Hugging Face's logo

JiabinQ
/
clear_tray_3cam

Safetensors
Model card Files
xet
Community
JiabinQ commited on
Commit
538f99e
·
verified ·
1 Parent(s): a9d8488

Upload folder using huggingface_hub

Browse files
Files changed (7) hide show
  1. checkpoint-003000/config.json +91 -0
  2. checkpoint-003000/model.safetensors +3 -0
  3. checkpoint-003000/policy_postprocessor.json +32 -0
  4. checkpoint-003000/policy_postprocessor_step_0_unnormalizer_processor.safetensors +3 -0
  5. checkpoint-003000/policy_preprocessor.json +87 -0
  6. checkpoint-003000/policy_preprocessor_step_2_normalizer_processor.safetensors +3 -0
  7. checkpoint-003000/train_config.json +204 -0
checkpoint-003000/config.json ADDED
@@ -0,0 +1,91 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "type": "pi05",
3
+ "n_obs_steps": 1,
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.top": {
20
+ "type": "VISUAL",
21
+ "shape": [
22
+ 3,
23
+ 480,
24
+ 640
25
+ ]
26
+ },
27
+ "observation.images.side": {
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
+ "push_to_hub": false,
47
+ "repo_id": null,
48
+ "private": null,
49
+ "tags": null,
50
+ "license": null,
51
+ "pretrained_path": "/root/autodl-tmp/lerobot_outputs/clear_tray_3cam/checkpoints/001000/pretrained_model",
52
+ "paligemma_variant": "gemma_2b",
53
+ "action_expert_variant": "gemma_300m",
54
+ "dtype": "bfloat16",
55
+ "chunk_size": 50,
56
+ "n_action_steps": 50,
57
+ "max_state_dim": 32,
58
+ "max_action_dim": 32,
59
+ "num_inference_steps": 10,
60
+ "time_sampling_beta_alpha": 1.5,
61
+ "time_sampling_beta_beta": 1.0,
62
+ "time_sampling_scale": 0.999,
63
+ "time_sampling_offset": 0.001,
64
+ "min_period": 0.004,
65
+ "max_period": 4.0,
66
+ "image_resolution": [
67
+ 224,
68
+ 224
69
+ ],
70
+ "empty_cameras": 0,
71
+ "tokenizer_max_length": 200,
72
+ "normalization_mapping": {
73
+ "VISUAL": "IDENTITY",
74
+ "STATE": "QUANTILES",
75
+ "ACTION": "QUANTILES"
76
+ },
77
+ "gradient_checkpointing": true,
78
+ "compile_model": true,
79
+ "compile_mode": "reduce-overhead",
80
+ "optimizer_lr": 2.5e-05,
81
+ "optimizer_betas": [
82
+ 0.9,
83
+ 0.95
84
+ ],
85
+ "optimizer_eps": 1e-08,
86
+ "optimizer_weight_decay": 0.01,
87
+ "optimizer_grad_clip_norm": 1.0,
88
+ "scheduler_warmup_steps": 1000,
89
+ "scheduler_decay_steps": 30000,
90
+ "scheduler_decay_lr": 2.5e-06
91
+ }
checkpoint-003000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:948da669107866b35b33a6f9d989cb4145523b16a645a8cc6d758f9381bc3298
3
+ size 7473096344
checkpoint-003000/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": "IDENTITY",
18
+ "STATE": "QUANTILES",
19
+ "ACTION": "QUANTILES"
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
+ }
checkpoint-003000/policy_postprocessor_step_0_unnormalizer_processor.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:779484752ddc67b23b42237e4ddf4e55b92f05fb52165a1ff2efe041e899b8fd
3
+ size 8512
checkpoint-003000/policy_preprocessor.json ADDED
@@ -0,0 +1,87 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "normalizer_processor",
16
+ "config": {
17
+ "eps": 1e-08,
18
+ "features": {
19
+ "observation.state": {
20
+ "type": "STATE",
21
+ "shape": [
22
+ 6
23
+ ]
24
+ },
25
+ "observation.images.wrist": {
26
+ "type": "VISUAL",
27
+ "shape": [
28
+ 3,
29
+ 480,
30
+ 640
31
+ ]
32
+ },
33
+ "observation.images.top": {
34
+ "type": "VISUAL",
35
+ "shape": [
36
+ 3,
37
+ 480,
38
+ 640
39
+ ]
40
+ },
41
+ "observation.images.side": {
42
+ "type": "VISUAL",
43
+ "shape": [
44
+ 3,
45
+ 480,
46
+ 640
47
+ ]
48
+ },
49
+ "action": {
50
+ "type": "ACTION",
51
+ "shape": [
52
+ 6
53
+ ]
54
+ }
55
+ },
56
+ "norm_map": {
57
+ "VISUAL": "IDENTITY",
58
+ "STATE": "QUANTILES",
59
+ "ACTION": "QUANTILES"
60
+ }
61
+ },
62
+ "state_file": "policy_preprocessor_step_2_normalizer_processor.safetensors"
63
+ },
64
+ {
65
+ "registry_name": "pi05_prepare_state_tokenizer_processor_step",
66
+ "config": {}
67
+ },
68
+ {
69
+ "registry_name": "tokenizer_processor",
70
+ "config": {
71
+ "max_length": 200,
72
+ "task_key": "task",
73
+ "padding_side": "right",
74
+ "padding": "max_length",
75
+ "truncation": true,
76
+ "tokenizer_name": "google/paligemma-3b-pt-224"
77
+ }
78
+ },
79
+ {
80
+ "registry_name": "device_processor",
81
+ "config": {
82
+ "device": "cuda",
83
+ "float_dtype": null
84
+ }
85
+ }
86
+ ]
87
+ }
checkpoint-003000/policy_preprocessor_step_2_normalizer_processor.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:779484752ddc67b23b42237e4ddf4e55b92f05fb52165a1ff2efe041e899b8fd
3
+ size 8512
checkpoint-003000/train_config.json ADDED
@@ -0,0 +1,204 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset": {
3
+ "repo_id": "JiabinQ/clear_tray_3cam",
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
+ "streaming": false
67
+ },
68
+ "env": null,
69
+ "policy": {
70
+ "type": "pi05",
71
+ "n_obs_steps": 1,
72
+ "input_features": {
73
+ "observation.state": {
74
+ "type": "STATE",
75
+ "shape": [
76
+ 6
77
+ ]
78
+ },
79
+ "observation.images.wrist": {
80
+ "type": "VISUAL",
81
+ "shape": [
82
+ 3,
83
+ 480,
84
+ 640
85
+ ]
86
+ },
87
+ "observation.images.top": {
88
+ "type": "VISUAL",
89
+ "shape": [
90
+ 3,
91
+ 480,
92
+ 640
93
+ ]
94
+ },
95
+ "observation.images.side": {
96
+ "type": "VISUAL",
97
+ "shape": [
98
+ 3,
99
+ 480,
100
+ 640
101
+ ]
102
+ }
103
+ },
104
+ "output_features": {
105
+ "action": {
106
+ "type": "ACTION",
107
+ "shape": [
108
+ 6
109
+ ]
110
+ }
111
+ },
112
+ "device": "cuda",
113
+ "use_amp": false,
114
+ "push_to_hub": false,
115
+ "repo_id": null,
116
+ "private": null,
117
+ "tags": null,
118
+ "license": null,
119
+ "pretrained_path": "/root/autodl-tmp/lerobot_outputs/clear_tray_3cam/checkpoints/001000/pretrained_model",
120
+ "paligemma_variant": "gemma_2b",
121
+ "action_expert_variant": "gemma_300m",
122
+ "dtype": "bfloat16",
123
+ "chunk_size": 50,
124
+ "n_action_steps": 50,
125
+ "max_state_dim": 32,
126
+ "max_action_dim": 32,
127
+ "num_inference_steps": 10,
128
+ "time_sampling_beta_alpha": 1.5,
129
+ "time_sampling_beta_beta": 1.0,
130
+ "time_sampling_scale": 0.999,
131
+ "time_sampling_offset": 0.001,
132
+ "min_period": 0.004,
133
+ "max_period": 4.0,
134
+ "image_resolution": [
135
+ 224,
136
+ 224
137
+ ],
138
+ "empty_cameras": 0,
139
+ "tokenizer_max_length": 200,
140
+ "normalization_mapping": {
141
+ "VISUAL": "IDENTITY",
142
+ "STATE": "QUANTILES",
143
+ "ACTION": "QUANTILES"
144
+ },
145
+ "gradient_checkpointing": true,
146
+ "compile_model": true,
147
+ "compile_mode": "reduce-overhead",
148
+ "optimizer_lr": 2.5e-05,
149
+ "optimizer_betas": [
150
+ 0.9,
151
+ 0.95
152
+ ],
153
+ "optimizer_eps": 1e-08,
154
+ "optimizer_weight_decay": 0.01,
155
+ "optimizer_grad_clip_norm": 1.0,
156
+ "scheduler_warmup_steps": 1000,
157
+ "scheduler_decay_steps": 30000,
158
+ "scheduler_decay_lr": 2.5e-06
159
+ },
160
+ "output_dir": "/root/autodl-tmp/lerobot_outputs/clear_tray_3cam",
161
+ "job_name": "pi05",
162
+ "resume": true,
163
+ "seed": 1000,
164
+ "num_workers": 10,
165
+ "batch_size": 50,
166
+ "steps": 12000,
167
+ "eval_freq": 20000,
168
+ "log_freq": 100,
169
+ "save_checkpoint": true,
170
+ "save_freq": 1000,
171
+ "use_policy_training_preset": true,
172
+ "optimizer": {
173
+ "type": "adamw",
174
+ "lr": 2.5e-05,
175
+ "weight_decay": 0.01,
176
+ "grad_clip_norm": 1.0,
177
+ "betas": [
178
+ 0.9,
179
+ 0.95
180
+ ],
181
+ "eps": 1e-08
182
+ },
183
+ "scheduler": {
184
+ "type": "cosine_decay_with_warmup",
185
+ "num_warmup_steps": 1000,
186
+ "num_decay_steps": 30000,
187
+ "peak_lr": 2.5e-05,
188
+ "decay_lr": 2.5e-06
189
+ },
190
+ "eval": {
191
+ "n_episodes": 50,
192
+ "batch_size": 50,
193
+ "use_async_envs": false
194
+ },
195
+ "wandb": {
196
+ "enable": true,
197
+ "disable_artifact": true,
198
+ "project": "clear_tray_3cam",
199
+ "entity": null,
200
+ "notes": "Pi0.5 training on AutoDL clear_tray_3cam",
201
+ "run_id": "6x61dxlo",
202
+ "mode": "offline"
203
+ }
204
+ }