Hugging Face's logo

jadechoghari
/
dot_aloha_sim_100k

Safetensors
Model card Files
xet
Community
jadechoghari HF Staff commited on
Commit
20714ee
·
verified ·
1 Parent(s): 3c950a3

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 +11 -0
  2. train/pusht_aloha_insert/checkpoints/010000/pretrained_model/config.json +126 -0
  3. train/pusht_aloha_insert/checkpoints/010000/pretrained_model/model.safetensors +3 -0
  4. train/pusht_aloha_insert/checkpoints/010000/pretrained_model/train_config.json +272 -0
  5. train/pusht_aloha_insert/checkpoints/010000/training_state/optimizer_param_groups.json +234 -0
  6. train/pusht_aloha_insert/checkpoints/010000/training_state/optimizer_state.safetensors +3 -0
  7. train/pusht_aloha_insert/checkpoints/010000/training_state/rng_state.safetensors +3 -0
  8. train/pusht_aloha_insert/checkpoints/010000/training_state/scheduler_state.json +14 -0
  9. train/pusht_aloha_insert/checkpoints/010000/training_state/training_step.json +3 -0
  10. train/pusht_aloha_insert/checkpoints/020000/pretrained_model/config.json +126 -0
  11. train/pusht_aloha_insert/checkpoints/020000/pretrained_model/model.safetensors +3 -0
  12. train/pusht_aloha_insert/checkpoints/020000/pretrained_model/train_config.json +272 -0
  13. train/pusht_aloha_insert/checkpoints/020000/training_state/optimizer_param_groups.json +234 -0
  14. train/pusht_aloha_insert/checkpoints/020000/training_state/optimizer_state.safetensors +3 -0
  15. train/pusht_aloha_insert/checkpoints/020000/training_state/rng_state.safetensors +3 -0
  16. train/pusht_aloha_insert/checkpoints/020000/training_state/scheduler_state.json +14 -0
  17. train/pusht_aloha_insert/checkpoints/020000/training_state/training_step.json +3 -0
  18. train/pusht_aloha_insert/checkpoints/030000/pretrained_model/config.json +126 -0
  19. train/pusht_aloha_insert/checkpoints/030000/pretrained_model/model.safetensors +3 -0
  20. train/pusht_aloha_insert/checkpoints/030000/pretrained_model/train_config.json +272 -0
  21. train/pusht_aloha_insert/checkpoints/030000/training_state/optimizer_param_groups.json +234 -0
  22. train/pusht_aloha_insert/checkpoints/030000/training_state/optimizer_state.safetensors +3 -0
  23. train/pusht_aloha_insert/checkpoints/030000/training_state/rng_state.safetensors +3 -0
  24. train/pusht_aloha_insert/checkpoints/030000/training_state/scheduler_state.json +14 -0
  25. train/pusht_aloha_insert/checkpoints/030000/training_state/training_step.json +3 -0
  26. train/pusht_aloha_insert/checkpoints/040000/pretrained_model/config.json +126 -0
  27. train/pusht_aloha_insert/checkpoints/040000/pretrained_model/model.safetensors +3 -0
  28. train/pusht_aloha_insert/checkpoints/040000/pretrained_model/train_config.json +272 -0
  29. train/pusht_aloha_insert/checkpoints/040000/training_state/optimizer_param_groups.json +234 -0
  30. train/pusht_aloha_insert/checkpoints/040000/training_state/optimizer_state.safetensors +3 -0
  31. train/pusht_aloha_insert/checkpoints/040000/training_state/rng_state.safetensors +3 -0
  32. train/pusht_aloha_insert/checkpoints/040000/training_state/scheduler_state.json +14 -0
  33. train/pusht_aloha_insert/checkpoints/040000/training_state/training_step.json +3 -0
  34. train/pusht_aloha_insert/checkpoints/050000/pretrained_model/config.json +126 -0
  35. train/pusht_aloha_insert/checkpoints/050000/pretrained_model/model.safetensors +3 -0
  36. train/pusht_aloha_insert/checkpoints/050000/pretrained_model/train_config.json +272 -0
  37. train/pusht_aloha_insert/checkpoints/050000/training_state/optimizer_param_groups.json +234 -0
  38. train/pusht_aloha_insert/checkpoints/050000/training_state/optimizer_state.safetensors +3 -0
  39. train/pusht_aloha_insert/checkpoints/050000/training_state/rng_state.safetensors +3 -0
  40. train/pusht_aloha_insert/checkpoints/050000/training_state/scheduler_state.json +14 -0
  41. train/pusht_aloha_insert/checkpoints/050000/training_state/training_step.json +3 -0
  42. train/pusht_aloha_insert/checkpoints/060000/pretrained_model/config.json +126 -0
  43. train/pusht_aloha_insert/checkpoints/060000/pretrained_model/model.safetensors +3 -0
  44. train/pusht_aloha_insert/checkpoints/060000/pretrained_model/train_config.json +272 -0
  45. train/pusht_aloha_insert/checkpoints/060000/training_state/optimizer_param_groups.json +234 -0
  46. train/pusht_aloha_insert/checkpoints/060000/training_state/optimizer_state.safetensors +3 -0
  47. train/pusht_aloha_insert/checkpoints/060000/training_state/rng_state.safetensors +3 -0
  48. train/pusht_aloha_insert/checkpoints/060000/training_state/scheduler_state.json +14 -0
  49. train/pusht_aloha_insert/checkpoints/060000/training_state/training_step.json +3 -0
  50. train/pusht_aloha_insert/checkpoints/070000/pretrained_model/config.json +126 -0
.gitattributes CHANGED
@@ -33,3 +33,14 @@ 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
+ train/pusht_aloha_insert/eval/videos_step_050000/eval_episode_0.mp4 filter=lfs diff=lfs merge=lfs -text
37
+ train/pusht_aloha_insert/eval/videos_step_050000/eval_episode_1.mp4 filter=lfs diff=lfs merge=lfs -text
38
+ train/pusht_aloha_insert/eval/videos_step_050000/eval_episode_2.mp4 filter=lfs diff=lfs merge=lfs -text
39
+ train/pusht_aloha_insert/eval/videos_step_050000/eval_episode_3.mp4 filter=lfs diff=lfs merge=lfs -text
40
+ train/pusht_aloha_insert/eval/videos_step_100000/eval_episode_0.mp4 filter=lfs diff=lfs merge=lfs -text
41
+ train/pusht_aloha_insert/eval/videos_step_100000/eval_episode_1.mp4 filter=lfs diff=lfs merge=lfs -text
42
+ train/pusht_aloha_insert/eval/videos_step_100000/eval_episode_2.mp4 filter=lfs diff=lfs merge=lfs -text
43
+ train/pusht_aloha_insert/eval/videos_step_100000/eval_episode_3.mp4 filter=lfs diff=lfs merge=lfs -text
44
+ train/pusht_aloha_insert/wandb/run-20250402_123201-i3t53n32/files/media/videos/eval/video_100000_53021abade0e8ca19824.mp4 filter=lfs diff=lfs merge=lfs -text
45
+ train/pusht_aloha_insert/wandb/run-20250402_123201-i3t53n32/files/media/videos/eval/video_50000_9fd910b23e2b29763685.mp4 filter=lfs diff=lfs merge=lfs -text
46
+ train/pusht_aloha_insert/wandb/run-20250402_123201-i3t53n32/run-i3t53n32.wandb filter=lfs diff=lfs merge=lfs -text
train/pusht_aloha_insert/checkpoints/010000/pretrained_model/config.json ADDED
@@ -0,0 +1,126 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "type": "dot",
3
+ "n_obs_steps": 3,
4
+ "normalization_mapping": {
5
+ "VISUAL": "MEAN_STD",
6
+ "STATE": "MIN_MAX",
7
+ "ENV": "MIN_MAX",
8
+ "ACTION": "MIN_MAX"
9
+ },
10
+ "input_features": {
11
+ "observation.images.top": {
12
+ "type": "VISUAL",
13
+ "shape": [
14
+ 3,
15
+ 480,
16
+ 640
17
+ ]
18
+ },
19
+ "observation.state": {
20
+ "type": "STATE",
21
+ "shape": [
22
+ 14
23
+ ]
24
+ }
25
+ },
26
+ "output_features": {
27
+ "action": {
28
+ "type": "ACTION",
29
+ "shape": [
30
+ 14
31
+ ]
32
+ }
33
+ },
34
+ "device": "cuda",
35
+ "use_amp": false,
36
+ "train_horizon": 150,
37
+ "inference_horizon": 100,
38
+ "lookback_obs_steps": 30,
39
+ "lookback_aug": 5,
40
+ "override_dataset_stats": false,
41
+ "new_dataset_stats": {
42
+ "action": {
43
+ "max": [
44
+ 512.0,
45
+ 512.0
46
+ ],
47
+ "min": [
48
+ 0.0,
49
+ 0.0
50
+ ]
51
+ },
52
+ "observation.environment_state": {
53
+ "max": [
54
+ 512.0,
55
+ 512.0,
56
+ 512.0,
57
+ 512.0,
58
+ 512.0,
59
+ 512.0,
60
+ 512.0,
61
+ 512.0,
62
+ 512.0,
63
+ 512.0,
64
+ 512.0,
65
+ 512.0,
66
+ 512.0,
67
+ 512.0,
68
+ 512.0,
69
+ 512.0
70
+ ],
71
+ "min": [
72
+ 0.0,
73
+ 0.0,
74
+ 0.0,
75
+ 0.0,
76
+ 0.0,
77
+ 0.0,
78
+ 0.0,
79
+ 0.0,
80
+ 0.0,
81
+ 0.0,
82
+ 0.0,
83
+ 0.0,
84
+ 0.0,
85
+ 0.0,
86
+ 0.0,
87
+ 0.0
88
+ ]
89
+ },
90
+ "observation.state": {
91
+ "max": [
92
+ 512.0,
93
+ 512.0
94
+ ],
95
+ "min": [
96
+ 0.0,
97
+ 0.0
98
+ ]
99
+ }
100
+ },
101
+ "vision_backbone": "resnet18",
102
+ "pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
103
+ "pre_norm": true,
104
+ "lora_rank": 20,
105
+ "merge_lora": false,
106
+ "dim_model": 128,
107
+ "n_heads": 8,
108
+ "dim_feedforward": 512,
109
+ "n_decoder_layers": 8,
110
+ "rescale_shape": [
111
+ 480,
112
+ 640
113
+ ],
114
+ "crop_scale": 0.8,
115
+ "state_noise": 0.01,
116
+ "noise_decay": 0.999995,
117
+ "dropout": 0.1,
118
+ "alpha": 0.98,
119
+ "train_alpha": 0.99,
120
+ "predict_every_n": 1,
121
+ "return_every_n": 1,
122
+ "optimizer_lr": 3e-05,
123
+ "optimizer_min_lr": 1e-05,
124
+ "optimizer_lr_cycle_steps": 100000,
125
+ "optimizer_weight_decay": 1e-05
126
+ }
train/pusht_aloha_insert/checkpoints/010000/pretrained_model/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76686e109f20a1acd8c8d1b8b6c9856caa06321732bf5c0d303aa89ccb76ece3
3
+ size 56555664
train/pusht_aloha_insert/checkpoints/010000/pretrained_model/train_config.json ADDED
@@ -0,0 +1,272 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset": {
3
+ "repo_id": "lerobot/aloha_sim_insertion_human",
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": "torchcodec"
66
+ },
67
+ "env": {
68
+ "type": "aloha",
69
+ "task": "AlohaInsertion-v0",
70
+ "fps": 50,
71
+ "features": {
72
+ "action": {
73
+ "type": "ACTION",
74
+ "shape": [
75
+ 14
76
+ ]
77
+ },
78
+ "agent_pos": {
79
+ "type": "STATE",
80
+ "shape": [
81
+ 14
82
+ ]
83
+ },
84
+ "pixels/top": {
85
+ "type": "VISUAL",
86
+ "shape": [
87
+ 480,
88
+ 640,
89
+ 3
90
+ ]
91
+ }
92
+ },
93
+ "features_map": {
94
+ "action": "action",
95
+ "agent_pos": "observation.state",
96
+ "top": "observation.image.top",
97
+ "pixels/top": "observation.images.top"
98
+ },
99
+ "episode_length": 500,
100
+ "obs_type": "pixels_agent_pos",
101
+ "render_mode": "rgb_array"
102
+ },
103
+ "policy": {
104
+ "type": "dot",
105
+ "n_obs_steps": 3,
106
+ "normalization_mapping": {
107
+ "VISUAL": "MEAN_STD",
108
+ "STATE": "MIN_MAX",
109
+ "ENV": "MIN_MAX",
110
+ "ACTION": "MIN_MAX"
111
+ },
112
+ "input_features": {
113
+ "observation.images.top": {
114
+ "type": "VISUAL",
115
+ "shape": [
116
+ 3,
117
+ 480,
118
+ 640
119
+ ]
120
+ },
121
+ "observation.state": {
122
+ "type": "STATE",
123
+ "shape": [
124
+ 14
125
+ ]
126
+ }
127
+ },
128
+ "output_features": {
129
+ "action": {
130
+ "type": "ACTION",
131
+ "shape": [
132
+ 14
133
+ ]
134
+ }
135
+ },
136
+ "device": "cuda",
137
+ "use_amp": false,
138
+ "train_horizon": 150,
139
+ "inference_horizon": 100,
140
+ "lookback_obs_steps": 30,
141
+ "lookback_aug": 5,
142
+ "override_dataset_stats": false,
143
+ "new_dataset_stats": {
144
+ "action": {
145
+ "max": [
146
+ 512.0,
147
+ 512.0
148
+ ],
149
+ "min": [
150
+ 0.0,
151
+ 0.0
152
+ ]
153
+ },
154
+ "observation.environment_state": {
155
+ "max": [
156
+ 512.0,
157
+ 512.0,
158
+ 512.0,
159
+ 512.0,
160
+ 512.0,
161
+ 512.0,
162
+ 512.0,
163
+ 512.0,
164
+ 512.0,
165
+ 512.0,
166
+ 512.0,
167
+ 512.0,
168
+ 512.0,
169
+ 512.0,
170
+ 512.0,
171
+ 512.0
172
+ ],
173
+ "min": [
174
+ 0.0,
175
+ 0.0,
176
+ 0.0,
177
+ 0.0,
178
+ 0.0,
179
+ 0.0,
180
+ 0.0,
181
+ 0.0,
182
+ 0.0,
183
+ 0.0,
184
+ 0.0,
185
+ 0.0,
186
+ 0.0,
187
+ 0.0,
188
+ 0.0,
189
+ 0.0
190
+ ]
191
+ },
192
+ "observation.state": {
193
+ "max": [
194
+ 512.0,
195
+ 512.0
196
+ ],
197
+ "min": [
198
+ 0.0,
199
+ 0.0
200
+ ]
201
+ }
202
+ },
203
+ "vision_backbone": "resnet18",
204
+ "pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
205
+ "pre_norm": true,
206
+ "lora_rank": 20,
207
+ "merge_lora": false,
208
+ "dim_model": 128,
209
+ "n_heads": 8,
210
+ "dim_feedforward": 512,
211
+ "n_decoder_layers": 8,
212
+ "rescale_shape": [
213
+ 480,
214
+ 640
215
+ ],
216
+ "crop_scale": 0.8,
217
+ "state_noise": 0.01,
218
+ "noise_decay": 0.999995,
219
+ "dropout": 0.1,
220
+ "alpha": 0.98,
221
+ "train_alpha": 0.99,
222
+ "predict_every_n": 1,
223
+ "return_every_n": 1,
224
+ "optimizer_lr": 3e-05,
225
+ "optimizer_min_lr": 1e-05,
226
+ "optimizer_lr_cycle_steps": 100000,
227
+ "optimizer_weight_decay": 1e-05
228
+ },
229
+ "output_dir": "outputs/train/pusht_aloha_insert",
230
+ "job_name": "aloha_dot",
231
+ "resume": false,
232
+ "seed": 100000,
233
+ "num_workers": 20,
234
+ "batch_size": 8,
235
+ "steps": 100000,
236
+ "eval_freq": 50000,
237
+ "log_freq": 1000,
238
+ "save_checkpoint": true,
239
+ "save_freq": 10000,
240
+ "use_policy_training_preset": true,
241
+ "optimizer": {
242
+ "type": "adamw",
243
+ "lr": 3e-05,
244
+ "weight_decay": 1e-05,
245
+ "grad_clip_norm": 10.0,
246
+ "betas": [
247
+ 0.9,
248
+ 0.999
249
+ ],
250
+ "eps": 1e-08
251
+ },
252
+ "scheduler": {
253
+ "type": "cosine_annealing",
254
+ "num_warmup_steps": 0,
255
+ "min_lr": 1e-05,
256
+ "T_max": 100000
257
+ },
258
+ "eval": {
259
+ "n_episodes": 50,
260
+ "batch_size": 50,
261
+ "use_async_envs": false
262
+ },
263
+ "wandb": {
264
+ "enable": true,
265
+ "disable_artifact": false,
266
+ "project": "aloha_insertion",
267
+ "entity": null,
268
+ "notes": null,
269
+ "run_id": null,
270
+ "mode": null
271
+ }
272
+ }
train/pusht_aloha_insert/checkpoints/010000/training_state/optimizer_param_groups.json ADDED
@@ -0,0 +1,234 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "lr": 2.951056516296821e-05,
4
+ "betas": [
5
+ 0.9,
6
+ 0.999
7
+ ],
8
+ "eps": 1e-08,
9
+ "weight_decay": 1e-05,
10
+ "amsgrad": false,
11
+ "foreach": null,
12
+ "maximize": false,
13
+ "capturable": false,
14
+ "differentiable": false,
15
+ "fused": null,
16
+ "initial_lr": 3e-05,
17
+ "params": [
18
+ 0,
19
+ 1,
20
+ 2,
21
+ 3,
22
+ 4,
23
+ 5,
24
+ 6,
25
+ 7,
26
+ 8,
27
+ 9,
28
+ 10,
29
+ 11,
30
+ 12,
31
+ 13,
32
+ 14,
33
+ 15,
34
+ 16,
35
+ 17,
36
+ 18,
37
+ 19,
38
+ 20,
39
+ 21,
40
+ 22,
41
+ 23,
42
+ 24,
43
+ 25,
44
+ 26,
45
+ 27,
46
+ 28,
47
+ 29,
48
+ 30,
49
+ 31,
50
+ 32,
51
+ 33,
52
+ 34,
53
+ 35,
54
+ 36,
55
+ 37,
56
+ 38,
57
+ 39,
58
+ 40,
59
+ 41,
60
+ 42,
61
+ 43,
62
+ 44,
63
+ 45,
64
+ 46,
65
+ 47,
66
+ 48,
67
+ 49,
68
+ 50,
69
+ 51,
70
+ 52,
71
+ 53,
72
+ 54,
73
+ 55,
74
+ 56,
75
+ 57,
76
+ 58,
77
+ 59,
78
+ 60,
79
+ 61,
80
+ 62,
81
+ 63,
82
+ 64,
83
+ 65,
84
+ 66,
85
+ 67,
86
+ 68,
87
+ 69,
88
+ 70,
89
+ 71,
90
+ 72,
91
+ 73,
92
+ 74,
93
+ 75,
94
+ 76,
95
+ 77,
96
+ 78,
97
+ 79,
98
+ 80,
99
+ 81,
100
+ 82,
101
+ 83,
102
+ 84,
103
+ 85,
104
+ 86,
105
+ 87,
106
+ 88,
107
+ 89,
108
+ 90,
109
+ 91,
110
+ 92,
111
+ 93,
112
+ 94,
113
+ 95,
114
+ 96,
115
+ 97,
116
+ 98,
117
+ 99,
118
+ 100,
119
+ 101,
120
+ 102,
121
+ 103,
122
+ 104,
123
+ 105,
124
+ 106,
125
+ 107,
126
+ 108,
127
+ 109,
128
+ 110,
129
+ 111,
130
+ 112,
131
+ 113,
132
+ 114,
133
+ 115,
134
+ 116,
135
+ 117,
136
+ 118,
137
+ 119,
138
+ 120,
139
+ 121,
140
+ 122,
141
+ 123,
142
+ 124,
143
+ 125,
144
+ 126,
145
+ 127,
146
+ 128,
147
+ 129,
148
+ 130,
149
+ 131,
150
+ 132,
151
+ 133,
152
+ 134,
153
+ 135,
154
+ 136,
155
+ 137,
156
+ 138,
157
+ 139,
158
+ 140,
159
+ 141,
160
+ 142,
161
+ 143,
162
+ 144,
163
+ 145,
164
+ 146,
165
+ 147,
166
+ 148,
167
+ 149,
168
+ 150,
169
+ 151,
170
+ 152,
171
+ 153,
172
+ 154,
173
+ 155,
174
+ 156,
175
+ 157,
176
+ 158,
177
+ 159,
178
+ 160,
179
+ 161,
180
+ 162,
181
+ 163,
182
+ 164,
183
+ 165,
184
+ 166,
185
+ 167,
186
+ 168,
187
+ 169,
188
+ 170,
189
+ 171,
190
+ 172,
191
+ 173,
192
+ 174,
193
+ 175,
194
+ 176,
195
+ 177,
196
+ 178,
197
+ 179,
198
+ 180,
199
+ 181,
200
+ 182,
201
+ 183,
202
+ 184,
203
+ 185,
204
+ 186,
205
+ 187,
206
+ 188,
207
+ 189,
208
+ 190,
209
+ 191,
210
+ 192,
211
+ 193,
212
+ 194,
213
+ 195,
214
+ 196,
215
+ 197,
216
+ 198,
217
+ 199,
218
+ 200,
219
+ 201,
220
+ 202,
221
+ 203,
222
+ 204,
223
+ 205,
224
+ 206,
225
+ 207,
226
+ 208,
227
+ 209,
228
+ 210,
229
+ 211,
230
+ 212,
231
+ 213
232
+ ]
233
+ }
234
+ ]
train/pusht_aloha_insert/checkpoints/010000/training_state/optimizer_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:705aa265d468816940e7b1ef04d3ffce316014d74c0ae1c8edf3723278a18190
3
+ size 23294304
train/pusht_aloha_insert/checkpoints/010000/training_state/rng_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c75fd12afbd2dfacc0c02da5f4b77c03662465e1f73c247b3a385760a8a582b
3
+ size 15708
train/pusht_aloha_insert/checkpoints/010000/training_state/scheduler_state.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "T_max": 100000,
3
+ "eta_min": 1e-05,
4
+ "base_lrs": [
5
+ 3e-05
6
+ ],
7
+ "last_epoch": 10000,
8
+ "verbose": false,
9
+ "_step_count": 10001,
10
+ "_get_lr_called_within_step": false,
11
+ "_last_lr": [
12
+ 2.951056516296821e-05
13
+ ]
14
+ }
train/pusht_aloha_insert/checkpoints/010000/training_state/training_step.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "step": 10000
3
+ }
train/pusht_aloha_insert/checkpoints/020000/pretrained_model/config.json ADDED
@@ -0,0 +1,126 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "type": "dot",
3
+ "n_obs_steps": 3,
4
+ "normalization_mapping": {
5
+ "VISUAL": "MEAN_STD",
6
+ "STATE": "MIN_MAX",
7
+ "ENV": "MIN_MAX",
8
+ "ACTION": "MIN_MAX"
9
+ },
10
+ "input_features": {
11
+ "observation.images.top": {
12
+ "type": "VISUAL",
13
+ "shape": [
14
+ 3,
15
+ 480,
16
+ 640
17
+ ]
18
+ },
19
+ "observation.state": {
20
+ "type": "STATE",
21
+ "shape": [
22
+ 14
23
+ ]
24
+ }
25
+ },
26
+ "output_features": {
27
+ "action": {
28
+ "type": "ACTION",
29
+ "shape": [
30
+ 14
31
+ ]
32
+ }
33
+ },
34
+ "device": "cuda",
35
+ "use_amp": false,
36
+ "train_horizon": 150,
37
+ "inference_horizon": 100,
38
+ "lookback_obs_steps": 30,
39
+ "lookback_aug": 5,
40
+ "override_dataset_stats": false,
41
+ "new_dataset_stats": {
42
+ "action": {
43
+ "max": [
44
+ 512.0,
45
+ 512.0
46
+ ],
47
+ "min": [
48
+ 0.0,
49
+ 0.0
50
+ ]
51
+ },
52
+ "observation.environment_state": {
53
+ "max": [
54
+ 512.0,
55
+ 512.0,
56
+ 512.0,
57
+ 512.0,
58
+ 512.0,
59
+ 512.0,
60
+ 512.0,
61
+ 512.0,
62
+ 512.0,
63
+ 512.0,
64
+ 512.0,
65
+ 512.0,
66
+ 512.0,
67
+ 512.0,
68
+ 512.0,
69
+ 512.0
70
+ ],
71
+ "min": [
72
+ 0.0,
73
+ 0.0,
74
+ 0.0,
75
+ 0.0,
76
+ 0.0,
77
+ 0.0,
78
+ 0.0,
79
+ 0.0,
80
+ 0.0,
81
+ 0.0,
82
+ 0.0,
83
+ 0.0,
84
+ 0.0,
85
+ 0.0,
86
+ 0.0,
87
+ 0.0
88
+ ]
89
+ },
90
+ "observation.state": {
91
+ "max": [
92
+ 512.0,
93
+ 512.0
94
+ ],
95
+ "min": [
96
+ 0.0,
97
+ 0.0
98
+ ]
99
+ }
100
+ },
101
+ "vision_backbone": "resnet18",
102
+ "pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
103
+ "pre_norm": true,
104
+ "lora_rank": 20,
105
+ "merge_lora": false,
106
+ "dim_model": 128,
107
+ "n_heads": 8,
108
+ "dim_feedforward": 512,
109
+ "n_decoder_layers": 8,
110
+ "rescale_shape": [
111
+ 480,
112
+ 640
113
+ ],
114
+ "crop_scale": 0.8,
115
+ "state_noise": 0.01,
116
+ "noise_decay": 0.999995,
117
+ "dropout": 0.1,
118
+ "alpha": 0.98,
119
+ "train_alpha": 0.99,
120
+ "predict_every_n": 1,
121
+ "return_every_n": 1,
122
+ "optimizer_lr": 3e-05,
123
+ "optimizer_min_lr": 1e-05,
124
+ "optimizer_lr_cycle_steps": 100000,
125
+ "optimizer_weight_decay": 1e-05
126
+ }
train/pusht_aloha_insert/checkpoints/020000/pretrained_model/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf51634d8edba7efa99c29a083dc0e7ab1222ffcbe406143c2dc04a567716dd9
3
+ size 56555664
train/pusht_aloha_insert/checkpoints/020000/pretrained_model/train_config.json ADDED
@@ -0,0 +1,272 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset": {
3
+ "repo_id": "lerobot/aloha_sim_insertion_human",
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": "torchcodec"
66
+ },
67
+ "env": {
68
+ "type": "aloha",
69
+ "task": "AlohaInsertion-v0",
70
+ "fps": 50,
71
+ "features": {
72
+ "action": {
73
+ "type": "ACTION",
74
+ "shape": [
75
+ 14
76
+ ]
77
+ },
78
+ "agent_pos": {
79
+ "type": "STATE",
80
+ "shape": [
81
+ 14
82
+ ]
83
+ },
84
+ "pixels/top": {
85
+ "type": "VISUAL",
86
+ "shape": [
87
+ 480,
88
+ 640,
89
+ 3
90
+ ]
91
+ }
92
+ },
93
+ "features_map": {
94
+ "action": "action",
95
+ "agent_pos": "observation.state",
96
+ "top": "observation.image.top",
97
+ "pixels/top": "observation.images.top"
98
+ },
99
+ "episode_length": 500,
100
+ "obs_type": "pixels_agent_pos",
101
+ "render_mode": "rgb_array"
102
+ },
103
+ "policy": {
104
+ "type": "dot",
105
+ "n_obs_steps": 3,
106
+ "normalization_mapping": {
107
+ "VISUAL": "MEAN_STD",
108
+ "STATE": "MIN_MAX",
109
+ "ENV": "MIN_MAX",
110
+ "ACTION": "MIN_MAX"
111
+ },
112
+ "input_features": {
113
+ "observation.images.top": {
114
+ "type": "VISUAL",
115
+ "shape": [
116
+ 3,
117
+ 480,
118
+ 640
119
+ ]
120
+ },
121
+ "observation.state": {
122
+ "type": "STATE",
123
+ "shape": [
124
+ 14
125
+ ]
126
+ }
127
+ },
128
+ "output_features": {
129
+ "action": {
130
+ "type": "ACTION",
131
+ "shape": [
132
+ 14
133
+ ]
134
+ }
135
+ },
136
+ "device": "cuda",
137
+ "use_amp": false,
138
+ "train_horizon": 150,
139
+ "inference_horizon": 100,
140
+ "lookback_obs_steps": 30,
141
+ "lookback_aug": 5,
142
+ "override_dataset_stats": false,
143
+ "new_dataset_stats": {
144
+ "action": {
145
+ "max": [
146
+ 512.0,
147
+ 512.0
148
+ ],
149
+ "min": [
150
+ 0.0,
151
+ 0.0
152
+ ]
153
+ },
154
+ "observation.environment_state": {
155
+ "max": [
156
+ 512.0,
157
+ 512.0,
158
+ 512.0,
159
+ 512.0,
160
+ 512.0,
161
+ 512.0,
162
+ 512.0,
163
+ 512.0,
164
+ 512.0,
165
+ 512.0,
166
+ 512.0,
167
+ 512.0,
168
+ 512.0,
169
+ 512.0,
170
+ 512.0,
171
+ 512.0
172
+ ],
173
+ "min": [
174
+ 0.0,
175
+ 0.0,
176
+ 0.0,
177
+ 0.0,
178
+ 0.0,
179
+ 0.0,
180
+ 0.0,
181
+ 0.0,
182
+ 0.0,
183
+ 0.0,
184
+ 0.0,
185
+ 0.0,
186
+ 0.0,
187
+ 0.0,
188
+ 0.0,
189
+ 0.0
190
+ ]
191
+ },
192
+ "observation.state": {
193
+ "max": [
194
+ 512.0,
195
+ 512.0
196
+ ],
197
+ "min": [
198
+ 0.0,
199
+ 0.0
200
+ ]
201
+ }
202
+ },
203
+ "vision_backbone": "resnet18",
204
+ "pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
205
+ "pre_norm": true,
206
+ "lora_rank": 20,
207
+ "merge_lora": false,
208
+ "dim_model": 128,
209
+ "n_heads": 8,
210
+ "dim_feedforward": 512,
211
+ "n_decoder_layers": 8,
212
+ "rescale_shape": [
213
+ 480,
214
+ 640
215
+ ],
216
+ "crop_scale": 0.8,
217
+ "state_noise": 0.01,
218
+ "noise_decay": 0.999995,
219
+ "dropout": 0.1,
220
+ "alpha": 0.98,
221
+ "train_alpha": 0.99,
222
+ "predict_every_n": 1,
223
+ "return_every_n": 1,
224
+ "optimizer_lr": 3e-05,
225
+ "optimizer_min_lr": 1e-05,
226
+ "optimizer_lr_cycle_steps": 100000,
227
+ "optimizer_weight_decay": 1e-05
228
+ },
229
+ "output_dir": "outputs/train/pusht_aloha_insert",
230
+ "job_name": "aloha_dot",
231
+ "resume": false,
232
+ "seed": 100000,
233
+ "num_workers": 20,
234
+ "batch_size": 8,
235
+ "steps": 100000,
236
+ "eval_freq": 50000,
237
+ "log_freq": 1000,
238
+ "save_checkpoint": true,
239
+ "save_freq": 10000,
240
+ "use_policy_training_preset": true,
241
+ "optimizer": {
242
+ "type": "adamw",
243
+ "lr": 3e-05,
244
+ "weight_decay": 1e-05,
245
+ "grad_clip_norm": 10.0,
246
+ "betas": [
247
+ 0.9,
248
+ 0.999
249
+ ],
250
+ "eps": 1e-08
251
+ },
252
+ "scheduler": {
253
+ "type": "cosine_annealing",
254
+ "num_warmup_steps": 0,
255
+ "min_lr": 1e-05,
256
+ "T_max": 100000
257
+ },
258
+ "eval": {
259
+ "n_episodes": 50,
260
+ "batch_size": 50,
261
+ "use_async_envs": false
262
+ },
263
+ "wandb": {
264
+ "enable": true,
265
+ "disable_artifact": false,
266
+ "project": "aloha_insertion",
267
+ "entity": null,
268
+ "notes": null,
269
+ "run_id": null,
270
+ "mode": null
271
+ }
272
+ }
train/pusht_aloha_insert/checkpoints/020000/training_state/optimizer_param_groups.json ADDED
@@ -0,0 +1,234 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "lr": 2.8090169943781097e-05,
4
+ "betas": [
5
+ 0.9,
6
+ 0.999
7
+ ],
8
+ "eps": 1e-08,
9
+ "weight_decay": 1e-05,
10
+ "amsgrad": false,
11
+ "foreach": null,
12
+ "maximize": false,
13
+ "capturable": false,
14
+ "differentiable": false,
15
+ "fused": null,
16
+ "initial_lr": 3e-05,
17
+ "params": [
18
+ 0,
19
+ 1,
20
+ 2,
21
+ 3,
22
+ 4,
23
+ 5,
24
+ 6,
25
+ 7,
26
+ 8,
27
+ 9,
28
+ 10,
29
+ 11,
30
+ 12,
31
+ 13,
32
+ 14,
33
+ 15,
34
+ 16,
35
+ 17,
36
+ 18,
37
+ 19,
38
+ 20,
39
+ 21,
40
+ 22,
41
+ 23,
42
+ 24,
43
+ 25,
44
+ 26,
45
+ 27,
46
+ 28,
47
+ 29,
48
+ 30,
49
+ 31,
50
+ 32,
51
+ 33,
52
+ 34,
53
+ 35,
54
+ 36,
55
+ 37,
56
+ 38,
57
+ 39,
58
+ 40,
59
+ 41,
60
+ 42,
61
+ 43,
62
+ 44,
63
+ 45,
64
+ 46,
65
+ 47,
66
+ 48,
67
+ 49,
68
+ 50,
69
+ 51,
70
+ 52,
71
+ 53,
72
+ 54,
73
+ 55,
74
+ 56,
75
+ 57,
76
+ 58,
77
+ 59,
78
+ 60,
79
+ 61,
80
+ 62,
81
+ 63,
82
+ 64,
83
+ 65,
84
+ 66,
85
+ 67,
86
+ 68,
87
+ 69,
88
+ 70,
89
+ 71,
90
+ 72,
91
+ 73,
92
+ 74,
93
+ 75,
94
+ 76,
95
+ 77,
96
+ 78,
97
+ 79,
98
+ 80,
99
+ 81,
100
+ 82,
101
+ 83,
102
+ 84,
103
+ 85,
104
+ 86,
105
+ 87,
106
+ 88,
107
+ 89,
108
+ 90,
109
+ 91,
110
+ 92,
111
+ 93,
112
+ 94,
113
+ 95,
114
+ 96,
115
+ 97,
116
+ 98,
117
+ 99,
118
+ 100,
119
+ 101,
120
+ 102,
121
+ 103,
122
+ 104,
123
+ 105,
124
+ 106,
125
+ 107,
126
+ 108,
127
+ 109,
128
+ 110,
129
+ 111,
130
+ 112,
131
+ 113,
132
+ 114,
133
+ 115,
134
+ 116,
135
+ 117,
136
+ 118,
137
+ 119,
138
+ 120,
139
+ 121,
140
+ 122,
141
+ 123,
142
+ 124,
143
+ 125,
144
+ 126,
145
+ 127,
146
+ 128,
147
+ 129,
148
+ 130,
149
+ 131,
150
+ 132,
151
+ 133,
152
+ 134,
153
+ 135,
154
+ 136,
155
+ 137,
156
+ 138,
157
+ 139,
158
+ 140,
159
+ 141,
160
+ 142,
161
+ 143,
162
+ 144,
163
+ 145,
164
+ 146,
165
+ 147,
166
+ 148,
167
+ 149,
168
+ 150,
169
+ 151,
170
+ 152,
171
+ 153,
172
+ 154,
173
+ 155,
174
+ 156,
175
+ 157,
176
+ 158,
177
+ 159,
178
+ 160,
179
+ 161,
180
+ 162,
181
+ 163,
182
+ 164,
183
+ 165,
184
+ 166,
185
+ 167,
186
+ 168,
187
+ 169,
188
+ 170,
189
+ 171,
190
+ 172,
191
+ 173,
192
+ 174,
193
+ 175,
194
+ 176,
195
+ 177,
196
+ 178,
197
+ 179,
198
+ 180,
199
+ 181,
200
+ 182,
201
+ 183,
202
+ 184,
203
+ 185,
204
+ 186,
205
+ 187,
206
+ 188,
207
+ 189,
208
+ 190,
209
+ 191,
210
+ 192,
211
+ 193,
212
+ 194,
213
+ 195,
214
+ 196,
215
+ 197,
216
+ 198,
217
+ 199,
218
+ 200,
219
+ 201,
220
+ 202,
221
+ 203,
222
+ 204,
223
+ 205,
224
+ 206,
225
+ 207,
226
+ 208,
227
+ 209,
228
+ 210,
229
+ 211,
230
+ 212,
231
+ 213
232
+ ]
233
+ }
234
+ ]
train/pusht_aloha_insert/checkpoints/020000/training_state/optimizer_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1574816ab4518808d264e1a81a099120559cc5cef5f9255e486a4c1f19942aa8
3
+ size 23294304
train/pusht_aloha_insert/checkpoints/020000/training_state/rng_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0bb41188bfa6a3f277ac5c3f4836663725c244a4d08404dc13c129e524756103
3
+ size 15708
train/pusht_aloha_insert/checkpoints/020000/training_state/scheduler_state.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "T_max": 100000,
3
+ "eta_min": 1e-05,
4
+ "base_lrs": [
5
+ 3e-05
6
+ ],
7
+ "last_epoch": 20000,
8
+ "verbose": false,
9
+ "_step_count": 20001,
10
+ "_get_lr_called_within_step": false,
11
+ "_last_lr": [
12
+ 2.8090169943781097e-05
13
+ ]
14
+ }
train/pusht_aloha_insert/checkpoints/020000/training_state/training_step.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "step": 20000
3
+ }
train/pusht_aloha_insert/checkpoints/030000/pretrained_model/config.json ADDED
@@ -0,0 +1,126 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "type": "dot",
3
+ "n_obs_steps": 3,
4
+ "normalization_mapping": {
5
+ "VISUAL": "MEAN_STD",
6
+ "STATE": "MIN_MAX",
7
+ "ENV": "MIN_MAX",
8
+ "ACTION": "MIN_MAX"
9
+ },
10
+ "input_features": {
11
+ "observation.images.top": {
12
+ "type": "VISUAL",
13
+ "shape": [
14
+ 3,
15
+ 480,
16
+ 640
17
+ ]
18
+ },
19
+ "observation.state": {
20
+ "type": "STATE",
21
+ "shape": [
22
+ 14
23
+ ]
24
+ }
25
+ },
26
+ "output_features": {
27
+ "action": {
28
+ "type": "ACTION",
29
+ "shape": [
30
+ 14
31
+ ]
32
+ }
33
+ },
34
+ "device": "cuda",
35
+ "use_amp": false,
36
+ "train_horizon": 150,
37
+ "inference_horizon": 100,
38
+ "lookback_obs_steps": 30,
39
+ "lookback_aug": 5,
40
+ "override_dataset_stats": false,
41
+ "new_dataset_stats": {
42
+ "action": {
43
+ "max": [
44
+ 512.0,
45
+ 512.0
46
+ ],
47
+ "min": [
48
+ 0.0,
49
+ 0.0
50
+ ]
51
+ },
52
+ "observation.environment_state": {
53
+ "max": [
54
+ 512.0,
55
+ 512.0,
56
+ 512.0,
57
+ 512.0,
58
+ 512.0,
59
+ 512.0,
60
+ 512.0,
61
+ 512.0,
62
+ 512.0,
63
+ 512.0,
64
+ 512.0,
65
+ 512.0,
66
+ 512.0,
67
+ 512.0,
68
+ 512.0,
69
+ 512.0
70
+ ],
71
+ "min": [
72
+ 0.0,
73
+ 0.0,
74
+ 0.0,
75
+ 0.0,
76
+ 0.0,
77
+ 0.0,
78
+ 0.0,
79
+ 0.0,
80
+ 0.0,
81
+ 0.0,
82
+ 0.0,
83
+ 0.0,
84
+ 0.0,
85
+ 0.0,
86
+ 0.0,
87
+ 0.0
88
+ ]
89
+ },
90
+ "observation.state": {
91
+ "max": [
92
+ 512.0,
93
+ 512.0
94
+ ],
95
+ "min": [
96
+ 0.0,
97
+ 0.0
98
+ ]
99
+ }
100
+ },
101
+ "vision_backbone": "resnet18",
102
+ "pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
103
+ "pre_norm": true,
104
+ "lora_rank": 20,
105
+ "merge_lora": false,
106
+ "dim_model": 128,
107
+ "n_heads": 8,
108
+ "dim_feedforward": 512,
109
+ "n_decoder_layers": 8,
110
+ "rescale_shape": [
111
+ 480,
112
+ 640
113
+ ],
114
+ "crop_scale": 0.8,
115
+ "state_noise": 0.01,
116
+ "noise_decay": 0.999995,
117
+ "dropout": 0.1,
118
+ "alpha": 0.98,
119
+ "train_alpha": 0.99,
120
+ "predict_every_n": 1,
121
+ "return_every_n": 1,
122
+ "optimizer_lr": 3e-05,
123
+ "optimizer_min_lr": 1e-05,
124
+ "optimizer_lr_cycle_steps": 100000,
125
+ "optimizer_weight_decay": 1e-05
126
+ }
train/pusht_aloha_insert/checkpoints/030000/pretrained_model/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:567daf258482dadc9ef7ad39d7ce5694328d8c1e7e981ada33e3a037f672d71c
3
+ size 56555664
train/pusht_aloha_insert/checkpoints/030000/pretrained_model/train_config.json ADDED
@@ -0,0 +1,272 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset": {
3
+ "repo_id": "lerobot/aloha_sim_insertion_human",
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": "torchcodec"
66
+ },
67
+ "env": {
68
+ "type": "aloha",
69
+ "task": "AlohaInsertion-v0",
70
+ "fps": 50,
71
+ "features": {
72
+ "action": {
73
+ "type": "ACTION",
74
+ "shape": [
75
+ 14
76
+ ]
77
+ },
78
+ "agent_pos": {
79
+ "type": "STATE",
80
+ "shape": [
81
+ 14
82
+ ]
83
+ },
84
+ "pixels/top": {
85
+ "type": "VISUAL",
86
+ "shape": [
87
+ 480,
88
+ 640,
89
+ 3
90
+ ]
91
+ }
92
+ },
93
+ "features_map": {
94
+ "action": "action",
95
+ "agent_pos": "observation.state",
96
+ "top": "observation.image.top",
97
+ "pixels/top": "observation.images.top"
98
+ },
99
+ "episode_length": 500,
100
+ "obs_type": "pixels_agent_pos",
101
+ "render_mode": "rgb_array"
102
+ },
103
+ "policy": {
104
+ "type": "dot",
105
+ "n_obs_steps": 3,
106
+ "normalization_mapping": {
107
+ "VISUAL": "MEAN_STD",
108
+ "STATE": "MIN_MAX",
109
+ "ENV": "MIN_MAX",
110
+ "ACTION": "MIN_MAX"
111
+ },
112
+ "input_features": {
113
+ "observation.images.top": {
114
+ "type": "VISUAL",
115
+ "shape": [
116
+ 3,
117
+ 480,
118
+ 640
119
+ ]
120
+ },
121
+ "observation.state": {
122
+ "type": "STATE",
123
+ "shape": [
124
+ 14
125
+ ]
126
+ }
127
+ },
128
+ "output_features": {
129
+ "action": {
130
+ "type": "ACTION",
131
+ "shape": [
132
+ 14
133
+ ]
134
+ }
135
+ },
136
+ "device": "cuda",
137
+ "use_amp": false,
138
+ "train_horizon": 150,
139
+ "inference_horizon": 100,
140
+ "lookback_obs_steps": 30,
141
+ "lookback_aug": 5,
142
+ "override_dataset_stats": false,
143
+ "new_dataset_stats": {
144
+ "action": {
145
+ "max": [
146
+ 512.0,
147
+ 512.0
148
+ ],
149
+ "min": [
150
+ 0.0,
151
+ 0.0
152
+ ]
153
+ },
154
+ "observation.environment_state": {
155
+ "max": [
156
+ 512.0,
157
+ 512.0,
158
+ 512.0,
159
+ 512.0,
160
+ 512.0,
161
+ 512.0,
162
+ 512.0,
163
+ 512.0,
164
+ 512.0,
165
+ 512.0,
166
+ 512.0,
167
+ 512.0,
168
+ 512.0,
169
+ 512.0,
170
+ 512.0,
171
+ 512.0
172
+ ],
173
+ "min": [
174
+ 0.0,
175
+ 0.0,
176
+ 0.0,
177
+ 0.0,
178
+ 0.0,
179
+ 0.0,
180
+ 0.0,
181
+ 0.0,
182
+ 0.0,
183
+ 0.0,
184
+ 0.0,
185
+ 0.0,
186
+ 0.0,
187
+ 0.0,
188
+ 0.0,
189
+ 0.0
190
+ ]
191
+ },
192
+ "observation.state": {
193
+ "max": [
194
+ 512.0,
195
+ 512.0
196
+ ],
197
+ "min": [
198
+ 0.0,
199
+ 0.0
200
+ ]
201
+ }
202
+ },
203
+ "vision_backbone": "resnet18",
204
+ "pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
205
+ "pre_norm": true,
206
+ "lora_rank": 20,
207
+ "merge_lora": false,
208
+ "dim_model": 128,
209
+ "n_heads": 8,
210
+ "dim_feedforward": 512,
211
+ "n_decoder_layers": 8,
212
+ "rescale_shape": [
213
+ 480,
214
+ 640
215
+ ],
216
+ "crop_scale": 0.8,
217
+ "state_noise": 0.01,
218
+ "noise_decay": 0.999995,
219
+ "dropout": 0.1,
220
+ "alpha": 0.98,
221
+ "train_alpha": 0.99,
222
+ "predict_every_n": 1,
223
+ "return_every_n": 1,
224
+ "optimizer_lr": 3e-05,
225
+ "optimizer_min_lr": 1e-05,
226
+ "optimizer_lr_cycle_steps": 100000,
227
+ "optimizer_weight_decay": 1e-05
228
+ },
229
+ "output_dir": "outputs/train/pusht_aloha_insert",
230
+ "job_name": "aloha_dot",
231
+ "resume": false,
232
+ "seed": 100000,
233
+ "num_workers": 20,
234
+ "batch_size": 8,
235
+ "steps": 100000,
236
+ "eval_freq": 50000,
237
+ "log_freq": 1000,
238
+ "save_checkpoint": true,
239
+ "save_freq": 10000,
240
+ "use_policy_training_preset": true,
241
+ "optimizer": {
242
+ "type": "adamw",
243
+ "lr": 3e-05,
244
+ "weight_decay": 1e-05,
245
+ "grad_clip_norm": 10.0,
246
+ "betas": [
247
+ 0.9,
248
+ 0.999
249
+ ],
250
+ "eps": 1e-08
251
+ },
252
+ "scheduler": {
253
+ "type": "cosine_annealing",
254
+ "num_warmup_steps": 0,
255
+ "min_lr": 1e-05,
256
+ "T_max": 100000
257
+ },
258
+ "eval": {
259
+ "n_episodes": 50,
260
+ "batch_size": 50,
261
+ "use_async_envs": false
262
+ },
263
+ "wandb": {
264
+ "enable": true,
265
+ "disable_artifact": false,
266
+ "project": "aloha_insertion",
267
+ "entity": null,
268
+ "notes": null,
269
+ "run_id": null,
270
+ "mode": null
271
+ }
272
+ }
train/pusht_aloha_insert/checkpoints/030000/training_state/optimizer_param_groups.json ADDED
@@ -0,0 +1,234 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "lr": 2.5877852522968503e-05,
4
+ "betas": [
5
+ 0.9,
6
+ 0.999
7
+ ],
8
+ "eps": 1e-08,
9
+ "weight_decay": 1e-05,
10
+ "amsgrad": false,
11
+ "foreach": null,
12
+ "maximize": false,
13
+ "capturable": false,
14
+ "differentiable": false,
15
+ "fused": null,
16
+ "initial_lr": 3e-05,
17
+ "params": [
18
+ 0,
19
+ 1,
20
+ 2,
21
+ 3,
22
+ 4,
23
+ 5,
24
+ 6,
25
+ 7,
26
+ 8,
27
+ 9,
28
+ 10,
29
+ 11,
30
+ 12,
31
+ 13,
32
+ 14,
33
+ 15,
34
+ 16,
35
+ 17,
36
+ 18,
37
+ 19,
38
+ 20,
39
+ 21,
40
+ 22,
41
+ 23,
42
+ 24,
43
+ 25,
44
+ 26,
45
+ 27,
46
+ 28,
47
+ 29,
48
+ 30,
49
+ 31,
50
+ 32,
51
+ 33,
52
+ 34,
53
+ 35,
54
+ 36,
55
+ 37,
56
+ 38,
57
+ 39,
58
+ 40,
59
+ 41,
60
+ 42,
61
+ 43,
62
+ 44,
63
+ 45,
64
+ 46,
65
+ 47,
66
+ 48,
67
+ 49,
68
+ 50,
69
+ 51,
70
+ 52,
71
+ 53,
72
+ 54,
73
+ 55,
74
+ 56,
75
+ 57,
76
+ 58,
77
+ 59,
78
+ 60,
79
+ 61,
80
+ 62,
81
+ 63,
82
+ 64,
83
+ 65,
84
+ 66,
85
+ 67,
86
+ 68,
87
+ 69,
88
+ 70,
89
+ 71,
90
+ 72,
91
+ 73,
92
+ 74,
93
+ 75,
94
+ 76,
95
+ 77,
96
+ 78,
97
+ 79,
98
+ 80,
99
+ 81,
100
+ 82,
101
+ 83,
102
+ 84,
103
+ 85,
104
+ 86,
105
+ 87,
106
+ 88,
107
+ 89,
108
+ 90,
109
+ 91,
110
+ 92,
111
+ 93,
112
+ 94,
113
+ 95,
114
+ 96,
115
+ 97,
116
+ 98,
117
+ 99,
118
+ 100,
119
+ 101,
120
+ 102,
121
+ 103,
122
+ 104,
123
+ 105,
124
+ 106,
125
+ 107,
126
+ 108,
127
+ 109,
128
+ 110,
129
+ 111,
130
+ 112,
131
+ 113,
132
+ 114,
133
+ 115,
134
+ 116,
135
+ 117,
136
+ 118,
137
+ 119,
138
+ 120,
139
+ 121,
140
+ 122,
141
+ 123,
142
+ 124,
143
+ 125,
144
+ 126,
145
+ 127,
146
+ 128,
147
+ 129,
148
+ 130,
149
+ 131,
150
+ 132,
151
+ 133,
152
+ 134,
153
+ 135,
154
+ 136,
155
+ 137,
156
+ 138,
157
+ 139,
158
+ 140,
159
+ 141,
160
+ 142,
161
+ 143,
162
+ 144,
163
+ 145,
164
+ 146,
165
+ 147,
166
+ 148,
167
+ 149,
168
+ 150,
169
+ 151,
170
+ 152,
171
+ 153,
172
+ 154,
173
+ 155,
174
+ 156,
175
+ 157,
176
+ 158,
177
+ 159,
178
+ 160,
179
+ 161,
180
+ 162,
181
+ 163,
182
+ 164,
183
+ 165,
184
+ 166,
185
+ 167,
186
+ 168,
187
+ 169,
188
+ 170,
189
+ 171,
190
+ 172,
191
+ 173,
192
+ 174,
193
+ 175,
194
+ 176,
195
+ 177,
196
+ 178,
197
+ 179,
198
+ 180,
199
+ 181,
200
+ 182,
201
+ 183,
202
+ 184,
203
+ 185,
204
+ 186,
205
+ 187,
206
+ 188,
207
+ 189,
208
+ 190,
209
+ 191,
210
+ 192,
211
+ 193,
212
+ 194,
213
+ 195,
214
+ 196,
215
+ 197,
216
+ 198,
217
+ 199,
218
+ 200,
219
+ 201,
220
+ 202,
221
+ 203,
222
+ 204,
223
+ 205,
224
+ 206,
225
+ 207,
226
+ 208,
227
+ 209,
228
+ 210,
229
+ 211,
230
+ 212,
231
+ 213
232
+ ]
233
+ }
234
+ ]
train/pusht_aloha_insert/checkpoints/030000/training_state/optimizer_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c38d4fe6471d7bf1a81f46938dc7f98bcdec17cafb325b6f6b5802c5a8af761
3
+ size 23294304
train/pusht_aloha_insert/checkpoints/030000/training_state/rng_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4eca69ecc53c011a5735e391802f340b9fd466e5d1062f4bae11b98d228e917
3
+ size 15708
train/pusht_aloha_insert/checkpoints/030000/training_state/scheduler_state.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "T_max": 100000,
3
+ "eta_min": 1e-05,
4
+ "base_lrs": [
5
+ 3e-05
6
+ ],
7
+ "last_epoch": 30000,
8
+ "verbose": false,
9
+ "_step_count": 30001,
10
+ "_get_lr_called_within_step": false,
11
+ "_last_lr": [
12
+ 2.5877852522968503e-05
13
+ ]
14
+ }
train/pusht_aloha_insert/checkpoints/030000/training_state/training_step.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "step": 30000
3
+ }
train/pusht_aloha_insert/checkpoints/040000/pretrained_model/config.json ADDED
@@ -0,0 +1,126 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "type": "dot",
3
+ "n_obs_steps": 3,
4
+ "normalization_mapping": {
5
+ "VISUAL": "MEAN_STD",
6
+ "STATE": "MIN_MAX",
7
+ "ENV": "MIN_MAX",
8
+ "ACTION": "MIN_MAX"
9
+ },
10
+ "input_features": {
11
+ "observation.images.top": {
12
+ "type": "VISUAL",
13
+ "shape": [
14
+ 3,
15
+ 480,
16
+ 640
17
+ ]
18
+ },
19
+ "observation.state": {
20
+ "type": "STATE",
21
+ "shape": [
22
+ 14
23
+ ]
24
+ }
25
+ },
26
+ "output_features": {
27
+ "action": {
28
+ "type": "ACTION",
29
+ "shape": [
30
+ 14
31
+ ]
32
+ }
33
+ },
34
+ "device": "cuda",
35
+ "use_amp": false,
36
+ "train_horizon": 150,
37
+ "inference_horizon": 100,
38
+ "lookback_obs_steps": 30,
39
+ "lookback_aug": 5,
40
+ "override_dataset_stats": false,
41
+ "new_dataset_stats": {
42
+ "action": {
43
+ "max": [
44
+ 512.0,
45
+ 512.0
46
+ ],
47
+ "min": [
48
+ 0.0,
49
+ 0.0
50
+ ]
51
+ },
52
+ "observation.environment_state": {
53
+ "max": [
54
+ 512.0,
55
+ 512.0,
56
+ 512.0,
57
+ 512.0,
58
+ 512.0,
59
+ 512.0,
60
+ 512.0,
61
+ 512.0,
62
+ 512.0,
63
+ 512.0,
64
+ 512.0,
65
+ 512.0,
66
+ 512.0,
67
+ 512.0,
68
+ 512.0,
69
+ 512.0
70
+ ],
71
+ "min": [
72
+ 0.0,
73
+ 0.0,
74
+ 0.0,
75
+ 0.0,
76
+ 0.0,
77
+ 0.0,
78
+ 0.0,
79
+ 0.0,
80
+ 0.0,
81
+ 0.0,
82
+ 0.0,
83
+ 0.0,
84
+ 0.0,
85
+ 0.0,
86
+ 0.0,
87
+ 0.0
88
+ ]
89
+ },
90
+ "observation.state": {
91
+ "max": [
92
+ 512.0,
93
+ 512.0
94
+ ],
95
+ "min": [
96
+ 0.0,
97
+ 0.0
98
+ ]
99
+ }
100
+ },
101
+ "vision_backbone": "resnet18",
102
+ "pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
103
+ "pre_norm": true,
104
+ "lora_rank": 20,
105
+ "merge_lora": false,
106
+ "dim_model": 128,
107
+ "n_heads": 8,
108
+ "dim_feedforward": 512,
109
+ "n_decoder_layers": 8,
110
+ "rescale_shape": [
111
+ 480,
112
+ 640
113
+ ],
114
+ "crop_scale": 0.8,
115
+ "state_noise": 0.01,
116
+ "noise_decay": 0.999995,
117
+ "dropout": 0.1,
118
+ "alpha": 0.98,
119
+ "train_alpha": 0.99,
120
+ "predict_every_n": 1,
121
+ "return_every_n": 1,
122
+ "optimizer_lr": 3e-05,
123
+ "optimizer_min_lr": 1e-05,
124
+ "optimizer_lr_cycle_steps": 100000,
125
+ "optimizer_weight_decay": 1e-05
126
+ }
train/pusht_aloha_insert/checkpoints/040000/pretrained_model/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:641c525c06195d4d6b3ed8416048c723cb161a87bbafd97e9cdf1329a017564b
3
+ size 56555664
train/pusht_aloha_insert/checkpoints/040000/pretrained_model/train_config.json ADDED
@@ -0,0 +1,272 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset": {
3
+ "repo_id": "lerobot/aloha_sim_insertion_human",
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": "torchcodec"
66
+ },
67
+ "env": {
68
+ "type": "aloha",
69
+ "task": "AlohaInsertion-v0",
70
+ "fps": 50,
71
+ "features": {
72
+ "action": {
73
+ "type": "ACTION",
74
+ "shape": [
75
+ 14
76
+ ]
77
+ },
78
+ "agent_pos": {
79
+ "type": "STATE",
80
+ "shape": [
81
+ 14
82
+ ]
83
+ },
84
+ "pixels/top": {
85
+ "type": "VISUAL",
86
+ "shape": [
87
+ 480,
88
+ 640,
89
+ 3
90
+ ]
91
+ }
92
+ },
93
+ "features_map": {
94
+ "action": "action",
95
+ "agent_pos": "observation.state",
96
+ "top": "observation.image.top",
97
+ "pixels/top": "observation.images.top"
98
+ },
99
+ "episode_length": 500,
100
+ "obs_type": "pixels_agent_pos",
101
+ "render_mode": "rgb_array"
102
+ },
103
+ "policy": {
104
+ "type": "dot",
105
+ "n_obs_steps": 3,
106
+ "normalization_mapping": {
107
+ "VISUAL": "MEAN_STD",
108
+ "STATE": "MIN_MAX",
109
+ "ENV": "MIN_MAX",
110
+ "ACTION": "MIN_MAX"
111
+ },
112
+ "input_features": {
113
+ "observation.images.top": {
114
+ "type": "VISUAL",
115
+ "shape": [
116
+ 3,
117
+ 480,
118
+ 640
119
+ ]
120
+ },
121
+ "observation.state": {
122
+ "type": "STATE",
123
+ "shape": [
124
+ 14
125
+ ]
126
+ }
127
+ },
128
+ "output_features": {
129
+ "action": {
130
+ "type": "ACTION",
131
+ "shape": [
132
+ 14
133
+ ]
134
+ }
135
+ },
136
+ "device": "cuda",
137
+ "use_amp": false,
138
+ "train_horizon": 150,
139
+ "inference_horizon": 100,
140
+ "lookback_obs_steps": 30,
141
+ "lookback_aug": 5,
142
+ "override_dataset_stats": false,
143
+ "new_dataset_stats": {
144
+ "action": {
145
+ "max": [
146
+ 512.0,
147
+ 512.0
148
+ ],
149
+ "min": [
150
+ 0.0,
151
+ 0.0
152
+ ]
153
+ },
154
+ "observation.environment_state": {
155
+ "max": [
156
+ 512.0,
157
+ 512.0,
158
+ 512.0,
159
+ 512.0,
160
+ 512.0,
161
+ 512.0,
162
+ 512.0,
163
+ 512.0,
164
+ 512.0,
165
+ 512.0,
166
+ 512.0,
167
+ 512.0,
168
+ 512.0,
169
+ 512.0,
170
+ 512.0,
171
+ 512.0
172
+ ],
173
+ "min": [
174
+ 0.0,
175
+ 0.0,
176
+ 0.0,
177
+ 0.0,
178
+ 0.0,
179
+ 0.0,
180
+ 0.0,
181
+ 0.0,
182
+ 0.0,
183
+ 0.0,
184
+ 0.0,
185
+ 0.0,
186
+ 0.0,
187
+ 0.0,
188
+ 0.0,
189
+ 0.0
190
+ ]
191
+ },
192
+ "observation.state": {
193
+ "max": [
194
+ 512.0,
195
+ 512.0
196
+ ],
197
+ "min": [
198
+ 0.0,
199
+ 0.0
200
+ ]
201
+ }
202
+ },
203
+ "vision_backbone": "resnet18",
204
+ "pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
205
+ "pre_norm": true,
206
+ "lora_rank": 20,
207
+ "merge_lora": false,
208
+ "dim_model": 128,
209
+ "n_heads": 8,
210
+ "dim_feedforward": 512,
211
+ "n_decoder_layers": 8,
212
+ "rescale_shape": [
213
+ 480,
214
+ 640
215
+ ],
216
+ "crop_scale": 0.8,
217
+ "state_noise": 0.01,
218
+ "noise_decay": 0.999995,
219
+ "dropout": 0.1,
220
+ "alpha": 0.98,
221
+ "train_alpha": 0.99,
222
+ "predict_every_n": 1,
223
+ "return_every_n": 1,
224
+ "optimizer_lr": 3e-05,
225
+ "optimizer_min_lr": 1e-05,
226
+ "optimizer_lr_cycle_steps": 100000,
227
+ "optimizer_weight_decay": 1e-05
228
+ },
229
+ "output_dir": "outputs/train/pusht_aloha_insert",
230
+ "job_name": "aloha_dot",
231
+ "resume": false,
232
+ "seed": 100000,
233
+ "num_workers": 20,
234
+ "batch_size": 8,
235
+ "steps": 100000,
236
+ "eval_freq": 50000,
237
+ "log_freq": 1000,
238
+ "save_checkpoint": true,
239
+ "save_freq": 10000,
240
+ "use_policy_training_preset": true,
241
+ "optimizer": {
242
+ "type": "adamw",
243
+ "lr": 3e-05,
244
+ "weight_decay": 1e-05,
245
+ "grad_clip_norm": 10.0,
246
+ "betas": [
247
+ 0.9,
248
+ 0.999
249
+ ],
250
+ "eps": 1e-08
251
+ },
252
+ "scheduler": {
253
+ "type": "cosine_annealing",
254
+ "num_warmup_steps": 0,
255
+ "min_lr": 1e-05,
256
+ "T_max": 100000
257
+ },
258
+ "eval": {
259
+ "n_episodes": 50,
260
+ "batch_size": 50,
261
+ "use_async_envs": false
262
+ },
263
+ "wandb": {
264
+ "enable": true,
265
+ "disable_artifact": false,
266
+ "project": "aloha_insertion",
267
+ "entity": null,
268
+ "notes": null,
269
+ "run_id": null,
270
+ "mode": null
271
+ }
272
+ }
train/pusht_aloha_insert/checkpoints/040000/training_state/optimizer_param_groups.json ADDED
@@ -0,0 +1,234 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "lr": 2.3090169943789145e-05,
4
+ "betas": [
5
+ 0.9,
6
+ 0.999
7
+ ],
8
+ "eps": 1e-08,
9
+ "weight_decay": 1e-05,
10
+ "amsgrad": false,
11
+ "foreach": null,
12
+ "maximize": false,
13
+ "capturable": false,
14
+ "differentiable": false,
15
+ "fused": null,
16
+ "initial_lr": 3e-05,
17
+ "params": [
18
+ 0,
19
+ 1,
20
+ 2,
21
+ 3,
22
+ 4,
23
+ 5,
24
+ 6,
25
+ 7,
26
+ 8,
27
+ 9,
28
+ 10,
29
+ 11,
30
+ 12,
31
+ 13,
32
+ 14,
33
+ 15,
34
+ 16,
35
+ 17,
36
+ 18,
37
+ 19,
38
+ 20,
39
+ 21,
40
+ 22,
41
+ 23,
42
+ 24,
43
+ 25,
44
+ 26,
45
+ 27,
46
+ 28,
47
+ 29,
48
+ 30,
49
+ 31,
50
+ 32,
51
+ 33,
52
+ 34,
53
+ 35,
54
+ 36,
55
+ 37,
56
+ 38,
57
+ 39,
58
+ 40,
59
+ 41,
60
+ 42,
61
+ 43,
62
+ 44,
63
+ 45,
64
+ 46,
65
+ 47,
66
+ 48,
67
+ 49,
68
+ 50,
69
+ 51,
70
+ 52,
71
+ 53,
72
+ 54,
73
+ 55,
74
+ 56,
75
+ 57,
76
+ 58,
77
+ 59,
78
+ 60,
79
+ 61,
80
+ 62,
81
+ 63,
82
+ 64,
83
+ 65,
84
+ 66,
85
+ 67,
86
+ 68,
87
+ 69,
88
+ 70,
89
+ 71,
90
+ 72,
91
+ 73,
92
+ 74,
93
+ 75,
94
+ 76,
95
+ 77,
96
+ 78,
97
+ 79,
98
+ 80,
99
+ 81,
100
+ 82,
101
+ 83,
102
+ 84,
103
+ 85,
104
+ 86,
105
+ 87,
106
+ 88,
107
+ 89,
108
+ 90,
109
+ 91,
110
+ 92,
111
+ 93,
112
+ 94,
113
+ 95,
114
+ 96,
115
+ 97,
116
+ 98,
117
+ 99,
118
+ 100,
119
+ 101,
120
+ 102,
121
+ 103,
122
+ 104,
123
+ 105,
124
+ 106,
125
+ 107,
126
+ 108,
127
+ 109,
128
+ 110,
129
+ 111,
130
+ 112,
131
+ 113,
132
+ 114,
133
+ 115,
134
+ 116,
135
+ 117,
136
+ 118,
137
+ 119,
138
+ 120,
139
+ 121,
140
+ 122,
141
+ 123,
142
+ 124,
143
+ 125,
144
+ 126,
145
+ 127,
146
+ 128,
147
+ 129,
148
+ 130,
149
+ 131,
150
+ 132,
151
+ 133,
152
+ 134,
153
+ 135,
154
+ 136,
155
+ 137,
156
+ 138,
157
+ 139,
158
+ 140,
159
+ 141,
160
+ 142,
161
+ 143,
162
+ 144,
163
+ 145,
164
+ 146,
165
+ 147,
166
+ 148,
167
+ 149,
168
+ 150,
169
+ 151,
170
+ 152,
171
+ 153,
172
+ 154,
173
+ 155,
174
+ 156,
175
+ 157,
176
+ 158,
177
+ 159,
178
+ 160,
179
+ 161,
180
+ 162,
181
+ 163,
182
+ 164,
183
+ 165,
184
+ 166,
185
+ 167,
186
+ 168,
187
+ 169,
188
+ 170,
189
+ 171,
190
+ 172,
191
+ 173,
192
+ 174,
193
+ 175,
194
+ 176,
195
+ 177,
196
+ 178,
197
+ 179,
198
+ 180,
199
+ 181,
200
+ 182,
201
+ 183,
202
+ 184,
203
+ 185,
204
+ 186,
205
+ 187,
206
+ 188,
207
+ 189,
208
+ 190,
209
+ 191,
210
+ 192,
211
+ 193,
212
+ 194,
213
+ 195,
214
+ 196,
215
+ 197,
216
+ 198,
217
+ 199,
218
+ 200,
219
+ 201,
220
+ 202,
221
+ 203,
222
+ 204,
223
+ 205,
224
+ 206,
225
+ 207,
226
+ 208,
227
+ 209,
228
+ 210,
229
+ 211,
230
+ 212,
231
+ 213
232
+ ]
233
+ }
234
+ ]
train/pusht_aloha_insert/checkpoints/040000/training_state/optimizer_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d11b61e59de58c16d20bfe172a53230b63236c362b095ace4a2d25620485387a
3
+ size 23294304
train/pusht_aloha_insert/checkpoints/040000/training_state/rng_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22dd01e1179f377c23e65ea9b355fbad3a003a91553e7e3b0601c5914ee76e28
3
+ size 15708
train/pusht_aloha_insert/checkpoints/040000/training_state/scheduler_state.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "T_max": 100000,
3
+ "eta_min": 1e-05,
4
+ "base_lrs": [
5
+ 3e-05
6
+ ],
7
+ "last_epoch": 40000,
8
+ "verbose": false,
9
+ "_step_count": 40001,
10
+ "_get_lr_called_within_step": false,
11
+ "_last_lr": [
12
+ 2.3090169943789145e-05
13
+ ]
14
+ }
train/pusht_aloha_insert/checkpoints/040000/training_state/training_step.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "step": 40000
3
+ }
train/pusht_aloha_insert/checkpoints/050000/pretrained_model/config.json ADDED
@@ -0,0 +1,126 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "type": "dot",
3
+ "n_obs_steps": 3,
4
+ "normalization_mapping": {
5
+ "VISUAL": "MEAN_STD",
6
+ "STATE": "MIN_MAX",
7
+ "ENV": "MIN_MAX",
8
+ "ACTION": "MIN_MAX"
9
+ },
10
+ "input_features": {
11
+ "observation.images.top": {
12
+ "type": "VISUAL",
13
+ "shape": [
14
+ 3,
15
+ 480,
16
+ 640
17
+ ]
18
+ },
19
+ "observation.state": {
20
+ "type": "STATE",
21
+ "shape": [
22
+ 14
23
+ ]
24
+ }
25
+ },
26
+ "output_features": {
27
+ "action": {
28
+ "type": "ACTION",
29
+ "shape": [
30
+ 14
31
+ ]
32
+ }
33
+ },
34
+ "device": "cuda",
35
+ "use_amp": false,
36
+ "train_horizon": 150,
37
+ "inference_horizon": 100,
38
+ "lookback_obs_steps": 30,
39
+ "lookback_aug": 5,
40
+ "override_dataset_stats": false,
41
+ "new_dataset_stats": {
42
+ "action": {
43
+ "max": [
44
+ 512.0,
45
+ 512.0
46
+ ],
47
+ "min": [
48
+ 0.0,
49
+ 0.0
50
+ ]
51
+ },
52
+ "observation.environment_state": {
53
+ "max": [
54
+ 512.0,
55
+ 512.0,
56
+ 512.0,
57
+ 512.0,
58
+ 512.0,
59
+ 512.0,
60
+ 512.0,
61
+ 512.0,
62
+ 512.0,
63
+ 512.0,
64
+ 512.0,
65
+ 512.0,
66
+ 512.0,
67
+ 512.0,
68
+ 512.0,
69
+ 512.0
70
+ ],
71
+ "min": [
72
+ 0.0,
73
+ 0.0,
74
+ 0.0,
75
+ 0.0,
76
+ 0.0,
77
+ 0.0,
78
+ 0.0,
79
+ 0.0,
80
+ 0.0,
81
+ 0.0,
82
+ 0.0,
83
+ 0.0,
84
+ 0.0,
85
+ 0.0,
86
+ 0.0,
87
+ 0.0
88
+ ]
89
+ },
90
+ "observation.state": {
91
+ "max": [
92
+ 512.0,
93
+ 512.0
94
+ ],
95
+ "min": [
96
+ 0.0,
97
+ 0.0
98
+ ]
99
+ }
100
+ },
101
+ "vision_backbone": "resnet18",
102
+ "pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
103
+ "pre_norm": true,
104
+ "lora_rank": 20,
105
+ "merge_lora": false,
106
+ "dim_model": 128,
107
+ "n_heads": 8,
108
+ "dim_feedforward": 512,
109
+ "n_decoder_layers": 8,
110
+ "rescale_shape": [
111
+ 480,
112
+ 640
113
+ ],
114
+ "crop_scale": 0.8,
115
+ "state_noise": 0.01,
116
+ "noise_decay": 0.999995,
117
+ "dropout": 0.1,
118
+ "alpha": 0.98,
119
+ "train_alpha": 0.99,
120
+ "predict_every_n": 1,
121
+ "return_every_n": 1,
122
+ "optimizer_lr": 3e-05,
123
+ "optimizer_min_lr": 1e-05,
124
+ "optimizer_lr_cycle_steps": 100000,
125
+ "optimizer_weight_decay": 1e-05
126
+ }
train/pusht_aloha_insert/checkpoints/050000/pretrained_model/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:165945987db981c57c67dd63fd7e96db27b7dbff2044704ccec9aeadbbb0414d
3
+ size 56555664
train/pusht_aloha_insert/checkpoints/050000/pretrained_model/train_config.json ADDED
@@ -0,0 +1,272 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset": {
3
+ "repo_id": "lerobot/aloha_sim_insertion_human",
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": "torchcodec"
66
+ },
67
+ "env": {
68
+ "type": "aloha",
69
+ "task": "AlohaInsertion-v0",
70
+ "fps": 50,
71
+ "features": {
72
+ "action": {
73
+ "type": "ACTION",
74
+ "shape": [
75
+ 14
76
+ ]
77
+ },
78
+ "agent_pos": {
79
+ "type": "STATE",
80
+ "shape": [
81
+ 14
82
+ ]
83
+ },
84
+ "pixels/top": {
85
+ "type": "VISUAL",
86
+ "shape": [
87
+ 480,
88
+ 640,
89
+ 3
90
+ ]
91
+ }
92
+ },
93
+ "features_map": {
94
+ "action": "action",
95
+ "agent_pos": "observation.state",
96
+ "top": "observation.image.top",
97
+ "pixels/top": "observation.images.top"
98
+ },
99
+ "episode_length": 500,
100
+ "obs_type": "pixels_agent_pos",
101
+ "render_mode": "rgb_array"
102
+ },
103
+ "policy": {
104
+ "type": "dot",
105
+ "n_obs_steps": 3,
106
+ "normalization_mapping": {
107
+ "VISUAL": "MEAN_STD",
108
+ "STATE": "MIN_MAX",
109
+ "ENV": "MIN_MAX",
110
+ "ACTION": "MIN_MAX"
111
+ },
112
+ "input_features": {
113
+ "observation.images.top": {
114
+ "type": "VISUAL",
115
+ "shape": [
116
+ 3,
117
+ 480,
118
+ 640
119
+ ]
120
+ },
121
+ "observation.state": {
122
+ "type": "STATE",
123
+ "shape": [
124
+ 14
125
+ ]
126
+ }
127
+ },
128
+ "output_features": {
129
+ "action": {
130
+ "type": "ACTION",
131
+ "shape": [
132
+ 14
133
+ ]
134
+ }
135
+ },
136
+ "device": "cuda",
137
+ "use_amp": false,
138
+ "train_horizon": 150,
139
+ "inference_horizon": 100,
140
+ "lookback_obs_steps": 30,
141
+ "lookback_aug": 5,
142
+ "override_dataset_stats": false,
143
+ "new_dataset_stats": {
144
+ "action": {
145
+ "max": [
146
+ 512.0,
147
+ 512.0
148
+ ],
149
+ "min": [
150
+ 0.0,
151
+ 0.0
152
+ ]
153
+ },
154
+ "observation.environment_state": {
155
+ "max": [
156
+ 512.0,
157
+ 512.0,
158
+ 512.0,
159
+ 512.0,
160
+ 512.0,
161
+ 512.0,
162
+ 512.0,
163
+ 512.0,
164
+ 512.0,
165
+ 512.0,
166
+ 512.0,
167
+ 512.0,
168
+ 512.0,
169
+ 512.0,
170
+ 512.0,
171
+ 512.0
172
+ ],
173
+ "min": [
174
+ 0.0,
175
+ 0.0,
176
+ 0.0,
177
+ 0.0,
178
+ 0.0,
179
+ 0.0,
180
+ 0.0,
181
+ 0.0,
182
+ 0.0,
183
+ 0.0,
184
+ 0.0,
185
+ 0.0,
186
+ 0.0,
187
+ 0.0,
188
+ 0.0,
189
+ 0.0
190
+ ]
191
+ },
192
+ "observation.state": {
193
+ "max": [
194
+ 512.0,
195
+ 512.0
196
+ ],
197
+ "min": [
198
+ 0.0,
199
+ 0.0
200
+ ]
201
+ }
202
+ },
203
+ "vision_backbone": "resnet18",
204
+ "pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
205
+ "pre_norm": true,
206
+ "lora_rank": 20,
207
+ "merge_lora": false,
208
+ "dim_model": 128,
209
+ "n_heads": 8,
210
+ "dim_feedforward": 512,
211
+ "n_decoder_layers": 8,
212
+ "rescale_shape": [
213
+ 480,
214
+ 640
215
+ ],
216
+ "crop_scale": 0.8,
217
+ "state_noise": 0.01,
218
+ "noise_decay": 0.999995,
219
+ "dropout": 0.1,
220
+ "alpha": 0.98,
221
+ "train_alpha": 0.99,
222
+ "predict_every_n": 1,
223
+ "return_every_n": 1,
224
+ "optimizer_lr": 3e-05,
225
+ "optimizer_min_lr": 1e-05,
226
+ "optimizer_lr_cycle_steps": 100000,
227
+ "optimizer_weight_decay": 1e-05
228
+ },
229
+ "output_dir": "outputs/train/pusht_aloha_insert",
230
+ "job_name": "aloha_dot",
231
+ "resume": false,
232
+ "seed": 100000,
233
+ "num_workers": 20,
234
+ "batch_size": 8,
235
+ "steps": 100000,
236
+ "eval_freq": 50000,
237
+ "log_freq": 1000,
238
+ "save_checkpoint": true,
239
+ "save_freq": 10000,
240
+ "use_policy_training_preset": true,
241
+ "optimizer": {
242
+ "type": "adamw",
243
+ "lr": 3e-05,
244
+ "weight_decay": 1e-05,
245
+ "grad_clip_norm": 10.0,
246
+ "betas": [
247
+ 0.9,
248
+ 0.999
249
+ ],
250
+ "eps": 1e-08
251
+ },
252
+ "scheduler": {
253
+ "type": "cosine_annealing",
254
+ "num_warmup_steps": 0,
255
+ "min_lr": 1e-05,
256
+ "T_max": 100000
257
+ },
258
+ "eval": {
259
+ "n_episodes": 50,
260
+ "batch_size": 50,
261
+ "use_async_envs": false
262
+ },
263
+ "wandb": {
264
+ "enable": true,
265
+ "disable_artifact": false,
266
+ "project": "aloha_insertion",
267
+ "entity": null,
268
+ "notes": null,
269
+ "run_id": null,
270
+ "mode": null
271
+ }
272
+ }
train/pusht_aloha_insert/checkpoints/050000/training_state/optimizer_param_groups.json ADDED
@@ -0,0 +1,234 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "lr": 2.000000000003065e-05,
4
+ "betas": [
5
+ 0.9,
6
+ 0.999
7
+ ],
8
+ "eps": 1e-08,
9
+ "weight_decay": 1e-05,
10
+ "amsgrad": false,
11
+ "foreach": null,
12
+ "maximize": false,
13
+ "capturable": false,
14
+ "differentiable": false,
15
+ "fused": null,
16
+ "initial_lr": 3e-05,
17
+ "params": [
18
+ 0,
19
+ 1,
20
+ 2,
21
+ 3,
22
+ 4,
23
+ 5,
24
+ 6,
25
+ 7,
26
+ 8,
27
+ 9,
28
+ 10,
29
+ 11,
30
+ 12,
31
+ 13,
32
+ 14,
33
+ 15,
34
+ 16,
35
+ 17,
36
+ 18,
37
+ 19,
38
+ 20,
39
+ 21,
40
+ 22,
41
+ 23,
42
+ 24,
43
+ 25,
44
+ 26,
45
+ 27,
46
+ 28,
47
+ 29,
48
+ 30,
49
+ 31,
50
+ 32,
51
+ 33,
52
+ 34,
53
+ 35,
54
+ 36,
55
+ 37,
56
+ 38,
57
+ 39,
58
+ 40,
59
+ 41,
60
+ 42,
61
+ 43,
62
+ 44,
63
+ 45,
64
+ 46,
65
+ 47,
66
+ 48,
67
+ 49,
68
+ 50,
69
+ 51,
70
+ 52,
71
+ 53,
72
+ 54,
73
+ 55,
74
+ 56,
75
+ 57,
76
+ 58,
77
+ 59,
78
+ 60,
79
+ 61,
80
+ 62,
81
+ 63,
82
+ 64,
83
+ 65,
84
+ 66,
85
+ 67,
86
+ 68,
87
+ 69,
88
+ 70,
89
+ 71,
90
+ 72,
91
+ 73,
92
+ 74,
93
+ 75,
94
+ 76,
95
+ 77,
96
+ 78,
97
+ 79,
98
+ 80,
99
+ 81,
100
+ 82,
101
+ 83,
102
+ 84,
103
+ 85,
104
+ 86,
105
+ 87,
106
+ 88,
107
+ 89,
108
+ 90,
109
+ 91,
110
+ 92,
111
+ 93,
112
+ 94,
113
+ 95,
114
+ 96,
115
+ 97,
116
+ 98,
117
+ 99,
118
+ 100,
119
+ 101,
120
+ 102,
121
+ 103,
122
+ 104,
123
+ 105,
124
+ 106,
125
+ 107,
126
+ 108,
127
+ 109,
128
+ 110,
129
+ 111,
130
+ 112,
131
+ 113,
132
+ 114,
133
+ 115,
134
+ 116,
135
+ 117,
136
+ 118,
137
+ 119,
138
+ 120,
139
+ 121,
140
+ 122,
141
+ 123,
142
+ 124,
143
+ 125,
144
+ 126,
145
+ 127,
146
+ 128,
147
+ 129,
148
+ 130,
149
+ 131,
150
+ 132,
151
+ 133,
152
+ 134,
153
+ 135,
154
+ 136,
155
+ 137,
156
+ 138,
157
+ 139,
158
+ 140,
159
+ 141,
160
+ 142,
161
+ 143,
162
+ 144,
163
+ 145,
164
+ 146,
165
+ 147,
166
+ 148,
167
+ 149,
168
+ 150,
169
+ 151,
170
+ 152,
171
+ 153,
172
+ 154,
173
+ 155,
174
+ 156,
175
+ 157,
176
+ 158,
177
+ 159,
178
+ 160,
179
+ 161,
180
+ 162,
181
+ 163,
182
+ 164,
183
+ 165,
184
+ 166,
185
+ 167,
186
+ 168,
187
+ 169,
188
+ 170,
189
+ 171,
190
+ 172,
191
+ 173,
192
+ 174,
193
+ 175,
194
+ 176,
195
+ 177,
196
+ 178,
197
+ 179,
198
+ 180,
199
+ 181,
200
+ 182,
201
+ 183,
202
+ 184,
203
+ 185,
204
+ 186,
205
+ 187,
206
+ 188,
207
+ 189,
208
+ 190,
209
+ 191,
210
+ 192,
211
+ 193,
212
+ 194,
213
+ 195,
214
+ 196,
215
+ 197,
216
+ 198,
217
+ 199,
218
+ 200,
219
+ 201,
220
+ 202,
221
+ 203,
222
+ 204,
223
+ 205,
224
+ 206,
225
+ 207,
226
+ 208,
227
+ 209,
228
+ 210,
229
+ 211,
230
+ 212,
231
+ 213
232
+ ]
233
+ }
234
+ ]
train/pusht_aloha_insert/checkpoints/050000/training_state/optimizer_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f99dc77f4d96f3f7ec7259b362c10f76d2bd4d38716af219e57a84b4cfec8480
3
+ size 23294304
train/pusht_aloha_insert/checkpoints/050000/training_state/rng_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:270bd10803197b703ce2841b3e6feacf3f412d75a219a0ed04699c60e50ea1dd
3
+ size 15708
train/pusht_aloha_insert/checkpoints/050000/training_state/scheduler_state.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "T_max": 100000,
3
+ "eta_min": 1e-05,
4
+ "base_lrs": [
5
+ 3e-05
6
+ ],
7
+ "last_epoch": 50000,
8
+ "verbose": false,
9
+ "_step_count": 50001,
10
+ "_get_lr_called_within_step": false,
11
+ "_last_lr": [
12
+ 2.000000000003065e-05
13
+ ]
14
+ }
train/pusht_aloha_insert/checkpoints/050000/training_state/training_step.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "step": 50000
3
+ }
train/pusht_aloha_insert/checkpoints/060000/pretrained_model/config.json ADDED
@@ -0,0 +1,126 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "type": "dot",
3
+ "n_obs_steps": 3,
4
+ "normalization_mapping": {
5
+ "VISUAL": "MEAN_STD",
6
+ "STATE": "MIN_MAX",
7
+ "ENV": "MIN_MAX",
8
+ "ACTION": "MIN_MAX"
9
+ },
10
+ "input_features": {
11
+ "observation.images.top": {
12
+ "type": "VISUAL",
13
+ "shape": [
14
+ 3,
15
+ 480,
16
+ 640
17
+ ]
18
+ },
19
+ "observation.state": {
20
+ "type": "STATE",
21
+ "shape": [
22
+ 14
23
+ ]
24
+ }
25
+ },
26
+ "output_features": {
27
+ "action": {
28
+ "type": "ACTION",
29
+ "shape": [
30
+ 14
31
+ ]
32
+ }
33
+ },
34
+ "device": "cuda",
35
+ "use_amp": false,
36
+ "train_horizon": 150,
37
+ "inference_horizon": 100,
38
+ "lookback_obs_steps": 30,
39
+ "lookback_aug": 5,
40
+ "override_dataset_stats": false,
41
+ "new_dataset_stats": {
42
+ "action": {
43
+ "max": [
44
+ 512.0,
45
+ 512.0
46
+ ],
47
+ "min": [
48
+ 0.0,
49
+ 0.0
50
+ ]
51
+ },
52
+ "observation.environment_state": {
53
+ "max": [
54
+ 512.0,
55
+ 512.0,
56
+ 512.0,
57
+ 512.0,
58
+ 512.0,
59
+ 512.0,
60
+ 512.0,
61
+ 512.0,
62
+ 512.0,
63
+ 512.0,
64
+ 512.0,
65
+ 512.0,
66
+ 512.0,
67
+ 512.0,
68
+ 512.0,
69
+ 512.0
70
+ ],
71
+ "min": [
72
+ 0.0,
73
+ 0.0,
74
+ 0.0,
75
+ 0.0,
76
+ 0.0,
77
+ 0.0,
78
+ 0.0,
79
+ 0.0,
80
+ 0.0,
81
+ 0.0,
82
+ 0.0,
83
+ 0.0,
84
+ 0.0,
85
+ 0.0,
86
+ 0.0,
87
+ 0.0
88
+ ]
89
+ },
90
+ "observation.state": {
91
+ "max": [
92
+ 512.0,
93
+ 512.0
94
+ ],
95
+ "min": [
96
+ 0.0,
97
+ 0.0
98
+ ]
99
+ }
100
+ },
101
+ "vision_backbone": "resnet18",
102
+ "pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
103
+ "pre_norm": true,
104
+ "lora_rank": 20,
105
+ "merge_lora": false,
106
+ "dim_model": 128,
107
+ "n_heads": 8,
108
+ "dim_feedforward": 512,
109
+ "n_decoder_layers": 8,
110
+ "rescale_shape": [
111
+ 480,
112
+ 640
113
+ ],
114
+ "crop_scale": 0.8,
115
+ "state_noise": 0.01,
116
+ "noise_decay": 0.999995,
117
+ "dropout": 0.1,
118
+ "alpha": 0.98,
119
+ "train_alpha": 0.99,
120
+ "predict_every_n": 1,
121
+ "return_every_n": 1,
122
+ "optimizer_lr": 3e-05,
123
+ "optimizer_min_lr": 1e-05,
124
+ "optimizer_lr_cycle_steps": 100000,
125
+ "optimizer_weight_decay": 1e-05
126
+ }
train/pusht_aloha_insert/checkpoints/060000/pretrained_model/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:daed214b6cdace6cfeea0742d8124795b2e8bc4f2445ce3ac136cf7f8d7d8b2f
3
+ size 56555664
train/pusht_aloha_insert/checkpoints/060000/pretrained_model/train_config.json ADDED
@@ -0,0 +1,272 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset": {
3
+ "repo_id": "lerobot/aloha_sim_insertion_human",
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": "torchcodec"
66
+ },
67
+ "env": {
68
+ "type": "aloha",
69
+ "task": "AlohaInsertion-v0",
70
+ "fps": 50,
71
+ "features": {
72
+ "action": {
73
+ "type": "ACTION",
74
+ "shape": [
75
+ 14
76
+ ]
77
+ },
78
+ "agent_pos": {
79
+ "type": "STATE",
80
+ "shape": [
81
+ 14
82
+ ]
83
+ },
84
+ "pixels/top": {
85
+ "type": "VISUAL",
86
+ "shape": [
87
+ 480,
88
+ 640,
89
+ 3
90
+ ]
91
+ }
92
+ },
93
+ "features_map": {
94
+ "action": "action",
95
+ "agent_pos": "observation.state",
96
+ "top": "observation.image.top",
97
+ "pixels/top": "observation.images.top"
98
+ },
99
+ "episode_length": 500,
100
+ "obs_type": "pixels_agent_pos",
101
+ "render_mode": "rgb_array"
102
+ },
103
+ "policy": {
104
+ "type": "dot",
105
+ "n_obs_steps": 3,
106
+ "normalization_mapping": {
107
+ "VISUAL": "MEAN_STD",
108
+ "STATE": "MIN_MAX",
109
+ "ENV": "MIN_MAX",
110
+ "ACTION": "MIN_MAX"
111
+ },
112
+ "input_features": {
113
+ "observation.images.top": {
114
+ "type": "VISUAL",
115
+ "shape": [
116
+ 3,
117
+ 480,
118
+ 640
119
+ ]
120
+ },
121
+ "observation.state": {
122
+ "type": "STATE",
123
+ "shape": [
124
+ 14
125
+ ]
126
+ }
127
+ },
128
+ "output_features": {
129
+ "action": {
130
+ "type": "ACTION",
131
+ "shape": [
132
+ 14
133
+ ]
134
+ }
135
+ },
136
+ "device": "cuda",
137
+ "use_amp": false,
138
+ "train_horizon": 150,
139
+ "inference_horizon": 100,
140
+ "lookback_obs_steps": 30,
141
+ "lookback_aug": 5,
142
+ "override_dataset_stats": false,
143
+ "new_dataset_stats": {
144
+ "action": {
145
+ "max": [
146
+ 512.0,
147
+ 512.0
148
+ ],
149
+ "min": [
150
+ 0.0,
151
+ 0.0
152
+ ]
153
+ },
154
+ "observation.environment_state": {
155
+ "max": [
156
+ 512.0,
157
+ 512.0,
158
+ 512.0,
159
+ 512.0,
160
+ 512.0,
161
+ 512.0,
162
+ 512.0,
163
+ 512.0,
164
+ 512.0,
165
+ 512.0,
166
+ 512.0,
167
+ 512.0,
168
+ 512.0,
169
+ 512.0,
170
+ 512.0,
171
+ 512.0
172
+ ],
173
+ "min": [
174
+ 0.0,
175
+ 0.0,
176
+ 0.0,
177
+ 0.0,
178
+ 0.0,
179
+ 0.0,
180
+ 0.0,
181
+ 0.0,
182
+ 0.0,
183
+ 0.0,
184
+ 0.0,
185
+ 0.0,
186
+ 0.0,
187
+ 0.0,
188
+ 0.0,
189
+ 0.0
190
+ ]
191
+ },
192
+ "observation.state": {
193
+ "max": [
194
+ 512.0,
195
+ 512.0
196
+ ],
197
+ "min": [
198
+ 0.0,
199
+ 0.0
200
+ ]
201
+ }
202
+ },
203
+ "vision_backbone": "resnet18",
204
+ "pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
205
+ "pre_norm": true,
206
+ "lora_rank": 20,
207
+ "merge_lora": false,
208
+ "dim_model": 128,
209
+ "n_heads": 8,
210
+ "dim_feedforward": 512,
211
+ "n_decoder_layers": 8,
212
+ "rescale_shape": [
213
+ 480,
214
+ 640
215
+ ],
216
+ "crop_scale": 0.8,
217
+ "state_noise": 0.01,
218
+ "noise_decay": 0.999995,
219
+ "dropout": 0.1,
220
+ "alpha": 0.98,
221
+ "train_alpha": 0.99,
222
+ "predict_every_n": 1,
223
+ "return_every_n": 1,
224
+ "optimizer_lr": 3e-05,
225
+ "optimizer_min_lr": 1e-05,
226
+ "optimizer_lr_cycle_steps": 100000,
227
+ "optimizer_weight_decay": 1e-05
228
+ },
229
+ "output_dir": "outputs/train/pusht_aloha_insert",
230
+ "job_name": "aloha_dot",
231
+ "resume": false,
232
+ "seed": 100000,
233
+ "num_workers": 20,
234
+ "batch_size": 8,
235
+ "steps": 100000,
236
+ "eval_freq": 50000,
237
+ "log_freq": 1000,
238
+ "save_checkpoint": true,
239
+ "save_freq": 10000,
240
+ "use_policy_training_preset": true,
241
+ "optimizer": {
242
+ "type": "adamw",
243
+ "lr": 3e-05,
244
+ "weight_decay": 1e-05,
245
+ "grad_clip_norm": 10.0,
246
+ "betas": [
247
+ 0.9,
248
+ 0.999
249
+ ],
250
+ "eps": 1e-08
251
+ },
252
+ "scheduler": {
253
+ "type": "cosine_annealing",
254
+ "num_warmup_steps": 0,
255
+ "min_lr": 1e-05,
256
+ "T_max": 100000
257
+ },
258
+ "eval": {
259
+ "n_episodes": 50,
260
+ "batch_size": 50,
261
+ "use_async_envs": false
262
+ },
263
+ "wandb": {
264
+ "enable": true,
265
+ "disable_artifact": false,
266
+ "project": "aloha_insertion",
267
+ "entity": null,
268
+ "notes": null,
269
+ "run_id": null,
270
+ "mode": null
271
+ }
272
+ }
train/pusht_aloha_insert/checkpoints/060000/training_state/optimizer_param_groups.json ADDED
@@ -0,0 +1,234 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "lr": 1.69098300562717e-05,
4
+ "betas": [
5
+ 0.9,
6
+ 0.999
7
+ ],
8
+ "eps": 1e-08,
9
+ "weight_decay": 1e-05,
10
+ "amsgrad": false,
11
+ "foreach": null,
12
+ "maximize": false,
13
+ "capturable": false,
14
+ "differentiable": false,
15
+ "fused": null,
16
+ "initial_lr": 3e-05,
17
+ "params": [
18
+ 0,
19
+ 1,
20
+ 2,
21
+ 3,
22
+ 4,
23
+ 5,
24
+ 6,
25
+ 7,
26
+ 8,
27
+ 9,
28
+ 10,
29
+ 11,
30
+ 12,
31
+ 13,
32
+ 14,
33
+ 15,
34
+ 16,
35
+ 17,
36
+ 18,
37
+ 19,
38
+ 20,
39
+ 21,
40
+ 22,
41
+ 23,
42
+ 24,
43
+ 25,
44
+ 26,
45
+ 27,
46
+ 28,
47
+ 29,
48
+ 30,
49
+ 31,
50
+ 32,
51
+ 33,
52
+ 34,
53
+ 35,
54
+ 36,
55
+ 37,
56
+ 38,
57
+ 39,
58
+ 40,
59
+ 41,
60
+ 42,
61
+ 43,
62
+ 44,
63
+ 45,
64
+ 46,
65
+ 47,
66
+ 48,
67
+ 49,
68
+ 50,
69
+ 51,
70
+ 52,
71
+ 53,
72
+ 54,
73
+ 55,
74
+ 56,
75
+ 57,
76
+ 58,
77
+ 59,
78
+ 60,
79
+ 61,
80
+ 62,
81
+ 63,
82
+ 64,
83
+ 65,
84
+ 66,
85
+ 67,
86
+ 68,
87
+ 69,
88
+ 70,
89
+ 71,
90
+ 72,
91
+ 73,
92
+ 74,
93
+ 75,
94
+ 76,
95
+ 77,
96
+ 78,
97
+ 79,
98
+ 80,
99
+ 81,
100
+ 82,
101
+ 83,
102
+ 84,
103
+ 85,
104
+ 86,
105
+ 87,
106
+ 88,
107
+ 89,
108
+ 90,
109
+ 91,
110
+ 92,
111
+ 93,
112
+ 94,
113
+ 95,
114
+ 96,
115
+ 97,
116
+ 98,
117
+ 99,
118
+ 100,
119
+ 101,
120
+ 102,
121
+ 103,
122
+ 104,
123
+ 105,
124
+ 106,
125
+ 107,
126
+ 108,
127
+ 109,
128
+ 110,
129
+ 111,
130
+ 112,
131
+ 113,
132
+ 114,
133
+ 115,
134
+ 116,
135
+ 117,
136
+ 118,
137
+ 119,
138
+ 120,
139
+ 121,
140
+ 122,
141
+ 123,
142
+ 124,
143
+ 125,
144
+ 126,
145
+ 127,
146
+ 128,
147
+ 129,
148
+ 130,
149
+ 131,
150
+ 132,
151
+ 133,
152
+ 134,
153
+ 135,
154
+ 136,
155
+ 137,
156
+ 138,
157
+ 139,
158
+ 140,
159
+ 141,
160
+ 142,
161
+ 143,
162
+ 144,
163
+ 145,
164
+ 146,
165
+ 147,
166
+ 148,
167
+ 149,
168
+ 150,
169
+ 151,
170
+ 152,
171
+ 153,
172
+ 154,
173
+ 155,
174
+ 156,
175
+ 157,
176
+ 158,
177
+ 159,
178
+ 160,
179
+ 161,
180
+ 162,
181
+ 163,
182
+ 164,
183
+ 165,
184
+ 166,
185
+ 167,
186
+ 168,
187
+ 169,
188
+ 170,
189
+ 171,
190
+ 172,
191
+ 173,
192
+ 174,
193
+ 175,
194
+ 176,
195
+ 177,
196
+ 178,
197
+ 179,
198
+ 180,
199
+ 181,
200
+ 182,
201
+ 183,
202
+ 184,
203
+ 185,
204
+ 186,
205
+ 187,
206
+ 188,
207
+ 189,
208
+ 190,
209
+ 191,
210
+ 192,
211
+ 193,
212
+ 194,
213
+ 195,
214
+ 196,
215
+ 197,
216
+ 198,
217
+ 199,
218
+ 200,
219
+ 201,
220
+ 202,
221
+ 203,
222
+ 204,
223
+ 205,
224
+ 206,
225
+ 207,
226
+ 208,
227
+ 209,
228
+ 210,
229
+ 211,
230
+ 212,
231
+ 213
232
+ ]
233
+ }
234
+ ]
train/pusht_aloha_insert/checkpoints/060000/training_state/optimizer_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b30da7b22379e7a1e95623f3cb63956d6b73ca40b867d0b7aa7082fa55a1aa0a
3
+ size 23294304
train/pusht_aloha_insert/checkpoints/060000/training_state/rng_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59e381ef625cad4666ac519343d9e2b7a58185cce8ceebfe4a0baa00e2e5a4e0
3
+ size 15708
train/pusht_aloha_insert/checkpoints/060000/training_state/scheduler_state.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "T_max": 100000,
3
+ "eta_min": 1e-05,
4
+ "base_lrs": [
5
+ 3e-05
6
+ ],
7
+ "last_epoch": 60000,
8
+ "verbose": false,
9
+ "_step_count": 60001,
10
+ "_get_lr_called_within_step": false,
11
+ "_last_lr": [
12
+ 1.69098300562717e-05
13
+ ]
14
+ }
train/pusht_aloha_insert/checkpoints/060000/training_state/training_step.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "step": 60000
3
+ }
train/pusht_aloha_insert/checkpoints/070000/pretrained_model/config.json ADDED
@@ -0,0 +1,126 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "type": "dot",
3
+ "n_obs_steps": 3,
4
+ "normalization_mapping": {
5
+ "VISUAL": "MEAN_STD",
6
+ "STATE": "MIN_MAX",
7
+ "ENV": "MIN_MAX",
8
+ "ACTION": "MIN_MAX"
9
+ },
10
+ "input_features": {
11
+ "observation.images.top": {
12
+ "type": "VISUAL",
13
+ "shape": [
14
+ 3,
15
+ 480,
16
+ 640
17
+ ]
18
+ },
19
+ "observation.state": {
20
+ "type": "STATE",
21
+ "shape": [
22
+ 14
23
+ ]
24
+ }
25
+ },
26
+ "output_features": {
27
+ "action": {
28
+ "type": "ACTION",
29
+ "shape": [
30
+ 14
31
+ ]
32
+ }
33
+ },
34
+ "device": "cuda",
35
+ "use_amp": false,
36
+ "train_horizon": 150,
37
+ "inference_horizon": 100,
38
+ "lookback_obs_steps": 30,
39
+ "lookback_aug": 5,
40
+ "override_dataset_stats": false,
41
+ "new_dataset_stats": {
42
+ "action": {
43
+ "max": [
44
+ 512.0,
45
+ 512.0
46
+ ],
47
+ "min": [
48
+ 0.0,
49
+ 0.0
50
+ ]
51
+ },
52
+ "observation.environment_state": {
53
+ "max": [
54
+ 512.0,
55
+ 512.0,
56
+ 512.0,
57
+ 512.0,
58
+ 512.0,
59
+ 512.0,
60
+ 512.0,
61
+ 512.0,
62
+ 512.0,
63
+ 512.0,
64
+ 512.0,
65
+ 512.0,
66
+ 512.0,
67
+ 512.0,
68
+ 512.0,
69
+ 512.0
70
+ ],
71
+ "min": [
72
+ 0.0,
73
+ 0.0,
74
+ 0.0,
75
+ 0.0,
76
+ 0.0,
77
+ 0.0,
78
+ 0.0,
79
+ 0.0,
80
+ 0.0,
81
+ 0.0,
82
+ 0.0,
83
+ 0.0,
84
+ 0.0,
85
+ 0.0,
86
+ 0.0,
87
+ 0.0
88
+ ]
89
+ },
90
+ "observation.state": {
91
+ "max": [
92
+ 512.0,
93
+ 512.0
94
+ ],
95
+ "min": [
96
+ 0.0,
97
+ 0.0
98
+ ]
99
+ }
100
+ },
101
+ "vision_backbone": "resnet18",
102
+ "pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
103
+ "pre_norm": true,
104
+ "lora_rank": 20,
105
+ "merge_lora": false,
106
+ "dim_model": 128,
107
+ "n_heads": 8,
108
+ "dim_feedforward": 512,
109
+ "n_decoder_layers": 8,
110
+ "rescale_shape": [
111
+ 480,
112
+ 640
113
+ ],
114
+ "crop_scale": 0.8,
115
+ "state_noise": 0.01,
116
+ "noise_decay": 0.999995,
117
+ "dropout": 0.1,
118
+ "alpha": 0.98,
119
+ "train_alpha": 0.99,
120
+ "predict_every_n": 1,
121
+ "return_every_n": 1,
122
+ "optimizer_lr": 3e-05,
123
+ "optimizer_min_lr": 1e-05,
124
+ "optimizer_lr_cycle_steps": 100000,
125
+ "optimizer_weight_decay": 1e-05
126
+ }