Hugging Face's logo

nahidalam
/
lerobot_act_so100_pickplace_small_20250322_231547

Safetensors
Model card Files Community
nahidalam commited on
Commit
a0d415a
·
1 Parent(s): 24b656f

initial

Browse files
Files changed (7) hide show
  1. pretrained_model/config.json +72 -0
  2. pretrained_model/model.safetensors +3 -0
  3. pretrained_model/train_config.json +177 -0
  4. training_state/optimizer_param_groups.json +189 -0
  5. training_state/optimizer_state.safetensors +3 -0
  6. training_state/rng_state.safetensors +3 -0
  7. training_state/training_step.json +3 -0
pretrained_model/config.json ADDED
@@ -0,0 +1,72 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "type": "act",
3
+ "n_obs_steps": 1,
4
+ "normalization_mapping": {
5
+ "VISUAL": "MEAN_STD",
6
+ "STATE": "MEAN_STD",
7
+ "ACTION": "MEAN_STD"
8
+ },
9
+ "input_features": {
10
+ "observation.state": {
11
+ "type": "STATE",
12
+ "shape": [
13
+ 12
14
+ ]
15
+ },
16
+ "observation.images.main": {
17
+ "type": "VISUAL",
18
+ "shape": [
19
+ 3,
20
+ 480,
21
+ 640
22
+ ]
23
+ },
24
+ "observation.images.cv": {
25
+ "type": "VISUAL",
26
+ "shape": [
27
+ 3,
28
+ 480,
29
+ 640
30
+ ]
31
+ },
32
+ "observation.images.webcam": {
33
+ "type": "VISUAL",
34
+ "shape": [
35
+ 3,
36
+ 480,
37
+ 640
38
+ ]
39
+ }
40
+ },
41
+ "output_features": {
42
+ "action": {
43
+ "type": "ACTION",
44
+ "shape": [
45
+ 12
46
+ ]
47
+ }
48
+ },
49
+ "device": "cuda",
50
+ "use_amp": false,
51
+ "chunk_size": 100,
52
+ "n_action_steps": 100,
53
+ "vision_backbone": "resnet18",
54
+ "pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
55
+ "replace_final_stride_with_dilation": false,
56
+ "pre_norm": false,
57
+ "dim_model": 512,
58
+ "n_heads": 8,
59
+ "dim_feedforward": 3200,
60
+ "feedforward_activation": "relu",
61
+ "n_encoder_layers": 4,
62
+ "n_decoder_layers": 1,
63
+ "use_vae": true,
64
+ "latent_dim": 32,
65
+ "n_vae_encoder_layers": 4,
66
+ "temporal_ensemble_coeff": null,
67
+ "dropout": 0.1,
68
+ "kl_weight": 10.0,
69
+ "optimizer_lr": 1e-05,
70
+ "optimizer_weight_decay": 0.0001,
71
+ "optimizer_lr_backbone": 1e-05
72
+ }
pretrained_model/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4e6e26bf72a44d8f75627e47225c1ab3ce0ed016da4deffb03e65864a663ce9
3
+ size 206750664
pretrained_model/train_config.json ADDED
@@ -0,0 +1,177 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset": {
3
+ "repo_id": "jchun/so100_pickplace_small_20250322_231547",
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
+ }
62
+ },
63
+ "revision": null,
64
+ "use_imagenet_stats": true,
65
+ "video_backend": "torchcodec"
66
+ },
67
+ "env": null,
68
+ "policy": {
69
+ "type": "act",
70
+ "n_obs_steps": 1,
71
+ "normalization_mapping": {
72
+ "VISUAL": "MEAN_STD",
73
+ "STATE": "MEAN_STD",
74
+ "ACTION": "MEAN_STD"
75
+ },
76
+ "input_features": {
77
+ "observation.state": {
78
+ "type": "STATE",
79
+ "shape": [
80
+ 12
81
+ ]
82
+ },
83
+ "observation.images.main": {
84
+ "type": "VISUAL",
85
+ "shape": [
86
+ 3,
87
+ 480,
88
+ 640
89
+ ]
90
+ },
91
+ "observation.images.cv": {
92
+ "type": "VISUAL",
93
+ "shape": [
94
+ 3,
95
+ 480,
96
+ 640
97
+ ]
98
+ },
99
+ "observation.images.webcam": {
100
+ "type": "VISUAL",
101
+ "shape": [
102
+ 3,
103
+ 480,
104
+ 640
105
+ ]
106
+ }
107
+ },
108
+ "output_features": {
109
+ "action": {
110
+ "type": "ACTION",
111
+ "shape": [
112
+ 12
113
+ ]
114
+ }
115
+ },
116
+ "device": "cuda",
117
+ "use_amp": false,
118
+ "chunk_size": 100,
119
+ "n_action_steps": 100,
120
+ "vision_backbone": "resnet18",
121
+ "pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
122
+ "replace_final_stride_with_dilation": false,
123
+ "pre_norm": false,
124
+ "dim_model": 512,
125
+ "n_heads": 8,
126
+ "dim_feedforward": 3200,
127
+ "feedforward_activation": "relu",
128
+ "n_encoder_layers": 4,
129
+ "n_decoder_layers": 1,
130
+ "use_vae": true,
131
+ "latent_dim": 32,
132
+ "n_vae_encoder_layers": 4,
133
+ "temporal_ensemble_coeff": null,
134
+ "dropout": 0.1,
135
+ "kl_weight": 10.0,
136
+ "optimizer_lr": 1e-05,
137
+ "optimizer_weight_decay": 0.0001,
138
+ "optimizer_lr_backbone": 1e-05
139
+ },
140
+ "output_dir": "outputs/train/act_so100_test",
141
+ "job_name": "act_train_base",
142
+ "resume": false,
143
+ "seed": 1000,
144
+ "num_workers": 4,
145
+ "batch_size": 32,
146
+ "steps": 100000,
147
+ "eval_freq": 20000,
148
+ "log_freq": 200,
149
+ "save_checkpoint": true,
150
+ "save_freq": 20000,
151
+ "use_policy_training_preset": true,
152
+ "optimizer": {
153
+ "type": "adamw",
154
+ "lr": 1e-05,
155
+ "weight_decay": 0.0001,
156
+ "grad_clip_norm": 10.0,
157
+ "betas": [
158
+ 0.9,
159
+ 0.999
160
+ ],
161
+ "eps": 1e-08
162
+ },
163
+ "scheduler": null,
164
+ "eval": {
165
+ "n_episodes": 50,
166
+ "batch_size": 50,
167
+ "use_async_envs": false
168
+ },
169
+ "wandb": {
170
+ "enable": true,
171
+ "disable_artifact": false,
172
+ "project": "lerobot",
173
+ "entity": null,
174
+ "notes": null,
175
+ "run_id": null
176
+ }
177
+ }
training_state/optimizer_param_groups.json ADDED
@@ -0,0 +1,189 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "lr": 1e-05,
4
+ "betas": [
5
+ 0.9,
6
+ 0.999
7
+ ],
8
+ "eps": 1e-08,
9
+ "weight_decay": 0.0001,
10
+ "amsgrad": false,
11
+ "foreach": null,
12
+ "maximize": false,
13
+ "capturable": false,
14
+ "differentiable": false,
15
+ "fused": null,
16
+ "params": [
17
+ 0,
18
+ 1,
19
+ 2,
20
+ 3,
21
+ 4,
22
+ 5,
23
+ 6,
24
+ 7,
25
+ 8,
26
+ 9,
27
+ 10,
28
+ 11,
29
+ 12,
30
+ 13,
31
+ 14,
32
+ 15,
33
+ 16,
34
+ 17,
35
+ 18,
36
+ 19,
37
+ 20,
38
+ 21,
39
+ 22,
40
+ 23,
41
+ 24,
42
+ 25,
43
+ 26,
44
+ 27,
45
+ 28,
46
+ 29,
47
+ 30,
48
+ 31,
49
+ 32,
50
+ 33,
51
+ 34,
52
+ 35,
53
+ 36,
54
+ 37,
55
+ 38,
56
+ 39,
57
+ 40,
58
+ 41,
59
+ 42,
60
+ 43,
61
+ 44,
62
+ 45,
63
+ 46,
64
+ 47,
65
+ 48,
66
+ 49,
67
+ 50,
68
+ 51,
69
+ 52,
70
+ 53,
71
+ 54,
72
+ 55,
73
+ 56,
74
+ 57,
75
+ 58,
76
+ 59,
77
+ 60,
78
+ 61,
79
+ 62,
80
+ 63,
81
+ 64,
82
+ 65,
83
+ 66,
84
+ 67,
85
+ 68,
86
+ 69,
87
+ 70,
88
+ 71,
89
+ 72,
90
+ 73,
91
+ 74,
92
+ 75,
93
+ 76,
94
+ 77,
95
+ 78,
96
+ 79,
97
+ 80,
98
+ 81,
99
+ 82,
100
+ 83,
101
+ 84,
102
+ 85,
103
+ 86,
104
+ 87,
105
+ 88,
106
+ 89,
107
+ 90,
108
+ 91,
109
+ 92,
110
+ 93,
111
+ 94,
112
+ 95,
113
+ 96,
114
+ 97,
115
+ 98,
116
+ 99,
117
+ 100,
118
+ 101,
119
+ 102,
120
+ 103,
121
+ 104,
122
+ 105,
123
+ 106,
124
+ 107,
125
+ 108,
126
+ 109,
127
+ 110,
128
+ 111,
129
+ 112,
130
+ 113,
131
+ 114,
132
+ 115,
133
+ 116,
134
+ 117,
135
+ 118,
136
+ 119,
137
+ 120,
138
+ 121,
139
+ 122,
140
+ 123,
141
+ 124,
142
+ 125,
143
+ 126,
144
+ 127,
145
+ 128,
146
+ 129,
147
+ 130,
148
+ 131,
149
+ 132
150
+ ]
151
+ },
152
+ {
153
+ "lr": 1e-05,
154
+ "betas": [
155
+ 0.9,
156
+ 0.999
157
+ ],
158
+ "eps": 1e-08,
159
+ "weight_decay": 0.0001,
160
+ "amsgrad": false,
161
+ "foreach": null,
162
+ "maximize": false,
163
+ "capturable": false,
164
+ "differentiable": false,
165
+ "fused": null,
166
+ "params": [
167
+ 133,
168
+ 134,
169
+ 135,
170
+ 136,
171
+ 137,
172
+ 138,
173
+ 139,
174
+ 140,
175
+ 141,
176
+ 142,
177
+ 143,
178
+ 144,
179
+ 145,
180
+ 146,
181
+ 147,
182
+ 148,
183
+ 149,
184
+ 150,
185
+ 151,
186
+ 152
187
+ ]
188
+ }
189
+ ]
training_state/optimizer_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2b348ff31ab59748a469ae43c8be1eb94fd3bb6c7cf9991bb5922764b99e7e2
3
+ size 412916012
training_state/rng_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9607d17ed3d14904bf9633b5983faf980893c130a656481418ba2e4821fa4c37
3
+ size 15708
training_state/training_step.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "step": 20000
3
+ }