neginr commited on
Commit
8973e34
·
verified ·
1 Parent(s): c9bd09b

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 sha256:5b12fe07f8e4f0880a03ed4199ccc4887af3927d7a8f0f43b98b452c1e8bbcee
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb0aff33c5a3343d59d502322b650667232e893e423630914912b4bd304bef7c
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:721914edacbfdb5e130c8319a1e60e1bc1b374c1a5ce35c926d53206b74d0d7c
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:324f9e67702446806779d701e8f4cbc436fa8b5e3d1b53fb1a8e2d0f7dd61cee
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:663df5ba6aaf37038103452f495da14fa22d52481d706cc66603e6821312a417
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fcb27cb140de55db04d57f39c73baf70516dd7740392005c913d642c162098da
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:318c7c2ba4257b047f562ef7c7c37aae47d387cf16ab148adeacfabdb219acfb
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f374c1cf9bc9ca793f72505ce0fad95d327437a733b1047977dc6e8e90b83bb
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -533,3 +533,250 @@
533
  {"current_steps": 497, "total_steps": 1230, "loss": 0.3695, "lr": 2.9753229259313578e-05, "epoch": 2.013164556962025, "percentage": 40.41, "elapsed_time": "4:32:09", "remaining_time": "6:41:24"}
534
  {"current_steps": 498, "total_steps": 1230, "loss": 0.3833, "lr": 2.9703637864506274e-05, "epoch": 2.0172151898734176, "percentage": 40.49, "elapsed_time": "4:32:39", "remaining_time": "6:40:45"}
535
  {"current_steps": 499, "total_steps": 1230, "loss": 0.3491, "lr": 2.965396831793362e-05, "epoch": 2.02126582278481, "percentage": 40.57, "elapsed_time": "4:33:07", "remaining_time": "6:40:06"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
533
  {"current_steps": 497, "total_steps": 1230, "loss": 0.3695, "lr": 2.9753229259313578e-05, "epoch": 2.013164556962025, "percentage": 40.41, "elapsed_time": "4:32:09", "remaining_time": "6:41:24"}
534
  {"current_steps": 498, "total_steps": 1230, "loss": 0.3833, "lr": 2.9703637864506274e-05, "epoch": 2.0172151898734176, "percentage": 40.49, "elapsed_time": "4:32:39", "remaining_time": "6:40:45"}
535
  {"current_steps": 499, "total_steps": 1230, "loss": 0.3491, "lr": 2.965396831793362e-05, "epoch": 2.02126582278481, "percentage": 40.57, "elapsed_time": "4:33:07", "remaining_time": "6:40:06"}
536
+ {"current_steps": 500, "total_steps": 1230, "loss": 0.3933, "lr": 2.9604221019627316e-05, "epoch": 2.0253164556962027, "percentage": 40.65, "elapsed_time": "4:33:39", "remaining_time": "6:39:32"}
537
+ {"current_steps": 501, "total_steps": 1230, "loss": 0.384, "lr": 2.955439637024526e-05, "epoch": 2.0293670886075947, "percentage": 40.73, "elapsed_time": "4:34:13", "remaining_time": "6:39:01"}
538
+ {"current_steps": 502, "total_steps": 1230, "loss": 0.3781, "lr": 2.9504494771068334e-05, "epoch": 2.0334177215189873, "percentage": 40.81, "elapsed_time": "4:34:48", "remaining_time": "6:38:31"}
539
+ {"current_steps": 503, "total_steps": 1230, "loss": 0.3875, "lr": 2.9454516623997156e-05, "epoch": 2.0374683544303798, "percentage": 40.89, "elapsed_time": "4:35:20", "remaining_time": "6:37:57"}
540
+ {"current_steps": 504, "total_steps": 1230, "loss": 0.3735, "lr": 2.9404462331548847e-05, "epoch": 2.0415189873417723, "percentage": 40.98, "elapsed_time": "4:35:58", "remaining_time": "6:37:32"}
541
+ {"current_steps": 505, "total_steps": 1230, "loss": 0.3778, "lr": 2.93543322968538e-05, "epoch": 2.0455696202531644, "percentage": 41.06, "elapsed_time": "4:36:35", "remaining_time": "6:37:04"}
542
+ {"current_steps": 506, "total_steps": 1230, "loss": 0.3545, "lr": 2.9304126923652428e-05, "epoch": 2.049620253164557, "percentage": 41.14, "elapsed_time": "4:37:08", "remaining_time": "6:36:32"}
543
+ {"current_steps": 507, "total_steps": 1230, "loss": 0.3692, "lr": 2.9253846616291896e-05, "epoch": 2.0536708860759494, "percentage": 41.22, "elapsed_time": "4:37:45", "remaining_time": "6:36:05"}
544
+ {"current_steps": 508, "total_steps": 1230, "loss": 0.3739, "lr": 2.9203491779722896e-05, "epoch": 2.057721518987342, "percentage": 41.3, "elapsed_time": "4:38:20", "remaining_time": "6:35:35"}
545
+ {"current_steps": 509, "total_steps": 1230, "loss": 0.39, "lr": 2.9153062819496357e-05, "epoch": 2.061772151898734, "percentage": 41.38, "elapsed_time": "4:38:51", "remaining_time": "6:34:59"}
546
+ {"current_steps": 510, "total_steps": 1230, "loss": 0.3735, "lr": 2.9102560141760178e-05, "epoch": 2.0658227848101265, "percentage": 41.46, "elapsed_time": "4:39:26", "remaining_time": "6:34:30"}
547
+ {"current_steps": 511, "total_steps": 1230, "loss": 0.3757, "lr": 2.9051984153256004e-05, "epoch": 2.069873417721519, "percentage": 41.54, "elapsed_time": "4:39:57", "remaining_time": "6:33:54"}
548
+ {"current_steps": 512, "total_steps": 1230, "loss": 0.3666, "lr": 2.900133526131588e-05, "epoch": 2.0739240506329115, "percentage": 41.63, "elapsed_time": "4:40:30", "remaining_time": "6:33:21"}
549
+ {"current_steps": 513, "total_steps": 1230, "loss": 0.3782, "lr": 2.8950613873859025e-05, "epoch": 2.0779746835443036, "percentage": 41.71, "elapsed_time": "4:40:58", "remaining_time": "6:32:42"}
550
+ {"current_steps": 514, "total_steps": 1230, "loss": 0.3714, "lr": 2.8899820399388515e-05, "epoch": 2.082025316455696, "percentage": 41.79, "elapsed_time": "4:41:28", "remaining_time": "6:32:06"}
551
+ {"current_steps": 515, "total_steps": 1230, "loss": 0.3787, "lr": 2.8848955246988012e-05, "epoch": 2.0860759493670886, "percentage": 41.87, "elapsed_time": "4:41:59", "remaining_time": "6:31:30"}
552
+ {"current_steps": 516, "total_steps": 1230, "loss": 0.3712, "lr": 2.879801882631847e-05, "epoch": 2.090126582278481, "percentage": 41.95, "elapsed_time": "4:42:33", "remaining_time": "6:30:58"}
553
+ {"current_steps": 517, "total_steps": 1230, "loss": 0.377, "lr": 2.8747011547614808e-05, "epoch": 2.094177215189873, "percentage": 42.03, "elapsed_time": "4:43:05", "remaining_time": "6:30:25"}
554
+ {"current_steps": 518, "total_steps": 1230, "loss": 0.3874, "lr": 2.8695933821682635e-05, "epoch": 2.0982278481012657, "percentage": 42.11, "elapsed_time": "4:43:38", "remaining_time": "6:29:51"}
555
+ {"current_steps": 519, "total_steps": 1230, "loss": 0.3664, "lr": 2.864478605989494e-05, "epoch": 2.1022784810126582, "percentage": 42.2, "elapsed_time": "4:44:09", "remaining_time": "6:29:17"}
556
+ {"current_steps": 520, "total_steps": 1230, "loss": 0.3751, "lr": 2.8593568674188765e-05, "epoch": 2.1063291139240508, "percentage": 42.28, "elapsed_time": "4:44:38", "remaining_time": "6:28:38"}
557
+ {"current_steps": 521, "total_steps": 1230, "loss": 0.3851, "lr": 2.8542282077061892e-05, "epoch": 2.110379746835443, "percentage": 42.36, "elapsed_time": "4:45:10", "remaining_time": "6:28:04"}
558
+ {"current_steps": 522, "total_steps": 1230, "loss": 0.3636, "lr": 2.8490926681569523e-05, "epoch": 2.1144303797468353, "percentage": 42.44, "elapsed_time": "4:45:41", "remaining_time": "6:27:28"}
559
+ {"current_steps": 523, "total_steps": 1230, "loss": 0.3736, "lr": 2.8439502901320956e-05, "epoch": 2.118481012658228, "percentage": 42.52, "elapsed_time": "4:46:14", "remaining_time": "6:26:56"}
560
+ {"current_steps": 524, "total_steps": 1230, "loss": 0.3452, "lr": 2.8388011150476237e-05, "epoch": 2.1225316455696204, "percentage": 42.6, "elapsed_time": "4:46:43", "remaining_time": "6:26:18"}
561
+ {"current_steps": 525, "total_steps": 1230, "loss": 0.3926, "lr": 2.8336451843742866e-05, "epoch": 2.1265822784810124, "percentage": 42.68, "elapsed_time": "4:47:13", "remaining_time": "6:25:42"}
562
+ {"current_steps": 526, "total_steps": 1230, "loss": 0.373, "lr": 2.8284825396372387e-05, "epoch": 2.130632911392405, "percentage": 42.76, "elapsed_time": "4:47:49", "remaining_time": "6:25:13"}
563
+ {"current_steps": 527, "total_steps": 1230, "loss": 0.3671, "lr": 2.8233132224157132e-05, "epoch": 2.1346835443037975, "percentage": 42.85, "elapsed_time": "4:48:20", "remaining_time": "6:24:38"}
564
+ {"current_steps": 528, "total_steps": 1230, "loss": 0.3673, "lr": 2.8181372743426805e-05, "epoch": 2.13873417721519, "percentage": 42.93, "elapsed_time": "4:48:50", "remaining_time": "6:24:02"}
565
+ {"current_steps": 529, "total_steps": 1230, "loss": 0.3543, "lr": 2.8129547371045128e-05, "epoch": 2.1427848101265825, "percentage": 43.01, "elapsed_time": "4:49:19", "remaining_time": "6:23:23"}
566
+ {"current_steps": 530, "total_steps": 1230, "loss": 0.3781, "lr": 2.8077656524406534e-05, "epoch": 2.1468354430379746, "percentage": 43.09, "elapsed_time": "4:49:45", "remaining_time": "6:22:42"}
567
+ {"current_steps": 531, "total_steps": 1230, "loss": 0.3966, "lr": 2.802570062143278e-05, "epoch": 2.150886075949367, "percentage": 43.17, "elapsed_time": "4:50:11", "remaining_time": "6:21:59"}
568
+ {"current_steps": 532, "total_steps": 1230, "loss": 0.3757, "lr": 2.7973680080569555e-05, "epoch": 2.1549367088607596, "percentage": 43.25, "elapsed_time": "4:50:41", "remaining_time": "6:21:23"}
569
+ {"current_steps": 533, "total_steps": 1230, "loss": 0.3779, "lr": 2.792159532078314e-05, "epoch": 2.1589873417721517, "percentage": 43.33, "elapsed_time": "4:51:11", "remaining_time": "6:20:47"}
570
+ {"current_steps": 534, "total_steps": 1230, "loss": 0.3887, "lr": 2.7869446761557033e-05, "epoch": 2.163037974683544, "percentage": 43.41, "elapsed_time": "4:51:43", "remaining_time": "6:20:13"}
571
+ {"current_steps": 535, "total_steps": 1230, "loss": 0.3792, "lr": 2.781723482288857e-05, "epoch": 2.1670886075949367, "percentage": 43.5, "elapsed_time": "4:52:13", "remaining_time": "6:19:37"}
572
+ {"current_steps": 536, "total_steps": 1230, "loss": 0.3795, "lr": 2.7764959925285517e-05, "epoch": 2.1711392405063292, "percentage": 43.58, "elapsed_time": "4:52:44", "remaining_time": "6:19:02"}
573
+ {"current_steps": 537, "total_steps": 1230, "loss": 0.3641, "lr": 2.771262248976272e-05, "epoch": 2.1751898734177217, "percentage": 43.66, "elapsed_time": "4:53:17", "remaining_time": "6:18:29"}
574
+ {"current_steps": 538, "total_steps": 1230, "loss": 0.3713, "lr": 2.7660222937838677e-05, "epoch": 2.179240506329114, "percentage": 43.74, "elapsed_time": "4:53:52", "remaining_time": "6:17:59"}
575
+ {"current_steps": 539, "total_steps": 1230, "loss": 0.3958, "lr": 2.7607761691532186e-05, "epoch": 2.1832911392405063, "percentage": 43.82, "elapsed_time": "4:54:28", "remaining_time": "6:17:31"}
576
+ {"current_steps": 540, "total_steps": 1230, "loss": 0.3912, "lr": 2.7555239173358916e-05, "epoch": 2.187341772151899, "percentage": 43.9, "elapsed_time": "4:55:02", "remaining_time": "6:16:59"}
577
+ {"current_steps": 541, "total_steps": 1230, "loss": 0.3784, "lr": 2.7502655806328e-05, "epoch": 2.191392405063291, "percentage": 43.98, "elapsed_time": "4:55:34", "remaining_time": "6:16:25"}
578
+ {"current_steps": 542, "total_steps": 1230, "loss": 0.3658, "lr": 2.7450012013938648e-05, "epoch": 2.1954430379746834, "percentage": 44.07, "elapsed_time": "4:56:06", "remaining_time": "6:15:51"}
579
+ {"current_steps": 543, "total_steps": 1230, "loss": 0.3766, "lr": 2.739730822017673e-05, "epoch": 2.199493670886076, "percentage": 44.15, "elapsed_time": "4:56:36", "remaining_time": "6:15:15"}
580
+ {"current_steps": 544, "total_steps": 1230, "loss": 0.37, "lr": 2.7344544849511355e-05, "epoch": 2.2035443037974685, "percentage": 44.23, "elapsed_time": "4:57:05", "remaining_time": "6:14:38"}
581
+ {"current_steps": 545, "total_steps": 1230, "loss": 0.3662, "lr": 2.7291722326891456e-05, "epoch": 2.207594936708861, "percentage": 44.31, "elapsed_time": "4:57:35", "remaining_time": "6:14:01"}
582
+ {"current_steps": 546, "total_steps": 1230, "loss": 0.3715, "lr": 2.723884107774236e-05, "epoch": 2.211645569620253, "percentage": 44.39, "elapsed_time": "4:58:07", "remaining_time": "6:13:27"}
583
+ {"current_steps": 547, "total_steps": 1230, "loss": 0.3779, "lr": 2.718590152796239e-05, "epoch": 2.2156962025316456, "percentage": 44.47, "elapsed_time": "4:58:36", "remaining_time": "6:12:50"}
584
+ {"current_steps": 548, "total_steps": 1230, "loss": 0.3765, "lr": 2.71329041039194e-05, "epoch": 2.219746835443038, "percentage": 44.55, "elapsed_time": "4:59:08", "remaining_time": "6:12:17"}
585
+ {"current_steps": 549, "total_steps": 1230, "loss": 0.3741, "lr": 2.7079849232447357e-05, "epoch": 2.22379746835443, "percentage": 44.63, "elapsed_time": "4:59:40", "remaining_time": "6:11:43"}
586
+ {"current_steps": 550, "total_steps": 1230, "loss": 0.3664, "lr": 2.7026737340842895e-05, "epoch": 2.2278481012658227, "percentage": 44.72, "elapsed_time": "5:00:14", "remaining_time": "6:11:12"}
587
+ {"current_steps": 551, "total_steps": 1230, "loss": 0.3898, "lr": 2.697356885686189e-05, "epoch": 2.231898734177215, "percentage": 44.8, "elapsed_time": "5:00:47", "remaining_time": "6:10:39"}
588
+ {"current_steps": 552, "total_steps": 1230, "loss": 0.3889, "lr": 2.6920344208716014e-05, "epoch": 2.2359493670886077, "percentage": 44.88, "elapsed_time": "5:01:19", "remaining_time": "6:10:06"}
589
+ {"current_steps": 553, "total_steps": 1230, "loss": 0.3865, "lr": 2.6867063825069252e-05, "epoch": 2.24, "percentage": 44.96, "elapsed_time": "5:01:53", "remaining_time": "6:09:35"}
590
+ {"current_steps": 554, "total_steps": 1230, "loss": 0.3858, "lr": 2.6813728135034494e-05, "epoch": 2.2440506329113923, "percentage": 45.04, "elapsed_time": "5:02:26", "remaining_time": "6:09:02"}
591
+ {"current_steps": 555, "total_steps": 1230, "loss": 0.3842, "lr": 2.6760337568170056e-05, "epoch": 2.248101265822785, "percentage": 45.12, "elapsed_time": "5:02:58", "remaining_time": "6:08:29"}
592
+ {"current_steps": 556, "total_steps": 1230, "loss": 0.3687, "lr": 2.6706892554476226e-05, "epoch": 2.2521518987341773, "percentage": 45.2, "elapsed_time": "5:03:28", "remaining_time": "6:07:53"}
593
+ {"current_steps": 557, "total_steps": 1230, "loss": 0.3806, "lr": 2.6653393524391795e-05, "epoch": 2.2562025316455694, "percentage": 45.28, "elapsed_time": "5:04:02", "remaining_time": "6:07:21"}
594
+ {"current_steps": 558, "total_steps": 1230, "loss": 0.3882, "lr": 2.6599840908790592e-05, "epoch": 2.260253164556962, "percentage": 45.37, "elapsed_time": "5:04:35", "remaining_time": "6:06:48"}
595
+ {"current_steps": 559, "total_steps": 1230, "loss": 0.3694, "lr": 2.6546235138978028e-05, "epoch": 2.2643037974683544, "percentage": 45.45, "elapsed_time": "5:05:04", "remaining_time": "6:06:11"}
596
+ {"current_steps": 560, "total_steps": 1230, "loss": 0.3893, "lr": 2.6492576646687597e-05, "epoch": 2.268354430379747, "percentage": 45.53, "elapsed_time": "5:05:31", "remaining_time": "6:05:32"}
597
+ {"current_steps": 561, "total_steps": 1230, "loss": 0.3833, "lr": 2.6438865864077425e-05, "epoch": 2.2724050632911394, "percentage": 45.61, "elapsed_time": "5:06:04", "remaining_time": "6:04:59"}
598
+ {"current_steps": 562, "total_steps": 1230, "loss": 0.3665, "lr": 2.6385103223726766e-05, "epoch": 2.2764556962025315, "percentage": 45.69, "elapsed_time": "5:06:40", "remaining_time": "6:04:30"}
599
+ {"current_steps": 563, "total_steps": 1230, "loss": 0.3718, "lr": 2.6331289158632537e-05, "epoch": 2.280506329113924, "percentage": 45.77, "elapsed_time": "5:07:13", "remaining_time": "6:03:58"}
600
+ {"current_steps": 564, "total_steps": 1230, "loss": 0.3782, "lr": 2.6277424102205817e-05, "epoch": 2.2845569620253166, "percentage": 45.85, "elapsed_time": "5:07:47", "remaining_time": "6:03:27"}
601
+ {"current_steps": 565, "total_steps": 1230, "loss": 0.3724, "lr": 2.6223508488268374e-05, "epoch": 2.2886075949367086, "percentage": 45.93, "elapsed_time": "5:08:25", "remaining_time": "6:03:00"}
602
+ {"current_steps": 566, "total_steps": 1230, "loss": 0.375, "lr": 2.6169542751049148e-05, "epoch": 2.292658227848101, "percentage": 46.02, "elapsed_time": "5:09:00", "remaining_time": "6:02:30"}
603
+ {"current_steps": 567, "total_steps": 1230, "loss": 0.3882, "lr": 2.6115527325180754e-05, "epoch": 2.2967088607594937, "percentage": 46.1, "elapsed_time": "5:09:33", "remaining_time": "6:01:58"}
604
+ {"current_steps": 568, "total_steps": 1230, "loss": 0.3757, "lr": 2.606146264569603e-05, "epoch": 2.300759493670886, "percentage": 46.18, "elapsed_time": "5:10:08", "remaining_time": "6:01:28"}
605
+ {"current_steps": 569, "total_steps": 1230, "loss": 0.3647, "lr": 2.6007349148024447e-05, "epoch": 2.3048101265822787, "percentage": 46.26, "elapsed_time": "5:10:34", "remaining_time": "6:00:47"}
606
+ {"current_steps": 570, "total_steps": 1230, "loss": 0.3851, "lr": 2.5953187267988694e-05, "epoch": 2.3088607594936708, "percentage": 46.34, "elapsed_time": "5:11:11", "remaining_time": "6:00:19"}
607
+ {"current_steps": 571, "total_steps": 1230, "loss": 0.3777, "lr": 2.5898977441801097e-05, "epoch": 2.3129113924050633, "percentage": 46.42, "elapsed_time": "5:11:41", "remaining_time": "5:59:43"}
608
+ {"current_steps": 572, "total_steps": 1230, "loss": 0.3783, "lr": 2.584472010606015e-05, "epoch": 2.316962025316456, "percentage": 46.5, "elapsed_time": "5:12:16", "remaining_time": "5:59:13"}
609
+ {"current_steps": 573, "total_steps": 1230, "loss": 0.3785, "lr": 2.5790415697746976e-05, "epoch": 2.321012658227848, "percentage": 46.59, "elapsed_time": "5:12:51", "remaining_time": "5:58:42"}
610
+ {"current_steps": 574, "total_steps": 1230, "loss": 0.3942, "lr": 2.5736064654221808e-05, "epoch": 2.3250632911392404, "percentage": 46.67, "elapsed_time": "5:13:23", "remaining_time": "5:58:09"}
611
+ {"current_steps": 575, "total_steps": 1230, "loss": 0.3714, "lr": 2.568166741322048e-05, "epoch": 2.329113924050633, "percentage": 46.75, "elapsed_time": "5:13:54", "remaining_time": "5:57:34"}
612
+ {"current_steps": 576, "total_steps": 1230, "loss": 0.3943, "lr": 2.56272244128509e-05, "epoch": 2.3331645569620254, "percentage": 46.83, "elapsed_time": "5:14:25", "remaining_time": "5:56:59"}
613
+ {"current_steps": 577, "total_steps": 1230, "loss": 0.3847, "lr": 2.55727360915895e-05, "epoch": 2.337215189873418, "percentage": 46.91, "elapsed_time": "5:14:55", "remaining_time": "5:56:24"}
614
+ {"current_steps": 578, "total_steps": 1230, "loss": 0.3773, "lr": 2.5518202888277734e-05, "epoch": 2.34126582278481, "percentage": 46.99, "elapsed_time": "5:15:34", "remaining_time": "5:55:58"}
615
+ {"current_steps": 579, "total_steps": 1230, "loss": 0.3925, "lr": 2.5463625242118523e-05, "epoch": 2.3453164556962025, "percentage": 47.07, "elapsed_time": "5:16:13", "remaining_time": "5:55:32"}
616
+ {"current_steps": 580, "total_steps": 1230, "loss": 0.3817, "lr": 2.5409003592672723e-05, "epoch": 2.349367088607595, "percentage": 47.15, "elapsed_time": "5:16:46", "remaining_time": "5:54:59"}
617
+ {"current_steps": 581, "total_steps": 1230, "loss": 0.3709, "lr": 2.535433837985559e-05, "epoch": 2.353417721518987, "percentage": 47.24, "elapsed_time": "5:17:20", "remaining_time": "5:54:28"}
618
+ {"current_steps": 582, "total_steps": 1230, "loss": 0.3964, "lr": 2.529963004393324e-05, "epoch": 2.3574683544303796, "percentage": 47.32, "elapsed_time": "5:17:52", "remaining_time": "5:53:54"}
619
+ {"current_steps": 583, "total_steps": 1230, "loss": 0.3799, "lr": 2.524487902551908e-05, "epoch": 2.361518987341772, "percentage": 47.4, "elapsed_time": "5:18:26", "remaining_time": "5:53:23"}
620
+ {"current_steps": 584, "total_steps": 1230, "loss": 0.3899, "lr": 2.519008576557029e-05, "epoch": 2.3655696202531646, "percentage": 47.48, "elapsed_time": "5:18:59", "remaining_time": "5:52:51"}
621
+ {"current_steps": 585, "total_steps": 1230, "loss": 0.4073, "lr": 2.5135250705384254e-05, "epoch": 2.369620253164557, "percentage": 47.56, "elapsed_time": "5:19:36", "remaining_time": "5:52:23"}
622
+ {"current_steps": 586, "total_steps": 1230, "loss": 0.3902, "lr": 2.5080374286595007e-05, "epoch": 2.3736708860759492, "percentage": 47.64, "elapsed_time": "5:20:06", "remaining_time": "5:51:47"}
623
+ {"current_steps": 587, "total_steps": 1230, "loss": 0.389, "lr": 2.5025456951169677e-05, "epoch": 2.3777215189873417, "percentage": 47.72, "elapsed_time": "5:20:41", "remaining_time": "5:51:17"}
624
+ {"current_steps": 588, "total_steps": 1230, "loss": 0.3923, "lr": 2.4970499141404942e-05, "epoch": 2.3817721518987343, "percentage": 47.8, "elapsed_time": "5:21:09", "remaining_time": "5:50:39"}
625
+ {"current_steps": 589, "total_steps": 1230, "loss": 0.3738, "lr": 2.491550129992345e-05, "epoch": 2.3858227848101268, "percentage": 47.89, "elapsed_time": "5:21:41", "remaining_time": "5:50:05"}
626
+ {"current_steps": 590, "total_steps": 1230, "loss": 0.3757, "lr": 2.486046386967024e-05, "epoch": 2.389873417721519, "percentage": 47.97, "elapsed_time": "5:22:15", "remaining_time": "5:49:34"}
627
+ {"current_steps": 591, "total_steps": 1230, "loss": 0.3855, "lr": 2.4805387293909214e-05, "epoch": 2.3939240506329114, "percentage": 48.05, "elapsed_time": "5:22:43", "remaining_time": "5:48:56"}
628
+ {"current_steps": 592, "total_steps": 1230, "loss": 0.3772, "lr": 2.4750272016219552e-05, "epoch": 2.397974683544304, "percentage": 48.13, "elapsed_time": "5:23:16", "remaining_time": "5:48:23"}
629
+ {"current_steps": 593, "total_steps": 1230, "loss": 0.3713, "lr": 2.4695118480492114e-05, "epoch": 2.4020253164556964, "percentage": 48.21, "elapsed_time": "5:23:45", "remaining_time": "5:47:46"}
630
+ {"current_steps": 594, "total_steps": 1230, "loss": 0.3843, "lr": 2.4639927130925898e-05, "epoch": 2.4060759493670885, "percentage": 48.29, "elapsed_time": "5:24:14", "remaining_time": "5:47:10"}
631
+ {"current_steps": 595, "total_steps": 1230, "loss": 0.3894, "lr": 2.458469841202444e-05, "epoch": 2.410126582278481, "percentage": 48.37, "elapsed_time": "5:24:48", "remaining_time": "5:46:38"}
632
+ {"current_steps": 596, "total_steps": 1230, "loss": 0.387, "lr": 2.452943276859226e-05, "epoch": 2.4141772151898735, "percentage": 48.46, "elapsed_time": "5:25:26", "remaining_time": "5:46:11"}
633
+ {"current_steps": 597, "total_steps": 1230, "loss": 0.3873, "lr": 2.447413064573125e-05, "epoch": 2.418227848101266, "percentage": 48.54, "elapsed_time": "5:26:01", "remaining_time": "5:45:41"}
634
+ {"current_steps": 598, "total_steps": 1230, "loss": 0.3745, "lr": 2.4418792488837095e-05, "epoch": 2.422278481012658, "percentage": 48.62, "elapsed_time": "5:26:35", "remaining_time": "5:45:10"}
635
+ {"current_steps": 599, "total_steps": 1230, "loss": 0.3623, "lr": 2.4363418743595713e-05, "epoch": 2.4263291139240506, "percentage": 48.7, "elapsed_time": "5:27:08", "remaining_time": "5:44:36"}
636
+ {"current_steps": 600, "total_steps": 1230, "loss": 0.3669, "lr": 2.430800985597963e-05, "epoch": 2.430379746835443, "percentage": 48.78, "elapsed_time": "5:27:40", "remaining_time": "5:44:03"}
637
+ {"current_steps": 601, "total_steps": 1230, "loss": 0.3794, "lr": 2.4252566272244415e-05, "epoch": 2.4344303797468356, "percentage": 48.86, "elapsed_time": "5:28:10", "remaining_time": "5:43:27"}
638
+ {"current_steps": 602, "total_steps": 1230, "loss": 0.3846, "lr": 2.4197088438925063e-05, "epoch": 2.4384810126582277, "percentage": 48.94, "elapsed_time": "5:28:38", "remaining_time": "5:42:49"}
639
+ {"current_steps": 603, "total_steps": 1230, "loss": 0.3865, "lr": 2.4141576802832417e-05, "epoch": 2.44253164556962, "percentage": 49.02, "elapsed_time": "5:29:12", "remaining_time": "5:42:18"}
640
+ {"current_steps": 604, "total_steps": 1230, "loss": 0.3885, "lr": 2.408603181104957e-05, "epoch": 2.4465822784810127, "percentage": 49.11, "elapsed_time": "5:29:38", "remaining_time": "5:41:39"}
641
+ {"current_steps": 605, "total_steps": 1230, "loss": 0.3955, "lr": 2.4030453910928245e-05, "epoch": 2.4506329113924052, "percentage": 49.19, "elapsed_time": "5:30:13", "remaining_time": "5:41:08"}
642
+ {"current_steps": 606, "total_steps": 1230, "loss": 0.3931, "lr": 2.397484355008521e-05, "epoch": 2.4546835443037973, "percentage": 49.27, "elapsed_time": "5:30:44", "remaining_time": "5:40:34"}
643
+ {"current_steps": 607, "total_steps": 1230, "loss": 0.3684, "lr": 2.3919201176398662e-05, "epoch": 2.45873417721519, "percentage": 49.35, "elapsed_time": "5:31:12", "remaining_time": "5:39:56"}
644
+ {"current_steps": 608, "total_steps": 1230, "loss": 0.3733, "lr": 2.3863527238004633e-05, "epoch": 2.4627848101265823, "percentage": 49.43, "elapsed_time": "5:31:49", "remaining_time": "5:39:27"}
645
+ {"current_steps": 609, "total_steps": 1230, "loss": 0.3792, "lr": 2.380782218329337e-05, "epoch": 2.466835443037975, "percentage": 49.51, "elapsed_time": "5:32:19", "remaining_time": "5:38:52"}
646
+ {"current_steps": 610, "total_steps": 1230, "loss": 0.3837, "lr": 2.3752086460905725e-05, "epoch": 2.470886075949367, "percentage": 49.59, "elapsed_time": "5:32:54", "remaining_time": "5:38:21"}
647
+ {"current_steps": 611, "total_steps": 1230, "loss": 0.3674, "lr": 2.3696320519729544e-05, "epoch": 2.4749367088607594, "percentage": 49.67, "elapsed_time": "5:33:26", "remaining_time": "5:37:48"}
648
+ {"current_steps": 612, "total_steps": 1230, "loss": 0.3892, "lr": 2.3640524808896045e-05, "epoch": 2.478987341772152, "percentage": 49.76, "elapsed_time": "5:34:02", "remaining_time": "5:37:18"}
649
+ {"current_steps": 613, "total_steps": 1230, "loss": 0.3731, "lr": 2.3584699777776222e-05, "epoch": 2.4830379746835445, "percentage": 49.84, "elapsed_time": "5:34:35", "remaining_time": "5:36:46"}
650
+ {"current_steps": 614, "total_steps": 1230, "loss": 0.3861, "lr": 2.3528845875977195e-05, "epoch": 2.4870886075949366, "percentage": 49.92, "elapsed_time": "5:35:08", "remaining_time": "5:36:13"}
651
+ {"current_steps": 615, "total_steps": 1230, "loss": 0.3709, "lr": 2.3472963553338614e-05, "epoch": 2.491139240506329, "percentage": 50.0, "elapsed_time": "5:35:35", "remaining_time": "5:35:35"}
652
+ {"current_steps": 616, "total_steps": 1230, "loss": 0.3873, "lr": 2.341705325992901e-05, "epoch": 2.4951898734177216, "percentage": 50.08, "elapsed_time": "5:36:10", "remaining_time": "5:35:05"}
653
+ {"current_steps": 617, "total_steps": 1230, "loss": 0.3871, "lr": 2.336111544604222e-05, "epoch": 2.499240506329114, "percentage": 50.16, "elapsed_time": "5:36:40", "remaining_time": "5:34:29"}
654
+ {"current_steps": 618, "total_steps": 1230, "loss": 0.3776, "lr": 2.33051505621937e-05, "epoch": 2.503291139240506, "percentage": 50.24, "elapsed_time": "5:37:08", "remaining_time": "5:33:51"}
655
+ {"current_steps": 619, "total_steps": 1230, "loss": 0.3842, "lr": 2.324915905911693e-05, "epoch": 2.5073417721518987, "percentage": 50.33, "elapsed_time": "5:37:43", "remaining_time": "5:33:21"}
656
+ {"current_steps": 620, "total_steps": 1230, "loss": 0.3835, "lr": 2.319314138775977e-05, "epoch": 2.511392405063291, "percentage": 50.41, "elapsed_time": "5:38:14", "remaining_time": "5:32:47"}
657
+ {"current_steps": 621, "total_steps": 1230, "loss": 0.3859, "lr": 2.3137097999280856e-05, "epoch": 2.5154430379746833, "percentage": 50.49, "elapsed_time": "5:38:47", "remaining_time": "5:32:14"}
658
+ {"current_steps": 622, "total_steps": 1230, "loss": 0.3549, "lr": 2.308102934504593e-05, "epoch": 2.519493670886076, "percentage": 50.57, "elapsed_time": "5:39:21", "remaining_time": "5:31:43"}
659
+ {"current_steps": 623, "total_steps": 1230, "loss": 0.3802, "lr": 2.3024935876624222e-05, "epoch": 2.5235443037974683, "percentage": 50.65, "elapsed_time": "5:39:50", "remaining_time": "5:31:06"}
660
+ {"current_steps": 624, "total_steps": 1230, "loss": 0.3795, "lr": 2.2968818045784813e-05, "epoch": 2.527594936708861, "percentage": 50.73, "elapsed_time": "5:40:23", "remaining_time": "5:30:34"}
661
+ {"current_steps": 625, "total_steps": 1230, "loss": 0.3666, "lr": 2.2912676304493006e-05, "epoch": 2.5316455696202533, "percentage": 50.81, "elapsed_time": "5:40:53", "remaining_time": "5:29:59"}
662
+ {"current_steps": 626, "total_steps": 1230, "loss": 0.3825, "lr": 2.2856511104906668e-05, "epoch": 2.5356962025316454, "percentage": 50.89, "elapsed_time": "5:41:24", "remaining_time": "5:29:24"}
663
+ {"current_steps": 627, "total_steps": 1230, "loss": 0.3683, "lr": 2.2800322899372586e-05, "epoch": 2.539746835443038, "percentage": 50.98, "elapsed_time": "5:41:52", "remaining_time": "5:28:47"}
664
+ {"current_steps": 628, "total_steps": 1230, "loss": 0.3654, "lr": 2.2744112140422844e-05, "epoch": 2.5437974683544304, "percentage": 51.06, "elapsed_time": "5:42:25", "remaining_time": "5:28:14"}
665
+ {"current_steps": 629, "total_steps": 1230, "loss": 0.4044, "lr": 2.2687879280771177e-05, "epoch": 2.547848101265823, "percentage": 51.14, "elapsed_time": "5:43:00", "remaining_time": "5:27:44"}
666
+ {"current_steps": 630, "total_steps": 1230, "loss": 0.3699, "lr": 2.26316247733093e-05, "epoch": 2.5518987341772155, "percentage": 51.22, "elapsed_time": "5:43:35", "remaining_time": "5:27:13"}
667
+ {"current_steps": 631, "total_steps": 1230, "loss": 0.3717, "lr": 2.257534907110328e-05, "epoch": 2.5559493670886075, "percentage": 51.3, "elapsed_time": "5:44:08", "remaining_time": "5:26:40"}
668
+ {"current_steps": 632, "total_steps": 1230, "loss": 0.3712, "lr": 2.2519052627389882e-05, "epoch": 2.56, "percentage": 51.38, "elapsed_time": "5:44:42", "remaining_time": "5:26:09"}
669
+ {"current_steps": 633, "total_steps": 1230, "loss": 0.3699, "lr": 2.246273589557294e-05, "epoch": 2.5640506329113926, "percentage": 51.46, "elapsed_time": "5:45:13", "remaining_time": "5:25:35"}
670
+ {"current_steps": 634, "total_steps": 1230, "loss": 0.366, "lr": 2.240639932921966e-05, "epoch": 2.5681012658227846, "percentage": 51.54, "elapsed_time": "5:45:41", "remaining_time": "5:24:58"}
671
+ {"current_steps": 635, "total_steps": 1230, "loss": 0.3686, "lr": 2.2350043382056995e-05, "epoch": 2.572151898734177, "percentage": 51.63, "elapsed_time": "5:46:06", "remaining_time": "5:24:18"}
672
+ {"current_steps": 636, "total_steps": 1230, "loss": 0.3843, "lr": 2.2293668507968015e-05, "epoch": 2.5762025316455697, "percentage": 51.71, "elapsed_time": "5:46:38", "remaining_time": "5:23:44"}
673
+ {"current_steps": 637, "total_steps": 1230, "loss": 0.4001, "lr": 2.2237275160988186e-05, "epoch": 2.580253164556962, "percentage": 51.79, "elapsed_time": "5:47:09", "remaining_time": "5:23:10"}
674
+ {"current_steps": 638, "total_steps": 1230, "loss": 0.36, "lr": 2.2180863795301787e-05, "epoch": 2.5843037974683547, "percentage": 51.87, "elapsed_time": "5:47:41", "remaining_time": "5:22:37"}
675
+ {"current_steps": 639, "total_steps": 1230, "loss": 0.3613, "lr": 2.212443486523819e-05, "epoch": 2.5883544303797468, "percentage": 51.95, "elapsed_time": "5:48:14", "remaining_time": "5:22:05"}
676
+ {"current_steps": 640, "total_steps": 1230, "loss": 0.3705, "lr": 2.2067988825268243e-05, "epoch": 2.5924050632911393, "percentage": 52.03, "elapsed_time": "5:48:52", "remaining_time": "5:21:36"}
677
+ {"current_steps": 641, "total_steps": 1230, "loss": 0.3709, "lr": 2.2011526130000596e-05, "epoch": 2.596455696202532, "percentage": 52.11, "elapsed_time": "5:49:22", "remaining_time": "5:21:02"}
678
+ {"current_steps": 642, "total_steps": 1230, "loss": 0.3847, "lr": 2.1955047234178038e-05, "epoch": 2.600506329113924, "percentage": 52.2, "elapsed_time": "5:49:52", "remaining_time": "5:20:26"}
679
+ {"current_steps": 643, "total_steps": 1230, "loss": 0.372, "lr": 2.1898552592673825e-05, "epoch": 2.6045569620253164, "percentage": 52.28, "elapsed_time": "5:50:26", "remaining_time": "5:19:55"}
680
+ {"current_steps": 644, "total_steps": 1230, "loss": 0.3875, "lr": 2.184204266048803e-05, "epoch": 2.608607594936709, "percentage": 52.36, "elapsed_time": "5:51:00", "remaining_time": "5:19:23"}
681
+ {"current_steps": 645, "total_steps": 1230, "loss": 0.3792, "lr": 2.1785517892743887e-05, "epoch": 2.6126582278481014, "percentage": 52.44, "elapsed_time": "5:51:32", "remaining_time": "5:18:50"}
682
+ {"current_steps": 646, "total_steps": 1230, "loss": 0.3672, "lr": 2.17289787446841e-05, "epoch": 2.616708860759494, "percentage": 52.52, "elapsed_time": "5:52:07", "remaining_time": "5:18:19"}
683
+ {"current_steps": 647, "total_steps": 1230, "loss": 0.3782, "lr": 2.1672425671667198e-05, "epoch": 2.620759493670886, "percentage": 52.6, "elapsed_time": "5:52:43", "remaining_time": "5:17:50"}
684
+ {"current_steps": 648, "total_steps": 1230, "loss": 0.3886, "lr": 2.161585912916385e-05, "epoch": 2.6248101265822785, "percentage": 52.68, "elapsed_time": "5:53:17", "remaining_time": "5:17:18"}
685
+ {"current_steps": 649, "total_steps": 1230, "loss": 0.3684, "lr": 2.1559279572753214e-05, "epoch": 2.628860759493671, "percentage": 52.76, "elapsed_time": "5:53:48", "remaining_time": "5:16:44"}
686
+ {"current_steps": 650, "total_steps": 1230, "loss": 0.375, "lr": 2.1502687458119268e-05, "epoch": 2.632911392405063, "percentage": 52.85, "elapsed_time": "5:54:19", "remaining_time": "5:16:09"}
687
+ {"current_steps": 651, "total_steps": 1230, "loss": 0.3833, "lr": 2.1446083241047116e-05, "epoch": 2.6369620253164556, "percentage": 52.93, "elapsed_time": "5:54:50", "remaining_time": "5:15:35"}
688
+ {"current_steps": 652, "total_steps": 1230, "loss": 0.3631, "lr": 2.1389467377419333e-05, "epoch": 2.641012658227848, "percentage": 53.01, "elapsed_time": "5:55:22", "remaining_time": "5:15:02"}
689
+ {"current_steps": 653, "total_steps": 1230, "loss": 0.3839, "lr": 2.133284032321232e-05, "epoch": 2.6450632911392407, "percentage": 53.09, "elapsed_time": "5:55:59", "remaining_time": "5:14:33"}
690
+ {"current_steps": 654, "total_steps": 1230, "loss": 0.3715, "lr": 2.1276202534492566e-05, "epoch": 2.649113924050633, "percentage": 53.17, "elapsed_time": "5:56:32", "remaining_time": "5:14:00"}
691
+ {"current_steps": 655, "total_steps": 1230, "loss": 0.3879, "lr": 2.121955446741306e-05, "epoch": 2.6531645569620252, "percentage": 53.25, "elapsed_time": "5:57:07", "remaining_time": "5:13:30"}
692
+ {"current_steps": 656, "total_steps": 1230, "loss": 0.38, "lr": 2.1162896578209517e-05, "epoch": 2.6572151898734178, "percentage": 53.33, "elapsed_time": "5:57:36", "remaining_time": "5:12:54"}
693
+ {"current_steps": 657, "total_steps": 1230, "loss": 0.3708, "lr": 2.1106229323196813e-05, "epoch": 2.6612658227848103, "percentage": 53.41, "elapsed_time": "5:58:08", "remaining_time": "5:12:21"}
694
+ {"current_steps": 658, "total_steps": 1230, "loss": 0.3523, "lr": 2.1049553158765214e-05, "epoch": 2.6653164556962023, "percentage": 53.5, "elapsed_time": "5:58:40", "remaining_time": "5:11:47"}
695
+ {"current_steps": 659, "total_steps": 1230, "loss": 0.3874, "lr": 2.0992868541376764e-05, "epoch": 2.669367088607595, "percentage": 53.58, "elapsed_time": "5:59:12", "remaining_time": "5:11:14"}
696
+ {"current_steps": 660, "total_steps": 1230, "loss": 0.3695, "lr": 2.093617592756158e-05, "epoch": 2.6734177215189874, "percentage": 53.66, "elapsed_time": "5:59:49", "remaining_time": "5:10:45"}
697
+ {"current_steps": 661, "total_steps": 1230, "loss": 0.3781, "lr": 2.0879475773914167e-05, "epoch": 2.67746835443038, "percentage": 53.74, "elapsed_time": "6:00:24", "remaining_time": "5:10:14"}
698
+ {"current_steps": 662, "total_steps": 1230, "loss": 0.3523, "lr": 2.082276853708978e-05, "epoch": 2.6815189873417724, "percentage": 53.82, "elapsed_time": "6:01:02", "remaining_time": "5:09:46"}
699
+ {"current_steps": 663, "total_steps": 1230, "loss": 0.3712, "lr": 2.076605467380071e-05, "epoch": 2.6855696202531645, "percentage": 53.9, "elapsed_time": "6:01:39", "remaining_time": "5:09:17"}
700
+ {"current_steps": 664, "total_steps": 1230, "loss": 0.3519, "lr": 2.0709334640812613e-05, "epoch": 2.689620253164557, "percentage": 53.98, "elapsed_time": "6:02:14", "remaining_time": "5:08:46"}
701
+ {"current_steps": 665, "total_steps": 1230, "loss": 0.3706, "lr": 2.0652608894940824e-05, "epoch": 2.6936708860759495, "percentage": 54.07, "elapsed_time": "6:02:42", "remaining_time": "5:08:09"}
702
+ {"current_steps": 666, "total_steps": 1230, "loss": 0.3828, "lr": 2.0595877893046722e-05, "epoch": 2.6977215189873416, "percentage": 54.15, "elapsed_time": "6:03:16", "remaining_time": "5:07:38"}
703
+ {"current_steps": 667, "total_steps": 1230, "loss": 0.3859, "lr": 2.0539142092033985e-05, "epoch": 2.701772151898734, "percentage": 54.23, "elapsed_time": "6:03:46", "remaining_time": "5:07:02"}
704
+ {"current_steps": 668, "total_steps": 1230, "loss": 0.3609, "lr": 2.048240194884496e-05, "epoch": 2.7058227848101266, "percentage": 54.31, "elapsed_time": "6:04:10", "remaining_time": "5:06:23"}
705
+ {"current_steps": 669, "total_steps": 1230, "loss": 0.3752, "lr": 2.042565792045695e-05, "epoch": 2.709873417721519, "percentage": 54.39, "elapsed_time": "6:04:41", "remaining_time": "5:05:48"}
706
+ {"current_steps": 670, "total_steps": 1230, "loss": 0.395, "lr": 2.036891046387857e-05, "epoch": 2.7139240506329116, "percentage": 54.47, "elapsed_time": "6:05:10", "remaining_time": "5:05:13"}
707
+ {"current_steps": 671, "total_steps": 1230, "loss": 0.3699, "lr": 2.0312160036146036e-05, "epoch": 2.7179746835443037, "percentage": 54.55, "elapsed_time": "6:05:44", "remaining_time": "5:04:41"}
708
+ {"current_steps": 672, "total_steps": 1230, "loss": 0.3662, "lr": 2.025540709431948e-05, "epoch": 2.7220253164556962, "percentage": 54.63, "elapsed_time": "6:06:15", "remaining_time": "5:04:07"}
709
+ {"current_steps": 673, "total_steps": 1230, "loss": 0.3669, "lr": 2.0198652095479298e-05, "epoch": 2.7260759493670887, "percentage": 54.72, "elapsed_time": "6:06:44", "remaining_time": "5:03:31"}
710
+ {"current_steps": 674, "total_steps": 1230, "loss": 0.3757, "lr": 2.014189549672245e-05, "epoch": 2.730126582278481, "percentage": 54.8, "elapsed_time": "6:07:17", "remaining_time": "5:02:58"}
711
+ {"current_steps": 675, "total_steps": 1230, "loss": 0.378, "lr": 2.0085137755158776e-05, "epoch": 2.7341772151898733, "percentage": 54.88, "elapsed_time": "6:07:52", "remaining_time": "5:02:28"}
712
+ {"current_steps": 676, "total_steps": 1230, "loss": 0.3711, "lr": 2.0028379327907327e-05, "epoch": 2.738227848101266, "percentage": 54.96, "elapsed_time": "6:08:25", "remaining_time": "5:01:55"}
713
+ {"current_steps": 677, "total_steps": 1230, "loss": 0.3717, "lr": 1.9971620672092676e-05, "epoch": 2.7422784810126584, "percentage": 55.04, "elapsed_time": "6:08:53", "remaining_time": "5:01:19"}
714
+ {"current_steps": 678, "total_steps": 1230, "loss": 0.3847, "lr": 1.991486224484123e-05, "epoch": 2.746329113924051, "percentage": 55.12, "elapsed_time": "6:09:31", "remaining_time": "5:00:50"}
715
+ {"current_steps": 679, "total_steps": 1230, "loss": 0.3699, "lr": 1.985810450327756e-05, "epoch": 2.750379746835443, "percentage": 55.2, "elapsed_time": "6:10:02", "remaining_time": "5:00:17"}
716
+ {"current_steps": 680, "total_steps": 1230, "loss": 0.3865, "lr": 1.9801347904520706e-05, "epoch": 2.7544303797468355, "percentage": 55.28, "elapsed_time": "6:10:33", "remaining_time": "4:59:43"}
717
+ {"current_steps": 681, "total_steps": 1230, "loss": 0.3761, "lr": 1.974459290568053e-05, "epoch": 2.758481012658228, "percentage": 55.37, "elapsed_time": "6:11:10", "remaining_time": "4:59:13"}
718
+ {"current_steps": 682, "total_steps": 1230, "loss": 0.3764, "lr": 1.968783996385397e-05, "epoch": 2.76253164556962, "percentage": 55.45, "elapsed_time": "6:11:40", "remaining_time": "4:58:38"}
719
+ {"current_steps": 683, "total_steps": 1230, "loss": 0.3903, "lr": 1.963108953612143e-05, "epoch": 2.7665822784810126, "percentage": 55.53, "elapsed_time": "6:12:08", "remaining_time": "4:58:02"}
720
+ {"current_steps": 684, "total_steps": 1230, "loss": 0.3848, "lr": 1.9574342079543056e-05, "epoch": 2.770632911392405, "percentage": 55.61, "elapsed_time": "6:12:48", "remaining_time": "4:57:35"}
721
+ {"current_steps": 685, "total_steps": 1230, "loss": 0.3997, "lr": 1.9517598051155046e-05, "epoch": 2.7746835443037976, "percentage": 55.69, "elapsed_time": "6:13:22", "remaining_time": "4:57:03"}
722
+ {"current_steps": 686, "total_steps": 1230, "loss": 0.3677, "lr": 1.9460857907966025e-05, "epoch": 2.77873417721519, "percentage": 55.77, "elapsed_time": "6:13:47", "remaining_time": "4:56:25"}
723
+ {"current_steps": 687, "total_steps": 1230, "loss": 0.3768, "lr": 1.9404122106953285e-05, "epoch": 2.782784810126582, "percentage": 55.85, "elapsed_time": "6:14:16", "remaining_time": "4:55:49"}
724
+ {"current_steps": 688, "total_steps": 1230, "loss": 0.3903, "lr": 1.9347391105059176e-05, "epoch": 2.7868354430379747, "percentage": 55.93, "elapsed_time": "6:14:50", "remaining_time": "4:55:18"}
725
+ {"current_steps": 689, "total_steps": 1230, "loss": 0.3828, "lr": 1.92906653591874e-05, "epoch": 2.790886075949367, "percentage": 56.02, "elapsed_time": "6:15:24", "remaining_time": "4:54:45"}
726
+ {"current_steps": 690, "total_steps": 1230, "loss": 0.3746, "lr": 1.9233945326199295e-05, "epoch": 2.7949367088607593, "percentage": 56.1, "elapsed_time": "6:16:00", "remaining_time": "4:54:15"}
727
+ {"current_steps": 691, "total_steps": 1230, "loss": 0.3657, "lr": 1.917723146291022e-05, "epoch": 2.798987341772152, "percentage": 56.18, "elapsed_time": "6:16:34", "remaining_time": "4:53:44"}
728
+ {"current_steps": 692, "total_steps": 1230, "loss": 0.3592, "lr": 1.912052422608584e-05, "epoch": 2.8030379746835443, "percentage": 56.26, "elapsed_time": "6:17:03", "remaining_time": "4:53:08"}
729
+ {"current_steps": 693, "total_steps": 1230, "loss": 0.4079, "lr": 1.9063824072438428e-05, "epoch": 2.807088607594937, "percentage": 56.34, "elapsed_time": "6:17:38", "remaining_time": "4:52:37"}
730
+ {"current_steps": 694, "total_steps": 1230, "loss": 0.3665, "lr": 1.9007131458623246e-05, "epoch": 2.8111392405063294, "percentage": 56.42, "elapsed_time": "6:18:07", "remaining_time": "4:52:02"}
731
+ {"current_steps": 695, "total_steps": 1230, "loss": 0.3834, "lr": 1.895044684123479e-05, "epoch": 2.8151898734177214, "percentage": 56.5, "elapsed_time": "6:18:37", "remaining_time": "4:51:27"}
732
+ {"current_steps": 696, "total_steps": 1230, "loss": 0.3889, "lr": 1.8893770676803194e-05, "epoch": 2.819240506329114, "percentage": 56.59, "elapsed_time": "6:19:13", "remaining_time": "4:50:57"}
733
+ {"current_steps": 697, "total_steps": 1230, "loss": 0.3813, "lr": 1.8837103421790486e-05, "epoch": 2.8232911392405065, "percentage": 56.67, "elapsed_time": "6:19:42", "remaining_time": "4:50:21"}
734
+ {"current_steps": 698, "total_steps": 1230, "loss": 0.3753, "lr": 1.8780445532586952e-05, "epoch": 2.8273417721518985, "percentage": 56.75, "elapsed_time": "6:20:13", "remaining_time": "4:49:47"}
735
+ {"current_steps": 699, "total_steps": 1230, "loss": 0.3838, "lr": 1.872379746550743e-05, "epoch": 2.831392405063291, "percentage": 56.83, "elapsed_time": "6:20:44", "remaining_time": "4:49:13"}
736
+ {"current_steps": 700, "total_steps": 1230, "loss": 0.3789, "lr": 1.866715967678769e-05, "epoch": 2.8354430379746836, "percentage": 56.91, "elapsed_time": "6:21:17", "remaining_time": "4:48:41"}
737
+ {"current_steps": 701, "total_steps": 1230, "loss": 0.3945, "lr": 1.861053262258067e-05, "epoch": 2.839493670886076, "percentage": 56.99, "elapsed_time": "6:21:47", "remaining_time": "4:48:06"}
738
+ {"current_steps": 702, "total_steps": 1230, "loss": 0.3824, "lr": 1.8553916758952897e-05, "epoch": 2.8435443037974686, "percentage": 57.07, "elapsed_time": "6:22:24", "remaining_time": "4:47:37"}
739
+ {"current_steps": 703, "total_steps": 1230, "loss": 0.359, "lr": 1.8497312541880735e-05, "epoch": 2.8475949367088607, "percentage": 57.15, "elapsed_time": "6:22:58", "remaining_time": "4:47:05"}
740
+ {"current_steps": 704, "total_steps": 1230, "loss": 0.3679, "lr": 1.8440720427246786e-05, "epoch": 2.851645569620253, "percentage": 57.24, "elapsed_time": "6:23:27", "remaining_time": "4:46:30"}
741
+ {"current_steps": 705, "total_steps": 1230, "loss": 0.3743, "lr": 1.8384140870836157e-05, "epoch": 2.8556962025316457, "percentage": 57.32, "elapsed_time": "6:23:57", "remaining_time": "4:45:55"}
742
+ {"current_steps": 706, "total_steps": 1230, "loss": 0.3642, "lr": 1.8327574328332806e-05, "epoch": 2.8597468354430378, "percentage": 57.4, "elapsed_time": "6:24:30", "remaining_time": "4:45:23"}
743
+ {"current_steps": 707, "total_steps": 1230, "loss": 0.3815, "lr": 1.8271021255315906e-05, "epoch": 2.8637974683544303, "percentage": 57.48, "elapsed_time": "6:24:58", "remaining_time": "4:44:47"}
744
+ {"current_steps": 708, "total_steps": 1230, "loss": 0.3863, "lr": 1.8214482107256117e-05, "epoch": 2.867848101265823, "percentage": 57.56, "elapsed_time": "6:25:29", "remaining_time": "4:44:13"}
745
+ {"current_steps": 709, "total_steps": 1230, "loss": 0.3857, "lr": 1.8157957339511968e-05, "epoch": 2.8718987341772153, "percentage": 57.64, "elapsed_time": "6:26:01", "remaining_time": "4:43:40"}
746
+ {"current_steps": 710, "total_steps": 1230, "loss": 0.369, "lr": 1.8101447407326182e-05, "epoch": 2.875949367088608, "percentage": 57.72, "elapsed_time": "6:26:31", "remaining_time": "4:43:05"}
747
+ {"current_steps": 711, "total_steps": 1230, "loss": 0.3763, "lr": 1.8044952765821966e-05, "epoch": 2.88, "percentage": 57.8, "elapsed_time": "6:27:04", "remaining_time": "4:42:32"}
748
+ {"current_steps": 712, "total_steps": 1230, "loss": 0.3867, "lr": 1.7988473869999407e-05, "epoch": 2.8840506329113924, "percentage": 57.89, "elapsed_time": "6:27:41", "remaining_time": "4:42:03"}
749
+ {"current_steps": 713, "total_steps": 1230, "loss": 0.3639, "lr": 1.7932011174731764e-05, "epoch": 2.888101265822785, "percentage": 57.97, "elapsed_time": "6:28:12", "remaining_time": "4:41:29"}
750
+ {"current_steps": 714, "total_steps": 1230, "loss": 0.3838, "lr": 1.7875565134761817e-05, "epoch": 2.892151898734177, "percentage": 58.05, "elapsed_time": "6:28:47", "remaining_time": "4:40:58"}
751
+ {"current_steps": 715, "total_steps": 1230, "loss": 0.373, "lr": 1.7819136204698226e-05, "epoch": 2.8962025316455695, "percentage": 58.13, "elapsed_time": "6:29:18", "remaining_time": "4:40:24"}
752
+ {"current_steps": 716, "total_steps": 1230, "loss": 0.3768, "lr": 1.776272483901182e-05, "epoch": 2.900253164556962, "percentage": 58.21, "elapsed_time": "6:29:48", "remaining_time": "4:39:50"}
753
+ {"current_steps": 717, "total_steps": 1230, "loss": 0.3784, "lr": 1.7706331492031995e-05, "epoch": 2.9043037974683545, "percentage": 58.29, "elapsed_time": "6:30:22", "remaining_time": "4:39:18"}
754
+ {"current_steps": 718, "total_steps": 1230, "loss": 0.3701, "lr": 1.764995661794301e-05, "epoch": 2.908354430379747, "percentage": 58.37, "elapsed_time": "6:30:53", "remaining_time": "4:38:44"}
755
+ {"current_steps": 719, "total_steps": 1230, "loss": 0.3662, "lr": 1.759360067078035e-05, "epoch": 2.912405063291139, "percentage": 58.46, "elapsed_time": "6:31:27", "remaining_time": "4:38:12"}
756
+ {"current_steps": 720, "total_steps": 1230, "loss": 0.3857, "lr": 1.7537264104427064e-05, "epoch": 2.9164556962025316, "percentage": 58.54, "elapsed_time": "6:31:55", "remaining_time": "4:37:36"}
757
+ {"current_steps": 721, "total_steps": 1230, "loss": 0.3899, "lr": 1.748094737261012e-05, "epoch": 2.920506329113924, "percentage": 58.62, "elapsed_time": "6:32:27", "remaining_time": "4:37:03"}
758
+ {"current_steps": 722, "total_steps": 1230, "loss": 0.3731, "lr": 1.7424650928896726e-05, "epoch": 2.9245569620253162, "percentage": 58.7, "elapsed_time": "6:33:01", "remaining_time": "4:36:31"}
759
+ {"current_steps": 723, "total_steps": 1230, "loss": 0.3535, "lr": 1.7368375226690712e-05, "epoch": 2.9286075949367087, "percentage": 58.78, "elapsed_time": "6:33:34", "remaining_time": "4:35:59"}
760
+ {"current_steps": 724, "total_steps": 1230, "loss": 0.3837, "lr": 1.731212071922883e-05, "epoch": 2.9326582278481013, "percentage": 58.86, "elapsed_time": "6:34:07", "remaining_time": "4:35:26"}
761
+ {"current_steps": 725, "total_steps": 1230, "loss": 0.3942, "lr": 1.7255887859577156e-05, "epoch": 2.9367088607594938, "percentage": 58.94, "elapsed_time": "6:34:35", "remaining_time": "4:34:51"}
762
+ {"current_steps": 726, "total_steps": 1230, "loss": 0.3804, "lr": 1.7199677100627427e-05, "epoch": 2.9407594936708863, "percentage": 59.02, "elapsed_time": "6:35:04", "remaining_time": "4:34:16"}
763
+ {"current_steps": 727, "total_steps": 1230, "loss": 0.3785, "lr": 1.7143488895093343e-05, "epoch": 2.9448101265822784, "percentage": 59.11, "elapsed_time": "6:35:36", "remaining_time": "4:33:42"}
764
+ {"current_steps": 728, "total_steps": 1230, "loss": 0.3636, "lr": 1.7087323695506994e-05, "epoch": 2.948860759493671, "percentage": 59.19, "elapsed_time": "6:36:07", "remaining_time": "4:33:08"}
765
+ {"current_steps": 729, "total_steps": 1230, "loss": 0.3576, "lr": 1.7031181954215194e-05, "epoch": 2.9529113924050634, "percentage": 59.27, "elapsed_time": "6:36:40", "remaining_time": "4:32:36"}
766
+ {"current_steps": 730, "total_steps": 1230, "loss": 0.3699, "lr": 1.6975064123375788e-05, "epoch": 2.9569620253164555, "percentage": 59.35, "elapsed_time": "6:37:12", "remaining_time": "4:32:03"}
767
+ {"current_steps": 731, "total_steps": 1230, "loss": 0.3678, "lr": 1.6918970654954084e-05, "epoch": 2.961012658227848, "percentage": 59.43, "elapsed_time": "6:37:44", "remaining_time": "4:31:30"}
768
+ {"current_steps": 732, "total_steps": 1230, "loss": 0.3774, "lr": 1.686290200071915e-05, "epoch": 2.9650632911392405, "percentage": 59.51, "elapsed_time": "6:38:19", "remaining_time": "4:30:59"}
769
+ {"current_steps": 733, "total_steps": 1230, "loss": 0.4029, "lr": 1.6806858612240234e-05, "epoch": 2.969113924050633, "percentage": 59.59, "elapsed_time": "6:38:53", "remaining_time": "4:30:27"}
770
+ {"current_steps": 734, "total_steps": 1230, "loss": 0.3866, "lr": 1.6750840940883078e-05, "epoch": 2.9731645569620255, "percentage": 59.67, "elapsed_time": "6:39:24", "remaining_time": "4:29:54"}
771
+ {"current_steps": 735, "total_steps": 1230, "loss": 0.3494, "lr": 1.6694849437806305e-05, "epoch": 2.9772151898734176, "percentage": 59.76, "elapsed_time": "6:39:55", "remaining_time": "4:29:20"}
772
+ {"current_steps": 736, "total_steps": 1230, "loss": 0.3943, "lr": 1.663888455395778e-05, "epoch": 2.98126582278481, "percentage": 59.84, "elapsed_time": "6:40:21", "remaining_time": "4:28:43"}
773
+ {"current_steps": 737, "total_steps": 1230, "loss": 0.3688, "lr": 1.6582946740070995e-05, "epoch": 2.9853164556962026, "percentage": 59.92, "elapsed_time": "6:40:52", "remaining_time": "4:28:09"}
774
+ {"current_steps": 738, "total_steps": 1230, "loss": 0.3708, "lr": 1.6527036446661396e-05, "epoch": 2.9893670886075947, "percentage": 60.0, "elapsed_time": "6:41:27", "remaining_time": "4:27:38"}
775
+ {"current_steps": 739, "total_steps": 1230, "loss": 0.3747, "lr": 1.6471154124022818e-05, "epoch": 2.993417721518987, "percentage": 60.08, "elapsed_time": "6:41:59", "remaining_time": "4:27:05"}
776
+ {"current_steps": 740, "total_steps": 1230, "loss": 0.3689, "lr": 1.6415300222223788e-05, "epoch": 2.9974683544303797, "percentage": 60.16, "elapsed_time": "6:42:25", "remaining_time": "4:26:28"}
777
+ {"current_steps": 741, "total_steps": 1230, "loss": 0.3513, "lr": 1.6359475191103958e-05, "epoch": 3.0015189873417722, "percentage": 60.24, "elapsed_time": "6:44:53", "remaining_time": "4:27:12"}
778
+ {"current_steps": 742, "total_steps": 1230, "loss": 0.2477, "lr": 1.6303679480270466e-05, "epoch": 3.0055696202531648, "percentage": 60.33, "elapsed_time": "6:45:26", "remaining_time": "4:26:39"}
779
+ {"current_steps": 743, "total_steps": 1230, "loss": 0.2883, "lr": 1.624791353909428e-05, "epoch": 3.009620253164557, "percentage": 60.41, "elapsed_time": "6:46:01", "remaining_time": "4:26:07"}
780
+ {"current_steps": 744, "total_steps": 1230, "loss": 0.2741, "lr": 1.619217781670663e-05, "epoch": 3.0136708860759494, "percentage": 60.49, "elapsed_time": "6:46:28", "remaining_time": "4:25:31"}
781
+ {"current_steps": 745, "total_steps": 1230, "loss": 0.2664, "lr": 1.6136472761995373e-05, "epoch": 3.017721518987342, "percentage": 60.57, "elapsed_time": "6:47:02", "remaining_time": "4:24:58"}
782
+ {"current_steps": 746, "total_steps": 1230, "loss": 0.2411, "lr": 1.608079882360134e-05, "epoch": 3.0217721518987344, "percentage": 60.65, "elapsed_time": "6:47:31", "remaining_time": "4:24:23"}