MCeut commited on
Commit
aefeda7
·
verified ·
1 Parent(s): 75f4163

Upload folder using huggingface_hub

Browse files
.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-20250821_235211-3qesni5p/run-3qesni5p.wandb filter=lfs diff=lfs merge=lfs -text
checkpoints/020000/pretrained_model/config.json ADDED
@@ -0,0 +1,88 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ 6
14
+ ]
15
+ },
16
+ "observation.images.front": {
17
+ "type": "VISUAL",
18
+ "shape": [
19
+ 3,
20
+ 480,
21
+ 640
22
+ ]
23
+ },
24
+ "observation.images.left": {
25
+ "type": "VISUAL",
26
+ "shape": [
27
+ 3,
28
+ 480,
29
+ 640
30
+ ]
31
+ }
32
+ },
33
+ "output_features": {
34
+ "action": {
35
+ "type": "ACTION",
36
+ "shape": [
37
+ 6
38
+ ]
39
+ }
40
+ },
41
+ "device": "cuda",
42
+ "use_amp": false,
43
+ "push_to_hub": true,
44
+ "repo_id": "/so101_smolvla_push_cube_test2",
45
+ "private": null,
46
+ "tags": null,
47
+ "license": null,
48
+ "chunk_size": 50,
49
+ "n_action_steps": 50,
50
+ "max_state_dim": 32,
51
+ "max_action_dim": 32,
52
+ "resize_imgs_with_padding": [
53
+ 512,
54
+ 512
55
+ ],
56
+ "empty_cameras": 0,
57
+ "adapt_to_pi_aloha": false,
58
+ "use_delta_joint_actions_aloha": false,
59
+ "tokenizer_max_length": 48,
60
+ "num_steps": 10,
61
+ "use_cache": true,
62
+ "freeze_vision_encoder": true,
63
+ "train_expert_only": true,
64
+ "train_state_proj": true,
65
+ "optimizer_lr": 0.0001,
66
+ "optimizer_betas": [
67
+ 0.9,
68
+ 0.95
69
+ ],
70
+ "optimizer_eps": 1e-08,
71
+ "optimizer_weight_decay": 1e-10,
72
+ "optimizer_grad_clip_norm": 10.0,
73
+ "scheduler_warmup_steps": 1000,
74
+ "scheduler_decay_steps": 30000,
75
+ "scheduler_decay_lr": 2.5e-06,
76
+ "vlm_model_name": "HuggingFaceTB/SmolVLM2-500M-Video-Instruct",
77
+ "load_vlm_weights": true,
78
+ "add_image_special_tokens": false,
79
+ "attention_mode": "cross_attn",
80
+ "prefix_length": 0,
81
+ "pad_language_to": "max_length",
82
+ "num_expert_layers": 0,
83
+ "num_vlm_layers": 16,
84
+ "self_attn_every_n_layers": 2,
85
+ "expert_width_multiplier": 0.75,
86
+ "min_period": 0.004,
87
+ "max_period": 4.0
88
+ }
checkpoints/020000/pretrained_model/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09d7ac4fe81f11c3bf69769634b34816233e4552a60f9c82187b6a327eed24cb
3
+ size 906713296
checkpoints/020000/pretrained_model/train_config.json ADDED
@@ -0,0 +1,200 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset": {
3
+ "repo_id": "MCeut/so101_push_cube_test1",
4
+ "root": null,
5
+ "episodes": null,
6
+ "image_transforms": {
7
+ "enable": false,
8
+ "max_num_transforms": 3,
9
+ "random_order": false,
10
+ "tfs": {
11
+ "brightness": {
12
+ "weight": 1.0,
13
+ "type": "ColorJitter",
14
+ "kwargs": {
15
+ "brightness": [
16
+ 0.8,
17
+ 1.2
18
+ ]
19
+ }
20
+ },
21
+ "contrast": {
22
+ "weight": 1.0,
23
+ "type": "ColorJitter",
24
+ "kwargs": {
25
+ "contrast": [
26
+ 0.8,
27
+ 1.2
28
+ ]
29
+ }
30
+ },
31
+ "saturation": {
32
+ "weight": 1.0,
33
+ "type": "ColorJitter",
34
+ "kwargs": {
35
+ "saturation": [
36
+ 0.5,
37
+ 1.5
38
+ ]
39
+ }
40
+ },
41
+ "hue": {
42
+ "weight": 1.0,
43
+ "type": "ColorJitter",
44
+ "kwargs": {
45
+ "hue": [
46
+ -0.05,
47
+ 0.05
48
+ ]
49
+ }
50
+ },
51
+ "sharpness": {
52
+ "weight": 1.0,
53
+ "type": "SharpnessJitter",
54
+ "kwargs": {
55
+ "sharpness": [
56
+ 0.5,
57
+ 1.5
58
+ ]
59
+ }
60
+ }
61
+ }
62
+ },
63
+ "revision": null,
64
+ "use_imagenet_stats": true,
65
+ "video_backend": "pyav"
66
+ },
67
+ "env": null,
68
+ "policy": {
69
+ "type": "smolvla",
70
+ "n_obs_steps": 1,
71
+ "normalization_mapping": {
72
+ "VISUAL": "IDENTITY",
73
+ "STATE": "MEAN_STD",
74
+ "ACTION": "MEAN_STD"
75
+ },
76
+ "input_features": {
77
+ "observation.state": {
78
+ "type": "STATE",
79
+ "shape": [
80
+ 6
81
+ ]
82
+ },
83
+ "observation.images.front": {
84
+ "type": "VISUAL",
85
+ "shape": [
86
+ 3,
87
+ 480,
88
+ 640
89
+ ]
90
+ },
91
+ "observation.images.left": {
92
+ "type": "VISUAL",
93
+ "shape": [
94
+ 3,
95
+ 480,
96
+ 640
97
+ ]
98
+ }
99
+ },
100
+ "output_features": {
101
+ "action": {
102
+ "type": "ACTION",
103
+ "shape": [
104
+ 6
105
+ ]
106
+ }
107
+ },
108
+ "device": "cuda",
109
+ "use_amp": false,
110
+ "push_to_hub": true,
111
+ "repo_id": "/so101_smolvla_push_cube_test2",
112
+ "private": null,
113
+ "tags": null,
114
+ "license": null,
115
+ "chunk_size": 50,
116
+ "n_action_steps": 50,
117
+ "max_state_dim": 32,
118
+ "max_action_dim": 32,
119
+ "resize_imgs_with_padding": [
120
+ 512,
121
+ 512
122
+ ],
123
+ "empty_cameras": 0,
124
+ "adapt_to_pi_aloha": false,
125
+ "use_delta_joint_actions_aloha": false,
126
+ "tokenizer_max_length": 48,
127
+ "num_steps": 10,
128
+ "use_cache": true,
129
+ "freeze_vision_encoder": true,
130
+ "train_expert_only": true,
131
+ "train_state_proj": true,
132
+ "optimizer_lr": 0.0001,
133
+ "optimizer_betas": [
134
+ 0.9,
135
+ 0.95
136
+ ],
137
+ "optimizer_eps": 1e-08,
138
+ "optimizer_weight_decay": 1e-10,
139
+ "optimizer_grad_clip_norm": 10.0,
140
+ "scheduler_warmup_steps": 1000,
141
+ "scheduler_decay_steps": 30000,
142
+ "scheduler_decay_lr": 2.5e-06,
143
+ "vlm_model_name": "HuggingFaceTB/SmolVLM2-500M-Video-Instruct",
144
+ "load_vlm_weights": true,
145
+ "add_image_special_tokens": false,
146
+ "attention_mode": "cross_attn",
147
+ "prefix_length": 0,
148
+ "pad_language_to": "max_length",
149
+ "num_expert_layers": 0,
150
+ "num_vlm_layers": 16,
151
+ "self_attn_every_n_layers": 2,
152
+ "expert_width_multiplier": 0.75,
153
+ "min_period": 0.004,
154
+ "max_period": 4.0
155
+ },
156
+ "output_dir": "outputs/train/so101_smolvla_push_cube_test2",
157
+ "job_name": "so101_smolvla_training_push_cube_test2",
158
+ "resume": false,
159
+ "seed": 1000,
160
+ "num_workers": 4,
161
+ "batch_size": 64,
162
+ "steps": 20000,
163
+ "eval_freq": 20000,
164
+ "log_freq": 200,
165
+ "save_checkpoint": true,
166
+ "save_freq": 20000,
167
+ "use_policy_training_preset": true,
168
+ "optimizer": {
169
+ "type": "adamw",
170
+ "lr": 0.0001,
171
+ "weight_decay": 1e-10,
172
+ "grad_clip_norm": 10.0,
173
+ "betas": [
174
+ 0.9,
175
+ 0.95
176
+ ],
177
+ "eps": 1e-08
178
+ },
179
+ "scheduler": {
180
+ "type": "cosine_decay_with_warmup",
181
+ "num_warmup_steps": 1000,
182
+ "num_decay_steps": 30000,
183
+ "peak_lr": 0.0001,
184
+ "decay_lr": 2.5e-06
185
+ },
186
+ "eval": {
187
+ "n_episodes": 50,
188
+ "batch_size": 50,
189
+ "use_async_envs": false
190
+ },
191
+ "wandb": {
192
+ "enable": true,
193
+ "disable_artifact": false,
194
+ "project": "lerobot",
195
+ "entity": null,
196
+ "notes": null,
197
+ "run_id": "3qesni5p",
198
+ "mode": null
199
+ }
200
+ }
checkpoints/020000/training_state/optimizer_param_groups.json ADDED
@@ -0,0 +1,527 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "lr": 2.6875000000000013e-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
+ ]
526
+ }
527
+ ]
checkpoints/020000/training_state/optimizer_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:555a818c77b95ae335a7bfc8252a5bc8a95873d9e7826dea0410b45e2a3b1e7d
3
+ size 412659164
checkpoints/020000/training_state/rng_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45d37f29dee32e280c7d7c4c3c3c626bdcddc32e429f1b8e9705c5a9227ea3cb
3
+ size 15708
checkpoints/020000/training_state/scheduler_state.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "base_lrs": [
3
+ 0.0001
4
+ ],
5
+ "last_epoch": 20000,
6
+ "_step_count": 20001,
7
+ "_get_lr_called_within_step": false,
8
+ "_last_lr": [
9
+ 2.6875000000000013e-05
10
+ ],
11
+ "lr_lambdas": [
12
+ null
13
+ ]
14
+ }
checkpoints/020000/training_state/training_step.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "step": 20000
3
+ }
wandb/debug-internal.log ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"time":"2025-08-21T23:52:11.757259626+02:00","level":"INFO","msg":"stream: starting","core version":"0.21.0"}
2
+ {"time":"2025-08-21T23:52:12.132021046+02:00","level":"INFO","msg":"stream: created new stream","id":"3qesni5p"}
3
+ {"time":"2025-08-21T23:52:12.132078765+02:00","level":"INFO","msg":"writer: Do: started","stream_id":"3qesni5p"}
4
+ {"time":"2025-08-21T23:52:12.132115895+02:00","level":"INFO","msg":"sender: started","stream_id":"3qesni5p"}
5
+ {"time":"2025-08-21T23:52:12.132147155+02:00","level":"INFO","msg":"handler: started","stream_id":"3qesni5p"}
6
+ {"time":"2025-08-21T23:52:12.132151414+02:00","level":"INFO","msg":"stream: started","id":"3qesni5p"}
7
+ {"time":"2025-08-22T06:01:02.138644824+02:00","level":"INFO","msg":"stream: closing","id":"3qesni5p"}
8
+ {"time":"2025-08-22T06:03:39.010797634+02:00","level":"INFO","msg":"fileTransfer: Close: file transfer manager closed"}
9
+ {"time":"2025-08-22T06:03:39.21518114+02:00","level":"INFO","msg":"handler: closed","stream_id":"3qesni5p"}
10
+ {"time":"2025-08-22T06:03:39.215212987+02:00","level":"INFO","msg":"writer: Close: closed","stream_id":"3qesni5p"}
11
+ {"time":"2025-08-22T06:03:39.215220482+02:00","level":"INFO","msg":"sender: closed","stream_id":"3qesni5p"}
12
+ {"time":"2025-08-22T06:03:39.221321624+02:00","level":"INFO","msg":"stream: closed","id":"3qesni5p"}
wandb/debug.log ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2025-08-21 23:52:11,541 INFO MainThread:2718618 [wandb_setup.py:_flush():80] Current SDK version is 0.21.0
2
+ 2025-08-21 23:52:11,541 INFO MainThread:2718618 [wandb_setup.py:_flush():80] Configure stats pid to 2718618
3
+ 2025-08-21 23:52:11,541 INFO MainThread:2718618 [wandb_setup.py:_flush():80] Loading settings from /home/collab/.config/wandb/settings
4
+ 2025-08-21 23:52:11,541 INFO MainThread:2718618 [wandb_setup.py:_flush():80] Loading settings from /home/collab/git/lerobot/wandb/settings
5
+ 2025-08-21 23:52:11,541 INFO MainThread:2718618 [wandb_setup.py:_flush():80] Loading settings from environment variables
6
+ 2025-08-21 23:52:11,541 INFO MainThread:2718618 [wandb_init.py:setup_run_log_directory():703] Logging user logs to outputs/train/so101_smolvla_push_cube_test2/wandb/run-20250821_235211-3qesni5p/logs/debug.log
7
+ 2025-08-21 23:52:11,541 INFO MainThread:2718618 [wandb_init.py:setup_run_log_directory():704] Logging internal logs to outputs/train/so101_smolvla_push_cube_test2/wandb/run-20250821_235211-3qesni5p/logs/debug-internal.log
8
+ 2025-08-21 23:52:11,542 INFO MainThread:2718618 [wandb_init.py:init():830] calling init triggers
9
+ 2025-08-21 23:52:11,542 INFO MainThread:2718618 [wandb_init.py:init():835] wandb.init called with sweep_config: {}
10
+ config: {'dataset': {'repo_id': 'MCeut/so101_push_cube_test1', 'root': None, 'episodes': None, 'image_transforms': {'enable': False, 'max_num_transforms': 3, 'random_order': False, 'tfs': {'brightness': {'weight': 1.0, 'type': 'ColorJitter', 'kwargs': {'brightness': [0.8, 1.2]}}, 'contrast': {'weight': 1.0, 'type': 'ColorJitter', 'kwargs': {'contrast': [0.8, 1.2]}}, 'saturation': {'weight': 1.0, 'type': 'ColorJitter', 'kwargs': {'saturation': [0.5, 1.5]}}, 'hue': {'weight': 1.0, 'type': 'ColorJitter', 'kwargs': {'hue': [-0.05, 0.05]}}, 'sharpness': {'weight': 1.0, 'type': 'SharpnessJitter', 'kwargs': {'sharpness': [0.5, 1.5]}}}}, 'revision': None, 'use_imagenet_stats': True, 'video_backend': 'pyav'}, 'env': None, 'policy': {'type': 'smolvla', 'n_obs_steps': 1, 'normalization_mapping': {'VISUAL': <NormalizationMode.IDENTITY: 'IDENTITY'>, 'STATE': <NormalizationMode.MEAN_STD: 'MEAN_STD'>, 'ACTION': <NormalizationMode.MEAN_STD: 'MEAN_STD'>}, 'input_features': {'observation.state': {'type': <FeatureType.STATE: 'STATE'>, 'shape': [6]}, 'observation.image2': {'type': <FeatureType.VISUAL: 'VISUAL'>, 'shape': [3, 256, 256]}, 'observation.image': {'type': <FeatureType.VISUAL: 'VISUAL'>, 'shape': [3, 256, 256]}, 'observation.image3': {'type': <FeatureType.VISUAL: 'VISUAL'>, 'shape': [3, 256, 256]}}, 'output_features': {'action': {'type': <FeatureType.ACTION: 'ACTION'>, 'shape': [6]}}, 'device': 'cuda', 'use_amp': False, 'push_to_hub': True, 'repo_id': '/so101_smolvla_push_cube_test2', 'private': None, 'tags': None, 'license': None, 'chunk_size': 50, 'n_action_steps': 50, 'max_state_dim': 32, 'max_action_dim': 32, 'resize_imgs_with_padding': [512, 512], 'empty_cameras': 0, 'adapt_to_pi_aloha': False, 'use_delta_joint_actions_aloha': False, 'tokenizer_max_length': 48, 'num_steps': 10, 'use_cache': True, 'freeze_vision_encoder': True, 'train_expert_only': True, 'train_state_proj': True, 'optimizer_lr': 0.0001, 'optimizer_betas': [0.9, 0.95], 'optimizer_eps': 1e-08, 'optimizer_weight_decay': 1e-10, 'optimizer_grad_clip_norm': 10.0, 'scheduler_warmup_steps': 1000, 'scheduler_decay_steps': 30000, 'scheduler_decay_lr': 2.5e-06, 'vlm_model_name': 'HuggingFaceTB/SmolVLM2-500M-Video-Instruct', 'load_vlm_weights': True, 'add_image_special_tokens': False, 'attention_mode': 'cross_attn', 'prefix_length': 0, 'pad_language_to': 'max_length', 'num_expert_layers': 0, 'num_vlm_layers': 16, 'self_attn_every_n_layers': 2, 'expert_width_multiplier': 0.75, 'min_period': 0.004, 'max_period': 4.0}, 'output_dir': 'outputs/train/so101_smolvla_push_cube_test2', 'job_name': 'so101_smolvla_training_push_cube_test2', 'resume': False, 'seed': 1000, 'num_workers': 4, 'batch_size': 64, 'steps': 20000, 'eval_freq': 20000, 'log_freq': 200, 'save_checkpoint': True, 'save_freq': 20000, 'use_policy_training_preset': True, 'optimizer': {'type': 'adamw', 'lr': 0.0001, 'weight_decay': 1e-10, 'grad_clip_norm': 10.0, 'betas': [0.9, 0.95], 'eps': 1e-08}, 'scheduler': {'type': 'cosine_decay_with_warmup', 'num_warmup_steps': 1000, 'num_decay_steps': 30000, 'peak_lr': 0.0001, 'decay_lr': 2.5e-06}, 'eval': {'n_episodes': 50, 'batch_size': 50, 'use_async_envs': False}, 'wandb': {'enable': True, 'disable_artifact': False, 'project': 'lerobot', 'entity': None, 'notes': None, 'run_id': None, 'mode': None}, '_wandb': {}}
11
+ 2025-08-21 23:52:11,542 INFO MainThread:2718618 [wandb_init.py:init():871] starting backend
12
+ 2025-08-21 23:52:11,747 INFO MainThread:2718618 [wandb_init.py:init():874] sending inform_init request
13
+ 2025-08-21 23:52:11,755 INFO MainThread:2718618 [wandb_init.py:init():882] backend started and connected
14
+ 2025-08-21 23:52:11,756 INFO MainThread:2718618 [wandb_init.py:init():953] updated telemetry
15
+ 2025-08-21 23:52:11,760 INFO MainThread:2718618 [wandb_init.py:init():977] communicating run to backend with 90.0 second timeout
16
+ 2025-08-21 23:52:12,365 INFO MainThread:2718618 [wandb_init.py:init():1029] starting run threads in backend
17
+ 2025-08-21 23:52:12,471 INFO MainThread:2718618 [wandb_run.py:_console_start():2458] atexit reg
18
+ 2025-08-21 23:52:12,471 INFO MainThread:2718618 [wandb_run.py:_redirect():2306] redirect: wrap_raw
19
+ 2025-08-21 23:52:12,471 INFO MainThread:2718618 [wandb_run.py:_redirect():2375] Wrapping output streams.
20
+ 2025-08-21 23:52:12,471 INFO MainThread:2718618 [wandb_run.py:_redirect():2398] Redirects installed.
21
+ 2025-08-21 23:52:12,472 INFO MainThread:2718618 [wandb_init.py:init():1075] run started, returning control to user process
22
+ 2025-08-22 06:01:02,138 INFO MsgRouterThr:2718618 [mailbox.py:close():129] [no run ID] Closing mailbox, abandoning 2 handles.
wandb/run-20250821_235211-3qesni5p/files/config.yaml ADDED
@@ -0,0 +1,258 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ _wandb:
2
+ value:
3
+ cli_version: 0.21.0
4
+ e:
5
+ kl5ugdoqcldc8c1uwtt9an4z1lal0evc:
6
+ args:
7
+ - --policy.path=lerobot/smolvla_base
8
+ - --dataset.repo_id=MCeut/so101_push_cube_test1
9
+ - --batch_size=64
10
+ - --steps=20000
11
+ - --output_dir=outputs/train/so101_smolvla_push_cube_test2
12
+ - --job_name=so101_smolvla_training_push_cube_test2
13
+ - --policy.device=cuda
14
+ - --wandb.enable=true
15
+ - --policy.repo_id=/so101_smolvla_push_cube_test2
16
+ - --dataset.video_backend=pyav
17
+ cpu_count: 8
18
+ cpu_count_logical: 16
19
+ cudaVersion: "12.2"
20
+ disk:
21
+ /:
22
+ total: "1654231658496"
23
+ used: "542871166976"
24
+ executable: /home/collab/miniconda3/envs/lerobot/bin/python3.10
25
+ git:
26
+ commit: 7f70b78f3221a2fa64ae09795b5989a58a61931d
27
+ remote: https://github.com/huggingface/lerobot.git
28
+ gpu: NVIDIA GeForce RTX 3090 Ti
29
+ gpu_count: 1
30
+ gpu_nvidia:
31
+ - architecture: Ampere
32
+ cudaCores: 10752
33
+ memoryTotal: "25757220864"
34
+ name: NVIDIA GeForce RTX 3090 Ti
35
+ uuid: GPU-870abedb-e007-b2f9-acff-2fbf869229ac
36
+ host: CL-ROBOLAB3
37
+ memory:
38
+ total: "33497321472"
39
+ os: Linux-6.8.0-65-generic-x86_64-with-glibc2.35
40
+ program: /home/collab/miniconda3/envs/lerobot/bin/lerobot-train
41
+ python: CPython 3.10.18
42
+ root: outputs/train/so101_smolvla_push_cube_test2
43
+ startedAt: "2025-08-21T21:52:11.541066Z"
44
+ writerId: kl5ugdoqcldc8c1uwtt9an4z1lal0evc
45
+ m: []
46
+ python_version: 3.10.18
47
+ t:
48
+ "1":
49
+ - 1
50
+ - 41
51
+ - 49
52
+ - 51
53
+ "2":
54
+ - 1
55
+ - 2
56
+ - 3
57
+ - 11
58
+ - 41
59
+ - 49
60
+ - 51
61
+ - 71
62
+ "3":
63
+ - 13
64
+ - 15
65
+ - 16
66
+ - 61
67
+ "4": 3.10.18
68
+ "5": 0.21.0
69
+ "10":
70
+ - 21
71
+ "12": 0.21.0
72
+ "13": linux-x86_64
73
+ batch_size:
74
+ value: 64
75
+ dataset:
76
+ value:
77
+ episodes: null
78
+ image_transforms:
79
+ enable: false
80
+ max_num_transforms: 3
81
+ random_order: false
82
+ tfs:
83
+ brightness:
84
+ kwargs:
85
+ brightness:
86
+ - 0.8
87
+ - 1.2
88
+ type: ColorJitter
89
+ weight: 1
90
+ contrast:
91
+ kwargs:
92
+ contrast:
93
+ - 0.8
94
+ - 1.2
95
+ type: ColorJitter
96
+ weight: 1
97
+ hue:
98
+ kwargs:
99
+ hue:
100
+ - -0.05
101
+ - 0.05
102
+ type: ColorJitter
103
+ weight: 1
104
+ saturation:
105
+ kwargs:
106
+ saturation:
107
+ - 0.5
108
+ - 1.5
109
+ type: ColorJitter
110
+ weight: 1
111
+ sharpness:
112
+ kwargs:
113
+ sharpness:
114
+ - 0.5
115
+ - 1.5
116
+ type: SharpnessJitter
117
+ weight: 1
118
+ repo_id: MCeut/so101_push_cube_test1
119
+ revision: null
120
+ root: null
121
+ use_imagenet_stats: true
122
+ video_backend: pyav
123
+ env:
124
+ value: null
125
+ eval:
126
+ value:
127
+ batch_size: 50
128
+ n_episodes: 50
129
+ use_async_envs: false
130
+ eval_freq:
131
+ value: 20000
132
+ job_name:
133
+ value: so101_smolvla_training_push_cube_test2
134
+ log_freq:
135
+ value: 200
136
+ num_workers:
137
+ value: 4
138
+ optimizer:
139
+ value:
140
+ betas:
141
+ - 0.9
142
+ - 0.95
143
+ eps: 1e-08
144
+ grad_clip_norm: 10
145
+ lr: 0.0001
146
+ type: adamw
147
+ weight_decay: 1e-10
148
+ output_dir:
149
+ value: outputs/train/so101_smolvla_push_cube_test2
150
+ policy:
151
+ value:
152
+ adapt_to_pi_aloha: false
153
+ add_image_special_tokens: false
154
+ attention_mode: cross_attn
155
+ chunk_size: 50
156
+ device: cuda
157
+ empty_cameras: 0
158
+ expert_width_multiplier: 0.75
159
+ freeze_vision_encoder: true
160
+ input_features:
161
+ observation.image:
162
+ shape:
163
+ - 3
164
+ - 256
165
+ - 256
166
+ type: VISUAL
167
+ observation.image2:
168
+ shape:
169
+ - 3
170
+ - 256
171
+ - 256
172
+ type: VISUAL
173
+ observation.image3:
174
+ shape:
175
+ - 3
176
+ - 256
177
+ - 256
178
+ type: VISUAL
179
+ observation.state:
180
+ shape:
181
+ - 6
182
+ type: STATE
183
+ license: null
184
+ load_vlm_weights: true
185
+ max_action_dim: 32
186
+ max_period: 4
187
+ max_state_dim: 32
188
+ min_period: 0.004
189
+ n_action_steps: 50
190
+ n_obs_steps: 1
191
+ normalization_mapping:
192
+ ACTION: MEAN_STD
193
+ STATE: MEAN_STD
194
+ VISUAL: IDENTITY
195
+ num_expert_layers: 0
196
+ num_steps: 10
197
+ num_vlm_layers: 16
198
+ optimizer_betas:
199
+ - 0.9
200
+ - 0.95
201
+ optimizer_eps: 1e-08
202
+ optimizer_grad_clip_norm: 10
203
+ optimizer_lr: 0.0001
204
+ optimizer_weight_decay: 1e-10
205
+ output_features:
206
+ action:
207
+ shape:
208
+ - 6
209
+ type: ACTION
210
+ pad_language_to: max_length
211
+ prefix_length: 0
212
+ private: null
213
+ push_to_hub: true
214
+ repo_id: /so101_smolvla_push_cube_test2
215
+ resize_imgs_with_padding:
216
+ - 512
217
+ - 512
218
+ scheduler_decay_lr: 2.5e-06
219
+ scheduler_decay_steps: 30000
220
+ scheduler_warmup_steps: 1000
221
+ self_attn_every_n_layers: 2
222
+ tags: null
223
+ tokenizer_max_length: 48
224
+ train_expert_only: true
225
+ train_state_proj: true
226
+ type: smolvla
227
+ use_amp: false
228
+ use_cache: true
229
+ use_delta_joint_actions_aloha: false
230
+ vlm_model_name: HuggingFaceTB/SmolVLM2-500M-Video-Instruct
231
+ resume:
232
+ value: false
233
+ save_checkpoint:
234
+ value: true
235
+ save_freq:
236
+ value: 20000
237
+ scheduler:
238
+ value:
239
+ decay_lr: 2.5e-06
240
+ num_decay_steps: 30000
241
+ num_warmup_steps: 1000
242
+ peak_lr: 0.0001
243
+ type: cosine_decay_with_warmup
244
+ seed:
245
+ value: 1000
246
+ steps:
247
+ value: 20000
248
+ use_policy_training_preset:
249
+ value: true
250
+ wandb:
251
+ value:
252
+ disable_artifact: false
253
+ enable: true
254
+ entity: null
255
+ mode: null
256
+ notes: null
257
+ project: lerobot
258
+ run_id: null
wandb/run-20250821_235211-3qesni5p/files/output.log ADDED
@@ -0,0 +1,340 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ Logs will be synced with wandb.
2
+ INFO 2025-08-21 23:52:12 db_utils.py:103 Track this run --> https://wandb.ai/mario-cavero-eut-eurecat/lerobot/runs/3qesni5p
3
+ INFO 2025-08-21 23:52:12 ts/train.py:127 Creating dataset
4
+ Resolving data files: 100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 45/45 [00:00<00:00, 254714.82it/s]
5
+ INFO 2025-08-21 23:52:12 ts/train.py:138 Creating policy
6
+ Loading HuggingFaceTB/SmolVLM2-500M-Video-Instruct weights ...
7
+ INFO 2025-08-21 23:52:17 odeling.py:1004 We will use 90% of the memory on device 0 for storing the model, and 10% for the buffer to avoid OOM. You can set `max_memory` in to a higher value to use more memory (at your own risk).
8
+ Reducing the number of VLM layers to 16 ...
9
+ [standardise_state_dict] 'normalize_inputs.buffer_observation_state.mean' ← ['normalize_inputs.so100-red_buffer_observation_state.mean', 'normalize_inputs.so100_buffer_observation_state.mean']
10
+ [standardise_state_dict] 'normalize_inputs.buffer_observation_state.std' ← ['normalize_inputs.so100-red_buffer_observation_state.std', 'normalize_inputs.so100_buffer_observation_state.std']
11
+ [standardise_state_dict] 'normalize_targets.buffer_action.mean' ← ['normalize_targets.so100-red_buffer_action.mean', 'normalize_targets.so100_buffer_action.mean']
12
+ [standardise_state_dict] 'normalize_targets.buffer_action.std' ← ['normalize_targets.so100-red_buffer_action.std', 'normalize_targets.so100_buffer_action.std']
13
+ [standardise_state_dict] 'unnormalize_outputs.buffer_action.mean' ← ['unnormalize_outputs.so100-red_buffer_action.mean', 'unnormalize_outputs.so100_buffer_action.mean']
14
+ [standardise_state_dict] 'unnormalize_outputs.buffer_action.std' ← ['unnormalize_outputs.so100-red_buffer_action.std', 'unnormalize_outputs.so100_buffer_action.std']
15
+ INFO 2025-08-21 23:52:25 ts/train.py:144 Creating optimizer and scheduler
16
+ INFO 2025-08-21 23:52:25 ts/train.py:156 Output dir: outputs/train/so101_smolvla_push_cube_test2
17
+ INFO 2025-08-21 23:52:25 ts/train.py:159 cfg.steps=20000 (20K)
18
+ INFO 2025-08-21 23:52:25 ts/train.py:160 dataset.num_frames=10648 (11K)
19
+ INFO 2025-08-21 23:52:25 ts/train.py:161 dataset.num_episodes=45
20
+ INFO 2025-08-21 23:52:25 ts/train.py:162 num_learnable_params=99880992 (100M)
21
+ INFO 2025-08-21 23:52:25 ts/train.py:163 num_total_params=450046212 (450M)
22
+ INFO 2025-08-21 23:52:25 ts/train.py:202 Start offline training on a fixed dataset
23
+ INFO 2025-08-21 23:56:11 ts/train.py:232 step:200 smpl:13K ep:54 epch:1.20 loss:0.118 grdn:0.670 lr:1.0e-05 updt_s:1.082 data_s:0.043
24
+ WARNING 2025-08-21 23:56:11 db_utils.py:141 WandB logging of key "losses_after_forward" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
25
+ WARNING 2025-08-21 23:56:11 db_utils.py:141 WandB logging of key "losses_after_rm_padding" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
26
+ INFO 2025-08-21 23:59:50 ts/train.py:232 step:400 smpl:26K ep:108 epch:2.40 loss:0.070 grdn:0.460 lr:3.0e-05 updt_s:1.067 data_s:0.022
27
+ WARNING 2025-08-21 23:59:50 db_utils.py:141 WandB logging of key "losses_after_forward" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
28
+ WARNING 2025-08-21 23:59:50 db_utils.py:141 WandB logging of key "losses_after_rm_padding" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
29
+ INFO 2025-08-22 00:03:29 ts/train.py:232 step:600 smpl:38K ep:162 epch:3.61 loss:0.059 grdn:0.514 lr:5.0e-05 updt_s:1.071 data_s:0.022
30
+ WARNING 2025-08-22 00:03:29 db_utils.py:141 WandB logging of key "losses_after_forward" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
31
+ WARNING 2025-08-22 00:03:29 db_utils.py:141 WandB logging of key "losses_after_rm_padding" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
32
+ INFO 2025-08-22 00:07:09 ts/train.py:232 step:800 smpl:51K ep:216 epch:4.81 loss:0.050 grdn:0.504 lr:7.0e-05 updt_s:1.068 data_s:0.026
33
+ WARNING 2025-08-22 00:07:09 db_utils.py:141 WandB logging of key "losses_after_forward" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
34
+ WARNING 2025-08-22 00:07:09 db_utils.py:141 WandB logging of key "losses_after_rm_padding" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
35
+ INFO 2025-08-22 00:10:49 ts/train.py:232 step:1K smpl:64K ep:270 epch:6.01 loss:0.045 grdn:0.504 lr:9.0e-05 updt_s:1.067 data_s:0.027
36
+ WARNING 2025-08-22 00:10:49 db_utils.py:141 WandB logging of key "losses_after_forward" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
37
+ WARNING 2025-08-22 00:10:49 db_utils.py:141 WandB logging of key "losses_after_rm_padding" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
38
+ INFO 2025-08-22 00:14:35 ts/train.py:232 step:1K smpl:77K ep:325 epch:7.21 loss:0.038 grdn:0.454 lr:1.0e-04 updt_s:1.071 data_s:0.054
39
+ WARNING 2025-08-22 00:14:35 db_utils.py:141 WandB logging of key "losses_after_forward" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
40
+ WARNING 2025-08-22 00:14:35 db_utils.py:141 WandB logging of key "losses_after_rm_padding" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
41
+ INFO 2025-08-22 00:18:15 ts/train.py:232 step:1K smpl:90K ep:379 epch:8.41 loss:0.035 grdn:0.426 lr:1.0e-04 updt_s:1.072 data_s:0.022
42
+ WARNING 2025-08-22 00:18:15 db_utils.py:141 WandB logging of key "losses_after_forward" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
43
+ WARNING 2025-08-22 00:18:15 db_utils.py:141 WandB logging of key "losses_after_rm_padding" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
44
+ INFO 2025-08-22 00:21:56 ts/train.py:232 step:2K smpl:102K ep:433 epch:9.62 loss:0.032 grdn:0.403 lr:9.9e-05 updt_s:1.070 data_s:0.029
45
+ WARNING 2025-08-22 00:21:56 db_utils.py:141 WandB logging of key "losses_after_forward" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
46
+ WARNING 2025-08-22 00:21:56 db_utils.py:141 WandB logging of key "losses_after_rm_padding" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
47
+ INFO 2025-08-22 00:25:36 ts/train.py:232 step:2K smpl:115K ep:487 epch:10.82 loss:0.029 grdn:0.365 lr:9.9e-05 updt_s:1.070 data_s:0.027
48
+ WARNING 2025-08-22 00:25:36 db_utils.py:141 WandB logging of key "losses_after_forward" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
49
+ WARNING 2025-08-22 00:25:36 db_utils.py:141 WandB logging of key "losses_after_rm_padding" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
50
+ INFO 2025-08-22 00:29:16 ts/train.py:232 step:2K smpl:128K ep:541 epch:12.02 loss:0.026 grdn:0.347 lr:9.9e-05 updt_s:1.069 data_s:0.027
51
+ WARNING 2025-08-22 00:29:16 db_utils.py:141 WandB logging of key "losses_after_forward" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
52
+ WARNING 2025-08-22 00:29:16 db_utils.py:141 WandB logging of key "losses_after_rm_padding" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
53
+ INFO 2025-08-22 00:33:01 ts/train.py:232 step:2K smpl:141K ep:595 epch:13.22 loss:0.026 grdn:0.334 lr:9.9e-05 updt_s:1.067 data_s:0.048
54
+ WARNING 2025-08-22 00:33:01 db_utils.py:141 WandB logging of key "losses_after_forward" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
55
+ WARNING 2025-08-22 00:33:01 db_utils.py:141 WandB logging of key "losses_after_rm_padding" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
56
+ INFO 2025-08-22 00:36:41 ts/train.py:232 step:2K smpl:154K ep:649 epch:14.43 loss:0.024 grdn:0.319 lr:9.9e-05 updt_s:1.073 data_s:0.023
57
+ WARNING 2025-08-22 00:36:41 db_utils.py:141 WandB logging of key "losses_after_forward" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
58
+ WARNING 2025-08-22 00:36:41 db_utils.py:141 WandB logging of key "losses_after_rm_padding" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
59
+ INFO 2025-08-22 00:40:21 ts/train.py:232 step:3K smpl:166K ep:703 epch:15.63 loss:0.023 grdn:0.301 lr:9.8e-05 updt_s:1.072 data_s:0.022
60
+ WARNING 2025-08-22 00:40:21 db_utils.py:141 WandB logging of key "losses_after_forward" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
61
+ WARNING 2025-08-22 00:40:21 db_utils.py:141 WandB logging of key "losses_after_rm_padding" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
62
+ INFO 2025-08-22 00:44:02 ts/train.py:232 step:3K smpl:179K ep:757 epch:16.83 loss:0.022 grdn:0.294 lr:9.8e-05 updt_s:1.072 data_s:0.028
63
+ WARNING 2025-08-22 00:44:02 db_utils.py:141 WandB logging of key "losses_after_forward" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
64
+ WARNING 2025-08-22 00:44:02 db_utils.py:141 WandB logging of key "losses_after_rm_padding" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
65
+ INFO 2025-08-22 00:47:42 ts/train.py:232 step:3K smpl:192K ep:811 epch:18.03 loss:0.021 grdn:0.302 lr:9.8e-05 updt_s:1.068 data_s:0.027
66
+ WARNING 2025-08-22 00:47:42 db_utils.py:141 WandB logging of key "losses_after_forward" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
67
+ WARNING 2025-08-22 00:47:42 db_utils.py:141 WandB logging of key "losses_after_rm_padding" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
68
+ INFO 2025-08-22 00:51:26 ts/train.py:232 step:3K smpl:205K ep:866 epch:19.23 loss:0.021 grdn:0.285 lr:9.7e-05 updt_s:1.068 data_s:0.050
69
+ WARNING 2025-08-22 00:51:26 db_utils.py:141 WandB logging of key "losses_after_forward" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
70
+ WARNING 2025-08-22 00:51:26 db_utils.py:141 WandB logging of key "losses_after_rm_padding" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
71
+ INFO 2025-08-22 00:55:07 ts/train.py:232 step:3K smpl:218K ep:920 epch:20.44 loss:0.020 grdn:0.271 lr:9.7e-05 updt_s:1.072 data_s:0.028
72
+ WARNING 2025-08-22 00:55:07 db_utils.py:141 WandB logging of key "losses_after_forward" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
73
+ WARNING 2025-08-22 00:55:07 db_utils.py:141 WandB logging of key "losses_after_rm_padding" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
74
+ INFO 2025-08-22 00:58:48 ts/train.py:232 step:4K smpl:230K ep:974 epch:21.64 loss:0.019 grdn:0.269 lr:9.7e-05 updt_s:1.071 data_s:0.025
75
+ WARNING 2025-08-22 00:58:48 db_utils.py:141 WandB logging of key "losses_after_forward" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
76
+ WARNING 2025-08-22 00:58:48 db_utils.py:141 WandB logging of key "losses_after_rm_padding" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
77
+ INFO 2025-08-22 01:02:27 ts/train.py:232 step:4K smpl:243K ep:1K epch:22.84 loss:0.018 grdn:0.259 lr:9.6e-05 updt_s:1.068 data_s:0.026
78
+ WARNING 2025-08-22 01:02:27 db_utils.py:141 WandB logging of key "losses_after_forward" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
79
+ WARNING 2025-08-22 01:02:27 db_utils.py:141 WandB logging of key "losses_after_rm_padding" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
80
+ INFO 2025-08-22 01:06:07 ts/train.py:232 step:4K smpl:256K ep:1K epch:24.04 loss:0.018 grdn:0.265 lr:9.6e-05 updt_s:1.068 data_s:0.025
81
+ WARNING 2025-08-22 01:06:07 db_utils.py:141 WandB logging of key "losses_after_forward" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
82
+ WARNING 2025-08-22 01:06:07 db_utils.py:141 WandB logging of key "losses_after_rm_padding" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
83
+ INFO 2025-08-22 01:09:51 ts/train.py:232 step:4K smpl:269K ep:1K epch:25.24 loss:0.017 grdn:0.256 lr:9.6e-05 updt_s:1.069 data_s:0.046
84
+ WARNING 2025-08-22 01:09:51 db_utils.py:141 WandB logging of key "losses_after_forward" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
85
+ WARNING 2025-08-22 01:09:51 db_utils.py:141 WandB logging of key "losses_after_rm_padding" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
86
+ INFO 2025-08-22 01:13:32 ts/train.py:232 step:4K smpl:282K ep:1K epch:26.45 loss:0.017 grdn:0.244 lr:9.5e-05 updt_s:1.071 data_s:0.027
87
+ WARNING 2025-08-22 01:13:32 db_utils.py:141 WandB logging of key "losses_after_forward" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
88
+ WARNING 2025-08-22 01:13:32 db_utils.py:141 WandB logging of key "losses_after_rm_padding" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
89
+ INFO 2025-08-22 01:17:12 ts/train.py:232 step:5K smpl:294K ep:1K epch:27.65 loss:0.017 grdn:0.250 lr:9.5e-05 updt_s:1.071 data_s:0.027
90
+ WARNING 2025-08-22 01:17:12 db_utils.py:141 WandB logging of key "losses_after_forward" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
91
+ WARNING 2025-08-22 01:17:12 db_utils.py:141 WandB logging of key "losses_after_rm_padding" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
92
+ INFO 2025-08-22 01:20:52 ts/train.py:232 step:5K smpl:307K ep:1K epch:28.85 loss:0.017 grdn:0.251 lr:9.4e-05 updt_s:1.073 data_s:0.022
93
+ WARNING 2025-08-22 01:20:52 db_utils.py:141 WandB logging of key "losses_after_forward" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
94
+ WARNING 2025-08-22 01:20:52 db_utils.py:141 WandB logging of key "losses_after_rm_padding" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
95
+ INFO 2025-08-22 01:24:33 ts/train.py:232 step:5K smpl:320K ep:1K epch:30.05 loss:0.016 grdn:0.238 lr:9.4e-05 updt_s:1.070 data_s:0.028
96
+ WARNING 2025-08-22 01:24:33 db_utils.py:141 WandB logging of key "losses_after_forward" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
97
+ WARNING 2025-08-22 01:24:33 db_utils.py:141 WandB logging of key "losses_after_rm_padding" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
98
+ INFO 2025-08-22 01:28:16 ts/train.py:232 step:5K smpl:333K ep:1K epch:31.25 loss:0.016 grdn:0.243 lr:9.3e-05 updt_s:1.068 data_s:0.046
99
+ WARNING 2025-08-22 01:28:16 db_utils.py:141 WandB logging of key "losses_after_forward" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
100
+ WARNING 2025-08-22 01:28:16 db_utils.py:141 WandB logging of key "losses_after_rm_padding" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
101
+ INFO 2025-08-22 01:31:56 ts/train.py:232 step:5K smpl:346K ep:1K epch:32.46 loss:0.015 grdn:0.235 lr:9.3e-05 updt_s:1.072 data_s:0.022
102
+ WARNING 2025-08-22 01:31:56 db_utils.py:141 WandB logging of key "losses_after_forward" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
103
+ WARNING 2025-08-22 01:31:56 db_utils.py:141 WandB logging of key "losses_after_rm_padding" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
104
+ INFO 2025-08-22 01:35:36 ts/train.py:232 step:6K smpl:358K ep:2K epch:33.66 loss:0.015 grdn:0.227 lr:9.2e-05 updt_s:1.073 data_s:0.022
105
+ WARNING 2025-08-22 01:35:36 db_utils.py:141 WandB logging of key "losses_after_forward" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
106
+ WARNING 2025-08-22 01:35:36 db_utils.py:141 WandB logging of key "losses_after_rm_padding" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
107
+ INFO 2025-08-22 01:39:16 ts/train.py:232 step:6K smpl:371K ep:2K epch:34.86 loss:0.015 grdn:0.226 lr:9.2e-05 updt_s:1.073 data_s:0.022
108
+ WARNING 2025-08-22 01:39:16 db_utils.py:141 WandB logging of key "losses_after_forward" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
109
+ WARNING 2025-08-22 01:39:16 db_utils.py:141 WandB logging of key "losses_after_rm_padding" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
110
+ INFO 2025-08-22 01:42:57 ts/train.py:232 step:6K smpl:384K ep:2K epch:36.06 loss:0.014 grdn:0.227 lr:9.1e-05 updt_s:1.073 data_s:0.025
111
+ WARNING 2025-08-22 01:42:57 db_utils.py:141 WandB logging of key "losses_after_forward" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
112
+ WARNING 2025-08-22 01:42:57 db_utils.py:141 WandB logging of key "losses_after_rm_padding" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
113
+ INFO 2025-08-22 01:46:40 ts/train.py:232 step:6K smpl:397K ep:2K epch:37.27 loss:0.014 grdn:0.226 lr:9.0e-05 updt_s:1.069 data_s:0.043
114
+ WARNING 2025-08-22 01:46:40 db_utils.py:141 WandB logging of key "losses_after_forward" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
115
+ WARNING 2025-08-22 01:46:40 db_utils.py:141 WandB logging of key "losses_after_rm_padding" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
116
+ INFO 2025-08-22 01:50:20 ts/train.py:232 step:6K smpl:410K ep:2K epch:38.47 loss:0.014 grdn:0.217 lr:9.0e-05 updt_s:1.074 data_s:0.022
117
+ WARNING 2025-08-22 01:50:20 db_utils.py:141 WandB logging of key "losses_after_forward" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
118
+ WARNING 2025-08-22 01:50:20 db_utils.py:141 WandB logging of key "losses_after_rm_padding" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
119
+ INFO 2025-08-22 01:54:01 ts/train.py:232 step:7K smpl:422K ep:2K epch:39.67 loss:0.014 grdn:0.217 lr:8.9e-05 updt_s:1.071 data_s:0.025
120
+ WARNING 2025-08-22 01:54:01 db_utils.py:141 WandB logging of key "losses_after_forward" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
121
+ WARNING 2025-08-22 01:54:01 db_utils.py:141 WandB logging of key "losses_after_rm_padding" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
122
+ INFO 2025-08-22 01:57:41 ts/train.py:232 step:7K smpl:435K ep:2K epch:40.87 loss:0.013 grdn:0.216 lr:8.8e-05 updt_s:1.073 data_s:0.023
123
+ WARNING 2025-08-22 01:57:41 db_utils.py:141 WandB logging of key "losses_after_forward" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
124
+ WARNING 2025-08-22 01:57:41 db_utils.py:141 WandB logging of key "losses_after_rm_padding" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
125
+ INFO 2025-08-22 02:01:21 ts/train.py:232 step:7K smpl:448K ep:2K epch:42.07 loss:0.013 grdn:0.216 lr:8.8e-05 updt_s:1.073 data_s:0.023
126
+ WARNING 2025-08-22 02:01:21 db_utils.py:141 WandB logging of key "losses_after_forward" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
127
+ WARNING 2025-08-22 02:01:21 db_utils.py:141 WandB logging of key "losses_after_rm_padding" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
128
+ INFO 2025-08-22 02:05:05 ts/train.py:232 step:7K smpl:461K ep:2K epch:43.28 loss:0.013 grdn:0.214 lr:8.7e-05 updt_s:1.066 data_s:0.049
129
+ WARNING 2025-08-22 02:05:05 db_utils.py:141 WandB logging of key "losses_after_forward" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
130
+ WARNING 2025-08-22 02:05:05 db_utils.py:141 WandB logging of key "losses_after_rm_padding" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
131
+ INFO 2025-08-22 02:08:45 ts/train.py:232 step:7K smpl:474K ep:2K epch:44.48 loss:0.013 grdn:0.216 lr:8.6e-05 updt_s:1.073 data_s:0.021
132
+ WARNING 2025-08-22 02:08:45 db_utils.py:141 WandB logging of key "losses_after_forward" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
133
+ WARNING 2025-08-22 02:08:45 db_utils.py:141 WandB logging of key "losses_after_rm_padding" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
134
+ INFO 2025-08-22 02:12:25 ts/train.py:232 step:8K smpl:486K ep:2K epch:45.68 loss:0.012 grdn:0.206 lr:8.6e-05 updt_s:1.072 data_s:0.023
135
+ WARNING 2025-08-22 02:12:25 db_utils.py:141 WandB logging of key "losses_after_forward" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
136
+ WARNING 2025-08-22 02:12:25 db_utils.py:141 WandB logging of key "losses_after_rm_padding" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
137
+ INFO 2025-08-22 02:16:05 ts/train.py:232 step:8K smpl:499K ep:2K epch:46.88 loss:0.012 grdn:0.199 lr:8.5e-05 updt_s:1.073 data_s:0.025
138
+ WARNING 2025-08-22 02:16:05 db_utils.py:141 WandB logging of key "losses_after_forward" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
139
+ WARNING 2025-08-22 02:16:05 db_utils.py:141 WandB logging of key "losses_after_rm_padding" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
140
+ INFO 2025-08-22 02:19:45 ts/train.py:232 step:8K smpl:512K ep:2K epch:48.08 loss:0.012 grdn:0.203 lr:8.4e-05 updt_s:1.071 data_s:0.023
141
+ WARNING 2025-08-22 02:19:45 db_utils.py:141 WandB logging of key "losses_after_forward" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
142
+ WARNING 2025-08-22 02:19:45 db_utils.py:141 WandB logging of key "losses_after_rm_padding" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
143
+ INFO 2025-08-22 02:23:29 ts/train.py:232 step:8K smpl:525K ep:2K epch:49.29 loss:0.012 grdn:0.199 lr:8.3e-05 updt_s:1.066 data_s:0.049
144
+ WARNING 2025-08-22 02:23:29 db_utils.py:141 WandB logging of key "losses_after_forward" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
145
+ WARNING 2025-08-22 02:23:29 db_utils.py:141 WandB logging of key "losses_after_rm_padding" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
146
+ INFO 2025-08-22 02:27:10 ts/train.py:232 step:8K smpl:538K ep:2K epch:50.49 loss:0.012 grdn:0.197 lr:8.3e-05 updt_s:1.073 data_s:0.023
147
+ WARNING 2025-08-22 02:27:10 db_utils.py:141 WandB logging of key "losses_after_forward" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
148
+ WARNING 2025-08-22 02:27:10 db_utils.py:141 WandB logging of key "losses_after_rm_padding" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
149
+ INFO 2025-08-22 02:30:50 ts/train.py:232 step:9K smpl:550K ep:2K epch:51.69 loss:0.011 grdn:0.189 lr:8.2e-05 updt_s:1.071 data_s:0.025
150
+ WARNING 2025-08-22 02:30:50 db_utils.py:141 WandB logging of key "losses_after_forward" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
151
+ WARNING 2025-08-22 02:30:50 db_utils.py:141 WandB logging of key "losses_after_rm_padding" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
152
+ INFO 2025-08-22 02:34:31 ts/train.py:232 step:9K smpl:563K ep:2K epch:52.89 loss:0.011 grdn:0.193 lr:8.1e-05 updt_s:1.071 data_s:0.029
153
+ WARNING 2025-08-22 02:34:31 db_utils.py:141 WandB logging of key "losses_after_forward" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
154
+ WARNING 2025-08-22 02:34:31 db_utils.py:141 WandB logging of key "losses_after_rm_padding" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
155
+ INFO 2025-08-22 02:38:11 ts/train.py:232 step:9K smpl:576K ep:2K epch:54.09 loss:0.011 grdn:0.193 lr:8.0e-05 updt_s:1.072 data_s:0.025
156
+ WARNING 2025-08-22 02:38:11 db_utils.py:141 WandB logging of key "losses_after_forward" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
157
+ WARNING 2025-08-22 02:38:11 db_utils.py:141 WandB logging of key "losses_after_rm_padding" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
158
+ INFO 2025-08-22 02:41:54 ts/train.py:232 step:9K smpl:589K ep:2K epch:55.30 loss:0.011 grdn:0.188 lr:7.9e-05 updt_s:1.068 data_s:0.045
159
+ WARNING 2025-08-22 02:41:54 db_utils.py:141 WandB logging of key "losses_after_forward" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
160
+ WARNING 2025-08-22 02:41:54 db_utils.py:141 WandB logging of key "losses_after_rm_padding" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
161
+ INFO 2025-08-22 02:45:35 ts/train.py:232 step:9K smpl:602K ep:3K epch:56.50 loss:0.011 grdn:0.188 lr:7.9e-05 updt_s:1.072 data_s:0.026
162
+ WARNING 2025-08-22 02:45:35 db_utils.py:141 WandB logging of key "losses_after_forward" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
163
+ WARNING 2025-08-22 02:45:35 db_utils.py:141 WandB logging of key "losses_after_rm_padding" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
164
+ INFO 2025-08-22 02:49:16 ts/train.py:232 step:10K smpl:614K ep:3K epch:57.70 loss:0.010 grdn:0.187 lr:7.8e-05 updt_s:1.073 data_s:0.027
165
+ WARNING 2025-08-22 02:49:16 db_utils.py:141 WandB logging of key "losses_after_forward" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
166
+ WARNING 2025-08-22 02:49:16 db_utils.py:141 WandB logging of key "losses_after_rm_padding" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
167
+ INFO 2025-08-22 02:52:56 ts/train.py:232 step:10K smpl:627K ep:3K epch:58.90 loss:0.010 grdn:0.179 lr:7.7e-05 updt_s:1.071 data_s:0.026
168
+ WARNING 2025-08-22 02:52:56 db_utils.py:141 WandB logging of key "losses_after_forward" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
169
+ WARNING 2025-08-22 02:52:56 db_utils.py:141 WandB logging of key "losses_after_rm_padding" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
170
+ INFO 2025-08-22 02:56:37 ts/train.py:232 step:10K smpl:640K ep:3K epch:60.11 loss:0.010 grdn:0.179 lr:7.6e-05 updt_s:1.071 data_s:0.025
171
+ WARNING 2025-08-22 02:56:37 db_utils.py:141 WandB logging of key "losses_after_forward" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
172
+ WARNING 2025-08-22 02:56:37 db_utils.py:141 WandB logging of key "losses_after_rm_padding" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
173
+ INFO 2025-08-22 03:00:21 ts/train.py:232 step:10K smpl:653K ep:3K epch:61.31 loss:0.010 grdn:0.172 lr:7.5e-05 updt_s:1.069 data_s:0.047
174
+ WARNING 2025-08-22 03:00:21 db_utils.py:141 WandB logging of key "losses_after_forward" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
175
+ WARNING 2025-08-22 03:00:21 db_utils.py:141 WandB logging of key "losses_after_rm_padding" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
176
+ INFO 2025-08-22 03:04:01 ts/train.py:232 step:10K smpl:666K ep:3K epch:62.51 loss:0.010 grdn:0.170 lr:7.4e-05 updt_s:1.071 data_s:0.025
177
+ WARNING 2025-08-22 03:04:01 db_utils.py:141 WandB logging of key "losses_after_forward" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
178
+ WARNING 2025-08-22 03:04:01 db_utils.py:141 WandB logging of key "losses_after_rm_padding" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
179
+ INFO 2025-08-22 03:07:42 ts/train.py:232 step:11K smpl:678K ep:3K epch:63.71 loss:0.010 grdn:0.174 lr:7.3e-05 updt_s:1.073 data_s:0.024
180
+ WARNING 2025-08-22 03:07:42 db_utils.py:141 WandB logging of key "losses_after_forward" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
181
+ WARNING 2025-08-22 03:07:42 db_utils.py:141 WandB logging of key "losses_after_rm_padding" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
182
+ INFO 2025-08-22 03:11:23 ts/train.py:232 step:11K smpl:691K ep:3K epch:64.91 loss:0.010 grdn:0.170 lr:7.2e-05 updt_s:1.074 data_s:0.026
183
+ WARNING 2025-08-22 03:11:23 db_utils.py:141 WandB logging of key "losses_after_forward" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
184
+ WARNING 2025-08-22 03:11:23 db_utils.py:141 WandB logging of key "losses_after_rm_padding" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
185
+ INFO 2025-08-22 03:15:03 ts/train.py:232 step:11K smpl:704K ep:3K epch:66.12 loss:0.010 grdn:0.168 lr:7.2e-05 updt_s:1.074 data_s:0.026
186
+ WARNING 2025-08-22 03:15:03 db_utils.py:141 WandB logging of key "losses_after_forward" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
187
+ WARNING 2025-08-22 03:15:03 db_utils.py:141 WandB logging of key "losses_after_rm_padding" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
188
+ INFO 2025-08-22 03:18:48 ts/train.py:232 step:11K smpl:717K ep:3K epch:67.32 loss:0.009 grdn:0.167 lr:7.1e-05 updt_s:1.070 data_s:0.048
189
+ WARNING 2025-08-22 03:18:48 db_utils.py:141 WandB logging of key "losses_after_forward" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
190
+ WARNING 2025-08-22 03:18:48 db_utils.py:141 WandB logging of key "losses_after_rm_padding" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
191
+ INFO 2025-08-22 03:22:28 ts/train.py:232 step:11K smpl:730K ep:3K epch:68.52 loss:0.009 grdn:0.164 lr:7.0e-05 updt_s:1.072 data_s:0.022
192
+ WARNING 2025-08-22 03:22:28 db_utils.py:141 WandB logging of key "losses_after_forward" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
193
+ WARNING 2025-08-22 03:22:28 db_utils.py:141 WandB logging of key "losses_after_rm_padding" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
194
+ INFO 2025-08-22 03:26:09 ts/train.py:232 step:12K smpl:742K ep:3K epch:69.72 loss:0.008 grdn:0.155 lr:6.9e-05 updt_s:1.074 data_s:0.025
195
+ WARNING 2025-08-22 03:26:09 db_utils.py:141 WandB logging of key "losses_after_forward" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
196
+ WARNING 2025-08-22 03:26:09 db_utils.py:141 WandB logging of key "losses_after_rm_padding" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
197
+ INFO 2025-08-22 03:29:49 ts/train.py:232 step:12K smpl:755K ep:3K epch:70.92 loss:0.009 grdn:0.161 lr:6.8e-05 updt_s:1.073 data_s:0.026
198
+ WARNING 2025-08-22 03:29:49 db_utils.py:141 WandB logging of key "losses_after_forward" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
199
+ WARNING 2025-08-22 03:29:49 db_utils.py:141 WandB logging of key "losses_after_rm_padding" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
200
+ INFO 2025-08-22 03:33:30 ts/train.py:232 step:12K smpl:768K ep:3K epch:72.13 loss:0.009 grdn:0.160 lr:6.7e-05 updt_s:1.071 data_s:0.028
201
+ WARNING 2025-08-22 03:33:30 db_utils.py:141 WandB logging of key "losses_after_forward" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
202
+ WARNING 2025-08-22 03:33:30 db_utils.py:141 WandB logging of key "losses_after_rm_padding" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
203
+ INFO 2025-08-22 03:37:14 ts/train.py:232 step:12K smpl:781K ep:3K epch:73.33 loss:0.008 grdn:0.162 lr:6.6e-05 updt_s:1.069 data_s:0.048
204
+ WARNING 2025-08-22 03:37:14 db_utils.py:141 WandB logging of key "losses_after_forward" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
205
+ WARNING 2025-08-22 03:37:14 db_utils.py:141 WandB logging of key "losses_after_rm_padding" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
206
+ INFO 2025-08-22 03:40:55 ts/train.py:232 step:12K smpl:794K ep:3K epch:74.53 loss:0.009 grdn:0.165 lr:6.5e-05 updt_s:1.073 data_s:0.025
207
+ WARNING 2025-08-22 03:40:55 db_utils.py:141 WandB logging of key "losses_after_forward" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
208
+ WARNING 2025-08-22 03:40:55 db_utils.py:141 WandB logging of key "losses_after_rm_padding" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
209
+ INFO 2025-08-22 03:44:35 ts/train.py:232 step:13K smpl:806K ep:3K epch:75.73 loss:0.008 grdn:0.156 lr:6.4e-05 updt_s:1.074 data_s:0.023
210
+ WARNING 2025-08-22 03:44:35 db_utils.py:141 WandB logging of key "losses_after_forward" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
211
+ WARNING 2025-08-22 03:44:35 db_utils.py:141 WandB logging of key "losses_after_rm_padding" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
212
+ INFO 2025-08-22 03:48:15 ts/train.py:232 step:13K smpl:819K ep:3K epch:76.93 loss:0.008 grdn:0.152 lr:6.3e-05 updt_s:1.075 data_s:0.020
213
+ WARNING 2025-08-22 03:48:15 db_utils.py:141 WandB logging of key "losses_after_forward" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
214
+ WARNING 2025-08-22 03:48:15 db_utils.py:141 WandB logging of key "losses_after_rm_padding" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
215
+ INFO 2025-08-22 03:51:56 ts/train.py:232 step:13K smpl:832K ep:4K epch:78.14 loss:0.008 grdn:0.155 lr:6.2e-05 updt_s:1.069 data_s:0.028
216
+ WARNING 2025-08-22 03:51:56 db_utils.py:141 WandB logging of key "losses_after_forward" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
217
+ WARNING 2025-08-22 03:51:56 db_utils.py:141 WandB logging of key "losses_after_rm_padding" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
218
+ INFO 2025-08-22 03:55:39 ts/train.py:232 step:13K smpl:845K ep:4K epch:79.34 loss:0.008 grdn:0.149 lr:6.1e-05 updt_s:1.068 data_s:0.046
219
+ WARNING 2025-08-22 03:55:39 db_utils.py:141 WandB logging of key "losses_after_forward" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
220
+ WARNING 2025-08-22 03:55:39 db_utils.py:141 WandB logging of key "losses_after_rm_padding" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
221
+ INFO 2025-08-22 03:59:20 ts/train.py:232 step:13K smpl:858K ep:4K epch:80.54 loss:0.008 grdn:0.156 lr:6.0e-05 updt_s:1.074 data_s:0.023
222
+ WARNING 2025-08-22 03:59:20 db_utils.py:141 WandB logging of key "losses_after_forward" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
223
+ WARNING 2025-08-22 03:59:20 db_utils.py:141 WandB logging of key "losses_after_rm_padding" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
224
+ INFO 2025-08-22 04:03:00 ts/train.py:232 step:14K smpl:870K ep:4K epch:81.74 loss:0.007 grdn:0.144 lr:5.9e-05 updt_s:1.070 data_s:0.027
225
+ WARNING 2025-08-22 04:03:00 db_utils.py:141 WandB logging of key "losses_after_forward" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
226
+ WARNING 2025-08-22 04:03:00 db_utils.py:141 WandB logging of key "losses_after_rm_padding" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
227
+ INFO 2025-08-22 04:06:40 ts/train.py:232 step:14K smpl:883K ep:4K epch:82.95 loss:0.008 grdn:0.147 lr:5.8e-05 updt_s:1.073 data_s:0.022
228
+ WARNING 2025-08-22 04:06:40 db_utils.py:141 WandB logging of key "losses_after_forward" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
229
+ WARNING 2025-08-22 04:06:40 db_utils.py:141 WandB logging of key "losses_after_rm_padding" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
230
+ INFO 2025-08-22 04:10:21 ts/train.py:232 step:14K smpl:896K ep:4K epch:84.15 loss:0.007 grdn:0.143 lr:5.7e-05 updt_s:1.074 data_s:0.025
231
+ WARNING 2025-08-22 04:10:21 db_utils.py:141 WandB logging of key "losses_after_forward" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
232
+ WARNING 2025-08-22 04:10:21 db_utils.py:141 WandB logging of key "losses_after_rm_padding" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
233
+ INFO 2025-08-22 04:14:05 ts/train.py:232 step:14K smpl:909K ep:4K epch:85.35 loss:0.007 grdn:0.142 lr:5.6e-05 updt_s:1.067 data_s:0.050
234
+ WARNING 2025-08-22 04:14:05 db_utils.py:141 WandB logging of key "losses_after_forward" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
235
+ WARNING 2025-08-22 04:14:05 db_utils.py:141 WandB logging of key "losses_after_rm_padding" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
236
+ INFO 2025-08-22 04:17:46 ts/train.py:232 step:14K smpl:922K ep:4K epch:86.55 loss:0.007 grdn:0.142 lr:5.5e-05 updt_s:1.072 data_s:0.025
237
+ WARNING 2025-08-22 04:17:46 db_utils.py:141 WandB logging of key "losses_after_forward" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
238
+ WARNING 2025-08-22 04:17:46 db_utils.py:141 WandB logging of key "losses_after_rm_padding" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
239
+ INFO 2025-08-22 04:21:27 ts/train.py:232 step:15K smpl:934K ep:4K epch:87.75 loss:0.007 grdn:0.144 lr:5.4e-05 updt_s:1.072 data_s:0.028
240
+ WARNING 2025-08-22 04:21:27 db_utils.py:141 WandB logging of key "losses_after_forward" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
241
+ WARNING 2025-08-22 04:21:27 db_utils.py:141 WandB logging of key "losses_after_rm_padding" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
242
+ INFO 2025-08-22 04:25:07 ts/train.py:232 step:15K smpl:947K ep:4K epch:88.96 loss:0.007 grdn:0.142 lr:5.3e-05 updt_s:1.075 data_s:0.022
243
+ WARNING 2025-08-22 04:25:07 db_utils.py:141 WandB logging of key "losses_after_forward" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
244
+ WARNING 2025-08-22 04:25:07 db_utils.py:141 WandB logging of key "losses_after_rm_padding" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
245
+ INFO 2025-08-22 04:28:48 ts/train.py:232 step:15K smpl:960K ep:4K epch:90.16 loss:0.007 grdn:0.133 lr:5.2e-05 updt_s:1.072 data_s:0.026
246
+ WARNING 2025-08-22 04:28:48 db_utils.py:141 WandB logging of key "losses_after_forward" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
247
+ WARNING 2025-08-22 04:28:48 db_utils.py:141 WandB logging of key "losses_after_rm_padding" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
248
+ INFO 2025-08-22 04:32:32 ts/train.py:232 step:15K smpl:973K ep:4K epch:91.36 loss:0.007 grdn:0.138 lr:5.1e-05 updt_s:1.067 data_s:0.050
249
+ WARNING 2025-08-22 04:32:32 db_utils.py:141 WandB logging of key "losses_after_forward" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
250
+ WARNING 2025-08-22 04:32:32 db_utils.py:141 WandB logging of key "losses_after_rm_padding" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
251
+ INFO 2025-08-22 04:36:12 ts/train.py:232 step:15K smpl:986K ep:4K epch:92.56 loss:0.007 grdn:0.135 lr:5.0e-05 updt_s:1.073 data_s:0.020
252
+ WARNING 2025-08-22 04:36:12 db_utils.py:141 WandB logging of key "losses_after_forward" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
253
+ WARNING 2025-08-22 04:36:12 db_utils.py:141 WandB logging of key "losses_after_rm_padding" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
254
+ INFO 2025-08-22 04:39:52 ts/train.py:232 step:16K smpl:998K ep:4K epch:93.76 loss:0.007 grdn:0.132 lr:4.9e-05 updt_s:1.072 data_s:0.026
255
+ WARNING 2025-08-22 04:39:52 db_utils.py:141 WandB logging of key "losses_after_forward" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
256
+ WARNING 2025-08-22 04:39:52 db_utils.py:141 WandB logging of key "losses_after_rm_padding" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
257
+ INFO 2025-08-22 04:43:33 ts/train.py:232 step:16K smpl:1M ep:4K epch:94.97 loss:0.007 grdn:0.135 lr:4.8e-05 updt_s:1.073 data_s:0.025
258
+ WARNING 2025-08-22 04:43:33 db_utils.py:141 WandB logging of key "losses_after_forward" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
259
+ WARNING 2025-08-22 04:43:33 db_utils.py:141 WandB logging of key "losses_after_rm_padding" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
260
+ INFO 2025-08-22 04:47:13 ts/train.py:232 step:16K smpl:1M ep:4K epch:96.17 loss:0.006 grdn:0.132 lr:4.7e-05 updt_s:1.068 data_s:0.027
261
+ WARNING 2025-08-22 04:47:13 db_utils.py:141 WandB logging of key "losses_after_forward" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
262
+ WARNING 2025-08-22 04:47:13 db_utils.py:141 WandB logging of key "losses_after_rm_padding" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
263
+ INFO 2025-08-22 04:50:57 ts/train.py:232 step:16K smpl:1M ep:4K epch:97.37 loss:0.006 grdn:0.133 lr:4.6e-05 updt_s:1.063 data_s:0.053
264
+ WARNING 2025-08-22 04:50:57 db_utils.py:141 WandB logging of key "losses_after_forward" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
265
+ WARNING 2025-08-22 04:50:57 db_utils.py:141 WandB logging of key "losses_after_rm_padding" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
266
+ INFO 2025-08-22 04:54:38 ts/train.py:232 step:16K smpl:1M ep:4K epch:98.57 loss:0.006 grdn:0.130 lr:4.5e-05 updt_s:1.073 data_s:0.028
267
+ WARNING 2025-08-22 04:54:38 db_utils.py:141 WandB logging of key "losses_after_forward" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
268
+ WARNING 2025-08-22 04:54:38 db_utils.py:141 WandB logging of key "losses_after_rm_padding" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
269
+ INFO 2025-08-22 04:58:18 ts/train.py:232 step:17K smpl:1M ep:4K epch:99.77 loss:0.006 grdn:0.123 lr:4.4e-05 updt_s:1.071 data_s:0.025
270
+ WARNING 2025-08-22 04:58:18 db_utils.py:141 WandB logging of key "losses_after_forward" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
271
+ WARNING 2025-08-22 04:58:18 db_utils.py:141 WandB logging of key "losses_after_rm_padding" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
272
+ INFO 2025-08-22 05:01:58 ts/train.py:232 step:17K smpl:1M ep:5K epch:100.98 loss:0.006 grdn:0.127 lr:4.3e-05 updt_s:1.072 data_s:0.026
273
+ WARNING 2025-08-22 05:01:58 db_utils.py:141 WandB logging of key "losses_after_forward" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
274
+ WARNING 2025-08-22 05:01:58 db_utils.py:141 WandB logging of key "losses_after_rm_padding" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
275
+ INFO 2025-08-22 05:05:39 ts/train.py:232 step:17K smpl:1M ep:5K epch:102.18 loss:0.006 grdn:0.124 lr:4.2e-05 updt_s:1.074 data_s:0.023
276
+ WARNING 2025-08-22 05:05:39 db_utils.py:141 WandB logging of key "losses_after_forward" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
277
+ WARNING 2025-08-22 05:05:39 db_utils.py:141 WandB logging of key "losses_after_rm_padding" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
278
+ INFO 2025-08-22 05:09:19 ts/train.py:232 step:17K smpl:1M ep:5K epch:103.38 loss:0.006 grdn:0.123 lr:4.1e-05 updt_s:1.067 data_s:0.028
279
+ WARNING 2025-08-22 05:09:19 db_utils.py:141 WandB logging of key "losses_after_forward" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
280
+ WARNING 2025-08-22 05:09:19 db_utils.py:141 WandB logging of key "losses_after_rm_padding" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
281
+ INFO 2025-08-22 05:13:03 ts/train.py:232 step:17K smpl:1M ep:5K epch:104.58 loss:0.006 grdn:0.119 lr:4.0e-05 updt_s:1.073 data_s:0.042
282
+ WARNING 2025-08-22 05:13:03 db_utils.py:141 WandB logging of key "losses_after_forward" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
283
+ WARNING 2025-08-22 05:13:03 db_utils.py:141 WandB logging of key "losses_after_rm_padding" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
284
+ INFO 2025-08-22 05:16:42 ts/train.py:232 step:18K smpl:1M ep:5K epch:105.79 loss:0.006 grdn:0.119 lr:3.9e-05 updt_s:1.073 data_s:0.021
285
+ WARNING 2025-08-22 05:16:42 db_utils.py:141 WandB logging of key "losses_after_forward" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
286
+ WARNING 2025-08-22 05:16:42 db_utils.py:141 WandB logging of key "losses_after_rm_padding" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
287
+ INFO 2025-08-22 05:20:22 ts/train.py:232 step:18K smpl:1M ep:5K epch:106.99 loss:0.006 grdn:0.120 lr:3.8e-05 updt_s:1.074 data_s:0.020
288
+ WARNING 2025-08-22 05:20:22 db_utils.py:141 WandB logging of key "losses_after_forward" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
289
+ WARNING 2025-08-22 05:20:22 db_utils.py:141 WandB logging of key "losses_after_rm_padding" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
290
+ INFO 2025-08-22 05:24:03 ts/train.py:232 step:18K smpl:1M ep:5K epch:108.19 loss:0.006 grdn:0.112 lr:3.7e-05 updt_s:1.073 data_s:0.025
291
+ WARNING 2025-08-22 05:24:03 db_utils.py:141 WandB logging of key "losses_after_forward" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
292
+ WARNING 2025-08-22 05:24:03 db_utils.py:141 WandB logging of key "losses_after_rm_padding" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
293
+ INFO 2025-08-22 05:27:43 ts/train.py:232 step:18K smpl:1M ep:5K epch:109.39 loss:0.006 grdn:0.114 lr:3.6e-05 updt_s:1.069 data_s:0.028
294
+ WARNING 2025-08-22 05:27:43 db_utils.py:141 WandB logging of key "losses_after_forward" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
295
+ WARNING 2025-08-22 05:27:43 db_utils.py:141 WandB logging of key "losses_after_rm_padding" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
296
+ INFO 2025-08-22 05:31:28 ts/train.py:232 step:18K smpl:1M ep:5K epch:110.59 loss:0.006 grdn:0.115 lr:3.5e-05 updt_s:1.069 data_s:0.049
297
+ WARNING 2025-08-22 05:31:28 db_utils.py:141 WandB logging of key "losses_after_forward" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
298
+ WARNING 2025-08-22 05:31:28 db_utils.py:141 WandB logging of key "losses_after_rm_padding" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
299
+ INFO 2025-08-22 05:35:08 ts/train.py:232 step:19K smpl:1M ep:5K epch:111.80 loss:0.006 grdn:0.115 lr:3.4e-05 updt_s:1.072 data_s:0.025
300
+ WARNING 2025-08-22 05:35:08 db_utils.py:141 WandB logging of key "losses_after_forward" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
301
+ WARNING 2025-08-22 05:35:08 db_utils.py:141 WandB logging of key "losses_after_rm_padding" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
302
+ INFO 2025-08-22 05:38:49 ts/train.py:232 step:19K smpl:1M ep:5K epch:113.00 loss:0.006 grdn:0.107 lr:3.3e-05 updt_s:1.072 data_s:0.028
303
+ WARNING 2025-08-22 05:38:49 db_utils.py:141 WandB logging of key "losses_after_forward" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
304
+ WARNING 2025-08-22 05:38:49 db_utils.py:141 WandB logging of key "losses_after_rm_padding" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
305
+ INFO 2025-08-22 05:42:29 ts/train.py:232 step:19K smpl:1M ep:5K epch:114.20 loss:0.006 grdn:0.111 lr:3.2e-05 updt_s:1.072 data_s:0.021
306
+ WARNING 2025-08-22 05:42:29 db_utils.py:141 WandB logging of key "losses_after_forward" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
307
+ WARNING 2025-08-22 05:42:29 db_utils.py:141 WandB logging of key "losses_after_rm_padding" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
308
+ INFO 2025-08-22 05:46:09 ts/train.py:232 step:19K smpl:1M ep:5K epch:115.40 loss:0.005 grdn:0.108 lr:3.1e-05 updt_s:1.069 data_s:0.028
309
+ WARNING 2025-08-22 05:46:09 db_utils.py:141 WandB logging of key "losses_after_forward" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
310
+ WARNING 2025-08-22 05:46:09 db_utils.py:141 WandB logging of key "losses_after_rm_padding" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
311
+ INFO 2025-08-22 05:49:54 ts/train.py:232 step:19K smpl:1M ep:5K epch:116.60 loss:0.005 grdn:0.107 lr:3.0e-05 updt_s:1.069 data_s:0.050
312
+ WARNING 2025-08-22 05:49:54 db_utils.py:141 WandB logging of key "losses_after_forward" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
313
+ WARNING 2025-08-22 05:49:54 db_utils.py:141 WandB logging of key "losses_after_rm_padding" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
314
+ INFO 2025-08-22 05:53:35 ts/train.py:232 step:20K smpl:1M ep:5K epch:117.81 loss:0.005 grdn:0.110 lr:2.9e-05 updt_s:1.073 data_s:0.028
315
+ WARNING 2025-08-22 05:53:35 db_utils.py:141 WandB logging of key "losses_after_forward" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
316
+ WARNING 2025-08-22 05:53:35 db_utils.py:141 WandB logging of key "losses_after_rm_padding" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
317
+ INFO 2025-08-22 05:57:16 ts/train.py:232 step:20K smpl:1M ep:5K epch:119.01 loss:0.005 grdn:0.102 lr:2.8e-05 updt_s:1.073 data_s:0.027
318
+ WARNING 2025-08-22 05:57:16 db_utils.py:141 WandB logging of key "losses_after_forward" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
319
+ WARNING 2025-08-22 05:57:16 db_utils.py:141 WandB logging of key "losses_after_rm_padding" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
320
+ INFO 2025-08-22 06:00:57 ts/train.py:232 step:20K smpl:1M ep:5K epch:120.21 loss:0.005 grdn:0.102 lr:2.7e-05 updt_s:1.071 data_s:0.028
321
+ WARNING 2025-08-22 06:00:57 db_utils.py:141 WandB logging of key "losses_after_forward" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
322
+ WARNING 2025-08-22 06:00:57 db_utils.py:141 WandB logging of key "losses_after_rm_padding" was ignored as its type "<class 'torch.Tensor'>" is not handled by this wrapper.
323
+ INFO 2025-08-22 06:00:57 ts/train.py:241 Checkpoint policy after step 20000
324
+ INFO 2025-08-22 06:01:01 ts/train.py:283 End of training
325
+ Traceback (most recent call last):
326
+ File "/home/collab/miniconda3/envs/lerobot/bin/lerobot-train", line 8, in <module>
327
+ sys.exit(main())
328
+ File "/home/collab/git/lerobot/src/lerobot/scripts/train.py", line 291, in main
329
+ train()
330
+ File "/home/collab/git/lerobot/src/lerobot/configs/parser.py", line 225, in wrapper_inner
331
+ response = fn(cfg, *args, **kwargs)
332
+ File "/home/collab/git/lerobot/src/lerobot/scripts/train.py", line 286, in train
333
+ policy.push_model_to_hub(cfg)
334
+ File "/home/collab/git/lerobot/src/lerobot/policies/pretrained.py", line 206, in push_model_to_hub
335
+ repo_id = api.create_repo(
336
+ File "/home/collab/.local/lib/python3.10/site-packages/huggingface_hub/utils/_validators.py", line 106, in _inner_fn
337
+ validate_repo_id(arg_value)
338
+ File "/home/collab/.local/lib/python3.10/site-packages/huggingface_hub/utils/_validators.py", line 160, in validate_repo_id
339
+ raise HFValidationError(
340
+ huggingface_hub.errors.HFValidationError: Repo id must use alphanumeric chars or '-', '_', '.', '--' and '..' are forbidden, '-' and '.' cannot start or end the name, max length is 96: '/so101_smolvla_push_cube_test2'.
wandb/run-20250821_235211-3qesni5p/files/requirements.txt ADDED
@@ -0,0 +1,163 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ inquirerpy==0.3.4
2
+ pyserial==3.5
3
+ distlib==0.3.9
4
+ colorama==0.4.6
5
+ MarkupSafe==3.0.2
6
+ cfgv==3.4.0
7
+ platformdirs==4.3.8
8
+ wrapt==1.17.2
9
+ bkstools==0.0.2.31
10
+ charset-normalizer==3.4.1
11
+ pyRobotiqGripper==1.0.0
12
+ pre_commit==4.2.0
13
+ PyYAML==6.0.2
14
+ identify==2.6.12
15
+ huggingface-hub==0.34.4
16
+ Jinja2==3.1.6
17
+ argcomplete==3.6.2
18
+ packaging==25.0
19
+ smmap==5.0.2
20
+ virtualenv==20.31.2
21
+ hf-xet==1.1.5
22
+ minimalmodbus==2.1.1
23
+ GitPython==3.1.44
24
+ pfzy==0.3.4
25
+ requests==2.32.3
26
+ filelock==3.18.0
27
+ tqdm==4.67.1
28
+ nodeenv==1.9.1
29
+ wcwidth==0.2.13
30
+ typing_extensions==4.14.1
31
+ prompt_toolkit==3.0.51
32
+ gitdb==4.0.12
33
+ numpy==2.1.3
34
+ importlib_resources==6.5.2
35
+ huggingface-hub==0.34.3
36
+ tzdata==2025.2
37
+ Werkzeug==3.1.3
38
+ mergedeep==1.3.4
39
+ promise==2.3
40
+ attrs==25.3.0
41
+ etils==1.13.0
42
+ pyyaml-include==1.4.1
43
+ google-pasta==0.2.0
44
+ lerobot==0.3.4
45
+ keras==3.11.1
46
+ tensorboard-data-server==0.7.2
47
+ deepdiff==8.5.0
48
+ psutil==7.0.0
49
+ xxhash==3.5.0
50
+ Flask==3.1.1
51
+ nvidia-cudnn-cu12==9.5.1.17
52
+ nvidia-cusparse-cu12==12.5.4.2
53
+ urllib3==2.5.0
54
+ networkx==3.4.2
55
+ optree==0.17.0
56
+ safetensors==0.6.1
57
+ nvidia-cublas-cu12==12.6.4.1
58
+ wheel==0.45.1
59
+ dill==0.3.8
60
+ itsdangerous==2.2.0
61
+ fsspec==2025.3.0
62
+ torchvision==0.22.1
63
+ draccus==0.10.0
64
+ protobuf==4.21.12
65
+ certifi==2025.8.3
66
+ termcolor==3.1.0
67
+ propcache==0.3.2
68
+ aiosignal==1.4.0
69
+ multiprocess==0.70.16
70
+ nvidia-curand-cu12==10.3.7.77
71
+ pillow==11.3.0
72
+ tensorflow-metadata==1.17.2
73
+ opt_einsum==3.4.0
74
+ multidict==6.6.3
75
+ sympy==1.14.0
76
+ h5py==3.14.0
77
+ aiohappyeyeballs==2.6.1
78
+ libclang==18.1.1
79
+ jsonlines==4.0.0
80
+ array_record==0.7.2
81
+ simple-parsing==0.1.7
82
+ regex==2025.7.34
83
+ async-timeout==5.0.1
84
+ blinker==1.9.0
85
+ rerun-sdk==0.22.1
86
+ annotated-types==0.7.0
87
+ nvidia-nccl-cu12==2.26.2
88
+ num2words==0.5.14
89
+ imageio-ffmpeg==0.6.0
90
+ flatbuffers==25.2.10
91
+ opencv-python-headless==4.12.0.88
92
+ zipp==3.23.0
93
+ einops==0.8.1
94
+ setuptools==78.1.1
95
+ typing-inspection==0.4.1
96
+ Markdown==3.8.2
97
+ toml==0.10.2
98
+ accelerate==1.10.0
99
+ evdev==1.9.2
100
+ typing-inspect==0.9.0
101
+ datasets==3.6.0
102
+ pydantic_core==2.33.2
103
+ cmake==4.0.3
104
+ diffusers==0.34.0
105
+ Farama-Notifications==0.0.4
106
+ tokenizers==0.21.4
107
+ Pygments==2.19.2
108
+ frozenlist==1.7.0
109
+ grpcio==1.74.0
110
+ cloudpickle==3.1.1
111
+ hf_transfer==0.1.9
112
+ nvidia-cusolver-cu12==11.7.1.2
113
+ aiohttp==3.12.15
114
+ av==15.0.0
115
+ docopt==0.6.2
116
+ astunparse==1.6.3
117
+ nvidia-cuda-nvrtc-cu12==12.6.77
118
+ importlib_metadata==8.7.0
119
+ pytz==2025.2
120
+ pyarrow==21.0.0
121
+ triton==3.3.1
122
+ sentry-sdk==2.34.1
123
+ pip==25.1
124
+ nvidia-cuda-cupti-cu12==12.6.80
125
+ gast==0.6.0
126
+ pynput==1.8.1
127
+ absl-py==2.3.1
128
+ mdurl==0.1.2
129
+ docstring_parser==0.17.0
130
+ wandb==0.21.0
131
+ tensorboard==2.19.0
132
+ mypy_extensions==1.1.0
133
+ tensorflow-io-gcs-filesystem==0.37.1
134
+ tensorflow-datasets==4.9.9
135
+ nvidia-cuda-runtime-cu12==12.6.77
136
+ gymnasium==0.29.1
137
+ yarl==1.20.1
138
+ six==1.17.0
139
+ tensorflow==2.19.0
140
+ python-xlib==0.33
141
+ nvidia-cusparselt-cu12==0.6.3
142
+ idna==3.10
143
+ rich==14.1.0
144
+ nvidia-cufft-cu12==11.3.0.4
145
+ python-dateutil==2.9.0.post0
146
+ ml_dtypes==0.5.3
147
+ nvidia-nvtx-cu12==12.6.77
148
+ click==8.2.1
149
+ namex==0.1.0
150
+ orderly-set==5.5.0
151
+ pandas==2.3.1
152
+ nvidia-nvjitlink-cu12==12.6.85
153
+ transformers==4.51.3
154
+ nvidia-cufile-cu12==1.11.1.6
155
+ dm-tree==0.1.9
156
+ torchcodec==0.5
157
+ torch==2.7.1
158
+ pydantic==2.11.7
159
+ markdown-it-py==3.0.0
160
+ imageio==2.37.0
161
+ immutabledict==4.2.1
162
+ mpmath==1.3.0
163
+ lerobot==0.3.4
wandb/run-20250821_235211-3qesni5p/files/wandb-metadata.json ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "os": "Linux-6.8.0-65-generic-x86_64-with-glibc2.35",
3
+ "python": "CPython 3.10.18",
4
+ "startedAt": "2025-08-21T21:52:11.541066Z",
5
+ "args": [
6
+ "--policy.path=lerobot/smolvla_base",
7
+ "--dataset.repo_id=MCeut/so101_push_cube_test1",
8
+ "--batch_size=64",
9
+ "--steps=20000",
10
+ "--output_dir=outputs/train/so101_smolvla_push_cube_test2",
11
+ "--job_name=so101_smolvla_training_push_cube_test2",
12
+ "--policy.device=cuda",
13
+ "--wandb.enable=true",
14
+ "--policy.repo_id=/so101_smolvla_push_cube_test2",
15
+ "--dataset.video_backend=pyav"
16
+ ],
17
+ "program": "/home/collab/miniconda3/envs/lerobot/bin/lerobot-train",
18
+ "git": {
19
+ "remote": "https://github.com/huggingface/lerobot.git",
20
+ "commit": "7f70b78f3221a2fa64ae09795b5989a58a61931d"
21
+ },
22
+ "root": "outputs/train/so101_smolvla_push_cube_test2",
23
+ "host": "CL-ROBOLAB3",
24
+ "executable": "/home/collab/miniconda3/envs/lerobot/bin/python3.10",
25
+ "cpu_count": 8,
26
+ "cpu_count_logical": 16,
27
+ "gpu": "NVIDIA GeForce RTX 3090 Ti",
28
+ "gpu_count": 1,
29
+ "disk": {
30
+ "/": {
31
+ "total": "1654231658496",
32
+ "used": "542871166976"
33
+ }
34
+ },
35
+ "memory": {
36
+ "total": "33497321472"
37
+ },
38
+ "gpu_nvidia": [
39
+ {
40
+ "name": "NVIDIA GeForce RTX 3090 Ti",
41
+ "memoryTotal": "25757220864",
42
+ "cudaCores": 10752,
43
+ "architecture": "Ampere",
44
+ "uuid": "GPU-870abedb-e007-b2f9-acff-2fbf869229ac"
45
+ }
46
+ ],
47
+ "cudaVersion": "12.2",
48
+ "writerId": "kl5ugdoqcldc8c1uwtt9an4z1lal0evc"
49
+ }
wandb/run-20250821_235211-3qesni5p/files/wandb-summary.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"train/grad_norm":0.10215238908305764,"train/lr":2.7316655657931005e-05,"train/episodes":5409.46656649136,"_runtime":22129.772105901,"train/update_s":1.0714523765462218,"_step":20000,"train/dataloading_s":0.027618777160241734,"train/steps":20000,"_wandb":{"runtime":22129},"train/epochs":120.21036814425244,"_timestamp":1.7558352576997418e+09,"train/loss":0.0033072722144424915,"train/samples":1280000}
wandb/run-20250821_235211-3qesni5p/logs/debug-core.log ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"time":"2025-08-21T23:52:11.572702566+02:00","level":"INFO","msg":"main: starting server","port-filename":"/tmp/tmp1qxgpxgq/port-2718618.txt","pid":2718618,"log-level":0,"disable-analytics":false,"shutdown-on-parent-exit":false,"enable-dcgm-profiling":false}
2
+ {"time":"2025-08-21T23:52:11.573167278+02:00","level":"INFO","msg":"server: accepting connections","addr":{"Name":"/tmp/wandb-2718618-2718717-2806837694/socket","Net":"unix"}}
3
+ {"time":"2025-08-21T23:52:11.573240759+02:00","level":"INFO","msg":"server: will exit if parent process dies","ppid":2718618}
4
+ {"time":"2025-08-21T23:52:11.747255103+02:00","level":"INFO","msg":"connection: ManageConnectionData: new connection created","id":"1(@)"}
5
+ {"time":"2025-08-21T23:52:11.757186961+02:00","level":"INFO","msg":"handleInformInit: received","streamId":"3qesni5p","id":"1(@)"}
6
+ {"time":"2025-08-21T23:52:12.13215952+02:00","level":"INFO","msg":"handleInformInit: stream started","streamId":"3qesni5p","id":"1(@)"}
7
+ {"time":"2025-08-22T06:01:02.138538447+02:00","level":"INFO","msg":"handleInformTeardown: server teardown initiated","id":"1(@)"}
8
+ {"time":"2025-08-22T06:01:02.138591885+02:00","level":"INFO","msg":"server is shutting down"}
9
+ {"time":"2025-08-22T06:01:02.138573063+02:00","level":"INFO","msg":"connection: closing","id":"1(@)"}
10
+ {"time":"2025-08-22T06:01:02.138658239+02:00","level":"INFO","msg":"connection: closed successfully","id":"1(@)"}
11
+ {"time":"2025-08-22T06:01:02.138658046+02:00","level":"INFO","msg":"server: listener closed","addr":{"Name":"/tmp/wandb-2718618-2718717-2806837694/socket","Net":"unix"}}
12
+ {"time":"2025-08-22T06:03:38.960645652+02:00","level":"ERROR","msg":"processOutgoingData: flush error","error":"write unix /tmp/wandb-2718618-2718717-2806837694/socket->@: use of closed network connection","id":"1(@)"}
13
+ {"time":"2025-08-22T06:03:39.222653168+02:00","level":"INFO","msg":"handleInformTeardown: server shutdown complete","id":"1(@)"}
14
+ {"time":"2025-08-22T06:03:39.222672193+02:00","level":"INFO","msg":"connection: ManageConnectionData: connection closed","id":"1(@)"}
15
+ {"time":"2025-08-22T06:03:39.222680169+02:00","level":"INFO","msg":"server is closed"}
wandb/run-20250821_235211-3qesni5p/logs/debug-internal.log ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"time":"2025-08-21T23:52:11.757259626+02:00","level":"INFO","msg":"stream: starting","core version":"0.21.0"}
2
+ {"time":"2025-08-21T23:52:12.132021046+02:00","level":"INFO","msg":"stream: created new stream","id":"3qesni5p"}
3
+ {"time":"2025-08-21T23:52:12.132078765+02:00","level":"INFO","msg":"writer: Do: started","stream_id":"3qesni5p"}
4
+ {"time":"2025-08-21T23:52:12.132115895+02:00","level":"INFO","msg":"sender: started","stream_id":"3qesni5p"}
5
+ {"time":"2025-08-21T23:52:12.132147155+02:00","level":"INFO","msg":"handler: started","stream_id":"3qesni5p"}
6
+ {"time":"2025-08-21T23:52:12.132151414+02:00","level":"INFO","msg":"stream: started","id":"3qesni5p"}
7
+ {"time":"2025-08-22T06:01:02.138644824+02:00","level":"INFO","msg":"stream: closing","id":"3qesni5p"}
8
+ {"time":"2025-08-22T06:03:39.010797634+02:00","level":"INFO","msg":"fileTransfer: Close: file transfer manager closed"}
9
+ {"time":"2025-08-22T06:03:39.21518114+02:00","level":"INFO","msg":"handler: closed","stream_id":"3qesni5p"}
10
+ {"time":"2025-08-22T06:03:39.215212987+02:00","level":"INFO","msg":"writer: Close: closed","stream_id":"3qesni5p"}
11
+ {"time":"2025-08-22T06:03:39.215220482+02:00","level":"INFO","msg":"sender: closed","stream_id":"3qesni5p"}
12
+ {"time":"2025-08-22T06:03:39.221321624+02:00","level":"INFO","msg":"stream: closed","id":"3qesni5p"}
wandb/run-20250821_235211-3qesni5p/logs/debug.log ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2025-08-21 23:52:11,541 INFO MainThread:2718618 [wandb_setup.py:_flush():80] Current SDK version is 0.21.0
2
+ 2025-08-21 23:52:11,541 INFO MainThread:2718618 [wandb_setup.py:_flush():80] Configure stats pid to 2718618
3
+ 2025-08-21 23:52:11,541 INFO MainThread:2718618 [wandb_setup.py:_flush():80] Loading settings from /home/collab/.config/wandb/settings
4
+ 2025-08-21 23:52:11,541 INFO MainThread:2718618 [wandb_setup.py:_flush():80] Loading settings from /home/collab/git/lerobot/wandb/settings
5
+ 2025-08-21 23:52:11,541 INFO MainThread:2718618 [wandb_setup.py:_flush():80] Loading settings from environment variables
6
+ 2025-08-21 23:52:11,541 INFO MainThread:2718618 [wandb_init.py:setup_run_log_directory():703] Logging user logs to outputs/train/so101_smolvla_push_cube_test2/wandb/run-20250821_235211-3qesni5p/logs/debug.log
7
+ 2025-08-21 23:52:11,541 INFO MainThread:2718618 [wandb_init.py:setup_run_log_directory():704] Logging internal logs to outputs/train/so101_smolvla_push_cube_test2/wandb/run-20250821_235211-3qesni5p/logs/debug-internal.log
8
+ 2025-08-21 23:52:11,542 INFO MainThread:2718618 [wandb_init.py:init():830] calling init triggers
9
+ 2025-08-21 23:52:11,542 INFO MainThread:2718618 [wandb_init.py:init():835] wandb.init called with sweep_config: {}
10
+ config: {'dataset': {'repo_id': 'MCeut/so101_push_cube_test1', 'root': None, 'episodes': None, 'image_transforms': {'enable': False, 'max_num_transforms': 3, 'random_order': False, 'tfs': {'brightness': {'weight': 1.0, 'type': 'ColorJitter', 'kwargs': {'brightness': [0.8, 1.2]}}, 'contrast': {'weight': 1.0, 'type': 'ColorJitter', 'kwargs': {'contrast': [0.8, 1.2]}}, 'saturation': {'weight': 1.0, 'type': 'ColorJitter', 'kwargs': {'saturation': [0.5, 1.5]}}, 'hue': {'weight': 1.0, 'type': 'ColorJitter', 'kwargs': {'hue': [-0.05, 0.05]}}, 'sharpness': {'weight': 1.0, 'type': 'SharpnessJitter', 'kwargs': {'sharpness': [0.5, 1.5]}}}}, 'revision': None, 'use_imagenet_stats': True, 'video_backend': 'pyav'}, 'env': None, 'policy': {'type': 'smolvla', 'n_obs_steps': 1, 'normalization_mapping': {'VISUAL': <NormalizationMode.IDENTITY: 'IDENTITY'>, 'STATE': <NormalizationMode.MEAN_STD: 'MEAN_STD'>, 'ACTION': <NormalizationMode.MEAN_STD: 'MEAN_STD'>}, 'input_features': {'observation.state': {'type': <FeatureType.STATE: 'STATE'>, 'shape': [6]}, 'observation.image2': {'type': <FeatureType.VISUAL: 'VISUAL'>, 'shape': [3, 256, 256]}, 'observation.image': {'type': <FeatureType.VISUAL: 'VISUAL'>, 'shape': [3, 256, 256]}, 'observation.image3': {'type': <FeatureType.VISUAL: 'VISUAL'>, 'shape': [3, 256, 256]}}, 'output_features': {'action': {'type': <FeatureType.ACTION: 'ACTION'>, 'shape': [6]}}, 'device': 'cuda', 'use_amp': False, 'push_to_hub': True, 'repo_id': '/so101_smolvla_push_cube_test2', 'private': None, 'tags': None, 'license': None, 'chunk_size': 50, 'n_action_steps': 50, 'max_state_dim': 32, 'max_action_dim': 32, 'resize_imgs_with_padding': [512, 512], 'empty_cameras': 0, 'adapt_to_pi_aloha': False, 'use_delta_joint_actions_aloha': False, 'tokenizer_max_length': 48, 'num_steps': 10, 'use_cache': True, 'freeze_vision_encoder': True, 'train_expert_only': True, 'train_state_proj': True, 'optimizer_lr': 0.0001, 'optimizer_betas': [0.9, 0.95], 'optimizer_eps': 1e-08, 'optimizer_weight_decay': 1e-10, 'optimizer_grad_clip_norm': 10.0, 'scheduler_warmup_steps': 1000, 'scheduler_decay_steps': 30000, 'scheduler_decay_lr': 2.5e-06, 'vlm_model_name': 'HuggingFaceTB/SmolVLM2-500M-Video-Instruct', 'load_vlm_weights': True, 'add_image_special_tokens': False, 'attention_mode': 'cross_attn', 'prefix_length': 0, 'pad_language_to': 'max_length', 'num_expert_layers': 0, 'num_vlm_layers': 16, 'self_attn_every_n_layers': 2, 'expert_width_multiplier': 0.75, 'min_period': 0.004, 'max_period': 4.0}, 'output_dir': 'outputs/train/so101_smolvla_push_cube_test2', 'job_name': 'so101_smolvla_training_push_cube_test2', 'resume': False, 'seed': 1000, 'num_workers': 4, 'batch_size': 64, 'steps': 20000, 'eval_freq': 20000, 'log_freq': 200, 'save_checkpoint': True, 'save_freq': 20000, 'use_policy_training_preset': True, 'optimizer': {'type': 'adamw', 'lr': 0.0001, 'weight_decay': 1e-10, 'grad_clip_norm': 10.0, 'betas': [0.9, 0.95], 'eps': 1e-08}, 'scheduler': {'type': 'cosine_decay_with_warmup', 'num_warmup_steps': 1000, 'num_decay_steps': 30000, 'peak_lr': 0.0001, 'decay_lr': 2.5e-06}, 'eval': {'n_episodes': 50, 'batch_size': 50, 'use_async_envs': False}, 'wandb': {'enable': True, 'disable_artifact': False, 'project': 'lerobot', 'entity': None, 'notes': None, 'run_id': None, 'mode': None}, '_wandb': {}}
11
+ 2025-08-21 23:52:11,542 INFO MainThread:2718618 [wandb_init.py:init():871] starting backend
12
+ 2025-08-21 23:52:11,747 INFO MainThread:2718618 [wandb_init.py:init():874] sending inform_init request
13
+ 2025-08-21 23:52:11,755 INFO MainThread:2718618 [wandb_init.py:init():882] backend started and connected
14
+ 2025-08-21 23:52:11,756 INFO MainThread:2718618 [wandb_init.py:init():953] updated telemetry
15
+ 2025-08-21 23:52:11,760 INFO MainThread:2718618 [wandb_init.py:init():977] communicating run to backend with 90.0 second timeout
16
+ 2025-08-21 23:52:12,365 INFO MainThread:2718618 [wandb_init.py:init():1029] starting run threads in backend
17
+ 2025-08-21 23:52:12,471 INFO MainThread:2718618 [wandb_run.py:_console_start():2458] atexit reg
18
+ 2025-08-21 23:52:12,471 INFO MainThread:2718618 [wandb_run.py:_redirect():2306] redirect: wrap_raw
19
+ 2025-08-21 23:52:12,471 INFO MainThread:2718618 [wandb_run.py:_redirect():2375] Wrapping output streams.
20
+ 2025-08-21 23:52:12,471 INFO MainThread:2718618 [wandb_run.py:_redirect():2398] Redirects installed.
21
+ 2025-08-21 23:52:12,472 INFO MainThread:2718618 [wandb_init.py:init():1075] run started, returning control to user process
22
+ 2025-08-22 06:01:02,138 INFO MsgRouterThr:2718618 [mailbox.py:close():129] [no run ID] Closing mailbox, abandoning 2 handles.
wandb/run-20250821_235211-3qesni5p/run-3qesni5p.wandb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eeed2423db1e5a16a72a78bd53a1ff5c72187b919db7453822b7519d47777257
3
+ size 1389160