Hugging Face's logo

bearlover365
/
d4_dataset_only_2_validation_episodes_diffusion_200000

Safetensors
Model card Files
xet
Community
bearlover365 commited on
Commit
04302ce
·
verified ·
1 Parent(s): 87096f1

Upload full checkpoint 200000

Browse files
Files changed (8) hide show
  1. pretrained_model/config.json +81 -0
  2. pretrained_model/model.safetensors +3 -0
  3. pretrained_model/train_config.json +198 -0
  4. training_state/optimizer_param_groups.json +233 -0
  5. training_state/optimizer_state.safetensors +3 -0
  6. training_state/rng_state.safetensors +3 -0
  7. training_state/scheduler_state.json +14 -0
  8. training_state/training_step.json +3 -0
pretrained_model/config.json ADDED
@@ -0,0 +1,81 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "type": "diffusion",
3
+ "n_obs_steps": 2,
4
+ "normalization_mapping": {
5
+ "VISUAL": "MEAN_STD",
6
+ "STATE": "MIN_MAX",
7
+ "ACTION": "MIN_MAX"
8
+ },
9
+ "input_features": {
10
+ "observation.state": {
11
+ "type": "STATE",
12
+ "shape": [
13
+ 6
14
+ ]
15
+ },
16
+ "observation.images.wrist": {
17
+ "type": "VISUAL",
18
+ "shape": [
19
+ 3,
20
+ 480,
21
+ 640
22
+ ]
23
+ }
24
+ },
25
+ "output_features": {
26
+ "action": {
27
+ "type": "ACTION",
28
+ "shape": [
29
+ 6
30
+ ]
31
+ }
32
+ },
33
+ "device": "cuda",
34
+ "use_amp": true,
35
+ "push_to_hub": true,
36
+ "repo_id": "bearlover365/d4_dataset_only_2_validation_episodes_diffusion",
37
+ "private": null,
38
+ "tags": null,
39
+ "license": null,
40
+ "horizon": 16,
41
+ "n_action_steps": 8,
42
+ "drop_n_last_frames": 7,
43
+ "vision_backbone": "resnet18",
44
+ "crop_shape": [
45
+ 84,
46
+ 84
47
+ ],
48
+ "crop_is_random": true,
49
+ "pretrained_backbone_weights": null,
50
+ "use_group_norm": true,
51
+ "spatial_softmax_num_keypoints": 32,
52
+ "use_separate_rgb_encoder_per_camera": false,
53
+ "down_dims": [
54
+ 512,
55
+ 1024,
56
+ 2048
57
+ ],
58
+ "kernel_size": 5,
59
+ "n_groups": 8,
60
+ "diffusion_step_embed_dim": 128,
61
+ "use_film_scale_modulation": true,
62
+ "noise_scheduler_type": "DDPM",
63
+ "num_train_timesteps": 100,
64
+ "beta_schedule": "squaredcos_cap_v2",
65
+ "beta_start": 0.0001,
66
+ "beta_end": 0.02,
67
+ "prediction_type": "epsilon",
68
+ "clip_sample": true,
69
+ "clip_sample_range": 1.0,
70
+ "num_inference_steps": 50,
71
+ "do_mask_loss_for_padding": false,
72
+ "optimizer_lr": 0.0001,
73
+ "optimizer_betas": [
74
+ 0.95,
75
+ 0.999
76
+ ],
77
+ "optimizer_eps": 1e-08,
78
+ "optimizer_weight_decay": 1e-06,
79
+ "scheduler_name": "cosine",
80
+ "scheduler_warmup_steps": 500
81
+ }
pretrained_model/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc15dcbd33ef3540f377cb18b9be6131d817d63b41ced9220cad231324c1cf35
3
+ size 1051837384
pretrained_model/train_config.json ADDED
@@ -0,0 +1,198 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset": {
3
+ "repo_id": "bearlover365/pick_place_up_to_four_white_socks_varying_daylight_intensity_train",
4
+ "root": null,
5
+ "episodes": null,
6
+ "val_episodes": [
7
+ 0,
8
+ 1
9
+ ],
10
+ "val_repo_id": "bearlover365/pick_place_up_to_four_white_socks_varying_daylight_intensity_validation_episode_0_and_72",
11
+ "image_transforms": {
12
+ "enable": false,
13
+ "max_num_transforms": 3,
14
+ "random_order": false,
15
+ "tfs": {
16
+ "brightness": {
17
+ "weight": 1.0,
18
+ "type": "ColorJitter",
19
+ "kwargs": {
20
+ "brightness": [
21
+ 0.8,
22
+ 1.2
23
+ ]
24
+ }
25
+ },
26
+ "contrast": {
27
+ "weight": 1.0,
28
+ "type": "ColorJitter",
29
+ "kwargs": {
30
+ "contrast": [
31
+ 0.8,
32
+ 1.2
33
+ ]
34
+ }
35
+ },
36
+ "saturation": {
37
+ "weight": 1.0,
38
+ "type": "ColorJitter",
39
+ "kwargs": {
40
+ "saturation": [
41
+ 0.5,
42
+ 1.5
43
+ ]
44
+ }
45
+ },
46
+ "hue": {
47
+ "weight": 1.0,
48
+ "type": "ColorJitter",
49
+ "kwargs": {
50
+ "hue": [
51
+ -0.05,
52
+ 0.05
53
+ ]
54
+ }
55
+ },
56
+ "sharpness": {
57
+ "weight": 1.0,
58
+ "type": "SharpnessJitter",
59
+ "kwargs": {
60
+ "sharpness": [
61
+ 0.5,
62
+ 1.5
63
+ ]
64
+ }
65
+ }
66
+ }
67
+ },
68
+ "revision": null,
69
+ "use_imagenet_stats": true,
70
+ "video_backend": "pyav"
71
+ },
72
+ "env": null,
73
+ "policy": {
74
+ "type": "diffusion",
75
+ "n_obs_steps": 2,
76
+ "normalization_mapping": {
77
+ "VISUAL": "MEAN_STD",
78
+ "STATE": "MIN_MAX",
79
+ "ACTION": "MIN_MAX"
80
+ },
81
+ "input_features": {
82
+ "observation.state": {
83
+ "type": "STATE",
84
+ "shape": [
85
+ 6
86
+ ]
87
+ },
88
+ "observation.images.wrist": {
89
+ "type": "VISUAL",
90
+ "shape": [
91
+ 3,
92
+ 480,
93
+ 640
94
+ ]
95
+ }
96
+ },
97
+ "output_features": {
98
+ "action": {
99
+ "type": "ACTION",
100
+ "shape": [
101
+ 6
102
+ ]
103
+ }
104
+ },
105
+ "device": "cuda",
106
+ "use_amp": true,
107
+ "push_to_hub": true,
108
+ "repo_id": "bearlover365/d4_dataset_only_2_validation_episodes_diffusion",
109
+ "private": null,
110
+ "tags": null,
111
+ "license": null,
112
+ "horizon": 16,
113
+ "n_action_steps": 8,
114
+ "drop_n_last_frames": 7,
115
+ "vision_backbone": "resnet18",
116
+ "crop_shape": [
117
+ 84,
118
+ 84
119
+ ],
120
+ "crop_is_random": true,
121
+ "pretrained_backbone_weights": null,
122
+ "use_group_norm": true,
123
+ "spatial_softmax_num_keypoints": 32,
124
+ "use_separate_rgb_encoder_per_camera": false,
125
+ "down_dims": [
126
+ 512,
127
+ 1024,
128
+ 2048
129
+ ],
130
+ "kernel_size": 5,
131
+ "n_groups": 8,
132
+ "diffusion_step_embed_dim": 128,
133
+ "use_film_scale_modulation": true,
134
+ "noise_scheduler_type": "DDPM",
135
+ "num_train_timesteps": 100,
136
+ "beta_schedule": "squaredcos_cap_v2",
137
+ "beta_start": 0.0001,
138
+ "beta_end": 0.02,
139
+ "prediction_type": "epsilon",
140
+ "clip_sample": true,
141
+ "clip_sample_range": 1.0,
142
+ "num_inference_steps": 50,
143
+ "do_mask_loss_for_padding": false,
144
+ "optimizer_lr": 0.0001,
145
+ "optimizer_betas": [
146
+ 0.95,
147
+ 0.999
148
+ ],
149
+ "optimizer_eps": 1e-08,
150
+ "optimizer_weight_decay": 1e-06,
151
+ "scheduler_name": "cosine",
152
+ "scheduler_warmup_steps": 500
153
+ },
154
+ "output_dir": "/teamspace/studios/this_studio/lerobot/outputs/train/d4_dataset_only_2_validation_episodes_diffusion_smoke_then_train_full_20250831_160813",
155
+ "job_name": "d4_dataset_only_2_validation_episodes_diffusion_smoke_then_train_full_20250831_160813_bs8_lr1.0e-04_bblrNone_smp2400000",
156
+ "resume": false,
157
+ "seed": 1000,
158
+ "num_workers": 4,
159
+ "batch_size": 8,
160
+ "steps": 300000,
161
+ "target_samples": null,
162
+ "eval_freq": 5000,
163
+ "log_freq": 200,
164
+ "save_checkpoint": true,
165
+ "save_freq": 50000,
166
+ "use_policy_training_preset": true,
167
+ "optimizer": {
168
+ "type": "adam",
169
+ "lr": 0.0001,
170
+ "weight_decay": 1e-06,
171
+ "grad_clip_norm": 10.0,
172
+ "betas": [
173
+ 0.95,
174
+ 0.999
175
+ ],
176
+ "eps": 1e-08
177
+ },
178
+ "scheduler": {
179
+ "type": "diffuser",
180
+ "num_warmup_steps": 500,
181
+ "name": "cosine"
182
+ },
183
+ "eval": {
184
+ "n_episodes": 50,
185
+ "batch_size": 50,
186
+ "use_async_envs": false
187
+ },
188
+ "initial_step": 0,
189
+ "wandb": {
190
+ "enable": true,
191
+ "disable_artifact": false,
192
+ "project": "lerobot",
193
+ "entity": "benfduffy-bearcover-gmbh",
194
+ "notes": null,
195
+ "run_id": "diff_full_1756656493",
196
+ "mode": null
197
+ }
198
+ }
training_state/optimizer_param_groups.json ADDED
@@ -0,0 +1,233 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "lr": 2.5075739307928014e-05,
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
+ "decoupled_weight_decay": false,
17
+ "initial_lr": 0.0001,
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
+ ]
232
+ }
233
+ ]
training_state/optimizer_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ccd8e71dc2f0e6fd2f89d05fd454513f73949dd9aabd2f5461ee58018c72689
3
+ size 2103678952
training_state/rng_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30a1af23306c79b815588f6cc5340f23c273d9175dbdc4a113fb0899c9922a67
3
+ size 15708
training_state/scheduler_state.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "base_lrs": [
3
+ 0.0001
4
+ ],
5
+ "last_epoch": 200000,
6
+ "_step_count": 200001,
7
+ "_get_lr_called_within_step": false,
8
+ "_last_lr": [
9
+ 2.5075739307928014e-05
10
+ ],
11
+ "lr_lambdas": [
12
+ null
13
+ ]
14
+ }
training_state/training_step.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "step": 200000
3
+ }