Hugging Face's logo

Spaces:
Jayant2304
/
commitment-os
Sleeping

App Files Community
commitment-os
File size: 28,028 Bytes
af8810b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
[
  {
    "loss": 0.6357966065406799,
    "grad_norm": 0.5020767450332642,
    "learning_rate": 0.0,
    "num_tokens": 2584.0,
    "completions/mean_length": 200.0,
    "completions/min_length": 20.0,
    "completions/max_length": 380.0,
    "completions/clipped_ratio": 0.0,
    "completions/mean_terminated_length": 200.0,
    "completions/min_terminated_length": 20.0,
    "completions/max_terminated_length": 380.0,
    "rewards/reward_function/mean": 0.574999988079071,
    "rewards/reward_function/std": 0.10606600344181061,
    "reward": 0.574999988079071,
    "reward_std": 0.10606600344181061,
    "frac_reward_zero_std": 0.0,
    "entropy": 0.26839178800582886,
    "clip_ratio/low_mean": 0.0,
    "clip_ratio/low_min": 0.0,
    "clip_ratio/high_mean": 0.0,
    "clip_ratio/high_max": 0.0,
    "clip_ratio/region_mean": 0.0,
    "step_time": 61.83920078600022,
    "epoch": 0.06666666666666667,
    "step": 1
  },
  {
    "loss": -0.24778124690055847,
    "grad_norm": 1.877001166343689,
    "learning_rate": 1.6666666666666667e-06,
    "num_tokens": 4297.0,
    "completions/mean_length": 35.5,
    "completions/min_length": 23.0,
    "completions/max_length": 48.0,
    "completions/clipped_ratio": 0.0,
    "completions/mean_terminated_length": 35.5,
    "completions/min_terminated_length": 23.0,
    "completions/max_terminated_length": 48.0,
    "rewards/reward_function/mean": 0.40209999680519104,
    "rewards/reward_function/std": 0.020647529512643814,
    "reward": 0.40209999680519104,
    "reward_std": 0.020647529512643814,
    "frac_reward_zero_std": 0.0,
    "entropy": 0.29453833028674126,
    "clip_ratio/low_mean": 0.0,
    "clip_ratio/low_min": 0.0,
    "clip_ratio/high_mean": 0.0,
    "clip_ratio/high_max": 0.0,
    "clip_ratio/region_mean": 0.0,
    "step_time": 14.531932316999928,
    "epoch": 0.13333333333333333,
    "step": 2
  },
  {
    "loss": -0.07843422889709473,
    "grad_norm": 1.543445110321045,
    "learning_rate": 3.3333333333333333e-06,
    "num_tokens": 5871.0,
    "completions/mean_length": 18.0,
    "completions/min_length": 16.0,
    "completions/max_length": 20.0,
    "completions/clipped_ratio": 0.0,
    "completions/mean_terminated_length": 18.0,
    "completions/min_terminated_length": 16.0,
    "completions/max_terminated_length": 20.0,
    "rewards/reward_function/mean": 0.4583500027656555,
    "rewards/reward_function/std": 0.058901991695165634,
    "reward": 0.4583500027656555,
    "reward_std": 0.058901991695165634,
    "frac_reward_zero_std": 0.0,
    "entropy": 0.1914939135313034,
    "clip_ratio/low_mean": 0.0,
    "clip_ratio/low_min": 0.0,
    "clip_ratio/high_mean": 0.0,
    "clip_ratio/high_max": 0.0,
    "clip_ratio/region_mean": 0.0,
    "step_time": 10.524165547000166,
    "epoch": 0.2,
    "step": 3
  },
  {
    "loss": 0.07059085369110107,
    "grad_norm": 1.5465283393859863,
    "learning_rate": 5e-06,
    "num_tokens": 7485.0,
    "completions/mean_length": 20.0,
    "completions/min_length": 18.0,
    "completions/max_length": 22.0,
    "completions/clipped_ratio": 0.0,
    "completions/mean_terminated_length": 20.0,
    "completions/min_terminated_length": 18.0,
    "completions/max_terminated_length": 22.0,
    "rewards/reward_function/mean": 0.4583500027656555,
    "rewards/reward_function/std": 0.058901991695165634,
    "reward": 0.4583500027656555,
    "reward_std": 0.058901991695165634,
    "frac_reward_zero_std": 0.0,
    "entropy": 0.1294238492846489,
    "clip_ratio/low_mean": 0.0,
    "clip_ratio/low_min": 0.0,
    "clip_ratio/high_mean": 0.0,
    "clip_ratio/high_max": 0.0,
    "clip_ratio/region_mean": 0.0,
    "step_time": 10.990043340000057,
    "epoch": 0.26666666666666666,
    "step": 4
  },
  {
    "loss": -0.008725225925445557,
    "grad_norm": 1.369038462638855,
    "learning_rate": 4.814814814814815e-06,
    "num_tokens": 8692.0,
    "completions/mean_length": 40.5,
    "completions/min_length": 40.0,
    "completions/max_length": 41.0,
    "completions/clipped_ratio": 0.0,
    "completions/mean_terminated_length": 40.5,
    "completions/min_terminated_length": 40.0,
    "completions/max_terminated_length": 41.0,
    "rewards/reward_function/mean": 0.5187499523162842,
    "rewards/reward_function/std": 0.18561552464962006,
    "reward": 0.5187499523162842,
    "reward_std": 0.18561550974845886,
    "frac_reward_zero_std": 0.0,
    "entropy": 0.19958198070526123,
    "clip_ratio/low_mean": 0.0,
    "clip_ratio/low_min": 0.0,
    "clip_ratio/high_mean": 0.0,
    "clip_ratio/high_max": 0.0,
    "clip_ratio/region_mean": 0.0,
    "step_time": 11.131567607000306,
    "epoch": 0.3333333333333333,
    "step": 5
  },
  {
    "loss": -0.07062190771102905,
    "grad_norm": 0.8509910702705383,
    "learning_rate": 4.62962962962963e-06,
    "num_tokens": 9862.0,
    "completions/mean_length": 40.0,
    "completions/min_length": 36.0,
    "completions/max_length": 44.0,
    "completions/clipped_ratio": 0.0,
    "completions/mean_terminated_length": 40.0,
    "completions/min_terminated_length": 36.0,
    "completions/max_terminated_length": 44.0,
    "rewards/reward_function/mean": 0.4437499940395355,
    "rewards/reward_function/std": 0.07954952120780945,
    "reward": 0.4437499940395355,
    "reward_std": 0.07954952120780945,
    "frac_reward_zero_std": 0.0,
    "entropy": 0.1297583170235157,
    "clip_ratio/low_mean": 0.0,
    "clip_ratio/low_min": 0.0,
    "clip_ratio/high_mean": 0.0,
    "clip_ratio/high_max": 0.0,
    "clip_ratio/region_mean": 0.0,
    "step_time": 11.613226033000046,
    "epoch": 0.4,
    "step": 6
  },
  {
    "loss": -5.960464477539062e-07,
    "grad_norm": 0.1141546443104744,
    "learning_rate": 4.444444444444444e-06,
    "num_tokens": 11000.0,
    "completions/mean_length": 19.0,
    "completions/min_length": 19.0,
    "completions/max_length": 19.0,
    "completions/clipped_ratio": 0.0,
    "completions/mean_terminated_length": 19.0,
    "completions/min_terminated_length": 19.0,
    "completions/max_terminated_length": 19.0,
    "rewards/reward_function/mean": 0.5349999666213989,
    "rewards/reward_function/std": 0.04949747025966644,
    "reward": 0.5349999666213989,
    "reward_std": 0.04949747025966644,
    "frac_reward_zero_std": 0.0,
    "entropy": 0.07411494851112366,
    "clip_ratio/low_mean": 0.0,
    "clip_ratio/low_min": 0.0,
    "clip_ratio/high_mean": 0.0,
    "clip_ratio/high_max": 0.0,
    "clip_ratio/region_mean": 0.0,
    "step_time": 8.378681117999804,
    "epoch": 0.4666666666666667,
    "step": 7
  },
  {
    "loss": -0.5384407639503479,
    "grad_norm": 0.575139045715332,
    "learning_rate": 4.2592592592592596e-06,
    "num_tokens": 12808.0,
    "completions/mean_length": 119.0,
    "completions/min_length": 28.0,
    "completions/max_length": 210.0,
    "completions/clipped_ratio": 0.0,
    "completions/mean_terminated_length": 119.0,
    "completions/min_terminated_length": 28.0,
    "completions/max_terminated_length": 210.0,
    "rewards/reward_function/mean": 0.6333500146865845,
    "rewards/reward_function/std": 0.023546643555164337,
    "reward": 0.6333500146865845,
    "reward_std": 0.023546643555164337,
    "frac_reward_zero_std": 0.0,
    "entropy": 0.2676837705075741,
    "clip_ratio/low_mean": 0.0,
    "clip_ratio/low_min": 0.0,
    "clip_ratio/high_mean": 0.0,
    "clip_ratio/high_max": 0.0,
    "clip_ratio/region_mean": 0.0,
    "step_time": 37.1004951179998,
    "epoch": 0.5333333333333333,
    "step": 8
  },
  {
    "loss": 0.0,
    "grad_norm": 0.14882154762744904,
    "learning_rate": 4.074074074074074e-06,
    "num_tokens": 14288.0,
    "completions/mean_length": 22.0,
    "completions/min_length": 22.0,
    "completions/max_length": 22.0,
    "completions/clipped_ratio": 0.0,
    "completions/mean_terminated_length": 22.0,
    "completions/min_terminated_length": 22.0,
    "completions/max_terminated_length": 22.0,
    "rewards/reward_function/mean": 0.4583500027656555,
    "rewards/reward_function/std": 0.058901991695165634,
    "reward": 0.4583500027656555,
    "reward_std": 0.058901991695165634,
    "frac_reward_zero_std": 0.0,
    "entropy": 0.0809866338968277,
    "clip_ratio/low_mean": 0.0,
    "clip_ratio/low_min": 0.0,
    "clip_ratio/high_mean": 0.0,
    "clip_ratio/high_max": 0.0,
    "clip_ratio/region_mean": 0.0,
    "step_time": 10.457592102000262,
    "epoch": 0.6,
    "step": 9
  },
  {
    "loss": -0.07851982116699219,
    "grad_norm": 1.6114908456802368,
    "learning_rate": 3.88888888888889e-06,
    "num_tokens": 16384.0,
    "completions/mean_length": 27.0,
    "completions/min_length": 24.0,
    "completions/max_length": 30.0,
    "completions/clipped_ratio": 0.0,
    "completions/mean_terminated_length": 27.0,
    "completions/min_terminated_length": 24.0,
    "completions/max_terminated_length": 30.0,
    "rewards/reward_function/mean": 0.5333499908447266,
    "rewards/reward_function/std": 0.16496798396110535,
    "reward": 0.5333499908447266,
    "reward_std": 0.16496798396110535,
    "frac_reward_zero_std": 0.0,
    "entropy": 0.4823211133480072,
    "clip_ratio/low_mean": 0.0,
    "clip_ratio/low_min": 0.0,
    "clip_ratio/high_mean": 0.0,
    "clip_ratio/high_max": 0.0,
    "clip_ratio/region_mean": 0.0,
    "step_time": 14.966705318999857,
    "epoch": 0.6666666666666666,
    "step": 10
  },
  {
    "loss": 0.0,
    "grad_norm": 0.0,
    "learning_rate": 3.7037037037037037e-06,
    "num_tokens": 17617.0,
    "completions/mean_length": 35.5,
    "completions/min_length": 16.0,
    "completions/max_length": 55.0,
    "completions/clipped_ratio": 0.0,
    "completions/mean_terminated_length": 35.5,
    "completions/min_terminated_length": 16.0,
    "completions/max_terminated_length": 55.0,
    "rewards/reward_function/mean": 0.41670000553131104,
    "rewards/reward_function/std": 0.0,
    "reward": 0.41670000553131104,
    "reward_std": 0.0,
    "frac_reward_zero_std": 1.0,
    "entropy": 0.9841015487909317,
    "clip_ratio/low_mean": 0.0,
    "clip_ratio/low_min": 0.0,
    "clip_ratio/high_mean": 0.0,
    "clip_ratio/high_max": 0.0,
    "clip_ratio/region_mean": 0.0,
    "step_time": 13.133867920999819,
    "epoch": 0.7333333333333333,
    "step": 11
  },
  {
    "loss": -0.05432739853858948,
    "grad_norm": 1.1030373573303223,
    "learning_rate": 3.5185185185185187e-06,
    "num_tokens": 19429.0,
    "completions/mean_length": 39.0,
    "completions/min_length": 36.0,
    "completions/max_length": 42.0,
    "completions/clipped_ratio": 0.0,
    "completions/mean_terminated_length": 39.0,
    "completions/min_terminated_length": 36.0,
    "completions/max_terminated_length": 42.0,
    "rewards/reward_function/mean": 0.5583499670028687,
    "rewards/reward_function/std": 0.08251935988664627,
    "reward": 0.5583499670028687,
    "reward_std": 0.08251935988664627,
    "frac_reward_zero_std": 0.0,
    "entropy": 0.12238830700516701,
    "clip_ratio/low_mean": 0.0,
    "clip_ratio/low_min": 0.0,
    "clip_ratio/high_mean": 0.0,
    "clip_ratio/high_max": 0.0,
    "clip_ratio/region_mean": 0.0,
    "step_time": 15.016316874000267,
    "epoch": 0.8,
    "step": 12
  },
  {
    "loss": 0.149135559797287,
    "grad_norm": 1.254807472229004,
    "learning_rate": 3.3333333333333333e-06,
    "num_tokens": 20626.0,
    "completions/mean_length": 35.5,
    "completions/min_length": 28.0,
    "completions/max_length": 43.0,
    "completions/clipped_ratio": 0.0,
    "completions/mean_terminated_length": 35.5,
    "completions/min_terminated_length": 28.0,
    "completions/max_terminated_length": 43.0,
    "rewards/reward_function/mean": 0.4583500027656555,
    "rewards/reward_function/std": 0.058901991695165634,
    "reward": 0.4583500027656555,
    "reward_std": 0.058901991695165634,
    "frac_reward_zero_std": 0.0,
    "entropy": 0.2583826147019863,
    "clip_ratio/low_mean": 0.0,
    "clip_ratio/low_min": 0.0,
    "clip_ratio/high_mean": 0.0,
    "clip_ratio/high_max": 0.0,
    "clip_ratio/region_mean": 0.0,
    "step_time": 11.519657740999946,
    "epoch": 0.8666666666666667,
    "step": 13
  },
  {
    "loss": 0.27955153584480286,
    "grad_norm": 1.167170763015747,
    "learning_rate": 3.1481481481481483e-06,
    "num_tokens": 22067.0,
    "completions/mean_length": 36.5,
    "completions/min_length": 22.0,
    "completions/max_length": 51.0,
    "completions/clipped_ratio": 0.0,
    "completions/mean_terminated_length": 36.5,
    "completions/min_terminated_length": 22.0,
    "completions/max_terminated_length": 51.0,
    "rewards/reward_function/mean": 0.40209999680519104,
    "rewards/reward_function/std": 0.020647529512643814,
    "reward": 0.40209999680519104,
    "reward_std": 0.020647529512643814,
    "frac_reward_zero_std": 0.0,
    "entropy": 0.24101658910512924,
    "clip_ratio/low_mean": 0.0,
    "clip_ratio/low_min": 0.0,
    "clip_ratio/high_mean": 0.0,
    "clip_ratio/high_max": 0.0,
    "clip_ratio/region_mean": 0.0,
    "step_time": 14.053339626000025,
    "epoch": 0.9333333333333333,
    "step": 14
  },
  {
    "loss": 0.06053304672241211,
    "grad_norm": 2.425391435623169,
    "learning_rate": 2.962962962962963e-06,
    "num_tokens": 23691.0,
    "completions/mean_length": 35.0,
    "completions/min_length": 32.0,
    "completions/max_length": 38.0,
    "completions/clipped_ratio": 0.0,
    "completions/mean_terminated_length": 35.0,
    "completions/min_terminated_length": 32.0,
    "completions/max_terminated_length": 38.0,
    "rewards/reward_function/mean": 0.4437499940395355,
    "rewards/reward_function/std": 0.07954952120780945,
    "reward": 0.4437499940395355,
    "reward_std": 0.07954952120780945,
    "frac_reward_zero_std": 0.0,
    "entropy": 0.25765860080718994,
    "clip_ratio/low_mean": 0.0,
    "clip_ratio/low_min": 0.0,
    "clip_ratio/high_mean": 0.0,
    "clip_ratio/high_max": 0.0,
    "clip_ratio/region_mean": 0.0,
    "step_time": 13.23964212199985,
    "epoch": 1.0,
    "step": 15
  },
  {
    "loss": 0.0,
    "grad_norm": 0.0,
    "learning_rate": 2.7777777777777783e-06,
    "num_tokens": 24930.0,
    "completions/mean_length": 56.5,
    "completions/min_length": 55.0,
    "completions/max_length": 58.0,
    "completions/clipped_ratio": 0.0,
    "completions/mean_terminated_length": 56.5,
    "completions/min_terminated_length": 55.0,
    "completions/max_terminated_length": 58.0,
    "rewards/reward_function/mean": 0.5,
    "rewards/reward_function/std": 0.0,
    "reward": 0.5,
    "reward_std": 0.0,
    "frac_reward_zero_std": 1.0,
    "entropy": 0.4330967664718628,
    "clip_ratio/low_mean": 0.0,
    "clip_ratio/low_min": 0.0,
    "clip_ratio/high_mean": 0.0,
    "clip_ratio/high_max": 0.0,
    "clip_ratio/region_mean": 0.0,
    "step_time": 13.377671128000202,
    "epoch": 1.0666666666666667,
    "step": 16
  },
  {
    "loss": 0.0672960877418518,
    "grad_norm": 1.6053359508514404,
    "learning_rate": 2.5925925925925925e-06,
    "num_tokens": 26072.0,
    "completions/mean_length": 21.0,
    "completions/min_length": 19.0,
    "completions/max_length": 23.0,
    "completions/clipped_ratio": 0.0,
    "completions/mean_terminated_length": 21.0,
    "completions/min_terminated_length": 19.0,
    "completions/max_terminated_length": 23.0,
    "rewards/reward_function/mean": 0.516700029373169,
    "rewards/reward_function/std": 0.1414213478565216,
    "reward": 0.516700029373169,
    "reward_std": 0.1414213478565216,
    "frac_reward_zero_std": 0.0,
    "entropy": 0.06669686548411846,
    "clip_ratio/low_mean": 0.0,
    "clip_ratio/low_min": 0.0,
    "clip_ratio/high_mean": 0.0,
    "clip_ratio/high_max": 0.0,
    "clip_ratio/region_mean": 0.0,
    "step_time": 8.82481953599995,
    "epoch": 1.1333333333333333,
    "step": 17
  },
  {
    "loss": -0.13629436492919922,
    "grad_norm": 1.381037950515747,
    "learning_rate": 2.4074074074074075e-06,
    "num_tokens": 27771.0,
    "completions/mean_length": 28.5,
    "completions/min_length": 23.0,
    "completions/max_length": 34.0,
    "completions/clipped_ratio": 0.0,
    "completions/mean_terminated_length": 28.5,
    "completions/min_terminated_length": 23.0,
    "completions/max_terminated_length": 34.0,
    "rewards/reward_function/mean": 0.5583499670028687,
    "rewards/reward_function/std": 0.08251935988664627,
    "reward": 0.5583499670028687,
    "reward_std": 0.08251935988664627,
    "frac_reward_zero_std": 0.0,
    "entropy": 0.12161804735660553,
    "clip_ratio/low_mean": 0.0,
    "clip_ratio/low_min": 0.0,
    "clip_ratio/high_mean": 0.0,
    "clip_ratio/high_max": 0.0,
    "clip_ratio/region_mean": 0.0,
    "step_time": 13.361655292000023,
    "epoch": 1.2,
    "step": 18
  },
  {
    "loss": -0.1279437243938446,
    "grad_norm": 2.226921558380127,
    "learning_rate": 2.222222222222222e-06,
    "num_tokens": 29251.0,
    "completions/mean_length": 22.0,
    "completions/min_length": 18.0,
    "completions/max_length": 26.0,
    "completions/clipped_ratio": 0.0,
    "completions/mean_terminated_length": 22.0,
    "completions/min_terminated_length": 18.0,
    "completions/max_terminated_length": 26.0,
    "rewards/reward_function/mean": 0.6021000146865845,
    "rewards/reward_function/std": 0.020647529512643814,
    "reward": 0.6021000146865845,
    "reward_std": 0.020647529512643814,
    "frac_reward_zero_std": 0.0,
    "entropy": 0.08564786985516548,
    "clip_ratio/low_mean": 0.0,
    "clip_ratio/low_min": 0.0,
    "clip_ratio/high_mean": 0.0,
    "clip_ratio/high_max": 0.0,
    "clip_ratio/region_mean": 0.0,
    "step_time": 11.087925465999888,
    "epoch": 1.2666666666666666,
    "step": 19
  },
  {
    "loss": 0.06728780269622803,
    "grad_norm": 1.0975555181503296,
    "learning_rate": 2.037037037037037e-06,
    "num_tokens": 30425.0,
    "completions/mean_length": 42.0,
    "completions/min_length": 38.0,
    "completions/max_length": 46.0,
    "completions/clipped_ratio": 0.0,
    "completions/mean_terminated_length": 42.0,
    "completions/min_terminated_length": 38.0,
    "completions/max_terminated_length": 46.0,
    "rewards/reward_function/mean": 0.5020999908447266,
    "rewards/reward_function/std": 0.1207738146185875,
    "reward": 0.5020999908447266,
    "reward_std": 0.1207738146185875,
    "frac_reward_zero_std": 0.0,
    "entropy": 0.16879020631313324,
    "clip_ratio/low_mean": 0.0,
    "clip_ratio/low_min": 0.0,
    "clip_ratio/high_mean": 0.0,
    "clip_ratio/high_max": 0.0,
    "clip_ratio/region_mean": 0.0,
    "step_time": 11.843729876999987,
    "epoch": 1.3333333333333333,
    "step": 20
  },
  {
    "loss": 0.054305046796798706,
    "grad_norm": 1.0439469814300537,
    "learning_rate": 1.8518518518518519e-06,
    "num_tokens": 32047.0,
    "completions/mean_length": 26.0,
    "completions/min_length": 24.0,
    "completions/max_length": 28.0,
    "completions/clipped_ratio": 0.0,
    "completions/mean_terminated_length": 26.0,
    "completions/min_terminated_length": 24.0,
    "completions/max_terminated_length": 28.0,
    "rewards/reward_function/mean": 0.543749988079071,
    "rewards/reward_function/std": 0.06187182664871216,
    "reward": 0.543749988079071,
    "reward_std": 0.06187182664871216,
    "frac_reward_zero_std": 0.0,
    "entropy": 0.09812109172344208,
    "clip_ratio/low_mean": 0.0,
    "clip_ratio/low_min": 0.0,
    "clip_ratio/high_mean": 0.0,
    "clip_ratio/high_max": 0.0,
    "clip_ratio/region_mean": 0.0,
    "step_time": 12.01839622600005,
    "epoch": 1.4,
    "step": 21
  },
  {
    "loss": -0.43347233533859253,
    "grad_norm": 0.6157990097999573,
    "learning_rate": 1.6666666666666667e-06,
    "num_tokens": 33354.0,
    "completions/mean_length": 72.5,
    "completions/min_length": 28.0,
    "completions/max_length": 117.0,
    "completions/clipped_ratio": 0.0,
    "completions/mean_terminated_length": 72.5,
    "completions/min_terminated_length": 28.0,
    "completions/max_terminated_length": 117.0,
    "rewards/reward_function/mean": 0.4437499940395355,
    "rewards/reward_function/std": 0.07954952120780945,
    "reward": 0.4437499940395355,
    "reward_std": 0.07954952120780945,
    "frac_reward_zero_std": 0.0,
    "entropy": 0.16432299464941025,
    "clip_ratio/low_mean": 0.0,
    "clip_ratio/low_min": 0.0,
    "clip_ratio/high_mean": 0.0,
    "clip_ratio/high_max": 0.0,
    "clip_ratio/region_mean": 0.0,
    "step_time": 21.621784166999987,
    "epoch": 1.4666666666666668,
    "step": 22
  },
  {
    "loss": 0.21844279766082764,
    "grad_norm": 1.18323814868927,
    "learning_rate": 1.4814814814814815e-06,
    "num_tokens": 35143.0,
    "completions/mean_length": 27.5,
    "completions/min_length": 19.0,
    "completions/max_length": 36.0,
    "completions/clipped_ratio": 0.0,
    "completions/mean_terminated_length": 27.5,
    "completions/min_terminated_length": 19.0,
    "completions/max_terminated_length": 36.0,
    "rewards/reward_function/mean": 0.6312500238418579,
    "rewards/reward_function/std": 0.18561552464962006,
    "reward": 0.6312500238418579,
    "reward_std": 0.18561550974845886,
    "frac_reward_zero_std": 0.0,
    "entropy": 0.10744666680693626,
    "clip_ratio/low_mean": 0.0,
    "clip_ratio/low_min": 0.0,
    "clip_ratio/high_mean": 0.0,
    "clip_ratio/high_max": 0.0,
    "clip_ratio/region_mean": 0.0,
    "step_time": 14.225728247999996,
    "epoch": 1.5333333333333332,
    "step": 23
  },
  {
    "loss": -0.6148233413696289,
    "grad_norm": 0.8197247982025146,
    "learning_rate": 1.2962962962962962e-06,
    "num_tokens": 36929.0,
    "completions/mean_length": 124.0,
    "completions/min_length": 16.0,
    "completions/max_length": 232.0,
    "completions/clipped_ratio": 0.0,
    "completions/mean_terminated_length": 124.0,
    "completions/min_terminated_length": 16.0,
    "completions/max_terminated_length": 232.0,
    "rewards/reward_function/mean": 0.4583500027656555,
    "rewards/reward_function/std": 0.058901991695165634,
    "reward": 0.4583500027656555,
    "reward_std": 0.058901991695165634,
    "frac_reward_zero_std": 0.0,
    "entropy": 0.6331216096878052,
    "clip_ratio/low_mean": 0.0,
    "clip_ratio/low_min": 0.0,
    "clip_ratio/high_mean": 0.0,
    "clip_ratio/high_max": 0.0,
    "clip_ratio/region_mean": 0.0,
    "step_time": 39.883540922000066,
    "epoch": 1.6,
    "step": 24
  },
  {
    "loss": -0.054349154233932495,
    "grad_norm": 1.030266284942627,
    "learning_rate": 1.111111111111111e-06,
    "num_tokens": 39023.0,
    "completions/mean_length": 26.0,
    "completions/min_length": 24.0,
    "completions/max_length": 28.0,
    "completions/clipped_ratio": 0.0,
    "completions/mean_terminated_length": 26.0,
    "completions/min_terminated_length": 24.0,
    "completions/max_terminated_length": 28.0,
    "rewards/reward_function/mean": 0.6749999523162842,
    "rewards/reward_function/std": 0.1237436980009079,
    "reward": 0.6749999523162842,
    "reward_std": 0.1237436980009079,
    "frac_reward_zero_std": 0.0,
    "entropy": 0.07906700298190117,
    "clip_ratio/low_mean": 0.0,
    "clip_ratio/low_min": 0.0,
    "clip_ratio/high_mean": 0.0,
    "clip_ratio/high_max": 0.0,
    "clip_ratio/region_mean": 0.0,
    "step_time": 14.697501995000039,
    "epoch": 1.6666666666666665,
    "step": 25
  },
  {
    "loss": 0.0,
    "grad_norm": 0.0,
    "learning_rate": 9.259259259259259e-07,
    "num_tokens": 40211.0,
    "completions/mean_length": 31.0,
    "completions/min_length": 22.0,
    "completions/max_length": 40.0,
    "completions/clipped_ratio": 0.0,
    "completions/mean_terminated_length": 31.0,
    "completions/min_terminated_length": 22.0,
    "completions/max_terminated_length": 40.0,
    "rewards/reward_function/mean": 0.6499999761581421,
    "rewards/reward_function/std": 0.0,
    "reward": 0.6499999761581421,
    "reward_std": 0.0,
    "frac_reward_zero_std": 1.0,
    "entropy": 0.14391540735960007,
    "clip_ratio/low_mean": 0.0,
    "clip_ratio/low_min": 0.0,
    "clip_ratio/high_mean": 0.0,
    "clip_ratio/high_max": 0.0,
    "clip_ratio/region_mean": 0.0,
    "step_time": 11.100019781000128,
    "epoch": 1.7333333333333334,
    "step": 26
  },
  {
    "loss": 0.11774009466171265,
    "grad_norm": 1.699737310409546,
    "learning_rate": 7.407407407407407e-07,
    "num_tokens": 42443.0,
    "completions/mean_length": 24.0,
    "completions/min_length": 20.0,
    "completions/max_length": 28.0,
    "completions/clipped_ratio": 0.0,
    "completions/mean_terminated_length": 24.0,
    "completions/min_terminated_length": 20.0,
    "completions/max_terminated_length": 28.0,
    "rewards/reward_function/mean": 0.574999988079071,
    "rewards/reward_function/std": 0.10606600344181061,
    "reward": 0.574999988079071,
    "reward_std": 0.10606600344181061,
    "frac_reward_zero_std": 0.0,
    "entropy": 0.14994759857654572,
    "clip_ratio/low_mean": 0.0,
    "clip_ratio/low_min": 0.0,
    "clip_ratio/high_mean": 0.0,
    "clip_ratio/high_max": 0.0,
    "clip_ratio/region_mean": 0.0,
    "step_time": 15.477631969999948,
    "epoch": 1.8,
    "step": 27
  },
  {
    "loss": -0.05434012413024902,
    "grad_norm": 0.8750740885734558,
    "learning_rate": 5.555555555555555e-07,
    "num_tokens": 44062.0,
    "completions/mean_length": 32.5,
    "completions/min_length": 30.0,
    "completions/max_length": 35.0,
    "completions/clipped_ratio": 0.0,
    "completions/mean_terminated_length": 32.5,
    "completions/min_terminated_length": 30.0,
    "completions/max_terminated_length": 35.0,
    "rewards/reward_function/mean": 0.6895999908447266,
    "rewards/reward_function/std": 0.10309616476297379,
    "reward": 0.6895999908447266,
    "reward_std": 0.10309616476297379,
    "frac_reward_zero_std": 0.0,
    "entropy": 0.142868272960186,
    "clip_ratio/low_mean": 0.0,
    "clip_ratio/low_min": 0.0,
    "clip_ratio/high_mean": 0.0,
    "clip_ratio/high_max": 0.0,
    "clip_ratio/region_mean": 0.0,
    "step_time": 12.90737977799995,
    "epoch": 1.8666666666666667,
    "step": 28
  },
  {
    "loss": 0.15356993675231934,
    "grad_norm": 1.543925404548645,
    "learning_rate": 3.7037037037037036e-07,
    "num_tokens": 45476.0,
    "completions/mean_length": 23.0,
    "completions/min_length": 18.0,
    "completions/max_length": 28.0,
    "completions/clipped_ratio": 0.0,
    "completions/mean_terminated_length": 23.0,
    "completions/min_terminated_length": 18.0,
    "completions/max_terminated_length": 28.0,
    "rewards/reward_function/mean": 0.6895999908447266,
    "rewards/reward_function/std": 0.10309616476297379,
    "reward": 0.6895999908447266,
    "reward_std": 0.10309616476297379,
    "frac_reward_zero_std": 0.0,
    "entropy": 0.17455117404460907,
    "clip_ratio/low_mean": 0.0,
    "clip_ratio/low_min": 0.0,
    "clip_ratio/high_mean": 0.0,
    "clip_ratio/high_max": 0.0,
    "clip_ratio/region_mean": 0.0,
    "step_time": 11.09434006399988,
    "epoch": 1.9333333333333333,
    "step": 29
  },
  {
    "loss": -0.030694186687469482,
    "grad_norm": 1.561765432357788,
    "learning_rate": 1.8518518518518518e-07,
    "num_tokens": 47096.0,
    "completions/mean_length": 23.0,
    "completions/min_length": 22.0,
    "completions/max_length": 24.0,
    "completions/clipped_ratio": 0.0,
    "completions/mean_terminated_length": 23.0,
    "completions/min_terminated_length": 22.0,
    "completions/max_terminated_length": 24.0,
    "rewards/reward_function/mean": 0.543749988079071,
    "rewards/reward_function/std": 0.06187182664871216,
    "reward": 0.543749988079071,
    "reward_std": 0.06187182664871216,
    "frac_reward_zero_std": 0.0,
    "entropy": 0.13204744830727577,
    "clip_ratio/low_mean": 0.0,
    "clip_ratio/low_min": 0.0,
    "clip_ratio/high_mean": 0.0,
    "clip_ratio/high_max": 0.0,
    "clip_ratio/region_mean": 0.0,
    "step_time": 11.530309271000078,
    "epoch": 2.0,
    "step": 30
  },
  {
    "train_runtime": 507.6102,
    "train_samples_per_second": 0.059,
    "train_steps_per_second": 0.059,
    "total_flos": 0.0,
    "train_loss": -0.021817301710446674,
    "epoch": 2.0,
    "step": 30
  }
]