Hugging Face's logo

Codingpae
/
20261009_groot_030000

Safetensors
Model card Files
xet
 Community
Codingpae commited on
Commit
67ef5b8
·
verified ·
1 Parent(s): 205897b

Upload folder using huggingface_hub

Browse files
Files changed (12) hide show
  1. pretrained_model/config.json +107 -0
  2. pretrained_model/model.safetensors +3 -0
  3. pretrained_model/policy_postprocessor.json +23 -0
  4. pretrained_model/policy_postprocessor_step_0_groot_action_unpack_unnormalize_v2.safetensors +3 -0
  5. pretrained_model/policy_preprocessor.json +78 -0
  6. pretrained_model/policy_preprocessor_step_2_groot_n1_7_pack_inputs_v1.safetensors +3 -0
  7. pretrained_model/train_config.json +260 -0
  8. training_state/optimizer_param_groups.json +577 -0
  9. training_state/optimizer_state.safetensors +3 -0
  10. training_state/rng_state.safetensors +3 -0
  11. training_state/scheduler_state.json +18 -0
  12. training_state/training_step.json +5 -0
pretrained_model/config.json ADDED
@@ -0,0 +1,107 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "type": "groot",
3
+ "n_obs_steps": 1,
4
+ "input_features": {
5
+ "observation.images.headcam": {
6
+ "type": "VISUAL",
7
+ "shape": [
8
+ 3,
9
+ 480,
10
+ 640
11
+ ]
12
+ },
13
+ "observation.images.camera_01": {
14
+ "type": "VISUAL",
15
+ "shape": [
16
+ 3,
17
+ 480,
18
+ 640
19
+ ]
20
+ },
21
+ "observation.images.camera_02": {
22
+ "type": "VISUAL",
23
+ "shape": [
24
+ 3,
25
+ 480,
26
+ 640
27
+ ]
28
+ },
29
+ "observation.state": {
30
+ "type": "STATE",
31
+ "shape": [
32
+ 16
33
+ ]
34
+ }
35
+ },
36
+ "output_features": {
37
+ "action": {
38
+ "type": "ACTION",
39
+ "shape": [
40
+ 16
41
+ ]
42
+ }
43
+ },
44
+ "device": "cuda",
45
+ "use_amp": false,
46
+ "use_peft": false,
47
+ "push_to_hub": false,
48
+ "repo_id": null,
49
+ "private": null,
50
+ "tags": null,
51
+ "license": null,
52
+ "pretrained_path": null,
53
+ "pretrained_revision": null,
54
+ "chunk_size": 40,
55
+ "n_action_steps": 40,
56
+ "max_state_dim": 132,
57
+ "max_action_dim": 132,
58
+ "normalization_mapping": {
59
+ "VISUAL": "IDENTITY",
60
+ "STATE": "IDENTITY",
61
+ "ACTION": "IDENTITY"
62
+ },
63
+ "base_model_path": "nvidia/GR00T-N1.7-3B",
64
+ "action_decode_transform": null,
65
+ "embodiment_tag": "new_embodiment",
66
+ "tune_llm": false,
67
+ "tune_visual": false,
68
+ "tune_projector": true,
69
+ "tune_diffusion_model": true,
70
+ "tune_vlln": true,
71
+ "tune_top_llm_layers": 0,
72
+ "num_inference_timesteps": null,
73
+ "rtc_ramp_rate": null,
74
+ "use_flash_attention": false,
75
+ "use_relative_actions": false,
76
+ "relative_exclude_joints": [],
77
+ "optimizer_lr": 0.0001,
78
+ "optimizer_betas": [
79
+ 0.9,
80
+ 0.999
81
+ ],
82
+ "optimizer_eps": 1e-08,
83
+ "optimizer_weight_decay": 1e-05,
84
+ "warmup_ratio": 0.05,
85
+ "use_bf16": true,
86
+ "model_params_fp32": true,
87
+ "image_size": [
88
+ 256,
89
+ 256
90
+ ],
91
+ "tokenizer_assets_repo": null,
92
+ "lora_rank": 0,
93
+ "lora_alpha": 16,
94
+ "lora_dropout": 0.1,
95
+ "lora_full_model": false,
96
+ "video_backend": "decord",
97
+ "balance_dataset_weights": true,
98
+ "balance_trajectory_weights": true,
99
+ "dataset_paths": null,
100
+ "output_dir": "./tmp/gr00t",
101
+ "save_steps": 1000,
102
+ "max_steps": 10000,
103
+ "batch_size": 32,
104
+ "dataloader_num_workers": 8,
105
+ "report_to": "wandb",
106
+ "resume": false
107
+ }
pretrained_model/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec1d5baf01b222d3c60699375d04745031398e320fb185ffaa3931e413b16921
3
+ size 12576215296
pretrained_model/policy_postprocessor.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "name": "policy_postprocessor",
3
+ "steps": [
4
+ {
5
+ "registry_name": "groot_action_unpack_unnormalize_v2",
6
+ "config": {
7
+ "env_action_dim": 16,
8
+ "normalize_min_max": true,
9
+ "clip_normalized_action": true,
10
+ "libero_gripper_action": false,
11
+ "libero_gripper_binarize": true
12
+ },
13
+ "state_file": "policy_postprocessor_step_0_groot_action_unpack_unnormalize_v2.safetensors"
14
+ },
15
+ {
16
+ "registry_name": "device_processor",
17
+ "config": {
18
+ "device": "cpu",
19
+ "float_dtype": null
20
+ }
21
+ }
22
+ ]
23
+ }
pretrained_model/policy_postprocessor_step_0_groot_action_unpack_unnormalize_v2.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dcc9abf8f22639e3706073a071efe88826689cce418886f77701490718f9a572
3
+ size 11160
pretrained_model/policy_preprocessor.json ADDED
@@ -0,0 +1,78 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "groot_n1_7_pack_inputs_v1",
16
+ "config": {
17
+ "state_horizon": 1,
18
+ "action_horizon": 40,
19
+ "valid_action_horizon": 40,
20
+ "video_horizon": null,
21
+ "max_state_dim": 132,
22
+ "max_action_dim": 132,
23
+ "language_key": "task",
24
+ "formalize_language": true,
25
+ "embodiment_tag": "new_embodiment",
26
+ "embodiment_mapping": {
27
+ "oxe_droid_relative_eef_relative_joint": 24,
28
+ "xdof_relative_eef_relative_joint": 27,
29
+ "xdof_relative_eef_relative_joint_subtask": 27,
30
+ "real_g1_relative_eef_relative_joints": 25,
31
+ "real_r1_pro_sharpa_relative_eef": 26,
32
+ "real_r1_pro_sharpa_relative_eef_human": 26,
33
+ "real_r1_pro_sharpa_relative_eef_maxinsights": 26,
34
+ "real_r1_pro_sharpa_relative_eef_mecka": 26,
35
+ "unitree_g1_full_body_with_waist_height_nav_cmd": 25,
36
+ "simpler_env_google": 0,
37
+ "simpler_env_widowx": 1,
38
+ "libero_sim": 2,
39
+ "new_embodiment": 10
40
+ },
41
+ "normalize_min_max": true,
42
+ "state_dropout_prob": 0.0,
43
+ "clip_outliers": true,
44
+ "use_percentiles": false,
45
+ "video_modality_keys": null,
46
+ "raw_stats": null,
47
+ "modality_config": null
48
+ },
49
+ "state_file": "policy_preprocessor_step_2_groot_n1_7_pack_inputs_v1.safetensors"
50
+ },
51
+ {
52
+ "registry_name": "groot_n1_7_vlm_encode_v1",
53
+ "config": {
54
+ "model_name": "nvidia/Cosmos-Reason2-2B",
55
+ "image_crop_size": [
56
+ 230,
57
+ 230
58
+ ],
59
+ "image_target_size": [
60
+ 256,
61
+ 256
62
+ ],
63
+ "shortest_image_edge": null,
64
+ "crop_fraction": null,
65
+ "use_albumentations": false,
66
+ "letter_box_transform": false,
67
+ "device": "cuda"
68
+ }
69
+ },
70
+ {
71
+ "registry_name": "device_processor",
72
+ "config": {
73
+ "device": "cuda",
74
+ "float_dtype": null
75
+ }
76
+ }
77
+ ]
78
+ }
pretrained_model/policy_preprocessor_step_2_groot_n1_7_pack_inputs_v1.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dcc9abf8f22639e3706073a071efe88826689cce418886f77701490718f9a572
3
+ size 11160
pretrained_model/train_config.json ADDED
@@ -0,0 +1,260 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset": {
3
+ "repo_id": "local/20261009",
4
+ "repo_type": "dataset",
5
+ "root": "/home/irteam/datasets/20261009",
6
+ "episodes": null,
7
+ "image_transforms": {
8
+ "enable": false,
9
+ "max_num_transforms": 3,
10
+ "random_order": false,
11
+ "tfs": {
12
+ "brightness": {
13
+ "weight": 1.0,
14
+ "type": "ColorJitter",
15
+ "kwargs": {
16
+ "brightness": [
17
+ 0.8,
18
+ 1.2
19
+ ]
20
+ }
21
+ },
22
+ "contrast": {
23
+ "weight": 1.0,
24
+ "type": "ColorJitter",
25
+ "kwargs": {
26
+ "contrast": [
27
+ 0.8,
28
+ 1.2
29
+ ]
30
+ }
31
+ },
32
+ "saturation": {
33
+ "weight": 1.0,
34
+ "type": "ColorJitter",
35
+ "kwargs": {
36
+ "saturation": [
37
+ 0.5,
38
+ 1.5
39
+ ]
40
+ }
41
+ },
42
+ "hue": {
43
+ "weight": 1.0,
44
+ "type": "ColorJitter",
45
+ "kwargs": {
46
+ "hue": [
47
+ -0.05,
48
+ 0.05
49
+ ]
50
+ }
51
+ },
52
+ "sharpness": {
53
+ "weight": 1.0,
54
+ "type": "SharpnessJitter",
55
+ "kwargs": {
56
+ "sharpness": [
57
+ 0.5,
58
+ 1.5
59
+ ]
60
+ }
61
+ },
62
+ "affine": {
63
+ "weight": 1.0,
64
+ "type": "RandomAffine",
65
+ "kwargs": {
66
+ "degrees": [
67
+ -5.0,
68
+ 5.0
69
+ ],
70
+ "translate": [
71
+ 0.05,
72
+ 0.05
73
+ ]
74
+ }
75
+ }
76
+ }
77
+ },
78
+ "revision": null,
79
+ "use_imagenet_stats": true,
80
+ "video_backend": "pyav",
81
+ "return_uint8": false,
82
+ "depth_output_unit": "mm",
83
+ "streaming": false,
84
+ "eval_split": 0.0
85
+ },
86
+ "env": null,
87
+ "policy": {
88
+ "type": "groot",
89
+ "n_obs_steps": 1,
90
+ "input_features": {
91
+ "observation.images.headcam": {
92
+ "type": "VISUAL",
93
+ "shape": [
94
+ 3,
95
+ 480,
96
+ 640
97
+ ]
98
+ },
99
+ "observation.images.camera_01": {
100
+ "type": "VISUAL",
101
+ "shape": [
102
+ 3,
103
+ 480,
104
+ 640
105
+ ]
106
+ },
107
+ "observation.images.camera_02": {
108
+ "type": "VISUAL",
109
+ "shape": [
110
+ 3,
111
+ 480,
112
+ 640
113
+ ]
114
+ },
115
+ "observation.state": {
116
+ "type": "STATE",
117
+ "shape": [
118
+ 16
119
+ ]
120
+ }
121
+ },
122
+ "output_features": {
123
+ "action": {
124
+ "type": "ACTION",
125
+ "shape": [
126
+ 16
127
+ ]
128
+ }
129
+ },
130
+ "device": "cuda",
131
+ "use_amp": false,
132
+ "use_peft": false,
133
+ "push_to_hub": false,
134
+ "repo_id": null,
135
+ "private": null,
136
+ "tags": null,
137
+ "license": null,
138
+ "pretrained_path": null,
139
+ "pretrained_revision": null,
140
+ "chunk_size": 40,
141
+ "n_action_steps": 40,
142
+ "max_state_dim": 132,
143
+ "max_action_dim": 132,
144
+ "normalization_mapping": {
145
+ "VISUAL": "IDENTITY",
146
+ "STATE": "IDENTITY",
147
+ "ACTION": "IDENTITY"
148
+ },
149
+ "base_model_path": "nvidia/GR00T-N1.7-3B",
150
+ "action_decode_transform": null,
151
+ "embodiment_tag": "new_embodiment",
152
+ "tune_llm": false,
153
+ "tune_visual": false,
154
+ "tune_projector": true,
155
+ "tune_diffusion_model": true,
156
+ "tune_vlln": true,
157
+ "tune_top_llm_layers": 0,
158
+ "num_inference_timesteps": null,
159
+ "rtc_ramp_rate": null,
160
+ "use_flash_attention": false,
161
+ "use_relative_actions": false,
162
+ "relative_exclude_joints": [],
163
+ "optimizer_lr": 0.0001,
164
+ "optimizer_betas": [
165
+ 0.9,
166
+ 0.999
167
+ ],
168
+ "optimizer_eps": 1e-08,
169
+ "optimizer_weight_decay": 1e-05,
170
+ "warmup_ratio": 0.05,
171
+ "use_bf16": true,
172
+ "model_params_fp32": true,
173
+ "image_size": [
174
+ 256,
175
+ 256
176
+ ],
177
+ "tokenizer_assets_repo": null,
178
+ "lora_rank": 0,
179
+ "lora_alpha": 16,
180
+ "lora_dropout": 0.1,
181
+ "lora_full_model": false,
182
+ "video_backend": "decord",
183
+ "balance_dataset_weights": true,
184
+ "balance_trajectory_weights": true,
185
+ "dataset_paths": null,
186
+ "output_dir": "./tmp/gr00t",
187
+ "save_steps": 1000,
188
+ "max_steps": 10000,
189
+ "batch_size": 32,
190
+ "dataloader_num_workers": 8,
191
+ "report_to": "wandb",
192
+ "resume": false
193
+ },
194
+ "reward_model": null,
195
+ "output_dir": "/home/irteam/datasets/train/20261009_groot",
196
+ "job_name": "20261009_groot",
197
+ "resume": false,
198
+ "seed": 1000,
199
+ "cudnn_deterministic": false,
200
+ "num_workers": 8,
201
+ "batch_size": 32,
202
+ "prefetch_factor": 4,
203
+ "persistent_workers": true,
204
+ "dataloader_multiprocessing_context": "spawn",
205
+ "steps": 30000,
206
+ "env_eval_freq": 20000,
207
+ "log_freq": 50,
208
+ "eval_steps": 0,
209
+ "max_eval_samples": 0,
210
+ "tolerance_s": 0.0001,
211
+ "save_checkpoint": true,
212
+ "save_freq": 2000,
213
+ "use_policy_training_preset": true,
214
+ "optimizer": {
215
+ "type": "adamw",
216
+ "lr": 0.0001,
217
+ "weight_decay": 1e-05,
218
+ "grad_clip_norm": 1.0,
219
+ "betas": [
220
+ 0.9,
221
+ 0.999
222
+ ],
223
+ "eps": 1e-08
224
+ },
225
+ "scheduler": {
226
+ "type": "diffuser",
227
+ "num_warmup_steps": 500,
228
+ "name": "cosine"
229
+ },
230
+ "eval": {
231
+ "n_episodes": 50,
232
+ "batch_size": 50,
233
+ "use_async_envs": true,
234
+ "recording": false,
235
+ "recording_repo_id": null,
236
+ "recording_private": false
237
+ },
238
+ "wandb": {
239
+ "enable": false,
240
+ "disable_artifact": false,
241
+ "project": "lerobot",
242
+ "entity": null,
243
+ "notes": null,
244
+ "run_id": null,
245
+ "mode": null,
246
+ "add_tags": true
247
+ },
248
+ "peft": null,
249
+ "job": {
250
+ "target": null,
251
+ "image": "huggingface/lerobot-gpu:latest",
252
+ "timeout": "2d",
253
+ "detach": false,
254
+ "tags": []
255
+ },
256
+ "save_checkpoint_to_hub": false,
257
+ "sample_weighting": null,
258
+ "rename_map": {},
259
+ "checkpoint_path": null
260
+ }
training_state/optimizer_param_groups.json ADDED
@@ -0,0 +1,577 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "lr": 0.0,
4
+ "betas": [
5
+ 0.9,
6
+ 0.999
7
+ ],
8
+ "eps": 1e-08,
9
+ "weight_decay": 1e-05,
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": 0.0001,
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
+ ]
287
+ },
288
+ {
289
+ "weight_decay": 0.0,
290
+ "lr": 0.0,
291
+ "betas": [
292
+ 0.9,
293
+ 0.999
294
+ ],
295
+ "eps": 1e-08,
296
+ "amsgrad": false,
297
+ "maximize": false,
298
+ "foreach": null,
299
+ "capturable": false,
300
+ "differentiable": false,
301
+ "fused": null,
302
+ "decoupled_weight_decay": true,
303
+ "initial_lr": 0.0001,
304
+ "params": [
305
+ 267,
306
+ 268,
307
+ 269,
308
+ 270,
309
+ 271,
310
+ 272,
311
+ 273,
312
+ 274,
313
+ 275,
314
+ 276,
315
+ 277,
316
+ 278,
317
+ 279,
318
+ 280,
319
+ 281,
320
+ 282,
321
+ 283,
322
+ 284,
323
+ 285,
324
+ 286,
325
+ 287,
326
+ 288,
327
+ 289,
328
+ 290,
329
+ 291,
330
+ 292,
331
+ 293,
332
+ 294,
333
+ 295,
334
+ 296,
335
+ 297,
336
+ 298,
337
+ 299,
338
+ 300,
339
+ 301,
340
+ 302,
341
+ 303,
342
+ 304,
343
+ 305,
344
+ 306,
345
+ 307,
346
+ 308,
347
+ 309,
348
+ 310,
349
+ 311,
350
+ 312,
351
+ 313,
352
+ 314,
353
+ 315,
354
+ 316,
355
+ 317,
356
+ 318,
357
+ 319,
358
+ 320,
359
+ 321,
360
+ 322,
361
+ 323,
362
+ 324,
363
+ 325,
364
+ 326,
365
+ 327,
366
+ 328,
367
+ 329,
368
+ 330,
369
+ 331,
370
+ 332,
371
+ 333,
372
+ 334,
373
+ 335,
374
+ 336,
375
+ 337,
376
+ 338,
377
+ 339,
378
+ 340,
379
+ 341,
380
+ 342,
381
+ 343,
382
+ 344,
383
+ 345,
384
+ 346,
385
+ 347,
386
+ 348,
387
+ 349,
388
+ 350,
389
+ 351,
390
+ 352,
391
+ 353,
392
+ 354,
393
+ 355,
394
+ 356,
395
+ 357,
396
+ 358,
397
+ 359,
398
+ 360,
399
+ 361,
400
+ 362,
401
+ 363,
402
+ 364,
403
+ 365,
404
+ 366,
405
+ 367,
406
+ 368,
407
+ 369,
408
+ 370,
409
+ 371,
410
+ 372,
411
+ 373,
412
+ 374,
413
+ 375,
414
+ 376,
415
+ 377,
416
+ 378,
417
+ 379,
418
+ 380,
419
+ 381,
420
+ 382,
421
+ 383,
422
+ 384,
423
+ 385,
424
+ 386,
425
+ 387,
426
+ 388,
427
+ 389,
428
+ 390,
429
+ 391,
430
+ 392,
431
+ 393,
432
+ 394,
433
+ 395,
434
+ 396,
435
+ 397,
436
+ 398,
437
+ 399,
438
+ 400,
439
+ 401,
440
+ 402,
441
+ 403,
442
+ 404,
443
+ 405,
444
+ 406,
445
+ 407,
446
+ 408,
447
+ 409,
448
+ 410,
449
+ 411,
450
+ 412,
451
+ 413,
452
+ 414,
453
+ 415,
454
+ 416,
455
+ 417,
456
+ 418,
457
+ 419,
458
+ 420,
459
+ 421,
460
+ 422,
461
+ 423,
462
+ 424,
463
+ 425,
464
+ 426,
465
+ 427,
466
+ 428,
467
+ 429,
468
+ 430,
469
+ 431,
470
+ 432,
471
+ 433,
472
+ 434,
473
+ 435,
474
+ 436,
475
+ 437,
476
+ 438,
477
+ 439,
478
+ 440,
479
+ 441,
480
+ 442,
481
+ 443,
482
+ 444,
483
+ 445,
484
+ 446,
485
+ 447,
486
+ 448,
487
+ 449,
488
+ 450,
489
+ 451,
490
+ 452,
491
+ 453,
492
+ 454,
493
+ 455,
494
+ 456,
495
+ 457,
496
+ 458,
497
+ 459,
498
+ 460,
499
+ 461,
500
+ 462,
501
+ 463,
502
+ 464,
503
+ 465,
504
+ 466,
505
+ 467,
506
+ 468,
507
+ 469,
508
+ 470,
509
+ 471,
510
+ 472,
511
+ 473,
512
+ 474,
513
+ 475,
514
+ 476,
515
+ 477,
516
+ 478,
517
+ 479,
518
+ 480,
519
+ 481,
520
+ 482,
521
+ 483,
522
+ 484,
523
+ 485,
524
+ 486,
525
+ 487,
526
+ 488,
527
+ 489,
528
+ 490,
529
+ 491,
530
+ 492,
531
+ 493,
532
+ 494,
533
+ 495,
534
+ 496,
535
+ 497,
536
+ 498,
537
+ 499,
538
+ 500,
539
+ 501,
540
+ 502,
541
+ 503,
542
+ 504,
543
+ 505,
544
+ 506,
545
+ 507,
546
+ 508,
547
+ 509,
548
+ 510,
549
+ 511,
550
+ 512,
551
+ 513,
552
+ 514,
553
+ 515,
554
+ 516,
555
+ 517,
556
+ 518,
557
+ 519,
558
+ 520,
559
+ 521,
560
+ 522,
561
+ 523,
562
+ 524,
563
+ 525,
564
+ 526,
565
+ 527,
566
+ 528,
567
+ 529,
568
+ 530,
569
+ 531,
570
+ 532,
571
+ 533,
572
+ 534,
573
+ 535,
574
+ 536
575
+ ]
576
+ }
577
+ ]
training_state/optimizer_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e13659cbbb5368630ee62e25c5ecf093b9625aef1525445f8f5406d18eb9252
3
+ size 12964276740
training_state/rng_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:293bc73d3cabef0dc81529889ffc02c17d3835ad98fde9bc912062d2222820fe
3
+ size 15708
training_state/scheduler_state.json ADDED
@@ -0,0 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "base_lrs": [
3
+ 0.0001,
4
+ 0.0001
5
+ ],
6
+ "last_epoch": 30000,
7
+ "_step_count": 30001,
8
+ "_is_initial": false,
9
+ "_get_lr_called_within_step": false,
10
+ "_last_lr": [
11
+ 0.0,
12
+ 0.0
13
+ ],
14
+ "lr_lambdas": [
15
+ null,
16
+ null
17
+ ]
18
+ }
training_state/training_step.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "step": 30000,
3
+ "num_processes": 1,
4
+ "batch_size": 32
5
+ }