gsmyrnis commited on
Commit
8587d9c
·
verified ·
1 Parent(s): d470d40

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:f180fca6d5af36ba2037d0db719c81b8140ecb50a8f1f2fab378a87c6b55b0db
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d35ad075b7817be95ac4d2ccee1f5207353c5850bec45e39941221eb01fed45
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:08df64d66b76bf16f544126fd93d5c1643d93635fc15ae821f22732eb97499e2
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8511160fc40c1ab1351d0f5ec390a25c5b7d0e40816c85942289262287f65a93
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:c91cccac3c820a489ea3d392f9aed3e761a8e98af53184d62986165e58010d98
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b18f6612a610a4fd918529cb4e6c01e735896d9282c4666474bfec193db7e0d4
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:36ef495d81430ae46aa17fed6c465f6791611a902ac9bff737f275cc2ce0477d
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3eb8d64d2528fb11089e5adfb24fcded065a30fce416c32d371a28f9628c0130
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -1001,3 +1001,236 @@
1001
  {"current_steps": 1001, "total_steps": 1235, "loss": 0.2186, "lr": 4.22084697268323e-06, "epoch": 4.052631578947368, "percentage": 81.05, "elapsed_time": "3:03:34", "remaining_time": "0:42:54"}
1002
  {"current_steps": 1002, "total_steps": 1235, "loss": 0.2373, "lr": 4.186160437003535e-06, "epoch": 4.05668016194332, "percentage": 81.13, "elapsed_time": "3:03:44", "remaining_time": "0:42:43"}
1003
  {"current_steps": 1003, "total_steps": 1235, "loss": 0.2334, "lr": 4.151600348363582e-06, "epoch": 4.060728744939271, "percentage": 81.21, "elapsed_time": "3:03:53", "remaining_time": "0:42:32"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1001
  {"current_steps": 1001, "total_steps": 1235, "loss": 0.2186, "lr": 4.22084697268323e-06, "epoch": 4.052631578947368, "percentage": 81.05, "elapsed_time": "3:03:34", "remaining_time": "0:42:54"}
1002
  {"current_steps": 1002, "total_steps": 1235, "loss": 0.2373, "lr": 4.186160437003535e-06, "epoch": 4.05668016194332, "percentage": 81.13, "elapsed_time": "3:03:44", "remaining_time": "0:42:43"}
1003
  {"current_steps": 1003, "total_steps": 1235, "loss": 0.2334, "lr": 4.151600348363582e-06, "epoch": 4.060728744939271, "percentage": 81.21, "elapsed_time": "3:03:53", "remaining_time": "0:42:32"}
1004
+ {"current_steps": 1004, "total_steps": 1235, "loss": 0.229, "lr": 4.11716698310493e-06, "epoch": 4.064777327935222, "percentage": 81.3, "elapsed_time": "3:04:03", "remaining_time": "0:42:20"}
1005
+ {"current_steps": 1005, "total_steps": 1235, "loss": 0.2208, "lr": 4.082860616555848e-06, "epoch": 4.068825910931174, "percentage": 81.38, "elapsed_time": "3:04:14", "remaining_time": "0:42:09"}
1006
+ {"current_steps": 1006, "total_steps": 1235, "loss": 0.2219, "lr": 4.048681523029125e-06, "epoch": 4.0728744939271255, "percentage": 81.46, "elapsed_time": "3:04:27", "remaining_time": "0:41:59"}
1007
+ {"current_steps": 1007, "total_steps": 1235, "loss": 0.2167, "lr": 4.014629975819882e-06, "epoch": 4.076923076923077, "percentage": 81.54, "elapsed_time": "3:04:36", "remaining_time": "0:41:47"}
1008
+ {"current_steps": 1008, "total_steps": 1235, "loss": 0.2349, "lr": 3.9807062472033855e-06, "epoch": 4.080971659919029, "percentage": 81.62, "elapsed_time": "3:04:48", "remaining_time": "0:41:37"}
1009
+ {"current_steps": 1009, "total_steps": 1235, "loss": 0.2333, "lr": 3.94691060843287e-06, "epoch": 4.08502024291498, "percentage": 81.7, "elapsed_time": "3:05:03", "remaining_time": "0:41:26"}
1010
+ {"current_steps": 1010, "total_steps": 1235, "loss": 0.2435, "lr": 3.913243329737353e-06, "epoch": 4.089068825910931, "percentage": 81.78, "elapsed_time": "3:05:14", "remaining_time": "0:41:15"}
1011
+ {"current_steps": 1011, "total_steps": 1235, "loss": 0.2197, "lr": 3.879704680319503e-06, "epoch": 4.093117408906883, "percentage": 81.86, "elapsed_time": "3:05:24", "remaining_time": "0:41:04"}
1012
+ {"current_steps": 1012, "total_steps": 1235, "loss": 0.228, "lr": 3.846294928353471e-06, "epoch": 4.097165991902834, "percentage": 81.94, "elapsed_time": "3:05:34", "remaining_time": "0:40:53"}
1013
+ {"current_steps": 1013, "total_steps": 1235, "loss": 0.2277, "lr": 3.8130143409827345e-06, "epoch": 4.101214574898785, "percentage": 82.02, "elapsed_time": "3:05:44", "remaining_time": "0:40:42"}
1014
+ {"current_steps": 1014, "total_steps": 1235, "loss": 0.2349, "lr": 3.7798631843179887e-06, "epoch": 4.105263157894737, "percentage": 82.11, "elapsed_time": "3:05:55", "remaining_time": "0:40:31"}
1015
+ {"current_steps": 1015, "total_steps": 1235, "loss": 0.2273, "lr": 3.7468417234349973e-06, "epoch": 4.109311740890688, "percentage": 82.19, "elapsed_time": "3:06:04", "remaining_time": "0:40:19"}
1016
+ {"current_steps": 1016, "total_steps": 1235, "loss": 0.2383, "lr": 3.7139502223724823e-06, "epoch": 4.113360323886639, "percentage": 82.27, "elapsed_time": "3:06:13", "remaining_time": "0:40:08"}
1017
+ {"current_steps": 1017, "total_steps": 1235, "loss": 0.2293, "lr": 3.6811889441300095e-06, "epoch": 4.117408906882591, "percentage": 82.35, "elapsed_time": "3:06:25", "remaining_time": "0:39:57"}
1018
+ {"current_steps": 1018, "total_steps": 1235, "loss": 0.2225, "lr": 3.648558150665886e-06, "epoch": 4.1214574898785425, "percentage": 82.43, "elapsed_time": "3:06:35", "remaining_time": "0:39:46"}
1019
+ {"current_steps": 1019, "total_steps": 1235, "loss": 0.2332, "lr": 3.616058102895075e-06, "epoch": 4.125506072874494, "percentage": 82.51, "elapsed_time": "3:06:48", "remaining_time": "0:39:35"}
1020
+ {"current_steps": 1020, "total_steps": 1235, "loss": 0.2285, "lr": 3.583689060687079e-06, "epoch": 4.129554655870446, "percentage": 82.59, "elapsed_time": "3:06:58", "remaining_time": "0:39:24"}
1021
+ {"current_steps": 1021, "total_steps": 1235, "loss": 0.2248, "lr": 3.5514512828639023e-06, "epoch": 4.133603238866397, "percentage": 82.67, "elapsed_time": "3:07:10", "remaining_time": "0:39:13"}
1022
+ {"current_steps": 1022, "total_steps": 1235, "loss": 0.2217, "lr": 3.51934502719796e-06, "epoch": 4.137651821862348, "percentage": 82.75, "elapsed_time": "3:07:20", "remaining_time": "0:39:02"}
1023
+ {"current_steps": 1023, "total_steps": 1235, "loss": 0.2189, "lr": 3.4873705504100185e-06, "epoch": 4.1417004048583, "percentage": 82.83, "elapsed_time": "3:07:29", "remaining_time": "0:38:51"}
1024
+ {"current_steps": 1024, "total_steps": 1235, "loss": 0.2295, "lr": 3.4555281081671345e-06, "epoch": 4.145748987854251, "percentage": 82.91, "elapsed_time": "3:07:39", "remaining_time": "0:38:40"}
1025
+ {"current_steps": 1025, "total_steps": 1235, "loss": 0.2342, "lr": 3.4238179550806326e-06, "epoch": 4.149797570850202, "percentage": 83.0, "elapsed_time": "3:07:50", "remaining_time": "0:38:29"}
1026
+ {"current_steps": 1026, "total_steps": 1235, "loss": 0.2184, "lr": 3.3922403447040497e-06, "epoch": 4.153846153846154, "percentage": 83.08, "elapsed_time": "3:07:59", "remaining_time": "0:38:17"}
1027
+ {"current_steps": 1027, "total_steps": 1235, "loss": 0.2394, "lr": 3.3607955295311247e-06, "epoch": 4.157894736842105, "percentage": 83.16, "elapsed_time": "3:08:11", "remaining_time": "0:38:06"}
1028
+ {"current_steps": 1028, "total_steps": 1235, "loss": 0.2258, "lr": 3.32948376099375e-06, "epoch": 4.161943319838056, "percentage": 83.24, "elapsed_time": "3:08:24", "remaining_time": "0:37:56"}
1029
+ {"current_steps": 1029, "total_steps": 1235, "loss": 0.2042, "lr": 3.2983052894599976e-06, "epoch": 4.165991902834008, "percentage": 83.32, "elapsed_time": "3:08:35", "remaining_time": "0:37:45"}
1030
+ {"current_steps": 1030, "total_steps": 1235, "loss": 0.2328, "lr": 3.2672603642320945e-06, "epoch": 4.17004048582996, "percentage": 83.4, "elapsed_time": "3:08:47", "remaining_time": "0:37:34"}
1031
+ {"current_steps": 1031, "total_steps": 1235, "loss": 0.2112, "lr": 3.236349233544438e-06, "epoch": 4.174089068825911, "percentage": 83.48, "elapsed_time": "3:08:56", "remaining_time": "0:37:23"}
1032
+ {"current_steps": 1032, "total_steps": 1235, "loss": 0.2329, "lr": 3.205572144561604e-06, "epoch": 4.178137651821863, "percentage": 83.56, "elapsed_time": "3:09:06", "remaining_time": "0:37:12"}
1033
+ {"current_steps": 1033, "total_steps": 1235, "loss": 0.2272, "lr": 3.174929343376374e-06, "epoch": 4.182186234817814, "percentage": 83.64, "elapsed_time": "3:09:18", "remaining_time": "0:37:01"}
1034
+ {"current_steps": 1034, "total_steps": 1235, "loss": 0.2424, "lr": 3.1444210750077777e-06, "epoch": 4.186234817813765, "percentage": 83.72, "elapsed_time": "3:09:29", "remaining_time": "0:36:50"}
1035
+ {"current_steps": 1035, "total_steps": 1235, "loss": 0.2305, "lr": 3.1140475833991046e-06, "epoch": 4.190283400809717, "percentage": 83.81, "elapsed_time": "3:09:41", "remaining_time": "0:36:39"}
1036
+ {"current_steps": 1036, "total_steps": 1235, "loss": 0.2189, "lr": 3.0838091114159895e-06, "epoch": 4.194331983805668, "percentage": 83.89, "elapsed_time": "3:09:51", "remaining_time": "0:36:28"}
1037
+ {"current_steps": 1037, "total_steps": 1235, "loss": 0.2157, "lr": 3.0537059008444524e-06, "epoch": 4.198380566801619, "percentage": 83.97, "elapsed_time": "3:10:00", "remaining_time": "0:36:16"}
1038
+ {"current_steps": 1038, "total_steps": 1235, "loss": 0.2237, "lr": 3.0237381923889563e-06, "epoch": 4.202429149797571, "percentage": 84.05, "elapsed_time": "3:10:10", "remaining_time": "0:36:05"}
1039
+ {"current_steps": 1039, "total_steps": 1235, "loss": 0.2125, "lr": 2.9939062256704997e-06, "epoch": 4.206477732793522, "percentage": 84.13, "elapsed_time": "3:10:19", "remaining_time": "0:35:54"}
1040
+ {"current_steps": 1040, "total_steps": 1235, "loss": 0.2324, "lr": 2.964210239224696e-06, "epoch": 4.2105263157894735, "percentage": 84.21, "elapsed_time": "3:10:32", "remaining_time": "0:35:43"}
1041
+ {"current_steps": 1041, "total_steps": 1235, "loss": 0.2282, "lr": 2.934650470499869e-06, "epoch": 4.2145748987854255, "percentage": 84.29, "elapsed_time": "3:10:43", "remaining_time": "0:35:32"}
1042
+ {"current_steps": 1042, "total_steps": 1235, "loss": 0.2207, "lr": 2.905227155855128e-06, "epoch": 4.218623481781377, "percentage": 84.37, "elapsed_time": "3:10:54", "remaining_time": "0:35:21"}
1043
+ {"current_steps": 1043, "total_steps": 1235, "loss": 0.2197, "lr": 2.875940530558519e-06, "epoch": 4.222672064777328, "percentage": 84.45, "elapsed_time": "3:11:06", "remaining_time": "0:35:10"}
1044
+ {"current_steps": 1044, "total_steps": 1235, "loss": 0.2298, "lr": 2.8467908287851154e-06, "epoch": 4.22672064777328, "percentage": 84.53, "elapsed_time": "3:11:16", "remaining_time": "0:34:59"}
1045
+ {"current_steps": 1045, "total_steps": 1235, "loss": 0.2123, "lr": 2.8177782836151603e-06, "epoch": 4.230769230769231, "percentage": 84.62, "elapsed_time": "3:11:26", "remaining_time": "0:34:48"}
1046
+ {"current_steps": 1046, "total_steps": 1235, "loss": 0.2164, "lr": 2.7889031270321874e-06, "epoch": 4.234817813765182, "percentage": 84.7, "elapsed_time": "3:11:35", "remaining_time": "0:34:37"}
1047
+ {"current_steps": 1047, "total_steps": 1235, "loss": 0.2312, "lr": 2.760165589921184e-06, "epoch": 4.238866396761134, "percentage": 84.78, "elapsed_time": "3:11:47", "remaining_time": "0:34:26"}
1048
+ {"current_steps": 1048, "total_steps": 1235, "loss": 0.2083, "lr": 2.7315659020667305e-06, "epoch": 4.242914979757085, "percentage": 84.86, "elapsed_time": "3:11:57", "remaining_time": "0:34:15"}
1049
+ {"current_steps": 1049, "total_steps": 1235, "loss": 0.2347, "lr": 2.703104292151164e-06, "epoch": 4.246963562753036, "percentage": 84.94, "elapsed_time": "3:12:07", "remaining_time": "0:34:04"}
1050
+ {"current_steps": 1050, "total_steps": 1235, "loss": 0.2254, "lr": 2.6747809877527607e-06, "epoch": 4.251012145748988, "percentage": 85.02, "elapsed_time": "3:12:17", "remaining_time": "0:33:52"}
1051
+ {"current_steps": 1051, "total_steps": 1235, "loss": 0.225, "lr": 2.6465962153439082e-06, "epoch": 4.255060728744939, "percentage": 85.1, "elapsed_time": "3:12:26", "remaining_time": "0:33:41"}
1052
+ {"current_steps": 1052, "total_steps": 1235, "loss": 0.2317, "lr": 2.618550200289303e-06, "epoch": 4.2591093117408905, "percentage": 85.18, "elapsed_time": "3:12:39", "remaining_time": "0:33:30"}
1053
+ {"current_steps": 1053, "total_steps": 1235, "loss": 0.2359, "lr": 2.59064316684412e-06, "epoch": 4.2631578947368425, "percentage": 85.26, "elapsed_time": "3:12:49", "remaining_time": "0:33:19"}
1054
+ {"current_steps": 1054, "total_steps": 1235, "loss": 0.2174, "lr": 2.562875338152264e-06, "epoch": 4.267206477732794, "percentage": 85.34, "elapsed_time": "3:13:01", "remaining_time": "0:33:08"}
1055
+ {"current_steps": 1055, "total_steps": 1235, "loss": 0.2308, "lr": 2.5352469362445552e-06, "epoch": 4.271255060728745, "percentage": 85.43, "elapsed_time": "3:13:14", "remaining_time": "0:32:58"}
1056
+ {"current_steps": 1056, "total_steps": 1235, "loss": 0.2106, "lr": 2.5077581820369523e-06, "epoch": 4.275303643724697, "percentage": 85.51, "elapsed_time": "3:13:23", "remaining_time": "0:32:46"}
1057
+ {"current_steps": 1057, "total_steps": 1235, "loss": 0.217, "lr": 2.480409295328803e-06, "epoch": 4.279352226720648, "percentage": 85.59, "elapsed_time": "3:13:32", "remaining_time": "0:32:35"}
1058
+ {"current_steps": 1058, "total_steps": 1235, "loss": 0.2222, "lr": 2.45320049480108e-06, "epoch": 4.283400809716599, "percentage": 85.67, "elapsed_time": "3:13:44", "remaining_time": "0:32:24"}
1059
+ {"current_steps": 1059, "total_steps": 1235, "loss": 0.2334, "lr": 2.4261319980146293e-06, "epoch": 4.287449392712551, "percentage": 85.75, "elapsed_time": "3:13:58", "remaining_time": "0:32:14"}
1060
+ {"current_steps": 1060, "total_steps": 1235, "loss": 0.2424, "lr": 2.399204021408421e-06, "epoch": 4.291497975708502, "percentage": 85.83, "elapsed_time": "3:14:09", "remaining_time": "0:32:03"}
1061
+ {"current_steps": 1061, "total_steps": 1235, "loss": 0.2291, "lr": 2.3724167802978395e-06, "epoch": 4.295546558704453, "percentage": 85.91, "elapsed_time": "3:14:19", "remaining_time": "0:31:52"}
1062
+ {"current_steps": 1062, "total_steps": 1235, "loss": 0.2226, "lr": 2.3457704888729625e-06, "epoch": 4.299595141700405, "percentage": 85.99, "elapsed_time": "3:14:31", "remaining_time": "0:31:41"}
1063
+ {"current_steps": 1063, "total_steps": 1235, "loss": 0.2274, "lr": 2.3192653601968162e-06, "epoch": 4.303643724696356, "percentage": 86.07, "elapsed_time": "3:14:41", "remaining_time": "0:31:30"}
1064
+ {"current_steps": 1064, "total_steps": 1235, "loss": 0.2334, "lr": 2.2929016062037057e-06, "epoch": 4.3076923076923075, "percentage": 86.15, "elapsed_time": "3:14:51", "remaining_time": "0:31:19"}
1065
+ {"current_steps": 1065, "total_steps": 1235, "loss": 0.2161, "lr": 2.2666794376975055e-06, "epoch": 4.3117408906882595, "percentage": 86.23, "elapsed_time": "3:15:01", "remaining_time": "0:31:07"}
1066
+ {"current_steps": 1066, "total_steps": 1235, "loss": 0.2379, "lr": 2.24059906434998e-06, "epoch": 4.315789473684211, "percentage": 86.32, "elapsed_time": "3:15:16", "remaining_time": "0:30:57"}
1067
+ {"current_steps": 1067, "total_steps": 1235, "loss": 0.2331, "lr": 2.214660694699091e-06, "epoch": 4.319838056680162, "percentage": 86.4, "elapsed_time": "3:15:30", "remaining_time": "0:30:46"}
1068
+ {"current_steps": 1068, "total_steps": 1235, "loss": 0.2189, "lr": 2.188864536147355e-06, "epoch": 4.323886639676114, "percentage": 86.48, "elapsed_time": "3:15:39", "remaining_time": "0:30:35"}
1069
+ {"current_steps": 1069, "total_steps": 1235, "loss": 0.2384, "lr": 2.1632107949601757e-06, "epoch": 4.327935222672065, "percentage": 86.56, "elapsed_time": "3:15:49", "remaining_time": "0:30:24"}
1070
+ {"current_steps": 1070, "total_steps": 1235, "loss": 0.2272, "lr": 2.137699676264171e-06, "epoch": 4.331983805668016, "percentage": 86.64, "elapsed_time": "3:16:00", "remaining_time": "0:30:13"}
1071
+ {"current_steps": 1071, "total_steps": 1235, "loss": 0.2214, "lr": 2.1123313840455738e-06, "epoch": 4.336032388663968, "percentage": 86.72, "elapsed_time": "3:16:10", "remaining_time": "0:30:02"}
1072
+ {"current_steps": 1072, "total_steps": 1235, "loss": 0.2385, "lr": 2.08710612114857e-06, "epoch": 4.340080971659919, "percentage": 86.8, "elapsed_time": "3:16:22", "remaining_time": "0:29:51"}
1073
+ {"current_steps": 1073, "total_steps": 1235, "loss": 0.2348, "lr": 2.0620240892736953e-06, "epoch": 4.34412955465587, "percentage": 86.88, "elapsed_time": "3:16:32", "remaining_time": "0:29:40"}
1074
+ {"current_steps": 1074, "total_steps": 1235, "loss": 0.2281, "lr": 2.0370854889762e-06, "epoch": 4.348178137651822, "percentage": 86.96, "elapsed_time": "3:16:41", "remaining_time": "0:29:29"}
1075
+ {"current_steps": 1075, "total_steps": 1235, "loss": 0.2205, "lr": 2.0122905196644726e-06, "epoch": 4.352226720647773, "percentage": 87.04, "elapsed_time": "3:16:49", "remaining_time": "0:29:17"}
1076
+ {"current_steps": 1076, "total_steps": 1235, "loss": 0.2263, "lr": 1.987639379598427e-06, "epoch": 4.3562753036437245, "percentage": 87.13, "elapsed_time": "3:16:59", "remaining_time": "0:29:06"}
1077
+ {"current_steps": 1077, "total_steps": 1235, "loss": 0.2266, "lr": 1.963132265887919e-06, "epoch": 4.3603238866396765, "percentage": 87.21, "elapsed_time": "3:17:10", "remaining_time": "0:28:55"}
1078
+ {"current_steps": 1078, "total_steps": 1235, "loss": 0.2184, "lr": 1.9387693744911784e-06, "epoch": 4.364372469635628, "percentage": 87.29, "elapsed_time": "3:17:19", "remaining_time": "0:28:44"}
1079
+ {"current_steps": 1079, "total_steps": 1235, "loss": 0.2199, "lr": 1.9145509002132368e-06, "epoch": 4.368421052631579, "percentage": 87.37, "elapsed_time": "3:17:28", "remaining_time": "0:28:33"}
1080
+ {"current_steps": 1080, "total_steps": 1235, "loss": 0.2264, "lr": 1.8904770367043723e-06, "epoch": 4.372469635627531, "percentage": 87.45, "elapsed_time": "3:17:37", "remaining_time": "0:28:21"}
1081
+ {"current_steps": 1081, "total_steps": 1235, "loss": 0.2214, "lr": 1.8665479764585504e-06, "epoch": 4.376518218623482, "percentage": 87.53, "elapsed_time": "3:17:47", "remaining_time": "0:28:10"}
1082
+ {"current_steps": 1082, "total_steps": 1235, "loss": 0.2207, "lr": 1.8427639108118977e-06, "epoch": 4.380566801619433, "percentage": 87.61, "elapsed_time": "3:17:57", "remaining_time": "0:27:59"}
1083
+ {"current_steps": 1083, "total_steps": 1235, "loss": 0.2178, "lr": 1.8191250299411755e-06, "epoch": 4.384615384615385, "percentage": 87.69, "elapsed_time": "3:18:07", "remaining_time": "0:27:48"}
1084
+ {"current_steps": 1084, "total_steps": 1235, "loss": 0.2265, "lr": 1.7956315228622446e-06, "epoch": 4.388663967611336, "percentage": 87.77, "elapsed_time": "3:18:20", "remaining_time": "0:27:37"}
1085
+ {"current_steps": 1085, "total_steps": 1235, "loss": 0.2186, "lr": 1.7722835774285553e-06, "epoch": 4.392712550607287, "percentage": 87.85, "elapsed_time": "3:18:28", "remaining_time": "0:27:26"}
1086
+ {"current_steps": 1086, "total_steps": 1235, "loss": 0.2228, "lr": 1.7490813803296624e-06, "epoch": 4.396761133603239, "percentage": 87.94, "elapsed_time": "3:18:41", "remaining_time": "0:27:15"}
1087
+ {"current_steps": 1087, "total_steps": 1235, "loss": 0.2393, "lr": 1.726025117089718e-06, "epoch": 4.40080971659919, "percentage": 88.02, "elapsed_time": "3:18:51", "remaining_time": "0:27:04"}
1088
+ {"current_steps": 1088, "total_steps": 1235, "loss": 0.2171, "lr": 1.70311497206598e-06, "epoch": 4.4048582995951415, "percentage": 88.1, "elapsed_time": "3:19:02", "remaining_time": "0:26:53"}
1089
+ {"current_steps": 1089, "total_steps": 1235, "loss": 0.228, "lr": 1.6803511284473638e-06, "epoch": 4.4089068825910935, "percentage": 88.18, "elapsed_time": "3:19:13", "remaining_time": "0:26:42"}
1090
+ {"current_steps": 1090, "total_steps": 1235, "loss": 0.2297, "lr": 1.6577337682529538e-06, "epoch": 4.412955465587045, "percentage": 88.26, "elapsed_time": "3:19:21", "remaining_time": "0:26:31"}
1091
+ {"current_steps": 1091, "total_steps": 1235, "loss": 0.2363, "lr": 1.6352630723305617e-06, "epoch": 4.417004048582996, "percentage": 88.34, "elapsed_time": "3:19:33", "remaining_time": "0:26:20"}
1092
+ {"current_steps": 1092, "total_steps": 1235, "loss": 0.2196, "lr": 1.612939220355272e-06, "epoch": 4.421052631578947, "percentage": 88.42, "elapsed_time": "3:19:42", "remaining_time": "0:26:09"}
1093
+ {"current_steps": 1093, "total_steps": 1235, "loss": 0.2369, "lr": 1.5907623908280112e-06, "epoch": 4.425101214574899, "percentage": 88.5, "elapsed_time": "3:19:53", "remaining_time": "0:25:58"}
1094
+ {"current_steps": 1094, "total_steps": 1235, "loss": 0.2226, "lr": 1.568732761074121e-06, "epoch": 4.42914979757085, "percentage": 88.58, "elapsed_time": "3:20:04", "remaining_time": "0:25:47"}
1095
+ {"current_steps": 1095, "total_steps": 1235, "loss": 0.2453, "lr": 1.5468505072419237e-06, "epoch": 4.433198380566802, "percentage": 88.66, "elapsed_time": "3:20:15", "remaining_time": "0:25:36"}
1096
+ {"current_steps": 1096, "total_steps": 1235, "loss": 0.2252, "lr": 1.5251158043013448e-06, "epoch": 4.437246963562753, "percentage": 88.74, "elapsed_time": "3:20:26", "remaining_time": "0:25:25"}
1097
+ {"current_steps": 1097, "total_steps": 1235, "loss": 0.2435, "lr": 1.5035288260424885e-06, "epoch": 4.441295546558704, "percentage": 88.83, "elapsed_time": "3:20:37", "remaining_time": "0:25:14"}
1098
+ {"current_steps": 1098, "total_steps": 1235, "loss": 0.1979, "lr": 1.4820897450742623e-06, "epoch": 4.445344129554655, "percentage": 88.91, "elapsed_time": "3:20:47", "remaining_time": "0:25:03"}
1099
+ {"current_steps": 1099, "total_steps": 1235, "loss": 0.2245, "lr": 1.4607987328229767e-06, "epoch": 4.449392712550607, "percentage": 88.99, "elapsed_time": "3:20:59", "remaining_time": "0:24:52"}
1100
+ {"current_steps": 1100, "total_steps": 1235, "loss": 0.2133, "lr": 1.4396559595310056e-06, "epoch": 4.4534412955465585, "percentage": 89.07, "elapsed_time": "3:21:09", "remaining_time": "0:24:41"}
1101
+ {"current_steps": 1101, "total_steps": 1235, "loss": 0.2093, "lr": 1.4186615942553973e-06, "epoch": 4.4574898785425106, "percentage": 89.15, "elapsed_time": "3:21:19", "remaining_time": "0:24:30"}
1102
+ {"current_steps": 1102, "total_steps": 1235, "loss": 0.2175, "lr": 1.3978158048665424e-06, "epoch": 4.461538461538462, "percentage": 89.23, "elapsed_time": "3:21:29", "remaining_time": "0:24:19"}
1103
+ {"current_steps": 1103, "total_steps": 1235, "loss": 0.2167, "lr": 1.3771187580468115e-06, "epoch": 4.465587044534413, "percentage": 89.31, "elapsed_time": "3:21:40", "remaining_time": "0:24:08"}
1104
+ {"current_steps": 1104, "total_steps": 1235, "loss": 0.2273, "lr": 1.3565706192892392e-06, "epoch": 4.469635627530364, "percentage": 89.39, "elapsed_time": "3:21:50", "remaining_time": "0:23:57"}
1105
+ {"current_steps": 1105, "total_steps": 1235, "loss": 0.2249, "lr": 1.3361715528961993e-06, "epoch": 4.473684210526316, "percentage": 89.47, "elapsed_time": "3:22:03", "remaining_time": "0:23:46"}
1106
+ {"current_steps": 1106, "total_steps": 1235, "loss": 0.2257, "lr": 1.3159217219780817e-06, "epoch": 4.477732793522267, "percentage": 89.55, "elapsed_time": "3:22:13", "remaining_time": "0:23:35"}
1107
+ {"current_steps": 1107, "total_steps": 1235, "loss": 0.2396, "lr": 1.2958212884519949e-06, "epoch": 4.481781376518219, "percentage": 89.64, "elapsed_time": "3:22:23", "remaining_time": "0:23:24"}
1108
+ {"current_steps": 1108, "total_steps": 1235, "loss": 0.3214, "lr": 1.2758704130404675e-06, "epoch": 4.48582995951417, "percentage": 89.72, "elapsed_time": "3:22:31", "remaining_time": "0:23:12"}
1109
+ {"current_steps": 1109, "total_steps": 1235, "loss": 0.2381, "lr": 1.2560692552701738e-06, "epoch": 4.489878542510121, "percentage": 89.8, "elapsed_time": "3:22:40", "remaining_time": "0:23:01"}
1110
+ {"current_steps": 1110, "total_steps": 1235, "loss": 0.2189, "lr": 1.2364179734706382e-06, "epoch": 4.493927125506072, "percentage": 89.88, "elapsed_time": "3:22:51", "remaining_time": "0:22:50"}
1111
+ {"current_steps": 1111, "total_steps": 1235, "loss": 0.2262, "lr": 1.2169167247729852e-06, "epoch": 4.497975708502024, "percentage": 89.96, "elapsed_time": "3:23:01", "remaining_time": "0:22:39"}
1112
+ {"current_steps": 1112, "total_steps": 1235, "loss": 0.2121, "lr": 1.1975656651086864e-06, "epoch": 4.502024291497976, "percentage": 90.04, "elapsed_time": "3:23:09", "remaining_time": "0:22:28"}
1113
+ {"current_steps": 1113, "total_steps": 1235, "loss": 0.2299, "lr": 1.1783649492082926e-06, "epoch": 4.506072874493928, "percentage": 90.12, "elapsed_time": "3:23:21", "remaining_time": "0:22:17"}
1114
+ {"current_steps": 1114, "total_steps": 1235, "loss": 0.2201, "lr": 1.1593147306002183e-06, "epoch": 4.510121457489879, "percentage": 90.2, "elapsed_time": "3:23:32", "remaining_time": "0:22:06"}
1115
+ {"current_steps": 1115, "total_steps": 1235, "loss": 0.2417, "lr": 1.140415161609505e-06, "epoch": 4.51417004048583, "percentage": 90.28, "elapsed_time": "3:23:42", "remaining_time": "0:21:55"}
1116
+ {"current_steps": 1116, "total_steps": 1235, "loss": 0.2364, "lr": 1.121666393356604e-06, "epoch": 4.518218623481781, "percentage": 90.36, "elapsed_time": "3:23:54", "remaining_time": "0:21:44"}
1117
+ {"current_steps": 1117, "total_steps": 1235, "loss": 0.2226, "lr": 1.1030685757561632e-06, "epoch": 4.522267206477733, "percentage": 90.45, "elapsed_time": "3:24:05", "remaining_time": "0:21:33"}
1118
+ {"current_steps": 1118, "total_steps": 1235, "loss": 0.2328, "lr": 1.0846218575158373e-06, "epoch": 4.526315789473684, "percentage": 90.53, "elapsed_time": "3:24:15", "remaining_time": "0:21:22"}
1119
+ {"current_steps": 1119, "total_steps": 1235, "loss": 0.2249, "lr": 1.066326386135097e-06, "epoch": 4.530364372469636, "percentage": 90.61, "elapsed_time": "3:24:24", "remaining_time": "0:21:11"}
1120
+ {"current_steps": 1120, "total_steps": 1235, "loss": 0.2186, "lr": 1.0481823079040398e-06, "epoch": 4.534412955465587, "percentage": 90.69, "elapsed_time": "3:24:35", "remaining_time": "0:21:00"}
1121
+ {"current_steps": 1121, "total_steps": 1235, "loss": 0.2146, "lr": 1.0301897679022344e-06, "epoch": 4.538461538461538, "percentage": 90.77, "elapsed_time": "3:24:45", "remaining_time": "0:20:49"}
1122
+ {"current_steps": 1122, "total_steps": 1235, "loss": 0.2284, "lr": 1.0123489099975491e-06, "epoch": 4.5425101214574894, "percentage": 90.85, "elapsed_time": "3:24:55", "remaining_time": "0:20:38"}
1123
+ {"current_steps": 1123, "total_steps": 1235, "loss": 0.2257, "lr": 9.9465987684501e-07, "epoch": 4.5465587044534415, "percentage": 90.93, "elapsed_time": "3:25:06", "remaining_time": "0:20:27"}
1124
+ {"current_steps": 1124, "total_steps": 1235, "loss": 0.2287, "lr": 9.771228098856534e-07, "epoch": 4.550607287449393, "percentage": 91.01, "elapsed_time": "3:25:16", "remaining_time": "0:20:16"}
1125
+ {"current_steps": 1125, "total_steps": 1235, "loss": 0.2201, "lr": 9.597378493454013e-07, "epoch": 4.554655870445345, "percentage": 91.09, "elapsed_time": "3:25:26", "remaining_time": "0:20:05"}
1126
+ {"current_steps": 1126, "total_steps": 1235, "loss": 0.2381, "lr": 9.425051342339353e-07, "epoch": 4.558704453441296, "percentage": 91.17, "elapsed_time": "3:25:37", "remaining_time": "0:19:54"}
1127
+ {"current_steps": 1127, "total_steps": 1235, "loss": 0.2374, "lr": 9.254248023435864e-07, "epoch": 4.562753036437247, "percentage": 91.26, "elapsed_time": "3:25:49", "remaining_time": "0:19:43"}
1128
+ {"current_steps": 1128, "total_steps": 1235, "loss": 0.2192, "lr": 9.084969902482288e-07, "epoch": 4.566801619433198, "percentage": 91.34, "elapsed_time": "3:25:57", "remaining_time": "0:19:32"}
1129
+ {"current_steps": 1129, "total_steps": 1235, "loss": 0.2252, "lr": 8.917218333021993e-07, "epoch": 4.57085020242915, "percentage": 91.42, "elapsed_time": "3:26:07", "remaining_time": "0:19:21"}
1130
+ {"current_steps": 1130, "total_steps": 1235, "loss": 0.2135, "lr": 8.750994656392109e-07, "epoch": 4.574898785425101, "percentage": 91.5, "elapsed_time": "3:26:18", "remaining_time": "0:19:10"}
1131
+ {"current_steps": 1131, "total_steps": 1235, "loss": 0.2198, "lr": 8.58630020171265e-07, "epoch": 4.578947368421053, "percentage": 91.58, "elapsed_time": "3:26:29", "remaining_time": "0:18:59"}
1132
+ {"current_steps": 1132, "total_steps": 1235, "loss": 0.2313, "lr": 8.423136285876099e-07, "epoch": 4.582995951417004, "percentage": 91.66, "elapsed_time": "3:26:40", "remaining_time": "0:18:48"}
1133
+ {"current_steps": 1133, "total_steps": 1235, "loss": 0.2235, "lr": 8.26150421353682e-07, "epoch": 4.587044534412955, "percentage": 91.74, "elapsed_time": "3:26:49", "remaining_time": "0:18:37"}
1134
+ {"current_steps": 1134, "total_steps": 1235, "loss": 0.218, "lr": 8.101405277100549e-07, "epoch": 4.5910931174089065, "percentage": 91.82, "elapsed_time": "3:27:01", "remaining_time": "0:18:26"}
1135
+ {"current_steps": 1135, "total_steps": 1235, "loss": 0.2216, "lr": 7.942840756714077e-07, "epoch": 4.5951417004048585, "percentage": 91.9, "elapsed_time": "3:27:11", "remaining_time": "0:18:15"}
1136
+ {"current_steps": 1136, "total_steps": 1235, "loss": 0.2151, "lr": 7.785811920255093e-07, "epoch": 4.59919028340081, "percentage": 91.98, "elapsed_time": "3:27:22", "remaining_time": "0:18:04"}
1137
+ {"current_steps": 1137, "total_steps": 1235, "loss": 0.2253, "lr": 7.630320023322024e-07, "epoch": 4.603238866396762, "percentage": 92.06, "elapsed_time": "3:27:34", "remaining_time": "0:17:53"}
1138
+ {"current_steps": 1138, "total_steps": 1235, "loss": 0.2256, "lr": 7.476366309223903e-07, "epoch": 4.607287449392713, "percentage": 92.15, "elapsed_time": "3:27:44", "remaining_time": "0:17:42"}
1139
+ {"current_steps": 1139, "total_steps": 1235, "loss": 0.2149, "lr": 7.323952008970537e-07, "epoch": 4.611336032388664, "percentage": 92.23, "elapsed_time": "3:27:53", "remaining_time": "0:17:31"}
1140
+ {"current_steps": 1140, "total_steps": 1235, "loss": 0.2099, "lr": 7.173078341262618e-07, "epoch": 4.615384615384615, "percentage": 92.31, "elapsed_time": "3:28:03", "remaining_time": "0:17:20"}
1141
+ {"current_steps": 1141, "total_steps": 1235, "loss": 0.2349, "lr": 7.023746512481989e-07, "epoch": 4.619433198380567, "percentage": 92.39, "elapsed_time": "3:28:13", "remaining_time": "0:17:09"}
1142
+ {"current_steps": 1142, "total_steps": 1235, "loss": 0.2206, "lr": 6.875957716681902e-07, "epoch": 4.623481781376518, "percentage": 92.47, "elapsed_time": "3:28:22", "remaining_time": "0:16:58"}
1143
+ {"current_steps": 1143, "total_steps": 1235, "loss": 0.2194, "lr": 6.729713135577687e-07, "epoch": 4.62753036437247, "percentage": 92.55, "elapsed_time": "3:28:32", "remaining_time": "0:16:47"}
1144
+ {"current_steps": 1144, "total_steps": 1235, "loss": 0.2248, "lr": 6.585013938537143e-07, "epoch": 4.631578947368421, "percentage": 92.63, "elapsed_time": "3:28:44", "remaining_time": "0:16:36"}
1145
+ {"current_steps": 1145, "total_steps": 1235, "loss": 0.2314, "lr": 6.441861282571115e-07, "epoch": 4.635627530364372, "percentage": 92.71, "elapsed_time": "3:28:53", "remaining_time": "0:16:25"}
1146
+ {"current_steps": 1146, "total_steps": 1235, "loss": 0.2283, "lr": 6.300256312324471e-07, "epoch": 4.6396761133603235, "percentage": 92.79, "elapsed_time": "3:29:03", "remaining_time": "0:16:14"}
1147
+ {"current_steps": 1147, "total_steps": 1235, "loss": 0.2317, "lr": 6.160200160066776e-07, "epoch": 4.6437246963562755, "percentage": 92.87, "elapsed_time": "3:29:14", "remaining_time": "0:16:03"}
1148
+ {"current_steps": 1148, "total_steps": 1235, "loss": 0.228, "lr": 6.021693945683327e-07, "epoch": 4.647773279352227, "percentage": 92.96, "elapsed_time": "3:29:23", "remaining_time": "0:15:52"}
1149
+ {"current_steps": 1149, "total_steps": 1235, "loss": 0.2167, "lr": 5.884738776666044e-07, "epoch": 4.651821862348179, "percentage": 93.04, "elapsed_time": "3:29:34", "remaining_time": "0:15:41"}
1150
+ {"current_steps": 1150, "total_steps": 1235, "loss": 0.2282, "lr": 5.749335748104878e-07, "epoch": 4.65587044534413, "percentage": 93.12, "elapsed_time": "3:29:47", "remaining_time": "0:15:30"}
1151
+ {"current_steps": 1151, "total_steps": 1235, "loss": 0.2181, "lr": 5.615485942678778e-07, "epoch": 4.659919028340081, "percentage": 93.2, "elapsed_time": "3:29:56", "remaining_time": "0:15:19"}
1152
+ {"current_steps": 1152, "total_steps": 1235, "loss": 0.2236, "lr": 5.483190430647289e-07, "epoch": 4.663967611336032, "percentage": 93.28, "elapsed_time": "3:30:05", "remaining_time": "0:15:08"}
1153
+ {"current_steps": 1153, "total_steps": 1235, "loss": 0.2157, "lr": 5.352450269841747e-07, "epoch": 4.668016194331984, "percentage": 93.36, "elapsed_time": "3:30:15", "remaining_time": "0:14:57"}
1154
+ {"current_steps": 1154, "total_steps": 1235, "loss": 0.2416, "lr": 5.22326650565701e-07, "epoch": 4.672064777327935, "percentage": 93.44, "elapsed_time": "3:30:29", "remaining_time": "0:14:46"}
1155
+ {"current_steps": 1155, "total_steps": 1235, "loss": 0.2345, "lr": 5.095640171043048e-07, "epoch": 4.676113360323887, "percentage": 93.52, "elapsed_time": "3:30:40", "remaining_time": "0:14:35"}
1156
+ {"current_steps": 1156, "total_steps": 1235, "loss": 0.2262, "lr": 4.969572286496594e-07, "epoch": 4.680161943319838, "percentage": 93.6, "elapsed_time": "3:30:50", "remaining_time": "0:14:24"}
1157
+ {"current_steps": 1157, "total_steps": 1235, "loss": 0.2022, "lr": 4.845063860053079e-07, "epoch": 4.684210526315789, "percentage": 93.68, "elapsed_time": "3:30:57", "remaining_time": "0:14:13"}
1158
+ {"current_steps": 1158, "total_steps": 1235, "loss": 0.2029, "lr": 4.7221158872785997e-07, "epoch": 4.6882591093117405, "percentage": 93.77, "elapsed_time": "3:31:06", "remaining_time": "0:14:02"}
1159
+ {"current_steps": 1159, "total_steps": 1235, "loss": 0.2237, "lr": 4.600729351261857e-07, "epoch": 4.6923076923076925, "percentage": 93.85, "elapsed_time": "3:31:16", "remaining_time": "0:13:51"}
1160
+ {"current_steps": 1160, "total_steps": 1235, "loss": 0.23, "lr": 4.4809052226063355e-07, "epoch": 4.696356275303644, "percentage": 93.93, "elapsed_time": "3:31:28", "remaining_time": "0:13:40"}
1161
+ {"current_steps": 1161, "total_steps": 1235, "loss": 0.2117, "lr": 4.3626444594226046e-07, "epoch": 4.700404858299595, "percentage": 94.01, "elapsed_time": "3:31:37", "remaining_time": "0:13:29"}
1162
+ {"current_steps": 1162, "total_steps": 1235, "loss": 0.1979, "lr": 4.245948007320588e-07, "epoch": 4.704453441295547, "percentage": 94.09, "elapsed_time": "3:31:47", "remaining_time": "0:13:18"}
1163
+ {"current_steps": 1163, "total_steps": 1235, "loss": 0.2384, "lr": 4.130816799401971e-07, "epoch": 4.708502024291498, "percentage": 94.17, "elapsed_time": "3:32:01", "remaining_time": "0:13:07"}
1164
+ {"current_steps": 1164, "total_steps": 1235, "loss": 0.2142, "lr": 4.017251756252827e-07, "epoch": 4.712550607287449, "percentage": 94.25, "elapsed_time": "3:32:14", "remaining_time": "0:12:56"}
1165
+ {"current_steps": 1165, "total_steps": 1235, "loss": 0.227, "lr": 3.9052537859362473e-07, "epoch": 4.716599190283401, "percentage": 94.33, "elapsed_time": "3:32:24", "remaining_time": "0:12:45"}
1166
+ {"current_steps": 1166, "total_steps": 1235, "loss": 0.2223, "lr": 3.7948237839849687e-07, "epoch": 4.720647773279352, "percentage": 94.41, "elapsed_time": "3:32:33", "remaining_time": "0:12:34"}
1167
+ {"current_steps": 1167, "total_steps": 1235, "loss": 0.2218, "lr": 3.6859626333943797e-07, "epoch": 4.724696356275303, "percentage": 94.49, "elapsed_time": "3:32:43", "remaining_time": "0:12:23"}
1168
+ {"current_steps": 1168, "total_steps": 1235, "loss": 0.2073, "lr": 3.578671204615347e-07, "epoch": 4.728744939271255, "percentage": 94.57, "elapsed_time": "3:32:54", "remaining_time": "0:12:12"}
1169
+ {"current_steps": 1169, "total_steps": 1235, "loss": 0.2282, "lr": 3.472950355547267e-07, "epoch": 4.732793522267206, "percentage": 94.66, "elapsed_time": "3:33:06", "remaining_time": "0:12:01"}
1170
+ {"current_steps": 1170, "total_steps": 1235, "loss": 0.2138, "lr": 3.3688009315312244e-07, "epoch": 4.7368421052631575, "percentage": 94.74, "elapsed_time": "3:33:18", "remaining_time": "0:11:51"}
1171
+ {"current_steps": 1171, "total_steps": 1235, "loss": 0.2216, "lr": 3.266223765343224e-07, "epoch": 4.7408906882591095, "percentage": 94.82, "elapsed_time": "3:33:29", "remaining_time": "0:11:40"}
1172
+ {"current_steps": 1172, "total_steps": 1235, "loss": 0.2106, "lr": 3.16521967718757e-07, "epoch": 4.744939271255061, "percentage": 94.9, "elapsed_time": "3:33:37", "remaining_time": "0:11:29"}
1173
+ {"current_steps": 1173, "total_steps": 1235, "loss": 0.237, "lr": 3.0657894746902726e-07, "epoch": 4.748987854251012, "percentage": 94.98, "elapsed_time": "3:33:48", "remaining_time": "0:11:18"}
1174
+ {"current_steps": 1174, "total_steps": 1235, "loss": 0.2157, "lr": 2.9679339528925654e-07, "epoch": 4.753036437246964, "percentage": 95.06, "elapsed_time": "3:33:58", "remaining_time": "0:11:07"}
1175
+ {"current_steps": 1175, "total_steps": 1235, "loss": 0.2297, "lr": 2.871653894244597e-07, "epoch": 4.757085020242915, "percentage": 95.14, "elapsed_time": "3:34:09", "remaining_time": "0:10:56"}
1176
+ {"current_steps": 1176, "total_steps": 1235, "loss": 0.2172, "lr": 2.7769500685991266e-07, "epoch": 4.761133603238866, "percentage": 95.22, "elapsed_time": "3:34:19", "remaining_time": "0:10:45"}
1177
+ {"current_steps": 1177, "total_steps": 1235, "loss": 0.2307, "lr": 2.683823233205485e-07, "epoch": 4.765182186234818, "percentage": 95.3, "elapsed_time": "3:34:33", "remaining_time": "0:10:34"}
1178
+ {"current_steps": 1178, "total_steps": 1235, "loss": 0.231, "lr": 2.592274132703287e-07, "epoch": 4.769230769230769, "percentage": 95.38, "elapsed_time": "3:34:43", "remaining_time": "0:10:23"}
1179
+ {"current_steps": 1179, "total_steps": 1235, "loss": 0.22, "lr": 2.502303499116754e-07, "epoch": 4.77327935222672, "percentage": 95.47, "elapsed_time": "3:34:53", "remaining_time": "0:10:12"}
1180
+ {"current_steps": 1180, "total_steps": 1235, "loss": 0.2218, "lr": 2.413912051848666e-07, "epoch": 4.777327935222672, "percentage": 95.55, "elapsed_time": "3:35:02", "remaining_time": "0:10:01"}
1181
+ {"current_steps": 1181, "total_steps": 1235, "loss": 0.2386, "lr": 2.3271004976746613e-07, "epoch": 4.781376518218623, "percentage": 95.63, "elapsed_time": "3:35:15", "remaining_time": "0:09:50"}
1182
+ {"current_steps": 1182, "total_steps": 1235, "loss": 0.2195, "lr": 2.2418695307376393e-07, "epoch": 4.7854251012145745, "percentage": 95.71, "elapsed_time": "3:35:24", "remaining_time": "0:09:39"}
1183
+ {"current_steps": 1183, "total_steps": 1235, "loss": 0.2168, "lr": 2.1582198325420968e-07, "epoch": 4.7894736842105265, "percentage": 95.79, "elapsed_time": "3:35:34", "remaining_time": "0:09:28"}
1184
+ {"current_steps": 1184, "total_steps": 1235, "loss": 0.2166, "lr": 2.0761520719488447e-07, "epoch": 4.793522267206478, "percentage": 95.87, "elapsed_time": "3:35:44", "remaining_time": "0:09:17"}
1185
+ {"current_steps": 1185, "total_steps": 1235, "loss": 0.2253, "lr": 1.9956669051694798e-07, "epoch": 4.797570850202429, "percentage": 95.95, "elapsed_time": "3:35:53", "remaining_time": "0:09:06"}
1186
+ {"current_steps": 1186, "total_steps": 1235, "loss": 0.2176, "lr": 1.916764975761254e-07, "epoch": 4.801619433198381, "percentage": 96.03, "elapsed_time": "3:36:03", "remaining_time": "0:08:55"}
1187
+ {"current_steps": 1187, "total_steps": 1235, "loss": 0.2281, "lr": 1.839446914621923e-07, "epoch": 4.805668016194332, "percentage": 96.11, "elapsed_time": "3:36:13", "remaining_time": "0:08:44"}
1188
+ {"current_steps": 1188, "total_steps": 1235, "loss": 0.2337, "lr": 1.7637133399845962e-07, "epoch": 4.809716599190283, "percentage": 96.19, "elapsed_time": "3:36:23", "remaining_time": "0:08:33"}
1189
+ {"current_steps": 1189, "total_steps": 1235, "loss": 0.2106, "lr": 1.6895648574129397e-07, "epoch": 4.813765182186235, "percentage": 96.28, "elapsed_time": "3:36:36", "remaining_time": "0:08:22"}
1190
+ {"current_steps": 1190, "total_steps": 1235, "loss": 0.2017, "lr": 1.6170020597962465e-07, "epoch": 4.817813765182186, "percentage": 96.36, "elapsed_time": "3:36:46", "remaining_time": "0:08:11"}
1191
+ {"current_steps": 1191, "total_steps": 1235, "loss": 0.2183, "lr": 1.5460255273447078e-07, "epoch": 4.821862348178137, "percentage": 96.44, "elapsed_time": "3:36:56", "remaining_time": "0:08:00"}
1192
+ {"current_steps": 1192, "total_steps": 1235, "loss": 0.2291, "lr": 1.4766358275847715e-07, "epoch": 4.825910931174089, "percentage": 96.52, "elapsed_time": "3:37:07", "remaining_time": "0:07:49"}
1193
+ {"current_steps": 1193, "total_steps": 1235, "loss": 0.2383, "lr": 1.4088335153546573e-07, "epoch": 4.82995951417004, "percentage": 96.6, "elapsed_time": "3:37:19", "remaining_time": "0:07:39"}
1194
+ {"current_steps": 1194, "total_steps": 1235, "loss": 0.2277, "lr": 1.3426191327998496e-07, "epoch": 4.834008097165992, "percentage": 96.68, "elapsed_time": "3:37:31", "remaining_time": "0:07:28"}
1195
+ {"current_steps": 1195, "total_steps": 1235, "loss": 0.2288, "lr": 1.277993209368744e-07, "epoch": 4.838056680161944, "percentage": 96.76, "elapsed_time": "3:37:41", "remaining_time": "0:07:17"}
1196
+ {"current_steps": 1196, "total_steps": 1235, "loss": 0.2307, "lr": 1.214956261808542e-07, "epoch": 4.842105263157895, "percentage": 96.84, "elapsed_time": "3:37:51", "remaining_time": "0:07:06"}
1197
+ {"current_steps": 1197, "total_steps": 1235, "loss": 0.2187, "lr": 1.1535087941609846e-07, "epoch": 4.846153846153846, "percentage": 96.92, "elapsed_time": "3:37:59", "remaining_time": "0:06:55"}
1198
+ {"current_steps": 1198, "total_steps": 1235, "loss": 0.2324, "lr": 1.0936512977583802e-07, "epoch": 4.850202429149798, "percentage": 97.0, "elapsed_time": "3:38:08", "remaining_time": "0:06:44"}
1199
+ {"current_steps": 1199, "total_steps": 1235, "loss": 0.2296, "lr": 1.0353842512196732e-07, "epoch": 4.854251012145749, "percentage": 97.09, "elapsed_time": "3:38:19", "remaining_time": "0:06:33"}
1200
+ {"current_steps": 1200, "total_steps": 1235, "loss": 0.2222, "lr": 9.787081204466253e-08, "epoch": 4.8582995951417, "percentage": 97.17, "elapsed_time": "3:38:30", "remaining_time": "0:06:22"}
1201
+ {"current_steps": 1201, "total_steps": 1235, "loss": 0.2225, "lr": 9.236233586200627e-08, "epoch": 4.862348178137652, "percentage": 97.25, "elapsed_time": "3:38:43", "remaining_time": "0:06:11"}
1202
+ {"current_steps": 1202, "total_steps": 1235, "loss": 0.226, "lr": 8.70130406196279e-08, "epoch": 4.866396761133603, "percentage": 97.33, "elapsed_time": "3:38:53", "remaining_time": "0:06:00"}
1203
+ {"current_steps": 1203, "total_steps": 1235, "loss": 0.2176, "lr": 8.182296909035047e-08, "epoch": 4.870445344129554, "percentage": 97.41, "elapsed_time": "3:39:05", "remaining_time": "0:05:49"}
1204
+ {"current_steps": 1204, "total_steps": 1235, "loss": 0.2315, "lr": 7.679216277384439e-08, "epoch": 4.874493927125506, "percentage": 97.49, "elapsed_time": "3:39:14", "remaining_time": "0:05:38"}
1205
+ {"current_steps": 1205, "total_steps": 1235, "loss": 0.2196, "lr": 7.19206618963053e-08, "epoch": 4.8785425101214575, "percentage": 97.57, "elapsed_time": "3:39:25", "remaining_time": "0:05:27"}
1206
+ {"current_steps": 1206, "total_steps": 1235, "loss": 0.2204, "lr": 6.720850541012347e-08, "epoch": 4.882591093117409, "percentage": 97.65, "elapsed_time": "3:39:34", "remaining_time": "0:05:16"}
1207
+ {"current_steps": 1207, "total_steps": 1235, "loss": 0.2419, "lr": 6.265573099357714e-08, "epoch": 4.886639676113361, "percentage": 97.73, "elapsed_time": "3:39:45", "remaining_time": "0:05:05"}
1208
+ {"current_steps": 1208, "total_steps": 1235, "loss": 0.2182, "lr": 5.826237505053067e-08, "epoch": 4.890688259109312, "percentage": 97.81, "elapsed_time": "3:39:59", "remaining_time": "0:04:55"}
1209
+ {"current_steps": 1209, "total_steps": 1235, "loss": 0.2235, "lr": 5.4028472710137e-08, "epoch": 4.894736842105263, "percentage": 97.89, "elapsed_time": "3:40:09", "remaining_time": "0:04:44"}
1210
+ {"current_steps": 1210, "total_steps": 1235, "loss": 0.23, "lr": 4.9954057826571146e-08, "epoch": 4.898785425101215, "percentage": 97.98, "elapsed_time": "3:40:20", "remaining_time": "0:04:33"}
1211
+ {"current_steps": 1211, "total_steps": 1235, "loss": 0.2228, "lr": 4.6039162978743776e-08, "epoch": 4.902834008097166, "percentage": 98.06, "elapsed_time": "3:40:30", "remaining_time": "0:04:22"}
1212
+ {"current_steps": 1212, "total_steps": 1235, "loss": 0.2178, "lr": 4.228381947004812e-08, "epoch": 4.906882591093117, "percentage": 98.14, "elapsed_time": "3:40:41", "remaining_time": "0:04:11"}
1213
+ {"current_steps": 1213, "total_steps": 1235, "loss": 0.2394, "lr": 3.868805732811343e-08, "epoch": 4.910931174089069, "percentage": 98.22, "elapsed_time": "3:40:55", "remaining_time": "0:04:00"}
1214
+ {"current_steps": 1214, "total_steps": 1235, "loss": 0.2291, "lr": 3.525190530455636e-08, "epoch": 4.91497975708502, "percentage": 98.3, "elapsed_time": "3:41:06", "remaining_time": "0:03:49"}
1215
+ {"current_steps": 1215, "total_steps": 1235, "loss": 0.2362, "lr": 3.197539087475887e-08, "epoch": 4.919028340080971, "percentage": 98.38, "elapsed_time": "3:41:15", "remaining_time": "0:03:38"}
1216
+ {"current_steps": 1216, "total_steps": 1235, "loss": 0.2292, "lr": 2.8858540237641786e-08, "epoch": 4.923076923076923, "percentage": 98.46, "elapsed_time": "3:41:30", "remaining_time": "0:03:27"}
1217
+ {"current_steps": 1217, "total_steps": 1235, "loss": 0.2286, "lr": 2.5901378315458247e-08, "epoch": 4.9271255060728745, "percentage": 98.54, "elapsed_time": "3:41:40", "remaining_time": "0:03:16"}
1218
+ {"current_steps": 1218, "total_steps": 1235, "loss": 0.2226, "lr": 2.3103928753598347e-08, "epoch": 4.931174089068826, "percentage": 98.62, "elapsed_time": "3:41:50", "remaining_time": "0:03:05"}
1219
+ {"current_steps": 1219, "total_steps": 1235, "loss": 0.2325, "lr": 2.0466213920393718e-08, "epoch": 4.935222672064778, "percentage": 98.7, "elapsed_time": "3:42:00", "remaining_time": "0:02:54"}
1220
+ {"current_steps": 1220, "total_steps": 1235, "loss": 0.2248, "lr": 1.7988254906942115e-08, "epoch": 4.939271255060729, "percentage": 98.79, "elapsed_time": "3:42:13", "remaining_time": "0:02:43"}
1221
+ {"current_steps": 1221, "total_steps": 1235, "loss": 0.2257, "lr": 1.5670071526936447e-08, "epoch": 4.94331983805668, "percentage": 98.87, "elapsed_time": "3:42:25", "remaining_time": "0:02:33"}
1222
+ {"current_steps": 1222, "total_steps": 1235, "loss": 0.2135, "lr": 1.3511682316509344e-08, "epoch": 4.947368421052632, "percentage": 98.95, "elapsed_time": "3:42:34", "remaining_time": "0:02:22"}
1223
+ {"current_steps": 1223, "total_steps": 1235, "loss": 0.2142, "lr": 1.1513104534086605e-08, "epoch": 4.951417004048583, "percentage": 99.03, "elapsed_time": "3:42:46", "remaining_time": "0:02:11"}
1224
+ {"current_steps": 1224, "total_steps": 1235, "loss": 0.217, "lr": 9.67435416023843e-09, "epoch": 4.955465587044534, "percentage": 99.11, "elapsed_time": "3:42:57", "remaining_time": "0:02:00"}
1225
+ {"current_steps": 1225, "total_steps": 1235, "loss": 0.2141, "lr": 7.995445897566178e-09, "epoch": 4.959514170040486, "percentage": 99.19, "elapsed_time": "3:43:06", "remaining_time": "0:01:49"}
1226
+ {"current_steps": 1226, "total_steps": 1235, "loss": 0.2427, "lr": 6.476393170578021e-09, "epoch": 4.963562753036437, "percentage": 99.27, "elapsed_time": "3:43:17", "remaining_time": "0:01:38"}
1227
+ {"current_steps": 1227, "total_steps": 1235, "loss": 0.2247, "lr": 5.11720812557348e-09, "epoch": 4.967611336032388, "percentage": 99.35, "elapsed_time": "3:43:28", "remaining_time": "0:01:27"}
1228
+ {"current_steps": 1228, "total_steps": 1235, "loss": 0.2207, "lr": 3.917901630563492e-09, "epoch": 4.97165991902834, "percentage": 99.43, "elapsed_time": "3:43:38", "remaining_time": "0:01:16"}
1229
+ {"current_steps": 1229, "total_steps": 1235, "loss": 0.2136, "lr": 2.878483275170485e-09, "epoch": 4.9757085020242915, "percentage": 99.51, "elapsed_time": "3:43:48", "remaining_time": "0:01:05"}
1230
+ {"current_steps": 1230, "total_steps": 1235, "loss": 0.2255, "lr": 1.998961370555108e-09, "epoch": 4.979757085020243, "percentage": 99.6, "elapsed_time": "3:44:00", "remaining_time": "0:00:54"}
1231
+ {"current_steps": 1231, "total_steps": 1235, "loss": 0.2293, "lr": 1.2793429493518361e-09, "epoch": 4.983805668016195, "percentage": 99.68, "elapsed_time": "3:44:13", "remaining_time": "0:00:43"}
1232
+ {"current_steps": 1232, "total_steps": 1235, "loss": 0.2257, "lr": 7.196337656112384e-10, "epoch": 4.987854251012146, "percentage": 99.76, "elapsed_time": "3:44:25", "remaining_time": "0:00:32"}
1233
+ {"current_steps": 1233, "total_steps": 1235, "loss": 0.2392, "lr": 3.198382947511292e-10, "epoch": 4.991902834008097, "percentage": 99.84, "elapsed_time": "3:44:40", "remaining_time": "0:00:21"}
1234
+ {"current_steps": 1234, "total_steps": 1235, "loss": 0.2313, "lr": 7.995973352770137e-11, "epoch": 4.995951417004049, "percentage": 99.92, "elapsed_time": "3:44:49", "remaining_time": "0:00:10"}
1235
+ {"current_steps": 1235, "total_steps": 1235, "loss": 0.2105, "lr": 0.0, "epoch": 5.0, "percentage": 100.0, "elapsed_time": "3:44:59", "remaining_time": "0:00:00"}
1236
+ {"current_steps": 1235, "total_steps": 1235, "epoch": 5.0, "percentage": 100.0, "elapsed_time": "3:47:07", "remaining_time": "0:00:00"}