neginr commited on
Commit
72a8218
·
verified ·
1 Parent(s): b11cfb8

Training in progress, epoch 4

Browse files
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3acbf56ed941b3ca73b94b13f75d6a7c9465e0c605ddf25aef0071f46cb35be1
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b97e19b66b726c389b08151a9acef30b8658631c828a973c9a2bc74056e0ce55
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:973689a06d5f868bf89df0ec994e5536d30aea63f698b090c88f7d0e804e0365
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c35055414c72586835eeaeda739d26c190bcaba7583b683ff6e640c963b6df44
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:f2007c7027905774efc2bcffb4ed9f3d575789cdd17f5b40a4577adccf19696e
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:849715b95267fbc432a4027658c11d7b8d6b403c058c2ff98294edfaf2da20e9
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:e8acf023eaebd68c8982c24085bf6f78ea3ef1cd19d323565ae5b2e0aae0c309
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a149a706e459c319883d49902c7ca590e93b025055cf1f2e185c1345e258606
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -991,3 +991,294 @@
991
  {"current_steps": 991, "total_steps": 1230, "loss": 0.1952, "lr": 4.426764539041861e-06, "epoch": 4.014177215189873, "percentage": 80.57, "elapsed_time": "8:46:57", "remaining_time": "2:07:05"}
992
  {"current_steps": 992, "total_steps": 1230, "loss": 0.1952, "lr": 4.391214415081582e-06, "epoch": 4.018227848101266, "percentage": 80.65, "elapsed_time": "8:47:33", "remaining_time": "2:06:34"}
993
  {"current_steps": 993, "total_steps": 1230, "loss": 0.1916, "lr": 4.355790002134579e-06, "epoch": 4.022278481012658, "percentage": 80.73, "elapsed_time": "8:48:09", "remaining_time": "2:06:03"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
991
  {"current_steps": 991, "total_steps": 1230, "loss": 0.1952, "lr": 4.426764539041861e-06, "epoch": 4.014177215189873, "percentage": 80.57, "elapsed_time": "8:46:57", "remaining_time": "2:07:05"}
992
  {"current_steps": 992, "total_steps": 1230, "loss": 0.1952, "lr": 4.391214415081582e-06, "epoch": 4.018227848101266, "percentage": 80.65, "elapsed_time": "8:47:33", "remaining_time": "2:06:34"}
993
  {"current_steps": 993, "total_steps": 1230, "loss": 0.1916, "lr": 4.355790002134579e-06, "epoch": 4.022278481012658, "percentage": 80.73, "elapsed_time": "8:48:09", "remaining_time": "2:06:03"}
994
+ {"current_steps": 994, "total_steps": 1230, "loss": 0.198, "lr": 4.320491585504207e-06, "epoch": 4.02632911392405, "percentage": 80.81, "elapsed_time": "8:48:40", "remaining_time": "2:05:31"}
995
+ {"current_steps": 995, "total_steps": 1230, "loss": 0.188, "lr": 4.2853194494790615e-06, "epoch": 4.030379746835443, "percentage": 80.89, "elapsed_time": "8:49:13", "remaining_time": "2:04:59"}
996
+ {"current_steps": 996, "total_steps": 1230, "loss": 0.1755, "lr": 4.250273877330691e-06, "epoch": 4.034430379746835, "percentage": 80.98, "elapsed_time": "8:49:50", "remaining_time": "2:04:28"}
997
+ {"current_steps": 997, "total_steps": 1230, "loss": 0.1741, "lr": 4.215355151311313e-06, "epoch": 4.038481012658228, "percentage": 81.06, "elapsed_time": "8:50:23", "remaining_time": "2:03:57"}
998
+ {"current_steps": 998, "total_steps": 1230, "loss": 0.2028, "lr": 4.180563552651542e-06, "epoch": 4.04253164556962, "percentage": 81.14, "elapsed_time": "8:50:54", "remaining_time": "2:03:24"}
999
+ {"current_steps": 999, "total_steps": 1230, "loss": 0.1891, "lr": 4.145899361558147e-06, "epoch": 4.046582278481012, "percentage": 81.22, "elapsed_time": "8:51:26", "remaining_time": "2:02:53"}
1000
+ {"current_steps": 1000, "total_steps": 1230, "loss": 0.1914, "lr": 4.111362857211738e-06, "epoch": 4.050632911392405, "percentage": 81.3, "elapsed_time": "8:51:57", "remaining_time": "2:02:20"}
1001
+ {"current_steps": 1001, "total_steps": 1230, "loss": 0.1672, "lr": 4.076954317764592e-06, "epoch": 4.054683544303797, "percentage": 81.38, "elapsed_time": "8:52:25", "remaining_time": "2:01:48"}
1002
+ {"current_steps": 1002, "total_steps": 1230, "loss": 0.1762, "lr": 4.042674020338335e-06, "epoch": 4.0587341772151895, "percentage": 81.46, "elapsed_time": "8:52:57", "remaining_time": "2:01:16"}
1003
+ {"current_steps": 1003, "total_steps": 1230, "loss": 0.1413, "lr": 4.0085222410217835e-06, "epoch": 4.062784810126582, "percentage": 81.54, "elapsed_time": "8:53:21", "remaining_time": "2:00:42"}
1004
+ {"current_steps": 1004, "total_steps": 1230, "loss": 0.174, "lr": 3.974499254868674e-06, "epoch": 4.0668354430379745, "percentage": 81.63, "elapsed_time": "8:53:50", "remaining_time": "2:00:10"}
1005
+ {"current_steps": 1005, "total_steps": 1230, "loss": 0.1975, "lr": 3.940605335895451e-06, "epoch": 4.0708860759493675, "percentage": 81.71, "elapsed_time": "8:54:18", "remaining_time": "1:59:37"}
1006
+ {"current_steps": 1006, "total_steps": 1230, "loss": 0.1708, "lr": 3.90684075707908e-06, "epoch": 4.0749367088607595, "percentage": 81.79, "elapsed_time": "8:54:52", "remaining_time": "1:59:05"}
1007
+ {"current_steps": 1007, "total_steps": 1230, "loss": 0.1759, "lr": 3.8732057903548505e-06, "epoch": 4.078987341772152, "percentage": 81.87, "elapsed_time": "8:55:18", "remaining_time": "1:58:32"}
1008
+ {"current_steps": 1008, "total_steps": 1230, "loss": 0.1763, "lr": 3.8397007066141375e-06, "epoch": 4.083037974683545, "percentage": 81.95, "elapsed_time": "8:55:48", "remaining_time": "1:58:00"}
1009
+ {"current_steps": 1009, "total_steps": 1230, "loss": 0.1885, "lr": 3.806325775702304e-06, "epoch": 4.087088607594937, "percentage": 82.03, "elapsed_time": "8:56:19", "remaining_time": "1:57:28"}
1010
+ {"current_steps": 1010, "total_steps": 1230, "loss": 0.1806, "lr": 3.773081266416434e-06, "epoch": 4.091139240506329, "percentage": 82.11, "elapsed_time": "8:56:47", "remaining_time": "1:56:55"}
1011
+ {"current_steps": 1011, "total_steps": 1230, "loss": 0.177, "lr": 3.739967446503245e-06, "epoch": 4.095189873417722, "percentage": 82.2, "elapsed_time": "8:57:19", "remaining_time": "1:56:23"}
1012
+ {"current_steps": 1012, "total_steps": 1230, "loss": 0.1701, "lr": 3.706984582656894e-06, "epoch": 4.099240506329114, "percentage": 82.28, "elapsed_time": "8:57:51", "remaining_time": "1:55:51"}
1013
+ {"current_steps": 1013, "total_steps": 1230, "loss": 0.1878, "lr": 3.6741329405168237e-06, "epoch": 4.103291139240507, "percentage": 82.36, "elapsed_time": "8:58:21", "remaining_time": "1:55:19"}
1014
+ {"current_steps": 1014, "total_steps": 1230, "loss": 0.192, "lr": 3.641412784665648e-06, "epoch": 4.107341772151899, "percentage": 82.44, "elapsed_time": "8:58:50", "remaining_time": "1:54:47"}
1015
+ {"current_steps": 1015, "total_steps": 1230, "loss": 0.1869, "lr": 3.608824378627005e-06, "epoch": 4.111392405063291, "percentage": 82.52, "elapsed_time": "8:59:23", "remaining_time": "1:54:15"}
1016
+ {"current_steps": 1016, "total_steps": 1230, "loss": 0.1903, "lr": 3.5763679848634337e-06, "epoch": 4.115443037974684, "percentage": 82.6, "elapsed_time": "8:59:56", "remaining_time": "1:53:43"}
1017
+ {"current_steps": 1017, "total_steps": 1230, "loss": 0.2104, "lr": 3.544043864774269e-06, "epoch": 4.119493670886076, "percentage": 82.68, "elapsed_time": "9:00:29", "remaining_time": "1:53:12"}
1018
+ {"current_steps": 1018, "total_steps": 1230, "loss": 0.17, "lr": 3.5118522786935282e-06, "epoch": 4.123544303797468, "percentage": 82.76, "elapsed_time": "9:00:58", "remaining_time": "1:52:39"}
1019
+ {"current_steps": 1019, "total_steps": 1230, "loss": 0.2014, "lr": 3.479793485887819e-06, "epoch": 4.127594936708861, "percentage": 82.85, "elapsed_time": "9:01:29", "remaining_time": "1:52:07"}
1020
+ {"current_steps": 1020, "total_steps": 1230, "loss": 0.1904, "lr": 3.4478677445542653e-06, "epoch": 4.131645569620253, "percentage": 82.93, "elapsed_time": "9:02:03", "remaining_time": "1:51:35"}
1021
+ {"current_steps": 1021, "total_steps": 1230, "loss": 0.1777, "lr": 3.4160753118183767e-06, "epoch": 4.135696202531646, "percentage": 83.01, "elapsed_time": "9:02:36", "remaining_time": "1:51:04"}
1022
+ {"current_steps": 1022, "total_steps": 1230, "loss": 0.1908, "lr": 3.3844164437320527e-06, "epoch": 4.139746835443038, "percentage": 83.09, "elapsed_time": "9:03:08", "remaining_time": "1:50:32"}
1023
+ {"current_steps": 1023, "total_steps": 1230, "loss": 0.1928, "lr": 3.3528913952714558e-06, "epoch": 4.14379746835443, "percentage": 83.17, "elapsed_time": "9:03:41", "remaining_time": "1:50:00"}
1024
+ {"current_steps": 1024, "total_steps": 1230, "loss": 0.1957, "lr": 3.321500420335e-06, "epoch": 4.147848101265823, "percentage": 83.25, "elapsed_time": "9:04:15", "remaining_time": "1:49:29"}
1025
+ {"current_steps": 1025, "total_steps": 1230, "loss": 0.2049, "lr": 3.290243771741275e-06, "epoch": 4.151898734177215, "percentage": 83.33, "elapsed_time": "9:04:51", "remaining_time": "1:48:58"}
1026
+ {"current_steps": 1026, "total_steps": 1230, "loss": 0.1955, "lr": 3.2591217012270325e-06, "epoch": 4.155949367088607, "percentage": 83.41, "elapsed_time": "9:05:24", "remaining_time": "1:48:26"}
1027
+ {"current_steps": 1027, "total_steps": 1230, "loss": 0.1795, "lr": 3.228134459445149e-06, "epoch": 4.16, "percentage": 83.5, "elapsed_time": "9:05:50", "remaining_time": "1:47:53"}
1028
+ {"current_steps": 1028, "total_steps": 1230, "loss": 0.1922, "lr": 3.1972822959626205e-06, "epoch": 4.164050632911392, "percentage": 83.58, "elapsed_time": "9:06:22", "remaining_time": "1:47:21"}
1029
+ {"current_steps": 1029, "total_steps": 1230, "loss": 0.1734, "lr": 3.166565459258513e-06, "epoch": 4.168101265822785, "percentage": 83.66, "elapsed_time": "9:06:52", "remaining_time": "1:46:49"}
1030
+ {"current_steps": 1030, "total_steps": 1230, "loss": 0.1742, "lr": 3.1359841967220193e-06, "epoch": 4.172151898734177, "percentage": 83.74, "elapsed_time": "9:07:23", "remaining_time": "1:46:17"}
1031
+ {"current_steps": 1031, "total_steps": 1230, "loss": 0.1953, "lr": 3.105538754650419e-06, "epoch": 4.176202531645569, "percentage": 83.82, "elapsed_time": "9:07:53", "remaining_time": "1:45:45"}
1032
+ {"current_steps": 1032, "total_steps": 1230, "loss": 0.2082, "lr": 3.07522937824712e-06, "epoch": 4.180253164556962, "percentage": 83.9, "elapsed_time": "9:08:25", "remaining_time": "1:45:13"}
1033
+ {"current_steps": 1033, "total_steps": 1230, "loss": 0.1932, "lr": 3.0450563116196697e-06, "epoch": 4.184303797468354, "percentage": 83.98, "elapsed_time": "9:08:56", "remaining_time": "1:44:41"}
1034
+ {"current_steps": 1034, "total_steps": 1230, "loss": 0.1793, "lr": 3.0150197977778008e-06, "epoch": 4.188354430379746, "percentage": 84.07, "elapsed_time": "9:09:21", "remaining_time": "1:44:08"}
1035
+ {"current_steps": 1035, "total_steps": 1230, "loss": 0.1865, "lr": 2.985120078631465e-06, "epoch": 4.192405063291139, "percentage": 84.15, "elapsed_time": "9:09:52", "remaining_time": "1:43:36"}
1036
+ {"current_steps": 1036, "total_steps": 1230, "loss": 0.192, "lr": 2.9553573949888893e-06, "epoch": 4.1964556962025314, "percentage": 84.23, "elapsed_time": "9:10:28", "remaining_time": "1:43:04"}
1037
+ {"current_steps": 1037, "total_steps": 1230, "loss": 0.2029, "lr": 2.9257319865546384e-06, "epoch": 4.200506329113924, "percentage": 84.31, "elapsed_time": "9:11:02", "remaining_time": "1:42:33"}
1038
+ {"current_steps": 1038, "total_steps": 1230, "loss": 0.1796, "lr": 2.896244091927678e-06, "epoch": 4.2045569620253165, "percentage": 84.39, "elapsed_time": "9:11:33", "remaining_time": "1:42:01"}
1039
+ {"current_steps": 1039, "total_steps": 1230, "loss": 0.1888, "lr": 2.8668939485994584e-06, "epoch": 4.2086075949367086, "percentage": 84.47, "elapsed_time": "9:12:09", "remaining_time": "1:41:30"}
1040
+ {"current_steps": 1040, "total_steps": 1230, "loss": 0.1884, "lr": 2.837681792951994e-06, "epoch": 4.2126582278481015, "percentage": 84.55, "elapsed_time": "9:12:38", "remaining_time": "1:40:57"}
1041
+ {"current_steps": 988, "total_steps": 1230, "loss": 0.2026, "lr": 4.534166308795815e-06, "epoch": 4.01620253164557, "percentage": 80.33, "elapsed_time": "0:00:44", "remaining_time": "0:00:10"}
1042
+ {"current_steps": 989, "total_steps": 1230, "loss": 0.2021, "lr": 4.498240773728859e-06, "epoch": 4.020253164556962, "percentage": 80.41, "elapsed_time": "0:01:20", "remaining_time": "0:00:19"}
1043
+ {"current_steps": 990, "total_steps": 1230, "loss": 0.1915, "lr": 4.462440087699609e-06, "epoch": 4.024303797468354, "percentage": 80.49, "elapsed_time": "0:01:54", "remaining_time": "0:00:27"}
1044
+ {"current_steps": 991, "total_steps": 1230, "loss": 0.1772, "lr": 4.426764539041861e-06, "epoch": 4.028354430379747, "percentage": 80.57, "elapsed_time": "0:02:23", "remaining_time": "0:00:34"}
1045
+ {"current_steps": 992, "total_steps": 1230, "loss": 0.1973, "lr": 4.391214415081582e-06, "epoch": 4.032405063291139, "percentage": 80.65, "elapsed_time": "0:02:57", "remaining_time": "0:00:42"}
1046
+ {"current_steps": 993, "total_steps": 1230, "loss": 0.1794, "lr": 4.355790002134579e-06, "epoch": 4.036455696202531, "percentage": 80.73, "elapsed_time": "0:03:34", "remaining_time": "0:00:51"}
1047
+ {"current_steps": 994, "total_steps": 1230, "loss": 0.1889, "lr": 4.320491585504207e-06, "epoch": 4.040506329113924, "percentage": 80.81, "elapsed_time": "0:04:07", "remaining_time": "0:00:58"}
1048
+ {"current_steps": 995, "total_steps": 1230, "loss": 0.1946, "lr": 4.2853194494790615e-06, "epoch": 4.044556962025316, "percentage": 80.89, "elapsed_time": "0:04:39", "remaining_time": "0:01:06"}
1049
+ {"current_steps": 996, "total_steps": 1230, "loss": 0.1898, "lr": 4.250273877330691e-06, "epoch": 4.048607594936709, "percentage": 80.98, "elapsed_time": "0:05:06", "remaining_time": "0:01:11"}
1050
+ {"current_steps": 997, "total_steps": 1230, "loss": 0.1792, "lr": 4.215355151311313e-06, "epoch": 4.052658227848101, "percentage": 81.06, "elapsed_time": "0:05:37", "remaining_time": "0:01:18"}
1051
+ {"current_steps": 998, "total_steps": 1230, "loss": 0.1652, "lr": 4.180563552651542e-06, "epoch": 4.056708860759493, "percentage": 81.14, "elapsed_time": "0:06:07", "remaining_time": "0:01:25"}
1052
+ {"current_steps": 999, "total_steps": 1230, "loss": 0.1779, "lr": 4.145899361558147e-06, "epoch": 4.060759493670886, "percentage": 81.22, "elapsed_time": "0:06:37", "remaining_time": "0:01:31"}
1053
+ {"current_steps": 1000, "total_steps": 1230, "loss": 0.1399, "lr": 4.111362857211738e-06, "epoch": 4.0648101265822785, "percentage": 81.3, "elapsed_time": "0:07:02", "remaining_time": "0:01:37"}
1054
+ {"current_steps": 1001, "total_steps": 1230, "loss": 0.1849, "lr": 4.076954317764592e-06, "epoch": 4.0688607594936705, "percentage": 81.38, "elapsed_time": "0:07:29", "remaining_time": "0:01:42"}
1055
+ {"current_steps": 1002, "total_steps": 1230, "loss": 0.1986, "lr": 4.042674020338335e-06, "epoch": 4.0729113924050635, "percentage": 81.46, "elapsed_time": "0:08:04", "remaining_time": "0:01:50"}
1056
+ {"current_steps": 1003, "total_steps": 1230, "loss": 0.1637, "lr": 4.0085222410217835e-06, "epoch": 4.076962025316456, "percentage": 81.54, "elapsed_time": "0:08:31", "remaining_time": "0:01:55"}
1057
+ {"current_steps": 1004, "total_steps": 1230, "loss": 0.1909, "lr": 3.974499254868674e-06, "epoch": 4.0810126582278485, "percentage": 81.63, "elapsed_time": "0:09:00", "remaining_time": "0:02:01"}
1058
+ {"current_steps": 1005, "total_steps": 1230, "loss": 0.1743, "lr": 3.940605335895451e-06, "epoch": 4.085063291139241, "percentage": 81.71, "elapsed_time": "0:09:31", "remaining_time": "0:02:07"}
1059
+ {"current_steps": 1006, "total_steps": 1230, "loss": 0.166, "lr": 3.90684075707908e-06, "epoch": 4.089113924050633, "percentage": 81.79, "elapsed_time": "0:09:57", "remaining_time": "0:02:13"}
1060
+ {"current_steps": 1007, "total_steps": 1230, "loss": 0.191, "lr": 3.8732057903548505e-06, "epoch": 4.093164556962026, "percentage": 81.87, "elapsed_time": "0:10:31", "remaining_time": "0:02:19"}
1061
+ {"current_steps": 1008, "total_steps": 1230, "loss": 0.1821, "lr": 3.8397007066141375e-06, "epoch": 4.097215189873418, "percentage": 81.95, "elapsed_time": "0:11:02", "remaining_time": "0:02:25"}
1062
+ {"current_steps": 1009, "total_steps": 1230, "loss": 0.1773, "lr": 3.806325775702304e-06, "epoch": 4.10126582278481, "percentage": 82.03, "elapsed_time": "0:11:35", "remaining_time": "0:02:32"}
1063
+ {"current_steps": 1010, "total_steps": 1230, "loss": 0.1817, "lr": 3.773081266416434e-06, "epoch": 4.105316455696203, "percentage": 82.11, "elapsed_time": "0:12:03", "remaining_time": "0:02:37"}
1064
+ {"current_steps": 1011, "total_steps": 1230, "loss": 0.1881, "lr": 3.739967446503245e-06, "epoch": 4.109367088607595, "percentage": 82.2, "elapsed_time": "0:12:33", "remaining_time": "0:02:43"}
1065
+ {"current_steps": 1012, "total_steps": 1230, "loss": 0.198, "lr": 3.706984582656894e-06, "epoch": 4.113417721518988, "percentage": 82.28, "elapsed_time": "0:13:08", "remaining_time": "0:02:49"}
1066
+ {"current_steps": 1013, "total_steps": 1230, "loss": 0.1874, "lr": 3.6741329405168237e-06, "epoch": 4.11746835443038, "percentage": 82.36, "elapsed_time": "0:13:39", "remaining_time": "0:02:55"}
1067
+ {"current_steps": 1014, "total_steps": 1230, "loss": 0.2054, "lr": 3.641412784665648e-06, "epoch": 4.121518987341772, "percentage": 82.44, "elapsed_time": "0:14:11", "remaining_time": "0:03:01"}
1068
+ {"current_steps": 1015, "total_steps": 1230, "loss": 0.1751, "lr": 3.608824378627005e-06, "epoch": 4.125569620253165, "percentage": 82.52, "elapsed_time": "0:14:41", "remaining_time": "0:03:06"}
1069
+ {"current_steps": 1016, "total_steps": 1230, "loss": 0.1985, "lr": 3.5763679848634337e-06, "epoch": 4.129620253164557, "percentage": 82.6, "elapsed_time": "0:15:13", "remaining_time": "0:03:12"}
1070
+ {"current_steps": 1017, "total_steps": 1230, "loss": 0.192, "lr": 3.544043864774269e-06, "epoch": 4.133670886075949, "percentage": 82.68, "elapsed_time": "0:15:46", "remaining_time": "0:03:18"}
1071
+ {"current_steps": 1018, "total_steps": 1230, "loss": 0.1894, "lr": 3.5118522786935282e-06, "epoch": 4.137721518987342, "percentage": 82.76, "elapsed_time": "0:16:24", "remaining_time": "0:03:24"}
1072
+ {"current_steps": 1019, "total_steps": 1230, "loss": 0.1834, "lr": 3.479793485887819e-06, "epoch": 4.141772151898734, "percentage": 82.85, "elapsed_time": "0:16:55", "remaining_time": "0:03:30"}
1073
+ {"current_steps": 1020, "total_steps": 1230, "loss": 0.1902, "lr": 3.4478677445542653e-06, "epoch": 4.145822784810127, "percentage": 82.93, "elapsed_time": "0:17:25", "remaining_time": "0:03:35"}
1074
+ {"current_steps": 1021, "total_steps": 1230, "loss": 0.212, "lr": 3.4160753118183767e-06, "epoch": 4.149873417721519, "percentage": 83.01, "elapsed_time": "0:18:05", "remaining_time": "0:03:42"}
1075
+ {"current_steps": 1022, "total_steps": 1230, "loss": 0.1944, "lr": 3.3844164437320527e-06, "epoch": 4.153924050632911, "percentage": 83.09, "elapsed_time": "0:18:36", "remaining_time": "0:03:47"}
1076
+ {"current_steps": 1023, "total_steps": 1230, "loss": 0.1778, "lr": 3.3528913952714558e-06, "epoch": 4.157974683544304, "percentage": 83.17, "elapsed_time": "0:19:05", "remaining_time": "0:03:51"}
1077
+ {"current_steps": 1024, "total_steps": 1230, "loss": 0.1932, "lr": 3.321500420335e-06, "epoch": 4.162025316455696, "percentage": 83.25, "elapsed_time": "0:19:36", "remaining_time": "0:03:56"}
1078
+ {"current_steps": 1025, "total_steps": 1230, "loss": 0.1894, "lr": 3.290243771741275e-06, "epoch": 4.166075949367088, "percentage": 83.33, "elapsed_time": "0:20:06", "remaining_time": "0:04:01"}
1079
+ {"current_steps": 1026, "total_steps": 1230, "loss": 0.1601, "lr": 3.2591217012270325e-06, "epoch": 4.170126582278481, "percentage": 83.41, "elapsed_time": "0:20:37", "remaining_time": "0:04:06"}
1080
+ {"current_steps": 1027, "total_steps": 1230, "loss": 0.2, "lr": 3.228134459445149e-06, "epoch": 4.174177215189873, "percentage": 83.5, "elapsed_time": "0:21:07", "remaining_time": "0:04:10"}
1081
+ {"current_steps": 1028, "total_steps": 1230, "loss": 0.1946, "lr": 3.1972822959626205e-06, "epoch": 4.178227848101266, "percentage": 83.58, "elapsed_time": "0:21:41", "remaining_time": "0:04:15"}
1082
+ {"current_steps": 1029, "total_steps": 1230, "loss": 0.1991, "lr": 3.166565459258513e-06, "epoch": 4.182278481012658, "percentage": 83.66, "elapsed_time": "0:22:14", "remaining_time": "0:04:20"}
1083
+ {"current_steps": 1030, "total_steps": 1230, "loss": 0.1748, "lr": 3.1359841967220193e-06, "epoch": 4.18632911392405, "percentage": 83.74, "elapsed_time": "0:22:37", "remaining_time": "0:04:23"}
1084
+ {"current_steps": 1031, "total_steps": 1230, "loss": 0.2036, "lr": 3.105538754650419e-06, "epoch": 4.190379746835443, "percentage": 83.82, "elapsed_time": "0:23:06", "remaining_time": "0:04:27"}
1085
+ {"current_steps": 1032, "total_steps": 1230, "loss": 0.1938, "lr": 3.07522937824712e-06, "epoch": 4.194430379746835, "percentage": 83.9, "elapsed_time": "0:23:38", "remaining_time": "0:04:32"}
1086
+ {"current_steps": 1033, "total_steps": 1230, "loss": 0.1828, "lr": 3.0450563116196697e-06, "epoch": 4.1984810126582275, "percentage": 83.98, "elapsed_time": "0:24:16", "remaining_time": "0:04:37"}
1087
+ {"current_steps": 1034, "total_steps": 1230, "loss": 0.1934, "lr": 3.0150197977778008e-06, "epoch": 4.2025316455696204, "percentage": 84.07, "elapsed_time": "0:24:44", "remaining_time": "0:04:41"}
1088
+ {"current_steps": 1035, "total_steps": 1230, "loss": 0.1941, "lr": 2.985120078631465e-06, "epoch": 4.2065822784810125, "percentage": 84.15, "elapsed_time": "0:25:22", "remaining_time": "0:04:46"}
1089
+ {"current_steps": 1036, "total_steps": 1230, "loss": 0.1653, "lr": 2.9553573949888893e-06, "epoch": 4.2106329113924055, "percentage": 84.23, "elapsed_time": "0:25:53", "remaining_time": "0:04:50"}
1090
+ {"current_steps": 1037, "total_steps": 1230, "loss": 0.1925, "lr": 2.9257319865546384e-06, "epoch": 4.2146835443037975, "percentage": 84.31, "elapsed_time": "0:26:22", "remaining_time": "0:04:54"}
1091
+ {"current_steps": 1038, "total_steps": 1230, "loss": 0.1702, "lr": 2.896244091927678e-06, "epoch": 4.21873417721519, "percentage": 84.39, "elapsed_time": "0:26:52", "remaining_time": "0:04:58"}
1092
+ {"current_steps": 1039, "total_steps": 1230, "loss": 0.2091, "lr": 2.8668939485994584e-06, "epoch": 4.222784810126583, "percentage": 84.47, "elapsed_time": "0:27:29", "remaining_time": "0:05:03"}
1093
+ {"current_steps": 1040, "total_steps": 1230, "loss": 0.1985, "lr": 2.837681792951994e-06, "epoch": 4.226835443037975, "percentage": 84.55, "elapsed_time": "0:28:03", "remaining_time": "0:05:07"}
1094
+ {"current_steps": 1041, "total_steps": 1230, "loss": 0.1556, "lr": 2.808607860255981e-06, "epoch": 4.230886075949367, "percentage": 84.63, "elapsed_time": "0:28:29", "remaining_time": "0:05:10"}
1095
+ {"current_steps": 1042, "total_steps": 1230, "loss": 0.1844, "lr": 2.7796723846688634e-06, "epoch": 4.23493670886076, "percentage": 84.72, "elapsed_time": "0:28:56", "remaining_time": "0:05:13"}
1096
+ {"current_steps": 1043, "total_steps": 1230, "loss": 0.1919, "lr": 2.7508755992329937e-06, "epoch": 4.238987341772152, "percentage": 84.8, "elapsed_time": "0:29:28", "remaining_time": "0:05:17"}
1097
+ {"current_steps": 1044, "total_steps": 1230, "loss": 0.205, "lr": 2.722217735873718e-06, "epoch": 4.243037974683545, "percentage": 84.88, "elapsed_time": "0:30:02", "remaining_time": "0:05:21"}
1098
+ {"current_steps": 1045, "total_steps": 1230, "loss": 0.1717, "lr": 2.6936990253975315e-06, "epoch": 4.247088607594937, "percentage": 84.96, "elapsed_time": "0:30:33", "remaining_time": "0:05:24"}
1099
+ {"current_steps": 1046, "total_steps": 1230, "loss": 0.1638, "lr": 2.665319697490205e-06, "epoch": 4.251139240506329, "percentage": 85.04, "elapsed_time": "0:31:04", "remaining_time": "0:05:28"}
1100
+ {"current_steps": 1047, "total_steps": 1230, "loss": 0.1736, "lr": 2.637079980714945e-06, "epoch": 4.255189873417722, "percentage": 85.12, "elapsed_time": "0:31:37", "remaining_time": "0:05:31"}
1101
+ {"current_steps": 1048, "total_steps": 1230, "loss": 0.1805, "lr": 2.6089801025105453e-06, "epoch": 4.259240506329114, "percentage": 85.2, "elapsed_time": "0:32:06", "remaining_time": "0:05:34"}
1102
+ {"current_steps": 1049, "total_steps": 1230, "loss": 0.1834, "lr": 2.581020289189571e-06, "epoch": 4.263291139240506, "percentage": 85.28, "elapsed_time": "0:32:35", "remaining_time": "0:05:37"}
1103
+ {"current_steps": 1050, "total_steps": 1230, "loss": 0.2028, "lr": 2.553200765936501e-06, "epoch": 4.267341772151899, "percentage": 85.37, "elapsed_time": "0:33:08", "remaining_time": "0:05:40"}
1104
+ {"current_steps": 1051, "total_steps": 1230, "loss": 0.1835, "lr": 2.525521756805962e-06, "epoch": 4.271392405063291, "percentage": 85.45, "elapsed_time": "0:33:37", "remaining_time": "0:05:43"}
1105
+ {"current_steps": 1052, "total_steps": 1230, "loss": 0.1557, "lr": 2.497983484720885e-06, "epoch": 4.275443037974684, "percentage": 85.53, "elapsed_time": "0:34:04", "remaining_time": "0:05:45"}
1106
+ {"current_steps": 1053, "total_steps": 1230, "loss": 0.1505, "lr": 2.470586171470728e-06, "epoch": 4.279493670886076, "percentage": 85.61, "elapsed_time": "0:34:33", "remaining_time": "0:05:48"}
1107
+ {"current_steps": 1054, "total_steps": 1230, "loss": 0.1879, "lr": 2.4433300377096836e-06, "epoch": 4.283544303797468, "percentage": 85.69, "elapsed_time": "0:35:07", "remaining_time": "0:05:51"}
1108
+ {"current_steps": 1055, "total_steps": 1230, "loss": 0.1772, "lr": 2.4162153029549073e-06, "epoch": 4.287594936708861, "percentage": 85.77, "elapsed_time": "0:35:39", "remaining_time": "0:05:54"}
1109
+ {"current_steps": 1056, "total_steps": 1230, "loss": 0.1889, "lr": 2.3892421855847458e-06, "epoch": 4.291645569620253, "percentage": 85.85, "elapsed_time": "0:36:16", "remaining_time": "0:05:58"}
1110
+ {"current_steps": 1057, "total_steps": 1230, "loss": 0.2053, "lr": 2.362410902836978e-06, "epoch": 4.295696202531645, "percentage": 85.93, "elapsed_time": "0:36:52", "remaining_time": "0:06:02"}
1111
+ {"current_steps": 1058, "total_steps": 1230, "loss": 0.1877, "lr": 2.3357216708070653e-06, "epoch": 4.299746835443038, "percentage": 86.02, "elapsed_time": "0:37:21", "remaining_time": "0:06:04"}
1112
+ {"current_steps": 1059, "total_steps": 1230, "loss": 0.1994, "lr": 2.309174704446411e-06, "epoch": 4.30379746835443, "percentage": 86.1, "elapsed_time": "0:37:54", "remaining_time": "0:06:07"}
1113
+ {"current_steps": 1060, "total_steps": 1230, "loss": 0.1796, "lr": 2.2827702175606437e-06, "epoch": 4.307848101265823, "percentage": 86.18, "elapsed_time": "0:38:28", "remaining_time": "0:06:10"}
1114
+ {"current_steps": 1061, "total_steps": 1230, "loss": 0.1896, "lr": 2.256508422807855e-06, "epoch": 4.311898734177215, "percentage": 86.26, "elapsed_time": "0:39:06", "remaining_time": "0:06:13"}
1115
+ {"current_steps": 1062, "total_steps": 1230, "loss": 0.1923, "lr": 2.230389531696946e-06, "epoch": 4.315949367088607, "percentage": 86.34, "elapsed_time": "0:39:36", "remaining_time": "0:06:15"}
1116
+ {"current_steps": 1063, "total_steps": 1230, "loss": 0.1777, "lr": 2.204413754585857e-06, "epoch": 4.32, "percentage": 86.42, "elapsed_time": "0:40:10", "remaining_time": "0:06:18"}
1117
+ {"current_steps": 1064, "total_steps": 1230, "loss": 0.1649, "lr": 2.1785813006799406e-06, "epoch": 4.324050632911392, "percentage": 86.5, "elapsed_time": "0:40:37", "remaining_time": "0:06:20"}
1118
+ {"current_steps": 1065, "total_steps": 1230, "loss": 0.1568, "lr": 2.1528923780302224e-06, "epoch": 4.328101265822784, "percentage": 86.59, "elapsed_time": "0:41:06", "remaining_time": "0:06:22"}
1119
+ {"current_steps": 1066, "total_steps": 1230, "loss": 0.1769, "lr": 2.127347193531757e-06, "epoch": 4.332151898734177, "percentage": 86.67, "elapsed_time": "0:41:37", "remaining_time": "0:06:24"}
1120
+ {"current_steps": 1067, "total_steps": 1230, "loss": 0.1992, "lr": 2.101945952921942e-06, "epoch": 4.3362025316455695, "percentage": 86.75, "elapsed_time": "0:42:09", "remaining_time": "0:06:26"}
1121
+ {"current_steps": 1068, "total_steps": 1230, "loss": 0.1819, "lr": 2.0766888607788906e-06, "epoch": 4.340253164556962, "percentage": 86.83, "elapsed_time": "0:42:41", "remaining_time": "0:06:28"}
1122
+ {"current_steps": 1069, "total_steps": 1230, "loss": 0.1691, "lr": 2.0515761205197337e-06, "epoch": 4.3443037974683545, "percentage": 86.91, "elapsed_time": "0:43:09", "remaining_time": "0:06:29"}
1123
+ {"current_steps": 1070, "total_steps": 1230, "loss": 0.2088, "lr": 2.0266079343990453e-06, "epoch": 4.348354430379747, "percentage": 86.99, "elapsed_time": "0:43:38", "remaining_time": "0:06:31"}
1124
+ {"current_steps": 1071, "total_steps": 1230, "loss": 0.2014, "lr": 2.0017845035071494e-06, "epoch": 4.3524050632911395, "percentage": 87.07, "elapsed_time": "0:44:16", "remaining_time": "0:06:34"}
1125
+ {"current_steps": 1072, "total_steps": 1230, "loss": 0.1844, "lr": 1.9771060277685537e-06, "epoch": 4.356455696202532, "percentage": 87.15, "elapsed_time": "0:44:47", "remaining_time": "0:06:36"}
1126
+ {"current_steps": 1073, "total_steps": 1230, "loss": 0.1832, "lr": 1.95257270594031e-06, "epoch": 4.360506329113924, "percentage": 87.24, "elapsed_time": "0:45:14", "remaining_time": "0:06:37"}
1127
+ {"current_steps": 1074, "total_steps": 1230, "loss": 0.2063, "lr": 1.9281847356104188e-06, "epoch": 4.364556962025317, "percentage": 87.32, "elapsed_time": "0:45:43", "remaining_time": "0:06:38"}
1128
+ {"current_steps": 1075, "total_steps": 1230, "loss": 0.1775, "lr": 1.9039423131962365e-06, "epoch": 4.368607594936709, "percentage": 87.4, "elapsed_time": "0:46:14", "remaining_time": "0:06:40"}
1129
+ {"current_steps": 1076, "total_steps": 1230, "loss": 0.1639, "lr": 1.8798456339429027e-06, "epoch": 4.372658227848102, "percentage": 87.48, "elapsed_time": "0:46:44", "remaining_time": "0:06:41"}
1130
+ {"current_steps": 1077, "total_steps": 1230, "loss": 0.1773, "lr": 1.8558948919217612e-06, "epoch": 4.376708860759494, "percentage": 87.56, "elapsed_time": "0:47:15", "remaining_time": "0:06:42"}
1131
+ {"current_steps": 1078, "total_steps": 1230, "loss": 0.1962, "lr": 1.8320902800287954e-06, "epoch": 4.380759493670886, "percentage": 87.64, "elapsed_time": "0:47:50", "remaining_time": "0:06:44"}
1132
+ {"current_steps": 1079, "total_steps": 1230, "loss": 0.1634, "lr": 1.8084319899830726e-06, "epoch": 4.384810126582279, "percentage": 87.72, "elapsed_time": "0:48:25", "remaining_time": "0:06:46"}
1133
+ {"current_steps": 1080, "total_steps": 1230, "loss": 0.1805, "lr": 1.7849202123252097e-06, "epoch": 4.388860759493671, "percentage": 87.8, "elapsed_time": "0:48:54", "remaining_time": "0:06:47"}
1134
+ {"current_steps": 1081, "total_steps": 1230, "loss": 0.1825, "lr": 1.7615551364158401e-06, "epoch": 4.392911392405063, "percentage": 87.89, "elapsed_time": "0:49:22", "remaining_time": "0:06:48"}
1135
+ {"current_steps": 1082, "total_steps": 1230, "loss": 0.1707, "lr": 1.738336950434061e-06, "epoch": 4.396962025316456, "percentage": 87.97, "elapsed_time": "0:49:52", "remaining_time": "0:06:49"}
1136
+ {"current_steps": 1083, "total_steps": 1230, "loss": 0.1913, "lr": 1.715265841375957e-06, "epoch": 4.401012658227848, "percentage": 88.05, "elapsed_time": "0:50:25", "remaining_time": "0:06:50"}
1137
+ {"current_steps": 1084, "total_steps": 1230, "loss": 0.1893, "lr": 1.6923419950530684e-06, "epoch": 4.405063291139241, "percentage": 88.13, "elapsed_time": "0:50:53", "remaining_time": "0:06:51"}
1138
+ {"current_steps": 1085, "total_steps": 1230, "loss": 0.1746, "lr": 1.6695655960909008e-06, "epoch": 4.409113924050633, "percentage": 88.21, "elapsed_time": "0:51:22", "remaining_time": "0:06:51"}
1139
+ {"current_steps": 1086, "total_steps": 1230, "loss": 0.1944, "lr": 1.646936827927441e-06, "epoch": 4.413164556962025, "percentage": 88.29, "elapsed_time": "0:51:55", "remaining_time": "0:06:53"}
1140
+ {"current_steps": 1087, "total_steps": 1230, "loss": 0.1665, "lr": 1.6244558728116766e-06, "epoch": 4.417215189873418, "percentage": 88.37, "elapsed_time": "0:52:23", "remaining_time": "0:06:53"}
1141
+ {"current_steps": 1088, "total_steps": 1230, "loss": 0.1803, "lr": 1.6021229118021265e-06, "epoch": 4.42126582278481, "percentage": 88.46, "elapsed_time": "0:52:56", "remaining_time": "0:06:54"}
1142
+ {"current_steps": 1089, "total_steps": 1230, "loss": 0.198, "lr": 1.5799381247653967e-06, "epoch": 4.425316455696202, "percentage": 88.54, "elapsed_time": "0:53:33", "remaining_time": "0:06:56"}
1143
+ {"current_steps": 1090, "total_steps": 1230, "loss": 0.1866, "lr": 1.5579016903747013e-06, "epoch": 4.429367088607595, "percentage": 88.62, "elapsed_time": "0:54:08", "remaining_time": "0:06:57"}
1144
+ {"current_steps": 1091, "total_steps": 1230, "loss": 0.1899, "lr": 1.5360137861084656e-06, "epoch": 4.433417721518987, "percentage": 88.7, "elapsed_time": "0:54:39", "remaining_time": "0:06:57"}
1145
+ {"current_steps": 1092, "total_steps": 1230, "loss": 0.2123, "lr": 1.5142745882488475e-06, "epoch": 4.43746835443038, "percentage": 88.78, "elapsed_time": "0:55:14", "remaining_time": "0:06:58"}
1146
+ {"current_steps": 1093, "total_steps": 1230, "loss": 0.1496, "lr": 1.4926842718803691e-06, "epoch": 4.441518987341772, "percentage": 88.86, "elapsed_time": "0:55:43", "remaining_time": "0:06:59"}
1147
+ {"current_steps": 1094, "total_steps": 1230, "loss": 0.1885, "lr": 1.4712430108884657e-06, "epoch": 4.445569620253164, "percentage": 88.94, "elapsed_time": "0:56:16", "remaining_time": "0:06:59"}
1148
+ {"current_steps": 1095, "total_steps": 1230, "loss": 0.1875, "lr": 1.4499509779581078e-06, "epoch": 4.449620253164557, "percentage": 89.02, "elapsed_time": "0:56:45", "remaining_time": "0:06:59"}
1149
+ {"current_steps": 1096, "total_steps": 1230, "loss": 0.1977, "lr": 1.4288083445723988e-06, "epoch": 4.453670886075949, "percentage": 89.11, "elapsed_time": "0:57:19", "remaining_time": "0:07:00"}
1150
+ {"current_steps": 1097, "total_steps": 1230, "loss": 0.1681, "lr": 1.4078152810112045e-06, "epoch": 4.457721518987341, "percentage": 89.19, "elapsed_time": "0:57:46", "remaining_time": "0:07:00"}
1151
+ {"current_steps": 1098, "total_steps": 1230, "loss": 0.1964, "lr": 1.3869719563497697e-06, "epoch": 4.461772151898734, "percentage": 89.27, "elapsed_time": "0:58:16", "remaining_time": "0:07:00"}
1152
+ {"current_steps": 1099, "total_steps": 1230, "loss": 0.1667, "lr": 1.3662785384573663e-06, "epoch": 4.465822784810126, "percentage": 89.35, "elapsed_time": "0:58:42", "remaining_time": "0:06:59"}
1153
+ {"current_steps": 1100, "total_steps": 1230, "loss": 0.2253, "lr": 1.3457351939959383e-06, "epoch": 4.469873417721519, "percentage": 89.43, "elapsed_time": "0:59:20", "remaining_time": "0:07:00"}
1154
+ {"current_steps": 1101, "total_steps": 1230, "loss": 0.2134, "lr": 1.3253420884187551e-06, "epoch": 4.473924050632911, "percentage": 89.51, "elapsed_time": "0:59:52", "remaining_time": "0:07:00"}
1155
+ {"current_steps": 1102, "total_steps": 1230, "loss": 0.1648, "lr": 1.3050993859690953e-06, "epoch": 4.4779746835443035, "percentage": 89.59, "elapsed_time": "1:00:27", "remaining_time": "0:07:01"}
1156
+ {"current_steps": 1103, "total_steps": 1230, "loss": 0.1856, "lr": 1.2850072496788869e-06, "epoch": 4.4820253164556965, "percentage": 89.67, "elapsed_time": "1:00:57", "remaining_time": "0:07:01"}
1157
+ {"current_steps": 1104, "total_steps": 1230, "loss": 0.1963, "lr": 1.2650658413674434e-06, "epoch": 4.4860759493670885, "percentage": 89.76, "elapsed_time": "1:01:30", "remaining_time": "0:07:01"}
1158
+ {"current_steps": 1105, "total_steps": 1230, "loss": 0.1681, "lr": 1.2452753216401226e-06, "epoch": 4.490126582278481, "percentage": 89.84, "elapsed_time": "1:01:58", "remaining_time": "0:07:00"}
1159
+ {"current_steps": 1106, "total_steps": 1230, "loss": 0.1784, "lr": 1.2256358498870503e-06, "epoch": 4.494177215189874, "percentage": 89.92, "elapsed_time": "1:02:25", "remaining_time": "0:06:59"}
1160
+ {"current_steps": 1107, "total_steps": 1230, "loss": 0.1895, "lr": 1.2061475842818337e-06, "epoch": 4.498227848101266, "percentage": 90.0, "elapsed_time": "1:02:55", "remaining_time": "0:06:59"}
1161
+ {"current_steps": 1108, "total_steps": 1230, "loss": 0.185, "lr": 1.1868106817802816e-06, "epoch": 4.502278481012659, "percentage": 90.08, "elapsed_time": "1:03:30", "remaining_time": "0:06:59"}
1162
+ {"current_steps": 1109, "total_steps": 1230, "loss": 0.1863, "lr": 1.1676252981191482e-06, "epoch": 4.506329113924051, "percentage": 90.16, "elapsed_time": "1:03:59", "remaining_time": "0:06:58"}
1163
+ {"current_steps": 1110, "total_steps": 1230, "loss": 0.1898, "lr": 1.1485915878148823e-06, "epoch": 4.510379746835443, "percentage": 90.24, "elapsed_time": "1:04:28", "remaining_time": "0:06:58"}
1164
+ {"current_steps": 1111, "total_steps": 1230, "loss": 0.1961, "lr": 1.1297097041623584e-06, "epoch": 4.514430379746836, "percentage": 90.33, "elapsed_time": "1:05:01", "remaining_time": "0:06:57"}
1165
+ {"current_steps": 1112, "total_steps": 1230, "loss": 0.1667, "lr": 1.1109797992336847e-06, "epoch": 4.518481012658228, "percentage": 90.41, "elapsed_time": "1:05:32", "remaining_time": "0:06:57"}
1166
+ {"current_steps": 1113, "total_steps": 1230, "loss": 0.1578, "lr": 1.092402023876933e-06, "epoch": 4.52253164556962, "percentage": 90.49, "elapsed_time": "1:06:09", "remaining_time": "0:06:57"}
1167
+ {"current_steps": 1114, "total_steps": 1230, "loss": 0.1943, "lr": 1.0739765277149527e-06, "epoch": 4.526582278481013, "percentage": 90.57, "elapsed_time": "1:06:40", "remaining_time": "0:06:56"}
1168
+ {"current_steps": 1115, "total_steps": 1230, "loss": 0.1916, "lr": 1.0557034591441596e-06, "epoch": 4.530632911392405, "percentage": 90.65, "elapsed_time": "1:07:10", "remaining_time": "0:06:55"}
1169
+ {"current_steps": 1116, "total_steps": 1230, "loss": 0.21, "lr": 1.0375829653333324e-06, "epoch": 4.534683544303798, "percentage": 90.73, "elapsed_time": "1:07:44", "remaining_time": "0:06:55"}
1170
+ {"current_steps": 1117, "total_steps": 1230, "loss": 0.1965, "lr": 1.0196151922224385e-06, "epoch": 4.53873417721519, "percentage": 90.81, "elapsed_time": "1:08:19", "remaining_time": "0:06:54"}
1171
+ {"current_steps": 1118, "total_steps": 1230, "loss": 0.2052, "lr": 1.0018002845214526e-06, "epoch": 4.542784810126582, "percentage": 90.89, "elapsed_time": "1:08:49", "remaining_time": "0:06:53"}
1172
+ {"current_steps": 1119, "total_steps": 1230, "loss": 0.1706, "lr": 9.841383857091947e-07, "epoch": 4.546835443037975, "percentage": 90.98, "elapsed_time": "1:09:16", "remaining_time": "0:06:52"}
1173
+ {"current_steps": 1120, "total_steps": 1230, "loss": 0.1837, "lr": 9.666296380321616e-07, "epoch": 4.550886075949367, "percentage": 91.06, "elapsed_time": "1:09:44", "remaining_time": "0:06:50"}
1174
+ {"current_steps": 1121, "total_steps": 1230, "loss": 0.1848, "lr": 9.492741825034124e-07, "epoch": 4.55493670886076, "percentage": 91.14, "elapsed_time": "1:10:18", "remaining_time": "0:06:50"}
1175
+ {"current_steps": 1122, "total_steps": 1230, "loss": 0.1855, "lr": 9.320721589013892e-07, "epoch": 4.558987341772152, "percentage": 91.22, "elapsed_time": "1:10:55", "remaining_time": "0:06:49"}
1176
+ {"current_steps": 1123, "total_steps": 1230, "loss": 0.1953, "lr": 9.150237057688339e-07, "epoch": 4.563037974683544, "percentage": 91.3, "elapsed_time": "1:11:31", "remaining_time": "0:06:48"}
1177
+ {"current_steps": 1124, "total_steps": 1230, "loss": 0.176, "lr": 8.981289604116328e-07, "epoch": 4.567088607594937, "percentage": 91.38, "elapsed_time": "1:11:57", "remaining_time": "0:06:47"}
1178
+ {"current_steps": 1125, "total_steps": 1230, "loss": 0.1817, "lr": 8.813880588977542e-07, "epoch": 4.571139240506329, "percentage": 91.46, "elapsed_time": "1:12:27", "remaining_time": "0:06:45"}
1179
+ {"current_steps": 1126, "total_steps": 1230, "loss": 0.1852, "lr": 8.648011360561126e-07, "epoch": 4.575189873417721, "percentage": 91.54, "elapsed_time": "1:12:57", "remaining_time": "0:06:44"}
1180
+ {"current_steps": 1127, "total_steps": 1230, "loss": 0.178, "lr": 8.483683254755037e-07, "epoch": 4.579240506329114, "percentage": 91.63, "elapsed_time": "1:13:23", "remaining_time": "0:06:42"}
1181
+ {"current_steps": 1128, "total_steps": 1230, "loss": 0.1615, "lr": 8.320897595035227e-07, "epoch": 4.583291139240506, "percentage": 91.71, "elapsed_time": "1:13:52", "remaining_time": "0:06:40"}
1182
+ {"current_steps": 1129, "total_steps": 1230, "loss": 0.1723, "lr": 8.159655692455093e-07, "epoch": 4.587341772151898, "percentage": 91.79, "elapsed_time": "1:14:26", "remaining_time": "0:06:39"}
1183
+ {"current_steps": 1130, "total_steps": 1230, "loss": 0.1538, "lr": 7.999958845634648e-07, "epoch": 4.591392405063291, "percentage": 91.87, "elapsed_time": "1:14:51", "remaining_time": "0:06:37"}
1184
+ {"current_steps": 1131, "total_steps": 1230, "loss": 0.1909, "lr": 7.841808340750478e-07, "epoch": 4.595443037974683, "percentage": 91.95, "elapsed_time": "1:15:24", "remaining_time": "0:06:36"}
1185
+ {"current_steps": 1132, "total_steps": 1230, "loss": 0.1602, "lr": 7.685205451524869e-07, "epoch": 4.599493670886076, "percentage": 92.03, "elapsed_time": "1:15:50", "remaining_time": "0:06:33"}
1186
+ {"current_steps": 1133, "total_steps": 1230, "loss": 0.1846, "lr": 7.530151439216027e-07, "epoch": 4.603544303797468, "percentage": 92.11, "elapsed_time": "1:16:15", "remaining_time": "0:06:31"}
1187
+ {"current_steps": 1134, "total_steps": 1230, "loss": 0.1628, "lr": 7.376647552607675e-07, "epoch": 4.6075949367088604, "percentage": 92.2, "elapsed_time": "1:16:50", "remaining_time": "0:06:30"}
1188
+ {"current_steps": 1135, "total_steps": 1230, "loss": 0.1689, "lr": 7.224695027998963e-07, "epoch": 4.611645569620253, "percentage": 92.28, "elapsed_time": "1:17:21", "remaining_time": "0:06:28"}
1189
+ {"current_steps": 1136, "total_steps": 1230, "loss": 0.1833, "lr": 7.07429508919466e-07, "epoch": 4.6156962025316455, "percentage": 92.36, "elapsed_time": "1:17:56", "remaining_time": "0:06:26"}
1190
+ {"current_steps": 1137, "total_steps": 1230, "loss": 0.1804, "lr": 6.925448947495206e-07, "epoch": 4.619746835443038, "percentage": 92.44, "elapsed_time": "1:18:25", "remaining_time": "0:06:24"}
1191
+ {"current_steps": 1138, "total_steps": 1230, "loss": 0.1968, "lr": 6.778157801686936e-07, "epoch": 4.6237974683544305, "percentage": 92.52, "elapsed_time": "1:19:03", "remaining_time": "0:06:23"}
1192
+ {"current_steps": 1139, "total_steps": 1230, "loss": 0.1808, "lr": 6.632422838032515e-07, "epoch": 4.627848101265823, "percentage": 92.6, "elapsed_time": "1:19:36", "remaining_time": "0:06:21"}
1193
+ {"current_steps": 1140, "total_steps": 1230, "loss": 0.1712, "lr": 6.488245230261281e-07, "epoch": 4.6318987341772155, "percentage": 92.68, "elapsed_time": "1:20:11", "remaining_time": "0:06:19"}
1194
+ {"current_steps": 1141, "total_steps": 1230, "loss": 0.1764, "lr": 6.345626139559868e-07, "epoch": 4.635949367088608, "percentage": 92.76, "elapsed_time": "1:20:44", "remaining_time": "0:06:17"}
1195
+ {"current_steps": 1142, "total_steps": 1230, "loss": 0.1668, "lr": 6.204566714562866e-07, "epoch": 4.64, "percentage": 92.85, "elapsed_time": "1:21:17", "remaining_time": "0:06:15"}
1196
+ {"current_steps": 1143, "total_steps": 1230, "loss": 0.1787, "lr": 6.06506809134344e-07, "epoch": 4.644050632911393, "percentage": 92.93, "elapsed_time": "1:21:44", "remaining_time": "0:06:13"}
1197
+ {"current_steps": 1144, "total_steps": 1230, "loss": 0.1929, "lr": 5.927131393404373e-07, "epoch": 4.648101265822785, "percentage": 93.01, "elapsed_time": "1:22:14", "remaining_time": "0:06:10"}
1198
+ {"current_steps": 1145, "total_steps": 1230, "loss": 0.1797, "lr": 5.790757731668817e-07, "epoch": 4.652151898734177, "percentage": 93.09, "elapsed_time": "1:22:48", "remaining_time": "0:06:08"}
1199
+ {"current_steps": 1146, "total_steps": 1230, "loss": 0.1991, "lr": 5.655948204471507e-07, "epoch": 4.65620253164557, "percentage": 93.17, "elapsed_time": "1:23:18", "remaining_time": "0:06:06"}
1200
+ {"current_steps": 1147, "total_steps": 1230, "loss": 0.2111, "lr": 5.522703897549875e-07, "epoch": 4.660253164556962, "percentage": 93.25, "elapsed_time": "1:23:55", "remaining_time": "0:06:04"}
1201
+ {"current_steps": 1148, "total_steps": 1230, "loss": 0.1722, "lr": 5.391025884035239e-07, "epoch": 4.664303797468355, "percentage": 93.33, "elapsed_time": "1:24:25", "remaining_time": "0:06:01"}
1202
+ {"current_steps": 1149, "total_steps": 1230, "loss": 0.1778, "lr": 5.260915224444207e-07, "epoch": 4.668354430379747, "percentage": 93.41, "elapsed_time": "1:24:54", "remaining_time": "0:05:59"}
1203
+ {"current_steps": 1150, "total_steps": 1230, "loss": 0.1842, "lr": 5.132372966670129e-07, "epoch": 4.672405063291139, "percentage": 93.5, "elapsed_time": "1:25:27", "remaining_time": "0:05:56"}
1204
+ {"current_steps": 1151, "total_steps": 1230, "loss": 0.2043, "lr": 5.005400145974704e-07, "epoch": 4.676455696202532, "percentage": 93.58, "elapsed_time": "1:25:56", "remaining_time": "0:05:53"}
1205
+ {"current_steps": 1152, "total_steps": 1230, "loss": 0.1709, "lr": 4.879997784979562e-07, "epoch": 4.680506329113924, "percentage": 93.66, "elapsed_time": "1:26:25", "remaining_time": "0:05:51"}
1206
+ {"current_steps": 1153, "total_steps": 1230, "loss": 0.2059, "lr": 4.7561668936580984e-07, "epoch": 4.684556962025317, "percentage": 93.74, "elapsed_time": "1:26:56", "remaining_time": "0:05:48"}
1207
+ {"current_steps": 1154, "total_steps": 1230, "loss": 0.1989, "lr": 4.6339084693272306e-07, "epoch": 4.688607594936709, "percentage": 93.82, "elapsed_time": "1:27:31", "remaining_time": "0:05:45"}
1208
+ {"current_steps": 1155, "total_steps": 1230, "loss": 0.1816, "lr": 4.5132234966395847e-07, "epoch": 4.692658227848101, "percentage": 93.9, "elapsed_time": "1:28:07", "remaining_time": "0:05:43"}
1209
+ {"current_steps": 1156, "total_steps": 1230, "loss": 0.1758, "lr": 4.3941129475752795e-07, "epoch": 4.696708860759494, "percentage": 93.98, "elapsed_time": "1:28:39", "remaining_time": "0:05:40"}
1210
+ {"current_steps": 1157, "total_steps": 1230, "loss": 0.1934, "lr": 4.27657778143431e-07, "epoch": 4.700759493670886, "percentage": 94.07, "elapsed_time": "1:29:13", "remaining_time": "0:05:37"}
1211
+ {"current_steps": 1158, "total_steps": 1230, "loss": 0.1955, "lr": 4.1606189448287757e-07, "epoch": 4.704810126582278, "percentage": 94.15, "elapsed_time": "1:29:51", "remaining_time": "0:05:35"}
1212
+ {"current_steps": 1159, "total_steps": 1230, "loss": 0.2042, "lr": 4.046237371675177e-07, "epoch": 4.708860759493671, "percentage": 94.23, "elapsed_time": "1:30:20", "remaining_time": "0:05:32"}
1213
+ {"current_steps": 1160, "total_steps": 1230, "loss": 0.1866, "lr": 3.9334339831869963e-07, "epoch": 4.712911392405063, "percentage": 94.31, "elapsed_time": "1:30:47", "remaining_time": "0:05:28"}
1214
+ {"current_steps": 1161, "total_steps": 1230, "loss": 0.1793, "lr": 3.8222096878671955e-07, "epoch": 4.716962025316455, "percentage": 94.39, "elapsed_time": "1:31:17", "remaining_time": "0:05:25"}
1215
+ {"current_steps": 1162, "total_steps": 1230, "loss": 0.1813, "lr": 3.7125653815009545e-07, "epoch": 4.721012658227848, "percentage": 94.47, "elapsed_time": "1:31:42", "remaining_time": "0:05:22"}
1216
+ {"current_steps": 1163, "total_steps": 1230, "loss": 0.1821, "lr": 3.6045019471484974e-07, "epoch": 4.72506329113924, "percentage": 94.55, "elapsed_time": "1:32:14", "remaining_time": "0:05:18"}
1217
+ {"current_steps": 1164, "total_steps": 1230, "loss": 0.186, "lr": 3.498020255137813e-07, "epoch": 4.729113924050633, "percentage": 94.63, "elapsed_time": "1:32:49", "remaining_time": "0:05:15"}
1218
+ {"current_steps": 1165, "total_steps": 1230, "loss": 0.163, "lr": 3.393121163057811e-07, "epoch": 4.733164556962025, "percentage": 94.72, "elapsed_time": "1:33:19", "remaining_time": "0:05:12"}
1219
+ {"current_steps": 1166, "total_steps": 1230, "loss": 0.1683, "lr": 3.289805515751399e-07, "epoch": 4.737215189873417, "percentage": 94.8, "elapsed_time": "1:33:52", "remaining_time": "0:05:09"}
1220
+ {"current_steps": 1167, "total_steps": 1230, "loss": 0.1811, "lr": 3.188074145308573e-07, "epoch": 4.74126582278481, "percentage": 94.88, "elapsed_time": "1:34:22", "remaining_time": "0:05:05"}
1221
+ {"current_steps": 1168, "total_steps": 1230, "loss": 0.1836, "lr": 3.087927871059804e-07, "epoch": 4.745316455696202, "percentage": 94.96, "elapsed_time": "1:34:53", "remaining_time": "0:05:02"}
1222
+ {"current_steps": 1169, "total_steps": 1230, "loss": 0.1826, "lr": 2.989367499569418e-07, "epoch": 4.749367088607595, "percentage": 95.04, "elapsed_time": "1:35:26", "remaining_time": "0:04:58"}
1223
+ {"current_steps": 1170, "total_steps": 1230, "loss": 0.2089, "lr": 2.8923938246290917e-07, "epoch": 4.7534177215189874, "percentage": 95.12, "elapsed_time": "1:35:58", "remaining_time": "0:04:55"}
1224
+ {"current_steps": 1171, "total_steps": 1230, "loss": 0.1669, "lr": 2.7970076272514804e-07, "epoch": 4.7574683544303795, "percentage": 95.2, "elapsed_time": "1:36:33", "remaining_time": "0:04:51"}
1225
+ {"current_steps": 1172, "total_steps": 1230, "loss": 0.1933, "lr": 2.703209675663887e-07, "epoch": 4.7615189873417725, "percentage": 95.28, "elapsed_time": "1:37:09", "remaining_time": "0:04:48"}
1226
+ {"current_steps": 1173, "total_steps": 1230, "loss": 0.1796, "lr": 2.6110007253021374e-07, "epoch": 4.7655696202531646, "percentage": 95.37, "elapsed_time": "1:37:44", "remaining_time": "0:04:44"}
1227
+ {"current_steps": 1174, "total_steps": 1230, "loss": 0.204, "lr": 2.520381518804471e-07, "epoch": 4.769620253164557, "percentage": 95.45, "elapsed_time": "1:38:16", "remaining_time": "0:04:41"}
1228
+ {"current_steps": 1175, "total_steps": 1230, "loss": 0.1822, "lr": 2.4313527860054585e-07, "epoch": 4.77367088607595, "percentage": 95.53, "elapsed_time": "1:38:45", "remaining_time": "0:04:37"}
1229
+ {"current_steps": 1176, "total_steps": 1230, "loss": 0.1942, "lr": 2.343915243930317e-07, "epoch": 4.777721518987342, "percentage": 95.61, "elapsed_time": "1:39:16", "remaining_time": "0:04:33"}
1230
+ {"current_steps": 1177, "total_steps": 1230, "loss": 0.1809, "lr": 2.2580695967889367e-07, "epoch": 4.781772151898734, "percentage": 95.69, "elapsed_time": "1:39:46", "remaining_time": "0:04:29"}
1231
+ {"current_steps": 1178, "total_steps": 1230, "loss": 0.1646, "lr": 2.1738165359704189e-07, "epoch": 4.785822784810127, "percentage": 95.77, "elapsed_time": "1:40:16", "remaining_time": "0:04:25"}
1232
+ {"current_steps": 1179, "total_steps": 1230, "loss": 0.1897, "lr": 2.0911567400373257e-07, "epoch": 4.789873417721519, "percentage": 95.85, "elapsed_time": "1:40:49", "remaining_time": "0:04:21"}
1233
+ {"current_steps": 1180, "total_steps": 1230, "loss": 0.1804, "lr": 2.0100908747202607e-07, "epoch": 4.793924050632912, "percentage": 95.93, "elapsed_time": "1:41:17", "remaining_time": "0:04:17"}
1234
+ {"current_steps": 1181, "total_steps": 1230, "loss": 0.1862, "lr": 1.9306195929125638e-07, "epoch": 4.797974683544304, "percentage": 96.02, "elapsed_time": "1:41:49", "remaining_time": "0:04:13"}
1235
+ {"current_steps": 1182, "total_steps": 1230, "loss": 0.1724, "lr": 1.8527435346650247e-07, "epoch": 4.802025316455696, "percentage": 96.1, "elapsed_time": "1:42:22", "remaining_time": "0:04:09"}
1236
+ {"current_steps": 1183, "total_steps": 1230, "loss": 0.1986, "lr": 1.7764633271807108e-07, "epoch": 4.806075949367089, "percentage": 96.18, "elapsed_time": "1:43:00", "remaining_time": "0:04:05"}
1237
+ {"current_steps": 1184, "total_steps": 1230, "loss": 0.1857, "lr": 1.7017795848099262e-07, "epoch": 4.810126582278481, "percentage": 96.26, "elapsed_time": "1:43:33", "remaining_time": "0:04:01"}
1238
+ {"current_steps": 1185, "total_steps": 1230, "loss": 0.1745, "lr": 1.6286929090452596e-07, "epoch": 4.814177215189874, "percentage": 96.34, "elapsed_time": "1:43:59", "remaining_time": "0:03:56"}
1239
+ {"current_steps": 1186, "total_steps": 1230, "loss": 0.2018, "lr": 1.557203888516745e-07, "epoch": 4.818227848101266, "percentage": 96.42, "elapsed_time": "1:44:28", "remaining_time": "0:03:52"}
1240
+ {"current_steps": 1187, "total_steps": 1230, "loss": 0.1791, "lr": 1.487313098987131e-07, "epoch": 4.822278481012658, "percentage": 96.5, "elapsed_time": "1:45:04", "remaining_time": "0:03:48"}
1241
+ {"current_steps": 1188, "total_steps": 1230, "loss": 0.1728, "lr": 1.4190211033472402e-07, "epoch": 4.826329113924051, "percentage": 96.59, "elapsed_time": "1:45:33", "remaining_time": "0:03:43"}
1242
+ {"current_steps": 1189, "total_steps": 1230, "loss": 0.1789, "lr": 1.3523284516113955e-07, "epoch": 4.830379746835443, "percentage": 96.67, "elapsed_time": "1:46:01", "remaining_time": "0:03:39"}
1243
+ {"current_steps": 1190, "total_steps": 1230, "loss": 0.171, "lr": 1.2872356809130682e-07, "epoch": 4.834430379746835, "percentage": 96.75, "elapsed_time": "1:46:33", "remaining_time": "0:03:34"}
1244
+ {"current_steps": 1191, "total_steps": 1230, "loss": 0.1925, "lr": 1.2237433155004807e-07, "epoch": 4.838481012658228, "percentage": 96.83, "elapsed_time": "1:47:03", "remaining_time": "0:03:30"}
1245
+ {"current_steps": 1192, "total_steps": 1230, "loss": 0.1855, "lr": 1.1618518667323886e-07, "epoch": 4.84253164556962, "percentage": 96.91, "elapsed_time": "1:47:36", "remaining_time": "0:03:25"}
1246
+ {"current_steps": 1193, "total_steps": 1230, "loss": 0.1907, "lr": 1.1015618330740385e-07, "epoch": 4.846582278481012, "percentage": 96.99, "elapsed_time": "1:48:04", "remaining_time": "0:03:21"}
1247
+ {"current_steps": 1194, "total_steps": 1230, "loss": 0.1678, "lr": 1.042873700093061e-07, "epoch": 4.850632911392405, "percentage": 97.07, "elapsed_time": "1:48:34", "remaining_time": "0:03:16"}
1248
+ {"current_steps": 1195, "total_steps": 1230, "loss": 0.1894, "lr": 9.857879404556291e-08, "epoch": 4.854683544303797, "percentage": 97.15, "elapsed_time": "1:48:59", "remaining_time": "0:03:11"}
1249
+ {"current_steps": 1196, "total_steps": 1230, "loss": 0.1957, "lr": 9.303050139225722e-08, "epoch": 4.85873417721519, "percentage": 97.24, "elapsed_time": "1:49:33", "remaining_time": "0:03:06"}
1250
+ {"current_steps": 1197, "total_steps": 1230, "loss": 0.1709, "lr": 8.76425367345779e-08, "epoch": 4.862784810126582, "percentage": 97.32, "elapsed_time": "1:50:04", "remaining_time": "0:03:02"}
1251
+ {"current_steps": 1198, "total_steps": 1230, "loss": 0.1924, "lr": 8.241494346644897e-08, "epoch": 4.866835443037974, "percentage": 97.4, "elapsed_time": "1:50:32", "remaining_time": "0:02:57"}
1252
+ {"current_steps": 1199, "total_steps": 1230, "loss": 0.1719, "lr": 7.734776369019204e-08, "epoch": 4.870886075949367, "percentage": 97.48, "elapsed_time": "1:51:07", "remaining_time": "0:02:52"}
1253
+ {"current_steps": 1200, "total_steps": 1230, "loss": 0.1726, "lr": 7.244103821617332e-08, "epoch": 4.874936708860759, "percentage": 97.56, "elapsed_time": "1:51:39", "remaining_time": "0:02:47"}
1254
+ {"current_steps": 1201, "total_steps": 1230, "loss": 0.1965, "lr": 6.769480656248606e-08, "epoch": 4.878987341772152, "percentage": 97.64, "elapsed_time": "1:52:12", "remaining_time": "0:02:42"}
1255
+ {"current_steps": 1202, "total_steps": 1230, "loss": 0.1681, "lr": 6.310910695462635e-08, "epoch": 4.883037974683544, "percentage": 97.72, "elapsed_time": "1:52:39", "remaining_time": "0:02:37"}
1256
+ {"current_steps": 1203, "total_steps": 1230, "loss": 0.1682, "lr": 5.8683976325191185e-08, "epoch": 4.8870886075949365, "percentage": 97.8, "elapsed_time": "1:53:12", "remaining_time": "0:02:32"}
1257
+ {"current_steps": 1204, "total_steps": 1230, "loss": 0.2096, "lr": 5.4419450313571984e-08, "epoch": 4.891139240506329, "percentage": 97.89, "elapsed_time": "1:53:47", "remaining_time": "0:02:27"}
1258
+ {"current_steps": 1205, "total_steps": 1230, "loss": 0.1944, "lr": 5.031556326567488e-08, "epoch": 4.8951898734177215, "percentage": 97.97, "elapsed_time": "1:54:24", "remaining_time": "0:02:22"}
1259
+ {"current_steps": 1206, "total_steps": 1230, "loss": 0.2026, "lr": 4.637234823364312e-08, "epoch": 4.899240506329114, "percentage": 98.05, "elapsed_time": "1:54:53", "remaining_time": "0:02:17"}
1260
+ {"current_steps": 1207, "total_steps": 1230, "loss": 0.1851, "lr": 4.258983697558838e-08, "epoch": 4.9032911392405065, "percentage": 98.13, "elapsed_time": "1:55:30", "remaining_time": "0:02:12"}
1261
+ {"current_steps": 1208, "total_steps": 1230, "loss": 0.178, "lr": 3.896805995533548e-08, "epoch": 4.907341772151899, "percentage": 98.21, "elapsed_time": "1:56:00", "remaining_time": "0:02:06"}
1262
+ {"current_steps": 1209, "total_steps": 1230, "loss": 0.2029, "lr": 3.550704634218028e-08, "epoch": 4.911392405063291, "percentage": 98.29, "elapsed_time": "1:56:31", "remaining_time": "0:02:01"}
1263
+ {"current_steps": 1210, "total_steps": 1230, "loss": 0.1822, "lr": 3.2206824010647676e-08, "epoch": 4.915443037974684, "percentage": 98.37, "elapsed_time": "1:57:04", "remaining_time": "0:01:56"}
1264
+ {"current_steps": 1211, "total_steps": 1230, "loss": 0.1821, "lr": 2.9067419540278476e-08, "epoch": 4.919493670886076, "percentage": 98.46, "elapsed_time": "1:57:29", "remaining_time": "0:01:50"}
1265
+ {"current_steps": 1212, "total_steps": 1230, "loss": 0.1926, "lr": 2.6088858215400638e-08, "epoch": 4.923544303797469, "percentage": 98.54, "elapsed_time": "1:57:59", "remaining_time": "0:01:45"}
1266
+ {"current_steps": 1213, "total_steps": 1230, "loss": 0.1909, "lr": 2.3271164024940564e-08, "epoch": 4.927594936708861, "percentage": 98.62, "elapsed_time": "1:58:34", "remaining_time": "0:01:39"}
1267
+ {"current_steps": 1214, "total_steps": 1230, "loss": 0.1872, "lr": 2.061435966221881e-08, "epoch": 4.931645569620253, "percentage": 98.7, "elapsed_time": "1:59:07", "remaining_time": "0:01:34"}
1268
+ {"current_steps": 1215, "total_steps": 1230, "loss": 0.1959, "lr": 1.811846652477245e-08, "epoch": 4.935696202531646, "percentage": 98.78, "elapsed_time": "1:59:40", "remaining_time": "0:01:28"}
1269
+ {"current_steps": 1216, "total_steps": 1230, "loss": 0.1821, "lr": 1.5783504714184106e-08, "epoch": 4.939746835443038, "percentage": 98.86, "elapsed_time": "2:00:09", "remaining_time": "0:01:23"}
1270
+ {"current_steps": 1217, "total_steps": 1230, "loss": 0.1785, "lr": 1.360949303591097e-08, "epoch": 4.943797468354431, "percentage": 98.94, "elapsed_time": "2:00:43", "remaining_time": "0:01:17"}
1271
+ {"current_steps": 1218, "total_steps": 1230, "loss": 0.2115, "lr": 1.1596448999144916e-08, "epoch": 4.947848101265823, "percentage": 99.02, "elapsed_time": "2:01:21", "remaining_time": "0:01:11"}
1272
+ {"current_steps": 1219, "total_steps": 1230, "loss": 0.1868, "lr": 9.744388816668172e-09, "epoch": 4.951898734177215, "percentage": 99.11, "elapsed_time": "2:01:50", "remaining_time": "0:01:05"}
1273
+ {"current_steps": 1220, "total_steps": 1230, "loss": 0.182, "lr": 8.05332740472009e-09, "epoch": 4.955949367088608, "percentage": 99.19, "elapsed_time": "2:02:21", "remaining_time": "0:01:00"}
1274
+ {"current_steps": 1221, "total_steps": 1230, "loss": 0.1949, "lr": 6.523278382872811e-09, "epoch": 4.96, "percentage": 99.27, "elapsed_time": "2:02:50", "remaining_time": "0:00:54"}
1275
+ {"current_steps": 1222, "total_steps": 1230, "loss": 0.1806, "lr": 5.15425407393133e-09, "epoch": 4.964050632911392, "percentage": 99.35, "elapsed_time": "2:03:25", "remaining_time": "0:00:48"}
1276
+ {"current_steps": 1223, "total_steps": 1230, "loss": 0.1842, "lr": 3.94626550383137e-09, "epoch": 4.968101265822785, "percentage": 99.43, "elapsed_time": "2:03:53", "remaining_time": "0:00:42"}
1277
+ {"current_steps": 1224, "total_steps": 1230, "loss": 0.1792, "lr": 2.899322401546112e-09, "epoch": 4.972151898734177, "percentage": 99.51, "elapsed_time": "2:04:22", "remaining_time": "0:00:36"}
1278
+ {"current_steps": 1225, "total_steps": 1230, "loss": 0.1809, "lr": 2.013433199010706e-09, "epoch": 4.976202531645569, "percentage": 99.59, "elapsed_time": "2:04:51", "remaining_time": "0:00:30"}
1279
+ {"current_steps": 1226, "total_steps": 1230, "loss": 0.1723, "lr": 1.2886050310556563e-09, "epoch": 4.980253164556962, "percentage": 99.67, "elapsed_time": "2:05:25", "remaining_time": "0:00:24"}
1280
+ {"current_steps": 1227, "total_steps": 1230, "loss": 0.2027, "lr": 7.248437353468695e-10, "epoch": 4.984303797468354, "percentage": 99.76, "elapsed_time": "2:06:03", "remaining_time": "0:00:18"}
1281
+ {"current_steps": 1228, "total_steps": 1230, "loss": 0.1795, "lr": 3.221538523412449e-10, "epoch": 4.988354430379747, "percentage": 99.84, "elapsed_time": "2:06:38", "remaining_time": "0:00:12"}
1282
+ {"current_steps": 1229, "total_steps": 1230, "loss": 0.1748, "lr": 8.053862524670663e-11, "epoch": 4.992405063291139, "percentage": 99.92, "elapsed_time": "2:07:13", "remaining_time": "0:00:06"}
1283
+ {"current_steps": 1230, "total_steps": 1230, "loss": 0.1637, "lr": 0.0, "epoch": 4.996455696202531, "percentage": 100.0, "elapsed_time": "2:07:45", "remaining_time": "0:00:00"}
1284
+ {"current_steps": 1230, "total_steps": 1230, "epoch": 4.996455696202531, "percentage": 100.0, "elapsed_time": "2:11:06", "remaining_time": "0:00:00"}
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:10297286d6545f1b308ec8c3ba3b9b510f8a7d4e278d157f3ad7bf77911b874a
3
- size 7224
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6dd6987f1a31637d0d06483fd1f40ba9e4cb6882f1007f103734ec5b104c67e
3
+ size 7288