Hugging Face's logo

felsager
/
smolvla_base_ee_rel

Robotics
LeRobot
Safetensors
smolvla
Model card Files
xet
 Community
felsager commited on
Commit
dd3a2f8
·
verified ·
1 Parent(s): c2fecb2

checkpoint 320000

Browse files
Files changed (15) hide show
  1. checkpoints/320000/pretrained_model/config.json +123 -0
  2. checkpoints/320000/pretrained_model/model.safetensors +3 -0
  3. checkpoints/320000/pretrained_model/policy_postprocessor.json +38 -0
  4. checkpoints/320000/pretrained_model/policy_postprocessor_step_0_unnormalizer_processor.safetensors +3 -0
  5. checkpoints/320000/pretrained_model/policy_preprocessor.json +123 -0
  6. checkpoints/320000/pretrained_model/policy_preprocessor_step_7_normalizer_processor.safetensors +3 -0
  7. checkpoints/320000/pretrained_model/tokenizer/chat_template.jinja +2 -0
  8. checkpoints/320000/pretrained_model/tokenizer/tokenizer.json +0 -0
  9. checkpoints/320000/pretrained_model/tokenizer/tokenizer_config.json +33 -0
  10. checkpoints/320000/pretrained_model/train_config.json +336 -0
  11. checkpoints/320000/training_state/optimizer_param_groups.json +521 -0
  12. checkpoints/320000/training_state/optimizer_state.safetensors +3 -0
  13. checkpoints/320000/training_state/rng_state.safetensors +3 -0
  14. checkpoints/320000/training_state/scheduler_state.json +15 -0
  15. checkpoints/320000/training_state/training_step.json +13 -0
checkpoints/320000/pretrained_model/config.json ADDED
@@ -0,0 +1,123 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "type": "smolvla",
3
+ "n_obs_steps": 1,
4
+ "input_features": {
5
+ "observation.images.top": {
6
+ "type": "VISUAL",
7
+ "shape": [
8
+ 3,
9
+ 480,
10
+ 640
11
+ ]
12
+ },
13
+ "observation.images.wrist": {
14
+ "type": "VISUAL",
15
+ "shape": [
16
+ 3,
17
+ 480,
18
+ 640
19
+ ]
20
+ },
21
+ "observation.images.side": {
22
+ "type": "VISUAL",
23
+ "shape": [
24
+ 3,
25
+ 480,
26
+ 640
27
+ ]
28
+ },
29
+ "observation.state": {
30
+ "type": "STATE",
31
+ "shape": [
32
+ 10
33
+ ]
34
+ },
35
+ "observation.images.top_padding_mask": {
36
+ "type": "STATE",
37
+ "shape": [
38
+ 1
39
+ ]
40
+ },
41
+ "observation.images.wrist_padding_mask": {
42
+ "type": "STATE",
43
+ "shape": [
44
+ 1
45
+ ]
46
+ },
47
+ "observation.images.side_padding_mask": {
48
+ "type": "STATE",
49
+ "shape": [
50
+ 1
51
+ ]
52
+ }
53
+ },
54
+ "output_features": {
55
+ "action": {
56
+ "type": "ACTION",
57
+ "shape": [
58
+ 10
59
+ ]
60
+ }
61
+ },
62
+ "device": "cuda",
63
+ "use_amp": false,
64
+ "use_peft": false,
65
+ "push_to_hub": true,
66
+ "repo_id": "felsager/smolvla_base_ee_rel",
67
+ "private": null,
68
+ "tags": null,
69
+ "license": null,
70
+ "pretrained_path": "outputs/train/smolvla_ee_rel_fresh_vlm/checkpoints/last/pretrained_model",
71
+ "pretrained_revision": null,
72
+ "chunk_size": 50,
73
+ "n_action_steps": 50,
74
+ "use_relative_ee": true,
75
+ "rotation_representation": "rot6d",
76
+ "rot6d_identity_norm": true,
77
+ "normalization_mapping": {
78
+ "VISUAL": "IDENTITY",
79
+ "STATE": "MEAN_STD",
80
+ "ACTION": "MEAN_STD"
81
+ },
82
+ "max_state_dim": 32,
83
+ "max_action_dim": 32,
84
+ "resize_imgs_with_padding": [
85
+ 512,
86
+ 512
87
+ ],
88
+ "empty_cameras": 0,
89
+ "adapt_to_pi_aloha": false,
90
+ "use_delta_joint_actions_aloha": false,
91
+ "tokenizer_max_length": 48,
92
+ "num_steps": 10,
93
+ "use_cache": true,
94
+ "freeze_vision_encoder": true,
95
+ "train_expert_only": true,
96
+ "train_state_proj": true,
97
+ "optimizer_lr": 0.0005,
98
+ "optimizer_betas": [
99
+ 0.9,
100
+ 0.95
101
+ ],
102
+ "optimizer_eps": 1e-08,
103
+ "optimizer_weight_decay": 1e-10,
104
+ "optimizer_grad_clip_norm": 10.0,
105
+ "scheduler_warmup_steps": 1000,
106
+ "scheduler_decay_steps": 300000,
107
+ "scheduler_decay_lr": 2.5e-06,
108
+ "vlm_model_name": "HuggingFaceTB/SmolVLM2-500M-Video-Instruct",
109
+ "load_vlm_weights": true,
110
+ "add_image_special_tokens": false,
111
+ "attention_mode": "cross_attn",
112
+ "prefix_length": 0,
113
+ "pad_language_to": "max_length",
114
+ "num_expert_layers": 0,
115
+ "num_vlm_layers": 16,
116
+ "self_attn_every_n_layers": 2,
117
+ "expert_width_multiplier": 0.75,
118
+ "min_period": 0.004,
119
+ "max_period": 4.0,
120
+ "rtc_config": null,
121
+ "compile_model": true,
122
+ "compile_mode": "default"
123
+ }
checkpoints/320000/pretrained_model/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:076bfc94b866522ab3381a2d42f8f57b2ae8206da0ed8c22341f0633fe4e2506
3
+ size 906712552
checkpoints/320000/pretrained_model/policy_postprocessor.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ 10
13
+ ]
14
+ }
15
+ },
16
+ "norm_map": {
17
+ "VISUAL": "IDENTITY",
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": "absolute_ee_actions",
26
+ "config": {
27
+ "enabled": true
28
+ }
29
+ },
30
+ {
31
+ "registry_name": "device_processor",
32
+ "config": {
33
+ "device": "cpu",
34
+ "float_dtype": null
35
+ }
36
+ }
37
+ ]
38
+ }
checkpoints/320000/pretrained_model/policy_postprocessor_step_0_unnormalizer_processor.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12cd2f222fa8ada0ca7e8f0149c55e7532516cb63930c3d6f737c848c9c1d524
3
+ size 2784
checkpoints/320000/pretrained_model/policy_preprocessor.json ADDED
@@ -0,0 +1,123 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "smolvla_new_line_processor",
16
+ "config": {}
17
+ },
18
+ {
19
+ "registry_name": "tokenizer_processor",
20
+ "config": {
21
+ "max_length": 48,
22
+ "task_key": "task",
23
+ "padding_side": "right",
24
+ "padding": "max_length",
25
+ "truncation": true,
26
+ "tokenizer_name": "tokenizer"
27
+ },
28
+ "artifacts": {
29
+ "tokenizer_name": "tokenizer"
30
+ }
31
+ },
32
+ {
33
+ "registry_name": "device_processor",
34
+ "config": {
35
+ "device": "cuda",
36
+ "float_dtype": null
37
+ }
38
+ },
39
+ {
40
+ "registry_name": "relative_ee_actions",
41
+ "config": {
42
+ "enabled": true,
43
+ "state_frame": 0,
44
+ "rot_repr": "rot6d"
45
+ }
46
+ },
47
+ {
48
+ "registry_name": "ee_state",
49
+ "config": {
50
+ "enabled": true,
51
+ "rot_repr": "rot6d"
52
+ }
53
+ },
54
+ {
55
+ "registry_name": "normalizer_processor",
56
+ "config": {
57
+ "eps": 1e-08,
58
+ "features": {
59
+ "observation.images.top": {
60
+ "type": "VISUAL",
61
+ "shape": [
62
+ 3,
63
+ 480,
64
+ 640
65
+ ]
66
+ },
67
+ "observation.images.wrist": {
68
+ "type": "VISUAL",
69
+ "shape": [
70
+ 3,
71
+ 480,
72
+ 640
73
+ ]
74
+ },
75
+ "observation.images.side": {
76
+ "type": "VISUAL",
77
+ "shape": [
78
+ 3,
79
+ 480,
80
+ 640
81
+ ]
82
+ },
83
+ "observation.state": {
84
+ "type": "STATE",
85
+ "shape": [
86
+ 10
87
+ ]
88
+ },
89
+ "observation.images.top_padding_mask": {
90
+ "type": "STATE",
91
+ "shape": [
92
+ 1
93
+ ]
94
+ },
95
+ "observation.images.wrist_padding_mask": {
96
+ "type": "STATE",
97
+ "shape": [
98
+ 1
99
+ ]
100
+ },
101
+ "observation.images.side_padding_mask": {
102
+ "type": "STATE",
103
+ "shape": [
104
+ 1
105
+ ]
106
+ },
107
+ "action": {
108
+ "type": "ACTION",
109
+ "shape": [
110
+ 10
111
+ ]
112
+ }
113
+ },
114
+ "norm_map": {
115
+ "VISUAL": "IDENTITY",
116
+ "STATE": "MEAN_STD",
117
+ "ACTION": "MEAN_STD"
118
+ }
119
+ },
120
+ "state_file": "policy_preprocessor_step_7_normalizer_processor.safetensors"
121
+ }
122
+ ]
123
+ }
checkpoints/320000/pretrained_model/policy_preprocessor_step_7_normalizer_processor.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56e0a9ba17ae5c2c68f38b1da7d99d78b7519b5509dbb217b5addbb906a9f32d
3
+ size 2776
checkpoints/320000/pretrained_model/tokenizer/chat_template.jinja ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ <|im_start|>{% for message in messages %}{{message['role'] | capitalize}}{% if message['content'][0]['type'] == 'image' %}{{':'}}{% else %}{{': '}}{% endif %}{% for line in message['content'] %}{% if line['type'] == 'text' %}{{line['text']}}{% elif line['type'] == 'image' %}{{ '<image>' }}{% endif %}{% endfor %}<end_of_utterance>
2
+ {% endfor %}{% if add_generation_prompt %}{{ 'Assistant:' }}{% endif %}
checkpoints/320000/pretrained_model/tokenizer/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoints/320000/pretrained_model/tokenizer/tokenizer_config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "backend": "tokenizers",
4
+ "bos_token": "<|im_start|>",
5
+ "clean_up_tokenization_spaces": false,
6
+ "end_of_utterance_token": "<end_of_utterance>",
7
+ "eos_token": "<end_of_utterance>",
8
+ "errors": "replace",
9
+ "fake_image_token": "<fake_token_around_image>",
10
+ "global_image_token": "<global-img>",
11
+ "image_token": "<image>",
12
+ "is_local": true,
13
+ "legacy": false,
14
+ "max_length": 48,
15
+ "model_max_length": 8192,
16
+ "model_specific_special_tokens": {
17
+ "end_of_utterance_token": "<end_of_utterance>",
18
+ "fake_image_token": "<fake_token_around_image>",
19
+ "global_image_token": "<global-img>",
20
+ "image_token": "<image>"
21
+ },
22
+ "pad_to_multiple_of": null,
23
+ "pad_token": "<|im_end|>",
24
+ "pad_token_type_id": 0,
25
+ "padding_side": "right",
26
+ "processor_class": "SmolVLMProcessor",
27
+ "stride": 0,
28
+ "tokenizer_class": "GPT2Tokenizer",
29
+ "truncation_side": "left",
30
+ "truncation_strategy": "longest_first",
31
+ "unk_token": "<|endoftext|>",
32
+ "vocab_size": 49152
33
+ }
checkpoints/320000/pretrained_model/train_config.json ADDED
@@ -0,0 +1,336 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset": {
3
+ "repo_id": "felsager/community_dataset_v3_ee_smolvla",
4
+ "repo_type": "dataset",
5
+ "root": null,
6
+ "episodes": null,
7
+ "exclude_episodes": null,
8
+ "image_transforms": {
9
+ "enable": false,
10
+ "max_num_transforms": 3,
11
+ "random_order": false,
12
+ "tfs": {
13
+ "brightness": {
14
+ "weight": 1.0,
15
+ "type": "ColorJitter",
16
+ "kwargs": {
17
+ "brightness": [
18
+ 0.8,
19
+ 1.2
20
+ ]
21
+ }
22
+ },
23
+ "contrast": {
24
+ "weight": 1.0,
25
+ "type": "ColorJitter",
26
+ "kwargs": {
27
+ "contrast": [
28
+ 0.8,
29
+ 1.2
30
+ ]
31
+ }
32
+ },
33
+ "saturation": {
34
+ "weight": 1.0,
35
+ "type": "ColorJitter",
36
+ "kwargs": {
37
+ "saturation": [
38
+ 0.5,
39
+ 1.5
40
+ ]
41
+ }
42
+ },
43
+ "hue": {
44
+ "weight": 1.0,
45
+ "type": "ColorJitter",
46
+ "kwargs": {
47
+ "hue": [
48
+ -0.05,
49
+ 0.05
50
+ ]
51
+ }
52
+ },
53
+ "sharpness": {
54
+ "weight": 1.0,
55
+ "type": "SharpnessJitter",
56
+ "kwargs": {
57
+ "sharpness": [
58
+ 0.5,
59
+ 1.5
60
+ ]
61
+ }
62
+ },
63
+ "affine": {
64
+ "weight": 1.0,
65
+ "type": "RandomAffine",
66
+ "kwargs": {
67
+ "degrees": [
68
+ -5.0,
69
+ 5.0
70
+ ],
71
+ "translate": [
72
+ 0.05,
73
+ 0.05
74
+ ]
75
+ }
76
+ }
77
+ }
78
+ },
79
+ "revision": null,
80
+ "use_imagenet_stats": true,
81
+ "video_backend": "torchcodec",
82
+ "return_uint8": false,
83
+ "depth_output_unit": "mm",
84
+ "streaming": false,
85
+ "eval_split": 0.01
86
+ },
87
+ "env": null,
88
+ "policy": {
89
+ "type": "smolvla",
90
+ "n_obs_steps": 1,
91
+ "input_features": {
92
+ "observation.images.top": {
93
+ "type": "VISUAL",
94
+ "shape": [
95
+ 3,
96
+ 480,
97
+ 640
98
+ ]
99
+ },
100
+ "observation.images.wrist": {
101
+ "type": "VISUAL",
102
+ "shape": [
103
+ 3,
104
+ 480,
105
+ 640
106
+ ]
107
+ },
108
+ "observation.images.side": {
109
+ "type": "VISUAL",
110
+ "shape": [
111
+ 3,
112
+ 480,
113
+ 640
114
+ ]
115
+ },
116
+ "observation.state": {
117
+ "type": "STATE",
118
+ "shape": [
119
+ 10
120
+ ]
121
+ },
122
+ "observation.images.top_padding_mask": {
123
+ "type": "STATE",
124
+ "shape": [
125
+ 1
126
+ ]
127
+ },
128
+ "observation.images.wrist_padding_mask": {
129
+ "type": "STATE",
130
+ "shape": [
131
+ 1
132
+ ]
133
+ },
134
+ "observation.images.side_padding_mask": {
135
+ "type": "STATE",
136
+ "shape": [
137
+ 1
138
+ ]
139
+ }
140
+ },
141
+ "output_features": {
142
+ "action": {
143
+ "type": "ACTION",
144
+ "shape": [
145
+ 10
146
+ ]
147
+ }
148
+ },
149
+ "device": "cuda",
150
+ "use_amp": false,
151
+ "use_peft": false,
152
+ "push_to_hub": true,
153
+ "repo_id": "felsager/smolvla_base_ee_rel",
154
+ "private": null,
155
+ "tags": null,
156
+ "license": null,
157
+ "pretrained_path": "outputs/train/smolvla_ee_rel_fresh_vlm/checkpoints/last/pretrained_model",
158
+ "pretrained_revision": null,
159
+ "chunk_size": 50,
160
+ "n_action_steps": 50,
161
+ "use_relative_ee": true,
162
+ "rotation_representation": "rot6d",
163
+ "rot6d_identity_norm": true,
164
+ "normalization_mapping": {
165
+ "VISUAL": "IDENTITY",
166
+ "STATE": "MEAN_STD",
167
+ "ACTION": "MEAN_STD"
168
+ },
169
+ "max_state_dim": 32,
170
+ "max_action_dim": 32,
171
+ "resize_imgs_with_padding": [
172
+ 512,
173
+ 512
174
+ ],
175
+ "empty_cameras": 0,
176
+ "adapt_to_pi_aloha": false,
177
+ "use_delta_joint_actions_aloha": false,
178
+ "tokenizer_max_length": 48,
179
+ "num_steps": 10,
180
+ "use_cache": true,
181
+ "freeze_vision_encoder": true,
182
+ "train_expert_only": true,
183
+ "train_state_proj": true,
184
+ "optimizer_lr": 0.0005,
185
+ "optimizer_betas": [
186
+ 0.9,
187
+ 0.95
188
+ ],
189
+ "optimizer_eps": 1e-08,
190
+ "optimizer_weight_decay": 1e-10,
191
+ "optimizer_grad_clip_norm": 10.0,
192
+ "scheduler_warmup_steps": 1000,
193
+ "scheduler_decay_steps": 300000,
194
+ "scheduler_decay_lr": 2.5e-06,
195
+ "vlm_model_name": "HuggingFaceTB/SmolVLM2-500M-Video-Instruct",
196
+ "load_vlm_weights": true,
197
+ "add_image_special_tokens": false,
198
+ "attention_mode": "cross_attn",
199
+ "prefix_length": 0,
200
+ "pad_language_to": "max_length",
201
+ "num_expert_layers": 0,
202
+ "num_vlm_layers": 16,
203
+ "self_attn_every_n_layers": 2,
204
+ "expert_width_multiplier": 0.75,
205
+ "min_period": 0.004,
206
+ "max_period": 4.0,
207
+ "rtc_config": null,
208
+ "compile_model": true,
209
+ "compile_mode": "default"
210
+ },
211
+ "reward_model": null,
212
+ "output_dir": "outputs/train/smolvla_ee_rel_resume_350k",
213
+ "job_name": "smolvla_pretrain_repro_resume_350k",
214
+ "resume": true,
215
+ "seed": 0,
216
+ "cudnn_deterministic": false,
217
+ "num_workers": 12,
218
+ "batch_size": 64,
219
+ "prefetch_factor": 1,
220
+ "persistent_workers": false,
221
+ "dataloader_multiprocessing_context": "spawn",
222
+ "steps": 350000,
223
+ "env_eval_freq": 20000,
224
+ "log_freq": 200,
225
+ "eval_steps": 5000,
226
+ "max_eval_samples": 20000,
227
+ "tolerance_s": 0.0001,
228
+ "save_checkpoint": true,
229
+ "save_freq": 20000,
230
+ "checkpoint_format": "safetensors",
231
+ "use_policy_training_preset": true,
232
+ "optimizer": {
233
+ "type": "adamw",
234
+ "lr": 0.0005,
235
+ "weight_decay": 1e-10,
236
+ "grad_clip_norm": 10.0,
237
+ "betas": [
238
+ 0.9,
239
+ 0.95
240
+ ],
241
+ "eps": 1e-08
242
+ },
243
+ "scheduler": {
244
+ "type": "cosine_decay_with_warmup",
245
+ "num_warmup_steps": 1000,
246
+ "num_decay_steps": 300000,
247
+ "peak_lr": 0.0005,
248
+ "decay_lr": 2.5e-06
249
+ },
250
+ "parallelism": {
251
+ "dp_replicate": 4,
252
+ "dp_shard": 1,
253
+ "context_parallel": {
254
+ "ring_degree": 1,
255
+ "ulysses_degree": 1
256
+ },
257
+ "cfg_parallel": 1
258
+ },
259
+ "accelerator": {
260
+ "mixed_precision": "bf16",
261
+ "gradient_accumulation": {
262
+ "steps": 1
263
+ },
264
+ "grad_scaler": {
265
+ "init_scale": 65536.0,
266
+ "growth_factor": 2.0,
267
+ "backoff_factor": 0.5,
268
+ "growth_interval": 2000
269
+ },
270
+ "fsdp": {
271
+ "reshard_after_forward": true,
272
+ "wrap_modules": null,
273
+ "min_num_params": null,
274
+ "cpu_offload": false,
275
+ "ignored_modules": null
276
+ },
277
+ "ddp": {
278
+ "find_unused_parameters": true,
279
+ "gradient_as_bucket_view": false,
280
+ "static_graph": false
281
+ },
282
+ "compile": {
283
+ "enabled": false,
284
+ "backend": "inductor",
285
+ "mode": null,
286
+ "regional": true
287
+ },
288
+ "activation_checkpointing": {
289
+ "mode": "none"
290
+ }
291
+ },
292
+ "eval": {
293
+ "n_episodes": 50,
294
+ "batch_size": 50,
295
+ "use_async_envs": true,
296
+ "recording": false,
297
+ "recording_repo_id": null,
298
+ "recording_private": false
299
+ },
300
+ "ema": {
301
+ "enable": false,
302
+ "decay": null,
303
+ "update_after_step": 0,
304
+ "inv_gamma": 1.0,
305
+ "power": 0.75,
306
+ "min_decay": 0.0,
307
+ "max_decay": 0.9999,
308
+ "use_for_eval": true
309
+ },
310
+ "wandb": {
311
+ "enable": true,
312
+ "disable_artifact": true,
313
+ "project": "lerobot",
314
+ "entity": "felsager-personal",
315
+ "notes": "Resumed from W&B run cfeeggx2; target 350000 total steps.",
316
+ "run_id": "tr2euj5g",
317
+ "resume": "must",
318
+ "mode": null,
319
+ "console": "wrap",
320
+ "console_multipart": false,
321
+ "console_chunk_max_seconds": 0,
322
+ "add_tags": true
323
+ },
324
+ "peft": null,
325
+ "job": {
326
+ "target": null,
327
+ "image": "huggingface/lerobot-gpu:latest",
328
+ "timeout": "2d",
329
+ "detach": false,
330
+ "tags": []
331
+ },
332
+ "save_checkpoint_to_hub": true,
333
+ "sample_weighting": null,
334
+ "rename_map": {},
335
+ "checkpoint_path": "outputs/train/smolvla_ee_rel_fresh_vlm/checkpoints/last"
336
+ }
checkpoints/320000/training_state/optimizer_param_groups.json ADDED
@@ -0,0 +1,521 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "lr": 2.5e-06,
4
+ "betas": [
5
+ 0.9,
6
+ 0.95
7
+ ],
8
+ "eps": 1e-08,
9
+ "weight_decay": 1e-10,
10
+ "amsgrad": false,
11
+ "maximize": false,
12
+ "foreach": null,
13
+ "capturable": false,
14
+ "differentiable": false,
15
+ "fused": null,
16
+ "decoupled_weight_decay": true,
17
+ "initial_lr": 0.0005,
18
+ "params": [
19
+ 0,
20
+ 1,
21
+ 2,
22
+ 3,
23
+ 4,
24
+ 5,
25
+ 6,
26
+ 7,
27
+ 8,
28
+ 9,
29
+ 10,
30
+ 11,
31
+ 12,
32
+ 13,
33
+ 14,
34
+ 15,
35
+ 16,
36
+ 17,
37
+ 18,
38
+ 19,
39
+ 20,
40
+ 21,
41
+ 22,
42
+ 23,
43
+ 24,
44
+ 25,
45
+ 26,
46
+ 27,
47
+ 28,
48
+ 29,
49
+ 30,
50
+ 31,
51
+ 32,
52
+ 33,
53
+ 34,
54
+ 35,
55
+ 36,
56
+ 37,
57
+ 38,
58
+ 39,
59
+ 40,
60
+ 41,
61
+ 42,
62
+ 43,
63
+ 44,
64
+ 45,
65
+ 46,
66
+ 47,
67
+ 48,
68
+ 49,
69
+ 50,
70
+ 51,
71
+ 52,
72
+ 53,
73
+ 54,
74
+ 55,
75
+ 56,
76
+ 57,
77
+ 58,
78
+ 59,
79
+ 60,
80
+ 61,
81
+ 62,
82
+ 63,
83
+ 64,
84
+ 65,
85
+ 66,
86
+ 67,
87
+ 68,
88
+ 69,
89
+ 70,
90
+ 71,
91
+ 72,
92
+ 73,
93
+ 74,
94
+ 75,
95
+ 76,
96
+ 77,
97
+ 78,
98
+ 79,
99
+ 80,
100
+ 81,
101
+ 82,
102
+ 83,
103
+ 84,
104
+ 85,
105
+ 86,
106
+ 87,
107
+ 88,
108
+ 89,
109
+ 90,
110
+ 91,
111
+ 92,
112
+ 93,
113
+ 94,
114
+ 95,
115
+ 96,
116
+ 97,
117
+ 98,
118
+ 99,
119
+ 100,
120
+ 101,
121
+ 102,
122
+ 103,
123
+ 104,
124
+ 105,
125
+ 106,
126
+ 107,
127
+ 108,
128
+ 109,
129
+ 110,
130
+ 111,
131
+ 112,
132
+ 113,
133
+ 114,
134
+ 115,
135
+ 116,
136
+ 117,
137
+ 118,
138
+ 119,
139
+ 120,
140
+ 121,
141
+ 122,
142
+ 123,
143
+ 124,
144
+ 125,
145
+ 126,
146
+ 127,
147
+ 128,
148
+ 129,
149
+ 130,
150
+ 131,
151
+ 132,
152
+ 133,
153
+ 134,
154
+ 135,
155
+ 136,
156
+ 137,
157
+ 138,
158
+ 139,
159
+ 140,
160
+ 141,
161
+ 142,
162
+ 143,
163
+ 144,
164
+ 145,
165
+ 146,
166
+ 147,
167
+ 148,
168
+ 149,
169
+ 150,
170
+ 151,
171
+ 152,
172
+ 153,
173
+ 154,
174
+ 155,
175
+ 156,
176
+ 157,
177
+ 158,
178
+ 159,
179
+ 160,
180
+ 161,
181
+ 162,
182
+ 163,
183
+ 164,
184
+ 165,
185
+ 166,
186
+ 167,
187
+ 168,
188
+ 169,
189
+ 170,
190
+ 171,
191
+ 172,
192
+ 173,
193
+ 174,
194
+ 175,
195
+ 176,
196
+ 177,
197
+ 178,
198
+ 179,
199
+ 180,
200
+ 181,
201
+ 182,
202
+ 183,
203
+ 184,
204
+ 185,
205
+ 186,
206
+ 187,
207
+ 188,
208
+ 189,
209
+ 190,
210
+ 191,
211
+ 192,
212
+ 193,
213
+ 194,
214
+ 195,
215
+ 196,
216
+ 197,
217
+ 198,
218
+ 199,
219
+ 200,
220
+ 201,
221
+ 202,
222
+ 203,
223
+ 204,
224
+ 205,
225
+ 206,
226
+ 207,
227
+ 208,
228
+ 209,
229
+ 210,
230
+ 211,
231
+ 212,
232
+ 213,
233
+ 214,
234
+ 215,
235
+ 216,
236
+ 217,
237
+ 218,
238
+ 219,
239
+ 220,
240
+ 221,
241
+ 222,
242
+ 223,
243
+ 224,
244
+ 225,
245
+ 226,
246
+ 227,
247
+ 228,
248
+ 229,
249
+ 230,
250
+ 231,
251
+ 232,
252
+ 233,
253
+ 234,
254
+ 235,
255
+ 236,
256
+ 237,
257
+ 238,
258
+ 239,
259
+ 240,
260
+ 241,
261
+ 242,
262
+ 243,
263
+ 244,
264
+ 245,
265
+ 246,
266
+ 247,
267
+ 248,
268
+ 249,
269
+ 250,
270
+ 251,
271
+ 252,
272
+ 253,
273
+ 254,
274
+ 255,
275
+ 256,
276
+ 257,
277
+ 258,
278
+ 259,
279
+ 260,
280
+ 261,
281
+ 262,
282
+ 263,
283
+ 264,
284
+ 265,
285
+ 266,
286
+ 267,
287
+ 268,
288
+ 269,
289
+ 270,
290
+ 271,
291
+ 272,
292
+ 273,
293
+ 274,
294
+ 275,
295
+ 276,
296
+ 277,
297
+ 278,
298
+ 279,
299
+ 280,
300
+ 281,
301
+ 282,
302
+ 283,
303
+ 284,
304
+ 285,
305
+ 286,
306
+ 287,
307
+ 288,
308
+ 289,
309
+ 290,
310
+ 291,
311
+ 292,
312
+ 293,
313
+ 294,
314
+ 295,
315
+ 296,
316
+ 297,
317
+ 298,
318
+ 299,
319
+ 300,
320
+ 301,
321
+ 302,
322
+ 303,
323
+ 304,
324
+ 305,
325
+ 306,
326
+ 307,
327
+ 308,
328
+ 309,
329
+ 310,
330
+ 311,
331
+ 312,
332
+ 313,
333
+ 314,
334
+ 315,
335
+ 316,
336
+ 317,
337
+ 318,
338
+ 319,
339
+ 320,
340
+ 321,
341
+ 322,
342
+ 323,
343
+ 324,
344
+ 325,
345
+ 326,
346
+ 327,
347
+ 328,
348
+ 329,
349
+ 330,
350
+ 331,
351
+ 332,
352
+ 333,
353
+ 334,
354
+ 335,
355
+ 336,
356
+ 337,
357
+ 338,
358
+ 339,
359
+ 340,
360
+ 341,
361
+ 342,
362
+ 343,
363
+ 344,
364
+ 345,
365
+ 346,
366
+ 347,
367
+ 348,
368
+ 349,
369
+ 350,
370
+ 351,
371
+ 352,
372
+ 353,
373
+ 354,
374
+ 355,
375
+ 356,
376
+ 357,
377
+ 358,
378
+ 359,
379
+ 360,
380
+ 361,
381
+ 362,
382
+ 363,
383
+ 364,
384
+ 365,
385
+ 366,
386
+ 367,
387
+ 368,
388
+ 369,
389
+ 370,
390
+ 371,
391
+ 372,
392
+ 373,
393
+ 374,
394
+ 375,
395
+ 376,
396
+ 377,
397
+ 378,
398
+ 379,
399
+ 380,
400
+ 381,
401
+ 382,
402
+ 383,
403
+ 384,
404
+ 385,
405
+ 386,
406
+ 387,
407
+ 388,
408
+ 389,
409
+ 390,
410
+ 391,
411
+ 392,
412
+ 393,
413
+ 394,
414
+ 395,
415
+ 396,
416
+ 397,
417
+ 398,
418
+ 399,
419
+ 400,
420
+ 401,
421
+ 402,
422
+ 403,
423
+ 404,
424
+ 405,
425
+ 406,
426
+ 407,
427
+ 408,
428
+ 409,
429
+ 410,
430
+ 411,
431
+ 412,
432
+ 413,
433
+ 414,
434
+ 415,
435
+ 416,
436
+ 417,
437
+ 418,
438
+ 419,
439
+ 420,
440
+ 421,
441
+ 422,
442
+ 423,
443
+ 424,
444
+ 425,
445
+ 426,
446
+ 427,
447
+ 428,
448
+ 429,
449
+ 430,
450
+ 431,
451
+ 432,
452
+ 433,
453
+ 434,
454
+ 435,
455
+ 436,
456
+ 437,
457
+ 438,
458
+ 439,
459
+ 440,
460
+ 441,
461
+ 442,
462
+ 443,
463
+ 444,
464
+ 445,
465
+ 446,
466
+ 447,
467
+ 448,
468
+ 449,
469
+ 450,
470
+ 451,
471
+ 452,
472
+ 453,
473
+ 454,
474
+ 455,
475
+ 456,
476
+ 457,
477
+ 458,
478
+ 459,
479
+ 460,
480
+ 461,
481
+ 462,
482
+ 463,
483
+ 464,
484
+ 465,
485
+ 466,
486
+ 467,
487
+ 468,
488
+ 469,
489
+ 470,
490
+ 471,
491
+ 472,
492
+ 473,
493
+ 474,
494
+ 475,
495
+ 476,
496
+ 477,
497
+ 478,
498
+ 479,
499
+ 480,
500
+ 481,
501
+ 482,
502
+ 483,
503
+ 484,
504
+ 485,
505
+ 486,
506
+ 487,
507
+ 488,
508
+ 489,
509
+ 490,
510
+ 491,
511
+ 492,
512
+ 493,
513
+ 494,
514
+ 495,
515
+ 496,
516
+ 497,
517
+ 498,
518
+ 499
519
+ ]
520
+ }
521
+ ]
checkpoints/320000/training_state/optimizer_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e8b1821ca8ca769a109bf704a48f461907364d4369d0f0a4ae8d8d9b405912f
3
+ size 412659164
checkpoints/320000/training_state/rng_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:51e645457af21540e5c3837b17be4686e2eb9d90b469f557169ef52904d9ffaf
3
+ size 15708
checkpoints/320000/training_state/scheduler_state.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "base_lrs": [
3
+ 0.0005
4
+ ],
5
+ "last_epoch": 320000,
6
+ "_step_count": 320001,
7
+ "_is_initial": false,
8
+ "_get_lr_called_within_step": false,
9
+ "_last_lr": [
10
+ 2.5e-06
11
+ ],
12
+ "lr_lambdas": [
13
+ null
14
+ ]
15
+ }
checkpoints/320000/training_state/training_step.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "step": 320000,
3
+ "dp_world_size": 4,
4
+ "batch_size": 64,
5
+ "grad_accum_steps": 1,
6
+ "mixed_precision": "bf16",
7
+ "parallelism": {
8
+ "dp_replicate": 4,
9
+ "dp_shard": 1,
10
+ "ring_degree": 1,
11
+ "ulysses_degree": 1
12
+ }
13
+ }