Hugging Face's logo

DragonHu
/
remove_block_uniform_ramdom_smolvla_base

Safetensors
Model card Files
xet
Community
DragonHu commited on
Commit
7f2d248
·
verified ·
1 Parent(s): 7abe328

dataset collected uniform random spwan block, add trained model fintuned 'lerobot/smolvla_base'

Browse files
Files changed (3) hide show
  1. config.json +88 -0
  2. model.safetensors +3 -0
  3. train_config.json +200 -0
config.json ADDED
@@ -0,0 +1,88 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "type": "smolvla",
3
+ "n_obs_steps": 1,
4
+ "normalization_mapping": {
5
+ "VISUAL": "IDENTITY",
6
+ "STATE": "MEAN_STD",
7
+ "ACTION": "MEAN_STD"
8
+ },
9
+ "input_features": {
10
+ "observation.image": {
11
+ "type": "VISUAL",
12
+ "shape": [
13
+ 3,
14
+ 256,
15
+ 256
16
+ ]
17
+ },
18
+ "observation.wrist_image": {
19
+ "type": "VISUAL",
20
+ "shape": [
21
+ 3,
22
+ 256,
23
+ 256
24
+ ]
25
+ },
26
+ "observation.state": {
27
+ "type": "STATE",
28
+ "shape": [
29
+ 6
30
+ ]
31
+ }
32
+ },
33
+ "output_features": {
34
+ "action": {
35
+ "type": "ACTION",
36
+ "shape": [
37
+ 7
38
+ ]
39
+ }
40
+ },
41
+ "device": "cuda",
42
+ "use_amp": false,
43
+ "push_to_hub": false,
44
+ "repo_id": null,
45
+ "private": null,
46
+ "tags": null,
47
+ "license": null,
48
+ "chunk_size": 5,
49
+ "n_action_steps": 5,
50
+ "max_state_dim": 32,
51
+ "max_action_dim": 32,
52
+ "resize_imgs_with_padding": [
53
+ 512,
54
+ 512
55
+ ],
56
+ "empty_cameras": 0,
57
+ "adapt_to_pi_aloha": false,
58
+ "use_delta_joint_actions_aloha": false,
59
+ "tokenizer_max_length": 48,
60
+ "num_steps": 10,
61
+ "use_cache": true,
62
+ "freeze_vision_encoder": true,
63
+ "train_expert_only": true,
64
+ "train_state_proj": true,
65
+ "optimizer_lr": 0.0001,
66
+ "optimizer_betas": [
67
+ 0.9,
68
+ 0.95
69
+ ],
70
+ "optimizer_eps": 1e-08,
71
+ "optimizer_weight_decay": 1e-10,
72
+ "optimizer_grad_clip_norm": 10,
73
+ "scheduler_warmup_steps": 1000,
74
+ "scheduler_decay_steps": 30000,
75
+ "scheduler_decay_lr": 2.5e-06,
76
+ "vlm_model_name": "HuggingFaceTB/SmolVLM2-500M-Video-Instruct",
77
+ "load_vlm_weights": false,
78
+ "add_image_special_tokens": false,
79
+ "attention_mode": "cross_attn",
80
+ "prefix_length": -1,
81
+ "pad_language_to": "longest",
82
+ "num_expert_layers": -1,
83
+ "num_vlm_layers": 16,
84
+ "self_attn_every_n_layers": 2,
85
+ "expert_width_multiplier": 0.75,
86
+ "min_period": 0.004,
87
+ "max_period": 4.0
88
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:016978679a18037585608825691ba9e5280ebc181f95c023548a3855ee6ed114
3
+ size 1197790032
train_config.json ADDED
@@ -0,0 +1,200 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset": {
3
+ "repo_id": "DragonHu/remove_red_block_from_plate_UR5_smolvla_mujoco",
4
+ "root": "./demo_data_language",
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": "smolvla",
70
+ "n_obs_steps": 1,
71
+ "normalization_mapping": {
72
+ "VISUAL": "IDENTITY",
73
+ "STATE": "MEAN_STD",
74
+ "ACTION": "MEAN_STD"
75
+ },
76
+ "input_features": {
77
+ "observation.image": {
78
+ "type": "VISUAL",
79
+ "shape": [
80
+ 3,
81
+ 256,
82
+ 256
83
+ ]
84
+ },
85
+ "observation.wrist_image": {
86
+ "type": "VISUAL",
87
+ "shape": [
88
+ 3,
89
+ 256,
90
+ 256
91
+ ]
92
+ },
93
+ "observation.state": {
94
+ "type": "STATE",
95
+ "shape": [
96
+ 6
97
+ ]
98
+ }
99
+ },
100
+ "output_features": {
101
+ "action": {
102
+ "type": "ACTION",
103
+ "shape": [
104
+ 7
105
+ ]
106
+ }
107
+ },
108
+ "device": "cuda",
109
+ "use_amp": false,
110
+ "push_to_hub": false,
111
+ "repo_id": null,
112
+ "private": null,
113
+ "tags": null,
114
+ "license": null,
115
+ "chunk_size": 5,
116
+ "n_action_steps": 5,
117
+ "max_state_dim": 32,
118
+ "max_action_dim": 32,
119
+ "resize_imgs_with_padding": [
120
+ 512,
121
+ 512
122
+ ],
123
+ "empty_cameras": 0,
124
+ "adapt_to_pi_aloha": false,
125
+ "use_delta_joint_actions_aloha": false,
126
+ "tokenizer_max_length": 48,
127
+ "num_steps": 10,
128
+ "use_cache": true,
129
+ "freeze_vision_encoder": true,
130
+ "train_expert_only": true,
131
+ "train_state_proj": true,
132
+ "optimizer_lr": 0.0001,
133
+ "optimizer_betas": [
134
+ 0.9,
135
+ 0.95
136
+ ],
137
+ "optimizer_eps": 1e-08,
138
+ "optimizer_weight_decay": 1e-10,
139
+ "optimizer_grad_clip_norm": 10,
140
+ "scheduler_warmup_steps": 1000,
141
+ "scheduler_decay_steps": 30000,
142
+ "scheduler_decay_lr": 2.5e-06,
143
+ "vlm_model_name": "HuggingFaceTB/SmolVLM2-500M-Video-Instruct",
144
+ "load_vlm_weights": false,
145
+ "add_image_special_tokens": false,
146
+ "attention_mode": "cross_attn",
147
+ "prefix_length": -1,
148
+ "pad_language_to": "longest",
149
+ "num_expert_layers": -1,
150
+ "num_vlm_layers": 16,
151
+ "self_attn_every_n_layers": 2,
152
+ "expert_width_multiplier": 0.75,
153
+ "min_period": 0.004,
154
+ "max_period": 4.0
155
+ },
156
+ "output_dir": "ckpt/smolvla_omy",
157
+ "job_name": "smolvla_remove_block",
158
+ "resume": false,
159
+ "seed": 42,
160
+ "num_workers": 8,
161
+ "batch_size": 16,
162
+ "steps": 20000,
163
+ "eval_freq": -1,
164
+ "log_freq": 50,
165
+ "save_checkpoint": true,
166
+ "save_freq": 10000,
167
+ "use_policy_training_preset": true,
168
+ "optimizer": {
169
+ "type": "adamw",
170
+ "lr": 0.0001,
171
+ "weight_decay": 1e-10,
172
+ "grad_clip_norm": 10,
173
+ "betas": [
174
+ 0.9,
175
+ 0.95
176
+ ],
177
+ "eps": 1e-08
178
+ },
179
+ "scheduler": {
180
+ "type": "cosine_decay_with_warmup",
181
+ "num_warmup_steps": 1000,
182
+ "num_decay_steps": 30000,
183
+ "peak_lr": 0.0001,
184
+ "decay_lr": 2.5e-06
185
+ },
186
+ "eval": {
187
+ "n_episodes": 50,
188
+ "batch_size": 50,
189
+ "use_async_envs": false
190
+ },
191
+ "wandb": {
192
+ "enable": true,
193
+ "disable_artifact": true,
194
+ "project": "smolvla_pnp_remove_block_random_uniform",
195
+ "entity": "wenxuan-hu97-centralesup-lec",
196
+ "notes": null,
197
+ "run_id": "iabuxg82",
198
+ "mode": null
199
+ }
200
+ }