neginr commited on
Commit
52999e8
·
verified ·
1 Parent(s): a75ac44

Training in progress, epoch 2

Browse files
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:159ba2d8e72acd528e87e4c80eb50ad7b1b237f0009531e79b0515766fda90fe
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4ba1af9d76095f050462021a355b86ba9dcb009ee8588e4c92fe878276f53eb
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:a1fed7f39ec8f1e6d7a3a27d99b92c4b779838cc9e73eade90e0e1a209ea0d6c
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3268362a4e64f8e57c9ea72150e1a4529784fc051a8c9efca8a39f3832020995
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:74a68be8ce806e3968bd38ee227427ee117d4666a2c9310e0702a8c602c188c5
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b9ad0e325f599a0c8cb5bda26c07a48d7ab2bba3a15887b49374d1f0c539cd5
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:733686fe6428c9a53fff096f0d9b80a912eda0f233cbbf9ce18d8c3ea087f3f7
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c202f72532dab20e1f21d6561a1bc6be610aeae860b5611167956d38df660b78
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -502,3 +502,250 @@
502
  {"current_steps": 502, "total_steps": 1230, "loss": 1.0316, "lr": 2.9504494771068334e-05, "epoch": 2.0334177215189873, "percentage": 40.81, "elapsed_time": "1:46:04", "remaining_time": "2:33:49"}
503
  {"current_steps": 503, "total_steps": 1230, "loss": 1.0244, "lr": 2.9454516623997156e-05, "epoch": 2.0374683544303798, "percentage": 40.89, "elapsed_time": "1:46:15", "remaining_time": "2:33:35"}
504
  {"current_steps": 504, "total_steps": 1230, "loss": 0.9767, "lr": 2.9404462331548847e-05, "epoch": 2.0415189873417723, "percentage": 40.98, "elapsed_time": "1:46:27", "remaining_time": "2:33:21"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
502
  {"current_steps": 502, "total_steps": 1230, "loss": 1.0316, "lr": 2.9504494771068334e-05, "epoch": 2.0334177215189873, "percentage": 40.81, "elapsed_time": "1:46:04", "remaining_time": "2:33:49"}
503
  {"current_steps": 503, "total_steps": 1230, "loss": 1.0244, "lr": 2.9454516623997156e-05, "epoch": 2.0374683544303798, "percentage": 40.89, "elapsed_time": "1:46:15", "remaining_time": "2:33:35"}
504
  {"current_steps": 504, "total_steps": 1230, "loss": 0.9767, "lr": 2.9404462331548847e-05, "epoch": 2.0415189873417723, "percentage": 40.98, "elapsed_time": "1:46:27", "remaining_time": "2:33:21"}
505
+ {"current_steps": 505, "total_steps": 1230, "loss": 0.9979, "lr": 2.93543322968538e-05, "epoch": 2.0455696202531644, "percentage": 41.06, "elapsed_time": "1:46:39", "remaining_time": "2:33:07"}
506
+ {"current_steps": 506, "total_steps": 1230, "loss": 1.0144, "lr": 2.9304126923652428e-05, "epoch": 2.049620253164557, "percentage": 41.14, "elapsed_time": "1:46:51", "remaining_time": "2:32:54"}
507
+ {"current_steps": 507, "total_steps": 1230, "loss": 1.0203, "lr": 2.9253846616291896e-05, "epoch": 2.0536708860759494, "percentage": 41.22, "elapsed_time": "1:47:03", "remaining_time": "2:32:40"}
508
+ {"current_steps": 508, "total_steps": 1230, "loss": 1.01, "lr": 2.9203491779722896e-05, "epoch": 2.057721518987342, "percentage": 41.3, "elapsed_time": "1:47:15", "remaining_time": "2:32:26"}
509
+ {"current_steps": 509, "total_steps": 1230, "loss": 1.0222, "lr": 2.9153062819496357e-05, "epoch": 2.061772151898734, "percentage": 41.38, "elapsed_time": "1:47:27", "remaining_time": "2:32:13"}
510
+ {"current_steps": 510, "total_steps": 1230, "loss": 1.0156, "lr": 2.9102560141760178e-05, "epoch": 2.0658227848101265, "percentage": 41.46, "elapsed_time": "1:47:39", "remaining_time": "2:31:58"}
511
+ {"current_steps": 511, "total_steps": 1230, "loss": 1.0281, "lr": 2.9051984153256004e-05, "epoch": 2.069873417721519, "percentage": 41.54, "elapsed_time": "1:47:51", "remaining_time": "2:31:45"}
512
+ {"current_steps": 512, "total_steps": 1230, "loss": 1.0026, "lr": 2.900133526131588e-05, "epoch": 2.0739240506329115, "percentage": 41.63, "elapsed_time": "1:48:03", "remaining_time": "2:31:31"}
513
+ {"current_steps": 513, "total_steps": 1230, "loss": 1.0188, "lr": 2.8950613873859025e-05, "epoch": 2.0779746835443036, "percentage": 41.71, "elapsed_time": "1:48:14", "remaining_time": "2:31:17"}
514
+ {"current_steps": 514, "total_steps": 1230, "loss": 1.0004, "lr": 2.8899820399388515e-05, "epoch": 2.082025316455696, "percentage": 41.79, "elapsed_time": "1:48:30", "remaining_time": "2:31:08"}
515
+ {"current_steps": 515, "total_steps": 1230, "loss": 1.0083, "lr": 2.8848955246988012e-05, "epoch": 2.0860759493670886, "percentage": 41.87, "elapsed_time": "1:48:41", "remaining_time": "2:30:54"}
516
+ {"current_steps": 516, "total_steps": 1230, "loss": 1.0294, "lr": 2.879801882631847e-05, "epoch": 2.090126582278481, "percentage": 41.95, "elapsed_time": "1:48:53", "remaining_time": "2:30:40"}
517
+ {"current_steps": 517, "total_steps": 1230, "loss": 1.0092, "lr": 2.8747011547614808e-05, "epoch": 2.094177215189873, "percentage": 42.03, "elapsed_time": "1:49:04", "remaining_time": "2:30:25"}
518
+ {"current_steps": 518, "total_steps": 1230, "loss": 1.0197, "lr": 2.8695933821682635e-05, "epoch": 2.0982278481012657, "percentage": 42.11, "elapsed_time": "1:49:16", "remaining_time": "2:30:11"}
519
+ {"current_steps": 519, "total_steps": 1230, "loss": 1.0186, "lr": 2.864478605989494e-05, "epoch": 2.1022784810126582, "percentage": 42.2, "elapsed_time": "1:49:27", "remaining_time": "2:29:57"}
520
+ {"current_steps": 520, "total_steps": 1230, "loss": 1.0343, "lr": 2.8593568674188765e-05, "epoch": 2.1063291139240508, "percentage": 42.28, "elapsed_time": "1:49:40", "remaining_time": "2:29:44"}
521
+ {"current_steps": 521, "total_steps": 1230, "loss": 1.0088, "lr": 2.8542282077061892e-05, "epoch": 2.110379746835443, "percentage": 42.36, "elapsed_time": "1:49:52", "remaining_time": "2:29:31"}
522
+ {"current_steps": 522, "total_steps": 1230, "loss": 1.0144, "lr": 2.8490926681569523e-05, "epoch": 2.1144303797468353, "percentage": 42.44, "elapsed_time": "1:50:03", "remaining_time": "2:29:16"}
523
+ {"current_steps": 523, "total_steps": 1230, "loss": 1.0294, "lr": 2.8439502901320956e-05, "epoch": 2.118481012658228, "percentage": 42.52, "elapsed_time": "1:50:15", "remaining_time": "2:29:02"}
524
+ {"current_steps": 524, "total_steps": 1230, "loss": 0.992, "lr": 2.8388011150476237e-05, "epoch": 2.1225316455696204, "percentage": 42.6, "elapsed_time": "1:50:27", "remaining_time": "2:28:49"}
525
+ {"current_steps": 525, "total_steps": 1230, "loss": 1.0206, "lr": 2.8336451843742866e-05, "epoch": 2.1265822784810124, "percentage": 42.68, "elapsed_time": "1:50:39", "remaining_time": "2:28:36"}
526
+ {"current_steps": 526, "total_steps": 1230, "loss": 1.0401, "lr": 2.8284825396372387e-05, "epoch": 2.130632911392405, "percentage": 42.76, "elapsed_time": "1:50:55", "remaining_time": "2:28:27"}
527
+ {"current_steps": 527, "total_steps": 1230, "loss": 1.0356, "lr": 2.8233132224157132e-05, "epoch": 2.1346835443037975, "percentage": 42.85, "elapsed_time": "1:51:06", "remaining_time": "2:28:13"}
528
+ {"current_steps": 528, "total_steps": 1230, "loss": 1.0133, "lr": 2.8181372743426805e-05, "epoch": 2.13873417721519, "percentage": 42.93, "elapsed_time": "1:51:18", "remaining_time": "2:27:59"}
529
+ {"current_steps": 529, "total_steps": 1230, "loss": 1.0211, "lr": 2.8129547371045128e-05, "epoch": 2.1427848101265825, "percentage": 43.01, "elapsed_time": "1:51:30", "remaining_time": "2:27:45"}
530
+ {"current_steps": 530, "total_steps": 1230, "loss": 1.0138, "lr": 2.8077656524406534e-05, "epoch": 2.1468354430379746, "percentage": 43.09, "elapsed_time": "1:51:41", "remaining_time": "2:27:31"}
531
+ {"current_steps": 531, "total_steps": 1230, "loss": 0.9967, "lr": 2.802570062143278e-05, "epoch": 2.150886075949367, "percentage": 43.17, "elapsed_time": "1:51:53", "remaining_time": "2:27:17"}
532
+ {"current_steps": 532, "total_steps": 1230, "loss": 1.0225, "lr": 2.7973680080569555e-05, "epoch": 2.1549367088607596, "percentage": 43.25, "elapsed_time": "1:52:05", "remaining_time": "2:27:03"}
533
+ {"current_steps": 533, "total_steps": 1230, "loss": 1.0073, "lr": 2.792159532078314e-05, "epoch": 2.1589873417721517, "percentage": 43.33, "elapsed_time": "1:52:18", "remaining_time": "2:26:51"}
534
+ {"current_steps": 534, "total_steps": 1230, "loss": 1.0165, "lr": 2.7869446761557033e-05, "epoch": 2.163037974683544, "percentage": 43.41, "elapsed_time": "1:52:30", "remaining_time": "2:26:38"}
535
+ {"current_steps": 535, "total_steps": 1230, "loss": 1.0297, "lr": 2.781723482288857e-05, "epoch": 2.1670886075949367, "percentage": 43.5, "elapsed_time": "1:52:41", "remaining_time": "2:26:24"}
536
+ {"current_steps": 536, "total_steps": 1230, "loss": 1.0158, "lr": 2.7764959925285517e-05, "epoch": 2.1711392405063292, "percentage": 43.58, "elapsed_time": "1:52:53", "remaining_time": "2:26:10"}
537
+ {"current_steps": 537, "total_steps": 1230, "loss": 1.0102, "lr": 2.771262248976272e-05, "epoch": 2.1751898734177217, "percentage": 43.66, "elapsed_time": "1:53:05", "remaining_time": "2:25:57"}
538
+ {"current_steps": 538, "total_steps": 1230, "loss": 1.0146, "lr": 2.7660222937838677e-05, "epoch": 2.179240506329114, "percentage": 43.74, "elapsed_time": "1:53:17", "remaining_time": "2:25:43"}
539
+ {"current_steps": 539, "total_steps": 1230, "loss": 1.005, "lr": 2.7607761691532186e-05, "epoch": 2.1832911392405063, "percentage": 43.82, "elapsed_time": "1:53:29", "remaining_time": "2:25:29"}
540
+ {"current_steps": 540, "total_steps": 1230, "loss": 1.0039, "lr": 2.7555239173358916e-05, "epoch": 2.187341772151899, "percentage": 43.9, "elapsed_time": "1:53:40", "remaining_time": "2:25:15"}
541
+ {"current_steps": 541, "total_steps": 1230, "loss": 1.0463, "lr": 2.7502655806328e-05, "epoch": 2.191392405063291, "percentage": 43.98, "elapsed_time": "1:53:53", "remaining_time": "2:25:03"}
542
+ {"current_steps": 542, "total_steps": 1230, "loss": 1.0132, "lr": 2.7450012013938648e-05, "epoch": 2.1954430379746834, "percentage": 44.07, "elapsed_time": "1:54:05", "remaining_time": "2:24:48"}
543
+ {"current_steps": 543, "total_steps": 1230, "loss": 1.0178, "lr": 2.739730822017673e-05, "epoch": 2.199493670886076, "percentage": 44.15, "elapsed_time": "1:54:17", "remaining_time": "2:24:35"}
544
+ {"current_steps": 544, "total_steps": 1230, "loss": 0.9993, "lr": 2.7344544849511355e-05, "epoch": 2.2035443037974685, "percentage": 44.23, "elapsed_time": "1:54:28", "remaining_time": "2:24:21"}
545
+ {"current_steps": 545, "total_steps": 1230, "loss": 1.0041, "lr": 2.7291722326891456e-05, "epoch": 2.207594936708861, "percentage": 44.31, "elapsed_time": "1:54:40", "remaining_time": "2:24:08"}
546
+ {"current_steps": 546, "total_steps": 1230, "loss": 1.0315, "lr": 2.723884107774236e-05, "epoch": 2.211645569620253, "percentage": 44.39, "elapsed_time": "1:54:52", "remaining_time": "2:23:54"}
547
+ {"current_steps": 547, "total_steps": 1230, "loss": 0.9958, "lr": 2.718590152796239e-05, "epoch": 2.2156962025316456, "percentage": 44.47, "elapsed_time": "1:55:04", "remaining_time": "2:23:40"}
548
+ {"current_steps": 548, "total_steps": 1230, "loss": 1.0172, "lr": 2.71329041039194e-05, "epoch": 2.219746835443038, "percentage": 44.55, "elapsed_time": "1:55:16", "remaining_time": "2:23:28"}
549
+ {"current_steps": 549, "total_steps": 1230, "loss": 1.0017, "lr": 2.7079849232447357e-05, "epoch": 2.22379746835443, "percentage": 44.63, "elapsed_time": "1:55:28", "remaining_time": "2:23:14"}
550
+ {"current_steps": 550, "total_steps": 1230, "loss": 1.0149, "lr": 2.7026737340842895e-05, "epoch": 2.2278481012658227, "percentage": 44.72, "elapsed_time": "1:55:41", "remaining_time": "2:23:01"}
551
+ {"current_steps": 551, "total_steps": 1230, "loss": 1.0218, "lr": 2.697356885686189e-05, "epoch": 2.231898734177215, "percentage": 44.8, "elapsed_time": "1:55:53", "remaining_time": "2:22:48"}
552
+ {"current_steps": 552, "total_steps": 1230, "loss": 1.0334, "lr": 2.6920344208716014e-05, "epoch": 2.2359493670886077, "percentage": 44.88, "elapsed_time": "1:56:04", "remaining_time": "2:22:33"}
553
+ {"current_steps": 553, "total_steps": 1230, "loss": 1.0204, "lr": 2.6867063825069252e-05, "epoch": 2.24, "percentage": 44.96, "elapsed_time": "1:56:15", "remaining_time": "2:22:19"}
554
+ {"current_steps": 554, "total_steps": 1230, "loss": 1.0272, "lr": 2.6813728135034494e-05, "epoch": 2.2440506329113923, "percentage": 45.04, "elapsed_time": "1:56:27", "remaining_time": "2:22:06"}
555
+ {"current_steps": 555, "total_steps": 1230, "loss": 0.9897, "lr": 2.6760337568170056e-05, "epoch": 2.248101265822785, "percentage": 45.12, "elapsed_time": "1:56:38", "remaining_time": "2:21:52"}
556
+ {"current_steps": 556, "total_steps": 1230, "loss": 1.0193, "lr": 2.6706892554476226e-05, "epoch": 2.2521518987341773, "percentage": 45.2, "elapsed_time": "1:56:55", "remaining_time": "2:21:44"}
557
+ {"current_steps": 557, "total_steps": 1230, "loss": 1.0257, "lr": 2.6653393524391795e-05, "epoch": 2.2562025316455694, "percentage": 45.28, "elapsed_time": "1:57:10", "remaining_time": "2:21:34"}
558
+ {"current_steps": 558, "total_steps": 1230, "loss": 1.0109, "lr": 2.6599840908790592e-05, "epoch": 2.260253164556962, "percentage": 45.37, "elapsed_time": "1:57:22", "remaining_time": "2:21:21"}
559
+ {"current_steps": 559, "total_steps": 1230, "loss": 1.0348, "lr": 2.6546235138978028e-05, "epoch": 2.2643037974683544, "percentage": 45.45, "elapsed_time": "1:57:34", "remaining_time": "2:21:08"}
560
+ {"current_steps": 560, "total_steps": 1230, "loss": 1.0228, "lr": 2.6492576646687597e-05, "epoch": 2.268354430379747, "percentage": 45.53, "elapsed_time": "1:57:46", "remaining_time": "2:20:54"}
561
+ {"current_steps": 561, "total_steps": 1230, "loss": 1.0199, "lr": 2.6438865864077425e-05, "epoch": 2.2724050632911394, "percentage": 45.61, "elapsed_time": "1:57:58", "remaining_time": "2:20:41"}
562
+ {"current_steps": 562, "total_steps": 1230, "loss": 1.0082, "lr": 2.6385103223726766e-05, "epoch": 2.2764556962025315, "percentage": 45.69, "elapsed_time": "1:58:10", "remaining_time": "2:20:27"}
563
+ {"current_steps": 563, "total_steps": 1230, "loss": 1.0314, "lr": 2.6331289158632537e-05, "epoch": 2.280506329113924, "percentage": 45.77, "elapsed_time": "1:58:22", "remaining_time": "2:20:14"}
564
+ {"current_steps": 564, "total_steps": 1230, "loss": 1.0369, "lr": 2.6277424102205817e-05, "epoch": 2.2845569620253166, "percentage": 45.85, "elapsed_time": "1:58:34", "remaining_time": "2:20:01"}
565
+ {"current_steps": 565, "total_steps": 1230, "loss": 1.0191, "lr": 2.6223508488268374e-05, "epoch": 2.2886075949367086, "percentage": 45.93, "elapsed_time": "1:58:50", "remaining_time": "2:19:51"}
566
+ {"current_steps": 566, "total_steps": 1230, "loss": 1.0309, "lr": 2.6169542751049148e-05, "epoch": 2.292658227848101, "percentage": 46.02, "elapsed_time": "1:59:02", "remaining_time": "2:19:38"}
567
+ {"current_steps": 567, "total_steps": 1230, "loss": 1.024, "lr": 2.6115527325180754e-05, "epoch": 2.2967088607594937, "percentage": 46.1, "elapsed_time": "1:59:13", "remaining_time": "2:19:24"}
568
+ {"current_steps": 568, "total_steps": 1230, "loss": 1.0219, "lr": 2.606146264569603e-05, "epoch": 2.300759493670886, "percentage": 46.18, "elapsed_time": "1:59:26", "remaining_time": "2:19:12"}
569
+ {"current_steps": 569, "total_steps": 1230, "loss": 1.0097, "lr": 2.6007349148024447e-05, "epoch": 2.3048101265822787, "percentage": 46.26, "elapsed_time": "1:59:38", "remaining_time": "2:18:58"}
570
+ {"current_steps": 570, "total_steps": 1230, "loss": 1.0181, "lr": 2.5953187267988694e-05, "epoch": 2.3088607594936708, "percentage": 46.34, "elapsed_time": "1:59:50", "remaining_time": "2:18:45"}
571
+ {"current_steps": 571, "total_steps": 1230, "loss": 1.0231, "lr": 2.5898977441801097e-05, "epoch": 2.3129113924050633, "percentage": 46.42, "elapsed_time": "2:00:01", "remaining_time": "2:18:31"}
572
+ {"current_steps": 572, "total_steps": 1230, "loss": 1.021, "lr": 2.584472010606015e-05, "epoch": 2.316962025316456, "percentage": 46.5, "elapsed_time": "2:00:13", "remaining_time": "2:18:18"}
573
+ {"current_steps": 573, "total_steps": 1230, "loss": 1.0194, "lr": 2.5790415697746976e-05, "epoch": 2.321012658227848, "percentage": 46.59, "elapsed_time": "2:00:27", "remaining_time": "2:18:07"}
574
+ {"current_steps": 574, "total_steps": 1230, "loss": 1.0297, "lr": 2.5736064654221808e-05, "epoch": 2.3250632911392404, "percentage": 46.67, "elapsed_time": "2:00:39", "remaining_time": "2:17:53"}
575
+ {"current_steps": 575, "total_steps": 1230, "loss": 1.0346, "lr": 2.568166741322048e-05, "epoch": 2.329113924050633, "percentage": 46.75, "elapsed_time": "2:00:51", "remaining_time": "2:17:40"}
576
+ {"current_steps": 576, "total_steps": 1230, "loss": 1.0632, "lr": 2.56272244128509e-05, "epoch": 2.3331645569620254, "percentage": 46.83, "elapsed_time": "2:01:05", "remaining_time": "2:17:29"}
577
+ {"current_steps": 577, "total_steps": 1230, "loss": 1.0164, "lr": 2.55727360915895e-05, "epoch": 2.337215189873418, "percentage": 46.91, "elapsed_time": "2:01:17", "remaining_time": "2:17:15"}
578
+ {"current_steps": 578, "total_steps": 1230, "loss": 1.0296, "lr": 2.5518202888277734e-05, "epoch": 2.34126582278481, "percentage": 46.99, "elapsed_time": "2:01:29", "remaining_time": "2:17:03"}
579
+ {"current_steps": 579, "total_steps": 1230, "loss": 1.0319, "lr": 2.5463625242118523e-05, "epoch": 2.3453164556962025, "percentage": 47.07, "elapsed_time": "2:01:41", "remaining_time": "2:16:49"}
580
+ {"current_steps": 580, "total_steps": 1230, "loss": 0.9987, "lr": 2.5409003592672723e-05, "epoch": 2.349367088607595, "percentage": 47.15, "elapsed_time": "2:01:56", "remaining_time": "2:16:39"}
581
+ {"current_steps": 581, "total_steps": 1230, "loss": 1.0275, "lr": 2.535433837985559e-05, "epoch": 2.353417721518987, "percentage": 47.24, "elapsed_time": "2:02:08", "remaining_time": "2:16:25"}
582
+ {"current_steps": 582, "total_steps": 1230, "loss": 1.0417, "lr": 2.529963004393324e-05, "epoch": 2.3574683544303796, "percentage": 47.32, "elapsed_time": "2:02:20", "remaining_time": "2:16:13"}
583
+ {"current_steps": 583, "total_steps": 1230, "loss": 1.0299, "lr": 2.524487902551908e-05, "epoch": 2.361518987341772, "percentage": 47.4, "elapsed_time": "2:02:32", "remaining_time": "2:15:59"}
584
+ {"current_steps": 584, "total_steps": 1230, "loss": 1.0352, "lr": 2.519008576557029e-05, "epoch": 2.3655696202531646, "percentage": 47.48, "elapsed_time": "2:02:44", "remaining_time": "2:15:46"}
585
+ {"current_steps": 585, "total_steps": 1230, "loss": 1.0333, "lr": 2.5135250705384254e-05, "epoch": 2.369620253164557, "percentage": 47.56, "elapsed_time": "2:02:56", "remaining_time": "2:15:32"}
586
+ {"current_steps": 586, "total_steps": 1230, "loss": 1.0294, "lr": 2.5080374286595007e-05, "epoch": 2.3736708860759492, "percentage": 47.64, "elapsed_time": "2:03:11", "remaining_time": "2:15:23"}
587
+ {"current_steps": 587, "total_steps": 1230, "loss": 1.0293, "lr": 2.5025456951169677e-05, "epoch": 2.3777215189873417, "percentage": 47.72, "elapsed_time": "2:03:23", "remaining_time": "2:15:09"}
588
+ {"current_steps": 588, "total_steps": 1230, "loss": 1.0303, "lr": 2.4970499141404942e-05, "epoch": 2.3817721518987343, "percentage": 47.8, "elapsed_time": "2:03:35", "remaining_time": "2:14:56"}
589
+ {"current_steps": 589, "total_steps": 1230, "loss": 1.0401, "lr": 2.491550129992345e-05, "epoch": 2.3858227848101268, "percentage": 47.89, "elapsed_time": "2:03:48", "remaining_time": "2:14:44"}
590
+ {"current_steps": 590, "total_steps": 1230, "loss": 1.0207, "lr": 2.486046386967024e-05, "epoch": 2.389873417721519, "percentage": 47.97, "elapsed_time": "2:03:59", "remaining_time": "2:14:30"}
591
+ {"current_steps": 591, "total_steps": 1230, "loss": 1.0406, "lr": 2.4805387293909214e-05, "epoch": 2.3939240506329114, "percentage": 48.05, "elapsed_time": "2:04:12", "remaining_time": "2:14:18"}
592
+ {"current_steps": 592, "total_steps": 1230, "loss": 1.0229, "lr": 2.4750272016219552e-05, "epoch": 2.397974683544304, "percentage": 48.13, "elapsed_time": "2:04:24", "remaining_time": "2:14:04"}
593
+ {"current_steps": 593, "total_steps": 1230, "loss": 1.0617, "lr": 2.4695118480492114e-05, "epoch": 2.4020253164556964, "percentage": 48.21, "elapsed_time": "2:04:40", "remaining_time": "2:13:55"}
594
+ {"current_steps": 594, "total_steps": 1230, "loss": 1.046, "lr": 2.4639927130925898e-05, "epoch": 2.4060759493670885, "percentage": 48.29, "elapsed_time": "2:04:52", "remaining_time": "2:13:42"}
595
+ {"current_steps": 595, "total_steps": 1230, "loss": 1.014, "lr": 2.458469841202444e-05, "epoch": 2.410126582278481, "percentage": 48.37, "elapsed_time": "2:05:05", "remaining_time": "2:13:29"}
596
+ {"current_steps": 596, "total_steps": 1230, "loss": 1.0333, "lr": 2.452943276859226e-05, "epoch": 2.4141772151898735, "percentage": 48.46, "elapsed_time": "2:05:17", "remaining_time": "2:13:16"}
597
+ {"current_steps": 597, "total_steps": 1230, "loss": 1.0272, "lr": 2.447413064573125e-05, "epoch": 2.418227848101266, "percentage": 48.54, "elapsed_time": "2:05:29", "remaining_time": "2:13:03"}
598
+ {"current_steps": 598, "total_steps": 1230, "loss": 1.0136, "lr": 2.4418792488837095e-05, "epoch": 2.422278481012658, "percentage": 48.62, "elapsed_time": "2:05:40", "remaining_time": "2:12:49"}
599
+ {"current_steps": 599, "total_steps": 1230, "loss": 1.0344, "lr": 2.4363418743595713e-05, "epoch": 2.4263291139240506, "percentage": 48.7, "elapsed_time": "2:05:53", "remaining_time": "2:12:37"}
600
+ {"current_steps": 600, "total_steps": 1230, "loss": 1.0136, "lr": 2.430800985597963e-05, "epoch": 2.430379746835443, "percentage": 48.78, "elapsed_time": "2:06:05", "remaining_time": "2:12:23"}
601
+ {"current_steps": 601, "total_steps": 1230, "loss": 0.9962, "lr": 2.4252566272244415e-05, "epoch": 2.4344303797468356, "percentage": 48.86, "elapsed_time": "2:06:16", "remaining_time": "2:12:09"}
602
+ {"current_steps": 602, "total_steps": 1230, "loss": 1.0033, "lr": 2.4197088438925063e-05, "epoch": 2.4384810126582277, "percentage": 48.94, "elapsed_time": "2:06:28", "remaining_time": "2:11:56"}
603
+ {"current_steps": 603, "total_steps": 1230, "loss": 1.0328, "lr": 2.4141576802832417e-05, "epoch": 2.44253164556962, "percentage": 49.02, "elapsed_time": "2:06:40", "remaining_time": "2:11:43"}
604
+ {"current_steps": 604, "total_steps": 1230, "loss": 1.0188, "lr": 2.408603181104957e-05, "epoch": 2.4465822784810127, "percentage": 49.11, "elapsed_time": "2:06:53", "remaining_time": "2:11:30"}
605
+ {"current_steps": 605, "total_steps": 1230, "loss": 1.0293, "lr": 2.4030453910928245e-05, "epoch": 2.4506329113924052, "percentage": 49.19, "elapsed_time": "2:07:05", "remaining_time": "2:11:17"}
606
+ {"current_steps": 606, "total_steps": 1230, "loss": 1.0048, "lr": 2.397484355008521e-05, "epoch": 2.4546835443037973, "percentage": 49.27, "elapsed_time": "2:07:17", "remaining_time": "2:11:03"}
607
+ {"current_steps": 607, "total_steps": 1230, "loss": 1.0101, "lr": 2.3919201176398662e-05, "epoch": 2.45873417721519, "percentage": 49.35, "elapsed_time": "2:07:29", "remaining_time": "2:10:51"}
608
+ {"current_steps": 608, "total_steps": 1230, "loss": 1.0176, "lr": 2.3863527238004633e-05, "epoch": 2.4627848101265823, "percentage": 49.43, "elapsed_time": "2:07:41", "remaining_time": "2:10:37"}
609
+ {"current_steps": 609, "total_steps": 1230, "loss": 1.0128, "lr": 2.380782218329337e-05, "epoch": 2.466835443037975, "percentage": 49.51, "elapsed_time": "2:07:52", "remaining_time": "2:10:24"}
610
+ {"current_steps": 610, "total_steps": 1230, "loss": 1.0605, "lr": 2.3752086460905725e-05, "epoch": 2.470886075949367, "percentage": 49.59, "elapsed_time": "2:08:04", "remaining_time": "2:10:10"}
611
+ {"current_steps": 611, "total_steps": 1230, "loss": 1.0373, "lr": 2.3696320519729544e-05, "epoch": 2.4749367088607594, "percentage": 49.67, "elapsed_time": "2:08:16", "remaining_time": "2:09:56"}
612
+ {"current_steps": 612, "total_steps": 1230, "loss": 1.044, "lr": 2.3640524808896045e-05, "epoch": 2.478987341772152, "percentage": 49.76, "elapsed_time": "2:08:28", "remaining_time": "2:09:44"}
613
+ {"current_steps": 613, "total_steps": 1230, "loss": 1.0313, "lr": 2.3584699777776222e-05, "epoch": 2.4830379746835445, "percentage": 49.84, "elapsed_time": "2:08:40", "remaining_time": "2:09:30"}
614
+ {"current_steps": 614, "total_steps": 1230, "loss": 1.0536, "lr": 2.3528845875977195e-05, "epoch": 2.4870886075949366, "percentage": 49.92, "elapsed_time": "2:08:52", "remaining_time": "2:09:17"}
615
+ {"current_steps": 615, "total_steps": 1230, "loss": 1.0121, "lr": 2.3472963553338614e-05, "epoch": 2.491139240506329, "percentage": 50.0, "elapsed_time": "2:09:04", "remaining_time": "2:09:04"}
616
+ {"current_steps": 616, "total_steps": 1230, "loss": 1.0136, "lr": 2.341705325992901e-05, "epoch": 2.4951898734177216, "percentage": 50.08, "elapsed_time": "2:09:15", "remaining_time": "2:08:50"}
617
+ {"current_steps": 617, "total_steps": 1230, "loss": 1.0064, "lr": 2.336111544604222e-05, "epoch": 2.499240506329114, "percentage": 50.16, "elapsed_time": "2:09:30", "remaining_time": "2:08:40"}
618
+ {"current_steps": 618, "total_steps": 1230, "loss": 1.0353, "lr": 2.33051505621937e-05, "epoch": 2.503291139240506, "percentage": 50.24, "elapsed_time": "2:09:43", "remaining_time": "2:08:28"}
619
+ {"current_steps": 619, "total_steps": 1230, "loss": 1.0052, "lr": 2.324915905911693e-05, "epoch": 2.5073417721518987, "percentage": 50.33, "elapsed_time": "2:09:55", "remaining_time": "2:08:14"}
620
+ {"current_steps": 620, "total_steps": 1230, "loss": 1.0206, "lr": 2.319314138775977e-05, "epoch": 2.511392405063291, "percentage": 50.41, "elapsed_time": "2:10:07", "remaining_time": "2:08:01"}
621
+ {"current_steps": 621, "total_steps": 1230, "loss": 1.0254, "lr": 2.3137097999280856e-05, "epoch": 2.5154430379746833, "percentage": 50.49, "elapsed_time": "2:10:19", "remaining_time": "2:07:48"}
622
+ {"current_steps": 622, "total_steps": 1230, "loss": 1.0299, "lr": 2.308102934504593e-05, "epoch": 2.519493670886076, "percentage": 50.57, "elapsed_time": "2:10:30", "remaining_time": "2:07:34"}
623
+ {"current_steps": 623, "total_steps": 1230, "loss": 1.0185, "lr": 2.3024935876624222e-05, "epoch": 2.5235443037974683, "percentage": 50.65, "elapsed_time": "2:10:44", "remaining_time": "2:07:22"}
624
+ {"current_steps": 624, "total_steps": 1230, "loss": 1.0012, "lr": 2.2968818045784813e-05, "epoch": 2.527594936708861, "percentage": 50.73, "elapsed_time": "2:10:56", "remaining_time": "2:07:10"}
625
+ {"current_steps": 625, "total_steps": 1230, "loss": 1.0038, "lr": 2.2912676304493006e-05, "epoch": 2.5316455696202533, "percentage": 50.81, "elapsed_time": "2:11:08", "remaining_time": "2:06:57"}
626
+ {"current_steps": 626, "total_steps": 1230, "loss": 1.0182, "lr": 2.2856511104906668e-05, "epoch": 2.5356962025316454, "percentage": 50.89, "elapsed_time": "2:11:20", "remaining_time": "2:06:43"}
627
+ {"current_steps": 627, "total_steps": 1230, "loss": 1.0375, "lr": 2.2800322899372586e-05, "epoch": 2.539746835443038, "percentage": 50.98, "elapsed_time": "2:11:32", "remaining_time": "2:06:30"}
628
+ {"current_steps": 628, "total_steps": 1230, "loss": 1.0266, "lr": 2.2744112140422844e-05, "epoch": 2.5437974683544304, "percentage": 51.06, "elapsed_time": "2:11:43", "remaining_time": "2:06:16"}
629
+ {"current_steps": 629, "total_steps": 1230, "loss": 1.0266, "lr": 2.2687879280771177e-05, "epoch": 2.547848101265823, "percentage": 51.14, "elapsed_time": "2:11:56", "remaining_time": "2:06:03"}
630
+ {"current_steps": 630, "total_steps": 1230, "loss": 1.0141, "lr": 2.26316247733093e-05, "epoch": 2.5518987341772155, "percentage": 51.22, "elapsed_time": "2:12:08", "remaining_time": "2:05:51"}
631
+ {"current_steps": 631, "total_steps": 1230, "loss": 1.0154, "lr": 2.257534907110328e-05, "epoch": 2.5559493670886075, "percentage": 51.3, "elapsed_time": "2:12:21", "remaining_time": "2:05:38"}
632
+ {"current_steps": 632, "total_steps": 1230, "loss": 1.0156, "lr": 2.2519052627389882e-05, "epoch": 2.56, "percentage": 51.38, "elapsed_time": "2:12:32", "remaining_time": "2:05:25"}
633
+ {"current_steps": 633, "total_steps": 1230, "loss": 0.9955, "lr": 2.246273589557294e-05, "epoch": 2.5640506329113926, "percentage": 51.46, "elapsed_time": "2:12:44", "remaining_time": "2:05:11"}
634
+ {"current_steps": 634, "total_steps": 1230, "loss": 1.0402, "lr": 2.240639932921966e-05, "epoch": 2.5681012658227846, "percentage": 51.54, "elapsed_time": "2:12:56", "remaining_time": "2:04:58"}
635
+ {"current_steps": 635, "total_steps": 1230, "loss": 1.0064, "lr": 2.2350043382056995e-05, "epoch": 2.572151898734177, "percentage": 51.63, "elapsed_time": "2:13:08", "remaining_time": "2:04:45"}
636
+ {"current_steps": 636, "total_steps": 1230, "loss": 1.025, "lr": 2.2293668507968015e-05, "epoch": 2.5762025316455697, "percentage": 51.71, "elapsed_time": "2:13:20", "remaining_time": "2:04:31"}
637
+ {"current_steps": 637, "total_steps": 1230, "loss": 1.0159, "lr": 2.2237275160988186e-05, "epoch": 2.580253164556962, "percentage": 51.79, "elapsed_time": "2:13:32", "remaining_time": "2:04:19"}
638
+ {"current_steps": 638, "total_steps": 1230, "loss": 1.0296, "lr": 2.2180863795301787e-05, "epoch": 2.5843037974683547, "percentage": 51.87, "elapsed_time": "2:13:46", "remaining_time": "2:04:07"}
639
+ {"current_steps": 639, "total_steps": 1230, "loss": 1.0728, "lr": 2.212443486523819e-05, "epoch": 2.5883544303797468, "percentage": 51.95, "elapsed_time": "2:13:57", "remaining_time": "2:03:53"}
640
+ {"current_steps": 640, "total_steps": 1230, "loss": 1.013, "lr": 2.2067988825268243e-05, "epoch": 2.5924050632911393, "percentage": 52.03, "elapsed_time": "2:14:09", "remaining_time": "2:03:40"}
641
+ {"current_steps": 641, "total_steps": 1230, "loss": 1.0317, "lr": 2.2011526130000596e-05, "epoch": 2.596455696202532, "percentage": 52.11, "elapsed_time": "2:14:20", "remaining_time": "2:03:26"}
642
+ {"current_steps": 642, "total_steps": 1230, "loss": 1.0247, "lr": 2.1955047234178038e-05, "epoch": 2.600506329113924, "percentage": 52.2, "elapsed_time": "2:14:31", "remaining_time": "2:03:12"}
643
+ {"current_steps": 643, "total_steps": 1230, "loss": 1.018, "lr": 2.1898552592673825e-05, "epoch": 2.6045569620253164, "percentage": 52.28, "elapsed_time": "2:14:45", "remaining_time": "2:03:01"}
644
+ {"current_steps": 644, "total_steps": 1230, "loss": 1.0404, "lr": 2.184204266048803e-05, "epoch": 2.608607594936709, "percentage": 52.36, "elapsed_time": "2:14:57", "remaining_time": "2:02:47"}
645
+ {"current_steps": 645, "total_steps": 1230, "loss": 1.0289, "lr": 2.1785517892743887e-05, "epoch": 2.6126582278481014, "percentage": 52.44, "elapsed_time": "2:15:08", "remaining_time": "2:02:34"}
646
+ {"current_steps": 646, "total_steps": 1230, "loss": 1.0195, "lr": 2.17289787446841e-05, "epoch": 2.616708860759494, "percentage": 52.52, "elapsed_time": "2:15:21", "remaining_time": "2:02:21"}
647
+ {"current_steps": 647, "total_steps": 1230, "loss": 1.0064, "lr": 2.1672425671667198e-05, "epoch": 2.620759493670886, "percentage": 52.6, "elapsed_time": "2:15:32", "remaining_time": "2:02:08"}
648
+ {"current_steps": 648, "total_steps": 1230, "loss": 1.0197, "lr": 2.161585912916385e-05, "epoch": 2.6248101265822785, "percentage": 52.68, "elapsed_time": "2:15:44", "remaining_time": "2:01:54"}
649
+ {"current_steps": 649, "total_steps": 1230, "loss": 1.0012, "lr": 2.1559279572753214e-05, "epoch": 2.628860759493671, "percentage": 52.76, "elapsed_time": "2:15:56", "remaining_time": "2:01:41"}
650
+ {"current_steps": 650, "total_steps": 1230, "loss": 1.0091, "lr": 2.1502687458119268e-05, "epoch": 2.632911392405063, "percentage": 52.85, "elapsed_time": "2:16:08", "remaining_time": "2:01:28"}
651
+ {"current_steps": 651, "total_steps": 1230, "loss": 1.0211, "lr": 2.1446083241047116e-05, "epoch": 2.6369620253164556, "percentage": 52.93, "elapsed_time": "2:16:20", "remaining_time": "2:01:15"}
652
+ {"current_steps": 652, "total_steps": 1230, "loss": 1.0314, "lr": 2.1389467377419333e-05, "epoch": 2.641012658227848, "percentage": 53.01, "elapsed_time": "2:16:32", "remaining_time": "2:01:02"}
653
+ {"current_steps": 653, "total_steps": 1230, "loss": 1.015, "lr": 2.133284032321232e-05, "epoch": 2.6450632911392407, "percentage": 53.09, "elapsed_time": "2:16:46", "remaining_time": "2:00:51"}
654
+ {"current_steps": 654, "total_steps": 1230, "loss": 1.0146, "lr": 2.1276202534492566e-05, "epoch": 2.649113924050633, "percentage": 53.17, "elapsed_time": "2:17:00", "remaining_time": "2:00:39"}
655
+ {"current_steps": 655, "total_steps": 1230, "loss": 1.034, "lr": 2.121955446741306e-05, "epoch": 2.6531645569620252, "percentage": 53.25, "elapsed_time": "2:17:11", "remaining_time": "2:00:26"}
656
+ {"current_steps": 656, "total_steps": 1230, "loss": 1.0341, "lr": 2.1162896578209517e-05, "epoch": 2.6572151898734178, "percentage": 53.33, "elapsed_time": "2:17:25", "remaining_time": "2:00:14"}
657
+ {"current_steps": 657, "total_steps": 1230, "loss": 1.0341, "lr": 2.1106229323196813e-05, "epoch": 2.6612658227848103, "percentage": 53.41, "elapsed_time": "2:17:37", "remaining_time": "2:00:01"}
658
+ {"current_steps": 658, "total_steps": 1230, "loss": 1.0003, "lr": 2.1049553158765214e-05, "epoch": 2.6653164556962023, "percentage": 53.5, "elapsed_time": "2:17:49", "remaining_time": "1:59:48"}
659
+ {"current_steps": 659, "total_steps": 1230, "loss": 1.0126, "lr": 2.0992868541376764e-05, "epoch": 2.669367088607595, "percentage": 53.58, "elapsed_time": "2:18:02", "remaining_time": "1:59:36"}
660
+ {"current_steps": 660, "total_steps": 1230, "loss": 1.0067, "lr": 2.093617592756158e-05, "epoch": 2.6734177215189874, "percentage": 53.66, "elapsed_time": "2:18:13", "remaining_time": "1:59:22"}
661
+ {"current_steps": 661, "total_steps": 1230, "loss": 1.0096, "lr": 2.0879475773914167e-05, "epoch": 2.67746835443038, "percentage": 53.74, "elapsed_time": "2:18:25", "remaining_time": "1:59:09"}
662
+ {"current_steps": 662, "total_steps": 1230, "loss": 1.0207, "lr": 2.082276853708978e-05, "epoch": 2.6815189873417724, "percentage": 53.82, "elapsed_time": "2:18:37", "remaining_time": "1:58:56"}
663
+ {"current_steps": 663, "total_steps": 1230, "loss": 1.0227, "lr": 2.076605467380071e-05, "epoch": 2.6855696202531645, "percentage": 53.9, "elapsed_time": "2:18:48", "remaining_time": "1:58:42"}
664
+ {"current_steps": 664, "total_steps": 1230, "loss": 1.037, "lr": 2.0709334640812613e-05, "epoch": 2.689620253164557, "percentage": 53.98, "elapsed_time": "2:18:59", "remaining_time": "1:58:28"}
665
+ {"current_steps": 665, "total_steps": 1230, "loss": 1.0335, "lr": 2.0652608894940824e-05, "epoch": 2.6936708860759495, "percentage": 54.07, "elapsed_time": "2:19:11", "remaining_time": "1:58:15"}
666
+ {"current_steps": 666, "total_steps": 1230, "loss": 1.0402, "lr": 2.0595877893046722e-05, "epoch": 2.6977215189873416, "percentage": 54.15, "elapsed_time": "2:19:23", "remaining_time": "1:58:02"}
667
+ {"current_steps": 667, "total_steps": 1230, "loss": 1.0244, "lr": 2.0539142092033985e-05, "epoch": 2.701772151898734, "percentage": 54.23, "elapsed_time": "2:19:34", "remaining_time": "1:57:48"}
668
+ {"current_steps": 668, "total_steps": 1230, "loss": 0.9953, "lr": 2.048240194884496e-05, "epoch": 2.7058227848101266, "percentage": 54.31, "elapsed_time": "2:19:45", "remaining_time": "1:57:35"}
669
+ {"current_steps": 669, "total_steps": 1230, "loss": 1.0152, "lr": 2.042565792045695e-05, "epoch": 2.709873417721519, "percentage": 54.39, "elapsed_time": "2:20:02", "remaining_time": "1:57:26"}
670
+ {"current_steps": 670, "total_steps": 1230, "loss": 1.0411, "lr": 2.036891046387857e-05, "epoch": 2.7139240506329116, "percentage": 54.47, "elapsed_time": "2:20:15", "remaining_time": "1:57:13"}
671
+ {"current_steps": 671, "total_steps": 1230, "loss": 1.0445, "lr": 2.0312160036146036e-05, "epoch": 2.7179746835443037, "percentage": 54.55, "elapsed_time": "2:20:26", "remaining_time": "1:57:00"}
672
+ {"current_steps": 672, "total_steps": 1230, "loss": 1.0534, "lr": 2.025540709431948e-05, "epoch": 2.7220253164556962, "percentage": 54.63, "elapsed_time": "2:20:38", "remaining_time": "1:56:46"}
673
+ {"current_steps": 673, "total_steps": 1230, "loss": 1.0255, "lr": 2.0198652095479298e-05, "epoch": 2.7260759493670887, "percentage": 54.72, "elapsed_time": "2:20:50", "remaining_time": "1:56:33"}
674
+ {"current_steps": 674, "total_steps": 1230, "loss": 1.0378, "lr": 2.014189549672245e-05, "epoch": 2.730126582278481, "percentage": 54.8, "elapsed_time": "2:21:02", "remaining_time": "1:56:21"}
675
+ {"current_steps": 675, "total_steps": 1230, "loss": 1.0016, "lr": 2.0085137755158776e-05, "epoch": 2.7341772151898733, "percentage": 54.88, "elapsed_time": "2:21:14", "remaining_time": "1:56:07"}
676
+ {"current_steps": 676, "total_steps": 1230, "loss": 1.0002, "lr": 2.0028379327907327e-05, "epoch": 2.738227848101266, "percentage": 54.96, "elapsed_time": "2:21:26", "remaining_time": "1:55:54"}
677
+ {"current_steps": 677, "total_steps": 1230, "loss": 1.0305, "lr": 1.9971620672092676e-05, "epoch": 2.7422784810126584, "percentage": 55.04, "elapsed_time": "2:21:37", "remaining_time": "1:55:41"}
678
+ {"current_steps": 678, "total_steps": 1230, "loss": 1.0186, "lr": 1.991486224484123e-05, "epoch": 2.746329113924051, "percentage": 55.12, "elapsed_time": "2:21:49", "remaining_time": "1:55:28"}
679
+ {"current_steps": 679, "total_steps": 1230, "loss": 1.0256, "lr": 1.985810450327756e-05, "epoch": 2.750379746835443, "percentage": 55.2, "elapsed_time": "2:22:00", "remaining_time": "1:55:14"}
680
+ {"current_steps": 680, "total_steps": 1230, "loss": 1.0284, "lr": 1.9801347904520706e-05, "epoch": 2.7544303797468355, "percentage": 55.28, "elapsed_time": "2:22:12", "remaining_time": "1:55:01"}
681
+ {"current_steps": 681, "total_steps": 1230, "loss": 1.0277, "lr": 1.974459290568053e-05, "epoch": 2.758481012658228, "percentage": 55.37, "elapsed_time": "2:22:24", "remaining_time": "1:54:48"}
682
+ {"current_steps": 682, "total_steps": 1230, "loss": 1.0364, "lr": 1.968783996385397e-05, "epoch": 2.76253164556962, "percentage": 55.45, "elapsed_time": "2:22:35", "remaining_time": "1:54:34"}
683
+ {"current_steps": 683, "total_steps": 1230, "loss": 0.9977, "lr": 1.963108953612143e-05, "epoch": 2.7665822784810126, "percentage": 55.53, "elapsed_time": "2:22:48", "remaining_time": "1:54:22"}
684
+ {"current_steps": 684, "total_steps": 1230, "loss": 1.0169, "lr": 1.9574342079543056e-05, "epoch": 2.770632911392405, "percentage": 55.61, "elapsed_time": "2:22:59", "remaining_time": "1:54:08"}
685
+ {"current_steps": 685, "total_steps": 1230, "loss": 1.0601, "lr": 1.9517598051155046e-05, "epoch": 2.7746835443037976, "percentage": 55.69, "elapsed_time": "2:23:11", "remaining_time": "1:53:55"}
686
+ {"current_steps": 686, "total_steps": 1230, "loss": 1.0058, "lr": 1.9460857907966025e-05, "epoch": 2.77873417721519, "percentage": 55.77, "elapsed_time": "2:23:22", "remaining_time": "1:53:41"}
687
+ {"current_steps": 687, "total_steps": 1230, "loss": 1.0154, "lr": 1.9404122106953285e-05, "epoch": 2.782784810126582, "percentage": 55.85, "elapsed_time": "2:23:34", "remaining_time": "1:53:28"}
688
+ {"current_steps": 688, "total_steps": 1230, "loss": 1.0419, "lr": 1.9347391105059176e-05, "epoch": 2.7868354430379747, "percentage": 55.93, "elapsed_time": "2:23:47", "remaining_time": "1:53:16"}
689
+ {"current_steps": 689, "total_steps": 1230, "loss": 1.0163, "lr": 1.92906653591874e-05, "epoch": 2.790886075949367, "percentage": 56.02, "elapsed_time": "2:24:02", "remaining_time": "1:53:06"}
690
+ {"current_steps": 690, "total_steps": 1230, "loss": 1.0062, "lr": 1.9233945326199295e-05, "epoch": 2.7949367088607593, "percentage": 56.1, "elapsed_time": "2:24:14", "remaining_time": "1:52:53"}
691
+ {"current_steps": 691, "total_steps": 1230, "loss": 1.0135, "lr": 1.917723146291022e-05, "epoch": 2.798987341772152, "percentage": 56.18, "elapsed_time": "2:24:26", "remaining_time": "1:52:40"}
692
+ {"current_steps": 692, "total_steps": 1230, "loss": 1.0201, "lr": 1.912052422608584e-05, "epoch": 2.8030379746835443, "percentage": 56.26, "elapsed_time": "2:24:39", "remaining_time": "1:52:27"}
693
+ {"current_steps": 693, "total_steps": 1230, "loss": 1.0372, "lr": 1.9063824072438428e-05, "epoch": 2.807088607594937, "percentage": 56.34, "elapsed_time": "2:24:51", "remaining_time": "1:52:15"}
694
+ {"current_steps": 694, "total_steps": 1230, "loss": 1.0269, "lr": 1.9007131458623246e-05, "epoch": 2.8111392405063294, "percentage": 56.42, "elapsed_time": "2:25:04", "remaining_time": "1:52:02"}
695
+ {"current_steps": 695, "total_steps": 1230, "loss": 1.016, "lr": 1.895044684123479e-05, "epoch": 2.8151898734177214, "percentage": 56.5, "elapsed_time": "2:25:15", "remaining_time": "1:51:49"}
696
+ {"current_steps": 696, "total_steps": 1230, "loss": 1.0334, "lr": 1.8893770676803194e-05, "epoch": 2.819240506329114, "percentage": 56.59, "elapsed_time": "2:25:30", "remaining_time": "1:51:38"}
697
+ {"current_steps": 697, "total_steps": 1230, "loss": 1.0144, "lr": 1.8837103421790486e-05, "epoch": 2.8232911392405065, "percentage": 56.67, "elapsed_time": "2:25:42", "remaining_time": "1:51:25"}
698
+ {"current_steps": 698, "total_steps": 1230, "loss": 1.0318, "lr": 1.8780445532586952e-05, "epoch": 2.8273417721518985, "percentage": 56.75, "elapsed_time": "2:25:53", "remaining_time": "1:51:11"}
699
+ {"current_steps": 699, "total_steps": 1230, "loss": 1.0252, "lr": 1.872379746550743e-05, "epoch": 2.831392405063291, "percentage": 56.83, "elapsed_time": "2:26:05", "remaining_time": "1:50:58"}
700
+ {"current_steps": 700, "total_steps": 1230, "loss": 1.016, "lr": 1.866715967678769e-05, "epoch": 2.8354430379746836, "percentage": 56.91, "elapsed_time": "2:26:17", "remaining_time": "1:50:45"}
701
+ {"current_steps": 701, "total_steps": 1230, "loss": 1.0189, "lr": 1.861053262258067e-05, "epoch": 2.839493670886076, "percentage": 56.99, "elapsed_time": "2:26:28", "remaining_time": "1:50:32"}
702
+ {"current_steps": 702, "total_steps": 1230, "loss": 1.0263, "lr": 1.8553916758952897e-05, "epoch": 2.8435443037974686, "percentage": 57.07, "elapsed_time": "2:26:44", "remaining_time": "1:50:22"}
703
+ {"current_steps": 703, "total_steps": 1230, "loss": 1.0072, "lr": 1.8497312541880735e-05, "epoch": 2.8475949367088607, "percentage": 57.15, "elapsed_time": "2:26:56", "remaining_time": "1:50:09"}
704
+ {"current_steps": 704, "total_steps": 1230, "loss": 1.0207, "lr": 1.8440720427246786e-05, "epoch": 2.851645569620253, "percentage": 57.24, "elapsed_time": "2:27:08", "remaining_time": "1:49:56"}
705
+ {"current_steps": 705, "total_steps": 1230, "loss": 1.0012, "lr": 1.8384140870836157e-05, "epoch": 2.8556962025316457, "percentage": 57.32, "elapsed_time": "2:27:20", "remaining_time": "1:49:43"}
706
+ {"current_steps": 706, "total_steps": 1230, "loss": 1.0301, "lr": 1.8327574328332806e-05, "epoch": 2.8597468354430378, "percentage": 57.4, "elapsed_time": "2:27:32", "remaining_time": "1:49:30"}
707
+ {"current_steps": 707, "total_steps": 1230, "loss": 1.0104, "lr": 1.8271021255315906e-05, "epoch": 2.8637974683544303, "percentage": 57.48, "elapsed_time": "2:27:44", "remaining_time": "1:49:17"}
708
+ {"current_steps": 708, "total_steps": 1230, "loss": 1.0108, "lr": 1.8214482107256117e-05, "epoch": 2.867848101265823, "percentage": 57.56, "elapsed_time": "2:27:56", "remaining_time": "1:49:04"}
709
+ {"current_steps": 709, "total_steps": 1230, "loss": 1.0078, "lr": 1.8157957339511968e-05, "epoch": 2.8718987341772153, "percentage": 57.64, "elapsed_time": "2:28:07", "remaining_time": "1:48:51"}
710
+ {"current_steps": 710, "total_steps": 1230, "loss": 1.0255, "lr": 1.8101447407326182e-05, "epoch": 2.875949367088608, "percentage": 57.72, "elapsed_time": "2:28:20", "remaining_time": "1:48:38"}
711
+ {"current_steps": 711, "total_steps": 1230, "loss": 1.0281, "lr": 1.8044952765821966e-05, "epoch": 2.88, "percentage": 57.8, "elapsed_time": "2:28:32", "remaining_time": "1:48:25"}
712
+ {"current_steps": 712, "total_steps": 1230, "loss": 1.0547, "lr": 1.7988473869999407e-05, "epoch": 2.8840506329113924, "percentage": 57.89, "elapsed_time": "2:28:43", "remaining_time": "1:48:12"}
713
+ {"current_steps": 713, "total_steps": 1230, "loss": 1.0419, "lr": 1.7932011174731764e-05, "epoch": 2.888101265822785, "percentage": 57.97, "elapsed_time": "2:28:56", "remaining_time": "1:47:59"}
714
+ {"current_steps": 714, "total_steps": 1230, "loss": 1.0017, "lr": 1.7875565134761817e-05, "epoch": 2.892151898734177, "percentage": 58.05, "elapsed_time": "2:29:08", "remaining_time": "1:47:47"}
715
+ {"current_steps": 715, "total_steps": 1230, "loss": 1.0331, "lr": 1.7819136204698226e-05, "epoch": 2.8962025316455695, "percentage": 58.13, "elapsed_time": "2:29:20", "remaining_time": "1:47:33"}
716
+ {"current_steps": 716, "total_steps": 1230, "loss": 1.0214, "lr": 1.776272483901182e-05, "epoch": 2.900253164556962, "percentage": 58.21, "elapsed_time": "2:29:32", "remaining_time": "1:47:20"}
717
+ {"current_steps": 717, "total_steps": 1230, "loss": 1.028, "lr": 1.7706331492031995e-05, "epoch": 2.9043037974683545, "percentage": 58.29, "elapsed_time": "2:29:44", "remaining_time": "1:47:07"}
718
+ {"current_steps": 718, "total_steps": 1230, "loss": 1.0152, "lr": 1.764995661794301e-05, "epoch": 2.908354430379747, "percentage": 58.37, "elapsed_time": "2:29:56", "remaining_time": "1:46:55"}
719
+ {"current_steps": 719, "total_steps": 1230, "loss": 1.0215, "lr": 1.759360067078035e-05, "epoch": 2.912405063291139, "percentage": 58.46, "elapsed_time": "2:30:07", "remaining_time": "1:46:42"}
720
+ {"current_steps": 720, "total_steps": 1230, "loss": 0.9806, "lr": 1.7537264104427064e-05, "epoch": 2.9164556962025316, "percentage": 58.54, "elapsed_time": "2:30:23", "remaining_time": "1:46:31"}
721
+ {"current_steps": 721, "total_steps": 1230, "loss": 1.0118, "lr": 1.748094737261012e-05, "epoch": 2.920506329113924, "percentage": 58.62, "elapsed_time": "2:30:35", "remaining_time": "1:46:18"}
722
+ {"current_steps": 722, "total_steps": 1230, "loss": 1.0264, "lr": 1.7424650928896726e-05, "epoch": 2.9245569620253162, "percentage": 58.7, "elapsed_time": "2:30:46", "remaining_time": "1:46:05"}
723
+ {"current_steps": 723, "total_steps": 1230, "loss": 1.0292, "lr": 1.7368375226690712e-05, "epoch": 2.9286075949367087, "percentage": 58.78, "elapsed_time": "2:30:58", "remaining_time": "1:45:52"}
724
+ {"current_steps": 724, "total_steps": 1230, "loss": 1.0492, "lr": 1.731212071922883e-05, "epoch": 2.9326582278481013, "percentage": 58.86, "elapsed_time": "2:31:11", "remaining_time": "1:45:39"}
725
+ {"current_steps": 725, "total_steps": 1230, "loss": 1.0587, "lr": 1.7255887859577156e-05, "epoch": 2.9367088607594938, "percentage": 58.94, "elapsed_time": "2:31:23", "remaining_time": "1:45:27"}
726
+ {"current_steps": 726, "total_steps": 1230, "loss": 1.0002, "lr": 1.7199677100627427e-05, "epoch": 2.9407594936708863, "percentage": 59.02, "elapsed_time": "2:31:34", "remaining_time": "1:45:13"}
727
+ {"current_steps": 727, "total_steps": 1230, "loss": 1.0168, "lr": 1.7143488895093343e-05, "epoch": 2.9448101265822784, "percentage": 59.11, "elapsed_time": "2:31:47", "remaining_time": "1:45:01"}
728
+ {"current_steps": 728, "total_steps": 1230, "loss": 1.0075, "lr": 1.7087323695506994e-05, "epoch": 2.948860759493671, "percentage": 59.19, "elapsed_time": "2:32:00", "remaining_time": "1:44:49"}
729
+ {"current_steps": 729, "total_steps": 1230, "loss": 1.046, "lr": 1.7031181954215194e-05, "epoch": 2.9529113924050634, "percentage": 59.27, "elapsed_time": "2:32:12", "remaining_time": "1:44:36"}
730
+ {"current_steps": 730, "total_steps": 1230, "loss": 1.0159, "lr": 1.6975064123375788e-05, "epoch": 2.9569620253164555, "percentage": 59.35, "elapsed_time": "2:32:25", "remaining_time": "1:44:23"}
731
+ {"current_steps": 731, "total_steps": 1230, "loss": 1.0125, "lr": 1.6918970654954084e-05, "epoch": 2.961012658227848, "percentage": 59.43, "elapsed_time": "2:32:36", "remaining_time": "1:44:10"}
732
+ {"current_steps": 732, "total_steps": 1230, "loss": 1.0451, "lr": 1.686290200071915e-05, "epoch": 2.9650632911392405, "percentage": 59.51, "elapsed_time": "2:32:49", "remaining_time": "1:43:57"}
733
+ {"current_steps": 733, "total_steps": 1230, "loss": 1.0166, "lr": 1.6806858612240234e-05, "epoch": 2.969113924050633, "percentage": 59.59, "elapsed_time": "2:33:00", "remaining_time": "1:43:44"}
734
+ {"current_steps": 734, "total_steps": 1230, "loss": 1.0102, "lr": 1.6750840940883078e-05, "epoch": 2.9731645569620255, "percentage": 59.67, "elapsed_time": "2:33:11", "remaining_time": "1:43:31"}
735
+ {"current_steps": 735, "total_steps": 1230, "loss": 1.0226, "lr": 1.6694849437806305e-05, "epoch": 2.9772151898734176, "percentage": 59.76, "elapsed_time": "2:33:23", "remaining_time": "1:43:18"}
736
+ {"current_steps": 736, "total_steps": 1230, "loss": 1.0135, "lr": 1.663888455395778e-05, "epoch": 2.98126582278481, "percentage": 59.84, "elapsed_time": "2:33:35", "remaining_time": "1:43:05"}
737
+ {"current_steps": 737, "total_steps": 1230, "loss": 1.0329, "lr": 1.6582946740070995e-05, "epoch": 2.9853164556962026, "percentage": 59.92, "elapsed_time": "2:33:47", "remaining_time": "1:42:52"}
738
+ {"current_steps": 738, "total_steps": 1230, "loss": 1.0298, "lr": 1.6527036446661396e-05, "epoch": 2.9893670886075947, "percentage": 60.0, "elapsed_time": "2:33:58", "remaining_time": "1:42:39"}
739
+ {"current_steps": 739, "total_steps": 1230, "loss": 1.0101, "lr": 1.6471154124022818e-05, "epoch": 2.993417721518987, "percentage": 60.08, "elapsed_time": "2:34:10", "remaining_time": "1:42:26"}
740
+ {"current_steps": 740, "total_steps": 1230, "loss": 1.0124, "lr": 1.6415300222223788e-05, "epoch": 2.9974683544303797, "percentage": 60.16, "elapsed_time": "2:34:26", "remaining_time": "1:42:15"}
741
+ {"current_steps": 741, "total_steps": 1230, "loss": 0.9767, "lr": 1.6359475191103958e-05, "epoch": 3.0015189873417722, "percentage": 60.24, "elapsed_time": "2:36:35", "remaining_time": "1:43:20"}
742
+ {"current_steps": 742, "total_steps": 1230, "loss": 0.8815, "lr": 1.6303679480270466e-05, "epoch": 3.0055696202531648, "percentage": 60.33, "elapsed_time": "2:36:47", "remaining_time": "1:43:07"}
743
+ {"current_steps": 743, "total_steps": 1230, "loss": 0.8533, "lr": 1.624791353909428e-05, "epoch": 3.009620253164557, "percentage": 60.41, "elapsed_time": "2:36:59", "remaining_time": "1:42:53"}
744
+ {"current_steps": 744, "total_steps": 1230, "loss": 0.8488, "lr": 1.619217781670663e-05, "epoch": 3.0136708860759494, "percentage": 60.49, "elapsed_time": "2:37:11", "remaining_time": "1:42:40"}
745
+ {"current_steps": 745, "total_steps": 1230, "loss": 0.8605, "lr": 1.6136472761995373e-05, "epoch": 3.017721518987342, "percentage": 60.57, "elapsed_time": "2:37:22", "remaining_time": "1:42:27"}
746
+ {"current_steps": 746, "total_steps": 1230, "loss": 0.8859, "lr": 1.608079882360134e-05, "epoch": 3.0217721518987344, "percentage": 60.65, "elapsed_time": "2:37:34", "remaining_time": "1:42:14"}
747
+ {"current_steps": 747, "total_steps": 1230, "loss": 0.8576, "lr": 1.60251564499148e-05, "epoch": 3.0258227848101265, "percentage": 60.73, "elapsed_time": "2:37:47", "remaining_time": "1:42:01"}
748
+ {"current_steps": 748, "total_steps": 1230, "loss": 0.8382, "lr": 1.596954608907176e-05, "epoch": 3.029873417721519, "percentage": 60.81, "elapsed_time": "2:38:01", "remaining_time": "1:41:50"}
749
+ {"current_steps": 749, "total_steps": 1230, "loss": 0.8637, "lr": 1.591396818895043e-05, "epoch": 3.0339240506329115, "percentage": 60.89, "elapsed_time": "2:38:13", "remaining_time": "1:41:36"}
750
+ {"current_steps": 750, "total_steps": 1230, "loss": 0.8703, "lr": 1.585842319716759e-05, "epoch": 3.037974683544304, "percentage": 60.98, "elapsed_time": "2:38:25", "remaining_time": "1:41:23"}
751
+ {"current_steps": 751, "total_steps": 1230, "loss": 0.8489, "lr": 1.5802911561074944e-05, "epoch": 3.042025316455696, "percentage": 61.06, "elapsed_time": "2:38:36", "remaining_time": "1:41:10"}