gsmyrnis commited on
Commit
5e62b69
·
verified ·
1 Parent(s): bb5fca2

Training in progress, epoch 5

Browse files
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:aa67225f66cc7ad59aae1efb3a36670d61d4050be6d74566f5cafb04f0d5cea2
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b84a5ebada539a5d2dab342608b2d0603249b0816d8e9c1ba26b9e74e5fa3e9f
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:07e80d6b67c2b38fe6b69ebec576d055bbec53092c8ed3a63f2a2522421af9a5
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84893245cfc4ee050b1554091232bf2998ca3adecf81dc211d30fec704911adb
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4b8128b01b1279cebe23493c28f3ea2672cf36794bdb9a3d84b303ba5da33645
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d15225517a5f0d6938a5ccfd3e9ae45e51a41e0e7a8fe455ab78698ce362c5a
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6911afacf14f4738295dba5dd8efcdb5c20659634a24f962846f4947bb9815b5
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55851e094a7f710d8a4b16ae976af6ca72f41de567a553cdd71e0d9e16ce99fe
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -994,3 +994,243 @@
994
  {"current_steps": 994, "total_steps": 1235, "loss": 0.2628, "lr": 4.467169815100549e-06, "epoch": 4.0242914979757085, "percentage": 80.49, "elapsed_time": "5:26:16", "remaining_time": "1:19:06"}
995
  {"current_steps": 995, "total_steps": 1235, "loss": 0.2675, "lr": 4.431605972355137e-06, "epoch": 4.02834008097166, "percentage": 80.57, "elapsed_time": "5:26:32", "remaining_time": "1:18:45"}
996
  {"current_steps": 996, "total_steps": 1235, "loss": 0.2775, "lr": 4.396166614073516e-06, "epoch": 4.032388663967612, "percentage": 80.65, "elapsed_time": "5:26:53", "remaining_time": "1:18:26"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
994
  {"current_steps": 994, "total_steps": 1235, "loss": 0.2628, "lr": 4.467169815100549e-06, "epoch": 4.0242914979757085, "percentage": 80.49, "elapsed_time": "5:26:16", "remaining_time": "1:19:06"}
995
  {"current_steps": 995, "total_steps": 1235, "loss": 0.2675, "lr": 4.431605972355137e-06, "epoch": 4.02834008097166, "percentage": 80.57, "elapsed_time": "5:26:32", "remaining_time": "1:18:45"}
996
  {"current_steps": 996, "total_steps": 1235, "loss": 0.2775, "lr": 4.396166614073516e-06, "epoch": 4.032388663967612, "percentage": 80.65, "elapsed_time": "5:26:53", "remaining_time": "1:18:26"}
997
+ {"current_steps": 997, "total_steps": 1235, "loss": 0.2632, "lr": 4.360852023627846e-06, "epoch": 4.036437246963563, "percentage": 80.73, "elapsed_time": "5:27:14", "remaining_time": "1:18:07"}
998
+ {"current_steps": 998, "total_steps": 1235, "loss": 0.2793, "lr": 4.325662483392656e-06, "epoch": 4.040485829959514, "percentage": 80.81, "elapsed_time": "5:27:37", "remaining_time": "1:17:48"}
999
+ {"current_steps": 999, "total_steps": 1235, "loss": 0.2692, "lr": 4.29059827474257e-06, "epoch": 4.044534412955466, "percentage": 80.89, "elapsed_time": "5:27:55", "remaining_time": "1:17:28"}
1000
+ {"current_steps": 1000, "total_steps": 1235, "loss": 0.2795, "lr": 4.255659678050063e-06, "epoch": 4.048582995951417, "percentage": 80.97, "elapsed_time": "5:28:18", "remaining_time": "1:17:09"}
1001
+ {"current_steps": 1001, "total_steps": 1235, "loss": 0.2623, "lr": 4.22084697268323e-06, "epoch": 4.052631578947368, "percentage": 81.05, "elapsed_time": "5:28:39", "remaining_time": "1:16:49"}
1002
+ {"current_steps": 1002, "total_steps": 1235, "loss": 0.2668, "lr": 4.186160437003535e-06, "epoch": 4.05668016194332, "percentage": 81.13, "elapsed_time": "5:28:59", "remaining_time": "1:16:30"}
1003
+ {"current_steps": 1003, "total_steps": 1235, "loss": 0.2492, "lr": 4.151600348363582e-06, "epoch": 4.060728744939271, "percentage": 81.21, "elapsed_time": "5:29:16", "remaining_time": "1:16:09"}
1004
+ {"current_steps": 1004, "total_steps": 1235, "loss": 0.2697, "lr": 4.11716698310493e-06, "epoch": 4.064777327935222, "percentage": 81.3, "elapsed_time": "5:29:36", "remaining_time": "1:15:50"}
1005
+ {"current_steps": 1005, "total_steps": 1235, "loss": 0.252, "lr": 4.082860616555848e-06, "epoch": 4.068825910931174, "percentage": 81.38, "elapsed_time": "5:29:56", "remaining_time": "1:15:30"}
1006
+ {"current_steps": 1006, "total_steps": 1235, "loss": 0.2743, "lr": 4.048681523029125e-06, "epoch": 4.0728744939271255, "percentage": 81.46, "elapsed_time": "5:30:18", "remaining_time": "1:15:11"}
1007
+ {"current_steps": 1007, "total_steps": 1235, "loss": 0.2655, "lr": 4.014629975819882e-06, "epoch": 4.076923076923077, "percentage": 81.54, "elapsed_time": "5:30:42", "remaining_time": "1:14:52"}
1008
+ {"current_steps": 1008, "total_steps": 1235, "loss": 0.2767, "lr": 3.9807062472033855e-06, "epoch": 4.080971659919029, "percentage": 81.62, "elapsed_time": "5:31:00", "remaining_time": "1:14:32"}
1009
+ {"current_steps": 1009, "total_steps": 1235, "loss": 0.2639, "lr": 3.94691060843287e-06, "epoch": 4.08502024291498, "percentage": 81.7, "elapsed_time": "5:31:20", "remaining_time": "1:14:12"}
1010
+ {"current_steps": 1010, "total_steps": 1235, "loss": 0.2463, "lr": 3.913243329737353e-06, "epoch": 4.089068825910931, "percentage": 81.78, "elapsed_time": "5:31:38", "remaining_time": "1:13:52"}
1011
+ {"current_steps": 1011, "total_steps": 1235, "loss": 0.2501, "lr": 3.879704680319503e-06, "epoch": 4.093117408906883, "percentage": 81.86, "elapsed_time": "5:31:56", "remaining_time": "1:13:32"}
1012
+ {"current_steps": 1012, "total_steps": 1235, "loss": 0.2705, "lr": 3.846294928353471e-06, "epoch": 4.097165991902834, "percentage": 81.94, "elapsed_time": "5:32:17", "remaining_time": "1:13:13"}
1013
+ {"current_steps": 1013, "total_steps": 1235, "loss": 0.2519, "lr": 3.8130143409827345e-06, "epoch": 4.101214574898785, "percentage": 82.02, "elapsed_time": "5:32:35", "remaining_time": "1:12:53"}
1014
+ {"current_steps": 1014, "total_steps": 1235, "loss": 0.2588, "lr": 3.7798631843179887e-06, "epoch": 4.105263157894737, "percentage": 82.11, "elapsed_time": "5:32:55", "remaining_time": "1:12:33"}
1015
+ {"current_steps": 1015, "total_steps": 1235, "loss": 0.2781, "lr": 3.7468417234349973e-06, "epoch": 4.109311740890688, "percentage": 82.19, "elapsed_time": "5:33:15", "remaining_time": "1:12:13"}
1016
+ {"current_steps": 1016, "total_steps": 1235, "loss": 0.2612, "lr": 3.7139502223724823e-06, "epoch": 4.113360323886639, "percentage": 82.27, "elapsed_time": "5:33:36", "remaining_time": "1:11:54"}
1017
+ {"current_steps": 1017, "total_steps": 1235, "loss": 0.2545, "lr": 3.6811889441300095e-06, "epoch": 4.117408906882591, "percentage": 82.35, "elapsed_time": "5:33:57", "remaining_time": "1:11:35"}
1018
+ {"current_steps": 1018, "total_steps": 1235, "loss": 0.2555, "lr": 3.648558150665886e-06, "epoch": 4.1214574898785425, "percentage": 82.43, "elapsed_time": "5:34:13", "remaining_time": "1:11:14"}
1019
+ {"current_steps": 1019, "total_steps": 1235, "loss": 0.2805, "lr": 3.616058102895075e-06, "epoch": 4.125506072874494, "percentage": 82.51, "elapsed_time": "5:34:32", "remaining_time": "1:10:54"}
1020
+ {"current_steps": 1020, "total_steps": 1235, "loss": 0.2672, "lr": 3.583689060687079e-06, "epoch": 4.129554655870446, "percentage": 82.59, "elapsed_time": "5:34:55", "remaining_time": "1:10:35"}
1021
+ {"current_steps": 1021, "total_steps": 1235, "loss": 0.255, "lr": 3.5514512828639023e-06, "epoch": 4.133603238866397, "percentage": 82.67, "elapsed_time": "5:35:14", "remaining_time": "1:10:15"}
1022
+ {"current_steps": 1022, "total_steps": 1235, "loss": 0.2396, "lr": 3.51934502719796e-06, "epoch": 4.137651821862348, "percentage": 82.75, "elapsed_time": "5:35:33", "remaining_time": "1:09:56"}
1023
+ {"current_steps": 1023, "total_steps": 1235, "loss": 0.2743, "lr": 3.4873705504100185e-06, "epoch": 4.1417004048583, "percentage": 82.83, "elapsed_time": "5:35:57", "remaining_time": "1:09:37"}
1024
+ {"current_steps": 1024, "total_steps": 1235, "loss": 0.2519, "lr": 3.4555281081671345e-06, "epoch": 4.145748987854251, "percentage": 82.91, "elapsed_time": "5:36:17", "remaining_time": "1:09:17"}
1025
+ {"current_steps": 1025, "total_steps": 1235, "loss": 0.2543, "lr": 3.4238179550806326e-06, "epoch": 4.149797570850202, "percentage": 83.0, "elapsed_time": "5:36:34", "remaining_time": "1:08:57"}
1026
+ {"current_steps": 1026, "total_steps": 1235, "loss": 0.2662, "lr": 3.3922403447040497e-06, "epoch": 4.153846153846154, "percentage": 83.08, "elapsed_time": "5:36:54", "remaining_time": "1:08:37"}
1027
+ {"current_steps": 1027, "total_steps": 1235, "loss": 0.2722, "lr": 3.3607955295311247e-06, "epoch": 4.157894736842105, "percentage": 83.16, "elapsed_time": "5:37:12", "remaining_time": "1:08:17"}
1028
+ {"current_steps": 1028, "total_steps": 1235, "loss": 0.2689, "lr": 3.32948376099375e-06, "epoch": 4.161943319838056, "percentage": 83.24, "elapsed_time": "5:37:32", "remaining_time": "1:07:58"}
1029
+ {"current_steps": 1029, "total_steps": 1235, "loss": 0.2562, "lr": 3.2983052894599976e-06, "epoch": 4.165991902834008, "percentage": 83.32, "elapsed_time": "5:37:50", "remaining_time": "1:07:37"}
1030
+ {"current_steps": 1030, "total_steps": 1235, "loss": 0.264, "lr": 3.2672603642320945e-06, "epoch": 4.17004048582996, "percentage": 83.4, "elapsed_time": "5:38:08", "remaining_time": "1:07:17"}
1031
+ {"current_steps": 1031, "total_steps": 1235, "loss": 0.2878, "lr": 3.236349233544438e-06, "epoch": 4.174089068825911, "percentage": 83.48, "elapsed_time": "5:38:29", "remaining_time": "1:06:58"}
1032
+ {"current_steps": 1032, "total_steps": 1235, "loss": 0.2484, "lr": 3.205572144561604e-06, "epoch": 4.178137651821863, "percentage": 83.56, "elapsed_time": "5:38:50", "remaining_time": "1:06:39"}
1033
+ {"current_steps": 1033, "total_steps": 1235, "loss": 0.2655, "lr": 3.174929343376374e-06, "epoch": 4.182186234817814, "percentage": 83.64, "elapsed_time": "5:39:11", "remaining_time": "1:06:19"}
1034
+ {"current_steps": 1034, "total_steps": 1235, "loss": 0.2509, "lr": 3.1444210750077777e-06, "epoch": 4.186234817813765, "percentage": 83.72, "elapsed_time": "5:39:26", "remaining_time": "1:05:59"}
1035
+ {"current_steps": 1035, "total_steps": 1235, "loss": 0.2513, "lr": 3.1140475833991046e-06, "epoch": 4.190283400809717, "percentage": 83.81, "elapsed_time": "5:39:45", "remaining_time": "1:05:39"}
1036
+ {"current_steps": 1036, "total_steps": 1235, "loss": 0.2618, "lr": 3.0838091114159895e-06, "epoch": 4.194331983805668, "percentage": 83.89, "elapsed_time": "5:40:02", "remaining_time": "1:05:19"}
1037
+ {"current_steps": 1037, "total_steps": 1235, "loss": 0.2621, "lr": 3.0537059008444524e-06, "epoch": 4.198380566801619, "percentage": 83.97, "elapsed_time": "5:40:27", "remaining_time": "1:05:00"}
1038
+ {"current_steps": 1038, "total_steps": 1235, "loss": 0.2738, "lr": 3.0237381923889563e-06, "epoch": 4.202429149797571, "percentage": 84.05, "elapsed_time": "5:40:46", "remaining_time": "1:04:40"}
1039
+ {"current_steps": 1039, "total_steps": 1235, "loss": 0.2459, "lr": 2.9939062256704997e-06, "epoch": 4.206477732793522, "percentage": 84.13, "elapsed_time": "5:41:03", "remaining_time": "1:04:20"}
1040
+ {"current_steps": 1040, "total_steps": 1235, "loss": 0.2363, "lr": 2.964210239224696e-06, "epoch": 4.2105263157894735, "percentage": 84.21, "elapsed_time": "5:41:20", "remaining_time": "1:04:00"}
1041
+ {"current_steps": 1041, "total_steps": 1235, "loss": 0.2637, "lr": 2.934650470499869e-06, "epoch": 4.2145748987854255, "percentage": 84.29, "elapsed_time": "5:41:38", "remaining_time": "1:03:40"}
1042
+ {"current_steps": 1042, "total_steps": 1235, "loss": 0.2724, "lr": 2.905227155855128e-06, "epoch": 4.218623481781377, "percentage": 84.37, "elapsed_time": "5:41:57", "remaining_time": "1:03:20"}
1043
+ {"current_steps": 1043, "total_steps": 1235, "loss": 0.2525, "lr": 2.875940530558519e-06, "epoch": 4.222672064777328, "percentage": 84.45, "elapsed_time": "5:42:17", "remaining_time": "1:03:00"}
1044
+ {"current_steps": 1044, "total_steps": 1235, "loss": 0.2689, "lr": 2.8467908287851154e-06, "epoch": 4.22672064777328, "percentage": 84.53, "elapsed_time": "5:42:36", "remaining_time": "1:02:40"}
1045
+ {"current_steps": 1045, "total_steps": 1235, "loss": 0.2559, "lr": 2.8177782836151603e-06, "epoch": 4.230769230769231, "percentage": 84.62, "elapsed_time": "5:42:52", "remaining_time": "1:02:20"}
1046
+ {"current_steps": 1046, "total_steps": 1235, "loss": 0.27, "lr": 2.7889031270321874e-06, "epoch": 4.234817813765182, "percentage": 84.7, "elapsed_time": "5:43:15", "remaining_time": "1:02:01"}
1047
+ {"current_steps": 1047, "total_steps": 1235, "loss": 0.2672, "lr": 2.760165589921184e-06, "epoch": 4.238866396761134, "percentage": 84.78, "elapsed_time": "5:43:37", "remaining_time": "1:01:42"}
1048
+ {"current_steps": 1048, "total_steps": 1235, "loss": 0.2477, "lr": 2.7315659020667305e-06, "epoch": 4.242914979757085, "percentage": 84.86, "elapsed_time": "5:43:57", "remaining_time": "1:01:22"}
1049
+ {"current_steps": 1049, "total_steps": 1235, "loss": 0.2673, "lr": 2.703104292151164e-06, "epoch": 4.246963562753036, "percentage": 84.94, "elapsed_time": "5:44:16", "remaining_time": "1:01:02"}
1050
+ {"current_steps": 1050, "total_steps": 1235, "loss": 0.2625, "lr": 2.6747809877527607e-06, "epoch": 4.251012145748988, "percentage": 85.02, "elapsed_time": "5:44:32", "remaining_time": "1:00:42"}
1051
+ {"current_steps": 1051, "total_steps": 1235, "loss": 0.2521, "lr": 2.6465962153439082e-06, "epoch": 4.255060728744939, "percentage": 85.1, "elapsed_time": "5:44:52", "remaining_time": "1:00:22"}
1052
+ {"current_steps": 1052, "total_steps": 1235, "loss": 0.2621, "lr": 2.618550200289303e-06, "epoch": 4.2591093117408905, "percentage": 85.18, "elapsed_time": "5:45:11", "remaining_time": "1:00:02"}
1053
+ {"current_steps": 1053, "total_steps": 1235, "loss": 0.2516, "lr": 2.59064316684412e-06, "epoch": 4.2631578947368425, "percentage": 85.26, "elapsed_time": "5:45:31", "remaining_time": "0:59:43"}
1054
+ {"current_steps": 1054, "total_steps": 1235, "loss": 0.2538, "lr": 2.562875338152264e-06, "epoch": 4.267206477732794, "percentage": 85.34, "elapsed_time": "5:45:52", "remaining_time": "0:59:23"}
1055
+ {"current_steps": 1055, "total_steps": 1235, "loss": 0.2573, "lr": 2.5352469362445552e-06, "epoch": 4.271255060728745, "percentage": 85.43, "elapsed_time": "5:46:07", "remaining_time": "0:59:03"}
1056
+ {"current_steps": 1056, "total_steps": 1235, "loss": 0.2392, "lr": 2.5077581820369523e-06, "epoch": 4.275303643724697, "percentage": 85.51, "elapsed_time": "5:46:21", "remaining_time": "0:58:42"}
1057
+ {"current_steps": 1057, "total_steps": 1235, "loss": 0.2581, "lr": 2.480409295328803e-06, "epoch": 4.279352226720648, "percentage": 85.59, "elapsed_time": "5:46:41", "remaining_time": "0:58:22"}
1058
+ {"current_steps": 1058, "total_steps": 1235, "loss": 0.266, "lr": 2.45320049480108e-06, "epoch": 4.283400809716599, "percentage": 85.67, "elapsed_time": "5:47:02", "remaining_time": "0:58:03"}
1059
+ {"current_steps": 1059, "total_steps": 1235, "loss": 0.2668, "lr": 2.4261319980146293e-06, "epoch": 4.287449392712551, "percentage": 85.75, "elapsed_time": "5:47:24", "remaining_time": "0:57:44"}
1060
+ {"current_steps": 1060, "total_steps": 1235, "loss": 0.261, "lr": 2.399204021408421e-06, "epoch": 4.291497975708502, "percentage": 85.83, "elapsed_time": "5:47:45", "remaining_time": "0:57:24"}
1061
+ {"current_steps": 1061, "total_steps": 1235, "loss": 0.2641, "lr": 2.3724167802978395e-06, "epoch": 4.295546558704453, "percentage": 85.91, "elapsed_time": "5:48:03", "remaining_time": "0:57:04"}
1062
+ {"current_steps": 1062, "total_steps": 1235, "loss": 0.258, "lr": 2.3457704888729625e-06, "epoch": 4.299595141700405, "percentage": 85.99, "elapsed_time": "5:48:21", "remaining_time": "0:56:44"}
1063
+ {"current_steps": 1063, "total_steps": 1235, "loss": 0.2683, "lr": 2.3192653601968162e-06, "epoch": 4.303643724696356, "percentage": 86.07, "elapsed_time": "5:48:43", "remaining_time": "0:56:25"}
1064
+ {"current_steps": 1064, "total_steps": 1235, "loss": 0.255, "lr": 2.2929016062037057e-06, "epoch": 4.3076923076923075, "percentage": 86.15, "elapsed_time": "5:49:01", "remaining_time": "0:56:05"}
1065
+ {"current_steps": 1065, "total_steps": 1235, "loss": 0.2544, "lr": 2.2666794376975055e-06, "epoch": 4.3117408906882595, "percentage": 86.23, "elapsed_time": "5:49:21", "remaining_time": "0:55:45"}
1066
+ {"current_steps": 1066, "total_steps": 1235, "loss": 0.2727, "lr": 2.24059906434998e-06, "epoch": 4.315789473684211, "percentage": 86.32, "elapsed_time": "5:49:42", "remaining_time": "0:55:26"}
1067
+ {"current_steps": 1067, "total_steps": 1235, "loss": 0.2851, "lr": 2.214660694699091e-06, "epoch": 4.319838056680162, "percentage": 86.4, "elapsed_time": "5:49:58", "remaining_time": "0:55:06"}
1068
+ {"current_steps": 1068, "total_steps": 1235, "loss": 0.2761, "lr": 2.188864536147355e-06, "epoch": 4.323886639676114, "percentage": 86.48, "elapsed_time": "5:50:21", "remaining_time": "0:54:47"}
1069
+ {"current_steps": 1069, "total_steps": 1235, "loss": 0.247, "lr": 2.1632107949601757e-06, "epoch": 4.327935222672065, "percentage": 86.56, "elapsed_time": "5:50:38", "remaining_time": "0:54:26"}
1070
+ {"current_steps": 1070, "total_steps": 1235, "loss": 0.2583, "lr": 2.137699676264171e-06, "epoch": 4.331983805668016, "percentage": 86.64, "elapsed_time": "5:50:55", "remaining_time": "0:54:06"}
1071
+ {"current_steps": 1071, "total_steps": 1235, "loss": 0.2772, "lr": 2.1123313840455738e-06, "epoch": 4.336032388663968, "percentage": 86.72, "elapsed_time": "5:51:15", "remaining_time": "0:53:47"}
1072
+ {"current_steps": 1072, "total_steps": 1235, "loss": 0.2553, "lr": 2.08710612114857e-06, "epoch": 4.340080971659919, "percentage": 86.8, "elapsed_time": "5:51:29", "remaining_time": "0:53:26"}
1073
+ {"current_steps": 1073, "total_steps": 1235, "loss": 0.2484, "lr": 2.0620240892736953e-06, "epoch": 4.34412955465587, "percentage": 86.88, "elapsed_time": "5:51:51", "remaining_time": "0:53:07"}
1074
+ {"current_steps": 1074, "total_steps": 1235, "loss": 0.2634, "lr": 2.0370854889762e-06, "epoch": 4.348178137651822, "percentage": 86.96, "elapsed_time": "5:52:12", "remaining_time": "0:52:47"}
1075
+ {"current_steps": 1075, "total_steps": 1235, "loss": 0.2736, "lr": 2.0122905196644726e-06, "epoch": 4.352226720647773, "percentage": 87.04, "elapsed_time": "5:52:33", "remaining_time": "0:52:28"}
1076
+ {"current_steps": 1076, "total_steps": 1235, "loss": 0.2717, "lr": 1.987639379598427e-06, "epoch": 4.3562753036437245, "percentage": 87.13, "elapsed_time": "5:52:53", "remaining_time": "0:52:08"}
1077
+ {"current_steps": 1077, "total_steps": 1235, "loss": 0.266, "lr": 1.963132265887919e-06, "epoch": 4.3603238866396765, "percentage": 87.21, "elapsed_time": "5:53:13", "remaining_time": "0:51:49"}
1078
+ {"current_steps": 1078, "total_steps": 1235, "loss": 0.2674, "lr": 1.9387693744911784e-06, "epoch": 4.364372469635628, "percentage": 87.29, "elapsed_time": "5:53:33", "remaining_time": "0:51:29"}
1079
+ {"current_steps": 1079, "total_steps": 1235, "loss": 0.2632, "lr": 1.9145509002132368e-06, "epoch": 4.368421052631579, "percentage": 87.37, "elapsed_time": "5:53:50", "remaining_time": "0:51:09"}
1080
+ {"current_steps": 1080, "total_steps": 1235, "loss": 0.2676, "lr": 1.8904770367043723e-06, "epoch": 4.372469635627531, "percentage": 87.45, "elapsed_time": "5:54:11", "remaining_time": "0:50:49"}
1081
+ {"current_steps": 1081, "total_steps": 1235, "loss": 0.2638, "lr": 1.8665479764585504e-06, "epoch": 4.376518218623482, "percentage": 87.53, "elapsed_time": "5:54:29", "remaining_time": "0:50:30"}
1082
+ {"current_steps": 1082, "total_steps": 1235, "loss": 0.2666, "lr": 1.8427639108118977e-06, "epoch": 4.380566801619433, "percentage": 87.61, "elapsed_time": "5:54:51", "remaining_time": "0:50:10"}
1083
+ {"current_steps": 1083, "total_steps": 1235, "loss": 0.2493, "lr": 1.8191250299411755e-06, "epoch": 4.384615384615385, "percentage": 87.69, "elapsed_time": "5:55:12", "remaining_time": "0:49:51"}
1084
+ {"current_steps": 1084, "total_steps": 1235, "loss": 0.2574, "lr": 1.7956315228622446e-06, "epoch": 4.388663967611336, "percentage": 87.77, "elapsed_time": "5:55:30", "remaining_time": "0:49:31"}
1085
+ {"current_steps": 1085, "total_steps": 1235, "loss": 0.25, "lr": 1.7722835774285553e-06, "epoch": 4.392712550607287, "percentage": 87.85, "elapsed_time": "5:55:48", "remaining_time": "0:49:11"}
1086
+ {"current_steps": 1086, "total_steps": 1235, "loss": 0.258, "lr": 1.7490813803296624e-06, "epoch": 4.396761133603239, "percentage": 87.94, "elapsed_time": "5:56:07", "remaining_time": "0:48:51"}
1087
+ {"current_steps": 1087, "total_steps": 1235, "loss": 0.2558, "lr": 1.726025117089718e-06, "epoch": 4.40080971659919, "percentage": 88.02, "elapsed_time": "5:56:27", "remaining_time": "0:48:31"}
1088
+ {"current_steps": 1088, "total_steps": 1235, "loss": 0.263, "lr": 1.70311497206598e-06, "epoch": 4.4048582995951415, "percentage": 88.1, "elapsed_time": "5:56:49", "remaining_time": "0:48:12"}
1089
+ {"current_steps": 1089, "total_steps": 1235, "loss": 0.2717, "lr": 1.6803511284473638e-06, "epoch": 4.4089068825910935, "percentage": 88.18, "elapsed_time": "5:57:08", "remaining_time": "0:47:52"}
1090
+ {"current_steps": 1090, "total_steps": 1235, "loss": 0.273, "lr": 1.6577337682529538e-06, "epoch": 4.412955465587045, "percentage": 88.26, "elapsed_time": "5:57:27", "remaining_time": "0:47:33"}
1091
+ {"current_steps": 1091, "total_steps": 1235, "loss": 0.2658, "lr": 1.6352630723305617e-06, "epoch": 4.417004048582996, "percentage": 88.34, "elapsed_time": "5:57:47", "remaining_time": "0:47:13"}
1092
+ {"current_steps": 1092, "total_steps": 1235, "loss": 0.2487, "lr": 1.612939220355272e-06, "epoch": 4.421052631578947, "percentage": 88.42, "elapsed_time": "5:58:07", "remaining_time": "0:46:53"}
1093
+ {"current_steps": 1093, "total_steps": 1235, "loss": 0.2803, "lr": 1.5907623908280112e-06, "epoch": 4.425101214574899, "percentage": 88.5, "elapsed_time": "5:58:27", "remaining_time": "0:46:34"}
1094
+ {"current_steps": 1094, "total_steps": 1235, "loss": 0.2764, "lr": 1.568732761074121e-06, "epoch": 4.42914979757085, "percentage": 88.58, "elapsed_time": "5:58:46", "remaining_time": "0:46:14"}
1095
+ {"current_steps": 1095, "total_steps": 1235, "loss": 0.2721, "lr": 1.5468505072419237e-06, "epoch": 4.433198380566802, "percentage": 88.66, "elapsed_time": "5:59:08", "remaining_time": "0:45:55"}
1096
+ {"current_steps": 1096, "total_steps": 1235, "loss": 0.2552, "lr": 1.5251158043013448e-06, "epoch": 4.437246963562753, "percentage": 88.74, "elapsed_time": "5:59:27", "remaining_time": "0:45:35"}
1097
+ {"current_steps": 1097, "total_steps": 1235, "loss": 0.2476, "lr": 1.5035288260424885e-06, "epoch": 4.441295546558704, "percentage": 88.83, "elapsed_time": "5:59:45", "remaining_time": "0:45:15"}
1098
+ {"current_steps": 1098, "total_steps": 1235, "loss": 0.2597, "lr": 1.4820897450742623e-06, "epoch": 4.445344129554655, "percentage": 88.91, "elapsed_time": "6:00:05", "remaining_time": "0:44:55"}
1099
+ {"current_steps": 1099, "total_steps": 1235, "loss": 0.263, "lr": 1.4607987328229767e-06, "epoch": 4.449392712550607, "percentage": 88.99, "elapsed_time": "6:00:22", "remaining_time": "0:44:35"}
1100
+ {"current_steps": 1100, "total_steps": 1235, "loss": 0.2573, "lr": 1.4396559595310056e-06, "epoch": 4.4534412955465585, "percentage": 89.07, "elapsed_time": "6:00:41", "remaining_time": "0:44:15"}
1101
+ {"current_steps": 1101, "total_steps": 1235, "loss": 0.2789, "lr": 1.4186615942553973e-06, "epoch": 4.4574898785425106, "percentage": 89.15, "elapsed_time": "6:01:01", "remaining_time": "0:43:56"}
1102
+ {"current_steps": 1102, "total_steps": 1235, "loss": 0.2669, "lr": 1.3978158048665424e-06, "epoch": 4.461538461538462, "percentage": 89.23, "elapsed_time": "6:01:20", "remaining_time": "0:43:36"}
1103
+ {"current_steps": 1103, "total_steps": 1235, "loss": 0.2721, "lr": 1.3771187580468115e-06, "epoch": 4.465587044534413, "percentage": 89.31, "elapsed_time": "6:01:38", "remaining_time": "0:43:16"}
1104
+ {"current_steps": 1104, "total_steps": 1235, "loss": 0.2566, "lr": 1.3565706192892392e-06, "epoch": 4.469635627530364, "percentage": 89.39, "elapsed_time": "6:01:56", "remaining_time": "0:42:56"}
1105
+ {"current_steps": 1105, "total_steps": 1235, "loss": 0.2618, "lr": 1.3361715528961993e-06, "epoch": 4.473684210526316, "percentage": 89.47, "elapsed_time": "6:02:14", "remaining_time": "0:42:36"}
1106
+ {"current_steps": 1106, "total_steps": 1235, "loss": 0.2644, "lr": 1.3159217219780817e-06, "epoch": 4.477732793522267, "percentage": 89.55, "elapsed_time": "6:02:35", "remaining_time": "0:42:17"}
1107
+ {"current_steps": 1107, "total_steps": 1235, "loss": 0.2504, "lr": 1.2958212884519949e-06, "epoch": 4.481781376518219, "percentage": 89.64, "elapsed_time": "6:02:53", "remaining_time": "0:41:57"}
1108
+ {"current_steps": 1108, "total_steps": 1235, "loss": 0.2617, "lr": 1.2758704130404675e-06, "epoch": 4.48582995951417, "percentage": 89.72, "elapsed_time": "6:03:13", "remaining_time": "0:41:37"}
1109
+ {"current_steps": 1109, "total_steps": 1235, "loss": 0.2685, "lr": 1.2560692552701738e-06, "epoch": 4.489878542510121, "percentage": 89.8, "elapsed_time": "6:03:32", "remaining_time": "0:41:18"}
1110
+ {"current_steps": 1110, "total_steps": 1235, "loss": 0.2646, "lr": 1.2364179734706382e-06, "epoch": 4.493927125506072, "percentage": 89.88, "elapsed_time": "6:03:53", "remaining_time": "0:40:58"}
1111
+ {"current_steps": 1111, "total_steps": 1235, "loss": 0.2605, "lr": 1.2169167247729852e-06, "epoch": 4.497975708502024, "percentage": 89.96, "elapsed_time": "6:04:15", "remaining_time": "0:40:39"}
1112
+ {"current_steps": 1112, "total_steps": 1235, "loss": 0.2704, "lr": 1.1975656651086864e-06, "epoch": 4.502024291497976, "percentage": 90.04, "elapsed_time": "6:04:37", "remaining_time": "0:40:19"}
1113
+ {"current_steps": 1113, "total_steps": 1235, "loss": 0.2599, "lr": 1.1783649492082926e-06, "epoch": 4.506072874493928, "percentage": 90.12, "elapsed_time": "6:04:57", "remaining_time": "0:40:00"}
1114
+ {"current_steps": 1114, "total_steps": 1235, "loss": 0.2571, "lr": 1.1593147306002183e-06, "epoch": 4.510121457489879, "percentage": 90.2, "elapsed_time": "6:05:19", "remaining_time": "0:39:40"}
1115
+ {"current_steps": 1115, "total_steps": 1235, "loss": 0.2752, "lr": 1.140415161609505e-06, "epoch": 4.51417004048583, "percentage": 90.28, "elapsed_time": "6:05:38", "remaining_time": "0:39:21"}
1116
+ {"current_steps": 1116, "total_steps": 1235, "loss": 0.2729, "lr": 1.121666393356604e-06, "epoch": 4.518218623481781, "percentage": 90.36, "elapsed_time": "6:05:58", "remaining_time": "0:39:01"}
1117
+ {"current_steps": 1117, "total_steps": 1235, "loss": 0.2629, "lr": 1.1030685757561632e-06, "epoch": 4.522267206477733, "percentage": 90.45, "elapsed_time": "6:06:17", "remaining_time": "0:38:41"}
1118
+ {"current_steps": 1118, "total_steps": 1235, "loss": 0.2497, "lr": 1.0846218575158373e-06, "epoch": 4.526315789473684, "percentage": 90.53, "elapsed_time": "6:06:36", "remaining_time": "0:38:22"}
1119
+ {"current_steps": 1119, "total_steps": 1235, "loss": 0.2611, "lr": 1.066326386135097e-06, "epoch": 4.530364372469636, "percentage": 90.61, "elapsed_time": "6:06:59", "remaining_time": "0:38:02"}
1120
+ {"current_steps": 1120, "total_steps": 1235, "loss": 0.2712, "lr": 1.0481823079040398e-06, "epoch": 4.534412955465587, "percentage": 90.69, "elapsed_time": "6:07:18", "remaining_time": "0:37:42"}
1121
+ {"current_steps": 1121, "total_steps": 1235, "loss": 0.2574, "lr": 1.0301897679022344e-06, "epoch": 4.538461538461538, "percentage": 90.77, "elapsed_time": "6:07:38", "remaining_time": "0:37:23"}
1122
+ {"current_steps": 1122, "total_steps": 1235, "loss": 0.251, "lr": 1.0123489099975491e-06, "epoch": 4.5425101214574894, "percentage": 90.85, "elapsed_time": "6:07:52", "remaining_time": "0:37:03"}
1123
+ {"current_steps": 1123, "total_steps": 1235, "loss": 0.2633, "lr": 9.9465987684501e-07, "epoch": 4.5465587044534415, "percentage": 90.93, "elapsed_time": "6:08:13", "remaining_time": "0:36:43"}
1124
+ {"current_steps": 1124, "total_steps": 1235, "loss": 0.2755, "lr": 9.771228098856534e-07, "epoch": 4.550607287449393, "percentage": 91.01, "elapsed_time": "6:08:35", "remaining_time": "0:36:24"}
1125
+ {"current_steps": 1125, "total_steps": 1235, "loss": 0.2836, "lr": 9.597378493454013e-07, "epoch": 4.554655870445345, "percentage": 91.09, "elapsed_time": "6:08:54", "remaining_time": "0:36:04"}
1126
+ {"current_steps": 1126, "total_steps": 1235, "loss": 0.2548, "lr": 9.425051342339353e-07, "epoch": 4.558704453441296, "percentage": 91.17, "elapsed_time": "6:09:15", "remaining_time": "0:35:44"}
1127
+ {"current_steps": 1127, "total_steps": 1235, "loss": 0.251, "lr": 9.254248023435864e-07, "epoch": 4.562753036437247, "percentage": 91.26, "elapsed_time": "6:09:30", "remaining_time": "0:35:24"}
1128
+ {"current_steps": 1128, "total_steps": 1235, "loss": 0.2536, "lr": 9.084969902482288e-07, "epoch": 4.566801619433198, "percentage": 91.34, "elapsed_time": "6:09:51", "remaining_time": "0:35:05"}
1129
+ {"current_steps": 1129, "total_steps": 1235, "loss": 0.2576, "lr": 8.917218333021993e-07, "epoch": 4.57085020242915, "percentage": 91.42, "elapsed_time": "6:10:11", "remaining_time": "0:34:45"}
1130
+ {"current_steps": 1130, "total_steps": 1235, "loss": 0.2576, "lr": 8.750994656392109e-07, "epoch": 4.574898785425101, "percentage": 91.5, "elapsed_time": "6:10:34", "remaining_time": "0:34:26"}
1131
+ {"current_steps": 1131, "total_steps": 1235, "loss": 0.2529, "lr": 8.58630020171265e-07, "epoch": 4.578947368421053, "percentage": 91.58, "elapsed_time": "6:10:52", "remaining_time": "0:34:06"}
1132
+ {"current_steps": 1132, "total_steps": 1235, "loss": 0.2635, "lr": 8.423136285876099e-07, "epoch": 4.582995951417004, "percentage": 91.66, "elapsed_time": "6:11:12", "remaining_time": "0:33:46"}
1133
+ {"current_steps": 1133, "total_steps": 1235, "loss": 0.2528, "lr": 8.26150421353682e-07, "epoch": 4.587044534412955, "percentage": 91.74, "elapsed_time": "6:11:30", "remaining_time": "0:33:26"}
1134
+ {"current_steps": 1134, "total_steps": 1235, "loss": 0.2546, "lr": 8.101405277100549e-07, "epoch": 4.5910931174089065, "percentage": 91.82, "elapsed_time": "6:11:48", "remaining_time": "0:33:06"}
1135
+ {"current_steps": 1135, "total_steps": 1235, "loss": 0.2656, "lr": 7.942840756714077e-07, "epoch": 4.5951417004048585, "percentage": 91.9, "elapsed_time": "6:12:06", "remaining_time": "0:32:47"}
1136
+ {"current_steps": 1136, "total_steps": 1235, "loss": 0.2659, "lr": 7.785811920255093e-07, "epoch": 4.59919028340081, "percentage": 91.98, "elapsed_time": "6:12:24", "remaining_time": "0:32:27"}
1137
+ {"current_steps": 1137, "total_steps": 1235, "loss": 0.267, "lr": 7.630320023322024e-07, "epoch": 4.603238866396762, "percentage": 92.06, "elapsed_time": "6:12:43", "remaining_time": "0:32:07"}
1138
+ {"current_steps": 1138, "total_steps": 1235, "loss": 0.2783, "lr": 7.476366309223903e-07, "epoch": 4.607287449392713, "percentage": 92.15, "elapsed_time": "6:13:01", "remaining_time": "0:31:47"}
1139
+ {"current_steps": 1139, "total_steps": 1235, "loss": 0.2679, "lr": 7.323952008970537e-07, "epoch": 4.611336032388664, "percentage": 92.23, "elapsed_time": "6:13:21", "remaining_time": "0:31:28"}
1140
+ {"current_steps": 1140, "total_steps": 1235, "loss": 0.2555, "lr": 7.173078341262618e-07, "epoch": 4.615384615384615, "percentage": 92.31, "elapsed_time": "6:13:38", "remaining_time": "0:31:08"}
1141
+ {"current_steps": 1141, "total_steps": 1235, "loss": 0.2531, "lr": 7.023746512481989e-07, "epoch": 4.619433198380567, "percentage": 92.39, "elapsed_time": "6:14:00", "remaining_time": "0:30:48"}
1142
+ {"current_steps": 1142, "total_steps": 1235, "loss": 0.2594, "lr": 6.875957716681902e-07, "epoch": 4.623481781376518, "percentage": 92.47, "elapsed_time": "6:14:17", "remaining_time": "0:30:28"}
1143
+ {"current_steps": 1143, "total_steps": 1235, "loss": 0.2621, "lr": 6.729713135577687e-07, "epoch": 4.62753036437247, "percentage": 92.55, "elapsed_time": "6:14:38", "remaining_time": "0:30:09"}
1144
+ {"current_steps": 1144, "total_steps": 1235, "loss": 0.2624, "lr": 6.585013938537143e-07, "epoch": 4.631578947368421, "percentage": 92.63, "elapsed_time": "6:14:59", "remaining_time": "0:29:49"}
1145
+ {"current_steps": 1145, "total_steps": 1235, "loss": 0.2501, "lr": 6.441861282571115e-07, "epoch": 4.635627530364372, "percentage": 92.71, "elapsed_time": "6:15:15", "remaining_time": "0:29:29"}
1146
+ {"current_steps": 1146, "total_steps": 1235, "loss": 0.2703, "lr": 6.300256312324471e-07, "epoch": 4.6396761133603235, "percentage": 92.79, "elapsed_time": "6:15:40", "remaining_time": "0:29:10"}
1147
+ {"current_steps": 1147, "total_steps": 1235, "loss": 0.2653, "lr": 6.160200160066776e-07, "epoch": 4.6437246963562755, "percentage": 92.87, "elapsed_time": "6:15:59", "remaining_time": "0:28:50"}
1148
+ {"current_steps": 1148, "total_steps": 1235, "loss": 0.2427, "lr": 6.021693945683327e-07, "epoch": 4.647773279352227, "percentage": 92.96, "elapsed_time": "6:16:16", "remaining_time": "0:28:30"}
1149
+ {"current_steps": 1149, "total_steps": 1235, "loss": 0.2716, "lr": 5.884738776666044e-07, "epoch": 4.651821862348179, "percentage": 93.04, "elapsed_time": "6:16:36", "remaining_time": "0:28:11"}
1150
+ {"current_steps": 1150, "total_steps": 1235, "loss": 0.2655, "lr": 5.749335748104878e-07, "epoch": 4.65587044534413, "percentage": 93.12, "elapsed_time": "6:16:54", "remaining_time": "0:27:51"}
1151
+ {"current_steps": 1151, "total_steps": 1235, "loss": 0.2518, "lr": 5.615485942678778e-07, "epoch": 4.659919028340081, "percentage": 93.2, "elapsed_time": "6:17:13", "remaining_time": "0:27:31"}
1152
+ {"current_steps": 1152, "total_steps": 1235, "loss": 0.27, "lr": 5.483190430647289e-07, "epoch": 4.663967611336032, "percentage": 93.28, "elapsed_time": "6:17:33", "remaining_time": "0:27:12"}
1153
+ {"current_steps": 1153, "total_steps": 1235, "loss": 0.2789, "lr": 5.352450269841747e-07, "epoch": 4.668016194331984, "percentage": 93.36, "elapsed_time": "6:17:55", "remaining_time": "0:26:52"}
1154
+ {"current_steps": 1154, "total_steps": 1235, "loss": 0.2476, "lr": 5.22326650565701e-07, "epoch": 4.672064777327935, "percentage": 93.44, "elapsed_time": "6:18:13", "remaining_time": "0:26:32"}
1155
+ {"current_steps": 1155, "total_steps": 1235, "loss": 0.2703, "lr": 5.095640171043048e-07, "epoch": 4.676113360323887, "percentage": 93.52, "elapsed_time": "6:18:34", "remaining_time": "0:26:13"}
1156
+ {"current_steps": 1156, "total_steps": 1235, "loss": 0.2532, "lr": 4.969572286496594e-07, "epoch": 4.680161943319838, "percentage": 93.6, "elapsed_time": "6:18:51", "remaining_time": "0:25:53"}
1157
+ {"current_steps": 1157, "total_steps": 1235, "loss": 0.2858, "lr": 4.845063860053079e-07, "epoch": 4.684210526315789, "percentage": 93.68, "elapsed_time": "6:19:11", "remaining_time": "0:25:33"}
1158
+ {"current_steps": 1158, "total_steps": 1235, "loss": 0.263, "lr": 4.7221158872785997e-07, "epoch": 4.6882591093117405, "percentage": 93.77, "elapsed_time": "6:19:29", "remaining_time": "0:25:14"}
1159
+ {"current_steps": 1159, "total_steps": 1235, "loss": 0.258, "lr": 4.600729351261857e-07, "epoch": 4.6923076923076925, "percentage": 93.85, "elapsed_time": "6:19:47", "remaining_time": "0:24:54"}
1160
+ {"current_steps": 1160, "total_steps": 1235, "loss": 0.2645, "lr": 4.4809052226063355e-07, "epoch": 4.696356275303644, "percentage": 93.93, "elapsed_time": "6:20:05", "remaining_time": "0:24:34"}
1161
+ {"current_steps": 1161, "total_steps": 1235, "loss": 0.257, "lr": 4.3626444594226046e-07, "epoch": 4.700404858299595, "percentage": 94.01, "elapsed_time": "6:20:22", "remaining_time": "0:24:14"}
1162
+ {"current_steps": 1162, "total_steps": 1235, "loss": 0.2522, "lr": 4.245948007320588e-07, "epoch": 4.704453441295547, "percentage": 94.09, "elapsed_time": "6:20:40", "remaining_time": "0:23:54"}
1163
+ {"current_steps": 1163, "total_steps": 1235, "loss": 0.2686, "lr": 4.130816799401971e-07, "epoch": 4.708502024291498, "percentage": 94.17, "elapsed_time": "6:21:00", "remaining_time": "0:23:35"}
1164
+ {"current_steps": 1164, "total_steps": 1235, "loss": 0.2498, "lr": 4.017251756252827e-07, "epoch": 4.712550607287449, "percentage": 94.25, "elapsed_time": "6:21:19", "remaining_time": "0:23:15"}
1165
+ {"current_steps": 1165, "total_steps": 1235, "loss": 0.2781, "lr": 3.9052537859362473e-07, "epoch": 4.716599190283401, "percentage": 94.33, "elapsed_time": "6:21:40", "remaining_time": "0:22:55"}
1166
+ {"current_steps": 1166, "total_steps": 1235, "loss": 0.2602, "lr": 3.7948237839849687e-07, "epoch": 4.720647773279352, "percentage": 94.41, "elapsed_time": "6:21:59", "remaining_time": "0:22:36"}
1167
+ {"current_steps": 1167, "total_steps": 1235, "loss": 0.2669, "lr": 3.6859626333943797e-07, "epoch": 4.724696356275303, "percentage": 94.49, "elapsed_time": "6:22:20", "remaining_time": "0:22:16"}
1168
+ {"current_steps": 1168, "total_steps": 1235, "loss": 0.2653, "lr": 3.578671204615347e-07, "epoch": 4.728744939271255, "percentage": 94.57, "elapsed_time": "6:22:42", "remaining_time": "0:21:57"}
1169
+ {"current_steps": 1169, "total_steps": 1235, "loss": 0.2635, "lr": 3.472950355547267e-07, "epoch": 4.732793522267206, "percentage": 94.66, "elapsed_time": "6:23:04", "remaining_time": "0:21:37"}
1170
+ {"current_steps": 1170, "total_steps": 1235, "loss": 0.2644, "lr": 3.3688009315312244e-07, "epoch": 4.7368421052631575, "percentage": 94.74, "elapsed_time": "6:23:27", "remaining_time": "0:21:18"}
1171
+ {"current_steps": 1171, "total_steps": 1235, "loss": 0.2532, "lr": 3.266223765343224e-07, "epoch": 4.7408906882591095, "percentage": 94.82, "elapsed_time": "6:23:48", "remaining_time": "0:20:58"}
1172
+ {"current_steps": 1172, "total_steps": 1235, "loss": 0.2701, "lr": 3.16521967718757e-07, "epoch": 4.744939271255061, "percentage": 94.9, "elapsed_time": "6:24:09", "remaining_time": "0:20:38"}
1173
+ {"current_steps": 1173, "total_steps": 1235, "loss": 0.2724, "lr": 3.0657894746902726e-07, "epoch": 4.748987854251012, "percentage": 94.98, "elapsed_time": "6:24:30", "remaining_time": "0:20:19"}
1174
+ {"current_steps": 1174, "total_steps": 1235, "loss": 0.2462, "lr": 2.9679339528925654e-07, "epoch": 4.753036437246964, "percentage": 95.06, "elapsed_time": "6:24:47", "remaining_time": "0:19:59"}
1175
+ {"current_steps": 1175, "total_steps": 1235, "loss": 0.2468, "lr": 2.871653894244597e-07, "epoch": 4.757085020242915, "percentage": 95.14, "elapsed_time": "6:25:07", "remaining_time": "0:19:39"}
1176
+ {"current_steps": 1176, "total_steps": 1235, "loss": 0.2656, "lr": 2.7769500685991266e-07, "epoch": 4.761133603238866, "percentage": 95.22, "elapsed_time": "6:25:28", "remaining_time": "0:19:20"}
1177
+ {"current_steps": 1177, "total_steps": 1235, "loss": 0.2578, "lr": 2.683823233205485e-07, "epoch": 4.765182186234818, "percentage": 95.3, "elapsed_time": "6:25:47", "remaining_time": "0:19:00"}
1178
+ {"current_steps": 1178, "total_steps": 1235, "loss": 0.264, "lr": 2.592274132703287e-07, "epoch": 4.769230769230769, "percentage": 95.38, "elapsed_time": "6:26:05", "remaining_time": "0:18:40"}
1179
+ {"current_steps": 1179, "total_steps": 1235, "loss": 0.2571, "lr": 2.502303499116754e-07, "epoch": 4.77327935222672, "percentage": 95.47, "elapsed_time": "6:26:28", "remaining_time": "0:18:21"}
1180
+ {"current_steps": 1180, "total_steps": 1235, "loss": 0.2628, "lr": 2.413912051848666e-07, "epoch": 4.777327935222672, "percentage": 95.55, "elapsed_time": "6:26:44", "remaining_time": "0:18:01"}
1181
+ {"current_steps": 1181, "total_steps": 1235, "loss": 0.2556, "lr": 2.3271004976746613e-07, "epoch": 4.781376518218623, "percentage": 95.63, "elapsed_time": "6:27:03", "remaining_time": "0:17:41"}
1182
+ {"current_steps": 1182, "total_steps": 1235, "loss": 0.2584, "lr": 2.2418695307376393e-07, "epoch": 4.7854251012145745, "percentage": 95.71, "elapsed_time": "6:27:21", "remaining_time": "0:17:22"}
1183
+ {"current_steps": 1183, "total_steps": 1235, "loss": 0.2709, "lr": 2.1582198325420968e-07, "epoch": 4.7894736842105265, "percentage": 95.79, "elapsed_time": "6:27:40", "remaining_time": "0:17:02"}
1184
+ {"current_steps": 1184, "total_steps": 1235, "loss": 0.2767, "lr": 2.0761520719488447e-07, "epoch": 4.793522267206478, "percentage": 95.87, "elapsed_time": "6:28:02", "remaining_time": "0:16:42"}
1185
+ {"current_steps": 1185, "total_steps": 1235, "loss": 0.2807, "lr": 1.9956669051694798e-07, "epoch": 4.797570850202429, "percentage": 95.95, "elapsed_time": "6:28:23", "remaining_time": "0:16:23"}
1186
+ {"current_steps": 1186, "total_steps": 1235, "loss": 0.264, "lr": 1.916764975761254e-07, "epoch": 4.801619433198381, "percentage": 96.03, "elapsed_time": "6:28:43", "remaining_time": "0:16:03"}
1187
+ {"current_steps": 1187, "total_steps": 1235, "loss": 0.2488, "lr": 1.839446914621923e-07, "epoch": 4.805668016194332, "percentage": 96.11, "elapsed_time": "6:29:03", "remaining_time": "0:15:43"}
1188
+ {"current_steps": 1188, "total_steps": 1235, "loss": 0.2656, "lr": 1.7637133399845962e-07, "epoch": 4.809716599190283, "percentage": 96.19, "elapsed_time": "6:29:26", "remaining_time": "0:15:24"}
1189
+ {"current_steps": 1189, "total_steps": 1235, "loss": 0.2714, "lr": 1.6895648574129397e-07, "epoch": 4.813765182186235, "percentage": 96.28, "elapsed_time": "6:29:43", "remaining_time": "0:15:04"}
1190
+ {"current_steps": 1190, "total_steps": 1235, "loss": 0.264, "lr": 1.6170020597962465e-07, "epoch": 4.817813765182186, "percentage": 96.36, "elapsed_time": "6:30:03", "remaining_time": "0:14:45"}
1191
+ {"current_steps": 1191, "total_steps": 1235, "loss": 0.275, "lr": 1.5460255273447078e-07, "epoch": 4.821862348178137, "percentage": 96.44, "elapsed_time": "6:30:21", "remaining_time": "0:14:25"}
1192
+ {"current_steps": 1192, "total_steps": 1235, "loss": 0.2677, "lr": 1.4766358275847715e-07, "epoch": 4.825910931174089, "percentage": 96.52, "elapsed_time": "6:30:38", "remaining_time": "0:14:05"}
1193
+ {"current_steps": 1193, "total_steps": 1235, "loss": 0.2698, "lr": 1.4088335153546573e-07, "epoch": 4.82995951417004, "percentage": 96.6, "elapsed_time": "6:30:57", "remaining_time": "0:13:45"}
1194
+ {"current_steps": 1194, "total_steps": 1235, "loss": 0.2741, "lr": 1.3426191327998496e-07, "epoch": 4.834008097165992, "percentage": 96.68, "elapsed_time": "6:31:16", "remaining_time": "0:13:26"}
1195
+ {"current_steps": 1195, "total_steps": 1235, "loss": 0.2523, "lr": 1.277993209368744e-07, "epoch": 4.838056680161944, "percentage": 96.76, "elapsed_time": "6:31:37", "remaining_time": "0:13:06"}
1196
+ {"current_steps": 1196, "total_steps": 1235, "loss": 0.2902, "lr": 1.214956261808542e-07, "epoch": 4.842105263157895, "percentage": 96.84, "elapsed_time": "6:31:56", "remaining_time": "0:12:46"}
1197
+ {"current_steps": 1197, "total_steps": 1235, "loss": 0.2614, "lr": 1.1535087941609846e-07, "epoch": 4.846153846153846, "percentage": 96.92, "elapsed_time": "6:32:18", "remaining_time": "0:12:27"}
1198
+ {"current_steps": 1198, "total_steps": 1235, "loss": 0.283, "lr": 1.0936512977583802e-07, "epoch": 4.850202429149798, "percentage": 97.0, "elapsed_time": "6:32:41", "remaining_time": "0:12:07"}
1199
+ {"current_steps": 1199, "total_steps": 1235, "loss": 0.258, "lr": 1.0353842512196732e-07, "epoch": 4.854251012145749, "percentage": 97.09, "elapsed_time": "6:33:00", "remaining_time": "0:11:47"}
1200
+ {"current_steps": 1200, "total_steps": 1235, "loss": 0.2529, "lr": 9.787081204466253e-08, "epoch": 4.8582995951417, "percentage": 97.17, "elapsed_time": "6:33:19", "remaining_time": "0:11:28"}
1201
+ {"current_steps": 1201, "total_steps": 1235, "loss": 0.2578, "lr": 9.236233586200627e-08, "epoch": 4.862348178137652, "percentage": 97.25, "elapsed_time": "6:33:38", "remaining_time": "0:11:08"}
1202
+ {"current_steps": 1202, "total_steps": 1235, "loss": 0.249, "lr": 8.70130406196279e-08, "epoch": 4.866396761133603, "percentage": 97.33, "elapsed_time": "6:33:59", "remaining_time": "0:10:49"}
1203
+ {"current_steps": 1203, "total_steps": 1235, "loss": 0.2855, "lr": 8.182296909035047e-08, "epoch": 4.870445344129554, "percentage": 97.41, "elapsed_time": "6:34:20", "remaining_time": "0:10:29"}
1204
+ {"current_steps": 1204, "total_steps": 1235, "loss": 0.2584, "lr": 7.679216277384439e-08, "epoch": 4.874493927125506, "percentage": 97.49, "elapsed_time": "6:34:37", "remaining_time": "0:10:09"}
1205
+ {"current_steps": 1205, "total_steps": 1235, "loss": 0.2682, "lr": 7.19206618963053e-08, "epoch": 4.8785425101214575, "percentage": 97.57, "elapsed_time": "6:34:56", "remaining_time": "0:09:49"}
1206
+ {"current_steps": 1206, "total_steps": 1235, "loss": 0.2702, "lr": 6.720850541012347e-08, "epoch": 4.882591093117409, "percentage": 97.65, "elapsed_time": "6:35:11", "remaining_time": "0:09:30"}
1207
+ {"current_steps": 1207, "total_steps": 1235, "loss": 0.2664, "lr": 6.265573099357714e-08, "epoch": 4.886639676113361, "percentage": 97.73, "elapsed_time": "6:35:31", "remaining_time": "0:09:10"}
1208
+ {"current_steps": 1208, "total_steps": 1235, "loss": 0.2632, "lr": 5.826237505053067e-08, "epoch": 4.890688259109312, "percentage": 97.81, "elapsed_time": "6:35:52", "remaining_time": "0:08:50"}
1209
+ {"current_steps": 1209, "total_steps": 1235, "loss": 0.2635, "lr": 5.4028472710137e-08, "epoch": 4.894736842105263, "percentage": 97.89, "elapsed_time": "6:36:11", "remaining_time": "0:08:31"}
1210
+ {"current_steps": 1210, "total_steps": 1235, "loss": 0.275, "lr": 4.9954057826571146e-08, "epoch": 4.898785425101215, "percentage": 97.98, "elapsed_time": "6:36:32", "remaining_time": "0:08:11"}
1211
+ {"current_steps": 1211, "total_steps": 1235, "loss": 0.2602, "lr": 4.6039162978743776e-08, "epoch": 4.902834008097166, "percentage": 98.06, "elapsed_time": "6:36:49", "remaining_time": "0:07:51"}
1212
+ {"current_steps": 1212, "total_steps": 1235, "loss": 0.2626, "lr": 4.228381947004812e-08, "epoch": 4.906882591093117, "percentage": 98.14, "elapsed_time": "6:37:10", "remaining_time": "0:07:32"}
1213
+ {"current_steps": 1213, "total_steps": 1235, "loss": 0.2668, "lr": 3.868805732811343e-08, "epoch": 4.910931174089069, "percentage": 98.22, "elapsed_time": "6:37:31", "remaining_time": "0:07:12"}
1214
+ {"current_steps": 1214, "total_steps": 1235, "loss": 0.2646, "lr": 3.525190530455636e-08, "epoch": 4.91497975708502, "percentage": 98.3, "elapsed_time": "6:37:48", "remaining_time": "0:06:52"}
1215
+ {"current_steps": 1215, "total_steps": 1235, "loss": 0.2616, "lr": 3.197539087475887e-08, "epoch": 4.919028340080971, "percentage": 98.38, "elapsed_time": "6:38:07", "remaining_time": "0:06:33"}
1216
+ {"current_steps": 1216, "total_steps": 1235, "loss": 0.2547, "lr": 2.8858540237641786e-08, "epoch": 4.923076923076923, "percentage": 98.46, "elapsed_time": "6:38:24", "remaining_time": "0:06:13"}
1217
+ {"current_steps": 1217, "total_steps": 1235, "loss": 0.2665, "lr": 2.5901378315458247e-08, "epoch": 4.9271255060728745, "percentage": 98.54, "elapsed_time": "6:38:45", "remaining_time": "0:05:53"}
1218
+ {"current_steps": 1218, "total_steps": 1235, "loss": 0.2731, "lr": 2.3103928753598347e-08, "epoch": 4.931174089068826, "percentage": 98.62, "elapsed_time": "6:39:06", "remaining_time": "0:05:34"}
1219
+ {"current_steps": 1219, "total_steps": 1235, "loss": 0.245, "lr": 2.0466213920393718e-08, "epoch": 4.935222672064778, "percentage": 98.7, "elapsed_time": "6:39:18", "remaining_time": "0:05:14"}
1220
+ {"current_steps": 1220, "total_steps": 1235, "loss": 0.2584, "lr": 1.7988254906942115e-08, "epoch": 4.939271255060729, "percentage": 98.79, "elapsed_time": "6:39:40", "remaining_time": "0:04:54"}
1221
+ {"current_steps": 1221, "total_steps": 1235, "loss": 0.2686, "lr": 1.5670071526936447e-08, "epoch": 4.94331983805668, "percentage": 98.87, "elapsed_time": "6:40:00", "remaining_time": "0:04:35"}
1222
+ {"current_steps": 1222, "total_steps": 1235, "loss": 0.2781, "lr": 1.3511682316509344e-08, "epoch": 4.947368421052632, "percentage": 98.95, "elapsed_time": "6:40:19", "remaining_time": "0:04:15"}
1223
+ {"current_steps": 1223, "total_steps": 1235, "loss": 0.2511, "lr": 1.1513104534086605e-08, "epoch": 4.951417004048583, "percentage": 99.03, "elapsed_time": "6:40:36", "remaining_time": "0:03:55"}
1224
+ {"current_steps": 1224, "total_steps": 1235, "loss": 0.2638, "lr": 9.67435416023843e-09, "epoch": 4.955465587044534, "percentage": 99.11, "elapsed_time": "6:40:58", "remaining_time": "0:03:36"}
1225
+ {"current_steps": 1225, "total_steps": 1235, "loss": 0.2607, "lr": 7.995445897566178e-09, "epoch": 4.959514170040486, "percentage": 99.19, "elapsed_time": "6:41:14", "remaining_time": "0:03:16"}
1226
+ {"current_steps": 1226, "total_steps": 1235, "loss": 0.2625, "lr": 6.476393170578021e-09, "epoch": 4.963562753036437, "percentage": 99.27, "elapsed_time": "6:41:33", "remaining_time": "0:02:56"}
1227
+ {"current_steps": 1227, "total_steps": 1235, "loss": 0.2468, "lr": 5.11720812557348e-09, "epoch": 4.967611336032388, "percentage": 99.35, "elapsed_time": "6:41:51", "remaining_time": "0:02:37"}
1228
+ {"current_steps": 1228, "total_steps": 1235, "loss": 0.2557, "lr": 3.917901630563492e-09, "epoch": 4.97165991902834, "percentage": 99.43, "elapsed_time": "6:42:13", "remaining_time": "0:02:17"}
1229
+ {"current_steps": 1229, "total_steps": 1235, "loss": 0.2547, "lr": 2.878483275170485e-09, "epoch": 4.9757085020242915, "percentage": 99.51, "elapsed_time": "6:42:30", "remaining_time": "0:01:57"}
1230
+ {"current_steps": 1230, "total_steps": 1235, "loss": 0.2629, "lr": 1.998961370555108e-09, "epoch": 4.979757085020243, "percentage": 99.6, "elapsed_time": "6:42:53", "remaining_time": "0:01:38"}
1231
+ {"current_steps": 1231, "total_steps": 1235, "loss": 0.2706, "lr": 1.2793429493518361e-09, "epoch": 4.983805668016195, "percentage": 99.68, "elapsed_time": "6:43:10", "remaining_time": "0:01:18"}
1232
+ {"current_steps": 1232, "total_steps": 1235, "loss": 0.2642, "lr": 7.196337656112384e-10, "epoch": 4.987854251012146, "percentage": 99.76, "elapsed_time": "6:43:25", "remaining_time": "0:00:58"}
1233
+ {"current_steps": 1233, "total_steps": 1235, "loss": 0.2614, "lr": 3.198382947511292e-10, "epoch": 4.991902834008097, "percentage": 99.84, "elapsed_time": "6:43:46", "remaining_time": "0:00:39"}
1234
+ {"current_steps": 1234, "total_steps": 1235, "loss": 0.2751, "lr": 7.995973352770137e-11, "epoch": 4.995951417004049, "percentage": 99.92, "elapsed_time": "6:44:08", "remaining_time": "0:00:19"}
1235
+ {"current_steps": 1235, "total_steps": 1235, "loss": 0.2679, "lr": 0.0, "epoch": 5.0, "percentage": 100.0, "elapsed_time": "6:44:29", "remaining_time": "0:00:00"}
1236
+ {"current_steps": 1235, "total_steps": 1235, "epoch": 5.0, "percentage": 100.0, "elapsed_time": "6:46:29", "remaining_time": "0:00:00"}