neginr commited on
Commit
2cd7600
·
verified ·
1 Parent(s): 544a837

Training in progress, epoch 4

Browse files
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:09def6feb79a1e6d6113edb03a685904e388c79fb14fab73a7db54784df22af6
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5214c8173246e8fec9495175291cdc859430b4daafd0890d022dcea0b75743e
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7488ffa0a9c6dd48960ad30dc9dff0ab79e0c8269afdca51f527c65cd64185d8
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7115957fc31cefaf66432f48be4bffbf28903b6924b1db175302b804478dc30
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5b6c5bac7b5666d0a41eef82d46420155355bd9796b15ac9199dcfceecc8b09b
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68bfc7bb81efd63d9a426c70f7fad142ffe9b04a3eb34022859678d3d4f54c27
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:77b2e190931e29eb937915596c9f7744363f75d4da89db9cfba85bea351349a2
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d8365cbd95759ea9fc6070c7abf3f216614c33684b97af07d425ba028c5510e
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -609,3 +609,153 @@
609
  {"current_steps": 609, "total_steps": 760, "loss": 0.4228, "lr": 9.24045367756401e-06, "epoch": 3.9934426229508198, "percentage": 80.13, "elapsed_time": "17:01:29", "remaining_time": "4:13:16"}
610
  {"current_steps": 610, "total_steps": 760, "loss": 0.4266, "lr": 9.123333963347166e-06, "epoch": 4.0, "percentage": 80.26, "elapsed_time": "17:03:04", "remaining_time": "4:11:34"}
611
  {"current_steps": 611, "total_steps": 760, "loss": 0.3947, "lr": 9.006865603271952e-06, "epoch": 4.00655737704918, "percentage": 80.39, "elapsed_time": "17:06:30", "remaining_time": "4:10:19"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
609
  {"current_steps": 609, "total_steps": 760, "loss": 0.4228, "lr": 9.24045367756401e-06, "epoch": 3.9934426229508198, "percentage": 80.13, "elapsed_time": "17:01:29", "remaining_time": "4:13:16"}
610
  {"current_steps": 610, "total_steps": 760, "loss": 0.4266, "lr": 9.123333963347166e-06, "epoch": 4.0, "percentage": 80.26, "elapsed_time": "17:03:04", "remaining_time": "4:11:34"}
611
  {"current_steps": 611, "total_steps": 760, "loss": 0.3947, "lr": 9.006865603271952e-06, "epoch": 4.00655737704918, "percentage": 80.39, "elapsed_time": "17:06:30", "remaining_time": "4:10:19"}
612
+ {"current_steps": 612, "total_steps": 760, "loss": 0.3972, "lr": 8.89105105427945e-06, "epoch": 4.0131147540983605, "percentage": 80.53, "elapsed_time": "17:08:09", "remaining_time": "4:08:38"}
613
+ {"current_steps": 613, "total_steps": 760, "loss": 0.3949, "lr": 8.775892759518321e-06, "epoch": 4.019672131147541, "percentage": 80.66, "elapsed_time": "17:09:49", "remaining_time": "4:06:57"}
614
+ {"current_steps": 614, "total_steps": 760, "loss": 0.3921, "lr": 8.661393148293355e-06, "epoch": 4.026229508196721, "percentage": 80.79, "elapsed_time": "17:11:29", "remaining_time": "4:05:16"}
615
+ {"current_steps": 615, "total_steps": 760, "loss": 0.3969, "lr": 8.547554636014177e-06, "epoch": 4.032786885245901, "percentage": 80.92, "elapsed_time": "17:13:09", "remaining_time": "4:03:35"}
616
+ {"current_steps": 616, "total_steps": 760, "loss": 0.3917, "lr": 8.434379624144261e-06, "epoch": 4.039344262295082, "percentage": 81.05, "elapsed_time": "17:14:48", "remaining_time": "4:01:54"}
617
+ {"current_steps": 617, "total_steps": 760, "loss": 0.3945, "lr": 8.321870500150347e-06, "epoch": 4.045901639344263, "percentage": 81.18, "elapsed_time": "17:16:28", "remaining_time": "4:00:13"}
618
+ {"current_steps": 618, "total_steps": 760, "loss": 0.393, "lr": 8.210029637452016e-06, "epoch": 4.052459016393443, "percentage": 81.32, "elapsed_time": "17:18:08", "remaining_time": "3:58:32"}
619
+ {"current_steps": 619, "total_steps": 760, "loss": 0.3921, "lr": 8.098859395371641e-06, "epoch": 4.059016393442623, "percentage": 81.45, "elapsed_time": "17:19:48", "remaining_time": "3:56:51"}
620
+ {"current_steps": 620, "total_steps": 760, "loss": 0.3975, "lr": 7.988362119084642e-06, "epoch": 4.065573770491803, "percentage": 81.58, "elapsed_time": "17:21:28", "remaining_time": "3:55:10"}
621
+ {"current_steps": 621, "total_steps": 760, "loss": 0.4002, "lr": 7.87854013956994e-06, "epoch": 4.072131147540984, "percentage": 81.71, "elapsed_time": "17:23:08", "remaining_time": "3:53:29"}
622
+ {"current_steps": 622, "total_steps": 760, "loss": 0.3881, "lr": 7.769395773560874e-06, "epoch": 4.078688524590164, "percentage": 81.84, "elapsed_time": "17:24:48", "remaining_time": "3:51:48"}
623
+ {"current_steps": 623, "total_steps": 760, "loss": 0.3894, "lr": 7.660931323496283e-06, "epoch": 4.085245901639344, "percentage": 81.97, "elapsed_time": "17:26:29", "remaining_time": "3:50:07"}
624
+ {"current_steps": 624, "total_steps": 760, "loss": 0.3936, "lr": 7.553149077471915e-06, "epoch": 4.091803278688524, "percentage": 82.11, "elapsed_time": "17:28:09", "remaining_time": "3:48:26"}
625
+ {"current_steps": 625, "total_steps": 760, "loss": 0.388, "lr": 7.446051309192204e-06, "epoch": 4.098360655737705, "percentage": 82.24, "elapsed_time": "17:29:51", "remaining_time": "3:46:46"}
626
+ {"current_steps": 626, "total_steps": 760, "loss": 0.3921, "lr": 7.3396402779222845e-06, "epoch": 4.104918032786885, "percentage": 82.37, "elapsed_time": "17:31:30", "remaining_time": "3:45:05"}
627
+ {"current_steps": 627, "total_steps": 760, "loss": 0.3905, "lr": 7.233918228440324e-06, "epoch": 4.111475409836066, "percentage": 82.5, "elapsed_time": "17:33:10", "remaining_time": "3:43:24"}
628
+ {"current_steps": 628, "total_steps": 760, "loss": 0.3961, "lr": 7.128887390990198e-06, "epoch": 4.118032786885246, "percentage": 82.63, "elapsed_time": "17:34:50", "remaining_time": "3:41:43"}
629
+ {"current_steps": 629, "total_steps": 760, "loss": 0.3947, "lr": 7.024549981234377e-06, "epoch": 4.1245901639344265, "percentage": 82.76, "elapsed_time": "17:36:29", "remaining_time": "3:40:01"}
630
+ {"current_steps": 630, "total_steps": 760, "loss": 0.3886, "lr": 6.9209082002072725e-06, "epoch": 4.131147540983607, "percentage": 82.89, "elapsed_time": "17:38:09", "remaining_time": "3:38:21"}
631
+ {"current_steps": 631, "total_steps": 760, "loss": 0.3867, "lr": 6.817964234268748e-06, "epoch": 4.137704918032787, "percentage": 83.03, "elapsed_time": "17:39:49", "remaining_time": "3:36:40"}
632
+ {"current_steps": 632, "total_steps": 760, "loss": 0.3847, "lr": 6.715720255058e-06, "epoch": 4.144262295081967, "percentage": 83.16, "elapsed_time": "17:41:28", "remaining_time": "3:34:59"}
633
+ {"current_steps": 633, "total_steps": 760, "loss": 0.3974, "lr": 6.614178419447781e-06, "epoch": 4.150819672131147, "percentage": 83.29, "elapsed_time": "17:43:10", "remaining_time": "3:33:18"}
634
+ {"current_steps": 634, "total_steps": 760, "loss": 0.397, "lr": 6.513340869498859e-06, "epoch": 4.157377049180328, "percentage": 83.42, "elapsed_time": "17:44:49", "remaining_time": "3:31:37"}
635
+ {"current_steps": 635, "total_steps": 760, "loss": 0.3931, "lr": 6.4132097324148556e-06, "epoch": 4.163934426229508, "percentage": 83.55, "elapsed_time": "17:46:29", "remaining_time": "3:29:56"}
636
+ {"current_steps": 636, "total_steps": 760, "loss": 0.389, "lr": 6.313787120497376e-06, "epoch": 4.170491803278688, "percentage": 83.68, "elapsed_time": "17:48:09", "remaining_time": "3:28:15"}
637
+ {"current_steps": 637, "total_steps": 760, "loss": 0.3956, "lr": 6.215075131101405e-06, "epoch": 4.177049180327868, "percentage": 83.82, "elapsed_time": "17:49:48", "remaining_time": "3:26:34"}
638
+ {"current_steps": 638, "total_steps": 760, "loss": 0.3968, "lr": 6.117075846591123e-06, "epoch": 4.18360655737705, "percentage": 83.95, "elapsed_time": "17:51:28", "remaining_time": "3:24:53"}
639
+ {"current_steps": 639, "total_steps": 760, "loss": 0.393, "lr": 6.019791334295955e-06, "epoch": 4.19016393442623, "percentage": 84.08, "elapsed_time": "17:53:07", "remaining_time": "3:23:12"}
640
+ {"current_steps": 640, "total_steps": 760, "loss": 0.3942, "lr": 5.923223646466923e-06, "epoch": 4.19672131147541, "percentage": 84.21, "elapsed_time": "17:54:47", "remaining_time": "3:21:31"}
641
+ {"current_steps": 641, "total_steps": 760, "loss": 0.3967, "lr": 5.827374820233407e-06, "epoch": 4.20327868852459, "percentage": 84.34, "elapsed_time": "17:56:27", "remaining_time": "3:19:50"}
642
+ {"current_steps": 642, "total_steps": 760, "loss": 0.394, "lr": 5.732246877560146e-06, "epoch": 4.2098360655737705, "percentage": 84.47, "elapsed_time": "17:58:06", "remaining_time": "3:18:09"}
643
+ {"current_steps": 643, "total_steps": 760, "loss": 0.3924, "lr": 5.637841825204588e-06, "epoch": 4.216393442622951, "percentage": 84.61, "elapsed_time": "17:59:46", "remaining_time": "3:16:28"}
644
+ {"current_steps": 644, "total_steps": 760, "loss": 0.394, "lr": 5.5441616546745646e-06, "epoch": 4.222950819672131, "percentage": 84.74, "elapsed_time": "18:01:27", "remaining_time": "3:14:47"}
645
+ {"current_steps": 645, "total_steps": 760, "loss": 0.3979, "lr": 5.451208342186229e-06, "epoch": 4.229508196721311, "percentage": 84.87, "elapsed_time": "18:03:07", "remaining_time": "3:13:06"}
646
+ {"current_steps": 646, "total_steps": 760, "loss": 0.3887, "lr": 5.358983848622452e-06, "epoch": 4.2360655737704915, "percentage": 85.0, "elapsed_time": "18:04:46", "remaining_time": "3:11:25"}
647
+ {"current_steps": 647, "total_steps": 760, "loss": 0.3969, "lr": 5.26749011949141e-06, "epoch": 4.242622950819672, "percentage": 85.13, "elapsed_time": "18:06:26", "remaining_time": "3:09:44"}
648
+ {"current_steps": 648, "total_steps": 760, "loss": 0.4017, "lr": 5.176729084885508e-06, "epoch": 4.249180327868853, "percentage": 85.26, "elapsed_time": "18:08:05", "remaining_time": "3:08:03"}
649
+ {"current_steps": 649, "total_steps": 760, "loss": 0.3927, "lr": 5.086702659440743e-06, "epoch": 4.255737704918033, "percentage": 85.39, "elapsed_time": "18:09:45", "remaining_time": "3:06:23"}
650
+ {"current_steps": 650, "total_steps": 760, "loss": 0.3848, "lr": 4.99741274229625e-06, "epoch": 4.262295081967213, "percentage": 85.53, "elapsed_time": "18:11:25", "remaining_time": "3:04:42"}
651
+ {"current_steps": 651, "total_steps": 760, "loss": 0.3924, "lr": 4.908861217054281e-06, "epoch": 4.268852459016394, "percentage": 85.66, "elapsed_time": "18:13:05", "remaining_time": "3:03:01"}
652
+ {"current_steps": 652, "total_steps": 760, "loss": 0.3935, "lr": 4.821049951740442e-06, "epoch": 4.275409836065574, "percentage": 85.79, "elapsed_time": "18:14:47", "remaining_time": "3:01:20"}
653
+ {"current_steps": 653, "total_steps": 760, "loss": 0.3887, "lr": 4.733980798764273e-06, "epoch": 4.281967213114754, "percentage": 85.92, "elapsed_time": "18:16:27", "remaining_time": "2:59:39"}
654
+ {"current_steps": 654, "total_steps": 760, "loss": 0.3943, "lr": 4.647655594880225e-06, "epoch": 4.288524590163934, "percentage": 86.05, "elapsed_time": "18:18:07", "remaining_time": "2:57:59"}
655
+ {"current_steps": 655, "total_steps": 760, "loss": 0.3914, "lr": 4.562076161148881e-06, "epoch": 4.295081967213115, "percentage": 86.18, "elapsed_time": "18:19:47", "remaining_time": "2:56:18"}
656
+ {"current_steps": 656, "total_steps": 760, "loss": 0.3912, "lr": 4.4772443028985004e-06, "epoch": 4.301639344262295, "percentage": 86.32, "elapsed_time": "18:21:26", "remaining_time": "2:54:37"}
657
+ {"current_steps": 657, "total_steps": 760, "loss": 0.3961, "lr": 4.393161809687021e-06, "epoch": 4.308196721311475, "percentage": 86.45, "elapsed_time": "18:23:06", "remaining_time": "2:52:56"}
658
+ {"current_steps": 658, "total_steps": 760, "loss": 0.3923, "lr": 4.3098304552642385e-06, "epoch": 4.314754098360655, "percentage": 86.58, "elapsed_time": "18:24:46", "remaining_time": "2:51:15"}
659
+ {"current_steps": 659, "total_steps": 760, "loss": 0.3961, "lr": 4.227251997534416e-06, "epoch": 4.321311475409836, "percentage": 86.71, "elapsed_time": "18:26:25", "remaining_time": "2:49:34"}
660
+ {"current_steps": 660, "total_steps": 760, "loss": 0.3866, "lr": 4.1454281785191995e-06, "epoch": 4.327868852459017, "percentage": 86.84, "elapsed_time": "18:28:05", "remaining_time": "2:47:53"}
661
+ {"current_steps": 661, "total_steps": 760, "loss": 0.3892, "lr": 4.064360724320846e-06, "epoch": 4.334426229508197, "percentage": 86.97, "elapsed_time": "18:29:45", "remaining_time": "2:46:12"}
662
+ {"current_steps": 662, "total_steps": 760, "loss": 0.3926, "lr": 3.984051345085855e-06, "epoch": 4.340983606557377, "percentage": 87.11, "elapsed_time": "18:31:25", "remaining_time": "2:44:31"}
663
+ {"current_steps": 663, "total_steps": 760, "loss": 0.3939, "lr": 3.90450173496887e-06, "epoch": 4.3475409836065575, "percentage": 87.24, "elapsed_time": "18:33:07", "remaining_time": "2:42:51"}
664
+ {"current_steps": 664, "total_steps": 760, "loss": 0.3874, "lr": 3.825713572096903e-06, "epoch": 4.354098360655738, "percentage": 87.37, "elapsed_time": "18:34:48", "remaining_time": "2:41:10"}
665
+ {"current_steps": 665, "total_steps": 760, "loss": 0.3971, "lr": 3.747688518534003e-06, "epoch": 4.360655737704918, "percentage": 87.5, "elapsed_time": "18:36:29", "remaining_time": "2:39:29"}
666
+ {"current_steps": 666, "total_steps": 760, "loss": 0.3943, "lr": 3.6704282202461515e-06, "epoch": 4.367213114754098, "percentage": 87.63, "elapsed_time": "18:38:10", "remaining_time": "2:37:49"}
667
+ {"current_steps": 667, "total_steps": 760, "loss": 0.3963, "lr": 3.5939343070665243e-06, "epoch": 4.3737704918032785, "percentage": 87.76, "elapsed_time": "18:39:49", "remaining_time": "2:36:08"}
668
+ {"current_steps": 668, "total_steps": 760, "loss": 0.3889, "lr": 3.518208392661184e-06, "epoch": 4.380327868852459, "percentage": 87.89, "elapsed_time": "18:41:31", "remaining_time": "2:34:27"}
669
+ {"current_steps": 669, "total_steps": 760, "loss": 0.3921, "lr": 3.4432520744949317e-06, "epoch": 4.386885245901639, "percentage": 88.03, "elapsed_time": "18:43:10", "remaining_time": "2:32:46"}
670
+ {"current_steps": 670, "total_steps": 760, "loss": 0.3906, "lr": 3.3690669337977e-06, "epoch": 4.39344262295082, "percentage": 88.16, "elapsed_time": "18:44:49", "remaining_time": "2:31:05"}
671
+ {"current_steps": 671, "total_steps": 760, "loss": 0.3886, "lr": 3.295654535531161e-06, "epoch": 4.4, "percentage": 88.29, "elapsed_time": "18:46:29", "remaining_time": "2:29:24"}
672
+ {"current_steps": 672, "total_steps": 760, "loss": 0.3923, "lr": 3.2230164283556918e-06, "epoch": 4.406557377049181, "percentage": 88.42, "elapsed_time": "18:48:09", "remaining_time": "2:27:44"}
673
+ {"current_steps": 673, "total_steps": 760, "loss": 0.3935, "lr": 3.151154144597741e-06, "epoch": 4.413114754098361, "percentage": 88.55, "elapsed_time": "18:49:49", "remaining_time": "2:26:03"}
674
+ {"current_steps": 674, "total_steps": 760, "loss": 0.3935, "lr": 3.080069200217497e-06, "epoch": 4.419672131147541, "percentage": 88.68, "elapsed_time": "18:51:28", "remaining_time": "2:24:22"}
675
+ {"current_steps": 675, "total_steps": 760, "loss": 0.397, "lr": 3.0097630947768695e-06, "epoch": 4.426229508196721, "percentage": 88.82, "elapsed_time": "18:53:07", "remaining_time": "2:22:41"}
676
+ {"current_steps": 676, "total_steps": 760, "loss": 0.3938, "lr": 2.9402373114079295e-06, "epoch": 4.432786885245902, "percentage": 88.95, "elapsed_time": "18:54:49", "remaining_time": "2:21:00"}
677
+ {"current_steps": 677, "total_steps": 760, "loss": 0.393, "lr": 2.871493316781546e-06, "epoch": 4.439344262295082, "percentage": 89.08, "elapsed_time": "18:56:29", "remaining_time": "2:19:20"}
678
+ {"current_steps": 678, "total_steps": 760, "loss": 0.3944, "lr": 2.803532561076492e-06, "epoch": 4.445901639344262, "percentage": 89.21, "elapsed_time": "18:58:09", "remaining_time": "2:17:39"}
679
+ {"current_steps": 679, "total_steps": 760, "loss": 0.3963, "lr": 2.7363564779488448e-06, "epoch": 4.452459016393442, "percentage": 89.34, "elapsed_time": "18:59:49", "remaining_time": "2:15:58"}
680
+ {"current_steps": 680, "total_steps": 760, "loss": 0.3911, "lr": 2.669966484501716e-06, "epoch": 4.459016393442623, "percentage": 89.47, "elapsed_time": "19:01:28", "remaining_time": "2:14:17"}
681
+ {"current_steps": 681, "total_steps": 760, "loss": 0.3932, "lr": 2.6043639812554043e-06, "epoch": 4.465573770491803, "percentage": 89.61, "elapsed_time": "19:03:08", "remaining_time": "2:12:36"}
682
+ {"current_steps": 682, "total_steps": 760, "loss": 0.393, "lr": 2.5395503521178143e-06, "epoch": 4.472131147540984, "percentage": 89.74, "elapsed_time": "19:04:47", "remaining_time": "2:10:55"}
683
+ {"current_steps": 683, "total_steps": 760, "loss": 0.3925, "lr": 2.4755269643552594e-06, "epoch": 4.478688524590164, "percentage": 89.87, "elapsed_time": "19:06:27", "remaining_time": "2:09:14"}
684
+ {"current_steps": 684, "total_steps": 760, "loss": 0.3972, "lr": 2.4122951685636674e-06, "epoch": 4.4852459016393444, "percentage": 90.0, "elapsed_time": "19:08:06", "remaining_time": "2:07:34"}
685
+ {"current_steps": 685, "total_steps": 760, "loss": 0.392, "lr": 2.3498562986400187e-06, "epoch": 4.491803278688525, "percentage": 90.13, "elapsed_time": "19:09:46", "remaining_time": "2:05:53"}
686
+ {"current_steps": 686, "total_steps": 760, "loss": 0.3961, "lr": 2.2882116717542634e-06, "epoch": 4.498360655737705, "percentage": 90.26, "elapsed_time": "19:11:25", "remaining_time": "2:04:12"}
687
+ {"current_steps": 687, "total_steps": 760, "loss": 0.3936, "lr": 2.22736258832152e-06, "epoch": 4.504918032786885, "percentage": 90.39, "elapsed_time": "19:13:06", "remaining_time": "2:02:31"}
688
+ {"current_steps": 688, "total_steps": 760, "loss": 0.3875, "lr": 2.1673103319746146e-06, "epoch": 4.511475409836065, "percentage": 90.53, "elapsed_time": "19:14:46", "remaining_time": "2:00:50"}
689
+ {"current_steps": 689, "total_steps": 760, "loss": 0.3972, "lr": 2.1080561695370425e-06, "epoch": 4.518032786885246, "percentage": 90.66, "elapsed_time": "19:16:25", "remaining_time": "1:59:10"}
690
+ {"current_steps": 690, "total_steps": 760, "loss": 0.3896, "lr": 2.049601350996233e-06, "epoch": 4.524590163934426, "percentage": 90.79, "elapsed_time": "19:18:05", "remaining_time": "1:57:29"}
691
+ {"current_steps": 691, "total_steps": 760, "loss": 0.3917, "lr": 1.9919471094771523e-06, "epoch": 4.531147540983606, "percentage": 90.92, "elapsed_time": "19:19:44", "remaining_time": "1:55:48"}
692
+ {"current_steps": 692, "total_steps": 760, "loss": 0.3904, "lr": 1.93509466121633e-06, "epoch": 4.537704918032787, "percentage": 91.05, "elapsed_time": "19:21:24", "remaining_time": "1:54:07"}
693
+ {"current_steps": 693, "total_steps": 760, "loss": 0.3973, "lr": 1.8790452055361764e-06, "epoch": 4.5442622950819676, "percentage": 91.18, "elapsed_time": "19:23:03", "remaining_time": "1:52:26"}
694
+ {"current_steps": 694, "total_steps": 760, "loss": 0.4002, "lr": 1.8237999248197002e-06, "epoch": 4.550819672131148, "percentage": 91.32, "elapsed_time": "19:24:42", "remaining_time": "1:50:45"}
695
+ {"current_steps": 695, "total_steps": 760, "loss": 0.4013, "lr": 1.7693599844855568e-06, "epoch": 4.557377049180328, "percentage": 91.45, "elapsed_time": "19:26:22", "remaining_time": "1:49:05"}
696
+ {"current_steps": 696, "total_steps": 760, "loss": 0.3943, "lr": 1.7157265329634354e-06, "epoch": 4.563934426229508, "percentage": 91.58, "elapsed_time": "19:28:02", "remaining_time": "1:47:24"}
697
+ {"current_steps": 697, "total_steps": 760, "loss": 0.3902, "lr": 1.6629007016698918e-06, "epoch": 4.5704918032786885, "percentage": 91.71, "elapsed_time": "19:29:41", "remaining_time": "1:45:43"}
698
+ {"current_steps": 698, "total_steps": 760, "loss": 0.3935, "lr": 1.6108836049844434e-06, "epoch": 4.577049180327869, "percentage": 91.84, "elapsed_time": "19:31:22", "remaining_time": "1:44:02"}
699
+ {"current_steps": 699, "total_steps": 760, "loss": 0.3932, "lr": 1.5596763402260462e-06, "epoch": 4.583606557377049, "percentage": 91.97, "elapsed_time": "19:33:03", "remaining_time": "1:42:22"}
700
+ {"current_steps": 700, "total_steps": 760, "loss": 0.3979, "lr": 1.5092799876299835e-06, "epoch": 4.590163934426229, "percentage": 92.11, "elapsed_time": "19:34:44", "remaining_time": "1:40:41"}
701
+ {"current_steps": 701, "total_steps": 760, "loss": 0.3975, "lr": 1.459695610325067e-06, "epoch": 4.5967213114754095, "percentage": 92.24, "elapsed_time": "19:36:24", "remaining_time": "1:39:00"}
702
+ {"current_steps": 702, "total_steps": 760, "loss": 0.3917, "lr": 1.4109242543111834e-06, "epoch": 4.60327868852459, "percentage": 92.37, "elapsed_time": "19:38:05", "remaining_time": "1:37:20"}
703
+ {"current_steps": 703, "total_steps": 760, "loss": 0.3922, "lr": 1.3629669484372722e-06, "epoch": 4.60983606557377, "percentage": 92.5, "elapsed_time": "19:39:47", "remaining_time": "1:35:39"}
704
+ {"current_steps": 704, "total_steps": 760, "loss": 0.3915, "lr": 1.3158247043795735e-06, "epoch": 4.616393442622951, "percentage": 92.63, "elapsed_time": "19:41:29", "remaining_time": "1:33:58"}
705
+ {"current_steps": 705, "total_steps": 760, "loss": 0.3948, "lr": 1.2694985166203311e-06, "epoch": 4.622950819672131, "percentage": 92.76, "elapsed_time": "19:43:10", "remaining_time": "1:32:18"}
706
+ {"current_steps": 706, "total_steps": 760, "loss": 0.3946, "lr": 1.2239893624267852e-06, "epoch": 4.629508196721312, "percentage": 92.89, "elapsed_time": "19:44:50", "remaining_time": "1:30:37"}
707
+ {"current_steps": 707, "total_steps": 760, "loss": 0.3922, "lr": 1.1792982018305677e-06, "epoch": 4.636065573770492, "percentage": 93.03, "elapsed_time": "19:46:31", "remaining_time": "1:28:56"}
708
+ {"current_steps": 708, "total_steps": 760, "loss": 0.3888, "lr": 1.1354259776074472e-06, "epoch": 4.642622950819672, "percentage": 93.16, "elapsed_time": "19:48:11", "remaining_time": "1:27:16"}
709
+ {"current_steps": 709, "total_steps": 760, "loss": 0.3993, "lr": 1.0923736152574428e-06, "epoch": 4.649180327868852, "percentage": 93.29, "elapsed_time": "19:49:50", "remaining_time": "1:25:35"}
710
+ {"current_steps": 710, "total_steps": 760, "loss": 0.3914, "lr": 1.050142022985292e-06, "epoch": 4.655737704918033, "percentage": 93.42, "elapsed_time": "19:51:30", "remaining_time": "1:23:54"}
711
+ {"current_steps": 711, "total_steps": 760, "loss": 0.3925, "lr": 1.0087320916813127e-06, "epoch": 4.662295081967213, "percentage": 93.55, "elapsed_time": "19:53:11", "remaining_time": "1:22:13"}
712
+ {"current_steps": 712, "total_steps": 760, "loss": 0.4015, "lr": 9.681446949025752e-07, "epoch": 4.668852459016393, "percentage": 93.68, "elapsed_time": "19:54:52", "remaining_time": "1:20:33"}
713
+ {"current_steps": 713, "total_steps": 760, "loss": 0.3953, "lr": 9.283806888545111e-07, "epoch": 4.675409836065574, "percentage": 93.82, "elapsed_time": "19:56:32", "remaining_time": "1:18:52"}
714
+ {"current_steps": 714, "total_steps": 760, "loss": 0.3999, "lr": 8.89440912372832e-07, "epoch": 4.6819672131147545, "percentage": 93.95, "elapsed_time": "19:58:12", "remaining_time": "1:17:11"}
715
+ {"current_steps": 715, "total_steps": 760, "loss": 0.3942, "lr": 8.513261869058209e-07, "epoch": 4.688524590163935, "percentage": 94.08, "elapsed_time": "19:59:52", "remaining_time": "1:15:30"}
716
+ {"current_steps": 716, "total_steps": 760, "loss": 0.3924, "lr": 8.140373164970428e-07, "epoch": 4.695081967213115, "percentage": 94.21, "elapsed_time": "20:01:33", "remaining_time": "1:13:50"}
717
+ {"current_steps": 717, "total_steps": 760, "loss": 0.3961, "lr": 7.775750877683452e-07, "epoch": 4.701639344262295, "percentage": 94.34, "elapsed_time": "20:03:13", "remaining_time": "1:12:09"}
718
+ {"current_steps": 718, "total_steps": 760, "loss": 0.3934, "lr": 7.419402699032852e-07, "epoch": 4.7081967213114755, "percentage": 94.47, "elapsed_time": "20:04:53", "remaining_time": "1:10:28"}
719
+ {"current_steps": 719, "total_steps": 760, "loss": 0.3826, "lr": 7.071336146308883e-07, "epoch": 4.714754098360656, "percentage": 94.61, "elapsed_time": "20:06:33", "remaining_time": "1:08:48"}
720
+ {"current_steps": 720, "total_steps": 760, "loss": 0.3908, "lr": 6.731558562097995e-07, "epoch": 4.721311475409836, "percentage": 94.74, "elapsed_time": "20:08:12", "remaining_time": "1:07:07"}
721
+ {"current_steps": 721, "total_steps": 760, "loss": 0.3933, "lr": 6.400077114128023e-07, "epoch": 4.727868852459016, "percentage": 94.87, "elapsed_time": "20:09:52", "remaining_time": "1:05:26"}
722
+ {"current_steps": 722, "total_steps": 760, "loss": 0.3965, "lr": 6.076898795116792e-07, "epoch": 4.7344262295081965, "percentage": 95.0, "elapsed_time": "20:11:31", "remaining_time": "1:03:45"}
723
+ {"current_steps": 723, "total_steps": 760, "loss": 0.3894, "lr": 5.762030422624732e-07, "epoch": 4.740983606557377, "percentage": 95.13, "elapsed_time": "20:13:11", "remaining_time": "1:02:05"}
724
+ {"current_steps": 724, "total_steps": 760, "loss": 0.396, "lr": 5.455478638911071e-07, "epoch": 4.747540983606557, "percentage": 95.26, "elapsed_time": "20:14:52", "remaining_time": "1:00:24"}
725
+ {"current_steps": 725, "total_steps": 760, "loss": 0.394, "lr": 5.15724991079356e-07, "epoch": 4.754098360655737, "percentage": 95.39, "elapsed_time": "20:16:32", "remaining_time": "0:58:43"}
726
+ {"current_steps": 726, "total_steps": 760, "loss": 0.3946, "lr": 4.867350529512261e-07, "epoch": 4.760655737704918, "percentage": 95.53, "elapsed_time": "20:18:12", "remaining_time": "0:57:03"}
727
+ {"current_steps": 727, "total_steps": 760, "loss": 0.3903, "lr": 4.5857866105966763e-07, "epoch": 4.767213114754099, "percentage": 95.66, "elapsed_time": "20:19:52", "remaining_time": "0:55:22"}
728
+ {"current_steps": 728, "total_steps": 760, "loss": 0.3886, "lr": 4.3125640937368373e-07, "epoch": 4.773770491803279, "percentage": 95.79, "elapsed_time": "20:21:31", "remaining_time": "0:53:41"}
729
+ {"current_steps": 729, "total_steps": 760, "loss": 0.3999, "lr": 4.047688742657885e-07, "epoch": 4.780327868852459, "percentage": 95.92, "elapsed_time": "20:23:11", "remaining_time": "0:52:00"}
730
+ {"current_steps": 730, "total_steps": 760, "loss": 0.3925, "lr": 3.791166144998704e-07, "epoch": 4.786885245901639, "percentage": 96.05, "elapsed_time": "20:24:51", "remaining_time": "0:50:20"}
731
+ {"current_steps": 731, "total_steps": 760, "loss": 0.3943, "lr": 3.54300171219375e-07, "epoch": 4.79344262295082, "percentage": 96.18, "elapsed_time": "20:26:31", "remaining_time": "0:48:39"}
732
+ {"current_steps": 732, "total_steps": 760, "loss": 0.3937, "lr": 3.3032006793590977e-07, "epoch": 4.8, "percentage": 96.32, "elapsed_time": "20:28:11", "remaining_time": "0:46:58"}
733
+ {"current_steps": 733, "total_steps": 760, "loss": 0.3971, "lr": 3.0717681051819935e-07, "epoch": 4.80655737704918, "percentage": 96.45, "elapsed_time": "20:29:51", "remaining_time": "0:45:18"}
734
+ {"current_steps": 734, "total_steps": 760, "loss": 0.3975, "lr": 2.848708871814054e-07, "epoch": 4.81311475409836, "percentage": 96.58, "elapsed_time": "20:31:30", "remaining_time": "0:43:37"}
735
+ {"current_steps": 735, "total_steps": 760, "loss": 0.3977, "lr": 2.634027684768414e-07, "epoch": 4.8196721311475414, "percentage": 96.71, "elapsed_time": "20:33:11", "remaining_time": "0:41:56"}
736
+ {"current_steps": 736, "total_steps": 760, "loss": 0.3942, "lr": 2.4277290728202063e-07, "epoch": 4.826229508196722, "percentage": 96.84, "elapsed_time": "20:34:50", "remaining_time": "0:40:16"}
737
+ {"current_steps": 737, "total_steps": 760, "loss": 0.388, "lr": 2.2298173879113481e-07, "epoch": 4.832786885245902, "percentage": 96.97, "elapsed_time": "20:36:30", "remaining_time": "0:38:35"}
738
+ {"current_steps": 738, "total_steps": 760, "loss": 0.3938, "lr": 2.040296805058528e-07, "epoch": 4.839344262295082, "percentage": 97.11, "elapsed_time": "20:38:10", "remaining_time": "0:36:54"}
739
+ {"current_steps": 739, "total_steps": 760, "loss": 0.3933, "lr": 1.859171322265141e-07, "epoch": 4.845901639344262, "percentage": 97.24, "elapsed_time": "20:39:50", "remaining_time": "0:35:13"}
740
+ {"current_steps": 740, "total_steps": 760, "loss": 0.3948, "lr": 1.6864447604370004e-07, "epoch": 4.852459016393443, "percentage": 97.37, "elapsed_time": "20:41:31", "remaining_time": "0:33:33"}
741
+ {"current_steps": 741, "total_steps": 760, "loss": 0.3854, "lr": 1.522120763301782e-07, "epoch": 4.859016393442623, "percentage": 97.5, "elapsed_time": "20:43:12", "remaining_time": "0:31:52"}
742
+ {"current_steps": 742, "total_steps": 760, "loss": 0.3922, "lr": 1.3662027973320614e-07, "epoch": 4.865573770491803, "percentage": 97.63, "elapsed_time": "20:44:52", "remaining_time": "0:30:11"}
743
+ {"current_steps": 743, "total_steps": 760, "loss": 0.3921, "lr": 1.2186941516722173e-07, "epoch": 4.872131147540983, "percentage": 97.76, "elapsed_time": "20:46:33", "remaining_time": "0:28:31"}
744
+ {"current_steps": 744, "total_steps": 760, "loss": 0.3951, "lr": 1.0795979380690657e-07, "epoch": 4.878688524590164, "percentage": 97.89, "elapsed_time": "20:48:14", "remaining_time": "0:26:50"}
745
+ {"current_steps": 745, "total_steps": 760, "loss": 0.3862, "lr": 9.489170908062228e-08, "epoch": 4.885245901639344, "percentage": 98.03, "elapsed_time": "20:49:54", "remaining_time": "0:25:09"}
746
+ {"current_steps": 746, "total_steps": 760, "loss": 0.3926, "lr": 8.266543666421544e-08, "epoch": 4.891803278688524, "percentage": 98.16, "elapsed_time": "20:51:33", "remaining_time": "0:23:29"}
747
+ {"current_steps": 747, "total_steps": 760, "loss": 0.3931, "lr": 7.128123447520452e-08, "epoch": 4.898360655737705, "percentage": 98.29, "elapsed_time": "20:53:12", "remaining_time": "0:21:48"}
748
+ {"current_steps": 748, "total_steps": 760, "loss": 0.3915, "lr": 6.073934266735303e-08, "epoch": 4.9049180327868855, "percentage": 98.42, "elapsed_time": "20:54:52", "remaining_time": "0:20:07"}
749
+ {"current_steps": 749, "total_steps": 760, "loss": 0.3911, "lr": 5.10399836255715e-08, "epoch": 4.911475409836066, "percentage": 98.55, "elapsed_time": "20:56:32", "remaining_time": "0:18:27"}
750
+ {"current_steps": 750, "total_steps": 760, "loss": 0.392, "lr": 4.218336196125439e-08, "epoch": 4.918032786885246, "percentage": 98.68, "elapsed_time": "20:58:11", "remaining_time": "0:16:46"}
751
+ {"current_steps": 751, "total_steps": 760, "loss": 0.397, "lr": 3.416966450795922e-08, "epoch": 4.924590163934426, "percentage": 98.82, "elapsed_time": "20:59:52", "remaining_time": "0:15:05"}
752
+ {"current_steps": 752, "total_steps": 760, "loss": 0.3909, "lr": 2.699906031745414e-08, "epoch": 4.9311475409836065, "percentage": 98.95, "elapsed_time": "21:01:31", "remaining_time": "0:13:25"}
753
+ {"current_steps": 753, "total_steps": 760, "loss": 0.3907, "lr": 2.067170065615187e-08, "epoch": 4.937704918032787, "percentage": 99.08, "elapsed_time": "21:03:11", "remaining_time": "0:11:44"}
754
+ {"current_steps": 754, "total_steps": 760, "loss": 0.3957, "lr": 1.5187719001943378e-08, "epoch": 4.944262295081967, "percentage": 99.21, "elapsed_time": "21:04:50", "remaining_time": "0:10:03"}
755
+ {"current_steps": 755, "total_steps": 760, "loss": 0.3926, "lr": 1.0547231041346806e-08, "epoch": 4.950819672131147, "percentage": 99.34, "elapsed_time": "21:06:32", "remaining_time": "0:08:23"}
756
+ {"current_steps": 756, "total_steps": 760, "loss": 0.3833, "lr": 6.750334667091629e-09, "epoch": 4.9573770491803275, "percentage": 99.47, "elapsed_time": "21:08:17", "remaining_time": "0:06:42"}
757
+ {"current_steps": 757, "total_steps": 760, "loss": 0.3949, "lr": 3.797109976035884e-09, "epoch": 4.963934426229509, "percentage": 99.61, "elapsed_time": "21:10:02", "remaining_time": "0:05:01"}
758
+ {"current_steps": 758, "total_steps": 760, "loss": 0.3927, "lr": 1.6876192675052695e-09, "epoch": 4.970491803278689, "percentage": 99.74, "elapsed_time": "21:11:43", "remaining_time": "0:03:21"}
759
+ {"current_steps": 759, "total_steps": 760, "loss": 0.3991, "lr": 4.219070419475557e-10, "epoch": 4.977049180327869, "percentage": 99.87, "elapsed_time": "21:13:23", "remaining_time": "0:01:40"}
760
+ {"current_steps": 760, "total_steps": 760, "loss": 0.392, "lr": 0.0, "epoch": 4.983606557377049, "percentage": 100.0, "elapsed_time": "21:15:03", "remaining_time": "0:00:00"}
761
+ {"current_steps": 760, "total_steps": 760, "epoch": 4.983606557377049, "percentage": 100.0, "elapsed_time": "21:17:58", "remaining_time": "0:00:00"}