huranokuma commited on
Commit
49a3f25
1 Parent(s): b947dde

End of training

Browse files
Files changed (3) hide show
  1. all_results.json +5 -5
  2. train_results.json +5 -5
  3. trainer_state.json +550 -1360
all_results.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "epoch": 3.0,
3
  "eval_accuracy": 0.7105720509450737,
4
  "eval_loss": 1.2192070484161377,
5
  "eval_runtime": 4409.7065,
@@ -7,9 +7,9 @@
7
  "eval_samples_per_second": 30.601,
8
  "eval_steps_per_second": 7.65,
9
  "perplexity": 3.384502922346475,
10
- "train_loss": 1.602629992106659,
11
- "train_runtime": 64476.8032,
12
  "train_samples": 134942,
13
- "train_samples_per_second": 6.279,
14
- "train_steps_per_second": 3.139
15
  }
 
1
  {
2
+ "epoch": 2.0,
3
  "eval_accuracy": 0.7105720509450737,
4
  "eval_loss": 1.2192070484161377,
5
  "eval_runtime": 4409.7065,
 
7
  "eval_samples_per_second": 30.601,
8
  "eval_steps_per_second": 7.65,
9
  "perplexity": 3.384502922346475,
10
+ "train_loss": 1.578441581144295,
11
+ "train_runtime": 31772.5798,
12
  "train_samples": 134942,
13
+ "train_samples_per_second": 8.494,
14
+ "train_steps_per_second": 4.247
15
  }
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
- "epoch": 3.0,
3
- "train_loss": 1.602629992106659,
4
- "train_runtime": 64476.8032,
5
  "train_samples": 134942,
6
- "train_samples_per_second": 6.279,
7
- "train_steps_per_second": 3.139
8
  }
 
1
  {
2
+ "epoch": 2.0,
3
+ "train_loss": 1.578441581144295,
4
+ "train_runtime": 31772.5798,
5
  "train_samples": 134942,
6
+ "train_samples_per_second": 8.494,
7
+ "train_steps_per_second": 4.247
8
  }
trainer_state.json CHANGED
@@ -1,2449 +1,1639 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 3.0,
5
- "global_step": 202413,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
9
  "log_history": [
10
  {
11
  "epoch": 0.01,
12
- "learning_rate": 4.9876490146383884e-05,
13
- "loss": 1.4737,
14
  "step": 500
15
  },
16
  {
17
  "epoch": 0.01,
18
- "learning_rate": 4.975298029276776e-05,
19
- "loss": 1.4854,
20
  "step": 1000
21
  },
22
  {
23
  "epoch": 0.02,
24
- "learning_rate": 4.962947043915164e-05,
25
- "loss": 1.5299,
26
  "step": 1500
27
  },
28
  {
29
  "epoch": 0.03,
30
- "learning_rate": 4.950596058553551e-05,
31
- "loss": 1.5417,
32
  "step": 2000
33
  },
34
  {
35
  "epoch": 0.04,
36
- "learning_rate": 4.9382450731919394e-05,
37
- "loss": 1.5408,
38
  "step": 2500
39
  },
40
  {
41
  "epoch": 0.04,
42
- "learning_rate": 4.9258940878303276e-05,
43
- "loss": 1.542,
44
  "step": 3000
45
  },
46
  {
47
  "epoch": 0.05,
48
- "learning_rate": 4.913543102468715e-05,
49
- "loss": 1.5424,
50
  "step": 3500
51
  },
52
  {
53
  "epoch": 0.06,
54
- "learning_rate": 4.901192117107103e-05,
55
- "loss": 1.5585,
56
  "step": 4000
57
  },
58
  {
59
  "epoch": 0.07,
60
- "learning_rate": 4.8888411317454905e-05,
61
- "loss": 1.5505,
62
  "step": 4500
63
  },
64
  {
65
  "epoch": 0.07,
66
- "learning_rate": 4.8764901463838787e-05,
67
- "loss": 1.5816,
68
  "step": 5000
69
  },
70
  {
71
  "epoch": 0.08,
72
- "learning_rate": 4.864139161022266e-05,
73
- "loss": 1.5698,
74
  "step": 5500
75
  },
76
  {
77
  "epoch": 0.09,
78
- "learning_rate": 4.851788175660654e-05,
79
- "loss": 1.573,
80
  "step": 6000
81
  },
82
  {
83
  "epoch": 0.1,
84
- "learning_rate": 4.839437190299042e-05,
85
- "loss": 1.5797,
86
  "step": 6500
87
  },
88
  {
89
  "epoch": 0.1,
90
- "learning_rate": 4.82708620493743e-05,
91
- "loss": 1.5854,
92
  "step": 7000
93
  },
94
  {
95
  "epoch": 0.11,
96
- "learning_rate": 4.814735219575818e-05,
97
- "loss": 1.5935,
98
  "step": 7500
99
  },
100
  {
101
  "epoch": 0.12,
102
- "learning_rate": 4.802384234214205e-05,
103
- "loss": 1.6072,
104
  "step": 8000
105
  },
106
  {
107
  "epoch": 0.13,
108
- "learning_rate": 4.7900332488525934e-05,
109
- "loss": 1.6015,
110
  "step": 8500
111
  },
112
  {
113
  "epoch": 0.13,
114
- "learning_rate": 4.7776822634909815e-05,
115
- "loss": 1.6086,
116
  "step": 9000
117
  },
118
  {
119
  "epoch": 0.14,
120
- "learning_rate": 4.7653312781293696e-05,
121
- "loss": 1.5901,
122
  "step": 9500
123
  },
124
  {
125
  "epoch": 0.15,
126
- "learning_rate": 4.752980292767758e-05,
127
- "loss": 1.5899,
128
  "step": 10000
129
  },
130
  {
131
  "epoch": 0.16,
132
- "learning_rate": 4.740629307406145e-05,
133
- "loss": 1.5804,
134
  "step": 10500
135
  },
136
  {
137
  "epoch": 0.16,
138
- "learning_rate": 4.728278322044533e-05,
139
- "loss": 1.6211,
140
  "step": 11000
141
  },
142
  {
143
  "epoch": 0.17,
144
- "learning_rate": 4.715927336682921e-05,
145
- "loss": 1.6268,
146
  "step": 11500
147
  },
148
  {
149
  "epoch": 0.18,
150
- "learning_rate": 4.703576351321309e-05,
151
- "loss": 1.5938,
152
  "step": 12000
153
  },
154
  {
155
  "epoch": 0.19,
156
- "learning_rate": 4.691225365959697e-05,
157
- "loss": 1.6143,
158
  "step": 12500
159
  },
160
  {
161
  "epoch": 0.19,
162
- "learning_rate": 4.6788743805980844e-05,
163
- "loss": 1.5977,
164
  "step": 13000
165
  },
166
  {
167
  "epoch": 0.2,
168
- "learning_rate": 4.6665233952364725e-05,
169
- "loss": 1.6157,
170
  "step": 13500
171
  },
172
  {
173
  "epoch": 0.21,
174
- "learning_rate": 4.65417240987486e-05,
175
- "loss": 1.6176,
176
  "step": 14000
177
  },
178
  {
179
  "epoch": 0.21,
180
- "learning_rate": 4.641821424513248e-05,
181
- "loss": 1.6032,
182
  "step": 14500
183
  },
184
  {
185
  "epoch": 0.22,
186
- "learning_rate": 4.6294704391516355e-05,
187
- "loss": 1.5959,
188
  "step": 15000
189
  },
190
  {
191
  "epoch": 0.23,
192
- "learning_rate": 4.6171194537900236e-05,
193
- "loss": 1.6247,
194
  "step": 15500
195
  },
196
  {
197
  "epoch": 0.24,
198
- "learning_rate": 4.604768468428412e-05,
199
- "loss": 1.615,
200
  "step": 16000
201
  },
202
  {
203
  "epoch": 0.24,
204
- "learning_rate": 4.592417483066799e-05,
205
- "loss": 1.6421,
206
  "step": 16500
207
  },
208
  {
209
  "epoch": 0.25,
210
- "learning_rate": 4.580066497705187e-05,
211
- "loss": 1.6377,
212
  "step": 17000
213
  },
214
  {
215
  "epoch": 0.26,
216
- "learning_rate": 4.567715512343575e-05,
217
- "loss": 1.6335,
218
  "step": 17500
219
  },
220
  {
221
  "epoch": 0.27,
222
- "learning_rate": 4.555364526981963e-05,
223
- "loss": 1.6476,
224
  "step": 18000
225
  },
226
  {
227
  "epoch": 0.27,
228
- "learning_rate": 4.543013541620351e-05,
229
- "loss": 1.6314,
230
  "step": 18500
231
  },
232
  {
233
  "epoch": 0.28,
234
- "learning_rate": 4.5306625562587384e-05,
235
- "loss": 1.637,
236
  "step": 19000
237
  },
238
  {
239
  "epoch": 0.29,
240
- "learning_rate": 4.5183115708971265e-05,
241
- "loss": 1.6289,
242
  "step": 19500
243
  },
244
  {
245
  "epoch": 0.3,
246
- "learning_rate": 4.505960585535514e-05,
247
- "loss": 1.6434,
248
  "step": 20000
249
  },
250
  {
251
  "epoch": 0.3,
252
- "learning_rate": 4.493609600173902e-05,
253
- "loss": 1.6458,
254
  "step": 20500
255
  },
256
  {
257
  "epoch": 0.31,
258
- "learning_rate": 4.48125861481229e-05,
259
- "loss": 1.629,
260
  "step": 21000
261
  },
262
  {
263
  "epoch": 0.32,
264
- "learning_rate": 4.4689076294506776e-05,
265
- "loss": 1.6385,
266
  "step": 21500
267
  },
268
  {
269
  "epoch": 0.33,
270
- "learning_rate": 4.456556644089066e-05,
271
- "loss": 1.6508,
272
  "step": 22000
273
  },
274
  {
275
  "epoch": 0.33,
276
- "learning_rate": 4.444205658727453e-05,
277
- "loss": 1.6715,
278
  "step": 22500
279
  },
280
  {
281
  "epoch": 0.34,
282
- "learning_rate": 4.431854673365841e-05,
283
- "loss": 1.6706,
284
  "step": 23000
285
  },
286
  {
287
  "epoch": 0.35,
288
- "learning_rate": 4.419503688004229e-05,
289
- "loss": 1.6633,
290
  "step": 23500
291
  },
292
  {
293
  "epoch": 0.36,
294
- "learning_rate": 4.407152702642617e-05,
295
- "loss": 1.6705,
296
  "step": 24000
297
  },
298
  {
299
  "epoch": 0.36,
300
- "learning_rate": 4.394801717281005e-05,
301
- "loss": 1.6609,
302
  "step": 24500
303
  },
304
  {
305
  "epoch": 0.37,
306
- "learning_rate": 4.382450731919392e-05,
307
- "loss": 1.6349,
308
  "step": 25000
309
  },
310
  {
311
  "epoch": 0.38,
312
- "learning_rate": 4.3700997465577804e-05,
313
- "loss": 1.6829,
314
  "step": 25500
315
  },
316
  {
317
  "epoch": 0.39,
318
- "learning_rate": 4.3577487611961686e-05,
319
- "loss": 1.6589,
320
  "step": 26000
321
  },
322
  {
323
  "epoch": 0.39,
324
- "learning_rate": 4.345397775834557e-05,
325
- "loss": 1.6871,
326
  "step": 26500
327
  },
328
  {
329
  "epoch": 0.4,
330
- "learning_rate": 4.333046790472944e-05,
331
- "loss": 1.6845,
332
  "step": 27000
333
  },
334
  {
335
  "epoch": 0.41,
336
- "learning_rate": 4.320695805111332e-05,
337
- "loss": 1.6754,
338
  "step": 27500
339
  },
340
  {
341
  "epoch": 0.41,
342
- "learning_rate": 4.30834481974972e-05,
343
- "loss": 1.6712,
344
  "step": 28000
345
  },
346
  {
347
  "epoch": 0.42,
348
- "learning_rate": 4.295993834388108e-05,
349
- "loss": 1.6638,
350
  "step": 28500
351
  },
352
  {
353
  "epoch": 0.43,
354
- "learning_rate": 4.283642849026496e-05,
355
- "loss": 1.6623,
356
  "step": 29000
357
  },
358
  {
359
  "epoch": 0.44,
360
- "learning_rate": 4.271291863664883e-05,
361
- "loss": 1.6832,
362
  "step": 29500
363
  },
364
  {
365
  "epoch": 0.44,
366
- "learning_rate": 4.2589408783032714e-05,
367
- "loss": 1.6583,
368
  "step": 30000
369
  },
370
  {
371
  "epoch": 0.45,
372
- "learning_rate": 4.2465898929416595e-05,
373
- "loss": 1.683,
374
  "step": 30500
375
  },
376
  {
377
  "epoch": 0.46,
378
- "learning_rate": 4.234238907580047e-05,
379
- "loss": 1.6799,
380
  "step": 31000
381
  },
382
  {
383
  "epoch": 0.47,
384
- "learning_rate": 4.221887922218435e-05,
385
- "loss": 1.6857,
386
  "step": 31500
387
  },
388
  {
389
  "epoch": 0.47,
390
- "learning_rate": 4.2095369368568225e-05,
391
- "loss": 1.6817,
392
  "step": 32000
393
  },
394
  {
395
  "epoch": 0.48,
396
- "learning_rate": 4.1971859514952106e-05,
397
- "loss": 1.6998,
398
  "step": 32500
399
  },
400
  {
401
  "epoch": 0.49,
402
- "learning_rate": 4.184834966133598e-05,
403
- "loss": 1.7106,
404
  "step": 33000
405
  },
406
  {
407
  "epoch": 0.5,
408
- "learning_rate": 4.172483980771986e-05,
409
- "loss": 1.7017,
410
  "step": 33500
411
  },
412
  {
413
  "epoch": 0.5,
414
- "learning_rate": 4.160132995410374e-05,
415
- "loss": 1.6984,
416
  "step": 34000
417
  },
418
  {
419
  "epoch": 0.51,
420
- "learning_rate": 4.147782010048762e-05,
421
- "loss": 1.6843,
422
  "step": 34500
423
  },
424
  {
425
  "epoch": 0.52,
426
- "learning_rate": 4.13543102468715e-05,
427
- "loss": 1.6751,
428
  "step": 35000
429
  },
430
  {
431
  "epoch": 0.53,
432
- "learning_rate": 4.123080039325537e-05,
433
- "loss": 1.7001,
434
  "step": 35500
435
  },
436
  {
437
  "epoch": 0.53,
438
- "learning_rate": 4.1107290539639254e-05,
439
- "loss": 1.696,
440
  "step": 36000
441
  },
442
  {
443
  "epoch": 0.54,
444
- "learning_rate": 4.0983780686023135e-05,
445
- "loss": 1.6911,
446
  "step": 36500
447
  },
448
  {
449
  "epoch": 0.55,
450
- "learning_rate": 4.086027083240701e-05,
451
- "loss": 1.6793,
452
  "step": 37000
453
  },
454
  {
455
  "epoch": 0.56,
456
- "learning_rate": 4.073676097879089e-05,
457
- "loss": 1.686,
458
  "step": 37500
459
  },
460
  {
461
  "epoch": 0.56,
462
- "learning_rate": 4.0613251125174765e-05,
463
- "loss": 1.6953,
464
  "step": 38000
465
  },
466
  {
467
  "epoch": 0.57,
468
- "learning_rate": 4.0489741271558646e-05,
469
- "loss": 1.6857,
470
  "step": 38500
471
  },
472
  {
473
  "epoch": 0.58,
474
- "learning_rate": 4.036623141794252e-05,
475
- "loss": 1.6844,
476
  "step": 39000
477
  },
478
  {
479
  "epoch": 0.59,
480
- "learning_rate": 4.02427215643264e-05,
481
- "loss": 1.6924,
482
  "step": 39500
483
  },
484
  {
485
  "epoch": 0.59,
486
- "learning_rate": 4.011921171071028e-05,
487
- "loss": 1.717,
488
  "step": 40000
489
  },
490
  {
491
  "epoch": 0.6,
492
- "learning_rate": 3.999570185709416e-05,
493
- "loss": 1.6964,
494
  "step": 40500
495
  },
496
  {
497
  "epoch": 0.61,
498
- "learning_rate": 3.987219200347804e-05,
499
- "loss": 1.699,
500
  "step": 41000
501
  },
502
  {
503
  "epoch": 0.62,
504
- "learning_rate": 3.974868214986191e-05,
505
- "loss": 1.6946,
506
  "step": 41500
507
  },
508
  {
509
  "epoch": 0.62,
510
- "learning_rate": 3.9625172296245794e-05,
511
- "loss": 1.7071,
512
  "step": 42000
513
  },
514
  {
515
  "epoch": 0.63,
516
- "learning_rate": 3.9501662442629675e-05,
517
- "loss": 1.7025,
518
  "step": 42500
519
  },
520
  {
521
  "epoch": 0.64,
522
- "learning_rate": 3.9378152589013556e-05,
523
- "loss": 1.6952,
524
  "step": 43000
525
  },
526
  {
527
  "epoch": 0.64,
528
- "learning_rate": 3.925464273539744e-05,
529
- "loss": 1.7177,
530
  "step": 43500
531
  },
532
  {
533
  "epoch": 0.65,
534
- "learning_rate": 3.913113288178131e-05,
535
- "loss": 1.7222,
536
  "step": 44000
537
  },
538
  {
539
  "epoch": 0.66,
540
- "learning_rate": 3.900762302816519e-05,
541
- "loss": 1.6949,
542
  "step": 44500
543
  },
544
  {
545
  "epoch": 0.67,
546
- "learning_rate": 3.888411317454907e-05,
547
- "loss": 1.6928,
548
  "step": 45000
549
  },
550
  {
551
  "epoch": 0.67,
552
- "learning_rate": 3.876060332093295e-05,
553
- "loss": 1.707,
554
  "step": 45500
555
  },
556
  {
557
  "epoch": 0.68,
558
- "learning_rate": 3.863709346731683e-05,
559
- "loss": 1.7227,
560
  "step": 46000
561
  },
562
  {
563
  "epoch": 0.69,
564
- "learning_rate": 3.8513583613700704e-05,
565
- "loss": 1.7294,
566
  "step": 46500
567
  },
568
  {
569
  "epoch": 0.7,
570
- "learning_rate": 3.8390073760084585e-05,
571
- "loss": 1.7305,
572
  "step": 47000
573
  },
574
  {
575
  "epoch": 0.7,
576
- "learning_rate": 3.826656390646846e-05,
577
- "loss": 1.6871,
578
  "step": 47500
579
  },
580
  {
581
  "epoch": 0.71,
582
- "learning_rate": 3.814305405285234e-05,
583
- "loss": 1.7227,
584
  "step": 48000
585
  },
586
  {
587
  "epoch": 0.72,
588
- "learning_rate": 3.8019544199236215e-05,
589
- "loss": 1.6963,
590
  "step": 48500
591
  },
592
  {
593
  "epoch": 0.73,
594
- "learning_rate": 3.7896034345620096e-05,
595
- "loss": 1.7107,
596
  "step": 49000
597
  },
598
  {
599
  "epoch": 0.73,
600
- "learning_rate": 3.777252449200398e-05,
601
- "loss": 1.7351,
602
  "step": 49500
603
  },
604
  {
605
  "epoch": 0.74,
606
- "learning_rate": 3.764901463838785e-05,
607
- "loss": 1.7234,
608
  "step": 50000
609
  },
610
  {
611
  "epoch": 0.75,
612
- "learning_rate": 3.752550478477173e-05,
613
- "loss": 1.715,
614
  "step": 50500
615
  },
616
  {
617
  "epoch": 0.76,
618
- "learning_rate": 3.7401994931155607e-05,
619
- "loss": 1.7139,
620
  "step": 51000
621
  },
622
  {
623
  "epoch": 0.76,
624
- "learning_rate": 3.727848507753949e-05,
625
- "loss": 1.7475,
626
  "step": 51500
627
  },
628
  {
629
  "epoch": 0.77,
630
- "learning_rate": 3.715497522392337e-05,
631
- "loss": 1.7425,
632
  "step": 52000
633
  },
634
  {
635
  "epoch": 0.78,
636
- "learning_rate": 3.703146537030724e-05,
637
- "loss": 1.7259,
638
  "step": 52500
639
  },
640
  {
641
  "epoch": 0.79,
642
- "learning_rate": 3.6907955516691124e-05,
643
- "loss": 1.7436,
644
  "step": 53000
645
  },
646
  {
647
  "epoch": 0.79,
648
- "learning_rate": 3.6784445663075e-05,
649
- "loss": 1.7127,
650
  "step": 53500
651
  },
652
  {
653
  "epoch": 0.8,
654
- "learning_rate": 3.666093580945888e-05,
655
- "loss": 1.7549,
656
  "step": 54000
657
  },
658
  {
659
  "epoch": 0.81,
660
- "learning_rate": 3.653742595584276e-05,
661
- "loss": 1.7076,
662
  "step": 54500
663
  },
664
  {
665
  "epoch": 0.82,
666
- "learning_rate": 3.6413916102226635e-05,
667
- "loss": 1.7495,
668
  "step": 55000
669
  },
670
  {
671
  "epoch": 0.82,
672
- "learning_rate": 3.6290406248610516e-05,
673
- "loss": 1.725,
674
  "step": 55500
675
  },
676
  {
677
  "epoch": 0.83,
678
- "learning_rate": 3.616689639499439e-05,
679
- "loss": 1.7273,
680
  "step": 56000
681
  },
682
  {
683
  "epoch": 0.84,
684
- "learning_rate": 3.604338654137827e-05,
685
- "loss": 1.7384,
686
  "step": 56500
687
  },
688
  {
689
  "epoch": 0.84,
690
- "learning_rate": 3.5919876687762146e-05,
691
- "loss": 1.7375,
692
  "step": 57000
693
  },
694
  {
695
  "epoch": 0.85,
696
- "learning_rate": 3.579636683414603e-05,
697
- "loss": 1.7467,
698
  "step": 57500
699
  },
700
  {
701
  "epoch": 0.86,
702
- "learning_rate": 3.567285698052991e-05,
703
- "loss": 1.7395,
704
  "step": 58000
705
  },
706
  {
707
  "epoch": 0.87,
708
- "learning_rate": 3.554934712691378e-05,
709
- "loss": 1.7334,
710
  "step": 58500
711
  },
712
  {
713
  "epoch": 0.87,
714
- "learning_rate": 3.5425837273297664e-05,
715
- "loss": 1.7382,
716
  "step": 59000
717
  },
718
  {
719
  "epoch": 0.88,
720
- "learning_rate": 3.530232741968154e-05,
721
- "loss": 1.7269,
722
  "step": 59500
723
  },
724
  {
725
  "epoch": 0.89,
726
- "learning_rate": 3.5178817566065426e-05,
727
- "loss": 1.7411,
728
  "step": 60000
729
  },
730
  {
731
  "epoch": 0.9,
732
- "learning_rate": 3.50553077124493e-05,
733
- "loss": 1.7492,
734
  "step": 60500
735
  },
736
  {
737
  "epoch": 0.9,
738
- "learning_rate": 3.493179785883318e-05,
739
- "loss": 1.7388,
740
  "step": 61000
741
  },
742
  {
743
  "epoch": 0.91,
744
- "learning_rate": 3.480828800521706e-05,
745
- "loss": 1.7327,
746
  "step": 61500
747
  },
748
  {
749
  "epoch": 0.92,
750
- "learning_rate": 3.468477815160094e-05,
751
- "loss": 1.7584,
752
  "step": 62000
753
  },
754
  {
755
  "epoch": 0.93,
756
- "learning_rate": 3.456126829798482e-05,
757
- "loss": 1.7346,
758
  "step": 62500
759
  },
760
  {
761
  "epoch": 0.93,
762
- "learning_rate": 3.443775844436869e-05,
763
- "loss": 1.7543,
764
  "step": 63000
765
  },
766
  {
767
  "epoch": 0.94,
768
- "learning_rate": 3.4314248590752574e-05,
769
- "loss": 1.7506,
770
  "step": 63500
771
  },
772
  {
773
  "epoch": 0.95,
774
- "learning_rate": 3.4190738737136455e-05,
775
- "loss": 1.7512,
776
  "step": 64000
777
  },
778
  {
779
  "epoch": 0.96,
780
- "learning_rate": 3.406722888352033e-05,
781
- "loss": 1.745,
782
  "step": 64500
783
  },
784
  {
785
  "epoch": 0.96,
786
- "learning_rate": 3.394371902990421e-05,
787
- "loss": 1.7638,
788
  "step": 65000
789
  },
790
  {
791
  "epoch": 0.97,
792
- "learning_rate": 3.3820209176288085e-05,
793
- "loss": 1.7539,
794
  "step": 65500
795
  },
796
  {
797
  "epoch": 0.98,
798
- "learning_rate": 3.3696699322671966e-05,
799
- "loss": 1.7421,
800
  "step": 66000
801
  },
802
  {
803
  "epoch": 0.99,
804
- "learning_rate": 3.357318946905584e-05,
805
- "loss": 1.7498,
806
  "step": 66500
807
  },
808
  {
809
  "epoch": 0.99,
810
- "learning_rate": 3.344967961543972e-05,
811
- "loss": 1.7766,
812
  "step": 67000
813
  },
814
  {
815
  "epoch": 1.0,
816
- "learning_rate": 3.33261697618236e-05,
817
- "loss": 1.7478,
818
  "step": 67500
819
  },
820
  {
821
  "epoch": 1.01,
822
- "learning_rate": 3.320265990820748e-05,
823
- "loss": 1.5057,
824
  "step": 68000
825
  },
826
  {
827
  "epoch": 1.02,
828
- "learning_rate": 3.307915005459136e-05,
829
- "loss": 1.5248,
830
  "step": 68500
831
  },
832
  {
833
  "epoch": 1.02,
834
- "learning_rate": 3.295564020097523e-05,
835
- "loss": 1.5344,
836
  "step": 69000
837
  },
838
  {
839
  "epoch": 1.03,
840
- "learning_rate": 3.2832130347359114e-05,
841
- "loss": 1.5177,
842
  "step": 69500
843
  },
844
  {
845
  "epoch": 1.04,
846
- "learning_rate": 3.2708620493742995e-05,
847
- "loss": 1.5255,
848
  "step": 70000
849
  },
850
  {
851
  "epoch": 1.04,
852
- "learning_rate": 3.258511064012687e-05,
853
- "loss": 1.5388,
854
  "step": 70500
855
  },
856
  {
857
  "epoch": 1.05,
858
- "learning_rate": 3.246160078651075e-05,
859
- "loss": 1.5187,
860
  "step": 71000
861
  },
862
  {
863
  "epoch": 1.06,
864
- "learning_rate": 3.2338090932894625e-05,
865
- "loss": 1.5371,
866
  "step": 71500
867
  },
868
  {
869
  "epoch": 1.07,
870
- "learning_rate": 3.2214581079278506e-05,
871
- "loss": 1.5466,
872
  "step": 72000
873
  },
874
  {
875
  "epoch": 1.07,
876
- "learning_rate": 3.209107122566239e-05,
877
- "loss": 1.5409,
878
  "step": 72500
879
  },
880
  {
881
  "epoch": 1.08,
882
- "learning_rate": 3.196756137204626e-05,
883
- "loss": 1.5329,
884
  "step": 73000
885
  },
886
  {
887
  "epoch": 1.09,
888
- "learning_rate": 3.184405151843014e-05,
889
- "loss": 1.5404,
890
  "step": 73500
891
  },
892
  {
893
  "epoch": 1.1,
894
- "learning_rate": 3.1720541664814017e-05,
895
- "loss": 1.5337,
896
  "step": 74000
897
  },
898
  {
899
  "epoch": 1.1,
900
- "learning_rate": 3.15970318111979e-05,
901
- "loss": 1.5479,
902
  "step": 74500
903
  },
904
  {
905
  "epoch": 1.11,
906
- "learning_rate": 3.147352195758177e-05,
907
- "loss": 1.5608,
908
  "step": 75000
909
  },
910
  {
911
  "epoch": 1.12,
912
- "learning_rate": 3.135001210396565e-05,
913
- "loss": 1.5568,
914
  "step": 75500
915
  },
916
  {
917
  "epoch": 1.13,
918
- "learning_rate": 3.1226502250349534e-05,
919
- "loss": 1.5503,
920
  "step": 76000
921
  },
922
  {
923
  "epoch": 1.13,
924
- "learning_rate": 3.110299239673341e-05,
925
- "loss": 1.5678,
926
  "step": 76500
927
  },
928
  {
929
  "epoch": 1.14,
930
- "learning_rate": 3.0979482543117297e-05,
931
- "loss": 1.5654,
932
  "step": 77000
933
  },
934
  {
935
  "epoch": 1.15,
936
- "learning_rate": 3.085597268950117e-05,
937
- "loss": 1.5808,
938
  "step": 77500
939
  },
940
  {
941
  "epoch": 1.16,
942
- "learning_rate": 3.073246283588505e-05,
943
- "loss": 1.5567,
944
  "step": 78000
945
  },
946
  {
947
  "epoch": 1.16,
948
- "learning_rate": 3.0608952982268926e-05,
949
- "loss": 1.5816,
950
  "step": 78500
951
  },
952
  {
953
  "epoch": 1.17,
954
- "learning_rate": 3.0485443128652808e-05,
955
- "loss": 1.5785,
956
  "step": 79000
957
  },
958
  {
959
  "epoch": 1.18,
960
- "learning_rate": 3.0361933275036685e-05,
961
- "loss": 1.569,
962
  "step": 79500
963
  },
964
  {
965
  "epoch": 1.19,
966
- "learning_rate": 3.0238423421420563e-05,
967
- "loss": 1.5772,
968
  "step": 80000
969
  },
970
  {
971
  "epoch": 1.19,
972
- "learning_rate": 3.0114913567804444e-05,
973
- "loss": 1.5652,
974
  "step": 80500
975
  },
976
  {
977
  "epoch": 1.2,
978
- "learning_rate": 2.9991403714188322e-05,
979
- "loss": 1.5571,
980
  "step": 81000
981
  },
982
  {
983
  "epoch": 1.21,
984
- "learning_rate": 2.98678938605722e-05,
985
- "loss": 1.5757,
986
  "step": 81500
987
  },
988
  {
989
  "epoch": 1.22,
990
- "learning_rate": 2.9744384006956077e-05,
991
- "loss": 1.5722,
992
  "step": 82000
993
  },
994
  {
995
  "epoch": 1.22,
996
- "learning_rate": 2.9620874153339955e-05,
997
- "loss": 1.5799,
998
  "step": 82500
999
  },
1000
  {
1001
  "epoch": 1.23,
1002
- "learning_rate": 2.9497364299723833e-05,
1003
- "loss": 1.5202,
1004
  "step": 83000
1005
  },
1006
  {
1007
  "epoch": 1.24,
1008
- "learning_rate": 2.9373854446107714e-05,
1009
- "loss": 1.5105,
1010
  "step": 83500
1011
  },
1012
  {
1013
  "epoch": 1.24,
1014
- "learning_rate": 2.9250344592491592e-05,
1015
- "loss": 1.5209,
1016
  "step": 84000
1017
  },
1018
  {
1019
  "epoch": 1.25,
1020
- "learning_rate": 2.912683473887547e-05,
1021
- "loss": 1.5088,
1022
  "step": 84500
1023
  },
1024
  {
1025
  "epoch": 1.26,
1026
- "learning_rate": 2.9003324885259347e-05,
1027
- "loss": 1.5088,
1028
  "step": 85000
1029
  },
1030
  {
1031
  "epoch": 1.27,
1032
- "learning_rate": 2.8879815031643225e-05,
1033
- "loss": 1.5258,
1034
  "step": 85500
1035
  },
1036
  {
1037
  "epoch": 1.27,
1038
- "learning_rate": 2.8756305178027103e-05,
1039
- "loss": 1.5262,
1040
  "step": 86000
1041
  },
1042
  {
1043
  "epoch": 1.28,
1044
- "learning_rate": 2.8632795324410984e-05,
1045
- "loss": 1.5241,
1046
  "step": 86500
1047
  },
1048
  {
1049
  "epoch": 1.29,
1050
- "learning_rate": 2.850928547079486e-05,
1051
- "loss": 1.5179,
1052
  "step": 87000
1053
  },
1054
  {
1055
  "epoch": 1.3,
1056
- "learning_rate": 2.838577561717874e-05,
1057
- "loss": 1.5123,
1058
  "step": 87500
1059
  },
1060
  {
1061
  "epoch": 1.3,
1062
- "learning_rate": 2.8262265763562617e-05,
1063
- "loss": 1.5073,
1064
  "step": 88000
1065
  },
1066
  {
1067
  "epoch": 1.31,
1068
- "learning_rate": 2.8138755909946495e-05,
1069
- "loss": 1.5279,
1070
  "step": 88500
1071
  },
1072
  {
1073
  "epoch": 1.32,
1074
- "learning_rate": 2.8015246056330373e-05,
1075
- "loss": 1.5394,
1076
  "step": 89000
1077
  },
1078
  {
1079
  "epoch": 1.33,
1080
- "learning_rate": 2.7891736202714254e-05,
1081
- "loss": 1.5415,
1082
  "step": 89500
1083
  },
1084
  {
1085
  "epoch": 1.33,
1086
- "learning_rate": 2.776822634909813e-05,
1087
- "loss": 1.5304,
1088
  "step": 90000
1089
  },
1090
  {
1091
  "epoch": 1.34,
1092
- "learning_rate": 2.764471649548201e-05,
1093
- "loss": 1.587,
1094
  "step": 90500
1095
  },
1096
  {
1097
  "epoch": 1.35,
1098
- "learning_rate": 2.7521206641865887e-05,
1099
- "loss": 1.5686,
1100
  "step": 91000
1101
  },
1102
  {
1103
  "epoch": 1.36,
1104
- "learning_rate": 2.7397696788249765e-05,
1105
- "loss": 1.5662,
1106
  "step": 91500
1107
  },
1108
  {
1109
  "epoch": 1.36,
1110
- "learning_rate": 2.7274186934633646e-05,
1111
- "loss": 1.5661,
1112
  "step": 92000
1113
  },
1114
  {
1115
  "epoch": 1.37,
1116
- "learning_rate": 2.7150677081017524e-05,
1117
- "loss": 1.5823,
1118
  "step": 92500
1119
  },
1120
  {
1121
  "epoch": 1.38,
1122
- "learning_rate": 2.70271672274014e-05,
1123
- "loss": 1.582,
1124
  "step": 93000
1125
  },
1126
  {
1127
  "epoch": 1.39,
1128
- "learning_rate": 2.690365737378528e-05,
1129
- "loss": 1.5836,
1130
  "step": 93500
1131
  },
1132
  {
1133
  "epoch": 1.39,
1134
- "learning_rate": 2.6780147520169157e-05,
1135
- "loss": 1.5729,
1136
  "step": 94000
1137
  },
1138
  {
1139
  "epoch": 1.4,
1140
- "learning_rate": 2.665663766655304e-05,
1141
- "loss": 1.5969,
1142
  "step": 94500
1143
  },
1144
  {
1145
  "epoch": 1.41,
1146
- "learning_rate": 2.653312781293692e-05,
1147
- "loss": 1.5878,
1148
  "step": 95000
1149
  },
1150
  {
1151
  "epoch": 1.42,
1152
- "learning_rate": 2.6409617959320797e-05,
1153
- "loss": 1.5956,
1154
  "step": 95500
1155
  },
1156
  {
1157
  "epoch": 1.42,
1158
- "learning_rate": 2.6286108105704678e-05,
1159
- "loss": 1.5827,
1160
  "step": 96000
1161
  },
1162
  {
1163
  "epoch": 1.43,
1164
- "learning_rate": 2.6162598252088556e-05,
1165
- "loss": 1.5935,
1166
  "step": 96500
1167
  },
1168
  {
1169
  "epoch": 1.44,
1170
- "learning_rate": 2.6039088398472433e-05,
1171
- "loss": 1.5929,
1172
  "step": 97000
1173
  },
1174
  {
1175
  "epoch": 1.45,
1176
- "learning_rate": 2.591557854485631e-05,
1177
- "loss": 1.5849,
1178
  "step": 97500
1179
  },
1180
  {
1181
  "epoch": 1.45,
1182
- "learning_rate": 2.579206869124019e-05,
1183
- "loss": 1.5819,
1184
  "step": 98000
1185
  },
1186
  {
1187
  "epoch": 1.46,
1188
- "learning_rate": 2.5668558837624067e-05,
1189
- "loss": 1.609,
1190
  "step": 98500
1191
  },
1192
  {
1193
  "epoch": 1.47,
1194
- "learning_rate": 2.5545048984007948e-05,
1195
- "loss": 1.6012,
1196
  "step": 99000
1197
  },
1198
  {
1199
  "epoch": 1.47,
1200
- "learning_rate": 2.5421539130391825e-05,
1201
- "loss": 1.6138,
1202
  "step": 99500
1203
  },
1204
  {
1205
  "epoch": 1.48,
1206
- "learning_rate": 2.5298029276775703e-05,
1207
- "loss": 1.6033,
1208
  "step": 100000
1209
  },
1210
  {
1211
  "epoch": 1.49,
1212
- "learning_rate": 2.517451942315958e-05,
1213
- "loss": 1.6153,
1214
  "step": 100500
1215
  },
1216
  {
1217
  "epoch": 1.5,
1218
- "learning_rate": 2.505100956954346e-05,
1219
- "loss": 1.6065,
1220
  "step": 101000
1221
  },
1222
  {
1223
  "epoch": 1.5,
1224
- "learning_rate": 2.492749971592734e-05,
1225
- "loss": 1.5978,
1226
  "step": 101500
1227
  },
1228
  {
1229
  "epoch": 1.51,
1230
- "learning_rate": 2.4803989862311218e-05,
1231
- "loss": 1.6077,
1232
  "step": 102000
1233
  },
1234
  {
1235
  "epoch": 1.52,
1236
- "learning_rate": 2.4680480008695095e-05,
1237
- "loss": 1.6067,
1238
  "step": 102500
1239
  },
1240
  {
1241
  "epoch": 1.53,
1242
- "learning_rate": 2.4556970155078973e-05,
1243
- "loss": 1.6115,
1244
  "step": 103000
1245
  },
1246
  {
1247
  "epoch": 1.53,
1248
- "learning_rate": 2.443346030146285e-05,
1249
- "loss": 1.6389,
1250
  "step": 103500
1251
  },
1252
  {
1253
  "epoch": 1.54,
1254
- "learning_rate": 2.430995044784673e-05,
1255
- "loss": 1.6116,
1256
  "step": 104000
1257
  },
1258
  {
1259
  "epoch": 1.55,
1260
- "learning_rate": 2.418644059423061e-05,
1261
- "loss": 1.6116,
1262
  "step": 104500
1263
  },
1264
  {
1265
  "epoch": 1.56,
1266
- "learning_rate": 2.4062930740614487e-05,
1267
- "loss": 1.6344,
1268
  "step": 105000
1269
  },
1270
  {
1271
  "epoch": 1.56,
1272
- "learning_rate": 2.3939420886998365e-05,
1273
- "loss": 1.643,
1274
  "step": 105500
1275
  },
1276
  {
1277
  "epoch": 1.57,
1278
- "learning_rate": 2.3815911033382243e-05,
1279
- "loss": 1.6408,
1280
  "step": 106000
1281
  },
1282
  {
1283
  "epoch": 1.58,
1284
- "learning_rate": 2.369240117976612e-05,
1285
- "loss": 1.6395,
1286
  "step": 106500
1287
  },
1288
  {
1289
  "epoch": 1.59,
1290
- "learning_rate": 2.3568891326150002e-05,
1291
- "loss": 1.6242,
1292
  "step": 107000
1293
  },
1294
  {
1295
  "epoch": 1.59,
1296
- "learning_rate": 2.344538147253388e-05,
1297
- "loss": 1.6318,
1298
  "step": 107500
1299
  },
1300
  {
1301
  "epoch": 1.6,
1302
- "learning_rate": 2.332187161891776e-05,
1303
- "loss": 1.6518,
1304
  "step": 108000
1305
  },
1306
  {
1307
  "epoch": 1.61,
1308
- "learning_rate": 2.319836176530164e-05,
1309
- "loss": 1.6437,
1310
  "step": 108500
1311
  },
1312
  {
1313
  "epoch": 1.62,
1314
- "learning_rate": 2.3074851911685516e-05,
1315
- "loss": 1.6284,
1316
  "step": 109000
1317
  },
1318
  {
1319
  "epoch": 1.62,
1320
- "learning_rate": 2.2951342058069394e-05,
1321
- "loss": 1.6549,
1322
  "step": 109500
1323
  },
1324
  {
1325
  "epoch": 1.63,
1326
- "learning_rate": 2.282783220445327e-05,
1327
- "loss": 1.6254,
1328
  "step": 110000
1329
  },
1330
  {
1331
  "epoch": 1.64,
1332
- "learning_rate": 2.2704322350837153e-05,
1333
- "loss": 1.633,
1334
  "step": 110500
1335
  },
1336
  {
1337
  "epoch": 1.65,
1338
- "learning_rate": 2.258081249722103e-05,
1339
- "loss": 1.6299,
1340
  "step": 111000
1341
  },
1342
  {
1343
  "epoch": 1.65,
1344
- "learning_rate": 2.2457302643604908e-05,
1345
- "loss": 1.6273,
1346
  "step": 111500
1347
  },
1348
  {
1349
  "epoch": 1.66,
1350
- "learning_rate": 2.2333792789988786e-05,
1351
- "loss": 1.623,
1352
  "step": 112000
1353
  },
1354
  {
1355
  "epoch": 1.67,
1356
- "learning_rate": 2.2210282936372664e-05,
1357
- "loss": 1.6519,
1358
  "step": 112500
1359
  },
1360
  {
1361
  "epoch": 1.67,
1362
- "learning_rate": 2.208677308275654e-05,
1363
- "loss": 1.6663,
1364
  "step": 113000
1365
  },
1366
  {
1367
  "epoch": 1.68,
1368
- "learning_rate": 2.1963263229140423e-05,
1369
- "loss": 1.6739,
1370
  "step": 113500
1371
  },
1372
  {
1373
  "epoch": 1.69,
1374
- "learning_rate": 2.18397533755243e-05,
1375
- "loss": 1.6302,
1376
  "step": 114000
1377
  },
1378
  {
1379
  "epoch": 1.7,
1380
- "learning_rate": 2.1716243521908178e-05,
1381
- "loss": 1.6341,
1382
  "step": 114500
1383
  },
1384
  {
1385
  "epoch": 1.7,
1386
- "learning_rate": 2.1592733668292056e-05,
1387
- "loss": 1.6467,
1388
  "step": 115000
1389
  },
1390
  {
1391
  "epoch": 1.71,
1392
- "learning_rate": 2.1469223814675937e-05,
1393
- "loss": 1.6351,
1394
  "step": 115500
1395
  },
1396
  {
1397
  "epoch": 1.72,
1398
- "learning_rate": 2.1345713961059815e-05,
1399
- "loss": 1.6497,
1400
  "step": 116000
1401
  },
1402
  {
1403
  "epoch": 1.73,
1404
- "learning_rate": 2.1222204107443692e-05,
1405
- "loss": 1.6473,
1406
  "step": 116500
1407
  },
1408
  {
1409
  "epoch": 1.73,
1410
- "learning_rate": 2.1098694253827574e-05,
1411
- "loss": 1.661,
1412
  "step": 117000
1413
  },
1414
  {
1415
  "epoch": 1.74,
1416
- "learning_rate": 2.097518440021145e-05,
1417
- "loss": 1.6653,
1418
  "step": 117500
1419
  },
1420
  {
1421
  "epoch": 1.75,
1422
- "learning_rate": 2.085167454659533e-05,
1423
- "loss": 1.6754,
1424
  "step": 118000
1425
  },
1426
  {
1427
  "epoch": 1.76,
1428
- "learning_rate": 2.0728164692979207e-05,
1429
- "loss": 1.6572,
1430
  "step": 118500
1431
  },
1432
  {
1433
  "epoch": 1.76,
1434
- "learning_rate": 2.0604654839363085e-05,
1435
- "loss": 1.6597,
1436
  "step": 119000
1437
  },
1438
  {
1439
  "epoch": 1.77,
1440
- "learning_rate": 2.0481144985746962e-05,
1441
- "loss": 1.6732,
1442
  "step": 119500
1443
  },
1444
  {
1445
  "epoch": 1.78,
1446
- "learning_rate": 2.0357635132130843e-05,
1447
- "loss": 1.684,
1448
  "step": 120000
1449
  },
1450
  {
1451
  "epoch": 1.79,
1452
- "learning_rate": 2.023412527851472e-05,
1453
- "loss": 1.6811,
1454
  "step": 120500
1455
  },
1456
  {
1457
  "epoch": 1.79,
1458
- "learning_rate": 2.01106154248986e-05,
1459
- "loss": 1.6646,
1460
  "step": 121000
1461
  },
1462
  {
1463
  "epoch": 1.8,
1464
- "learning_rate": 1.9987105571282477e-05,
1465
- "loss": 1.649,
1466
  "step": 121500
1467
  },
1468
  {
1469
  "epoch": 1.81,
1470
- "learning_rate": 1.9863595717666354e-05,
1471
- "loss": 1.6541,
1472
  "step": 122000
1473
  },
1474
  {
1475
  "epoch": 1.82,
1476
- "learning_rate": 1.9740085864050235e-05,
1477
- "loss": 1.679,
1478
  "step": 122500
1479
  },
1480
  {
1481
  "epoch": 1.82,
1482
- "learning_rate": 1.9616576010434113e-05,
1483
- "loss": 1.679,
1484
  "step": 123000
1485
  },
1486
  {
1487
  "epoch": 1.83,
1488
- "learning_rate": 1.949306615681799e-05,
1489
- "loss": 1.6787,
1490
  "step": 123500
1491
  },
1492
  {
1493
  "epoch": 1.84,
1494
- "learning_rate": 1.9369556303201872e-05,
1495
- "loss": 1.6788,
1496
- "step": 124000
1497
  },
1498
  {
1499
  "epoch": 1.85,
1500
- "learning_rate": 1.924604644958575e-05,
1501
- "loss": 1.6826,
1502
  "step": 124500
1503
  },
1504
  {
1505
  "epoch": 1.85,
1506
- "learning_rate": 1.9122536595969628e-05,
1507
- "loss": 1.6844,
1508
  "step": 125000
1509
  },
1510
  {
1511
  "epoch": 1.86,
1512
- "learning_rate": 1.8999026742353505e-05,
1513
- "loss": 1.6819,
1514
  "step": 125500
1515
  },
1516
  {
1517
  "epoch": 1.87,
1518
- "learning_rate": 1.8875516888737386e-05,
1519
- "loss": 1.6694,
1520
  "step": 126000
1521
  },
1522
  {
1523
  "epoch": 1.87,
1524
- "learning_rate": 1.8752007035121264e-05,
1525
- "loss": 1.6982,
1526
  "step": 126500
1527
  },
1528
  {
1529
  "epoch": 1.88,
1530
- "learning_rate": 1.8628497181505142e-05,
1531
- "loss": 1.6862,
1532
  "step": 127000
1533
  },
1534
  {
1535
  "epoch": 1.89,
1536
- "learning_rate": 1.850498732788902e-05,
1537
- "loss": 1.6608,
1538
  "step": 127500
1539
  },
1540
  {
1541
  "epoch": 1.9,
1542
- "learning_rate": 1.8381477474272897e-05,
1543
- "loss": 1.6839,
1544
  "step": 128000
1545
  },
1546
  {
1547
  "epoch": 1.9,
1548
- "learning_rate": 1.8257967620656775e-05,
1549
- "loss": 1.675,
1550
  "step": 128500
1551
  },
1552
  {
1553
  "epoch": 1.91,
1554
- "learning_rate": 1.8134457767040656e-05,
1555
- "loss": 1.6948,
1556
  "step": 129000
1557
  },
1558
  {
1559
  "epoch": 1.92,
1560
- "learning_rate": 1.8010947913424534e-05,
1561
- "loss": 1.6957,
1562
  "step": 129500
1563
  },
1564
  {
1565
  "epoch": 1.93,
1566
- "learning_rate": 1.7887438059808412e-05,
1567
- "loss": 1.7279,
1568
  "step": 130000
1569
  },
1570
  {
1571
  "epoch": 1.93,
1572
- "learning_rate": 1.776392820619229e-05,
1573
- "loss": 1.6884,
1574
  "step": 130500
1575
  },
1576
  {
1577
  "epoch": 1.94,
1578
- "learning_rate": 1.7640418352576167e-05,
1579
- "loss": 1.685,
1580
  "step": 131000
1581
  },
1582
  {
1583
  "epoch": 1.95,
1584
- "learning_rate": 1.751690849896005e-05,
1585
- "loss": 1.724,
1586
  "step": 131500
1587
  },
1588
  {
1589
  "epoch": 1.96,
1590
- "learning_rate": 1.7393398645343926e-05,
1591
- "loss": 1.7142,
1592
  "step": 132000
1593
  },
1594
  {
1595
  "epoch": 1.96,
1596
- "learning_rate": 1.7269888791727804e-05,
1597
- "loss": 1.7141,
1598
  "step": 132500
1599
  },
1600
  {
1601
  "epoch": 1.97,
1602
- "learning_rate": 1.7146378938111685e-05,
1603
- "loss": 1.7107,
1604
  "step": 133000
1605
  },
1606
  {
1607
  "epoch": 1.98,
1608
- "learning_rate": 1.7022869084495563e-05,
1609
- "loss": 1.7284,
1610
  "step": 133500
1611
  },
1612
  {
1613
  "epoch": 1.99,
1614
- "learning_rate": 1.689935923087944e-05,
1615
- "loss": 1.7204,
1616
  "step": 134000
1617
  },
1618
  {
1619
  "epoch": 1.99,
1620
- "learning_rate": 1.6775849377263318e-05,
1621
- "loss": 1.7406,
1622
  "step": 134500
1623
  },
1624
  {
1625
  "epoch": 2.0,
1626
- "learning_rate": 1.66523395236472e-05,
1627
- "loss": 1.6716,
1628
- "step": 135000
1629
- },
1630
- {
1631
- "epoch": 2.01,
1632
- "learning_rate": 1.6528829670031077e-05,
1633
- "loss": 1.484,
1634
- "step": 135500
1635
- },
1636
- {
1637
- "epoch": 2.02,
1638
- "learning_rate": 1.6405319816414955e-05,
1639
- "loss": 1.4839,
1640
- "step": 136000
1641
- },
1642
- {
1643
- "epoch": 2.02,
1644
- "learning_rate": 1.6281809962798833e-05,
1645
- "loss": 1.4848,
1646
- "step": 136500
1647
- },
1648
- {
1649
- "epoch": 2.03,
1650
- "learning_rate": 1.615830010918271e-05,
1651
- "loss": 1.4659,
1652
- "step": 137000
1653
- },
1654
- {
1655
- "epoch": 2.04,
1656
- "learning_rate": 1.6034790255566588e-05,
1657
- "loss": 1.4711,
1658
- "step": 137500
1659
- },
1660
- {
1661
- "epoch": 2.05,
1662
- "learning_rate": 1.591128040195047e-05,
1663
- "loss": 1.4763,
1664
- "step": 138000
1665
- },
1666
- {
1667
- "epoch": 2.05,
1668
- "learning_rate": 1.5787770548334347e-05,
1669
- "loss": 1.471,
1670
- "step": 138500
1671
- },
1672
- {
1673
- "epoch": 2.06,
1674
- "learning_rate": 1.5664260694718225e-05,
1675
- "loss": 1.4713,
1676
- "step": 139000
1677
- },
1678
- {
1679
- "epoch": 2.07,
1680
- "learning_rate": 1.5540750841102102e-05,
1681
- "loss": 1.4905,
1682
- "step": 139500
1683
- },
1684
- {
1685
- "epoch": 2.07,
1686
- "learning_rate": 1.541724098748598e-05,
1687
- "loss": 1.4808,
1688
- "step": 140000
1689
- },
1690
- {
1691
- "epoch": 2.08,
1692
- "learning_rate": 1.529373113386986e-05,
1693
- "loss": 1.4741,
1694
- "step": 140500
1695
- },
1696
- {
1697
- "epoch": 2.09,
1698
- "learning_rate": 1.5170221280253737e-05,
1699
- "loss": 1.4827,
1700
- "step": 141000
1701
- },
1702
- {
1703
- "epoch": 2.1,
1704
- "learning_rate": 1.5046711426637618e-05,
1705
- "loss": 1.4905,
1706
- "step": 141500
1707
- },
1708
- {
1709
- "epoch": 2.1,
1710
- "learning_rate": 1.4923201573021498e-05,
1711
- "loss": 1.483,
1712
- "step": 142000
1713
- },
1714
- {
1715
- "epoch": 2.11,
1716
- "learning_rate": 1.4799691719405376e-05,
1717
- "loss": 1.475,
1718
- "step": 142500
1719
- },
1720
- {
1721
- "epoch": 2.12,
1722
- "learning_rate": 1.4676181865789253e-05,
1723
- "loss": 1.4909,
1724
- "step": 143000
1725
- },
1726
- {
1727
- "epoch": 2.13,
1728
- "learning_rate": 1.4552672012173133e-05,
1729
- "loss": 1.4882,
1730
- "step": 143500
1731
- },
1732
- {
1733
- "epoch": 2.13,
1734
- "learning_rate": 1.442916215855701e-05,
1735
- "loss": 1.5022,
1736
- "step": 144000
1737
- },
1738
- {
1739
- "epoch": 2.14,
1740
- "learning_rate": 1.4305652304940888e-05,
1741
- "loss": 1.4856,
1742
- "step": 144500
1743
- },
1744
- {
1745
- "epoch": 2.15,
1746
- "learning_rate": 1.4182142451324768e-05,
1747
- "loss": 1.4868,
1748
- "step": 145000
1749
- },
1750
- {
1751
- "epoch": 2.16,
1752
- "learning_rate": 1.4058632597708645e-05,
1753
- "loss": 1.5068,
1754
- "step": 145500
1755
- },
1756
- {
1757
- "epoch": 2.16,
1758
- "learning_rate": 1.3935122744092525e-05,
1759
- "loss": 1.504,
1760
- "step": 146000
1761
- },
1762
- {
1763
- "epoch": 2.17,
1764
- "learning_rate": 1.3811612890476403e-05,
1765
- "loss": 1.5079,
1766
- "step": 146500
1767
- },
1768
- {
1769
- "epoch": 2.18,
1770
- "learning_rate": 1.368810303686028e-05,
1771
- "loss": 1.4974,
1772
- "step": 147000
1773
- },
1774
- {
1775
- "epoch": 2.19,
1776
- "learning_rate": 1.356459318324416e-05,
1777
- "loss": 1.5066,
1778
- "step": 147500
1779
- },
1780
- {
1781
- "epoch": 2.19,
1782
- "learning_rate": 1.3441083329628038e-05,
1783
- "loss": 1.5036,
1784
- "step": 148000
1785
- },
1786
- {
1787
- "epoch": 2.2,
1788
- "learning_rate": 1.3317573476011915e-05,
1789
- "loss": 1.5227,
1790
- "step": 148500
1791
- },
1792
- {
1793
- "epoch": 2.21,
1794
- "learning_rate": 1.3194063622395795e-05,
1795
- "loss": 1.5115,
1796
- "step": 149000
1797
- },
1798
- {
1799
- "epoch": 2.22,
1800
- "learning_rate": 1.3070553768779673e-05,
1801
- "loss": 1.4878,
1802
- "step": 149500
1803
- },
1804
- {
1805
- "epoch": 2.22,
1806
- "learning_rate": 1.2947043915163554e-05,
1807
- "loss": 1.5091,
1808
- "step": 150000
1809
- },
1810
- {
1811
- "epoch": 2.23,
1812
- "learning_rate": 1.2823534061547431e-05,
1813
- "loss": 1.4812,
1814
- "step": 150500
1815
- },
1816
- {
1817
- "epoch": 2.24,
1818
- "learning_rate": 1.270002420793131e-05,
1819
- "loss": 1.4963,
1820
- "step": 151000
1821
- },
1822
- {
1823
- "epoch": 2.25,
1824
- "learning_rate": 1.2576514354315189e-05,
1825
- "loss": 1.5092,
1826
- "step": 151500
1827
- },
1828
- {
1829
- "epoch": 2.25,
1830
- "learning_rate": 1.2453004500699066e-05,
1831
- "loss": 1.5039,
1832
- "step": 152000
1833
- },
1834
- {
1835
- "epoch": 2.26,
1836
- "learning_rate": 1.2329494647082946e-05,
1837
- "loss": 1.5113,
1838
- "step": 152500
1839
- },
1840
- {
1841
- "epoch": 2.27,
1842
- "learning_rate": 1.2205984793466823e-05,
1843
- "loss": 1.5233,
1844
- "step": 153000
1845
- },
1846
- {
1847
- "epoch": 2.28,
1848
- "learning_rate": 1.2082474939850701e-05,
1849
- "loss": 1.5063,
1850
- "step": 153500
1851
- },
1852
- {
1853
- "epoch": 2.28,
1854
- "learning_rate": 1.195896508623458e-05,
1855
- "loss": 1.5,
1856
- "step": 154000
1857
- },
1858
- {
1859
- "epoch": 2.29,
1860
- "learning_rate": 1.1835455232618458e-05,
1861
- "loss": 1.5069,
1862
- "step": 154500
1863
- },
1864
- {
1865
- "epoch": 2.3,
1866
- "learning_rate": 1.1711945379002338e-05,
1867
- "loss": 1.5275,
1868
- "step": 155000
1869
- },
1870
- {
1871
- "epoch": 2.3,
1872
- "learning_rate": 1.1588435525386216e-05,
1873
- "loss": 1.5147,
1874
- "step": 155500
1875
- },
1876
- {
1877
- "epoch": 2.31,
1878
- "learning_rate": 1.1464925671770093e-05,
1879
- "loss": 1.5021,
1880
- "step": 156000
1881
- },
1882
- {
1883
- "epoch": 2.32,
1884
- "learning_rate": 1.1341415818153973e-05,
1885
- "loss": 1.5065,
1886
- "step": 156500
1887
- },
1888
- {
1889
- "epoch": 2.33,
1890
- "learning_rate": 1.1217905964537852e-05,
1891
- "loss": 1.5268,
1892
- "step": 157000
1893
- },
1894
- {
1895
- "epoch": 2.33,
1896
- "learning_rate": 1.109439611092173e-05,
1897
- "loss": 1.512,
1898
- "step": 157500
1899
- },
1900
- {
1901
- "epoch": 2.34,
1902
- "learning_rate": 1.0970886257305608e-05,
1903
- "loss": 1.5226,
1904
- "step": 158000
1905
- },
1906
- {
1907
- "epoch": 2.35,
1908
- "learning_rate": 1.0847376403689487e-05,
1909
- "loss": 1.5127,
1910
- "step": 158500
1911
- },
1912
- {
1913
- "epoch": 2.36,
1914
- "learning_rate": 1.0723866550073365e-05,
1915
- "loss": 1.4933,
1916
- "step": 159000
1917
- },
1918
- {
1919
- "epoch": 2.36,
1920
- "learning_rate": 1.0600356696457244e-05,
1921
- "loss": 1.5301,
1922
- "step": 159500
1923
- },
1924
- {
1925
- "epoch": 2.37,
1926
- "learning_rate": 1.0476846842841122e-05,
1927
- "loss": 1.5302,
1928
- "step": 160000
1929
- },
1930
- {
1931
- "epoch": 2.38,
1932
- "learning_rate": 1.0353336989225001e-05,
1933
- "loss": 1.5325,
1934
- "step": 160500
1935
- },
1936
- {
1937
- "epoch": 2.39,
1938
- "learning_rate": 1.022982713560888e-05,
1939
- "loss": 1.5217,
1940
- "step": 161000
1941
- },
1942
- {
1943
- "epoch": 2.39,
1944
- "learning_rate": 1.0106317281992759e-05,
1945
- "loss": 1.5094,
1946
- "step": 161500
1947
- },
1948
- {
1949
- "epoch": 2.4,
1950
- "learning_rate": 9.982807428376636e-06,
1951
- "loss": 1.5011,
1952
- "step": 162000
1953
- },
1954
- {
1955
- "epoch": 2.41,
1956
- "learning_rate": 9.859297574760514e-06,
1957
- "loss": 1.523,
1958
- "step": 162500
1959
- },
1960
- {
1961
- "epoch": 2.42,
1962
- "learning_rate": 9.735787721144394e-06,
1963
- "loss": 1.5268,
1964
- "step": 163000
1965
- },
1966
- {
1967
- "epoch": 2.42,
1968
- "learning_rate": 9.612277867528271e-06,
1969
- "loss": 1.526,
1970
- "step": 163500
1971
- },
1972
- {
1973
- "epoch": 2.43,
1974
- "learning_rate": 9.488768013912149e-06,
1975
- "loss": 1.5427,
1976
- "step": 164000
1977
- },
1978
- {
1979
- "epoch": 2.44,
1980
- "learning_rate": 9.365258160296028e-06,
1981
- "loss": 1.5325,
1982
- "step": 164500
1983
- },
1984
- {
1985
- "epoch": 2.45,
1986
- "learning_rate": 9.241748306679908e-06,
1987
- "loss": 1.5152,
1988
- "step": 165000
1989
- },
1990
- {
1991
- "epoch": 2.45,
1992
- "learning_rate": 9.118238453063786e-06,
1993
- "loss": 1.5045,
1994
- "step": 165500
1995
- },
1996
- {
1997
- "epoch": 2.46,
1998
- "learning_rate": 8.994728599447665e-06,
1999
- "loss": 1.5008,
2000
- "step": 166000
2001
- },
2002
- {
2003
- "epoch": 2.47,
2004
- "learning_rate": 8.871218745831543e-06,
2005
- "loss": 1.515,
2006
- "step": 166500
2007
- },
2008
- {
2009
- "epoch": 2.48,
2010
- "learning_rate": 8.74770889221542e-06,
2011
- "loss": 1.5166,
2012
- "step": 167000
2013
- },
2014
- {
2015
- "epoch": 2.48,
2016
- "learning_rate": 8.6241990385993e-06,
2017
- "loss": 1.5336,
2018
- "step": 167500
2019
- },
2020
- {
2021
- "epoch": 2.49,
2022
- "learning_rate": 8.500689184983178e-06,
2023
- "loss": 1.527,
2024
- "step": 168000
2025
- },
2026
- {
2027
- "epoch": 2.5,
2028
- "learning_rate": 8.377179331367055e-06,
2029
- "loss": 1.5306,
2030
- "step": 168500
2031
- },
2032
- {
2033
- "epoch": 2.5,
2034
- "learning_rate": 8.253669477750937e-06,
2035
- "loss": 1.5094,
2036
- "step": 169000
2037
- },
2038
- {
2039
- "epoch": 2.51,
2040
- "learning_rate": 8.130159624134814e-06,
2041
- "loss": 1.5227,
2042
- "step": 169500
2043
- },
2044
- {
2045
- "epoch": 2.52,
2046
- "learning_rate": 8.006649770518692e-06,
2047
- "loss": 1.5454,
2048
- "step": 170000
2049
- },
2050
- {
2051
- "epoch": 2.53,
2052
- "learning_rate": 7.883139916902572e-06,
2053
- "loss": 1.547,
2054
- "step": 170500
2055
- },
2056
- {
2057
- "epoch": 2.53,
2058
- "learning_rate": 7.75963006328645e-06,
2059
- "loss": 1.5398,
2060
- "step": 171000
2061
- },
2062
- {
2063
- "epoch": 2.54,
2064
- "learning_rate": 7.636120209670327e-06,
2065
- "loss": 1.541,
2066
- "step": 171500
2067
- },
2068
- {
2069
- "epoch": 2.55,
2070
- "learning_rate": 7.5126103560542065e-06,
2071
- "loss": 1.5379,
2072
- "step": 172000
2073
- },
2074
- {
2075
- "epoch": 2.56,
2076
- "learning_rate": 7.389100502438084e-06,
2077
- "loss": 1.5276,
2078
- "step": 172500
2079
- },
2080
- {
2081
- "epoch": 2.56,
2082
- "learning_rate": 7.265590648821963e-06,
2083
- "loss": 1.521,
2084
- "step": 173000
2085
- },
2086
- {
2087
- "epoch": 2.57,
2088
- "learning_rate": 7.142080795205842e-06,
2089
- "loss": 1.5233,
2090
- "step": 173500
2091
- },
2092
- {
2093
- "epoch": 2.58,
2094
- "learning_rate": 7.018570941589721e-06,
2095
- "loss": 1.5517,
2096
- "step": 174000
2097
- },
2098
- {
2099
- "epoch": 2.59,
2100
- "learning_rate": 6.895061087973599e-06,
2101
- "loss": 1.5515,
2102
- "step": 174500
2103
- },
2104
- {
2105
- "epoch": 2.59,
2106
- "learning_rate": 6.771551234357477e-06,
2107
- "loss": 1.5417,
2108
- "step": 175000
2109
- },
2110
- {
2111
- "epoch": 2.6,
2112
- "learning_rate": 6.648041380741356e-06,
2113
- "loss": 1.5306,
2114
- "step": 175500
2115
- },
2116
- {
2117
- "epoch": 2.61,
2118
- "learning_rate": 6.524531527125234e-06,
2119
- "loss": 1.5262,
2120
- "step": 176000
2121
- },
2122
- {
2123
- "epoch": 2.62,
2124
- "learning_rate": 6.401021673509112e-06,
2125
- "loss": 1.5289,
2126
- "step": 176500
2127
- },
2128
- {
2129
- "epoch": 2.62,
2130
- "learning_rate": 6.277511819892991e-06,
2131
- "loss": 1.53,
2132
- "step": 177000
2133
- },
2134
- {
2135
- "epoch": 2.63,
2136
- "learning_rate": 6.15400196627687e-06,
2137
- "loss": 1.5116,
2138
- "step": 177500
2139
- },
2140
- {
2141
- "epoch": 2.64,
2142
- "learning_rate": 6.030492112660748e-06,
2143
- "loss": 1.528,
2144
- "step": 178000
2145
- },
2146
- {
2147
- "epoch": 2.65,
2148
- "learning_rate": 5.906982259044627e-06,
2149
- "loss": 1.5376,
2150
- "step": 178500
2151
- },
2152
- {
2153
- "epoch": 2.65,
2154
- "learning_rate": 5.783472405428506e-06,
2155
- "loss": 1.5413,
2156
- "step": 179000
2157
- },
2158
- {
2159
- "epoch": 2.66,
2160
- "learning_rate": 5.659962551812384e-06,
2161
- "loss": 1.5402,
2162
- "step": 179500
2163
- },
2164
- {
2165
- "epoch": 2.67,
2166
- "learning_rate": 5.536452698196262e-06,
2167
- "loss": 1.56,
2168
- "step": 180000
2169
- },
2170
- {
2171
- "epoch": 2.68,
2172
- "learning_rate": 5.412942844580141e-06,
2173
- "loss": 1.5423,
2174
- "step": 180500
2175
- },
2176
- {
2177
- "epoch": 2.68,
2178
- "learning_rate": 5.289432990964019e-06,
2179
- "loss": 1.5453,
2180
- "step": 181000
2181
- },
2182
- {
2183
- "epoch": 2.69,
2184
- "learning_rate": 5.165923137347898e-06,
2185
- "loss": 1.5136,
2186
- "step": 181500
2187
- },
2188
- {
2189
- "epoch": 2.7,
2190
- "learning_rate": 5.0424132837317765e-06,
2191
- "loss": 1.5321,
2192
- "step": 182000
2193
- },
2194
- {
2195
- "epoch": 2.7,
2196
- "learning_rate": 4.918903430115654e-06,
2197
- "loss": 1.5518,
2198
- "step": 182500
2199
- },
2200
- {
2201
- "epoch": 2.71,
2202
- "learning_rate": 4.795393576499534e-06,
2203
- "loss": 1.5524,
2204
- "step": 183000
2205
- },
2206
- {
2207
- "epoch": 2.72,
2208
- "learning_rate": 4.671883722883412e-06,
2209
- "loss": 1.5433,
2210
- "step": 183500
2211
- },
2212
- {
2213
- "epoch": 2.73,
2214
- "learning_rate": 4.54837386926729e-06,
2215
- "loss": 1.5441,
2216
- "step": 184000
2217
- },
2218
- {
2219
- "epoch": 2.73,
2220
- "learning_rate": 4.424864015651169e-06,
2221
- "loss": 1.5566,
2222
- "step": 184500
2223
- },
2224
- {
2225
- "epoch": 2.74,
2226
- "learning_rate": 4.301354162035048e-06,
2227
- "loss": 1.518,
2228
- "step": 185000
2229
- },
2230
- {
2231
- "epoch": 2.75,
2232
- "learning_rate": 4.177844308418926e-06,
2233
- "loss": 1.5277,
2234
- "step": 185500
2235
- },
2236
- {
2237
- "epoch": 2.76,
2238
- "learning_rate": 4.054334454802804e-06,
2239
- "loss": 1.5427,
2240
- "step": 186000
2241
- },
2242
- {
2243
- "epoch": 2.76,
2244
- "learning_rate": 3.930824601186683e-06,
2245
- "loss": 1.5548,
2246
- "step": 186500
2247
- },
2248
- {
2249
- "epoch": 2.77,
2250
- "learning_rate": 3.807314747570561e-06,
2251
- "loss": 1.5419,
2252
- "step": 187000
2253
- },
2254
- {
2255
- "epoch": 2.78,
2256
- "learning_rate": 3.68380489395444e-06,
2257
- "loss": 1.5493,
2258
- "step": 187500
2259
- },
2260
- {
2261
- "epoch": 2.79,
2262
- "learning_rate": 3.5602950403383183e-06,
2263
- "loss": 1.5695,
2264
- "step": 188000
2265
- },
2266
- {
2267
- "epoch": 2.79,
2268
- "learning_rate": 3.436785186722197e-06,
2269
- "loss": 1.5429,
2270
- "step": 188500
2271
- },
2272
- {
2273
- "epoch": 2.8,
2274
- "learning_rate": 3.313275333106075e-06,
2275
- "loss": 1.5547,
2276
- "step": 189000
2277
- },
2278
- {
2279
- "epoch": 2.81,
2280
- "learning_rate": 3.189765479489954e-06,
2281
- "loss": 1.5306,
2282
- "step": 189500
2283
- },
2284
- {
2285
- "epoch": 2.82,
2286
- "learning_rate": 3.0662556258738323e-06,
2287
- "loss": 1.5336,
2288
- "step": 190000
2289
- },
2290
- {
2291
- "epoch": 2.82,
2292
- "learning_rate": 2.942745772257711e-06,
2293
- "loss": 1.5276,
2294
- "step": 190500
2295
- },
2296
- {
2297
- "epoch": 2.83,
2298
- "learning_rate": 2.8192359186415894e-06,
2299
- "loss": 1.5453,
2300
- "step": 191000
2301
- },
2302
- {
2303
- "epoch": 2.84,
2304
- "learning_rate": 2.6957260650254676e-06,
2305
- "loss": 1.5501,
2306
- "step": 191500
2307
- },
2308
- {
2309
- "epoch": 2.85,
2310
- "learning_rate": 2.5722162114093466e-06,
2311
- "loss": 1.5465,
2312
- "step": 192000
2313
- },
2314
- {
2315
- "epoch": 2.85,
2316
- "learning_rate": 2.448706357793225e-06,
2317
- "loss": 1.5485,
2318
- "step": 192500
2319
- },
2320
- {
2321
- "epoch": 2.86,
2322
- "learning_rate": 2.3251965041771034e-06,
2323
- "loss": 1.5467,
2324
- "step": 193000
2325
- },
2326
- {
2327
- "epoch": 2.87,
2328
- "learning_rate": 2.201686650560982e-06,
2329
- "loss": 1.5694,
2330
- "step": 193500
2331
- },
2332
- {
2333
- "epoch": 2.88,
2334
- "learning_rate": 2.0781767969448606e-06,
2335
- "loss": 1.5629,
2336
- "step": 194000
2337
- },
2338
- {
2339
- "epoch": 2.88,
2340
- "learning_rate": 1.9546669433287387e-06,
2341
- "loss": 1.534,
2342
- "step": 194500
2343
- },
2344
- {
2345
- "epoch": 2.89,
2346
- "learning_rate": 1.8311570897126173e-06,
2347
- "loss": 1.5503,
2348
- "step": 195000
2349
- },
2350
- {
2351
- "epoch": 2.9,
2352
- "learning_rate": 1.707647236096496e-06,
2353
- "loss": 1.5639,
2354
- "step": 195500
2355
- },
2356
- {
2357
- "epoch": 2.9,
2358
- "learning_rate": 1.5841373824803743e-06,
2359
- "loss": 1.5585,
2360
- "step": 196000
2361
- },
2362
- {
2363
- "epoch": 2.91,
2364
- "learning_rate": 1.4606275288642529e-06,
2365
- "loss": 1.5703,
2366
- "step": 196500
2367
- },
2368
- {
2369
- "epoch": 2.92,
2370
- "learning_rate": 1.3371176752481315e-06,
2371
- "loss": 1.5633,
2372
- "step": 197000
2373
- },
2374
- {
2375
- "epoch": 2.93,
2376
- "learning_rate": 1.2136078216320098e-06,
2377
- "loss": 1.5459,
2378
- "step": 197500
2379
- },
2380
- {
2381
- "epoch": 2.93,
2382
- "learning_rate": 1.0900979680158882e-06,
2383
- "loss": 1.5609,
2384
- "step": 198000
2385
- },
2386
- {
2387
- "epoch": 2.94,
2388
- "learning_rate": 9.665881143997668e-07,
2389
- "loss": 1.557,
2390
- "step": 198500
2391
- },
2392
- {
2393
- "epoch": 2.95,
2394
- "learning_rate": 8.430782607836453e-07,
2395
- "loss": 1.5799,
2396
- "step": 199000
2397
- },
2398
- {
2399
- "epoch": 2.96,
2400
- "learning_rate": 7.195684071675239e-07,
2401
- "loss": 1.5691,
2402
- "step": 199500
2403
- },
2404
- {
2405
- "epoch": 2.96,
2406
- "learning_rate": 5.960585535514024e-07,
2407
- "loss": 1.5571,
2408
- "step": 200000
2409
- },
2410
- {
2411
- "epoch": 2.97,
2412
- "learning_rate": 4.7254869993528084e-07,
2413
- "loss": 1.5483,
2414
- "step": 200500
2415
- },
2416
- {
2417
- "epoch": 2.98,
2418
- "learning_rate": 3.490388463191593e-07,
2419
- "loss": 1.5659,
2420
- "step": 201000
2421
- },
2422
- {
2423
- "epoch": 2.99,
2424
- "learning_rate": 2.2552899270303785e-07,
2425
- "loss": 1.5672,
2426
- "step": 201500
2427
- },
2428
- {
2429
- "epoch": 2.99,
2430
- "learning_rate": 1.0201913908691636e-07,
2431
- "loss": 1.578,
2432
- "step": 202000
2433
- },
2434
- {
2435
- "epoch": 3.0,
2436
- "step": 202413,
2437
- "total_flos": 3.759621873629921e+17,
2438
- "train_loss": 1.602629992106659,
2439
- "train_runtime": 64476.8032,
2440
- "train_samples_per_second": 6.279,
2441
- "train_steps_per_second": 3.139
2442
  }
2443
  ],
2444
- "max_steps": 202413,
2445
- "num_train_epochs": 3,
2446
- "total_flos": 3.759621873629921e+17,
2447
  "trial_name": null,
2448
  "trial_params": null
2449
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 2.0,
5
+ "global_step": 134942,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
9
  "log_history": [
10
  {
11
  "epoch": 0.01,
12
+ "learning_rate": 4.981473521957582e-05,
13
+ "loss": 1.4713,
14
  "step": 500
15
  },
16
  {
17
  "epoch": 0.01,
18
+ "learning_rate": 4.962947043915164e-05,
19
+ "loss": 1.48,
20
  "step": 1000
21
  },
22
  {
23
  "epoch": 0.02,
24
+ "learning_rate": 4.944420565872746e-05,
25
+ "loss": 1.5275,
26
  "step": 1500
27
  },
28
  {
29
  "epoch": 0.03,
30
+ "learning_rate": 4.9258940878303276e-05,
31
+ "loss": 1.5373,
32
  "step": 2000
33
  },
34
  {
35
  "epoch": 0.04,
36
+ "learning_rate": 4.907367609787909e-05,
37
+ "loss": 1.5363,
38
  "step": 2500
39
  },
40
  {
41
  "epoch": 0.04,
42
+ "learning_rate": 4.8888411317454905e-05,
43
+ "loss": 1.5386,
44
  "step": 3000
45
  },
46
  {
47
  "epoch": 0.05,
48
+ "learning_rate": 4.8703146537030724e-05,
49
+ "loss": 1.5377,
50
  "step": 3500
51
  },
52
  {
53
  "epoch": 0.06,
54
+ "learning_rate": 4.851788175660654e-05,
55
+ "loss": 1.5505,
56
  "step": 4000
57
  },
58
  {
59
  "epoch": 0.07,
60
+ "learning_rate": 4.833261697618236e-05,
61
+ "loss": 1.5443,
62
  "step": 4500
63
  },
64
  {
65
  "epoch": 0.07,
66
+ "learning_rate": 4.814735219575818e-05,
67
+ "loss": 1.5775,
68
  "step": 5000
69
  },
70
  {
71
  "epoch": 0.08,
72
+ "learning_rate": 4.7962087415334e-05,
73
+ "loss": 1.5587,
74
  "step": 5500
75
  },
76
  {
77
  "epoch": 0.09,
78
+ "learning_rate": 4.7776822634909815e-05,
79
+ "loss": 1.566,
80
  "step": 6000
81
  },
82
  {
83
  "epoch": 0.1,
84
+ "learning_rate": 4.7591557854485634e-05,
85
+ "loss": 1.5715,
86
  "step": 6500
87
  },
88
  {
89
  "epoch": 0.1,
90
+ "learning_rate": 4.740629307406145e-05,
91
+ "loss": 1.5798,
92
  "step": 7000
93
  },
94
  {
95
  "epoch": 0.11,
96
+ "learning_rate": 4.722102829363727e-05,
97
+ "loss": 1.5844,
98
  "step": 7500
99
  },
100
  {
101
  "epoch": 0.12,
102
+ "learning_rate": 4.703576351321309e-05,
103
+ "loss": 1.5983,
104
  "step": 8000
105
  },
106
  {
107
  "epoch": 0.13,
108
+ "learning_rate": 4.685049873278891e-05,
109
+ "loss": 1.5914,
110
  "step": 8500
111
  },
112
  {
113
  "epoch": 0.13,
114
+ "learning_rate": 4.6665233952364725e-05,
115
+ "loss": 1.5988,
116
  "step": 9000
117
  },
118
  {
119
  "epoch": 0.14,
120
+ "learning_rate": 4.6479969171940543e-05,
121
+ "loss": 1.5802,
122
  "step": 9500
123
  },
124
  {
125
  "epoch": 0.15,
126
+ "learning_rate": 4.6294704391516355e-05,
127
+ "loss": 1.5803,
128
  "step": 10000
129
  },
130
  {
131
  "epoch": 0.16,
132
+ "learning_rate": 4.610943961109217e-05,
133
+ "loss": 1.567,
134
  "step": 10500
135
  },
136
  {
137
  "epoch": 0.16,
138
+ "learning_rate": 4.592417483066799e-05,
139
+ "loss": 1.612,
140
  "step": 11000
141
  },
142
  {
143
  "epoch": 0.17,
144
+ "learning_rate": 4.573891005024381e-05,
145
+ "loss": 1.6182,
146
  "step": 11500
147
  },
148
  {
149
  "epoch": 0.18,
150
+ "learning_rate": 4.555364526981963e-05,
151
+ "loss": 1.5818,
152
  "step": 12000
153
  },
154
  {
155
  "epoch": 0.19,
156
+ "learning_rate": 4.5368380489395447e-05,
157
+ "loss": 1.602,
158
  "step": 12500
159
  },
160
  {
161
  "epoch": 0.19,
162
+ "learning_rate": 4.5183115708971265e-05,
163
+ "loss": 1.5877,
164
  "step": 13000
165
  },
166
  {
167
  "epoch": 0.2,
168
+ "learning_rate": 4.499785092854708e-05,
169
+ "loss": 1.5995,
170
  "step": 13500
171
  },
172
  {
173
  "epoch": 0.21,
174
+ "learning_rate": 4.48125861481229e-05,
175
+ "loss": 1.6053,
176
  "step": 14000
177
  },
178
  {
179
  "epoch": 0.21,
180
+ "learning_rate": 4.462732136769871e-05,
181
+ "loss": 1.5905,
182
  "step": 14500
183
  },
184
  {
185
  "epoch": 0.22,
186
+ "learning_rate": 4.444205658727453e-05,
187
+ "loss": 1.5788,
188
  "step": 15000
189
  },
190
  {
191
  "epoch": 0.23,
192
+ "learning_rate": 4.425679180685035e-05,
193
+ "loss": 1.6116,
194
  "step": 15500
195
  },
196
  {
197
  "epoch": 0.24,
198
+ "learning_rate": 4.407152702642617e-05,
199
+ "loss": 1.602,
200
  "step": 16000
201
  },
202
  {
203
  "epoch": 0.24,
204
+ "learning_rate": 4.3886262246001986e-05,
205
+ "loss": 1.6282,
206
  "step": 16500
207
  },
208
  {
209
  "epoch": 0.25,
210
+ "learning_rate": 4.3700997465577804e-05,
211
+ "loss": 1.6232,
212
  "step": 17000
213
  },
214
  {
215
  "epoch": 0.26,
216
+ "learning_rate": 4.351573268515363e-05,
217
+ "loss": 1.6178,
218
  "step": 17500
219
  },
220
  {
221
  "epoch": 0.27,
222
+ "learning_rate": 4.333046790472944e-05,
223
+ "loss": 1.6305,
224
  "step": 18000
225
  },
226
  {
227
  "epoch": 0.27,
228
+ "learning_rate": 4.314520312430526e-05,
229
+ "loss": 1.614,
230
  "step": 18500
231
  },
232
  {
233
  "epoch": 0.28,
234
+ "learning_rate": 4.295993834388108e-05,
235
+ "loss": 1.6242,
236
  "step": 19000
237
  },
238
  {
239
  "epoch": 0.29,
240
+ "learning_rate": 4.2774673563456896e-05,
241
+ "loss": 1.6125,
242
  "step": 19500
243
  },
244
  {
245
  "epoch": 0.3,
246
+ "learning_rate": 4.2589408783032714e-05,
247
+ "loss": 1.6274,
248
  "step": 20000
249
  },
250
  {
251
  "epoch": 0.3,
252
+ "learning_rate": 4.240414400260853e-05,
253
+ "loss": 1.6265,
254
  "step": 20500
255
  },
256
  {
257
  "epoch": 0.31,
258
+ "learning_rate": 4.221887922218435e-05,
259
+ "loss": 1.6125,
260
  "step": 21000
261
  },
262
  {
263
  "epoch": 0.32,
264
+ "learning_rate": 4.203361444176017e-05,
265
+ "loss": 1.6225,
266
  "step": 21500
267
  },
268
  {
269
  "epoch": 0.33,
270
+ "learning_rate": 4.184834966133598e-05,
271
+ "loss": 1.631,
272
  "step": 22000
273
  },
274
  {
275
  "epoch": 0.33,
276
+ "learning_rate": 4.16630848809118e-05,
277
+ "loss": 1.6501,
278
  "step": 22500
279
  },
280
  {
281
  "epoch": 0.34,
282
+ "learning_rate": 4.147782010048762e-05,
283
+ "loss": 1.6484,
284
  "step": 23000
285
  },
286
  {
287
  "epoch": 0.35,
288
+ "learning_rate": 4.1292555320063436e-05,
289
+ "loss": 1.6428,
290
  "step": 23500
291
  },
292
  {
293
  "epoch": 0.36,
294
+ "learning_rate": 4.1107290539639254e-05,
295
+ "loss": 1.6506,
296
  "step": 24000
297
  },
298
  {
299
  "epoch": 0.36,
300
+ "learning_rate": 4.092202575921507e-05,
301
+ "loss": 1.6386,
302
  "step": 24500
303
  },
304
  {
305
  "epoch": 0.37,
306
+ "learning_rate": 4.073676097879089e-05,
307
+ "loss": 1.6137,
308
  "step": 25000
309
  },
310
  {
311
  "epoch": 0.38,
312
+ "learning_rate": 4.055149619836671e-05,
313
+ "loss": 1.6623,
314
  "step": 25500
315
  },
316
  {
317
  "epoch": 0.39,
318
+ "learning_rate": 4.036623141794252e-05,
319
+ "loss": 1.6357,
320
  "step": 26000
321
  },
322
  {
323
  "epoch": 0.39,
324
+ "learning_rate": 4.018096663751834e-05,
325
+ "loss": 1.6643,
326
  "step": 26500
327
  },
328
  {
329
  "epoch": 0.4,
330
+ "learning_rate": 3.999570185709416e-05,
331
+ "loss": 1.6583,
332
  "step": 27000
333
  },
334
  {
335
  "epoch": 0.41,
336
+ "learning_rate": 3.9810437076669975e-05,
337
+ "loss": 1.6552,
338
  "step": 27500
339
  },
340
  {
341
  "epoch": 0.41,
342
+ "learning_rate": 3.9625172296245794e-05,
343
+ "loss": 1.6485,
344
  "step": 28000
345
  },
346
  {
347
  "epoch": 0.42,
348
+ "learning_rate": 3.943990751582161e-05,
349
+ "loss": 1.6431,
350
  "step": 28500
351
  },
352
  {
353
  "epoch": 0.43,
354
+ "learning_rate": 3.925464273539744e-05,
355
+ "loss": 1.6368,
356
  "step": 29000
357
  },
358
  {
359
  "epoch": 0.44,
360
+ "learning_rate": 3.906937795497325e-05,
361
+ "loss": 1.6616,
362
  "step": 29500
363
  },
364
  {
365
  "epoch": 0.44,
366
+ "learning_rate": 3.888411317454907e-05,
367
+ "loss": 1.6341,
368
  "step": 30000
369
  },
370
  {
371
  "epoch": 0.45,
372
+ "learning_rate": 3.8698848394124885e-05,
373
+ "loss": 1.6563,
374
  "step": 30500
375
  },
376
  {
377
  "epoch": 0.46,
378
+ "learning_rate": 3.8513583613700704e-05,
379
+ "loss": 1.6536,
380
  "step": 31000
381
  },
382
  {
383
  "epoch": 0.47,
384
+ "learning_rate": 3.832831883327652e-05,
385
+ "loss": 1.6615,
386
  "step": 31500
387
  },
388
  {
389
  "epoch": 0.47,
390
+ "learning_rate": 3.814305405285234e-05,
391
+ "loss": 1.6548,
392
  "step": 32000
393
  },
394
  {
395
  "epoch": 0.48,
396
+ "learning_rate": 3.795778927242816e-05,
397
+ "loss": 1.6732,
398
  "step": 32500
399
  },
400
  {
401
  "epoch": 0.49,
402
+ "learning_rate": 3.777252449200398e-05,
403
+ "loss": 1.6839,
404
  "step": 33000
405
  },
406
  {
407
  "epoch": 0.5,
408
+ "learning_rate": 3.7587259711579795e-05,
409
+ "loss": 1.6735,
410
  "step": 33500
411
  },
412
  {
413
  "epoch": 0.5,
414
+ "learning_rate": 3.7401994931155607e-05,
415
+ "loss": 1.672,
416
  "step": 34000
417
  },
418
  {
419
  "epoch": 0.51,
420
+ "learning_rate": 3.7216730150731425e-05,
421
+ "loss": 1.6569,
422
  "step": 34500
423
  },
424
  {
425
  "epoch": 0.52,
426
+ "learning_rate": 3.703146537030724e-05,
427
+ "loss": 1.6462,
428
  "step": 35000
429
  },
430
  {
431
  "epoch": 0.53,
432
+ "learning_rate": 3.684620058988306e-05,
433
+ "loss": 1.6683,
434
  "step": 35500
435
  },
436
  {
437
  "epoch": 0.53,
438
+ "learning_rate": 3.666093580945888e-05,
439
+ "loss": 1.6682,
440
  "step": 36000
441
  },
442
  {
443
  "epoch": 0.54,
444
+ "learning_rate": 3.64756710290347e-05,
445
+ "loss": 1.6598,
446
  "step": 36500
447
  },
448
  {
449
  "epoch": 0.55,
450
+ "learning_rate": 3.6290406248610516e-05,
451
+ "loss": 1.6505,
452
  "step": 37000
453
  },
454
  {
455
  "epoch": 0.56,
456
+ "learning_rate": 3.6105141468186335e-05,
457
+ "loss": 1.6535,
458
  "step": 37500
459
  },
460
  {
461
  "epoch": 0.56,
462
+ "learning_rate": 3.5919876687762146e-05,
463
+ "loss": 1.6637,
464
  "step": 38000
465
  },
466
  {
467
  "epoch": 0.57,
468
+ "learning_rate": 3.5734611907337965e-05,
469
+ "loss": 1.6534,
470
  "step": 38500
471
  },
472
  {
473
  "epoch": 0.58,
474
+ "learning_rate": 3.554934712691378e-05,
475
+ "loss": 1.6512,
476
  "step": 39000
477
  },
478
  {
479
  "epoch": 0.59,
480
+ "learning_rate": 3.53640823464896e-05,
481
+ "loss": 1.6602,
482
  "step": 39500
483
  },
484
  {
485
  "epoch": 0.59,
486
+ "learning_rate": 3.5178817566065426e-05,
487
+ "loss": 1.6802,
488
  "step": 40000
489
  },
490
  {
491
  "epoch": 0.6,
492
+ "learning_rate": 3.4993552785641245e-05,
493
+ "loss": 1.6637,
494
  "step": 40500
495
  },
496
  {
497
  "epoch": 0.61,
498
+ "learning_rate": 3.480828800521706e-05,
499
+ "loss": 1.6669,
500
  "step": 41000
501
  },
502
  {
503
  "epoch": 0.62,
504
+ "learning_rate": 3.4623023224792874e-05,
505
+ "loss": 1.6595,
506
  "step": 41500
507
  },
508
  {
509
  "epoch": 0.62,
510
+ "learning_rate": 3.443775844436869e-05,
511
+ "loss": 1.6746,
512
  "step": 42000
513
  },
514
  {
515
  "epoch": 0.63,
516
+ "learning_rate": 3.425249366394451e-05,
517
+ "loss": 1.6679,
518
  "step": 42500
519
  },
520
  {
521
  "epoch": 0.64,
522
+ "learning_rate": 3.406722888352033e-05,
523
+ "loss": 1.6596,
524
  "step": 43000
525
  },
526
  {
527
  "epoch": 0.64,
528
+ "learning_rate": 3.388196410309615e-05,
529
+ "loss": 1.6818,
530
  "step": 43500
531
  },
532
  {
533
  "epoch": 0.65,
534
+ "learning_rate": 3.3696699322671966e-05,
535
+ "loss": 1.6862,
536
  "step": 44000
537
  },
538
  {
539
  "epoch": 0.66,
540
+ "learning_rate": 3.3511434542247784e-05,
541
+ "loss": 1.6578,
542
  "step": 44500
543
  },
544
  {
545
  "epoch": 0.67,
546
+ "learning_rate": 3.33261697618236e-05,
547
+ "loss": 1.6567,
548
  "step": 45000
549
  },
550
  {
551
  "epoch": 0.67,
552
+ "learning_rate": 3.314090498139942e-05,
553
+ "loss": 1.6701,
554
  "step": 45500
555
  },
556
  {
557
  "epoch": 0.68,
558
+ "learning_rate": 3.295564020097523e-05,
559
+ "loss": 1.6861,
560
  "step": 46000
561
  },
562
  {
563
  "epoch": 0.69,
564
+ "learning_rate": 3.277037542055105e-05,
565
+ "loss": 1.6905,
566
  "step": 46500
567
  },
568
  {
569
  "epoch": 0.7,
570
+ "learning_rate": 3.258511064012687e-05,
571
+ "loss": 1.6935,
572
  "step": 47000
573
  },
574
  {
575
  "epoch": 0.7,
576
+ "learning_rate": 3.239984585970269e-05,
577
+ "loss": 1.6464,
578
  "step": 47500
579
  },
580
  {
581
  "epoch": 0.71,
582
+ "learning_rate": 3.2214581079278506e-05,
583
+ "loss": 1.6827,
584
  "step": 48000
585
  },
586
  {
587
  "epoch": 0.72,
588
+ "learning_rate": 3.2029316298854324e-05,
589
+ "loss": 1.6565,
590
  "step": 48500
591
  },
592
  {
593
  "epoch": 0.73,
594
+ "learning_rate": 3.184405151843014e-05,
595
+ "loss": 1.6695,
596
  "step": 49000
597
  },
598
  {
599
  "epoch": 0.73,
600
+ "learning_rate": 3.165878673800596e-05,
601
+ "loss": 1.6949,
602
  "step": 49500
603
  },
604
  {
605
  "epoch": 0.74,
606
+ "learning_rate": 3.147352195758177e-05,
607
+ "loss": 1.6847,
608
  "step": 50000
609
  },
610
  {
611
  "epoch": 0.75,
612
+ "learning_rate": 3.128825717715759e-05,
613
+ "loss": 1.6726,
614
  "step": 50500
615
  },
616
  {
617
  "epoch": 0.76,
618
+ "learning_rate": 3.110299239673341e-05,
619
+ "loss": 1.6729,
620
  "step": 51000
621
  },
622
  {
623
  "epoch": 0.76,
624
+ "learning_rate": 3.0917727616309234e-05,
625
+ "loss": 1.7076,
626
  "step": 51500
627
  },
628
  {
629
  "epoch": 0.77,
630
+ "learning_rate": 3.073246283588505e-05,
631
+ "loss": 1.7006,
632
  "step": 52000
633
  },
634
  {
635
  "epoch": 0.78,
636
+ "learning_rate": 3.054719805546087e-05,
637
+ "loss": 1.6812,
638
  "step": 52500
639
  },
640
  {
641
  "epoch": 0.79,
642
+ "learning_rate": 3.0361933275036685e-05,
643
+ "loss": 1.6976,
644
  "step": 53000
645
  },
646
  {
647
  "epoch": 0.79,
648
+ "learning_rate": 3.0176668494612504e-05,
649
+ "loss": 1.6668,
650
  "step": 53500
651
  },
652
  {
653
  "epoch": 0.8,
654
+ "learning_rate": 2.9991403714188322e-05,
655
+ "loss": 1.7091,
656
  "step": 54000
657
  },
658
  {
659
  "epoch": 0.81,
660
+ "learning_rate": 2.9806138933764137e-05,
661
+ "loss": 1.6627,
662
  "step": 54500
663
  },
664
  {
665
  "epoch": 0.82,
666
+ "learning_rate": 2.9620874153339955e-05,
667
+ "loss": 1.7057,
668
  "step": 55000
669
  },
670
  {
671
  "epoch": 0.82,
672
+ "learning_rate": 2.9435609372915773e-05,
673
+ "loss": 1.6779,
674
  "step": 55500
675
  },
676
  {
677
  "epoch": 0.83,
678
+ "learning_rate": 2.9250344592491592e-05,
679
+ "loss": 1.6818,
680
  "step": 56000
681
  },
682
  {
683
  "epoch": 0.84,
684
+ "learning_rate": 2.9065079812067407e-05,
685
+ "loss": 1.692,
686
  "step": 56500
687
  },
688
  {
689
  "epoch": 0.84,
690
+ "learning_rate": 2.8879815031643225e-05,
691
+ "loss": 1.6898,
692
  "step": 57000
693
  },
694
  {
695
  "epoch": 0.85,
696
+ "learning_rate": 2.8694550251219043e-05,
697
+ "loss": 1.6998,
698
  "step": 57500
699
  },
700
  {
701
  "epoch": 0.86,
702
+ "learning_rate": 2.850928547079486e-05,
703
+ "loss": 1.691,
704
  "step": 58000
705
  },
706
  {
707
  "epoch": 0.87,
708
+ "learning_rate": 2.832402069037068e-05,
709
+ "loss": 1.6854,
710
  "step": 58500
711
  },
712
  {
713
  "epoch": 0.87,
714
+ "learning_rate": 2.8138755909946495e-05,
715
+ "loss": 1.6901,
716
  "step": 59000
717
  },
718
  {
719
  "epoch": 0.88,
720
+ "learning_rate": 2.7953491129522313e-05,
721
+ "loss": 1.6782,
722
  "step": 59500
723
  },
724
  {
725
  "epoch": 0.89,
726
+ "learning_rate": 2.776822634909813e-05,
727
+ "loss": 1.6921,
728
  "step": 60000
729
  },
730
  {
731
  "epoch": 0.9,
732
+ "learning_rate": 2.758296156867395e-05,
733
+ "loss": 1.6973,
734
  "step": 60500
735
  },
736
  {
737
  "epoch": 0.9,
738
+ "learning_rate": 2.7397696788249765e-05,
739
+ "loss": 1.6879,
740
  "step": 61000
741
  },
742
  {
743
  "epoch": 0.91,
744
+ "learning_rate": 2.7212432007825583e-05,
745
+ "loss": 1.6839,
746
  "step": 61500
747
  },
748
  {
749
  "epoch": 0.92,
750
+ "learning_rate": 2.70271672274014e-05,
751
+ "loss": 1.7067,
752
  "step": 62000
753
  },
754
  {
755
  "epoch": 0.93,
756
+ "learning_rate": 2.684190244697722e-05,
757
+ "loss": 1.6797,
758
  "step": 62500
759
  },
760
  {
761
  "epoch": 0.93,
762
+ "learning_rate": 2.665663766655304e-05,
763
+ "loss": 1.7041,
764
  "step": 63000
765
  },
766
  {
767
  "epoch": 0.94,
768
+ "learning_rate": 2.647137288612886e-05,
769
+ "loss": 1.6987,
770
  "step": 63500
771
  },
772
  {
773
  "epoch": 0.95,
774
+ "learning_rate": 2.6286108105704678e-05,
775
+ "loss": 1.7034,
776
  "step": 64000
777
  },
778
  {
779
  "epoch": 0.96,
780
+ "learning_rate": 2.6100843325280493e-05,
781
+ "loss": 1.694,
782
  "step": 64500
783
  },
784
  {
785
  "epoch": 0.96,
786
+ "learning_rate": 2.591557854485631e-05,
787
+ "loss": 1.7114,
788
  "step": 65000
789
  },
790
  {
791
  "epoch": 0.97,
792
+ "learning_rate": 2.573031376443213e-05,
793
+ "loss": 1.7016,
794
  "step": 65500
795
  },
796
  {
797
  "epoch": 0.98,
798
+ "learning_rate": 2.5545048984007948e-05,
799
+ "loss": 1.6879,
800
  "step": 66000
801
  },
802
  {
803
  "epoch": 0.99,
804
+ "learning_rate": 2.5359784203583763e-05,
805
+ "loss": 1.6962,
806
  "step": 66500
807
  },
808
  {
809
  "epoch": 0.99,
810
+ "learning_rate": 2.517451942315958e-05,
811
+ "loss": 1.7212,
812
  "step": 67000
813
  },
814
  {
815
  "epoch": 1.0,
816
+ "learning_rate": 2.49892546427354e-05,
817
+ "loss": 1.6942,
818
  "step": 67500
819
  },
820
  {
821
  "epoch": 1.01,
822
+ "learning_rate": 2.4803989862311218e-05,
823
+ "loss": 1.4384,
824
  "step": 68000
825
  },
826
  {
827
  "epoch": 1.02,
828
+ "learning_rate": 2.4618725081887032e-05,
829
+ "loss": 1.458,
830
  "step": 68500
831
  },
832
  {
833
  "epoch": 1.02,
834
+ "learning_rate": 2.443346030146285e-05,
835
+ "loss": 1.4683,
836
  "step": 69000
837
  },
838
  {
839
  "epoch": 1.03,
840
+ "learning_rate": 2.424819552103867e-05,
841
+ "loss": 1.4516,
842
  "step": 69500
843
  },
844
  {
845
  "epoch": 1.04,
846
+ "learning_rate": 2.4062930740614487e-05,
847
+ "loss": 1.4581,
848
  "step": 70000
849
  },
850
  {
851
  "epoch": 1.04,
852
+ "learning_rate": 2.3877665960190306e-05,
853
+ "loss": 1.4695,
854
  "step": 70500
855
  },
856
  {
857
  "epoch": 1.05,
858
+ "learning_rate": 2.369240117976612e-05,
859
+ "loss": 1.4513,
860
  "step": 71000
861
  },
862
  {
863
  "epoch": 1.06,
864
+ "learning_rate": 2.3507136399341942e-05,
865
+ "loss": 1.4649,
866
  "step": 71500
867
  },
868
  {
869
  "epoch": 1.07,
870
+ "learning_rate": 2.332187161891776e-05,
871
+ "loss": 1.4755,
872
  "step": 72000
873
  },
874
  {
875
  "epoch": 1.07,
876
+ "learning_rate": 2.3136606838493576e-05,
877
+ "loss": 1.4694,
878
  "step": 72500
879
  },
880
  {
881
  "epoch": 1.08,
882
+ "learning_rate": 2.2951342058069394e-05,
883
+ "loss": 1.4587,
884
  "step": 73000
885
  },
886
  {
887
  "epoch": 1.09,
888
+ "learning_rate": 2.2766077277645212e-05,
889
+ "loss": 1.4701,
890
  "step": 73500
891
  },
892
  {
893
  "epoch": 1.1,
894
+ "learning_rate": 2.258081249722103e-05,
895
+ "loss": 1.4596,
896
  "step": 74000
897
  },
898
  {
899
  "epoch": 1.1,
900
+ "learning_rate": 2.2395547716796845e-05,
901
+ "loss": 1.4757,
902
  "step": 74500
903
  },
904
  {
905
  "epoch": 1.11,
906
+ "learning_rate": 2.2210282936372664e-05,
907
+ "loss": 1.4876,
908
  "step": 75000
909
  },
910
  {
911
  "epoch": 1.12,
912
+ "learning_rate": 2.2025018155948482e-05,
913
+ "loss": 1.4819,
914
  "step": 75500
915
  },
916
  {
917
  "epoch": 1.13,
918
+ "learning_rate": 2.18397533755243e-05,
919
+ "loss": 1.4758,
920
  "step": 76000
921
  },
922
  {
923
  "epoch": 1.13,
924
+ "learning_rate": 2.165448859510012e-05,
925
+ "loss": 1.4917,
926
  "step": 76500
927
  },
928
  {
929
  "epoch": 1.14,
930
+ "learning_rate": 2.1469223814675937e-05,
931
+ "loss": 1.4939,
932
  "step": 77000
933
  },
934
  {
935
  "epoch": 1.15,
936
+ "learning_rate": 2.1283959034251755e-05,
937
+ "loss": 1.509,
938
  "step": 77500
939
  },
940
  {
941
  "epoch": 1.16,
942
+ "learning_rate": 2.1098694253827574e-05,
943
+ "loss": 1.4854,
944
  "step": 78000
945
  },
946
  {
947
  "epoch": 1.16,
948
+ "learning_rate": 2.091342947340339e-05,
949
+ "loss": 1.5043,
950
  "step": 78500
951
  },
952
  {
953
  "epoch": 1.17,
954
+ "learning_rate": 2.0728164692979207e-05,
955
+ "loss": 1.5026,
956
  "step": 79000
957
  },
958
  {
959
  "epoch": 1.18,
960
+ "learning_rate": 2.0542899912555025e-05,
961
+ "loss": 1.4936,
962
  "step": 79500
963
  },
964
  {
965
  "epoch": 1.19,
966
+ "learning_rate": 2.0357635132130843e-05,
967
+ "loss": 1.5001,
968
  "step": 80000
969
  },
970
  {
971
  "epoch": 1.19,
972
+ "learning_rate": 2.0172370351706658e-05,
973
+ "loss": 1.4855,
974
  "step": 80500
975
  },
976
  {
977
  "epoch": 1.2,
978
+ "learning_rate": 1.9987105571282477e-05,
979
+ "loss": 1.4758,
980
  "step": 81000
981
  },
982
  {
983
  "epoch": 1.21,
984
+ "learning_rate": 1.9801840790858295e-05,
985
+ "loss": 1.496,
986
  "step": 81500
987
  },
988
  {
989
  "epoch": 1.22,
990
+ "learning_rate": 1.9616576010434113e-05,
991
+ "loss": 1.4905,
992
  "step": 82000
993
  },
994
  {
995
  "epoch": 1.22,
996
+ "learning_rate": 1.9431311230009928e-05,
997
+ "loss": 1.4971,
998
  "step": 82500
999
  },
1000
  {
1001
  "epoch": 1.23,
1002
+ "learning_rate": 1.924604644958575e-05,
1003
+ "loss": 1.4487,
1004
  "step": 83000
1005
  },
1006
  {
1007
  "epoch": 1.24,
1008
+ "learning_rate": 1.9060781669161568e-05,
1009
+ "loss": 1.4366,
1010
  "step": 83500
1011
  },
1012
  {
1013
  "epoch": 1.24,
1014
+ "learning_rate": 1.8875516888737386e-05,
1015
+ "loss": 1.4482,
1016
  "step": 84000
1017
  },
1018
  {
1019
  "epoch": 1.25,
1020
+ "learning_rate": 1.86902521083132e-05,
1021
+ "loss": 1.4364,
1022
  "step": 84500
1023
  },
1024
  {
1025
  "epoch": 1.26,
1026
+ "learning_rate": 1.850498732788902e-05,
1027
+ "loss": 1.4334,
1028
  "step": 85000
1029
  },
1030
  {
1031
  "epoch": 1.27,
1032
+ "learning_rate": 1.8319722547464838e-05,
1033
+ "loss": 1.45,
1034
  "step": 85500
1035
  },
1036
  {
1037
  "epoch": 1.27,
1038
+ "learning_rate": 1.8134457767040656e-05,
1039
+ "loss": 1.4507,
1040
  "step": 86000
1041
  },
1042
  {
1043
  "epoch": 1.28,
1044
+ "learning_rate": 1.794919298661647e-05,
1045
+ "loss": 1.4476,
1046
  "step": 86500
1047
  },
1048
  {
1049
  "epoch": 1.29,
1050
+ "learning_rate": 1.776392820619229e-05,
1051
+ "loss": 1.4402,
1052
  "step": 87000
1053
  },
1054
  {
1055
  "epoch": 1.3,
1056
+ "learning_rate": 1.7578663425768108e-05,
1057
+ "loss": 1.4357,
1058
  "step": 87500
1059
  },
1060
  {
1061
  "epoch": 1.3,
1062
+ "learning_rate": 1.7393398645343926e-05,
1063
+ "loss": 1.4292,
1064
  "step": 88000
1065
  },
1066
  {
1067
  "epoch": 1.31,
1068
+ "learning_rate": 1.7208133864919744e-05,
1069
+ "loss": 1.4501,
1070
  "step": 88500
1071
  },
1072
  {
1073
  "epoch": 1.32,
1074
+ "learning_rate": 1.7022869084495563e-05,
1075
+ "loss": 1.4635,
1076
  "step": 89000
1077
  },
1078
  {
1079
  "epoch": 1.33,
1080
+ "learning_rate": 1.683760430407138e-05,
1081
+ "loss": 1.4629,
1082
  "step": 89500
1083
  },
1084
  {
1085
  "epoch": 1.33,
1086
+ "learning_rate": 1.66523395236472e-05,
1087
+ "loss": 1.4496,
1088
  "step": 90000
1089
  },
1090
  {
1091
  "epoch": 1.34,
1092
+ "learning_rate": 1.6467074743223014e-05,
1093
+ "loss": 1.5029,
1094
  "step": 90500
1095
  },
1096
  {
1097
  "epoch": 1.35,
1098
+ "learning_rate": 1.6281809962798833e-05,
1099
+ "loss": 1.4813,
1100
  "step": 91000
1101
  },
1102
  {
1103
  "epoch": 1.36,
1104
+ "learning_rate": 1.609654518237465e-05,
1105
+ "loss": 1.4797,
1106
  "step": 91500
1107
  },
1108
  {
1109
  "epoch": 1.36,
1110
+ "learning_rate": 1.591128040195047e-05,
1111
+ "loss": 1.4808,
1112
  "step": 92000
1113
  },
1114
  {
1115
  "epoch": 1.37,
1116
+ "learning_rate": 1.5726015621526284e-05,
1117
+ "loss": 1.4953,
1118
  "step": 92500
1119
  },
1120
  {
1121
  "epoch": 1.38,
1122
+ "learning_rate": 1.5540750841102102e-05,
1123
+ "loss": 1.4928,
1124
  "step": 93000
1125
  },
1126
  {
1127
  "epoch": 1.39,
1128
+ "learning_rate": 1.535548606067792e-05,
1129
+ "loss": 1.4918,
1130
  "step": 93500
1131
  },
1132
  {
1133
  "epoch": 1.39,
1134
+ "learning_rate": 1.5170221280253737e-05,
1135
+ "loss": 1.4859,
1136
  "step": 94000
1137
  },
1138
  {
1139
  "epoch": 1.4,
1140
+ "learning_rate": 1.4984956499829559e-05,
1141
+ "loss": 1.5046,
1142
  "step": 94500
1143
  },
1144
  {
1145
  "epoch": 1.41,
1146
+ "learning_rate": 1.4799691719405376e-05,
1147
+ "loss": 1.4953,
1148
  "step": 95000
1149
  },
1150
  {
1151
  "epoch": 1.42,
1152
+ "learning_rate": 1.4614426938981194e-05,
1153
+ "loss": 1.5017,
1154
  "step": 95500
1155
  },
1156
  {
1157
  "epoch": 1.42,
1158
+ "learning_rate": 1.442916215855701e-05,
1159
+ "loss": 1.4902,
1160
  "step": 96000
1161
  },
1162
  {
1163
  "epoch": 1.43,
1164
+ "learning_rate": 1.4243897378132829e-05,
1165
+ "loss": 1.5008,
1166
  "step": 96500
1167
  },
1168
  {
1169
  "epoch": 1.44,
1170
+ "learning_rate": 1.4058632597708645e-05,
1171
+ "loss": 1.5013,
1172
  "step": 97000
1173
  },
1174
  {
1175
  "epoch": 1.45,
1176
+ "learning_rate": 1.3873367817284464e-05,
1177
+ "loss": 1.4889,
1178
  "step": 97500
1179
  },
1180
  {
1181
  "epoch": 1.45,
1182
+ "learning_rate": 1.368810303686028e-05,
1183
+ "loss": 1.4879,
1184
  "step": 98000
1185
  },
1186
  {
1187
  "epoch": 1.46,
1188
+ "learning_rate": 1.3502838256436099e-05,
1189
+ "loss": 1.5108,
1190
  "step": 98500
1191
  },
1192
  {
1193
  "epoch": 1.47,
1194
+ "learning_rate": 1.3317573476011915e-05,
1195
+ "loss": 1.5042,
1196
  "step": 99000
1197
  },
1198
  {
1199
  "epoch": 1.47,
1200
+ "learning_rate": 1.3132308695587734e-05,
1201
+ "loss": 1.5153,
1202
  "step": 99500
1203
  },
1204
  {
1205
  "epoch": 1.48,
1206
+ "learning_rate": 1.2947043915163554e-05,
1207
+ "loss": 1.5044,
1208
  "step": 100000
1209
  },
1210
  {
1211
  "epoch": 1.49,
1212
+ "learning_rate": 1.2761779134739372e-05,
1213
+ "loss": 1.5163,
1214
  "step": 100500
1215
  },
1216
  {
1217
  "epoch": 1.5,
1218
+ "learning_rate": 1.2576514354315189e-05,
1219
+ "loss": 1.5069,
1220
  "step": 101000
1221
  },
1222
  {
1223
  "epoch": 1.5,
1224
+ "learning_rate": 1.2391249573891007e-05,
1225
+ "loss": 1.4993,
1226
  "step": 101500
1227
  },
1228
  {
1229
  "epoch": 1.51,
1230
+ "learning_rate": 1.2205984793466823e-05,
1231
+ "loss": 1.5073,
1232
  "step": 102000
1233
  },
1234
  {
1235
  "epoch": 1.52,
1236
+ "learning_rate": 1.2020720013042642e-05,
1237
+ "loss": 1.5076,
1238
  "step": 102500
1239
  },
1240
  {
1241
  "epoch": 1.53,
1242
+ "learning_rate": 1.1835455232618458e-05,
1243
+ "loss": 1.5086,
1244
  "step": 103000
1245
  },
1246
  {
1247
  "epoch": 1.53,
1248
+ "learning_rate": 1.1650190452194277e-05,
1249
+ "loss": 1.535,
1250
  "step": 103500
1251
  },
1252
  {
1253
  "epoch": 1.54,
1254
+ "learning_rate": 1.1464925671770093e-05,
1255
+ "loss": 1.5124,
1256
  "step": 104000
1257
  },
1258
  {
1259
  "epoch": 1.55,
1260
+ "learning_rate": 1.1279660891345913e-05,
1261
+ "loss": 1.5062,
1262
  "step": 104500
1263
  },
1264
  {
1265
  "epoch": 1.56,
1266
+ "learning_rate": 1.109439611092173e-05,
1267
+ "loss": 1.5339,
1268
  "step": 105000
1269
  },
1270
  {
1271
  "epoch": 1.56,
1272
+ "learning_rate": 1.0909131330497548e-05,
1273
+ "loss": 1.5385,
1274
  "step": 105500
1275
  },
1276
  {
1277
  "epoch": 1.57,
1278
+ "learning_rate": 1.0723866550073365e-05,
1279
+ "loss": 1.5343,
1280
  "step": 106000
1281
  },
1282
  {
1283
  "epoch": 1.58,
1284
+ "learning_rate": 1.0538601769649183e-05,
1285
+ "loss": 1.5351,
1286
  "step": 106500
1287
  },
1288
  {
1289
  "epoch": 1.59,
1290
+ "learning_rate": 1.0353336989225001e-05,
1291
+ "loss": 1.5182,
1292
  "step": 107000
1293
  },
1294
  {
1295
  "epoch": 1.59,
1296
+ "learning_rate": 1.016807220880082e-05,
1297
+ "loss": 1.5242,
1298
  "step": 107500
1299
  },
1300
  {
1301
  "epoch": 1.6,
1302
+ "learning_rate": 9.982807428376636e-06,
1303
+ "loss": 1.5444,
1304
  "step": 108000
1305
  },
1306
  {
1307
  "epoch": 1.61,
1308
+ "learning_rate": 9.797542647952455e-06,
1309
+ "loss": 1.533,
1310
  "step": 108500
1311
  },
1312
  {
1313
  "epoch": 1.62,
1314
+ "learning_rate": 9.612277867528271e-06,
1315
+ "loss": 1.5202,
1316
  "step": 109000
1317
  },
1318
  {
1319
  "epoch": 1.62,
1320
+ "learning_rate": 9.42701308710409e-06,
1321
+ "loss": 1.5468,
1322
  "step": 109500
1323
  },
1324
  {
1325
  "epoch": 1.63,
1326
+ "learning_rate": 9.241748306679908e-06,
1327
+ "loss": 1.5181,
1328
  "step": 110000
1329
  },
1330
  {
1331
  "epoch": 1.64,
1332
+ "learning_rate": 9.056483526255726e-06,
1333
+ "loss": 1.5231,
1334
  "step": 110500
1335
  },
1336
  {
1337
  "epoch": 1.65,
1338
+ "learning_rate": 8.871218745831543e-06,
1339
+ "loss": 1.5209,
1340
  "step": 111000
1341
  },
1342
  {
1343
  "epoch": 1.65,
1344
+ "learning_rate": 8.685953965407361e-06,
1345
+ "loss": 1.52,
1346
  "step": 111500
1347
  },
1348
  {
1349
  "epoch": 1.66,
1350
+ "learning_rate": 8.500689184983178e-06,
1351
+ "loss": 1.5131,
1352
  "step": 112000
1353
  },
1354
  {
1355
  "epoch": 1.67,
1356
+ "learning_rate": 8.315424404558996e-06,
1357
+ "loss": 1.5404,
1358
  "step": 112500
1359
  },
1360
  {
1361
  "epoch": 1.67,
1362
+ "learning_rate": 8.130159624134814e-06,
1363
+ "loss": 1.5523,
1364
  "step": 113000
1365
  },
1366
  {
1367
  "epoch": 1.68,
1368
+ "learning_rate": 7.944894843710633e-06,
1369
+ "loss": 1.5608,
1370
  "step": 113500
1371
  },
1372
  {
1373
  "epoch": 1.69,
1374
+ "learning_rate": 7.75963006328645e-06,
1375
+ "loss": 1.5172,
1376
  "step": 114000
1377
  },
1378
  {
1379
  "epoch": 1.7,
1380
+ "learning_rate": 7.574365282862267e-06,
1381
+ "loss": 1.5192,
1382
  "step": 114500
1383
  },
1384
  {
1385
  "epoch": 1.7,
1386
+ "learning_rate": 7.389100502438084e-06,
1387
+ "loss": 1.5329,
1388
  "step": 115000
1389
  },
1390
  {
1391
  "epoch": 1.71,
1392
+ "learning_rate": 7.203835722013903e-06,
1393
+ "loss": 1.5195,
1394
  "step": 115500
1395
  },
1396
  {
1397
  "epoch": 1.72,
1398
+ "learning_rate": 7.018570941589721e-06,
1399
+ "loss": 1.5377,
1400
  "step": 116000
1401
  },
1402
  {
1403
  "epoch": 1.73,
1404
+ "learning_rate": 6.833306161165538e-06,
1405
+ "loss": 1.5332,
1406
  "step": 116500
1407
  },
1408
  {
1409
  "epoch": 1.73,
1410
+ "learning_rate": 6.648041380741356e-06,
1411
+ "loss": 1.546,
1412
  "step": 117000
1413
  },
1414
  {
1415
  "epoch": 1.74,
1416
+ "learning_rate": 6.462776600317173e-06,
1417
+ "loss": 1.5475,
1418
  "step": 117500
1419
  },
1420
  {
1421
  "epoch": 1.75,
1422
+ "learning_rate": 6.277511819892991e-06,
1423
+ "loss": 1.5593,
1424
  "step": 118000
1425
  },
1426
  {
1427
  "epoch": 1.76,
1428
+ "learning_rate": 6.092247039468809e-06,
1429
+ "loss": 1.5384,
1430
  "step": 118500
1431
  },
1432
  {
1433
  "epoch": 1.76,
1434
+ "learning_rate": 5.906982259044627e-06,
1435
+ "loss": 1.5448,
1436
  "step": 119000
1437
  },
1438
  {
1439
  "epoch": 1.77,
1440
+ "learning_rate": 5.721717478620445e-06,
1441
+ "loss": 1.5546,
1442
  "step": 119500
1443
  },
1444
  {
1445
  "epoch": 1.78,
1446
+ "learning_rate": 5.536452698196262e-06,
1447
+ "loss": 1.5641,
1448
  "step": 120000
1449
  },
1450
  {
1451
  "epoch": 1.79,
1452
+ "learning_rate": 5.3511879177720805e-06,
1453
+ "loss": 1.5636,
1454
  "step": 120500
1455
  },
1456
  {
1457
  "epoch": 1.79,
1458
+ "learning_rate": 5.165923137347898e-06,
1459
+ "loss": 1.5474,
1460
  "step": 121000
1461
  },
1462
  {
1463
  "epoch": 1.8,
1464
+ "learning_rate": 4.980658356923715e-06,
1465
+ "loss": 1.5317,
1466
  "step": 121500
1467
  },
1468
  {
1469
  "epoch": 1.81,
1470
+ "learning_rate": 4.795393576499534e-06,
1471
+ "loss": 1.5344,
1472
  "step": 122000
1473
  },
1474
  {
1475
  "epoch": 1.82,
1476
+ "learning_rate": 4.610128796075351e-06,
1477
+ "loss": 1.5568,
1478
  "step": 122500
1479
  },
1480
  {
1481
  "epoch": 1.82,
1482
+ "learning_rate": 4.424864015651169e-06,
1483
+ "loss": 1.5598,
1484
  "step": 123000
1485
  },
1486
  {
1487
  "epoch": 1.83,
1488
+ "learning_rate": 4.239599235226987e-06,
1489
+ "loss": 1.559,
1490
  "step": 123500
1491
  },
1492
  {
1493
  "epoch": 1.84,
1494
+ "learning_rate": 4.054334454802804e-06,
1495
+ "loss": 1.5571,
1496
+ "step": 124000
1497
  },
1498
  {
1499
  "epoch": 1.85,
1500
+ "learning_rate": 3.869069674378622e-06,
1501
+ "loss": 1.5597,
1502
  "step": 124500
1503
  },
1504
  {
1505
  "epoch": 1.85,
1506
+ "learning_rate": 3.68380489395444e-06,
1507
+ "loss": 1.5629,
1508
  "step": 125000
1509
  },
1510
  {
1511
  "epoch": 1.86,
1512
+ "learning_rate": 3.4985401135302576e-06,
1513
+ "loss": 1.5573,
1514
  "step": 125500
1515
  },
1516
  {
1517
  "epoch": 1.87,
1518
+ "learning_rate": 3.313275333106075e-06,
1519
+ "loss": 1.5486,
1520
  "step": 126000
1521
  },
1522
  {
1523
  "epoch": 1.87,
1524
+ "learning_rate": 3.1280105526818934e-06,
1525
+ "loss": 1.5755,
1526
  "step": 126500
1527
  },
1528
  {
1529
  "epoch": 1.88,
1530
+ "learning_rate": 2.942745772257711e-06,
1531
+ "loss": 1.5626,
1532
  "step": 127000
1533
  },
1534
  {
1535
  "epoch": 1.89,
1536
+ "learning_rate": 2.7574809918335287e-06,
1537
+ "loss": 1.5385,
1538
  "step": 127500
1539
  },
1540
  {
1541
  "epoch": 1.9,
1542
+ "learning_rate": 2.5722162114093466e-06,
1543
+ "loss": 1.5594,
1544
  "step": 128000
1545
  },
1546
  {
1547
  "epoch": 1.9,
1548
+ "learning_rate": 2.386951430985164e-06,
1549
+ "loss": 1.5513,
1550
  "step": 128500
1551
  },
1552
  {
1553
  "epoch": 1.91,
1554
+ "learning_rate": 2.201686650560982e-06,
1555
+ "loss": 1.5725,
1556
  "step": 129000
1557
  },
1558
  {
1559
  "epoch": 1.92,
1560
+ "learning_rate": 2.0164218701368e-06,
1561
+ "loss": 1.5727,
1562
  "step": 129500
1563
  },
1564
  {
1565
  "epoch": 1.93,
1566
+ "learning_rate": 1.8311570897126173e-06,
1567
+ "loss": 1.6023,
1568
  "step": 130000
1569
  },
1570
  {
1571
  "epoch": 1.93,
1572
+ "learning_rate": 1.645892309288435e-06,
1573
+ "loss": 1.5643,
1574
  "step": 130500
1575
  },
1576
  {
1577
  "epoch": 1.94,
1578
+ "learning_rate": 1.4606275288642529e-06,
1579
+ "loss": 1.5606,
1580
  "step": 131000
1581
  },
1582
  {
1583
  "epoch": 1.95,
1584
+ "learning_rate": 1.2753627484400705e-06,
1585
+ "loss": 1.5998,
1586
  "step": 131500
1587
  },
1588
  {
1589
  "epoch": 1.96,
1590
+ "learning_rate": 1.0900979680158882e-06,
1591
+ "loss": 1.5882,
1592
  "step": 132000
1593
  },
1594
  {
1595
  "epoch": 1.96,
1596
+ "learning_rate": 9.048331875917061e-07,
1597
+ "loss": 1.59,
1598
  "step": 132500
1599
  },
1600
  {
1601
  "epoch": 1.97,
1602
+ "learning_rate": 7.195684071675239e-07,
1603
+ "loss": 1.5851,
1604
  "step": 133000
1605
  },
1606
  {
1607
  "epoch": 1.98,
1608
+ "learning_rate": 5.343036267433415e-07,
1609
+ "loss": 1.6012,
1610
  "step": 133500
1611
  },
1612
  {
1613
  "epoch": 1.99,
1614
+ "learning_rate": 3.490388463191593e-07,
1615
+ "loss": 1.5951,
1616
  "step": 134000
1617
  },
1618
  {
1619
  "epoch": 1.99,
1620
+ "learning_rate": 1.637740658949771e-07,
1621
+ "loss": 1.6155,
1622
  "step": 134500
1623
  },
1624
  {
1625
  "epoch": 2.0,
1626
+ "step": 134942,
1627
+ "total_flos": 2.5064145824199475e+17,
1628
+ "train_loss": 1.578441581144295,
1629
+ "train_runtime": 31772.5798,
1630
+ "train_samples_per_second": 8.494,
1631
+ "train_steps_per_second": 4.247
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1632
  }
1633
  ],
1634
+ "max_steps": 134942,
1635
+ "num_train_epochs": 2,
1636
+ "total_flos": 2.5064145824199475e+17,
1637
  "trial_name": null,
1638
  "trial_params": null
1639
  }