binhng commited on
Commit
9b75ef0
·
verified ·
1 Parent(s): ac1cbed

Initial commit

Browse files
pretrained_model/config.json ADDED
@@ -0,0 +1,155 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "type": "pi0",
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.images.image": {
11
+ "type": "VISUAL",
12
+ "shape": [
13
+ 3,
14
+ 256,
15
+ 256
16
+ ]
17
+ },
18
+ "observation.images.wrist_image": {
19
+ "type": "VISUAL",
20
+ "shape": [
21
+ 3,
22
+ 256,
23
+ 256
24
+ ]
25
+ },
26
+ "observation.images.image_depth": {
27
+ "type": "VISUAL",
28
+ "shape": [
29
+ 3,
30
+ 256,
31
+ 256
32
+ ]
33
+ },
34
+ "observation.images.wrist_depth": {
35
+ "type": "VISUAL",
36
+ "shape": [
37
+ 3,
38
+ 256,
39
+ 256
40
+ ]
41
+ },
42
+ "observation.images.image_mask": {
43
+ "type": "VISUAL",
44
+ "shape": [
45
+ 3,
46
+ 256,
47
+ 256
48
+ ]
49
+ },
50
+ "observation.images.wrist_mask": {
51
+ "type": "VISUAL",
52
+ "shape": [
53
+ 3,
54
+ 256,
55
+ 256
56
+ ]
57
+ },
58
+ "observation.images.object_of_interest_mask": {
59
+ "type": "VISUAL",
60
+ "shape": [
61
+ 3,
62
+ 256,
63
+ 256
64
+ ]
65
+ },
66
+ "observation.images.object_of_interest_wrist_mask": {
67
+ "type": "VISUAL",
68
+ "shape": [
69
+ 3,
70
+ 256,
71
+ 256
72
+ ]
73
+ },
74
+ "observation.state": {
75
+ "type": "STATE",
76
+ "shape": [
77
+ 8
78
+ ]
79
+ },
80
+ "observation.states.ee_state": {
81
+ "type": "STATE",
82
+ "shape": [
83
+ 6
84
+ ]
85
+ },
86
+ "observation.states.joint_state": {
87
+ "type": "STATE",
88
+ "shape": [
89
+ 7
90
+ ]
91
+ },
92
+ "observation.states.gripper_state": {
93
+ "type": "STATE",
94
+ "shape": [
95
+ 2
96
+ ]
97
+ }
98
+ },
99
+ "output_features": {
100
+ "action": {
101
+ "type": "ACTION",
102
+ "shape": [
103
+ 7
104
+ ]
105
+ }
106
+ },
107
+ "device": "cuda",
108
+ "use_amp": false,
109
+ "gradient_accumulation_steps": 2,
110
+ "chunk_size": 50,
111
+ "n_action_steps": 50,
112
+ "visual_prompt": false,
113
+ "use_both_origin": false,
114
+ "zero_init": false,
115
+ "coordinate_text_prod": false,
116
+ "coordinate_posEmbed_prod": false,
117
+ "posEmbed_to_preTrained": false,
118
+ "num_obs_layers": 30,
119
+ "last_obs_layers": false,
120
+ "add_posEmbed": false,
121
+ "not_used_coord": false,
122
+ "use_depth": false,
123
+ "depth_model_type": "frozen_siglip",
124
+ "use_track": true,
125
+ "track_mask": false,
126
+ "use_slot_att": "none",
127
+ "future_obj": "all",
128
+ "max_state_dim": 32,
129
+ "max_action_dim": 32,
130
+ "resize_imgs_with_padding": [
131
+ 224,
132
+ 224
133
+ ],
134
+ "empty_cameras": 0,
135
+ "adapt_to_pi_aloha": false,
136
+ "use_delta_joint_actions_aloha": false,
137
+ "tokenizer_max_length": 48,
138
+ "proj_width": 1024,
139
+ "num_steps": 10,
140
+ "use_cache": true,
141
+ "attention_implementation": "eager",
142
+ "freeze_vision_encoder": true,
143
+ "train_expert_only": false,
144
+ "train_state_proj": true,
145
+ "optimizer_lr": 0.0001,
146
+ "optimizer_betas": [
147
+ 0.9,
148
+ 0.95
149
+ ],
150
+ "optimizer_eps": 1e-08,
151
+ "optimizer_weight_decay": 1e-10,
152
+ "scheduler_warmup_steps": 1000,
153
+ "scheduler_decay_steps": 240000,
154
+ "scheduler_decay_lr": 2.5e-06
155
+ }
pretrained_model/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22148399f6a0b3bb3c979434c1ef58139aaa02ba2d403646820c71707e6233bc
3
+ size 7782298616
pretrained_model/train_config.json ADDED
@@ -0,0 +1,365 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset": {
3
+ "repo_id": "ducido/calvin_task_D_D_scale_100_lerobo_format",
4
+ "root": "/mnt/vast-orga/projects/extern/kisski/kisski-umg-fairpact-2/dir.project/nghiem/VLA_Dataset/merged_libero_scale_40_mask_depth_cotracker_noops_lerobot_patch_size7_chunk10_mask_interest",
5
+ "episodes": null,
6
+ "image_transforms": {
7
+ "enable": true,
8
+ "max_num_transforms": 3,
9
+ "random_order": false,
10
+ "image_tfs": {
11
+ "hue": {
12
+ "weight": 1.0,
13
+ "type": "ColorJitter",
14
+ "kwargs": {
15
+ "hue": [
16
+ -0.05,
17
+ 0.05
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
+ "sharpness": {
32
+ "weight": 1.0,
33
+ "type": "SharpnessJitter",
34
+ "kwargs": {
35
+ "sharpness": [
36
+ 0.5,
37
+ 1.5
38
+ ]
39
+ }
40
+ },
41
+ "brightness": {
42
+ "weight": 1.0,
43
+ "type": "ColorJitter",
44
+ "kwargs": {
45
+ "brightness": [
46
+ 0.8,
47
+ 1.2
48
+ ]
49
+ }
50
+ },
51
+ "saturation": {
52
+ "weight": 1.0,
53
+ "type": "ColorJitter",
54
+ "kwargs": {
55
+ "saturation": [
56
+ 0.5,
57
+ 1.5
58
+ ]
59
+ }
60
+ },
61
+ "crop_resize": {
62
+ "weight": 1.0,
63
+ "type": "RandomResizedCrop",
64
+ "kwargs": {
65
+ "size": [
66
+ 256,
67
+ 256
68
+ ],
69
+ "ratio": [
70
+ 1,
71
+ 1
72
+ ],
73
+ "scale": [
74
+ 0.9,
75
+ 0.95
76
+ ]
77
+ }
78
+ },
79
+ "rotate": {
80
+ "weight": 1.0,
81
+ "type": "RandomRotate",
82
+ "kwargs": {
83
+ "degrees": [
84
+ -5,
85
+ 5
86
+ ]
87
+ }
88
+ }
89
+ },
90
+ "wrist_tfs": {
91
+ "hue": {
92
+ "weight": 1.0,
93
+ "type": "ColorJitter",
94
+ "kwargs": {
95
+ "hue": [
96
+ -0.05,
97
+ 0.05
98
+ ]
99
+ }
100
+ },
101
+ "contrast": {
102
+ "weight": 1.0,
103
+ "type": "ColorJitter",
104
+ "kwargs": {
105
+ "contrast": [
106
+ 0.8,
107
+ 1.2
108
+ ]
109
+ }
110
+ },
111
+ "sharpness": {
112
+ "weight": 1.0,
113
+ "type": "SharpnessJitter",
114
+ "kwargs": {
115
+ "sharpness": [
116
+ 0.5,
117
+ 1.5
118
+ ]
119
+ }
120
+ },
121
+ "brightness": {
122
+ "weight": 1.0,
123
+ "type": "ColorJitter",
124
+ "kwargs": {
125
+ "brightness": [
126
+ 0.8,
127
+ 1.2
128
+ ]
129
+ }
130
+ },
131
+ "saturation": {
132
+ "weight": 1.0,
133
+ "type": "ColorJitter",
134
+ "kwargs": {
135
+ "saturation": [
136
+ 0.5,
137
+ 1.5
138
+ ]
139
+ }
140
+ }
141
+ }
142
+ },
143
+ "revision": null,
144
+ "use_imagenet_stats": true,
145
+ "video_backend": "torchcodec",
146
+ "vqa_data_path": null
147
+ },
148
+ "env": null,
149
+ "policy": {
150
+ "type": "pi0",
151
+ "n_obs_steps": 1,
152
+ "normalization_mapping": {
153
+ "VISUAL": "IDENTITY",
154
+ "STATE": "MEAN_STD",
155
+ "ACTION": "MEAN_STD"
156
+ },
157
+ "input_features": {
158
+ "observation.images.image": {
159
+ "type": "VISUAL",
160
+ "shape": [
161
+ 3,
162
+ 256,
163
+ 256
164
+ ]
165
+ },
166
+ "observation.images.wrist_image": {
167
+ "type": "VISUAL",
168
+ "shape": [
169
+ 3,
170
+ 256,
171
+ 256
172
+ ]
173
+ },
174
+ "observation.images.image_depth": {
175
+ "type": "VISUAL",
176
+ "shape": [
177
+ 3,
178
+ 256,
179
+ 256
180
+ ]
181
+ },
182
+ "observation.images.wrist_depth": {
183
+ "type": "VISUAL",
184
+ "shape": [
185
+ 3,
186
+ 256,
187
+ 256
188
+ ]
189
+ },
190
+ "observation.images.image_mask": {
191
+ "type": "VISUAL",
192
+ "shape": [
193
+ 3,
194
+ 256,
195
+ 256
196
+ ]
197
+ },
198
+ "observation.images.wrist_mask": {
199
+ "type": "VISUAL",
200
+ "shape": [
201
+ 3,
202
+ 256,
203
+ 256
204
+ ]
205
+ },
206
+ "observation.images.object_of_interest_mask": {
207
+ "type": "VISUAL",
208
+ "shape": [
209
+ 3,
210
+ 256,
211
+ 256
212
+ ]
213
+ },
214
+ "observation.images.object_of_interest_wrist_mask": {
215
+ "type": "VISUAL",
216
+ "shape": [
217
+ 3,
218
+ 256,
219
+ 256
220
+ ]
221
+ },
222
+ "observation.state": {
223
+ "type": "STATE",
224
+ "shape": [
225
+ 8
226
+ ]
227
+ },
228
+ "observation.states.ee_state": {
229
+ "type": "STATE",
230
+ "shape": [
231
+ 6
232
+ ]
233
+ },
234
+ "observation.states.joint_state": {
235
+ "type": "STATE",
236
+ "shape": [
237
+ 7
238
+ ]
239
+ },
240
+ "observation.states.gripper_state": {
241
+ "type": "STATE",
242
+ "shape": [
243
+ 2
244
+ ]
245
+ }
246
+ },
247
+ "output_features": {
248
+ "action": {
249
+ "type": "ACTION",
250
+ "shape": [
251
+ 7
252
+ ]
253
+ }
254
+ },
255
+ "device": "cuda",
256
+ "use_amp": false,
257
+ "gradient_accumulation_steps": 2,
258
+ "chunk_size": 50,
259
+ "n_action_steps": 50,
260
+ "visual_prompt": false,
261
+ "use_both_origin": false,
262
+ "zero_init": false,
263
+ "coordinate_text_prod": false,
264
+ "coordinate_posEmbed_prod": false,
265
+ "posEmbed_to_preTrained": false,
266
+ "num_obs_layers": 30,
267
+ "last_obs_layers": false,
268
+ "add_posEmbed": false,
269
+ "not_used_coord": false,
270
+ "use_depth": false,
271
+ "depth_model_type": "frozen_siglip",
272
+ "use_track": true,
273
+ "track_mask": false,
274
+ "use_slot_att": "none",
275
+ "future_obj": "all",
276
+ "max_state_dim": 32,
277
+ "max_action_dim": 32,
278
+ "resize_imgs_with_padding": [
279
+ 224,
280
+ 224
281
+ ],
282
+ "empty_cameras": 0,
283
+ "adapt_to_pi_aloha": false,
284
+ "use_delta_joint_actions_aloha": false,
285
+ "tokenizer_max_length": 48,
286
+ "proj_width": 1024,
287
+ "num_steps": 10,
288
+ "use_cache": true,
289
+ "attention_implementation": "eager",
290
+ "freeze_vision_encoder": true,
291
+ "train_expert_only": false,
292
+ "train_state_proj": true,
293
+ "optimizer_lr": 0.0001,
294
+ "optimizer_betas": [
295
+ 0.9,
296
+ 0.95
297
+ ],
298
+ "optimizer_eps": 1e-08,
299
+ "optimizer_weight_decay": 1e-10,
300
+ "scheduler_warmup_steps": 1000,
301
+ "scheduler_decay_steps": 240000,
302
+ "scheduler_decay_lr": 2.5e-06
303
+ },
304
+ "output_dir": "outputs/train/2025-11-26/07-49-56_libero_merge_40_scales_use_tracktrue10_maskfalse_future_objtrue_slotnonedualimage_original_batch18",
305
+ "job_name": "libero_merge_40_scales_use_tracktrue10_maskfalse_future_objtrue_slotnonedualimage_original_batch18",
306
+ "visual_prompt": false,
307
+ "use_both_origin": false,
308
+ "zero_init": false,
309
+ "coordinate_text_prod": false,
310
+ "coordinate_posEmbed_prod": false,
311
+ "posEmbed_to_preTrained": false,
312
+ "num_obs_layers": 30,
313
+ "last_obs_layers": false,
314
+ "add_posEmbed": false,
315
+ "not_used_coord": false,
316
+ "train_expert_only": false,
317
+ "use_depth": false,
318
+ "use_track": true,
319
+ "track_mask": false,
320
+ "use_slot_att": "none",
321
+ "future_obj": true,
322
+ "depth_model_type": "frozen_siglip",
323
+ "resume": false,
324
+ "seed": 42,
325
+ "num_workers": 8,
326
+ "batch_size": 18,
327
+ "steps": 100000,
328
+ "eval_freq": 20000,
329
+ "log_freq": 200,
330
+ "save_checkpoint": true,
331
+ "save_freq": 10000,
332
+ "use_policy_training_preset": true,
333
+ "optimizer": {
334
+ "type": "adamw",
335
+ "lr": 0.0001,
336
+ "weight_decay": 1e-10,
337
+ "grad_clip_norm": 10.0,
338
+ "betas": [
339
+ 0.9,
340
+ 0.95
341
+ ],
342
+ "eps": 1e-08
343
+ },
344
+ "scheduler": {
345
+ "type": "cosine_decay_with_warmup",
346
+ "num_warmup_steps": 1000,
347
+ "num_decay_steps": 240000,
348
+ "peak_lr": 0.0001,
349
+ "decay_lr": 2.5e-06
350
+ },
351
+ "eval": {
352
+ "n_episodes": 50,
353
+ "batch_size": 50,
354
+ "use_async_envs": false
355
+ },
356
+ "wandb": {
357
+ "enable": true,
358
+ "disable_artifact": true,
359
+ "project": "pi0_lerobot",
360
+ "entity": "Robotics_VLA",
361
+ "notes": null,
362
+ "run_id": null,
363
+ "mode": "offline"
364
+ }
365
+ }
training_state/optimizer_param_groups.json ADDED
@@ -0,0 +1,854 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.0001,
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
+ 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
+ 500,
520
+ 501,
521
+ 502,
522
+ 503,
523
+ 504,
524
+ 505,
525
+ 506,
526
+ 507,
527
+ 508,
528
+ 509,
529
+ 510,
530
+ 511,
531
+ 512,
532
+ 513,
533
+ 514,
534
+ 515,
535
+ 516,
536
+ 517,
537
+ 518,
538
+ 519,
539
+ 520,
540
+ 521,
541
+ 522,
542
+ 523,
543
+ 524,
544
+ 525,
545
+ 526,
546
+ 527,
547
+ 528,
548
+ 529,
549
+ 530,
550
+ 531,
551
+ 532,
552
+ 533,
553
+ 534,
554
+ 535,
555
+ 536,
556
+ 537,
557
+ 538,
558
+ 539,
559
+ 540,
560
+ 541,
561
+ 542,
562
+ 543,
563
+ 544,
564
+ 545,
565
+ 546,
566
+ 547,
567
+ 548,
568
+ 549,
569
+ 550,
570
+ 551,
571
+ 552,
572
+ 553,
573
+ 554,
574
+ 555,
575
+ 556,
576
+ 557,
577
+ 558,
578
+ 559,
579
+ 560,
580
+ 561,
581
+ 562,
582
+ 563,
583
+ 564,
584
+ 565,
585
+ 566,
586
+ 567,
587
+ 568,
588
+ 569,
589
+ 570,
590
+ 571,
591
+ 572,
592
+ 573,
593
+ 574,
594
+ 575,
595
+ 576,
596
+ 577,
597
+ 578,
598
+ 579,
599
+ 580,
600
+ 581,
601
+ 582,
602
+ 583,
603
+ 584,
604
+ 585,
605
+ 586,
606
+ 587,
607
+ 588,
608
+ 589,
609
+ 590,
610
+ 591,
611
+ 592,
612
+ 593,
613
+ 594,
614
+ 595,
615
+ 596,
616
+ 597,
617
+ 598,
618
+ 599,
619
+ 600,
620
+ 601,
621
+ 602,
622
+ 603,
623
+ 604,
624
+ 605,
625
+ 606,
626
+ 607,
627
+ 608,
628
+ 609,
629
+ 610,
630
+ 611,
631
+ 612,
632
+ 613,
633
+ 614,
634
+ 615,
635
+ 616,
636
+ 617,
637
+ 618,
638
+ 619,
639
+ 620,
640
+ 621,
641
+ 622,
642
+ 623,
643
+ 624,
644
+ 625,
645
+ 626,
646
+ 627,
647
+ 628,
648
+ 629,
649
+ 630,
650
+ 631,
651
+ 632,
652
+ 633,
653
+ 634,
654
+ 635,
655
+ 636,
656
+ 637,
657
+ 638,
658
+ 639,
659
+ 640,
660
+ 641,
661
+ 642,
662
+ 643,
663
+ 644,
664
+ 645,
665
+ 646,
666
+ 647,
667
+ 648,
668
+ 649,
669
+ 650,
670
+ 651,
671
+ 652,
672
+ 653,
673
+ 654,
674
+ 655,
675
+ 656,
676
+ 657,
677
+ 658,
678
+ 659,
679
+ 660,
680
+ 661,
681
+ 662,
682
+ 663,
683
+ 664,
684
+ 665,
685
+ 666,
686
+ 667,
687
+ 668,
688
+ 669,
689
+ 670,
690
+ 671,
691
+ 672,
692
+ 673,
693
+ 674,
694
+ 675,
695
+ 676,
696
+ 677,
697
+ 678,
698
+ 679,
699
+ 680,
700
+ 681,
701
+ 682,
702
+ 683,
703
+ 684,
704
+ 685,
705
+ 686,
706
+ 687,
707
+ 688,
708
+ 689,
709
+ 690,
710
+ 691,
711
+ 692,
712
+ 693,
713
+ 694,
714
+ 695,
715
+ 696,
716
+ 697,
717
+ 698,
718
+ 699,
719
+ 700,
720
+ 701,
721
+ 702,
722
+ 703,
723
+ 704,
724
+ 705,
725
+ 706,
726
+ 707,
727
+ 708,
728
+ 709,
729
+ 710,
730
+ 711,
731
+ 712,
732
+ 713,
733
+ 714,
734
+ 715,
735
+ 716,
736
+ 717,
737
+ 718,
738
+ 719,
739
+ 720,
740
+ 721,
741
+ 722,
742
+ 723,
743
+ 724,
744
+ 725,
745
+ 726,
746
+ 727,
747
+ 728,
748
+ 729,
749
+ 730,
750
+ 731,
751
+ 732,
752
+ 733,
753
+ 734,
754
+ 735,
755
+ 736,
756
+ 737,
757
+ 738,
758
+ 739,
759
+ 740,
760
+ 741,
761
+ 742,
762
+ 743,
763
+ 744,
764
+ 745,
765
+ 746,
766
+ 747,
767
+ 748,
768
+ 749,
769
+ 750,
770
+ 751,
771
+ 752,
772
+ 753,
773
+ 754,
774
+ 755,
775
+ 756,
776
+ 757,
777
+ 758,
778
+ 759,
779
+ 760,
780
+ 761,
781
+ 762,
782
+ 763,
783
+ 764,
784
+ 765,
785
+ 766,
786
+ 767,
787
+ 768,
788
+ 769,
789
+ 770,
790
+ 771,
791
+ 772,
792
+ 773,
793
+ 774,
794
+ 775,
795
+ 776,
796
+ 777,
797
+ 778,
798
+ 779,
799
+ 780,
800
+ 781,
801
+ 782,
802
+ 783,
803
+ 784,
804
+ 785,
805
+ 786,
806
+ 787,
807
+ 788,
808
+ 789,
809
+ 790,
810
+ 791,
811
+ 792,
812
+ 793,
813
+ 794,
814
+ 795,
815
+ 796,
816
+ 797,
817
+ 798,
818
+ 799,
819
+ 800,
820
+ 801,
821
+ 802,
822
+ 803,
823
+ 804,
824
+ 805,
825
+ 806,
826
+ 807,
827
+ 808,
828
+ 809,
829
+ 810,
830
+ 811,
831
+ 812,
832
+ 813,
833
+ 814,
834
+ 815,
835
+ 816,
836
+ 817,
837
+ 818,
838
+ 819,
839
+ 820,
840
+ 821,
841
+ 822,
842
+ 823,
843
+ 824,
844
+ 825,
845
+ 826,
846
+ 827,
847
+ 828,
848
+ 829,
849
+ 830,
850
+ 831,
851
+ 832
852
+ ]
853
+ }
854
+ ]
training_state/optimizer_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff95e0e3e92078d6d6573a7854a9246b1b236d8bb2342cc40daab41ddec9632a
3
+ size 11744935524
training_state/rng_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8bccb16bc4c612ac69941a06039465333c475278dd8d0939a8794ae849b4abe3
3
+ size 15708
training_state/scheduler_state.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "base_lrs": [
3
+ 0.0001
4
+ ],
5
+ "last_epoch": 240000,
6
+ "_step_count": 240001,
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
+ }
training_state/training_step.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "step": 60000
3
+ }