Hugging Face's logo

ahmetkca
/
smolvla_pnp_15k_steps_checkpoint

Safetensors
Model card Files Community
1
ahmetkca commited on
Commit
a1c9b02
·
verified ·
1 Parent(s): c8d0907

Upload folder using huggingface_hub

Browse files
Files changed (3) hide show
  1. config.json +83 -0
  2. model.safetensors +3 -0
  3. train_config.json +195 -0
config.json ADDED
@@ -0,0 +1,83 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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.state": {
11
+ "type": "STATE",
12
+ "shape": [
13
+ 6
14
+ ]
15
+ },
16
+ "observation.images.front": {
17
+ "type": "VISUAL",
18
+ "shape": [
19
+ 3,
20
+ 360,
21
+ 640
22
+ ]
23
+ },
24
+ "observation.images.top": {
25
+ "type": "VISUAL",
26
+ "shape": [
27
+ 3,
28
+ 480,
29
+ 640
30
+ ]
31
+ }
32
+ },
33
+ "output_features": {
34
+ "action": {
35
+ "type": "ACTION",
36
+ "shape": [
37
+ 6
38
+ ]
39
+ }
40
+ },
41
+ "device": "cuda",
42
+ "use_amp": false,
43
+ "chunk_size": 50,
44
+ "n_action_steps": 50,
45
+ "max_state_dim": 32,
46
+ "max_action_dim": 32,
47
+ "resize_imgs_with_padding": [
48
+ 512,
49
+ 512
50
+ ],
51
+ "empty_cameras": 0,
52
+ "adapt_to_pi_aloha": false,
53
+ "use_delta_joint_actions_aloha": false,
54
+ "tokenizer_max_length": 48,
55
+ "num_steps": 10,
56
+ "use_cache": true,
57
+ "freeze_vision_encoder": true,
58
+ "train_expert_only": true,
59
+ "train_state_proj": true,
60
+ "optimizer_lr": 0.0001,
61
+ "optimizer_betas": [
62
+ 0.9,
63
+ 0.95
64
+ ],
65
+ "optimizer_eps": 1e-08,
66
+ "optimizer_weight_decay": 1e-10,
67
+ "optimizer_grad_clip_norm": 10.0,
68
+ "scheduler_warmup_steps": 1000,
69
+ "scheduler_decay_steps": 30000,
70
+ "scheduler_decay_lr": 2.5e-06,
71
+ "vlm_model_name": "HuggingFaceTB/SmolVLM2-500M-Video-Instruct",
72
+ "load_vlm_weights": true,
73
+ "add_image_special_tokens": false,
74
+ "attention_mode": "cross_attn",
75
+ "prefix_length": 0,
76
+ "pad_language_to": "max_length",
77
+ "num_expert_layers": 0,
78
+ "num_vlm_layers": 16,
79
+ "self_attn_every_n_layers": 2,
80
+ "expert_width_multiplier": 0.75,
81
+ "min_period": 0.004,
82
+ "max_period": 4.0
83
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87e76304bae9f41102212ecf8f692a833377945d6fd56865e86addaf72eaf9dd
3
+ size 906713296
train_config.json ADDED
@@ -0,0 +1,195 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset": {
3
+ "repo_id": "sam-qc/pnp-lego",
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": "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.state": {
78
+ "type": "STATE",
79
+ "shape": [
80
+ 6
81
+ ]
82
+ },
83
+ "observation.images.front": {
84
+ "type": "VISUAL",
85
+ "shape": [
86
+ 3,
87
+ 360,
88
+ 640
89
+ ]
90
+ },
91
+ "observation.images.top": {
92
+ "type": "VISUAL",
93
+ "shape": [
94
+ 3,
95
+ 480,
96
+ 640
97
+ ]
98
+ }
99
+ },
100
+ "output_features": {
101
+ "action": {
102
+ "type": "ACTION",
103
+ "shape": [
104
+ 6
105
+ ]
106
+ }
107
+ },
108
+ "device": "cuda",
109
+ "use_amp": false,
110
+ "chunk_size": 50,
111
+ "n_action_steps": 50,
112
+ "max_state_dim": 32,
113
+ "max_action_dim": 32,
114
+ "resize_imgs_with_padding": [
115
+ 512,
116
+ 512
117
+ ],
118
+ "empty_cameras": 0,
119
+ "adapt_to_pi_aloha": false,
120
+ "use_delta_joint_actions_aloha": false,
121
+ "tokenizer_max_length": 48,
122
+ "num_steps": 10,
123
+ "use_cache": true,
124
+ "freeze_vision_encoder": true,
125
+ "train_expert_only": true,
126
+ "train_state_proj": true,
127
+ "optimizer_lr": 0.0001,
128
+ "optimizer_betas": [
129
+ 0.9,
130
+ 0.95
131
+ ],
132
+ "optimizer_eps": 1e-08,
133
+ "optimizer_weight_decay": 1e-10,
134
+ "optimizer_grad_clip_norm": 10.0,
135
+ "scheduler_warmup_steps": 1000,
136
+ "scheduler_decay_steps": 30000,
137
+ "scheduler_decay_lr": 2.5e-06,
138
+ "vlm_model_name": "HuggingFaceTB/SmolVLM2-500M-Video-Instruct",
139
+ "load_vlm_weights": true,
140
+ "add_image_special_tokens": false,
141
+ "attention_mode": "cross_attn",
142
+ "prefix_length": 0,
143
+ "pad_language_to": "max_length",
144
+ "num_expert_layers": 0,
145
+ "num_vlm_layers": 16,
146
+ "self_attn_every_n_layers": 2,
147
+ "expert_width_multiplier": 0.75,
148
+ "min_period": 0.004,
149
+ "max_period": 4.0
150
+ },
151
+ "output_dir": "outputs/train/my_smolvla_test102",
152
+ "job_name": "my_smolvla_test102",
153
+ "resume": false,
154
+ "seed": 1000,
155
+ "num_workers": 4,
156
+ "batch_size": 64,
157
+ "steps": 30000,
158
+ "eval_freq": 20000,
159
+ "log_freq": 200,
160
+ "save_checkpoint": true,
161
+ "save_freq": 5000,
162
+ "use_policy_training_preset": true,
163
+ "optimizer": {
164
+ "type": "adamw",
165
+ "lr": 0.0001,
166
+ "weight_decay": 1e-10,
167
+ "grad_clip_norm": 10.0,
168
+ "betas": [
169
+ 0.9,
170
+ 0.95
171
+ ],
172
+ "eps": 1e-08
173
+ },
174
+ "scheduler": {
175
+ "type": "cosine_decay_with_warmup",
176
+ "num_warmup_steps": 1000,
177
+ "num_decay_steps": 30000,
178
+ "peak_lr": 0.0001,
179
+ "decay_lr": 2.5e-06
180
+ },
181
+ "eval": {
182
+ "n_episodes": 50,
183
+ "batch_size": 50,
184
+ "use_async_envs": false
185
+ },
186
+ "wandb": {
187
+ "enable": true,
188
+ "disable_artifact": false,
189
+ "project": "my_smolvla_test102",
190
+ "entity": null,
191
+ "notes": null,
192
+ "run_id": "s10b8uzw",
193
+ "mode": null
194
+ }
195
+ }