Hugging Face's logo

shashuo0104
/
act-pusht

Safetensors
Model card Files
xet
Community
1
shashuo0104 commited on
Commit
83ebfe7
·
verified ·
1 Parent(s): a7f2528

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/001000/pretrained_model/config.json +65 -0
  3. checkpoints/001000/pretrained_model/model.safetensors +3 -0
  4. checkpoints/001000/pretrained_model/train_config.json +211 -0
  5. checkpoints/001000/training_state/optimizer_param_groups.json +191 -0
  6. checkpoints/001000/training_state/optimizer_state.safetensors +3 -0
  7. checkpoints/001000/training_state/rng_state.safetensors +3 -0
  8. checkpoints/001000/training_state/training_step.json +3 -0
  9. checkpoints/002000/pretrained_model/config.json +65 -0
  10. checkpoints/002000/pretrained_model/model.safetensors +3 -0
  11. checkpoints/002000/pretrained_model/train_config.json +211 -0
  12. checkpoints/002000/training_state/optimizer_param_groups.json +191 -0
  13. checkpoints/002000/training_state/optimizer_state.safetensors +3 -0
  14. checkpoints/002000/training_state/rng_state.safetensors +3 -0
  15. checkpoints/002000/training_state/training_step.json +3 -0
  16. checkpoints/003000/pretrained_model/config.json +65 -0
  17. checkpoints/003000/pretrained_model/model.safetensors +3 -0
  18. checkpoints/003000/pretrained_model/train_config.json +211 -0
  19. checkpoints/003000/training_state/optimizer_param_groups.json +191 -0
  20. checkpoints/003000/training_state/optimizer_state.safetensors +3 -0
  21. checkpoints/003000/training_state/rng_state.safetensors +3 -0
  22. checkpoints/003000/training_state/training_step.json +3 -0
  23. checkpoints/004000/pretrained_model/config.json +65 -0
  24. checkpoints/004000/pretrained_model/model.safetensors +3 -0
  25. checkpoints/004000/pretrained_model/train_config.json +211 -0
  26. checkpoints/004000/training_state/optimizer_param_groups.json +191 -0
  27. checkpoints/004000/training_state/optimizer_state.safetensors +3 -0
  28. checkpoints/004000/training_state/rng_state.safetensors +3 -0
  29. checkpoints/004000/training_state/training_step.json +3 -0
  30. checkpoints/005000/pretrained_model/config.json +65 -0
  31. checkpoints/005000/pretrained_model/model.safetensors +3 -0
  32. checkpoints/005000/pretrained_model/train_config.json +211 -0
  33. checkpoints/005000/training_state/optimizer_param_groups.json +191 -0
  34. checkpoints/005000/training_state/optimizer_state.safetensors +3 -0
  35. checkpoints/005000/training_state/rng_state.safetensors +3 -0
  36. checkpoints/005000/training_state/training_step.json +3 -0
  37. checkpoints/006000/pretrained_model/config.json +65 -0
  38. checkpoints/006000/pretrained_model/model.safetensors +3 -0
  39. checkpoints/006000/pretrained_model/train_config.json +211 -0
  40. checkpoints/006000/training_state/optimizer_param_groups.json +191 -0
  41. checkpoints/006000/training_state/optimizer_state.safetensors +3 -0
  42. checkpoints/006000/training_state/rng_state.safetensors +3 -0
  43. checkpoints/006000/training_state/training_step.json +3 -0
  44. checkpoints/007000/pretrained_model/config.json +65 -0
  45. checkpoints/007000/pretrained_model/model.safetensors +3 -0
  46. checkpoints/007000/pretrained_model/train_config.json +211 -0
  47. checkpoints/007000/training_state/optimizer_param_groups.json +191 -0
  48. checkpoints/007000/training_state/optimizer_state.safetensors +3 -0
  49. checkpoints/007000/training_state/rng_state.safetensors +3 -0
  50. checkpoints/007000/training_state/training_step.json +3 -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-7fd56jqi.wandb filter=lfs diff=lfs merge=lfs -text
37
+ wandb/run-20250907_001603-7fd56jqi/run-7fd56jqi.wandb filter=lfs diff=lfs merge=lfs -text
checkpoints/001000/pretrained_model/config.json ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "type": "act",
3
+ "n_obs_steps": 1,
4
+ "normalization_mapping": {
5
+ "VISUAL": "MEAN_STD",
6
+ "STATE": "MEAN_STD",
7
+ "ACTION": "MEAN_STD"
8
+ },
9
+ "relative_actions": false,
10
+ "input_features": {
11
+ "observation.state": {
12
+ "type": "STATE",
13
+ "shape": [
14
+ 2
15
+ ]
16
+ },
17
+ "observation.images.front": {
18
+ "type": "VISUAL",
19
+ "shape": [
20
+ 3,
21
+ 240,
22
+ 240
23
+ ]
24
+ },
25
+ "observation.images.wrist": {
26
+ "type": "VISUAL",
27
+ "shape": [
28
+ 3,
29
+ 240,
30
+ 240
31
+ ]
32
+ }
33
+ },
34
+ "output_features": {
35
+ "action": {
36
+ "type": "ACTION",
37
+ "shape": [
38
+ 2
39
+ ]
40
+ }
41
+ },
42
+ "device": "cuda",
43
+ "use_amp": false,
44
+ "chunk_size": 50,
45
+ "n_action_steps": 50,
46
+ "vision_backbone": "resnet18",
47
+ "pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
48
+ "replace_final_stride_with_dilation": 0,
49
+ "pre_norm": false,
50
+ "dim_model": 512,
51
+ "n_heads": 8,
52
+ "dim_feedforward": 3200,
53
+ "feedforward_activation": "relu",
54
+ "n_encoder_layers": 4,
55
+ "n_decoder_layers": 1,
56
+ "use_vae": true,
57
+ "latent_dim": 32,
58
+ "n_vae_encoder_layers": 4,
59
+ "temporal_ensemble_coeff": null,
60
+ "dropout": 0.1,
61
+ "kl_weight": 10.0,
62
+ "optimizer_lr": 1e-05,
63
+ "optimizer_weight_decay": 0.0001,
64
+ "optimizer_lr_backbone": 1e-05
65
+ }
checkpoints/001000/pretrained_model/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:020d2fc9c027a05260fd70c93381488e0aa0f917a6520ab13059c1946f641c07
3
+ size 206463376
checkpoints/001000/pretrained_model/train_config.json ADDED
@@ -0,0 +1,211 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset": {
3
+ "repo_id": "pusht_60_v5",
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
+ -5,
75
+ 5
76
+ ]
77
+ }
78
+ },
79
+ "crop": {
80
+ "weight": 1.0,
81
+ "type": "RandomCrop",
82
+ "kwargs": {
83
+ "size": [
84
+ 200,
85
+ 200
86
+ ]
87
+ }
88
+ }
89
+ },
90
+ "downsample": {
91
+ "resize": {
92
+ "weight": 1.0,
93
+ "type": "Resize",
94
+ "kwargs": {
95
+ "size": [
96
+ 240,
97
+ 240
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": "act",
110
+ "n_obs_steps": 1,
111
+ "normalization_mapping": {
112
+ "VISUAL": "MEAN_STD",
113
+ "STATE": "MEAN_STD",
114
+ "ACTION": "MEAN_STD"
115
+ },
116
+ "relative_actions": false,
117
+ "input_features": {
118
+ "observation.state": {
119
+ "type": "STATE",
120
+ "shape": [
121
+ 2
122
+ ]
123
+ },
124
+ "observation.images.front": {
125
+ "type": "VISUAL",
126
+ "shape": [
127
+ 3,
128
+ 240,
129
+ 240
130
+ ]
131
+ },
132
+ "observation.images.wrist": {
133
+ "type": "VISUAL",
134
+ "shape": [
135
+ 3,
136
+ 240,
137
+ 240
138
+ ]
139
+ }
140
+ },
141
+ "output_features": {
142
+ "action": {
143
+ "type": "ACTION",
144
+ "shape": [
145
+ 2
146
+ ]
147
+ }
148
+ },
149
+ "device": "cuda",
150
+ "use_amp": false,
151
+ "chunk_size": 50,
152
+ "n_action_steps": 50,
153
+ "vision_backbone": "resnet18",
154
+ "pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
155
+ "replace_final_stride_with_dilation": 0,
156
+ "pre_norm": false,
157
+ "dim_model": 512,
158
+ "n_heads": 8,
159
+ "dim_feedforward": 3200,
160
+ "feedforward_activation": "relu",
161
+ "n_encoder_layers": 4,
162
+ "n_decoder_layers": 1,
163
+ "use_vae": true,
164
+ "latent_dim": 32,
165
+ "n_vae_encoder_layers": 4,
166
+ "temporal_ensemble_coeff": null,
167
+ "dropout": 0.1,
168
+ "kl_weight": 10.0,
169
+ "optimizer_lr": 1e-05,
170
+ "optimizer_weight_decay": 0.0001,
171
+ "optimizer_lr_backbone": 1e-05
172
+ },
173
+ "output_dir": "outputs/train/pusht_60_v5/2025-09-07_00-15-58_act_abs_v5",
174
+ "job_name": "2025-09-07_00-15-58_act_abs_v5",
175
+ "resume": false,
176
+ "seed": 100000,
177
+ "num_workers": 4,
178
+ "batch_size": 512,
179
+ "steps": 20000,
180
+ "eval_freq": 2000,
181
+ "log_freq": 200,
182
+ "save_checkpoint": true,
183
+ "save_freq": 1000,
184
+ "use_policy_training_preset": true,
185
+ "optimizer": {
186
+ "type": "adamw",
187
+ "lr": 1e-05,
188
+ "weight_decay": 0.0001,
189
+ "grad_clip_norm": 10.0,
190
+ "betas": [
191
+ 0.9,
192
+ 0.999
193
+ ],
194
+ "eps": 1e-08
195
+ },
196
+ "scheduler": null,
197
+ "eval": {
198
+ "n_episodes": 50,
199
+ "batch_size": 50,
200
+ "use_async_envs": false
201
+ },
202
+ "wandb": {
203
+ "enable": true,
204
+ "disable_artifact": true,
205
+ "project": "lerobot",
206
+ "entity": null,
207
+ "notes": null,
208
+ "run_id": null,
209
+ "mode": null
210
+ }
211
+ }
checkpoints/001000/training_state/optimizer_param_groups.json ADDED
@@ -0,0 +1,191 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "lr": 1e-05,
4
+ "betas": [
5
+ 0.9,
6
+ 0.999
7
+ ],
8
+ "eps": 1e-08,
9
+ "weight_decay": 0.0001,
10
+ "amsgrad": false,
11
+ "maximize": false,
12
+ "foreach": null,
13
+ "capturable": false,
14
+ "differentiable": false,
15
+ "fused": null,
16
+ "decoupled_weight_decay": true,
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
+ ]
152
+ },
153
+ {
154
+ "lr": 1e-05,
155
+ "betas": [
156
+ 0.9,
157
+ 0.999
158
+ ],
159
+ "eps": 1e-08,
160
+ "weight_decay": 0.0001,
161
+ "amsgrad": false,
162
+ "maximize": false,
163
+ "foreach": null,
164
+ "capturable": false,
165
+ "differentiable": false,
166
+ "fused": null,
167
+ "decoupled_weight_decay": true,
168
+ "params": [
169
+ 133,
170
+ 134,
171
+ 135,
172
+ 136,
173
+ 137,
174
+ 138,
175
+ 139,
176
+ 140,
177
+ 141,
178
+ 142,
179
+ 143,
180
+ 144,
181
+ 145,
182
+ 146,
183
+ 147,
184
+ 148,
185
+ 149,
186
+ 150,
187
+ 151,
188
+ 152
189
+ ]
190
+ }
191
+ ]
checkpoints/001000/training_state/optimizer_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ef6b5e680cfd1b392bb2953656eac5ceb104e8f4c590387f11e1ca073aff780
3
+ size 412547284
checkpoints/001000/training_state/rng_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6eadfa1f674d3ccccf26430052dd368b44f382d356ab0d97567e56373456b966
3
+ size 15708
checkpoints/001000/training_state/training_step.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "step": 1000
3
+ }
checkpoints/002000/pretrained_model/config.json ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "type": "act",
3
+ "n_obs_steps": 1,
4
+ "normalization_mapping": {
5
+ "VISUAL": "MEAN_STD",
6
+ "STATE": "MEAN_STD",
7
+ "ACTION": "MEAN_STD"
8
+ },
9
+ "relative_actions": false,
10
+ "input_features": {
11
+ "observation.state": {
12
+ "type": "STATE",
13
+ "shape": [
14
+ 2
15
+ ]
16
+ },
17
+ "observation.images.front": {
18
+ "type": "VISUAL",
19
+ "shape": [
20
+ 3,
21
+ 240,
22
+ 240
23
+ ]
24
+ },
25
+ "observation.images.wrist": {
26
+ "type": "VISUAL",
27
+ "shape": [
28
+ 3,
29
+ 240,
30
+ 240
31
+ ]
32
+ }
33
+ },
34
+ "output_features": {
35
+ "action": {
36
+ "type": "ACTION",
37
+ "shape": [
38
+ 2
39
+ ]
40
+ }
41
+ },
42
+ "device": "cuda",
43
+ "use_amp": false,
44
+ "chunk_size": 50,
45
+ "n_action_steps": 50,
46
+ "vision_backbone": "resnet18",
47
+ "pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
48
+ "replace_final_stride_with_dilation": 0,
49
+ "pre_norm": false,
50
+ "dim_model": 512,
51
+ "n_heads": 8,
52
+ "dim_feedforward": 3200,
53
+ "feedforward_activation": "relu",
54
+ "n_encoder_layers": 4,
55
+ "n_decoder_layers": 1,
56
+ "use_vae": true,
57
+ "latent_dim": 32,
58
+ "n_vae_encoder_layers": 4,
59
+ "temporal_ensemble_coeff": null,
60
+ "dropout": 0.1,
61
+ "kl_weight": 10.0,
62
+ "optimizer_lr": 1e-05,
63
+ "optimizer_weight_decay": 0.0001,
64
+ "optimizer_lr_backbone": 1e-05
65
+ }
checkpoints/002000/pretrained_model/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:729b5b6b4b434182720ffb94099495c6bc36b0c530269be4268e2bbe7c321255
3
+ size 206463376
checkpoints/002000/pretrained_model/train_config.json ADDED
@@ -0,0 +1,211 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset": {
3
+ "repo_id": "pusht_60_v5",
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
+ -5,
75
+ 5
76
+ ]
77
+ }
78
+ },
79
+ "crop": {
80
+ "weight": 1.0,
81
+ "type": "RandomCrop",
82
+ "kwargs": {
83
+ "size": [
84
+ 200,
85
+ 200
86
+ ]
87
+ }
88
+ }
89
+ },
90
+ "downsample": {
91
+ "resize": {
92
+ "weight": 1.0,
93
+ "type": "Resize",
94
+ "kwargs": {
95
+ "size": [
96
+ 240,
97
+ 240
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": "act",
110
+ "n_obs_steps": 1,
111
+ "normalization_mapping": {
112
+ "VISUAL": "MEAN_STD",
113
+ "STATE": "MEAN_STD",
114
+ "ACTION": "MEAN_STD"
115
+ },
116
+ "relative_actions": false,
117
+ "input_features": {
118
+ "observation.state": {
119
+ "type": "STATE",
120
+ "shape": [
121
+ 2
122
+ ]
123
+ },
124
+ "observation.images.front": {
125
+ "type": "VISUAL",
126
+ "shape": [
127
+ 3,
128
+ 240,
129
+ 240
130
+ ]
131
+ },
132
+ "observation.images.wrist": {
133
+ "type": "VISUAL",
134
+ "shape": [
135
+ 3,
136
+ 240,
137
+ 240
138
+ ]
139
+ }
140
+ },
141
+ "output_features": {
142
+ "action": {
143
+ "type": "ACTION",
144
+ "shape": [
145
+ 2
146
+ ]
147
+ }
148
+ },
149
+ "device": "cuda",
150
+ "use_amp": false,
151
+ "chunk_size": 50,
152
+ "n_action_steps": 50,
153
+ "vision_backbone": "resnet18",
154
+ "pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
155
+ "replace_final_stride_with_dilation": 0,
156
+ "pre_norm": false,
157
+ "dim_model": 512,
158
+ "n_heads": 8,
159
+ "dim_feedforward": 3200,
160
+ "feedforward_activation": "relu",
161
+ "n_encoder_layers": 4,
162
+ "n_decoder_layers": 1,
163
+ "use_vae": true,
164
+ "latent_dim": 32,
165
+ "n_vae_encoder_layers": 4,
166
+ "temporal_ensemble_coeff": null,
167
+ "dropout": 0.1,
168
+ "kl_weight": 10.0,
169
+ "optimizer_lr": 1e-05,
170
+ "optimizer_weight_decay": 0.0001,
171
+ "optimizer_lr_backbone": 1e-05
172
+ },
173
+ "output_dir": "outputs/train/pusht_60_v5/2025-09-07_00-15-58_act_abs_v5",
174
+ "job_name": "2025-09-07_00-15-58_act_abs_v5",
175
+ "resume": false,
176
+ "seed": 100000,
177
+ "num_workers": 4,
178
+ "batch_size": 512,
179
+ "steps": 20000,
180
+ "eval_freq": 2000,
181
+ "log_freq": 200,
182
+ "save_checkpoint": true,
183
+ "save_freq": 1000,
184
+ "use_policy_training_preset": true,
185
+ "optimizer": {
186
+ "type": "adamw",
187
+ "lr": 1e-05,
188
+ "weight_decay": 0.0001,
189
+ "grad_clip_norm": 10.0,
190
+ "betas": [
191
+ 0.9,
192
+ 0.999
193
+ ],
194
+ "eps": 1e-08
195
+ },
196
+ "scheduler": null,
197
+ "eval": {
198
+ "n_episodes": 50,
199
+ "batch_size": 50,
200
+ "use_async_envs": false
201
+ },
202
+ "wandb": {
203
+ "enable": true,
204
+ "disable_artifact": true,
205
+ "project": "lerobot",
206
+ "entity": null,
207
+ "notes": null,
208
+ "run_id": null,
209
+ "mode": null
210
+ }
211
+ }
checkpoints/002000/training_state/optimizer_param_groups.json ADDED
@@ -0,0 +1,191 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "lr": 1e-05,
4
+ "betas": [
5
+ 0.9,
6
+ 0.999
7
+ ],
8
+ "eps": 1e-08,
9
+ "weight_decay": 0.0001,
10
+ "amsgrad": false,
11
+ "maximize": false,
12
+ "foreach": null,
13
+ "capturable": false,
14
+ "differentiable": false,
15
+ "fused": null,
16
+ "decoupled_weight_decay": true,
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
+ ]
152
+ },
153
+ {
154
+ "lr": 1e-05,
155
+ "betas": [
156
+ 0.9,
157
+ 0.999
158
+ ],
159
+ "eps": 1e-08,
160
+ "weight_decay": 0.0001,
161
+ "amsgrad": false,
162
+ "maximize": false,
163
+ "foreach": null,
164
+ "capturable": false,
165
+ "differentiable": false,
166
+ "fused": null,
167
+ "decoupled_weight_decay": true,
168
+ "params": [
169
+ 133,
170
+ 134,
171
+ 135,
172
+ 136,
173
+ 137,
174
+ 138,
175
+ 139,
176
+ 140,
177
+ 141,
178
+ 142,
179
+ 143,
180
+ 144,
181
+ 145,
182
+ 146,
183
+ 147,
184
+ 148,
185
+ 149,
186
+ 150,
187
+ 151,
188
+ 152
189
+ ]
190
+ }
191
+ ]
checkpoints/002000/training_state/optimizer_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:422c68efe76edc51735c9315416c8ccb39a6c28ec644449afea69db32af1f8bd
3
+ size 412547284
checkpoints/002000/training_state/rng_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db04b4dbf8a133b35c0130f41ed5e18e7b1c12a89d4707de501fdc16fb7818d1
3
+ size 15708
checkpoints/002000/training_state/training_step.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "step": 2000
3
+ }
checkpoints/003000/pretrained_model/config.json ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "type": "act",
3
+ "n_obs_steps": 1,
4
+ "normalization_mapping": {
5
+ "VISUAL": "MEAN_STD",
6
+ "STATE": "MEAN_STD",
7
+ "ACTION": "MEAN_STD"
8
+ },
9
+ "relative_actions": false,
10
+ "input_features": {
11
+ "observation.state": {
12
+ "type": "STATE",
13
+ "shape": [
14
+ 2
15
+ ]
16
+ },
17
+ "observation.images.front": {
18
+ "type": "VISUAL",
19
+ "shape": [
20
+ 3,
21
+ 240,
22
+ 240
23
+ ]
24
+ },
25
+ "observation.images.wrist": {
26
+ "type": "VISUAL",
27
+ "shape": [
28
+ 3,
29
+ 240,
30
+ 240
31
+ ]
32
+ }
33
+ },
34
+ "output_features": {
35
+ "action": {
36
+ "type": "ACTION",
37
+ "shape": [
38
+ 2
39
+ ]
40
+ }
41
+ },
42
+ "device": "cuda",
43
+ "use_amp": false,
44
+ "chunk_size": 50,
45
+ "n_action_steps": 50,
46
+ "vision_backbone": "resnet18",
47
+ "pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
48
+ "replace_final_stride_with_dilation": 0,
49
+ "pre_norm": false,
50
+ "dim_model": 512,
51
+ "n_heads": 8,
52
+ "dim_feedforward": 3200,
53
+ "feedforward_activation": "relu",
54
+ "n_encoder_layers": 4,
55
+ "n_decoder_layers": 1,
56
+ "use_vae": true,
57
+ "latent_dim": 32,
58
+ "n_vae_encoder_layers": 4,
59
+ "temporal_ensemble_coeff": null,
60
+ "dropout": 0.1,
61
+ "kl_weight": 10.0,
62
+ "optimizer_lr": 1e-05,
63
+ "optimizer_weight_decay": 0.0001,
64
+ "optimizer_lr_backbone": 1e-05
65
+ }
checkpoints/003000/pretrained_model/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:992ed2f8d512f33e2004e68316834ea8dc1dd767e0a639d5208067f62f021fd9
3
+ size 206463376
checkpoints/003000/pretrained_model/train_config.json ADDED
@@ -0,0 +1,211 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset": {
3
+ "repo_id": "pusht_60_v5",
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
+ -5,
75
+ 5
76
+ ]
77
+ }
78
+ },
79
+ "crop": {
80
+ "weight": 1.0,
81
+ "type": "RandomCrop",
82
+ "kwargs": {
83
+ "size": [
84
+ 200,
85
+ 200
86
+ ]
87
+ }
88
+ }
89
+ },
90
+ "downsample": {
91
+ "resize": {
92
+ "weight": 1.0,
93
+ "type": "Resize",
94
+ "kwargs": {
95
+ "size": [
96
+ 240,
97
+ 240
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": "act",
110
+ "n_obs_steps": 1,
111
+ "normalization_mapping": {
112
+ "VISUAL": "MEAN_STD",
113
+ "STATE": "MEAN_STD",
114
+ "ACTION": "MEAN_STD"
115
+ },
116
+ "relative_actions": false,
117
+ "input_features": {
118
+ "observation.state": {
119
+ "type": "STATE",
120
+ "shape": [
121
+ 2
122
+ ]
123
+ },
124
+ "observation.images.front": {
125
+ "type": "VISUAL",
126
+ "shape": [
127
+ 3,
128
+ 240,
129
+ 240
130
+ ]
131
+ },
132
+ "observation.images.wrist": {
133
+ "type": "VISUAL",
134
+ "shape": [
135
+ 3,
136
+ 240,
137
+ 240
138
+ ]
139
+ }
140
+ },
141
+ "output_features": {
142
+ "action": {
143
+ "type": "ACTION",
144
+ "shape": [
145
+ 2
146
+ ]
147
+ }
148
+ },
149
+ "device": "cuda",
150
+ "use_amp": false,
151
+ "chunk_size": 50,
152
+ "n_action_steps": 50,
153
+ "vision_backbone": "resnet18",
154
+ "pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
155
+ "replace_final_stride_with_dilation": 0,
156
+ "pre_norm": false,
157
+ "dim_model": 512,
158
+ "n_heads": 8,
159
+ "dim_feedforward": 3200,
160
+ "feedforward_activation": "relu",
161
+ "n_encoder_layers": 4,
162
+ "n_decoder_layers": 1,
163
+ "use_vae": true,
164
+ "latent_dim": 32,
165
+ "n_vae_encoder_layers": 4,
166
+ "temporal_ensemble_coeff": null,
167
+ "dropout": 0.1,
168
+ "kl_weight": 10.0,
169
+ "optimizer_lr": 1e-05,
170
+ "optimizer_weight_decay": 0.0001,
171
+ "optimizer_lr_backbone": 1e-05
172
+ },
173
+ "output_dir": "outputs/train/pusht_60_v5/2025-09-07_00-15-58_act_abs_v5",
174
+ "job_name": "2025-09-07_00-15-58_act_abs_v5",
175
+ "resume": false,
176
+ "seed": 100000,
177
+ "num_workers": 4,
178
+ "batch_size": 512,
179
+ "steps": 20000,
180
+ "eval_freq": 2000,
181
+ "log_freq": 200,
182
+ "save_checkpoint": true,
183
+ "save_freq": 1000,
184
+ "use_policy_training_preset": true,
185
+ "optimizer": {
186
+ "type": "adamw",
187
+ "lr": 1e-05,
188
+ "weight_decay": 0.0001,
189
+ "grad_clip_norm": 10.0,
190
+ "betas": [
191
+ 0.9,
192
+ 0.999
193
+ ],
194
+ "eps": 1e-08
195
+ },
196
+ "scheduler": null,
197
+ "eval": {
198
+ "n_episodes": 50,
199
+ "batch_size": 50,
200
+ "use_async_envs": false
201
+ },
202
+ "wandb": {
203
+ "enable": true,
204
+ "disable_artifact": true,
205
+ "project": "lerobot",
206
+ "entity": null,
207
+ "notes": null,
208
+ "run_id": null,
209
+ "mode": null
210
+ }
211
+ }
checkpoints/003000/training_state/optimizer_param_groups.json ADDED
@@ -0,0 +1,191 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "lr": 1e-05,
4
+ "betas": [
5
+ 0.9,
6
+ 0.999
7
+ ],
8
+ "eps": 1e-08,
9
+ "weight_decay": 0.0001,
10
+ "amsgrad": false,
11
+ "maximize": false,
12
+ "foreach": null,
13
+ "capturable": false,
14
+ "differentiable": false,
15
+ "fused": null,
16
+ "decoupled_weight_decay": true,
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
+ ]
152
+ },
153
+ {
154
+ "lr": 1e-05,
155
+ "betas": [
156
+ 0.9,
157
+ 0.999
158
+ ],
159
+ "eps": 1e-08,
160
+ "weight_decay": 0.0001,
161
+ "amsgrad": false,
162
+ "maximize": false,
163
+ "foreach": null,
164
+ "capturable": false,
165
+ "differentiable": false,
166
+ "fused": null,
167
+ "decoupled_weight_decay": true,
168
+ "params": [
169
+ 133,
170
+ 134,
171
+ 135,
172
+ 136,
173
+ 137,
174
+ 138,
175
+ 139,
176
+ 140,
177
+ 141,
178
+ 142,
179
+ 143,
180
+ 144,
181
+ 145,
182
+ 146,
183
+ 147,
184
+ 148,
185
+ 149,
186
+ 150,
187
+ 151,
188
+ 152
189
+ ]
190
+ }
191
+ ]
checkpoints/003000/training_state/optimizer_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc1f2d283d11471e346b731c314dcc4bbac1f620a4d854d279f9b3e4265e9497
3
+ size 412547284
checkpoints/003000/training_state/rng_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd4bf23d64701cdc36136ad7da04d728eff26b25aa73b0389cfdeead16322434
3
+ size 15708
checkpoints/003000/training_state/training_step.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "step": 3000
3
+ }
checkpoints/004000/pretrained_model/config.json ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "type": "act",
3
+ "n_obs_steps": 1,
4
+ "normalization_mapping": {
5
+ "VISUAL": "MEAN_STD",
6
+ "STATE": "MEAN_STD",
7
+ "ACTION": "MEAN_STD"
8
+ },
9
+ "relative_actions": false,
10
+ "input_features": {
11
+ "observation.state": {
12
+ "type": "STATE",
13
+ "shape": [
14
+ 2
15
+ ]
16
+ },
17
+ "observation.images.front": {
18
+ "type": "VISUAL",
19
+ "shape": [
20
+ 3,
21
+ 240,
22
+ 240
23
+ ]
24
+ },
25
+ "observation.images.wrist": {
26
+ "type": "VISUAL",
27
+ "shape": [
28
+ 3,
29
+ 240,
30
+ 240
31
+ ]
32
+ }
33
+ },
34
+ "output_features": {
35
+ "action": {
36
+ "type": "ACTION",
37
+ "shape": [
38
+ 2
39
+ ]
40
+ }
41
+ },
42
+ "device": "cuda",
43
+ "use_amp": false,
44
+ "chunk_size": 50,
45
+ "n_action_steps": 50,
46
+ "vision_backbone": "resnet18",
47
+ "pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
48
+ "replace_final_stride_with_dilation": 0,
49
+ "pre_norm": false,
50
+ "dim_model": 512,
51
+ "n_heads": 8,
52
+ "dim_feedforward": 3200,
53
+ "feedforward_activation": "relu",
54
+ "n_encoder_layers": 4,
55
+ "n_decoder_layers": 1,
56
+ "use_vae": true,
57
+ "latent_dim": 32,
58
+ "n_vae_encoder_layers": 4,
59
+ "temporal_ensemble_coeff": null,
60
+ "dropout": 0.1,
61
+ "kl_weight": 10.0,
62
+ "optimizer_lr": 1e-05,
63
+ "optimizer_weight_decay": 0.0001,
64
+ "optimizer_lr_backbone": 1e-05
65
+ }
checkpoints/004000/pretrained_model/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9f2b915036430d64363d79301d4e285e37e5e0556f8298731d537a0d5a34def
3
+ size 206463376
checkpoints/004000/pretrained_model/train_config.json ADDED
@@ -0,0 +1,211 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset": {
3
+ "repo_id": "pusht_60_v5",
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
+ -5,
75
+ 5
76
+ ]
77
+ }
78
+ },
79
+ "crop": {
80
+ "weight": 1.0,
81
+ "type": "RandomCrop",
82
+ "kwargs": {
83
+ "size": [
84
+ 200,
85
+ 200
86
+ ]
87
+ }
88
+ }
89
+ },
90
+ "downsample": {
91
+ "resize": {
92
+ "weight": 1.0,
93
+ "type": "Resize",
94
+ "kwargs": {
95
+ "size": [
96
+ 240,
97
+ 240
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": "act",
110
+ "n_obs_steps": 1,
111
+ "normalization_mapping": {
112
+ "VISUAL": "MEAN_STD",
113
+ "STATE": "MEAN_STD",
114
+ "ACTION": "MEAN_STD"
115
+ },
116
+ "relative_actions": false,
117
+ "input_features": {
118
+ "observation.state": {
119
+ "type": "STATE",
120
+ "shape": [
121
+ 2
122
+ ]
123
+ },
124
+ "observation.images.front": {
125
+ "type": "VISUAL",
126
+ "shape": [
127
+ 3,
128
+ 240,
129
+ 240
130
+ ]
131
+ },
132
+ "observation.images.wrist": {
133
+ "type": "VISUAL",
134
+ "shape": [
135
+ 3,
136
+ 240,
137
+ 240
138
+ ]
139
+ }
140
+ },
141
+ "output_features": {
142
+ "action": {
143
+ "type": "ACTION",
144
+ "shape": [
145
+ 2
146
+ ]
147
+ }
148
+ },
149
+ "device": "cuda",
150
+ "use_amp": false,
151
+ "chunk_size": 50,
152
+ "n_action_steps": 50,
153
+ "vision_backbone": "resnet18",
154
+ "pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
155
+ "replace_final_stride_with_dilation": 0,
156
+ "pre_norm": false,
157
+ "dim_model": 512,
158
+ "n_heads": 8,
159
+ "dim_feedforward": 3200,
160
+ "feedforward_activation": "relu",
161
+ "n_encoder_layers": 4,
162
+ "n_decoder_layers": 1,
163
+ "use_vae": true,
164
+ "latent_dim": 32,
165
+ "n_vae_encoder_layers": 4,
166
+ "temporal_ensemble_coeff": null,
167
+ "dropout": 0.1,
168
+ "kl_weight": 10.0,
169
+ "optimizer_lr": 1e-05,
170
+ "optimizer_weight_decay": 0.0001,
171
+ "optimizer_lr_backbone": 1e-05
172
+ },
173
+ "output_dir": "outputs/train/pusht_60_v5/2025-09-07_00-15-58_act_abs_v5",
174
+ "job_name": "2025-09-07_00-15-58_act_abs_v5",
175
+ "resume": false,
176
+ "seed": 100000,
177
+ "num_workers": 4,
178
+ "batch_size": 512,
179
+ "steps": 20000,
180
+ "eval_freq": 2000,
181
+ "log_freq": 200,
182
+ "save_checkpoint": true,
183
+ "save_freq": 1000,
184
+ "use_policy_training_preset": true,
185
+ "optimizer": {
186
+ "type": "adamw",
187
+ "lr": 1e-05,
188
+ "weight_decay": 0.0001,
189
+ "grad_clip_norm": 10.0,
190
+ "betas": [
191
+ 0.9,
192
+ 0.999
193
+ ],
194
+ "eps": 1e-08
195
+ },
196
+ "scheduler": null,
197
+ "eval": {
198
+ "n_episodes": 50,
199
+ "batch_size": 50,
200
+ "use_async_envs": false
201
+ },
202
+ "wandb": {
203
+ "enable": true,
204
+ "disable_artifact": true,
205
+ "project": "lerobot",
206
+ "entity": null,
207
+ "notes": null,
208
+ "run_id": null,
209
+ "mode": null
210
+ }
211
+ }
checkpoints/004000/training_state/optimizer_param_groups.json ADDED
@@ -0,0 +1,191 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "lr": 1e-05,
4
+ "betas": [
5
+ 0.9,
6
+ 0.999
7
+ ],
8
+ "eps": 1e-08,
9
+ "weight_decay": 0.0001,
10
+ "amsgrad": false,
11
+ "maximize": false,
12
+ "foreach": null,
13
+ "capturable": false,
14
+ "differentiable": false,
15
+ "fused": null,
16
+ "decoupled_weight_decay": true,
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
+ ]
152
+ },
153
+ {
154
+ "lr": 1e-05,
155
+ "betas": [
156
+ 0.9,
157
+ 0.999
158
+ ],
159
+ "eps": 1e-08,
160
+ "weight_decay": 0.0001,
161
+ "amsgrad": false,
162
+ "maximize": false,
163
+ "foreach": null,
164
+ "capturable": false,
165
+ "differentiable": false,
166
+ "fused": null,
167
+ "decoupled_weight_decay": true,
168
+ "params": [
169
+ 133,
170
+ 134,
171
+ 135,
172
+ 136,
173
+ 137,
174
+ 138,
175
+ 139,
176
+ 140,
177
+ 141,
178
+ 142,
179
+ 143,
180
+ 144,
181
+ 145,
182
+ 146,
183
+ 147,
184
+ 148,
185
+ 149,
186
+ 150,
187
+ 151,
188
+ 152
189
+ ]
190
+ }
191
+ ]
checkpoints/004000/training_state/optimizer_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:facf43c01c61c9544c1a2909980219676a7227db836b73fc5267ed7a0d79f113
3
+ size 412547284
checkpoints/004000/training_state/rng_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dea718e10ce112ecb1819309f2e726844aa0072a3f5e9a9d97223efb9be0b8cc
3
+ size 15708
checkpoints/004000/training_state/training_step.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "step": 4000
3
+ }
checkpoints/005000/pretrained_model/config.json ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "type": "act",
3
+ "n_obs_steps": 1,
4
+ "normalization_mapping": {
5
+ "VISUAL": "MEAN_STD",
6
+ "STATE": "MEAN_STD",
7
+ "ACTION": "MEAN_STD"
8
+ },
9
+ "relative_actions": false,
10
+ "input_features": {
11
+ "observation.state": {
12
+ "type": "STATE",
13
+ "shape": [
14
+ 2
15
+ ]
16
+ },
17
+ "observation.images.front": {
18
+ "type": "VISUAL",
19
+ "shape": [
20
+ 3,
21
+ 240,
22
+ 240
23
+ ]
24
+ },
25
+ "observation.images.wrist": {
26
+ "type": "VISUAL",
27
+ "shape": [
28
+ 3,
29
+ 240,
30
+ 240
31
+ ]
32
+ }
33
+ },
34
+ "output_features": {
35
+ "action": {
36
+ "type": "ACTION",
37
+ "shape": [
38
+ 2
39
+ ]
40
+ }
41
+ },
42
+ "device": "cuda",
43
+ "use_amp": false,
44
+ "chunk_size": 50,
45
+ "n_action_steps": 50,
46
+ "vision_backbone": "resnet18",
47
+ "pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
48
+ "replace_final_stride_with_dilation": 0,
49
+ "pre_norm": false,
50
+ "dim_model": 512,
51
+ "n_heads": 8,
52
+ "dim_feedforward": 3200,
53
+ "feedforward_activation": "relu",
54
+ "n_encoder_layers": 4,
55
+ "n_decoder_layers": 1,
56
+ "use_vae": true,
57
+ "latent_dim": 32,
58
+ "n_vae_encoder_layers": 4,
59
+ "temporal_ensemble_coeff": null,
60
+ "dropout": 0.1,
61
+ "kl_weight": 10.0,
62
+ "optimizer_lr": 1e-05,
63
+ "optimizer_weight_decay": 0.0001,
64
+ "optimizer_lr_backbone": 1e-05
65
+ }
checkpoints/005000/pretrained_model/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1518f08ff3c9ab2187d8dc74fb37f4a0e06979ce2d1466c929508d96b28a0240
3
+ size 206463376
checkpoints/005000/pretrained_model/train_config.json ADDED
@@ -0,0 +1,211 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset": {
3
+ "repo_id": "pusht_60_v5",
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
+ -5,
75
+ 5
76
+ ]
77
+ }
78
+ },
79
+ "crop": {
80
+ "weight": 1.0,
81
+ "type": "RandomCrop",
82
+ "kwargs": {
83
+ "size": [
84
+ 200,
85
+ 200
86
+ ]
87
+ }
88
+ }
89
+ },
90
+ "downsample": {
91
+ "resize": {
92
+ "weight": 1.0,
93
+ "type": "Resize",
94
+ "kwargs": {
95
+ "size": [
96
+ 240,
97
+ 240
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": "act",
110
+ "n_obs_steps": 1,
111
+ "normalization_mapping": {
112
+ "VISUAL": "MEAN_STD",
113
+ "STATE": "MEAN_STD",
114
+ "ACTION": "MEAN_STD"
115
+ },
116
+ "relative_actions": false,
117
+ "input_features": {
118
+ "observation.state": {
119
+ "type": "STATE",
120
+ "shape": [
121
+ 2
122
+ ]
123
+ },
124
+ "observation.images.front": {
125
+ "type": "VISUAL",
126
+ "shape": [
127
+ 3,
128
+ 240,
129
+ 240
130
+ ]
131
+ },
132
+ "observation.images.wrist": {
133
+ "type": "VISUAL",
134
+ "shape": [
135
+ 3,
136
+ 240,
137
+ 240
138
+ ]
139
+ }
140
+ },
141
+ "output_features": {
142
+ "action": {
143
+ "type": "ACTION",
144
+ "shape": [
145
+ 2
146
+ ]
147
+ }
148
+ },
149
+ "device": "cuda",
150
+ "use_amp": false,
151
+ "chunk_size": 50,
152
+ "n_action_steps": 50,
153
+ "vision_backbone": "resnet18",
154
+ "pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
155
+ "replace_final_stride_with_dilation": 0,
156
+ "pre_norm": false,
157
+ "dim_model": 512,
158
+ "n_heads": 8,
159
+ "dim_feedforward": 3200,
160
+ "feedforward_activation": "relu",
161
+ "n_encoder_layers": 4,
162
+ "n_decoder_layers": 1,
163
+ "use_vae": true,
164
+ "latent_dim": 32,
165
+ "n_vae_encoder_layers": 4,
166
+ "temporal_ensemble_coeff": null,
167
+ "dropout": 0.1,
168
+ "kl_weight": 10.0,
169
+ "optimizer_lr": 1e-05,
170
+ "optimizer_weight_decay": 0.0001,
171
+ "optimizer_lr_backbone": 1e-05
172
+ },
173
+ "output_dir": "outputs/train/pusht_60_v5/2025-09-07_00-15-58_act_abs_v5",
174
+ "job_name": "2025-09-07_00-15-58_act_abs_v5",
175
+ "resume": false,
176
+ "seed": 100000,
177
+ "num_workers": 4,
178
+ "batch_size": 512,
179
+ "steps": 20000,
180
+ "eval_freq": 2000,
181
+ "log_freq": 200,
182
+ "save_checkpoint": true,
183
+ "save_freq": 1000,
184
+ "use_policy_training_preset": true,
185
+ "optimizer": {
186
+ "type": "adamw",
187
+ "lr": 1e-05,
188
+ "weight_decay": 0.0001,
189
+ "grad_clip_norm": 10.0,
190
+ "betas": [
191
+ 0.9,
192
+ 0.999
193
+ ],
194
+ "eps": 1e-08
195
+ },
196
+ "scheduler": null,
197
+ "eval": {
198
+ "n_episodes": 50,
199
+ "batch_size": 50,
200
+ "use_async_envs": false
201
+ },
202
+ "wandb": {
203
+ "enable": true,
204
+ "disable_artifact": true,
205
+ "project": "lerobot",
206
+ "entity": null,
207
+ "notes": null,
208
+ "run_id": null,
209
+ "mode": null
210
+ }
211
+ }
checkpoints/005000/training_state/optimizer_param_groups.json ADDED
@@ -0,0 +1,191 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "lr": 1e-05,
4
+ "betas": [
5
+ 0.9,
6
+ 0.999
7
+ ],
8
+ "eps": 1e-08,
9
+ "weight_decay": 0.0001,
10
+ "amsgrad": false,
11
+ "maximize": false,
12
+ "foreach": null,
13
+ "capturable": false,
14
+ "differentiable": false,
15
+ "fused": null,
16
+ "decoupled_weight_decay": true,
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
+ ]
152
+ },
153
+ {
154
+ "lr": 1e-05,
155
+ "betas": [
156
+ 0.9,
157
+ 0.999
158
+ ],
159
+ "eps": 1e-08,
160
+ "weight_decay": 0.0001,
161
+ "amsgrad": false,
162
+ "maximize": false,
163
+ "foreach": null,
164
+ "capturable": false,
165
+ "differentiable": false,
166
+ "fused": null,
167
+ "decoupled_weight_decay": true,
168
+ "params": [
169
+ 133,
170
+ 134,
171
+ 135,
172
+ 136,
173
+ 137,
174
+ 138,
175
+ 139,
176
+ 140,
177
+ 141,
178
+ 142,
179
+ 143,
180
+ 144,
181
+ 145,
182
+ 146,
183
+ 147,
184
+ 148,
185
+ 149,
186
+ 150,
187
+ 151,
188
+ 152
189
+ ]
190
+ }
191
+ ]
checkpoints/005000/training_state/optimizer_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d9de02b2d02ff90245ce78756fdcfcae45d367962eaa72c322fc24cea0ccf5a
3
+ size 412547284
checkpoints/005000/training_state/rng_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab7d2c7ec5a229efcbb32ca18fbc91117053c07b01d5f1311fc0225ef5f367ae
3
+ size 15708
checkpoints/005000/training_state/training_step.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "step": 5000
3
+ }
checkpoints/006000/pretrained_model/config.json ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "type": "act",
3
+ "n_obs_steps": 1,
4
+ "normalization_mapping": {
5
+ "VISUAL": "MEAN_STD",
6
+ "STATE": "MEAN_STD",
7
+ "ACTION": "MEAN_STD"
8
+ },
9
+ "relative_actions": false,
10
+ "input_features": {
11
+ "observation.state": {
12
+ "type": "STATE",
13
+ "shape": [
14
+ 2
15
+ ]
16
+ },
17
+ "observation.images.front": {
18
+ "type": "VISUAL",
19
+ "shape": [
20
+ 3,
21
+ 240,
22
+ 240
23
+ ]
24
+ },
25
+ "observation.images.wrist": {
26
+ "type": "VISUAL",
27
+ "shape": [
28
+ 3,
29
+ 240,
30
+ 240
31
+ ]
32
+ }
33
+ },
34
+ "output_features": {
35
+ "action": {
36
+ "type": "ACTION",
37
+ "shape": [
38
+ 2
39
+ ]
40
+ }
41
+ },
42
+ "device": "cuda",
43
+ "use_amp": false,
44
+ "chunk_size": 50,
45
+ "n_action_steps": 50,
46
+ "vision_backbone": "resnet18",
47
+ "pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
48
+ "replace_final_stride_with_dilation": 0,
49
+ "pre_norm": false,
50
+ "dim_model": 512,
51
+ "n_heads": 8,
52
+ "dim_feedforward": 3200,
53
+ "feedforward_activation": "relu",
54
+ "n_encoder_layers": 4,
55
+ "n_decoder_layers": 1,
56
+ "use_vae": true,
57
+ "latent_dim": 32,
58
+ "n_vae_encoder_layers": 4,
59
+ "temporal_ensemble_coeff": null,
60
+ "dropout": 0.1,
61
+ "kl_weight": 10.0,
62
+ "optimizer_lr": 1e-05,
63
+ "optimizer_weight_decay": 0.0001,
64
+ "optimizer_lr_backbone": 1e-05
65
+ }
checkpoints/006000/pretrained_model/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d29ec89439c2316e82b1587a19a71e040074bf06c6fcffc6f2e87775ec3b54d
3
+ size 206463376
checkpoints/006000/pretrained_model/train_config.json ADDED
@@ -0,0 +1,211 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset": {
3
+ "repo_id": "pusht_60_v5",
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
+ -5,
75
+ 5
76
+ ]
77
+ }
78
+ },
79
+ "crop": {
80
+ "weight": 1.0,
81
+ "type": "RandomCrop",
82
+ "kwargs": {
83
+ "size": [
84
+ 200,
85
+ 200
86
+ ]
87
+ }
88
+ }
89
+ },
90
+ "downsample": {
91
+ "resize": {
92
+ "weight": 1.0,
93
+ "type": "Resize",
94
+ "kwargs": {
95
+ "size": [
96
+ 240,
97
+ 240
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": "act",
110
+ "n_obs_steps": 1,
111
+ "normalization_mapping": {
112
+ "VISUAL": "MEAN_STD",
113
+ "STATE": "MEAN_STD",
114
+ "ACTION": "MEAN_STD"
115
+ },
116
+ "relative_actions": false,
117
+ "input_features": {
118
+ "observation.state": {
119
+ "type": "STATE",
120
+ "shape": [
121
+ 2
122
+ ]
123
+ },
124
+ "observation.images.front": {
125
+ "type": "VISUAL",
126
+ "shape": [
127
+ 3,
128
+ 240,
129
+ 240
130
+ ]
131
+ },
132
+ "observation.images.wrist": {
133
+ "type": "VISUAL",
134
+ "shape": [
135
+ 3,
136
+ 240,
137
+ 240
138
+ ]
139
+ }
140
+ },
141
+ "output_features": {
142
+ "action": {
143
+ "type": "ACTION",
144
+ "shape": [
145
+ 2
146
+ ]
147
+ }
148
+ },
149
+ "device": "cuda",
150
+ "use_amp": false,
151
+ "chunk_size": 50,
152
+ "n_action_steps": 50,
153
+ "vision_backbone": "resnet18",
154
+ "pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
155
+ "replace_final_stride_with_dilation": 0,
156
+ "pre_norm": false,
157
+ "dim_model": 512,
158
+ "n_heads": 8,
159
+ "dim_feedforward": 3200,
160
+ "feedforward_activation": "relu",
161
+ "n_encoder_layers": 4,
162
+ "n_decoder_layers": 1,
163
+ "use_vae": true,
164
+ "latent_dim": 32,
165
+ "n_vae_encoder_layers": 4,
166
+ "temporal_ensemble_coeff": null,
167
+ "dropout": 0.1,
168
+ "kl_weight": 10.0,
169
+ "optimizer_lr": 1e-05,
170
+ "optimizer_weight_decay": 0.0001,
171
+ "optimizer_lr_backbone": 1e-05
172
+ },
173
+ "output_dir": "outputs/train/pusht_60_v5/2025-09-07_00-15-58_act_abs_v5",
174
+ "job_name": "2025-09-07_00-15-58_act_abs_v5",
175
+ "resume": false,
176
+ "seed": 100000,
177
+ "num_workers": 4,
178
+ "batch_size": 512,
179
+ "steps": 20000,
180
+ "eval_freq": 2000,
181
+ "log_freq": 200,
182
+ "save_checkpoint": true,
183
+ "save_freq": 1000,
184
+ "use_policy_training_preset": true,
185
+ "optimizer": {
186
+ "type": "adamw",
187
+ "lr": 1e-05,
188
+ "weight_decay": 0.0001,
189
+ "grad_clip_norm": 10.0,
190
+ "betas": [
191
+ 0.9,
192
+ 0.999
193
+ ],
194
+ "eps": 1e-08
195
+ },
196
+ "scheduler": null,
197
+ "eval": {
198
+ "n_episodes": 50,
199
+ "batch_size": 50,
200
+ "use_async_envs": false
201
+ },
202
+ "wandb": {
203
+ "enable": true,
204
+ "disable_artifact": true,
205
+ "project": "lerobot",
206
+ "entity": null,
207
+ "notes": null,
208
+ "run_id": null,
209
+ "mode": null
210
+ }
211
+ }
checkpoints/006000/training_state/optimizer_param_groups.json ADDED
@@ -0,0 +1,191 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "lr": 1e-05,
4
+ "betas": [
5
+ 0.9,
6
+ 0.999
7
+ ],
8
+ "eps": 1e-08,
9
+ "weight_decay": 0.0001,
10
+ "amsgrad": false,
11
+ "maximize": false,
12
+ "foreach": null,
13
+ "capturable": false,
14
+ "differentiable": false,
15
+ "fused": null,
16
+ "decoupled_weight_decay": true,
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
+ ]
152
+ },
153
+ {
154
+ "lr": 1e-05,
155
+ "betas": [
156
+ 0.9,
157
+ 0.999
158
+ ],
159
+ "eps": 1e-08,
160
+ "weight_decay": 0.0001,
161
+ "amsgrad": false,
162
+ "maximize": false,
163
+ "foreach": null,
164
+ "capturable": false,
165
+ "differentiable": false,
166
+ "fused": null,
167
+ "decoupled_weight_decay": true,
168
+ "params": [
169
+ 133,
170
+ 134,
171
+ 135,
172
+ 136,
173
+ 137,
174
+ 138,
175
+ 139,
176
+ 140,
177
+ 141,
178
+ 142,
179
+ 143,
180
+ 144,
181
+ 145,
182
+ 146,
183
+ 147,
184
+ 148,
185
+ 149,
186
+ 150,
187
+ 151,
188
+ 152
189
+ ]
190
+ }
191
+ ]
checkpoints/006000/training_state/optimizer_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98d308855d2e14b97cbd43c8796d04d0ed701366edc48c242bb06d2ded52c1e3
3
+ size 412547284
checkpoints/006000/training_state/rng_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:468da71908520580c7c1bdcded078acaa040698a397131f1e01dd22f729ad463
3
+ size 15708
checkpoints/006000/training_state/training_step.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "step": 6000
3
+ }
checkpoints/007000/pretrained_model/config.json ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "type": "act",
3
+ "n_obs_steps": 1,
4
+ "normalization_mapping": {
5
+ "VISUAL": "MEAN_STD",
6
+ "STATE": "MEAN_STD",
7
+ "ACTION": "MEAN_STD"
8
+ },
9
+ "relative_actions": false,
10
+ "input_features": {
11
+ "observation.state": {
12
+ "type": "STATE",
13
+ "shape": [
14
+ 2
15
+ ]
16
+ },
17
+ "observation.images.front": {
18
+ "type": "VISUAL",
19
+ "shape": [
20
+ 3,
21
+ 240,
22
+ 240
23
+ ]
24
+ },
25
+ "observation.images.wrist": {
26
+ "type": "VISUAL",
27
+ "shape": [
28
+ 3,
29
+ 240,
30
+ 240
31
+ ]
32
+ }
33
+ },
34
+ "output_features": {
35
+ "action": {
36
+ "type": "ACTION",
37
+ "shape": [
38
+ 2
39
+ ]
40
+ }
41
+ },
42
+ "device": "cuda",
43
+ "use_amp": false,
44
+ "chunk_size": 50,
45
+ "n_action_steps": 50,
46
+ "vision_backbone": "resnet18",
47
+ "pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
48
+ "replace_final_stride_with_dilation": 0,
49
+ "pre_norm": false,
50
+ "dim_model": 512,
51
+ "n_heads": 8,
52
+ "dim_feedforward": 3200,
53
+ "feedforward_activation": "relu",
54
+ "n_encoder_layers": 4,
55
+ "n_decoder_layers": 1,
56
+ "use_vae": true,
57
+ "latent_dim": 32,
58
+ "n_vae_encoder_layers": 4,
59
+ "temporal_ensemble_coeff": null,
60
+ "dropout": 0.1,
61
+ "kl_weight": 10.0,
62
+ "optimizer_lr": 1e-05,
63
+ "optimizer_weight_decay": 0.0001,
64
+ "optimizer_lr_backbone": 1e-05
65
+ }
checkpoints/007000/pretrained_model/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ab8605806082228ba0ac215d7cfda0c1d6f14dbf77a80eb7eb5c3927f8e8930
3
+ size 206463376
checkpoints/007000/pretrained_model/train_config.json ADDED
@@ -0,0 +1,211 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset": {
3
+ "repo_id": "pusht_60_v5",
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
+ -5,
75
+ 5
76
+ ]
77
+ }
78
+ },
79
+ "crop": {
80
+ "weight": 1.0,
81
+ "type": "RandomCrop",
82
+ "kwargs": {
83
+ "size": [
84
+ 200,
85
+ 200
86
+ ]
87
+ }
88
+ }
89
+ },
90
+ "downsample": {
91
+ "resize": {
92
+ "weight": 1.0,
93
+ "type": "Resize",
94
+ "kwargs": {
95
+ "size": [
96
+ 240,
97
+ 240
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": "act",
110
+ "n_obs_steps": 1,
111
+ "normalization_mapping": {
112
+ "VISUAL": "MEAN_STD",
113
+ "STATE": "MEAN_STD",
114
+ "ACTION": "MEAN_STD"
115
+ },
116
+ "relative_actions": false,
117
+ "input_features": {
118
+ "observation.state": {
119
+ "type": "STATE",
120
+ "shape": [
121
+ 2
122
+ ]
123
+ },
124
+ "observation.images.front": {
125
+ "type": "VISUAL",
126
+ "shape": [
127
+ 3,
128
+ 240,
129
+ 240
130
+ ]
131
+ },
132
+ "observation.images.wrist": {
133
+ "type": "VISUAL",
134
+ "shape": [
135
+ 3,
136
+ 240,
137
+ 240
138
+ ]
139
+ }
140
+ },
141
+ "output_features": {
142
+ "action": {
143
+ "type": "ACTION",
144
+ "shape": [
145
+ 2
146
+ ]
147
+ }
148
+ },
149
+ "device": "cuda",
150
+ "use_amp": false,
151
+ "chunk_size": 50,
152
+ "n_action_steps": 50,
153
+ "vision_backbone": "resnet18",
154
+ "pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
155
+ "replace_final_stride_with_dilation": 0,
156
+ "pre_norm": false,
157
+ "dim_model": 512,
158
+ "n_heads": 8,
159
+ "dim_feedforward": 3200,
160
+ "feedforward_activation": "relu",
161
+ "n_encoder_layers": 4,
162
+ "n_decoder_layers": 1,
163
+ "use_vae": true,
164
+ "latent_dim": 32,
165
+ "n_vae_encoder_layers": 4,
166
+ "temporal_ensemble_coeff": null,
167
+ "dropout": 0.1,
168
+ "kl_weight": 10.0,
169
+ "optimizer_lr": 1e-05,
170
+ "optimizer_weight_decay": 0.0001,
171
+ "optimizer_lr_backbone": 1e-05
172
+ },
173
+ "output_dir": "outputs/train/pusht_60_v5/2025-09-07_00-15-58_act_abs_v5",
174
+ "job_name": "2025-09-07_00-15-58_act_abs_v5",
175
+ "resume": false,
176
+ "seed": 100000,
177
+ "num_workers": 4,
178
+ "batch_size": 512,
179
+ "steps": 20000,
180
+ "eval_freq": 2000,
181
+ "log_freq": 200,
182
+ "save_checkpoint": true,
183
+ "save_freq": 1000,
184
+ "use_policy_training_preset": true,
185
+ "optimizer": {
186
+ "type": "adamw",
187
+ "lr": 1e-05,
188
+ "weight_decay": 0.0001,
189
+ "grad_clip_norm": 10.0,
190
+ "betas": [
191
+ 0.9,
192
+ 0.999
193
+ ],
194
+ "eps": 1e-08
195
+ },
196
+ "scheduler": null,
197
+ "eval": {
198
+ "n_episodes": 50,
199
+ "batch_size": 50,
200
+ "use_async_envs": false
201
+ },
202
+ "wandb": {
203
+ "enable": true,
204
+ "disable_artifact": true,
205
+ "project": "lerobot",
206
+ "entity": null,
207
+ "notes": null,
208
+ "run_id": null,
209
+ "mode": null
210
+ }
211
+ }
checkpoints/007000/training_state/optimizer_param_groups.json ADDED
@@ -0,0 +1,191 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "lr": 1e-05,
4
+ "betas": [
5
+ 0.9,
6
+ 0.999
7
+ ],
8
+ "eps": 1e-08,
9
+ "weight_decay": 0.0001,
10
+ "amsgrad": false,
11
+ "maximize": false,
12
+ "foreach": null,
13
+ "capturable": false,
14
+ "differentiable": false,
15
+ "fused": null,
16
+ "decoupled_weight_decay": true,
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
+ ]
152
+ },
153
+ {
154
+ "lr": 1e-05,
155
+ "betas": [
156
+ 0.9,
157
+ 0.999
158
+ ],
159
+ "eps": 1e-08,
160
+ "weight_decay": 0.0001,
161
+ "amsgrad": false,
162
+ "maximize": false,
163
+ "foreach": null,
164
+ "capturable": false,
165
+ "differentiable": false,
166
+ "fused": null,
167
+ "decoupled_weight_decay": true,
168
+ "params": [
169
+ 133,
170
+ 134,
171
+ 135,
172
+ 136,
173
+ 137,
174
+ 138,
175
+ 139,
176
+ 140,
177
+ 141,
178
+ 142,
179
+ 143,
180
+ 144,
181
+ 145,
182
+ 146,
183
+ 147,
184
+ 148,
185
+ 149,
186
+ 150,
187
+ 151,
188
+ 152
189
+ ]
190
+ }
191
+ ]
checkpoints/007000/training_state/optimizer_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:311d74b61d32243c0989ffac3592202cbc7d9a918301ab674439e861dc658425
3
+ size 412547284
checkpoints/007000/training_state/rng_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc8724a606eabf9298bbd5aa5ed4288663c5e24de08aef1a5807e61ebff2bc0c
3
+ size 15708
checkpoints/007000/training_state/training_step.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "step": 7000
3
+ }