Robotics
LeRobot
Safetensors
act
so101
simstudio
alexhegit commited on
Commit
2aa9d80
·
verified ·
1 Parent(s): 747b10c

ACT 50K fine-tune on so101-simstudio-lab01-pnp (MI300X)

Browse files
config.json ADDED
@@ -0,0 +1,80 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "type": "act",
3
+ "n_obs_steps": 1,
4
+ "input_features": {
5
+ "observation.state": {
6
+ "type": "STATE",
7
+ "shape": [
8
+ 15
9
+ ]
10
+ },
11
+ "observation.images.camera_front": {
12
+ "type": "VISUAL",
13
+ "shape": [
14
+ 3,
15
+ 480,
16
+ 640
17
+ ]
18
+ },
19
+ "observation.images.camera_top": {
20
+ "type": "VISUAL",
21
+ "shape": [
22
+ 3,
23
+ 480,
24
+ 640
25
+ ]
26
+ },
27
+ "observation.images.camera_wrist": {
28
+ "type": "VISUAL",
29
+ "shape": [
30
+ 3,
31
+ 480,
32
+ 640
33
+ ]
34
+ }
35
+ },
36
+ "output_features": {
37
+ "action": {
38
+ "type": "ACTION",
39
+ "shape": [
40
+ 6
41
+ ]
42
+ }
43
+ },
44
+ "device": "cuda",
45
+ "use_amp": false,
46
+ "use_peft": false,
47
+ "push_to_hub": false,
48
+ "repo_id": null,
49
+ "private": null,
50
+ "tags": null,
51
+ "license": null,
52
+ "pretrained_path": null,
53
+ "pretrained_revision": null,
54
+ "chunk_size": 100,
55
+ "n_action_steps": 100,
56
+ "normalization_mapping": {
57
+ "VISUAL": "MEAN_STD",
58
+ "STATE": "MEAN_STD",
59
+ "ACTION": "MEAN_STD"
60
+ },
61
+ "vision_backbone": "resnet18",
62
+ "pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
63
+ "replace_final_stride_with_dilation": false,
64
+ "pre_norm": false,
65
+ "dim_model": 512,
66
+ "n_heads": 8,
67
+ "dim_feedforward": 3200,
68
+ "feedforward_activation": "relu",
69
+ "n_encoder_layers": 4,
70
+ "n_decoder_layers": 1,
71
+ "use_vae": true,
72
+ "latent_dim": 32,
73
+ "n_vae_encoder_layers": 4,
74
+ "temporal_ensemble_coeff": null,
75
+ "dropout": 0.1,
76
+ "kl_weight": 10.0,
77
+ "optimizer_lr": 1e-05,
78
+ "optimizer_weight_decay": 0.0001,
79
+ "optimizer_lr_backbone": 1e-05
80
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af5ef212f0875e273b16762dd75052679caf4b8bac9c2d0dda381855b590f594
3
+ size 206736600
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
+ }
policy_postprocessor_step_0_unnormalizer_processor.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c6b31aebcca42af91d8b5de053b47ac49c8bb83ab40033055fc6b395da0de8b
3
+ size 9116
policy_preprocessor.json ADDED
@@ -0,0 +1,72 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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.camera_front": {
33
+ "type": "VISUAL",
34
+ "shape": [
35
+ 3,
36
+ 480,
37
+ 640
38
+ ]
39
+ },
40
+ "observation.images.camera_top": {
41
+ "type": "VISUAL",
42
+ "shape": [
43
+ 3,
44
+ 480,
45
+ 640
46
+ ]
47
+ },
48
+ "observation.images.camera_wrist": {
49
+ "type": "VISUAL",
50
+ "shape": [
51
+ 3,
52
+ 480,
53
+ 640
54
+ ]
55
+ },
56
+ "action": {
57
+ "type": "ACTION",
58
+ "shape": [
59
+ 6
60
+ ]
61
+ }
62
+ },
63
+ "norm_map": {
64
+ "VISUAL": "MEAN_STD",
65
+ "STATE": "MEAN_STD",
66
+ "ACTION": "MEAN_STD"
67
+ }
68
+ },
69
+ "state_file": "policy_preprocessor_step_3_normalizer_processor.safetensors"
70
+ }
71
+ ]
72
+ }
policy_preprocessor_step_3_normalizer_processor.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e64de46a1e52c9a378ef7c2102c0e84a5922211036d500e601b116d893b1eeb7
3
+ size 9124
train_config.json ADDED
@@ -0,0 +1,227 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset": {
3
+ "repo_id": "alexhegit/so101-simstudio-lab01-pnp",
4
+ "root": "./datasets/so101-simstudio-lab01-pnp",
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": "pyav",
80
+ "return_uint8": false,
81
+ "depth_output_unit": "mm",
82
+ "streaming": false,
83
+ "eval_split": 0.0
84
+ },
85
+ "env": null,
86
+ "policy": {
87
+ "type": "act",
88
+ "n_obs_steps": 1,
89
+ "input_features": {
90
+ "observation.state": {
91
+ "type": "STATE",
92
+ "shape": [
93
+ 15
94
+ ]
95
+ },
96
+ "observation.images.camera_front": {
97
+ "type": "VISUAL",
98
+ "shape": [
99
+ 3,
100
+ 480,
101
+ 640
102
+ ]
103
+ },
104
+ "observation.images.camera_top": {
105
+ "type": "VISUAL",
106
+ "shape": [
107
+ 3,
108
+ 480,
109
+ 640
110
+ ]
111
+ },
112
+ "observation.images.camera_wrist": {
113
+ "type": "VISUAL",
114
+ "shape": [
115
+ 3,
116
+ 480,
117
+ 640
118
+ ]
119
+ }
120
+ },
121
+ "output_features": {
122
+ "action": {
123
+ "type": "ACTION",
124
+ "shape": [
125
+ 6
126
+ ]
127
+ }
128
+ },
129
+ "device": "cuda",
130
+ "use_amp": false,
131
+ "use_peft": false,
132
+ "push_to_hub": false,
133
+ "repo_id": null,
134
+ "private": null,
135
+ "tags": null,
136
+ "license": null,
137
+ "pretrained_path": null,
138
+ "pretrained_revision": null,
139
+ "chunk_size": 100,
140
+ "n_action_steps": 100,
141
+ "normalization_mapping": {
142
+ "VISUAL": "MEAN_STD",
143
+ "STATE": "MEAN_STD",
144
+ "ACTION": "MEAN_STD"
145
+ },
146
+ "vision_backbone": "resnet18",
147
+ "pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
148
+ "replace_final_stride_with_dilation": false,
149
+ "pre_norm": false,
150
+ "dim_model": 512,
151
+ "n_heads": 8,
152
+ "dim_feedforward": 3200,
153
+ "feedforward_activation": "relu",
154
+ "n_encoder_layers": 4,
155
+ "n_decoder_layers": 1,
156
+ "use_vae": true,
157
+ "latent_dim": 32,
158
+ "n_vae_encoder_layers": 4,
159
+ "temporal_ensemble_coeff": null,
160
+ "dropout": 0.1,
161
+ "kl_weight": 10.0,
162
+ "optimizer_lr": 1e-05,
163
+ "optimizer_weight_decay": 0.0001,
164
+ "optimizer_lr_backbone": 1e-05
165
+ },
166
+ "reward_model": null,
167
+ "output_dir": "outputs/train/lab01_pnp_act",
168
+ "job_name": "lab01_pnp_act",
169
+ "resume": false,
170
+ "seed": 1000,
171
+ "cudnn_deterministic": false,
172
+ "num_workers": 4,
173
+ "batch_size": 128,
174
+ "prefetch_factor": 4,
175
+ "persistent_workers": true,
176
+ "steps": 50000,
177
+ "env_eval_freq": 20000,
178
+ "log_freq": 200,
179
+ "eval_steps": 0,
180
+ "max_eval_samples": 0,
181
+ "tolerance_s": 0.0001,
182
+ "save_checkpoint": true,
183
+ "save_freq": 10000,
184
+ "use_policy_training_preset": true,
185
+ "optimizer": {
186
+ "type": "adamw",
187
+ "lr": 1e-05,
188
+ "weight_decay": 0.0001,
189
+ "grad_clip_norm": 10.0,
190
+ "betas": [
191
+ 0.9,
192
+ 0.999
193
+ ],
194
+ "eps": 1e-08
195
+ },
196
+ "scheduler": null,
197
+ "eval": {
198
+ "n_episodes": 50,
199
+ "batch_size": 14,
200
+ "use_async_envs": true,
201
+ "recording": false,
202
+ "recording_repo_id": null,
203
+ "recording_private": false
204
+ },
205
+ "wandb": {
206
+ "enable": false,
207
+ "disable_artifact": false,
208
+ "project": "lerobot",
209
+ "entity": null,
210
+ "notes": null,
211
+ "run_id": null,
212
+ "mode": null,
213
+ "add_tags": true
214
+ },
215
+ "peft": null,
216
+ "job": {
217
+ "target": null,
218
+ "image": "huggingface/lerobot-gpu:latest",
219
+ "timeout": "2d",
220
+ "detach": false,
221
+ "tags": []
222
+ },
223
+ "save_checkpoint_to_hub": false,
224
+ "sample_weighting": null,
225
+ "rename_map": {},
226
+ "checkpoint_path": null
227
+ }