dq158 commited on
Commit
1a93375
1 Parent(s): 854aacf

Training in progress, epoch 1, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:60dc7f8671c4c17982a811e4984593f0c3535fd555759795d60042e3a5adb7fc
3
  size 3132668808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b3b20ffefbf39834750af10d015b9eed68cd596b93af1f481063a3d79802a5f
3
  size 3132668808
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8995940419c3fb1677d1bac070b49168479dac19d9f741e9e9a0af3710fd4185
3
  size 6265677800
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a0a1d720a80a21f86b42834921fbf49934f7bdfc51e665b031c0c39aa508f0b
3
  size 6265677800
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ae6b276e348c31a90cab7075facf1bb3541eaeb11d70ad9b91c352518debac06
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3421260c744085d195b4dfe974251448594371f7199bcdc2e3cfc3fce23873b
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e970628affc15d17d6307c6dc54e341d0d029b9ac0392cb2b10502b969143d0e
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f8da858e1f3097d422bf787beb7750f6f9549fbe3c5811eb4fcc0804eb3bc89
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -3,1241 +3,323 @@
3
  "best_model_checkpoint": null,
4
  "epoch": 1.0,
5
  "eval_steps": 500,
6
- "global_step": 102042,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
- "epoch": 0.0,
13
  "learning_rate": 0.0001,
14
- "loss": 4.3493,
15
  "step": 500
16
  },
17
- {
18
- "epoch": 0.01,
19
- "learning_rate": 9.999976257135674e-05,
20
- "loss": 3.8335,
21
- "step": 1000
22
- },
23
- {
24
- "epoch": 0.01,
25
- "learning_rate": 9.999905028768184e-05,
26
- "loss": 3.9255,
27
- "step": 1500
28
- },
29
- {
30
- "epoch": 0.02,
31
- "learning_rate": 9.999786315574e-05,
32
- "loss": 3.7355,
33
- "step": 2000
34
- },
35
- {
36
- "epoch": 0.02,
37
- "learning_rate": 9.999620118680553e-05,
38
- "loss": 3.7969,
39
- "step": 2500
40
- },
41
- {
42
- "epoch": 0.03,
43
- "learning_rate": 9.999406439666243e-05,
44
- "loss": 3.7387,
45
- "step": 3000
46
- },
47
- {
48
- "epoch": 0.03,
49
- "learning_rate": 9.999145280560409e-05,
50
- "loss": 3.8608,
51
- "step": 3500
52
- },
53
- {
54
- "epoch": 0.04,
55
- "learning_rate": 9.998836643843319e-05,
56
- "loss": 3.6775,
57
- "step": 4000
58
- },
59
  {
60
  "epoch": 0.04,
61
- "learning_rate": 9.998480532446138e-05,
62
- "loss": 3.7057,
63
- "step": 4500
64
- },
65
- {
66
- "epoch": 0.05,
67
- "learning_rate": 9.99807694975091e-05,
68
- "loss": 3.7363,
69
- "step": 5000
70
- },
71
- {
72
- "epoch": 0.05,
73
- "learning_rate": 9.997625899590519e-05,
74
- "loss": 3.6594,
75
- "step": 5500
76
- },
77
- {
78
- "epoch": 0.06,
79
- "learning_rate": 9.997127386248653e-05,
80
- "loss": 3.7544,
81
- "step": 6000
82
  },
83
  {
84
  "epoch": 0.06,
85
- "learning_rate": 9.996581414459764e-05,
86
- "loss": 3.7367,
87
- "step": 6500
88
- },
89
- {
90
- "epoch": 0.07,
91
- "learning_rate": 9.99598798940903e-05,
92
- "loss": 3.747,
93
- "step": 7000
94
- },
95
- {
96
- "epoch": 0.07,
97
- "learning_rate": 9.995347116732293e-05,
98
- "loss": 3.657,
99
- "step": 7500
100
- },
101
- {
102
- "epoch": 0.08,
103
- "learning_rate": 9.994658802516012e-05,
104
- "loss": 3.6693,
105
- "step": 8000
106
  },
107
  {
108
  "epoch": 0.08,
109
- "learning_rate": 9.99392305329721e-05,
110
- "loss": 3.7089,
111
- "step": 8500
112
- },
113
- {
114
- "epoch": 0.09,
115
- "learning_rate": 9.993139876063405e-05,
116
- "loss": 3.7451,
117
- "step": 9000
118
- },
119
- {
120
- "epoch": 0.09,
121
- "learning_rate": 9.992309278252545e-05,
122
- "loss": 3.7237,
123
- "step": 9500
124
- },
125
- {
126
- "epoch": 0.1,
127
- "learning_rate": 9.991431267752937e-05,
128
- "loss": 3.4406,
129
- "step": 10000
130
  },
131
  {
132
  "epoch": 0.1,
133
- "learning_rate": 9.990505852903175e-05,
134
- "loss": 3.7062,
135
- "step": 10500
136
- },
137
- {
138
- "epoch": 0.11,
139
- "learning_rate": 9.98953304249206e-05,
140
- "loss": 3.5576,
141
- "step": 11000
142
- },
143
- {
144
- "epoch": 0.11,
145
- "learning_rate": 9.988512845758513e-05,
146
- "loss": 3.5236,
147
- "step": 11500
148
- },
149
- {
150
- "epoch": 0.12,
151
- "learning_rate": 9.987445272391492e-05,
152
- "loss": 3.7762,
153
- "step": 12000
154
  },
155
  {
156
  "epoch": 0.12,
157
- "learning_rate": 9.986330332529895e-05,
158
- "loss": 3.4135,
159
- "step": 12500
160
- },
161
- {
162
- "epoch": 0.13,
163
- "learning_rate": 9.985168036762471e-05,
164
- "loss": 3.6875,
165
- "step": 13000
166
- },
167
- {
168
- "epoch": 0.13,
169
- "learning_rate": 9.983958396127711e-05,
170
- "loss": 3.5069,
171
- "step": 13500
172
- },
173
- {
174
- "epoch": 0.14,
175
- "learning_rate": 9.982701422113747e-05,
176
- "loss": 3.6714,
177
- "step": 14000
178
  },
179
  {
180
  "epoch": 0.14,
181
- "learning_rate": 9.981397126658248e-05,
182
- "loss": 3.648,
183
- "step": 14500
184
- },
185
- {
186
- "epoch": 0.15,
187
- "learning_rate": 9.980045522148293e-05,
188
- "loss": 3.486,
189
- "step": 15000
190
- },
191
- {
192
- "epoch": 0.15,
193
- "learning_rate": 9.978646621420271e-05,
194
- "loss": 3.5997,
195
- "step": 15500
196
- },
197
- {
198
- "epoch": 0.16,
199
- "learning_rate": 9.977200437759747e-05,
200
- "loss": 3.4384,
201
- "step": 16000
202
  },
203
  {
204
  "epoch": 0.16,
205
- "learning_rate": 9.975706984901333e-05,
206
- "loss": 3.4892,
207
- "step": 16500
208
- },
209
- {
210
- "epoch": 0.17,
211
- "learning_rate": 9.974166277028572e-05,
212
- "loss": 3.5377,
213
- "step": 17000
214
- },
215
- {
216
- "epoch": 0.17,
217
- "learning_rate": 9.97257832877379e-05,
218
- "loss": 3.5742,
219
- "step": 17500
220
- },
221
- {
222
- "epoch": 0.18,
223
- "learning_rate": 9.970943155217964e-05,
224
- "loss": 3.4612,
225
- "step": 18000
226
  },
227
  {
228
  "epoch": 0.18,
229
- "learning_rate": 9.969260771890576e-05,
230
- "loss": 3.5934,
231
- "step": 18500
232
- },
233
- {
234
- "epoch": 0.19,
235
- "learning_rate": 9.967531194769464e-05,
236
- "loss": 3.5276,
237
- "step": 19000
238
- },
239
- {
240
- "epoch": 0.19,
241
- "learning_rate": 9.965754440280674e-05,
242
- "loss": 3.6521,
243
- "step": 19500
244
- },
245
- {
246
- "epoch": 0.2,
247
- "learning_rate": 9.963930525298303e-05,
248
- "loss": 3.5624,
249
- "step": 20000
250
  },
251
  {
252
  "epoch": 0.2,
253
- "learning_rate": 9.962059467144337e-05,
254
- "loss": 3.4004,
255
- "step": 20500
256
- },
257
- {
258
- "epoch": 0.21,
259
- "learning_rate": 9.960141283588489e-05,
260
- "loss": 3.5858,
261
- "step": 21000
262
- },
263
- {
264
- "epoch": 0.21,
265
- "learning_rate": 9.958175992848027e-05,
266
- "loss": 3.6671,
267
- "step": 21500
268
- },
269
- {
270
- "epoch": 0.22,
271
- "learning_rate": 9.956163613587604e-05,
272
- "loss": 3.5015,
273
- "step": 22000
274
  },
275
  {
276
  "epoch": 0.22,
277
- "learning_rate": 9.954104164919077e-05,
278
- "loss": 3.4195,
279
- "step": 22500
280
- },
281
- {
282
- "epoch": 0.23,
283
- "learning_rate": 9.951997666401333e-05,
284
- "loss": 3.5104,
285
- "step": 23000
286
- },
287
- {
288
- "epoch": 0.23,
289
- "learning_rate": 9.949844138040094e-05,
290
- "loss": 3.4158,
291
- "step": 23500
292
- },
293
- {
294
- "epoch": 0.24,
295
- "learning_rate": 9.947643600287732e-05,
296
- "loss": 3.582,
297
- "step": 24000
298
- },
299
- {
300
- "epoch": 0.24,
301
- "learning_rate": 9.945396074043077e-05,
302
- "loss": 3.4935,
303
- "step": 24500
304
  },
305
  {
306
  "epoch": 0.24,
307
- "learning_rate": 9.943101580651212e-05,
308
- "loss": 3.4876,
309
- "step": 25000
310
- },
311
- {
312
- "epoch": 0.25,
313
- "learning_rate": 9.940760141903273e-05,
314
- "loss": 3.7247,
315
- "step": 25500
316
  },
317
  {
318
  "epoch": 0.25,
319
- "learning_rate": 9.938371780036249e-05,
320
- "loss": 3.5805,
321
- "step": 26000
322
- },
323
- {
324
- "epoch": 0.26,
325
- "learning_rate": 9.93593651773276e-05,
326
- "loss": 3.5109,
327
- "step": 26500
328
- },
329
- {
330
- "epoch": 0.26,
331
- "learning_rate": 9.933454378120844e-05,
332
- "loss": 3.4585,
333
- "step": 27000
334
- },
335
- {
336
- "epoch": 0.27,
337
- "learning_rate": 9.930925384773743e-05,
338
- "loss": 3.4606,
339
- "step": 27500
340
  },
341
  {
342
  "epoch": 0.27,
343
- "learning_rate": 9.928349561709678e-05,
344
- "loss": 3.6355,
345
- "step": 28000
346
- },
347
- {
348
- "epoch": 0.28,
349
- "learning_rate": 9.925726933391615e-05,
350
- "loss": 3.5646,
351
- "step": 28500
352
- },
353
- {
354
- "epoch": 0.28,
355
- "learning_rate": 9.923057524727037e-05,
356
- "loss": 3.5079,
357
- "step": 29000
358
- },
359
- {
360
- "epoch": 0.29,
361
- "learning_rate": 9.920341361067706e-05,
362
- "loss": 3.5164,
363
- "step": 29500
364
  },
365
  {
366
  "epoch": 0.29,
367
- "learning_rate": 9.917578468209427e-05,
368
- "loss": 3.5347,
369
- "step": 30000
370
- },
371
- {
372
- "epoch": 0.3,
373
- "learning_rate": 9.914768872391793e-05,
374
- "loss": 3.5879,
375
- "step": 30500
376
- },
377
- {
378
- "epoch": 0.3,
379
- "learning_rate": 9.911912600297948e-05,
380
- "loss": 3.4959,
381
- "step": 31000
382
- },
383
- {
384
- "epoch": 0.31,
385
- "learning_rate": 9.90900967905432e-05,
386
- "loss": 3.4136,
387
- "step": 31500
388
  },
389
  {
390
  "epoch": 0.31,
391
- "learning_rate": 9.906060136230379e-05,
392
- "loss": 3.5489,
393
- "step": 32000
394
- },
395
- {
396
- "epoch": 0.32,
397
- "learning_rate": 9.903063999838364e-05,
398
- "loss": 3.528,
399
- "step": 32500
400
- },
401
- {
402
- "epoch": 0.32,
403
- "learning_rate": 9.900021298333013e-05,
404
- "loss": 3.3378,
405
- "step": 33000
406
- },
407
- {
408
- "epoch": 0.33,
409
- "learning_rate": 9.896932060611313e-05,
410
- "loss": 3.585,
411
- "step": 33500
412
  },
413
  {
414
  "epoch": 0.33,
415
- "learning_rate": 9.893796316012198e-05,
416
- "loss": 3.4112,
417
- "step": 34000
418
- },
419
- {
420
- "epoch": 0.34,
421
- "learning_rate": 9.890614094316295e-05,
422
- "loss": 3.459,
423
- "step": 34500
424
- },
425
- {
426
- "epoch": 0.34,
427
- "learning_rate": 9.887385425745628e-05,
428
- "loss": 3.5127,
429
- "step": 35000
430
- },
431
- {
432
- "epoch": 0.35,
433
- "learning_rate": 9.884110340963331e-05,
434
- "loss": 3.5508,
435
- "step": 35500
436
  },
437
  {
438
  "epoch": 0.35,
439
- "learning_rate": 9.880788871073363e-05,
440
- "loss": 3.4557,
441
- "step": 36000
442
- },
443
- {
444
- "epoch": 0.36,
445
- "learning_rate": 9.877421047620206e-05,
446
- "loss": 3.548,
447
- "step": 36500
448
- },
449
- {
450
- "epoch": 0.36,
451
- "learning_rate": 9.874006902588571e-05,
452
- "loss": 3.5211,
453
- "step": 37000
454
- },
455
- {
456
- "epoch": 0.37,
457
- "learning_rate": 9.87054646840309e-05,
458
- "loss": 3.5219,
459
- "step": 37500
460
  },
461
  {
462
  "epoch": 0.37,
463
- "learning_rate": 9.867039777928014e-05,
464
- "loss": 3.4758,
465
- "step": 38000
466
- },
467
- {
468
- "epoch": 0.38,
469
- "learning_rate": 9.863486864466888e-05,
470
- "loss": 3.5237,
471
- "step": 38500
472
- },
473
- {
474
- "epoch": 0.38,
475
- "learning_rate": 9.859887761762253e-05,
476
- "loss": 3.4578,
477
- "step": 39000
478
- },
479
- {
480
- "epoch": 0.39,
481
- "learning_rate": 9.856242503995313e-05,
482
- "loss": 3.3907,
483
- "step": 39500
484
  },
485
  {
486
  "epoch": 0.39,
487
- "learning_rate": 9.852551125785606e-05,
488
- "loss": 3.491,
489
- "step": 40000
490
- },
491
- {
492
- "epoch": 0.4,
493
- "learning_rate": 9.848813662190694e-05,
494
- "loss": 3.3904,
495
- "step": 40500
496
- },
497
- {
498
- "epoch": 0.4,
499
- "learning_rate": 9.845030148705815e-05,
500
- "loss": 3.468,
501
- "step": 41000
502
- },
503
- {
504
- "epoch": 0.41,
505
- "learning_rate": 9.841200621263542e-05,
506
- "loss": 3.4502,
507
- "step": 41500
508
  },
509
  {
510
  "epoch": 0.41,
511
- "learning_rate": 9.83732511623346e-05,
512
- "loss": 3.5973,
513
- "step": 42000
514
- },
515
- {
516
- "epoch": 0.42,
517
- "learning_rate": 9.833403670421803e-05,
518
- "loss": 3.5283,
519
- "step": 42500
520
- },
521
- {
522
- "epoch": 0.42,
523
- "learning_rate": 9.829436321071115e-05,
524
- "loss": 3.4095,
525
- "step": 43000
526
- },
527
- {
528
- "epoch": 0.43,
529
- "learning_rate": 9.825423105859887e-05,
530
- "loss": 3.559,
531
- "step": 43500
532
  },
533
  {
534
  "epoch": 0.43,
535
- "learning_rate": 9.821364062902214e-05,
536
- "loss": 3.3601,
537
- "step": 44000
538
- },
539
- {
540
- "epoch": 0.44,
541
- "learning_rate": 9.817259230747415e-05,
542
- "loss": 3.4913,
543
- "step": 44500
544
- },
545
- {
546
- "epoch": 0.44,
547
- "learning_rate": 9.813108648379681e-05,
548
- "loss": 3.4763,
549
- "step": 45000
550
- },
551
- {
552
- "epoch": 0.45,
553
- "learning_rate": 9.808912355217697e-05,
554
- "loss": 3.5386,
555
- "step": 45500
556
  },
557
  {
558
  "epoch": 0.45,
559
- "learning_rate": 9.804670391114267e-05,
560
- "loss": 3.4405,
561
- "step": 46000
562
- },
563
- {
564
- "epoch": 0.46,
565
- "learning_rate": 9.800382796355949e-05,
566
- "loss": 3.4371,
567
- "step": 46500
568
- },
569
- {
570
- "epoch": 0.46,
571
- "learning_rate": 9.796049611662652e-05,
572
- "loss": 3.3831,
573
- "step": 47000
574
- },
575
- {
576
- "epoch": 0.47,
577
- "learning_rate": 9.79167087818726e-05,
578
- "loss": 3.4013,
579
- "step": 47500
580
  },
581
  {
582
  "epoch": 0.47,
583
- "learning_rate": 9.787246637515249e-05,
584
- "loss": 3.5502,
585
- "step": 48000
586
- },
587
- {
588
- "epoch": 0.48,
589
- "learning_rate": 9.782776931664271e-05,
590
- "loss": 3.4542,
591
- "step": 48500
592
- },
593
- {
594
- "epoch": 0.48,
595
- "learning_rate": 9.778261803083776e-05,
596
- "loss": 3.6167,
597
- "step": 49000
598
- },
599
- {
600
- "epoch": 0.49,
601
- "learning_rate": 9.773701294654602e-05,
602
- "loss": 3.4164,
603
- "step": 49500
604
- },
605
- {
606
- "epoch": 0.49,
607
- "learning_rate": 9.769095449688556e-05,
608
- "loss": 3.4077,
609
- "step": 50000
610
  },
611
  {
612
  "epoch": 0.49,
613
- "learning_rate": 9.764444311928023e-05,
614
- "loss": 3.4122,
615
- "step": 50500
616
- },
617
- {
618
- "epoch": 0.5,
619
- "learning_rate": 9.759747925545534e-05,
620
- "loss": 3.427,
621
- "step": 51000
622
- },
623
- {
624
- "epoch": 0.5,
625
- "learning_rate": 9.755006335143357e-05,
626
- "loss": 3.4952,
627
- "step": 51500
628
- },
629
- {
630
- "epoch": 0.51,
631
- "learning_rate": 9.750219585753065e-05,
632
- "loss": 3.352,
633
- "step": 52000
634
  },
635
  {
636
  "epoch": 0.51,
637
- "learning_rate": 9.745387722835115e-05,
638
- "loss": 3.4342,
639
- "step": 52500
640
- },
641
- {
642
- "epoch": 0.52,
643
- "learning_rate": 9.740510792278415e-05,
644
- "loss": 3.416,
645
- "step": 53000
646
- },
647
- {
648
- "epoch": 0.52,
649
- "learning_rate": 9.735588840399882e-05,
650
- "loss": 3.4641,
651
- "step": 53500
652
- },
653
- {
654
- "epoch": 0.53,
655
- "learning_rate": 9.730621913944015e-05,
656
- "loss": 3.5079,
657
- "step": 54000
658
  },
659
  {
660
  "epoch": 0.53,
661
- "learning_rate": 9.725610060082433e-05,
662
- "loss": 3.4015,
663
- "step": 54500
664
- },
665
- {
666
- "epoch": 0.54,
667
- "learning_rate": 9.720553326413446e-05,
668
- "loss": 3.5635,
669
- "step": 55000
670
- },
671
- {
672
- "epoch": 0.54,
673
- "learning_rate": 9.715451760961589e-05,
674
- "loss": 3.406,
675
- "step": 55500
676
- },
677
- {
678
- "epoch": 0.55,
679
- "learning_rate": 9.710305412177174e-05,
680
- "loss": 3.433,
681
- "step": 56000
682
  },
683
  {
684
  "epoch": 0.55,
685
- "learning_rate": 9.705114328935823e-05,
686
- "loss": 3.4758,
687
- "step": 56500
688
- },
689
- {
690
- "epoch": 0.56,
691
- "learning_rate": 9.699878560538014e-05,
692
- "loss": 3.3005,
693
- "step": 57000
694
- },
695
- {
696
- "epoch": 0.56,
697
- "learning_rate": 9.694598156708598e-05,
698
- "loss": 3.4903,
699
- "step": 57500
700
- },
701
- {
702
- "epoch": 0.57,
703
- "learning_rate": 9.689273167596342e-05,
704
- "loss": 3.4764,
705
- "step": 58000
706
  },
707
  {
708
  "epoch": 0.57,
709
- "learning_rate": 9.683903643773445e-05,
710
- "loss": 3.4686,
711
- "step": 58500
712
- },
713
- {
714
- "epoch": 0.58,
715
- "learning_rate": 9.678489636235053e-05,
716
- "loss": 3.374,
717
- "step": 59000
718
- },
719
- {
720
- "epoch": 0.58,
721
- "learning_rate": 9.673031196398788e-05,
722
- "loss": 3.5763,
723
- "step": 59500
724
- },
725
- {
726
- "epoch": 0.59,
727
- "learning_rate": 9.667528376104247e-05,
728
- "loss": 3.4036,
729
- "step": 60000
730
  },
731
  {
732
  "epoch": 0.59,
733
- "learning_rate": 9.66198122761252e-05,
734
- "loss": 3.3415,
735
- "step": 60500
736
- },
737
- {
738
- "epoch": 0.6,
739
- "learning_rate": 9.656389803605679e-05,
740
- "loss": 3.5519,
741
- "step": 61000
742
- },
743
- {
744
- "epoch": 0.6,
745
- "learning_rate": 9.650754157186296e-05,
746
- "loss": 3.3572,
747
- "step": 61500
748
- },
749
- {
750
- "epoch": 0.61,
751
- "learning_rate": 9.645074341876925e-05,
752
- "loss": 3.4291,
753
- "step": 62000
754
  },
755
  {
756
  "epoch": 0.61,
757
- "learning_rate": 9.639350411619601e-05,
758
- "loss": 3.5119,
759
- "step": 62500
760
- },
761
- {
762
- "epoch": 0.62,
763
- "learning_rate": 9.633582420775323e-05,
764
- "loss": 3.495,
765
- "step": 63000
766
- },
767
- {
768
- "epoch": 0.62,
769
- "learning_rate": 9.627770424123541e-05,
770
- "loss": 3.4069,
771
- "step": 63500
772
- },
773
- {
774
- "epoch": 0.63,
775
- "learning_rate": 9.621914476861635e-05,
776
- "loss": 3.514,
777
- "step": 64000
778
  },
779
  {
780
  "epoch": 0.63,
781
- "learning_rate": 9.616014634604387e-05,
782
- "loss": 3.3943,
783
- "step": 64500
784
- },
785
- {
786
- "epoch": 0.64,
787
- "learning_rate": 9.61007095338346e-05,
788
- "loss": 3.5189,
789
- "step": 65000
790
- },
791
- {
792
- "epoch": 0.64,
793
- "learning_rate": 9.60408348964686e-05,
794
- "loss": 3.5516,
795
- "step": 65500
796
- },
797
- {
798
- "epoch": 0.65,
799
- "learning_rate": 9.598052300258406e-05,
800
- "loss": 3.5183,
801
- "step": 66000
802
  },
803
  {
804
  "epoch": 0.65,
805
- "learning_rate": 9.591977442497177e-05,
806
- "loss": 3.3721,
807
- "step": 66500
808
- },
809
- {
810
- "epoch": 0.66,
811
- "learning_rate": 9.58585897405699e-05,
812
- "loss": 3.4398,
813
- "step": 67000
814
- },
815
- {
816
- "epoch": 0.66,
817
- "learning_rate": 9.579696953045823e-05,
818
- "loss": 3.4518,
819
- "step": 67500
820
- },
821
- {
822
- "epoch": 0.67,
823
- "learning_rate": 9.573491437985294e-05,
824
- "loss": 3.4266,
825
- "step": 68000
826
  },
827
  {
828
  "epoch": 0.67,
829
- "learning_rate": 9.56724248781008e-05,
830
- "loss": 3.3549,
831
- "step": 68500
832
- },
833
- {
834
- "epoch": 0.68,
835
- "learning_rate": 9.560950161867372e-05,
836
- "loss": 3.4515,
837
- "step": 69000
838
- },
839
- {
840
- "epoch": 0.68,
841
- "learning_rate": 9.55461451991631e-05,
842
- "loss": 3.4913,
843
- "step": 69500
844
- },
845
- {
846
- "epoch": 0.69,
847
- "learning_rate": 9.548235622127404e-05,
848
- "loss": 3.3973,
849
- "step": 70000
850
  },
851
  {
852
  "epoch": 0.69,
853
- "learning_rate": 9.54181352908198e-05,
854
- "loss": 3.5171,
855
- "step": 70500
856
- },
857
- {
858
- "epoch": 0.7,
859
- "learning_rate": 9.535348301771588e-05,
860
- "loss": 3.5624,
861
- "step": 71000
862
- },
863
- {
864
- "epoch": 0.7,
865
- "learning_rate": 9.528840001597435e-05,
866
- "loss": 3.4559,
867
- "step": 71500
868
- },
869
- {
870
- "epoch": 0.71,
871
- "learning_rate": 9.522288690369799e-05,
872
- "loss": 3.4169,
873
- "step": 72000
874
  },
875
  {
876
  "epoch": 0.71,
877
- "learning_rate": 9.515694430307434e-05,
878
- "loss": 3.4379,
879
- "step": 72500
880
- },
881
- {
882
- "epoch": 0.72,
883
- "learning_rate": 9.509057284036989e-05,
884
- "loss": 3.4608,
885
- "step": 73000
886
- },
887
- {
888
- "epoch": 0.72,
889
- "learning_rate": 9.502377314592413e-05,
890
- "loss": 3.4762,
891
- "step": 73500
892
- },
893
- {
894
- "epoch": 0.73,
895
- "learning_rate": 9.495654585414345e-05,
896
- "loss": 3.4797,
897
- "step": 74000
898
- },
899
- {
900
- "epoch": 0.73,
901
- "learning_rate": 9.488889160349526e-05,
902
- "loss": 3.374,
903
- "step": 74500
904
  },
905
  {
906
  "epoch": 0.73,
907
- "learning_rate": 9.482081103650184e-05,
908
- "loss": 3.2698,
909
- "step": 75000
910
- },
911
- {
912
- "epoch": 0.74,
913
- "learning_rate": 9.475230479973423e-05,
914
- "loss": 3.4349,
915
- "step": 75500
916
  },
917
  {
918
  "epoch": 0.74,
919
- "learning_rate": 9.468337354380617e-05,
920
- "loss": 3.4253,
921
- "step": 76000
922
- },
923
- {
924
- "epoch": 0.75,
925
- "learning_rate": 9.461401792336784e-05,
926
- "loss": 3.3638,
927
- "step": 76500
928
- },
929
- {
930
- "epoch": 0.75,
931
- "learning_rate": 9.454423859709966e-05,
932
- "loss": 3.4588,
933
- "step": 77000
934
- },
935
- {
936
- "epoch": 0.76,
937
- "learning_rate": 9.447403622770609e-05,
938
- "loss": 3.4846,
939
- "step": 77500
940
  },
941
  {
942
  "epoch": 0.76,
943
- "learning_rate": 9.440341148190923e-05,
944
- "loss": 3.396,
945
- "step": 78000
946
- },
947
- {
948
- "epoch": 0.77,
949
- "learning_rate": 9.433236503044259e-05,
950
- "loss": 3.3593,
951
- "step": 78500
952
- },
953
- {
954
- "epoch": 0.77,
955
- "learning_rate": 9.426089754804469e-05,
956
- "loss": 3.4798,
957
- "step": 79000
958
- },
959
- {
960
- "epoch": 0.78,
961
- "learning_rate": 9.418900971345262e-05,
962
- "loss": 3.3476,
963
- "step": 79500
964
  },
965
  {
966
  "epoch": 0.78,
967
- "learning_rate": 9.411670220939559e-05,
968
- "loss": 3.4381,
969
- "step": 80000
970
- },
971
- {
972
- "epoch": 0.79,
973
- "learning_rate": 9.404397572258856e-05,
974
- "loss": 3.4423,
975
- "step": 80500
976
- },
977
- {
978
- "epoch": 0.79,
979
- "learning_rate": 9.397083094372551e-05,
980
- "loss": 3.4221,
981
- "step": 81000
982
- },
983
- {
984
- "epoch": 0.8,
985
- "learning_rate": 9.389726856747314e-05,
986
- "loss": 3.2973,
987
- "step": 81500
988
  },
989
  {
990
  "epoch": 0.8,
991
- "learning_rate": 9.382328929246398e-05,
992
- "loss": 3.5298,
993
- "step": 82000
994
- },
995
- {
996
- "epoch": 0.81,
997
- "learning_rate": 9.374889382129004e-05,
998
- "loss": 3.4197,
999
- "step": 82500
1000
- },
1001
- {
1002
- "epoch": 0.81,
1003
- "learning_rate": 9.367408286049593e-05,
1004
- "loss": 3.3814,
1005
- "step": 83000
1006
- },
1007
- {
1008
- "epoch": 0.82,
1009
- "learning_rate": 9.359885712057224e-05,
1010
- "loss": 3.4306,
1011
- "step": 83500
1012
  },
1013
  {
1014
  "epoch": 0.82,
1015
- "learning_rate": 9.35232173159488e-05,
1016
- "loss": 3.2837,
1017
- "step": 84000
1018
- },
1019
- {
1020
- "epoch": 0.83,
1021
- "learning_rate": 9.344716416498784e-05,
1022
- "loss": 3.4308,
1023
- "step": 84500
1024
- },
1025
- {
1026
- "epoch": 0.83,
1027
- "learning_rate": 9.337069838997725e-05,
1028
- "loss": 3.442,
1029
- "step": 85000
1030
- },
1031
- {
1032
- "epoch": 0.84,
1033
- "learning_rate": 9.32938207171236e-05,
1034
- "loss": 3.4769,
1035
- "step": 85500
1036
  },
1037
  {
1038
  "epoch": 0.84,
1039
- "learning_rate": 9.321653187654538e-05,
1040
- "loss": 3.4215,
1041
- "step": 86000
1042
- },
1043
- {
1044
- "epoch": 0.85,
1045
- "learning_rate": 9.313883260226596e-05,
1046
- "loss": 3.5156,
1047
- "step": 86500
1048
- },
1049
- {
1050
- "epoch": 0.85,
1051
- "learning_rate": 9.306072363220665e-05,
1052
- "loss": 3.3513,
1053
- "step": 87000
1054
- },
1055
- {
1056
- "epoch": 0.86,
1057
- "learning_rate": 9.298220570817979e-05,
1058
- "loss": 3.394,
1059
- "step": 87500
1060
  },
1061
  {
1062
  "epoch": 0.86,
1063
- "learning_rate": 9.290327957588148e-05,
1064
- "loss": 3.3759,
1065
- "step": 88000
1066
- },
1067
- {
1068
- "epoch": 0.87,
1069
- "learning_rate": 9.282394598488472e-05,
1070
- "loss": 3.5047,
1071
- "step": 88500
1072
- },
1073
- {
1074
- "epoch": 0.87,
1075
- "learning_rate": 9.27442056886322e-05,
1076
- "loss": 3.2584,
1077
- "step": 89000
1078
- },
1079
- {
1080
- "epoch": 0.88,
1081
- "learning_rate": 9.266405944442911e-05,
1082
- "loss": 3.4081,
1083
- "step": 89500
1084
  },
1085
  {
1086
  "epoch": 0.88,
1087
- "learning_rate": 9.258350801343602e-05,
1088
- "loss": 3.3415,
1089
- "step": 90000
1090
- },
1091
- {
1092
- "epoch": 0.89,
1093
- "learning_rate": 9.250255216066161e-05,
1094
- "loss": 3.4027,
1095
- "step": 90500
1096
- },
1097
- {
1098
- "epoch": 0.89,
1099
- "learning_rate": 9.242119265495543e-05,
1100
- "loss": 3.3915,
1101
- "step": 91000
1102
- },
1103
- {
1104
- "epoch": 0.9,
1105
- "learning_rate": 9.233943026900053e-05,
1106
- "loss": 3.3392,
1107
- "step": 91500
1108
  },
1109
  {
1110
  "epoch": 0.9,
1111
- "learning_rate": 9.225726577930622e-05,
1112
- "loss": 3.425,
1113
- "step": 92000
1114
- },
1115
- {
1116
- "epoch": 0.91,
1117
- "learning_rate": 9.217469996620064e-05,
1118
- "loss": 3.4224,
1119
- "step": 92500
1120
- },
1121
- {
1122
- "epoch": 0.91,
1123
- "learning_rate": 9.209173361382335e-05,
1124
- "loss": 3.2976,
1125
- "step": 93000
1126
- },
1127
- {
1128
- "epoch": 0.92,
1129
- "learning_rate": 9.200836751011788e-05,
1130
- "loss": 3.4793,
1131
- "step": 93500
1132
  },
1133
  {
1134
  "epoch": 0.92,
1135
- "learning_rate": 9.192460244682425e-05,
1136
- "loss": 3.4458,
1137
- "step": 94000
1138
- },
1139
- {
1140
- "epoch": 0.93,
1141
- "learning_rate": 9.184043921947149e-05,
1142
- "loss": 3.3354,
1143
- "step": 94500
1144
- },
1145
- {
1146
- "epoch": 0.93,
1147
- "learning_rate": 9.175587862737006e-05,
1148
- "loss": 3.389,
1149
- "step": 95000
1150
- },
1151
- {
1152
- "epoch": 0.94,
1153
- "learning_rate": 9.167092147360419e-05,
1154
- "loss": 3.4702,
1155
- "step": 95500
1156
  },
1157
  {
1158
  "epoch": 0.94,
1159
- "learning_rate": 9.158556856502435e-05,
1160
- "loss": 3.4509,
1161
- "step": 96000
1162
- },
1163
- {
1164
- "epoch": 0.95,
1165
- "learning_rate": 9.149982071223957e-05,
1166
- "loss": 3.3319,
1167
- "step": 96500
1168
- },
1169
- {
1170
- "epoch": 0.95,
1171
- "learning_rate": 9.14136787296097e-05,
1172
- "loss": 3.3012,
1173
- "step": 97000
1174
- },
1175
- {
1176
- "epoch": 0.96,
1177
- "learning_rate": 9.132714343523769e-05,
1178
- "loss": 3.2865,
1179
- "step": 97500
1180
  },
1181
  {
1182
  "epoch": 0.96,
1183
- "learning_rate": 9.124021565096186e-05,
1184
- "loss": 3.5052,
1185
- "step": 98000
1186
- },
1187
- {
1188
- "epoch": 0.97,
1189
- "learning_rate": 9.115289620234805e-05,
1190
- "loss": 3.3569,
1191
- "step": 98500
1192
- },
1193
- {
1194
- "epoch": 0.97,
1195
- "learning_rate": 9.106518591868176e-05,
1196
- "loss": 3.3748,
1197
- "step": 99000
1198
- },
1199
- {
1200
- "epoch": 0.98,
1201
- "learning_rate": 9.097708563296035e-05,
1202
- "loss": 3.464,
1203
- "step": 99500
1204
- },
1205
- {
1206
- "epoch": 0.98,
1207
- "learning_rate": 9.088859618188508e-05,
1208
- "loss": 3.4513,
1209
- "step": 100000
1210
  },
1211
  {
1212
  "epoch": 0.98,
1213
- "learning_rate": 9.079971840585315e-05,
1214
- "loss": 3.454,
1215
- "step": 100500
1216
- },
1217
- {
1218
- "epoch": 0.99,
1219
- "learning_rate": 9.071045314894976e-05,
1220
- "loss": 3.2833,
1221
- "step": 101000
1222
- },
1223
- {
1224
- "epoch": 0.99,
1225
- "learning_rate": 9.062080125894005e-05,
1226
- "loss": 3.4265,
1227
- "step": 101500
1228
  },
1229
  {
1230
  "epoch": 1.0,
1231
- "learning_rate": 9.053076358726112e-05,
1232
- "loss": 3.3792,
1233
- "step": 102000
1234
  },
1235
  {
1236
  "epoch": 1.0,
1237
  "eval_bleu": 1.0,
1238
  "eval_brevity_penalty": 1.0,
1239
  "eval_length_ratio": 1.0,
1240
- "eval_loss": 3.2881875038146973,
1241
  "eval_precisions": [
1242
  1.0,
1243
  1.0,
@@ -1245,15 +327,15 @@
1245
  1.0
1246
  ],
1247
  "eval_reference_length": 5805056,
1248
- "eval_runtime": 12725.3279,
1249
- "eval_samples_per_second": 0.891,
1250
- "eval_steps_per_second": 0.891,
1251
  "eval_translation_length": 5805056,
1252
- "step": 102042
1253
  }
1254
  ],
1255
  "logging_steps": 500,
1256
- "max_steps": 510210,
1257
  "num_train_epochs": 5,
1258
  "save_steps": 500,
1259
  "total_flos": 2.351831312404316e+17,
 
3
  "best_model_checkpoint": null,
4
  "epoch": 1.0,
5
  "eval_steps": 500,
6
+ "global_step": 25511,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
+ "epoch": 0.02,
13
  "learning_rate": 0.0001,
14
+ "loss": 3.8798,
15
  "step": 500
16
  },
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
17
  {
18
  "epoch": 0.04,
19
+ "learning_rate": 9.999617887970705e-05,
20
+ "loss": 3.3824,
21
+ "step": 1000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
22
  },
23
  {
24
  "epoch": 0.06,
25
+ "learning_rate": 9.998471610286659e-05,
26
+ "loss": 3.3404,
27
+ "step": 1500
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
28
  },
29
  {
30
  "epoch": 0.08,
31
+ "learning_rate": 9.996561342150463e-05,
32
+ "loss": 3.3427,
33
+ "step": 2000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
34
  },
35
  {
36
  "epoch": 0.1,
37
+ "learning_rate": 9.993887375536685e-05,
38
+ "loss": 3.2575,
39
+ "step": 2500
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
40
  },
41
  {
42
  "epoch": 0.12,
43
+ "learning_rate": 9.990450119147252e-05,
44
+ "loss": 3.2676,
45
+ "step": 3000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
46
  },
47
  {
48
  "epoch": 0.14,
49
+ "learning_rate": 9.98625009834897e-05,
50
+ "loss": 3.1225,
51
+ "step": 3500
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
52
  },
53
  {
54
  "epoch": 0.16,
55
+ "learning_rate": 9.981287955093226e-05,
56
+ "loss": 3.1038,
57
+ "step": 4000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
58
  },
59
  {
60
  "epoch": 0.18,
61
+ "learning_rate": 9.97556444781787e-05,
62
+ "loss": 3.132,
63
+ "step": 4500
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
64
  },
65
  {
66
  "epoch": 0.2,
67
+ "learning_rate": 9.969080451331299e-05,
68
+ "loss": 3.1255,
69
+ "step": 5000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
70
  },
71
  {
72
  "epoch": 0.22,
73
+ "learning_rate": 9.96183695667873e-05,
74
+ "loss": 3.1358,
75
+ "step": 5500
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  },
77
  {
78
  "epoch": 0.24,
79
+ "learning_rate": 9.95383507099074e-05,
80
+ "loss": 3.1162,
81
+ "step": 6000
 
 
 
 
 
 
82
  },
83
  {
84
  "epoch": 0.25,
85
+ "learning_rate": 9.945076017314044e-05,
86
+ "loss": 3.0475,
87
+ "step": 6500
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
88
  },
89
  {
90
  "epoch": 0.27,
91
+ "learning_rate": 9.935561134424548e-05,
92
+ "loss": 3.0587,
93
+ "step": 7000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
94
  },
95
  {
96
  "epoch": 0.29,
97
+ "learning_rate": 9.925291876622738e-05,
98
+ "loss": 3.0822,
99
+ "step": 7500
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
100
  },
101
  {
102
  "epoch": 0.31,
103
+ "learning_rate": 9.914269813511388e-05,
104
+ "loss": 3.0829,
105
+ "step": 8000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
106
  },
107
  {
108
  "epoch": 0.33,
109
+ "learning_rate": 9.902496629755661e-05,
110
+ "loss": 3.0594,
111
+ "step": 8500
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
112
  },
113
  {
114
  "epoch": 0.35,
115
+ "learning_rate": 9.88997412482561e-05,
116
+ "loss": 3.0949,
117
+ "step": 9000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
118
  },
119
  {
120
  "epoch": 0.37,
121
+ "learning_rate": 9.876704212721141e-05,
122
+ "loss": 3.0807,
123
+ "step": 9500
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
124
  },
125
  {
126
  "epoch": 0.39,
127
+ "learning_rate": 9.862688921679476e-05,
128
+ "loss": 2.9289,
129
+ "step": 10000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
130
  },
131
  {
132
  "epoch": 0.41,
133
+ "learning_rate": 9.847930393865132e-05,
134
+ "loss": 3.0059,
135
+ "step": 10500
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
136
  },
137
  {
138
  "epoch": 0.43,
139
+ "learning_rate": 9.832430885042515e-05,
140
+ "loss": 3.0391,
141
+ "step": 11000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
142
  },
143
  {
144
  "epoch": 0.45,
145
+ "learning_rate": 9.816192764231132e-05,
146
+ "loss": 3.0225,
147
+ "step": 11500
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
148
  },
149
  {
150
  "epoch": 0.47,
151
+ "learning_rate": 9.799218513343504e-05,
152
+ "loss": 3.0199,
153
+ "step": 12000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
154
  },
155
  {
156
  "epoch": 0.49,
157
+ "learning_rate": 9.781510726805807e-05,
158
+ "loss": 3.0201,
159
+ "step": 12500
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
160
  },
161
  {
162
  "epoch": 0.51,
163
+ "learning_rate": 9.763072111161344e-05,
164
+ "loss": 3.0321,
165
+ "step": 13000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
166
  },
167
  {
168
  "epoch": 0.53,
169
+ "learning_rate": 9.743905484656852e-05,
170
+ "loss": 2.8965,
171
+ "step": 13500
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
172
  },
173
  {
174
  "epoch": 0.55,
175
+ "learning_rate": 9.724013776811747e-05,
176
+ "loss": 3.0016,
177
+ "step": 14000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
178
  },
179
  {
180
  "epoch": 0.57,
181
+ "learning_rate": 9.70340002797037e-05,
182
+ "loss": 3.0327,
183
+ "step": 14500
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
184
  },
185
  {
186
  "epoch": 0.59,
187
+ "learning_rate": 9.682067388837286e-05,
188
+ "loss": 3.036,
189
+ "step": 15000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
190
  },
191
  {
192
  "epoch": 0.61,
193
+ "learning_rate": 9.660019119995702e-05,
194
+ "loss": 3.0152,
195
+ "step": 15500
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
196
  },
197
  {
198
  "epoch": 0.63,
199
+ "learning_rate": 9.63725859140912e-05,
200
+ "loss": 2.9673,
201
+ "step": 16000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
202
  },
203
  {
204
  "epoch": 0.65,
205
+ "learning_rate": 9.613789281906243e-05,
206
+ "loss": 3.0032,
207
+ "step": 16500
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
208
  },
209
  {
210
  "epoch": 0.67,
211
+ "learning_rate": 9.589614778649267e-05,
212
+ "loss": 2.9865,
213
+ "step": 17000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
214
  },
215
  {
216
  "epoch": 0.69,
217
+ "learning_rate": 9.564738776585591e-05,
218
+ "loss": 3.0042,
219
+ "step": 17500
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
220
  },
221
  {
222
  "epoch": 0.71,
223
+ "learning_rate": 9.539165077883064e-05,
224
+ "loss": 2.988,
225
+ "step": 18000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
226
  },
227
  {
228
  "epoch": 0.73,
229
+ "learning_rate": 9.51289759134885e-05,
230
+ "loss": 2.9729,
231
+ "step": 18500
 
 
 
 
 
 
232
  },
233
  {
234
  "epoch": 0.74,
235
+ "learning_rate": 9.485940331831984e-05,
236
+ "loss": 2.9924,
237
+ "step": 19000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
238
  },
239
  {
240
  "epoch": 0.76,
241
+ "learning_rate": 9.45829741960972e-05,
242
+ "loss": 2.96,
243
+ "step": 19500
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
244
  },
245
  {
246
  "epoch": 0.78,
247
+ "learning_rate": 9.429973079757773e-05,
248
+ "loss": 2.9702,
249
+ "step": 20000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
250
  },
251
  {
252
  "epoch": 0.8,
253
+ "learning_rate": 9.400971641504533e-05,
254
+ "loss": 2.9362,
255
+ "step": 20500
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
256
  },
257
  {
258
  "epoch": 0.82,
259
+ "learning_rate": 9.371297537569369e-05,
260
+ "loss": 2.9421,
261
+ "step": 21000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
262
  },
263
  {
264
  "epoch": 0.84,
265
+ "learning_rate": 9.340955303485112e-05,
266
+ "loss": 2.8557,
267
+ "step": 21500
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
268
  },
269
  {
270
  "epoch": 0.86,
271
+ "learning_rate": 9.309949576904817e-05,
272
+ "loss": 2.8443,
273
+ "step": 22000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
274
  },
275
  {
276
  "epoch": 0.88,
277
+ "learning_rate": 9.278285096892927e-05,
278
+ "loss": 2.8352,
279
+ "step": 22500
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
280
  },
281
  {
282
  "epoch": 0.9,
283
+ "learning_rate": 9.245966703200923e-05,
284
+ "loss": 2.8187,
285
+ "step": 23000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
286
  },
287
  {
288
  "epoch": 0.92,
289
+ "learning_rate": 9.212999335527607e-05,
290
+ "loss": 2.887,
291
+ "step": 23500
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
292
  },
293
  {
294
  "epoch": 0.94,
295
+ "learning_rate": 9.179388032764086e-05,
296
+ "loss": 2.9268,
297
+ "step": 24000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
298
  },
299
  {
300
  "epoch": 0.96,
301
+ "learning_rate": 9.145137932223598e-05,
302
+ "loss": 2.9458,
303
+ "step": 24500
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
304
  },
305
  {
306
  "epoch": 0.98,
307
+ "learning_rate": 9.110254268856312e-05,
308
+ "loss": 2.8961,
309
+ "step": 25000
 
 
 
 
 
 
 
 
 
 
 
 
310
  },
311
  {
312
  "epoch": 1.0,
313
+ "learning_rate": 9.074742374449192e-05,
314
+ "loss": 2.9421,
315
+ "step": 25500
316
  },
317
  {
318
  "epoch": 1.0,
319
  "eval_bleu": 1.0,
320
  "eval_brevity_penalty": 1.0,
321
  "eval_length_ratio": 1.0,
322
+ "eval_loss": 2.790889024734497,
323
  "eval_precisions": [
324
  1.0,
325
  1.0,
 
327
  1.0
328
  ],
329
  "eval_reference_length": 5805056,
330
+ "eval_runtime": 9395.1429,
331
+ "eval_samples_per_second": 1.207,
332
+ "eval_steps_per_second": 0.302,
333
  "eval_translation_length": 5805056,
334
+ "step": 25511
335
  }
336
  ],
337
  "logging_steps": 500,
338
+ "max_steps": 127555,
339
  "num_train_epochs": 5,
340
  "save_steps": 500,
341
  "total_flos": 2.351831312404316e+17,
last-checkpoint/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8b7c1932490056bb6997d0067ffe79c8e4cad2c1f98c97f997d02b0594f0b2e8
3
  size 4728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c32a9c65221d103b02faab497de247bbdfc7b9598acc0b6597ea2949b830722
3
  size 4728