jjr1007 commited on
Commit
fd8400c
·
verified ·
1 Parent(s): 937428a

Upload folder using huggingface_hub

Browse files
028000/pretrained_model/config.json ADDED
@@ -0,0 +1,89 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "type": "diffusion",
3
+ "n_obs_steps": 2,
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
+ },
20
+ "output_features": {
21
+ "action": {
22
+ "type": "ACTION",
23
+ "shape": [
24
+ 6
25
+ ]
26
+ }
27
+ },
28
+ "device": "cuda",
29
+ "use_amp": false,
30
+ "use_peft": false,
31
+ "push_to_hub": true,
32
+ "repo_id": "jjr1007/diffusion_dino",
33
+ "private": null,
34
+ "tags": null,
35
+ "license": null,
36
+ "pretrained_path": null,
37
+ "horizon": 64,
38
+ "n_action_steps": 48,
39
+ "normalization_mapping": {
40
+ "VISUAL": "MEAN_STD",
41
+ "STATE": "MIN_MAX",
42
+ "ACTION": "MIN_MAX"
43
+ },
44
+ "drop_n_last_frames": 7,
45
+ "vision_backbone": "dinov3",
46
+ "resize_shape": [
47
+ 320,
48
+ 240
49
+ ],
50
+ "crop_ratio": 1.0,
51
+ "crop_shape": null,
52
+ "crop_is_random": true,
53
+ "pretrained_backbone_weights": null,
54
+ "use_group_norm": true,
55
+ "spatial_softmax_num_keypoints": 32,
56
+ "use_separate_rgb_encoder_per_camera": false,
57
+ "train_vision_backbone": false,
58
+ "vision_backbone_lr": null,
59
+ "down_dims": [
60
+ 512,
61
+ 1024,
62
+ 2048
63
+ ],
64
+ "kernel_size": 5,
65
+ "n_groups": 8,
66
+ "diffusion_step_embed_dim": 128,
67
+ "use_film_scale_modulation": true,
68
+ "noise_scheduler_type": "DDPM",
69
+ "num_train_timesteps": 100,
70
+ "beta_schedule": "squaredcos_cap_v2",
71
+ "beta_start": 0.0001,
72
+ "beta_end": 0.02,
73
+ "prediction_type": "epsilon",
74
+ "clip_sample": true,
75
+ "clip_sample_range": 1.0,
76
+ "num_inference_steps": null,
77
+ "compile_model": false,
78
+ "compile_mode": "reduce-overhead",
79
+ "do_mask_loss_for_padding": false,
80
+ "optimizer_lr": 0.0001,
81
+ "optimizer_betas": [
82
+ 0.95,
83
+ 0.999
84
+ ],
85
+ "optimizer_eps": 1e-08,
86
+ "optimizer_weight_decay": 1e-06,
87
+ "scheduler_name": "cosine",
88
+ "scheduler_warmup_steps": 500
89
+ }
028000/pretrained_model/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8973fc2e27835e365eeec5eeba2e2de39b80087565b32c15514dcae331e0caf6
3
+ size 1349829864
028000/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": "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
+ }
028000/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:fb88af6bf44a28ec138d979c9415f8d658b0fd6e6e5c658ca8418f8eb0f6d4a9
3
+ size 6560
028000/pretrained_model/policy_preprocessor.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "action": {
41
+ "type": "ACTION",
42
+ "shape": [
43
+ 6
44
+ ]
45
+ }
46
+ },
47
+ "norm_map": {
48
+ "VISUAL": "MEAN_STD",
49
+ "STATE": "MIN_MAX",
50
+ "ACTION": "MIN_MAX"
51
+ }
52
+ },
53
+ "state_file": "policy_preprocessor_step_3_normalizer_processor.safetensors"
54
+ }
55
+ ]
56
+ }
028000/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:b7d2ca5025a5c02b7e8ac1d880b1e3238d66bd2e3baf3ec516c7770f926368c1
3
+ size 6568
028000/pretrained_model/train_config.json ADDED
@@ -0,0 +1,225 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset": {
3
+ "repo_id": "jjr1007/may12_final_cut_all",
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
+ "return_uint8": false,
81
+ "streaming": false
82
+ },
83
+ "env": null,
84
+ "policy": {
85
+ "type": "diffusion",
86
+ "n_obs_steps": 2,
87
+ "input_features": {
88
+ "observation.state": {
89
+ "type": "STATE",
90
+ "shape": [
91
+ 6
92
+ ]
93
+ },
94
+ "observation.images.front": {
95
+ "type": "VISUAL",
96
+ "shape": [
97
+ 3,
98
+ 1080,
99
+ 1920
100
+ ]
101
+ }
102
+ },
103
+ "output_features": {
104
+ "action": {
105
+ "type": "ACTION",
106
+ "shape": [
107
+ 6
108
+ ]
109
+ }
110
+ },
111
+ "device": "cuda",
112
+ "use_amp": false,
113
+ "use_peft": false,
114
+ "push_to_hub": true,
115
+ "repo_id": "jjr1007/diffusion_dino",
116
+ "private": null,
117
+ "tags": null,
118
+ "license": null,
119
+ "pretrained_path": null,
120
+ "horizon": 64,
121
+ "n_action_steps": 48,
122
+ "normalization_mapping": {
123
+ "VISUAL": "MEAN_STD",
124
+ "STATE": "MIN_MAX",
125
+ "ACTION": "MIN_MAX"
126
+ },
127
+ "drop_n_last_frames": 7,
128
+ "vision_backbone": "dinov3",
129
+ "resize_shape": [
130
+ 320,
131
+ 240
132
+ ],
133
+ "crop_ratio": 1.0,
134
+ "crop_shape": null,
135
+ "crop_is_random": true,
136
+ "pretrained_backbone_weights": null,
137
+ "use_group_norm": true,
138
+ "spatial_softmax_num_keypoints": 32,
139
+ "use_separate_rgb_encoder_per_camera": false,
140
+ "train_vision_backbone": false,
141
+ "vision_backbone_lr": null,
142
+ "down_dims": [
143
+ 512,
144
+ 1024,
145
+ 2048
146
+ ],
147
+ "kernel_size": 5,
148
+ "n_groups": 8,
149
+ "diffusion_step_embed_dim": 128,
150
+ "use_film_scale_modulation": true,
151
+ "noise_scheduler_type": "DDPM",
152
+ "num_train_timesteps": 100,
153
+ "beta_schedule": "squaredcos_cap_v2",
154
+ "beta_start": 0.0001,
155
+ "beta_end": 0.02,
156
+ "prediction_type": "epsilon",
157
+ "clip_sample": true,
158
+ "clip_sample_range": 1.0,
159
+ "num_inference_steps": null,
160
+ "compile_model": false,
161
+ "compile_mode": "reduce-overhead",
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
+ "reward_model": null,
174
+ "output_dir": "outputs/run_diffusion_dino",
175
+ "job_name": "diffusion",
176
+ "resume": false,
177
+ "seed": 1000,
178
+ "cudnn_deterministic": false,
179
+ "num_workers": 4,
180
+ "batch_size": 90,
181
+ "prefetch_factor": 4,
182
+ "persistent_workers": true,
183
+ "steps": 30000,
184
+ "eval_freq": 1000,
185
+ "log_freq": 100,
186
+ "tolerance_s": 0.0001,
187
+ "save_checkpoint": true,
188
+ "save_freq": 2000,
189
+ "use_policy_training_preset": true,
190
+ "optimizer": {
191
+ "type": "adam",
192
+ "lr": 0.0001,
193
+ "weight_decay": 1e-06,
194
+ "grad_clip_norm": 10.0,
195
+ "betas": [
196
+ 0.95,
197
+ 0.999
198
+ ],
199
+ "eps": 1e-08
200
+ },
201
+ "scheduler": {
202
+ "type": "diffuser",
203
+ "num_warmup_steps": 500,
204
+ "name": "cosine"
205
+ },
206
+ "eval": {
207
+ "n_episodes": 50,
208
+ "batch_size": 8,
209
+ "use_async_envs": true
210
+ },
211
+ "wandb": {
212
+ "enable": true,
213
+ "disable_artifact": false,
214
+ "project": "multitask-dit-experiments",
215
+ "entity": null,
216
+ "notes": null,
217
+ "run_id": "diffusion_ddpm_dino_final_h64a48",
218
+ "mode": null,
219
+ "add_tags": true
220
+ },
221
+ "peft": null,
222
+ "sample_weighting": null,
223
+ "rename_map": {},
224
+ "checkpoint_path": null
225
+ }
028000/training_state/optimizer_param_groups.json ADDED
@@ -0,0 +1,173 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "lr": 1.1298305091066664e-06,
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
+ ]
172
+ }
173
+ ]
028000/training_state/optimizer_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:69193bbb6e443a530a00d46c0fc96a1a8dcfc1d8f501ace898b84eecf6686a8e
3
+ size 2014315648
028000/training_state/rng_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32da71e69d0f53c942895092bbe1eb1816d1335df87030cbba671a912c455c3b
3
+ size 15708
028000/training_state/scheduler_state.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "base_lrs": [
3
+ 0.0001
4
+ ],
5
+ "last_epoch": 28000,
6
+ "_step_count": 28001,
7
+ "_is_initial": false,
8
+ "_get_lr_called_within_step": false,
9
+ "_last_lr": [
10
+ 1.1298305091066664e-06
11
+ ],
12
+ "lr_lambdas": [
13
+ null
14
+ ]
15
+ }
028000/training_state/training_step.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "step": 28000
3
+ }