Robotics
LeRobot
Safetensors
diffusion
SieloRobotics commited on
Commit
7c92eb6
·
verified ·
1 Parent(s): 1896b4d

checkpoint 025000

Browse files
checkpoints/025000/pretrained_model/config.json ADDED
@@ -0,0 +1,130 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "type": "diffusion",
3
+ "n_obs_steps": 2,
4
+ "input_features": {
5
+ "observation.state": {
6
+ "type": "STATE",
7
+ "shape": [
8
+ 19
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.ee_pose": {
28
+ "type": "STATE",
29
+ "shape": [
30
+ 10
31
+ ]
32
+ },
33
+ "observation.ee_state": {
34
+ "type": "STATE",
35
+ "shape": [
36
+ 19
37
+ ]
38
+ },
39
+ "observation.joints": {
40
+ "type": "STATE",
41
+ "shape": [
42
+ 7
43
+ ]
44
+ }
45
+ },
46
+ "output_features": {
47
+ "action": {
48
+ "type": "ACTION",
49
+ "shape": [
50
+ 160
51
+ ]
52
+ },
53
+ "action.ee_pose": {
54
+ "type": "ACTION",
55
+ "shape": [
56
+ 10
57
+ ]
58
+ },
59
+ "action.joints": {
60
+ "type": "ACTION",
61
+ "shape": [
62
+ 7
63
+ ]
64
+ }
65
+ },
66
+ "device": "cuda",
67
+ "use_amp": false,
68
+ "use_peft": false,
69
+ "push_to_hub": true,
70
+ "repo_id": "SieloRobotics/Diffusion_ee_chunk_bottle",
71
+ "private": null,
72
+ "tags": null,
73
+ "license": null,
74
+ "pretrained_path": null,
75
+ "pretrained_revision": null,
76
+ "horizon": 8,
77
+ "n_action_steps": 1,
78
+ "normalization_mapping": {
79
+ "VISUAL": "MEAN_STD",
80
+ "STATE": "MIN_MAX",
81
+ "ACTION": "MIN_MAX"
82
+ },
83
+ "drop_n_last_frames": 22,
84
+ "vision_backbone": "resnet18",
85
+ "resize_shape": [
86
+ 240,
87
+ 320
88
+ ],
89
+ "crop_ratio": 0.95,
90
+ "crop_shape": [
91
+ 228,
92
+ 304
93
+ ],
94
+ "crop_is_random": true,
95
+ "pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
96
+ "use_group_norm": false,
97
+ "spatial_softmax_num_keypoints": 32,
98
+ "use_separate_rgb_encoder_per_camera": true,
99
+ "down_dims": [
100
+ 512,
101
+ 1024,
102
+ 2048
103
+ ],
104
+ "kernel_size": 5,
105
+ "n_groups": 8,
106
+ "diffusion_step_embed_dim": 128,
107
+ "use_film_scale_modulation": true,
108
+ "gradient_checkpointing": false,
109
+ "noise_scheduler_type": "DDPM",
110
+ "num_train_timesteps": 100,
111
+ "beta_schedule": "squaredcos_cap_v2",
112
+ "beta_start": 0.0001,
113
+ "beta_end": 0.02,
114
+ "prediction_type": "epsilon",
115
+ "clip_sample": true,
116
+ "clip_sample_range": 1.5,
117
+ "num_inference_steps": null,
118
+ "compile_model": true,
119
+ "compile_mode": "reduce-overhead",
120
+ "do_mask_loss_for_padding": false,
121
+ "optimizer_lr": 0.0002,
122
+ "optimizer_betas": [
123
+ 0.95,
124
+ 0.999
125
+ ],
126
+ "optimizer_eps": 1e-08,
127
+ "optimizer_weight_decay": 1e-06,
128
+ "scheduler_name": "cosine",
129
+ "scheduler_warmup_steps": 500
130
+ }
checkpoints/025000/pretrained_model/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8463915a14f5a833e432f1ad25cfb2be53829fa233443396ec886008725ae06e
3
+ size 1116596856
checkpoints/025000/pretrained_model/policy_postprocessor.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ 160
13
+ ]
14
+ },
15
+ "action.ee_pose": {
16
+ "type": "ACTION",
17
+ "shape": [
18
+ 10
19
+ ]
20
+ },
21
+ "action.joints": {
22
+ "type": "ACTION",
23
+ "shape": [
24
+ 7
25
+ ]
26
+ }
27
+ },
28
+ "norm_map": {
29
+ "VISUAL": "MEAN_STD",
30
+ "STATE": "MIN_MAX",
31
+ "ACTION": "MIN_MAX"
32
+ }
33
+ },
34
+ "state_file": "policy_postprocessor_step_0_unnormalizer_processor.safetensors"
35
+ },
36
+ {
37
+ "registry_name": "device_processor",
38
+ "config": {
39
+ "device": "cpu",
40
+ "float_dtype": null
41
+ }
42
+ }
43
+ ]
44
+ }
checkpoints/025000/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 sha256:20fdb48bbc100c5923254b547f08f85ceb0d70247c98d189fa126fdd16b06e15
3
+ size 22652
checkpoints/025000/pretrained_model/policy_preprocessor.json ADDED
@@ -0,0 +1,94 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "device_processor",
16
+ "config": {
17
+ "device": "cuda",
18
+ "float_dtype": null
19
+ }
20
+ },
21
+ {
22
+ "registry_name": "normalizer_processor",
23
+ "config": {
24
+ "eps": 1e-08,
25
+ "features": {
26
+ "observation.state": {
27
+ "type": "STATE",
28
+ "shape": [
29
+ 19
30
+ ]
31
+ },
32
+ "observation.images.top": {
33
+ "type": "VISUAL",
34
+ "shape": [
35
+ 3,
36
+ 480,
37
+ 640
38
+ ]
39
+ },
40
+ "observation.images.wrist": {
41
+ "type": "VISUAL",
42
+ "shape": [
43
+ 3,
44
+ 480,
45
+ 640
46
+ ]
47
+ },
48
+ "observation.ee_pose": {
49
+ "type": "STATE",
50
+ "shape": [
51
+ 10
52
+ ]
53
+ },
54
+ "observation.ee_state": {
55
+ "type": "STATE",
56
+ "shape": [
57
+ 19
58
+ ]
59
+ },
60
+ "observation.joints": {
61
+ "type": "STATE",
62
+ "shape": [
63
+ 7
64
+ ]
65
+ },
66
+ "action": {
67
+ "type": "ACTION",
68
+ "shape": [
69
+ 160
70
+ ]
71
+ },
72
+ "action.ee_pose": {
73
+ "type": "ACTION",
74
+ "shape": [
75
+ 10
76
+ ]
77
+ },
78
+ "action.joints": {
79
+ "type": "ACTION",
80
+ "shape": [
81
+ 7
82
+ ]
83
+ }
84
+ },
85
+ "norm_map": {
86
+ "VISUAL": "MEAN_STD",
87
+ "STATE": "MIN_MAX",
88
+ "ACTION": "MIN_MAX"
89
+ }
90
+ },
91
+ "state_file": "policy_preprocessor_step_3_normalizer_processor.safetensors"
92
+ }
93
+ ]
94
+ }
checkpoints/025000/pretrained_model/policy_preprocessor_step_3_normalizer_processor.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b76e3e1d9ae699337b6c8f7786c999b28d8dcac5bd324a7e24426a846376e822
3
+ size 22660
checkpoints/025000/pretrained_model/train_config.json ADDED
@@ -0,0 +1,444 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset": {
3
+ "repo_id": "SieloRobotics/ee_chunk",
4
+ "repo_type": "dataset",
5
+ "root": null,
6
+ "episodes": [
7
+ 15,
8
+ 16,
9
+ 17,
10
+ 18,
11
+ 19,
12
+ 20,
13
+ 21,
14
+ 22,
15
+ 23,
16
+ 29,
17
+ 30,
18
+ 31,
19
+ 32,
20
+ 33,
21
+ 34,
22
+ 38,
23
+ 39,
24
+ 42,
25
+ 64,
26
+ 65,
27
+ 66,
28
+ 67,
29
+ 68,
30
+ 69,
31
+ 70,
32
+ 71,
33
+ 72,
34
+ 77,
35
+ 78,
36
+ 79,
37
+ 80,
38
+ 81,
39
+ 82,
40
+ 83,
41
+ 102,
42
+ 103,
43
+ 104,
44
+ 105,
45
+ 106,
46
+ 107,
47
+ 108,
48
+ 109,
49
+ 110,
50
+ 112,
51
+ 113,
52
+ 118,
53
+ 119,
54
+ 120,
55
+ 121,
56
+ 122,
57
+ 123,
58
+ 126,
59
+ 128,
60
+ 129,
61
+ 153,
62
+ 154,
63
+ 155,
64
+ 156,
65
+ 157,
66
+ 158,
67
+ 160,
68
+ 166,
69
+ 167,
70
+ 168,
71
+ 169,
72
+ 170,
73
+ 171,
74
+ 179,
75
+ 181,
76
+ 183,
77
+ 189,
78
+ 191,
79
+ 193,
80
+ 194,
81
+ 199,
82
+ 201,
83
+ 203,
84
+ 206,
85
+ 212,
86
+ 214,
87
+ 220,
88
+ 221,
89
+ 223,
90
+ 229,
91
+ 230,
92
+ 231,
93
+ 232,
94
+ 234,
95
+ 235,
96
+ 236,
97
+ 237,
98
+ 239,
99
+ 243,
100
+ 247,
101
+ 253,
102
+ 254,
103
+ 259,
104
+ 260,
105
+ 261,
106
+ 262,
107
+ 266,
108
+ 267,
109
+ 268,
110
+ 269,
111
+ 270,
112
+ 280,
113
+ 285,
114
+ 287,
115
+ 288,
116
+ 293,
117
+ 296,
118
+ 301
119
+ ],
120
+ "exclude_episodes": null,
121
+ "image_transforms": {
122
+ "enable": false,
123
+ "max_num_transforms": 3,
124
+ "random_order": false,
125
+ "tfs": {
126
+ "brightness": {
127
+ "weight": 1.0,
128
+ "type": "ColorJitter",
129
+ "kwargs": {
130
+ "brightness": [
131
+ 0.8,
132
+ 1.2
133
+ ]
134
+ }
135
+ },
136
+ "contrast": {
137
+ "weight": 1.0,
138
+ "type": "ColorJitter",
139
+ "kwargs": {
140
+ "contrast": [
141
+ 0.8,
142
+ 1.2
143
+ ]
144
+ }
145
+ },
146
+ "saturation": {
147
+ "weight": 1.0,
148
+ "type": "ColorJitter",
149
+ "kwargs": {
150
+ "saturation": [
151
+ 0.5,
152
+ 1.5
153
+ ]
154
+ }
155
+ },
156
+ "hue": {
157
+ "weight": 1.0,
158
+ "type": "ColorJitter",
159
+ "kwargs": {
160
+ "hue": [
161
+ -0.05,
162
+ 0.05
163
+ ]
164
+ }
165
+ },
166
+ "sharpness": {
167
+ "weight": 1.0,
168
+ "type": "SharpnessJitter",
169
+ "kwargs": {
170
+ "sharpness": [
171
+ 0.5,
172
+ 1.5
173
+ ]
174
+ }
175
+ },
176
+ "affine": {
177
+ "weight": 1.0,
178
+ "type": "RandomAffine",
179
+ "kwargs": {
180
+ "degrees": [
181
+ -5.0,
182
+ 5.0
183
+ ],
184
+ "translate": [
185
+ 0.05,
186
+ 0.05
187
+ ]
188
+ }
189
+ }
190
+ }
191
+ },
192
+ "revision": "main",
193
+ "use_imagenet_stats": true,
194
+ "video_backend": "torchcodec",
195
+ "return_uint8": false,
196
+ "depth_output_unit": "mm",
197
+ "streaming": false,
198
+ "eval_split": 0.1
199
+ },
200
+ "env": null,
201
+ "policy": {
202
+ "type": "diffusion",
203
+ "n_obs_steps": 2,
204
+ "input_features": {
205
+ "observation.state": {
206
+ "type": "STATE",
207
+ "shape": [
208
+ 19
209
+ ]
210
+ },
211
+ "observation.images.top": {
212
+ "type": "VISUAL",
213
+ "shape": [
214
+ 3,
215
+ 480,
216
+ 640
217
+ ]
218
+ },
219
+ "observation.images.wrist": {
220
+ "type": "VISUAL",
221
+ "shape": [
222
+ 3,
223
+ 480,
224
+ 640
225
+ ]
226
+ },
227
+ "observation.ee_pose": {
228
+ "type": "STATE",
229
+ "shape": [
230
+ 10
231
+ ]
232
+ },
233
+ "observation.ee_state": {
234
+ "type": "STATE",
235
+ "shape": [
236
+ 19
237
+ ]
238
+ },
239
+ "observation.joints": {
240
+ "type": "STATE",
241
+ "shape": [
242
+ 7
243
+ ]
244
+ }
245
+ },
246
+ "output_features": {
247
+ "action": {
248
+ "type": "ACTION",
249
+ "shape": [
250
+ 160
251
+ ]
252
+ },
253
+ "action.ee_pose": {
254
+ "type": "ACTION",
255
+ "shape": [
256
+ 10
257
+ ]
258
+ },
259
+ "action.joints": {
260
+ "type": "ACTION",
261
+ "shape": [
262
+ 7
263
+ ]
264
+ }
265
+ },
266
+ "device": "cuda",
267
+ "use_amp": false,
268
+ "use_peft": false,
269
+ "push_to_hub": true,
270
+ "repo_id": "SieloRobotics/Diffusion_ee_chunk_bottle",
271
+ "private": null,
272
+ "tags": null,
273
+ "license": null,
274
+ "pretrained_path": null,
275
+ "pretrained_revision": null,
276
+ "horizon": 8,
277
+ "n_action_steps": 1,
278
+ "normalization_mapping": {
279
+ "VISUAL": "MEAN_STD",
280
+ "STATE": "MIN_MAX",
281
+ "ACTION": "MIN_MAX"
282
+ },
283
+ "drop_n_last_frames": 22,
284
+ "vision_backbone": "resnet18",
285
+ "resize_shape": [
286
+ 240,
287
+ 320
288
+ ],
289
+ "crop_ratio": 0.95,
290
+ "crop_shape": [
291
+ 228,
292
+ 304
293
+ ],
294
+ "crop_is_random": true,
295
+ "pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
296
+ "use_group_norm": false,
297
+ "spatial_softmax_num_keypoints": 32,
298
+ "use_separate_rgb_encoder_per_camera": true,
299
+ "down_dims": [
300
+ 512,
301
+ 1024,
302
+ 2048
303
+ ],
304
+ "kernel_size": 5,
305
+ "n_groups": 8,
306
+ "diffusion_step_embed_dim": 128,
307
+ "use_film_scale_modulation": true,
308
+ "gradient_checkpointing": false,
309
+ "noise_scheduler_type": "DDPM",
310
+ "num_train_timesteps": 100,
311
+ "beta_schedule": "squaredcos_cap_v2",
312
+ "beta_start": 0.0001,
313
+ "beta_end": 0.02,
314
+ "prediction_type": "epsilon",
315
+ "clip_sample": true,
316
+ "clip_sample_range": 1.5,
317
+ "num_inference_steps": null,
318
+ "compile_model": true,
319
+ "compile_mode": "reduce-overhead",
320
+ "do_mask_loss_for_padding": false,
321
+ "optimizer_lr": 0.0002,
322
+ "optimizer_betas": [
323
+ 0.95,
324
+ 0.999
325
+ ],
326
+ "optimizer_eps": 1e-08,
327
+ "optimizer_weight_decay": 1e-06,
328
+ "scheduler_name": "cosine",
329
+ "scheduler_warmup_steps": 500
330
+ },
331
+ "reward_model": null,
332
+ "output_dir": "outputs/train/dp_ee_chunk_bottle",
333
+ "job_name": "dp_ee_chunk_bottle",
334
+ "resume": false,
335
+ "seed": 1000,
336
+ "cudnn_deterministic": false,
337
+ "num_workers": 8,
338
+ "batch_size": 256,
339
+ "prefetch_factor": 4,
340
+ "persistent_workers": true,
341
+ "dataloader_multiprocessing_context": "spawn",
342
+ "steps": 25000,
343
+ "env_eval_freq": 20000,
344
+ "log_freq": 200,
345
+ "eval_steps": 2000,
346
+ "max_eval_samples": 2000,
347
+ "tolerance_s": 0.0001,
348
+ "save_checkpoint": true,
349
+ "save_freq": 2500,
350
+ "checkpoint_format": "safetensors",
351
+ "use_policy_training_preset": true,
352
+ "optimizer": {
353
+ "type": "adam",
354
+ "lr": 0.0002,
355
+ "weight_decay": 1e-06,
356
+ "grad_clip_norm": 10.0,
357
+ "betas": [
358
+ 0.95,
359
+ 0.999
360
+ ],
361
+ "eps": 1e-08
362
+ },
363
+ "scheduler": {
364
+ "type": "diffuser",
365
+ "num_warmup_steps": 500,
366
+ "name": "cosine"
367
+ },
368
+ "parallelism": {
369
+ "dp_replicate": 1,
370
+ "dp_shard": 1,
371
+ "context_parallel": {
372
+ "ring_degree": 1,
373
+ "ulysses_degree": 1
374
+ },
375
+ "cfg_parallel": 1
376
+ },
377
+ "accelerator": {
378
+ "mixed_precision": "no",
379
+ "gradient_accumulation": {
380
+ "steps": 1
381
+ },
382
+ "fsdp": {
383
+ "reshard_after_forward": true,
384
+ "wrap_modules": null,
385
+ "min_num_params": null,
386
+ "cpu_offload": false,
387
+ "ignored_modules": null
388
+ },
389
+ "ddp": {
390
+ "find_unused_parameters": true,
391
+ "gradient_as_bucket_view": false,
392
+ "static_graph": false
393
+ },
394
+ "compile": {
395
+ "enabled": false,
396
+ "backend": "inductor",
397
+ "mode": null,
398
+ "regional": true
399
+ },
400
+ "activation_checkpointing": {
401
+ "mode": "none"
402
+ }
403
+ },
404
+ "eval": {
405
+ "n_episodes": 50,
406
+ "batch_size": 8,
407
+ "use_async_envs": true,
408
+ "recording": false,
409
+ "recording_repo_id": null,
410
+ "recording_private": false
411
+ },
412
+ "ema": {
413
+ "enable": false,
414
+ "decay": null,
415
+ "update_after_step": 0,
416
+ "inv_gamma": 1.0,
417
+ "power": 0.75,
418
+ "min_decay": 0.0,
419
+ "max_decay": 0.9999,
420
+ "use_for_eval": true
421
+ },
422
+ "wandb": {
423
+ "enable": true,
424
+ "disable_artifact": false,
425
+ "project": "arlo_ee_chunk",
426
+ "entity": null,
427
+ "notes": "relative-EE 160-D chunk action, grey-bottle task, 10% held out",
428
+ "run_id": "kkmm1741",
429
+ "mode": null,
430
+ "add_tags": true
431
+ },
432
+ "peft": null,
433
+ "job": {
434
+ "target": null,
435
+ "image": "huggingface/lerobot-gpu:latest",
436
+ "timeout": "2d",
437
+ "detach": false,
438
+ "tags": []
439
+ },
440
+ "save_checkpoint_to_hub": true,
441
+ "sample_weighting": null,
442
+ "rename_map": {},
443
+ "checkpoint_path": null
444
+ }
checkpoints/025000/training_state/optimizer_param_groups.json ADDED
@@ -0,0 +1,297 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "lr": 0.0,
4
+ "betas": [
5
+ 0.95,
6
+ 0.999
7
+ ],
8
+ "eps": 1e-08,
9
+ "weight_decay": 1e-06,
10
+ "amsgrad": false,
11
+ "maximize": false,
12
+ "foreach": null,
13
+ "capturable": false,
14
+ "differentiable": false,
15
+ "fused": null,
16
+ "decoupled_weight_decay": false,
17
+ "initial_lr": 0.0002,
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
+ ]
296
+ }
297
+ ]
checkpoints/025000/training_state/optimizer_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f712aef2599613311699b7831926f1d85884d94a1a4b16c9486d916d0080b1d7
3
+ size 2233013120
checkpoints/025000/training_state/rng_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ae0854f1a778fa674b3e472cbe50cb6699902caba89534d52103c27ee4d101b
3
+ size 15708
checkpoints/025000/training_state/scheduler_state.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "base_lrs": [
3
+ 0.0002
4
+ ],
5
+ "last_epoch": 25000,
6
+ "_step_count": 25001,
7
+ "_is_initial": false,
8
+ "_get_lr_called_within_step": false,
9
+ "_last_lr": [
10
+ 0.0
11
+ ],
12
+ "lr_lambdas": [
13
+ null
14
+ ]
15
+ }
checkpoints/025000/training_state/training_step.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "step": 25000,
3
+ "dp_world_size": 1,
4
+ "batch_size": 256,
5
+ "grad_accum_steps": 1,
6
+ "parallelism": {
7
+ "dp_replicate": 1,
8
+ "dp_shard": 1,
9
+ "ring_degree": 1,
10
+ "ulysses_degree": 1
11
+ }
12
+ }