LegrandFrederic commited on
Commit
6a253f9
·
verified ·
1 Parent(s): 3c52539

Upload trainer_state.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. trainer_state.json +616 -0
trainer_state.json ADDED
@@ -0,0 +1,616 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 9.903614457831326,
5
+ "eval_steps": 500,
6
+ "global_step": 822,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.12048192771084337,
13
+ "grad_norm": 2.6048758029937744,
14
+ "learning_rate": 4.761904761904762e-05,
15
+ "loss": 1.2322,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.24096385542168675,
20
+ "grad_norm": 2.073004722595215,
21
+ "learning_rate": 9.523809523809524e-05,
22
+ "loss": 0.4195,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.3614457831325301,
27
+ "grad_norm": 1.133252501487732,
28
+ "learning_rate": 0.00014285714285714287,
29
+ "loss": 0.1977,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.4819277108433735,
34
+ "grad_norm": 0.7059364914894104,
35
+ "learning_rate": 0.00019047619047619048,
36
+ "loss": 0.1374,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.6024096385542169,
41
+ "grad_norm": 0.7211808562278748,
42
+ "learning_rate": 0.0001999480933568615,
43
+ "loss": 0.1198,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.7228915662650602,
48
+ "grad_norm": 0.5436549782752991,
49
+ "learning_rate": 0.00019973731496914914,
50
+ "loss": 0.0994,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.8433734939759037,
55
+ "grad_norm": 0.612585186958313,
56
+ "learning_rate": 0.00019936476229183133,
57
+ "loss": 0.096,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.963855421686747,
62
+ "grad_norm": 0.6169544458389282,
63
+ "learning_rate": 0.00019883103960671305,
64
+ "loss": 0.086,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 1.0843373493975903,
69
+ "grad_norm": 0.5241321921348572,
70
+ "learning_rate": 0.00019813701261394136,
71
+ "loss": 0.0838,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 1.2048192771084336,
76
+ "grad_norm": 0.3530048429965973,
77
+ "learning_rate": 0.00019728380702783643,
78
+ "loss": 0.0685,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 1.3253012048192772,
83
+ "grad_norm": 0.4779577851295471,
84
+ "learning_rate": 0.00019627280675097908,
85
+ "loss": 0.0667,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 1.4457831325301205,
90
+ "grad_norm": 0.7595181465148926,
91
+ "learning_rate": 0.00019510565162951537,
92
+ "loss": 0.0626,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 1.5662650602409638,
97
+ "grad_norm": 0.4125242531299591,
98
+ "learning_rate": 0.00019378423479332046,
99
+ "loss": 0.0563,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 1.6867469879518073,
104
+ "grad_norm": 0.3203200697898865,
105
+ "learning_rate": 0.0001923106995853349,
106
+ "loss": 0.0621,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 1.8072289156626506,
111
+ "grad_norm": 0.3810570240020752,
112
+ "learning_rate": 0.00019068743608505455,
113
+ "loss": 0.0582,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 1.927710843373494,
118
+ "grad_norm": 0.2916155457496643,
119
+ "learning_rate": 0.00018891707723181294,
120
+ "loss": 0.0598,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 2.0481927710843375,
125
+ "grad_norm": 0.5267001986503601,
126
+ "learning_rate": 0.00018700249455414394,
127
+ "loss": 0.0541,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 2.1686746987951806,
132
+ "grad_norm": 0.33983558416366577,
133
+ "learning_rate": 0.0001849467935121521,
134
+ "loss": 0.0524,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 2.289156626506024,
139
+ "grad_norm": 0.36935296654701233,
140
+ "learning_rate": 0.000182753308460445,
141
+ "loss": 0.0526,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 2.4096385542168672,
146
+ "grad_norm": 0.4720439016819,
147
+ "learning_rate": 0.0001804255972397977,
148
+ "loss": 0.0478,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 2.5301204819277108,
153
+ "grad_norm": 0.572353720664978,
154
+ "learning_rate": 0.00017796743540632223,
155
+ "loss": 0.0504,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 2.6506024096385543,
160
+ "grad_norm": 0.35790249705314636,
161
+ "learning_rate": 0.0001753828101075017,
162
+ "loss": 0.0476,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 2.7710843373493974,
167
+ "grad_norm": 0.3537259101867676,
168
+ "learning_rate": 0.00017267591361502232,
169
+ "loss": 0.0456,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 2.891566265060241,
174
+ "grad_norm": 0.34377923607826233,
175
+ "learning_rate": 0.00016985113652489374,
176
+ "loss": 0.0473,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 3.0120481927710845,
181
+ "grad_norm": 0.32719871401786804,
182
+ "learning_rate": 0.00016691306063588583,
183
+ "loss": 0.046,
184
+ "step": 250
185
+ },
186
+ {
187
+ "epoch": 3.1325301204819276,
188
+ "grad_norm": 0.30426010489463806,
189
+ "learning_rate": 0.0001638664515178348,
190
+ "loss": 0.045,
191
+ "step": 260
192
+ },
193
+ {
194
+ "epoch": 3.253012048192771,
195
+ "grad_norm": 0.4393266439437866,
196
+ "learning_rate": 0.00016071625078187114,
197
+ "loss": 0.0407,
198
+ "step": 270
199
+ },
200
+ {
201
+ "epoch": 3.3734939759036147,
202
+ "grad_norm": 0.48441895842552185,
203
+ "learning_rate": 0.00015746756806510838,
204
+ "loss": 0.0403,
205
+ "step": 280
206
+ },
207
+ {
208
+ "epoch": 3.4939759036144578,
209
+ "grad_norm": 0.2893245220184326,
210
+ "learning_rate": 0.00015412567274279316,
211
+ "loss": 0.039,
212
+ "step": 290
213
+ },
214
+ {
215
+ "epoch": 3.6144578313253013,
216
+ "grad_norm": 0.33335432410240173,
217
+ "learning_rate": 0.00015069598538135906,
218
+ "loss": 0.0374,
219
+ "step": 300
220
+ },
221
+ {
222
+ "epoch": 3.734939759036145,
223
+ "grad_norm": 0.36576047539711,
224
+ "learning_rate": 0.0001471840689462482,
225
+ "loss": 0.0424,
226
+ "step": 310
227
+ },
228
+ {
229
+ "epoch": 3.855421686746988,
230
+ "grad_norm": 0.2801503539085388,
231
+ "learning_rate": 0.00014359561977876102,
232
+ "loss": 0.0332,
233
+ "step": 320
234
+ },
235
+ {
236
+ "epoch": 3.9759036144578315,
237
+ "grad_norm": 0.29735037684440613,
238
+ "learning_rate": 0.00013993645835656953,
239
+ "loss": 0.0355,
240
+ "step": 330
241
+ },
242
+ {
243
+ "epoch": 4.096385542168675,
244
+ "grad_norm": 0.43135517835617065,
245
+ "learning_rate": 0.0001362125198528817,
246
+ "loss": 0.0442,
247
+ "step": 340
248
+ },
249
+ {
250
+ "epoch": 4.216867469879518,
251
+ "grad_norm": 0.38527563214302063,
252
+ "learning_rate": 0.00013242984450956828,
253
+ "loss": 0.0356,
254
+ "step": 350
255
+ },
256
+ {
257
+ "epoch": 4.337349397590361,
258
+ "grad_norm": 0.3635711073875427,
259
+ "learning_rate": 0.00012859456783986893,
260
+ "loss": 0.041,
261
+ "step": 360
262
+ },
263
+ {
264
+ "epoch": 4.457831325301205,
265
+ "grad_norm": 0.2927173972129822,
266
+ "learning_rate": 0.00012471291067656697,
267
+ "loss": 0.034,
268
+ "step": 370
269
+ },
270
+ {
271
+ "epoch": 4.578313253012048,
272
+ "grad_norm": 0.407322496175766,
273
+ "learning_rate": 0.00012079116908177593,
274
+ "loss": 0.0327,
275
+ "step": 380
276
+ },
277
+ {
278
+ "epoch": 4.698795180722891,
279
+ "grad_norm": 0.33329063653945923,
280
+ "learning_rate": 0.00011683570413470383,
281
+ "loss": 0.0339,
282
+ "step": 390
283
+ },
284
+ {
285
+ "epoch": 4.8192771084337345,
286
+ "grad_norm": 0.2710469663143158,
287
+ "learning_rate": 0.00011285293161395946,
288
+ "loss": 0.0299,
289
+ "step": 400
290
+ },
291
+ {
292
+ "epoch": 4.9397590361445785,
293
+ "grad_norm": 0.308614045381546,
294
+ "learning_rate": 0.00010884931159113586,
295
+ "loss": 0.0386,
296
+ "step": 410
297
+ },
298
+ {
299
+ "epoch": 5.0602409638554215,
300
+ "grad_norm": 0.3434526324272156,
301
+ "learning_rate": 0.00010483133795255071,
302
+ "loss": 0.0367,
303
+ "step": 420
304
+ },
305
+ {
306
+ "epoch": 5.180722891566265,
307
+ "grad_norm": 0.3069072961807251,
308
+ "learning_rate": 0.00010080552786613899,
309
+ "loss": 0.0356,
310
+ "step": 430
311
+ },
312
+ {
313
+ "epoch": 5.301204819277109,
314
+ "grad_norm": 0.2935517430305481,
315
+ "learning_rate": 9.677841121058273e-05,
316
+ "loss": 0.0304,
317
+ "step": 440
318
+ },
319
+ {
320
+ "epoch": 5.421686746987952,
321
+ "grad_norm": 0.3041512072086334,
322
+ "learning_rate": 9.275651998382377e-05,
323
+ "loss": 0.0289,
324
+ "step": 450
325
+ },
326
+ {
327
+ "epoch": 5.542168674698795,
328
+ "grad_norm": 0.30504339933395386,
329
+ "learning_rate": 8.874637770813946e-05,
330
+ "loss": 0.0302,
331
+ "step": 460
332
+ },
333
+ {
334
+ "epoch": 5.662650602409639,
335
+ "grad_norm": 0.20522096753120422,
336
+ "learning_rate": 8.475448884896547e-05,
337
+ "loss": 0.029,
338
+ "step": 470
339
+ },
340
+ {
341
+ "epoch": 5.783132530120482,
342
+ "grad_norm": 0.2943919897079468,
343
+ "learning_rate": 8.078732826462915e-05,
344
+ "loss": 0.0288,
345
+ "step": 480
346
+ },
347
+ {
348
+ "epoch": 5.903614457831325,
349
+ "grad_norm": 0.328308641910553,
350
+ "learning_rate": 7.685133070410571e-05,
351
+ "loss": 0.0237,
352
+ "step": 490
353
+ },
354
+ {
355
+ "epoch": 6.024096385542169,
356
+ "grad_norm": 0.425624281167984,
357
+ "learning_rate": 7.295288036983163e-05,
358
+ "loss": 0.0303,
359
+ "step": 500
360
+ },
361
+ {
362
+ "epoch": 6.144578313253012,
363
+ "grad_norm": 0.2587184011936188,
364
+ "learning_rate": 6.909830056250527e-05,
365
+ "loss": 0.0246,
366
+ "step": 510
367
+ },
368
+ {
369
+ "epoch": 6.265060240963855,
370
+ "grad_norm": 0.35053542256355286,
371
+ "learning_rate": 6.52938434246697e-05,
372
+ "loss": 0.0273,
373
+ "step": 520
374
+ },
375
+ {
376
+ "epoch": 6.385542168674699,
377
+ "grad_norm": 0.2893577516078949,
378
+ "learning_rate": 6.154567979971493e-05,
379
+ "loss": 0.026,
380
+ "step": 530
381
+ },
382
+ {
383
+ "epoch": 6.506024096385542,
384
+ "grad_norm": 0.22769379615783691,
385
+ "learning_rate": 5.785988922274711e-05,
386
+ "loss": 0.029,
387
+ "step": 540
388
+ },
389
+ {
390
+ "epoch": 6.626506024096385,
391
+ "grad_norm": 0.3005225956439972,
392
+ "learning_rate": 5.424245005956048e-05,
393
+ "loss": 0.0246,
394
+ "step": 550
395
+ },
396
+ {
397
+ "epoch": 6.746987951807229,
398
+ "grad_norm": 0.2721225321292877,
399
+ "learning_rate": 5.069922980970626e-05,
400
+ "loss": 0.0256,
401
+ "step": 560
402
+ },
403
+ {
404
+ "epoch": 6.867469879518072,
405
+ "grad_norm": 0.23859107494354248,
406
+ "learning_rate": 4.723597558938672e-05,
407
+ "loss": 0.0295,
408
+ "step": 570
409
+ },
410
+ {
411
+ "epoch": 6.9879518072289155,
412
+ "grad_norm": 0.2128613144159317,
413
+ "learning_rate": 4.385830480961192e-05,
414
+ "loss": 0.0271,
415
+ "step": 580
416
+ },
417
+ {
418
+ "epoch": 7.108433734939759,
419
+ "grad_norm": 0.15234726667404175,
420
+ "learning_rate": 4.057169606473827e-05,
421
+ "loss": 0.0209,
422
+ "step": 590
423
+ },
424
+ {
425
+ "epoch": 7.228915662650603,
426
+ "grad_norm": 0.1998305469751358,
427
+ "learning_rate": 3.738148024616863e-05,
428
+ "loss": 0.0236,
429
+ "step": 600
430
+ },
431
+ {
432
+ "epoch": 7.349397590361446,
433
+ "grad_norm": 0.16628368198871613,
434
+ "learning_rate": 3.429283189562694e-05,
435
+ "loss": 0.022,
436
+ "step": 610
437
+ },
438
+ {
439
+ "epoch": 7.469879518072289,
440
+ "grad_norm": 0.22349688410758972,
441
+ "learning_rate": 3.131076081203247e-05,
442
+ "loss": 0.0218,
443
+ "step": 620
444
+ },
445
+ {
446
+ "epoch": 7.590361445783133,
447
+ "grad_norm": 0.1814289093017578,
448
+ "learning_rate": 2.84401039255879e-05,
449
+ "loss": 0.0201,
450
+ "step": 630
451
+ },
452
+ {
453
+ "epoch": 7.710843373493976,
454
+ "grad_norm": 0.228335902094841,
455
+ "learning_rate": 2.5685517452260567e-05,
456
+ "loss": 0.0224,
457
+ "step": 640
458
+ },
459
+ {
460
+ "epoch": 7.831325301204819,
461
+ "grad_norm": 0.1545294225215912,
462
+ "learning_rate": 2.3051469341383402e-05,
463
+ "loss": 0.0238,
464
+ "step": 650
465
+ },
466
+ {
467
+ "epoch": 7.951807228915663,
468
+ "grad_norm": 0.1964937150478363,
469
+ "learning_rate": 2.0542232028624586e-05,
470
+ "loss": 0.0232,
471
+ "step": 660
472
+ },
473
+ {
474
+ "epoch": 8.072289156626505,
475
+ "grad_norm": 0.15069320797920227,
476
+ "learning_rate": 1.8161875506081293e-05,
477
+ "loss": 0.0206,
478
+ "step": 670
479
+ },
480
+ {
481
+ "epoch": 8.19277108433735,
482
+ "grad_norm": 0.13602782785892487,
483
+ "learning_rate": 1.5914260720737795e-05,
484
+ "loss": 0.0187,
485
+ "step": 680
486
+ },
487
+ {
488
+ "epoch": 8.313253012048193,
489
+ "grad_norm": 0.19349129498004913,
490
+ "learning_rate": 1.3803033311995072e-05,
491
+ "loss": 0.0192,
492
+ "step": 690
493
+ },
494
+ {
495
+ "epoch": 8.433734939759036,
496
+ "grad_norm": 0.1513078659772873,
497
+ "learning_rate": 1.1831617698430609e-05,
498
+ "loss": 0.0171,
499
+ "step": 700
500
+ },
501
+ {
502
+ "epoch": 8.55421686746988,
503
+ "grad_norm": 0.15297076106071472,
504
+ "learning_rate": 1.0003211523378796e-05,
505
+ "loss": 0.0187,
506
+ "step": 710
507
+ },
508
+ {
509
+ "epoch": 8.674698795180722,
510
+ "grad_norm": 0.1606190949678421,
511
+ "learning_rate": 8.32078046834176e-06,
512
+ "loss": 0.0198,
513
+ "step": 720
514
+ },
515
+ {
516
+ "epoch": 8.795180722891565,
517
+ "grad_norm": 0.11450409889221191,
518
+ "learning_rate": 6.787053442643232e-06,
519
+ "loss": 0.0196,
520
+ "step": 730
521
+ },
522
+ {
523
+ "epoch": 8.91566265060241,
524
+ "grad_norm": 0.23408889770507812,
525
+ "learning_rate": 5.40451815712748e-06,
526
+ "loss": 0.0197,
527
+ "step": 740
528
+ },
529
+ {
530
+ "epoch": 9.036144578313253,
531
+ "grad_norm": 0.19213688373565674,
532
+ "learning_rate": 4.175417089083378e-06,
533
+ "loss": 0.0193,
534
+ "step": 750
535
+ },
536
+ {
537
+ "epoch": 9.156626506024097,
538
+ "grad_norm": 0.13061603903770447,
539
+ "learning_rate": 3.1017438449379434e-06,
540
+ "loss": 0.0217,
541
+ "step": 760
542
+ },
543
+ {
544
+ "epoch": 9.27710843373494,
545
+ "grad_norm": 0.20497524738311768,
546
+ "learning_rate": 2.1852399266194314e-06,
547
+ "loss": 0.0206,
548
+ "step": 770
549
+ },
550
+ {
551
+ "epoch": 9.397590361445783,
552
+ "grad_norm": 0.16401517391204834,
553
+ "learning_rate": 1.4273919068349184e-06,
554
+ "loss": 0.0218,
555
+ "step": 780
556
+ },
557
+ {
558
+ "epoch": 9.518072289156626,
559
+ "grad_norm": 0.08886178582906723,
560
+ "learning_rate": 8.294290178437969e-07,
561
+ "loss": 0.0181,
562
+ "step": 790
563
+ },
564
+ {
565
+ "epoch": 9.638554216867469,
566
+ "grad_norm": 0.1821727752685547,
567
+ "learning_rate": 3.923211576387087e-07,
568
+ "loss": 0.0182,
569
+ "step": 800
570
+ },
571
+ {
572
+ "epoch": 9.759036144578314,
573
+ "grad_norm": 0.17254865169525146,
574
+ "learning_rate": 1.1677731676733584e-07,
575
+ "loss": 0.0193,
576
+ "step": 810
577
+ },
578
+ {
579
+ "epoch": 9.879518072289157,
580
+ "grad_norm": 0.18676318228244781,
581
+ "learning_rate": 3.244428347204398e-09,
582
+ "loss": 0.0161,
583
+ "step": 820
584
+ },
585
+ {
586
+ "epoch": 9.903614457831326,
587
+ "step": 822,
588
+ "total_flos": 1.0767742262918784e+17,
589
+ "train_loss": 0.05996827910361934,
590
+ "train_runtime": 931.6223,
591
+ "train_samples_per_second": 56.469,
592
+ "train_steps_per_second": 0.882
593
+ }
594
+ ],
595
+ "logging_steps": 10,
596
+ "max_steps": 822,
597
+ "num_input_tokens_seen": 0,
598
+ "num_train_epochs": 10,
599
+ "save_steps": 10000,
600
+ "stateful_callbacks": {
601
+ "TrainerControl": {
602
+ "args": {
603
+ "should_epoch_stop": false,
604
+ "should_evaluate": false,
605
+ "should_log": false,
606
+ "should_save": true,
607
+ "should_training_stop": true
608
+ },
609
+ "attributes": {}
610
+ }
611
+ },
612
+ "total_flos": 1.0767742262918784e+17,
613
+ "train_batch_size": 64,
614
+ "trial_name": null,
615
+ "trial_params": null
616
+ }