ "kwargs": {
45
+ "brightness": [
46
+ 0.8,
47
+ 1.2
48
+ ]
49
+ }
50
+ },
51
+ "saturation": {
52
+ "weight": 1.0,
53
+ "type": "ColorJitter",
54
+ "kwargs": {
55
+ "saturation": [
56
+ 0.5,
57
+ 1.5
58
+ ]
59
+ }
60
+ },
61
+ "crop_resize": {
62
+ "weight": 1.0,
63
+ "type": "RandomResizedCrop",
64
+ "kwargs": {
65
+ "size": [
66
+ 256,
67
+ 256
68
+ ],
69
+ "ratio": [
70
+ 1,
71
+ 1
72
+ ],
73
+ "scale": [
74
+ 0.9,
75
+ 0.95
76
+ ]
77
+ }
78
+ },
79
+ "rotate": {
80
+ "weight": 1.0,
81
+ "type": "RandomRotate",
82
+ "kwargs": {
83
+ "degrees": [
84
+ -5,
85
+ 5
86
+ ]
87
+ }
88
+ }
89
+ },
90
+ "wrist_tfs": {
91
+ "hue": {
92
+ "weight": 1.0,
93
+ "type": "ColorJitter",
94
+ "kwargs": {
95
+ "hue": [
96
+ -0.05,
97
+ 0.05
98
+ ]
99
+ }
100
+ },
101
+ "contrast": {
102
+ "weight": 1.0,
103
+ "type": "ColorJitter",
104
+ "kwargs": {
105
+ "contrast": [
106
+ 0.8,
107
+ 1.2
108
+ ]
109
+ }
110
+ },
111
+ "sharpness": {
112
+ "weight": 1.0,
113
+ "type": "SharpnessJitter",
114
+ "kwargs": {
115
+ "sharpness": [
116
+ 0.5,
117
+ 1.5
118
+ ]
119
+ }
120
+ },
121
+ "brightness": {
122
+ "weight": 1.0,
123
+ "type": "ColorJitter",
124
+ "kwargs": {
125
+ "brightness": [
126
+ 0.8,
127
+ 1.2
128
+ ]
129
+ }
130
+ },
131
+ "saturation": {
132
+ "weight": 1.0,
133
+ "type": "ColorJitter",
134
+ "kwargs": {
135
+ "saturation": [
136
+ 0.5,
137
+ 1.5
138
+ ]
139
+ }
140
+ }
141
+ }
142
+ },
143
+ "revision": null,
144
+ "use_imagenet_stats": true,
145
+ "video_backend": "torchcodec",
146
+ "vqa_data_path": null
147
+ },
148
+ "env": null,
149
+ "policy": {
150
+ "type": "litevla-ms",
151
+ "n_obs_steps": 1,
152
+ "normalization_mapping": {
153
+ "VISUAL": "IDENTITY",
154
+ "STATE": "MEAN_STD",
155
+ "ACTION": "MEAN_STD"
156
+ },
157
+ "input_features": {
158
+ "observation.state": {
159
+ "type": "STATE",
160
+ "shape": [
161
+ 4
162
+ ]
163
+ },
164
+ "observation.environment_state": {
165
+ "type": "ENV",
166
+ "shape": [
167
+ 39
168
+ ]
169
+ },
170
+ "observation.image": {
171
+ "type": "VISUAL",
172
+ "shape": [
173
+ 3,
174
+ 480,
175
+ 480
176
+ ]
177
+ }
178
+ },
179
+ "output_features": {
180
+ "action": {
181
+ "type": "ACTION",
182
+ "shape": [
183
+ 4
184
+ ]
185
+ }
186
+ },
187
+ "device": "cuda",
188
+ "use_amp": false,
189
+ "gradient_accumulation_steps": 1,
190
+ "chunk_size": 50,
191
+ "n_action_steps": 1,
192
+ "max_state_dim": 32,
193
+ "max_action_dim": 32,
194
+ "resize_imgs_with_padding": [
195
+ 512,
196
+ 512
197
+ ],
198
+ "empty_cameras": 0,
199
+ "adapt_to_pi_aloha": false,
200
+ "use_delta_joint_actions_aloha": false,
201
+ "tokenizer_max_length": 48,
202
+ "num_steps": 10,
203
+ "use_cache": true,
204
+ "freeze_vision_encoder": true,
205
+ "train_expert_only": false,
206
+ "train_state_proj": true,
207
+ "optimizer_lr": 0.0001,
208
+ "optimizer_betas": [
209
+ 0.9,
210
+ 0.95
211
+ ],
212
+ "optimizer_eps": 1e-08,
213
+ "optimizer_weight_decay": 1e-10,
214
+ "optimizer_grad_clip_norm": 10,
215
+ "scheduler_warmup_steps": 1000,
216
+ "scheduler_decay_steps": 100000,
217
+ "scheduler_decay_lr": 2.5e-06,
218
+ "vlm_model_name": "/pfss/mlde/workspaces/mlde_wsp_IAS_SAMMerge/VLA/duc/VLA-Humanoid-MW/SmolVLM2-500M-Video-Instruct",
219
+ "load_vlm_weights": true,
220
+ "add_image_special_tokens": false,
221
+ "attention_mode": "cross_attn",
222
+ "prefix_length": 0,
223
+ "pad_language_to": "max_length",
224
+ "num_expert_layers": 0,
225
+ "num_vlm_layers": 16,
226
+ "self_attn_every_n_layers": 2,
227
+ "expert_width_multiplier": 0.75,
228
+ "min_period": 0.004,
229
+ "max_period": 4.0,
230
+ "of_path": "/pfss/mlde/workspaces/mlde_wsp_IAS_SAMMerge/VLA/duc/VLA-Humanoid-MW/ori_mw_if/ori_mw_100%_of.h5"
231
+ },
232
+ "output_dir": "outputs/train/2026-02-09/08-44-30_MW_100%_scratch_litevla-ms_lastlayer",
233
+ "job_name": "MW_100%_scratch_litevla-ms_lastlayer",
234
+ "resume": false,
235
+ "seed": 42,
236
+ "num_workers": 8,
237
+ "batch_size": 64,
238
+ "steps": 100000,
239
+ "eval_freq": 20000,
240
+ "log_freq": 200,
241
+ "save_checkpoint": true,
242
+ "save_freq": 10000,
243
+ "use_policy_training_preset": true,
244
+ "optimizer": {
245
+ "type": "adamw",
246
+ "lr": 0.0001,
247
+ "weight_decay": 1e-10,
248
+ "grad_clip_norm": 10,
249
+ "betas": [
250
+ 0.9,
251
+ 0.95
252
+ ],
253
+ "eps": 1e-08
254
+ },
255
+ "scheduler": {
256
+ "type": "cosine_decay_with_warmup",
257
+ "num_warmup_steps": 1000,
258
+ "num_decay_steps": 100000,
259
+ "peak_lr": 0.0001,
260
+ "decay_lr": 2.5e-06
261
+ },
262
+ "eval": {
263
+ "n_episodes": 50,
264
+ "batch_size": 50,
265
+ "use_async_envs": false
266
+ },
267
+ "wandb": {
268
+ "enable": true,
269
+ "disable_artifact": true,
270
+ "project": "LiteVLA-MS",
271
+ "entity": "Robotics_VLA",
272
+ "notes": null,
273
+ "run_id": null,
274
+ "mode": "online"
275
+ }
276
+ }
checkpoints/060000/pretrained_model_migrated/README.md ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: lerobot/smolvla_base
3
+ datasets: unknown
4
+ library_name: lerobot
5
+ license: apache-2.0
6
+ model_name: smolvla
7
+ pipeline_tag: robotics
8
+ tags:
9
+ - smolvla
10
+ - robotics
11
+ - lerobot
12
+ ---
13
+
14
+ # Model Card for smolvla
15
+
16
+ <!-- Provide a quick summary of what the model is/does. -->
17
+
18
+
19
+ [SmolVLA](https://huggingface.co/papers/2506.01844) is a compact, efficient vision-language-action model that achieves competitive performance at reduced computational costs and can be deployed on consumer-grade hardware.
20
+
21
+
22
+ This policy has been trained and pushed to the Hub using [LeRobot](https://github.com/huggingface/lerobot).
23
+ See the full documentation at [LeRobot Docs](https://huggingface.co/docs/lerobot/index).
24
+
25
+ ---
26
+
27
+ ## How to Get Started with the Model
28
+
29
+ For a complete walkthrough, see the [training guide](https://huggingface.co/docs/lerobot/il_robots#train-a-policy).
30
+ Below is the short version on how to train and run inference/eval:
31
+
32
+ ### Train from scratch
33
+
34
+ ```bash
35
+ lerobot-train \
36
+ --dataset.repo_id=${HF_USER}/<dataset> \
37
+ --policy.type=act \
38
+ --output_dir=outputs/train/<desired_policy_repo_id> \
39
+ --job_name=lerobot_training \
40
+ --policy.device=cuda \
41
+ --policy.repo_id=${HF_USER}/<desired_policy_repo_id>
42
+ --wandb.enable=true
43
+ ```
44
+
45
+ _Writes checkpoints to `outputs/train/<desired_policy_repo_id>/checkpoints/`._
46
+
47
+ ### Evaluate the policy/run inference
48
+
49
+ ```bash
50
+ lerobot-record \
51
+ --robot.type=so100_follower \
52
+ --dataset.repo_id=<hf_user>/eval_<dataset> \
53
+ --policy.path=<hf_user>/<desired_policy_repo_id> \
54
+ --episodes=10
55
+ ```
56
+
57
+ Prefix the dataset repo with **eval\_** and supply `--policy.path` pointing to a local or hub checkpoint.
58
+
59
+ ---
60
+
61
+ ## Model Details
62
+
63
+ - **License:** apache-2.0
checkpoints/060000/pretrained_model_migrated/config.json ADDED
@@ -0,0 +1,88 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "type": "smolvla",
3
+ "n_obs_steps": 1,
4
+ "input_features": {
5
+ "observation.state": {
6
+ "type": "STATE",
7
+ "shape": [
8
+ 4
9
+ ]
10
+ },
11
+ "observation.environment_state": {
12
+ "type": "STATE",
13
+ "shape": [
14
+ 39
15
+ ]
16
+ },
17
+ "observation.image": {
18
+ "type": "VISUAL",
19
+ "shape": [
20
+ 3,
21
+ 480,
22
+ 480
23
+ ]
24
+ }
25
+ },
26
+ "output_features": {
27
+ "action": {
28
+ "type": "ACTION",
29
+ "shape": [
30
+ 4
31
+ ]
32
+ }
33
+ },
34
+ "device": "cuda",
35
+ "use_amp": false,
36
+ "push_to_hub": true,
37
+ "repo_id": null,
38
+ "private": null,
39
+ "tags": null,
40
+ "license": null,
41
+ "pretrained_path": null,
42
+ "chunk_size": 50,
43
+ "n_action_steps": 1,
44
+ "normalization_mapping": {
45
+ "VISUAL": "IDENTITY",
46
+ "STATE": "MEAN_STD",
47
+ "ACTION": "MEAN_STD"
48
+ },
49
+ "max_state_dim": 32,
50
+ "max_action_dim": 32,
51
+ "resize_imgs_with_padding": [
52
+ 512,
53
+ 512
54
+ ],
55
+ "empty_cameras": 0,
56
+ "adapt_to_pi_aloha": false,
57
+ "use_delta_joint_actions_aloha": false,
58
+ "tokenizer_max_length": 48,
59
+ "num_steps": 10,
60
+ "use_cache": true,
61
+ "freeze_vision_encoder": true,
62
+ "train_expert_only": false,
63
+ "train_state_proj": true,
64
+ "optimizer_lr": 0.0001,
65
+ "optimizer_betas": [
66
+ 0.9,
67
+ 0.95
68
+ ],
69
+ "optimizer_eps": 1e-08,
70
+ "optimizer_weight_decay": 1e-10,
71
+ "optimizer_grad_clip_norm": 10,
72
+ "scheduler_warmup_steps": 1000,
73
+ "scheduler_decay_steps": 100000,
74
+ "scheduler_decay_lr": 2.5e-06,
75
+ "vlm_model_name": "/pfss/mlde/workspaces/mlde_wsp_IAS_SAMMerge/VLA/duc/VLA-Humanoid-MW/SmolVLM2-500M-Video-Instruct",
76
+ "load_vlm_weights": true,
77
+ "add_image_special_tokens": false,
78
+ "attention_mode": "cross_attn",
79
+ "prefix_length": 0,
80
+ "pad_language_to": "max_length",
81
+ "num_expert_layers": 0,
82
+ "num_vlm_layers": 16,
83
+ "self_attn_every_n_layers": 2,
84
+ "expert_width_multiplier": 0.75,
85
+ "min_period": 0.004,
86
+ "max_period": 4.0,
87
+ "rtc_config": null
88
+ }
checkpoints/060000/pretrained_model_migrated/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3e2268f9f67327eeabe9fdf407cf2b7d07d2a96cc169200311dc06b0306ba57
3
+ size 1800257992
checkpoints/060000/pretrained_model_migrated/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
+ 4
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
+ }
checkpoints/060000/pretrained_model_migrated/policy_postprocessor_step_0_unnormalizer_processor.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43908d0b2a031735826c3fdd8ae685421f8880c66cd1c66c4fd71bd71be68f18
3
+ size 352
checkpoints/060000/pretrained_model_migrated/policy_preprocessor.json ADDED
@@ -0,0 +1,77 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "/pfss/mlde/workspaces/mlde_wsp_IAS_SAMMerge/VLA/duc/VLA-Humanoid-MW/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
+ 4
45
+ ]
46
+ },
47
+ "observation.environment_state": {
48
+ "type": "STATE",
49
+ "shape": [
50
+ 39
51
+ ]
52
+ },
53
+ "observation.image": {
54
+ "type": "VISUAL",
55
+ "shape": [
56
+ 3,
57
+ 480,
58
+ 480
59
+ ]
60
+ },
61
+ "action": {
62
+ "type": "ACTION",
63
+ "shape": [
64
+ 4
65
+ ]
66
+ }
67
+ },
68
+ "norm_map": {
69
+ "VISUAL": "IDENTITY",
70
+ "STATE": "MEAN_STD",
71
+ "ACTION": "MEAN_STD"
72
+ }
73
+ },
74
+ "state_file": "policy_preprocessor_step_5_normalizer_processor.safetensors"
75
+ }
76
+ ]
77
+ }
checkpoints/060000/pretrained_model_migrated/policy_preprocessor_step_5_normalizer_processor.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43908d0b2a031735826c3fdd8ae685421f8880c66cd1c66c4fd71bd71be68f18
3
+ size 352
checkpoints/060000/training_state/optimizer_param_groups.json ADDED
@@ -0,0 +1,529 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "lr": 3.618542152422132e-05,
4
+ "betas": [
5
+ 0.9,
6
+ 0.95
7
+ ],
8
+ "eps": 1e-08,
9
+ "weight_decay": 1e-10,
10
+ "amsgrad": false,
11
+ "maximize": false,
12
+ "foreach": null,
13
+ "capturable": false,
14
+ "differentiable": false,
15
+ "fused": null,
16
+ "decoupled_weight_decay": true,
17
+ "initial_lr": 0.0001,
18
+ "params": [
19
+ 0,
20
+ 1,
21
+ 2,
22
+ 3,
23
+ 4,
24
+ 5,
25
+ 6,
26
+ 7,
27
+ 8,
28
+ 9,
29
+ 10,
30
+ 11,
31
+ 12,
32
+ 13,
33
+ 14,
34
+ 15,
35
+ 16,
36
+ 17,
37
+ 18,
38
+ 19,
39
+ 20,
40
+ 21,
41
+ 22,
42
+ 23,
43
+ 24,
44
+ 25,
45
+ 26,
46
+ 27,
47
+ 28,
48
+ 29,
49
+ 30,
50
+ 31,
51
+ 32,
52
+ 33,
53
+ 34,
54
+ 35,
55
+ 36,
56
+ 37,
57
+ 38,
58
+ 39,
59
+ 40,
60
+ 41,
61
+ 42,
62
+ 43,
63
+ 44,
64
+ 45,
65
+ 46,
66
+ 47,
67
+ 48,
68
+ 49,
69
+ 50,
70
+ 51,
71
+ 52,
72
+ 53,
73
+ 54,
74
+ 55,
75
+ 56,
76
+ 57,
77
+ 58,
78
+ 59,
79
+ 60,
80
+ 61,
81
+ 62,
82
+ 63,
83
+ 64,
84
+ 65,
85
+ 66,
86
+ 67,
87
+ 68,
88
+ 69,
89
+ 70,
90
+ 71,
91
+ 72,
92
+ 73,
93
+ 74,
94
+ 75,
95
+ 76,
96
+ 77,
97
+ 78,
98
+ 79,
99
+ 80,
100
+ 81,
101
+ 82,
102
+ 83,
103
+ 84,
104
+ 85,
105
+ 86,
106
+ 87,
107
+ 88,
108
+ 89,
109
+ 90,
110
+ 91,
111
+ 92,
112
+ 93,
113
+ 94,
114
+ 95,
115
+ 96,
116
+ 97,
117
+ 98,
118
+ 99,
119
+ 100,
120
+ 101,
121
+ 102,
122
+ 103,
123
+ 104,
124
+ 105,
125
+ 106,
126
+ 107,
127
+ 108,
128
+ 109,
129
+ 110,
130
+ 111,
131
+ 112,
132
+ 113,
133
+ 114,
134
+ 115,
135
+ 116,
136
+ 117,
137
+ 118,
138
+ 119,
139
+ 120,
140
+ 121,
141
+ 122,
142
+ 123,
143
+ 124,
144
+ 125,
145
+ 126,
146
+ 127,
147
+ 128,
148
+ 129,
149
+ 130,
150
+ 131,
151
+ 132,
152
+ 133,
153
+ 134,
154
+ 135,
155
+ 136,
156
+ 137,
157
+ 138,
158
+ 139,
159
+ 140,
160
+ 141,
161
+ 142,
162
+ 143,
163
+ 144,
164
+ 145,
165
+ 146,
166
+ 147,
167
+ 148,
168
+ 149,
169
+ 150,
170
+ 151,
171
+ 152,
172
+ 153,
173
+ 154,
174
+ 155,
175
+ 156,
176
+ 157,
177
+ 158,
178
+ 159,
179
+ 160,
180
+ 161,
181
+ 162,
182
+ 163,
183
+ 164,
184
+ 165,
185
+ 166,
186
+ 167,
187
+ 168,
188
+ 169,
189
+ 170,
190
+ 171,
191
+ 172,
192
+ 173,
193
+ 174,
194
+ 175,
195
+ 176,
196
+ 177,
197
+ 178,
198
+ 179,
199
+ 180,
200
+ 181,
201
+ 182,
202
+ 183,
203
+ 184,
204
+ 185,
205
+ 186,
206
+ 187,
207
+ 188,
208
+ 189,
209
+ 190,
210
+ 191,
211
+ 192,
212
+ 193,
213
+ 194,
214
+ 195,
215
+ 196,
216
+ 197,
217
+ 198,
218
+ 199,
219
+ 200,
220
+ 201,
221
+ 202,
222
+ 203,
223
+ 204,
224
+ 205,
225
+ 206,
226
+ 207,
227
+ 208,
228
+ 209,
229
+ 210,
230
+ 211,
231
+ 212,
232
+ 213,
233
+ 214,
234
+ 215,
235
+ 216,
236
+ 217,
237
+ 218,
238
+ 219,
239
+ 220,
240
+ 221,
241
+ 222,
242
+ 223,
243
+ 224,
244
+ 225,
245
+ 226,
246
+ 227,
247
+ 228,
248
+ 229,
249
+ 230,
250
+ 231,
251
+ 232,
252
+ 233,
253
+ 234,
254
+ 235,
255
+ 236,
256
+ 237,
257
+ 238,
258
+ 239,
259
+ 240,
260
+ 241,
261
+ 242,
262
+ 243,
263
+ 244,
264
+ 245,
265
+ 246,
266
+ 247,
267
+ 248,
268
+ 249,
269
+ 250,
270
+ 251,
271
+ 252,
272
+ 253,
273
+ 254,
274
+ 255,
275
+ 256,
276
+ 257,
277
+ 258,
278
+ 259,
279
+ 260,
280
+ 261,
281
+ 262,
282
+ 263,
283
+ 264,
284
+ 265,
285
+ 266,
286
+ 267,
287
+ 268,
288
+ 269,
289
+ 270,
290
+ 271,
291
+ 272,
292
+ 273,
293
+ 274,
294
+ 275,
295
+ 276,
296
+ 277,
297
+ 278,
298
+ 279,
299
+ 280,
300
+ 281,
301
+ 282,
302
+ 283,
303
+ 284,
304
+ 285,
305
+ 286,
306
+ 287,
307
+ 288,
308
+ 289,
309
+ 290,
310
+ 291,
311
+ 292,
312
+ 293,
313
+ 294,
314
+ 295,
315
+ 296,
316
+ 297,
317
+ 298,
318
+ 299,
319
+ 300,
320
+ 301,
321
+ 302,
322
+ 303,
323
+ 304,
324
+ 305,
325
+ 306,
326
+ 307,
327
+ 308,
328
+ 309,
329
+ 310,
330
+ 311,
331
+ 312,
332
+ 313,
333
+ 314,
334
+ 315,
335
+ 316,
336
+ 317,
337
+ 318,
338
+ 319,
339
+ 320,
340
+ 321,
341
+ 322,
342
+ 323,
343
+ 324,
344
+ 325,
345
+ 326,
346
+ 327,
347
+ 328,
348
+ 329,
349
+ 330,
350
+ 331,
351
+ 332,
352
+ 333,
353
+ 334,
354
+ 335,
355
+ 336,
356
+ 337,
357
+ 338,
358
+ 339,
359
+ 340,
360
+ 341,
361
+ 342,
362
+ 343,
363
+ 344,
364
+ 345,
365
+ 346,
366
+ 347,
367
+ 348,
368
+ 349,
369
+ 350,
370
+ 351,
371
+ 352,
372
+ 353,
373
+ 354,
374
+ 355,
375
+ 356,
376
+ 357,
377
+ 358,
378
+ 359,
379
+ 360,
380
+ 361,
381
+ 362,
382
+ 363,
383
+ 364,
384
+ 365,
385
+ 366,
386
+ 367,
387
+ 368,
388
+ 369,
389
+ 370,
390
+ 371,
391
+ 372,
392
+ 373,
393
+ 374,
394
+ 375,
395
+ 376,
396
+ 377,
397
+ 378,
398
+ 379,
399
+ 380,
400
+ 381,
401
+ 382,
402
+ 383,
403
+ 384,
404
+ 385,
405
+ 386,
406
+ 387,
407
+ 388,
408
+ 389,
409
+ 390,
410
+ 391,
411
+ 392,
412
+ 393,
413
+ 394,
414
+ 395,
415
+ 396,
416
+ 397,
417
+ 398,
418
+ 399,
419
+ 400,
420
+ 401,
421
+ 402,
422
+ 403,
423
+ 404,
424
+ 405,
425
+ 406,
426
+ 407,
427
+ 408,
428
+ 409,
429
+ 410,
430
+ 411,
431
+ 412,
432
+ 413,
433
+ 414,
434
+ 415,
435
+ 416,
436
+ 417,
437
+ 418,
438
+ 419,
439
+ 420,
440
+ 421,
441
+ 422,
442
+ 423,
443
+ 424,
444
+ 425,
445
+ 426,
446
+ 427,
447
+ 428,
448
+ 429,
449
+ 430,
450
+ 431,
451
+ 432,
452
+ 433,
453
+ 434,
454
+ 435,
455
+ 436,
456
+ 437,
457
+ 438,
458
+ 439,
459
+ 440,
460
+ 441,
461
+ 442,
462
+ 443,
463
+ 444,
464
+ 445,
465
+ 446,
466
+ 447,
467
+ 448,
468
+ 449,
469
+ 450,
470
+ 451,
471
+ 452,
472
+ 453,
473
+ 454,
474
+ 455,
475
+ 456,
476
+ 457,
477
+ 458,
478
+ 459,
479
+ 460,
480
+ 461,
481
+ 462,
482
+ 463,
483
+ 464,
484
+ 465,
485
+ 466,
486
+ 467,
487
+ 468,
488
+ 469,
489
+ 470,
490
+ 471,
491
+ 472,
492
+ 473,
493
+ 474,
494
+ 475,
495
+ 476,
496
+ 477,
497
+ 478,
498
+ 479,
499
+ 480,
500
+ 481,
501
+ 482,
502
+ 483,
503
+ 484,
504
+ 485,
505
+ 486,
506
+ 487,
507
+ 488,
508
+ 489,
509
+ 490,
510
+ 491,
511
+ 492,
512
+ 493,
513
+ 494,
514
+ 495,
515
+ 496,
516
+ 497,
517
+ 498,
518
+ 499,
519
+ 500,
520
+ 501,
521
+ 502,
522
+ 503,
523
+ 504,
524
+ 505,
525
+ 506,
526
+ 507
527
+ ]
528
+ }
529
+ ]
checkpoints/060000/training_state/optimizer_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db2574e3763c77d9f80c4dd0b46fe9afef3c16091606e4e3dcb1ba3a70ec562d
3
+ size 1333741212
checkpoints/060000/training_state/rng_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60372e80cab5665fd3f1cb8517c951204775532cde1f0bda1a616e76bac27cdf
3
+ size 15708
checkpoints/060000/training_state/scheduler_state.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "base_lrs": [
3
+ 0.0001
4
+ ],
5
+ "last_epoch": 60000,
6
+ "_step_count": 60001,
7
+ "_is_initial": false,
8
+ "_get_lr_called_within_step": false,
9
+ "_last_lr": [
10
+ 3.618542152422132e-05
11
+ ],
12
+ "lr_lambdas": [
13
+ null
14
+ ]
15
+ }
checkpoints/060000/training_state/training_step.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "step": 60000
3
+ }
checkpoints/070000/pretrained_model/config.json ADDED
@@ -0,0 +1,83 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "type": "litevla-ms",
3
+ "n_obs_steps": 1,
4
+ "normalization_mapping": {
5
+ "VISUAL": "IDENTITY",
6
+ "STATE": "MEAN_STD",
7
+ "ACTION": "MEAN_STD"
8
+ },
9
+ "input_features": {
10
+ "observation.state": {
11
+ "type": "STATE",
12
+ "shape": [
13
+ 4
14
+ ]
15
+ },
16
+ "observation.environment_state": {
17
+ "type": "ENV",
18
+ "shape": [
19
+ 39
20
+ ]
21
+ },
22
+ "observation.image": {
23
+ "type": "VISUAL",
24
+ "shape": [
25
+ 3,
26
+ 480,
27
+ 480
28
+ ]
29
+ }
30
+ },
31
+ "output_features": {
32
+ "action": {
33
+ "type": "ACTION",
34
+ "shape": [
35
+ 4
36
+ ]
37
+ }
38
+ },
39
+ "device": "cuda",
40
+ "use_amp": false,
41
+ "gradient_accumulation_steps": 1,
42
+ "chunk_size": 50,
43
+ "n_action_steps": 1,
44
+ "max_state_dim": 32,
45
+ "max_action_dim": 32,
46
+ "resize_imgs_with_padding": [
47
+ 512,
48
+ 512
49
+ ],
50
+ "empty_cameras": 0,
51
+ "adapt_to_pi_aloha": false,
52
+ "use_delta_joint_actions_aloha": false,
53
+ "tokenizer_max_length": 48,
54
+ "num_steps": 10,
55
+ "use_cache": true,
56
+ "freeze_vision_encoder": true,
57
+ "train_expert_only": false,
58
+ "train_state_proj": true,
59
+ "optimizer_lr": 0.0001,
60
+ "optimizer_betas": [
61
+ 0.9,
62
+ 0.95
63
+ ],
64
+ "optimizer_eps": 1e-08,
65
+ "optimizer_weight_decay": 1e-10,
66
+ "optimizer_grad_clip_norm": 10,
67
+ "scheduler_warmup_steps": 1000,
68
+ "scheduler_decay_steps": 100000,
69
+ "scheduler_decay_lr": 2.5e-06,
70
+ "vlm_model_name": "/pfss/mlde/workspaces/mlde_wsp_IAS_SAMMerge/VLA/duc/VLA-Humanoid-MW/SmolVLM2-500M-Video-Instruct",
71
+ "load_vlm_weights": true,
72
+ "add_image_special_tokens": false,
73
+ "attention_mode": "cross_attn",
74
+ "prefix_length": 0,
75
+ "pad_language_to": "max_length",
76
+ "num_expert_layers": 0,
77
+ "num_vlm_layers": 16,
78
+ "self_attn_every_n_layers": 2,
79
+ "expert_width_multiplier": 0.75,
80
+ "min_period": 0.004,
81
+ "max_period": 4.0,
82
+ "of_path": "/pfss/mlde/workspaces/mlde_wsp_IAS_SAMMerge/VLA/duc/VLA-Humanoid-MW/ori_mw_if/ori_mw_100%_of.h5"
83
+ }
checkpoints/070000/pretrained_model/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e37cb00007cf6ac091eff0dc4c1ce71f4f291a5eca19b5b21fec4323c507fd2d
3
+ size 934390312
checkpoints/070000/pretrained_model/train_config.json ADDED
@@ -0,0 +1,276 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset": {
3
+ "repo_id": ".",
4
+ "root": "/pfss/mlde/workspaces/mlde_wsp_IAS_SAMMerge/VLA/duc/VLA-Humanoid-MW/metaworld_mt50",
5
+ "episodes": null,
6
+ "image_transforms": {
7
+ "enable": true,
8
+ "max_num_transforms": 3,
9
+ "random_order": false,
10
+ "image_tfs": {
11
+ "hue": {
12
+ "weight": 1.0,
13
+ "type": "ColorJitter",
14
+ "kwargs": {
15
+ "hue": [
16
+ -0.05,
17
+ 0.05
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
+ "sharpness": {
32
+ "weight": 1.0,
33
+ "type": "SharpnessJitter",
34
+ "kwargs": {
35
+ "sharpness": [
36
+ 0.5,
37
+ 1.5
38
+ ]
39
+ }
40
+ },
41
+ "brightness": {
42
+ "weight": 1.0,
43
+ "type": "ColorJitter",
44
+ "kwargs": {
45
+ "brightness": [
46
+ 0.8,
47
+ 1.2
48
+ ]
49
+ }
50
+ },
51
+ "saturation": {
52
+ "weight": 1.0,
53
+ "type": "ColorJitter",
54
+ "kwargs": {
55
+ "saturation": [
56
+ 0.5,
57
+ 1.5
58
+ ]
59
+ }
60
+ },
61
+ "crop_resize": {
62
+ "weight": 1.0,
63
+ "type": "RandomResizedCrop",
64
+ "kwargs": {
65
+ "size": [
66
+ 256,
67
+ 256
68
+ ],
69
+ "ratio": [
70
+ 1,
71
+ 1
72
+ ],
73
+ "scale": [
74
+ 0.9,
75
+ 0.95
76
+ ]
77
+ }
78
+ },
79
+ "rotate": {
80
+ "weight": 1.0,
81
+ "type": "RandomRotate",
82
+ "kwargs": {
83
+ "degrees": [
84
+ -5,
85
+ 5
86
+ ]
87
+ }
88
+ }
89
+ },
90
+ "wrist_tfs": {
91
+ "hue": {
92
+ "weight": 1.0,
93
+ "type": "ColorJitter",
94
+ "kwargs": {
95
+ "hue": [
96
+ -0.05,
97
+ 0.05
98
+ ]
99
+ }
100
+ },
101
+ "contrast": {
102
+ "weight": 1.0,
103
+ "type": "ColorJitter",
104
+ "kwargs": {
105
+ "contrast": [
106
+ 0.8,
107
+ 1.2
108
+ ]
109
+ }
110
+ },
111
+ "sharpness": {
112
+ "weight": 1.0,
113
+ "type": "SharpnessJitter",
114
+ "kwargs": {
115
+ "sharpness": [
116
+ 0.5,
117
+ 1.5
118
+ ]
119
+ }
120
+ },
121
+ "brightness": {
122
+ "weight": 1.0,
123
+ "type": "ColorJitter",
124
+ "kwargs": {
125
+ "brightness": [
126
+ 0.8,
127
+ 1.2
128
+ ]
129
+ }
130
+ },
131
+ "saturation": {
132
+ "weight": 1.0,
133
+ "type": "ColorJitter",
134
+ "kwargs": {
135
+ "saturation": [
136
+ 0.5,
137
+ 1.5
138
+ ]
139
+ }
140
+ }
141
+ }
142
+ },
143
+ "revision": null,
144
+ "use_imagenet_stats": true,
145
+ "video_backend": "torchcodec",
146
+ "vqa_data_path": null
147
+ },
148
+ "env": null,
149
+ "policy": {
150
+ "type": "litevla-ms",
151
+ "n_obs_steps": 1,
152
+ "normalization_mapping": {
153
+ "VISUAL": "IDENTITY",
154
+ "STATE": "MEAN_STD",
155
+ "ACTION": "MEAN_STD"
156
+ },
157
+ "input_features": {
158
+ "observation.state": {
159
+ "type": "STATE",
160
+ "shape": [
161
+ 4
162
+ ]
163
+ },
164
+ "observation.environment_state": {
165
+ "type": "ENV",
166
+ "shape": [
167
+ 39
168
+ ]
169
+ },
170
+ "observation.image": {
171
+ "type": "VISUAL",
172
+ "shape": [
173
+ 3,
174
+ 480,
175
+ 480
176
+ ]
177
+ }
178
+ },
179
+ "output_features": {
180
+ "action": {
181
+ "type": "ACTION",
182
+ "shape": [
183
+ 4
184
+ ]
185
+ }
186
+ },
187
+ "device": "cuda",
188
+ "use_amp": false,
189
+ "gradient_accumulation_steps": 1,
190
+ "chunk_size": 50,
191
+ "n_action_steps": 1,
192
+ "max_state_dim": 32,
193
+ "max_action_dim": 32,
194
+ "resize_imgs_with_padding": [
195
+ 512,
196
+ 512
197
+ ],
198
+ "empty_cameras": 0,
199
+ "adapt_to_pi_aloha": false,
200
+ "use_delta_joint_actions_aloha": false,
201
+ "tokenizer_max_length": 48,
202
+ "num_steps": 10,
203
+ "use_cache": true,
204
+ "freeze_vision_encoder": true,
205
+ "train_expert_only": false,
206
+ "train_state_proj": true,
207
+ "optimizer_lr": 0.0001,
208
+ "optimizer_betas": [
209
+ 0.9,
210
+ 0.95
211
+ ],
212
+ "optimizer_eps": 1e-08,
213
+ "optimizer_weight_decay": 1e-10,
214
+ "optimizer_grad_clip_norm": 10,
215
+ "scheduler_warmup_steps": 1000,
216
+ "scheduler_decay_steps": 100000,
217
+ "scheduler_decay_lr": 2.5e-06,
218
+ "vlm_model_name": "/pfss/mlde/workspaces/mlde_wsp_IAS_SAMMerge/VLA/duc/VLA-Humanoid-MW/SmolVLM2-500M-Video-Instruct",
219
+ "load_vlm_weights": true,
220
+ "add_image_special_tokens": false,
221
+ "attention_mode": "cross_attn",
222
+ "prefix_length": 0,
223
+ "pad_language_to": "max_length",
224
+ "num_expert_layers": 0,
225
+ "num_vlm_layers": 16,
226
+ "self_attn_every_n_layers": 2,
227
+ "expert_width_multiplier": 0.75,
228
+ "min_period": 0.004,
229
+ "max_period": 4.0,
230
+ "of_path": "/pfss/mlde/workspaces/mlde_wsp_IAS_SAMMerge/VLA/duc/VLA-Humanoid-MW/ori_mw_if/ori_mw_100%_of.h5"
231
+ },
232
+ "output_dir": "outputs/train/2026-02-09/08-44-30_MW_100%_scratch_litevla-ms_lastlayer",
233
+ "job_name": "MW_100%_scratch_litevla-ms_lastlayer",
234
+ "resume": false,
235
+ "seed": 42,
236
+ "num_workers": 8,
237
+ "batch_size": 64,
238
+ "steps": 100000,
239
+ "eval_freq": 20000,
240
+ "log_freq": 200,
241
+ "save_checkpoint": true,
242
+ "save_freq": 10000,
243
+ "use_policy_training_preset": true,
244
+ "optimizer": {
245
+ "type": "adamw",
246
+ "lr": 0.0001,
247
+ "weight_decay": 1e-10,
248
+ "grad_clip_norm": 10,
249
+ "betas": [
250
+ 0.9,
251
+ 0.95
252
+ ],
253
+ "eps": 1e-08
254
+ },
255
+ "scheduler": {
256
+ "type": "cosine_decay_with_warmup",
257
+ "num_warmup_steps": 1000,
258
+ "num_decay_steps": 100000,
259
+ "peak_lr": 0.0001,
260
+ "decay_lr": 2.5e-06
261
+ },
262
+ "eval": {
263
+ "n_episodes": 50,
264
+ "batch_size": 50,
265
+ "use_async_envs": false
266
+ },
267
+ "wandb": {
268
+ "enable": true,
269
+ "disable_artifact": true,
270
+ "project": "LiteVLA-MS",
271
+ "entity": "Robotics_VLA",
272
+ "notes": null,
273
+ "run_id": null,
274
+ "mode": "online"
275
+ }
276
+ }
checkpoints/070000/training_state/optimizer_param_groups.json ADDED
@@ -0,0 +1,529 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "lr": 2.259546895074194e-05,
4
+ "betas": [
5
+ 0.9,
6
+ 0.95
7
+ ],
8
+ "eps": 1e-08,
9
+ "weight_decay": 1e-10,
10
+ "amsgrad": false,
11
+ "maximize": false,
12
+ "foreach": null,
13
+ "capturable": false,
14
+ "differentiable": false,
15
+ "fused": null,
16
+ "decoupled_weight_decay": true,
17
+ "initial_lr": 0.0001,
18
+ "params": [
19
+ 0,
20
+ 1,
21
+ 2,
22
+ 3,
23
+ 4,
24
+ 5,
25
+ 6,
26
+ 7,
27
+ 8,
28
+ 9,
29
+ 10,
30
+ 11,
31
+ 12,
32
+ 13,
33
+ 14,
34
+ 15,
35
+ 16,
36
+ 17,
37
+ 18,
38
+ 19,
39
+ 20,
40
+ 21,
41
+ 22,
42
+ 23,
43
+ 24,
44
+ 25,
45
+ 26,
46
+ 27,
47
+ 28,
48
+ 29,
49
+ 30,
50
+ 31,
51
+ 32,
52
+ 33,
53
+ 34,
54
+ 35,
55
+ 36,
56
+ 37,
57
+ 38,
58
+ 39,
59
+ 40,
60
+ 41,
61
+ 42,
62
+ 43,
63
+ 44,
64
+ 45,
65
+ 46,
66
+ 47,
67
+ 48,
68
+ 49,
69
+ 50,
70
+ 51,
71
+ 52,
72
+ 53,
73
+ 54,
74
+ 55,
75
+ 56,
76
+ 57,
77
+ 58,
78
+ 59,
79
+ 60,
80
+ 61,
81
+ 62,
82
+ 63,
83
+ 64,
84
+ 65,
85
+ 66,
86
+ 67,
87
+ 68,
88
+ 69,
89
+ 70,
90
+ 71,
91
+ 72,
92
+ 73,
93
+ 74,
94
+ 75,
95
+ 76,
96
+ 77,
97
+ 78,
98
+ 79,
99
+ 80,
100
+ 81,
101
+ 82,
102
+ 83,
103
+ 84,
104
+ 85,
105
+ 86,
106
+ 87,
107
+ 88,
108
+ 89,
109
+ 90,
110
+ 91,
111
+ 92,
112
+ 93,
113
+ 94,
114
+ 95,
115
+ 96,
116
+ 97,
117
+ 98,
118
+ 99,
119
+ 100,
120
+ 101,
121
+ 102,
122
+ 103,
123
+ 104,
124
+ 105,
125
+ 106,
126
+ 107,
127
+ 108,
128
+ 109,
129
+ 110,
130
+ 111,
131
+ 112,
132
+ 113,
133
+ 114,
134
+ 115,
135
+ 116,
136
+ 117,
137
+ 118,
138
+ 119,
139
+ 120,
140
+ 121,
141
+ 122,
142
+ 123,
143
+ 124,
144
+ 125,
145
+ 126,
146
+ 127,
147
+ 128,
148
+ 129,
149
+ 130,
150
+ 131,
151
+ 132,
152
+ 133,
153
+ 134,
154
+ 135,
155
+ 136,
156
+ 137,
157
+ 138,
158
+ 139,
159
+ 140,
160
+ 141,
161
+ 142,
162
+ 143,
163
+ 144,
164
+ 145,
165
+ 146,
166
+ 147,
167
+ 148,
168
+ 149,
169
+ 150,
170
+ 151,
171
+ 152,
172
+ 153,
173
+ 154,
174
+ 155,
175
+ 156,
176
+ 157,
177
+ 158,
178
+ 159,
179
+ 160,
180
+ 161,
181
+ 162,
182
+ 163,
183
+ 164,
184
+ 165,
185
+ 166,
186
+ 167,
187
+ 168,
188
+ 169,
189
+ 170,
190
+ 171,
191
+ 172,
192
+ 173,
193
+ 174,
194
+ 175,
195
+ 176,
196
+ 177,
197
+ 178,
198
+ 179,
199
+ 180,
200
+ 181,
201
+ 182,
202
+ 183,
203
+ 184,
204
+ 185,
205
+ 186,
206
+ 187,
207
+ 188,
208
+ 189,
209
+ 190,
210
+ 191,
211
+ 192,
212
+ 193,
213
+ 194,
214
+ 195,
215
+ 196,
216
+ 197,
217
+ 198,
218
+ 199,
219
+ 200,
220
+ 201,
221
+ 202,
222
+ 203,
223
+ 204,
224
+ 205,
225
+ 206,
226
+ 207,
227
+ 208,
228
+ 209,
229
+ 210,
230
+ 211,
231
+ 212,
232
+ 213,
233
+ 214,
234
+ 215,
235
+ 216,
236
+ 217,
237
+ 218,
238
+ 219,
239
+ 220,
240
+ 221,
241
+ 222,
242
+ 223,
243
+ 224,
244
+ 225,
245
+ 226,
246
+ 227,
247
+ 228,
248
+ 229,
249
+ 230,
250
+ 231,
251
+ 232,
252
+ 233,
253
+ 234,
254
+ 235,
255
+ 236,
256
+ 237,
257
+ 238,
258
+ 239,
259
+ 240,
260
+ 241,
261
+ 242,
262
+ 243,
263
+ 244,
264
+ 245,
265
+ 246,
266
+ 247,
267
+ 248,
268
+ 249,
269
+ 250,
270
+ 251,
271
+ 252,
272
+ 253,
273
+ 254,
274
+ 255,
275
+ 256,
276
+ 257,
277
+ 258,
278
+ 259,
279
+ 260,
280
+ 261,
281
+ 262,
282
+ 263,
283
+ 264,
284
+ 265,
285
+ 266,
286
+ 267,
287
+ 268,
288
+ 269,
289
+ 270,
290
+ 271,
291
+ 272,
292
+ 273,
293
+ 274,
294
+ 275,
295
+ 276,
296
+ 277,
297
+ 278,
298
+ 279,
299
+ 280,
300
+ 281,
301
+ 282,
302
+ 283,
303
+ 284,
304
+ 285,
305
+ 286,
306
+ 287,
307
+ 288,
308
+ 289,
309
+ 290,
310
+ 291,
311
+ 292,
312
+ 293,
313
+ 294,
314
+ 295,
315
+ 296,
316
+ 297,
317
+ 298,
318
+ 299,
319
+ 300,
320
+ 301,
321
+ 302,
322
+ 303,
323
+ 304,
324
+ 305,
325
+ 306,
326
+ 307,
327
+ 308,
328
+ 309,
329
+ 310,
330
+ 311,
331
+ 312,
332
+ 313,
333
+ 314,
334
+ 315,
335
+ 316,
336
+ 317,
337
+ 318,
338
+ 319,
339
+ 320,
340
+ 321,
341
+ 322,
342
+ 323,
343
+ 324,
344
+ 325,
345
+ 326,
346
+ 327,
347
+ 328,
348
+ 329,
349
+ 330,
350
+ 331,
351
+ 332,
352
+ 333,
353
+ 334,
354
+ 335,
355
+ 336,
356
+ 337,
357
+ 338,
358
+ 339,
359
+ 340,
360
+ 341,
361
+ 342,
362
+ 343,
363
+ 344,
364
+ 345,
365
+ 346,
366
+ 347,
367
+ 348,
368
+ 349,
369
+ 350,
370
+ 351,
371
+ 352,
372
+ 353,
373
+ 354,
374
+ 355,
375
+ 356,
376
+ 357,
377
+ 358,
378
+ 359,
379
+ 360,
380
+ 361,
381
+ 362,
382
+ 363,
383
+ 364,
384
+ 365,
385
+ 366,
386
+ 367,
387
+ 368,
388
+ 369,
389
+ 370,
390
+ 371,
391
+ 372,
392
+ 373,
393
+ 374,
394
+ 375,
395
+ 376,
396
+ 377,
397
+ 378,
398
+ 379,
399
+ 380,
400
+ 381,
401
+ 382,
402
+ 383,
403
+ 384,
404
+ 385,
405
+ 386,
406
+ 387,
407
+ 388,
408
+ 389,
409
+ 390,
410
+ 391,
411
+ 392,
412
+ 393,
413
+ 394,
414
+ 395,
415
+ 396,
416
+ 397,
417
+ 398,
418
+ 399,
419
+ 400,
420
+ 401,
421
+ 402,
422
+ 403,
423
+ 404,
424
+ 405,
425
+ 406,
426
+ 407,
427
+ 408,
428
+ 409,
429
+ 410,
430
+ 411,
431
+ 412,
432
+ 413,
433
+ 414,
434
+ 415,
435
+ 416,
436
+ 417,
437
+ 418,
438
+ 419,
439
+ 420,
440
+ 421,
441
+ 422,
442
+ 423,
443
+ 424,
444
+ 425,
445
+ 426,
446
+ 427,
447
+ 428,
448
+ 429,
449
+ 430,
450
+ 431,
451
+ 432,
452
+ 433,
453
+ 434,
454
+ 435,
455
+ 436,
456
+ 437,
457
+ 438,
458
+ 439,
459
+ 440,
460
+ 441,
461
+ 442,
462
+ 443,
463
+ 444,
464
+ 445,
465
+ 446,
466
+ 447,
467
+ 448,
468
+ 449,
469
+ 450,
470
+ 451,
471
+ 452,
472
+ 453,
473
+ 454,
474
+ 455,
475
+ 456,
476
+ 457,
477
+ 458,
478
+ 459,
479
+ 460,
480
+ 461,
481
+ 462,
482
+ 463,
483
+ 464,
484
+ 465,
485
+ 466,
486
+ 467,
487
+ 468,
488
+ 469,
489
+ 470,
490
+ 471,
491
+ 472,
492
+ 473,
493
+ 474,
494
+ 475,
495
+ 476,
496
+ 477,
497
+ 478,
498
+ 479,
499
+ 480,
500
+ 481,
501
+ 482,
502
+ 483,
503
+ 484,
504
+ 485,
505
+ 486,
506
+ 487,
507
+ 488,
508
+ 489,
509
+ 490,
510
+ 491,
511
+ 492,
512
+ 493,
513
+ 494,
514
+ 495,
515
+ 496,
516
+ 497,
517
+ 498,
518
+ 499,
519
+ 500,
520
+ 501,
521
+ 502,
522
+ 503,
523
+ 504,
524
+ 505,
525
+ 506,
526
+ 507
527
+ ]
528
+ }
529
+ ]
checkpoints/070000/training_state/optimizer_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:195fb0a22415dc179470b7cad1b4e4790862cf49530bc56ccc9242fb9b0c8b04
3
+ size 1333741212
checkpoints/070000/training_state/rng_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8db075e66e8192ed5ce15fd42d6cd690707219740c3dad7980a57ca2e2975fa9
3
+ size 15708
checkpoints/070000/training_state/scheduler_state.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "base_lrs": [
3
+ 0.0001
4
+ ],
5
+ "last_epoch": 70000,
6
+ "_step_count": 70001,
7
+ "_is_initial": false,
8
+ "_get_lr_called_within_step": false,
9
+ "_last_lr": [
10
+ 2.259546895074194e-05
11
+ ],
12
+ "lr_lambdas": [
13
+ null
14
+ ]
15
+ }
checkpoints/070000/training_state/training_step.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "step": 70000
3
+ }
checkpoints/080000/pretrained_model/config.json ADDED
@@ -0,0 +1,81 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "type": "smolvla",
3
+ "n_obs_steps": 1,
4
+ "normalization_mapping": {
5
+ "VISUAL": "IDENTITY",
6
+ "STATE": "MEAN_STD",
7
+ "ACTION": "MEAN_STD"
8
+ },
9
+ "input_features": {
10
+ "observation.state": {
11
+ "type": "STATE",
12
+ "shape": [
13
+ 4
14
+ ]
15
+ },
16
+ "observation.environment_state": {
17
+ "type": "ENV",
18
+ "shape": [
19
+ 39
20
+ ]
21
+ },
22
+ "observation.image": {
23
+ "type": "VISUAL",
24
+ "shape": [
25
+ 3,
26
+ 480,
27
+ 480
28
+ ]
29
+ }
30
+ },
31
+ "output_features": {
32
+ "action": {
33
+ "type": "ACTION",
34
+ "shape": [
35
+ 4
36
+ ]
37
+ }
38
+ },
39
+ "device": "cuda",
40
+ "use_amp": false,
41
+ "chunk_size": 50,
42
+ "n_action_steps": 1,
43
+ "max_state_dim": 32,
44
+ "max_action_dim": 32,
45
+ "resize_imgs_with_padding": [
46
+ 512,
47
+ 512
48
+ ],
49
+ "empty_cameras": 0,
50
+ "adapt_to_pi_aloha": false,
51
+ "use_delta_joint_actions_aloha": false,
52
+ "tokenizer_max_length": 48,
53
+ "num_steps": 10,
54
+ "use_cache": true,
55
+ "freeze_vision_encoder": true,
56
+ "train_expert_only": false,
57
+ "train_state_proj": true,
58
+ "optimizer_lr": 0.0001,
59
+ "optimizer_betas": [
60
+ 0.9,
61
+ 0.95
62
+ ],
63
+ "optimizer_eps": 1e-08,
64
+ "optimizer_weight_decay": 1e-10,
65
+ "optimizer_grad_clip_norm": 10,
66
+ "scheduler_warmup_steps": 1000,
67
+ "scheduler_decay_steps": 100000,
68
+ "scheduler_decay_lr": 2.5e-06,
69
+ "vlm_model_name": "/pfss/mlde/workspaces/mlde_wsp_IAS_SAMMerge/VLA/duc/VLA-Humanoid-MW/SmolVLM2-500M-Video-Instruct",
70
+ "load_vlm_weights": true,
71
+ "add_image_special_tokens": false,
72
+ "attention_mode": "cross_attn",
73
+ "prefix_length": 0,
74
+ "pad_language_to": "max_length",
75
+ "num_expert_layers": 0,
76
+ "num_vlm_layers": 16,
77
+ "self_attn_every_n_layers": 2,
78
+ "expert_width_multiplier": 0.75,
79
+ "min_period": 0.004,
80
+ "max_period": 4.0
81
+ }
checkpoints/080000/pretrained_model/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81eea4a01f04ff2aaa08e33a891802d496ddb5e281b3cdf4873dfd3368cd3e3f
3
+ size 934390312