Hugging Face's logo

abdul004
/
so101_dot_policy_v5

Robotics
LeRobot
Safetensors
dot
decoder-only-transformer
imitation-learning
so101
experimental
Model card Files
xet
Community
abdul004 commited on
Commit
181debe
·
verified ·
1 Parent(s): a69fdbb

Upload folder using huggingface_hub

Browse files
Files changed (10) hide show
  1. checkpoints/038000/pretrained_model/config.json +141 -0
  2. checkpoints/038000/pretrained_model/model.safetensors +3 -0
  3. checkpoints/038000/pretrained_model/policy_postprocessor.json +12 -0
  4. checkpoints/038000/pretrained_model/policy_preprocessor.json +22 -0
  5. checkpoints/038000/pretrained_model/train_config.json +276 -0
  6. checkpoints/038000/training_state/optimizer_param_groups.json +235 -0
  7. checkpoints/038000/training_state/optimizer_state.safetensors +3 -0
  8. checkpoints/038000/training_state/rng_state.safetensors +3 -0
  9. checkpoints/038000/training_state/scheduler_state.json +13 -0
  10. checkpoints/038000/training_state/training_step.json +3 -0
checkpoints/038000/pretrained_model/config.json ADDED
@@ -0,0 +1,141 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "type": "dot",
3
+ "n_obs_steps": 3,
4
+ "input_features": {
5
+ "observation.state": {
6
+ "type": "STATE",
7
+ "shape": [
8
+ 6
9
+ ]
10
+ },
11
+ "observation.images.wrist": {
12
+ "type": "VISUAL",
13
+ "shape": [
14
+ 3,
15
+ 480,
16
+ 640
17
+ ]
18
+ },
19
+ "observation.images.overhead": {
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": "abdul004/so101_dot_policy_v5",
41
+ "private": null,
42
+ "tags": null,
43
+ "license": null,
44
+ "pretrained_path": "/root/lerobot/outputs/train/so101_v5_dot/checkpoints/last/pretrained_model",
45
+ "train_horizon": 150,
46
+ "inference_horizon": 100,
47
+ "lookback_obs_steps": 30,
48
+ "lookback_aug": 5,
49
+ "normalization_mapping": {
50
+ "VISUAL": "MEAN_STD",
51
+ "STATE": "MIN_MAX",
52
+ "ENV": "MIN_MAX",
53
+ "ACTION": "MIN_MAX"
54
+ },
55
+ "override_dataset_stats": false,
56
+ "new_dataset_stats": {
57
+ "action": {
58
+ "max": [
59
+ 512.0,
60
+ 512.0
61
+ ],
62
+ "min": [
63
+ 0.0,
64
+ 0.0
65
+ ]
66
+ },
67
+ "observation.environment_state": {
68
+ "max": [
69
+ 512.0,
70
+ 512.0,
71
+ 512.0,
72
+ 512.0,
73
+ 512.0,
74
+ 512.0,
75
+ 512.0,
76
+ 512.0,
77
+ 512.0,
78
+ 512.0,
79
+ 512.0,
80
+ 512.0,
81
+ 512.0,
82
+ 512.0,
83
+ 512.0,
84
+ 512.0
85
+ ],
86
+ "min": [
87
+ 0.0,
88
+ 0.0,
89
+ 0.0,
90
+ 0.0,
91
+ 0.0,
92
+ 0.0,
93
+ 0.0,
94
+ 0.0,
95
+ 0.0,
96
+ 0.0,
97
+ 0.0,
98
+ 0.0,
99
+ 0.0,
100
+ 0.0,
101
+ 0.0,
102
+ 0.0
103
+ ]
104
+ },
105
+ "observation.state": {
106
+ "max": [
107
+ 512.0,
108
+ 512.0
109
+ ],
110
+ "min": [
111
+ 0.0,
112
+ 0.0
113
+ ]
114
+ }
115
+ },
116
+ "vision_backbone": "resnet18",
117
+ "pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
118
+ "pre_norm": true,
119
+ "lora_rank": 20,
120
+ "merge_lora": false,
121
+ "dim_model": 128,
122
+ "n_heads": 8,
123
+ "dim_feedforward": 512,
124
+ "n_decoder_layers": 8,
125
+ "rescale_shape": [
126
+ 96,
127
+ 96
128
+ ],
129
+ "crop_scale": 0.8,
130
+ "state_noise": 0.01,
131
+ "noise_decay": 0.999995,
132
+ "dropout": 0.1,
133
+ "alpha": 0.75,
134
+ "train_alpha": 0.9,
135
+ "predict_every_n": 1,
136
+ "return_every_n": 1,
137
+ "optimizer_lr": 3e-05,
138
+ "optimizer_min_lr": 1e-05,
139
+ "optimizer_lr_cycle_steps": 300000,
140
+ "optimizer_weight_decay": 1e-05
141
+ }
checkpoints/038000/pretrained_model/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a39806aef2ff3e745c4ed36287ab07c028950c60fc503dd3ff53411dc6dbe7f
3
+ size 56549048
checkpoints/038000/pretrained_model/policy_postprocessor.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "name": "policy_postprocessor",
3
+ "steps": [
4
+ {
5
+ "registry_name": "device_processor",
6
+ "config": {
7
+ "device": "cpu",
8
+ "float_dtype": null
9
+ }
10
+ }
11
+ ]
12
+ }
checkpoints/038000/pretrained_model/policy_preprocessor.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ }
checkpoints/038000/pretrained_model/train_config.json ADDED
@@ -0,0 +1,276 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset": {
3
+ "repo_id": "abdul004/so101_ball_in_cup_v5",
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
+ "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": "torchcodec",
80
+ "streaming": false
81
+ },
82
+ "env": null,
83
+ "policy": {
84
+ "type": "dot",
85
+ "n_obs_steps": 3,
86
+ "input_features": {
87
+ "observation.state": {
88
+ "type": "STATE",
89
+ "shape": [
90
+ 6
91
+ ]
92
+ },
93
+ "observation.images.wrist": {
94
+ "type": "VISUAL",
95
+ "shape": [
96
+ 3,
97
+ 480,
98
+ 640
99
+ ]
100
+ },
101
+ "observation.images.overhead": {
102
+ "type": "VISUAL",
103
+ "shape": [
104
+ 3,
105
+ 480,
106
+ 640
107
+ ]
108
+ }
109
+ },
110
+ "output_features": {
111
+ "action": {
112
+ "type": "ACTION",
113
+ "shape": [
114
+ 6
115
+ ]
116
+ }
117
+ },
118
+ "device": "cuda",
119
+ "use_amp": false,
120
+ "use_peft": false,
121
+ "push_to_hub": true,
122
+ "repo_id": "abdul004/so101_dot_policy_v5",
123
+ "private": null,
124
+ "tags": null,
125
+ "license": null,
126
+ "pretrained_path": "/root/lerobot/outputs/train/so101_v5_dot/checkpoints/last/pretrained_model",
127
+ "train_horizon": 150,
128
+ "inference_horizon": 100,
129
+ "lookback_obs_steps": 30,
130
+ "lookback_aug": 5,
131
+ "normalization_mapping": {
132
+ "VISUAL": "MEAN_STD",
133
+ "STATE": "MIN_MAX",
134
+ "ENV": "MIN_MAX",
135
+ "ACTION": "MIN_MAX"
136
+ },
137
+ "override_dataset_stats": false,
138
+ "new_dataset_stats": {
139
+ "action": {
140
+ "max": [
141
+ 512.0,
142
+ 512.0
143
+ ],
144
+ "min": [
145
+ 0.0,
146
+ 0.0
147
+ ]
148
+ },
149
+ "observation.environment_state": {
150
+ "max": [
151
+ 512.0,
152
+ 512.0,
153
+ 512.0,
154
+ 512.0,
155
+ 512.0,
156
+ 512.0,
157
+ 512.0,
158
+ 512.0,
159
+ 512.0,
160
+ 512.0,
161
+ 512.0,
162
+ 512.0,
163
+ 512.0,
164
+ 512.0,
165
+ 512.0,
166
+ 512.0
167
+ ],
168
+ "min": [
169
+ 0.0,
170
+ 0.0,
171
+ 0.0,
172
+ 0.0,
173
+ 0.0,
174
+ 0.0,
175
+ 0.0,
176
+ 0.0,
177
+ 0.0,
178
+ 0.0,
179
+ 0.0,
180
+ 0.0,
181
+ 0.0,
182
+ 0.0,
183
+ 0.0,
184
+ 0.0
185
+ ]
186
+ },
187
+ "observation.state": {
188
+ "max": [
189
+ 512.0,
190
+ 512.0
191
+ ],
192
+ "min": [
193
+ 0.0,
194
+ 0.0
195
+ ]
196
+ }
197
+ },
198
+ "vision_backbone": "resnet18",
199
+ "pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
200
+ "pre_norm": true,
201
+ "lora_rank": 20,
202
+ "merge_lora": false,
203
+ "dim_model": 128,
204
+ "n_heads": 8,
205
+ "dim_feedforward": 512,
206
+ "n_decoder_layers": 8,
207
+ "rescale_shape": [
208
+ 96,
209
+ 96
210
+ ],
211
+ "crop_scale": 0.8,
212
+ "state_noise": 0.01,
213
+ "noise_decay": 0.999995,
214
+ "dropout": 0.1,
215
+ "alpha": 0.75,
216
+ "train_alpha": 0.9,
217
+ "predict_every_n": 1,
218
+ "return_every_n": 1,
219
+ "optimizer_lr": 3e-05,
220
+ "optimizer_min_lr": 1e-05,
221
+ "optimizer_lr_cycle_steps": 300000,
222
+ "optimizer_weight_decay": 1e-05
223
+ },
224
+ "output_dir": "outputs/train/so101_v5_dot",
225
+ "job_name": "dot",
226
+ "resume": true,
227
+ "seed": 1000,
228
+ "num_workers": 24,
229
+ "batch_size": 12,
230
+ "steps": 100000,
231
+ "eval_freq": -1,
232
+ "log_freq": 100,
233
+ "tolerance_s": 0.0001,
234
+ "save_checkpoint": true,
235
+ "save_freq": 1000,
236
+ "use_policy_training_preset": true,
237
+ "optimizer": {
238
+ "type": "adamw",
239
+ "lr": 3e-05,
240
+ "weight_decay": 1e-05,
241
+ "grad_clip_norm": 10.0,
242
+ "betas": [
243
+ 0.9,
244
+ 0.999
245
+ ],
246
+ "eps": 1e-08
247
+ },
248
+ "scheduler": {
249
+ "type": "cosine_annealing",
250
+ "num_warmup_steps": 0,
251
+ "min_lr": 1e-05,
252
+ "T_max": 300000
253
+ },
254
+ "eval": {
255
+ "n_episodes": 50,
256
+ "batch_size": 50,
257
+ "use_async_envs": false
258
+ },
259
+ "wandb": {
260
+ "enable": false,
261
+ "disable_artifact": false,
262
+ "project": "lerobot",
263
+ "entity": null,
264
+ "notes": null,
265
+ "run_id": null,
266
+ "mode": null
267
+ },
268
+ "peft": null,
269
+ "use_rabc": false,
270
+ "rabc_progress_path": null,
271
+ "rabc_kappa": 0.01,
272
+ "rabc_epsilon": 1e-06,
273
+ "rabc_head_mode": "sparse",
274
+ "rename_map": {},
275
+ "checkpoint_path": "/root/lerobot/outputs/train/so101_v5_dot/checkpoints/last"
276
+ }
checkpoints/038000/training_state/optimizer_param_groups.json ADDED
@@ -0,0 +1,235 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "lr": 2.921863151594776e-05,
4
+ "betas": [
5
+ 0.9,
6
+ 0.999
7
+ ],
8
+ "eps": 1e-08,
9
+ "weight_decay": 1e-05,
10
+ "amsgrad": false,
11
+ "maximize": false,
12
+ "foreach": null,
13
+ "capturable": false,
14
+ "differentiable": false,
15
+ "fused": null,
16
+ "decoupled_weight_decay": true,
17
+ "initial_lr": 3e-05,
18
+ "params": [
19
+ 0,
20
+ 1,
21
+ 2,
22
+ 3,
23
+ 4,
24
+ 5,
25
+ 6,
26
+ 7,
27
+ 8,
28
+ 9,
29
+ 10,
30
+ 11,
31
+ 12,
32
+ 13,
33
+ 14,
34
+ 15,
35
+ 16,
36
+ 17,
37
+ 18,
38
+ 19,
39
+ 20,
40
+ 21,
41
+ 22,
42
+ 23,
43
+ 24,
44
+ 25,
45
+ 26,
46
+ 27,
47
+ 28,
48
+ 29,
49
+ 30,
50
+ 31,
51
+ 32,
52
+ 33,
53
+ 34,
54
+ 35,
55
+ 36,
56
+ 37,
57
+ 38,
58
+ 39,
59
+ 40,
60
+ 41,
61
+ 42,
62
+ 43,
63
+ 44,
64
+ 45,
65
+ 46,
66
+ 47,
67
+ 48,
68
+ 49,
69
+ 50,
70
+ 51,
71
+ 52,
72
+ 53,
73
+ 54,
74
+ 55,
75
+ 56,
76
+ 57,
77
+ 58,
78
+ 59,
79
+ 60,
80
+ 61,
81
+ 62,
82
+ 63,
83
+ 64,
84
+ 65,
85
+ 66,
86
+ 67,
87
+ 68,
88
+ 69,
89
+ 70,
90
+ 71,
91
+ 72,
92
+ 73,
93
+ 74,
94
+ 75,
95
+ 76,
96
+ 77,
97
+ 78,
98
+ 79,
99
+ 80,
100
+ 81,
101
+ 82,
102
+ 83,
103
+ 84,
104
+ 85,
105
+ 86,
106
+ 87,
107
+ 88,
108
+ 89,
109
+ 90,
110
+ 91,
111
+ 92,
112
+ 93,
113
+ 94,
114
+ 95,
115
+ 96,
116
+ 97,
117
+ 98,
118
+ 99,
119
+ 100,
120
+ 101,
121
+ 102,
122
+ 103,
123
+ 104,
124
+ 105,
125
+ 106,
126
+ 107,
127
+ 108,
128
+ 109,
129
+ 110,
130
+ 111,
131
+ 112,
132
+ 113,
133
+ 114,
134
+ 115,
135
+ 116,
136
+ 117,
137
+ 118,
138
+ 119,
139
+ 120,
140
+ 121,
141
+ 122,
142
+ 123,
143
+ 124,
144
+ 125,
145
+ 126,
146
+ 127,
147
+ 128,
148
+ 129,
149
+ 130,
150
+ 131,
151
+ 132,
152
+ 133,
153
+ 134,
154
+ 135,
155
+ 136,
156
+ 137,
157
+ 138,
158
+ 139,
159
+ 140,
160
+ 141,
161
+ 142,
162
+ 143,
163
+ 144,
164
+ 145,
165
+ 146,
166
+ 147,
167
+ 148,
168
+ 149,
169
+ 150,
170
+ 151,
171
+ 152,
172
+ 153,
173
+ 154,
174
+ 155,
175
+ 156,
176
+ 157,
177
+ 158,
178
+ 159,
179
+ 160,
180
+ 161,
181
+ 162,
182
+ 163,
183
+ 164,
184
+ 165,
185
+ 166,
186
+ 167,
187
+ 168,
188
+ 169,
189
+ 170,
190
+ 171,
191
+ 172,
192
+ 173,
193
+ 174,
194
+ 175,
195
+ 176,
196
+ 177,
197
+ 178,
198
+ 179,
199
+ 180,
200
+ 181,
201
+ 182,
202
+ 183,
203
+ 184,
204
+ 185,
205
+ 186,
206
+ 187,
207
+ 188,
208
+ 189,
209
+ 190,
210
+ 191,
211
+ 192,
212
+ 193,
213
+ 194,
214
+ 195,
215
+ 196,
216
+ 197,
217
+ 198,
218
+ 199,
219
+ 200,
220
+ 201,
221
+ 202,
222
+ 203,
223
+ 204,
224
+ 205,
225
+ 206,
226
+ 207,
227
+ 208,
228
+ 209,
229
+ 210,
230
+ 211,
231
+ 212,
232
+ 213
233
+ ]
234
+ }
235
+ ]
checkpoints/038000/training_state/optimizer_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e86a32d1f9b258f413e7413781aed92d6edaad8aa7844cb2eb62b905cf54aa88
3
+ size 23280936
checkpoints/038000/training_state/rng_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07b0795197a077b4868d3743e5cb480644ecf3975053cffc48c158265dc10b45
3
+ size 15708
checkpoints/038000/training_state/scheduler_state.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "T_max": 300000,
3
+ "eta_min": 1e-05,
4
+ "base_lrs": [
5
+ 3e-05
6
+ ],
7
+ "last_epoch": 38000,
8
+ "_step_count": 38001,
9
+ "_get_lr_called_within_step": false,
10
+ "_last_lr": [
11
+ 2.921863151594776e-05
12
+ ]
13
+ }
checkpoints/038000/training_state/training_step.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "step": 38000
3
+ }