gsmyrnis commited on
Commit
6ce525b
·
verified ·
1 Parent(s): 04b8140

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 sha256:55ead82bdcaada82f674963d94586f543f1bde0a78bc871ef9907a710b36a49e
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6cf42afb86d62a083d60b3cc4d5b395833f608c3ef636e849ff293f2ac2b524c
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1c67187c7c772e0e0d6ec836e360a7206ab6a5a3daa6beb91573de3dded6f0bb
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18c3fe684253aadf9dc1c1f2a810b14169b3d3c27d3a822e5bdcb3183d90eea0
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:146f639d93e92c8d4e7b8829740ab85ff339b41cf50195f72f0f4a900d2e7548
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ff005296959ed0fa9c874b9f7c3887591111be49bbcc44e6b961c1f10c59e44
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:961e63781b41a094c88122466744dae794137863d0f6a0ccfcb8e4340ffdd356
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e93a49a3a4681e408feb8c822aca9660116a29949b9898c91a216a43776d5f1e
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -446,3 +446,251 @@
446
  {"current_steps": 446, "total_steps": 1105, "loss": 1.1017, "lr": 2.9798610746154532e-05, "epoch": 2.015783540022548, "percentage": 40.36, "elapsed_time": "3:04:06", "remaining_time": "4:32:02"}
447
  {"current_steps": 447, "total_steps": 1105, "loss": 1.1485, "lr": 2.9743456879215934e-05, "epoch": 2.020293122886133, "percentage": 40.45, "elapsed_time": "3:04:30", "remaining_time": "4:31:36"}
448
  {"current_steps": 448, "total_steps": 1105, "loss": 1.1234, "lr": 2.9688205683855247e-05, "epoch": 2.024802705749718, "percentage": 40.54, "elapsed_time": "3:04:53", "remaining_time": "4:31:08"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
446
  {"current_steps": 446, "total_steps": 1105, "loss": 1.1017, "lr": 2.9798610746154532e-05, "epoch": 2.015783540022548, "percentage": 40.36, "elapsed_time": "3:04:06", "remaining_time": "4:32:02"}
447
  {"current_steps": 447, "total_steps": 1105, "loss": 1.1485, "lr": 2.9743456879215934e-05, "epoch": 2.020293122886133, "percentage": 40.45, "elapsed_time": "3:04:30", "remaining_time": "4:31:36"}
448
  {"current_steps": 448, "total_steps": 1105, "loss": 1.1234, "lr": 2.9688205683855247e-05, "epoch": 2.024802705749718, "percentage": 40.54, "elapsed_time": "3:04:53", "remaining_time": "4:31:08"}
449
+ {"current_steps": 449, "total_steps": 1105, "loss": 1.1622, "lr": 2.9632857711982513e-05, "epoch": 2.0293122886133035, "percentage": 40.63, "elapsed_time": "3:05:17", "remaining_time": "4:30:43"}
450
+ {"current_steps": 450, "total_steps": 1105, "loss": 1.1436, "lr": 2.9577413516474475e-05, "epoch": 2.0338218714768885, "percentage": 40.72, "elapsed_time": "3:05:41", "remaining_time": "4:30:17"}
451
+ {"current_steps": 451, "total_steps": 1105, "loss": 1.1373, "lr": 2.952187365116907e-05, "epoch": 2.0383314543404736, "percentage": 40.81, "elapsed_time": "3:06:05", "remaining_time": "4:29:50"}
452
+ {"current_steps": 452, "total_steps": 1105, "loss": 1.1314, "lr": 2.9466238670859896e-05, "epoch": 2.0428410372040586, "percentage": 40.9, "elapsed_time": "3:06:28", "remaining_time": "4:29:24"}
453
+ {"current_steps": 453, "total_steps": 1105, "loss": 1.131, "lr": 2.941050913129067e-05, "epoch": 2.0473506200676437, "percentage": 41.0, "elapsed_time": "3:06:52", "remaining_time": "4:28:57"}
454
+ {"current_steps": 454, "total_steps": 1105, "loss": 1.1443, "lr": 2.9354685589149637e-05, "epoch": 2.0518602029312287, "percentage": 41.09, "elapsed_time": "3:07:16", "remaining_time": "4:28:32"}
455
+ {"current_steps": 455, "total_steps": 1105, "loss": 1.1524, "lr": 2.9298768602064087e-05, "epoch": 2.0563697857948138, "percentage": 41.18, "elapsed_time": "3:07:40", "remaining_time": "4:28:05"}
456
+ {"current_steps": 456, "total_steps": 1105, "loss": 1.1224, "lr": 2.9242758728594718e-05, "epoch": 2.0608793686583993, "percentage": 41.27, "elapsed_time": "3:08:05", "remaining_time": "4:27:41"}
457
+ {"current_steps": 457, "total_steps": 1105, "loss": 1.1243, "lr": 2.9186656528230087e-05, "epoch": 2.0653889515219843, "percentage": 41.36, "elapsed_time": "3:08:29", "remaining_time": "4:27:15"}
458
+ {"current_steps": 458, "total_steps": 1105, "loss": 1.137, "lr": 2.9130462561380997e-05, "epoch": 2.0698985343855694, "percentage": 41.45, "elapsed_time": "3:08:53", "remaining_time": "4:26:49"}
459
+ {"current_steps": 459, "total_steps": 1105, "loss": 1.1696, "lr": 2.907417738937495e-05, "epoch": 2.0744081172491544, "percentage": 41.54, "elapsed_time": "3:09:17", "remaining_time": "4:26:24"}
460
+ {"current_steps": 460, "total_steps": 1105, "loss": 1.1436, "lr": 2.9017801574450485e-05, "epoch": 2.0789177001127395, "percentage": 41.63, "elapsed_time": "3:09:41", "remaining_time": "4:25:58"}
461
+ {"current_steps": 461, "total_steps": 1105, "loss": 1.1267, "lr": 2.8961335679751573e-05, "epoch": 2.0834272829763245, "percentage": 41.72, "elapsed_time": "3:10:06", "remaining_time": "4:25:33"}
462
+ {"current_steps": 462, "total_steps": 1105, "loss": 1.1237, "lr": 2.890478026932202e-05, "epoch": 2.08793686583991, "percentage": 41.81, "elapsed_time": "3:10:31", "remaining_time": "4:25:09"}
463
+ {"current_steps": 463, "total_steps": 1105, "loss": 1.1434, "lr": 2.8848135908099806e-05, "epoch": 2.092446448703495, "percentage": 41.9, "elapsed_time": "3:10:55", "remaining_time": "4:24:43"}
464
+ {"current_steps": 464, "total_steps": 1105, "loss": 1.1771, "lr": 2.8791403161911447e-05, "epoch": 2.09695603156708, "percentage": 41.99, "elapsed_time": "3:11:18", "remaining_time": "4:24:17"}
465
+ {"current_steps": 465, "total_steps": 1105, "loss": 1.1277, "lr": 2.873458259746636e-05, "epoch": 2.101465614430665, "percentage": 42.08, "elapsed_time": "3:11:43", "remaining_time": "4:23:52"}
466
+ {"current_steps": 466, "total_steps": 1105, "loss": 1.1269, "lr": 2.8677674782351164e-05, "epoch": 2.10597519729425, "percentage": 42.17, "elapsed_time": "3:12:08", "remaining_time": "4:23:27"}
467
+ {"current_steps": 467, "total_steps": 1105, "loss": 1.1464, "lr": 2.862068028502406e-05, "epoch": 2.1104847801578352, "percentage": 42.26, "elapsed_time": "3:12:32", "remaining_time": "4:23:02"}
468
+ {"current_steps": 468, "total_steps": 1105, "loss": 1.1323, "lr": 2.8563599674809105e-05, "epoch": 2.1149943630214203, "percentage": 42.35, "elapsed_time": "3:12:56", "remaining_time": "4:22:36"}
469
+ {"current_steps": 469, "total_steps": 1105, "loss": 1.1214, "lr": 2.8506433521890567e-05, "epoch": 2.119503945885006, "percentage": 42.44, "elapsed_time": "3:13:20", "remaining_time": "4:22:10"}
470
+ {"current_steps": 443, "total_steps": 1105, "loss": 1.1425, "lr": 2.9963482871953764e-05, "epoch": 2.004509582863585, "percentage": 40.09, "elapsed_time": "0:00:49", "remaining_time": "0:01:14"}
471
+ {"current_steps": 444, "total_steps": 1105, "loss": 1.09, "lr": 2.9908624291991924e-05, "epoch": 2.00901916572717, "percentage": 40.18, "elapsed_time": "0:01:14", "remaining_time": "0:01:51"}
472
+ {"current_steps": 445, "total_steps": 1105, "loss": 1.0997, "lr": 2.9853666733733223e-05, "epoch": 2.013528748590755, "percentage": 40.27, "elapsed_time": "0:01:38", "remaining_time": "0:02:26"}
473
+ {"current_steps": 446, "total_steps": 1105, "loss": 1.1173, "lr": 2.9798610746154532e-05, "epoch": 2.0180383314543406, "percentage": 40.36, "elapsed_time": "0:02:04", "remaining_time": "0:03:03"}
474
+ {"current_steps": 447, "total_steps": 1105, "loss": 1.1565, "lr": 2.9743456879215934e-05, "epoch": 2.0225479143179257, "percentage": 40.45, "elapsed_time": "0:02:28", "remaining_time": "0:03:39"}
475
+ {"current_steps": 448, "total_steps": 1105, "loss": 1.1474, "lr": 2.9688205683855247e-05, "epoch": 2.0270574971815107, "percentage": 40.54, "elapsed_time": "0:02:52", "remaining_time": "0:04:13"}
476
+ {"current_steps": 449, "total_steps": 1105, "loss": 1.1469, "lr": 2.9632857711982513e-05, "epoch": 2.031567080045096, "percentage": 40.63, "elapsed_time": "0:03:16", "remaining_time": "0:04:47"}
477
+ {"current_steps": 450, "total_steps": 1105, "loss": 1.1349, "lr": 2.9577413516474475e-05, "epoch": 2.036076662908681, "percentage": 40.72, "elapsed_time": "0:03:40", "remaining_time": "0:05:21"}
478
+ {"current_steps": 451, "total_steps": 1105, "loss": 1.1425, "lr": 2.952187365116907e-05, "epoch": 2.040586245772266, "percentage": 40.81, "elapsed_time": "0:04:05", "remaining_time": "0:05:55"}
479
+ {"current_steps": 452, "total_steps": 1105, "loss": 1.1047, "lr": 2.9466238670859896e-05, "epoch": 2.0450958286358514, "percentage": 40.9, "elapsed_time": "0:04:28", "remaining_time": "0:06:27"}
480
+ {"current_steps": 453, "total_steps": 1105, "loss": 1.1675, "lr": 2.941050913129067e-05, "epoch": 2.0496054114994364, "percentage": 41.0, "elapsed_time": "0:04:53", "remaining_time": "0:07:02"}
481
+ {"current_steps": 454, "total_steps": 1105, "loss": 1.1582, "lr": 2.9354685589149637e-05, "epoch": 2.0541149943630215, "percentage": 41.09, "elapsed_time": "0:05:17", "remaining_time": "0:07:35"}
482
+ {"current_steps": 455, "total_steps": 1105, "loss": 1.1187, "lr": 2.9298768602064087e-05, "epoch": 2.0586245772266065, "percentage": 41.18, "elapsed_time": "0:05:42", "remaining_time": "0:08:09"}
483
+ {"current_steps": 456, "total_steps": 1105, "loss": 1.1371, "lr": 2.9242758728594718e-05, "epoch": 2.0631341600901916, "percentage": 41.27, "elapsed_time": "0:06:06", "remaining_time": "0:08:42"}
484
+ {"current_steps": 457, "total_steps": 1105, "loss": 1.1186, "lr": 2.9186656528230087e-05, "epoch": 2.0676437429537766, "percentage": 41.36, "elapsed_time": "0:06:30", "remaining_time": "0:09:13"}
485
+ {"current_steps": 458, "total_steps": 1105, "loss": 1.1398, "lr": 2.9130462561380997e-05, "epoch": 2.0721533258173617, "percentage": 41.45, "elapsed_time": "0:06:55", "remaining_time": "0:09:46"}
486
+ {"current_steps": 459, "total_steps": 1105, "loss": 1.1667, "lr": 2.907417738937495e-05, "epoch": 2.076662908680947, "percentage": 41.54, "elapsed_time": "0:07:19", "remaining_time": "0:10:18"}
487
+ {"current_steps": 460, "total_steps": 1105, "loss": 1.1543, "lr": 2.9017801574450485e-05, "epoch": 2.081172491544532, "percentage": 41.63, "elapsed_time": "0:07:43", "remaining_time": "0:10:50"}
488
+ {"current_steps": 461, "total_steps": 1105, "loss": 1.1274, "lr": 2.8961335679751573e-05, "epoch": 2.0856820744081173, "percentage": 41.72, "elapsed_time": "0:08:08", "remaining_time": "0:11:22"}
489
+ {"current_steps": 462, "total_steps": 1105, "loss": 1.1209, "lr": 2.890478026932202e-05, "epoch": 2.0901916572717023, "percentage": 41.81, "elapsed_time": "0:08:33", "remaining_time": "0:11:55"}
490
+ {"current_steps": 463, "total_steps": 1105, "loss": 1.1813, "lr": 2.8848135908099806e-05, "epoch": 2.0947012401352874, "percentage": 41.9, "elapsed_time": "0:08:57", "remaining_time": "0:12:25"}
491
+ {"current_steps": 464, "total_steps": 1105, "loss": 1.1332, "lr": 2.8791403161911447e-05, "epoch": 2.0992108229988724, "percentage": 41.99, "elapsed_time": "0:09:22", "remaining_time": "0:12:57"}
492
+ {"current_steps": 465, "total_steps": 1105, "loss": 1.1085, "lr": 2.873458259746636e-05, "epoch": 2.103720405862458, "percentage": 42.08, "elapsed_time": "0:09:47", "remaining_time": "0:13:28"}
493
+ {"current_steps": 466, "total_steps": 1105, "loss": 1.1581, "lr": 2.8677674782351164e-05, "epoch": 2.108229988726043, "percentage": 42.17, "elapsed_time": "0:10:12", "remaining_time": "0:13:59"}
494
+ {"current_steps": 467, "total_steps": 1105, "loss": 1.1436, "lr": 2.862068028502406e-05, "epoch": 2.112739571589628, "percentage": 42.26, "elapsed_time": "0:10:36", "remaining_time": "0:14:29"}
495
+ {"current_steps": 468, "total_steps": 1105, "loss": 1.1296, "lr": 2.8563599674809105e-05, "epoch": 2.117249154453213, "percentage": 42.35, "elapsed_time": "0:11:00", "remaining_time": "0:14:58"}
496
+ {"current_steps": 469, "total_steps": 1105, "loss": 1.1233, "lr": 2.8506433521890567e-05, "epoch": 2.121758737316798, "percentage": 42.44, "elapsed_time": "0:11:25", "remaining_time": "0:15:29"}
497
+ {"current_steps": 470, "total_steps": 1105, "loss": 1.1435, "lr": 2.844918239730719e-05, "epoch": 2.126268320180383, "percentage": 42.53, "elapsed_time": "0:11:49", "remaining_time": "0:15:58"}
498
+ {"current_steps": 471, "total_steps": 1105, "loss": 1.1283, "lr": 2.8391846872946515e-05, "epoch": 2.1307779030439686, "percentage": 42.62, "elapsed_time": "0:12:14", "remaining_time": "0:16:28"}
499
+ {"current_steps": 472, "total_steps": 1105, "loss": 1.1391, "lr": 2.8334427521539173e-05, "epoch": 2.1352874859075537, "percentage": 42.71, "elapsed_time": "0:12:38", "remaining_time": "0:16:56"}
500
+ {"current_steps": 473, "total_steps": 1105, "loss": 1.1298, "lr": 2.827692491665314e-05, "epoch": 2.1397970687711387, "percentage": 42.81, "elapsed_time": "0:13:02", "remaining_time": "0:17:25"}
501
+ {"current_steps": 474, "total_steps": 1105, "loss": 1.1369, "lr": 2.821933963268801e-05, "epoch": 2.144306651634724, "percentage": 42.9, "elapsed_time": "0:13:26", "remaining_time": "0:17:53"}
502
+ {"current_steps": 475, "total_steps": 1105, "loss": 1.1321, "lr": 2.81616722448693e-05, "epoch": 2.148816234498309, "percentage": 42.99, "elapsed_time": "0:13:50", "remaining_time": "0:18:21"}
503
+ {"current_steps": 476, "total_steps": 1105, "loss": 1.1221, "lr": 2.810392332924264e-05, "epoch": 2.153325817361894, "percentage": 43.08, "elapsed_time": "0:14:14", "remaining_time": "0:18:49"}
504
+ {"current_steps": 477, "total_steps": 1105, "loss": 1.1705, "lr": 2.804609346266806e-05, "epoch": 2.157835400225479, "percentage": 43.17, "elapsed_time": "0:14:40", "remaining_time": "0:19:19"}
505
+ {"current_steps": 478, "total_steps": 1105, "loss": 1.1579, "lr": 2.7988183222814223e-05, "epoch": 2.1623449830890644, "percentage": 43.26, "elapsed_time": "0:15:04", "remaining_time": "0:19:46"}
506
+ {"current_steps": 479, "total_steps": 1105, "loss": 1.1108, "lr": 2.7930193188152645e-05, "epoch": 2.1668545659526495, "percentage": 43.35, "elapsed_time": "0:15:28", "remaining_time": "0:20:13"}
507
+ {"current_steps": 480, "total_steps": 1105, "loss": 1.1335, "lr": 2.7872123937951915e-05, "epoch": 2.1713641488162345, "percentage": 43.44, "elapsed_time": "0:15:52", "remaining_time": "0:20:40"}
508
+ {"current_steps": 481, "total_steps": 1105, "loss": 1.1442, "lr": 2.7813976052271914e-05, "epoch": 2.1758737316798196, "percentage": 43.53, "elapsed_time": "0:16:16", "remaining_time": "0:21:06"}
509
+ {"current_steps": 482, "total_steps": 1105, "loss": 1.126, "lr": 2.7755750111958043e-05, "epoch": 2.1803833145434046, "percentage": 43.62, "elapsed_time": "0:16:40", "remaining_time": "0:21:33"}
510
+ {"current_steps": 483, "total_steps": 1105, "loss": 1.1356, "lr": 2.7697446698635376e-05, "epoch": 2.1848928974069897, "percentage": 43.71, "elapsed_time": "0:17:05", "remaining_time": "0:22:01"}
511
+ {"current_steps": 484, "total_steps": 1105, "loss": 1.1487, "lr": 2.7639066394702877e-05, "epoch": 2.189402480270575, "percentage": 43.8, "elapsed_time": "0:17:30", "remaining_time": "0:22:27"}
512
+ {"current_steps": 485, "total_steps": 1105, "loss": 1.1462, "lr": 2.7580609783327585e-05, "epoch": 2.19391206313416, "percentage": 43.89, "elapsed_time": "0:17:54", "remaining_time": "0:22:53"}
513
+ {"current_steps": 486, "total_steps": 1105, "loss": 1.1323, "lr": 2.7522077448438777e-05, "epoch": 2.1984216459977453, "percentage": 43.98, "elapsed_time": "0:18:17", "remaining_time": "0:23:18"}
514
+ {"current_steps": 487, "total_steps": 1105, "loss": 1.1427, "lr": 2.7463469974722138e-05, "epoch": 2.2029312288613303, "percentage": 44.07, "elapsed_time": "0:18:42", "remaining_time": "0:23:44"}
515
+ {"current_steps": 488, "total_steps": 1105, "loss": 1.1519, "lr": 2.7404787947613932e-05, "epoch": 2.2074408117249154, "percentage": 44.16, "elapsed_time": "0:19:06", "remaining_time": "0:24:08"}
516
+ {"current_steps": 489, "total_steps": 1105, "loss": 1.1392, "lr": 2.734603195329514e-05, "epoch": 2.2119503945885004, "percentage": 44.25, "elapsed_time": "0:19:30", "remaining_time": "0:24:34"}
517
+ {"current_steps": 490, "total_steps": 1105, "loss": 1.1275, "lr": 2.7287202578685605e-05, "epoch": 2.216459977452086, "percentage": 44.34, "elapsed_time": "0:19:53", "remaining_time": "0:24:58"}
518
+ {"current_steps": 491, "total_steps": 1105, "loss": 1.1526, "lr": 2.722830041143817e-05, "epoch": 2.220969560315671, "percentage": 44.43, "elapsed_time": "0:20:17", "remaining_time": "0:25:22"}
519
+ {"current_steps": 492, "total_steps": 1105, "loss": 1.1207, "lr": 2.7169326039932835e-05, "epoch": 2.225479143179256, "percentage": 44.52, "elapsed_time": "0:20:43", "remaining_time": "0:25:49"}
520
+ {"current_steps": 493, "total_steps": 1105, "loss": 1.1063, "lr": 2.711028005327083e-05, "epoch": 2.229988726042841, "percentage": 44.62, "elapsed_time": "0:21:07", "remaining_time": "0:26:13"}
521
+ {"current_steps": 494, "total_steps": 1105, "loss": 1.1673, "lr": 2.705116304126876e-05, "epoch": 2.234498308906426, "percentage": 44.71, "elapsed_time": "0:21:32", "remaining_time": "0:26:38"}
522
+ {"current_steps": 495, "total_steps": 1105, "loss": 1.1836, "lr": 2.6991975594452723e-05, "epoch": 2.239007891770011, "percentage": 44.8, "elapsed_time": "0:21:56", "remaining_time": "0:27:02"}
523
+ {"current_steps": 496, "total_steps": 1105, "loss": 1.1466, "lr": 2.6932718304052393e-05, "epoch": 2.243517474633596, "percentage": 44.89, "elapsed_time": "0:22:21", "remaining_time": "0:27:26"}
524
+ {"current_steps": 497, "total_steps": 1105, "loss": 1.1179, "lr": 2.6873391761995103e-05, "epoch": 2.2480270574971817, "percentage": 44.98, "elapsed_time": "0:22:45", "remaining_time": "0:27:50"}
525
+ {"current_steps": 498, "total_steps": 1105, "loss": 1.1742, "lr": 2.6813996560899976e-05, "epoch": 2.2525366403607667, "percentage": 45.07, "elapsed_time": "0:23:09", "remaining_time": "0:28:13"}
526
+ {"current_steps": 499, "total_steps": 1105, "loss": 1.1355, "lr": 2.6754533294071953e-05, "epoch": 2.2570462232243518, "percentage": 45.16, "elapsed_time": "0:23:33", "remaining_time": "0:28:36"}
527
+ {"current_steps": 500, "total_steps": 1105, "loss": 1.1437, "lr": 2.669500255549591e-05, "epoch": 2.261555806087937, "percentage": 45.25, "elapsed_time": "0:23:57", "remaining_time": "0:28:59"}
528
+ {"current_steps": 501, "total_steps": 1105, "loss": 1.1356, "lr": 2.663540493983068e-05, "epoch": 2.266065388951522, "percentage": 45.34, "elapsed_time": "0:24:21", "remaining_time": "0:29:21"}
529
+ {"current_steps": 502, "total_steps": 1105, "loss": 1.1199, "lr": 2.6575741042403166e-05, "epoch": 2.270574971815107, "percentage": 45.43, "elapsed_time": "0:24:45", "remaining_time": "0:29:44"}
530
+ {"current_steps": 503, "total_steps": 1105, "loss": 1.1226, "lr": 2.6516011459202356e-05, "epoch": 2.275084554678692, "percentage": 45.52, "elapsed_time": "0:25:08", "remaining_time": "0:30:05"}
531
+ {"current_steps": 504, "total_steps": 1105, "loss": 1.1609, "lr": 2.645621678687337e-05, "epoch": 2.2795941375422775, "percentage": 45.61, "elapsed_time": "0:25:33", "remaining_time": "0:30:28"}
532
+ {"current_steps": 505, "total_steps": 1105, "loss": 1.1194, "lr": 2.6396357622711524e-05, "epoch": 2.2841037204058625, "percentage": 45.7, "elapsed_time": "0:25:56", "remaining_time": "0:30:49"}
533
+ {"current_steps": 506, "total_steps": 1105, "loss": 1.1294, "lr": 2.633643456465635e-05, "epoch": 2.2886133032694476, "percentage": 45.79, "elapsed_time": "0:26:21", "remaining_time": "0:31:11"}
534
+ {"current_steps": 507, "total_steps": 1105, "loss": 1.1577, "lr": 2.6276448211285605e-05, "epoch": 2.2931228861330326, "percentage": 45.88, "elapsed_time": "0:26:45", "remaining_time": "0:31:33"}
535
+ {"current_steps": 508, "total_steps": 1105, "loss": 1.1246, "lr": 2.6216399161809337e-05, "epoch": 2.2976324689966177, "percentage": 45.97, "elapsed_time": "0:27:10", "remaining_time": "0:31:55"}
536
+ {"current_steps": 509, "total_steps": 1105, "loss": 1.1165, "lr": 2.6156288016063847e-05, "epoch": 2.302142051860203, "percentage": 46.06, "elapsed_time": "0:27:34", "remaining_time": "0:32:17"}
537
+ {"current_steps": 510, "total_steps": 1105, "loss": 1.1214, "lr": 2.609611537450573e-05, "epoch": 2.306651634723788, "percentage": 46.15, "elapsed_time": "0:27:58", "remaining_time": "0:32:38"}
538
+ {"current_steps": 511, "total_steps": 1105, "loss": 1.0946, "lr": 2.6035881838205885e-05, "epoch": 2.3111612175873733, "percentage": 46.24, "elapsed_time": "0:28:22", "remaining_time": "0:32:59"}
539
+ {"current_steps": 512, "total_steps": 1105, "loss": 1.1042, "lr": 2.5975588008843478e-05, "epoch": 2.3156708004509583, "percentage": 46.33, "elapsed_time": "0:28:46", "remaining_time": "0:33:19"}
540
+ {"current_steps": 513, "total_steps": 1105, "loss": 1.1589, "lr": 2.591523448869994e-05, "epoch": 2.3201803833145433, "percentage": 46.43, "elapsed_time": "0:29:10", "remaining_time": "0:33:40"}
541
+ {"current_steps": 514, "total_steps": 1105, "loss": 1.147, "lr": 2.5854821880652975e-05, "epoch": 2.3246899661781284, "percentage": 46.52, "elapsed_time": "0:29:34", "remaining_time": "0:34:00"}
542
+ {"current_steps": 515, "total_steps": 1105, "loss": 1.1334, "lr": 2.5794350788170532e-05, "epoch": 2.3291995490417134, "percentage": 46.61, "elapsed_time": "0:29:59", "remaining_time": "0:34:21"}
543
+ {"current_steps": 516, "total_steps": 1105, "loss": 1.1029, "lr": 2.5733821815304748e-05, "epoch": 2.333709131905299, "percentage": 46.7, "elapsed_time": "0:30:24", "remaining_time": "0:34:42"}
544
+ {"current_steps": 517, "total_steps": 1105, "loss": 1.1323, "lr": 2.5673235566685935e-05, "epoch": 2.338218714768884, "percentage": 46.79, "elapsed_time": "0:30:48", "remaining_time": "0:35:02"}
545
+ {"current_steps": 518, "total_steps": 1105, "loss": 1.1247, "lr": 2.5612592647516546e-05, "epoch": 2.342728297632469, "percentage": 46.88, "elapsed_time": "0:31:12", "remaining_time": "0:35:21"}
546
+ {"current_steps": 519, "total_steps": 1105, "loss": 1.1469, "lr": 2.555189366356513e-05, "epoch": 2.347237880496054, "percentage": 46.97, "elapsed_time": "0:31:37", "remaining_time": "0:35:42"}
547
+ {"current_steps": 520, "total_steps": 1105, "loss": 1.1336, "lr": 2.5491139221160242e-05, "epoch": 2.351747463359639, "percentage": 47.06, "elapsed_time": "0:32:01", "remaining_time": "0:36:01"}
548
+ {"current_steps": 521, "total_steps": 1105, "loss": 1.144, "lr": 2.5430329927184455e-05, "epoch": 2.356257046223224, "percentage": 47.15, "elapsed_time": "0:32:25", "remaining_time": "0:36:21"}
549
+ {"current_steps": 522, "total_steps": 1105, "loss": 1.1686, "lr": 2.536946638906824e-05, "epoch": 2.3607666290868092, "percentage": 47.24, "elapsed_time": "0:32:50", "remaining_time": "0:36:40"}
550
+ {"current_steps": 523, "total_steps": 1105, "loss": 1.1353, "lr": 2.5308549214783917e-05, "epoch": 2.3652762119503947, "percentage": 47.33, "elapsed_time": "0:33:13", "remaining_time": "0:36:58"}
551
+ {"current_steps": 524, "total_steps": 1105, "loss": 1.1313, "lr": 2.5247579012839584e-05, "epoch": 2.3697857948139798, "percentage": 47.42, "elapsed_time": "0:33:37", "remaining_time": "0:37:17"}
552
+ {"current_steps": 525, "total_steps": 1105, "loss": 1.1436, "lr": 2.518655639227305e-05, "epoch": 2.374295377677565, "percentage": 47.51, "elapsed_time": "0:34:01", "remaining_time": "0:37:35"}
553
+ {"current_steps": 526, "total_steps": 1105, "loss": 1.1892, "lr": 2.512548196264573e-05, "epoch": 2.37880496054115, "percentage": 47.6, "elapsed_time": "0:34:25", "remaining_time": "0:37:53"}
554
+ {"current_steps": 527, "total_steps": 1105, "loss": 1.1438, "lr": 2.5064356334036567e-05, "epoch": 2.383314543404735, "percentage": 47.69, "elapsed_time": "0:34:49", "remaining_time": "0:38:11"}
555
+ {"current_steps": 528, "total_steps": 1105, "loss": 1.1457, "lr": 2.500318011703593e-05, "epoch": 2.3878241262683204, "percentage": 47.78, "elapsed_time": "0:35:13", "remaining_time": "0:38:29"}
556
+ {"current_steps": 529, "total_steps": 1105, "loss": 1.1069, "lr": 2.494195392273953e-05, "epoch": 2.3923337091319055, "percentage": 47.87, "elapsed_time": "0:35:37", "remaining_time": "0:38:47"}
557
+ {"current_steps": 530, "total_steps": 1105, "loss": 1.1199, "lr": 2.4880678362742297e-05, "epoch": 2.3968432919954905, "percentage": 47.96, "elapsed_time": "0:36:01", "remaining_time": "0:39:05"}
558
+ {"current_steps": 531, "total_steps": 1105, "loss": 1.1343, "lr": 2.481935404913229e-05, "epoch": 2.4013528748590756, "percentage": 48.05, "elapsed_time": "0:36:25", "remaining_time": "0:39:22"}
559
+ {"current_steps": 532, "total_steps": 1105, "loss": 1.1369, "lr": 2.475798159448457e-05, "epoch": 2.4058624577226606, "percentage": 48.14, "elapsed_time": "0:36:49", "remaining_time": "0:39:40"}
560
+ {"current_steps": 533, "total_steps": 1105, "loss": 1.1265, "lr": 2.4696561611855083e-05, "epoch": 2.4103720405862457, "percentage": 48.24, "elapsed_time": "0:37:13", "remaining_time": "0:39:57"}
561
+ {"current_steps": 534, "total_steps": 1105, "loss": 1.1198, "lr": 2.463509471477453e-05, "epoch": 2.4148816234498307, "percentage": 48.33, "elapsed_time": "0:37:38", "remaining_time": "0:40:14"}
562
+ {"current_steps": 535, "total_steps": 1105, "loss": 1.1118, "lr": 2.4573581517242264e-05, "epoch": 2.419391206313416, "percentage": 48.42, "elapsed_time": "0:38:02", "remaining_time": "0:40:31"}
563
+ {"current_steps": 536, "total_steps": 1105, "loss": 1.1439, "lr": 2.4512022633720116e-05, "epoch": 2.4239007891770012, "percentage": 48.51, "elapsed_time": "0:38:26", "remaining_time": "0:40:48"}
564
+ {"current_steps": 537, "total_steps": 1105, "loss": 1.1203, "lr": 2.445041867912629e-05, "epoch": 2.4284103720405863, "percentage": 48.6, "elapsed_time": "0:38:50", "remaining_time": "0:41:04"}
565
+ {"current_steps": 538, "total_steps": 1105, "loss": 1.1115, "lr": 2.4388770268829217e-05, "epoch": 2.4329199549041713, "percentage": 48.69, "elapsed_time": "0:39:14", "remaining_time": "0:41:21"}
566
+ {"current_steps": 539, "total_steps": 1105, "loss": 1.1489, "lr": 2.4327078018641382e-05, "epoch": 2.4374295377677564, "percentage": 48.78, "elapsed_time": "0:39:38", "remaining_time": "0:41:37"}
567
+ {"current_steps": 540, "total_steps": 1105, "loss": 1.1301, "lr": 2.426534254481321e-05, "epoch": 2.4419391206313414, "percentage": 48.87, "elapsed_time": "0:40:02", "remaining_time": "0:41:53"}
568
+ {"current_steps": 541, "total_steps": 1105, "loss": 1.1425, "lr": 2.4203564464026873e-05, "epoch": 2.4464487034949265, "percentage": 48.96, "elapsed_time": "0:40:26", "remaining_time": "0:42:10"}
569
+ {"current_steps": 542, "total_steps": 1105, "loss": 1.1284, "lr": 2.4141744393390178e-05, "epoch": 2.450958286358512, "percentage": 49.05, "elapsed_time": "0:40:51", "remaining_time": "0:42:26"}
570
+ {"current_steps": 543, "total_steps": 1105, "loss": 1.1325, "lr": 2.4079882950430337e-05, "epoch": 2.455467869222097, "percentage": 49.14, "elapsed_time": "0:41:16", "remaining_time": "0:42:42"}
571
+ {"current_steps": 544, "total_steps": 1105, "loss": 1.1131, "lr": 2.401798075308786e-05, "epoch": 2.459977452085682, "percentage": 49.23, "elapsed_time": "0:41:40", "remaining_time": "0:42:58"}
572
+ {"current_steps": 545, "total_steps": 1105, "loss": 1.1617, "lr": 2.3956038419710348e-05, "epoch": 2.464487034949267, "percentage": 49.32, "elapsed_time": "0:42:03", "remaining_time": "0:43:13"}
573
+ {"current_steps": 546, "total_steps": 1105, "loss": 1.1731, "lr": 2.389405656904632e-05, "epoch": 2.468996617812852, "percentage": 49.41, "elapsed_time": "0:42:27", "remaining_time": "0:43:28"}
574
+ {"current_steps": 547, "total_steps": 1105, "loss": 1.157, "lr": 2.383203582023905e-05, "epoch": 2.4735062006764377, "percentage": 49.5, "elapsed_time": "0:42:51", "remaining_time": "0:43:42"}
575
+ {"current_steps": 548, "total_steps": 1105, "loss": 1.135, "lr": 2.376997679282036e-05, "epoch": 2.4780157835400227, "percentage": 49.59, "elapsed_time": "0:43:15", "remaining_time": "0:43:57"}
576
+ {"current_steps": 549, "total_steps": 1105, "loss": 1.1232, "lr": 2.370788010670444e-05, "epoch": 2.4825253664036078, "percentage": 49.68, "elapsed_time": "0:43:39", "remaining_time": "0:44:12"}
577
+ {"current_steps": 550, "total_steps": 1105, "loss": 1.1191, "lr": 2.3645746382181668e-05, "epoch": 2.487034949267193, "percentage": 49.77, "elapsed_time": "0:44:04", "remaining_time": "0:44:28"}
578
+ {"current_steps": 551, "total_steps": 1105, "loss": 1.0964, "lr": 2.3583576239912382e-05, "epoch": 2.491544532130778, "percentage": 49.86, "elapsed_time": "0:44:28", "remaining_time": "0:44:42"}
579
+ {"current_steps": 552, "total_steps": 1105, "loss": 1.094, "lr": 2.3521370300920726e-05, "epoch": 2.496054114994363, "percentage": 49.95, "elapsed_time": "0:44:52", "remaining_time": "0:44:57"}
580
+ {"current_steps": 553, "total_steps": 1105, "loss": 1.1179, "lr": 2.3459129186588405e-05, "epoch": 2.500563697857948, "percentage": 50.05, "elapsed_time": "0:45:16", "remaining_time": "0:45:11"}
581
+ {"current_steps": 554, "total_steps": 1105, "loss": 1.1423, "lr": 2.33968535186485e-05, "epoch": 2.5050732807215335, "percentage": 50.14, "elapsed_time": "0:45:40", "remaining_time": "0:45:25"}
582
+ {"current_steps": 555, "total_steps": 1105, "loss": 1.1271, "lr": 2.3334543919179245e-05, "epoch": 2.5095828635851185, "percentage": 50.23, "elapsed_time": "0:46:04", "remaining_time": "0:45:39"}
583
+ {"current_steps": 556, "total_steps": 1105, "loss": 1.1359, "lr": 2.3272201010597836e-05, "epoch": 2.5140924464487036, "percentage": 50.32, "elapsed_time": "0:46:28", "remaining_time": "0:45:53"}
584
+ {"current_steps": 557, "total_steps": 1105, "loss": 1.1066, "lr": 2.3209825415654166e-05, "epoch": 2.5186020293122886, "percentage": 50.41, "elapsed_time": "0:46:52", "remaining_time": "0:46:06"}
585
+ {"current_steps": 558, "total_steps": 1105, "loss": 1.1546, "lr": 2.314741775742467e-05, "epoch": 2.5231116121758737, "percentage": 50.5, "elapsed_time": "0:47:16", "remaining_time": "0:46:20"}
586
+ {"current_steps": 559, "total_steps": 1105, "loss": 1.162, "lr": 2.3084978659306048e-05, "epoch": 2.5276211950394587, "percentage": 50.59, "elapsed_time": "0:47:40", "remaining_time": "0:46:34"}
587
+ {"current_steps": 560, "total_steps": 1105, "loss": 1.1933, "lr": 2.3022508745009066e-05, "epoch": 2.5321307779030438, "percentage": 50.68, "elapsed_time": "0:48:04", "remaining_time": "0:46:47"}
588
+ {"current_steps": 561, "total_steps": 1105, "loss": 1.1575, "lr": 2.296000863855229e-05, "epoch": 2.5366403607666292, "percentage": 50.77, "elapsed_time": "0:48:28", "remaining_time": "0:47:00"}
589
+ {"current_steps": 562, "total_steps": 1105, "loss": 1.1705, "lr": 2.289747896425593e-05, "epoch": 2.5411499436302143, "percentage": 50.86, "elapsed_time": "0:48:52", "remaining_time": "0:47:13"}
590
+ {"current_steps": 563, "total_steps": 1105, "loss": 1.1934, "lr": 2.2834920346735497e-05, "epoch": 2.5456595264937993, "percentage": 50.95, "elapsed_time": "0:49:17", "remaining_time": "0:47:26"}
591
+ {"current_steps": 564, "total_steps": 1105, "loss": 1.1527, "lr": 2.2772333410895645e-05, "epoch": 2.5501691093573844, "percentage": 51.04, "elapsed_time": "0:49:41", "remaining_time": "0:47:40"}
592
+ {"current_steps": 565, "total_steps": 1105, "loss": 1.1469, "lr": 2.2709718781923916e-05, "epoch": 2.5546786922209694, "percentage": 51.13, "elapsed_time": "0:50:06", "remaining_time": "0:47:53"}
593
+ {"current_steps": 566, "total_steps": 1105, "loss": 1.1806, "lr": 2.2647077085284453e-05, "epoch": 2.559188275084555, "percentage": 51.22, "elapsed_time": "0:50:29", "remaining_time": "0:48:05"}
594
+ {"current_steps": 567, "total_steps": 1105, "loss": 1.1697, "lr": 2.2584408946711793e-05, "epoch": 2.5636978579481395, "percentage": 51.31, "elapsed_time": "0:50:53", "remaining_time": "0:48:17"}
595
+ {"current_steps": 568, "total_steps": 1105, "loss": 1.1315, "lr": 2.2521714992204616e-05, "epoch": 2.568207440811725, "percentage": 51.4, "elapsed_time": "0:51:17", "remaining_time": "0:48:29"}
596
+ {"current_steps": 569, "total_steps": 1105, "loss": 1.1197, "lr": 2.2458995848019462e-05, "epoch": 2.57271702367531, "percentage": 51.49, "elapsed_time": "0:51:41", "remaining_time": "0:48:41"}
597
+ {"current_steps": 570, "total_steps": 1105, "loss": 1.1538, "lr": 2.2396252140664508e-05, "epoch": 2.577226606538895, "percentage": 51.58, "elapsed_time": "0:52:05", "remaining_time": "0:48:53"}
598
+ {"current_steps": 571, "total_steps": 1105, "loss": 1.131, "lr": 2.233348449689328e-05, "epoch": 2.58173618940248, "percentage": 51.67, "elapsed_time": "0:52:29", "remaining_time": "0:49:05"}
599
+ {"current_steps": 572, "total_steps": 1105, "loss": 1.1242, "lr": 2.227069354369842e-05, "epoch": 2.5862457722660652, "percentage": 51.76, "elapsed_time": "0:52:53", "remaining_time": "0:49:17"}
600
+ {"current_steps": 573, "total_steps": 1105, "loss": 1.1325, "lr": 2.22078799083054e-05, "epoch": 2.5907553551296507, "percentage": 51.86, "elapsed_time": "0:53:17", "remaining_time": "0:49:28"}
601
+ {"current_steps": 574, "total_steps": 1105, "loss": 1.1353, "lr": 2.2145044218166274e-05, "epoch": 2.5952649379932358, "percentage": 51.95, "elapsed_time": "0:53:41", "remaining_time": "0:49:40"}
602
+ {"current_steps": 575, "total_steps": 1105, "loss": 1.1672, "lr": 2.2082187100953413e-05, "epoch": 2.599774520856821, "percentage": 52.04, "elapsed_time": "0:54:05", "remaining_time": "0:49:51"}
603
+ {"current_steps": 576, "total_steps": 1105, "loss": 1.1122, "lr": 2.2019309184553205e-05, "epoch": 2.604284103720406, "percentage": 52.13, "elapsed_time": "0:54:29", "remaining_time": "0:50:02"}
604
+ {"current_steps": 577, "total_steps": 1105, "loss": 1.14, "lr": 2.1956411097059803e-05, "epoch": 2.608793686583991, "percentage": 52.22, "elapsed_time": "0:54:53", "remaining_time": "0:50:13"}
605
+ {"current_steps": 578, "total_steps": 1105, "loss": 1.0837, "lr": 2.1893493466768877e-05, "epoch": 2.613303269447576, "percentage": 52.31, "elapsed_time": "0:55:17", "remaining_time": "0:50:24"}
606
+ {"current_steps": 579, "total_steps": 1105, "loss": 1.1064, "lr": 2.18305569221713e-05, "epoch": 2.617812852311161, "percentage": 52.4, "elapsed_time": "0:55:41", "remaining_time": "0:50:35"}
607
+ {"current_steps": 580, "total_steps": 1105, "loss": 1.1406, "lr": 2.176760209194685e-05, "epoch": 2.6223224351747465, "percentage": 52.49, "elapsed_time": "0:56:05", "remaining_time": "0:50:46"}
608
+ {"current_steps": 581, "total_steps": 1105, "loss": 1.1352, "lr": 2.1704629604958017e-05, "epoch": 2.6268320180383316, "percentage": 52.58, "elapsed_time": "0:56:29", "remaining_time": "0:50:56"}
609
+ {"current_steps": 582, "total_steps": 1105, "loss": 1.132, "lr": 2.1641640090243628e-05, "epoch": 2.6313416009019166, "percentage": 52.67, "elapsed_time": "0:56:53", "remaining_time": "0:51:07"}
610
+ {"current_steps": 583, "total_steps": 1105, "loss": 1.1355, "lr": 2.1578634177012613e-05, "epoch": 2.6358511837655016, "percentage": 52.76, "elapsed_time": "0:57:18", "remaining_time": "0:51:18"}
611
+ {"current_steps": 584, "total_steps": 1105, "loss": 1.1611, "lr": 2.1515612494637704e-05, "epoch": 2.6403607666290867, "percentage": 52.85, "elapsed_time": "0:57:42", "remaining_time": "0:51:28"}
612
+ {"current_steps": 585, "total_steps": 1105, "loss": 1.1392, "lr": 2.1452575672649165e-05, "epoch": 2.644870349492672, "percentage": 52.94, "elapsed_time": "0:58:06", "remaining_time": "0:51:38"}
613
+ {"current_steps": 586, "total_steps": 1105, "loss": 1.1101, "lr": 2.138952434072848e-05, "epoch": 2.649379932356257, "percentage": 53.03, "elapsed_time": "0:58:30", "remaining_time": "0:51:49"}
614
+ {"current_steps": 587, "total_steps": 1105, "loss": 1.1562, "lr": 2.132645912870208e-05, "epoch": 2.6538895152198423, "percentage": 53.12, "elapsed_time": "0:58:55", "remaining_time": "0:51:59"}
615
+ {"current_steps": 588, "total_steps": 1105, "loss": 1.1755, "lr": 2.1263380666535043e-05, "epoch": 2.6583990980834273, "percentage": 53.21, "elapsed_time": "0:59:19", "remaining_time": "0:52:09"}
616
+ {"current_steps": 589, "total_steps": 1105, "loss": 1.1473, "lr": 2.12002895843248e-05, "epoch": 2.6629086809470124, "percentage": 53.3, "elapsed_time": "0:59:43", "remaining_time": "0:52:19"}
617
+ {"current_steps": 590, "total_steps": 1105, "loss": 1.1255, "lr": 2.1137186512294844e-05, "epoch": 2.6674182638105974, "percentage": 53.39, "elapsed_time": "1:00:07", "remaining_time": "0:52:28"}
618
+ {"current_steps": 591, "total_steps": 1105, "loss": 1.1284, "lr": 2.1074072080788453e-05, "epoch": 2.6719278466741825, "percentage": 53.48, "elapsed_time": "1:00:32", "remaining_time": "0:52:38"}
619
+ {"current_steps": 592, "total_steps": 1105, "loss": 1.1517, "lr": 2.1010946920262362e-05, "epoch": 2.676437429537768, "percentage": 53.57, "elapsed_time": "1:00:55", "remaining_time": "0:52:48"}
620
+ {"current_steps": 593, "total_steps": 1105, "loss": 1.1441, "lr": 2.0947811661280478e-05, "epoch": 2.680947012401353, "percentage": 53.67, "elapsed_time": "1:01:20", "remaining_time": "0:52:57"}
621
+ {"current_steps": 594, "total_steps": 1105, "loss": 1.1628, "lr": 2.088466693450758e-05, "epoch": 2.685456595264938, "percentage": 53.76, "elapsed_time": "1:01:44", "remaining_time": "0:53:06"}
622
+ {"current_steps": 595, "total_steps": 1105, "loss": 1.1581, "lr": 2.0821513370703034e-05, "epoch": 2.689966178128523, "percentage": 53.85, "elapsed_time": "1:02:08", "remaining_time": "0:53:15"}
623
+ {"current_steps": 596, "total_steps": 1105, "loss": 1.1147, "lr": 2.075835160071448e-05, "epoch": 2.694475760992108, "percentage": 53.94, "elapsed_time": "1:02:32", "remaining_time": "0:53:24"}
624
+ {"current_steps": 597, "total_steps": 1105, "loss": 1.1043, "lr": 2.069518225547151e-05, "epoch": 2.698985343855693, "percentage": 54.03, "elapsed_time": "1:02:55", "remaining_time": "0:53:32"}
625
+ {"current_steps": 598, "total_steps": 1105, "loss": 1.1651, "lr": 2.0632005965979408e-05, "epoch": 2.7034949267192783, "percentage": 54.12, "elapsed_time": "1:03:19", "remaining_time": "0:53:41"}
626
+ {"current_steps": 599, "total_steps": 1105, "loss": 1.1176, "lr": 2.0568823363312816e-05, "epoch": 2.7080045095828638, "percentage": 54.21, "elapsed_time": "1:03:43", "remaining_time": "0:53:49"}
627
+ {"current_steps": 600, "total_steps": 1105, "loss": 1.111, "lr": 2.0505635078609436e-05, "epoch": 2.712514092446449, "percentage": 54.3, "elapsed_time": "1:04:07", "remaining_time": "0:53:57"}
628
+ {"current_steps": 601, "total_steps": 1105, "loss": 1.1097, "lr": 2.044244174306374e-05, "epoch": 2.717023675310034, "percentage": 54.39, "elapsed_time": "1:04:31", "remaining_time": "0:54:06"}
629
+ {"current_steps": 602, "total_steps": 1105, "loss": 1.1247, "lr": 2.037924398792064e-05, "epoch": 2.721533258173619, "percentage": 54.48, "elapsed_time": "1:04:55", "remaining_time": "0:54:15"}
630
+ {"current_steps": 603, "total_steps": 1105, "loss": 1.1051, "lr": 2.0316042444469204e-05, "epoch": 2.726042841037204, "percentage": 54.57, "elapsed_time": "1:05:19", "remaining_time": "0:54:23"}
631
+ {"current_steps": 604, "total_steps": 1105, "loss": 1.1318, "lr": 2.0252837744036338e-05, "epoch": 2.7305524239007894, "percentage": 54.66, "elapsed_time": "1:05:43", "remaining_time": "0:54:31"}
632
+ {"current_steps": 605, "total_steps": 1105, "loss": 1.1434, "lr": 2.018963051798048e-05, "epoch": 2.735062006764374, "percentage": 54.75, "elapsed_time": "1:06:07", "remaining_time": "0:54:38"}
633
+ {"current_steps": 606, "total_steps": 1105, "loss": 1.1544, "lr": 2.012642139768531e-05, "epoch": 2.7395715896279595, "percentage": 54.84, "elapsed_time": "1:06:31", "remaining_time": "0:54:46"}
634
+ {"current_steps": 607, "total_steps": 1105, "loss": 1.1426, "lr": 2.006321101455341e-05, "epoch": 2.7440811724915446, "percentage": 54.93, "elapsed_time": "1:06:55", "remaining_time": "0:54:54"}
635
+ {"current_steps": 608, "total_steps": 1105, "loss": 1.2021, "lr": 2e-05, "epoch": 2.7485907553551296, "percentage": 55.02, "elapsed_time": "1:07:19", "remaining_time": "0:55:01"}
636
+ {"current_steps": 609, "total_steps": 1105, "loss": 1.0932, "lr": 1.9936788985446597e-05, "epoch": 2.7531003382187147, "percentage": 55.11, "elapsed_time": "1:07:44", "remaining_time": "0:55:10"}
637
+ {"current_steps": 610, "total_steps": 1105, "loss": 1.1272, "lr": 1.9873578602314695e-05, "epoch": 2.7576099210822997, "percentage": 55.2, "elapsed_time": "1:08:08", "remaining_time": "0:55:17"}
638
+ {"current_steps": 611, "total_steps": 1105, "loss": 1.1251, "lr": 1.981036948201953e-05, "epoch": 2.7621195039458852, "percentage": 55.29, "elapsed_time": "1:08:32", "remaining_time": "0:55:24"}
639
+ {"current_steps": 612, "total_steps": 1105, "loss": 1.136, "lr": 1.974716225596367e-05, "epoch": 2.7666290868094703, "percentage": 55.38, "elapsed_time": "1:08:55", "remaining_time": "0:55:31"}
640
+ {"current_steps": 613, "total_steps": 1105, "loss": 1.136, "lr": 1.9683957555530803e-05, "epoch": 2.7711386696730553, "percentage": 55.48, "elapsed_time": "1:09:19", "remaining_time": "0:55:38"}
641
+ {"current_steps": 614, "total_steps": 1105, "loss": 1.165, "lr": 1.962075601207936e-05, "epoch": 2.7756482525366404, "percentage": 55.57, "elapsed_time": "1:09:43", "remaining_time": "0:55:45"}
642
+ {"current_steps": 615, "total_steps": 1105, "loss": 1.1583, "lr": 1.9557558256936266e-05, "epoch": 2.7801578354002254, "percentage": 55.66, "elapsed_time": "1:10:07", "remaining_time": "0:55:52"}
643
+ {"current_steps": 616, "total_steps": 1105, "loss": 1.1401, "lr": 1.9494364921390564e-05, "epoch": 2.7846674182638105, "percentage": 55.75, "elapsed_time": "1:10:31", "remaining_time": "0:55:59"}
644
+ {"current_steps": 617, "total_steps": 1105, "loss": 1.1577, "lr": 1.9431176636687188e-05, "epoch": 2.7891770011273955, "percentage": 55.84, "elapsed_time": "1:10:55", "remaining_time": "0:56:06"}
645
+ {"current_steps": 618, "total_steps": 1105, "loss": 1.1414, "lr": 1.93679940340206e-05, "epoch": 2.793686583990981, "percentage": 55.93, "elapsed_time": "1:11:19", "remaining_time": "0:56:12"}
646
+ {"current_steps": 619, "total_steps": 1105, "loss": 1.1203, "lr": 1.9304817744528498e-05, "epoch": 2.798196166854566, "percentage": 56.02, "elapsed_time": "1:11:43", "remaining_time": "0:56:19"}
647
+ {"current_steps": 620, "total_steps": 1105, "loss": 1.1297, "lr": 1.9241648399285528e-05, "epoch": 2.802705749718151, "percentage": 56.11, "elapsed_time": "1:12:08", "remaining_time": "0:56:25"}
648
+ {"current_steps": 621, "total_steps": 1105, "loss": 1.1407, "lr": 1.9178486629296966e-05, "epoch": 2.807215332581736, "percentage": 56.2, "elapsed_time": "1:12:31", "remaining_time": "0:56:31"}
649
+ {"current_steps": 622, "total_steps": 1105, "loss": 1.1245, "lr": 1.9115333065492428e-05, "epoch": 2.811724915445321, "percentage": 56.29, "elapsed_time": "1:12:55", "remaining_time": "0:56:37"}
650
+ {"current_steps": 623, "total_steps": 1105, "loss": 1.1172, "lr": 1.9052188338719532e-05, "epoch": 2.8162344983089063, "percentage": 56.38, "elapsed_time": "1:13:19", "remaining_time": "0:56:43"}
651
+ {"current_steps": 624, "total_steps": 1105, "loss": 1.1366, "lr": 1.8989053079737644e-05, "epoch": 2.8207440811724913, "percentage": 56.47, "elapsed_time": "1:13:43", "remaining_time": "0:56:49"}
652
+ {"current_steps": 625, "total_steps": 1105, "loss": 1.139, "lr": 1.8925927919211554e-05, "epoch": 2.825253664036077, "percentage": 56.56, "elapsed_time": "1:14:07", "remaining_time": "0:56:55"}
653
+ {"current_steps": 626, "total_steps": 1105, "loss": 1.1449, "lr": 1.886281348770516e-05, "epoch": 2.829763246899662, "percentage": 56.65, "elapsed_time": "1:14:30", "remaining_time": "0:57:00"}
654
+ {"current_steps": 627, "total_steps": 1105, "loss": 1.1023, "lr": 1.879971041567521e-05, "epoch": 2.834272829763247, "percentage": 56.74, "elapsed_time": "1:14:54", "remaining_time": "0:57:06"}
655
+ {"current_steps": 628, "total_steps": 1105, "loss": 1.15, "lr": 1.8736619333464964e-05, "epoch": 2.838782412626832, "percentage": 56.83, "elapsed_time": "1:15:18", "remaining_time": "0:57:12"}
656
+ {"current_steps": 629, "total_steps": 1105, "loss": 1.1224, "lr": 1.8673540871297927e-05, "epoch": 2.843291995490417, "percentage": 56.92, "elapsed_time": "1:15:42", "remaining_time": "0:57:17"}
657
+ {"current_steps": 630, "total_steps": 1105, "loss": 1.1588, "lr": 1.861047565927152e-05, "epoch": 2.8478015783540025, "percentage": 57.01, "elapsed_time": "1:16:06", "remaining_time": "0:57:23"}
658
+ {"current_steps": 631, "total_steps": 1105, "loss": 1.1225, "lr": 1.8547424327350838e-05, "epoch": 2.852311161217587, "percentage": 57.1, "elapsed_time": "1:16:30", "remaining_time": "0:57:28"}
659
+ {"current_steps": 632, "total_steps": 1105, "loss": 1.1342, "lr": 1.84843875053623e-05, "epoch": 2.8568207440811726, "percentage": 57.19, "elapsed_time": "1:16:55", "remaining_time": "0:57:34"}
660
+ {"current_steps": 633, "total_steps": 1105, "loss": 1.1192, "lr": 1.8421365822987393e-05, "epoch": 2.8613303269447576, "percentage": 57.29, "elapsed_time": "1:17:18", "remaining_time": "0:57:38"}
661
+ {"current_steps": 634, "total_steps": 1105, "loss": 1.1382, "lr": 1.8358359909756382e-05, "epoch": 2.8658399098083427, "percentage": 57.38, "elapsed_time": "1:17:43", "remaining_time": "0:57:44"}
662
+ {"current_steps": 635, "total_steps": 1105, "loss": 1.1524, "lr": 1.829537039504199e-05, "epoch": 2.8703494926719277, "percentage": 57.47, "elapsed_time": "1:18:07", "remaining_time": "0:57:49"}
663
+ {"current_steps": 636, "total_steps": 1105, "loss": 1.1339, "lr": 1.8232397908053154e-05, "epoch": 2.874859075535513, "percentage": 57.56, "elapsed_time": "1:18:31", "remaining_time": "0:57:54"}
664
+ {"current_steps": 637, "total_steps": 1105, "loss": 1.128, "lr": 1.8169443077828708e-05, "epoch": 2.8793686583990983, "percentage": 57.65, "elapsed_time": "1:18:55", "remaining_time": "0:57:59"}
665
+ {"current_steps": 638, "total_steps": 1105, "loss": 1.182, "lr": 1.8106506533231127e-05, "epoch": 2.8838782412626833, "percentage": 57.74, "elapsed_time": "1:19:20", "remaining_time": "0:58:04"}
666
+ {"current_steps": 639, "total_steps": 1105, "loss": 1.1371, "lr": 1.80435889029402e-05, "epoch": 2.8883878241262684, "percentage": 57.83, "elapsed_time": "1:19:44", "remaining_time": "0:58:08"}
667
+ {"current_steps": 640, "total_steps": 1105, "loss": 1.1188, "lr": 1.7980690815446806e-05, "epoch": 2.8928974069898534, "percentage": 57.92, "elapsed_time": "1:20:07", "remaining_time": "0:58:13"}
668
+ {"current_steps": 641, "total_steps": 1105, "loss": 1.1429, "lr": 1.791781289904659e-05, "epoch": 2.8974069898534385, "percentage": 58.01, "elapsed_time": "1:20:31", "remaining_time": "0:58:17"}
669
+ {"current_steps": 642, "total_steps": 1105, "loss": 1.1067, "lr": 1.785495578183373e-05, "epoch": 2.9019165727170235, "percentage": 58.1, "elapsed_time": "1:20:55", "remaining_time": "0:58:21"}
670
+ {"current_steps": 643, "total_steps": 1105, "loss": 1.1242, "lr": 1.779212009169461e-05, "epoch": 2.9064261555806086, "percentage": 58.19, "elapsed_time": "1:21:19", "remaining_time": "0:58:25"}
671
+ {"current_steps": 644, "total_steps": 1105, "loss": 1.1276, "lr": 1.7729306456301588e-05, "epoch": 2.910935738444194, "percentage": 58.28, "elapsed_time": "1:21:43", "remaining_time": "0:58:30"}
672
+ {"current_steps": 645, "total_steps": 1105, "loss": 1.1769, "lr": 1.766651550310673e-05, "epoch": 2.915445321307779, "percentage": 58.37, "elapsed_time": "1:22:07", "remaining_time": "0:58:34"}
673
+ {"current_steps": 646, "total_steps": 1105, "loss": 1.1418, "lr": 1.76037478593355e-05, "epoch": 2.919954904171364, "percentage": 58.46, "elapsed_time": "1:22:31", "remaining_time": "0:58:38"}
674
+ {"current_steps": 647, "total_steps": 1105, "loss": 1.111, "lr": 1.754100415198054e-05, "epoch": 2.924464487034949, "percentage": 58.55, "elapsed_time": "1:22:55", "remaining_time": "0:58:42"}
675
+ {"current_steps": 648, "total_steps": 1105, "loss": 1.1651, "lr": 1.7478285007795387e-05, "epoch": 2.9289740698985343, "percentage": 58.64, "elapsed_time": "1:23:19", "remaining_time": "0:58:46"}
676
+ {"current_steps": 649, "total_steps": 1105, "loss": 1.1216, "lr": 1.7415591053288213e-05, "epoch": 2.9334836527621198, "percentage": 58.73, "elapsed_time": "1:23:43", "remaining_time": "0:58:49"}
677
+ {"current_steps": 650, "total_steps": 1105, "loss": 1.1385, "lr": 1.7352922914715553e-05, "epoch": 2.9379932356257044, "percentage": 58.82, "elapsed_time": "1:24:07", "remaining_time": "0:58:53"}
678
+ {"current_steps": 651, "total_steps": 1105, "loss": 1.1394, "lr": 1.729028121807609e-05, "epoch": 2.94250281848929, "percentage": 58.91, "elapsed_time": "1:24:32", "remaining_time": "0:58:57"}
679
+ {"current_steps": 652, "total_steps": 1105, "loss": 1.1459, "lr": 1.7227666589104362e-05, "epoch": 2.947012401352875, "percentage": 59.0, "elapsed_time": "1:24:56", "remaining_time": "0:59:00"}
680
+ {"current_steps": 653, "total_steps": 1105, "loss": 1.1022, "lr": 1.7165079653264506e-05, "epoch": 2.95152198421646, "percentage": 59.1, "elapsed_time": "1:25:20", "remaining_time": "0:59:04"}
681
+ {"current_steps": 654, "total_steps": 1105, "loss": 1.1305, "lr": 1.710252103574408e-05, "epoch": 2.956031567080045, "percentage": 59.19, "elapsed_time": "1:25:44", "remaining_time": "0:59:07"}
682
+ {"current_steps": 655, "total_steps": 1105, "loss": 1.1358, "lr": 1.7039991361447707e-05, "epoch": 2.96054114994363, "percentage": 59.28, "elapsed_time": "1:26:08", "remaining_time": "0:59:11"}
683
+ {"current_steps": 656, "total_steps": 1105, "loss": 1.096, "lr": 1.6977491254990944e-05, "epoch": 2.9650507328072155, "percentage": 59.37, "elapsed_time": "1:26:32", "remaining_time": "0:59:13"}
684
+ {"current_steps": 657, "total_steps": 1105, "loss": 1.1379, "lr": 1.6915021340693952e-05, "epoch": 2.9695603156708006, "percentage": 59.46, "elapsed_time": "1:26:56", "remaining_time": "0:59:17"}
685
+ {"current_steps": 658, "total_steps": 1105, "loss": 1.14, "lr": 1.6852582242575338e-05, "epoch": 2.9740698985343856, "percentage": 59.55, "elapsed_time": "1:27:20", "remaining_time": "0:59:20"}
686
+ {"current_steps": 659, "total_steps": 1105, "loss": 1.1568, "lr": 1.679017458434584e-05, "epoch": 2.9785794813979707, "percentage": 59.64, "elapsed_time": "1:27:44", "remaining_time": "0:59:23"}
687
+ {"current_steps": 660, "total_steps": 1105, "loss": 1.1519, "lr": 1.6727798989402174e-05, "epoch": 2.9830890642615557, "percentage": 59.73, "elapsed_time": "1:28:08", "remaining_time": "0:59:25"}
688
+ {"current_steps": 661, "total_steps": 1105, "loss": 1.15, "lr": 1.666545608082076e-05, "epoch": 2.987598647125141, "percentage": 59.82, "elapsed_time": "1:28:32", "remaining_time": "0:59:28"}
689
+ {"current_steps": 662, "total_steps": 1105, "loss": 1.1248, "lr": 1.6603146481351503e-05, "epoch": 2.992108229988726, "percentage": 59.91, "elapsed_time": "1:28:56", "remaining_time": "0:59:31"}
690
+ {"current_steps": 663, "total_steps": 1105, "loss": 1.1115, "lr": 1.65408708134116e-05, "epoch": 2.9966178128523113, "percentage": 60.0, "elapsed_time": "1:29:20", "remaining_time": "0:59:33"}
691
+ {"current_steps": 664, "total_steps": 1105, "loss": 1.0905, "lr": 1.6478629699079278e-05, "epoch": 3.0033821871476887, "percentage": 60.09, "elapsed_time": "1:32:10", "remaining_time": "1:01:13"}
692
+ {"current_steps": 665, "total_steps": 1105, "loss": 1.0713, "lr": 1.6416423760087625e-05, "epoch": 3.007891770011274, "percentage": 60.18, "elapsed_time": "1:32:34", "remaining_time": "1:01:15"}
693
+ {"current_steps": 666, "total_steps": 1105, "loss": 1.0468, "lr": 1.6354253617818342e-05, "epoch": 3.012401352874859, "percentage": 60.27, "elapsed_time": "1:32:58", "remaining_time": "1:01:17"}
694
+ {"current_steps": 667, "total_steps": 1105, "loss": 1.116, "lr": 1.6292119893295567e-05, "epoch": 3.0169109357384443, "percentage": 60.36, "elapsed_time": "1:33:22", "remaining_time": "1:01:18"}
695
+ {"current_steps": 668, "total_steps": 1105, "loss": 1.0563, "lr": 1.6230023207179653e-05, "epoch": 3.0214205186020293, "percentage": 60.45, "elapsed_time": "1:33:46", "remaining_time": "1:01:20"}
696
+ {"current_steps": 669, "total_steps": 1105, "loss": 1.0638, "lr": 1.6167964179760954e-05, "epoch": 3.0259301014656144, "percentage": 60.54, "elapsed_time": "1:34:10", "remaining_time": "1:01:22"}
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:929df364a31c44e2d94e00fbc4c1550b045bbf09501760210eaa3480608b4a46
3
- size 7352
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f51d049d22d45f60f3dc8ad33332756add24d81b10096d79e8523b00ac7db4e
3
+ size 7480