Hugging Face's logo

xieyucheng123
/
so101-act

Robotics
LeRobot
Safetensors
act
Model card Files
xet
 Community
xieyucheng123 commited on
Commit
8afca68
·
verified ·
1 Parent(s): 617377f

Upload folder using huggingface_hub

Browse files
Files changed (22) hide show
  1. checkpoints/005000/pretrained_model/config.json +72 -0
  2. checkpoints/005000/pretrained_model/model.safetensors +3 -0
  3. checkpoints/005000/pretrained_model/policy_postprocessor.json +32 -0
  4. checkpoints/005000/pretrained_model/policy_postprocessor_step_0_unnormalizer_processor.safetensors +3 -0
  5. checkpoints/005000/pretrained_model/policy_preprocessor.json +64 -0
  6. checkpoints/005000/pretrained_model/policy_preprocessor_step_3_normalizer_processor.safetensors +3 -0
  7. checkpoints/005000/pretrained_model/train_config.json +221 -0
  8. checkpoints/005000/training_state/optimizer_param_groups.json +191 -0
  9. checkpoints/005000/training_state/optimizer_state.safetensors +3 -0
  10. checkpoints/005000/training_state/rng_state.safetensors +3 -0
  11. checkpoints/005000/training_state/training_step.json +5 -0
  12. checkpoints/010000/pretrained_model/config.json +72 -0
  13. checkpoints/010000/pretrained_model/model.safetensors +3 -0
  14. checkpoints/010000/pretrained_model/policy_postprocessor.json +32 -0
  15. checkpoints/010000/pretrained_model/policy_postprocessor_step_0_unnormalizer_processor.safetensors +3 -0
  16. checkpoints/010000/pretrained_model/policy_preprocessor.json +64 -0
  17. checkpoints/010000/pretrained_model/policy_preprocessor_step_3_normalizer_processor.safetensors +3 -0
  18. checkpoints/010000/pretrained_model/train_config.json +221 -0
  19. checkpoints/010000/training_state/optimizer_param_groups.json +191 -0
  20. checkpoints/010000/training_state/optimizer_state.safetensors +3 -0
  21. checkpoints/010000/training_state/rng_state.safetensors +3 -0
  22. checkpoints/010000/training_state/training_step.json +5 -0
checkpoints/005000/pretrained_model/config.json ADDED
@@ -0,0 +1,72 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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.up": {
12
+ "type": "VISUAL",
13
+ "shape": [
14
+ 3,
15
+ 480,
16
+ 640
17
+ ]
18
+ },
19
+ "observation.images.side": {
20
+ "type": "VISUAL",
21
+ "shape": [
22
+ 3,
23
+ 480,
24
+ 640
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
+ "use_peft": false,
39
+ "push_to_hub": true,
40
+ "repo_id": "xieyucheng123/so101-act",
41
+ "private": null,
42
+ "tags": null,
43
+ "license": null,
44
+ "pretrained_path": null,
45
+ "pretrained_revision": null,
46
+ "chunk_size": 100,
47
+ "n_action_steps": 100,
48
+ "normalization_mapping": {
49
+ "VISUAL": "MEAN_STD",
50
+ "STATE": "MEAN_STD",
51
+ "ACTION": "MEAN_STD"
52
+ },
53
+ "vision_backbone": "resnet18",
54
+ "pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
55
+ "replace_final_stride_with_dilation": false,
56
+ "pre_norm": false,
57
+ "dim_model": 512,
58
+ "n_heads": 8,
59
+ "dim_feedforward": 3200,
60
+ "feedforward_activation": "relu",
61
+ "n_encoder_layers": 4,
62
+ "n_decoder_layers": 1,
63
+ "use_vae": true,
64
+ "latent_dim": 32,
65
+ "n_vae_encoder_layers": 4,
66
+ "temporal_ensemble_coeff": null,
67
+ "dropout": 0.1,
68
+ "kl_weight": 10.0,
69
+ "optimizer_lr": 1e-05,
70
+ "optimizer_weight_decay": 0.0001,
71
+ "optimizer_lr_backbone": 1e-05
72
+ }
checkpoints/005000/pretrained_model/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c8c890af11497b97c929390577406a5784673af5f99309567e0686f888abcae
3
+ size 206699736
checkpoints/005000/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
+ }
checkpoints/005000/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 sha256:234c8937ad146f0189a2283751c2043fc0a6a6211e22a43e6e630c22f1ca271d
3
+ size 3740
checkpoints/005000/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.up": {
33
+ "type": "VISUAL",
34
+ "shape": [
35
+ 3,
36
+ 480,
37
+ 640
38
+ ]
39
+ },
40
+ "observation.images.side": {
41
+ "type": "VISUAL",
42
+ "shape": [
43
+ 3,
44
+ 480,
45
+ 640
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
+ }
checkpoints/005000/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 sha256:657a4800699e00504f476714703316422ed257dd85b6d3f1e617a7ff0218b9f1
3
+ size 3748
checkpoints/005000/pretrained_model/train_config.json ADDED
@@ -0,0 +1,221 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset": {
3
+ "repo_id": "lerobot/svla_so101_pickplace",
4
+ "repo_type": "dataset",
5
+ "root": null,
6
+ "episodes": null,
7
+ "image_transforms": {
8
+ "enable": false,
9
+ "max_num_transforms": 3,
10
+ "random_order": false,
11
+ "tfs": {
12
+ "brightness": {
13
+ "weight": 1.0,
14
+ "type": "ColorJitter",
15
+ "kwargs": {
16
+ "brightness": [
17
+ 0.8,
18
+ 1.2
19
+ ]
20
+ }
21
+ },
22
+ "contrast": {
23
+ "weight": 1.0,
24
+ "type": "ColorJitter",
25
+ "kwargs": {
26
+ "contrast": [
27
+ 0.8,
28
+ 1.2
29
+ ]
30
+ }
31
+ },
32
+ "saturation": {
33
+ "weight": 1.0,
34
+ "type": "ColorJitter",
35
+ "kwargs": {
36
+ "saturation": [
37
+ 0.5,
38
+ 1.5
39
+ ]
40
+ }
41
+ },
42
+ "hue": {
43
+ "weight": 1.0,
44
+ "type": "ColorJitter",
45
+ "kwargs": {
46
+ "hue": [
47
+ -0.05,
48
+ 0.05
49
+ ]
50
+ }
51
+ },
52
+ "sharpness": {
53
+ "weight": 1.0,
54
+ "type": "SharpnessJitter",
55
+ "kwargs": {
56
+ "sharpness": [
57
+ 0.5,
58
+ 1.5
59
+ ]
60
+ }
61
+ },
62
+ "affine": {
63
+ "weight": 1.0,
64
+ "type": "RandomAffine",
65
+ "kwargs": {
66
+ "degrees": [
67
+ -5.0,
68
+ 5.0
69
+ ],
70
+ "translate": [
71
+ 0.05,
72
+ 0.05
73
+ ]
74
+ }
75
+ }
76
+ }
77
+ },
78
+ "revision": null,
79
+ "use_imagenet_stats": true,
80
+ "video_backend": "torchcodec",
81
+ "return_uint8": false,
82
+ "depth_output_unit": "mm",
83
+ "streaming": false,
84
+ "eval_split": 0.0
85
+ },
86
+ "env": null,
87
+ "policy": {
88
+ "type": "act",
89
+ "n_obs_steps": 1,
90
+ "input_features": {
91
+ "observation.state": {
92
+ "type": "STATE",
93
+ "shape": [
94
+ 6
95
+ ]
96
+ },
97
+ "observation.images.up": {
98
+ "type": "VISUAL",
99
+ "shape": [
100
+ 3,
101
+ 480,
102
+ 640
103
+ ]
104
+ },
105
+ "observation.images.side": {
106
+ "type": "VISUAL",
107
+ "shape": [
108
+ 3,
109
+ 480,
110
+ 640
111
+ ]
112
+ }
113
+ },
114
+ "output_features": {
115
+ "action": {
116
+ "type": "ACTION",
117
+ "shape": [
118
+ 6
119
+ ]
120
+ }
121
+ },
122
+ "device": "cuda",
123
+ "use_amp": false,
124
+ "use_peft": false,
125
+ "push_to_hub": true,
126
+ "repo_id": "xieyucheng123/so101-act",
127
+ "private": null,
128
+ "tags": null,
129
+ "license": null,
130
+ "pretrained_path": null,
131
+ "pretrained_revision": null,
132
+ "chunk_size": 100,
133
+ "n_action_steps": 100,
134
+ "normalization_mapping": {
135
+ "VISUAL": "MEAN_STD",
136
+ "STATE": "MEAN_STD",
137
+ "ACTION": "MEAN_STD"
138
+ },
139
+ "vision_backbone": "resnet18",
140
+ "pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
141
+ "replace_final_stride_with_dilation": false,
142
+ "pre_norm": false,
143
+ "dim_model": 512,
144
+ "n_heads": 8,
145
+ "dim_feedforward": 3200,
146
+ "feedforward_activation": "relu",
147
+ "n_encoder_layers": 4,
148
+ "n_decoder_layers": 1,
149
+ "use_vae": true,
150
+ "latent_dim": 32,
151
+ "n_vae_encoder_layers": 4,
152
+ "temporal_ensemble_coeff": null,
153
+ "dropout": 0.1,
154
+ "kl_weight": 10.0,
155
+ "optimizer_lr": 1e-05,
156
+ "optimizer_weight_decay": 0.0001,
157
+ "optimizer_lr_backbone": 1e-05
158
+ },
159
+ "reward_model": null,
160
+ "output_dir": "/kaggle/working/outputs/train/so101_act",
161
+ "job_name": "act",
162
+ "resume": false,
163
+ "seed": 1000,
164
+ "cudnn_deterministic": false,
165
+ "num_workers": 4,
166
+ "batch_size": 16,
167
+ "prefetch_factor": 4,
168
+ "persistent_workers": true,
169
+ "dataloader_multiprocessing_context": "spawn",
170
+ "steps": 10000,
171
+ "env_eval_freq": 20000,
172
+ "log_freq": 100,
173
+ "eval_steps": 0,
174
+ "max_eval_samples": 0,
175
+ "tolerance_s": 0.0001,
176
+ "save_checkpoint": true,
177
+ "save_freq": 5000,
178
+ "use_policy_training_preset": true,
179
+ "optimizer": {
180
+ "type": "adamw",
181
+ "lr": 1e-05,
182
+ "weight_decay": 0.0001,
183
+ "grad_clip_norm": 10.0,
184
+ "betas": [
185
+ 0.9,
186
+ 0.999
187
+ ],
188
+ "eps": 1e-08
189
+ },
190
+ "scheduler": null,
191
+ "eval": {
192
+ "n_episodes": 50,
193
+ "batch_size": 2,
194
+ "use_async_envs": true,
195
+ "recording": false,
196
+ "recording_repo_id": null,
197
+ "recording_private": false
198
+ },
199
+ "wandb": {
200
+ "enable": false,
201
+ "disable_artifact": false,
202
+ "project": "lerobot",
203
+ "entity": null,
204
+ "notes": null,
205
+ "run_id": null,
206
+ "mode": null,
207
+ "add_tags": true
208
+ },
209
+ "peft": null,
210
+ "job": {
211
+ "target": null,
212
+ "image": "huggingface/lerobot-gpu:latest",
213
+ "timeout": "2d",
214
+ "detach": false,
215
+ "tags": []
216
+ },
217
+ "save_checkpoint_to_hub": false,
218
+ "sample_weighting": null,
219
+ "rename_map": {},
220
+ "checkpoint_path": null
221
+ }
checkpoints/005000/training_state/optimizer_param_groups.json ADDED
@@ -0,0 +1,191 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "lr": 1e-05,
4
+ "betas": [
5
+ 0.9,
6
+ 0.999
7
+ ],
8
+ "eps": 1e-08,
9
+ "weight_decay": 0.0001,
10
+ "amsgrad": false,
11
+ "maximize": false,
12
+ "foreach": null,
13
+ "capturable": false,
14
+ "differentiable": false,
15
+ "fused": null,
16
+ "decoupled_weight_decay": true,
17
+ "params": [
18
+ 0,
19
+ 1,
20
+ 2,
21
+ 3,
22
+ 4,
23
+ 5,
24
+ 6,
25
+ 7,
26
+ 8,
27
+ 9,
28
+ 10,
29
+ 11,
30
+ 12,
31
+ 13,
32
+ 14,
33
+ 15,
34
+ 16,
35
+ 17,
36
+ 18,
37
+ 19,
38
+ 20,
39
+ 21,
40
+ 22,
41
+ 23,
42
+ 24,
43
+ 25,
44
+ 26,
45
+ 27,
46
+ 28,
47
+ 29,
48
+ 30,
49
+ 31,
50
+ 32,
51
+ 33,
52
+ 34,
53
+ 35,
54
+ 36,
55
+ 37,
56
+ 38,
57
+ 39,
58
+ 40,
59
+ 41,
60
+ 42,
61
+ 43,
62
+ 44,
63
+ 45,
64
+ 46,
65
+ 47,
66
+ 48,
67
+ 49,
68
+ 50,
69
+ 51,
70
+ 52,
71
+ 53,
72
+ 54,
73
+ 55,
74
+ 56,
75
+ 57,
76
+ 58,
77
+ 59,
78
+ 60,
79
+ 61,
80
+ 62,
81
+ 63,
82
+ 64,
83
+ 65,
84
+ 66,
85
+ 67,
86
+ 68,
87
+ 69,
88
+ 70,
89
+ 71,
90
+ 72,
91
+ 73,
92
+ 74,
93
+ 75,
94
+ 76,
95
+ 77,
96
+ 78,
97
+ 79,
98
+ 80,
99
+ 81,
100
+ 82,
101
+ 83,
102
+ 84,
103
+ 85,
104
+ 86,
105
+ 87,
106
+ 88,
107
+ 89,
108
+ 90,
109
+ 91,
110
+ 92,
111
+ 93,
112
+ 94,
113
+ 95,
114
+ 96,
115
+ 97,
116
+ 98,
117
+ 99,
118
+ 100,
119
+ 101,
120
+ 102,
121
+ 103,
122
+ 104,
123
+ 105,
124
+ 106,
125
+ 107,
126
+ 108,
127
+ 109,
128
+ 110,
129
+ 111,
130
+ 112,
131
+ 113,
132
+ 114,
133
+ 115,
134
+ 116,
135
+ 117,
136
+ 118,
137
+ 119,
138
+ 120,
139
+ 121,
140
+ 122,
141
+ 123,
142
+ 124,
143
+ 125,
144
+ 126,
145
+ 127,
146
+ 128,
147
+ 129,
148
+ 130,
149
+ 131,
150
+ 132
151
+ ]
152
+ },
153
+ {
154
+ "lr": 1e-05,
155
+ "betas": [
156
+ 0.9,
157
+ 0.999
158
+ ],
159
+ "eps": 1e-08,
160
+ "weight_decay": 0.0001,
161
+ "amsgrad": false,
162
+ "maximize": false,
163
+ "foreach": null,
164
+ "capturable": false,
165
+ "differentiable": false,
166
+ "fused": null,
167
+ "decoupled_weight_decay": true,
168
+ "params": [
169
+ 133,
170
+ 134,
171
+ 135,
172
+ 136,
173
+ 137,
174
+ 138,
175
+ 139,
176
+ 140,
177
+ 141,
178
+ 142,
179
+ 143,
180
+ 144,
181
+ 145,
182
+ 146,
183
+ 147,
184
+ 148,
185
+ 149,
186
+ 150,
187
+ 151,
188
+ 152
189
+ ]
190
+ }
191
+ ]
checkpoints/005000/training_state/optimizer_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8becc747e4d0779f534268e02c859deba10e0472aeadf03fdda65be164cb9def
3
+ size 412817652
checkpoints/005000/training_state/rng_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:780d9dd15b6a3bf183692208e7dd7d7c63685282463cdc48b7cf8b6192b8a86f
3
+ size 15708
checkpoints/005000/training_state/training_step.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "step": 5000,
3
+ "num_processes": 1,
4
+ "batch_size": 16
5
+ }
checkpoints/010000/pretrained_model/config.json ADDED
@@ -0,0 +1,72 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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.up": {
12
+ "type": "VISUAL",
13
+ "shape": [
14
+ 3,
15
+ 480,
16
+ 640
17
+ ]
18
+ },
19
+ "observation.images.side": {
20
+ "type": "VISUAL",
21
+ "shape": [
22
+ 3,
23
+ 480,
24
+ 640
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
+ "use_peft": false,
39
+ "push_to_hub": true,
40
+ "repo_id": "xieyucheng123/so101-act",
41
+ "private": null,
42
+ "tags": null,
43
+ "license": null,
44
+ "pretrained_path": null,
45
+ "pretrained_revision": null,
46
+ "chunk_size": 100,
47
+ "n_action_steps": 100,
48
+ "normalization_mapping": {
49
+ "VISUAL": "MEAN_STD",
50
+ "STATE": "MEAN_STD",
51
+ "ACTION": "MEAN_STD"
52
+ },
53
+ "vision_backbone": "resnet18",
54
+ "pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
55
+ "replace_final_stride_with_dilation": false,
56
+ "pre_norm": false,
57
+ "dim_model": 512,
58
+ "n_heads": 8,
59
+ "dim_feedforward": 3200,
60
+ "feedforward_activation": "relu",
61
+ "n_encoder_layers": 4,
62
+ "n_decoder_layers": 1,
63
+ "use_vae": true,
64
+ "latent_dim": 32,
65
+ "n_vae_encoder_layers": 4,
66
+ "temporal_ensemble_coeff": null,
67
+ "dropout": 0.1,
68
+ "kl_weight": 10.0,
69
+ "optimizer_lr": 1e-05,
70
+ "optimizer_weight_decay": 0.0001,
71
+ "optimizer_lr_backbone": 1e-05
72
+ }
checkpoints/010000/pretrained_model/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0040f73c88377ae7bb0b09c3bd6ae208ca54af62952d918c5c47b54170948de7
3
+ size 206699736
checkpoints/010000/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
+ }
checkpoints/010000/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 sha256:234c8937ad146f0189a2283751c2043fc0a6a6211e22a43e6e630c22f1ca271d
3
+ size 3740
checkpoints/010000/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.up": {
33
+ "type": "VISUAL",
34
+ "shape": [
35
+ 3,
36
+ 480,
37
+ 640
38
+ ]
39
+ },
40
+ "observation.images.side": {
41
+ "type": "VISUAL",
42
+ "shape": [
43
+ 3,
44
+ 480,
45
+ 640
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
+ }
checkpoints/010000/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 sha256:657a4800699e00504f476714703316422ed257dd85b6d3f1e617a7ff0218b9f1
3
+ size 3748
checkpoints/010000/pretrained_model/train_config.json ADDED
@@ -0,0 +1,221 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset": {
3
+ "repo_id": "lerobot/svla_so101_pickplace",
4
+ "repo_type": "dataset",
5
+ "root": null,
6
+ "episodes": null,
7
+ "image_transforms": {
8
+ "enable": false,
9
+ "max_num_transforms": 3,
10
+ "random_order": false,
11
+ "tfs": {
12
+ "brightness": {
13
+ "weight": 1.0,
14
+ "type": "ColorJitter",
15
+ "kwargs": {
16
+ "brightness": [
17
+ 0.8,
18
+ 1.2
19
+ ]
20
+ }
21
+ },
22
+ "contrast": {
23
+ "weight": 1.0,
24
+ "type": "ColorJitter",
25
+ "kwargs": {
26
+ "contrast": [
27
+ 0.8,
28
+ 1.2
29
+ ]
30
+ }
31
+ },
32
+ "saturation": {
33
+ "weight": 1.0,
34
+ "type": "ColorJitter",
35
+ "kwargs": {
36
+ "saturation": [
37
+ 0.5,
38
+ 1.5
39
+ ]
40
+ }
41
+ },
42
+ "hue": {
43
+ "weight": 1.0,
44
+ "type": "ColorJitter",
45
+ "kwargs": {
46
+ "hue": [
47
+ -0.05,
48
+ 0.05
49
+ ]
50
+ }
51
+ },
52
+ "sharpness": {
53
+ "weight": 1.0,
54
+ "type": "SharpnessJitter",
55
+ "kwargs": {
56
+ "sharpness": [
57
+ 0.5,
58
+ 1.5
59
+ ]
60
+ }
61
+ },
62
+ "affine": {
63
+ "weight": 1.0,
64
+ "type": "RandomAffine",
65
+ "kwargs": {
66
+ "degrees": [
67
+ -5.0,
68
+ 5.0
69
+ ],
70
+ "translate": [
71
+ 0.05,
72
+ 0.05
73
+ ]
74
+ }
75
+ }
76
+ }
77
+ },
78
+ "revision": null,
79
+ "use_imagenet_stats": true,
80
+ "video_backend": "torchcodec",
81
+ "return_uint8": false,
82
+ "depth_output_unit": "mm",
83
+ "streaming": false,
84
+ "eval_split": 0.0
85
+ },
86
+ "env": null,
87
+ "policy": {
88
+ "type": "act",
89
+ "n_obs_steps": 1,
90
+ "input_features": {
91
+ "observation.state": {
92
+ "type": "STATE",
93
+ "shape": [
94
+ 6
95
+ ]
96
+ },
97
+ "observation.images.up": {
98
+ "type": "VISUAL",
99
+ "shape": [
100
+ 3,
101
+ 480,
102
+ 640
103
+ ]
104
+ },
105
+ "observation.images.side": {
106
+ "type": "VISUAL",
107
+ "shape": [
108
+ 3,
109
+ 480,
110
+ 640
111
+ ]
112
+ }
113
+ },
114
+ "output_features": {
115
+ "action": {
116
+ "type": "ACTION",
117
+ "shape": [
118
+ 6
119
+ ]
120
+ }
121
+ },
122
+ "device": "cuda",
123
+ "use_amp": false,
124
+ "use_peft": false,
125
+ "push_to_hub": true,
126
+ "repo_id": "xieyucheng123/so101-act",
127
+ "private": null,
128
+ "tags": null,
129
+ "license": null,
130
+ "pretrained_path": null,
131
+ "pretrained_revision": null,
132
+ "chunk_size": 100,
133
+ "n_action_steps": 100,
134
+ "normalization_mapping": {
135
+ "VISUAL": "MEAN_STD",
136
+ "STATE": "MEAN_STD",
137
+ "ACTION": "MEAN_STD"
138
+ },
139
+ "vision_backbone": "resnet18",
140
+ "pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
141
+ "replace_final_stride_with_dilation": false,
142
+ "pre_norm": false,
143
+ "dim_model": 512,
144
+ "n_heads": 8,
145
+ "dim_feedforward": 3200,
146
+ "feedforward_activation": "relu",
147
+ "n_encoder_layers": 4,
148
+ "n_decoder_layers": 1,
149
+ "use_vae": true,
150
+ "latent_dim": 32,
151
+ "n_vae_encoder_layers": 4,
152
+ "temporal_ensemble_coeff": null,
153
+ "dropout": 0.1,
154
+ "kl_weight": 10.0,
155
+ "optimizer_lr": 1e-05,
156
+ "optimizer_weight_decay": 0.0001,
157
+ "optimizer_lr_backbone": 1e-05
158
+ },
159
+ "reward_model": null,
160
+ "output_dir": "/kaggle/working/outputs/train/so101_act",
161
+ "job_name": "act",
162
+ "resume": false,
163
+ "seed": 1000,
164
+ "cudnn_deterministic": false,
165
+ "num_workers": 4,
166
+ "batch_size": 16,
167
+ "prefetch_factor": 4,
168
+ "persistent_workers": true,
169
+ "dataloader_multiprocessing_context": "spawn",
170
+ "steps": 10000,
171
+ "env_eval_freq": 20000,
172
+ "log_freq": 100,
173
+ "eval_steps": 0,
174
+ "max_eval_samples": 0,
175
+ "tolerance_s": 0.0001,
176
+ "save_checkpoint": true,
177
+ "save_freq": 5000,
178
+ "use_policy_training_preset": true,
179
+ "optimizer": {
180
+ "type": "adamw",
181
+ "lr": 1e-05,
182
+ "weight_decay": 0.0001,
183
+ "grad_clip_norm": 10.0,
184
+ "betas": [
185
+ 0.9,
186
+ 0.999
187
+ ],
188
+ "eps": 1e-08
189
+ },
190
+ "scheduler": null,
191
+ "eval": {
192
+ "n_episodes": 50,
193
+ "batch_size": 2,
194
+ "use_async_envs": true,
195
+ "recording": false,
196
+ "recording_repo_id": null,
197
+ "recording_private": false
198
+ },
199
+ "wandb": {
200
+ "enable": false,
201
+ "disable_artifact": false,
202
+ "project": "lerobot",
203
+ "entity": null,
204
+ "notes": null,
205
+ "run_id": null,
206
+ "mode": null,
207
+ "add_tags": true
208
+ },
209
+ "peft": null,
210
+ "job": {
211
+ "target": null,
212
+ "image": "huggingface/lerobot-gpu:latest",
213
+ "timeout": "2d",
214
+ "detach": false,
215
+ "tags": []
216
+ },
217
+ "save_checkpoint_to_hub": false,
218
+ "sample_weighting": null,
219
+ "rename_map": {},
220
+ "checkpoint_path": null
221
+ }
checkpoints/010000/training_state/optimizer_param_groups.json ADDED
@@ -0,0 +1,191 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "lr": 1e-05,
4
+ "betas": [
5
+ 0.9,
6
+ 0.999
7
+ ],
8
+ "eps": 1e-08,
9
+ "weight_decay": 0.0001,
10
+ "amsgrad": false,
11
+ "maximize": false,
12
+ "foreach": null,
13
+ "capturable": false,
14
+ "differentiable": false,
15
+ "fused": null,
16
+ "decoupled_weight_decay": true,
17
+ "params": [
18
+ 0,
19
+ 1,
20
+ 2,
21
+ 3,
22
+ 4,
23
+ 5,
24
+ 6,
25
+ 7,
26
+ 8,
27
+ 9,
28
+ 10,
29
+ 11,
30
+ 12,
31
+ 13,
32
+ 14,
33
+ 15,
34
+ 16,
35
+ 17,
36
+ 18,
37
+ 19,
38
+ 20,
39
+ 21,
40
+ 22,
41
+ 23,
42
+ 24,
43
+ 25,
44
+ 26,
45
+ 27,
46
+ 28,
47
+ 29,
48
+ 30,
49
+ 31,
50
+ 32,
51
+ 33,
52
+ 34,
53
+ 35,
54
+ 36,
55
+ 37,
56
+ 38,
57
+ 39,
58
+ 40,
59
+ 41,
60
+ 42,
61
+ 43,
62
+ 44,
63
+ 45,
64
+ 46,
65
+ 47,
66
+ 48,
67
+ 49,
68
+ 50,
69
+ 51,
70
+ 52,
71
+ 53,
72
+ 54,
73
+ 55,
74
+ 56,
75
+ 57,
76
+ 58,
77
+ 59,
78
+ 60,
79
+ 61,
80
+ 62,
81
+ 63,
82
+ 64,
83
+ 65,
84
+ 66,
85
+ 67,
86
+ 68,
87
+ 69,
88
+ 70,
89
+ 71,
90
+ 72,
91
+ 73,
92
+ 74,
93
+ 75,
94
+ 76,
95
+ 77,
96
+ 78,
97
+ 79,
98
+ 80,
99
+ 81,
100
+ 82,
101
+ 83,
102
+ 84,
103
+ 85,
104
+ 86,
105
+ 87,
106
+ 88,
107
+ 89,
108
+ 90,
109
+ 91,
110
+ 92,
111
+ 93,
112
+ 94,
113
+ 95,
114
+ 96,
115
+ 97,
116
+ 98,
117
+ 99,
118
+ 100,
119
+ 101,
120
+ 102,
121
+ 103,
122
+ 104,
123
+ 105,
124
+ 106,
125
+ 107,
126
+ 108,
127
+ 109,
128
+ 110,
129
+ 111,
130
+ 112,
131
+ 113,
132
+ 114,
133
+ 115,
134
+ 116,
135
+ 117,
136
+ 118,
137
+ 119,
138
+ 120,
139
+ 121,
140
+ 122,
141
+ 123,
142
+ 124,
143
+ 125,
144
+ 126,
145
+ 127,
146
+ 128,
147
+ 129,
148
+ 130,
149
+ 131,
150
+ 132
151
+ ]
152
+ },
153
+ {
154
+ "lr": 1e-05,
155
+ "betas": [
156
+ 0.9,
157
+ 0.999
158
+ ],
159
+ "eps": 1e-08,
160
+ "weight_decay": 0.0001,
161
+ "amsgrad": false,
162
+ "maximize": false,
163
+ "foreach": null,
164
+ "capturable": false,
165
+ "differentiable": false,
166
+ "fused": null,
167
+ "decoupled_weight_decay": true,
168
+ "params": [
169
+ 133,
170
+ 134,
171
+ 135,
172
+ 136,
173
+ 137,
174
+ 138,
175
+ 139,
176
+ 140,
177
+ 141,
178
+ 142,
179
+ 143,
180
+ 144,
181
+ 145,
182
+ 146,
183
+ 147,
184
+ 148,
185
+ 149,
186
+ 150,
187
+ 151,
188
+ 152
189
+ ]
190
+ }
191
+ ]
checkpoints/010000/training_state/optimizer_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17ad578ede7cfc8bfec11b43ddd59add41cad82008e7bf9873516ca8891df8b9
3
+ size 412817652
checkpoints/010000/training_state/rng_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8209532729ee425f57fec0e569229ae68c28739d8b02f97e95630a13493e6c2c
3
+ size 15708
checkpoints/010000/training_state/training_step.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "step": 10000,
3
+ "num_processes": 1,
4
+ "batch_size": 16
5
+ }