Hugging Face's logo

hayren
/
eval_act_so100_test

Safetensors
Model card Files
xet
Community
1
hayren commited on
Commit
8bd8f80
·
verified ·
1 Parent(s): f36a39c

Upload folder using huggingface_hub

Browse files
Files changed (35) hide show
  1. 020000/pretrained_model/config.json +62 -0
  2. 020000/pretrained_model/model.safetensors +3 -0
  3. 020000/pretrained_model/train_config.json +167 -0
  4. 020000/training_state/optimizer_param_groups.json +189 -0
  5. 020000/training_state/optimizer_state.safetensors +3 -0
  6. 020000/training_state/rng_state.safetensors +3 -0
  7. 020000/training_state/training_step.json +3 -0
  8. 040000/pretrained_model/config.json +62 -0
  9. 040000/pretrained_model/model.safetensors +3 -0
  10. 040000/pretrained_model/train_config.json +167 -0
  11. 040000/training_state/optimizer_param_groups.json +189 -0
  12. 040000/training_state/optimizer_state.safetensors +3 -0
  13. 040000/training_state/rng_state.safetensors +3 -0
  14. 040000/training_state/training_step.json +3 -0
  15. 060000/pretrained_model/config.json +62 -0
  16. 060000/pretrained_model/model.safetensors +3 -0
  17. 060000/pretrained_model/train_config.json +167 -0
  18. 060000/training_state/optimizer_param_groups.json +189 -0
  19. 060000/training_state/optimizer_state.safetensors +3 -0
  20. 060000/training_state/rng_state.safetensors +3 -0
  21. 060000/training_state/training_step.json +3 -0
  22. 080000/pretrained_model/config.json +62 -0
  23. 080000/pretrained_model/model.safetensors +3 -0
  24. 080000/pretrained_model/train_config.json +167 -0
  25. 080000/training_state/optimizer_param_groups.json +189 -0
  26. 080000/training_state/optimizer_state.safetensors +3 -0
  27. 080000/training_state/rng_state.safetensors +3 -0
  28. 080000/training_state/training_step.json +3 -0
  29. 100000/pretrained_model/config.json +62 -0
  30. 100000/pretrained_model/model.safetensors +3 -0
  31. 100000/pretrained_model/train_config.json +167 -0
  32. 100000/training_state/optimizer_param_groups.json +189 -0
  33. 100000/training_state/optimizer_state.safetensors +3 -0
  34. 100000/training_state/rng_state.safetensors +3 -0
  35. 100000/training_state/training_step.json +3 -0
020000/pretrained_model/config.json ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "input_features": {
10
+ "observation.state": {
11
+ "type": "STATE",
12
+ "shape": [
13
+ 6
14
+ ]
15
+ },
16
+ "observation.images.laptop": {
17
+ "type": "VISUAL",
18
+ "shape": [
19
+ 3,
20
+ 480,
21
+ 640
22
+ ]
23
+ },
24
+ "observation.images.phone": {
25
+ "type": "VISUAL",
26
+ "shape": [
27
+ 3,
28
+ 480,
29
+ 640
30
+ ]
31
+ }
32
+ },
33
+ "output_features": {
34
+ "action": {
35
+ "type": "ACTION",
36
+ "shape": [
37
+ 6
38
+ ]
39
+ }
40
+ },
41
+ "chunk_size": 100,
42
+ "n_action_steps": 100,
43
+ "vision_backbone": "resnet18",
44
+ "pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
45
+ "replace_final_stride_with_dilation": false,
46
+ "pre_norm": false,
47
+ "dim_model": 512,
48
+ "n_heads": 8,
49
+ "dim_feedforward": 3200,
50
+ "feedforward_activation": "relu",
51
+ "n_encoder_layers": 4,
52
+ "n_decoder_layers": 1,
53
+ "use_vae": true,
54
+ "latent_dim": 32,
55
+ "n_vae_encoder_layers": 4,
56
+ "temporal_ensemble_coeff": null,
57
+ "dropout": 0.1,
58
+ "kl_weight": 10.0,
59
+ "optimizer_lr": 1e-05,
60
+ "optimizer_weight_decay": 0.0001,
61
+ "optimizer_lr_backbone": 1e-05
62
+ }
020000/pretrained_model/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b3c357d48705eb0427ed73f4368fe212f9eca6ec0d3195300729fd0644032c8
3
+ size 206701072
020000/pretrained_model/train_config.json ADDED
@@ -0,0 +1,167 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset": {
3
+ "repo_id": "gdut508/so100_test",
4
+ "episodes": null,
5
+ "image_transforms": {
6
+ "enable": false,
7
+ "max_num_transforms": 3,
8
+ "random_order": false,
9
+ "tfs": {
10
+ "brightness": {
11
+ "weight": 1.0,
12
+ "type": "ColorJitter",
13
+ "kwargs": {
14
+ "brightness": [
15
+ 0.8,
16
+ 1.2
17
+ ]
18
+ }
19
+ },
20
+ "contrast": {
21
+ "weight": 1.0,
22
+ "type": "ColorJitter",
23
+ "kwargs": {
24
+ "contrast": [
25
+ 0.8,
26
+ 1.2
27
+ ]
28
+ }
29
+ },
30
+ "saturation": {
31
+ "weight": 1.0,
32
+ "type": "ColorJitter",
33
+ "kwargs": {
34
+ "saturation": [
35
+ 0.5,
36
+ 1.5
37
+ ]
38
+ }
39
+ },
40
+ "hue": {
41
+ "weight": 1.0,
42
+ "type": "ColorJitter",
43
+ "kwargs": {
44
+ "hue": [
45
+ -0.05,
46
+ 0.05
47
+ ]
48
+ }
49
+ },
50
+ "sharpness": {
51
+ "weight": 1.0,
52
+ "type": "SharpnessJitter",
53
+ "kwargs": {
54
+ "sharpness": [
55
+ 0.5,
56
+ 1.5
57
+ ]
58
+ }
59
+ }
60
+ }
61
+ },
62
+ "local_files_only": false,
63
+ "use_imagenet_stats": true,
64
+ "video_backend": "pyav"
65
+ },
66
+ "env": null,
67
+ "policy": {
68
+ "type": "act",
69
+ "n_obs_steps": 1,
70
+ "normalization_mapping": {
71
+ "VISUAL": "MEAN_STD",
72
+ "STATE": "MEAN_STD",
73
+ "ACTION": "MEAN_STD"
74
+ },
75
+ "input_features": {
76
+ "observation.state": {
77
+ "type": "STATE",
78
+ "shape": [
79
+ 6
80
+ ]
81
+ },
82
+ "observation.images.laptop": {
83
+ "type": "VISUAL",
84
+ "shape": [
85
+ 3,
86
+ 480,
87
+ 640
88
+ ]
89
+ },
90
+ "observation.images.phone": {
91
+ "type": "VISUAL",
92
+ "shape": [
93
+ 3,
94
+ 480,
95
+ 640
96
+ ]
97
+ }
98
+ },
99
+ "output_features": {
100
+ "action": {
101
+ "type": "ACTION",
102
+ "shape": [
103
+ 6
104
+ ]
105
+ }
106
+ },
107
+ "chunk_size": 100,
108
+ "n_action_steps": 100,
109
+ "vision_backbone": "resnet18",
110
+ "pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
111
+ "replace_final_stride_with_dilation": false,
112
+ "pre_norm": false,
113
+ "dim_model": 512,
114
+ "n_heads": 8,
115
+ "dim_feedforward": 3200,
116
+ "feedforward_activation": "relu",
117
+ "n_encoder_layers": 4,
118
+ "n_decoder_layers": 1,
119
+ "use_vae": true,
120
+ "latent_dim": 32,
121
+ "n_vae_encoder_layers": 4,
122
+ "temporal_ensemble_coeff": null,
123
+ "dropout": 0.1,
124
+ "kl_weight": 10.0,
125
+ "optimizer_lr": 1e-05,
126
+ "optimizer_weight_decay": 0.0001,
127
+ "optimizer_lr_backbone": 1e-05
128
+ },
129
+ "output_dir": "outputs/train/act_so100_test",
130
+ "job_name": "act_so100_test",
131
+ "resume": false,
132
+ "device": "cuda",
133
+ "use_amp": false,
134
+ "seed": 1000,
135
+ "num_workers": 4,
136
+ "batch_size": 8,
137
+ "steps": 100000,
138
+ "eval_freq": 20000,
139
+ "log_freq": 200,
140
+ "save_checkpoint": true,
141
+ "save_freq": 20000,
142
+ "use_policy_training_preset": true,
143
+ "optimizer": {
144
+ "type": "adamw",
145
+ "lr": 1e-05,
146
+ "weight_decay": 0.0001,
147
+ "grad_clip_norm": 10.0,
148
+ "betas": [
149
+ 0.9,
150
+ 0.999
151
+ ],
152
+ "eps": 1e-08
153
+ },
154
+ "scheduler": null,
155
+ "eval": {
156
+ "n_episodes": 50,
157
+ "batch_size": 50,
158
+ "use_async_envs": false
159
+ },
160
+ "wandb": {
161
+ "enable": true,
162
+ "disable_artifact": false,
163
+ "project": "lerobot",
164
+ "entity": null,
165
+ "notes": null
166
+ }
167
+ }
020000/training_state/optimizer_param_groups.json ADDED
@@ -0,0 +1,189 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "foreach": null,
12
+ "maximize": false,
13
+ "capturable": false,
14
+ "differentiable": false,
15
+ "fused": null,
16
+ "params": [
17
+ 0,
18
+ 1,
19
+ 2,
20
+ 3,
21
+ 4,
22
+ 5,
23
+ 6,
24
+ 7,
25
+ 8,
26
+ 9,
27
+ 10,
28
+ 11,
29
+ 12,
30
+ 13,
31
+ 14,
32
+ 15,
33
+ 16,
34
+ 17,
35
+ 18,
36
+ 19,
37
+ 20,
38
+ 21,
39
+ 22,
40
+ 23,
41
+ 24,
42
+ 25,
43
+ 26,
44
+ 27,
45
+ 28,
46
+ 29,
47
+ 30,
48
+ 31,
49
+ 32,
50
+ 33,
51
+ 34,
52
+ 35,
53
+ 36,
54
+ 37,
55
+ 38,
56
+ 39,
57
+ 40,
58
+ 41,
59
+ 42,
60
+ 43,
61
+ 44,
62
+ 45,
63
+ 46,
64
+ 47,
65
+ 48,
66
+ 49,
67
+ 50,
68
+ 51,
69
+ 52,
70
+ 53,
71
+ 54,
72
+ 55,
73
+ 56,
74
+ 57,
75
+ 58,
76
+ 59,
77
+ 60,
78
+ 61,
79
+ 62,
80
+ 63,
81
+ 64,
82
+ 65,
83
+ 66,
84
+ 67,
85
+ 68,
86
+ 69,
87
+ 70,
88
+ 71,
89
+ 72,
90
+ 73,
91
+ 74,
92
+ 75,
93
+ 76,
94
+ 77,
95
+ 78,
96
+ 79,
97
+ 80,
98
+ 81,
99
+ 82,
100
+ 83,
101
+ 84,
102
+ 85,
103
+ 86,
104
+ 87,
105
+ 88,
106
+ 89,
107
+ 90,
108
+ 91,
109
+ 92,
110
+ 93,
111
+ 94,
112
+ 95,
113
+ 96,
114
+ 97,
115
+ 98,
116
+ 99,
117
+ 100,
118
+ 101,
119
+ 102,
120
+ 103,
121
+ 104,
122
+ 105,
123
+ 106,
124
+ 107,
125
+ 108,
126
+ 109,
127
+ 110,
128
+ 111,
129
+ 112,
130
+ 113,
131
+ 114,
132
+ 115,
133
+ 116,
134
+ 117,
135
+ 118,
136
+ 119,
137
+ 120,
138
+ 121,
139
+ 122,
140
+ 123,
141
+ 124,
142
+ 125,
143
+ 126,
144
+ 127,
145
+ 128,
146
+ 129,
147
+ 130,
148
+ 131,
149
+ 132
150
+ ]
151
+ },
152
+ {
153
+ "lr": 1e-05,
154
+ "betas": [
155
+ 0.9,
156
+ 0.999
157
+ ],
158
+ "eps": 1e-08,
159
+ "weight_decay": 0.0001,
160
+ "amsgrad": false,
161
+ "foreach": null,
162
+ "maximize": false,
163
+ "capturable": false,
164
+ "differentiable": false,
165
+ "fused": null,
166
+ "params": [
167
+ 133,
168
+ 134,
169
+ 135,
170
+ 136,
171
+ 137,
172
+ 138,
173
+ 139,
174
+ 140,
175
+ 141,
176
+ 142,
177
+ 143,
178
+ 144,
179
+ 145,
180
+ 146,
181
+ 147,
182
+ 148,
183
+ 149,
184
+ 150,
185
+ 151,
186
+ 152
187
+ ]
188
+ }
189
+ ]
020000/training_state/optimizer_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba602ce1c6953936d84a75b2c25fdbebfc21f1883aa2a705f62073bd5d84f2a3
3
+ size 412817652
020000/training_state/rng_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b6024ea278c4bc7cec5a96677253189e4d83a628fac01b1bafa0edd122c3b71
3
+ size 15708
020000/training_state/training_step.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "step": 20000
3
+ }
040000/pretrained_model/config.json ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "input_features": {
10
+ "observation.state": {
11
+ "type": "STATE",
12
+ "shape": [
13
+ 6
14
+ ]
15
+ },
16
+ "observation.images.laptop": {
17
+ "type": "VISUAL",
18
+ "shape": [
19
+ 3,
20
+ 480,
21
+ 640
22
+ ]
23
+ },
24
+ "observation.images.phone": {
25
+ "type": "VISUAL",
26
+ "shape": [
27
+ 3,
28
+ 480,
29
+ 640
30
+ ]
31
+ }
32
+ },
33
+ "output_features": {
34
+ "action": {
35
+ "type": "ACTION",
36
+ "shape": [
37
+ 6
38
+ ]
39
+ }
40
+ },
41
+ "chunk_size": 100,
42
+ "n_action_steps": 100,
43
+ "vision_backbone": "resnet18",
44
+ "pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
45
+ "replace_final_stride_with_dilation": false,
46
+ "pre_norm": false,
47
+ "dim_model": 512,
48
+ "n_heads": 8,
49
+ "dim_feedforward": 3200,
50
+ "feedforward_activation": "relu",
51
+ "n_encoder_layers": 4,
52
+ "n_decoder_layers": 1,
53
+ "use_vae": true,
54
+ "latent_dim": 32,
55
+ "n_vae_encoder_layers": 4,
56
+ "temporal_ensemble_coeff": null,
57
+ "dropout": 0.1,
58
+ "kl_weight": 10.0,
59
+ "optimizer_lr": 1e-05,
60
+ "optimizer_weight_decay": 0.0001,
61
+ "optimizer_lr_backbone": 1e-05
62
+ }
040000/pretrained_model/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c90d7581631adefdfe230f926bf434bd665b09451853ab6eb57efcfe4fa3474c
3
+ size 206701072
040000/pretrained_model/train_config.json ADDED
@@ -0,0 +1,167 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset": {
3
+ "repo_id": "gdut508/so100_test",
4
+ "episodes": null,
5
+ "image_transforms": {
6
+ "enable": false,
7
+ "max_num_transforms": 3,
8
+ "random_order": false,
9
+ "tfs": {
10
+ "brightness": {
11
+ "weight": 1.0,
12
+ "type": "ColorJitter",
13
+ "kwargs": {
14
+ "brightness": [
15
+ 0.8,
16
+ 1.2
17
+ ]
18
+ }
19
+ },
20
+ "contrast": {
21
+ "weight": 1.0,
22
+ "type": "ColorJitter",
23
+ "kwargs": {
24
+ "contrast": [
25
+ 0.8,
26
+ 1.2
27
+ ]
28
+ }
29
+ },
30
+ "saturation": {
31
+ "weight": 1.0,
32
+ "type": "ColorJitter",
33
+ "kwargs": {
34
+ "saturation": [
35
+ 0.5,
36
+ 1.5
37
+ ]
38
+ }
39
+ },
40
+ "hue": {
41
+ "weight": 1.0,
42
+ "type": "ColorJitter",
43
+ "kwargs": {
44
+ "hue": [
45
+ -0.05,
46
+ 0.05
47
+ ]
48
+ }
49
+ },
50
+ "sharpness": {
51
+ "weight": 1.0,
52
+ "type": "SharpnessJitter",
53
+ "kwargs": {
54
+ "sharpness": [
55
+ 0.5,
56
+ 1.5
57
+ ]
58
+ }
59
+ }
60
+ }
61
+ },
62
+ "local_files_only": false,
63
+ "use_imagenet_stats": true,
64
+ "video_backend": "pyav"
65
+ },
66
+ "env": null,
67
+ "policy": {
68
+ "type": "act",
69
+ "n_obs_steps": 1,
70
+ "normalization_mapping": {
71
+ "VISUAL": "MEAN_STD",
72
+ "STATE": "MEAN_STD",
73
+ "ACTION": "MEAN_STD"
74
+ },
75
+ "input_features": {
76
+ "observation.state": {
77
+ "type": "STATE",
78
+ "shape": [
79
+ 6
80
+ ]
81
+ },
82
+ "observation.images.laptop": {
83
+ "type": "VISUAL",
84
+ "shape": [
85
+ 3,
86
+ 480,
87
+ 640
88
+ ]
89
+ },
90
+ "observation.images.phone": {
91
+ "type": "VISUAL",
92
+ "shape": [
93
+ 3,
94
+ 480,
95
+ 640
96
+ ]
97
+ }
98
+ },
99
+ "output_features": {
100
+ "action": {
101
+ "type": "ACTION",
102
+ "shape": [
103
+ 6
104
+ ]
105
+ }
106
+ },
107
+ "chunk_size": 100,
108
+ "n_action_steps": 100,
109
+ "vision_backbone": "resnet18",
110
+ "pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
111
+ "replace_final_stride_with_dilation": false,
112
+ "pre_norm": false,
113
+ "dim_model": 512,
114
+ "n_heads": 8,
115
+ "dim_feedforward": 3200,
116
+ "feedforward_activation": "relu",
117
+ "n_encoder_layers": 4,
118
+ "n_decoder_layers": 1,
119
+ "use_vae": true,
120
+ "latent_dim": 32,
121
+ "n_vae_encoder_layers": 4,
122
+ "temporal_ensemble_coeff": null,
123
+ "dropout": 0.1,
124
+ "kl_weight": 10.0,
125
+ "optimizer_lr": 1e-05,
126
+ "optimizer_weight_decay": 0.0001,
127
+ "optimizer_lr_backbone": 1e-05
128
+ },
129
+ "output_dir": "outputs/train/act_so100_test",
130
+ "job_name": "act_so100_test",
131
+ "resume": false,
132
+ "device": "cuda",
133
+ "use_amp": false,
134
+ "seed": 1000,
135
+ "num_workers": 4,
136
+ "batch_size": 8,
137
+ "steps": 100000,
138
+ "eval_freq": 20000,
139
+ "log_freq": 200,
140
+ "save_checkpoint": true,
141
+ "save_freq": 20000,
142
+ "use_policy_training_preset": true,
143
+ "optimizer": {
144
+ "type": "adamw",
145
+ "lr": 1e-05,
146
+ "weight_decay": 0.0001,
147
+ "grad_clip_norm": 10.0,
148
+ "betas": [
149
+ 0.9,
150
+ 0.999
151
+ ],
152
+ "eps": 1e-08
153
+ },
154
+ "scheduler": null,
155
+ "eval": {
156
+ "n_episodes": 50,
157
+ "batch_size": 50,
158
+ "use_async_envs": false
159
+ },
160
+ "wandb": {
161
+ "enable": true,
162
+ "disable_artifact": false,
163
+ "project": "lerobot",
164
+ "entity": null,
165
+ "notes": null
166
+ }
167
+ }
040000/training_state/optimizer_param_groups.json ADDED
@@ -0,0 +1,189 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "foreach": null,
12
+ "maximize": false,
13
+ "capturable": false,
14
+ "differentiable": false,
15
+ "fused": null,
16
+ "params": [
17
+ 0,
18
+ 1,
19
+ 2,
20
+ 3,
21
+ 4,
22
+ 5,
23
+ 6,
24
+ 7,
25
+ 8,
26
+ 9,
27
+ 10,
28
+ 11,
29
+ 12,
30
+ 13,
31
+ 14,
32
+ 15,
33
+ 16,
34
+ 17,
35
+ 18,
36
+ 19,
37
+ 20,
38
+ 21,
39
+ 22,
40
+ 23,
41
+ 24,
42
+ 25,
43
+ 26,
44
+ 27,
45
+ 28,
46
+ 29,
47
+ 30,
48
+ 31,
49
+ 32,
50
+ 33,
51
+ 34,
52
+ 35,
53
+ 36,
54
+ 37,
55
+ 38,
56
+ 39,
57
+ 40,
58
+ 41,
59
+ 42,
60
+ 43,
61
+ 44,
62
+ 45,
63
+ 46,
64
+ 47,
65
+ 48,
66
+ 49,
67
+ 50,
68
+ 51,
69
+ 52,
70
+ 53,
71
+ 54,
72
+ 55,
73
+ 56,
74
+ 57,
75
+ 58,
76
+ 59,
77
+ 60,
78
+ 61,
79
+ 62,
80
+ 63,
81
+ 64,
82
+ 65,
83
+ 66,
84
+ 67,
85
+ 68,
86
+ 69,
87
+ 70,
88
+ 71,
89
+ 72,
90
+ 73,
91
+ 74,
92
+ 75,
93
+ 76,
94
+ 77,
95
+ 78,
96
+ 79,
97
+ 80,
98
+ 81,
99
+ 82,
100
+ 83,
101
+ 84,
102
+ 85,
103
+ 86,
104
+ 87,
105
+ 88,
106
+ 89,
107
+ 90,
108
+ 91,
109
+ 92,
110
+ 93,
111
+ 94,
112
+ 95,
113
+ 96,
114
+ 97,
115
+ 98,
116
+ 99,
117
+ 100,
118
+ 101,
119
+ 102,
120
+ 103,
121
+ 104,
122
+ 105,
123
+ 106,
124
+ 107,
125
+ 108,
126
+ 109,
127
+ 110,
128
+ 111,
129
+ 112,
130
+ 113,
131
+ 114,
132
+ 115,
133
+ 116,
134
+ 117,
135
+ 118,
136
+ 119,
137
+ 120,
138
+ 121,
139
+ 122,
140
+ 123,
141
+ 124,
142
+ 125,
143
+ 126,
144
+ 127,
145
+ 128,
146
+ 129,
147
+ 130,
148
+ 131,
149
+ 132
150
+ ]
151
+ },
152
+ {
153
+ "lr": 1e-05,
154
+ "betas": [
155
+ 0.9,
156
+ 0.999
157
+ ],
158
+ "eps": 1e-08,
159
+ "weight_decay": 0.0001,
160
+ "amsgrad": false,
161
+ "foreach": null,
162
+ "maximize": false,
163
+ "capturable": false,
164
+ "differentiable": false,
165
+ "fused": null,
166
+ "params": [
167
+ 133,
168
+ 134,
169
+ 135,
170
+ 136,
171
+ 137,
172
+ 138,
173
+ 139,
174
+ 140,
175
+ 141,
176
+ 142,
177
+ 143,
178
+ 144,
179
+ 145,
180
+ 146,
181
+ 147,
182
+ 148,
183
+ 149,
184
+ 150,
185
+ 151,
186
+ 152
187
+ ]
188
+ }
189
+ ]
040000/training_state/optimizer_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:693374489e8658051d18332e677d3555e6ca9c6009d799331348d85616ab3c0a
3
+ size 412817652
040000/training_state/rng_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ebeb88ed8b415db6eeaef7266b1578bf97c240272641f0ac7e4ea893544bac7c
3
+ size 15708
040000/training_state/training_step.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "step": 40000
3
+ }
060000/pretrained_model/config.json ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "input_features": {
10
+ "observation.state": {
11
+ "type": "STATE",
12
+ "shape": [
13
+ 6
14
+ ]
15
+ },
16
+ "observation.images.laptop": {
17
+ "type": "VISUAL",
18
+ "shape": [
19
+ 3,
20
+ 480,
21
+ 640
22
+ ]
23
+ },
24
+ "observation.images.phone": {
25
+ "type": "VISUAL",
26
+ "shape": [
27
+ 3,
28
+ 480,
29
+ 640
30
+ ]
31
+ }
32
+ },
33
+ "output_features": {
34
+ "action": {
35
+ "type": "ACTION",
36
+ "shape": [
37
+ 6
38
+ ]
39
+ }
40
+ },
41
+ "chunk_size": 100,
42
+ "n_action_steps": 100,
43
+ "vision_backbone": "resnet18",
44
+ "pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
45
+ "replace_final_stride_with_dilation": false,
46
+ "pre_norm": false,
47
+ "dim_model": 512,
48
+ "n_heads": 8,
49
+ "dim_feedforward": 3200,
50
+ "feedforward_activation": "relu",
51
+ "n_encoder_layers": 4,
52
+ "n_decoder_layers": 1,
53
+ "use_vae": true,
54
+ "latent_dim": 32,
55
+ "n_vae_encoder_layers": 4,
56
+ "temporal_ensemble_coeff": null,
57
+ "dropout": 0.1,
58
+ "kl_weight": 10.0,
59
+ "optimizer_lr": 1e-05,
60
+ "optimizer_weight_decay": 0.0001,
61
+ "optimizer_lr_backbone": 1e-05
62
+ }
060000/pretrained_model/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b90f7ef7c5c12062f8a5fc8a645fa971a550ad8e307ca7815a2b5a8e35dad4d4
3
+ size 206701072
060000/pretrained_model/train_config.json ADDED
@@ -0,0 +1,167 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset": {
3
+ "repo_id": "gdut508/so100_test",
4
+ "episodes": null,
5
+ "image_transforms": {
6
+ "enable": false,
7
+ "max_num_transforms": 3,
8
+ "random_order": false,
9
+ "tfs": {
10
+ "brightness": {
11
+ "weight": 1.0,
12
+ "type": "ColorJitter",
13
+ "kwargs": {
14
+ "brightness": [
15
+ 0.8,
16
+ 1.2
17
+ ]
18
+ }
19
+ },
20
+ "contrast": {
21
+ "weight": 1.0,
22
+ "type": "ColorJitter",
23
+ "kwargs": {
24
+ "contrast": [
25
+ 0.8,
26
+ 1.2
27
+ ]
28
+ }
29
+ },
30
+ "saturation": {
31
+ "weight": 1.0,
32
+ "type": "ColorJitter",
33
+ "kwargs": {
34
+ "saturation": [
35
+ 0.5,
36
+ 1.5
37
+ ]
38
+ }
39
+ },
40
+ "hue": {
41
+ "weight": 1.0,
42
+ "type": "ColorJitter",
43
+ "kwargs": {
44
+ "hue": [
45
+ -0.05,
46
+ 0.05
47
+ ]
48
+ }
49
+ },
50
+ "sharpness": {
51
+ "weight": 1.0,
52
+ "type": "SharpnessJitter",
53
+ "kwargs": {
54
+ "sharpness": [
55
+ 0.5,
56
+ 1.5
57
+ ]
58
+ }
59
+ }
60
+ }
61
+ },
62
+ "local_files_only": false,
63
+ "use_imagenet_stats": true,
64
+ "video_backend": "pyav"
65
+ },
66
+ "env": null,
67
+ "policy": {
68
+ "type": "act",
69
+ "n_obs_steps": 1,
70
+ "normalization_mapping": {
71
+ "VISUAL": "MEAN_STD",
72
+ "STATE": "MEAN_STD",
73
+ "ACTION": "MEAN_STD"
74
+ },
75
+ "input_features": {
76
+ "observation.state": {
77
+ "type": "STATE",
78
+ "shape": [
79
+ 6
80
+ ]
81
+ },
82
+ "observation.images.laptop": {
83
+ "type": "VISUAL",
84
+ "shape": [
85
+ 3,
86
+ 480,
87
+ 640
88
+ ]
89
+ },
90
+ "observation.images.phone": {
91
+ "type": "VISUAL",
92
+ "shape": [
93
+ 3,
94
+ 480,
95
+ 640
96
+ ]
97
+ }
98
+ },
99
+ "output_features": {
100
+ "action": {
101
+ "type": "ACTION",
102
+ "shape": [
103
+ 6
104
+ ]
105
+ }
106
+ },
107
+ "chunk_size": 100,
108
+ "n_action_steps": 100,
109
+ "vision_backbone": "resnet18",
110
+ "pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
111
+ "replace_final_stride_with_dilation": false,
112
+ "pre_norm": false,
113
+ "dim_model": 512,
114
+ "n_heads": 8,
115
+ "dim_feedforward": 3200,
116
+ "feedforward_activation": "relu",
117
+ "n_encoder_layers": 4,
118
+ "n_decoder_layers": 1,
119
+ "use_vae": true,
120
+ "latent_dim": 32,
121
+ "n_vae_encoder_layers": 4,
122
+ "temporal_ensemble_coeff": null,
123
+ "dropout": 0.1,
124
+ "kl_weight": 10.0,
125
+ "optimizer_lr": 1e-05,
126
+ "optimizer_weight_decay": 0.0001,
127
+ "optimizer_lr_backbone": 1e-05
128
+ },
129
+ "output_dir": "outputs/train/act_so100_test",
130
+ "job_name": "act_so100_test",
131
+ "resume": false,
132
+ "device": "cuda",
133
+ "use_amp": false,
134
+ "seed": 1000,
135
+ "num_workers": 4,
136
+ "batch_size": 8,
137
+ "steps": 100000,
138
+ "eval_freq": 20000,
139
+ "log_freq": 200,
140
+ "save_checkpoint": true,
141
+ "save_freq": 20000,
142
+ "use_policy_training_preset": true,
143
+ "optimizer": {
144
+ "type": "adamw",
145
+ "lr": 1e-05,
146
+ "weight_decay": 0.0001,
147
+ "grad_clip_norm": 10.0,
148
+ "betas": [
149
+ 0.9,
150
+ 0.999
151
+ ],
152
+ "eps": 1e-08
153
+ },
154
+ "scheduler": null,
155
+ "eval": {
156
+ "n_episodes": 50,
157
+ "batch_size": 50,
158
+ "use_async_envs": false
159
+ },
160
+ "wandb": {
161
+ "enable": true,
162
+ "disable_artifact": false,
163
+ "project": "lerobot",
164
+ "entity": null,
165
+ "notes": null
166
+ }
167
+ }
060000/training_state/optimizer_param_groups.json ADDED
@@ -0,0 +1,189 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "foreach": null,
12
+ "maximize": false,
13
+ "capturable": false,
14
+ "differentiable": false,
15
+ "fused": null,
16
+ "params": [
17
+ 0,
18
+ 1,
19
+ 2,
20
+ 3,
21
+ 4,
22
+ 5,
23
+ 6,
24
+ 7,
25
+ 8,
26
+ 9,
27
+ 10,
28
+ 11,
29
+ 12,
30
+ 13,
31
+ 14,
32
+ 15,
33
+ 16,
34
+ 17,
35
+ 18,
36
+ 19,
37
+ 20,
38
+ 21,
39
+ 22,
40
+ 23,
41
+ 24,
42
+ 25,
43
+ 26,
44
+ 27,
45
+ 28,
46
+ 29,
47
+ 30,
48
+ 31,
49
+ 32,
50
+ 33,
51
+ 34,
52
+ 35,
53
+ 36,
54
+ 37,
55
+ 38,
56
+ 39,
57
+ 40,
58
+ 41,
59
+ 42,
60
+ 43,
61
+ 44,
62
+ 45,
63
+ 46,
64
+ 47,
65
+ 48,
66
+ 49,
67
+ 50,
68
+ 51,
69
+ 52,
70
+ 53,
71
+ 54,
72
+ 55,
73
+ 56,
74
+ 57,
75
+ 58,
76
+ 59,
77
+ 60,
78
+ 61,
79
+ 62,
80
+ 63,
81
+ 64,
82
+ 65,
83
+ 66,
84
+ 67,
85
+ 68,
86
+ 69,
87
+ 70,
88
+ 71,
89
+ 72,
90
+ 73,
91
+ 74,
92
+ 75,
93
+ 76,
94
+ 77,
95
+ 78,
96
+ 79,
97
+ 80,
98
+ 81,
99
+ 82,
100
+ 83,
101
+ 84,
102
+ 85,
103
+ 86,
104
+ 87,
105
+ 88,
106
+ 89,
107
+ 90,
108
+ 91,
109
+ 92,
110
+ 93,
111
+ 94,
112
+ 95,
113
+ 96,
114
+ 97,
115
+ 98,
116
+ 99,
117
+ 100,
118
+ 101,
119
+ 102,
120
+ 103,
121
+ 104,
122
+ 105,
123
+ 106,
124
+ 107,
125
+ 108,
126
+ 109,
127
+ 110,
128
+ 111,
129
+ 112,
130
+ 113,
131
+ 114,
132
+ 115,
133
+ 116,
134
+ 117,
135
+ 118,
136
+ 119,
137
+ 120,
138
+ 121,
139
+ 122,
140
+ 123,
141
+ 124,
142
+ 125,
143
+ 126,
144
+ 127,
145
+ 128,
146
+ 129,
147
+ 130,
148
+ 131,
149
+ 132
150
+ ]
151
+ },
152
+ {
153
+ "lr": 1e-05,
154
+ "betas": [
155
+ 0.9,
156
+ 0.999
157
+ ],
158
+ "eps": 1e-08,
159
+ "weight_decay": 0.0001,
160
+ "amsgrad": false,
161
+ "foreach": null,
162
+ "maximize": false,
163
+ "capturable": false,
164
+ "differentiable": false,
165
+ "fused": null,
166
+ "params": [
167
+ 133,
168
+ 134,
169
+ 135,
170
+ 136,
171
+ 137,
172
+ 138,
173
+ 139,
174
+ 140,
175
+ 141,
176
+ 142,
177
+ 143,
178
+ 144,
179
+ 145,
180
+ 146,
181
+ 147,
182
+ 148,
183
+ 149,
184
+ 150,
185
+ 151,
186
+ 152
187
+ ]
188
+ }
189
+ ]
060000/training_state/optimizer_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95b4bcd59b02cda512039f461c26b7cc7204a290cd98b9fa6e587f4a89a2a852
3
+ size 412817652
060000/training_state/rng_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7719bc7f23334dc1a8e20f7a7e908295c93250f9f7aa355707a0a88be90b748d
3
+ size 15708
060000/training_state/training_step.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "step": 60000
3
+ }
080000/pretrained_model/config.json ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "input_features": {
10
+ "observation.state": {
11
+ "type": "STATE",
12
+ "shape": [
13
+ 6
14
+ ]
15
+ },
16
+ "observation.images.laptop": {
17
+ "type": "VISUAL",
18
+ "shape": [
19
+ 3,
20
+ 480,
21
+ 640
22
+ ]
23
+ },
24
+ "observation.images.phone": {
25
+ "type": "VISUAL",
26
+ "shape": [
27
+ 3,
28
+ 480,
29
+ 640
30
+ ]
31
+ }
32
+ },
33
+ "output_features": {
34
+ "action": {
35
+ "type": "ACTION",
36
+ "shape": [
37
+ 6
38
+ ]
39
+ }
40
+ },
41
+ "chunk_size": 100,
42
+ "n_action_steps": 100,
43
+ "vision_backbone": "resnet18",
44
+ "pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
45
+ "replace_final_stride_with_dilation": false,
46
+ "pre_norm": false,
47
+ "dim_model": 512,
48
+ "n_heads": 8,
49
+ "dim_feedforward": 3200,
50
+ "feedforward_activation": "relu",
51
+ "n_encoder_layers": 4,
52
+ "n_decoder_layers": 1,
53
+ "use_vae": true,
54
+ "latent_dim": 32,
55
+ "n_vae_encoder_layers": 4,
56
+ "temporal_ensemble_coeff": null,
57
+ "dropout": 0.1,
58
+ "kl_weight": 10.0,
59
+ "optimizer_lr": 1e-05,
60
+ "optimizer_weight_decay": 0.0001,
61
+ "optimizer_lr_backbone": 1e-05
62
+ }
080000/pretrained_model/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:827999aa0ddfdb7b75251eb0992dbc79f226e872517a1db0860cd122b75d6d27
3
+ size 206701072
080000/pretrained_model/train_config.json ADDED
@@ -0,0 +1,167 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset": {
3
+ "repo_id": "gdut508/so100_test",
4
+ "episodes": null,
5
+ "image_transforms": {
6
+ "enable": false,
7
+ "max_num_transforms": 3,
8
+ "random_order": false,
9
+ "tfs": {
10
+ "brightness": {
11
+ "weight": 1.0,
12
+ "type": "ColorJitter",
13
+ "kwargs": {
14
+ "brightness": [
15
+ 0.8,
16
+ 1.2
17
+ ]
18
+ }
19
+ },
20
+ "contrast": {
21
+ "weight": 1.0,
22
+ "type": "ColorJitter",
23
+ "kwargs": {
24
+ "contrast": [
25
+ 0.8,
26
+ 1.2
27
+ ]
28
+ }
29
+ },
30
+ "saturation": {
31
+ "weight": 1.0,
32
+ "type": "ColorJitter",
33
+ "kwargs": {
34
+ "saturation": [
35
+ 0.5,
36
+ 1.5
37
+ ]
38
+ }
39
+ },
40
+ "hue": {
41
+ "weight": 1.0,
42
+ "type": "ColorJitter",
43
+ "kwargs": {
44
+ "hue": [
45
+ -0.05,
46
+ 0.05
47
+ ]
48
+ }
49
+ },
50
+ "sharpness": {
51
+ "weight": 1.0,
52
+ "type": "SharpnessJitter",
53
+ "kwargs": {
54
+ "sharpness": [
55
+ 0.5,
56
+ 1.5
57
+ ]
58
+ }
59
+ }
60
+ }
61
+ },
62
+ "local_files_only": false,
63
+ "use_imagenet_stats": true,
64
+ "video_backend": "pyav"
65
+ },
66
+ "env": null,
67
+ "policy": {
68
+ "type": "act",
69
+ "n_obs_steps": 1,
70
+ "normalization_mapping": {
71
+ "VISUAL": "MEAN_STD",
72
+ "STATE": "MEAN_STD",
73
+ "ACTION": "MEAN_STD"
74
+ },
75
+ "input_features": {
76
+ "observation.state": {
77
+ "type": "STATE",
78
+ "shape": [
79
+ 6
80
+ ]
81
+ },
82
+ "observation.images.laptop": {
83
+ "type": "VISUAL",
84
+ "shape": [
85
+ 3,
86
+ 480,
87
+ 640
88
+ ]
89
+ },
90
+ "observation.images.phone": {
91
+ "type": "VISUAL",
92
+ "shape": [
93
+ 3,
94
+ 480,
95
+ 640
96
+ ]
97
+ }
98
+ },
99
+ "output_features": {
100
+ "action": {
101
+ "type": "ACTION",
102
+ "shape": [
103
+ 6
104
+ ]
105
+ }
106
+ },
107
+ "chunk_size": 100,
108
+ "n_action_steps": 100,
109
+ "vision_backbone": "resnet18",
110
+ "pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
111
+ "replace_final_stride_with_dilation": false,
112
+ "pre_norm": false,
113
+ "dim_model": 512,
114
+ "n_heads": 8,
115
+ "dim_feedforward": 3200,
116
+ "feedforward_activation": "relu",
117
+ "n_encoder_layers": 4,
118
+ "n_decoder_layers": 1,
119
+ "use_vae": true,
120
+ "latent_dim": 32,
121
+ "n_vae_encoder_layers": 4,
122
+ "temporal_ensemble_coeff": null,
123
+ "dropout": 0.1,
124
+ "kl_weight": 10.0,
125
+ "optimizer_lr": 1e-05,
126
+ "optimizer_weight_decay": 0.0001,
127
+ "optimizer_lr_backbone": 1e-05
128
+ },
129
+ "output_dir": "outputs/train/act_so100_test",
130
+ "job_name": "act_so100_test",
131
+ "resume": false,
132
+ "device": "cuda",
133
+ "use_amp": false,
134
+ "seed": 1000,
135
+ "num_workers": 4,
136
+ "batch_size": 8,
137
+ "steps": 100000,
138
+ "eval_freq": 20000,
139
+ "log_freq": 200,
140
+ "save_checkpoint": true,
141
+ "save_freq": 20000,
142
+ "use_policy_training_preset": true,
143
+ "optimizer": {
144
+ "type": "adamw",
145
+ "lr": 1e-05,
146
+ "weight_decay": 0.0001,
147
+ "grad_clip_norm": 10.0,
148
+ "betas": [
149
+ 0.9,
150
+ 0.999
151
+ ],
152
+ "eps": 1e-08
153
+ },
154
+ "scheduler": null,
155
+ "eval": {
156
+ "n_episodes": 50,
157
+ "batch_size": 50,
158
+ "use_async_envs": false
159
+ },
160
+ "wandb": {
161
+ "enable": true,
162
+ "disable_artifact": false,
163
+ "project": "lerobot",
164
+ "entity": null,
165
+ "notes": null
166
+ }
167
+ }
080000/training_state/optimizer_param_groups.json ADDED
@@ -0,0 +1,189 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "foreach": null,
12
+ "maximize": false,
13
+ "capturable": false,
14
+ "differentiable": false,
15
+ "fused": null,
16
+ "params": [
17
+ 0,
18
+ 1,
19
+ 2,
20
+ 3,
21
+ 4,
22
+ 5,
23
+ 6,
24
+ 7,
25
+ 8,
26
+ 9,
27
+ 10,
28
+ 11,
29
+ 12,
30
+ 13,
31
+ 14,
32
+ 15,
33
+ 16,
34
+ 17,
35
+ 18,
36
+ 19,
37
+ 20,
38
+ 21,
39
+ 22,
40
+ 23,
41
+ 24,
42
+ 25,
43
+ 26,
44
+ 27,
45
+ 28,
46
+ 29,
47
+ 30,
48
+ 31,
49
+ 32,
50
+ 33,
51
+ 34,
52
+ 35,
53
+ 36,
54
+ 37,
55
+ 38,
56
+ 39,
57
+ 40,
58
+ 41,
59
+ 42,
60
+ 43,
61
+ 44,
62
+ 45,
63
+ 46,
64
+ 47,
65
+ 48,
66
+ 49,
67
+ 50,
68
+ 51,
69
+ 52,
70
+ 53,
71
+ 54,
72
+ 55,
73
+ 56,
74
+ 57,
75
+ 58,
76
+ 59,
77
+ 60,
78
+ 61,
79
+ 62,
80
+ 63,
81
+ 64,
82
+ 65,
83
+ 66,
84
+ 67,
85
+ 68,
86
+ 69,
87
+ 70,
88
+ 71,
89
+ 72,
90
+ 73,
91
+ 74,
92
+ 75,
93
+ 76,
94
+ 77,
95
+ 78,
96
+ 79,
97
+ 80,
98
+ 81,
99
+ 82,
100
+ 83,
101
+ 84,
102
+ 85,
103
+ 86,
104
+ 87,
105
+ 88,
106
+ 89,
107
+ 90,
108
+ 91,
109
+ 92,
110
+ 93,
111
+ 94,
112
+ 95,
113
+ 96,
114
+ 97,
115
+ 98,
116
+ 99,
117
+ 100,
118
+ 101,
119
+ 102,
120
+ 103,
121
+ 104,
122
+ 105,
123
+ 106,
124
+ 107,
125
+ 108,
126
+ 109,
127
+ 110,
128
+ 111,
129
+ 112,
130
+ 113,
131
+ 114,
132
+ 115,
133
+ 116,
134
+ 117,
135
+ 118,
136
+ 119,
137
+ 120,
138
+ 121,
139
+ 122,
140
+ 123,
141
+ 124,
142
+ 125,
143
+ 126,
144
+ 127,
145
+ 128,
146
+ 129,
147
+ 130,
148
+ 131,
149
+ 132
150
+ ]
151
+ },
152
+ {
153
+ "lr": 1e-05,
154
+ "betas": [
155
+ 0.9,
156
+ 0.999
157
+ ],
158
+ "eps": 1e-08,
159
+ "weight_decay": 0.0001,
160
+ "amsgrad": false,
161
+ "foreach": null,
162
+ "maximize": false,
163
+ "capturable": false,
164
+ "differentiable": false,
165
+ "fused": null,
166
+ "params": [
167
+ 133,
168
+ 134,
169
+ 135,
170
+ 136,
171
+ 137,
172
+ 138,
173
+ 139,
174
+ 140,
175
+ 141,
176
+ 142,
177
+ 143,
178
+ 144,
179
+ 145,
180
+ 146,
181
+ 147,
182
+ 148,
183
+ 149,
184
+ 150,
185
+ 151,
186
+ 152
187
+ ]
188
+ }
189
+ ]
080000/training_state/optimizer_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a291108a9da99af13c4b5e15d3a6402e04051f56fa6af788e3c6144805d99424
3
+ size 412817652
080000/training_state/rng_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:733e2be4f002093cad140e583bcee9532fe4939df0c253e3460a67e8c4520b83
3
+ size 15708
080000/training_state/training_step.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "step": 80000
3
+ }
100000/pretrained_model/config.json ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "input_features": {
10
+ "observation.state": {
11
+ "type": "STATE",
12
+ "shape": [
13
+ 6
14
+ ]
15
+ },
16
+ "observation.images.laptop": {
17
+ "type": "VISUAL",
18
+ "shape": [
19
+ 3,
20
+ 480,
21
+ 640
22
+ ]
23
+ },
24
+ "observation.images.phone": {
25
+ "type": "VISUAL",
26
+ "shape": [
27
+ 3,
28
+ 480,
29
+ 640
30
+ ]
31
+ }
32
+ },
33
+ "output_features": {
34
+ "action": {
35
+ "type": "ACTION",
36
+ "shape": [
37
+ 6
38
+ ]
39
+ }
40
+ },
41
+ "chunk_size": 100,
42
+ "n_action_steps": 100,
43
+ "vision_backbone": "resnet18",
44
+ "pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
45
+ "replace_final_stride_with_dilation": false,
46
+ "pre_norm": false,
47
+ "dim_model": 512,
48
+ "n_heads": 8,
49
+ "dim_feedforward": 3200,
50
+ "feedforward_activation": "relu",
51
+ "n_encoder_layers": 4,
52
+ "n_decoder_layers": 1,
53
+ "use_vae": true,
54
+ "latent_dim": 32,
55
+ "n_vae_encoder_layers": 4,
56
+ "temporal_ensemble_coeff": null,
57
+ "dropout": 0.1,
58
+ "kl_weight": 10.0,
59
+ "optimizer_lr": 1e-05,
60
+ "optimizer_weight_decay": 0.0001,
61
+ "optimizer_lr_backbone": 1e-05
62
+ }
100000/pretrained_model/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:988eaf2bc6e780bee2f832b22f2b12e6da8a491be283256d100a87b420e1a66e
3
+ size 206701072
100000/pretrained_model/train_config.json ADDED
@@ -0,0 +1,167 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset": {
3
+ "repo_id": "gdut508/so100_test",
4
+ "episodes": null,
5
+ "image_transforms": {
6
+ "enable": false,
7
+ "max_num_transforms": 3,
8
+ "random_order": false,
9
+ "tfs": {
10
+ "brightness": {
11
+ "weight": 1.0,
12
+ "type": "ColorJitter",
13
+ "kwargs": {
14
+ "brightness": [
15
+ 0.8,
16
+ 1.2
17
+ ]
18
+ }
19
+ },
20
+ "contrast": {
21
+ "weight": 1.0,
22
+ "type": "ColorJitter",
23
+ "kwargs": {
24
+ "contrast": [
25
+ 0.8,
26
+ 1.2
27
+ ]
28
+ }
29
+ },
30
+ "saturation": {
31
+ "weight": 1.0,
32
+ "type": "ColorJitter",
33
+ "kwargs": {
34
+ "saturation": [
35
+ 0.5,
36
+ 1.5
37
+ ]
38
+ }
39
+ },
40
+ "hue": {
41
+ "weight": 1.0,
42
+ "type": "ColorJitter",
43
+ "kwargs": {
44
+ "hue": [
45
+ -0.05,
46
+ 0.05
47
+ ]
48
+ }
49
+ },
50
+ "sharpness": {
51
+ "weight": 1.0,
52
+ "type": "SharpnessJitter",
53
+ "kwargs": {
54
+ "sharpness": [
55
+ 0.5,
56
+ 1.5
57
+ ]
58
+ }
59
+ }
60
+ }
61
+ },
62
+ "local_files_only": false,
63
+ "use_imagenet_stats": true,
64
+ "video_backend": "pyav"
65
+ },
66
+ "env": null,
67
+ "policy": {
68
+ "type": "act",
69
+ "n_obs_steps": 1,
70
+ "normalization_mapping": {
71
+ "VISUAL": "MEAN_STD",
72
+ "STATE": "MEAN_STD",
73
+ "ACTION": "MEAN_STD"
74
+ },
75
+ "input_features": {
76
+ "observation.state": {
77
+ "type": "STATE",
78
+ "shape": [
79
+ 6
80
+ ]
81
+ },
82
+ "observation.images.laptop": {
83
+ "type": "VISUAL",
84
+ "shape": [
85
+ 3,
86
+ 480,
87
+ 640
88
+ ]
89
+ },
90
+ "observation.images.phone": {
91
+ "type": "VISUAL",
92
+ "shape": [
93
+ 3,
94
+ 480,
95
+ 640
96
+ ]
97
+ }
98
+ },
99
+ "output_features": {
100
+ "action": {
101
+ "type": "ACTION",
102
+ "shape": [
103
+ 6
104
+ ]
105
+ }
106
+ },
107
+ "chunk_size": 100,
108
+ "n_action_steps": 100,
109
+ "vision_backbone": "resnet18",
110
+ "pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
111
+ "replace_final_stride_with_dilation": false,
112
+ "pre_norm": false,
113
+ "dim_model": 512,
114
+ "n_heads": 8,
115
+ "dim_feedforward": 3200,
116
+ "feedforward_activation": "relu",
117
+ "n_encoder_layers": 4,
118
+ "n_decoder_layers": 1,
119
+ "use_vae": true,
120
+ "latent_dim": 32,
121
+ "n_vae_encoder_layers": 4,
122
+ "temporal_ensemble_coeff": null,
123
+ "dropout": 0.1,
124
+ "kl_weight": 10.0,
125
+ "optimizer_lr": 1e-05,
126
+ "optimizer_weight_decay": 0.0001,
127
+ "optimizer_lr_backbone": 1e-05
128
+ },
129
+ "output_dir": "outputs/train/act_so100_test",
130
+ "job_name": "act_so100_test",
131
+ "resume": false,
132
+ "device": "cuda",
133
+ "use_amp": false,
134
+ "seed": 1000,
135
+ "num_workers": 4,
136
+ "batch_size": 8,
137
+ "steps": 100000,
138
+ "eval_freq": 20000,
139
+ "log_freq": 200,
140
+ "save_checkpoint": true,
141
+ "save_freq": 20000,
142
+ "use_policy_training_preset": true,
143
+ "optimizer": {
144
+ "type": "adamw",
145
+ "lr": 1e-05,
146
+ "weight_decay": 0.0001,
147
+ "grad_clip_norm": 10.0,
148
+ "betas": [
149
+ 0.9,
150
+ 0.999
151
+ ],
152
+ "eps": 1e-08
153
+ },
154
+ "scheduler": null,
155
+ "eval": {
156
+ "n_episodes": 50,
157
+ "batch_size": 50,
158
+ "use_async_envs": false
159
+ },
160
+ "wandb": {
161
+ "enable": true,
162
+ "disable_artifact": false,
163
+ "project": "lerobot",
164
+ "entity": null,
165
+ "notes": null
166
+ }
167
+ }
100000/training_state/optimizer_param_groups.json ADDED
@@ -0,0 +1,189 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "foreach": null,
12
+ "maximize": false,
13
+ "capturable": false,
14
+ "differentiable": false,
15
+ "fused": null,
16
+ "params": [
17
+ 0,
18
+ 1,
19
+ 2,
20
+ 3,
21
+ 4,
22
+ 5,
23
+ 6,
24
+ 7,
25
+ 8,
26
+ 9,
27
+ 10,
28
+ 11,
29
+ 12,
30
+ 13,
31
+ 14,
32
+ 15,
33
+ 16,
34
+ 17,
35
+ 18,
36
+ 19,
37
+ 20,
38
+ 21,
39
+ 22,
40
+ 23,
41
+ 24,
42
+ 25,
43
+ 26,
44
+ 27,
45
+ 28,
46
+ 29,
47
+ 30,
48
+ 31,
49
+ 32,
50
+ 33,
51
+ 34,
52
+ 35,
53
+ 36,
54
+ 37,
55
+ 38,
56
+ 39,
57
+ 40,
58
+ 41,
59
+ 42,
60
+ 43,
61
+ 44,
62
+ 45,
63
+ 46,
64
+ 47,
65
+ 48,
66
+ 49,
67
+ 50,
68
+ 51,
69
+ 52,
70
+ 53,
71
+ 54,
72
+ 55,
73
+ 56,
74
+ 57,
75
+ 58,
76
+ 59,
77
+ 60,
78
+ 61,
79
+ 62,
80
+ 63,
81
+ 64,
82
+ 65,
83
+ 66,
84
+ 67,
85
+ 68,
86
+ 69,
87
+ 70,
88
+ 71,
89
+ 72,
90
+ 73,
91
+ 74,
92
+ 75,
93
+ 76,
94
+ 77,
95
+ 78,
96
+ 79,
97
+ 80,
98
+ 81,
99
+ 82,
100
+ 83,
101
+ 84,
102
+ 85,
103
+ 86,
104
+ 87,
105
+ 88,
106
+ 89,
107
+ 90,
108
+ 91,
109
+ 92,
110
+ 93,
111
+ 94,
112
+ 95,
113
+ 96,
114
+ 97,
115
+ 98,
116
+ 99,
117
+ 100,
118
+ 101,
119
+ 102,
120
+ 103,
121
+ 104,
122
+ 105,
123
+ 106,
124
+ 107,
125
+ 108,
126
+ 109,
127
+ 110,
128
+ 111,
129
+ 112,
130
+ 113,
131
+ 114,
132
+ 115,
133
+ 116,
134
+ 117,
135
+ 118,
136
+ 119,
137
+ 120,
138
+ 121,
139
+ 122,
140
+ 123,
141
+ 124,
142
+ 125,
143
+ 126,
144
+ 127,
145
+ 128,
146
+ 129,
147
+ 130,
148
+ 131,
149
+ 132
150
+ ]
151
+ },
152
+ {
153
+ "lr": 1e-05,
154
+ "betas": [
155
+ 0.9,
156
+ 0.999
157
+ ],
158
+ "eps": 1e-08,
159
+ "weight_decay": 0.0001,
160
+ "amsgrad": false,
161
+ "foreach": null,
162
+ "maximize": false,
163
+ "capturable": false,
164
+ "differentiable": false,
165
+ "fused": null,
166
+ "params": [
167
+ 133,
168
+ 134,
169
+ 135,
170
+ 136,
171
+ 137,
172
+ 138,
173
+ 139,
174
+ 140,
175
+ 141,
176
+ 142,
177
+ 143,
178
+ 144,
179
+ 145,
180
+ 146,
181
+ 147,
182
+ 148,
183
+ 149,
184
+ 150,
185
+ 151,
186
+ 152
187
+ ]
188
+ }
189
+ ]
100000/training_state/optimizer_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba12fa93e375098a27ecb37eea921ff8c5c6a68f5f435ee65306ade89b7d3ff4
3
+ size 412817652
100000/training_state/rng_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e07bb0176d9f1f1f2a942cf90c72d07d27c72e47d65cc8e01b0622c2866e68c9
3
+ size 15708
100000/training_state/training_step.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "step": 100000
3
+ }