Hugging Face's logo

siyulw2025
/
trash_picking_cache

Safetensors
Model card Files
xet
Community
siyulw2025 commited on
Commit
fe7a495
·
verified ·
1 Parent(s): 508c908

Upload all checkpoints from 20k to 100k

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. trash_picking_cache/020000/pretrained_model/config.json +69 -0
  2. trash_picking_cache/020000/pretrained_model/model.safetensors +3 -0
  3. trash_picking_cache/020000/pretrained_model/policy_postprocessor.json +32 -0
  4. trash_picking_cache/020000/pretrained_model/policy_postprocessor_step_0_unnormalizer_processor.safetensors +3 -0
  5. trash_picking_cache/020000/pretrained_model/policy_preprocessor.json +64 -0
  6. trash_picking_cache/020000/pretrained_model/policy_preprocessor_step_3_normalizer_processor.safetensors +3 -0
  7. trash_picking_cache/020000/pretrained_model/train_config.json +176 -0
  8. trash_picking_cache/020000/training_state/optimizer_param_groups.json +191 -0
  9. trash_picking_cache/020000/training_state/optimizer_state.safetensors +3 -0
  10. trash_picking_cache/020000/training_state/rng_state.safetensors +3 -0
  11. trash_picking_cache/020000/training_state/training_step.json +3 -0
  12. trash_picking_cache/040000/pretrained_model/config.json +69 -0
  13. trash_picking_cache/040000/pretrained_model/model.safetensors +3 -0
  14. trash_picking_cache/040000/pretrained_model/policy_postprocessor.json +32 -0
  15. trash_picking_cache/040000/pretrained_model/policy_postprocessor_step_0_unnormalizer_processor.safetensors +3 -0
  16. trash_picking_cache/040000/pretrained_model/policy_preprocessor.json +64 -0
  17. trash_picking_cache/040000/pretrained_model/policy_preprocessor_step_3_normalizer_processor.safetensors +3 -0
  18. trash_picking_cache/040000/pretrained_model/train_config.json +176 -0
  19. trash_picking_cache/040000/training_state/optimizer_param_groups.json +191 -0
  20. trash_picking_cache/040000/training_state/optimizer_state.safetensors +3 -0
  21. trash_picking_cache/040000/training_state/rng_state.safetensors +3 -0
  22. trash_picking_cache/040000/training_state/training_step.json +3 -0
  23. trash_picking_cache/060000/pretrained_model/config.json +69 -0
  24. trash_picking_cache/060000/pretrained_model/model.safetensors +3 -0
  25. trash_picking_cache/060000/pretrained_model/policy_postprocessor.json +32 -0
  26. trash_picking_cache/060000/pretrained_model/policy_postprocessor_step_0_unnormalizer_processor.safetensors +3 -0
  27. trash_picking_cache/060000/pretrained_model/policy_preprocessor.json +64 -0
  28. trash_picking_cache/060000/pretrained_model/policy_preprocessor_step_3_normalizer_processor.safetensors +3 -0
  29. trash_picking_cache/060000/pretrained_model/train_config.json +176 -0
  30. trash_picking_cache/060000/training_state/optimizer_param_groups.json +191 -0
  31. trash_picking_cache/060000/training_state/optimizer_state.safetensors +3 -0
  32. trash_picking_cache/060000/training_state/rng_state.safetensors +3 -0
  33. trash_picking_cache/060000/training_state/training_step.json +3 -0
  34. trash_picking_cache/080000/pretrained_model/config.json +69 -0
  35. trash_picking_cache/080000/pretrained_model/model.safetensors +3 -0
  36. trash_picking_cache/080000/pretrained_model/policy_postprocessor.json +32 -0
  37. trash_picking_cache/080000/pretrained_model/policy_postprocessor_step_0_unnormalizer_processor.safetensors +3 -0
  38. trash_picking_cache/080000/pretrained_model/policy_preprocessor.json +64 -0
  39. trash_picking_cache/080000/pretrained_model/policy_preprocessor_step_3_normalizer_processor.safetensors +3 -0
  40. trash_picking_cache/080000/pretrained_model/train_config.json +176 -0
  41. trash_picking_cache/080000/training_state/optimizer_param_groups.json +191 -0
  42. trash_picking_cache/080000/training_state/optimizer_state.safetensors +3 -0
  43. trash_picking_cache/080000/training_state/rng_state.safetensors +3 -0
  44. trash_picking_cache/080000/training_state/training_step.json +3 -0
  45. trash_picking_cache/100000/pretrained_model/config.json +69 -0
  46. trash_picking_cache/100000/pretrained_model/model.safetensors +3 -0
  47. trash_picking_cache/100000/pretrained_model/policy_postprocessor.json +32 -0
  48. trash_picking_cache/100000/pretrained_model/policy_postprocessor_step_0_unnormalizer_processor.safetensors +3 -0
  49. trash_picking_cache/100000/pretrained_model/policy_preprocessor.json +64 -0
  50. trash_picking_cache/100000/pretrained_model/policy_preprocessor_step_3_normalizer_processor.safetensors +3 -0
trash_picking_cache/020000/pretrained_model/config.json ADDED
@@ -0,0 +1,69 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "type": "act",
3
+ "n_obs_steps": 1,
4
+ "input_features": {
5
+ "observation.state": {
6
+ "type": "STATE",
7
+ "shape": [
8
+ 6
9
+ ]
10
+ },
11
+ "observation.images.front": {
12
+ "type": "VISUAL",
13
+ "shape": [
14
+ 3,
15
+ 1080,
16
+ 1920
17
+ ]
18
+ },
19
+ "observation.images.top": {
20
+ "type": "VISUAL",
21
+ "shape": [
22
+ 3,
23
+ 720,
24
+ 1280
25
+ ]
26
+ }
27
+ },
28
+ "output_features": {
29
+ "action": {
30
+ "type": "ACTION",
31
+ "shape": [
32
+ 6
33
+ ]
34
+ }
35
+ },
36
+ "device": "cuda",
37
+ "use_amp": false,
38
+ "push_to_hub": true,
39
+ "repo_id": "siyulw2025/trash_picking",
40
+ "private": null,
41
+ "tags": null,
42
+ "license": null,
43
+ "chunk_size": 100,
44
+ "n_action_steps": 100,
45
+ "normalization_mapping": {
46
+ "VISUAL": "MEAN_STD",
47
+ "STATE": "MEAN_STD",
48
+ "ACTION": "MEAN_STD"
49
+ },
50
+ "vision_backbone": "resnet18",
51
+ "pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
52
+ "replace_final_stride_with_dilation": false,
53
+ "pre_norm": false,
54
+ "dim_model": 512,
55
+ "n_heads": 8,
56
+ "dim_feedforward": 3200,
57
+ "feedforward_activation": "relu",
58
+ "n_encoder_layers": 4,
59
+ "n_decoder_layers": 1,
60
+ "use_vae": true,
61
+ "latent_dim": 32,
62
+ "n_vae_encoder_layers": 4,
63
+ "temporal_ensemble_coeff": null,
64
+ "dropout": 0.1,
65
+ "kl_weight": 10.0,
66
+ "optimizer_lr": 1e-05,
67
+ "optimizer_weight_decay": 0.0001,
68
+ "optimizer_lr_backbone": 1e-05
69
+ }
trash_picking_cache/020000/pretrained_model/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1006116557366e94083cc4bd0318a07993c170f6db5877ed06c67950cd35cd30
3
+ size 206699736
trash_picking_cache/020000/pretrained_model/policy_postprocessor.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "name": "policy_postprocessor",
3
+ "steps": [
4
+ {
5
+ "registry_name": "unnormalizer_processor",
6
+ "config": {
7
+ "eps": 1e-08,
8
+ "features": {
9
+ "action": {
10
+ "type": "ACTION",
11
+ "shape": [
12
+ 6
13
+ ]
14
+ }
15
+ },
16
+ "norm_map": {
17
+ "VISUAL": "MEAN_STD",
18
+ "STATE": "MEAN_STD",
19
+ "ACTION": "MEAN_STD"
20
+ }
21
+ },
22
+ "state_file": "policy_postprocessor_step_0_unnormalizer_processor.safetensors"
23
+ },
24
+ {
25
+ "registry_name": "device_processor",
26
+ "config": {
27
+ "device": "cpu",
28
+ "float_dtype": null
29
+ }
30
+ }
31
+ ]
32
+ }
trash_picking_cache/020000/pretrained_model/policy_postprocessor_step_0_unnormalizer_processor.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:984d7923641cde3536b62f7fcee347ab4a2c5e24c09af3b8c4382083afb0172f
3
+ size 3748
trash_picking_cache/020000/pretrained_model/policy_preprocessor.json ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "name": "policy_preprocessor",
3
+ "steps": [
4
+ {
5
+ "registry_name": "rename_observations_processor",
6
+ "config": {
7
+ "rename_map": {}
8
+ }
9
+ },
10
+ {
11
+ "registry_name": "to_batch_processor",
12
+ "config": {}
13
+ },
14
+ {
15
+ "registry_name": "device_processor",
16
+ "config": {
17
+ "device": "cuda",
18
+ "float_dtype": null
19
+ }
20
+ },
21
+ {
22
+ "registry_name": "normalizer_processor",
23
+ "config": {
24
+ "eps": 1e-08,
25
+ "features": {
26
+ "observation.state": {
27
+ "type": "STATE",
28
+ "shape": [
29
+ 6
30
+ ]
31
+ },
32
+ "observation.images.front": {
33
+ "type": "VISUAL",
34
+ "shape": [
35
+ 3,
36
+ 1080,
37
+ 1920
38
+ ]
39
+ },
40
+ "observation.images.top": {
41
+ "type": "VISUAL",
42
+ "shape": [
43
+ 3,
44
+ 720,
45
+ 1280
46
+ ]
47
+ },
48
+ "action": {
49
+ "type": "ACTION",
50
+ "shape": [
51
+ 6
52
+ ]
53
+ }
54
+ },
55
+ "norm_map": {
56
+ "VISUAL": "MEAN_STD",
57
+ "STATE": "MEAN_STD",
58
+ "ACTION": "MEAN_STD"
59
+ }
60
+ },
61
+ "state_file": "policy_preprocessor_step_3_normalizer_processor.safetensors"
62
+ }
63
+ ]
64
+ }
trash_picking_cache/020000/pretrained_model/policy_preprocessor_step_3_normalizer_processor.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:984d7923641cde3536b62f7fcee347ab4a2c5e24c09af3b8c4382083afb0172f
3
+ size 3748
trash_picking_cache/020000/pretrained_model/train_config.json ADDED
@@ -0,0 +1,176 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset": {
3
+ "repo_id": "siyulw2025/minions001",
4
+ "root": null,
5
+ "episodes": null,
6
+ "image_transforms": {
7
+ "enable": false,
8
+ "max_num_transforms": 3,
9
+ "random_order": false,
10
+ "tfs": {
11
+ "brightness": {
12
+ "weight": 1.0,
13
+ "type": "ColorJitter",
14
+ "kwargs": {
15
+ "brightness": [
16
+ 0.8,
17
+ 1.2
18
+ ]
19
+ }
20
+ },
21
+ "contrast": {
22
+ "weight": 1.0,
23
+ "type": "ColorJitter",
24
+ "kwargs": {
25
+ "contrast": [
26
+ 0.8,
27
+ 1.2
28
+ ]
29
+ }
30
+ },
31
+ "saturation": {
32
+ "weight": 1.0,
33
+ "type": "ColorJitter",
34
+ "kwargs": {
35
+ "saturation": [
36
+ 0.5,
37
+ 1.5
38
+ ]
39
+ }
40
+ },
41
+ "hue": {
42
+ "weight": 1.0,
43
+ "type": "ColorJitter",
44
+ "kwargs": {
45
+ "hue": [
46
+ -0.05,
47
+ 0.05
48
+ ]
49
+ }
50
+ },
51
+ "sharpness": {
52
+ "weight": 1.0,
53
+ "type": "SharpnessJitter",
54
+ "kwargs": {
55
+ "sharpness": [
56
+ 0.5,
57
+ 1.5
58
+ ]
59
+ }
60
+ }
61
+ }
62
+ },
63
+ "revision": null,
64
+ "use_imagenet_stats": true,
65
+ "video_backend": "torchcodec",
66
+ "streaming": false
67
+ },
68
+ "env": null,
69
+ "policy": {
70
+ "type": "act",
71
+ "n_obs_steps": 1,
72
+ "input_features": {
73
+ "observation.state": {
74
+ "type": "STATE",
75
+ "shape": [
76
+ 6
77
+ ]
78
+ },
79
+ "observation.images.front": {
80
+ "type": "VISUAL",
81
+ "shape": [
82
+ 3,
83
+ 1080,
84
+ 1920
85
+ ]
86
+ },
87
+ "observation.images.top": {
88
+ "type": "VISUAL",
89
+ "shape": [
90
+ 3,
91
+ 720,
92
+ 1280
93
+ ]
94
+ }
95
+ },
96
+ "output_features": {
97
+ "action": {
98
+ "type": "ACTION",
99
+ "shape": [
100
+ 6
101
+ ]
102
+ }
103
+ },
104
+ "device": "cuda",
105
+ "use_amp": false,
106
+ "push_to_hub": true,
107
+ "repo_id": "siyulw2025/trash_picking",
108
+ "private": null,
109
+ "tags": null,
110
+ "license": null,
111
+ "chunk_size": 100,
112
+ "n_action_steps": 100,
113
+ "normalization_mapping": {
114
+ "VISUAL": "MEAN_STD",
115
+ "STATE": "MEAN_STD",
116
+ "ACTION": "MEAN_STD"
117
+ },
118
+ "vision_backbone": "resnet18",
119
+ "pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
120
+ "replace_final_stride_with_dilation": false,
121
+ "pre_norm": false,
122
+ "dim_model": 512,
123
+ "n_heads": 8,
124
+ "dim_feedforward": 3200,
125
+ "feedforward_activation": "relu",
126
+ "n_encoder_layers": 4,
127
+ "n_decoder_layers": 1,
128
+ "use_vae": true,
129
+ "latent_dim": 32,
130
+ "n_vae_encoder_layers": 4,
131
+ "temporal_ensemble_coeff": null,
132
+ "dropout": 0.1,
133
+ "kl_weight": 10.0,
134
+ "optimizer_lr": 1e-05,
135
+ "optimizer_weight_decay": 0.0001,
136
+ "optimizer_lr_backbone": 1e-05
137
+ },
138
+ "output_dir": "outputs/train/minions001",
139
+ "job_name": "trash_picking",
140
+ "resume": false,
141
+ "seed": 1000,
142
+ "num_workers": 4,
143
+ "batch_size": 1,
144
+ "steps": 100000,
145
+ "eval_freq": 20000,
146
+ "log_freq": 200,
147
+ "save_checkpoint": true,
148
+ "save_freq": 20000,
149
+ "use_policy_training_preset": true,
150
+ "optimizer": {
151
+ "type": "adamw",
152
+ "lr": 1e-05,
153
+ "weight_decay": 0.0001,
154
+ "grad_clip_norm": 10.0,
155
+ "betas": [
156
+ 0.9,
157
+ 0.999
158
+ ],
159
+ "eps": 1e-08
160
+ },
161
+ "scheduler": null,
162
+ "eval": {
163
+ "n_episodes": 50,
164
+ "batch_size": 50,
165
+ "use_async_envs": false
166
+ },
167
+ "wandb": {
168
+ "enable": false,
169
+ "disable_artifact": false,
170
+ "project": "lerobot",
171
+ "entity": null,
172
+ "notes": null,
173
+ "run_id": null,
174
+ "mode": null
175
+ }
176
+ }
trash_picking_cache/020000/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
+ ]
trash_picking_cache/020000/training_state/optimizer_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21265bf4b106adf567558c9c9bc43e854d31ef50c6325ca3a1a07932a6f14736
3
+ size 412817652
trash_picking_cache/020000/training_state/rng_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf718f1bdfb1eeeec7e1e2bd4bf735eac73f90071d1ca60b51728a94a0d9cbb2
3
+ size 15708
trash_picking_cache/020000/training_state/training_step.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "step": 20000
3
+ }
trash_picking_cache/040000/pretrained_model/config.json ADDED
@@ -0,0 +1,69 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "type": "act",
3
+ "n_obs_steps": 1,
4
+ "input_features": {
5
+ "observation.state": {
6
+ "type": "STATE",
7
+ "shape": [
8
+ 6
9
+ ]
10
+ },
11
+ "observation.images.front": {
12
+ "type": "VISUAL",
13
+ "shape": [
14
+ 3,
15
+ 1080,
16
+ 1920
17
+ ]
18
+ },
19
+ "observation.images.top": {
20
+ "type": "VISUAL",
21
+ "shape": [
22
+ 3,
23
+ 720,
24
+ 1280
25
+ ]
26
+ }
27
+ },
28
+ "output_features": {
29
+ "action": {
30
+ "type": "ACTION",
31
+ "shape": [
32
+ 6
33
+ ]
34
+ }
35
+ },
36
+ "device": "cuda",
37
+ "use_amp": false,
38
+ "push_to_hub": true,
39
+ "repo_id": "siyulw2025/trash_picking",
40
+ "private": null,
41
+ "tags": null,
42
+ "license": null,
43
+ "chunk_size": 100,
44
+ "n_action_steps": 100,
45
+ "normalization_mapping": {
46
+ "VISUAL": "MEAN_STD",
47
+ "STATE": "MEAN_STD",
48
+ "ACTION": "MEAN_STD"
49
+ },
50
+ "vision_backbone": "resnet18",
51
+ "pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
52
+ "replace_final_stride_with_dilation": false,
53
+ "pre_norm": false,
54
+ "dim_model": 512,
55
+ "n_heads": 8,
56
+ "dim_feedforward": 3200,
57
+ "feedforward_activation": "relu",
58
+ "n_encoder_layers": 4,
59
+ "n_decoder_layers": 1,
60
+ "use_vae": true,
61
+ "latent_dim": 32,
62
+ "n_vae_encoder_layers": 4,
63
+ "temporal_ensemble_coeff": null,
64
+ "dropout": 0.1,
65
+ "kl_weight": 10.0,
66
+ "optimizer_lr": 1e-05,
67
+ "optimizer_weight_decay": 0.0001,
68
+ "optimizer_lr_backbone": 1e-05
69
+ }
trash_picking_cache/040000/pretrained_model/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5851011d160c7f390495a0f73981ba72d3e239d9b5e4fdd4f48c618f60eaa4f
3
+ size 206699736
trash_picking_cache/040000/pretrained_model/policy_postprocessor.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "name": "policy_postprocessor",
3
+ "steps": [
4
+ {
5
+ "registry_name": "unnormalizer_processor",
6
+ "config": {
7
+ "eps": 1e-08,
8
+ "features": {
9
+ "action": {
10
+ "type": "ACTION",
11
+ "shape": [
12
+ 6
13
+ ]
14
+ }
15
+ },
16
+ "norm_map": {
17
+ "VISUAL": "MEAN_STD",
18
+ "STATE": "MEAN_STD",
19
+ "ACTION": "MEAN_STD"
20
+ }
21
+ },
22
+ "state_file": "policy_postprocessor_step_0_unnormalizer_processor.safetensors"
23
+ },
24
+ {
25
+ "registry_name": "device_processor",
26
+ "config": {
27
+ "device": "cpu",
28
+ "float_dtype": null
29
+ }
30
+ }
31
+ ]
32
+ }
trash_picking_cache/040000/pretrained_model/policy_postprocessor_step_0_unnormalizer_processor.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:984d7923641cde3536b62f7fcee347ab4a2c5e24c09af3b8c4382083afb0172f
3
+ size 3748
trash_picking_cache/040000/pretrained_model/policy_preprocessor.json ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "name": "policy_preprocessor",
3
+ "steps": [
4
+ {
5
+ "registry_name": "rename_observations_processor",
6
+ "config": {
7
+ "rename_map": {}
8
+ }
9
+ },
10
+ {
11
+ "registry_name": "to_batch_processor",
12
+ "config": {}
13
+ },
14
+ {
15
+ "registry_name": "device_processor",
16
+ "config": {
17
+ "device": "cuda",
18
+ "float_dtype": null
19
+ }
20
+ },
21
+ {
22
+ "registry_name": "normalizer_processor",
23
+ "config": {
24
+ "eps": 1e-08,
25
+ "features": {
26
+ "observation.state": {
27
+ "type": "STATE",
28
+ "shape": [
29
+ 6
30
+ ]
31
+ },
32
+ "observation.images.front": {
33
+ "type": "VISUAL",
34
+ "shape": [
35
+ 3,
36
+ 1080,
37
+ 1920
38
+ ]
39
+ },
40
+ "observation.images.top": {
41
+ "type": "VISUAL",
42
+ "shape": [
43
+ 3,
44
+ 720,
45
+ 1280
46
+ ]
47
+ },
48
+ "action": {
49
+ "type": "ACTION",
50
+ "shape": [
51
+ 6
52
+ ]
53
+ }
54
+ },
55
+ "norm_map": {
56
+ "VISUAL": "MEAN_STD",
57
+ "STATE": "MEAN_STD",
58
+ "ACTION": "MEAN_STD"
59
+ }
60
+ },
61
+ "state_file": "policy_preprocessor_step_3_normalizer_processor.safetensors"
62
+ }
63
+ ]
64
+ }
trash_picking_cache/040000/pretrained_model/policy_preprocessor_step_3_normalizer_processor.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:984d7923641cde3536b62f7fcee347ab4a2c5e24c09af3b8c4382083afb0172f
3
+ size 3748
trash_picking_cache/040000/pretrained_model/train_config.json ADDED
@@ -0,0 +1,176 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset": {
3
+ "repo_id": "siyulw2025/minions001",
4
+ "root": null,
5
+ "episodes": null,
6
+ "image_transforms": {
7
+ "enable": false,
8
+ "max_num_transforms": 3,
9
+ "random_order": false,
10
+ "tfs": {
11
+ "brightness": {
12
+ "weight": 1.0,
13
+ "type": "ColorJitter",
14
+ "kwargs": {
15
+ "brightness": [
16
+ 0.8,
17
+ 1.2
18
+ ]
19
+ }
20
+ },
21
+ "contrast": {
22
+ "weight": 1.0,
23
+ "type": "ColorJitter",
24
+ "kwargs": {
25
+ "contrast": [
26
+ 0.8,
27
+ 1.2
28
+ ]
29
+ }
30
+ },
31
+ "saturation": {
32
+ "weight": 1.0,
33
+ "type": "ColorJitter",
34
+ "kwargs": {
35
+ "saturation": [
36
+ 0.5,
37
+ 1.5
38
+ ]
39
+ }
40
+ },
41
+ "hue": {
42
+ "weight": 1.0,
43
+ "type": "ColorJitter",
44
+ "kwargs": {
45
+ "hue": [
46
+ -0.05,
47
+ 0.05
48
+ ]
49
+ }
50
+ },
51
+ "sharpness": {
52
+ "weight": 1.0,
53
+ "type": "SharpnessJitter",
54
+ "kwargs": {
55
+ "sharpness": [
56
+ 0.5,
57
+ 1.5
58
+ ]
59
+ }
60
+ }
61
+ }
62
+ },
63
+ "revision": null,
64
+ "use_imagenet_stats": true,
65
+ "video_backend": "torchcodec",
66
+ "streaming": false
67
+ },
68
+ "env": null,
69
+ "policy": {
70
+ "type": "act",
71
+ "n_obs_steps": 1,
72
+ "input_features": {
73
+ "observation.state": {
74
+ "type": "STATE",
75
+ "shape": [
76
+ 6
77
+ ]
78
+ },
79
+ "observation.images.front": {
80
+ "type": "VISUAL",
81
+ "shape": [
82
+ 3,
83
+ 1080,
84
+ 1920
85
+ ]
86
+ },
87
+ "observation.images.top": {
88
+ "type": "VISUAL",
89
+ "shape": [
90
+ 3,
91
+ 720,
92
+ 1280
93
+ ]
94
+ }
95
+ },
96
+ "output_features": {
97
+ "action": {
98
+ "type": "ACTION",
99
+ "shape": [
100
+ 6
101
+ ]
102
+ }
103
+ },
104
+ "device": "cuda",
105
+ "use_amp": false,
106
+ "push_to_hub": true,
107
+ "repo_id": "siyulw2025/trash_picking",
108
+ "private": null,
109
+ "tags": null,
110
+ "license": null,
111
+ "chunk_size": 100,
112
+ "n_action_steps": 100,
113
+ "normalization_mapping": {
114
+ "VISUAL": "MEAN_STD",
115
+ "STATE": "MEAN_STD",
116
+ "ACTION": "MEAN_STD"
117
+ },
118
+ "vision_backbone": "resnet18",
119
+ "pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
120
+ "replace_final_stride_with_dilation": false,
121
+ "pre_norm": false,
122
+ "dim_model": 512,
123
+ "n_heads": 8,
124
+ "dim_feedforward": 3200,
125
+ "feedforward_activation": "relu",
126
+ "n_encoder_layers": 4,
127
+ "n_decoder_layers": 1,
128
+ "use_vae": true,
129
+ "latent_dim": 32,
130
+ "n_vae_encoder_layers": 4,
131
+ "temporal_ensemble_coeff": null,
132
+ "dropout": 0.1,
133
+ "kl_weight": 10.0,
134
+ "optimizer_lr": 1e-05,
135
+ "optimizer_weight_decay": 0.0001,
136
+ "optimizer_lr_backbone": 1e-05
137
+ },
138
+ "output_dir": "outputs/train/minions001",
139
+ "job_name": "trash_picking",
140
+ "resume": false,
141
+ "seed": 1000,
142
+ "num_workers": 4,
143
+ "batch_size": 1,
144
+ "steps": 100000,
145
+ "eval_freq": 20000,
146
+ "log_freq": 200,
147
+ "save_checkpoint": true,
148
+ "save_freq": 20000,
149
+ "use_policy_training_preset": true,
150
+ "optimizer": {
151
+ "type": "adamw",
152
+ "lr": 1e-05,
153
+ "weight_decay": 0.0001,
154
+ "grad_clip_norm": 10.0,
155
+ "betas": [
156
+ 0.9,
157
+ 0.999
158
+ ],
159
+ "eps": 1e-08
160
+ },
161
+ "scheduler": null,
162
+ "eval": {
163
+ "n_episodes": 50,
164
+ "batch_size": 50,
165
+ "use_async_envs": false
166
+ },
167
+ "wandb": {
168
+ "enable": false,
169
+ "disable_artifact": false,
170
+ "project": "lerobot",
171
+ "entity": null,
172
+ "notes": null,
173
+ "run_id": null,
174
+ "mode": null
175
+ }
176
+ }
trash_picking_cache/040000/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
+ ]
trash_picking_cache/040000/training_state/optimizer_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ca84a67caaa3d7ab8baab5148afba9908c594edc7ed0be6f927bccbd34dfb17
3
+ size 412817652
trash_picking_cache/040000/training_state/rng_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8ea4422d6fc035e71ce8ce213c42aa304232e1f2550326cd04e5fd1283ab23c
3
+ size 15708
trash_picking_cache/040000/training_state/training_step.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "step": 40000
3
+ }
trash_picking_cache/060000/pretrained_model/config.json ADDED
@@ -0,0 +1,69 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "type": "act",
3
+ "n_obs_steps": 1,
4
+ "input_features": {
5
+ "observation.state": {
6
+ "type": "STATE",
7
+ "shape": [
8
+ 6
9
+ ]
10
+ },
11
+ "observation.images.front": {
12
+ "type": "VISUAL",
13
+ "shape": [
14
+ 3,
15
+ 1080,
16
+ 1920
17
+ ]
18
+ },
19
+ "observation.images.top": {
20
+ "type": "VISUAL",
21
+ "shape": [
22
+ 3,
23
+ 720,
24
+ 1280
25
+ ]
26
+ }
27
+ },
28
+ "output_features": {
29
+ "action": {
30
+ "type": "ACTION",
31
+ "shape": [
32
+ 6
33
+ ]
34
+ }
35
+ },
36
+ "device": "cuda",
37
+ "use_amp": false,
38
+ "push_to_hub": true,
39
+ "repo_id": "siyulw2025/trash_picking",
40
+ "private": null,
41
+ "tags": null,
42
+ "license": null,
43
+ "chunk_size": 100,
44
+ "n_action_steps": 100,
45
+ "normalization_mapping": {
46
+ "VISUAL": "MEAN_STD",
47
+ "STATE": "MEAN_STD",
48
+ "ACTION": "MEAN_STD"
49
+ },
50
+ "vision_backbone": "resnet18",
51
+ "pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
52
+ "replace_final_stride_with_dilation": false,
53
+ "pre_norm": false,
54
+ "dim_model": 512,
55
+ "n_heads": 8,
56
+ "dim_feedforward": 3200,
57
+ "feedforward_activation": "relu",
58
+ "n_encoder_layers": 4,
59
+ "n_decoder_layers": 1,
60
+ "use_vae": true,
61
+ "latent_dim": 32,
62
+ "n_vae_encoder_layers": 4,
63
+ "temporal_ensemble_coeff": null,
64
+ "dropout": 0.1,
65
+ "kl_weight": 10.0,
66
+ "optimizer_lr": 1e-05,
67
+ "optimizer_weight_decay": 0.0001,
68
+ "optimizer_lr_backbone": 1e-05
69
+ }
trash_picking_cache/060000/pretrained_model/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75e1d5aaa05bff51993d9c8dba642e45326cbd64c5d7fdc1e1f779e080c2390d
3
+ size 206699736
trash_picking_cache/060000/pretrained_model/policy_postprocessor.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "name": "policy_postprocessor",
3
+ "steps": [
4
+ {
5
+ "registry_name": "unnormalizer_processor",
6
+ "config": {
7
+ "eps": 1e-08,
8
+ "features": {
9
+ "action": {
10
+ "type": "ACTION",
11
+ "shape": [
12
+ 6
13
+ ]
14
+ }
15
+ },
16
+ "norm_map": {
17
+ "VISUAL": "MEAN_STD",
18
+ "STATE": "MEAN_STD",
19
+ "ACTION": "MEAN_STD"
20
+ }
21
+ },
22
+ "state_file": "policy_postprocessor_step_0_unnormalizer_processor.safetensors"
23
+ },
24
+ {
25
+ "registry_name": "device_processor",
26
+ "config": {
27
+ "device": "cpu",
28
+ "float_dtype": null
29
+ }
30
+ }
31
+ ]
32
+ }
trash_picking_cache/060000/pretrained_model/policy_postprocessor_step_0_unnormalizer_processor.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:984d7923641cde3536b62f7fcee347ab4a2c5e24c09af3b8c4382083afb0172f
3
+ size 3748
trash_picking_cache/060000/pretrained_model/policy_preprocessor.json ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "name": "policy_preprocessor",
3
+ "steps": [
4
+ {
5
+ "registry_name": "rename_observations_processor",
6
+ "config": {
7
+ "rename_map": {}
8
+ }
9
+ },
10
+ {
11
+ "registry_name": "to_batch_processor",
12
+ "config": {}
13
+ },
14
+ {
15
+ "registry_name": "device_processor",
16
+ "config": {
17
+ "device": "cuda",
18
+ "float_dtype": null
19
+ }
20
+ },
21
+ {
22
+ "registry_name": "normalizer_processor",
23
+ "config": {
24
+ "eps": 1e-08,
25
+ "features": {
26
+ "observation.state": {
27
+ "type": "STATE",
28
+ "shape": [
29
+ 6
30
+ ]
31
+ },
32
+ "observation.images.front": {
33
+ "type": "VISUAL",
34
+ "shape": [
35
+ 3,
36
+ 1080,
37
+ 1920
38
+ ]
39
+ },
40
+ "observation.images.top": {
41
+ "type": "VISUAL",
42
+ "shape": [
43
+ 3,
44
+ 720,
45
+ 1280
46
+ ]
47
+ },
48
+ "action": {
49
+ "type": "ACTION",
50
+ "shape": [
51
+ 6
52
+ ]
53
+ }
54
+ },
55
+ "norm_map": {
56
+ "VISUAL": "MEAN_STD",
57
+ "STATE": "MEAN_STD",
58
+ "ACTION": "MEAN_STD"
59
+ }
60
+ },
61
+ "state_file": "policy_preprocessor_step_3_normalizer_processor.safetensors"
62
+ }
63
+ ]
64
+ }
trash_picking_cache/060000/pretrained_model/policy_preprocessor_step_3_normalizer_processor.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:984d7923641cde3536b62f7fcee347ab4a2c5e24c09af3b8c4382083afb0172f
3
+ size 3748
trash_picking_cache/060000/pretrained_model/train_config.json ADDED
@@ -0,0 +1,176 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset": {
3
+ "repo_id": "siyulw2025/minions001",
4
+ "root": null,
5
+ "episodes": null,
6
+ "image_transforms": {
7
+ "enable": false,
8
+ "max_num_transforms": 3,
9
+ "random_order": false,
10
+ "tfs": {
11
+ "brightness": {
12
+ "weight": 1.0,
13
+ "type": "ColorJitter",
14
+ "kwargs": {
15
+ "brightness": [
16
+ 0.8,
17
+ 1.2
18
+ ]
19
+ }
20
+ },
21
+ "contrast": {
22
+ "weight": 1.0,
23
+ "type": "ColorJitter",
24
+ "kwargs": {
25
+ "contrast": [
26
+ 0.8,
27
+ 1.2
28
+ ]
29
+ }
30
+ },
31
+ "saturation": {
32
+ "weight": 1.0,
33
+ "type": "ColorJitter",
34
+ "kwargs": {
35
+ "saturation": [
36
+ 0.5,
37
+ 1.5
38
+ ]
39
+ }
40
+ },
41
+ "hue": {
42
+ "weight": 1.0,
43
+ "type": "ColorJitter",
44
+ "kwargs": {
45
+ "hue": [
46
+ -0.05,
47
+ 0.05
48
+ ]
49
+ }
50
+ },
51
+ "sharpness": {
52
+ "weight": 1.0,
53
+ "type": "SharpnessJitter",
54
+ "kwargs": {
55
+ "sharpness": [
56
+ 0.5,
57
+ 1.5
58
+ ]
59
+ }
60
+ }
61
+ }
62
+ },
63
+ "revision": null,
64
+ "use_imagenet_stats": true,
65
+ "video_backend": "torchcodec",
66
+ "streaming": false
67
+ },
68
+ "env": null,
69
+ "policy": {
70
+ "type": "act",
71
+ "n_obs_steps": 1,
72
+ "input_features": {
73
+ "observation.state": {
74
+ "type": "STATE",
75
+ "shape": [
76
+ 6
77
+ ]
78
+ },
79
+ "observation.images.front": {
80
+ "type": "VISUAL",
81
+ "shape": [
82
+ 3,
83
+ 1080,
84
+ 1920
85
+ ]
86
+ },
87
+ "observation.images.top": {
88
+ "type": "VISUAL",
89
+ "shape": [
90
+ 3,
91
+ 720,
92
+ 1280
93
+ ]
94
+ }
95
+ },
96
+ "output_features": {
97
+ "action": {
98
+ "type": "ACTION",
99
+ "shape": [
100
+ 6
101
+ ]
102
+ }
103
+ },
104
+ "device": "cuda",
105
+ "use_amp": false,
106
+ "push_to_hub": true,
107
+ "repo_id": "siyulw2025/trash_picking",
108
+ "private": null,
109
+ "tags": null,
110
+ "license": null,
111
+ "chunk_size": 100,
112
+ "n_action_steps": 100,
113
+ "normalization_mapping": {
114
+ "VISUAL": "MEAN_STD",
115
+ "STATE": "MEAN_STD",
116
+ "ACTION": "MEAN_STD"
117
+ },
118
+ "vision_backbone": "resnet18",
119
+ "pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
120
+ "replace_final_stride_with_dilation": false,
121
+ "pre_norm": false,
122
+ "dim_model": 512,
123
+ "n_heads": 8,
124
+ "dim_feedforward": 3200,
125
+ "feedforward_activation": "relu",
126
+ "n_encoder_layers": 4,
127
+ "n_decoder_layers": 1,
128
+ "use_vae": true,
129
+ "latent_dim": 32,
130
+ "n_vae_encoder_layers": 4,
131
+ "temporal_ensemble_coeff": null,
132
+ "dropout": 0.1,
133
+ "kl_weight": 10.0,
134
+ "optimizer_lr": 1e-05,
135
+ "optimizer_weight_decay": 0.0001,
136
+ "optimizer_lr_backbone": 1e-05
137
+ },
138
+ "output_dir": "outputs/train/minions001",
139
+ "job_name": "trash_picking",
140
+ "resume": false,
141
+ "seed": 1000,
142
+ "num_workers": 4,
143
+ "batch_size": 1,
144
+ "steps": 100000,
145
+ "eval_freq": 20000,
146
+ "log_freq": 200,
147
+ "save_checkpoint": true,
148
+ "save_freq": 20000,
149
+ "use_policy_training_preset": true,
150
+ "optimizer": {
151
+ "type": "adamw",
152
+ "lr": 1e-05,
153
+ "weight_decay": 0.0001,
154
+ "grad_clip_norm": 10.0,
155
+ "betas": [
156
+ 0.9,
157
+ 0.999
158
+ ],
159
+ "eps": 1e-08
160
+ },
161
+ "scheduler": null,
162
+ "eval": {
163
+ "n_episodes": 50,
164
+ "batch_size": 50,
165
+ "use_async_envs": false
166
+ },
167
+ "wandb": {
168
+ "enable": false,
169
+ "disable_artifact": false,
170
+ "project": "lerobot",
171
+ "entity": null,
172
+ "notes": null,
173
+ "run_id": null,
174
+ "mode": null
175
+ }
176
+ }
trash_picking_cache/060000/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
+ ]
trash_picking_cache/060000/training_state/optimizer_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c43d408b79b1eec09d2b0030c0d6881577f6d1a0fddf2f4f1ad48e3b9af3cac7
3
+ size 412817652
trash_picking_cache/060000/training_state/rng_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39810b9253b9b27d34d4e8c12db0f53da3fa1fec1068a89ae24b055d6b425e28
3
+ size 15708
trash_picking_cache/060000/training_state/training_step.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "step": 60000
3
+ }
trash_picking_cache/080000/pretrained_model/config.json ADDED
@@ -0,0 +1,69 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "type": "act",
3
+ "n_obs_steps": 1,
4
+ "input_features": {
5
+ "observation.state": {
6
+ "type": "STATE",
7
+ "shape": [
8
+ 6
9
+ ]
10
+ },
11
+ "observation.images.front": {
12
+ "type": "VISUAL",
13
+ "shape": [
14
+ 3,
15
+ 1080,
16
+ 1920
17
+ ]
18
+ },
19
+ "observation.images.top": {
20
+ "type": "VISUAL",
21
+ "shape": [
22
+ 3,
23
+ 720,
24
+ 1280
25
+ ]
26
+ }
27
+ },
28
+ "output_features": {
29
+ "action": {
30
+ "type": "ACTION",
31
+ "shape": [
32
+ 6
33
+ ]
34
+ }
35
+ },
36
+ "device": "cuda",
37
+ "use_amp": false,
38
+ "push_to_hub": true,
39
+ "repo_id": "siyulw2025/trash_picking",
40
+ "private": null,
41
+ "tags": null,
42
+ "license": null,
43
+ "chunk_size": 100,
44
+ "n_action_steps": 100,
45
+ "normalization_mapping": {
46
+ "VISUAL": "MEAN_STD",
47
+ "STATE": "MEAN_STD",
48
+ "ACTION": "MEAN_STD"
49
+ },
50
+ "vision_backbone": "resnet18",
51
+ "pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
52
+ "replace_final_stride_with_dilation": false,
53
+ "pre_norm": false,
54
+ "dim_model": 512,
55
+ "n_heads": 8,
56
+ "dim_feedforward": 3200,
57
+ "feedforward_activation": "relu",
58
+ "n_encoder_layers": 4,
59
+ "n_decoder_layers": 1,
60
+ "use_vae": true,
61
+ "latent_dim": 32,
62
+ "n_vae_encoder_layers": 4,
63
+ "temporal_ensemble_coeff": null,
64
+ "dropout": 0.1,
65
+ "kl_weight": 10.0,
66
+ "optimizer_lr": 1e-05,
67
+ "optimizer_weight_decay": 0.0001,
68
+ "optimizer_lr_backbone": 1e-05
69
+ }
trash_picking_cache/080000/pretrained_model/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3bfb4a2f6268ee8b6af3555e44ef3c0ea68ad737260a4b827773aeae3c81e63f
3
+ size 206699736
trash_picking_cache/080000/pretrained_model/policy_postprocessor.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "name": "policy_postprocessor",
3
+ "steps": [
4
+ {
5
+ "registry_name": "unnormalizer_processor",
6
+ "config": {
7
+ "eps": 1e-08,
8
+ "features": {
9
+ "action": {
10
+ "type": "ACTION",
11
+ "shape": [
12
+ 6
13
+ ]
14
+ }
15
+ },
16
+ "norm_map": {
17
+ "VISUAL": "MEAN_STD",
18
+ "STATE": "MEAN_STD",
19
+ "ACTION": "MEAN_STD"
20
+ }
21
+ },
22
+ "state_file": "policy_postprocessor_step_0_unnormalizer_processor.safetensors"
23
+ },
24
+ {
25
+ "registry_name": "device_processor",
26
+ "config": {
27
+ "device": "cpu",
28
+ "float_dtype": null
29
+ }
30
+ }
31
+ ]
32
+ }
trash_picking_cache/080000/pretrained_model/policy_postprocessor_step_0_unnormalizer_processor.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:984d7923641cde3536b62f7fcee347ab4a2c5e24c09af3b8c4382083afb0172f
3
+ size 3748
trash_picking_cache/080000/pretrained_model/policy_preprocessor.json ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "name": "policy_preprocessor",
3
+ "steps": [
4
+ {
5
+ "registry_name": "rename_observations_processor",
6
+ "config": {
7
+ "rename_map": {}
8
+ }
9
+ },
10
+ {
11
+ "registry_name": "to_batch_processor",
12
+ "config": {}
13
+ },
14
+ {
15
+ "registry_name": "device_processor",
16
+ "config": {
17
+ "device": "cuda",
18
+ "float_dtype": null
19
+ }
20
+ },
21
+ {
22
+ "registry_name": "normalizer_processor",
23
+ "config": {
24
+ "eps": 1e-08,
25
+ "features": {
26
+ "observation.state": {
27
+ "type": "STATE",
28
+ "shape": [
29
+ 6
30
+ ]
31
+ },
32
+ "observation.images.front": {
33
+ "type": "VISUAL",
34
+ "shape": [
35
+ 3,
36
+ 1080,
37
+ 1920
38
+ ]
39
+ },
40
+ "observation.images.top": {
41
+ "type": "VISUAL",
42
+ "shape": [
43
+ 3,
44
+ 720,
45
+ 1280
46
+ ]
47
+ },
48
+ "action": {
49
+ "type": "ACTION",
50
+ "shape": [
51
+ 6
52
+ ]
53
+ }
54
+ },
55
+ "norm_map": {
56
+ "VISUAL": "MEAN_STD",
57
+ "STATE": "MEAN_STD",
58
+ "ACTION": "MEAN_STD"
59
+ }
60
+ },
61
+ "state_file": "policy_preprocessor_step_3_normalizer_processor.safetensors"
62
+ }
63
+ ]
64
+ }
trash_picking_cache/080000/pretrained_model/policy_preprocessor_step_3_normalizer_processor.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:984d7923641cde3536b62f7fcee347ab4a2c5e24c09af3b8c4382083afb0172f
3
+ size 3748
trash_picking_cache/080000/pretrained_model/train_config.json ADDED
@@ -0,0 +1,176 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset": {
3
+ "repo_id": "siyulw2025/minions001",
4
+ "root": null,
5
+ "episodes": null,
6
+ "image_transforms": {
7
+ "enable": false,
8
+ "max_num_transforms": 3,
9
+ "random_order": false,
10
+ "tfs": {
11
+ "brightness": {
12
+ "weight": 1.0,
13
+ "type": "ColorJitter",
14
+ "kwargs": {
15
+ "brightness": [
16
+ 0.8,
17
+ 1.2
18
+ ]
19
+ }
20
+ },
21
+ "contrast": {
22
+ "weight": 1.0,
23
+ "type": "ColorJitter",
24
+ "kwargs": {
25
+ "contrast": [
26
+ 0.8,
27
+ 1.2
28
+ ]
29
+ }
30
+ },
31
+ "saturation": {
32
+ "weight": 1.0,
33
+ "type": "ColorJitter",
34
+ "kwargs": {
35
+ "saturation": [
36
+ 0.5,
37
+ 1.5
38
+ ]
39
+ }
40
+ },
41
+ "hue": {
42
+ "weight": 1.0,
43
+ "type": "ColorJitter",
44
+ "kwargs": {
45
+ "hue": [
46
+ -0.05,
47
+ 0.05
48
+ ]
49
+ }
50
+ },
51
+ "sharpness": {
52
+ "weight": 1.0,
53
+ "type": "SharpnessJitter",
54
+ "kwargs": {
55
+ "sharpness": [
56
+ 0.5,
57
+ 1.5
58
+ ]
59
+ }
60
+ }
61
+ }
62
+ },
63
+ "revision": null,
64
+ "use_imagenet_stats": true,
65
+ "video_backend": "torchcodec",
66
+ "streaming": false
67
+ },
68
+ "env": null,
69
+ "policy": {
70
+ "type": "act",
71
+ "n_obs_steps": 1,
72
+ "input_features": {
73
+ "observation.state": {
74
+ "type": "STATE",
75
+ "shape": [
76
+ 6
77
+ ]
78
+ },
79
+ "observation.images.front": {
80
+ "type": "VISUAL",
81
+ "shape": [
82
+ 3,
83
+ 1080,
84
+ 1920
85
+ ]
86
+ },
87
+ "observation.images.top": {
88
+ "type": "VISUAL",
89
+ "shape": [
90
+ 3,
91
+ 720,
92
+ 1280
93
+ ]
94
+ }
95
+ },
96
+ "output_features": {
97
+ "action": {
98
+ "type": "ACTION",
99
+ "shape": [
100
+ 6
101
+ ]
102
+ }
103
+ },
104
+ "device": "cuda",
105
+ "use_amp": false,
106
+ "push_to_hub": true,
107
+ "repo_id": "siyulw2025/trash_picking",
108
+ "private": null,
109
+ "tags": null,
110
+ "license": null,
111
+ "chunk_size": 100,
112
+ "n_action_steps": 100,
113
+ "normalization_mapping": {
114
+ "VISUAL": "MEAN_STD",
115
+ "STATE": "MEAN_STD",
116
+ "ACTION": "MEAN_STD"
117
+ },
118
+ "vision_backbone": "resnet18",
119
+ "pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
120
+ "replace_final_stride_with_dilation": false,
121
+ "pre_norm": false,
122
+ "dim_model": 512,
123
+ "n_heads": 8,
124
+ "dim_feedforward": 3200,
125
+ "feedforward_activation": "relu",
126
+ "n_encoder_layers": 4,
127
+ "n_decoder_layers": 1,
128
+ "use_vae": true,
129
+ "latent_dim": 32,
130
+ "n_vae_encoder_layers": 4,
131
+ "temporal_ensemble_coeff": null,
132
+ "dropout": 0.1,
133
+ "kl_weight": 10.0,
134
+ "optimizer_lr": 1e-05,
135
+ "optimizer_weight_decay": 0.0001,
136
+ "optimizer_lr_backbone": 1e-05
137
+ },
138
+ "output_dir": "outputs/train/minions001",
139
+ "job_name": "trash_picking",
140
+ "resume": false,
141
+ "seed": 1000,
142
+ "num_workers": 4,
143
+ "batch_size": 1,
144
+ "steps": 100000,
145
+ "eval_freq": 20000,
146
+ "log_freq": 200,
147
+ "save_checkpoint": true,
148
+ "save_freq": 20000,
149
+ "use_policy_training_preset": true,
150
+ "optimizer": {
151
+ "type": "adamw",
152
+ "lr": 1e-05,
153
+ "weight_decay": 0.0001,
154
+ "grad_clip_norm": 10.0,
155
+ "betas": [
156
+ 0.9,
157
+ 0.999
158
+ ],
159
+ "eps": 1e-08
160
+ },
161
+ "scheduler": null,
162
+ "eval": {
163
+ "n_episodes": 50,
164
+ "batch_size": 50,
165
+ "use_async_envs": false
166
+ },
167
+ "wandb": {
168
+ "enable": false,
169
+ "disable_artifact": false,
170
+ "project": "lerobot",
171
+ "entity": null,
172
+ "notes": null,
173
+ "run_id": null,
174
+ "mode": null
175
+ }
176
+ }
trash_picking_cache/080000/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
+ ]
trash_picking_cache/080000/training_state/optimizer_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:abe202eee8048e0d2c60f5ccc4fd439b44c9b0cbbfc5a412626765fc69b20b85
3
+ size 412817652
trash_picking_cache/080000/training_state/rng_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94f61873e337b8f2ae0a067aa07ea6f1635fd67bd7497422edbffd8ddccfbd90
3
+ size 15708
trash_picking_cache/080000/training_state/training_step.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "step": 80000
3
+ }
trash_picking_cache/100000/pretrained_model/config.json ADDED
@@ -0,0 +1,69 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "type": "act",
3
+ "n_obs_steps": 1,
4
+ "input_features": {
5
+ "observation.state": {
6
+ "type": "STATE",
7
+ "shape": [
8
+ 6
9
+ ]
10
+ },
11
+ "observation.images.front": {
12
+ "type": "VISUAL",
13
+ "shape": [
14
+ 3,
15
+ 1080,
16
+ 1920
17
+ ]
18
+ },
19
+ "observation.images.top": {
20
+ "type": "VISUAL",
21
+ "shape": [
22
+ 3,
23
+ 720,
24
+ 1280
25
+ ]
26
+ }
27
+ },
28
+ "output_features": {
29
+ "action": {
30
+ "type": "ACTION",
31
+ "shape": [
32
+ 6
33
+ ]
34
+ }
35
+ },
36
+ "device": "cuda",
37
+ "use_amp": false,
38
+ "push_to_hub": true,
39
+ "repo_id": "siyulw2025/trash_picking",
40
+ "private": null,
41
+ "tags": null,
42
+ "license": null,
43
+ "chunk_size": 100,
44
+ "n_action_steps": 100,
45
+ "normalization_mapping": {
46
+ "VISUAL": "MEAN_STD",
47
+ "STATE": "MEAN_STD",
48
+ "ACTION": "MEAN_STD"
49
+ },
50
+ "vision_backbone": "resnet18",
51
+ "pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
52
+ "replace_final_stride_with_dilation": false,
53
+ "pre_norm": false,
54
+ "dim_model": 512,
55
+ "n_heads": 8,
56
+ "dim_feedforward": 3200,
57
+ "feedforward_activation": "relu",
58
+ "n_encoder_layers": 4,
59
+ "n_decoder_layers": 1,
60
+ "use_vae": true,
61
+ "latent_dim": 32,
62
+ "n_vae_encoder_layers": 4,
63
+ "temporal_ensemble_coeff": null,
64
+ "dropout": 0.1,
65
+ "kl_weight": 10.0,
66
+ "optimizer_lr": 1e-05,
67
+ "optimizer_weight_decay": 0.0001,
68
+ "optimizer_lr_backbone": 1e-05
69
+ }
trash_picking_cache/100000/pretrained_model/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8051aef401c6756053d8606c72491f602769f595b958c3b3d48ebae00fd9ea05
3
+ size 206699736
trash_picking_cache/100000/pretrained_model/policy_postprocessor.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "name": "policy_postprocessor",
3
+ "steps": [
4
+ {
5
+ "registry_name": "unnormalizer_processor",
6
+ "config": {
7
+ "eps": 1e-08,
8
+ "features": {
9
+ "action": {
10
+ "type": "ACTION",
11
+ "shape": [
12
+ 6
13
+ ]
14
+ }
15
+ },
16
+ "norm_map": {
17
+ "VISUAL": "MEAN_STD",
18
+ "STATE": "MEAN_STD",
19
+ "ACTION": "MEAN_STD"
20
+ }
21
+ },
22
+ "state_file": "policy_postprocessor_step_0_unnormalizer_processor.safetensors"
23
+ },
24
+ {
25
+ "registry_name": "device_processor",
26
+ "config": {
27
+ "device": "cpu",
28
+ "float_dtype": null
29
+ }
30
+ }
31
+ ]
32
+ }
trash_picking_cache/100000/pretrained_model/policy_postprocessor_step_0_unnormalizer_processor.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:984d7923641cde3536b62f7fcee347ab4a2c5e24c09af3b8c4382083afb0172f
3
+ size 3748
trash_picking_cache/100000/pretrained_model/policy_preprocessor.json ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "name": "policy_preprocessor",
3
+ "steps": [
4
+ {
5
+ "registry_name": "rename_observations_processor",
6
+ "config": {
7
+ "rename_map": {}
8
+ }
9
+ },
10
+ {
11
+ "registry_name": "to_batch_processor",
12
+ "config": {}
13
+ },
14
+ {
15
+ "registry_name": "device_processor",
16
+ "config": {
17
+ "device": "cuda",
18
+ "float_dtype": null
19
+ }
20
+ },
21
+ {
22
+ "registry_name": "normalizer_processor",
23
+ "config": {
24
+ "eps": 1e-08,
25
+ "features": {
26
+ "observation.state": {
27
+ "type": "STATE",
28
+ "shape": [
29
+ 6
30
+ ]
31
+ },
32
+ "observation.images.front": {
33
+ "type": "VISUAL",
34
+ "shape": [
35
+ 3,
36
+ 1080,
37
+ 1920
38
+ ]
39
+ },
40
+ "observation.images.top": {
41
+ "type": "VISUAL",
42
+ "shape": [
43
+ 3,
44
+ 720,
45
+ 1280
46
+ ]
47
+ },
48
+ "action": {
49
+ "type": "ACTION",
50
+ "shape": [
51
+ 6
52
+ ]
53
+ }
54
+ },
55
+ "norm_map": {
56
+ "VISUAL": "MEAN_STD",
57
+ "STATE": "MEAN_STD",
58
+ "ACTION": "MEAN_STD"
59
+ }
60
+ },
61
+ "state_file": "policy_preprocessor_step_3_normalizer_processor.safetensors"
62
+ }
63
+ ]
64
+ }
trash_picking_cache/100000/pretrained_model/policy_preprocessor_step_3_normalizer_processor.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:984d7923641cde3536b62f7fcee347ab4a2c5e24c09af3b8c4382083afb0172f
3
+ size 3748