Hugging Face's logo

shashuo0104
/
dp-insert-rope

Safetensors
Model card Files
xet
 Community
1
shashuo0104 commited on
Commit
7b90fff
·
verified ·
1 Parent(s): 93a38ba

Upload folder using huggingface_hub

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. .gitattributes +2 -0
  2. checkpoints/000100/pretrained_model/config.json +85 -0
  3. checkpoints/000100/pretrained_model/model.safetensors +3 -0
  4. checkpoints/000100/pretrained_model/train_config.json +235 -0
  5. checkpoints/000100/training_state/optimizer_param_groups.json +233 -0
  6. checkpoints/000100/training_state/optimizer_state.safetensors +3 -0
  7. checkpoints/000100/training_state/rng_state.safetensors +3 -0
  8. checkpoints/000100/training_state/scheduler_state.json +14 -0
  9. checkpoints/000100/training_state/training_step.json +3 -0
  10. checkpoints/000200/pretrained_model/config.json +85 -0
  11. checkpoints/000200/pretrained_model/model.safetensors +3 -0
  12. checkpoints/000200/pretrained_model/train_config.json +235 -0
  13. checkpoints/000200/training_state/optimizer_param_groups.json +233 -0
  14. checkpoints/000200/training_state/optimizer_state.safetensors +3 -0
  15. checkpoints/000200/training_state/rng_state.safetensors +3 -0
  16. checkpoints/000200/training_state/scheduler_state.json +14 -0
  17. checkpoints/000200/training_state/training_step.json +3 -0
  18. checkpoints/000300/pretrained_model/config.json +85 -0
  19. checkpoints/000300/pretrained_model/model.safetensors +3 -0
  20. checkpoints/000300/pretrained_model/train_config.json +235 -0
  21. checkpoints/000300/training_state/optimizer_param_groups.json +233 -0
  22. checkpoints/000300/training_state/optimizer_state.safetensors +3 -0
  23. checkpoints/000300/training_state/rng_state.safetensors +3 -0
  24. checkpoints/000300/training_state/scheduler_state.json +14 -0
  25. checkpoints/000300/training_state/training_step.json +3 -0
  26. checkpoints/000400/pretrained_model/config.json +85 -0
  27. checkpoints/000400/pretrained_model/model.safetensors +3 -0
  28. checkpoints/000400/pretrained_model/train_config.json +235 -0
  29. checkpoints/000400/training_state/optimizer_param_groups.json +233 -0
  30. checkpoints/000400/training_state/optimizer_state.safetensors +3 -0
  31. checkpoints/000400/training_state/rng_state.safetensors +3 -0
  32. checkpoints/000400/training_state/scheduler_state.json +14 -0
  33. checkpoints/000400/training_state/training_step.json +3 -0
  34. checkpoints/000500/pretrained_model/config.json +85 -0
  35. checkpoints/000500/pretrained_model/model.safetensors +3 -0
  36. checkpoints/000500/pretrained_model/train_config.json +235 -0
  37. checkpoints/000500/training_state/optimizer_param_groups.json +233 -0
  38. checkpoints/000500/training_state/optimizer_state.safetensors +3 -0
  39. checkpoints/000500/training_state/rng_state.safetensors +3 -0
  40. checkpoints/000500/training_state/scheduler_state.json +14 -0
  41. checkpoints/000500/training_state/training_step.json +3 -0
  42. checkpoints/000600/pretrained_model/config.json +85 -0
  43. checkpoints/000600/pretrained_model/model.safetensors +3 -0
  44. checkpoints/000600/pretrained_model/train_config.json +235 -0
  45. checkpoints/000600/training_state/optimizer_param_groups.json +233 -0
  46. checkpoints/000600/training_state/optimizer_state.safetensors +3 -0
  47. checkpoints/000600/training_state/rng_state.safetensors +3 -0
  48. checkpoints/000600/training_state/scheduler_state.json +14 -0
  49. checkpoints/000600/training_state/training_step.json +3 -0
  50. checkpoints/000700/pretrained_model/config.json +85 -0
.gitattributes CHANGED
@@ -33,3 +33,5 @@ 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/latest-run/run-n0hjf8w2.wandb filter=lfs diff=lfs merge=lfs -text
37
+ wandb/run-20250826_023146-n0hjf8w2/run-n0hjf8w2.wandb filter=lfs diff=lfs merge=lfs -text
checkpoints/000100/pretrained_model/config.json ADDED
@@ -0,0 +1,85 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "type": "diffusion",
3
+ "n_obs_steps": 1,
4
+ "normalization_mapping": {
5
+ "VISUAL": "MEAN_STD",
6
+ "STATE": "MIN_MAX",
7
+ "ACTION": "MIN_MAX"
8
+ },
9
+ "relative_actions": false,
10
+ "input_features": {
11
+ "observation.state": {
12
+ "type": "STATE",
13
+ "shape": [
14
+ 8
15
+ ]
16
+ },
17
+ "observation.images.front": {
18
+ "type": "VISUAL",
19
+ "shape": [
20
+ 3,
21
+ 120,
22
+ 212
23
+ ]
24
+ },
25
+ "observation.images.wrist": {
26
+ "type": "VISUAL",
27
+ "shape": [
28
+ 3,
29
+ 120,
30
+ 212
31
+ ]
32
+ }
33
+ },
34
+ "output_features": {
35
+ "action": {
36
+ "type": "ACTION",
37
+ "shape": [
38
+ 8
39
+ ]
40
+ }
41
+ },
42
+ "device": "cuda",
43
+ "use_amp": false,
44
+ "horizon": 64,
45
+ "n_action_steps": 50,
46
+ "drop_n_last_frames": 13,
47
+ "vision_backbone": "resnet18",
48
+ "crop_shape": [
49
+ 120,
50
+ 212
51
+ ],
52
+ "random_rotation_deg": 0.0,
53
+ "pretrained_backbone_weights": null,
54
+ "use_group_norm": true,
55
+ "spatial_softmax_num_keypoints": 32,
56
+ "use_separate_rgb_encoder_per_camera": false,
57
+ "down_dims": [
58
+ 512,
59
+ 1024,
60
+ 2048
61
+ ],
62
+ "kernel_size": 5,
63
+ "n_groups": 8,
64
+ "diffusion_step_embed_dim": 128,
65
+ "use_film_scale_modulation": true,
66
+ "noise_scheduler_type": "DDPM",
67
+ "num_train_timesteps": 100,
68
+ "beta_schedule": "squaredcos_cap_v2",
69
+ "beta_start": 0.0001,
70
+ "beta_end": 0.02,
71
+ "prediction_type": "epsilon",
72
+ "clip_sample": true,
73
+ "clip_sample_range": 1.0,
74
+ "num_inference_steps": 10,
75
+ "do_mask_loss_for_padding": false,
76
+ "optimizer_lr": 0.0001,
77
+ "optimizer_betas": [
78
+ 0.95,
79
+ 0.999
80
+ ],
81
+ "optimizer_eps": 1e-08,
82
+ "optimizer_weight_decay": 1e-06,
83
+ "scheduler_name": "cosine",
84
+ "scheduler_warmup_steps": 500
85
+ }
checkpoints/000100/pretrained_model/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8aaed3da011dd1e9a4499f92c947f3101e84aef4876f547773a83357adbbcfa
3
+ size 1051407792
checkpoints/000100/pretrained_model/train_config.json ADDED
@@ -0,0 +1,235 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset": {
3
+ "repo_id": "black_table_insert_rope_downsampled_v7",
4
+ "root": null,
5
+ "episodes": null,
6
+ "image_transforms": {
7
+ "enable": true,
8
+ "max_num_transforms": 3,
9
+ "random_order": true,
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
+ "perspective": {
62
+ "weight": 1.0,
63
+ "type": "RandomPerspective",
64
+ "kwargs": {
65
+ "distortion_scale": 0.025,
66
+ "p": 1.0
67
+ }
68
+ },
69
+ "rotation": {
70
+ "weight": 1.0,
71
+ "type": "RandomRotation",
72
+ "kwargs": {
73
+ "degrees": [
74
+ -2,
75
+ 2
76
+ ]
77
+ }
78
+ },
79
+ "crop": {
80
+ "weight": 1.0,
81
+ "type": "RandomCrop",
82
+ "kwargs": {
83
+ "size": [
84
+ 110,
85
+ 202
86
+ ]
87
+ }
88
+ }
89
+ },
90
+ "downsample": {
91
+ "resize": {
92
+ "weight": 1.0,
93
+ "type": "Resize",
94
+ "kwargs": {
95
+ "size": [
96
+ 120,
97
+ 212
98
+ ]
99
+ }
100
+ }
101
+ }
102
+ },
103
+ "revision": null,
104
+ "use_imagenet_stats": true,
105
+ "video_backend": "torchcodec"
106
+ },
107
+ "env": null,
108
+ "policy": {
109
+ "type": "diffusion",
110
+ "n_obs_steps": 1,
111
+ "normalization_mapping": {
112
+ "VISUAL": "MEAN_STD",
113
+ "STATE": "MIN_MAX",
114
+ "ACTION": "MIN_MAX"
115
+ },
116
+ "relative_actions": false,
117
+ "input_features": {
118
+ "observation.state": {
119
+ "type": "STATE",
120
+ "shape": [
121
+ 8
122
+ ]
123
+ },
124
+ "observation.images.front": {
125
+ "type": "VISUAL",
126
+ "shape": [
127
+ 3,
128
+ 120,
129
+ 212
130
+ ]
131
+ },
132
+ "observation.images.wrist": {
133
+ "type": "VISUAL",
134
+ "shape": [
135
+ 3,
136
+ 120,
137
+ 212
138
+ ]
139
+ }
140
+ },
141
+ "output_features": {
142
+ "action": {
143
+ "type": "ACTION",
144
+ "shape": [
145
+ 8
146
+ ]
147
+ }
148
+ },
149
+ "device": "cuda",
150
+ "use_amp": false,
151
+ "horizon": 64,
152
+ "n_action_steps": 50,
153
+ "drop_n_last_frames": 13,
154
+ "vision_backbone": "resnet18",
155
+ "crop_shape": [
156
+ 120,
157
+ 212
158
+ ],
159
+ "random_rotation_deg": 0.0,
160
+ "pretrained_backbone_weights": null,
161
+ "use_group_norm": true,
162
+ "spatial_softmax_num_keypoints": 32,
163
+ "use_separate_rgb_encoder_per_camera": false,
164
+ "down_dims": [
165
+ 512,
166
+ 1024,
167
+ 2048
168
+ ],
169
+ "kernel_size": 5,
170
+ "n_groups": 8,
171
+ "diffusion_step_embed_dim": 128,
172
+ "use_film_scale_modulation": true,
173
+ "noise_scheduler_type": "DDPM",
174
+ "num_train_timesteps": 100,
175
+ "beta_schedule": "squaredcos_cap_v2",
176
+ "beta_start": 0.0001,
177
+ "beta_end": 0.02,
178
+ "prediction_type": "epsilon",
179
+ "clip_sample": true,
180
+ "clip_sample_range": 1.0,
181
+ "num_inference_steps": 10,
182
+ "do_mask_loss_for_padding": false,
183
+ "optimizer_lr": 0.0001,
184
+ "optimizer_betas": [
185
+ 0.95,
186
+ 0.999
187
+ ],
188
+ "optimizer_eps": 1e-08,
189
+ "optimizer_weight_decay": 1e-06,
190
+ "scheduler_name": "cosine",
191
+ "scheduler_warmup_steps": 500
192
+ },
193
+ "output_dir": "outputs/train/black_table_insert_rope_downsampled_v7/2025-08-26_02-31-41_diffusion_Te50_abs_ds_1000",
194
+ "job_name": "2025-08-26_02-31-41_diffusion_Te50_abs_ds_1000",
195
+ "resume": false,
196
+ "seed": 100000,
197
+ "num_workers": 4,
198
+ "batch_size": 1024,
199
+ "steps": 5000,
200
+ "eval_freq": 2000,
201
+ "log_freq": 100,
202
+ "save_checkpoint": true,
203
+ "save_freq": 100,
204
+ "use_policy_training_preset": true,
205
+ "optimizer": {
206
+ "type": "adam",
207
+ "lr": 0.0001,
208
+ "weight_decay": 1e-06,
209
+ "grad_clip_norm": 10.0,
210
+ "betas": [
211
+ 0.95,
212
+ 0.999
213
+ ],
214
+ "eps": 1e-08
215
+ },
216
+ "scheduler": {
217
+ "type": "diffuser",
218
+ "num_warmup_steps": 500,
219
+ "name": "cosine"
220
+ },
221
+ "eval": {
222
+ "n_episodes": 50,
223
+ "batch_size": 50,
224
+ "use_async_envs": false
225
+ },
226
+ "wandb": {
227
+ "enable": true,
228
+ "disable_artifact": true,
229
+ "project": "lerobot",
230
+ "entity": null,
231
+ "notes": null,
232
+ "run_id": null,
233
+ "mode": null
234
+ }
235
+ }
checkpoints/000100/training_state/optimizer_param_groups.json ADDED
@@ -0,0 +1,233 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "lr": 2e-05,
4
+ "betas": [
5
+ 0.95,
6
+ 0.999
7
+ ],
8
+ "eps": 1e-08,
9
+ "weight_decay": 1e-06,
10
+ "amsgrad": false,
11
+ "maximize": false,
12
+ "foreach": null,
13
+ "capturable": false,
14
+ "differentiable": false,
15
+ "fused": null,
16
+ "decoupled_weight_decay": false,
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
+ ]
232
+ }
233
+ ]
checkpoints/000100/training_state/optimizer_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b79d7b1968a66da3003aed2118508f7a0d6e1c518fc5f687174fae0a3d4490e9
3
+ size 2102818808
checkpoints/000100/training_state/rng_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2adc758ee68afce7e9d3da943f08fbf815716014ad8fa31dfb8da13863dc668
3
+ size 15708
checkpoints/000100/training_state/scheduler_state.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "base_lrs": [
3
+ 0.0001
4
+ ],
5
+ "last_epoch": 100,
6
+ "_step_count": 101,
7
+ "_get_lr_called_within_step": false,
8
+ "_last_lr": [
9
+ 2e-05
10
+ ],
11
+ "lr_lambdas": [
12
+ null
13
+ ]
14
+ }
checkpoints/000100/training_state/training_step.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "step": 100
3
+ }
checkpoints/000200/pretrained_model/config.json ADDED
@@ -0,0 +1,85 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "type": "diffusion",
3
+ "n_obs_steps": 1,
4
+ "normalization_mapping": {
5
+ "VISUAL": "MEAN_STD",
6
+ "STATE": "MIN_MAX",
7
+ "ACTION": "MIN_MAX"
8
+ },
9
+ "relative_actions": false,
10
+ "input_features": {
11
+ "observation.state": {
12
+ "type": "STATE",
13
+ "shape": [
14
+ 8
15
+ ]
16
+ },
17
+ "observation.images.front": {
18
+ "type": "VISUAL",
19
+ "shape": [
20
+ 3,
21
+ 120,
22
+ 212
23
+ ]
24
+ },
25
+ "observation.images.wrist": {
26
+ "type": "VISUAL",
27
+ "shape": [
28
+ 3,
29
+ 120,
30
+ 212
31
+ ]
32
+ }
33
+ },
34
+ "output_features": {
35
+ "action": {
36
+ "type": "ACTION",
37
+ "shape": [
38
+ 8
39
+ ]
40
+ }
41
+ },
42
+ "device": "cuda",
43
+ "use_amp": false,
44
+ "horizon": 64,
45
+ "n_action_steps": 50,
46
+ "drop_n_last_frames": 13,
47
+ "vision_backbone": "resnet18",
48
+ "crop_shape": [
49
+ 120,
50
+ 212
51
+ ],
52
+ "random_rotation_deg": 0.0,
53
+ "pretrained_backbone_weights": null,
54
+ "use_group_norm": true,
55
+ "spatial_softmax_num_keypoints": 32,
56
+ "use_separate_rgb_encoder_per_camera": false,
57
+ "down_dims": [
58
+ 512,
59
+ 1024,
60
+ 2048
61
+ ],
62
+ "kernel_size": 5,
63
+ "n_groups": 8,
64
+ "diffusion_step_embed_dim": 128,
65
+ "use_film_scale_modulation": true,
66
+ "noise_scheduler_type": "DDPM",
67
+ "num_train_timesteps": 100,
68
+ "beta_schedule": "squaredcos_cap_v2",
69
+ "beta_start": 0.0001,
70
+ "beta_end": 0.02,
71
+ "prediction_type": "epsilon",
72
+ "clip_sample": true,
73
+ "clip_sample_range": 1.0,
74
+ "num_inference_steps": 10,
75
+ "do_mask_loss_for_padding": false,
76
+ "optimizer_lr": 0.0001,
77
+ "optimizer_betas": [
78
+ 0.95,
79
+ 0.999
80
+ ],
81
+ "optimizer_eps": 1e-08,
82
+ "optimizer_weight_decay": 1e-06,
83
+ "scheduler_name": "cosine",
84
+ "scheduler_warmup_steps": 500
85
+ }
checkpoints/000200/pretrained_model/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b843ba2d1dba6d33cef803c308b8abcbd5c508dcc88b1428572d6b8cfa26d063
3
+ size 1051407792
checkpoints/000200/pretrained_model/train_config.json ADDED
@@ -0,0 +1,235 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset": {
3
+ "repo_id": "black_table_insert_rope_downsampled_v7",
4
+ "root": null,
5
+ "episodes": null,
6
+ "image_transforms": {
7
+ "enable": true,
8
+ "max_num_transforms": 3,
9
+ "random_order": true,
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
+ "perspective": {
62
+ "weight": 1.0,
63
+ "type": "RandomPerspective",
64
+ "kwargs": {
65
+ "distortion_scale": 0.025,
66
+ "p": 1.0
67
+ }
68
+ },
69
+ "rotation": {
70
+ "weight": 1.0,
71
+ "type": "RandomRotation",
72
+ "kwargs": {
73
+ "degrees": [
74
+ -2,
75
+ 2
76
+ ]
77
+ }
78
+ },
79
+ "crop": {
80
+ "weight": 1.0,
81
+ "type": "RandomCrop",
82
+ "kwargs": {
83
+ "size": [
84
+ 110,
85
+ 202
86
+ ]
87
+ }
88
+ }
89
+ },
90
+ "downsample": {
91
+ "resize": {
92
+ "weight": 1.0,
93
+ "type": "Resize",
94
+ "kwargs": {
95
+ "size": [
96
+ 120,
97
+ 212
98
+ ]
99
+ }
100
+ }
101
+ }
102
+ },
103
+ "revision": null,
104
+ "use_imagenet_stats": true,
105
+ "video_backend": "torchcodec"
106
+ },
107
+ "env": null,
108
+ "policy": {
109
+ "type": "diffusion",
110
+ "n_obs_steps": 1,
111
+ "normalization_mapping": {
112
+ "VISUAL": "MEAN_STD",
113
+ "STATE": "MIN_MAX",
114
+ "ACTION": "MIN_MAX"
115
+ },
116
+ "relative_actions": false,
117
+ "input_features": {
118
+ "observation.state": {
119
+ "type": "STATE",
120
+ "shape": [
121
+ 8
122
+ ]
123
+ },
124
+ "observation.images.front": {
125
+ "type": "VISUAL",
126
+ "shape": [
127
+ 3,
128
+ 120,
129
+ 212
130
+ ]
131
+ },
132
+ "observation.images.wrist": {
133
+ "type": "VISUAL",
134
+ "shape": [
135
+ 3,
136
+ 120,
137
+ 212
138
+ ]
139
+ }
140
+ },
141
+ "output_features": {
142
+ "action": {
143
+ "type": "ACTION",
144
+ "shape": [
145
+ 8
146
+ ]
147
+ }
148
+ },
149
+ "device": "cuda",
150
+ "use_amp": false,
151
+ "horizon": 64,
152
+ "n_action_steps": 50,
153
+ "drop_n_last_frames": 13,
154
+ "vision_backbone": "resnet18",
155
+ "crop_shape": [
156
+ 120,
157
+ 212
158
+ ],
159
+ "random_rotation_deg": 0.0,
160
+ "pretrained_backbone_weights": null,
161
+ "use_group_norm": true,
162
+ "spatial_softmax_num_keypoints": 32,
163
+ "use_separate_rgb_encoder_per_camera": false,
164
+ "down_dims": [
165
+ 512,
166
+ 1024,
167
+ 2048
168
+ ],
169
+ "kernel_size": 5,
170
+ "n_groups": 8,
171
+ "diffusion_step_embed_dim": 128,
172
+ "use_film_scale_modulation": true,
173
+ "noise_scheduler_type": "DDPM",
174
+ "num_train_timesteps": 100,
175
+ "beta_schedule": "squaredcos_cap_v2",
176
+ "beta_start": 0.0001,
177
+ "beta_end": 0.02,
178
+ "prediction_type": "epsilon",
179
+ "clip_sample": true,
180
+ "clip_sample_range": 1.0,
181
+ "num_inference_steps": 10,
182
+ "do_mask_loss_for_padding": false,
183
+ "optimizer_lr": 0.0001,
184
+ "optimizer_betas": [
185
+ 0.95,
186
+ 0.999
187
+ ],
188
+ "optimizer_eps": 1e-08,
189
+ "optimizer_weight_decay": 1e-06,
190
+ "scheduler_name": "cosine",
191
+ "scheduler_warmup_steps": 500
192
+ },
193
+ "output_dir": "outputs/train/black_table_insert_rope_downsampled_v7/2025-08-26_02-31-41_diffusion_Te50_abs_ds_1000",
194
+ "job_name": "2025-08-26_02-31-41_diffusion_Te50_abs_ds_1000",
195
+ "resume": false,
196
+ "seed": 100000,
197
+ "num_workers": 4,
198
+ "batch_size": 1024,
199
+ "steps": 5000,
200
+ "eval_freq": 2000,
201
+ "log_freq": 100,
202
+ "save_checkpoint": true,
203
+ "save_freq": 100,
204
+ "use_policy_training_preset": true,
205
+ "optimizer": {
206
+ "type": "adam",
207
+ "lr": 0.0001,
208
+ "weight_decay": 1e-06,
209
+ "grad_clip_norm": 10.0,
210
+ "betas": [
211
+ 0.95,
212
+ 0.999
213
+ ],
214
+ "eps": 1e-08
215
+ },
216
+ "scheduler": {
217
+ "type": "diffuser",
218
+ "num_warmup_steps": 500,
219
+ "name": "cosine"
220
+ },
221
+ "eval": {
222
+ "n_episodes": 50,
223
+ "batch_size": 50,
224
+ "use_async_envs": false
225
+ },
226
+ "wandb": {
227
+ "enable": true,
228
+ "disable_artifact": true,
229
+ "project": "lerobot",
230
+ "entity": null,
231
+ "notes": null,
232
+ "run_id": null,
233
+ "mode": null
234
+ }
235
+ }
checkpoints/000200/training_state/optimizer_param_groups.json ADDED
@@ -0,0 +1,233 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "lr": 4e-05,
4
+ "betas": [
5
+ 0.95,
6
+ 0.999
7
+ ],
8
+ "eps": 1e-08,
9
+ "weight_decay": 1e-06,
10
+ "amsgrad": false,
11
+ "maximize": false,
12
+ "foreach": null,
13
+ "capturable": false,
14
+ "differentiable": false,
15
+ "fused": null,
16
+ "decoupled_weight_decay": false,
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
+ ]
232
+ }
233
+ ]
checkpoints/000200/training_state/optimizer_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb01b60ec7988864a05e52f9ae028e082f032db6a97631232c7716186c2b7e7e
3
+ size 2102818808
checkpoints/000200/training_state/rng_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:806eaed0a3a202c65866ebe8e130af8ddbd658e168ecf05719f27818db21a699
3
+ size 15708
checkpoints/000200/training_state/scheduler_state.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "base_lrs": [
3
+ 0.0001
4
+ ],
5
+ "last_epoch": 200,
6
+ "_step_count": 201,
7
+ "_get_lr_called_within_step": false,
8
+ "_last_lr": [
9
+ 4e-05
10
+ ],
11
+ "lr_lambdas": [
12
+ null
13
+ ]
14
+ }
checkpoints/000200/training_state/training_step.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "step": 200
3
+ }
checkpoints/000300/pretrained_model/config.json ADDED
@@ -0,0 +1,85 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "type": "diffusion",
3
+ "n_obs_steps": 1,
4
+ "normalization_mapping": {
5
+ "VISUAL": "MEAN_STD",
6
+ "STATE": "MIN_MAX",
7
+ "ACTION": "MIN_MAX"
8
+ },
9
+ "relative_actions": false,
10
+ "input_features": {
11
+ "observation.state": {
12
+ "type": "STATE",
13
+ "shape": [
14
+ 8
15
+ ]
16
+ },
17
+ "observation.images.front": {
18
+ "type": "VISUAL",
19
+ "shape": [
20
+ 3,
21
+ 120,
22
+ 212
23
+ ]
24
+ },
25
+ "observation.images.wrist": {
26
+ "type": "VISUAL",
27
+ "shape": [
28
+ 3,
29
+ 120,
30
+ 212
31
+ ]
32
+ }
33
+ },
34
+ "output_features": {
35
+ "action": {
36
+ "type": "ACTION",
37
+ "shape": [
38
+ 8
39
+ ]
40
+ }
41
+ },
42
+ "device": "cuda",
43
+ "use_amp": false,
44
+ "horizon": 64,
45
+ "n_action_steps": 50,
46
+ "drop_n_last_frames": 13,
47
+ "vision_backbone": "resnet18",
48
+ "crop_shape": [
49
+ 120,
50
+ 212
51
+ ],
52
+ "random_rotation_deg": 0.0,
53
+ "pretrained_backbone_weights": null,
54
+ "use_group_norm": true,
55
+ "spatial_softmax_num_keypoints": 32,
56
+ "use_separate_rgb_encoder_per_camera": false,
57
+ "down_dims": [
58
+ 512,
59
+ 1024,
60
+ 2048
61
+ ],
62
+ "kernel_size": 5,
63
+ "n_groups": 8,
64
+ "diffusion_step_embed_dim": 128,
65
+ "use_film_scale_modulation": true,
66
+ "noise_scheduler_type": "DDPM",
67
+ "num_train_timesteps": 100,
68
+ "beta_schedule": "squaredcos_cap_v2",
69
+ "beta_start": 0.0001,
70
+ "beta_end": 0.02,
71
+ "prediction_type": "epsilon",
72
+ "clip_sample": true,
73
+ "clip_sample_range": 1.0,
74
+ "num_inference_steps": 10,
75
+ "do_mask_loss_for_padding": false,
76
+ "optimizer_lr": 0.0001,
77
+ "optimizer_betas": [
78
+ 0.95,
79
+ 0.999
80
+ ],
81
+ "optimizer_eps": 1e-08,
82
+ "optimizer_weight_decay": 1e-06,
83
+ "scheduler_name": "cosine",
84
+ "scheduler_warmup_steps": 500
85
+ }
checkpoints/000300/pretrained_model/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:64d33b58955175db83e68c5ad2f84f38ba06a24303957a4e2272a52f67612149
3
+ size 1051407792
checkpoints/000300/pretrained_model/train_config.json ADDED
@@ -0,0 +1,235 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset": {
3
+ "repo_id": "black_table_insert_rope_downsampled_v7",
4
+ "root": null,
5
+ "episodes": null,
6
+ "image_transforms": {
7
+ "enable": true,
8
+ "max_num_transforms": 3,
9
+ "random_order": true,
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
+ "perspective": {
62
+ "weight": 1.0,
63
+ "type": "RandomPerspective",
64
+ "kwargs": {
65
+ "distortion_scale": 0.025,
66
+ "p": 1.0
67
+ }
68
+ },
69
+ "rotation": {
70
+ "weight": 1.0,
71
+ "type": "RandomRotation",
72
+ "kwargs": {
73
+ "degrees": [
74
+ -2,
75
+ 2
76
+ ]
77
+ }
78
+ },
79
+ "crop": {
80
+ "weight": 1.0,
81
+ "type": "RandomCrop",
82
+ "kwargs": {
83
+ "size": [
84
+ 110,
85
+ 202
86
+ ]
87
+ }
88
+ }
89
+ },
90
+ "downsample": {
91
+ "resize": {
92
+ "weight": 1.0,
93
+ "type": "Resize",
94
+ "kwargs": {
95
+ "size": [
96
+ 120,
97
+ 212
98
+ ]
99
+ }
100
+ }
101
+ }
102
+ },
103
+ "revision": null,
104
+ "use_imagenet_stats": true,
105
+ "video_backend": "torchcodec"
106
+ },
107
+ "env": null,
108
+ "policy": {
109
+ "type": "diffusion",
110
+ "n_obs_steps": 1,
111
+ "normalization_mapping": {
112
+ "VISUAL": "MEAN_STD",
113
+ "STATE": "MIN_MAX",
114
+ "ACTION": "MIN_MAX"
115
+ },
116
+ "relative_actions": false,
117
+ "input_features": {
118
+ "observation.state": {
119
+ "type": "STATE",
120
+ "shape": [
121
+ 8
122
+ ]
123
+ },
124
+ "observation.images.front": {
125
+ "type": "VISUAL",
126
+ "shape": [
127
+ 3,
128
+ 120,
129
+ 212
130
+ ]
131
+ },
132
+ "observation.images.wrist": {
133
+ "type": "VISUAL",
134
+ "shape": [
135
+ 3,
136
+ 120,
137
+ 212
138
+ ]
139
+ }
140
+ },
141
+ "output_features": {
142
+ "action": {
143
+ "type": "ACTION",
144
+ "shape": [
145
+ 8
146
+ ]
147
+ }
148
+ },
149
+ "device": "cuda",
150
+ "use_amp": false,
151
+ "horizon": 64,
152
+ "n_action_steps": 50,
153
+ "drop_n_last_frames": 13,
154
+ "vision_backbone": "resnet18",
155
+ "crop_shape": [
156
+ 120,
157
+ 212
158
+ ],
159
+ "random_rotation_deg": 0.0,
160
+ "pretrained_backbone_weights": null,
161
+ "use_group_norm": true,
162
+ "spatial_softmax_num_keypoints": 32,
163
+ "use_separate_rgb_encoder_per_camera": false,
164
+ "down_dims": [
165
+ 512,
166
+ 1024,
167
+ 2048
168
+ ],
169
+ "kernel_size": 5,
170
+ "n_groups": 8,
171
+ "diffusion_step_embed_dim": 128,
172
+ "use_film_scale_modulation": true,
173
+ "noise_scheduler_type": "DDPM",
174
+ "num_train_timesteps": 100,
175
+ "beta_schedule": "squaredcos_cap_v2",
176
+ "beta_start": 0.0001,
177
+ "beta_end": 0.02,
178
+ "prediction_type": "epsilon",
179
+ "clip_sample": true,
180
+ "clip_sample_range": 1.0,
181
+ "num_inference_steps": 10,
182
+ "do_mask_loss_for_padding": false,
183
+ "optimizer_lr": 0.0001,
184
+ "optimizer_betas": [
185
+ 0.95,
186
+ 0.999
187
+ ],
188
+ "optimizer_eps": 1e-08,
189
+ "optimizer_weight_decay": 1e-06,
190
+ "scheduler_name": "cosine",
191
+ "scheduler_warmup_steps": 500
192
+ },
193
+ "output_dir": "outputs/train/black_table_insert_rope_downsampled_v7/2025-08-26_02-31-41_diffusion_Te50_abs_ds_1000",
194
+ "job_name": "2025-08-26_02-31-41_diffusion_Te50_abs_ds_1000",
195
+ "resume": false,
196
+ "seed": 100000,
197
+ "num_workers": 4,
198
+ "batch_size": 1024,
199
+ "steps": 5000,
200
+ "eval_freq": 2000,
201
+ "log_freq": 100,
202
+ "save_checkpoint": true,
203
+ "save_freq": 100,
204
+ "use_policy_training_preset": true,
205
+ "optimizer": {
206
+ "type": "adam",
207
+ "lr": 0.0001,
208
+ "weight_decay": 1e-06,
209
+ "grad_clip_norm": 10.0,
210
+ "betas": [
211
+ 0.95,
212
+ 0.999
213
+ ],
214
+ "eps": 1e-08
215
+ },
216
+ "scheduler": {
217
+ "type": "diffuser",
218
+ "num_warmup_steps": 500,
219
+ "name": "cosine"
220
+ },
221
+ "eval": {
222
+ "n_episodes": 50,
223
+ "batch_size": 50,
224
+ "use_async_envs": false
225
+ },
226
+ "wandb": {
227
+ "enable": true,
228
+ "disable_artifact": true,
229
+ "project": "lerobot",
230
+ "entity": null,
231
+ "notes": null,
232
+ "run_id": null,
233
+ "mode": null
234
+ }
235
+ }
checkpoints/000300/training_state/optimizer_param_groups.json ADDED
@@ -0,0 +1,233 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "lr": 6e-05,
4
+ "betas": [
5
+ 0.95,
6
+ 0.999
7
+ ],
8
+ "eps": 1e-08,
9
+ "weight_decay": 1e-06,
10
+ "amsgrad": false,
11
+ "maximize": false,
12
+ "foreach": null,
13
+ "capturable": false,
14
+ "differentiable": false,
15
+ "fused": null,
16
+ "decoupled_weight_decay": false,
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
+ ]
232
+ }
233
+ ]
checkpoints/000300/training_state/optimizer_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68d6c674bc6e6bc81dfb10f045497da5f10fe0475e566b69f34db4dd451a8e35
3
+ size 2102818808
checkpoints/000300/training_state/rng_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:147bbcf752ab1f24834d2b6f1fe6da79421377e0f0cf7686f6d63d23570cbcda
3
+ size 15708
checkpoints/000300/training_state/scheduler_state.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "base_lrs": [
3
+ 0.0001
4
+ ],
5
+ "last_epoch": 300,
6
+ "_step_count": 301,
7
+ "_get_lr_called_within_step": false,
8
+ "_last_lr": [
9
+ 6e-05
10
+ ],
11
+ "lr_lambdas": [
12
+ null
13
+ ]
14
+ }
checkpoints/000300/training_state/training_step.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "step": 300
3
+ }
checkpoints/000400/pretrained_model/config.json ADDED
@@ -0,0 +1,85 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "type": "diffusion",
3
+ "n_obs_steps": 1,
4
+ "normalization_mapping": {
5
+ "VISUAL": "MEAN_STD",
6
+ "STATE": "MIN_MAX",
7
+ "ACTION": "MIN_MAX"
8
+ },
9
+ "relative_actions": false,
10
+ "input_features": {
11
+ "observation.state": {
12
+ "type": "STATE",
13
+ "shape": [
14
+ 8
15
+ ]
16
+ },
17
+ "observation.images.front": {
18
+ "type": "VISUAL",
19
+ "shape": [
20
+ 3,
21
+ 120,
22
+ 212
23
+ ]
24
+ },
25
+ "observation.images.wrist": {
26
+ "type": "VISUAL",
27
+ "shape": [
28
+ 3,
29
+ 120,
30
+ 212
31
+ ]
32
+ }
33
+ },
34
+ "output_features": {
35
+ "action": {
36
+ "type": "ACTION",
37
+ "shape": [
38
+ 8
39
+ ]
40
+ }
41
+ },
42
+ "device": "cuda",
43
+ "use_amp": false,
44
+ "horizon": 64,
45
+ "n_action_steps": 50,
46
+ "drop_n_last_frames": 13,
47
+ "vision_backbone": "resnet18",
48
+ "crop_shape": [
49
+ 120,
50
+ 212
51
+ ],
52
+ "random_rotation_deg": 0.0,
53
+ "pretrained_backbone_weights": null,
54
+ "use_group_norm": true,
55
+ "spatial_softmax_num_keypoints": 32,
56
+ "use_separate_rgb_encoder_per_camera": false,
57
+ "down_dims": [
58
+ 512,
59
+ 1024,
60
+ 2048
61
+ ],
62
+ "kernel_size": 5,
63
+ "n_groups": 8,
64
+ "diffusion_step_embed_dim": 128,
65
+ "use_film_scale_modulation": true,
66
+ "noise_scheduler_type": "DDPM",
67
+ "num_train_timesteps": 100,
68
+ "beta_schedule": "squaredcos_cap_v2",
69
+ "beta_start": 0.0001,
70
+ "beta_end": 0.02,
71
+ "prediction_type": "epsilon",
72
+ "clip_sample": true,
73
+ "clip_sample_range": 1.0,
74
+ "num_inference_steps": 10,
75
+ "do_mask_loss_for_padding": false,
76
+ "optimizer_lr": 0.0001,
77
+ "optimizer_betas": [
78
+ 0.95,
79
+ 0.999
80
+ ],
81
+ "optimizer_eps": 1e-08,
82
+ "optimizer_weight_decay": 1e-06,
83
+ "scheduler_name": "cosine",
84
+ "scheduler_warmup_steps": 500
85
+ }
checkpoints/000400/pretrained_model/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e76bbab34444bd2d36e04cb94472b39e41361d6ecceda342ebf5206c53c40aa
3
+ size 1051407792
checkpoints/000400/pretrained_model/train_config.json ADDED
@@ -0,0 +1,235 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset": {
3
+ "repo_id": "black_table_insert_rope_downsampled_v7",
4
+ "root": null,
5
+ "episodes": null,
6
+ "image_transforms": {
7
+ "enable": true,
8
+ "max_num_transforms": 3,
9
+ "random_order": true,
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
+ "perspective": {
62
+ "weight": 1.0,
63
+ "type": "RandomPerspective",
64
+ "kwargs": {
65
+ "distortion_scale": 0.025,
66
+ "p": 1.0
67
+ }
68
+ },
69
+ "rotation": {
70
+ "weight": 1.0,
71
+ "type": "RandomRotation",
72
+ "kwargs": {
73
+ "degrees": [
74
+ -2,
75
+ 2
76
+ ]
77
+ }
78
+ },
79
+ "crop": {
80
+ "weight": 1.0,
81
+ "type": "RandomCrop",
82
+ "kwargs": {
83
+ "size": [
84
+ 110,
85
+ 202
86
+ ]
87
+ }
88
+ }
89
+ },
90
+ "downsample": {
91
+ "resize": {
92
+ "weight": 1.0,
93
+ "type": "Resize",
94
+ "kwargs": {
95
+ "size": [
96
+ 120,
97
+ 212
98
+ ]
99
+ }
100
+ }
101
+ }
102
+ },
103
+ "revision": null,
104
+ "use_imagenet_stats": true,
105
+ "video_backend": "torchcodec"
106
+ },
107
+ "env": null,
108
+ "policy": {
109
+ "type": "diffusion",
110
+ "n_obs_steps": 1,
111
+ "normalization_mapping": {
112
+ "VISUAL": "MEAN_STD",
113
+ "STATE": "MIN_MAX",
114
+ "ACTION": "MIN_MAX"
115
+ },
116
+ "relative_actions": false,
117
+ "input_features": {
118
+ "observation.state": {
119
+ "type": "STATE",
120
+ "shape": [
121
+ 8
122
+ ]
123
+ },
124
+ "observation.images.front": {
125
+ "type": "VISUAL",
126
+ "shape": [
127
+ 3,
128
+ 120,
129
+ 212
130
+ ]
131
+ },
132
+ "observation.images.wrist": {
133
+ "type": "VISUAL",
134
+ "shape": [
135
+ 3,
136
+ 120,
137
+ 212
138
+ ]
139
+ }
140
+ },
141
+ "output_features": {
142
+ "action": {
143
+ "type": "ACTION",
144
+ "shape": [
145
+ 8
146
+ ]
147
+ }
148
+ },
149
+ "device": "cuda",
150
+ "use_amp": false,
151
+ "horizon": 64,
152
+ "n_action_steps": 50,
153
+ "drop_n_last_frames": 13,
154
+ "vision_backbone": "resnet18",
155
+ "crop_shape": [
156
+ 120,
157
+ 212
158
+ ],
159
+ "random_rotation_deg": 0.0,
160
+ "pretrained_backbone_weights": null,
161
+ "use_group_norm": true,
162
+ "spatial_softmax_num_keypoints": 32,
163
+ "use_separate_rgb_encoder_per_camera": false,
164
+ "down_dims": [
165
+ 512,
166
+ 1024,
167
+ 2048
168
+ ],
169
+ "kernel_size": 5,
170
+ "n_groups": 8,
171
+ "diffusion_step_embed_dim": 128,
172
+ "use_film_scale_modulation": true,
173
+ "noise_scheduler_type": "DDPM",
174
+ "num_train_timesteps": 100,
175
+ "beta_schedule": "squaredcos_cap_v2",
176
+ "beta_start": 0.0001,
177
+ "beta_end": 0.02,
178
+ "prediction_type": "epsilon",
179
+ "clip_sample": true,
180
+ "clip_sample_range": 1.0,
181
+ "num_inference_steps": 10,
182
+ "do_mask_loss_for_padding": false,
183
+ "optimizer_lr": 0.0001,
184
+ "optimizer_betas": [
185
+ 0.95,
186
+ 0.999
187
+ ],
188
+ "optimizer_eps": 1e-08,
189
+ "optimizer_weight_decay": 1e-06,
190
+ "scheduler_name": "cosine",
191
+ "scheduler_warmup_steps": 500
192
+ },
193
+ "output_dir": "outputs/train/black_table_insert_rope_downsampled_v7/2025-08-26_02-31-41_diffusion_Te50_abs_ds_1000",
194
+ "job_name": "2025-08-26_02-31-41_diffusion_Te50_abs_ds_1000",
195
+ "resume": false,
196
+ "seed": 100000,
197
+ "num_workers": 4,
198
+ "batch_size": 1024,
199
+ "steps": 5000,
200
+ "eval_freq": 2000,
201
+ "log_freq": 100,
202
+ "save_checkpoint": true,
203
+ "save_freq": 100,
204
+ "use_policy_training_preset": true,
205
+ "optimizer": {
206
+ "type": "adam",
207
+ "lr": 0.0001,
208
+ "weight_decay": 1e-06,
209
+ "grad_clip_norm": 10.0,
210
+ "betas": [
211
+ 0.95,
212
+ 0.999
213
+ ],
214
+ "eps": 1e-08
215
+ },
216
+ "scheduler": {
217
+ "type": "diffuser",
218
+ "num_warmup_steps": 500,
219
+ "name": "cosine"
220
+ },
221
+ "eval": {
222
+ "n_episodes": 50,
223
+ "batch_size": 50,
224
+ "use_async_envs": false
225
+ },
226
+ "wandb": {
227
+ "enable": true,
228
+ "disable_artifact": true,
229
+ "project": "lerobot",
230
+ "entity": null,
231
+ "notes": null,
232
+ "run_id": null,
233
+ "mode": null
234
+ }
235
+ }
checkpoints/000400/training_state/optimizer_param_groups.json ADDED
@@ -0,0 +1,233 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "lr": 8e-05,
4
+ "betas": [
5
+ 0.95,
6
+ 0.999
7
+ ],
8
+ "eps": 1e-08,
9
+ "weight_decay": 1e-06,
10
+ "amsgrad": false,
11
+ "maximize": false,
12
+ "foreach": null,
13
+ "capturable": false,
14
+ "differentiable": false,
15
+ "fused": null,
16
+ "decoupled_weight_decay": false,
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
+ ]
232
+ }
233
+ ]
checkpoints/000400/training_state/optimizer_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90c1c08e1618c370762d528f645ffc2cf2236fef3473985b4f1d277a41f077e7
3
+ size 2102818808
checkpoints/000400/training_state/rng_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd2a20d558d1c9ad67c4b2514cd766f312726696dfcec7e54d03d473de680f91
3
+ size 15708
checkpoints/000400/training_state/scheduler_state.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "base_lrs": [
3
+ 0.0001
4
+ ],
5
+ "last_epoch": 400,
6
+ "_step_count": 401,
7
+ "_get_lr_called_within_step": false,
8
+ "_last_lr": [
9
+ 8e-05
10
+ ],
11
+ "lr_lambdas": [
12
+ null
13
+ ]
14
+ }
checkpoints/000400/training_state/training_step.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "step": 400
3
+ }
checkpoints/000500/pretrained_model/config.json ADDED
@@ -0,0 +1,85 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "type": "diffusion",
3
+ "n_obs_steps": 1,
4
+ "normalization_mapping": {
5
+ "VISUAL": "MEAN_STD",
6
+ "STATE": "MIN_MAX",
7
+ "ACTION": "MIN_MAX"
8
+ },
9
+ "relative_actions": false,
10
+ "input_features": {
11
+ "observation.state": {
12
+ "type": "STATE",
13
+ "shape": [
14
+ 8
15
+ ]
16
+ },
17
+ "observation.images.front": {
18
+ "type": "VISUAL",
19
+ "shape": [
20
+ 3,
21
+ 120,
22
+ 212
23
+ ]
24
+ },
25
+ "observation.images.wrist": {
26
+ "type": "VISUAL",
27
+ "shape": [
28
+ 3,
29
+ 120,
30
+ 212
31
+ ]
32
+ }
33
+ },
34
+ "output_features": {
35
+ "action": {
36
+ "type": "ACTION",
37
+ "shape": [
38
+ 8
39
+ ]
40
+ }
41
+ },
42
+ "device": "cuda",
43
+ "use_amp": false,
44
+ "horizon": 64,
45
+ "n_action_steps": 50,
46
+ "drop_n_last_frames": 13,
47
+ "vision_backbone": "resnet18",
48
+ "crop_shape": [
49
+ 120,
50
+ 212
51
+ ],
52
+ "random_rotation_deg": 0.0,
53
+ "pretrained_backbone_weights": null,
54
+ "use_group_norm": true,
55
+ "spatial_softmax_num_keypoints": 32,
56
+ "use_separate_rgb_encoder_per_camera": false,
57
+ "down_dims": [
58
+ 512,
59
+ 1024,
60
+ 2048
61
+ ],
62
+ "kernel_size": 5,
63
+ "n_groups": 8,
64
+ "diffusion_step_embed_dim": 128,
65
+ "use_film_scale_modulation": true,
66
+ "noise_scheduler_type": "DDPM",
67
+ "num_train_timesteps": 100,
68
+ "beta_schedule": "squaredcos_cap_v2",
69
+ "beta_start": 0.0001,
70
+ "beta_end": 0.02,
71
+ "prediction_type": "epsilon",
72
+ "clip_sample": true,
73
+ "clip_sample_range": 1.0,
74
+ "num_inference_steps": 10,
75
+ "do_mask_loss_for_padding": false,
76
+ "optimizer_lr": 0.0001,
77
+ "optimizer_betas": [
78
+ 0.95,
79
+ 0.999
80
+ ],
81
+ "optimizer_eps": 1e-08,
82
+ "optimizer_weight_decay": 1e-06,
83
+ "scheduler_name": "cosine",
84
+ "scheduler_warmup_steps": 500
85
+ }
checkpoints/000500/pretrained_model/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ea341b595e4cbebd82cc2567755a3f07faa3e283598e566ca4039d08196a883
3
+ size 1051407792
checkpoints/000500/pretrained_model/train_config.json ADDED
@@ -0,0 +1,235 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset": {
3
+ "repo_id": "black_table_insert_rope_downsampled_v7",
4
+ "root": null,
5
+ "episodes": null,
6
+ "image_transforms": {
7
+ "enable": true,
8
+ "max_num_transforms": 3,
9
+ "random_order": true,
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
+ "perspective": {
62
+ "weight": 1.0,
63
+ "type": "RandomPerspective",
64
+ "kwargs": {
65
+ "distortion_scale": 0.025,
66
+ "p": 1.0
67
+ }
68
+ },
69
+ "rotation": {
70
+ "weight": 1.0,
71
+ "type": "RandomRotation",
72
+ "kwargs": {
73
+ "degrees": [
74
+ -2,
75
+ 2
76
+ ]
77
+ }
78
+ },
79
+ "crop": {
80
+ "weight": 1.0,
81
+ "type": "RandomCrop",
82
+ "kwargs": {
83
+ "size": [
84
+ 110,
85
+ 202
86
+ ]
87
+ }
88
+ }
89
+ },
90
+ "downsample": {
91
+ "resize": {
92
+ "weight": 1.0,
93
+ "type": "Resize",
94
+ "kwargs": {
95
+ "size": [
96
+ 120,
97
+ 212
98
+ ]
99
+ }
100
+ }
101
+ }
102
+ },
103
+ "revision": null,
104
+ "use_imagenet_stats": true,
105
+ "video_backend": "torchcodec"
106
+ },
107
+ "env": null,
108
+ "policy": {
109
+ "type": "diffusion",
110
+ "n_obs_steps": 1,
111
+ "normalization_mapping": {
112
+ "VISUAL": "MEAN_STD",
113
+ "STATE": "MIN_MAX",
114
+ "ACTION": "MIN_MAX"
115
+ },
116
+ "relative_actions": false,
117
+ "input_features": {
118
+ "observation.state": {
119
+ "type": "STATE",
120
+ "shape": [
121
+ 8
122
+ ]
123
+ },
124
+ "observation.images.front": {
125
+ "type": "VISUAL",
126
+ "shape": [
127
+ 3,
128
+ 120,
129
+ 212
130
+ ]
131
+ },
132
+ "observation.images.wrist": {
133
+ "type": "VISUAL",
134
+ "shape": [
135
+ 3,
136
+ 120,
137
+ 212
138
+ ]
139
+ }
140
+ },
141
+ "output_features": {
142
+ "action": {
143
+ "type": "ACTION",
144
+ "shape": [
145
+ 8
146
+ ]
147
+ }
148
+ },
149
+ "device": "cuda",
150
+ "use_amp": false,
151
+ "horizon": 64,
152
+ "n_action_steps": 50,
153
+ "drop_n_last_frames": 13,
154
+ "vision_backbone": "resnet18",
155
+ "crop_shape": [
156
+ 120,
157
+ 212
158
+ ],
159
+ "random_rotation_deg": 0.0,
160
+ "pretrained_backbone_weights": null,
161
+ "use_group_norm": true,
162
+ "spatial_softmax_num_keypoints": 32,
163
+ "use_separate_rgb_encoder_per_camera": false,
164
+ "down_dims": [
165
+ 512,
166
+ 1024,
167
+ 2048
168
+ ],
169
+ "kernel_size": 5,
170
+ "n_groups": 8,
171
+ "diffusion_step_embed_dim": 128,
172
+ "use_film_scale_modulation": true,
173
+ "noise_scheduler_type": "DDPM",
174
+ "num_train_timesteps": 100,
175
+ "beta_schedule": "squaredcos_cap_v2",
176
+ "beta_start": 0.0001,
177
+ "beta_end": 0.02,
178
+ "prediction_type": "epsilon",
179
+ "clip_sample": true,
180
+ "clip_sample_range": 1.0,
181
+ "num_inference_steps": 10,
182
+ "do_mask_loss_for_padding": false,
183
+ "optimizer_lr": 0.0001,
184
+ "optimizer_betas": [
185
+ 0.95,
186
+ 0.999
187
+ ],
188
+ "optimizer_eps": 1e-08,
189
+ "optimizer_weight_decay": 1e-06,
190
+ "scheduler_name": "cosine",
191
+ "scheduler_warmup_steps": 500
192
+ },
193
+ "output_dir": "outputs/train/black_table_insert_rope_downsampled_v7/2025-08-26_02-31-41_diffusion_Te50_abs_ds_1000",
194
+ "job_name": "2025-08-26_02-31-41_diffusion_Te50_abs_ds_1000",
195
+ "resume": false,
196
+ "seed": 100000,
197
+ "num_workers": 4,
198
+ "batch_size": 1024,
199
+ "steps": 5000,
200
+ "eval_freq": 2000,
201
+ "log_freq": 100,
202
+ "save_checkpoint": true,
203
+ "save_freq": 100,
204
+ "use_policy_training_preset": true,
205
+ "optimizer": {
206
+ "type": "adam",
207
+ "lr": 0.0001,
208
+ "weight_decay": 1e-06,
209
+ "grad_clip_norm": 10.0,
210
+ "betas": [
211
+ 0.95,
212
+ 0.999
213
+ ],
214
+ "eps": 1e-08
215
+ },
216
+ "scheduler": {
217
+ "type": "diffuser",
218
+ "num_warmup_steps": 500,
219
+ "name": "cosine"
220
+ },
221
+ "eval": {
222
+ "n_episodes": 50,
223
+ "batch_size": 50,
224
+ "use_async_envs": false
225
+ },
226
+ "wandb": {
227
+ "enable": true,
228
+ "disable_artifact": true,
229
+ "project": "lerobot",
230
+ "entity": null,
231
+ "notes": null,
232
+ "run_id": null,
233
+ "mode": null
234
+ }
235
+ }
checkpoints/000500/training_state/optimizer_param_groups.json ADDED
@@ -0,0 +1,233 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "lr": 0.0001,
4
+ "betas": [
5
+ 0.95,
6
+ 0.999
7
+ ],
8
+ "eps": 1e-08,
9
+ "weight_decay": 1e-06,
10
+ "amsgrad": false,
11
+ "maximize": false,
12
+ "foreach": null,
13
+ "capturable": false,
14
+ "differentiable": false,
15
+ "fused": null,
16
+ "decoupled_weight_decay": false,
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
+ ]
232
+ }
233
+ ]
checkpoints/000500/training_state/optimizer_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7fad8c614b78f92e506ab135770ec861b14453337c5f72ec502fed4b7f64ca36
3
+ size 2102818808
checkpoints/000500/training_state/rng_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f611f12c82a110f42d764ad9cfc083674dbb6661a7565d13905457992609cd9a
3
+ size 15708
checkpoints/000500/training_state/scheduler_state.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "base_lrs": [
3
+ 0.0001
4
+ ],
5
+ "last_epoch": 500,
6
+ "_step_count": 501,
7
+ "_get_lr_called_within_step": false,
8
+ "_last_lr": [
9
+ 0.0001
10
+ ],
11
+ "lr_lambdas": [
12
+ null
13
+ ]
14
+ }
checkpoints/000500/training_state/training_step.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "step": 500
3
+ }
checkpoints/000600/pretrained_model/config.json ADDED
@@ -0,0 +1,85 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "type": "diffusion",
3
+ "n_obs_steps": 1,
4
+ "normalization_mapping": {
5
+ "VISUAL": "MEAN_STD",
6
+ "STATE": "MIN_MAX",
7
+ "ACTION": "MIN_MAX"
8
+ },
9
+ "relative_actions": false,
10
+ "input_features": {
11
+ "observation.state": {
12
+ "type": "STATE",
13
+ "shape": [
14
+ 8
15
+ ]
16
+ },
17
+ "observation.images.front": {
18
+ "type": "VISUAL",
19
+ "shape": [
20
+ 3,
21
+ 120,
22
+ 212
23
+ ]
24
+ },
25
+ "observation.images.wrist": {
26
+ "type": "VISUAL",
27
+ "shape": [
28
+ 3,
29
+ 120,
30
+ 212
31
+ ]
32
+ }
33
+ },
34
+ "output_features": {
35
+ "action": {
36
+ "type": "ACTION",
37
+ "shape": [
38
+ 8
39
+ ]
40
+ }
41
+ },
42
+ "device": "cuda",
43
+ "use_amp": false,
44
+ "horizon": 64,
45
+ "n_action_steps": 50,
46
+ "drop_n_last_frames": 13,
47
+ "vision_backbone": "resnet18",
48
+ "crop_shape": [
49
+ 120,
50
+ 212
51
+ ],
52
+ "random_rotation_deg": 0.0,
53
+ "pretrained_backbone_weights": null,
54
+ "use_group_norm": true,
55
+ "spatial_softmax_num_keypoints": 32,
56
+ "use_separate_rgb_encoder_per_camera": false,
57
+ "down_dims": [
58
+ 512,
59
+ 1024,
60
+ 2048
61
+ ],
62
+ "kernel_size": 5,
63
+ "n_groups": 8,
64
+ "diffusion_step_embed_dim": 128,
65
+ "use_film_scale_modulation": true,
66
+ "noise_scheduler_type": "DDPM",
67
+ "num_train_timesteps": 100,
68
+ "beta_schedule": "squaredcos_cap_v2",
69
+ "beta_start": 0.0001,
70
+ "beta_end": 0.02,
71
+ "prediction_type": "epsilon",
72
+ "clip_sample": true,
73
+ "clip_sample_range": 1.0,
74
+ "num_inference_steps": 10,
75
+ "do_mask_loss_for_padding": false,
76
+ "optimizer_lr": 0.0001,
77
+ "optimizer_betas": [
78
+ 0.95,
79
+ 0.999
80
+ ],
81
+ "optimizer_eps": 1e-08,
82
+ "optimizer_weight_decay": 1e-06,
83
+ "scheduler_name": "cosine",
84
+ "scheduler_warmup_steps": 500
85
+ }
checkpoints/000600/pretrained_model/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65e7f2755d16f292e851b471c2f37eded9d0eb9adbc47cfb5fc7baa67b43ec1f
3
+ size 1051407792
checkpoints/000600/pretrained_model/train_config.json ADDED
@@ -0,0 +1,235 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset": {
3
+ "repo_id": "black_table_insert_rope_downsampled_v7",
4
+ "root": null,
5
+ "episodes": null,
6
+ "image_transforms": {
7
+ "enable": true,
8
+ "max_num_transforms": 3,
9
+ "random_order": true,
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
+ "perspective": {
62
+ "weight": 1.0,
63
+ "type": "RandomPerspective",
64
+ "kwargs": {
65
+ "distortion_scale": 0.025,
66
+ "p": 1.0
67
+ }
68
+ },
69
+ "rotation": {
70
+ "weight": 1.0,
71
+ "type": "RandomRotation",
72
+ "kwargs": {
73
+ "degrees": [
74
+ -2,
75
+ 2
76
+ ]
77
+ }
78
+ },
79
+ "crop": {
80
+ "weight": 1.0,
81
+ "type": "RandomCrop",
82
+ "kwargs": {
83
+ "size": [
84
+ 110,
85
+ 202
86
+ ]
87
+ }
88
+ }
89
+ },
90
+ "downsample": {
91
+ "resize": {
92
+ "weight": 1.0,
93
+ "type": "Resize",
94
+ "kwargs": {
95
+ "size": [
96
+ 120,
97
+ 212
98
+ ]
99
+ }
100
+ }
101
+ }
102
+ },
103
+ "revision": null,
104
+ "use_imagenet_stats": true,
105
+ "video_backend": "torchcodec"
106
+ },
107
+ "env": null,
108
+ "policy": {
109
+ "type": "diffusion",
110
+ "n_obs_steps": 1,
111
+ "normalization_mapping": {
112
+ "VISUAL": "MEAN_STD",
113
+ "STATE": "MIN_MAX",
114
+ "ACTION": "MIN_MAX"
115
+ },
116
+ "relative_actions": false,
117
+ "input_features": {
118
+ "observation.state": {
119
+ "type": "STATE",
120
+ "shape": [
121
+ 8
122
+ ]
123
+ },
124
+ "observation.images.front": {
125
+ "type": "VISUAL",
126
+ "shape": [
127
+ 3,
128
+ 120,
129
+ 212
130
+ ]
131
+ },
132
+ "observation.images.wrist": {
133
+ "type": "VISUAL",
134
+ "shape": [
135
+ 3,
136
+ 120,
137
+ 212
138
+ ]
139
+ }
140
+ },
141
+ "output_features": {
142
+ "action": {
143
+ "type": "ACTION",
144
+ "shape": [
145
+ 8
146
+ ]
147
+ }
148
+ },
149
+ "device": "cuda",
150
+ "use_amp": false,
151
+ "horizon": 64,
152
+ "n_action_steps": 50,
153
+ "drop_n_last_frames": 13,
154
+ "vision_backbone": "resnet18",
155
+ "crop_shape": [
156
+ 120,
157
+ 212
158
+ ],
159
+ "random_rotation_deg": 0.0,
160
+ "pretrained_backbone_weights": null,
161
+ "use_group_norm": true,
162
+ "spatial_softmax_num_keypoints": 32,
163
+ "use_separate_rgb_encoder_per_camera": false,
164
+ "down_dims": [
165
+ 512,
166
+ 1024,
167
+ 2048
168
+ ],
169
+ "kernel_size": 5,
170
+ "n_groups": 8,
171
+ "diffusion_step_embed_dim": 128,
172
+ "use_film_scale_modulation": true,
173
+ "noise_scheduler_type": "DDPM",
174
+ "num_train_timesteps": 100,
175
+ "beta_schedule": "squaredcos_cap_v2",
176
+ "beta_start": 0.0001,
177
+ "beta_end": 0.02,
178
+ "prediction_type": "epsilon",
179
+ "clip_sample": true,
180
+ "clip_sample_range": 1.0,
181
+ "num_inference_steps": 10,
182
+ "do_mask_loss_for_padding": false,
183
+ "optimizer_lr": 0.0001,
184
+ "optimizer_betas": [
185
+ 0.95,
186
+ 0.999
187
+ ],
188
+ "optimizer_eps": 1e-08,
189
+ "optimizer_weight_decay": 1e-06,
190
+ "scheduler_name": "cosine",
191
+ "scheduler_warmup_steps": 500
192
+ },
193
+ "output_dir": "outputs/train/black_table_insert_rope_downsampled_v7/2025-08-26_02-31-41_diffusion_Te50_abs_ds_1000",
194
+ "job_name": "2025-08-26_02-31-41_diffusion_Te50_abs_ds_1000",
195
+ "resume": false,
196
+ "seed": 100000,
197
+ "num_workers": 4,
198
+ "batch_size": 1024,
199
+ "steps": 5000,
200
+ "eval_freq": 2000,
201
+ "log_freq": 100,
202
+ "save_checkpoint": true,
203
+ "save_freq": 100,
204
+ "use_policy_training_preset": true,
205
+ "optimizer": {
206
+ "type": "adam",
207
+ "lr": 0.0001,
208
+ "weight_decay": 1e-06,
209
+ "grad_clip_norm": 10.0,
210
+ "betas": [
211
+ 0.95,
212
+ 0.999
213
+ ],
214
+ "eps": 1e-08
215
+ },
216
+ "scheduler": {
217
+ "type": "diffuser",
218
+ "num_warmup_steps": 500,
219
+ "name": "cosine"
220
+ },
221
+ "eval": {
222
+ "n_episodes": 50,
223
+ "batch_size": 50,
224
+ "use_async_envs": false
225
+ },
226
+ "wandb": {
227
+ "enable": true,
228
+ "disable_artifact": true,
229
+ "project": "lerobot",
230
+ "entity": null,
231
+ "notes": null,
232
+ "run_id": null,
233
+ "mode": null
234
+ }
235
+ }
checkpoints/000600/training_state/optimizer_param_groups.json ADDED
@@ -0,0 +1,233 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "lr": 9.987820251299122e-05,
4
+ "betas": [
5
+ 0.95,
6
+ 0.999
7
+ ],
8
+ "eps": 1e-08,
9
+ "weight_decay": 1e-06,
10
+ "amsgrad": false,
11
+ "maximize": false,
12
+ "foreach": null,
13
+ "capturable": false,
14
+ "differentiable": false,
15
+ "fused": null,
16
+ "decoupled_weight_decay": false,
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
+ ]
232
+ }
233
+ ]
checkpoints/000600/training_state/optimizer_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:044f56cd5b534eed3d537a3d02879ed966f314b1ab6902b1f4a078d45bf35f46
3
+ size 2102818808
checkpoints/000600/training_state/rng_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:327173e6f68df7fdd6d5e7bb1b32f20c680f54550673f0d069a4fa5bdb597591
3
+ size 15708
checkpoints/000600/training_state/scheduler_state.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "base_lrs": [
3
+ 0.0001
4
+ ],
5
+ "last_epoch": 600,
6
+ "_step_count": 601,
7
+ "_get_lr_called_within_step": false,
8
+ "_last_lr": [
9
+ 9.987820251299122e-05
10
+ ],
11
+ "lr_lambdas": [
12
+ null
13
+ ]
14
+ }
checkpoints/000600/training_state/training_step.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "step": 600
3
+ }
checkpoints/000700/pretrained_model/config.json ADDED
@@ -0,0 +1,85 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "type": "diffusion",
3
+ "n_obs_steps": 1,
4
+ "normalization_mapping": {
5
+ "VISUAL": "MEAN_STD",
6
+ "STATE": "MIN_MAX",
7
+ "ACTION": "MIN_MAX"
8
+ },
9
+ "relative_actions": false,
10
+ "input_features": {
11
+ "observation.state": {
12
+ "type": "STATE",
13
+ "shape": [
14
+ 8
15
+ ]
16
+ },
17
+ "observation.images.front": {
18
+ "type": "VISUAL",
19
+ "shape": [
20
+ 3,
21
+ 120,
22
+ 212
23
+ ]
24
+ },
25
+ "observation.images.wrist": {
26
+ "type": "VISUAL",
27
+ "shape": [
28
+ 3,
29
+ 120,
30
+ 212
31
+ ]
32
+ }
33
+ },
34
+ "output_features": {
35
+ "action": {
36
+ "type": "ACTION",
37
+ "shape": [
38
+ 8
39
+ ]
40
+ }
41
+ },
42
+ "device": "cuda",
43
+ "use_amp": false,
44
+ "horizon": 64,
45
+ "n_action_steps": 50,
46
+ "drop_n_last_frames": 13,
47
+ "vision_backbone": "resnet18",
48
+ "crop_shape": [
49
+ 120,
50
+ 212
51
+ ],
52
+ "random_rotation_deg": 0.0,
53
+ "pretrained_backbone_weights": null,
54
+ "use_group_norm": true,
55
+ "spatial_softmax_num_keypoints": 32,
56
+ "use_separate_rgb_encoder_per_camera": false,
57
+ "down_dims": [
58
+ 512,
59
+ 1024,
60
+ 2048
61
+ ],
62
+ "kernel_size": 5,
63
+ "n_groups": 8,
64
+ "diffusion_step_embed_dim": 128,
65
+ "use_film_scale_modulation": true,
66
+ "noise_scheduler_type": "DDPM",
67
+ "num_train_timesteps": 100,
68
+ "beta_schedule": "squaredcos_cap_v2",
69
+ "beta_start": 0.0001,
70
+ "beta_end": 0.02,
71
+ "prediction_type": "epsilon",
72
+ "clip_sample": true,
73
+ "clip_sample_range": 1.0,
74
+ "num_inference_steps": 10,
75
+ "do_mask_loss_for_padding": false,
76
+ "optimizer_lr": 0.0001,
77
+ "optimizer_betas": [
78
+ 0.95,
79
+ 0.999
80
+ ],
81
+ "optimizer_eps": 1e-08,
82
+ "optimizer_weight_decay": 1e-06,
83
+ "scheduler_name": "cosine",
84
+ "scheduler_warmup_steps": 500
85
+ }