TreeePlanter commited on
Commit
c454745
·
verified ·
1 Parent(s): dd7b3d5

Upload folder using huggingface_hub

Browse files
pretrained_model/config.json ADDED
@@ -0,0 +1,90 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "type": "diffusion",
3
+ "n_obs_steps": 2,
4
+ "input_features": {
5
+ "observation.state": {
6
+ "type": "STATE",
7
+ "shape": [
8
+ 15
9
+ ]
10
+ },
11
+ "observation.images.third_person": {
12
+ "type": "VISUAL",
13
+ "shape": [
14
+ 3,
15
+ 256,
16
+ 256
17
+ ]
18
+ },
19
+ "observation.images.eye_in_hand": {
20
+ "type": "VISUAL",
21
+ "shape": [
22
+ 3,
23
+ 256,
24
+ 256
25
+ ]
26
+ }
27
+ },
28
+ "output_features": {
29
+ "action": {
30
+ "type": "ACTION",
31
+ "shape": [
32
+ 7
33
+ ]
34
+ }
35
+ },
36
+ "device": "cuda",
37
+ "use_amp": false,
38
+ "push_to_hub": false,
39
+ "repo_id": null,
40
+ "private": null,
41
+ "tags": null,
42
+ "license": null,
43
+ "pretrained_path": null,
44
+ "horizon": 16,
45
+ "n_action_steps": 8,
46
+ "normalization_mapping": {
47
+ "VISUAL": "MEAN_STD",
48
+ "STATE": "MIN_MAX",
49
+ "ACTION": "MIN_MAX"
50
+ },
51
+ "drop_n_last_frames": 7,
52
+ "vision_backbone": "resnet18",
53
+ "crop_shape": [
54
+ 224,
55
+ 224
56
+ ],
57
+ "crop_is_random": true,
58
+ "pretrained_backbone_weights": null,
59
+ "use_group_norm": true,
60
+ "spatial_softmax_num_keypoints": 32,
61
+ "use_separate_rgb_encoder_per_camera": false,
62
+ "down_dims": [
63
+ 256,
64
+ 512,
65
+ 1024
66
+ ],
67
+ "kernel_size": 5,
68
+ "n_groups": 8,
69
+ "diffusion_step_embed_dim": 256,
70
+ "use_film_scale_modulation": true,
71
+ "noise_scheduler_type": "DDPM",
72
+ "num_train_timesteps": 100,
73
+ "beta_schedule": "squaredcos_cap_v2",
74
+ "beta_start": 0.0001,
75
+ "beta_end": 0.02,
76
+ "prediction_type": "epsilon",
77
+ "clip_sample": true,
78
+ "clip_sample_range": 1.0,
79
+ "num_inference_steps": null,
80
+ "do_mask_loss_for_padding": false,
81
+ "optimizer_lr": 0.0001,
82
+ "optimizer_betas": [
83
+ 0.95,
84
+ 0.999
85
+ ],
86
+ "optimizer_eps": 1e-08,
87
+ "optimizer_weight_decay": 1e-06,
88
+ "scheduler_name": "cosine",
89
+ "scheduler_warmup_steps": 500
90
+ }
pretrained_model/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:183072171830d825d45a501af722c9792081630ae2f085f4f02c29398820e5e8
3
+ size 322089540
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
+ 7
13
+ ]
14
+ }
15
+ },
16
+ "norm_map": {
17
+ "VISUAL": "MEAN_STD",
18
+ "STATE": "MIN_MAX",
19
+ "ACTION": "MIN_MAX"
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
+ }
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 sha256:692a0c30e51b6de83a7085b039584252ff65047ecc0b8b576f4f7153c30dedac
3
+ size 8096
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
+ 15
30
+ ]
31
+ },
32
+ "observation.images.third_person": {
33
+ "type": "VISUAL",
34
+ "shape": [
35
+ 3,
36
+ 256,
37
+ 256
38
+ ]
39
+ },
40
+ "observation.images.eye_in_hand": {
41
+ "type": "VISUAL",
42
+ "shape": [
43
+ 3,
44
+ 256,
45
+ 256
46
+ ]
47
+ },
48
+ "action": {
49
+ "type": "ACTION",
50
+ "shape": [
51
+ 7
52
+ ]
53
+ }
54
+ },
55
+ "norm_map": {
56
+ "VISUAL": "MEAN_STD",
57
+ "STATE": "MIN_MAX",
58
+ "ACTION": "MIN_MAX"
59
+ }
60
+ },
61
+ "state_file": "policy_preprocessor_step_3_normalizer_processor.safetensors"
62
+ }
63
+ ]
64
+ }
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 sha256:692a0c30e51b6de83a7085b039584252ff65047ecc0b8b576f4f7153c30dedac
3
+ size 8096
pretrained_model/train_config.json ADDED
@@ -0,0 +1,217 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset": {
3
+ "repo_id": "/home/shuo/research/datasets/steerDP/calvin_D_train_new",
4
+ "root": null,
5
+ "episodes": null,
6
+ "image_transforms": {
7
+ "enable": true,
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
+ "affine": {
62
+ "weight": 1.0,
63
+ "type": "RandomAffine",
64
+ "kwargs": {
65
+ "degrees": [
66
+ -5.0,
67
+ 5.0
68
+ ],
69
+ "translate": [
70
+ 0.05,
71
+ 0.05
72
+ ]
73
+ }
74
+ }
75
+ }
76
+ },
77
+ "revision": null,
78
+ "use_imagenet_stats": true,
79
+ "video_backend": "pyav",
80
+ "streaming": false
81
+ },
82
+ "env": null,
83
+ "policy": {
84
+ "type": "diffusion",
85
+ "n_obs_steps": 2,
86
+ "input_features": {
87
+ "observation.state": {
88
+ "type": "STATE",
89
+ "shape": [
90
+ 15
91
+ ]
92
+ },
93
+ "observation.images.third_person": {
94
+ "type": "VISUAL",
95
+ "shape": [
96
+ 3,
97
+ 256,
98
+ 256
99
+ ]
100
+ },
101
+ "observation.images.eye_in_hand": {
102
+ "type": "VISUAL",
103
+ "shape": [
104
+ 3,
105
+ 256,
106
+ 256
107
+ ]
108
+ }
109
+ },
110
+ "output_features": {
111
+ "action": {
112
+ "type": "ACTION",
113
+ "shape": [
114
+ 7
115
+ ]
116
+ }
117
+ },
118
+ "device": "cuda",
119
+ "use_amp": false,
120
+ "push_to_hub": false,
121
+ "repo_id": null,
122
+ "private": null,
123
+ "tags": null,
124
+ "license": null,
125
+ "pretrained_path": null,
126
+ "horizon": 16,
127
+ "n_action_steps": 8,
128
+ "normalization_mapping": {
129
+ "VISUAL": "MEAN_STD",
130
+ "STATE": "MIN_MAX",
131
+ "ACTION": "MIN_MAX"
132
+ },
133
+ "drop_n_last_frames": 7,
134
+ "vision_backbone": "resnet18",
135
+ "crop_shape": [
136
+ 224,
137
+ 224
138
+ ],
139
+ "crop_is_random": true,
140
+ "pretrained_backbone_weights": null,
141
+ "use_group_norm": true,
142
+ "spatial_softmax_num_keypoints": 32,
143
+ "use_separate_rgb_encoder_per_camera": false,
144
+ "down_dims": [
145
+ 256,
146
+ 512,
147
+ 1024
148
+ ],
149
+ "kernel_size": 5,
150
+ "n_groups": 8,
151
+ "diffusion_step_embed_dim": 256,
152
+ "use_film_scale_modulation": true,
153
+ "noise_scheduler_type": "DDPM",
154
+ "num_train_timesteps": 100,
155
+ "beta_schedule": "squaredcos_cap_v2",
156
+ "beta_start": 0.0001,
157
+ "beta_end": 0.02,
158
+ "prediction_type": "epsilon",
159
+ "clip_sample": true,
160
+ "clip_sample_range": 1.0,
161
+ "num_inference_steps": null,
162
+ "do_mask_loss_for_padding": false,
163
+ "optimizer_lr": 0.0001,
164
+ "optimizer_betas": [
165
+ 0.95,
166
+ 0.999
167
+ ],
168
+ "optimizer_eps": 1e-08,
169
+ "optimizer_weight_decay": 1e-06,
170
+ "scheduler_name": "cosine",
171
+ "scheduler_warmup_steps": 500
172
+ },
173
+ "output_dir": "outputs/train/2025-12-04/11-01-15_diffusion",
174
+ "job_name": "diffusion",
175
+ "resume": false,
176
+ "seed": 1000,
177
+ "num_workers": 4,
178
+ "batch_size": 16,
179
+ "steps": 200000,
180
+ "eval_freq": 20000,
181
+ "log_freq": 200,
182
+ "save_checkpoint": true,
183
+ "save_freq": 20000,
184
+ "use_policy_training_preset": true,
185
+ "optimizer": {
186
+ "type": "adam",
187
+ "lr": 0.0001,
188
+ "weight_decay": 1e-06,
189
+ "grad_clip_norm": 10.0,
190
+ "betas": [
191
+ 0.95,
192
+ 0.999
193
+ ],
194
+ "eps": 1e-08
195
+ },
196
+ "scheduler": {
197
+ "type": "diffuser",
198
+ "num_warmup_steps": 500,
199
+ "name": "cosine"
200
+ },
201
+ "eval": {
202
+ "n_episodes": 50,
203
+ "batch_size": 50,
204
+ "use_async_envs": false
205
+ },
206
+ "wandb": {
207
+ "enable": true,
208
+ "disable_artifact": false,
209
+ "project": "lerobot",
210
+ "entity": null,
211
+ "notes": null,
212
+ "run_id": "29sv6zg5",
213
+ "mode": null
214
+ },
215
+ "checkpoint_path": null,
216
+ "rename_map": {}
217
+ }
training_state/optimizer_param_groups.json ADDED
@@ -0,0 +1,232 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "lr": 0.0,
4
+ "betas": [
5
+ 0.95,
6
+ 0.999
7
+ ],
8
+ "eps": 1e-08,
9
+ "weight_decay": 1e-06,
10
+ "amsgrad": false,
11
+ "maximize": false,
12
+ "foreach": null,
13
+ "capturable": false,
14
+ "differentiable": false,
15
+ "fused": null,
16
+ "initial_lr": 0.0001,
17
+ "params": [
18
+ 0,
19
+ 1,
20
+ 2,
21
+ 3,
22
+ 4,
23
+ 5,
24
+ 6,
25
+ 7,
26
+ 8,
27
+ 9,
28
+ 10,
29
+ 11,
30
+ 12,
31
+ 13,
32
+ 14,
33
+ 15,
34
+ 16,
35
+ 17,
36
+ 18,
37
+ 19,
38
+ 20,
39
+ 21,
40
+ 22,
41
+ 23,
42
+ 24,
43
+ 25,
44
+ 26,
45
+ 27,
46
+ 28,
47
+ 29,
48
+ 30,
49
+ 31,
50
+ 32,
51
+ 33,
52
+ 34,
53
+ 35,
54
+ 36,
55
+ 37,
56
+ 38,
57
+ 39,
58
+ 40,
59
+ 41,
60
+ 42,
61
+ 43,
62
+ 44,
63
+ 45,
64
+ 46,
65
+ 47,
66
+ 48,
67
+ 49,
68
+ 50,
69
+ 51,
70
+ 52,
71
+ 53,
72
+ 54,
73
+ 55,
74
+ 56,
75
+ 57,
76
+ 58,
77
+ 59,
78
+ 60,
79
+ 61,
80
+ 62,
81
+ 63,
82
+ 64,
83
+ 65,
84
+ 66,
85
+ 67,
86
+ 68,
87
+ 69,
88
+ 70,
89
+ 71,
90
+ 72,
91
+ 73,
92
+ 74,
93
+ 75,
94
+ 76,
95
+ 77,
96
+ 78,
97
+ 79,
98
+ 80,
99
+ 81,
100
+ 82,
101
+ 83,
102
+ 84,
103
+ 85,
104
+ 86,
105
+ 87,
106
+ 88,
107
+ 89,
108
+ 90,
109
+ 91,
110
+ 92,
111
+ 93,
112
+ 94,
113
+ 95,
114
+ 96,
115
+ 97,
116
+ 98,
117
+ 99,
118
+ 100,
119
+ 101,
120
+ 102,
121
+ 103,
122
+ 104,
123
+ 105,
124
+ 106,
125
+ 107,
126
+ 108,
127
+ 109,
128
+ 110,
129
+ 111,
130
+ 112,
131
+ 113,
132
+ 114,
133
+ 115,
134
+ 116,
135
+ 117,
136
+ 118,
137
+ 119,
138
+ 120,
139
+ 121,
140
+ 122,
141
+ 123,
142
+ 124,
143
+ 125,
144
+ 126,
145
+ 127,
146
+ 128,
147
+ 129,
148
+ 130,
149
+ 131,
150
+ 132,
151
+ 133,
152
+ 134,
153
+ 135,
154
+ 136,
155
+ 137,
156
+ 138,
157
+ 139,
158
+ 140,
159
+ 141,
160
+ 142,
161
+ 143,
162
+ 144,
163
+ 145,
164
+ 146,
165
+ 147,
166
+ 148,
167
+ 149,
168
+ 150,
169
+ 151,
170
+ 152,
171
+ 153,
172
+ 154,
173
+ 155,
174
+ 156,
175
+ 157,
176
+ 158,
177
+ 159,
178
+ 160,
179
+ 161,
180
+ 162,
181
+ 163,
182
+ 164,
183
+ 165,
184
+ 166,
185
+ 167,
186
+ 168,
187
+ 169,
188
+ 170,
189
+ 171,
190
+ 172,
191
+ 173,
192
+ 174,
193
+ 175,
194
+ 176,
195
+ 177,
196
+ 178,
197
+ 179,
198
+ 180,
199
+ 181,
200
+ 182,
201
+ 183,
202
+ 184,
203
+ 185,
204
+ 186,
205
+ 187,
206
+ 188,
207
+ 189,
208
+ 190,
209
+ 191,
210
+ 192,
211
+ 193,
212
+ 194,
213
+ 195,
214
+ 196,
215
+ 197,
216
+ 198,
217
+ 199,
218
+ 200,
219
+ 201,
220
+ 202,
221
+ 203,
222
+ 204,
223
+ 205,
224
+ 206,
225
+ 207,
226
+ 208,
227
+ 209,
228
+ 210,
229
+ 211
230
+ ]
231
+ }
232
+ ]
training_state/optimizer_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d817e54d38d16fbf03a3b87347653c94e93eadbda1ad0d25592c4029f9e433e4
3
+ size 644183936
training_state/rng_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:911b560e974d0867f2fc009ec605740d24d1284cdb4cfa50d734cdc36644ddd2
3
+ size 15708
training_state/scheduler_state.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "base_lrs": [
3
+ 0.0001
4
+ ],
5
+ "last_epoch": 200000,
6
+ "verbose": false,
7
+ "_step_count": 200001,
8
+ "_get_lr_called_within_step": false,
9
+ "_last_lr": [
10
+ 0.0
11
+ ],
12
+ "lr_lambdas": [
13
+ null
14
+ ]
15
+ }
training_state/training_step.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "step": 200000
3
+ }