longcld commited on
Commit
aeb17f3
1 Parent(s): cae6c3b
Files changed (6) hide show
  1. optimizer.pt +1 -1
  2. pytorch_model.bin +1 -1
  3. rng_state.pth +1 -1
  4. scheduler.pt +1 -1
  5. trainer_state.json +283 -2683
  6. training_args.bin +1 -1
optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fdc34e2e47086c7a34ea5ee8d3562d5b6b66f1ea45326193b00908f17b5bf7a3
3
  size 1585984129
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56b3ff3cce4ef8e49fa4c59072c6499687aa372fa12842008e8f39537d3e6a0e
3
  size 1585984129
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:79c82d7e5310f416c1ab222e1a591e1824480fc18976a8c5eeb173bcfb30ebfa
3
  size 1561347007
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d7d7fb723eb0c2d71a5eda5e801ccd48fcd10990290682024235012643fb9a2
3
  size 1561347007
rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:67e78d591e76f80e47adbe4d9f1571760365ce91d4011dc19f09e4ad8f081e23
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b431fedf18bd02974328712d5cc0081c06a69badeef4de985c24dfa9b4feab51
3
  size 14503
scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3bc19e6b36b8a2a51bb1ee19b9c7fcdc52459615ee5f86e7754251d09a61ad6e
3
  size 623
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4c62cbc98de557b5a87208e5039ca31193d26b6ce6ab86d4857cb1c4af8a283
3
  size 623
trainer_state.json CHANGED
@@ -1,3256 +1,856 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 9.565962534874451,
5
- "global_step": 54000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
9
  "log_history": [
10
  {
11
  "epoch": 0.02,
12
- "learning_rate": 0.0004991142604074402,
13
- "loss": 2.333,
14
  "step": 100
15
  },
16
  {
17
  "epoch": 0.04,
18
- "learning_rate": 0.0004982285208148805,
19
- "loss": 2.3899,
20
  "step": 200
21
  },
22
  {
23
  "epoch": 0.05,
24
- "learning_rate": 0.0004973427812223207,
25
- "loss": 2.4422,
26
  "step": 300
27
  },
28
  {
29
  "epoch": 0.07,
30
- "learning_rate": 0.0004964570416297609,
31
- "loss": 2.4359,
32
  "step": 400
33
  },
34
  {
35
  "epoch": 0.09,
36
- "learning_rate": 0.0004955713020372011,
37
- "loss": 2.3725,
38
  "step": 500
39
  },
40
  {
41
  "epoch": 0.11,
42
- "learning_rate": 0.0004946855624446413,
43
- "loss": 2.4478,
44
  "step": 600
45
  },
46
  {
47
  "epoch": 0.12,
48
- "learning_rate": 0.0004937998228520815,
49
- "loss": 2.4036,
50
  "step": 700
51
  },
52
  {
53
  "epoch": 0.14,
54
- "learning_rate": 0.0004929140832595217,
55
- "loss": 2.3984,
56
  "step": 800
57
  },
58
  {
59
  "epoch": 0.16,
60
- "learning_rate": 0.0004920283436669619,
61
- "loss": 2.3836,
62
  "step": 900
63
  },
64
  {
65
  "epoch": 0.18,
66
- "learning_rate": 0.0004911426040744021,
67
- "loss": 2.3708,
68
  "step": 1000
69
  },
70
  {
71
  "epoch": 0.19,
72
- "learning_rate": 0.0004902568644818423,
73
- "loss": 2.3009,
74
  "step": 1100
75
  },
76
  {
77
  "epoch": 0.21,
78
- "learning_rate": 0.0004893711248892826,
79
- "loss": 2.367,
80
  "step": 1200
81
  },
82
  {
83
  "epoch": 0.23,
84
- "learning_rate": 0.0004884853852967228,
85
- "loss": 2.3713,
86
  "step": 1300
87
  },
88
  {
89
  "epoch": 0.25,
90
- "learning_rate": 0.000487599645704163,
91
- "loss": 2.3609,
92
  "step": 1400
93
  },
94
  {
95
  "epoch": 0.27,
96
- "learning_rate": 0.00048671390611160323,
97
- "loss": 2.3181,
98
  "step": 1500
99
  },
100
  {
101
  "epoch": 0.28,
102
- "learning_rate": 0.00048582816651904345,
103
- "loss": 2.3249,
104
  "step": 1600
105
  },
106
  {
107
  "epoch": 0.3,
108
- "learning_rate": 0.0004849424269264836,
109
- "loss": 2.3505,
110
  "step": 1700
111
  },
112
  {
113
  "epoch": 0.32,
114
- "learning_rate": 0.00048405668733392384,
115
- "loss": 2.2962,
116
  "step": 1800
117
  },
118
  {
119
  "epoch": 0.34,
120
- "learning_rate": 0.00048317094774136406,
121
- "loss": 2.3446,
122
  "step": 1900
123
  },
124
  {
125
  "epoch": 0.35,
126
- "learning_rate": 0.0004822852081488043,
127
- "loss": 2.308,
128
  "step": 2000
129
  },
130
  {
131
  "epoch": 0.37,
132
- "learning_rate": 0.00048139946855624445,
133
- "loss": 2.2919,
134
  "step": 2100
135
  },
136
  {
137
  "epoch": 0.39,
138
- "learning_rate": 0.0004805137289636847,
139
- "loss": 2.308,
140
  "step": 2200
141
  },
142
  {
143
  "epoch": 0.41,
144
- "learning_rate": 0.0004796279893711249,
145
- "loss": 2.2863,
146
  "step": 2300
147
  },
148
  {
149
  "epoch": 0.43,
150
- "learning_rate": 0.0004787422497785651,
151
- "loss": 2.2976,
152
  "step": 2400
153
  },
154
  {
155
  "epoch": 0.44,
156
- "learning_rate": 0.00047785651018600534,
157
- "loss": 2.288,
158
  "step": 2500
159
  },
160
  {
161
  "epoch": 0.46,
162
- "learning_rate": 0.0004769707705934455,
163
- "loss": 2.2771,
164
  "step": 2600
165
  },
166
  {
167
  "epoch": 0.48,
168
- "learning_rate": 0.00047608503100088573,
169
- "loss": 2.2608,
170
  "step": 2700
171
  },
172
  {
173
  "epoch": 0.5,
174
- "learning_rate": 0.00047519929140832595,
175
- "loss": 2.2227,
176
  "step": 2800
177
  },
178
  {
179
  "epoch": 0.51,
180
- "learning_rate": 0.0004743135518157662,
181
- "loss": 2.2823,
182
  "step": 2900
183
  },
184
  {
185
  "epoch": 0.53,
186
- "learning_rate": 0.0004734278122232064,
187
- "loss": 2.1959,
188
  "step": 3000
189
  },
190
  {
191
  "epoch": 0.55,
192
- "learning_rate": 0.00047254207263064656,
193
- "loss": 2.2388,
194
  "step": 3100
195
  },
196
  {
197
  "epoch": 0.57,
198
- "learning_rate": 0.0004716563330380868,
199
- "loss": 2.252,
200
  "step": 3200
201
  },
202
  {
203
  "epoch": 0.58,
204
- "learning_rate": 0.000470770593445527,
205
- "loss": 2.2295,
206
  "step": 3300
207
  },
208
  {
209
  "epoch": 0.6,
210
- "learning_rate": 0.00046988485385296723,
211
- "loss": 2.2035,
212
  "step": 3400
213
  },
214
  {
215
  "epoch": 0.62,
216
- "learning_rate": 0.0004689991142604074,
217
- "loss": 2.285,
218
  "step": 3500
219
  },
220
  {
221
  "epoch": 0.64,
222
- "learning_rate": 0.00046811337466784767,
223
- "loss": 2.2439,
224
  "step": 3600
225
  },
226
  {
227
  "epoch": 0.66,
228
- "learning_rate": 0.0004672276350752879,
229
- "loss": 2.2378,
230
  "step": 3700
231
  },
232
  {
233
  "epoch": 0.67,
234
- "learning_rate": 0.0004663418954827281,
235
- "loss": 2.2499,
236
  "step": 3800
237
  },
238
  {
239
  "epoch": 0.69,
240
- "learning_rate": 0.00046545615589016834,
241
- "loss": 2.1999,
242
  "step": 3900
243
  },
244
  {
245
  "epoch": 0.71,
246
- "learning_rate": 0.0004645704162976085,
247
- "loss": 2.1862,
248
  "step": 4000
249
  },
250
  {
251
  "epoch": 0.73,
252
- "learning_rate": 0.00046368467670504873,
253
- "loss": 2.217,
254
  "step": 4100
255
  },
256
  {
257
  "epoch": 0.74,
258
- "learning_rate": 0.00046279893711248895,
259
- "loss": 2.2083,
260
  "step": 4200
261
  },
262
  {
263
  "epoch": 0.76,
264
- "learning_rate": 0.00046191319751992917,
265
- "loss": 2.1784,
266
  "step": 4300
267
  },
268
  {
269
  "epoch": 0.78,
270
- "learning_rate": 0.0004610274579273694,
271
- "loss": 2.1467,
272
  "step": 4400
273
  },
274
  {
275
  "epoch": 0.8,
276
- "learning_rate": 0.00046014171833480956,
277
- "loss": 2.2254,
278
  "step": 4500
279
  },
280
  {
281
  "epoch": 0.81,
282
- "learning_rate": 0.0004592559787422498,
283
- "loss": 2.2067,
284
  "step": 4600
285
  },
286
  {
287
  "epoch": 0.83,
288
- "learning_rate": 0.00045837023914969,
289
- "loss": 2.2011,
290
  "step": 4700
291
  },
292
  {
293
  "epoch": 0.85,
294
- "learning_rate": 0.0004574844995571302,
295
- "loss": 2.1521,
296
  "step": 4800
297
  },
298
  {
299
  "epoch": 0.87,
300
- "learning_rate": 0.0004565987599645704,
301
- "loss": 2.193,
302
  "step": 4900
303
  },
304
  {
305
  "epoch": 0.89,
306
- "learning_rate": 0.0004557130203720106,
307
- "loss": 2.1709,
308
  "step": 5000
309
  },
310
  {
311
  "epoch": 0.9,
312
- "learning_rate": 0.00045482728077945084,
313
- "loss": 2.1806,
314
  "step": 5100
315
  },
316
  {
317
  "epoch": 0.92,
318
- "learning_rate": 0.00045394154118689106,
319
- "loss": 2.1895,
320
  "step": 5200
321
  },
322
  {
323
  "epoch": 0.94,
324
- "learning_rate": 0.0004530558015943313,
325
- "loss": 2.203,
326
  "step": 5300
327
  },
328
  {
329
  "epoch": 0.96,
330
- "learning_rate": 0.00045217006200177145,
331
- "loss": 2.1686,
332
  "step": 5400
333
  },
334
  {
335
  "epoch": 0.97,
336
- "learning_rate": 0.00045128432240921167,
337
- "loss": 2.1461,
338
  "step": 5500
339
  },
340
  {
341
  "epoch": 0.99,
342
- "learning_rate": 0.0004503985828166519,
343
- "loss": 2.1239,
344
  "step": 5600
345
  },
346
  {
347
  "epoch": 1.01,
348
- "learning_rate": 0.0004495128432240921,
349
- "loss": 2.0857,
350
  "step": 5700
351
  },
352
  {
353
  "epoch": 1.03,
354
- "learning_rate": 0.00044862710363153234,
355
- "loss": 2.0997,
356
  "step": 5800
357
  },
358
  {
359
  "epoch": 1.05,
360
- "learning_rate": 0.0004477413640389725,
361
- "loss": 2.0756,
362
  "step": 5900
363
  },
364
  {
365
  "epoch": 1.06,
366
- "learning_rate": 0.0004468556244464128,
367
- "loss": 2.0468,
368
  "step": 6000
369
  },
370
  {
371
  "epoch": 1.08,
372
- "learning_rate": 0.000445969884853853,
373
- "loss": 2.0412,
374
  "step": 6100
375
  },
376
  {
377
  "epoch": 1.1,
378
- "learning_rate": 0.0004450841452612932,
379
- "loss": 2.0289,
380
  "step": 6200
381
  },
382
  {
383
  "epoch": 1.12,
384
- "learning_rate": 0.0004441984056687334,
385
- "loss": 2.07,
386
  "step": 6300
387
  },
388
  {
389
  "epoch": 1.13,
390
- "learning_rate": 0.0004433126660761736,
391
- "loss": 2.039,
392
  "step": 6400
393
  },
394
  {
395
  "epoch": 1.15,
396
- "learning_rate": 0.00044242692648361384,
397
- "loss": 2.0749,
398
  "step": 6500
399
  },
400
  {
401
  "epoch": 1.17,
402
- "learning_rate": 0.00044154118689105406,
403
- "loss": 2.0776,
404
  "step": 6600
405
  },
406
  {
407
  "epoch": 1.19,
408
- "learning_rate": 0.0004406554472984943,
409
- "loss": 2.0375,
410
  "step": 6700
411
  },
412
  {
413
  "epoch": 1.2,
414
- "learning_rate": 0.00043976970770593445,
415
- "loss": 2.0512,
416
  "step": 6800
417
  },
418
  {
419
  "epoch": 1.22,
420
- "learning_rate": 0.00043888396811337467,
421
- "loss": 2.0449,
422
  "step": 6900
423
  },
424
  {
425
  "epoch": 1.24,
426
- "learning_rate": 0.0004379982285208149,
427
- "loss": 2.0157,
428
  "step": 7000
429
  },
430
  {
431
  "epoch": 1.26,
432
- "learning_rate": 0.0004371124889282551,
433
- "loss": 2.0406,
434
  "step": 7100
435
  },
436
  {
437
  "epoch": 1.28,
438
- "learning_rate": 0.00043622674933569533,
439
- "loss": 2.039,
440
  "step": 7200
441
  },
442
  {
443
  "epoch": 1.29,
444
- "learning_rate": 0.0004353410097431355,
445
- "loss": 2.0525,
446
  "step": 7300
447
  },
448
  {
449
  "epoch": 1.31,
450
- "learning_rate": 0.0004344552701505757,
451
- "loss": 2.0217,
452
  "step": 7400
453
  },
454
  {
455
  "epoch": 1.33,
456
- "learning_rate": 0.00043356953055801595,
457
- "loss": 2.0398,
458
  "step": 7500
459
  },
460
  {
461
  "epoch": 1.35,
462
- "learning_rate": 0.00043268379096545617,
463
- "loss": 2.0426,
464
  "step": 7600
465
  },
466
  {
467
  "epoch": 1.36,
468
- "learning_rate": 0.00043179805137289634,
469
- "loss": 2.0565,
470
  "step": 7700
471
  },
472
  {
473
  "epoch": 1.38,
474
- "learning_rate": 0.00043091231178033656,
475
- "loss": 1.9831,
476
  "step": 7800
477
  },
478
  {
479
  "epoch": 1.4,
480
- "learning_rate": 0.0004300265721877768,
481
- "loss": 2.0202,
482
  "step": 7900
483
  },
484
  {
485
  "epoch": 1.42,
486
- "learning_rate": 0.000429140832595217,
487
- "loss": 2.0607,
488
  "step": 8000
489
  },
490
  {
491
  "epoch": 1.43,
492
- "learning_rate": 0.0004282550930026572,
493
- "loss": 2.0394,
494
  "step": 8100
495
  },
496
  {
497
  "epoch": 1.45,
498
- "learning_rate": 0.0004273693534100974,
499
- "loss": 2.0303,
500
  "step": 8200
501
  },
502
  {
503
  "epoch": 1.47,
504
- "learning_rate": 0.00042648361381753767,
505
- "loss": 2.0451,
506
  "step": 8300
507
  },
508
  {
509
  "epoch": 1.49,
510
- "learning_rate": 0.0004255978742249779,
511
- "loss": 2.0185,
512
  "step": 8400
513
  },
514
  {
515
  "epoch": 1.51,
516
- "learning_rate": 0.0004247121346324181,
517
- "loss": 2.0064,
518
  "step": 8500
519
  },
520
  {
521
  "epoch": 1.52,
522
- "learning_rate": 0.00042382639503985833,
523
- "loss": 2.0093,
524
  "step": 8600
525
  },
526
  {
527
  "epoch": 1.54,
528
- "learning_rate": 0.0004229406554472985,
529
- "loss": 1.9924,
530
  "step": 8700
531
  },
532
  {
533
  "epoch": 1.56,
534
- "learning_rate": 0.0004220549158547387,
535
- "loss": 2.0301,
536
  "step": 8800
537
  },
538
  {
539
  "epoch": 1.58,
540
- "learning_rate": 0.00042116917626217894,
541
- "loss": 1.9849,
542
  "step": 8900
543
  },
544
  {
545
  "epoch": 1.59,
546
- "learning_rate": 0.00042028343666961917,
547
- "loss": 2.0016,
548
  "step": 9000
549
  },
550
  {
551
  "epoch": 1.61,
552
- "learning_rate": 0.00041939769707705933,
553
- "loss": 1.9805,
554
  "step": 9100
555
  },
556
  {
557
  "epoch": 1.63,
558
- "learning_rate": 0.00041851195748449956,
559
- "loss": 2.0216,
560
  "step": 9200
561
  },
562
  {
563
  "epoch": 1.65,
564
- "learning_rate": 0.0004176262178919398,
565
- "loss": 1.9921,
566
  "step": 9300
567
  },
568
  {
569
  "epoch": 1.67,
570
- "learning_rate": 0.00041674047829938,
571
- "loss": 1.9857,
572
  "step": 9400
573
  },
574
  {
575
  "epoch": 1.68,
576
- "learning_rate": 0.0004158547387068202,
577
- "loss": 2.011,
578
  "step": 9500
579
  },
580
  {
581
  "epoch": 1.7,
582
- "learning_rate": 0.0004149689991142604,
583
- "loss": 2.0079,
584
  "step": 9600
585
  },
586
  {
587
  "epoch": 1.72,
588
- "learning_rate": 0.0004140832595217006,
589
- "loss": 2.0178,
590
  "step": 9700
591
  },
592
  {
593
  "epoch": 1.74,
594
- "learning_rate": 0.00041319751992914083,
595
- "loss": 1.9978,
596
  "step": 9800
597
  },
598
  {
599
  "epoch": 1.75,
600
- "learning_rate": 0.00041231178033658105,
601
- "loss": 1.9585,
602
  "step": 9900
603
  },
604
  {
605
  "epoch": 1.77,
606
- "learning_rate": 0.0004114260407440213,
607
- "loss": 1.9802,
608
  "step": 10000
609
  },
610
  {
611
  "epoch": 1.79,
612
- "learning_rate": 0.00041054030115146144,
613
- "loss": 1.9912,
614
  "step": 10100
615
  },
616
  {
617
  "epoch": 1.81,
618
- "learning_rate": 0.00040965456155890167,
619
- "loss": 2.0093,
620
  "step": 10200
621
  },
622
  {
623
  "epoch": 1.82,
624
- "learning_rate": 0.0004087688219663419,
625
- "loss": 1.9695,
626
  "step": 10300
627
  },
628
  {
629
  "epoch": 1.84,
630
- "learning_rate": 0.0004078830823737821,
631
- "loss": 2.0003,
632
  "step": 10400
633
  },
634
  {
635
  "epoch": 1.86,
636
- "learning_rate": 0.0004069973427812223,
637
- "loss": 2.0081,
638
  "step": 10500
639
  },
640
  {
641
  "epoch": 1.88,
642
- "learning_rate": 0.0004061116031886625,
643
- "loss": 1.9888,
644
  "step": 10600
645
  },
646
  {
647
  "epoch": 1.9,
648
- "learning_rate": 0.0004052258635961028,
649
- "loss": 2.0072,
650
  "step": 10700
651
  },
652
  {
653
  "epoch": 1.91,
654
- "learning_rate": 0.000404340124003543,
655
- "loss": 2.0097,
656
  "step": 10800
657
  },
658
  {
659
  "epoch": 1.93,
660
- "learning_rate": 0.0004034543844109832,
661
- "loss": 2.0066,
662
  "step": 10900
663
  },
664
  {
665
  "epoch": 1.95,
666
- "learning_rate": 0.0004025686448184234,
667
- "loss": 1.9976,
668
  "step": 11000
669
  },
670
  {
671
  "epoch": 1.97,
672
- "learning_rate": 0.0004016829052258636,
673
- "loss": 1.9543,
674
  "step": 11100
675
  },
676
  {
677
  "epoch": 1.98,
678
- "learning_rate": 0.00040079716563330383,
679
- "loss": 1.9676,
680
  "step": 11200
681
  },
682
  {
683
  "epoch": 2.0,
684
- "learning_rate": 0.00039991142604074405,
685
- "loss": 1.9547,
686
  "step": 11300
687
  },
688
  {
689
  "epoch": 2.02,
690
- "learning_rate": 0.0003990256864481843,
691
- "loss": 1.8447,
692
  "step": 11400
693
  },
694
  {
695
  "epoch": 2.04,
696
- "learning_rate": 0.00039813994685562444,
697
- "loss": 1.9108,
698
  "step": 11500
699
  },
700
  {
701
  "epoch": 2.05,
702
- "learning_rate": 0.00039725420726306466,
703
- "loss": 1.8746,
704
  "step": 11600
705
  },
706
  {
707
  "epoch": 2.07,
708
- "learning_rate": 0.0003963684676705049,
709
- "loss": 1.864,
710
  "step": 11700
711
  },
712
  {
713
  "epoch": 2.09,
714
- "learning_rate": 0.0003954827280779451,
715
- "loss": 1.8742,
716
  "step": 11800
717
  },
718
  {
719
  "epoch": 2.11,
720
- "learning_rate": 0.0003945969884853853,
721
- "loss": 1.8111,
722
  "step": 11900
723
  },
724
  {
725
  "epoch": 2.13,
726
- "learning_rate": 0.0003937112488928255,
727
- "loss": 1.8708,
728
  "step": 12000
729
  },
730
  {
731
  "epoch": 2.14,
732
- "learning_rate": 0.0003928255093002657,
733
- "loss": 1.8909,
734
  "step": 12100
735
  },
736
  {
737
  "epoch": 2.16,
738
- "learning_rate": 0.00039193976970770594,
739
- "loss": 1.8941,
740
  "step": 12200
741
  },
742
  {
743
  "epoch": 2.18,
744
- "learning_rate": 0.00039105403011514616,
745
- "loss": 1.8875,
746
  "step": 12300
747
  },
748
  {
749
  "epoch": 2.2,
750
- "learning_rate": 0.00039016829052258633,
751
- "loss": 1.8948,
752
  "step": 12400
753
  },
754
  {
755
  "epoch": 2.21,
756
- "learning_rate": 0.00038928255093002655,
757
- "loss": 1.8865,
758
  "step": 12500
759
  },
760
  {
761
  "epoch": 2.23,
762
- "learning_rate": 0.0003883968113374668,
763
- "loss": 1.8871,
764
  "step": 12600
765
  },
766
  {
767
  "epoch": 2.25,
768
- "learning_rate": 0.000387511071744907,
769
- "loss": 1.8811,
770
  "step": 12700
771
  },
772
  {
773
  "epoch": 2.27,
774
- "learning_rate": 0.0003866253321523472,
775
- "loss": 1.8876,
776
  "step": 12800
777
  },
778
  {
779
  "epoch": 2.29,
780
- "learning_rate": 0.0003857395925597874,
781
- "loss": 1.8702,
782
  "step": 12900
783
  },
784
  {
785
  "epoch": 2.3,
786
- "learning_rate": 0.00038485385296722766,
787
- "loss": 1.9055,
788
  "step": 13000
789
  },
790
  {
791
  "epoch": 2.32,
792
- "learning_rate": 0.0003839681133746679,
793
- "loss": 1.8816,
794
  "step": 13100
795
  },
796
  {
797
  "epoch": 2.34,
798
- "learning_rate": 0.0003830823737821081,
799
- "loss": 1.8652,
800
  "step": 13200
801
  },
802
  {
803
  "epoch": 2.36,
804
- "learning_rate": 0.00038219663418954827,
805
- "loss": 1.8891,
806
  "step": 13300
807
  },
808
  {
809
  "epoch": 2.37,
810
- "learning_rate": 0.0003813108945969885,
811
- "loss": 1.9039,
812
  "step": 13400
813
  },
814
  {
815
  "epoch": 2.39,
816
- "learning_rate": 0.0003804251550044287,
817
- "loss": 1.8558,
818
  "step": 13500
819
  },
820
  {
821
  "epoch": 2.41,
822
- "learning_rate": 0.00037953941541186894,
823
- "loss": 1.8471,
824
  "step": 13600
825
  },
826
  {
827
  "epoch": 2.43,
828
- "learning_rate": 0.00037865367581930916,
829
- "loss": 1.8532,
830
  "step": 13700
831
  },
832
  {
833
  "epoch": 2.44,
834
- "learning_rate": 0.00037776793622674933,
835
- "loss": 1.8786,
836
  "step": 13800
837
  },
838
  {
839
  "epoch": 2.46,
840
- "learning_rate": 0.00037688219663418955,
841
- "loss": 1.8285,
842
  "step": 13900
843
  },
844
  {
845
  "epoch": 2.48,
846
- "learning_rate": 0.00037599645704162977,
847
- "loss": 1.8505,
848
  "step": 14000
849
- },
850
- {
851
- "epoch": 2.5,
852
- "learning_rate": 0.00037511071744907,
853
- "loss": 1.8604,
854
- "step": 14100
855
- },
856
- {
857
- "epoch": 2.52,
858
- "learning_rate": 0.0003742249778565102,
859
- "loss": 1.8684,
860
- "step": 14200
861
- },
862
- {
863
- "epoch": 2.53,
864
- "learning_rate": 0.0003733392382639504,
865
- "loss": 1.8241,
866
- "step": 14300
867
- },
868
- {
869
- "epoch": 2.55,
870
- "learning_rate": 0.0003724534986713906,
871
- "loss": 1.8601,
872
- "step": 14400
873
- },
874
- {
875
- "epoch": 2.57,
876
- "learning_rate": 0.0003715677590788308,
877
- "loss": 1.8582,
878
- "step": 14500
879
- },
880
- {
881
- "epoch": 2.59,
882
- "learning_rate": 0.00037068201948627105,
883
- "loss": 1.8555,
884
- "step": 14600
885
- },
886
- {
887
- "epoch": 2.6,
888
- "learning_rate": 0.0003697962798937112,
889
- "loss": 1.8905,
890
- "step": 14700
891
- },
892
- {
893
- "epoch": 2.62,
894
- "learning_rate": 0.00036891054030115144,
895
- "loss": 1.8754,
896
- "step": 14800
897
- },
898
- {
899
- "epoch": 2.64,
900
- "learning_rate": 0.00036802480070859166,
901
- "loss": 1.8835,
902
- "step": 14900
903
- },
904
- {
905
- "epoch": 2.66,
906
- "learning_rate": 0.0003671390611160319,
907
- "loss": 1.847,
908
- "step": 15000
909
- },
910
- {
911
- "epoch": 2.67,
912
- "learning_rate": 0.0003662533215234721,
913
- "loss": 1.8621,
914
- "step": 15100
915
- },
916
- {
917
- "epoch": 2.69,
918
- "learning_rate": 0.00036536758193091227,
919
- "loss": 1.8558,
920
- "step": 15200
921
- },
922
- {
923
- "epoch": 2.71,
924
- "learning_rate": 0.0003644818423383525,
925
- "loss": 1.8349,
926
- "step": 15300
927
- },
928
- {
929
- "epoch": 2.73,
930
- "learning_rate": 0.00036359610274579277,
931
- "loss": 1.8698,
932
- "step": 15400
933
- },
934
- {
935
- "epoch": 2.75,
936
- "learning_rate": 0.000362710363153233,
937
- "loss": 1.8925,
938
- "step": 15500
939
- },
940
- {
941
- "epoch": 2.76,
942
- "learning_rate": 0.0003618246235606732,
943
- "loss": 1.8347,
944
- "step": 15600
945
- },
946
- {
947
- "epoch": 2.78,
948
- "learning_rate": 0.0003609388839681134,
949
- "loss": 1.869,
950
- "step": 15700
951
- },
952
- {
953
- "epoch": 2.8,
954
- "learning_rate": 0.0003600531443755536,
955
- "loss": 1.82,
956
- "step": 15800
957
- },
958
- {
959
- "epoch": 2.82,
960
- "learning_rate": 0.0003591674047829938,
961
- "loss": 1.8407,
962
- "step": 15900
963
- },
964
- {
965
- "epoch": 2.83,
966
- "learning_rate": 0.00035828166519043405,
967
- "loss": 1.8458,
968
- "step": 16000
969
- },
970
- {
971
- "epoch": 2.85,
972
- "learning_rate": 0.0003573959255978742,
973
- "loss": 1.8568,
974
- "step": 16100
975
- },
976
- {
977
- "epoch": 2.87,
978
- "learning_rate": 0.00035651018600531444,
979
- "loss": 1.855,
980
- "step": 16200
981
- },
982
- {
983
- "epoch": 2.89,
984
- "learning_rate": 0.00035562444641275466,
985
- "loss": 1.841,
986
- "step": 16300
987
- },
988
- {
989
- "epoch": 2.91,
990
- "learning_rate": 0.0003547387068201949,
991
- "loss": 1.814,
992
- "step": 16400
993
- },
994
- {
995
- "epoch": 2.92,
996
- "learning_rate": 0.0003538529672276351,
997
- "loss": 1.8102,
998
- "step": 16500
999
- },
1000
- {
1001
- "epoch": 2.94,
1002
- "learning_rate": 0.00035296722763507527,
1003
- "loss": 1.8517,
1004
- "step": 16600
1005
- },
1006
- {
1007
- "epoch": 2.96,
1008
- "learning_rate": 0.0003520814880425155,
1009
- "loss": 1.8326,
1010
- "step": 16700
1011
- },
1012
- {
1013
- "epoch": 2.98,
1014
- "learning_rate": 0.0003511957484499557,
1015
- "loss": 1.8514,
1016
- "step": 16800
1017
- },
1018
- {
1019
- "epoch": 2.99,
1020
- "learning_rate": 0.00035031000885739594,
1021
- "loss": 1.863,
1022
- "step": 16900
1023
- },
1024
- {
1025
- "epoch": 3.01,
1026
- "learning_rate": 0.00034942426926483616,
1027
- "loss": 1.779,
1028
- "step": 17000
1029
- },
1030
- {
1031
- "epoch": 3.03,
1032
- "learning_rate": 0.0003485385296722763,
1033
- "loss": 1.7412,
1034
- "step": 17100
1035
- },
1036
- {
1037
- "epoch": 3.05,
1038
- "learning_rate": 0.00034765279007971655,
1039
- "loss": 1.7293,
1040
- "step": 17200
1041
- },
1042
- {
1043
- "epoch": 3.06,
1044
- "learning_rate": 0.00034676705048715677,
1045
- "loss": 1.7102,
1046
- "step": 17300
1047
- },
1048
- {
1049
- "epoch": 3.08,
1050
- "learning_rate": 0.000345881310894597,
1051
- "loss": 1.7713,
1052
- "step": 17400
1053
- },
1054
- {
1055
- "epoch": 3.1,
1056
- "learning_rate": 0.00034499557130203716,
1057
- "loss": 1.7884,
1058
- "step": 17500
1059
- },
1060
- {
1061
- "epoch": 3.12,
1062
- "learning_rate": 0.0003441098317094774,
1063
- "loss": 1.7567,
1064
- "step": 17600
1065
- },
1066
- {
1067
- "epoch": 3.14,
1068
- "learning_rate": 0.00034322409211691766,
1069
- "loss": 1.7192,
1070
- "step": 17700
1071
- },
1072
- {
1073
- "epoch": 3.15,
1074
- "learning_rate": 0.0003423383525243579,
1075
- "loss": 1.7205,
1076
- "step": 17800
1077
- },
1078
- {
1079
- "epoch": 3.17,
1080
- "learning_rate": 0.0003414526129317981,
1081
- "loss": 1.7175,
1082
- "step": 17900
1083
- },
1084
- {
1085
- "epoch": 3.19,
1086
- "learning_rate": 0.00034056687333923827,
1087
- "loss": 1.7627,
1088
- "step": 18000
1089
- },
1090
- {
1091
- "epoch": 3.21,
1092
- "learning_rate": 0.0003396811337466785,
1093
- "loss": 1.7404,
1094
- "step": 18100
1095
- },
1096
- {
1097
- "epoch": 3.22,
1098
- "learning_rate": 0.0003387953941541187,
1099
- "loss": 1.7664,
1100
- "step": 18200
1101
- },
1102
- {
1103
- "epoch": 3.24,
1104
- "learning_rate": 0.00033790965456155893,
1105
- "loss": 1.7307,
1106
- "step": 18300
1107
- },
1108
- {
1109
- "epoch": 3.26,
1110
- "learning_rate": 0.00033702391496899915,
1111
- "loss": 1.7245,
1112
- "step": 18400
1113
- },
1114
- {
1115
- "epoch": 3.28,
1116
- "learning_rate": 0.0003361381753764393,
1117
- "loss": 1.7643,
1118
- "step": 18500
1119
- },
1120
- {
1121
- "epoch": 3.29,
1122
- "learning_rate": 0.00033525243578387954,
1123
- "loss": 1.7469,
1124
- "step": 18600
1125
- },
1126
- {
1127
- "epoch": 3.31,
1128
- "learning_rate": 0.00033436669619131977,
1129
- "loss": 1.7639,
1130
- "step": 18700
1131
- },
1132
- {
1133
- "epoch": 3.33,
1134
- "learning_rate": 0.00033348095659876,
1135
- "loss": 1.7364,
1136
- "step": 18800
1137
- },
1138
- {
1139
- "epoch": 3.35,
1140
- "learning_rate": 0.00033259521700620016,
1141
- "loss": 1.7284,
1142
- "step": 18900
1143
- },
1144
- {
1145
- "epoch": 3.37,
1146
- "learning_rate": 0.0003317094774136404,
1147
- "loss": 1.7461,
1148
- "step": 19000
1149
- },
1150
- {
1151
- "epoch": 3.38,
1152
- "learning_rate": 0.0003308237378210806,
1153
- "loss": 1.7558,
1154
- "step": 19100
1155
- },
1156
- {
1157
- "epoch": 3.4,
1158
- "learning_rate": 0.0003299379982285208,
1159
- "loss": 1.7578,
1160
- "step": 19200
1161
- },
1162
- {
1163
- "epoch": 3.42,
1164
- "learning_rate": 0.00032905225863596104,
1165
- "loss": 1.7989,
1166
- "step": 19300
1167
- },
1168
- {
1169
- "epoch": 3.44,
1170
- "learning_rate": 0.0003281665190434012,
1171
- "loss": 1.7949,
1172
- "step": 19400
1173
- },
1174
- {
1175
- "epoch": 3.45,
1176
- "learning_rate": 0.00032728077945084143,
1177
- "loss": 1.777,
1178
- "step": 19500
1179
- },
1180
- {
1181
- "epoch": 3.47,
1182
- "learning_rate": 0.00032639503985828165,
1183
- "loss": 1.777,
1184
- "step": 19600
1185
- },
1186
- {
1187
- "epoch": 3.49,
1188
- "learning_rate": 0.0003255093002657219,
1189
- "loss": 1.7626,
1190
- "step": 19700
1191
- },
1192
- {
1193
- "epoch": 3.51,
1194
- "learning_rate": 0.0003246235606731621,
1195
- "loss": 1.7843,
1196
- "step": 19800
1197
- },
1198
- {
1199
- "epoch": 3.53,
1200
- "learning_rate": 0.00032373782108060227,
1201
- "loss": 1.7301,
1202
- "step": 19900
1203
- },
1204
- {
1205
- "epoch": 3.54,
1206
- "learning_rate": 0.0003228520814880425,
1207
- "loss": 1.7561,
1208
- "step": 20000
1209
- },
1210
- {
1211
- "epoch": 3.56,
1212
- "learning_rate": 0.00032196634189548276,
1213
- "loss": 1.7534,
1214
- "step": 20100
1215
- },
1216
- {
1217
- "epoch": 3.58,
1218
- "learning_rate": 0.000321080602302923,
1219
- "loss": 1.753,
1220
- "step": 20200
1221
- },
1222
- {
1223
- "epoch": 3.6,
1224
- "learning_rate": 0.00032019486271036315,
1225
- "loss": 1.7259,
1226
- "step": 20300
1227
- },
1228
- {
1229
- "epoch": 3.61,
1230
- "learning_rate": 0.0003193091231178034,
1231
- "loss": 1.789,
1232
- "step": 20400
1233
- },
1234
- {
1235
- "epoch": 3.63,
1236
- "learning_rate": 0.0003184233835252436,
1237
- "loss": 1.7771,
1238
- "step": 20500
1239
- },
1240
- {
1241
- "epoch": 3.65,
1242
- "learning_rate": 0.0003175376439326838,
1243
- "loss": 1.7308,
1244
- "step": 20600
1245
- },
1246
- {
1247
- "epoch": 3.67,
1248
- "learning_rate": 0.00031665190434012404,
1249
- "loss": 1.7568,
1250
- "step": 20700
1251
- },
1252
- {
1253
- "epoch": 3.68,
1254
- "learning_rate": 0.0003157661647475642,
1255
- "loss": 1.7393,
1256
- "step": 20800
1257
- },
1258
- {
1259
- "epoch": 3.7,
1260
- "learning_rate": 0.00031488042515500443,
1261
- "loss": 1.7593,
1262
- "step": 20900
1263
- },
1264
- {
1265
- "epoch": 3.72,
1266
- "learning_rate": 0.00031399468556244465,
1267
- "loss": 1.732,
1268
- "step": 21000
1269
- },
1270
- {
1271
- "epoch": 3.74,
1272
- "learning_rate": 0.0003131089459698849,
1273
- "loss": 1.7342,
1274
- "step": 21100
1275
- },
1276
- {
1277
- "epoch": 3.76,
1278
- "learning_rate": 0.0003122232063773251,
1279
- "loss": 1.7386,
1280
- "step": 21200
1281
- },
1282
- {
1283
- "epoch": 3.77,
1284
- "learning_rate": 0.00031133746678476526,
1285
- "loss": 1.7394,
1286
- "step": 21300
1287
- },
1288
- {
1289
- "epoch": 3.79,
1290
- "learning_rate": 0.0003104517271922055,
1291
- "loss": 1.7439,
1292
- "step": 21400
1293
- },
1294
- {
1295
- "epoch": 3.81,
1296
- "learning_rate": 0.0003095659875996457,
1297
- "loss": 1.7053,
1298
- "step": 21500
1299
- },
1300
- {
1301
- "epoch": 3.83,
1302
- "learning_rate": 0.00030868024800708593,
1303
- "loss": 1.7022,
1304
- "step": 21600
1305
- },
1306
- {
1307
- "epoch": 3.84,
1308
- "learning_rate": 0.0003077945084145261,
1309
- "loss": 1.7254,
1310
- "step": 21700
1311
- },
1312
- {
1313
- "epoch": 3.86,
1314
- "learning_rate": 0.0003069087688219663,
1315
- "loss": 1.712,
1316
- "step": 21800
1317
- },
1318
- {
1319
- "epoch": 3.88,
1320
- "learning_rate": 0.00030602302922940654,
1321
- "loss": 1.7565,
1322
- "step": 21900
1323
- },
1324
- {
1325
- "epoch": 3.9,
1326
- "learning_rate": 0.00030513728963684676,
1327
- "loss": 1.7495,
1328
- "step": 22000
1329
- },
1330
- {
1331
- "epoch": 3.91,
1332
- "learning_rate": 0.000304251550044287,
1333
- "loss": 1.7435,
1334
- "step": 22100
1335
- },
1336
- {
1337
- "epoch": 3.93,
1338
- "learning_rate": 0.00030336581045172715,
1339
- "loss": 1.7649,
1340
- "step": 22200
1341
- },
1342
- {
1343
- "epoch": 3.95,
1344
- "learning_rate": 0.0003024800708591674,
1345
- "loss": 1.743,
1346
- "step": 22300
1347
- },
1348
- {
1349
- "epoch": 3.97,
1350
- "learning_rate": 0.00030159433126660765,
1351
- "loss": 1.7332,
1352
- "step": 22400
1353
- },
1354
- {
1355
- "epoch": 3.99,
1356
- "learning_rate": 0.00030070859167404787,
1357
- "loss": 1.6918,
1358
- "step": 22500
1359
- },
1360
- {
1361
- "epoch": 4.0,
1362
- "learning_rate": 0.0002998228520814881,
1363
- "loss": 1.6936,
1364
- "step": 22600
1365
- },
1366
- {
1367
- "epoch": 4.02,
1368
- "learning_rate": 0.00029893711248892826,
1369
- "loss": 1.6353,
1370
- "step": 22700
1371
- },
1372
- {
1373
- "epoch": 4.04,
1374
- "learning_rate": 0.0002980513728963685,
1375
- "loss": 1.6311,
1376
- "step": 22800
1377
- },
1378
- {
1379
- "epoch": 4.06,
1380
- "learning_rate": 0.0002971656333038087,
1381
- "loss": 1.6385,
1382
- "step": 22900
1383
- },
1384
- {
1385
- "epoch": 4.07,
1386
- "learning_rate": 0.00029627989371124893,
1387
- "loss": 1.6188,
1388
- "step": 23000
1389
- },
1390
- {
1391
- "epoch": 4.09,
1392
- "learning_rate": 0.0002953941541186891,
1393
- "loss": 1.6043,
1394
- "step": 23100
1395
- },
1396
- {
1397
- "epoch": 4.11,
1398
- "learning_rate": 0.0002945084145261293,
1399
- "loss": 1.6233,
1400
- "step": 23200
1401
- },
1402
- {
1403
- "epoch": 4.13,
1404
- "learning_rate": 0.00029362267493356954,
1405
- "loss": 1.6249,
1406
- "step": 23300
1407
- },
1408
- {
1409
- "epoch": 4.15,
1410
- "learning_rate": 0.00029273693534100976,
1411
- "loss": 1.6264,
1412
- "step": 23400
1413
- },
1414
- {
1415
- "epoch": 4.16,
1416
- "learning_rate": 0.00029185119574845,
1417
- "loss": 1.6343,
1418
- "step": 23500
1419
- },
1420
- {
1421
- "epoch": 4.18,
1422
- "learning_rate": 0.00029096545615589015,
1423
- "loss": 1.6157,
1424
- "step": 23600
1425
- },
1426
- {
1427
- "epoch": 4.2,
1428
- "learning_rate": 0.00029007971656333037,
1429
- "loss": 1.6384,
1430
- "step": 23700
1431
- },
1432
- {
1433
- "epoch": 4.22,
1434
- "learning_rate": 0.0002891939769707706,
1435
- "loss": 1.65,
1436
- "step": 23800
1437
- },
1438
- {
1439
- "epoch": 4.23,
1440
- "learning_rate": 0.0002883082373782108,
1441
- "loss": 1.6624,
1442
- "step": 23900
1443
- },
1444
- {
1445
- "epoch": 4.25,
1446
- "learning_rate": 0.00028742249778565104,
1447
- "loss": 1.6375,
1448
- "step": 24000
1449
- },
1450
- {
1451
- "epoch": 4.27,
1452
- "learning_rate": 0.0002865367581930912,
1453
- "loss": 1.6722,
1454
- "step": 24100
1455
- },
1456
- {
1457
- "epoch": 4.29,
1458
- "learning_rate": 0.00028565101860053143,
1459
- "loss": 1.6491,
1460
- "step": 24200
1461
- },
1462
- {
1463
- "epoch": 4.3,
1464
- "learning_rate": 0.00028476527900797165,
1465
- "loss": 1.6498,
1466
- "step": 24300
1467
- },
1468
- {
1469
- "epoch": 4.32,
1470
- "learning_rate": 0.00028387953941541187,
1471
- "loss": 1.6559,
1472
- "step": 24400
1473
- },
1474
- {
1475
- "epoch": 4.34,
1476
- "learning_rate": 0.00028299379982285204,
1477
- "loss": 1.6044,
1478
- "step": 24500
1479
- },
1480
- {
1481
- "epoch": 4.36,
1482
- "learning_rate": 0.00028210806023029226,
1483
- "loss": 1.6661,
1484
- "step": 24600
1485
- },
1486
- {
1487
- "epoch": 4.38,
1488
- "learning_rate": 0.0002812223206377325,
1489
- "loss": 1.6478,
1490
- "step": 24700
1491
- },
1492
- {
1493
- "epoch": 4.39,
1494
- "learning_rate": 0.00028033658104517276,
1495
- "loss": 1.6382,
1496
- "step": 24800
1497
- },
1498
- {
1499
- "epoch": 4.41,
1500
- "learning_rate": 0.000279450841452613,
1501
- "loss": 1.6339,
1502
- "step": 24900
1503
- },
1504
- {
1505
- "epoch": 4.43,
1506
- "learning_rate": 0.00027856510186005315,
1507
- "loss": 1.6223,
1508
- "step": 25000
1509
- },
1510
- {
1511
- "epoch": 4.45,
1512
- "learning_rate": 0.00027767936226749337,
1513
- "loss": 1.6472,
1514
- "step": 25100
1515
- },
1516
- {
1517
- "epoch": 4.46,
1518
- "learning_rate": 0.0002767936226749336,
1519
- "loss": 1.6333,
1520
- "step": 25200
1521
- },
1522
- {
1523
- "epoch": 4.48,
1524
- "learning_rate": 0.0002759078830823738,
1525
- "loss": 1.6384,
1526
- "step": 25300
1527
- },
1528
- {
1529
- "epoch": 4.5,
1530
- "learning_rate": 0.00027502214348981404,
1531
- "loss": 1.6005,
1532
- "step": 25400
1533
- },
1534
- {
1535
- "epoch": 4.52,
1536
- "learning_rate": 0.0002741364038972542,
1537
- "loss": 1.6455,
1538
- "step": 25500
1539
- },
1540
- {
1541
- "epoch": 4.53,
1542
- "learning_rate": 0.0002732506643046944,
1543
- "loss": 1.6201,
1544
- "step": 25600
1545
- },
1546
- {
1547
- "epoch": 4.55,
1548
- "learning_rate": 0.00027236492471213465,
1549
- "loss": 1.6439,
1550
- "step": 25700
1551
- },
1552
- {
1553
- "epoch": 4.57,
1554
- "learning_rate": 0.00027147918511957487,
1555
- "loss": 1.6261,
1556
- "step": 25800
1557
- },
1558
- {
1559
- "epoch": 4.59,
1560
- "learning_rate": 0.00027059344552701504,
1561
- "loss": 1.6236,
1562
- "step": 25900
1563
- },
1564
- {
1565
- "epoch": 4.61,
1566
- "learning_rate": 0.00026970770593445526,
1567
- "loss": 1.6156,
1568
- "step": 26000
1569
- },
1570
- {
1571
- "epoch": 4.62,
1572
- "learning_rate": 0.0002688219663418955,
1573
- "loss": 1.6597,
1574
- "step": 26100
1575
- },
1576
- {
1577
- "epoch": 4.64,
1578
- "learning_rate": 0.0002679362267493357,
1579
- "loss": 1.635,
1580
- "step": 26200
1581
- },
1582
- {
1583
- "epoch": 4.66,
1584
- "learning_rate": 0.0002670504871567759,
1585
- "loss": 1.6202,
1586
- "step": 26300
1587
- },
1588
- {
1589
- "epoch": 4.68,
1590
- "learning_rate": 0.0002661647475642161,
1591
- "loss": 1.6413,
1592
- "step": 26400
1593
- },
1594
- {
1595
- "epoch": 4.69,
1596
- "learning_rate": 0.0002652790079716563,
1597
- "loss": 1.6363,
1598
- "step": 26500
1599
- },
1600
- {
1601
- "epoch": 4.71,
1602
- "learning_rate": 0.00026439326837909654,
1603
- "loss": 1.6283,
1604
- "step": 26600
1605
- },
1606
- {
1607
- "epoch": 4.73,
1608
- "learning_rate": 0.00026350752878653676,
1609
- "loss": 1.6437,
1610
- "step": 26700
1611
- },
1612
- {
1613
- "epoch": 4.75,
1614
- "learning_rate": 0.000262621789193977,
1615
- "loss": 1.6456,
1616
- "step": 26800
1617
- },
1618
- {
1619
- "epoch": 4.77,
1620
- "learning_rate": 0.00026173604960141715,
1621
- "loss": 1.6076,
1622
- "step": 26900
1623
- },
1624
- {
1625
- "epoch": 4.78,
1626
- "learning_rate": 0.00026085031000885737,
1627
- "loss": 1.6429,
1628
- "step": 27000
1629
- },
1630
- {
1631
- "epoch": 4.8,
1632
- "learning_rate": 0.00025996457041629764,
1633
- "loss": 1.6635,
1634
- "step": 27100
1635
- },
1636
- {
1637
- "epoch": 4.82,
1638
- "learning_rate": 0.00025907883082373787,
1639
- "loss": 1.6269,
1640
- "step": 27200
1641
- },
1642
- {
1643
- "epoch": 4.84,
1644
- "learning_rate": 0.00025819309123117803,
1645
- "loss": 1.6282,
1646
- "step": 27300
1647
- },
1648
- {
1649
- "epoch": 4.85,
1650
- "learning_rate": 0.00025730735163861826,
1651
- "loss": 1.5984,
1652
- "step": 27400
1653
- },
1654
- {
1655
- "epoch": 4.87,
1656
- "learning_rate": 0.0002564216120460585,
1657
- "loss": 1.6434,
1658
- "step": 27500
1659
- },
1660
- {
1661
- "epoch": 4.89,
1662
- "learning_rate": 0.0002555358724534987,
1663
- "loss": 1.641,
1664
- "step": 27600
1665
- },
1666
- {
1667
- "epoch": 4.91,
1668
- "learning_rate": 0.0002546501328609389,
1669
- "loss": 1.6232,
1670
- "step": 27700
1671
- },
1672
- {
1673
- "epoch": 4.92,
1674
- "learning_rate": 0.0002537643932683791,
1675
- "loss": 1.5679,
1676
- "step": 27800
1677
- },
1678
- {
1679
- "epoch": 4.94,
1680
- "learning_rate": 0.0002528786536758193,
1681
- "loss": 1.6289,
1682
- "step": 27900
1683
- },
1684
- {
1685
- "epoch": 4.96,
1686
- "learning_rate": 0.00025199291408325953,
1687
- "loss": 1.6466,
1688
- "step": 28000
1689
- },
1690
- {
1691
- "epoch": 4.98,
1692
- "learning_rate": 0.00025110717449069975,
1693
- "loss": 1.6467,
1694
- "step": 28100
1695
- },
1696
- {
1697
- "epoch": 5.0,
1698
- "learning_rate": 0.00025022143489814,
1699
- "loss": 1.6348,
1700
- "step": 28200
1701
- },
1702
- {
1703
- "epoch": 5.01,
1704
- "learning_rate": 0.0002493356953055802,
1705
- "loss": 1.58,
1706
- "step": 28300
1707
- },
1708
- {
1709
- "epoch": 5.03,
1710
- "learning_rate": 0.00024844995571302037,
1711
- "loss": 1.5345,
1712
- "step": 28400
1713
- },
1714
- {
1715
- "epoch": 5.05,
1716
- "learning_rate": 0.0002475642161204606,
1717
- "loss": 1.5501,
1718
- "step": 28500
1719
- },
1720
- {
1721
- "epoch": 5.07,
1722
- "learning_rate": 0.0002466784765279008,
1723
- "loss": 1.5667,
1724
- "step": 28600
1725
- },
1726
- {
1727
- "epoch": 5.08,
1728
- "learning_rate": 0.00024579273693534103,
1729
- "loss": 1.5045,
1730
- "step": 28700
1731
- },
1732
- {
1733
- "epoch": 5.1,
1734
- "learning_rate": 0.00024490699734278125,
1735
- "loss": 1.5721,
1736
- "step": 28800
1737
- },
1738
- {
1739
- "epoch": 5.12,
1740
- "learning_rate": 0.00024402125775022145,
1741
- "loss": 1.5339,
1742
- "step": 28900
1743
- },
1744
- {
1745
- "epoch": 5.14,
1746
- "learning_rate": 0.00024313551815766167,
1747
- "loss": 1.5543,
1748
- "step": 29000
1749
- },
1750
- {
1751
- "epoch": 5.15,
1752
- "learning_rate": 0.00024224977856510187,
1753
- "loss": 1.5568,
1754
- "step": 29100
1755
- },
1756
- {
1757
- "epoch": 5.17,
1758
- "learning_rate": 0.0002413640389725421,
1759
- "loss": 1.5496,
1760
- "step": 29200
1761
- },
1762
- {
1763
- "epoch": 5.19,
1764
- "learning_rate": 0.00024047829937998228,
1765
- "loss": 1.5492,
1766
- "step": 29300
1767
- },
1768
- {
1769
- "epoch": 5.21,
1770
- "learning_rate": 0.0002395925597874225,
1771
- "loss": 1.571,
1772
- "step": 29400
1773
- },
1774
- {
1775
- "epoch": 5.23,
1776
- "learning_rate": 0.00023870682019486273,
1777
- "loss": 1.5495,
1778
- "step": 29500
1779
- },
1780
- {
1781
- "epoch": 5.24,
1782
- "learning_rate": 0.00023782108060230292,
1783
- "loss": 1.538,
1784
- "step": 29600
1785
- },
1786
- {
1787
- "epoch": 5.26,
1788
- "learning_rate": 0.00023693534100974314,
1789
- "loss": 1.5464,
1790
- "step": 29700
1791
- },
1792
- {
1793
- "epoch": 5.28,
1794
- "learning_rate": 0.00023604960141718334,
1795
- "loss": 1.5523,
1796
- "step": 29800
1797
- },
1798
- {
1799
- "epoch": 5.3,
1800
- "learning_rate": 0.00023516386182462356,
1801
- "loss": 1.526,
1802
- "step": 29900
1803
- },
1804
- {
1805
- "epoch": 5.31,
1806
- "learning_rate": 0.00023427812223206375,
1807
- "loss": 1.5692,
1808
- "step": 30000
1809
- },
1810
- {
1811
- "epoch": 5.33,
1812
- "learning_rate": 0.000233392382639504,
1813
- "loss": 1.548,
1814
- "step": 30100
1815
- },
1816
- {
1817
- "epoch": 5.35,
1818
- "learning_rate": 0.00023250664304694422,
1819
- "loss": 1.575,
1820
- "step": 30200
1821
- },
1822
- {
1823
- "epoch": 5.37,
1824
- "learning_rate": 0.00023162090345438442,
1825
- "loss": 1.5104,
1826
- "step": 30300
1827
- },
1828
- {
1829
- "epoch": 5.39,
1830
- "learning_rate": 0.00023073516386182464,
1831
- "loss": 1.558,
1832
- "step": 30400
1833
- },
1834
- {
1835
- "epoch": 5.4,
1836
- "learning_rate": 0.00022984942426926484,
1837
- "loss": 1.5481,
1838
- "step": 30500
1839
- },
1840
- {
1841
- "epoch": 5.42,
1842
- "learning_rate": 0.00022896368467670506,
1843
- "loss": 1.5538,
1844
- "step": 30600
1845
- },
1846
- {
1847
- "epoch": 5.44,
1848
- "learning_rate": 0.00022807794508414525,
1849
- "loss": 1.4957,
1850
- "step": 30700
1851
- },
1852
- {
1853
- "epoch": 5.46,
1854
- "learning_rate": 0.00022719220549158547,
1855
- "loss": 1.5547,
1856
- "step": 30800
1857
- },
1858
- {
1859
- "epoch": 5.47,
1860
- "learning_rate": 0.0002263064658990257,
1861
- "loss": 1.573,
1862
- "step": 30900
1863
- },
1864
- {
1865
- "epoch": 5.49,
1866
- "learning_rate": 0.0002254207263064659,
1867
- "loss": 1.5508,
1868
- "step": 31000
1869
- },
1870
- {
1871
- "epoch": 5.51,
1872
- "learning_rate": 0.0002245349867139061,
1873
- "loss": 1.5452,
1874
- "step": 31100
1875
- },
1876
- {
1877
- "epoch": 5.53,
1878
- "learning_rate": 0.00022364924712134633,
1879
- "loss": 1.5031,
1880
- "step": 31200
1881
- },
1882
- {
1883
- "epoch": 5.54,
1884
- "learning_rate": 0.00022276350752878656,
1885
- "loss": 1.5238,
1886
- "step": 31300
1887
- },
1888
- {
1889
- "epoch": 5.56,
1890
- "learning_rate": 0.00022187776793622675,
1891
- "loss": 1.5511,
1892
- "step": 31400
1893
- },
1894
- {
1895
- "epoch": 5.58,
1896
- "learning_rate": 0.00022099202834366697,
1897
- "loss": 1.5784,
1898
- "step": 31500
1899
- },
1900
- {
1901
- "epoch": 5.6,
1902
- "learning_rate": 0.0002201062887511072,
1903
- "loss": 1.5487,
1904
- "step": 31600
1905
- },
1906
- {
1907
- "epoch": 5.62,
1908
- "learning_rate": 0.0002192205491585474,
1909
- "loss": 1.5496,
1910
- "step": 31700
1911
- },
1912
- {
1913
- "epoch": 5.63,
1914
- "learning_rate": 0.0002183348095659876,
1915
- "loss": 1.5414,
1916
- "step": 31800
1917
- },
1918
- {
1919
- "epoch": 5.65,
1920
- "learning_rate": 0.0002174490699734278,
1921
- "loss": 1.5677,
1922
- "step": 31900
1923
- },
1924
- {
1925
- "epoch": 5.67,
1926
- "learning_rate": 0.00021656333038086803,
1927
- "loss": 1.5408,
1928
- "step": 32000
1929
- },
1930
- {
1931
- "epoch": 5.69,
1932
- "learning_rate": 0.00021567759078830822,
1933
- "loss": 1.5122,
1934
- "step": 32100
1935
- },
1936
- {
1937
- "epoch": 5.7,
1938
- "learning_rate": 0.00021479185119574845,
1939
- "loss": 1.5275,
1940
- "step": 32200
1941
- },
1942
- {
1943
- "epoch": 5.72,
1944
- "learning_rate": 0.00021390611160318867,
1945
- "loss": 1.5314,
1946
- "step": 32300
1947
- },
1948
- {
1949
- "epoch": 5.74,
1950
- "learning_rate": 0.0002130203720106289,
1951
- "loss": 1.5405,
1952
- "step": 32400
1953
- },
1954
- {
1955
- "epoch": 5.76,
1956
- "learning_rate": 0.0002121346324180691,
1957
- "loss": 1.5039,
1958
- "step": 32500
1959
- },
1960
- {
1961
- "epoch": 5.77,
1962
- "learning_rate": 0.0002112488928255093,
1963
- "loss": 1.5173,
1964
- "step": 32600
1965
- },
1966
- {
1967
- "epoch": 5.79,
1968
- "learning_rate": 0.00021036315323294953,
1969
- "loss": 1.564,
1970
- "step": 32700
1971
- },
1972
- {
1973
- "epoch": 5.81,
1974
- "learning_rate": 0.00020947741364038972,
1975
- "loss": 1.5666,
1976
- "step": 32800
1977
- },
1978
- {
1979
- "epoch": 5.83,
1980
- "learning_rate": 0.00020859167404782994,
1981
- "loss": 1.5539,
1982
- "step": 32900
1983
- },
1984
- {
1985
- "epoch": 5.85,
1986
- "learning_rate": 0.00020770593445527017,
1987
- "loss": 1.5436,
1988
- "step": 33000
1989
- },
1990
- {
1991
- "epoch": 5.86,
1992
- "learning_rate": 0.00020682019486271036,
1993
- "loss": 1.5431,
1994
- "step": 33100
1995
- },
1996
- {
1997
- "epoch": 5.88,
1998
- "learning_rate": 0.00020593445527015058,
1999
- "loss": 1.5364,
2000
- "step": 33200
2001
- },
2002
- {
2003
- "epoch": 5.9,
2004
- "learning_rate": 0.00020504871567759078,
2005
- "loss": 1.5186,
2006
- "step": 33300
2007
- },
2008
- {
2009
- "epoch": 5.92,
2010
- "learning_rate": 0.000204162976085031,
2011
- "loss": 1.5308,
2012
- "step": 33400
2013
- },
2014
- {
2015
- "epoch": 5.93,
2016
- "learning_rate": 0.0002032772364924712,
2017
- "loss": 1.5218,
2018
- "step": 33500
2019
- },
2020
- {
2021
- "epoch": 5.95,
2022
- "learning_rate": 0.00020239149689991144,
2023
- "loss": 1.547,
2024
- "step": 33600
2025
- },
2026
- {
2027
- "epoch": 5.97,
2028
- "learning_rate": 0.00020150575730735166,
2029
- "loss": 1.554,
2030
- "step": 33700
2031
- },
2032
- {
2033
- "epoch": 5.99,
2034
- "learning_rate": 0.00020062001771479186,
2035
- "loss": 1.5563,
2036
- "step": 33800
2037
- },
2038
- {
2039
- "epoch": 6.01,
2040
- "learning_rate": 0.00019973427812223208,
2041
- "loss": 1.5311,
2042
- "step": 33900
2043
- },
2044
- {
2045
- "epoch": 6.02,
2046
- "learning_rate": 0.00019884853852967228,
2047
- "loss": 1.4537,
2048
- "step": 34000
2049
- },
2050
- {
2051
- "epoch": 6.04,
2052
- "learning_rate": 0.0001979627989371125,
2053
- "loss": 1.4493,
2054
- "step": 34100
2055
- },
2056
- {
2057
- "epoch": 6.06,
2058
- "learning_rate": 0.0001970770593445527,
2059
- "loss": 1.462,
2060
- "step": 34200
2061
- },
2062
- {
2063
- "epoch": 6.08,
2064
- "learning_rate": 0.00019619131975199291,
2065
- "loss": 1.4879,
2066
- "step": 34300
2067
- },
2068
- {
2069
- "epoch": 6.09,
2070
- "learning_rate": 0.00019530558015943314,
2071
- "loss": 1.46,
2072
- "step": 34400
2073
- },
2074
- {
2075
- "epoch": 6.11,
2076
- "learning_rate": 0.00019441984056687333,
2077
- "loss": 1.4318,
2078
- "step": 34500
2079
- },
2080
- {
2081
- "epoch": 6.13,
2082
- "learning_rate": 0.00019353410097431355,
2083
- "loss": 1.448,
2084
- "step": 34600
2085
- },
2086
- {
2087
- "epoch": 6.15,
2088
- "learning_rate": 0.00019264836138175375,
2089
- "loss": 1.4615,
2090
- "step": 34700
2091
- },
2092
- {
2093
- "epoch": 6.16,
2094
- "learning_rate": 0.000191762621789194,
2095
- "loss": 1.4537,
2096
- "step": 34800
2097
- },
2098
- {
2099
- "epoch": 6.18,
2100
- "learning_rate": 0.0001908768821966342,
2101
- "loss": 1.4697,
2102
- "step": 34900
2103
- },
2104
- {
2105
- "epoch": 6.2,
2106
- "learning_rate": 0.00018999114260407441,
2107
- "loss": 1.4502,
2108
- "step": 35000
2109
- },
2110
- {
2111
- "epoch": 6.22,
2112
- "learning_rate": 0.00018910540301151464,
2113
- "loss": 1.4421,
2114
- "step": 35100
2115
- },
2116
- {
2117
- "epoch": 6.24,
2118
- "learning_rate": 0.00018821966341895483,
2119
- "loss": 1.456,
2120
- "step": 35200
2121
- },
2122
- {
2123
- "epoch": 6.25,
2124
- "learning_rate": 0.00018733392382639505,
2125
- "loss": 1.4647,
2126
- "step": 35300
2127
- },
2128
- {
2129
- "epoch": 6.27,
2130
- "learning_rate": 0.00018644818423383525,
2131
- "loss": 1.4854,
2132
- "step": 35400
2133
- },
2134
- {
2135
- "epoch": 6.29,
2136
- "learning_rate": 0.00018556244464127547,
2137
- "loss": 1.4589,
2138
- "step": 35500
2139
- },
2140
- {
2141
- "epoch": 6.31,
2142
- "learning_rate": 0.00018467670504871566,
2143
- "loss": 1.4537,
2144
- "step": 35600
2145
- },
2146
- {
2147
- "epoch": 6.32,
2148
- "learning_rate": 0.00018379096545615589,
2149
- "loss": 1.4602,
2150
- "step": 35700
2151
- },
2152
- {
2153
- "epoch": 6.34,
2154
- "learning_rate": 0.0001829052258635961,
2155
- "loss": 1.487,
2156
- "step": 35800
2157
- },
2158
- {
2159
- "epoch": 6.36,
2160
- "learning_rate": 0.00018201948627103633,
2161
- "loss": 1.4731,
2162
- "step": 35900
2163
- },
2164
- {
2165
- "epoch": 6.38,
2166
- "learning_rate": 0.00018113374667847655,
2167
- "loss": 1.4487,
2168
- "step": 36000
2169
- },
2170
- {
2171
- "epoch": 6.4,
2172
- "learning_rate": 0.00018024800708591675,
2173
- "loss": 1.4505,
2174
- "step": 36100
2175
- },
2176
- {
2177
- "epoch": 6.41,
2178
- "learning_rate": 0.00017936226749335697,
2179
- "loss": 1.4525,
2180
- "step": 36200
2181
- },
2182
- {
2183
- "epoch": 6.43,
2184
- "learning_rate": 0.00017847652790079716,
2185
- "loss": 1.4717,
2186
- "step": 36300
2187
- },
2188
- {
2189
- "epoch": 6.45,
2190
- "learning_rate": 0.00017759078830823738,
2191
- "loss": 1.4803,
2192
- "step": 36400
2193
- },
2194
- {
2195
- "epoch": 6.47,
2196
- "learning_rate": 0.0001767050487156776,
2197
- "loss": 1.4443,
2198
- "step": 36500
2199
- },
2200
- {
2201
- "epoch": 6.48,
2202
- "learning_rate": 0.0001758193091231178,
2203
- "loss": 1.4659,
2204
- "step": 36600
2205
- },
2206
- {
2207
- "epoch": 6.5,
2208
- "learning_rate": 0.00017493356953055802,
2209
- "loss": 1.4918,
2210
- "step": 36700
2211
- },
2212
- {
2213
- "epoch": 6.52,
2214
- "learning_rate": 0.00017404782993799822,
2215
- "loss": 1.4444,
2216
- "step": 36800
2217
- },
2218
- {
2219
- "epoch": 6.54,
2220
- "learning_rate": 0.00017316209034543844,
2221
- "loss": 1.4804,
2222
- "step": 36900
2223
- },
2224
- {
2225
- "epoch": 6.55,
2226
- "learning_rate": 0.00017227635075287863,
2227
- "loss": 1.4815,
2228
- "step": 37000
2229
- },
2230
- {
2231
- "epoch": 6.57,
2232
- "learning_rate": 0.00017139061116031888,
2233
- "loss": 1.4791,
2234
- "step": 37100
2235
- },
2236
- {
2237
- "epoch": 6.59,
2238
- "learning_rate": 0.0001705048715677591,
2239
- "loss": 1.4677,
2240
- "step": 37200
2241
- },
2242
- {
2243
- "epoch": 6.61,
2244
- "learning_rate": 0.0001696191319751993,
2245
- "loss": 1.4453,
2246
- "step": 37300
2247
- },
2248
- {
2249
- "epoch": 6.63,
2250
- "learning_rate": 0.00016873339238263952,
2251
- "loss": 1.4632,
2252
- "step": 37400
2253
- },
2254
- {
2255
- "epoch": 6.64,
2256
- "learning_rate": 0.00016784765279007972,
2257
- "loss": 1.4676,
2258
- "step": 37500
2259
- },
2260
- {
2261
- "epoch": 6.66,
2262
- "learning_rate": 0.00016696191319751994,
2263
- "loss": 1.4879,
2264
- "step": 37600
2265
- },
2266
- {
2267
- "epoch": 6.68,
2268
- "learning_rate": 0.00016607617360496013,
2269
- "loss": 1.4755,
2270
- "step": 37700
2271
- },
2272
- {
2273
- "epoch": 6.7,
2274
- "learning_rate": 0.00016519043401240036,
2275
- "loss": 1.4617,
2276
- "step": 37800
2277
- },
2278
- {
2279
- "epoch": 6.71,
2280
- "learning_rate": 0.00016430469441984058,
2281
- "loss": 1.4597,
2282
- "step": 37900
2283
- },
2284
- {
2285
- "epoch": 6.73,
2286
- "learning_rate": 0.00016341895482728077,
2287
- "loss": 1.4442,
2288
- "step": 38000
2289
- },
2290
- {
2291
- "epoch": 6.75,
2292
- "learning_rate": 0.000162533215234721,
2293
- "loss": 1.4734,
2294
- "step": 38100
2295
- },
2296
- {
2297
- "epoch": 6.77,
2298
- "learning_rate": 0.0001616474756421612,
2299
- "loss": 1.471,
2300
- "step": 38200
2301
- },
2302
- {
2303
- "epoch": 6.78,
2304
- "learning_rate": 0.00016076173604960144,
2305
- "loss": 1.4606,
2306
- "step": 38300
2307
- },
2308
- {
2309
- "epoch": 6.8,
2310
- "learning_rate": 0.00015987599645704163,
2311
- "loss": 1.4626,
2312
- "step": 38400
2313
- },
2314
- {
2315
- "epoch": 6.82,
2316
- "learning_rate": 0.00015899025686448185,
2317
- "loss": 1.4648,
2318
- "step": 38500
2319
- },
2320
- {
2321
- "epoch": 6.84,
2322
- "learning_rate": 0.00015810451727192208,
2323
- "loss": 1.4665,
2324
- "step": 38600
2325
- },
2326
- {
2327
- "epoch": 6.86,
2328
- "learning_rate": 0.00015721877767936227,
2329
- "loss": 1.4483,
2330
- "step": 38700
2331
- },
2332
- {
2333
- "epoch": 6.87,
2334
- "learning_rate": 0.0001563330380868025,
2335
- "loss": 1.4638,
2336
- "step": 38800
2337
- },
2338
- {
2339
- "epoch": 6.89,
2340
- "learning_rate": 0.0001554472984942427,
2341
- "loss": 1.4695,
2342
- "step": 38900
2343
- },
2344
- {
2345
- "epoch": 6.91,
2346
- "learning_rate": 0.0001545615589016829,
2347
- "loss": 1.4487,
2348
- "step": 39000
2349
- },
2350
- {
2351
- "epoch": 6.93,
2352
- "learning_rate": 0.0001536758193091231,
2353
- "loss": 1.4547,
2354
- "step": 39100
2355
- },
2356
- {
2357
- "epoch": 6.94,
2358
- "learning_rate": 0.00015279007971656333,
2359
- "loss": 1.4757,
2360
- "step": 39200
2361
- },
2362
- {
2363
- "epoch": 6.96,
2364
- "learning_rate": 0.00015190434012400355,
2365
- "loss": 1.4709,
2366
- "step": 39300
2367
- },
2368
- {
2369
- "epoch": 6.98,
2370
- "learning_rate": 0.00015101860053144374,
2371
- "loss": 1.438,
2372
- "step": 39400
2373
- },
2374
- {
2375
- "epoch": 7.0,
2376
- "learning_rate": 0.000150132860938884,
2377
- "loss": 1.4504,
2378
- "step": 39500
2379
- },
2380
- {
2381
- "epoch": 7.02,
2382
- "learning_rate": 0.00014924712134632419,
2383
- "loss": 1.4182,
2384
- "step": 39600
2385
- },
2386
- {
2387
- "epoch": 7.03,
2388
- "learning_rate": 0.0001483613817537644,
2389
- "loss": 1.3538,
2390
- "step": 39700
2391
- },
2392
- {
2393
- "epoch": 7.05,
2394
- "learning_rate": 0.0001474756421612046,
2395
- "loss": 1.3627,
2396
- "step": 39800
2397
- },
2398
- {
2399
- "epoch": 7.07,
2400
- "learning_rate": 0.00014658990256864482,
2401
- "loss": 1.3909,
2402
- "step": 39900
2403
- },
2404
- {
2405
- "epoch": 7.09,
2406
- "learning_rate": 0.00014570416297608505,
2407
- "loss": 1.4015,
2408
- "step": 40000
2409
- },
2410
- {
2411
- "epoch": 7.1,
2412
- "learning_rate": 0.00014481842338352524,
2413
- "loss": 1.4001,
2414
- "step": 40100
2415
- },
2416
- {
2417
- "epoch": 7.12,
2418
- "learning_rate": 0.00014393268379096546,
2419
- "loss": 1.3875,
2420
- "step": 40200
2421
- },
2422
- {
2423
- "epoch": 7.14,
2424
- "learning_rate": 0.00014304694419840566,
2425
- "loss": 1.4087,
2426
- "step": 40300
2427
- },
2428
- {
2429
- "epoch": 7.16,
2430
- "learning_rate": 0.00014216120460584588,
2431
- "loss": 1.4053,
2432
- "step": 40400
2433
- },
2434
- {
2435
- "epoch": 7.17,
2436
- "learning_rate": 0.00014127546501328607,
2437
- "loss": 1.3912,
2438
- "step": 40500
2439
- },
2440
- {
2441
- "epoch": 7.19,
2442
- "learning_rate": 0.00014038972542072632,
2443
- "loss": 1.4045,
2444
- "step": 40600
2445
- },
2446
- {
2447
- "epoch": 7.21,
2448
- "learning_rate": 0.00013950398582816655,
2449
- "loss": 1.3781,
2450
- "step": 40700
2451
- },
2452
- {
2453
- "epoch": 7.23,
2454
- "learning_rate": 0.00013861824623560674,
2455
- "loss": 1.4017,
2456
- "step": 40800
2457
- },
2458
- {
2459
- "epoch": 7.25,
2460
- "learning_rate": 0.00013773250664304696,
2461
- "loss": 1.3905,
2462
- "step": 40900
2463
- },
2464
- {
2465
- "epoch": 7.26,
2466
- "learning_rate": 0.00013684676705048716,
2467
- "loss": 1.4088,
2468
- "step": 41000
2469
- },
2470
- {
2471
- "epoch": 7.28,
2472
- "learning_rate": 0.00013596102745792738,
2473
- "loss": 1.427,
2474
- "step": 41100
2475
- },
2476
- {
2477
- "epoch": 7.3,
2478
- "learning_rate": 0.00013507528786536757,
2479
- "loss": 1.3799,
2480
- "step": 41200
2481
- },
2482
- {
2483
- "epoch": 7.32,
2484
- "learning_rate": 0.0001341895482728078,
2485
- "loss": 1.3973,
2486
- "step": 41300
2487
- },
2488
- {
2489
- "epoch": 7.33,
2490
- "learning_rate": 0.00013330380868024802,
2491
- "loss": 1.4444,
2492
- "step": 41400
2493
- },
2494
- {
2495
- "epoch": 7.35,
2496
- "learning_rate": 0.0001324180690876882,
2497
- "loss": 1.3977,
2498
- "step": 41500
2499
- },
2500
- {
2501
- "epoch": 7.37,
2502
- "learning_rate": 0.00013153232949512843,
2503
- "loss": 1.413,
2504
- "step": 41600
2505
- },
2506
- {
2507
- "epoch": 7.39,
2508
- "learning_rate": 0.00013064658990256863,
2509
- "loss": 1.3855,
2510
- "step": 41700
2511
- },
2512
- {
2513
- "epoch": 7.4,
2514
- "learning_rate": 0.00012976085031000888,
2515
- "loss": 1.3802,
2516
- "step": 41800
2517
- },
2518
- {
2519
- "epoch": 7.42,
2520
- "learning_rate": 0.00012887511071744907,
2521
- "loss": 1.3871,
2522
- "step": 41900
2523
- },
2524
- {
2525
- "epoch": 7.44,
2526
- "learning_rate": 0.0001279893711248893,
2527
- "loss": 1.3736,
2528
- "step": 42000
2529
- },
2530
- {
2531
- "epoch": 7.46,
2532
- "learning_rate": 0.00012710363153232952,
2533
- "loss": 1.4049,
2534
- "step": 42100
2535
- },
2536
- {
2537
- "epoch": 7.48,
2538
- "learning_rate": 0.0001262178919397697,
2539
- "loss": 1.3547,
2540
- "step": 42200
2541
- },
2542
- {
2543
- "epoch": 7.49,
2544
- "learning_rate": 0.00012533215234720993,
2545
- "loss": 1.3899,
2546
- "step": 42300
2547
- },
2548
- {
2549
- "epoch": 7.51,
2550
- "learning_rate": 0.00012444641275465013,
2551
- "loss": 1.3879,
2552
- "step": 42400
2553
- },
2554
- {
2555
- "epoch": 7.53,
2556
- "learning_rate": 0.00012356067316209035,
2557
- "loss": 1.386,
2558
- "step": 42500
2559
- },
2560
- {
2561
- "epoch": 7.55,
2562
- "learning_rate": 0.00012267493356953057,
2563
- "loss": 1.3889,
2564
- "step": 42600
2565
- },
2566
- {
2567
- "epoch": 7.56,
2568
- "learning_rate": 0.00012178919397697078,
2569
- "loss": 1.4047,
2570
- "step": 42700
2571
- },
2572
- {
2573
- "epoch": 7.58,
2574
- "learning_rate": 0.00012090345438441099,
2575
- "loss": 1.3835,
2576
- "step": 42800
2577
- },
2578
- {
2579
- "epoch": 7.6,
2580
- "learning_rate": 0.0001200177147918512,
2581
- "loss": 1.3969,
2582
- "step": 42900
2583
- },
2584
- {
2585
- "epoch": 7.62,
2586
- "learning_rate": 0.0001191319751992914,
2587
- "loss": 1.4,
2588
- "step": 43000
2589
- },
2590
- {
2591
- "epoch": 7.64,
2592
- "learning_rate": 0.00011824623560673161,
2593
- "loss": 1.3735,
2594
- "step": 43100
2595
- },
2596
- {
2597
- "epoch": 7.65,
2598
- "learning_rate": 0.00011736049601417183,
2599
- "loss": 1.3813,
2600
- "step": 43200
2601
- },
2602
- {
2603
- "epoch": 7.67,
2604
- "learning_rate": 0.00011647475642161206,
2605
- "loss": 1.3986,
2606
- "step": 43300
2607
- },
2608
- {
2609
- "epoch": 7.69,
2610
- "learning_rate": 0.00011558901682905227,
2611
- "loss": 1.3971,
2612
- "step": 43400
2613
- },
2614
- {
2615
- "epoch": 7.71,
2616
- "learning_rate": 0.00011470327723649247,
2617
- "loss": 1.4061,
2618
- "step": 43500
2619
- },
2620
- {
2621
- "epoch": 7.72,
2622
- "learning_rate": 0.00011381753764393268,
2623
- "loss": 1.3679,
2624
- "step": 43600
2625
- },
2626
- {
2627
- "epoch": 7.74,
2628
- "learning_rate": 0.00011293179805137289,
2629
- "loss": 1.3995,
2630
- "step": 43700
2631
- },
2632
- {
2633
- "epoch": 7.76,
2634
- "learning_rate": 0.0001120460584588131,
2635
- "loss": 1.3876,
2636
- "step": 43800
2637
- },
2638
- {
2639
- "epoch": 7.78,
2640
- "learning_rate": 0.00011116031886625333,
2641
- "loss": 1.3797,
2642
- "step": 43900
2643
- },
2644
- {
2645
- "epoch": 7.79,
2646
- "learning_rate": 0.00011027457927369354,
2647
- "loss": 1.3738,
2648
- "step": 44000
2649
- },
2650
- {
2651
- "epoch": 7.81,
2652
- "learning_rate": 0.00010938883968113375,
2653
- "loss": 1.3694,
2654
- "step": 44100
2655
- },
2656
- {
2657
- "epoch": 7.83,
2658
- "learning_rate": 0.00010850310008857396,
2659
- "loss": 1.4214,
2660
- "step": 44200
2661
- },
2662
- {
2663
- "epoch": 7.85,
2664
- "learning_rate": 0.00010761736049601417,
2665
- "loss": 1.4109,
2666
- "step": 44300
2667
- },
2668
- {
2669
- "epoch": 7.87,
2670
- "learning_rate": 0.00010673162090345438,
2671
- "loss": 1.3824,
2672
- "step": 44400
2673
- },
2674
- {
2675
- "epoch": 7.88,
2676
- "learning_rate": 0.0001058458813108946,
2677
- "loss": 1.399,
2678
- "step": 44500
2679
- },
2680
- {
2681
- "epoch": 7.9,
2682
- "learning_rate": 0.00010496014171833482,
2683
- "loss": 1.3917,
2684
- "step": 44600
2685
- },
2686
- {
2687
- "epoch": 7.92,
2688
- "learning_rate": 0.00010407440212577503,
2689
- "loss": 1.422,
2690
- "step": 44700
2691
- },
2692
- {
2693
- "epoch": 7.94,
2694
- "learning_rate": 0.00010318866253321524,
2695
- "loss": 1.3856,
2696
- "step": 44800
2697
- },
2698
- {
2699
- "epoch": 7.95,
2700
- "learning_rate": 0.00010230292294065544,
2701
- "loss": 1.3747,
2702
- "step": 44900
2703
- },
2704
- {
2705
- "epoch": 7.97,
2706
- "learning_rate": 0.00010141718334809567,
2707
- "loss": 1.3847,
2708
- "step": 45000
2709
- },
2710
- {
2711
- "epoch": 7.99,
2712
- "learning_rate": 0.00010053144375553587,
2713
- "loss": 1.3937,
2714
- "step": 45100
2715
- },
2716
- {
2717
- "epoch": 8.01,
2718
- "learning_rate": 9.964570416297608e-05,
2719
- "loss": 1.3614,
2720
- "step": 45200
2721
- },
2722
- {
2723
- "epoch": 8.02,
2724
- "learning_rate": 9.87599645704163e-05,
2725
- "loss": 1.3446,
2726
- "step": 45300
2727
- },
2728
- {
2729
- "epoch": 8.04,
2730
- "learning_rate": 9.787422497785651e-05,
2731
- "loss": 1.3427,
2732
- "step": 45400
2733
- },
2734
- {
2735
- "epoch": 8.06,
2736
- "learning_rate": 9.698848538529672e-05,
2737
- "loss": 1.3139,
2738
- "step": 45500
2739
- },
2740
- {
2741
- "epoch": 8.08,
2742
- "learning_rate": 9.610274579273694e-05,
2743
- "loss": 1.319,
2744
- "step": 45600
2745
- },
2746
- {
2747
- "epoch": 8.1,
2748
- "learning_rate": 9.521700620017715e-05,
2749
- "loss": 1.3558,
2750
- "step": 45700
2751
- },
2752
- {
2753
- "epoch": 8.11,
2754
- "learning_rate": 9.433126660761736e-05,
2755
- "loss": 1.3171,
2756
- "step": 45800
2757
- },
2758
- {
2759
- "epoch": 8.13,
2760
- "learning_rate": 9.344552701505757e-05,
2761
- "loss": 1.3402,
2762
- "step": 45900
2763
- },
2764
- {
2765
- "epoch": 8.15,
2766
- "learning_rate": 9.255978742249779e-05,
2767
- "loss": 1.3222,
2768
- "step": 46000
2769
- },
2770
- {
2771
- "epoch": 8.17,
2772
- "learning_rate": 9.1674047829938e-05,
2773
- "loss": 1.3373,
2774
- "step": 46100
2775
- },
2776
- {
2777
- "epoch": 8.18,
2778
- "learning_rate": 9.078830823737822e-05,
2779
- "loss": 1.3553,
2780
- "step": 46200
2781
- },
2782
- {
2783
- "epoch": 8.2,
2784
- "learning_rate": 8.990256864481843e-05,
2785
- "loss": 1.3406,
2786
- "step": 46300
2787
- },
2788
- {
2789
- "epoch": 8.22,
2790
- "learning_rate": 8.901682905225864e-05,
2791
- "loss": 1.3249,
2792
- "step": 46400
2793
- },
2794
- {
2795
- "epoch": 8.24,
2796
- "learning_rate": 8.813108945969885e-05,
2797
- "loss": 1.3145,
2798
- "step": 46500
2799
- },
2800
- {
2801
- "epoch": 8.26,
2802
- "learning_rate": 8.724534986713905e-05,
2803
- "loss": 1.3527,
2804
- "step": 46600
2805
- },
2806
- {
2807
- "epoch": 8.27,
2808
- "learning_rate": 8.635961027457928e-05,
2809
- "loss": 1.3283,
2810
- "step": 46700
2811
- },
2812
- {
2813
- "epoch": 8.29,
2814
- "learning_rate": 8.54738706820195e-05,
2815
- "loss": 1.3233,
2816
- "step": 46800
2817
- },
2818
- {
2819
- "epoch": 8.31,
2820
- "learning_rate": 8.45881310894597e-05,
2821
- "loss": 1.3495,
2822
- "step": 46900
2823
- },
2824
- {
2825
- "epoch": 8.33,
2826
- "learning_rate": 8.370239149689991e-05,
2827
- "loss": 1.3476,
2828
- "step": 47000
2829
- },
2830
- {
2831
- "epoch": 8.34,
2832
- "learning_rate": 8.281665190434012e-05,
2833
- "loss": 1.3237,
2834
- "step": 47100
2835
- },
2836
- {
2837
- "epoch": 8.36,
2838
- "learning_rate": 8.193091231178033e-05,
2839
- "loss": 1.3465,
2840
- "step": 47200
2841
- },
2842
- {
2843
- "epoch": 8.38,
2844
- "learning_rate": 8.104517271922054e-05,
2845
- "loss": 1.3308,
2846
- "step": 47300
2847
- },
2848
- {
2849
- "epoch": 8.4,
2850
- "learning_rate": 8.015943312666077e-05,
2851
- "loss": 1.3414,
2852
- "step": 47400
2853
- },
2854
- {
2855
- "epoch": 8.41,
2856
- "learning_rate": 7.927369353410098e-05,
2857
- "loss": 1.3329,
2858
- "step": 47500
2859
- },
2860
- {
2861
- "epoch": 8.43,
2862
- "learning_rate": 7.838795394154119e-05,
2863
- "loss": 1.346,
2864
- "step": 47600
2865
- },
2866
- {
2867
- "epoch": 8.45,
2868
- "learning_rate": 7.75022143489814e-05,
2869
- "loss": 1.3453,
2870
- "step": 47700
2871
- },
2872
- {
2873
- "epoch": 8.47,
2874
- "learning_rate": 7.661647475642161e-05,
2875
- "loss": 1.3197,
2876
- "step": 47800
2877
- },
2878
- {
2879
- "epoch": 8.49,
2880
- "learning_rate": 7.573073516386182e-05,
2881
- "loss": 1.3247,
2882
- "step": 47900
2883
- },
2884
- {
2885
- "epoch": 8.5,
2886
- "learning_rate": 7.484499557130204e-05,
2887
- "loss": 1.3389,
2888
- "step": 48000
2889
- },
2890
- {
2891
- "epoch": 8.52,
2892
- "learning_rate": 7.395925597874226e-05,
2893
- "loss": 1.3421,
2894
- "step": 48100
2895
- },
2896
- {
2897
- "epoch": 8.54,
2898
- "learning_rate": 7.307351638618247e-05,
2899
- "loss": 1.3203,
2900
- "step": 48200
2901
- },
2902
- {
2903
- "epoch": 8.56,
2904
- "learning_rate": 7.218777679362268e-05,
2905
- "loss": 1.3218,
2906
- "step": 48300
2907
- },
2908
- {
2909
- "epoch": 8.57,
2910
- "learning_rate": 7.130203720106288e-05,
2911
- "loss": 1.3637,
2912
- "step": 48400
2913
- },
2914
- {
2915
- "epoch": 8.59,
2916
- "learning_rate": 7.041629760850309e-05,
2917
- "loss": 1.3239,
2918
- "step": 48500
2919
- },
2920
- {
2921
- "epoch": 8.61,
2922
- "learning_rate": 6.953055801594331e-05,
2923
- "loss": 1.3559,
2924
- "step": 48600
2925
- },
2926
- {
2927
- "epoch": 8.63,
2928
- "learning_rate": 6.864481842338352e-05,
2929
- "loss": 1.3263,
2930
- "step": 48700
2931
- },
2932
- {
2933
- "epoch": 8.64,
2934
- "learning_rate": 6.775907883082374e-05,
2935
- "loss": 1.3626,
2936
- "step": 48800
2937
- },
2938
- {
2939
- "epoch": 8.66,
2940
- "learning_rate": 6.687333923826395e-05,
2941
- "loss": 1.3125,
2942
- "step": 48900
2943
- },
2944
- {
2945
- "epoch": 8.68,
2946
- "learning_rate": 6.598759964570416e-05,
2947
- "loss": 1.3079,
2948
- "step": 49000
2949
- },
2950
- {
2951
- "epoch": 8.7,
2952
- "learning_rate": 6.510186005314437e-05,
2953
- "loss": 1.3478,
2954
- "step": 49100
2955
- },
2956
- {
2957
- "epoch": 8.72,
2958
- "learning_rate": 6.421612046058459e-05,
2959
- "loss": 1.3252,
2960
- "step": 49200
2961
- },
2962
- {
2963
- "epoch": 8.73,
2964
- "learning_rate": 6.33303808680248e-05,
2965
- "loss": 1.3619,
2966
- "step": 49300
2967
- },
2968
- {
2969
- "epoch": 8.75,
2970
- "learning_rate": 6.244464127546502e-05,
2971
- "loss": 1.3281,
2972
- "step": 49400
2973
- },
2974
- {
2975
- "epoch": 8.77,
2976
- "learning_rate": 6.155890168290523e-05,
2977
- "loss": 1.316,
2978
- "step": 49500
2979
- },
2980
- {
2981
- "epoch": 8.79,
2982
- "learning_rate": 6.067316209034544e-05,
2983
- "loss": 1.3324,
2984
- "step": 49600
2985
- },
2986
- {
2987
- "epoch": 8.8,
2988
- "learning_rate": 5.9787422497785654e-05,
2989
- "loss": 1.3282,
2990
- "step": 49700
2991
- },
2992
- {
2993
- "epoch": 8.82,
2994
- "learning_rate": 5.890168290522586e-05,
2995
- "loss": 1.3412,
2996
- "step": 49800
2997
- },
2998
- {
2999
- "epoch": 8.84,
3000
- "learning_rate": 5.801594331266608e-05,
3001
- "loss": 1.3228,
3002
- "step": 49900
3003
- },
3004
- {
3005
- "epoch": 8.86,
3006
- "learning_rate": 5.713020372010629e-05,
3007
- "loss": 1.3367,
3008
- "step": 50000
3009
- },
3010
- {
3011
- "epoch": 8.88,
3012
- "learning_rate": 5.62444641275465e-05,
3013
- "loss": 1.3259,
3014
- "step": 50100
3015
- },
3016
- {
3017
- "epoch": 8.89,
3018
- "learning_rate": 5.5358724534986716e-05,
3019
- "loss": 1.3245,
3020
- "step": 50200
3021
- },
3022
- {
3023
- "epoch": 8.91,
3024
- "learning_rate": 5.4472984942426924e-05,
3025
- "loss": 1.3405,
3026
- "step": 50300
3027
- },
3028
- {
3029
- "epoch": 8.93,
3030
- "learning_rate": 5.358724534986714e-05,
3031
- "loss": 1.3278,
3032
- "step": 50400
3033
- },
3034
- {
3035
- "epoch": 8.95,
3036
- "learning_rate": 5.2701505757307354e-05,
3037
- "loss": 1.3012,
3038
- "step": 50500
3039
- },
3040
- {
3041
- "epoch": 8.96,
3042
- "learning_rate": 5.181576616474756e-05,
3043
- "loss": 1.2933,
3044
- "step": 50600
3045
- },
3046
- {
3047
- "epoch": 8.98,
3048
- "learning_rate": 5.093002657218778e-05,
3049
- "loss": 1.3753,
3050
- "step": 50700
3051
- },
3052
- {
3053
- "epoch": 9.0,
3054
- "learning_rate": 5.004428697962799e-05,
3055
- "loss": 1.3211,
3056
- "step": 50800
3057
- },
3058
- {
3059
- "epoch": 9.02,
3060
- "learning_rate": 4.91585473870682e-05,
3061
- "loss": 1.3282,
3062
- "step": 50900
3063
- },
3064
- {
3065
- "epoch": 9.03,
3066
- "learning_rate": 4.827280779450841e-05,
3067
- "loss": 1.2949,
3068
- "step": 51000
3069
- },
3070
- {
3071
- "epoch": 9.05,
3072
- "learning_rate": 4.738706820194863e-05,
3073
- "loss": 1.2804,
3074
- "step": 51100
3075
- },
3076
- {
3077
- "epoch": 9.07,
3078
- "learning_rate": 4.650132860938884e-05,
3079
- "loss": 1.2732,
3080
- "step": 51200
3081
- },
3082
- {
3083
- "epoch": 9.09,
3084
- "learning_rate": 4.561558901682905e-05,
3085
- "loss": 1.2743,
3086
- "step": 51300
3087
- },
3088
- {
3089
- "epoch": 9.11,
3090
- "learning_rate": 4.472984942426927e-05,
3091
- "loss": 1.2978,
3092
- "step": 51400
3093
- },
3094
- {
3095
- "epoch": 9.12,
3096
- "learning_rate": 4.384410983170948e-05,
3097
- "loss": 1.3016,
3098
- "step": 51500
3099
- },
3100
- {
3101
- "epoch": 9.14,
3102
- "learning_rate": 4.2958370239149686e-05,
3103
- "loss": 1.3,
3104
- "step": 51600
3105
- },
3106
- {
3107
- "epoch": 9.16,
3108
- "learning_rate": 4.20726306465899e-05,
3109
- "loss": 1.2877,
3110
- "step": 51700
3111
- },
3112
- {
3113
- "epoch": 9.18,
3114
- "learning_rate": 4.1186891054030117e-05,
3115
- "loss": 1.2664,
3116
- "step": 51800
3117
- },
3118
- {
3119
- "epoch": 9.19,
3120
- "learning_rate": 4.030115146147033e-05,
3121
- "loss": 1.2769,
3122
- "step": 51900
3123
- },
3124
- {
3125
- "epoch": 9.21,
3126
- "learning_rate": 3.941541186891054e-05,
3127
- "loss": 1.2926,
3128
- "step": 52000
3129
- },
3130
- {
3131
- "epoch": 9.23,
3132
- "learning_rate": 3.8529672276350755e-05,
3133
- "loss": 1.2731,
3134
- "step": 52100
3135
- },
3136
- {
3137
- "epoch": 9.25,
3138
- "learning_rate": 3.764393268379097e-05,
3139
- "loss": 1.2806,
3140
- "step": 52200
3141
- },
3142
- {
3143
- "epoch": 9.26,
3144
- "learning_rate": 3.675819309123118e-05,
3145
- "loss": 1.2822,
3146
- "step": 52300
3147
- },
3148
- {
3149
- "epoch": 9.28,
3150
- "learning_rate": 3.587245349867139e-05,
3151
- "loss": 1.2866,
3152
- "step": 52400
3153
- },
3154
- {
3155
- "epoch": 9.3,
3156
- "learning_rate": 3.498671390611161e-05,
3157
- "loss": 1.29,
3158
- "step": 52500
3159
- },
3160
- {
3161
- "epoch": 9.32,
3162
- "learning_rate": 3.410097431355182e-05,
3163
- "loss": 1.2734,
3164
- "step": 52600
3165
- },
3166
- {
3167
- "epoch": 9.34,
3168
- "learning_rate": 3.3215234720992025e-05,
3169
- "loss": 1.309,
3170
- "step": 52700
3171
- },
3172
- {
3173
- "epoch": 9.35,
3174
- "learning_rate": 3.232949512843225e-05,
3175
- "loss": 1.2796,
3176
- "step": 52800
3177
- },
3178
- {
3179
- "epoch": 9.37,
3180
- "learning_rate": 3.1443755535872456e-05,
3181
- "loss": 1.2581,
3182
- "step": 52900
3183
- },
3184
- {
3185
- "epoch": 9.39,
3186
- "learning_rate": 3.0558015943312664e-05,
3187
- "loss": 1.2936,
3188
- "step": 53000
3189
- },
3190
- {
3191
- "epoch": 9.41,
3192
- "learning_rate": 2.967227635075288e-05,
3193
- "loss": 1.3346,
3194
- "step": 53100
3195
- },
3196
- {
3197
- "epoch": 9.42,
3198
- "learning_rate": 2.878653675819309e-05,
3199
- "loss": 1.3168,
3200
- "step": 53200
3201
- },
3202
- {
3203
- "epoch": 9.44,
3204
- "learning_rate": 2.7900797165633306e-05,
3205
- "loss": 1.3255,
3206
- "step": 53300
3207
- },
3208
- {
3209
- "epoch": 9.46,
3210
- "learning_rate": 2.7015057573073517e-05,
3211
- "loss": 1.2798,
3212
- "step": 53400
3213
- },
3214
- {
3215
- "epoch": 9.48,
3216
- "learning_rate": 2.612931798051373e-05,
3217
- "loss": 1.2846,
3218
- "step": 53500
3219
- },
3220
- {
3221
- "epoch": 9.5,
3222
- "learning_rate": 2.5243578387953944e-05,
3223
- "loss": 1.2615,
3224
- "step": 53600
3225
- },
3226
- {
3227
- "epoch": 9.51,
3228
- "learning_rate": 2.4357838795394153e-05,
3229
- "loss": 1.2692,
3230
- "step": 53700
3231
- },
3232
- {
3233
- "epoch": 9.53,
3234
- "learning_rate": 2.3472099202834368e-05,
3235
- "loss": 1.2845,
3236
- "step": 53800
3237
- },
3238
- {
3239
- "epoch": 9.55,
3240
- "learning_rate": 2.258635961027458e-05,
3241
- "loss": 1.284,
3242
- "step": 53900
3243
- },
3244
- {
3245
- "epoch": 9.57,
3246
- "learning_rate": 2.170062001771479e-05,
3247
- "loss": 1.3194,
3248
- "step": 54000
3249
  }
3250
  ],
3251
  "max_steps": 56450,
3252
  "num_train_epochs": 10,
3253
- "total_flos": 1.0185474088615219e+18,
3254
  "trial_name": null,
3255
  "trial_params": null
3256
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 2.4800495992205835,
5
+ "global_step": 14000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
9
  "log_history": [
10
  {
11
  "epoch": 0.02,
12
+ "learning_rate": 9.982285208148806e-06,
13
+ "loss": 1.2518,
14
  "step": 100
15
  },
16
  {
17
  "epoch": 0.04,
18
+ "learning_rate": 9.964570416297609e-06,
19
+ "loss": 1.2505,
20
  "step": 200
21
  },
22
  {
23
  "epoch": 0.05,
24
+ "learning_rate": 9.946855624446414e-06,
25
+ "loss": 1.2781,
26
  "step": 300
27
  },
28
  {
29
  "epoch": 0.07,
30
+ "learning_rate": 9.929140832595217e-06,
31
+ "loss": 1.2509,
32
  "step": 400
33
  },
34
  {
35
  "epoch": 0.09,
36
+ "learning_rate": 9.911426040744022e-06,
37
+ "loss": 1.2275,
38
  "step": 500
39
  },
40
  {
41
  "epoch": 0.11,
42
+ "learning_rate": 9.893711248892827e-06,
43
+ "loss": 1.2583,
44
  "step": 600
45
  },
46
  {
47
  "epoch": 0.12,
48
+ "learning_rate": 9.87599645704163e-06,
49
+ "loss": 1.2391,
50
  "step": 700
51
  },
52
  {
53
  "epoch": 0.14,
54
+ "learning_rate": 9.858281665190435e-06,
55
+ "loss": 1.2406,
56
  "step": 800
57
  },
58
  {
59
  "epoch": 0.16,
60
+ "learning_rate": 9.840566873339238e-06,
61
+ "loss": 1.2467,
62
  "step": 900
63
  },
64
  {
65
  "epoch": 0.18,
66
+ "learning_rate": 9.822852081488043e-06,
67
+ "loss": 1.251,
68
  "step": 1000
69
  },
70
  {
71
  "epoch": 0.19,
72
+ "learning_rate": 9.805137289636848e-06,
73
+ "loss": 1.2033,
74
  "step": 1100
75
  },
76
  {
77
  "epoch": 0.21,
78
+ "learning_rate": 9.787422497785651e-06,
79
+ "loss": 1.2345,
80
  "step": 1200
81
  },
82
  {
83
  "epoch": 0.23,
84
+ "learning_rate": 9.769707705934456e-06,
85
+ "loss": 1.2463,
86
  "step": 1300
87
  },
88
  {
89
  "epoch": 0.25,
90
+ "learning_rate": 9.751992914083261e-06,
91
+ "loss": 1.237,
92
  "step": 1400
93
  },
94
  {
95
  "epoch": 0.27,
96
+ "learning_rate": 9.734278122232064e-06,
97
+ "loss": 1.2276,
98
  "step": 1500
99
  },
100
  {
101
  "epoch": 0.28,
102
+ "learning_rate": 9.71656333038087e-06,
103
+ "loss": 1.2274,
104
  "step": 1600
105
  },
106
  {
107
  "epoch": 0.3,
108
+ "learning_rate": 9.698848538529672e-06,
109
+ "loss": 1.2487,
110
  "step": 1700
111
  },
112
  {
113
  "epoch": 0.32,
114
+ "learning_rate": 9.681133746678477e-06,
115
+ "loss": 1.2168,
116
  "step": 1800
117
  },
118
  {
119
  "epoch": 0.34,
120
+ "learning_rate": 9.663418954827282e-06,
121
+ "loss": 1.2465,
122
  "step": 1900
123
  },
124
  {
125
  "epoch": 0.35,
126
+ "learning_rate": 9.645704162976086e-06,
127
+ "loss": 1.2375,
128
  "step": 2000
129
  },
130
  {
131
  "epoch": 0.37,
132
+ "learning_rate": 9.627989371124889e-06,
133
+ "loss": 1.2178,
134
  "step": 2100
135
  },
136
  {
137
  "epoch": 0.39,
138
+ "learning_rate": 9.610274579273694e-06,
139
+ "loss": 1.2438,
140
  "step": 2200
141
  },
142
  {
143
  "epoch": 0.41,
144
+ "learning_rate": 9.592559787422499e-06,
145
+ "loss": 1.2365,
146
  "step": 2300
147
  },
148
  {
149
  "epoch": 0.43,
150
+ "learning_rate": 9.574844995571303e-06,
151
+ "loss": 1.2508,
152
  "step": 2400
153
  },
154
  {
155
  "epoch": 0.44,
156
+ "learning_rate": 9.557130203720107e-06,
157
+ "loss": 1.2316,
158
  "step": 2500
159
  },
160
  {
161
  "epoch": 0.46,
162
+ "learning_rate": 9.539415411868912e-06,
163
+ "loss": 1.2448,
164
  "step": 2600
165
  },
166
  {
167
  "epoch": 0.48,
168
+ "learning_rate": 9.521700620017715e-06,
169
+ "loss": 1.2259,
170
  "step": 2700
171
  },
172
  {
173
  "epoch": 0.5,
174
+ "learning_rate": 9.50398582816652e-06,
175
+ "loss": 1.2091,
176
  "step": 2800
177
  },
178
  {
179
  "epoch": 0.51,
180
+ "learning_rate": 9.486271036315325e-06,
181
+ "loss": 1.2292,
182
  "step": 2900
183
  },
184
  {
185
  "epoch": 0.53,
186
+ "learning_rate": 9.46855624446413e-06,
187
+ "loss": 1.2013,
188
  "step": 3000
189
  },
190
  {
191
  "epoch": 0.55,
192
+ "learning_rate": 9.450841452612933e-06,
193
+ "loss": 1.2216,
194
  "step": 3100
195
  },
196
  {
197
  "epoch": 0.57,
198
+ "learning_rate": 9.433126660761736e-06,
199
+ "loss": 1.2353,
200
  "step": 3200
201
  },
202
  {
203
  "epoch": 0.58,
204
+ "learning_rate": 9.415411868910541e-06,
205
+ "loss": 1.2189,
206
  "step": 3300
207
  },
208
  {
209
  "epoch": 0.6,
210
+ "learning_rate": 9.397697077059346e-06,
211
+ "loss": 1.2103,
212
  "step": 3400
213
  },
214
  {
215
  "epoch": 0.62,
216
+ "learning_rate": 9.379982285208149e-06,
217
+ "loss": 1.2514,
218
  "step": 3500
219
  },
220
  {
221
  "epoch": 0.64,
222
+ "learning_rate": 9.362267493356954e-06,
223
+ "loss": 1.2227,
224
  "step": 3600
225
  },
226
  {
227
  "epoch": 0.66,
228
+ "learning_rate": 9.344552701505759e-06,
229
+ "loss": 1.2287,
230
  "step": 3700
231
  },
232
  {
233
  "epoch": 0.67,
234
+ "learning_rate": 9.326837909654562e-06,
235
+ "loss": 1.2374,
236
  "step": 3800
237
  },
238
  {
239
  "epoch": 0.69,
240
+ "learning_rate": 9.309123117803367e-06,
241
+ "loss": 1.2078,
242
  "step": 3900
243
  },
244
  {
245
  "epoch": 0.71,
246
+ "learning_rate": 9.29140832595217e-06,
247
+ "loss": 1.2001,
248
  "step": 4000
249
  },
250
  {
251
  "epoch": 0.73,
252
+ "learning_rate": 9.273693534100975e-06,
253
+ "loss": 1.2325,
254
  "step": 4100
255
  },
256
  {
257
  "epoch": 0.74,
258
+ "learning_rate": 9.25597874224978e-06,
259
+ "loss": 1.2311,
260
  "step": 4200
261
  },
262
  {
263
  "epoch": 0.76,
264
+ "learning_rate": 9.238263950398583e-06,
265
+ "loss": 1.2056,
266
  "step": 4300
267
  },
268
  {
269
  "epoch": 0.78,
270
+ "learning_rate": 9.220549158547388e-06,
271
+ "loss": 1.1852,
272
  "step": 4400
273
  },
274
  {
275
  "epoch": 0.8,
276
+ "learning_rate": 9.202834366696191e-06,
277
+ "loss": 1.2417,
278
  "step": 4500
279
  },
280
  {
281
  "epoch": 0.81,
282
+ "learning_rate": 9.185119574844996e-06,
283
+ "loss": 1.2329,
284
  "step": 4600
285
  },
286
  {
287
  "epoch": 0.83,
288
+ "learning_rate": 9.167404782993801e-06,
289
+ "loss": 1.2252,
290
  "step": 4700
291
  },
292
  {
293
  "epoch": 0.85,
294
+ "learning_rate": 9.149689991142604e-06,
295
+ "loss": 1.2052,
296
  "step": 4800
297
  },
298
  {
299
  "epoch": 0.87,
300
+ "learning_rate": 9.13197519929141e-06,
301
+ "loss": 1.2238,
302
  "step": 4900
303
  },
304
  {
305
  "epoch": 0.89,
306
+ "learning_rate": 9.114260407440213e-06,
307
+ "loss": 1.2166,
308
  "step": 5000
309
  },
310
  {
311
  "epoch": 0.9,
312
+ "learning_rate": 9.096545615589017e-06,
313
+ "loss": 1.2269,
314
  "step": 5100
315
  },
316
  {
317
  "epoch": 0.92,
318
+ "learning_rate": 9.078830823737822e-06,
319
+ "loss": 1.232,
320
  "step": 5200
321
  },
322
  {
323
  "epoch": 0.94,
324
+ "learning_rate": 9.061116031886627e-06,
325
+ "loss": 1.2372,
326
  "step": 5300
327
  },
328
  {
329
  "epoch": 0.96,
330
+ "learning_rate": 9.04340124003543e-06,
331
+ "loss": 1.2281,
332
  "step": 5400
333
  },
334
  {
335
  "epoch": 0.97,
336
+ "learning_rate": 9.025686448184234e-06,
337
+ "loss": 1.2031,
338
  "step": 5500
339
  },
340
  {
341
  "epoch": 0.99,
342
+ "learning_rate": 9.007971656333039e-06,
343
+ "loss": 1.1884,
344
  "step": 5600
345
  },
346
  {
347
  "epoch": 1.01,
348
+ "learning_rate": 8.990256864481844e-06,
349
+ "loss": 1.1951,
350
  "step": 5700
351
  },
352
  {
353
  "epoch": 1.03,
354
+ "learning_rate": 8.972542072630648e-06,
355
+ "loss": 1.2428,
356
  "step": 5800
357
  },
358
  {
359
  "epoch": 1.05,
360
+ "learning_rate": 8.954827280779452e-06,
361
+ "loss": 1.2197,
362
  "step": 5900
363
  },
364
  {
365
  "epoch": 1.06,
366
+ "learning_rate": 8.937112488928255e-06,
367
+ "loss": 1.1972,
368
  "step": 6000
369
  },
370
  {
371
  "epoch": 1.08,
372
+ "learning_rate": 8.91939769707706e-06,
373
+ "loss": 1.1989,
374
  "step": 6100
375
  },
376
  {
377
  "epoch": 1.1,
378
+ "learning_rate": 8.901682905225865e-06,
379
+ "loss": 1.1922,
380
  "step": 6200
381
  },
382
  {
383
  "epoch": 1.12,
384
+ "learning_rate": 8.883968113374668e-06,
385
+ "loss": 1.2149,
386
  "step": 6300
387
  },
388
  {
389
  "epoch": 1.13,
390
+ "learning_rate": 8.866253321523473e-06,
391
+ "loss": 1.1956,
392
  "step": 6400
393
  },
394
  {
395
  "epoch": 1.15,
396
+ "learning_rate": 8.848538529672278e-06,
397
+ "loss": 1.2049,
398
  "step": 6500
399
  },
400
  {
401
  "epoch": 1.17,
402
+ "learning_rate": 8.830823737821081e-06,
403
+ "loss": 1.2201,
404
  "step": 6600
405
  },
406
  {
407
  "epoch": 1.19,
408
+ "learning_rate": 8.813108945969886e-06,
409
+ "loss": 1.206,
410
  "step": 6700
411
  },
412
  {
413
  "epoch": 1.2,
414
+ "learning_rate": 8.795394154118689e-06,
415
+ "loss": 1.2079,
416
  "step": 6800
417
  },
418
  {
419
  "epoch": 1.22,
420
+ "learning_rate": 8.777679362267494e-06,
421
+ "loss": 1.2033,
422
  "step": 6900
423
  },
424
  {
425
  "epoch": 1.24,
426
+ "learning_rate": 8.759964570416299e-06,
427
+ "loss": 1.1853,
428
  "step": 7000
429
  },
430
  {
431
  "epoch": 1.26,
432
+ "learning_rate": 8.742249778565102e-06,
433
+ "loss": 1.1822,
434
  "step": 7100
435
  },
436
  {
437
  "epoch": 1.28,
438
+ "learning_rate": 8.724534986713907e-06,
439
+ "loss": 1.1834,
440
  "step": 7200
441
  },
442
  {
443
  "epoch": 1.29,
444
+ "learning_rate": 8.70682019486271e-06,
445
+ "loss": 1.2146,
446
  "step": 7300
447
  },
448
  {
449
  "epoch": 1.31,
450
+ "learning_rate": 8.689105403011515e-06,
451
+ "loss": 1.1983,
452
  "step": 7400
453
  },
454
  {
455
  "epoch": 1.33,
456
+ "learning_rate": 8.67139061116032e-06,
457
+ "loss": 1.2084,
458
  "step": 7500
459
  },
460
  {
461
  "epoch": 1.35,
462
+ "learning_rate": 8.653675819309125e-06,
463
+ "loss": 1.2055,
464
  "step": 7600
465
  },
466
  {
467
  "epoch": 1.36,
468
+ "learning_rate": 8.635961027457928e-06,
469
+ "loss": 1.2199,
470
  "step": 7700
471
  },
472
  {
473
  "epoch": 1.38,
474
+ "learning_rate": 8.618246235606731e-06,
475
+ "loss": 1.1745,
476
  "step": 7800
477
  },
478
  {
479
  "epoch": 1.4,
480
+ "learning_rate": 8.600531443755536e-06,
481
+ "loss": 1.195,
482
  "step": 7900
483
  },
484
  {
485
  "epoch": 1.42,
486
+ "learning_rate": 8.582816651904341e-06,
487
+ "loss": 1.2223,
488
  "step": 8000
489
  },
490
  {
491
  "epoch": 1.43,
492
+ "learning_rate": 8.565101860053146e-06,
493
+ "loss": 1.1919,
494
  "step": 8100
495
  },
496
  {
497
  "epoch": 1.45,
498
+ "learning_rate": 8.54738706820195e-06,
499
+ "loss": 1.2043,
500
  "step": 8200
501
  },
502
  {
503
  "epoch": 1.47,
504
+ "learning_rate": 8.529672276350753e-06,
505
+ "loss": 1.2102,
506
  "step": 8300
507
  },
508
  {
509
  "epoch": 1.49,
510
+ "learning_rate": 8.511957484499558e-06,
511
+ "loss": 1.1839,
512
  "step": 8400
513
  },
514
  {
515
  "epoch": 1.51,
516
+ "learning_rate": 8.494242692648362e-06,
517
+ "loss": 1.1889,
518
  "step": 8500
519
  },
520
  {
521
  "epoch": 1.52,
522
+ "learning_rate": 8.476527900797167e-06,
523
+ "loss": 1.1858,
524
  "step": 8600
525
  },
526
  {
527
  "epoch": 1.54,
528
+ "learning_rate": 8.45881310894597e-06,
529
+ "loss": 1.1706,
530
  "step": 8700
531
  },
532
  {
533
  "epoch": 1.56,
534
+ "learning_rate": 8.441098317094775e-06,
535
+ "loss": 1.2071,
536
  "step": 8800
537
  },
538
  {
539
  "epoch": 1.58,
540
+ "learning_rate": 8.423383525243579e-06,
541
+ "loss": 1.1671,
542
  "step": 8900
543
  },
544
  {
545
  "epoch": 1.59,
546
+ "learning_rate": 8.405668733392384e-06,
547
+ "loss": 1.1837,
548
  "step": 9000
549
  },
550
  {
551
  "epoch": 1.61,
552
+ "learning_rate": 8.387953941541187e-06,
553
+ "loss": 1.1627,
554
  "step": 9100
555
  },
556
  {
557
  "epoch": 1.63,
558
+ "learning_rate": 8.370239149689992e-06,
559
+ "loss": 1.2027,
560
  "step": 9200
561
  },
562
  {
563
  "epoch": 1.65,
564
+ "learning_rate": 8.352524357838797e-06,
565
+ "loss": 1.1831,
566
  "step": 9300
567
  },
568
  {
569
  "epoch": 1.67,
570
+ "learning_rate": 8.3348095659876e-06,
571
+ "loss": 1.1941,
572
  "step": 9400
573
  },
574
  {
575
  "epoch": 1.68,
576
+ "learning_rate": 8.317094774136405e-06,
577
+ "loss": 1.2047,
578
  "step": 9500
579
  },
580
  {
581
  "epoch": 1.7,
582
+ "learning_rate": 8.299379982285208e-06,
583
+ "loss": 1.2045,
584
  "step": 9600
585
  },
586
  {
587
  "epoch": 1.72,
588
+ "learning_rate": 8.281665190434013e-06,
589
+ "loss": 1.2022,
590
  "step": 9700
591
  },
592
  {
593
  "epoch": 1.74,
594
+ "learning_rate": 8.263950398582818e-06,
595
+ "loss": 1.1934,
596
  "step": 9800
597
  },
598
  {
599
  "epoch": 1.75,
600
+ "learning_rate": 8.246235606731621e-06,
601
+ "loss": 1.1672,
602
  "step": 9900
603
  },
604
  {
605
  "epoch": 1.77,
606
+ "learning_rate": 8.228520814880426e-06,
607
+ "loss": 1.1802,
608
  "step": 10000
609
  },
610
  {
611
  "epoch": 1.79,
612
+ "learning_rate": 8.210806023029229e-06,
613
+ "loss": 1.1933,
614
  "step": 10100
615
  },
616
  {
617
  "epoch": 1.81,
618
+ "learning_rate": 8.193091231178034e-06,
619
+ "loss": 1.205,
620
  "step": 10200
621
  },
622
  {
623
  "epoch": 1.82,
624
+ "learning_rate": 8.175376439326839e-06,
625
+ "loss": 1.1844,
626
  "step": 10300
627
  },
628
  {
629
  "epoch": 1.84,
630
+ "learning_rate": 8.157661647475644e-06,
631
+ "loss": 1.197,
632
  "step": 10400
633
  },
634
  {
635
  "epoch": 1.86,
636
+ "learning_rate": 8.139946855624447e-06,
637
+ "loss": 1.1978,
638
  "step": 10500
639
  },
640
  {
641
  "epoch": 1.88,
642
+ "learning_rate": 8.12223206377325e-06,
643
+ "loss": 1.2017,
644
  "step": 10600
645
  },
646
  {
647
  "epoch": 1.9,
648
+ "learning_rate": 8.104517271922055e-06,
649
+ "loss": 1.2067,
650
  "step": 10700
651
  },
652
  {
653
  "epoch": 1.91,
654
+ "learning_rate": 8.08680248007086e-06,
655
+ "loss": 1.2042,
656
  "step": 10800
657
  },
658
  {
659
  "epoch": 1.93,
660
+ "learning_rate": 8.069087688219665e-06,
661
+ "loss": 1.206,
662
  "step": 10900
663
  },
664
  {
665
  "epoch": 1.95,
666
+ "learning_rate": 8.051372896368468e-06,
667
+ "loss": 1.1987,
668
  "step": 11000
669
  },
670
  {
671
  "epoch": 1.97,
672
+ "learning_rate": 8.033658104517273e-06,
673
+ "loss": 1.1688,
674
  "step": 11100
675
  },
676
  {
677
  "epoch": 1.98,
678
+ "learning_rate": 8.015943312666076e-06,
679
+ "loss": 1.1723,
680
  "step": 11200
681
  },
682
  {
683
  "epoch": 2.0,
684
+ "learning_rate": 7.998228520814881e-06,
685
+ "loss": 1.1676,
686
  "step": 11300
687
  },
688
  {
689
  "epoch": 2.02,
690
+ "learning_rate": 7.980513728963686e-06,
691
+ "loss": 1.1638,
692
  "step": 11400
693
  },
694
  {
695
  "epoch": 2.04,
696
+ "learning_rate": 7.96279893711249e-06,
697
+ "loss": 1.2048,
698
  "step": 11500
699
  },
700
  {
701
  "epoch": 2.05,
702
+ "learning_rate": 7.945084145261294e-06,
703
+ "loss": 1.1705,
704
  "step": 11600
705
  },
706
  {
707
  "epoch": 2.07,
708
+ "learning_rate": 7.927369353410098e-06,
709
+ "loss": 1.1734,
710
  "step": 11700
711
  },
712
  {
713
  "epoch": 2.09,
714
+ "learning_rate": 7.909654561558902e-06,
715
+ "loss": 1.1781,
716
  "step": 11800
717
  },
718
  {
719
  "epoch": 2.11,
720
+ "learning_rate": 7.891939769707706e-06,
721
+ "loss": 1.1313,
722
  "step": 11900
723
  },
724
  {
725
  "epoch": 2.13,
726
+ "learning_rate": 7.87422497785651e-06,
727
+ "loss": 1.1673,
728
  "step": 12000
729
  },
730
  {
731
  "epoch": 2.14,
732
+ "learning_rate": 7.856510186005316e-06,
733
+ "loss": 1.1926,
734
  "step": 12100
735
  },
736
  {
737
  "epoch": 2.16,
738
+ "learning_rate": 7.838795394154119e-06,
739
+ "loss": 1.1832,
740
  "step": 12200
741
  },
742
  {
743
  "epoch": 2.18,
744
+ "learning_rate": 7.821080602302924e-06,
745
+ "loss": 1.1921,
746
  "step": 12300
747
  },
748
  {
749
  "epoch": 2.2,
750
+ "learning_rate": 7.803365810451727e-06,
751
+ "loss": 1.1869,
752
  "step": 12400
753
  },
754
  {
755
  "epoch": 2.21,
756
+ "learning_rate": 7.785651018600532e-06,
757
+ "loss": 1.1816,
758
  "step": 12500
759
  },
760
  {
761
  "epoch": 2.23,
762
+ "learning_rate": 7.767936226749337e-06,
763
+ "loss": 1.1784,
764
  "step": 12600
765
  },
766
  {
767
  "epoch": 2.25,
768
+ "learning_rate": 7.750221434898142e-06,
769
+ "loss": 1.1809,
770
  "step": 12700
771
  },
772
  {
773
  "epoch": 2.27,
774
+ "learning_rate": 7.732506643046945e-06,
775
+ "loss": 1.1713,
776
  "step": 12800
777
  },
778
  {
779
  "epoch": 2.29,
780
+ "learning_rate": 7.714791851195748e-06,
781
+ "loss": 1.178,
782
  "step": 12900
783
  },
784
  {
785
  "epoch": 2.3,
786
+ "learning_rate": 7.697077059344553e-06,
787
+ "loss": 1.1915,
788
  "step": 13000
789
  },
790
  {
791
  "epoch": 2.32,
792
+ "learning_rate": 7.679362267493358e-06,
793
+ "loss": 1.1814,
794
  "step": 13100
795
  },
796
  {
797
  "epoch": 2.34,
798
+ "learning_rate": 7.661647475642163e-06,
799
+ "loss": 1.1598,
800
  "step": 13200
801
  },
802
  {
803
  "epoch": 2.36,
804
+ "learning_rate": 7.643932683790966e-06,
805
+ "loss": 1.192,
806
  "step": 13300
807
  },
808
  {
809
  "epoch": 2.37,
810
+ "learning_rate": 7.62621789193977e-06,
811
+ "loss": 1.1932,
812
  "step": 13400
813
  },
814
  {
815
  "epoch": 2.39,
816
+ "learning_rate": 7.608503100088574e-06,
817
+ "loss": 1.1586,
818
  "step": 13500
819
  },
820
  {
821
  "epoch": 2.41,
822
+ "learning_rate": 7.590788308237379e-06,
823
+ "loss": 1.1614,
824
  "step": 13600
825
  },
826
  {
827
  "epoch": 2.43,
828
+ "learning_rate": 7.573073516386183e-06,
829
+ "loss": 1.1527,
830
  "step": 13700
831
  },
832
  {
833
  "epoch": 2.44,
834
+ "learning_rate": 7.555358724534987e-06,
835
+ "loss": 1.181,
836
  "step": 13800
837
  },
838
  {
839
  "epoch": 2.46,
840
+ "learning_rate": 7.537643932683791e-06,
841
+ "loss": 1.1306,
842
  "step": 13900
843
  },
844
  {
845
  "epoch": 2.48,
846
+ "learning_rate": 7.519929140832596e-06,
847
+ "loss": 1.1611,
848
  "step": 14000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
849
  }
850
  ],
851
  "max_steps": 56450,
852
  "num_train_epochs": 10,
853
+ "total_flos": 2.6418120801513984e+17,
854
  "trial_name": null,
855
  "trial_params": null
856
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3221b52b8f1f14be224fbb7a9db3407c9da00f2b698658a34ba2f313e87d1aa6
3
  size 2607
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85b729c2bf5e5da7c93edfde6c806aafe35d4ac091859be47c5f440ea211e569
3
  size 2607