Robotics
LeRobot
Safetensors
smolvla
felsager commited on
Commit
cedc577
·
verified ·
1 Parent(s): 25fcc37

checkpoint 080000

Browse files
checkpoints/080000/pretrained_model/config.json ADDED
@@ -0,0 +1,105 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "type": "smolvla",
3
+ "n_obs_steps": 1,
4
+ "input_features": {
5
+ "observation.state": {
6
+ "type": "STATE",
7
+ "shape": [
8
+ 10
9
+ ]
10
+ },
11
+ "observation.images.top": {
12
+ "type": "VISUAL",
13
+ "shape": [
14
+ 3,
15
+ 480,
16
+ 640
17
+ ]
18
+ },
19
+ "observation.images.wrist": {
20
+ "type": "VISUAL",
21
+ "shape": [
22
+ 3,
23
+ 480,
24
+ 640
25
+ ]
26
+ },
27
+ "observation.images.empty_camera_0": {
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
+ 10
41
+ ]
42
+ }
43
+ },
44
+ "device": "cuda",
45
+ "use_amp": false,
46
+ "use_peft": false,
47
+ "push_to_hub": true,
48
+ "repo_id": "felsager/smolvla_ee_pick_cube_longest_warmup",
49
+ "private": null,
50
+ "tags": null,
51
+ "license": null,
52
+ "pretrained_path": "felsager/smolvla_base_ee_rel",
53
+ "pretrained_revision": null,
54
+ "chunk_size": 50,
55
+ "n_action_steps": 50,
56
+ "use_relative_ee": true,
57
+ "rotation_representation": "rot6d",
58
+ "rot6d_identity_norm": true,
59
+ "normalization_mapping": {
60
+ "VISUAL": "IDENTITY",
61
+ "STATE": "MEAN_STD",
62
+ "ACTION": "MEAN_STD"
63
+ },
64
+ "max_state_dim": 32,
65
+ "max_action_dim": 32,
66
+ "resize_imgs_with_padding": [
67
+ 512,
68
+ 512
69
+ ],
70
+ "empty_cameras": 1,
71
+ "adapt_to_pi_aloha": false,
72
+ "use_delta_joint_actions_aloha": false,
73
+ "tokenizer_max_length": 48,
74
+ "num_steps": 10,
75
+ "use_cache": true,
76
+ "freeze_vision_encoder": true,
77
+ "train_expert_only": true,
78
+ "train_state_proj": true,
79
+ "optimizer_lr": 0.001,
80
+ "optimizer_betas": [
81
+ 0.9,
82
+ 0.95
83
+ ],
84
+ "optimizer_eps": 1e-08,
85
+ "optimizer_weight_decay": 1e-10,
86
+ "optimizer_grad_clip_norm": 10.0,
87
+ "scheduler_warmup_steps": 20000,
88
+ "scheduler_decay_steps": 80000,
89
+ "scheduler_decay_lr": 2.5e-06,
90
+ "vlm_model_name": "HuggingFaceTB/SmolVLM2-500M-Video-Instruct",
91
+ "load_vlm_weights": true,
92
+ "add_image_special_tokens": false,
93
+ "attention_mode": "cross_attn",
94
+ "prefix_length": 0,
95
+ "pad_language_to": "max_length",
96
+ "num_expert_layers": 0,
97
+ "num_vlm_layers": 16,
98
+ "self_attn_every_n_layers": 2,
99
+ "expert_width_multiplier": 0.75,
100
+ "min_period": 0.004,
101
+ "max_period": 4.0,
102
+ "rtc_config": null,
103
+ "compile_model": true,
104
+ "compile_mode": "default"
105
+ }
checkpoints/080000/pretrained_model/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0198c6b6cce6ce36bce987507549c1c4c5573e5d36f28d083a751e328639783
3
+ size 906712552
checkpoints/080000/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/080000/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 sha256:7f43fe07f444f4e0c67b9a877e30d4e71c113d4c968411d4d64f82c4635ab21a
3
+ size 10872
checkpoints/080000/pretrained_model/policy_preprocessor.json ADDED
@@ -0,0 +1,105 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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.state": {
60
+ "type": "STATE",
61
+ "shape": [
62
+ 10
63
+ ]
64
+ },
65
+ "observation.images.top": {
66
+ "type": "VISUAL",
67
+ "shape": [
68
+ 3,
69
+ 480,
70
+ 640
71
+ ]
72
+ },
73
+ "observation.images.wrist": {
74
+ "type": "VISUAL",
75
+ "shape": [
76
+ 3,
77
+ 480,
78
+ 640
79
+ ]
80
+ },
81
+ "observation.images.empty_camera_0": {
82
+ "type": "VISUAL",
83
+ "shape": [
84
+ 3,
85
+ 480,
86
+ 640
87
+ ]
88
+ },
89
+ "action": {
90
+ "type": "ACTION",
91
+ "shape": [
92
+ 10
93
+ ]
94
+ }
95
+ },
96
+ "norm_map": {
97
+ "VISUAL": "IDENTITY",
98
+ "STATE": "MEAN_STD",
99
+ "ACTION": "MEAN_STD"
100
+ }
101
+ },
102
+ "state_file": "policy_preprocessor_step_7_normalizer_processor.safetensors"
103
+ }
104
+ ]
105
+ }
checkpoints/080000/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 sha256:21c0613203fa10134c30734fbeb412cb0508562c1a624b83fcb411caf3607ab4
3
+ size 10880
checkpoints/080000/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/080000/pretrained_model/tokenizer/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoints/080000/pretrained_model/tokenizer/tokenizer_config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": false,
13
+ "legacy": false,
14
+ "model_max_length": 8192,
15
+ "model_specific_special_tokens": {
16
+ "end_of_utterance_token": "<end_of_utterance>",
17
+ "fake_image_token": "<fake_token_around_image>",
18
+ "global_image_token": "<global-img>",
19
+ "image_token": "<image>"
20
+ },
21
+ "pad_token": "<|im_end|>",
22
+ "processor_class": "SmolVLMProcessor",
23
+ "tokenizer_class": "GPT2Tokenizer",
24
+ "truncation_side": "left",
25
+ "unk_token": "<|endoftext|>",
26
+ "vocab_size": 49152
27
+ }
checkpoints/080000/pretrained_model/train_config.json ADDED
@@ -0,0 +1,1319 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset": {
3
+ "repo_id": "felsager/vla_cubes_big",
4
+ "repo_type": "dataset",
5
+ "root": null,
6
+ "episodes": [
7
+ 0,
8
+ 1,
9
+ 2,
10
+ 3,
11
+ 4,
12
+ 5,
13
+ 6,
14
+ 7,
15
+ 8,
16
+ 9,
17
+ 10,
18
+ 11,
19
+ 12,
20
+ 13,
21
+ 14,
22
+ 15,
23
+ 16,
24
+ 17,
25
+ 18,
26
+ 19,
27
+ 20,
28
+ 21,
29
+ 22,
30
+ 23,
31
+ 24,
32
+ 25,
33
+ 26,
34
+ 27,
35
+ 28,
36
+ 29,
37
+ 30,
38
+ 31,
39
+ 32,
40
+ 33,
41
+ 34,
42
+ 35,
43
+ 36,
44
+ 37,
45
+ 38,
46
+ 39,
47
+ 40,
48
+ 41,
49
+ 42,
50
+ 43,
51
+ 44,
52
+ 45,
53
+ 46,
54
+ 47,
55
+ 48,
56
+ 49,
57
+ 50,
58
+ 51,
59
+ 52,
60
+ 53,
61
+ 54,
62
+ 55,
63
+ 56,
64
+ 57,
65
+ 58,
66
+ 59,
67
+ 60,
68
+ 61,
69
+ 62,
70
+ 63,
71
+ 64,
72
+ 65,
73
+ 66,
74
+ 67,
75
+ 68,
76
+ 69,
77
+ 70,
78
+ 71,
79
+ 72,
80
+ 73,
81
+ 74,
82
+ 75,
83
+ 76,
84
+ 77,
85
+ 78,
86
+ 79,
87
+ 80,
88
+ 81,
89
+ 82,
90
+ 83,
91
+ 84,
92
+ 85,
93
+ 86,
94
+ 87,
95
+ 88,
96
+ 89,
97
+ 90,
98
+ 91,
99
+ 92,
100
+ 93,
101
+ 94,
102
+ 95,
103
+ 96,
104
+ 97,
105
+ 98,
106
+ 99,
107
+ 100,
108
+ 101,
109
+ 102,
110
+ 103,
111
+ 104,
112
+ 105,
113
+ 106,
114
+ 107,
115
+ 108,
116
+ 109,
117
+ 110,
118
+ 111,
119
+ 112,
120
+ 113,
121
+ 114,
122
+ 115,
123
+ 116,
124
+ 117,
125
+ 118,
126
+ 119,
127
+ 120,
128
+ 121,
129
+ 122,
130
+ 123,
131
+ 124,
132
+ 125,
133
+ 126,
134
+ 127,
135
+ 128,
136
+ 129,
137
+ 130,
138
+ 131,
139
+ 132,
140
+ 133,
141
+ 134,
142
+ 135,
143
+ 136,
144
+ 137,
145
+ 138,
146
+ 139,
147
+ 140,
148
+ 141,
149
+ 142,
150
+ 143,
151
+ 144,
152
+ 145,
153
+ 146,
154
+ 147,
155
+ 148,
156
+ 149,
157
+ 150,
158
+ 151,
159
+ 152,
160
+ 153,
161
+ 154,
162
+ 155,
163
+ 156,
164
+ 157,
165
+ 158,
166
+ 159,
167
+ 160,
168
+ 161,
169
+ 162,
170
+ 163,
171
+ 164,
172
+ 165,
173
+ 166,
174
+ 167,
175
+ 168,
176
+ 169,
177
+ 170,
178
+ 171,
179
+ 172,
180
+ 173,
181
+ 174,
182
+ 175,
183
+ 176,
184
+ 177,
185
+ 178,
186
+ 179,
187
+ 180,
188
+ 181,
189
+ 182,
190
+ 183,
191
+ 184,
192
+ 185,
193
+ 186,
194
+ 187,
195
+ 188,
196
+ 189,
197
+ 190,
198
+ 191,
199
+ 192,
200
+ 193,
201
+ 194,
202
+ 195,
203
+ 196,
204
+ 197,
205
+ 198,
206
+ 199,
207
+ 200,
208
+ 201,
209
+ 202,
210
+ 203,
211
+ 204,
212
+ 205,
213
+ 206,
214
+ 207,
215
+ 208,
216
+ 209,
217
+ 210,
218
+ 211,
219
+ 212,
220
+ 213,
221
+ 214,
222
+ 215,
223
+ 216,
224
+ 217,
225
+ 218,
226
+ 219,
227
+ 220,
228
+ 221,
229
+ 222,
230
+ 223,
231
+ 224,
232
+ 225,
233
+ 226,
234
+ 227,
235
+ 228,
236
+ 229,
237
+ 230,
238
+ 231,
239
+ 232,
240
+ 233,
241
+ 234,
242
+ 235,
243
+ 236,
244
+ 237,
245
+ 238,
246
+ 239,
247
+ 240,
248
+ 241,
249
+ 242,
250
+ 243,
251
+ 244,
252
+ 245,
253
+ 246,
254
+ 247,
255
+ 248,
256
+ 249,
257
+ 250,
258
+ 251,
259
+ 252,
260
+ 253,
261
+ 254,
262
+ 255,
263
+ 256,
264
+ 257,
265
+ 258,
266
+ 259,
267
+ 260,
268
+ 261,
269
+ 262,
270
+ 263,
271
+ 264,
272
+ 265,
273
+ 266,
274
+ 267,
275
+ 268,
276
+ 269,
277
+ 270,
278
+ 271,
279
+ 272,
280
+ 273,
281
+ 274,
282
+ 275,
283
+ 276,
284
+ 277,
285
+ 278,
286
+ 279,
287
+ 280,
288
+ 281,
289
+ 282,
290
+ 283,
291
+ 284,
292
+ 285,
293
+ 286,
294
+ 287,
295
+ 288,
296
+ 289,
297
+ 290,
298
+ 291,
299
+ 292,
300
+ 293,
301
+ 294,
302
+ 295,
303
+ 296,
304
+ 297,
305
+ 298,
306
+ 299,
307
+ 300,
308
+ 301,
309
+ 302,
310
+ 303,
311
+ 304,
312
+ 305,
313
+ 306,
314
+ 307,
315
+ 308,
316
+ 309,
317
+ 310,
318
+ 311,
319
+ 312,
320
+ 313,
321
+ 314,
322
+ 315,
323
+ 316,
324
+ 317,
325
+ 318,
326
+ 319,
327
+ 320,
328
+ 321,
329
+ 322,
330
+ 323,
331
+ 324,
332
+ 325,
333
+ 326,
334
+ 327,
335
+ 328,
336
+ 329,
337
+ 330,
338
+ 331,
339
+ 332,
340
+ 333,
341
+ 334,
342
+ 335,
343
+ 336,
344
+ 337,
345
+ 338,
346
+ 339,
347
+ 340,
348
+ 341,
349
+ 342,
350
+ 343,
351
+ 344,
352
+ 345,
353
+ 346,
354
+ 347,
355
+ 348,
356
+ 349,
357
+ 350,
358
+ 351,
359
+ 352,
360
+ 353,
361
+ 354,
362
+ 355,
363
+ 356,
364
+ 357,
365
+ 358,
366
+ 359,
367
+ 360,
368
+ 361,
369
+ 362,
370
+ 363,
371
+ 364,
372
+ 365,
373
+ 366,
374
+ 367,
375
+ 368,
376
+ 369,
377
+ 370,
378
+ 371,
379
+ 372,
380
+ 373,
381
+ 374,
382
+ 375,
383
+ 376,
384
+ 377,
385
+ 378,
386
+ 379,
387
+ 380,
388
+ 381,
389
+ 382,
390
+ 383,
391
+ 384,
392
+ 385,
393
+ 386,
394
+ 387,
395
+ 388,
396
+ 389,
397
+ 390,
398
+ 391,
399
+ 392,
400
+ 393,
401
+ 394,
402
+ 395,
403
+ 396,
404
+ 397,
405
+ 398,
406
+ 399,
407
+ 400,
408
+ 401,
409
+ 402,
410
+ 403,
411
+ 404,
412
+ 405,
413
+ 406,
414
+ 407,
415
+ 408,
416
+ 409,
417
+ 410,
418
+ 411,
419
+ 412,
420
+ 413,
421
+ 414,
422
+ 415,
423
+ 416,
424
+ 417,
425
+ 418,
426
+ 419,
427
+ 420,
428
+ 421,
429
+ 422,
430
+ 423,
431
+ 424,
432
+ 425,
433
+ 426,
434
+ 427,
435
+ 428,
436
+ 429,
437
+ 430,
438
+ 431,
439
+ 432,
440
+ 433,
441
+ 434,
442
+ 435,
443
+ 436,
444
+ 437,
445
+ 438,
446
+ 439,
447
+ 440,
448
+ 441,
449
+ 442,
450
+ 443,
451
+ 444,
452
+ 445,
453
+ 446,
454
+ 447,
455
+ 448,
456
+ 449,
457
+ 450,
458
+ 451,
459
+ 452,
460
+ 453,
461
+ 454,
462
+ 455,
463
+ 456,
464
+ 457,
465
+ 458,
466
+ 459,
467
+ 460,
468
+ 461,
469
+ 462,
470
+ 463,
471
+ 464,
472
+ 465,
473
+ 466,
474
+ 467,
475
+ 468,
476
+ 469,
477
+ 470,
478
+ 471,
479
+ 472,
480
+ 473,
481
+ 474,
482
+ 475,
483
+ 476,
484
+ 477,
485
+ 478,
486
+ 479,
487
+ 480,
488
+ 481,
489
+ 482,
490
+ 483,
491
+ 484,
492
+ 485,
493
+ 486,
494
+ 487,
495
+ 488,
496
+ 489,
497
+ 490,
498
+ 491,
499
+ 492,
500
+ 493,
501
+ 494,
502
+ 495,
503
+ 496,
504
+ 497,
505
+ 498,
506
+ 499,
507
+ 500,
508
+ 501,
509
+ 502,
510
+ 503,
511
+ 504,
512
+ 505,
513
+ 506,
514
+ 507,
515
+ 508,
516
+ 509,
517
+ 510,
518
+ 511,
519
+ 512,
520
+ 513,
521
+ 514,
522
+ 515,
523
+ 516,
524
+ 517,
525
+ 518,
526
+ 519,
527
+ 520,
528
+ 521,
529
+ 522,
530
+ 523,
531
+ 524,
532
+ 525,
533
+ 526,
534
+ 527,
535
+ 528,
536
+ 529,
537
+ 530,
538
+ 531,
539
+ 532,
540
+ 533,
541
+ 534,
542
+ 535,
543
+ 536,
544
+ 537,
545
+ 538,
546
+ 539,
547
+ 540,
548
+ 541,
549
+ 542,
550
+ 543,
551
+ 544,
552
+ 545,
553
+ 546,
554
+ 547,
555
+ 548,
556
+ 549,
557
+ 550,
558
+ 551,
559
+ 552,
560
+ 553,
561
+ 554,
562
+ 555,
563
+ 556,
564
+ 557,
565
+ 558,
566
+ 559,
567
+ 560,
568
+ 561,
569
+ 562,
570
+ 563,
571
+ 564,
572
+ 565,
573
+ 566,
574
+ 567,
575
+ 568,
576
+ 569,
577
+ 570,
578
+ 571,
579
+ 572,
580
+ 573,
581
+ 574,
582
+ 575,
583
+ 576,
584
+ 577,
585
+ 578,
586
+ 579,
587
+ 580,
588
+ 581,
589
+ 582,
590
+ 583,
591
+ 584,
592
+ 585,
593
+ 586,
594
+ 587,
595
+ 588,
596
+ 589,
597
+ 590,
598
+ 591,
599
+ 592,
600
+ 593,
601
+ 594,
602
+ 595,
603
+ 596,
604
+ 597,
605
+ 598,
606
+ 599,
607
+ 600,
608
+ 601,
609
+ 602,
610
+ 603,
611
+ 604,
612
+ 605,
613
+ 606,
614
+ 607,
615
+ 608,
616
+ 609,
617
+ 610,
618
+ 611,
619
+ 612,
620
+ 613,
621
+ 614,
622
+ 615,
623
+ 616,
624
+ 617,
625
+ 618,
626
+ 619,
627
+ 620,
628
+ 621,
629
+ 622,
630
+ 623,
631
+ 624,
632
+ 625,
633
+ 626,
634
+ 627,
635
+ 628,
636
+ 629,
637
+ 630,
638
+ 631,
639
+ 632,
640
+ 633,
641
+ 634,
642
+ 635,
643
+ 636,
644
+ 637,
645
+ 638,
646
+ 639,
647
+ 640,
648
+ 641,
649
+ 642,
650
+ 643,
651
+ 644,
652
+ 645,
653
+ 646,
654
+ 647,
655
+ 648,
656
+ 649,
657
+ 650,
658
+ 651,
659
+ 652,
660
+ 653,
661
+ 654,
662
+ 655,
663
+ 656,
664
+ 657,
665
+ 658,
666
+ 659,
667
+ 660,
668
+ 661,
669
+ 662,
670
+ 663,
671
+ 664,
672
+ 665,
673
+ 666,
674
+ 667,
675
+ 668,
676
+ 669,
677
+ 670,
678
+ 671,
679
+ 672,
680
+ 673,
681
+ 674,
682
+ 675,
683
+ 676,
684
+ 677,
685
+ 678,
686
+ 679,
687
+ 680,
688
+ 681,
689
+ 682,
690
+ 683,
691
+ 684,
692
+ 685,
693
+ 686,
694
+ 687,
695
+ 688,
696
+ 689,
697
+ 690,
698
+ 691,
699
+ 692,
700
+ 693,
701
+ 694,
702
+ 695,
703
+ 696,
704
+ 697,
705
+ 698,
706
+ 699,
707
+ 700,
708
+ 701,
709
+ 702,
710
+ 703,
711
+ 704,
712
+ 705,
713
+ 706,
714
+ 707,
715
+ 708,
716
+ 709,
717
+ 710,
718
+ 711,
719
+ 712,
720
+ 713,
721
+ 714,
722
+ 715,
723
+ 716,
724
+ 717,
725
+ 718,
726
+ 719,
727
+ 720,
728
+ 721,
729
+ 722,
730
+ 723,
731
+ 724,
732
+ 725,
733
+ 726,
734
+ 727,
735
+ 728,
736
+ 729,
737
+ 730,
738
+ 731,
739
+ 732,
740
+ 733,
741
+ 734,
742
+ 735,
743
+ 736,
744
+ 737,
745
+ 738,
746
+ 739,
747
+ 740,
748
+ 741,
749
+ 742,
750
+ 743,
751
+ 744,
752
+ 745,
753
+ 746,
754
+ 747,
755
+ 748,
756
+ 749,
757
+ 750,
758
+ 751,
759
+ 752,
760
+ 753,
761
+ 754,
762
+ 755,
763
+ 756,
764
+ 757,
765
+ 758,
766
+ 759,
767
+ 760,
768
+ 761,
769
+ 762,
770
+ 763,
771
+ 764,
772
+ 765,
773
+ 766,
774
+ 767,
775
+ 768,
776
+ 769,
777
+ 770,
778
+ 771,
779
+ 772,
780
+ 773,
781
+ 774,
782
+ 775,
783
+ 776,
784
+ 777,
785
+ 778,
786
+ 779,
787
+ 780,
788
+ 781,
789
+ 782,
790
+ 783,
791
+ 784,
792
+ 785,
793
+ 786,
794
+ 787,
795
+ 788,
796
+ 789,
797
+ 790,
798
+ 791,
799
+ 792,
800
+ 793,
801
+ 794,
802
+ 795,
803
+ 796,
804
+ 797,
805
+ 798,
806
+ 799,
807
+ 800,
808
+ 801,
809
+ 802,
810
+ 803,
811
+ 804,
812
+ 805,
813
+ 806,
814
+ 807,
815
+ 808,
816
+ 809,
817
+ 810,
818
+ 811,
819
+ 812,
820
+ 813,
821
+ 814,
822
+ 815,
823
+ 816,
824
+ 817,
825
+ 818,
826
+ 819,
827
+ 820,
828
+ 821,
829
+ 822,
830
+ 823,
831
+ 824,
832
+ 825,
833
+ 826,
834
+ 827,
835
+ 828,
836
+ 829,
837
+ 830,
838
+ 831,
839
+ 832,
840
+ 833,
841
+ 834,
842
+ 835,
843
+ 836,
844
+ 837,
845
+ 838,
846
+ 839,
847
+ 840,
848
+ 841,
849
+ 842,
850
+ 843,
851
+ 844,
852
+ 845,
853
+ 846,
854
+ 847,
855
+ 848,
856
+ 849,
857
+ 850,
858
+ 851,
859
+ 852,
860
+ 853,
861
+ 854,
862
+ 855,
863
+ 856,
864
+ 857,
865
+ 858,
866
+ 859,
867
+ 860,
868
+ 861,
869
+ 862,
870
+ 863,
871
+ 864,
872
+ 865,
873
+ 866,
874
+ 867,
875
+ 868,
876
+ 869,
877
+ 870,
878
+ 871,
879
+ 872,
880
+ 873,
881
+ 874,
882
+ 875,
883
+ 876,
884
+ 877,
885
+ 878,
886
+ 879,
887
+ 880,
888
+ 881,
889
+ 882,
890
+ 883,
891
+ 884,
892
+ 885,
893
+ 886,
894
+ 887,
895
+ 888,
896
+ 889,
897
+ 890,
898
+ 891,
899
+ 892,
900
+ 893,
901
+ 894,
902
+ 895,
903
+ 896,
904
+ 897,
905
+ 898,
906
+ 899,
907
+ 900,
908
+ 901,
909
+ 902,
910
+ 903,
911
+ 904,
912
+ 905,
913
+ 906,
914
+ 907,
915
+ 908,
916
+ 909,
917
+ 910,
918
+ 911,
919
+ 912,
920
+ 913,
921
+ 914,
922
+ 915,
923
+ 916,
924
+ 917,
925
+ 918,
926
+ 919,
927
+ 920,
928
+ 921,
929
+ 922,
930
+ 923,
931
+ 924,
932
+ 925,
933
+ 926,
934
+ 927,
935
+ 928,
936
+ 929,
937
+ 930,
938
+ 931,
939
+ 932,
940
+ 933,
941
+ 934,
942
+ 935,
943
+ 936,
944
+ 937,
945
+ 938,
946
+ 939,
947
+ 940,
948
+ 941,
949
+ 942,
950
+ 943,
951
+ 944,
952
+ 945,
953
+ 946,
954
+ 947,
955
+ 948,
956
+ 949,
957
+ 950,
958
+ 951,
959
+ 952,
960
+ 953,
961
+ 954,
962
+ 955,
963
+ 956,
964
+ 957,
965
+ 958,
966
+ 959,
967
+ 960,
968
+ 961,
969
+ 962,
970
+ 963,
971
+ 964,
972
+ 965,
973
+ 966,
974
+ 967,
975
+ 968,
976
+ 969,
977
+ 970,
978
+ 971,
979
+ 972,
980
+ 973,
981
+ 974,
982
+ 975,
983
+ 976,
984
+ 977,
985
+ 978,
986
+ 979,
987
+ 980,
988
+ 981,
989
+ 982,
990
+ 983,
991
+ 984,
992
+ 985,
993
+ 986,
994
+ 987,
995
+ 988,
996
+ 989,
997
+ 990,
998
+ 991,
999
+ 992,
1000
+ 993,
1001
+ 994,
1002
+ 995,
1003
+ 996,
1004
+ 997,
1005
+ 998,
1006
+ 999
1007
+ ],
1008
+ "exclude_episodes": null,
1009
+ "image_transforms": {
1010
+ "enable": false,
1011
+ "max_num_transforms": 3,
1012
+ "random_order": false,
1013
+ "tfs": {
1014
+ "brightness": {
1015
+ "weight": 1.0,
1016
+ "type": "ColorJitter",
1017
+ "kwargs": {
1018
+ "brightness": [
1019
+ 0.8,
1020
+ 1.2
1021
+ ]
1022
+ }
1023
+ },
1024
+ "contrast": {
1025
+ "weight": 1.0,
1026
+ "type": "ColorJitter",
1027
+ "kwargs": {
1028
+ "contrast": [
1029
+ 0.8,
1030
+ 1.2
1031
+ ]
1032
+ }
1033
+ },
1034
+ "saturation": {
1035
+ "weight": 1.0,
1036
+ "type": "ColorJitter",
1037
+ "kwargs": {
1038
+ "saturation": [
1039
+ 0.5,
1040
+ 1.5
1041
+ ]
1042
+ }
1043
+ },
1044
+ "hue": {
1045
+ "weight": 1.0,
1046
+ "type": "ColorJitter",
1047
+ "kwargs": {
1048
+ "hue": [
1049
+ -0.05,
1050
+ 0.05
1051
+ ]
1052
+ }
1053
+ },
1054
+ "sharpness": {
1055
+ "weight": 1.0,
1056
+ "type": "SharpnessJitter",
1057
+ "kwargs": {
1058
+ "sharpness": [
1059
+ 0.5,
1060
+ 1.5
1061
+ ]
1062
+ }
1063
+ },
1064
+ "affine": {
1065
+ "weight": 1.0,
1066
+ "type": "RandomAffine",
1067
+ "kwargs": {
1068
+ "degrees": [
1069
+ -5.0,
1070
+ 5.0
1071
+ ],
1072
+ "translate": [
1073
+ 0.05,
1074
+ 0.05
1075
+ ]
1076
+ }
1077
+ }
1078
+ }
1079
+ },
1080
+ "revision": null,
1081
+ "use_imagenet_stats": true,
1082
+ "video_backend": "torchcodec",
1083
+ "return_uint8": true,
1084
+ "depth_output_unit": "mm",
1085
+ "streaming": false,
1086
+ "eval_split": 0.0
1087
+ },
1088
+ "env": null,
1089
+ "policy": {
1090
+ "type": "smolvla",
1091
+ "n_obs_steps": 1,
1092
+ "input_features": {
1093
+ "observation.state": {
1094
+ "type": "STATE",
1095
+ "shape": [
1096
+ 10
1097
+ ]
1098
+ },
1099
+ "observation.images.top": {
1100
+ "type": "VISUAL",
1101
+ "shape": [
1102
+ 3,
1103
+ 480,
1104
+ 640
1105
+ ]
1106
+ },
1107
+ "observation.images.wrist": {
1108
+ "type": "VISUAL",
1109
+ "shape": [
1110
+ 3,
1111
+ 480,
1112
+ 640
1113
+ ]
1114
+ },
1115
+ "observation.images.empty_camera_0": {
1116
+ "type": "VISUAL",
1117
+ "shape": [
1118
+ 3,
1119
+ 480,
1120
+ 640
1121
+ ]
1122
+ }
1123
+ },
1124
+ "output_features": {
1125
+ "action": {
1126
+ "type": "ACTION",
1127
+ "shape": [
1128
+ 10
1129
+ ]
1130
+ }
1131
+ },
1132
+ "device": "cuda",
1133
+ "use_amp": false,
1134
+ "use_peft": false,
1135
+ "push_to_hub": true,
1136
+ "repo_id": "felsager/smolvla_ee_pick_cube_longest_warmup",
1137
+ "private": null,
1138
+ "tags": null,
1139
+ "license": null,
1140
+ "pretrained_path": "felsager/smolvla_base_ee_rel",
1141
+ "pretrained_revision": null,
1142
+ "chunk_size": 50,
1143
+ "n_action_steps": 50,
1144
+ "use_relative_ee": true,
1145
+ "rotation_representation": "rot6d",
1146
+ "rot6d_identity_norm": true,
1147
+ "normalization_mapping": {
1148
+ "VISUAL": "IDENTITY",
1149
+ "STATE": "MEAN_STD",
1150
+ "ACTION": "MEAN_STD"
1151
+ },
1152
+ "max_state_dim": 32,
1153
+ "max_action_dim": 32,
1154
+ "resize_imgs_with_padding": [
1155
+ 512,
1156
+ 512
1157
+ ],
1158
+ "empty_cameras": 1,
1159
+ "adapt_to_pi_aloha": false,
1160
+ "use_delta_joint_actions_aloha": false,
1161
+ "tokenizer_max_length": 48,
1162
+ "num_steps": 10,
1163
+ "use_cache": true,
1164
+ "freeze_vision_encoder": true,
1165
+ "train_expert_only": true,
1166
+ "train_state_proj": true,
1167
+ "optimizer_lr": 0.001,
1168
+ "optimizer_betas": [
1169
+ 0.9,
1170
+ 0.95
1171
+ ],
1172
+ "optimizer_eps": 1e-08,
1173
+ "optimizer_weight_decay": 1e-10,
1174
+ "optimizer_grad_clip_norm": 10.0,
1175
+ "scheduler_warmup_steps": 20000,
1176
+ "scheduler_decay_steps": 80000,
1177
+ "scheduler_decay_lr": 2.5e-06,
1178
+ "vlm_model_name": "HuggingFaceTB/SmolVLM2-500M-Video-Instruct",
1179
+ "load_vlm_weights": true,
1180
+ "add_image_special_tokens": false,
1181
+ "attention_mode": "cross_attn",
1182
+ "prefix_length": 0,
1183
+ "pad_language_to": "max_length",
1184
+ "num_expert_layers": 0,
1185
+ "num_vlm_layers": 16,
1186
+ "self_attn_every_n_layers": 2,
1187
+ "expert_width_multiplier": 0.75,
1188
+ "min_period": 0.004,
1189
+ "max_period": 4.0,
1190
+ "rtc_config": null,
1191
+ "compile_model": true,
1192
+ "compile_mode": "default"
1193
+ },
1194
+ "reward_model": null,
1195
+ "output_dir": "/work/sim_vla_ws/runs/train/new_pretrain_longest_warmup",
1196
+ "job_name": "new_pretrain_longest_warmup",
1197
+ "resume": false,
1198
+ "seed": 0,
1199
+ "cudnn_deterministic": false,
1200
+ "num_workers": 32,
1201
+ "batch_size": 64,
1202
+ "prefetch_factor": 1,
1203
+ "persistent_workers": true,
1204
+ "dataloader_multiprocessing_context": "spawn",
1205
+ "steps": 80000,
1206
+ "env_eval_freq": 20000,
1207
+ "log_freq": 250,
1208
+ "eval_steps": 0,
1209
+ "max_eval_samples": 0,
1210
+ "tolerance_s": 0.0001,
1211
+ "save_checkpoint": true,
1212
+ "save_freq": 10000,
1213
+ "checkpoint_format": "safetensors",
1214
+ "use_policy_training_preset": true,
1215
+ "optimizer": {
1216
+ "type": "adamw",
1217
+ "lr": 0.001,
1218
+ "weight_decay": 1e-10,
1219
+ "grad_clip_norm": 10.0,
1220
+ "betas": [
1221
+ 0.9,
1222
+ 0.95
1223
+ ],
1224
+ "eps": 1e-08
1225
+ },
1226
+ "scheduler": {
1227
+ "type": "cosine_decay_with_warmup",
1228
+ "num_warmup_steps": 20000,
1229
+ "num_decay_steps": 80000,
1230
+ "peak_lr": 0.001,
1231
+ "decay_lr": 2.5e-06
1232
+ },
1233
+ "parallelism": {
1234
+ "dp_replicate": 4,
1235
+ "dp_shard": 1,
1236
+ "context_parallel": {
1237
+ "ring_degree": 1,
1238
+ "ulysses_degree": 1
1239
+ },
1240
+ "cfg_parallel": 1
1241
+ },
1242
+ "accelerator": {
1243
+ "mixed_precision": "bf16",
1244
+ "gradient_accumulation": {
1245
+ "steps": 1
1246
+ },
1247
+ "grad_scaler": {
1248
+ "init_scale": 65536.0,
1249
+ "growth_factor": 2.0,
1250
+ "backoff_factor": 0.5,
1251
+ "growth_interval": 2000
1252
+ },
1253
+ "fsdp": {
1254
+ "reshard_after_forward": true,
1255
+ "wrap_modules": null,
1256
+ "min_num_params": null,
1257
+ "cpu_offload": false,
1258
+ "ignored_modules": null
1259
+ },
1260
+ "ddp": {
1261
+ "find_unused_parameters": true,
1262
+ "gradient_as_bucket_view": false,
1263
+ "static_graph": false
1264
+ },
1265
+ "compile": {
1266
+ "enabled": false,
1267
+ "backend": "inductor",
1268
+ "mode": null,
1269
+ "regional": true
1270
+ },
1271
+ "activation_checkpointing": {
1272
+ "mode": "none"
1273
+ }
1274
+ },
1275
+ "eval": {
1276
+ "n_episodes": 50,
1277
+ "batch_size": 50,
1278
+ "use_async_envs": true,
1279
+ "recording": false,
1280
+ "recording_repo_id": null,
1281
+ "recording_private": false
1282
+ },
1283
+ "ema": {
1284
+ "enable": false,
1285
+ "decay": null,
1286
+ "update_after_step": 0,
1287
+ "inv_gamma": 1.0,
1288
+ "power": 0.75,
1289
+ "min_decay": 0.0,
1290
+ "max_decay": 0.9999,
1291
+ "use_for_eval": true
1292
+ },
1293
+ "wandb": {
1294
+ "enable": true,
1295
+ "disable_artifact": false,
1296
+ "project": "lerobot",
1297
+ "entity": null,
1298
+ "notes": null,
1299
+ "run_id": "tzfvy5dt",
1300
+ "resume": null,
1301
+ "mode": null,
1302
+ "console": "wrap",
1303
+ "console_multipart": false,
1304
+ "console_chunk_max_seconds": 0,
1305
+ "add_tags": true
1306
+ },
1307
+ "peft": null,
1308
+ "job": {
1309
+ "target": null,
1310
+ "image": "huggingface/lerobot-gpu:latest",
1311
+ "timeout": "2d",
1312
+ "detach": false,
1313
+ "tags": []
1314
+ },
1315
+ "save_checkpoint_to_hub": true,
1316
+ "sample_weighting": null,
1317
+ "rename_map": {},
1318
+ "checkpoint_path": null
1319
+ }
checkpoints/080000/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": 0.001,
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/080000/training_state/optimizer_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f52ea523a0f4a660f31e5276235b85a57074dff56074bc6a660c6d37b8de5e86
3
+ size 412659164
checkpoints/080000/training_state/rng_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:668c7baa279c8af5797862c84d6b29fe33e6790d385a23f78f001163736bb4b8
3
+ size 15708
checkpoints/080000/training_state/scheduler_state.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "base_lrs": [
3
+ 0.001
4
+ ],
5
+ "last_epoch": 80000,
6
+ "_step_count": 80001,
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/080000/training_state/training_step.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "step": 80000,
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
+ }