neginr commited on
Commit
00ecc00
·
verified ·
1 Parent(s): dbfeeb1

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:e9730f89d08dfa12709bfaa4dadc2f6e3d2dfdd68da63b6176983a6c0f5d3be8
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3fb72767070f1852e0d97a527a91e3befcfc9f631da93c8b70656c629d6c9eac
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:56542a30f5db7b9bc703b1f9edd6fbea2df1b7506de46d06755c5d7be4836415
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37bf5e32f5dc45dee46e39a99113a8609d4c76867cbcb0acb0a8fbe707e6c19b
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:085f03322cbd8ce6ae38cb56348ce87003c3606b2535f68725fa80cab1eb8f4d
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39ba9088568797ee4618f6f20de08cd625ae805adf1709585e098adfae6a4ce6
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:af4ca1d9a295fc9c7a490a21d8e228555fc4949c7ac7034e6929edfcde4dcb9f
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d13f78e38199d67936e5d5673a28bf60420f5b780acac587d5af306da45eb97
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -501,3 +501,353 @@
501
  {"current_steps": 501, "total_steps": 1245, "loss": 0.3534, "lr": 2.987016436128694e-05, "epoch": 2.0100300902708126, "percentage": 40.24, "elapsed_time": "4:28:49", "remaining_time": "6:39:12"}
502
  {"current_steps": 502, "total_steps": 1245, "loss": 0.3504, "lr": 2.982133323265469e-05, "epoch": 2.0140421263791373, "percentage": 40.32, "elapsed_time": "4:29:18", "remaining_time": "6:38:36"}
503
  {"current_steps": 503, "total_steps": 1245, "loss": 0.3853, "lr": 2.9772424829939103e-05, "epoch": 2.0180541624874624, "percentage": 40.4, "elapsed_time": "4:29:54", "remaining_time": "6:38:09"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
501
  {"current_steps": 501, "total_steps": 1245, "loss": 0.3534, "lr": 2.987016436128694e-05, "epoch": 2.0100300902708126, "percentage": 40.24, "elapsed_time": "4:28:49", "remaining_time": "6:39:12"}
502
  {"current_steps": 502, "total_steps": 1245, "loss": 0.3504, "lr": 2.982133323265469e-05, "epoch": 2.0140421263791373, "percentage": 40.32, "elapsed_time": "4:29:18", "remaining_time": "6:38:36"}
503
  {"current_steps": 503, "total_steps": 1245, "loss": 0.3853, "lr": 2.9772424829939103e-05, "epoch": 2.0180541624874624, "percentage": 40.4, "elapsed_time": "4:29:54", "remaining_time": "6:38:09"}
504
+ {"current_steps": 504, "total_steps": 1245, "loss": 0.3575, "lr": 2.9723439537950653e-05, "epoch": 2.0220661985957875, "percentage": 40.48, "elapsed_time": "4:30:30", "remaining_time": "6:37:42"}
505
+ {"current_steps": 505, "total_steps": 1245, "loss": 0.3763, "lr": 2.9674377742104798e-05, "epoch": 2.026078234704112, "percentage": 40.56, "elapsed_time": "4:31:03", "remaining_time": "6:37:11"}
506
+ {"current_steps": 506, "total_steps": 1245, "loss": 0.3411, "lr": 2.962523982841891e-05, "epoch": 2.0300902708124373, "percentage": 40.64, "elapsed_time": "4:31:35", "remaining_time": "6:36:39"}
507
+ {"current_steps": 507, "total_steps": 1245, "loss": 0.3615, "lr": 2.9576026183509258e-05, "epoch": 2.0341023069207624, "percentage": 40.72, "elapsed_time": "4:32:14", "remaining_time": "6:36:17"}
508
+ {"current_steps": 508, "total_steps": 1245, "loss": 0.3768, "lr": 2.9526737194587972e-05, "epoch": 2.038114343029087, "percentage": 40.8, "elapsed_time": "4:32:43", "remaining_time": "6:35:40"}
509
+ {"current_steps": 509, "total_steps": 1245, "loss": 0.3486, "lr": 2.9477373249459974e-05, "epoch": 2.0421263791374122, "percentage": 40.88, "elapsed_time": "4:33:13", "remaining_time": "6:35:04"}
510
+ {"current_steps": 510, "total_steps": 1245, "loss": 0.3605, "lr": 2.9427934736519962e-05, "epoch": 2.0461384152457374, "percentage": 40.96, "elapsed_time": "4:33:43", "remaining_time": "6:34:29"}
511
+ {"current_steps": 511, "total_steps": 1245, "loss": 0.3753, "lr": 2.937842204474929e-05, "epoch": 2.050150451354062, "percentage": 41.04, "elapsed_time": "4:34:16", "remaining_time": "6:33:57"}
512
+ {"current_steps": 512, "total_steps": 1245, "loss": 0.3814, "lr": 2.932883556371301e-05, "epoch": 2.054162487462387, "percentage": 41.12, "elapsed_time": "4:34:51", "remaining_time": "6:33:30"}
513
+ {"current_steps": 513, "total_steps": 1245, "loss": 0.3453, "lr": 2.9279175683556684e-05, "epoch": 2.0581745235707123, "percentage": 41.2, "elapsed_time": "4:35:14", "remaining_time": "6:32:44"}
514
+ {"current_steps": 514, "total_steps": 1245, "loss": 0.3307, "lr": 2.922944279500343e-05, "epoch": 2.062186559679037, "percentage": 41.29, "elapsed_time": "4:35:47", "remaining_time": "6:32:13"}
515
+ {"current_steps": 515, "total_steps": 1245, "loss": 0.3499, "lr": 2.9179637289350757e-05, "epoch": 2.066198595787362, "percentage": 41.37, "elapsed_time": "4:36:17", "remaining_time": "6:31:38"}
516
+ {"current_steps": 516, "total_steps": 1245, "loss": 0.3509, "lr": 2.9129759558467546e-05, "epoch": 2.070210631895687, "percentage": 41.45, "elapsed_time": "4:36:51", "remaining_time": "6:31:09"}
517
+ {"current_steps": 517, "total_steps": 1245, "loss": 0.3506, "lr": 2.9079809994790937e-05, "epoch": 2.074222668004012, "percentage": 41.53, "elapsed_time": "4:37:29", "remaining_time": "6:30:45"}
518
+ {"current_steps": 518, "total_steps": 1245, "loss": 0.3772, "lr": 2.9029788991323253e-05, "epoch": 2.078234704112337, "percentage": 41.61, "elapsed_time": "4:38:01", "remaining_time": "6:30:12"}
519
+ {"current_steps": 519, "total_steps": 1245, "loss": 0.3491, "lr": 2.8979696941628894e-05, "epoch": 2.082246740220662, "percentage": 41.69, "elapsed_time": "4:38:29", "remaining_time": "6:29:33"}
520
+ {"current_steps": 520, "total_steps": 1245, "loss": 0.3844, "lr": 2.892953423983126e-05, "epoch": 2.086258776328987, "percentage": 41.77, "elapsed_time": "4:39:04", "remaining_time": "6:29:05"}
521
+ {"current_steps": 521, "total_steps": 1245, "loss": 0.3784, "lr": 2.8879301280609645e-05, "epoch": 2.090270812437312, "percentage": 41.85, "elapsed_time": "4:39:37", "remaining_time": "6:28:35"}
522
+ {"current_steps": 522, "total_steps": 1245, "loss": 0.3465, "lr": 2.8828998459196113e-05, "epoch": 2.094282848545637, "percentage": 41.93, "elapsed_time": "4:40:06", "remaining_time": "6:27:57"}
523
+ {"current_steps": 523, "total_steps": 1245, "loss": 0.3295, "lr": 2.877862617137241e-05, "epoch": 2.0982948846539617, "percentage": 42.01, "elapsed_time": "4:40:38", "remaining_time": "6:27:24"}
524
+ {"current_steps": 524, "total_steps": 1245, "loss": 0.3599, "lr": 2.872818481346684e-05, "epoch": 2.102306920762287, "percentage": 42.09, "elapsed_time": "4:41:12", "remaining_time": "6:26:55"}
525
+ {"current_steps": 525, "total_steps": 1245, "loss": 0.371, "lr": 2.8677674782351164e-05, "epoch": 2.106318956870612, "percentage": 42.17, "elapsed_time": "4:41:44", "remaining_time": "6:26:22"}
526
+ {"current_steps": 526, "total_steps": 1245, "loss": 0.3658, "lr": 2.862709647543744e-05, "epoch": 2.1103309929789367, "percentage": 42.25, "elapsed_time": "4:42:18", "remaining_time": "6:25:53"}
527
+ {"current_steps": 527, "total_steps": 1245, "loss": 0.362, "lr": 2.8576450290674934e-05, "epoch": 2.114343029087262, "percentage": 42.33, "elapsed_time": "4:42:49", "remaining_time": "6:25:19"}
528
+ {"current_steps": 528, "total_steps": 1245, "loss": 0.3587, "lr": 2.8525736626546963e-05, "epoch": 2.118355065195587, "percentage": 42.41, "elapsed_time": "4:43:18", "remaining_time": "6:24:42"}
529
+ {"current_steps": 529, "total_steps": 1245, "loss": 0.379, "lr": 2.8474955882067776e-05, "epoch": 2.1223671013039116, "percentage": 42.49, "elapsed_time": "4:43:50", "remaining_time": "6:24:11"}
530
+ {"current_steps": 530, "total_steps": 1245, "loss": 0.3465, "lr": 2.8424108456779423e-05, "epoch": 2.1263791374122367, "percentage": 42.57, "elapsed_time": "4:44:29", "remaining_time": "6:23:48"}
531
+ {"current_steps": 531, "total_steps": 1245, "loss": 0.3605, "lr": 2.8373194750748566e-05, "epoch": 2.130391173520562, "percentage": 42.65, "elapsed_time": "4:45:02", "remaining_time": "6:23:16"}
532
+ {"current_steps": 532, "total_steps": 1245, "loss": 0.363, "lr": 2.8322215164563393e-05, "epoch": 2.1344032096288865, "percentage": 42.73, "elapsed_time": "4:45:36", "remaining_time": "6:22:46"}
533
+ {"current_steps": 533, "total_steps": 1245, "loss": 0.3842, "lr": 2.8271170099330415e-05, "epoch": 2.1384152457372116, "percentage": 42.81, "elapsed_time": "4:46:09", "remaining_time": "6:22:15"}
534
+ {"current_steps": 534, "total_steps": 1245, "loss": 0.3578, "lr": 2.822005995667135e-05, "epoch": 2.1424272818455368, "percentage": 42.89, "elapsed_time": "4:46:41", "remaining_time": "6:21:42"}
535
+ {"current_steps": 535, "total_steps": 1245, "loss": 0.3661, "lr": 2.8168885138719927e-05, "epoch": 2.1464393179538614, "percentage": 42.97, "elapsed_time": "4:47:10", "remaining_time": "6:21:06"}
536
+ {"current_steps": 536, "total_steps": 1245, "loss": 0.3737, "lr": 2.8117646048118748e-05, "epoch": 2.1504513540621866, "percentage": 43.05, "elapsed_time": "4:47:41", "remaining_time": "6:20:33"}
537
+ {"current_steps": 537, "total_steps": 1245, "loss": 0.3412, "lr": 2.8066343088016105e-05, "epoch": 2.1544633901705117, "percentage": 43.13, "elapsed_time": "4:48:10", "remaining_time": "6:19:56"}
538
+ {"current_steps": 538, "total_steps": 1245, "loss": 0.3568, "lr": 2.8014976662062818e-05, "epoch": 2.1584754262788364, "percentage": 43.21, "elapsed_time": "4:48:36", "remaining_time": "6:19:16"}
539
+ {"current_steps": 539, "total_steps": 1245, "loss": 0.37, "lr": 2.796354717440907e-05, "epoch": 2.1624874623871615, "percentage": 43.29, "elapsed_time": "4:49:08", "remaining_time": "6:18:43"}
540
+ {"current_steps": 540, "total_steps": 1245, "loss": 0.3521, "lr": 2.791205502970118e-05, "epoch": 2.1664994984954866, "percentage": 43.37, "elapsed_time": "4:49:38", "remaining_time": "6:18:08"}
541
+ {"current_steps": 541, "total_steps": 1245, "loss": 0.3595, "lr": 2.7860500633078475e-05, "epoch": 2.1705115346038113, "percentage": 43.45, "elapsed_time": "4:50:12", "remaining_time": "6:17:39"}
542
+ {"current_steps": 542, "total_steps": 1245, "loss": 0.355, "lr": 2.7808884390170074e-05, "epoch": 2.1745235707121364, "percentage": 43.53, "elapsed_time": "4:50:46", "remaining_time": "6:17:09"}
543
+ {"current_steps": 543, "total_steps": 1245, "loss": 0.3593, "lr": 2.775720670709171e-05, "epoch": 2.1785356068204615, "percentage": 43.61, "elapsed_time": "4:51:13", "remaining_time": "6:16:30"}
544
+ {"current_steps": 544, "total_steps": 1245, "loss": 0.3725, "lr": 2.7705467990442497e-05, "epoch": 2.1825476429287862, "percentage": 43.69, "elapsed_time": "4:51:44", "remaining_time": "6:15:56"}
545
+ {"current_steps": 545, "total_steps": 1245, "loss": 0.3554, "lr": 2.7653668647301797e-05, "epoch": 2.1865596790371113, "percentage": 43.78, "elapsed_time": "4:52:16", "remaining_time": "6:15:24"}
546
+ {"current_steps": 546, "total_steps": 1245, "loss": 0.354, "lr": 2.760180908522596e-05, "epoch": 2.1905717151454365, "percentage": 43.86, "elapsed_time": "4:52:50", "remaining_time": "6:14:54"}
547
+ {"current_steps": 547, "total_steps": 1245, "loss": 0.373, "lr": 2.754988971224514e-05, "epoch": 2.194583751253761, "percentage": 43.94, "elapsed_time": "4:53:22", "remaining_time": "6:14:21"}
548
+ {"current_steps": 548, "total_steps": 1245, "loss": 0.3649, "lr": 2.749791093686008e-05, "epoch": 2.1985957873620863, "percentage": 44.02, "elapsed_time": "4:53:57", "remaining_time": "6:13:53"}
549
+ {"current_steps": 549, "total_steps": 1245, "loss": 0.3726, "lr": 2.7445873168038906e-05, "epoch": 2.2026078234704114, "percentage": 44.1, "elapsed_time": "4:54:29", "remaining_time": "6:13:21"}
550
+ {"current_steps": 550, "total_steps": 1245, "loss": 0.3659, "lr": 2.7393776815213903e-05, "epoch": 2.206619859578736, "percentage": 44.18, "elapsed_time": "4:54:57", "remaining_time": "6:12:43"}
551
+ {"current_steps": 551, "total_steps": 1245, "loss": 0.3688, "lr": 2.7341622288278288e-05, "epoch": 2.210631895687061, "percentage": 44.26, "elapsed_time": "4:55:31", "remaining_time": "6:12:13"}
552
+ {"current_steps": 552, "total_steps": 1245, "loss": 0.3655, "lr": 2.7289409997583002e-05, "epoch": 2.2146439317953863, "percentage": 44.34, "elapsed_time": "4:56:06", "remaining_time": "6:11:44"}
553
+ {"current_steps": 553, "total_steps": 1245, "loss": 0.3678, "lr": 2.7237140353933445e-05, "epoch": 2.218655967903711, "percentage": 44.42, "elapsed_time": "4:56:38", "remaining_time": "6:11:12"}
554
+ {"current_steps": 554, "total_steps": 1245, "loss": 0.3539, "lr": 2.7184813768586305e-05, "epoch": 2.222668004012036, "percentage": 44.5, "elapsed_time": "4:57:09", "remaining_time": "6:10:38"}
555
+ {"current_steps": 555, "total_steps": 1245, "loss": 0.3549, "lr": 2.7132430653246263e-05, "epoch": 2.2266800401203612, "percentage": 44.58, "elapsed_time": "4:57:41", "remaining_time": "6:10:05"}
556
+ {"current_steps": 556, "total_steps": 1245, "loss": 0.3837, "lr": 2.7079991420062782e-05, "epoch": 2.230692076228686, "percentage": 44.66, "elapsed_time": "4:58:19", "remaining_time": "6:09:41"}
557
+ {"current_steps": 557, "total_steps": 1245, "loss": 0.3724, "lr": 2.7027496481626858e-05, "epoch": 2.234704112337011, "percentage": 44.74, "elapsed_time": "4:58:52", "remaining_time": "6:09:10"}
558
+ {"current_steps": 558, "total_steps": 1245, "loss": 0.3381, "lr": 2.6974946250967776e-05, "epoch": 2.238716148445336, "percentage": 44.82, "elapsed_time": "4:59:24", "remaining_time": "6:08:37"}
559
+ {"current_steps": 559, "total_steps": 1245, "loss": 0.3695, "lr": 2.692234114154986e-05, "epoch": 2.242728184553661, "percentage": 44.9, "elapsed_time": "4:59:55", "remaining_time": "6:08:03"}
560
+ {"current_steps": 560, "total_steps": 1245, "loss": 0.3434, "lr": 2.6869681567269223e-05, "epoch": 2.246740220661986, "percentage": 44.98, "elapsed_time": "5:00:26", "remaining_time": "6:07:30"}
561
+ {"current_steps": 561, "total_steps": 1245, "loss": 0.3547, "lr": 2.68169679424505e-05, "epoch": 2.250752256770311, "percentage": 45.06, "elapsed_time": "5:00:53", "remaining_time": "6:06:51"}
562
+ {"current_steps": 562, "total_steps": 1245, "loss": 0.3558, "lr": 2.6764200681843596e-05, "epoch": 2.254764292878636, "percentage": 45.14, "elapsed_time": "5:01:26", "remaining_time": "6:06:20"}
563
+ {"current_steps": 563, "total_steps": 1245, "loss": 0.372, "lr": 2.6711380200620426e-05, "epoch": 2.258776328986961, "percentage": 45.22, "elapsed_time": "5:02:00", "remaining_time": "6:05:50"}
564
+ {"current_steps": 564, "total_steps": 1245, "loss": 0.359, "lr": 2.6658506914371635e-05, "epoch": 2.262788365095286, "percentage": 45.3, "elapsed_time": "5:02:36", "remaining_time": "6:05:23"}
565
+ {"current_steps": 565, "total_steps": 1245, "loss": 0.3697, "lr": 2.6605581239103347e-05, "epoch": 2.2668004012036107, "percentage": 45.38, "elapsed_time": "5:03:10", "remaining_time": "6:04:52"}
566
+ {"current_steps": 566, "total_steps": 1245, "loss": 0.3623, "lr": 2.6552603591233875e-05, "epoch": 2.270812437311936, "percentage": 45.46, "elapsed_time": "5:03:40", "remaining_time": "6:04:17"}
567
+ {"current_steps": 567, "total_steps": 1245, "loss": 0.3526, "lr": 2.6499574387590454e-05, "epoch": 2.274824473420261, "percentage": 45.54, "elapsed_time": "5:04:13", "remaining_time": "6:03:46"}
568
+ {"current_steps": 568, "total_steps": 1245, "loss": 0.3695, "lr": 2.6446494045405965e-05, "epoch": 2.2788365095285856, "percentage": 45.62, "elapsed_time": "5:04:46", "remaining_time": "6:03:15"}
569
+ {"current_steps": 569, "total_steps": 1245, "loss": 0.3877, "lr": 2.6393362982315632e-05, "epoch": 2.2828485456369108, "percentage": 45.7, "elapsed_time": "5:05:20", "remaining_time": "6:02:45"}
570
+ {"current_steps": 570, "total_steps": 1245, "loss": 0.3528, "lr": 2.6340181616353767e-05, "epoch": 2.286860581745236, "percentage": 45.78, "elapsed_time": "5:05:57", "remaining_time": "6:02:19"}
571
+ {"current_steps": 571, "total_steps": 1245, "loss": 0.3377, "lr": 2.6286950365950445e-05, "epoch": 2.2908726178535606, "percentage": 45.86, "elapsed_time": "5:06:27", "remaining_time": "6:01:44"}
572
+ {"current_steps": 572, "total_steps": 1245, "loss": 0.3639, "lr": 2.623366964992825e-05, "epoch": 2.2948846539618857, "percentage": 45.94, "elapsed_time": "5:06:59", "remaining_time": "6:01:11"}
573
+ {"current_steps": 573, "total_steps": 1245, "loss": 0.3817, "lr": 2.618033988749895e-05, "epoch": 2.298896690070211, "percentage": 46.02, "elapsed_time": "5:07:27", "remaining_time": "6:00:34"}
574
+ {"current_steps": 574, "total_steps": 1245, "loss": 0.3671, "lr": 2.612696149826021e-05, "epoch": 2.3029087261785355, "percentage": 46.1, "elapsed_time": "5:07:53", "remaining_time": "5:59:55"}
575
+ {"current_steps": 575, "total_steps": 1245, "loss": 0.352, "lr": 2.6073534902192295e-05, "epoch": 2.3069207622868606, "percentage": 46.18, "elapsed_time": "5:08:22", "remaining_time": "5:59:19"}
576
+ {"current_steps": 576, "total_steps": 1245, "loss": 0.3712, "lr": 2.6020060519654756e-05, "epoch": 2.3109327983951857, "percentage": 46.27, "elapsed_time": "5:08:57", "remaining_time": "5:58:50"}
577
+ {"current_steps": 577, "total_steps": 1245, "loss": 0.3516, "lr": 2.5966538771383124e-05, "epoch": 2.3149448345035104, "percentage": 46.35, "elapsed_time": "5:09:23", "remaining_time": "5:58:11"}
578
+ {"current_steps": 578, "total_steps": 1245, "loss": 0.3683, "lr": 2.591297007848561e-05, "epoch": 2.3189568706118355, "percentage": 46.43, "elapsed_time": "5:09:55", "remaining_time": "5:57:38"}
579
+ {"current_steps": 579, "total_steps": 1245, "loss": 0.3656, "lr": 2.585935486243978e-05, "epoch": 2.3229689067201607, "percentage": 46.51, "elapsed_time": "5:10:23", "remaining_time": "5:57:01"}
580
+ {"current_steps": 580, "total_steps": 1245, "loss": 0.366, "lr": 2.580569354508925e-05, "epoch": 2.3269809428284853, "percentage": 46.59, "elapsed_time": "5:10:58", "remaining_time": "5:56:32"}
581
+ {"current_steps": 581, "total_steps": 1245, "loss": 0.3499, "lr": 2.5751986548640345e-05, "epoch": 2.3309929789368105, "percentage": 46.67, "elapsed_time": "5:11:29", "remaining_time": "5:55:59"}
582
+ {"current_steps": 582, "total_steps": 1245, "loss": 0.3671, "lr": 2.5698234295658816e-05, "epoch": 2.3350050150451356, "percentage": 46.75, "elapsed_time": "5:12:01", "remaining_time": "5:55:27"}
583
+ {"current_steps": 583, "total_steps": 1245, "loss": 0.3755, "lr": 2.5644437209066464e-05, "epoch": 2.3390170511534603, "percentage": 46.83, "elapsed_time": "5:12:30", "remaining_time": "5:54:51"}
584
+ {"current_steps": 584, "total_steps": 1245, "loss": 0.3799, "lr": 2.5590595712137863e-05, "epoch": 2.3430290872617854, "percentage": 46.91, "elapsed_time": "5:13:05", "remaining_time": "5:54:22"}
585
+ {"current_steps": 585, "total_steps": 1245, "loss": 0.3677, "lr": 2.5536710228496986e-05, "epoch": 2.3470411233701105, "percentage": 46.99, "elapsed_time": "5:13:38", "remaining_time": "5:53:51"}
586
+ {"current_steps": 586, "total_steps": 1245, "loss": 0.3654, "lr": 2.5482781182113928e-05, "epoch": 2.351053159478435, "percentage": 47.07, "elapsed_time": "5:14:14", "remaining_time": "5:53:23"}
587
+ {"current_steps": 587, "total_steps": 1245, "loss": 0.3515, "lr": 2.5428808997301486e-05, "epoch": 2.3550651955867603, "percentage": 47.15, "elapsed_time": "5:14:43", "remaining_time": "5:52:47"}
588
+ {"current_steps": 588, "total_steps": 1245, "loss": 0.3656, "lr": 2.5374794098711915e-05, "epoch": 2.3590772316950854, "percentage": 47.23, "elapsed_time": "5:15:20", "remaining_time": "5:52:20"}
589
+ {"current_steps": 589, "total_steps": 1245, "loss": 0.369, "lr": 2.5320736911333503e-05, "epoch": 2.36308926780341, "percentage": 47.31, "elapsed_time": "5:15:56", "remaining_time": "5:51:53"}
590
+ {"current_steps": 590, "total_steps": 1245, "loss": 0.3541, "lr": 2.5266637860487294e-05, "epoch": 2.3671013039117352, "percentage": 47.39, "elapsed_time": "5:16:31", "remaining_time": "5:51:23"}
591
+ {"current_steps": 591, "total_steps": 1245, "loss": 0.3703, "lr": 2.521249737182371e-05, "epoch": 2.3711133400200604, "percentage": 47.47, "elapsed_time": "5:16:58", "remaining_time": "5:50:46"}
592
+ {"current_steps": 592, "total_steps": 1245, "loss": 0.3784, "lr": 2.5158315871319185e-05, "epoch": 2.375125376128385, "percentage": 47.55, "elapsed_time": "5:17:31", "remaining_time": "5:50:14"}
593
+ {"current_steps": 593, "total_steps": 1245, "loss": 0.3651, "lr": 2.5104093785272854e-05, "epoch": 2.37913741223671, "percentage": 47.63, "elapsed_time": "5:18:02", "remaining_time": "5:49:40"}
594
+ {"current_steps": 594, "total_steps": 1245, "loss": 0.3472, "lr": 2.504983154030316e-05, "epoch": 2.3831494483450353, "percentage": 47.71, "elapsed_time": "5:18:31", "remaining_time": "5:49:05"}
595
+ {"current_steps": 595, "total_steps": 1245, "loss": 0.3667, "lr": 2.499552956334454e-05, "epoch": 2.38716148445336, "percentage": 47.79, "elapsed_time": "5:19:02", "remaining_time": "5:48:31"}
596
+ {"current_steps": 596, "total_steps": 1245, "loss": 0.3749, "lr": 2.4941188281644016e-05, "epoch": 2.391173520561685, "percentage": 47.87, "elapsed_time": "5:19:32", "remaining_time": "5:47:57"}
597
+ {"current_steps": 597, "total_steps": 1245, "loss": 0.3676, "lr": 2.4886808122757882e-05, "epoch": 2.39518555667001, "percentage": 47.95, "elapsed_time": "5:20:13", "remaining_time": "5:47:34"}
598
+ {"current_steps": 598, "total_steps": 1245, "loss": 0.3626, "lr": 2.4832389514548303e-05, "epoch": 2.399197592778335, "percentage": 48.03, "elapsed_time": "5:20:41", "remaining_time": "5:46:58"}
599
+ {"current_steps": 599, "total_steps": 1245, "loss": 0.3884, "lr": 2.4777932885179957e-05, "epoch": 2.40320962888666, "percentage": 48.11, "elapsed_time": "5:21:15", "remaining_time": "5:46:27"}
600
+ {"current_steps": 600, "total_steps": 1245, "loss": 0.3688, "lr": 2.4723438663116692e-05, "epoch": 2.407221664994985, "percentage": 48.19, "elapsed_time": "5:21:43", "remaining_time": "5:45:51"}
601
+ {"current_steps": 601, "total_steps": 1245, "loss": 0.3696, "lr": 2.4668907277118114e-05, "epoch": 2.41123370110331, "percentage": 48.27, "elapsed_time": "5:22:19", "remaining_time": "5:45:23"}
602
+ {"current_steps": 602, "total_steps": 1245, "loss": 0.374, "lr": 2.4614339156236246e-05, "epoch": 2.415245737211635, "percentage": 48.35, "elapsed_time": "5:22:46", "remaining_time": "5:44:45"}
603
+ {"current_steps": 603, "total_steps": 1245, "loss": 0.3774, "lr": 2.455973472981214e-05, "epoch": 2.41925777331996, "percentage": 48.43, "elapsed_time": "5:23:15", "remaining_time": "5:44:10"}
604
+ {"current_steps": 604, "total_steps": 1245, "loss": 0.3647, "lr": 2.45050944274725e-05, "epoch": 2.4232698094282847, "percentage": 48.51, "elapsed_time": "5:23:50", "remaining_time": "5:43:40"}
605
+ {"current_steps": 605, "total_steps": 1245, "loss": 0.3909, "lr": 2.445041867912629e-05, "epoch": 2.42728184553661, "percentage": 48.59, "elapsed_time": "5:24:21", "remaining_time": "5:43:07"}
606
+ {"current_steps": 606, "total_steps": 1245, "loss": 0.3721, "lr": 2.4395707914961378e-05, "epoch": 2.431293881644935, "percentage": 48.67, "elapsed_time": "5:24:56", "remaining_time": "5:42:37"}
607
+ {"current_steps": 607, "total_steps": 1245, "loss": 0.3705, "lr": 2.4340962565441125e-05, "epoch": 2.4353059177532597, "percentage": 48.76, "elapsed_time": "5:25:30", "remaining_time": "5:42:07"}
608
+ {"current_steps": 499, "total_steps": 1230, "loss": 0.3794, "lr": 2.965396831793362e-05, "epoch": 2.0283544303797467, "percentage": 40.57, "elapsed_time": "0:00:40", "remaining_time": "0:00:58"}
609
+ {"current_steps": 500, "total_steps": 1230, "loss": 0.3646, "lr": 2.9604221019627316e-05, "epoch": 2.0324050632911392, "percentage": 40.65, "elapsed_time": "0:01:12", "remaining_time": "0:01:45"}
610
+ {"current_steps": 501, "total_steps": 1230, "loss": 0.3712, "lr": 2.955439637024526e-05, "epoch": 2.0364556962025318, "percentage": 40.73, "elapsed_time": "0:01:43", "remaining_time": "0:02:31"}
611
+ {"current_steps": 502, "total_steps": 1230, "loss": 0.3769, "lr": 2.9504494771068334e-05, "epoch": 2.0405063291139243, "percentage": 40.81, "elapsed_time": "0:02:13", "remaining_time": "0:03:13"}
612
+ {"current_steps": 503, "total_steps": 1230, "loss": 0.3704, "lr": 2.9454516623997156e-05, "epoch": 2.0445569620253163, "percentage": 40.89, "elapsed_time": "0:02:45", "remaining_time": "0:03:58"}
613
+ {"current_steps": 504, "total_steps": 1230, "loss": 0.3664, "lr": 2.9404462331548847e-05, "epoch": 2.048607594936709, "percentage": 40.98, "elapsed_time": "0:03:13", "remaining_time": "0:04:39"}
614
+ {"current_steps": 505, "total_steps": 1230, "loss": 0.386, "lr": 2.93543322968538e-05, "epoch": 2.0526582278481014, "percentage": 41.06, "elapsed_time": "0:03:47", "remaining_time": "0:05:27"}
615
+ {"current_steps": 506, "total_steps": 1230, "loss": 0.365, "lr": 2.9304126923652428e-05, "epoch": 2.056708860759494, "percentage": 41.14, "elapsed_time": "0:04:15", "remaining_time": "0:06:04"}
616
+ {"current_steps": 507, "total_steps": 1230, "loss": 0.375, "lr": 2.9253846616291896e-05, "epoch": 2.060759493670886, "percentage": 41.22, "elapsed_time": "0:04:51", "remaining_time": "0:06:55"}
617
+ {"current_steps": 508, "total_steps": 1230, "loss": 0.3548, "lr": 2.9203491779722896e-05, "epoch": 2.0648101265822785, "percentage": 41.3, "elapsed_time": "0:05:23", "remaining_time": "0:07:39"}
618
+ {"current_steps": 509, "total_steps": 1230, "loss": 0.3919, "lr": 2.9153062819496357e-05, "epoch": 2.068860759493671, "percentage": 41.38, "elapsed_time": "0:05:53", "remaining_time": "0:08:20"}
619
+ {"current_steps": 510, "total_steps": 1230, "loss": 0.37, "lr": 2.9102560141760178e-05, "epoch": 2.0729113924050635, "percentage": 41.46, "elapsed_time": "0:06:22", "remaining_time": "0:09:00"}
620
+ {"current_steps": 511, "total_steps": 1230, "loss": 0.3547, "lr": 2.9051984153256004e-05, "epoch": 2.0769620253164556, "percentage": 41.54, "elapsed_time": "0:06:53", "remaining_time": "0:09:42"}
621
+ {"current_steps": 512, "total_steps": 1230, "loss": 0.3675, "lr": 2.900133526131588e-05, "epoch": 2.081012658227848, "percentage": 41.63, "elapsed_time": "0:07:23", "remaining_time": "0:10:21"}
622
+ {"current_steps": 513, "total_steps": 1230, "loss": 0.3631, "lr": 2.8950613873859025e-05, "epoch": 2.0850632911392406, "percentage": 41.71, "elapsed_time": "0:07:52", "remaining_time": "0:11:00"}
623
+ {"current_steps": 514, "total_steps": 1230, "loss": 0.3604, "lr": 2.8899820399388515e-05, "epoch": 2.089113924050633, "percentage": 41.79, "elapsed_time": "0:08:22", "remaining_time": "0:11:40"}
624
+ {"current_steps": 515, "total_steps": 1230, "loss": 0.3765, "lr": 2.8848955246988012e-05, "epoch": 2.093164556962025, "percentage": 41.87, "elapsed_time": "0:08:53", "remaining_time": "0:12:20"}
625
+ {"current_steps": 516, "total_steps": 1230, "loss": 0.3641, "lr": 2.879801882631847e-05, "epoch": 2.0972151898734177, "percentage": 41.95, "elapsed_time": "0:09:26", "remaining_time": "0:13:04"}
626
+ {"current_steps": 517, "total_steps": 1230, "loss": 0.3408, "lr": 2.8747011547614808e-05, "epoch": 2.1012658227848102, "percentage": 42.03, "elapsed_time": "0:09:58", "remaining_time": "0:13:45"}
627
+ {"current_steps": 518, "total_steps": 1230, "loss": 0.3737, "lr": 2.8695933821682635e-05, "epoch": 2.1053164556962027, "percentage": 42.11, "elapsed_time": "0:10:28", "remaining_time": "0:14:24"}
628
+ {"current_steps": 519, "total_steps": 1230, "loss": 0.3503, "lr": 2.864478605989494e-05, "epoch": 2.109367088607595, "percentage": 42.2, "elapsed_time": "0:10:55", "remaining_time": "0:14:58"}
629
+ {"current_steps": 520, "total_steps": 1230, "loss": 0.3605, "lr": 2.8593568674188765e-05, "epoch": 2.1134177215189873, "percentage": 42.28, "elapsed_time": "0:11:28", "remaining_time": "0:15:40"}
630
+ {"current_steps": 521, "total_steps": 1230, "loss": 0.3562, "lr": 2.8542282077061892e-05, "epoch": 2.11746835443038, "percentage": 42.36, "elapsed_time": "0:12:01", "remaining_time": "0:16:21"}
631
+ {"current_steps": 522, "total_steps": 1230, "loss": 0.3549, "lr": 2.8490926681569523e-05, "epoch": 2.1215189873417724, "percentage": 42.44, "elapsed_time": "0:12:36", "remaining_time": "0:17:06"}
632
+ {"current_steps": 523, "total_steps": 1230, "loss": 0.3404, "lr": 2.8439502901320956e-05, "epoch": 2.1255696202531644, "percentage": 42.52, "elapsed_time": "0:13:09", "remaining_time": "0:17:46"}
633
+ {"current_steps": 524, "total_steps": 1230, "loss": 0.3433, "lr": 2.8388011150476237e-05, "epoch": 2.129620253164557, "percentage": 42.6, "elapsed_time": "0:13:42", "remaining_time": "0:18:27"}
634
+ {"current_steps": 525, "total_steps": 1230, "loss": 0.3393, "lr": 2.8336451843742866e-05, "epoch": 2.1336708860759495, "percentage": 42.68, "elapsed_time": "0:14:12", "remaining_time": "0:19:04"}
635
+ {"current_steps": 526, "total_steps": 1230, "loss": 0.3677, "lr": 2.8284825396372387e-05, "epoch": 2.137721518987342, "percentage": 42.76, "elapsed_time": "0:14:41", "remaining_time": "0:19:40"}
636
+ {"current_steps": 527, "total_steps": 1230, "loss": 0.3652, "lr": 2.8233132224157132e-05, "epoch": 2.141772151898734, "percentage": 42.85, "elapsed_time": "0:15:19", "remaining_time": "0:20:26"}
637
+ {"current_steps": 528, "total_steps": 1230, "loss": 0.3767, "lr": 2.8181372743426805e-05, "epoch": 2.1458227848101266, "percentage": 42.93, "elapsed_time": "0:15:51", "remaining_time": "0:21:04"}
638
+ {"current_steps": 529, "total_steps": 1230, "loss": 0.3597, "lr": 2.8129547371045128e-05, "epoch": 2.149873417721519, "percentage": 43.01, "elapsed_time": "0:16:21", "remaining_time": "0:21:39"}
639
+ {"current_steps": 530, "total_steps": 1230, "loss": 0.3496, "lr": 2.8077656524406534e-05, "epoch": 2.1539240506329116, "percentage": 43.09, "elapsed_time": "0:16:56", "remaining_time": "0:22:22"}
640
+ {"current_steps": 531, "total_steps": 1230, "loss": 0.3377, "lr": 2.802570062143278e-05, "epoch": 2.1579746835443037, "percentage": 43.17, "elapsed_time": "0:17:24", "remaining_time": "0:22:55"}
641
+ {"current_steps": 532, "total_steps": 1230, "loss": 0.3658, "lr": 2.7973680080569555e-05, "epoch": 2.162025316455696, "percentage": 43.25, "elapsed_time": "0:17:58", "remaining_time": "0:23:35"}
642
+ {"current_steps": 533, "total_steps": 1230, "loss": 0.3665, "lr": 2.792159532078314e-05, "epoch": 2.1660759493670887, "percentage": 43.33, "elapsed_time": "0:18:30", "remaining_time": "0:24:12"}
643
+ {"current_steps": 534, "total_steps": 1230, "loss": 0.374, "lr": 2.7869446761557033e-05, "epoch": 2.170126582278481, "percentage": 43.41, "elapsed_time": "0:18:58", "remaining_time": "0:24:43"}
644
+ {"current_steps": 535, "total_steps": 1230, "loss": 0.3523, "lr": 2.781723482288857e-05, "epoch": 2.1741772151898733, "percentage": 43.5, "elapsed_time": "0:19:32", "remaining_time": "0:25:23"}
645
+ {"current_steps": 536, "total_steps": 1230, "loss": 0.3435, "lr": 2.7764959925285517e-05, "epoch": 2.178227848101266, "percentage": 43.58, "elapsed_time": "0:20:03", "remaining_time": "0:25:58"}
646
+ {"current_steps": 537, "total_steps": 1230, "loss": 0.3742, "lr": 2.771262248976272e-05, "epoch": 2.1822784810126583, "percentage": 43.66, "elapsed_time": "0:20:33", "remaining_time": "0:26:32"}
647
+ {"current_steps": 538, "total_steps": 1230, "loss": 0.3561, "lr": 2.7660222937838677e-05, "epoch": 2.186329113924051, "percentage": 43.74, "elapsed_time": "0:21:02", "remaining_time": "0:27:03"}
648
+ {"current_steps": 539, "total_steps": 1230, "loss": 0.363, "lr": 2.7607761691532186e-05, "epoch": 2.190379746835443, "percentage": 43.82, "elapsed_time": "0:21:37", "remaining_time": "0:27:43"}
649
+ {"current_steps": 540, "total_steps": 1230, "loss": 0.3592, "lr": 2.7555239173358916e-05, "epoch": 2.1944303797468354, "percentage": 43.9, "elapsed_time": "0:22:13", "remaining_time": "0:28:23"}
650
+ {"current_steps": 541, "total_steps": 1230, "loss": 0.3851, "lr": 2.7502655806328e-05, "epoch": 2.198481012658228, "percentage": 43.98, "elapsed_time": "0:22:48", "remaining_time": "0:29:03"}
651
+ {"current_steps": 542, "total_steps": 1230, "loss": 0.3535, "lr": 2.7450012013938648e-05, "epoch": 2.2025316455696204, "percentage": 44.07, "elapsed_time": "0:23:23", "remaining_time": "0:29:40"}
652
+ {"current_steps": 543, "total_steps": 1230, "loss": 0.3539, "lr": 2.739730822017673e-05, "epoch": 2.2065822784810125, "percentage": 44.15, "elapsed_time": "0:23:57", "remaining_time": "0:30:18"}
653
+ {"current_steps": 544, "total_steps": 1230, "loss": 0.3581, "lr": 2.7344544849511355e-05, "epoch": 2.210632911392405, "percentage": 44.23, "elapsed_time": "0:24:31", "remaining_time": "0:30:55"}
654
+ {"current_steps": 545, "total_steps": 1230, "loss": 0.3545, "lr": 2.7291722326891456e-05, "epoch": 2.2146835443037975, "percentage": 44.31, "elapsed_time": "0:24:58", "remaining_time": "0:31:23"}
655
+ {"current_steps": 546, "total_steps": 1230, "loss": 0.3682, "lr": 2.723884107774236e-05, "epoch": 2.21873417721519, "percentage": 44.39, "elapsed_time": "0:25:36", "remaining_time": "0:32:04"}
656
+ {"current_steps": 547, "total_steps": 1230, "loss": 0.3649, "lr": 2.718590152796239e-05, "epoch": 2.222784810126582, "percentage": 44.47, "elapsed_time": "0:26:11", "remaining_time": "0:32:41"}
657
+ {"current_steps": 548, "total_steps": 1230, "loss": 0.3618, "lr": 2.71329041039194e-05, "epoch": 2.2268354430379746, "percentage": 44.55, "elapsed_time": "0:26:48", "remaining_time": "0:33:21"}
658
+ {"current_steps": 549, "total_steps": 1230, "loss": 0.3714, "lr": 2.7079849232447357e-05, "epoch": 2.230886075949367, "percentage": 44.63, "elapsed_time": "0:27:21", "remaining_time": "0:33:55"}
659
+ {"current_steps": 550, "total_steps": 1230, "loss": 0.3447, "lr": 2.7026737340842895e-05, "epoch": 2.2349367088607597, "percentage": 44.72, "elapsed_time": "0:27:53", "remaining_time": "0:34:29"}
660
+ {"current_steps": 551, "total_steps": 1230, "loss": 0.3589, "lr": 2.697356885686189e-05, "epoch": 2.2389873417721518, "percentage": 44.8, "elapsed_time": "0:28:22", "remaining_time": "0:34:57"}
661
+ {"current_steps": 552, "total_steps": 1230, "loss": 0.3541, "lr": 2.6920344208716014e-05, "epoch": 2.2430379746835443, "percentage": 44.88, "elapsed_time": "0:28:52", "remaining_time": "0:35:28"}
662
+ {"current_steps": 553, "total_steps": 1230, "loss": 0.3829, "lr": 2.6867063825069252e-05, "epoch": 2.247088607594937, "percentage": 44.96, "elapsed_time": "0:29:23", "remaining_time": "0:35:59"}
663
+ {"current_steps": 554, "total_steps": 1230, "loss": 0.3605, "lr": 2.6813728135034494e-05, "epoch": 2.2511392405063293, "percentage": 45.04, "elapsed_time": "0:29:49", "remaining_time": "0:36:23"}
664
+ {"current_steps": 555, "total_steps": 1230, "loss": 0.3484, "lr": 2.6760337568170056e-05, "epoch": 2.2551898734177214, "percentage": 45.12, "elapsed_time": "0:30:19", "remaining_time": "0:36:52"}
665
+ {"current_steps": 556, "total_steps": 1230, "loss": 0.3765, "lr": 2.6706892554476226e-05, "epoch": 2.259240506329114, "percentage": 45.2, "elapsed_time": "0:30:48", "remaining_time": "0:37:21"}
666
+ {"current_steps": 557, "total_steps": 1230, "loss": 0.3809, "lr": 2.6653393524391795e-05, "epoch": 2.2632911392405064, "percentage": 45.28, "elapsed_time": "0:31:20", "remaining_time": "0:37:52"}
667
+ {"current_steps": 558, "total_steps": 1230, "loss": 0.367, "lr": 2.6599840908790592e-05, "epoch": 2.267341772151899, "percentage": 45.37, "elapsed_time": "0:31:56", "remaining_time": "0:38:28"}
668
+ {"current_steps": 559, "total_steps": 1230, "loss": 0.3886, "lr": 2.6546235138978028e-05, "epoch": 2.271392405063291, "percentage": 45.45, "elapsed_time": "0:32:29", "remaining_time": "0:38:59"}
669
+ {"current_steps": 560, "total_steps": 1230, "loss": 0.3449, "lr": 2.6492576646687597e-05, "epoch": 2.2754430379746835, "percentage": 45.53, "elapsed_time": "0:33:05", "remaining_time": "0:39:35"}
670
+ {"current_steps": 561, "total_steps": 1230, "loss": 0.3582, "lr": 2.6438865864077425e-05, "epoch": 2.279493670886076, "percentage": 45.61, "elapsed_time": "0:33:38", "remaining_time": "0:40:07"}
671
+ {"current_steps": 562, "total_steps": 1230, "loss": 0.3657, "lr": 2.6385103223726766e-05, "epoch": 2.2835443037974685, "percentage": 45.69, "elapsed_time": "0:34:08", "remaining_time": "0:40:34"}
672
+ {"current_steps": 563, "total_steps": 1230, "loss": 0.3776, "lr": 2.6331289158632537e-05, "epoch": 2.2875949367088606, "percentage": 45.77, "elapsed_time": "0:34:45", "remaining_time": "0:41:11"}
673
+ {"current_steps": 564, "total_steps": 1230, "loss": 0.3502, "lr": 2.6277424102205817e-05, "epoch": 2.291645569620253, "percentage": 45.85, "elapsed_time": "0:35:18", "remaining_time": "0:41:41"}
674
+ {"current_steps": 565, "total_steps": 1230, "loss": 0.3612, "lr": 2.6223508488268374e-05, "epoch": 2.2956962025316456, "percentage": 45.93, "elapsed_time": "0:35:53", "remaining_time": "0:42:15"}
675
+ {"current_steps": 566, "total_steps": 1230, "loss": 0.3801, "lr": 2.6169542751049148e-05, "epoch": 2.299746835443038, "percentage": 46.02, "elapsed_time": "0:36:23", "remaining_time": "0:42:41"}
676
+ {"current_steps": 567, "total_steps": 1230, "loss": 0.3731, "lr": 2.6115527325180754e-05, "epoch": 2.3037974683544302, "percentage": 46.1, "elapsed_time": "0:36:54", "remaining_time": "0:43:09"}
677
+ {"current_steps": 568, "total_steps": 1230, "loss": 0.3623, "lr": 2.606146264569603e-05, "epoch": 2.3078481012658227, "percentage": 46.18, "elapsed_time": "0:37:28", "remaining_time": "0:43:41"}
678
+ {"current_steps": 569, "total_steps": 1230, "loss": 0.353, "lr": 2.6007349148024447e-05, "epoch": 2.3118987341772153, "percentage": 46.26, "elapsed_time": "0:38:05", "remaining_time": "0:44:15"}
679
+ {"current_steps": 570, "total_steps": 1230, "loss": 0.3658, "lr": 2.5953187267988694e-05, "epoch": 2.3159493670886078, "percentage": 46.34, "elapsed_time": "0:38:35", "remaining_time": "0:44:40"}
680
+ {"current_steps": 571, "total_steps": 1230, "loss": 0.3624, "lr": 2.5898977441801097e-05, "epoch": 2.32, "percentage": 46.42, "elapsed_time": "0:39:06", "remaining_time": "0:45:08"}
681
+ {"current_steps": 572, "total_steps": 1230, "loss": 0.3655, "lr": 2.584472010606015e-05, "epoch": 2.3240506329113924, "percentage": 46.5, "elapsed_time": "0:39:42", "remaining_time": "0:45:40"}
682
+ {"current_steps": 573, "total_steps": 1230, "loss": 0.3738, "lr": 2.5790415697746976e-05, "epoch": 2.328101265822785, "percentage": 46.59, "elapsed_time": "0:40:18", "remaining_time": "0:46:12"}
683
+ {"current_steps": 574, "total_steps": 1230, "loss": 0.3592, "lr": 2.5736064654221808e-05, "epoch": 2.3321518987341774, "percentage": 46.67, "elapsed_time": "0:40:48", "remaining_time": "0:46:38"}
684
+ {"current_steps": 575, "total_steps": 1230, "loss": 0.3763, "lr": 2.568166741322048e-05, "epoch": 2.3362025316455695, "percentage": 46.75, "elapsed_time": "0:41:23", "remaining_time": "0:47:09"}
685
+ {"current_steps": 576, "total_steps": 1230, "loss": 0.3702, "lr": 2.56272244128509e-05, "epoch": 2.340253164556962, "percentage": 46.83, "elapsed_time": "0:42:00", "remaining_time": "0:47:41"}
686
+ {"current_steps": 577, "total_steps": 1230, "loss": 0.3636, "lr": 2.55727360915895e-05, "epoch": 2.3443037974683545, "percentage": 46.91, "elapsed_time": "0:42:29", "remaining_time": "0:48:05"}
687
+ {"current_steps": 578, "total_steps": 1230, "loss": 0.3658, "lr": 2.5518202888277734e-05, "epoch": 2.348354430379747, "percentage": 46.99, "elapsed_time": "0:43:02", "remaining_time": "0:48:32"}
688
+ {"current_steps": 579, "total_steps": 1230, "loss": 0.3637, "lr": 2.5463625242118523e-05, "epoch": 2.352405063291139, "percentage": 47.07, "elapsed_time": "0:43:35", "remaining_time": "0:49:00"}
689
+ {"current_steps": 580, "total_steps": 1230, "loss": 0.3637, "lr": 2.5409003592672723e-05, "epoch": 2.3564556962025316, "percentage": 47.15, "elapsed_time": "0:44:05", "remaining_time": "0:49:24"}
690
+ {"current_steps": 581, "total_steps": 1230, "loss": 0.3605, "lr": 2.535433837985559e-05, "epoch": 2.360506329113924, "percentage": 47.24, "elapsed_time": "0:44:32", "remaining_time": "0:49:45"}
691
+ {"current_steps": 582, "total_steps": 1230, "loss": 0.3651, "lr": 2.529963004393324e-05, "epoch": 2.3645569620253166, "percentage": 47.32, "elapsed_time": "0:45:05", "remaining_time": "0:50:12"}
692
+ {"current_steps": 583, "total_steps": 1230, "loss": 0.3603, "lr": 2.524487902551908e-05, "epoch": 2.3686075949367087, "percentage": 47.4, "elapsed_time": "0:45:40", "remaining_time": "0:50:41"}
693
+ {"current_steps": 584, "total_steps": 1230, "loss": 0.3718, "lr": 2.519008576557029e-05, "epoch": 2.372658227848101, "percentage": 47.48, "elapsed_time": "0:46:15", "remaining_time": "0:51:10"}
694
+ {"current_steps": 585, "total_steps": 1230, "loss": 0.3844, "lr": 2.5135250705384254e-05, "epoch": 2.3767088607594937, "percentage": 47.56, "elapsed_time": "0:46:48", "remaining_time": "0:51:36"}
695
+ {"current_steps": 586, "total_steps": 1230, "loss": 0.3814, "lr": 2.5080374286595007e-05, "epoch": 2.3807594936708862, "percentage": 47.64, "elapsed_time": "0:47:23", "remaining_time": "0:52:04"}
696
+ {"current_steps": 587, "total_steps": 1230, "loss": 0.3456, "lr": 2.5025456951169677e-05, "epoch": 2.3848101265822783, "percentage": 47.72, "elapsed_time": "0:47:49", "remaining_time": "0:52:23"}
697
+ {"current_steps": 588, "total_steps": 1230, "loss": 0.3701, "lr": 2.4970499141404942e-05, "epoch": 2.388860759493671, "percentage": 47.8, "elapsed_time": "0:48:21", "remaining_time": "0:52:48"}
698
+ {"current_steps": 589, "total_steps": 1230, "loss": 0.341, "lr": 2.491550129992345e-05, "epoch": 2.3929113924050633, "percentage": 47.89, "elapsed_time": "0:48:54", "remaining_time": "0:53:13"}
699
+ {"current_steps": 590, "total_steps": 1230, "loss": 0.3457, "lr": 2.486046386967024e-05, "epoch": 2.396962025316456, "percentage": 47.97, "elapsed_time": "0:49:26", "remaining_time": "0:53:38"}
700
+ {"current_steps": 591, "total_steps": 1230, "loss": 0.3509, "lr": 2.4805387293909214e-05, "epoch": 2.401012658227848, "percentage": 48.05, "elapsed_time": "0:49:56", "remaining_time": "0:54:00"}
701
+ {"current_steps": 592, "total_steps": 1230, "loss": 0.3502, "lr": 2.4750272016219552e-05, "epoch": 2.4050632911392404, "percentage": 48.13, "elapsed_time": "0:50:28", "remaining_time": "0:54:24"}
702
+ {"current_steps": 593, "total_steps": 1230, "loss": 0.3773, "lr": 2.4695118480492114e-05, "epoch": 2.409113924050633, "percentage": 48.21, "elapsed_time": "0:51:01", "remaining_time": "0:54:48"}
703
+ {"current_steps": 594, "total_steps": 1230, "loss": 0.3505, "lr": 2.4639927130925898e-05, "epoch": 2.4131645569620255, "percentage": 48.29, "elapsed_time": "0:51:30", "remaining_time": "0:55:08"}
704
+ {"current_steps": 595, "total_steps": 1230, "loss": 0.3624, "lr": 2.458469841202444e-05, "epoch": 2.4172151898734175, "percentage": 48.37, "elapsed_time": "0:52:05", "remaining_time": "0:55:35"}
705
+ {"current_steps": 596, "total_steps": 1230, "loss": 0.3644, "lr": 2.452943276859226e-05, "epoch": 2.42126582278481, "percentage": 48.46, "elapsed_time": "0:52:39", "remaining_time": "0:56:00"}
706
+ {"current_steps": 597, "total_steps": 1230, "loss": 0.3773, "lr": 2.447413064573125e-05, "epoch": 2.4253164556962026, "percentage": 48.54, "elapsed_time": "0:53:13", "remaining_time": "0:56:26"}
707
+ {"current_steps": 598, "total_steps": 1230, "loss": 0.3777, "lr": 2.4418792488837095e-05, "epoch": 2.429367088607595, "percentage": 48.62, "elapsed_time": "0:53:48", "remaining_time": "0:56:51"}
708
+ {"current_steps": 599, "total_steps": 1230, "loss": 0.3791, "lr": 2.4363418743595713e-05, "epoch": 2.433417721518987, "percentage": 48.7, "elapsed_time": "0:54:25", "remaining_time": "0:57:20"}
709
+ {"current_steps": 600, "total_steps": 1230, "loss": 0.3596, "lr": 2.430800985597963e-05, "epoch": 2.4374683544303797, "percentage": 48.78, "elapsed_time": "0:55:00", "remaining_time": "0:57:45"}
710
+ {"current_steps": 601, "total_steps": 1230, "loss": 0.3639, "lr": 2.4252566272244415e-05, "epoch": 2.441518987341772, "percentage": 48.86, "elapsed_time": "0:55:29", "remaining_time": "0:58:05"}
711
+ {"current_steps": 602, "total_steps": 1230, "loss": 0.3685, "lr": 2.4197088438925063e-05, "epoch": 2.4455696202531647, "percentage": 48.94, "elapsed_time": "0:56:06", "remaining_time": "0:58:31"}
712
+ {"current_steps": 603, "total_steps": 1230, "loss": 0.3678, "lr": 2.4141576802832417e-05, "epoch": 2.449620253164557, "percentage": 49.02, "elapsed_time": "0:56:38", "remaining_time": "0:58:53"}
713
+ {"current_steps": 604, "total_steps": 1230, "loss": 0.3552, "lr": 2.408603181104957e-05, "epoch": 2.4536708860759493, "percentage": 49.11, "elapsed_time": "0:57:09", "remaining_time": "0:59:14"}
714
+ {"current_steps": 605, "total_steps": 1230, "loss": 0.3678, "lr": 2.4030453910928245e-05, "epoch": 2.457721518987342, "percentage": 49.19, "elapsed_time": "0:57:44", "remaining_time": "0:59:38"}
715
+ {"current_steps": 606, "total_steps": 1230, "loss": 0.352, "lr": 2.397484355008521e-05, "epoch": 2.4617721518987343, "percentage": 49.27, "elapsed_time": "0:58:11", "remaining_time": "0:59:55"}
716
+ {"current_steps": 607, "total_steps": 1230, "loss": 0.3728, "lr": 2.3919201176398662e-05, "epoch": 2.4658227848101264, "percentage": 49.35, "elapsed_time": "0:58:39", "remaining_time": "1:00:12"}
717
+ {"current_steps": 608, "total_steps": 1230, "loss": 0.3669, "lr": 2.3863527238004633e-05, "epoch": 2.469873417721519, "percentage": 49.43, "elapsed_time": "0:59:13", "remaining_time": "1:00:34"}
718
+ {"current_steps": 609, "total_steps": 1230, "loss": 0.3678, "lr": 2.380782218329337e-05, "epoch": 2.4739240506329114, "percentage": 49.51, "elapsed_time": "0:59:48", "remaining_time": "1:00:59"}
719
+ {"current_steps": 610, "total_steps": 1230, "loss": 0.3533, "lr": 2.3752086460905725e-05, "epoch": 2.477974683544304, "percentage": 49.59, "elapsed_time": "1:00:18", "remaining_time": "1:01:17"}
720
+ {"current_steps": 611, "total_steps": 1230, "loss": 0.3726, "lr": 2.3696320519729544e-05, "epoch": 2.482025316455696, "percentage": 49.67, "elapsed_time": "1:00:50", "remaining_time": "1:01:38"}
721
+ {"current_steps": 612, "total_steps": 1230, "loss": 0.3617, "lr": 2.3640524808896045e-05, "epoch": 2.4860759493670885, "percentage": 49.76, "elapsed_time": "1:01:22", "remaining_time": "1:01:58"}
722
+ {"current_steps": 613, "total_steps": 1230, "loss": 0.3765, "lr": 2.3584699777776222e-05, "epoch": 2.490126582278481, "percentage": 49.84, "elapsed_time": "1:01:53", "remaining_time": "1:02:17"}
723
+ {"current_steps": 614, "total_steps": 1230, "loss": 0.3733, "lr": 2.3528845875977195e-05, "epoch": 2.4941772151898736, "percentage": 49.92, "elapsed_time": "1:02:28", "remaining_time": "1:02:40"}
724
+ {"current_steps": 615, "total_steps": 1230, "loss": 0.366, "lr": 2.3472963553338614e-05, "epoch": 2.4982278481012656, "percentage": 50.0, "elapsed_time": "1:03:01", "remaining_time": "1:03:01"}
725
+ {"current_steps": 616, "total_steps": 1230, "loss": 0.3444, "lr": 2.341705325992901e-05, "epoch": 2.502278481012658, "percentage": 50.08, "elapsed_time": "1:03:31", "remaining_time": "1:03:18"}
726
+ {"current_steps": 617, "total_steps": 1230, "loss": 0.3782, "lr": 2.336111544604222e-05, "epoch": 2.5063291139240507, "percentage": 50.16, "elapsed_time": "1:04:04", "remaining_time": "1:03:40"}
727
+ {"current_steps": 618, "total_steps": 1230, "loss": 0.3595, "lr": 2.33051505621937e-05, "epoch": 2.510379746835443, "percentage": 50.24, "elapsed_time": "1:04:36", "remaining_time": "1:03:58"}
728
+ {"current_steps": 619, "total_steps": 1230, "loss": 0.3643, "lr": 2.324915905911693e-05, "epoch": 2.5144303797468357, "percentage": 50.33, "elapsed_time": "1:05:11", "remaining_time": "1:04:20"}
729
+ {"current_steps": 620, "total_steps": 1230, "loss": 0.384, "lr": 2.319314138775977e-05, "epoch": 2.5184810126582278, "percentage": 50.41, "elapsed_time": "1:05:40", "remaining_time": "1:04:36"}
730
+ {"current_steps": 621, "total_steps": 1230, "loss": 0.3735, "lr": 2.3137097999280856e-05, "epoch": 2.5225316455696203, "percentage": 50.49, "elapsed_time": "1:06:13", "remaining_time": "1:04:56"}
731
+ {"current_steps": 622, "total_steps": 1230, "loss": 0.3589, "lr": 2.308102934504593e-05, "epoch": 2.526582278481013, "percentage": 50.57, "elapsed_time": "1:06:45", "remaining_time": "1:05:15"}
732
+ {"current_steps": 623, "total_steps": 1230, "loss": 0.3678, "lr": 2.3024935876624222e-05, "epoch": 2.530632911392405, "percentage": 50.65, "elapsed_time": "1:07:14", "remaining_time": "1:05:31"}
733
+ {"current_steps": 624, "total_steps": 1230, "loss": 0.3488, "lr": 2.2968818045784813e-05, "epoch": 2.5346835443037974, "percentage": 50.73, "elapsed_time": "1:07:45", "remaining_time": "1:05:47"}
734
+ {"current_steps": 625, "total_steps": 1230, "loss": 0.3906, "lr": 2.2912676304493006e-05, "epoch": 2.53873417721519, "percentage": 50.81, "elapsed_time": "1:08:15", "remaining_time": "1:06:04"}
735
+ {"current_steps": 626, "total_steps": 1230, "loss": 0.3561, "lr": 2.2856511104906668e-05, "epoch": 2.5427848101265824, "percentage": 50.89, "elapsed_time": "1:08:46", "remaining_time": "1:06:21"}
736
+ {"current_steps": 627, "total_steps": 1230, "loss": 0.3452, "lr": 2.2800322899372586e-05, "epoch": 2.546835443037975, "percentage": 50.98, "elapsed_time": "1:09:16", "remaining_time": "1:06:36"}
737
+ {"current_steps": 628, "total_steps": 1230, "loss": 0.3711, "lr": 2.2744112140422844e-05, "epoch": 2.550886075949367, "percentage": 51.06, "elapsed_time": "1:09:48", "remaining_time": "1:06:54"}
738
+ {"current_steps": 629, "total_steps": 1230, "loss": 0.3586, "lr": 2.2687879280771177e-05, "epoch": 2.5549367088607595, "percentage": 51.14, "elapsed_time": "1:10:13", "remaining_time": "1:07:05"}
739
+ {"current_steps": 630, "total_steps": 1230, "loss": 0.3549, "lr": 2.26316247733093e-05, "epoch": 2.558987341772152, "percentage": 51.22, "elapsed_time": "1:10:44", "remaining_time": "1:07:22"}
740
+ {"current_steps": 631, "total_steps": 1230, "loss": 0.3654, "lr": 2.257534907110328e-05, "epoch": 2.563037974683544, "percentage": 51.3, "elapsed_time": "1:11:16", "remaining_time": "1:07:39"}
741
+ {"current_steps": 632, "total_steps": 1230, "loss": 0.3278, "lr": 2.2519052627389882e-05, "epoch": 2.5670886075949366, "percentage": 51.38, "elapsed_time": "1:11:52", "remaining_time": "1:08:00"}
742
+ {"current_steps": 633, "total_steps": 1230, "loss": 0.3612, "lr": 2.246273589557294e-05, "epoch": 2.571139240506329, "percentage": 51.46, "elapsed_time": "1:12:29", "remaining_time": "1:08:21"}
743
+ {"current_steps": 634, "total_steps": 1230, "loss": 0.365, "lr": 2.240639932921966e-05, "epoch": 2.5751898734177217, "percentage": 51.54, "elapsed_time": "1:13:01", "remaining_time": "1:08:38"}
744
+ {"current_steps": 635, "total_steps": 1230, "loss": 0.369, "lr": 2.2350043382056995e-05, "epoch": 2.579240506329114, "percentage": 51.63, "elapsed_time": "1:13:32", "remaining_time": "1:08:54"}
745
+ {"current_steps": 636, "total_steps": 1230, "loss": 0.3836, "lr": 2.2293668507968015e-05, "epoch": 2.5832911392405062, "percentage": 51.71, "elapsed_time": "1:13:59", "remaining_time": "1:09:06"}
746
+ {"current_steps": 637, "total_steps": 1230, "loss": 0.3633, "lr": 2.2237275160988186e-05, "epoch": 2.5873417721518988, "percentage": 51.79, "elapsed_time": "1:14:25", "remaining_time": "1:09:17"}
747
+ {"current_steps": 638, "total_steps": 1230, "loss": 0.3484, "lr": 2.2180863795301787e-05, "epoch": 2.5913924050632913, "percentage": 51.87, "elapsed_time": "1:14:56", "remaining_time": "1:09:32"}
748
+ {"current_steps": 639, "total_steps": 1230, "loss": 0.3794, "lr": 2.212443486523819e-05, "epoch": 2.5954430379746833, "percentage": 51.95, "elapsed_time": "1:15:26", "remaining_time": "1:09:46"}
749
+ {"current_steps": 640, "total_steps": 1230, "loss": 0.3538, "lr": 2.2067988825268243e-05, "epoch": 2.599493670886076, "percentage": 52.03, "elapsed_time": "1:15:59", "remaining_time": "1:10:03"}
750
+ {"current_steps": 641, "total_steps": 1230, "loss": 0.3532, "lr": 2.2011526130000596e-05, "epoch": 2.6035443037974684, "percentage": 52.11, "elapsed_time": "1:16:29", "remaining_time": "1:10:17"}
751
+ {"current_steps": 642, "total_steps": 1230, "loss": 0.3779, "lr": 2.1955047234178038e-05, "epoch": 2.607594936708861, "percentage": 52.2, "elapsed_time": "1:17:02", "remaining_time": "1:10:34"}
752
+ {"current_steps": 643, "total_steps": 1230, "loss": 0.3653, "lr": 2.1898552592673825e-05, "epoch": 2.6116455696202534, "percentage": 52.28, "elapsed_time": "1:17:38", "remaining_time": "1:10:52"}
753
+ {"current_steps": 644, "total_steps": 1230, "loss": 0.3589, "lr": 2.184204266048803e-05, "epoch": 2.6156962025316455, "percentage": 52.36, "elapsed_time": "1:18:10", "remaining_time": "1:11:08"}
754
+ {"current_steps": 645, "total_steps": 1230, "loss": 0.3519, "lr": 2.1785517892743887e-05, "epoch": 2.619746835443038, "percentage": 52.44, "elapsed_time": "1:18:46", "remaining_time": "1:11:26"}
755
+ {"current_steps": 646, "total_steps": 1230, "loss": 0.3844, "lr": 2.17289787446841e-05, "epoch": 2.6237974683544305, "percentage": 52.52, "elapsed_time": "1:19:21", "remaining_time": "1:11:44"}
756
+ {"current_steps": 647, "total_steps": 1230, "loss": 0.3621, "lr": 2.1672425671667198e-05, "epoch": 2.6278481012658226, "percentage": 52.6, "elapsed_time": "1:19:52", "remaining_time": "1:11:58"}
757
+ {"current_steps": 648, "total_steps": 1230, "loss": 0.3393, "lr": 2.161585912916385e-05, "epoch": 2.631898734177215, "percentage": 52.68, "elapsed_time": "1:20:22", "remaining_time": "1:12:11"}
758
+ {"current_steps": 649, "total_steps": 1230, "loss": 0.3594, "lr": 2.1559279572753214e-05, "epoch": 2.6359493670886076, "percentage": 52.76, "elapsed_time": "1:20:58", "remaining_time": "1:12:29"}
759
+ {"current_steps": 650, "total_steps": 1230, "loss": 0.3629, "lr": 2.1502687458119268e-05, "epoch": 2.64, "percentage": 52.85, "elapsed_time": "1:21:28", "remaining_time": "1:12:42"}
760
+ {"current_steps": 651, "total_steps": 1230, "loss": 0.3572, "lr": 2.1446083241047116e-05, "epoch": 2.6440506329113926, "percentage": 52.93, "elapsed_time": "1:21:52", "remaining_time": "1:12:49"}
761
+ {"current_steps": 652, "total_steps": 1230, "loss": 0.3624, "lr": 2.1389467377419333e-05, "epoch": 2.6481012658227847, "percentage": 53.01, "elapsed_time": "1:22:19", "remaining_time": "1:12:59"}
762
+ {"current_steps": 653, "total_steps": 1230, "loss": 0.3761, "lr": 2.133284032321232e-05, "epoch": 2.6521518987341772, "percentage": 53.09, "elapsed_time": "1:22:54", "remaining_time": "1:13:15"}
763
+ {"current_steps": 654, "total_steps": 1230, "loss": 0.3437, "lr": 2.1276202534492566e-05, "epoch": 2.6562025316455697, "percentage": 53.17, "elapsed_time": "1:23:31", "remaining_time": "1:13:33"}
764
+ {"current_steps": 655, "total_steps": 1230, "loss": 0.361, "lr": 2.121955446741306e-05, "epoch": 2.660253164556962, "percentage": 53.25, "elapsed_time": "1:24:03", "remaining_time": "1:13:47"}
765
+ {"current_steps": 656, "total_steps": 1230, "loss": 0.3756, "lr": 2.1162896578209517e-05, "epoch": 2.6643037974683543, "percentage": 53.33, "elapsed_time": "1:24:35", "remaining_time": "1:14:00"}
766
+ {"current_steps": 657, "total_steps": 1230, "loss": 0.3502, "lr": 2.1106229323196813e-05, "epoch": 2.668354430379747, "percentage": 53.41, "elapsed_time": "1:25:12", "remaining_time": "1:14:18"}
767
+ {"current_steps": 658, "total_steps": 1230, "loss": 0.384, "lr": 2.1049553158765214e-05, "epoch": 2.6724050632911394, "percentage": 53.5, "elapsed_time": "1:25:45", "remaining_time": "1:14:33"}
768
+ {"current_steps": 659, "total_steps": 1230, "loss": 0.3645, "lr": 2.0992868541376764e-05, "epoch": 2.676455696202532, "percentage": 53.58, "elapsed_time": "1:26:15", "remaining_time": "1:14:44"}
769
+ {"current_steps": 660, "total_steps": 1230, "loss": 0.3976, "lr": 2.093617592756158e-05, "epoch": 2.680506329113924, "percentage": 53.66, "elapsed_time": "1:26:51", "remaining_time": "1:15:00"}
770
+ {"current_steps": 661, "total_steps": 1230, "loss": 0.3856, "lr": 2.0879475773914167e-05, "epoch": 2.6845569620253165, "percentage": 53.74, "elapsed_time": "1:27:22", "remaining_time": "1:15:12"}
771
+ {"current_steps": 662, "total_steps": 1230, "loss": 0.3747, "lr": 2.082276853708978e-05, "epoch": 2.688607594936709, "percentage": 53.82, "elapsed_time": "1:27:56", "remaining_time": "1:15:27"}
772
+ {"current_steps": 663, "total_steps": 1230, "loss": 0.3715, "lr": 2.076605467380071e-05, "epoch": 2.692658227848101, "percentage": 53.9, "elapsed_time": "1:28:28", "remaining_time": "1:15:39"}
773
+ {"current_steps": 664, "total_steps": 1230, "loss": 0.3744, "lr": 2.0709334640812613e-05, "epoch": 2.6967088607594936, "percentage": 53.98, "elapsed_time": "1:28:58", "remaining_time": "1:15:50"}
774
+ {"current_steps": 665, "total_steps": 1230, "loss": 0.3764, "lr": 2.0652608894940824e-05, "epoch": 2.700759493670886, "percentage": 54.07, "elapsed_time": "1:29:28", "remaining_time": "1:16:01"}
775
+ {"current_steps": 666, "total_steps": 1230, "loss": 0.3835, "lr": 2.0595877893046722e-05, "epoch": 2.7048101265822786, "percentage": 54.15, "elapsed_time": "1:29:59", "remaining_time": "1:16:12"}
776
+ {"current_steps": 667, "total_steps": 1230, "loss": 0.3717, "lr": 2.0539142092033985e-05, "epoch": 2.708860759493671, "percentage": 54.23, "elapsed_time": "1:30:31", "remaining_time": "1:16:24"}
777
+ {"current_steps": 668, "total_steps": 1230, "loss": 0.3794, "lr": 2.048240194884496e-05, "epoch": 2.712911392405063, "percentage": 54.31, "elapsed_time": "1:31:01", "remaining_time": "1:16:34"}
778
+ {"current_steps": 669, "total_steps": 1230, "loss": 0.3765, "lr": 2.042565792045695e-05, "epoch": 2.7169620253164557, "percentage": 54.39, "elapsed_time": "1:31:36", "remaining_time": "1:16:49"}
779
+ {"current_steps": 670, "total_steps": 1230, "loss": 0.348, "lr": 2.036891046387857e-05, "epoch": 2.721012658227848, "percentage": 54.47, "elapsed_time": "1:32:11", "remaining_time": "1:17:03"}
780
+ {"current_steps": 671, "total_steps": 1230, "loss": 0.3549, "lr": 2.0312160036146036e-05, "epoch": 2.7250632911392403, "percentage": 54.55, "elapsed_time": "1:32:42", "remaining_time": "1:17:13"}
781
+ {"current_steps": 672, "total_steps": 1230, "loss": 0.371, "lr": 2.025540709431948e-05, "epoch": 2.729113924050633, "percentage": 54.63, "elapsed_time": "1:33:18", "remaining_time": "1:17:28"}
782
+ {"current_steps": 673, "total_steps": 1230, "loss": 0.3617, "lr": 2.0198652095479298e-05, "epoch": 2.7331645569620253, "percentage": 54.72, "elapsed_time": "1:33:53", "remaining_time": "1:17:42"}
783
+ {"current_steps": 674, "total_steps": 1230, "loss": 0.3705, "lr": 2.014189549672245e-05, "epoch": 2.737215189873418, "percentage": 54.8, "elapsed_time": "1:34:29", "remaining_time": "1:17:56"}
784
+ {"current_steps": 675, "total_steps": 1230, "loss": 0.3323, "lr": 2.0085137755158776e-05, "epoch": 2.7412658227848103, "percentage": 54.88, "elapsed_time": "1:34:59", "remaining_time": "1:18:06"}
785
+ {"current_steps": 676, "total_steps": 1230, "loss": 0.3579, "lr": 2.0028379327907327e-05, "epoch": 2.7453164556962024, "percentage": 54.96, "elapsed_time": "1:35:35", "remaining_time": "1:18:20"}
786
+ {"current_steps": 677, "total_steps": 1230, "loss": 0.3498, "lr": 1.9971620672092676e-05, "epoch": 2.749367088607595, "percentage": 55.04, "elapsed_time": "1:36:13", "remaining_time": "1:18:35"}
787
+ {"current_steps": 678, "total_steps": 1230, "loss": 0.3581, "lr": 1.991486224484123e-05, "epoch": 2.7534177215189874, "percentage": 55.12, "elapsed_time": "1:36:44", "remaining_time": "1:18:45"}
788
+ {"current_steps": 679, "total_steps": 1230, "loss": 0.3789, "lr": 1.985810450327756e-05, "epoch": 2.7574683544303795, "percentage": 55.2, "elapsed_time": "1:37:21", "remaining_time": "1:19:00"}
789
+ {"current_steps": 680, "total_steps": 1230, "loss": 0.3737, "lr": 1.9801347904520706e-05, "epoch": 2.761518987341772, "percentage": 55.28, "elapsed_time": "1:37:56", "remaining_time": "1:19:13"}
790
+ {"current_steps": 681, "total_steps": 1230, "loss": 0.3607, "lr": 1.974459290568053e-05, "epoch": 2.7655696202531646, "percentage": 55.37, "elapsed_time": "1:38:24", "remaining_time": "1:19:19"}
791
+ {"current_steps": 682, "total_steps": 1230, "loss": 0.3565, "lr": 1.968783996385397e-05, "epoch": 2.769620253164557, "percentage": 55.45, "elapsed_time": "1:38:49", "remaining_time": "1:19:24"}
792
+ {"current_steps": 683, "total_steps": 1230, "loss": 0.3688, "lr": 1.963108953612143e-05, "epoch": 2.7736708860759496, "percentage": 55.53, "elapsed_time": "1:39:24", "remaining_time": "1:19:36"}
793
+ {"current_steps": 684, "total_steps": 1230, "loss": 0.356, "lr": 1.9574342079543056e-05, "epoch": 2.7777215189873417, "percentage": 55.61, "elapsed_time": "1:39:56", "remaining_time": "1:19:46"}
794
+ {"current_steps": 685, "total_steps": 1230, "loss": 0.3637, "lr": 1.9517598051155046e-05, "epoch": 2.781772151898734, "percentage": 55.69, "elapsed_time": "1:40:29", "remaining_time": "1:19:57"}
795
+ {"current_steps": 686, "total_steps": 1230, "loss": 0.3746, "lr": 1.9460857907966025e-05, "epoch": 2.7858227848101267, "percentage": 55.77, "elapsed_time": "1:41:03", "remaining_time": "1:20:08"}
796
+ {"current_steps": 687, "total_steps": 1230, "loss": 0.3697, "lr": 1.9404122106953285e-05, "epoch": 2.7898734177215188, "percentage": 55.85, "elapsed_time": "1:41:34", "remaining_time": "1:20:16"}
797
+ {"current_steps": 688, "total_steps": 1230, "loss": 0.3559, "lr": 1.9347391105059176e-05, "epoch": 2.7939240506329113, "percentage": 55.93, "elapsed_time": "1:42:05", "remaining_time": "1:20:25"}
798
+ {"current_steps": 689, "total_steps": 1230, "loss": 0.3775, "lr": 1.92906653591874e-05, "epoch": 2.797974683544304, "percentage": 56.02, "elapsed_time": "1:42:44", "remaining_time": "1:20:40"}
799
+ {"current_steps": 690, "total_steps": 1230, "loss": 0.3662, "lr": 1.9233945326199295e-05, "epoch": 2.8020253164556963, "percentage": 56.1, "elapsed_time": "1:43:16", "remaining_time": "1:20:49"}
800
+ {"current_steps": 691, "total_steps": 1230, "loss": 0.3757, "lr": 1.917723146291022e-05, "epoch": 2.806075949367089, "percentage": 56.18, "elapsed_time": "1:43:45", "remaining_time": "1:20:56"}
801
+ {"current_steps": 692, "total_steps": 1230, "loss": 0.3567, "lr": 1.912052422608584e-05, "epoch": 2.810126582278481, "percentage": 56.26, "elapsed_time": "1:44:18", "remaining_time": "1:21:05"}
802
+ {"current_steps": 693, "total_steps": 1230, "loss": 0.3846, "lr": 1.9063824072438428e-05, "epoch": 2.8141772151898734, "percentage": 56.34, "elapsed_time": "1:44:50", "remaining_time": "1:21:14"}
803
+ {"current_steps": 694, "total_steps": 1230, "loss": 0.349, "lr": 1.9007131458623246e-05, "epoch": 2.818227848101266, "percentage": 56.42, "elapsed_time": "1:45:19", "remaining_time": "1:21:20"}
804
+ {"current_steps": 695, "total_steps": 1230, "loss": 0.378, "lr": 1.895044684123479e-05, "epoch": 2.822278481012658, "percentage": 56.5, "elapsed_time": "1:45:48", "remaining_time": "1:21:27"}
805
+ {"current_steps": 696, "total_steps": 1230, "loss": 0.3559, "lr": 1.8893770676803194e-05, "epoch": 2.8263291139240505, "percentage": 56.59, "elapsed_time": "1:46:14", "remaining_time": "1:21:31"}
806
+ {"current_steps": 697, "total_steps": 1230, "loss": 0.3481, "lr": 1.8837103421790486e-05, "epoch": 2.830379746835443, "percentage": 56.67, "elapsed_time": "1:46:43", "remaining_time": "1:21:37"}
807
+ {"current_steps": 698, "total_steps": 1230, "loss": 0.3553, "lr": 1.8780445532586952e-05, "epoch": 2.8344303797468355, "percentage": 56.75, "elapsed_time": "1:47:13", "remaining_time": "1:21:43"}
808
+ {"current_steps": 699, "total_steps": 1230, "loss": 0.3609, "lr": 1.872379746550743e-05, "epoch": 2.838481012658228, "percentage": 56.83, "elapsed_time": "1:47:43", "remaining_time": "1:21:49"}
809
+ {"current_steps": 700, "total_steps": 1230, "loss": 0.3456, "lr": 1.866715967678769e-05, "epoch": 2.84253164556962, "percentage": 56.91, "elapsed_time": "1:48:14", "remaining_time": "1:21:57"}
810
+ {"current_steps": 701, "total_steps": 1230, "loss": 0.366, "lr": 1.861053262258067e-05, "epoch": 2.8465822784810126, "percentage": 56.99, "elapsed_time": "1:48:47", "remaining_time": "1:22:06"}
811
+ {"current_steps": 702, "total_steps": 1230, "loss": 0.3661, "lr": 1.8553916758952897e-05, "epoch": 2.850632911392405, "percentage": 57.07, "elapsed_time": "1:49:17", "remaining_time": "1:22:11"}
812
+ {"current_steps": 703, "total_steps": 1230, "loss": 0.3594, "lr": 1.8497312541880735e-05, "epoch": 2.8546835443037972, "percentage": 57.15, "elapsed_time": "1:49:49", "remaining_time": "1:22:19"}
813
+ {"current_steps": 704, "total_steps": 1230, "loss": 0.3565, "lr": 1.8440720427246786e-05, "epoch": 2.8587341772151897, "percentage": 57.24, "elapsed_time": "1:50:22", "remaining_time": "1:22:27"}
814
+ {"current_steps": 705, "total_steps": 1230, "loss": 0.382, "lr": 1.8384140870836157e-05, "epoch": 2.8627848101265823, "percentage": 57.32, "elapsed_time": "1:50:55", "remaining_time": "1:22:36"}
815
+ {"current_steps": 706, "total_steps": 1230, "loss": 0.3685, "lr": 1.8327574328332806e-05, "epoch": 2.8668354430379748, "percentage": 57.4, "elapsed_time": "1:51:29", "remaining_time": "1:22:45"}
816
+ {"current_steps": 707, "total_steps": 1230, "loss": 0.3444, "lr": 1.8271021255315906e-05, "epoch": 2.8708860759493673, "percentage": 57.48, "elapsed_time": "1:51:59", "remaining_time": "1:22:50"}
817
+ {"current_steps": 708, "total_steps": 1230, "loss": 0.3612, "lr": 1.8214482107256117e-05, "epoch": 2.8749367088607594, "percentage": 57.56, "elapsed_time": "1:52:35", "remaining_time": "1:23:00"}
818
+ {"current_steps": 709, "total_steps": 1230, "loss": 0.3603, "lr": 1.8157957339511968e-05, "epoch": 2.878987341772152, "percentage": 57.64, "elapsed_time": "1:53:05", "remaining_time": "1:23:06"}
819
+ {"current_steps": 710, "total_steps": 1230, "loss": 0.3605, "lr": 1.8101447407326182e-05, "epoch": 2.8830379746835444, "percentage": 57.72, "elapsed_time": "1:53:39", "remaining_time": "1:23:14"}
820
+ {"current_steps": 711, "total_steps": 1230, "loss": 0.3617, "lr": 1.8044952765821966e-05, "epoch": 2.8870886075949365, "percentage": 57.8, "elapsed_time": "1:54:01", "remaining_time": "1:23:14"}
821
+ {"current_steps": 712, "total_steps": 1230, "loss": 0.3694, "lr": 1.7988473869999407e-05, "epoch": 2.891139240506329, "percentage": 57.89, "elapsed_time": "1:54:31", "remaining_time": "1:23:19"}
822
+ {"current_steps": 713, "total_steps": 1230, "loss": 0.3517, "lr": 1.7932011174731764e-05, "epoch": 2.8951898734177215, "percentage": 57.97, "elapsed_time": "1:55:02", "remaining_time": "1:23:25"}
823
+ {"current_steps": 714, "total_steps": 1230, "loss": 0.352, "lr": 1.7875565134761817e-05, "epoch": 2.899240506329114, "percentage": 58.05, "elapsed_time": "1:55:27", "remaining_time": "1:23:26"}
824
+ {"current_steps": 715, "total_steps": 1230, "loss": 0.3711, "lr": 1.7819136204698226e-05, "epoch": 2.9032911392405065, "percentage": 58.13, "elapsed_time": "1:56:00", "remaining_time": "1:23:33"}
825
+ {"current_steps": 716, "total_steps": 1230, "loss": 0.3403, "lr": 1.776272483901182e-05, "epoch": 2.9073417721518986, "percentage": 58.21, "elapsed_time": "1:56:32", "remaining_time": "1:23:39"}
826
+ {"current_steps": 717, "total_steps": 1230, "loss": 0.3657, "lr": 1.7706331492031995e-05, "epoch": 2.911392405063291, "percentage": 58.29, "elapsed_time": "1:57:14", "remaining_time": "1:23:52"}
827
+ {"current_steps": 718, "total_steps": 1230, "loss": 0.3715, "lr": 1.764995661794301e-05, "epoch": 2.9154430379746836, "percentage": 58.37, "elapsed_time": "1:57:45", "remaining_time": "1:23:58"}
828
+ {"current_steps": 719, "total_steps": 1230, "loss": 0.3556, "lr": 1.759360067078035e-05, "epoch": 2.9194936708860757, "percentage": 58.46, "elapsed_time": "1:58:17", "remaining_time": "1:24:04"}
829
+ {"current_steps": 720, "total_steps": 1230, "loss": 0.3536, "lr": 1.7537264104427064e-05, "epoch": 2.923544303797468, "percentage": 58.54, "elapsed_time": "1:58:47", "remaining_time": "1:24:08"}
830
+ {"current_steps": 721, "total_steps": 1230, "loss": 0.3579, "lr": 1.748094737261012e-05, "epoch": 2.9275949367088607, "percentage": 58.62, "elapsed_time": "1:59:17", "remaining_time": "1:24:13"}
831
+ {"current_steps": 722, "total_steps": 1230, "loss": 0.3681, "lr": 1.7424650928896726e-05, "epoch": 2.9316455696202532, "percentage": 58.7, "elapsed_time": "1:59:52", "remaining_time": "1:24:20"}
832
+ {"current_steps": 723, "total_steps": 1230, "loss": 0.3778, "lr": 1.7368375226690712e-05, "epoch": 2.9356962025316458, "percentage": 58.78, "elapsed_time": "2:00:24", "remaining_time": "1:24:26"}
833
+ {"current_steps": 724, "total_steps": 1230, "loss": 0.3525, "lr": 1.731212071922883e-05, "epoch": 2.939746835443038, "percentage": 58.86, "elapsed_time": "2:00:52", "remaining_time": "1:24:28"}
834
+ {"current_steps": 725, "total_steps": 1230, "loss": 0.3531, "lr": 1.7255887859577156e-05, "epoch": 2.9437974683544303, "percentage": 58.94, "elapsed_time": "2:01:20", "remaining_time": "1:24:31"}
835
+ {"current_steps": 726, "total_steps": 1230, "loss": 0.3722, "lr": 1.7199677100627427e-05, "epoch": 2.947848101265823, "percentage": 59.02, "elapsed_time": "2:01:48", "remaining_time": "1:24:33"}
836
+ {"current_steps": 727, "total_steps": 1230, "loss": 0.3611, "lr": 1.7143488895093343e-05, "epoch": 2.951898734177215, "percentage": 59.11, "elapsed_time": "2:02:23", "remaining_time": "1:24:40"}
837
+ {"current_steps": 728, "total_steps": 1230, "loss": 0.3554, "lr": 1.7087323695506994e-05, "epoch": 2.9559493670886074, "percentage": 59.19, "elapsed_time": "2:02:55", "remaining_time": "1:24:45"}
838
+ {"current_steps": 729, "total_steps": 1230, "loss": 0.3544, "lr": 1.7031181954215194e-05, "epoch": 2.96, "percentage": 59.27, "elapsed_time": "2:03:24", "remaining_time": "1:24:48"}
839
+ {"current_steps": 730, "total_steps": 1230, "loss": 0.3648, "lr": 1.6975064123375788e-05, "epoch": 2.9640506329113925, "percentage": 59.35, "elapsed_time": "2:03:57", "remaining_time": "1:24:54"}
840
+ {"current_steps": 731, "total_steps": 1230, "loss": 0.3709, "lr": 1.6918970654954084e-05, "epoch": 2.968101265822785, "percentage": 59.43, "elapsed_time": "2:04:28", "remaining_time": "1:24:58"}
841
+ {"current_steps": 732, "total_steps": 1230, "loss": 0.3347, "lr": 1.686290200071915e-05, "epoch": 2.972151898734177, "percentage": 59.51, "elapsed_time": "2:05:01", "remaining_time": "1:25:03"}
842
+ {"current_steps": 733, "total_steps": 1230, "loss": 0.3947, "lr": 1.6806858612240234e-05, "epoch": 2.9762025316455696, "percentage": 59.59, "elapsed_time": "2:05:36", "remaining_time": "1:25:09"}
843
+ {"current_steps": 734, "total_steps": 1230, "loss": 0.359, "lr": 1.6750840940883078e-05, "epoch": 2.980253164556962, "percentage": 59.67, "elapsed_time": "2:06:06", "remaining_time": "1:25:13"}
844
+ {"current_steps": 735, "total_steps": 1230, "loss": 0.3499, "lr": 1.6694849437806305e-05, "epoch": 2.984303797468354, "percentage": 59.76, "elapsed_time": "2:06:34", "remaining_time": "1:25:14"}
845
+ {"current_steps": 736, "total_steps": 1230, "loss": 0.3588, "lr": 1.663888455395778e-05, "epoch": 2.9883544303797467, "percentage": 59.84, "elapsed_time": "2:07:02", "remaining_time": "1:25:16"}
846
+ {"current_steps": 737, "total_steps": 1230, "loss": 0.3599, "lr": 1.6582946740070995e-05, "epoch": 2.992405063291139, "percentage": 59.92, "elapsed_time": "2:07:36", "remaining_time": "1:25:21"}
847
+ {"current_steps": 738, "total_steps": 1230, "loss": 0.3842, "lr": 1.6527036446661396e-05, "epoch": 2.9964556962025317, "percentage": 60.0, "elapsed_time": "2:08:05", "remaining_time": "1:25:23"}
848
+ {"current_steps": 739, "total_steps": 1230, "loss": 0.3476, "lr": 1.6471154124022818e-05, "epoch": 3.0005063291139242, "percentage": 60.08, "elapsed_time": "2:11:06", "remaining_time": "1:27:06"}
849
+ {"current_steps": 740, "total_steps": 1230, "loss": 0.2679, "lr": 1.6415300222223788e-05, "epoch": 3.0045569620253163, "percentage": 60.16, "elapsed_time": "2:11:37", "remaining_time": "1:27:09"}
850
+ {"current_steps": 741, "total_steps": 1230, "loss": 0.2675, "lr": 1.6359475191103958e-05, "epoch": 3.008607594936709, "percentage": 60.24, "elapsed_time": "2:12:09", "remaining_time": "1:27:12"}
851
+ {"current_steps": 742, "total_steps": 1230, "loss": 0.2449, "lr": 1.6303679480270466e-05, "epoch": 3.0126582278481013, "percentage": 60.33, "elapsed_time": "2:12:41", "remaining_time": "1:27:16"}
852
+ {"current_steps": 743, "total_steps": 1230, "loss": 0.275, "lr": 1.624791353909428e-05, "epoch": 3.016708860759494, "percentage": 60.41, "elapsed_time": "2:13:15", "remaining_time": "1:27:20"}
853
+ {"current_steps": 744, "total_steps": 1230, "loss": 0.2396, "lr": 1.619217781670663e-05, "epoch": 3.020759493670886, "percentage": 60.49, "elapsed_time": "2:13:42", "remaining_time": "1:27:20"}
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f326e54cb3a3fb2e579c058e1894522dfbfe2e9a324e63f1ba99adbb93c24a13
3
- size 7224
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7403f95443c44b8e00fc09bb09d1c3d1ac8882e03012f4de3b5c101566fa296
3
+ size 7352