neginr commited on
Commit
f18c15a
·
verified ·
1 Parent(s): d115b4e

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 sha256:1cd705d43bf2ee195f6da60111faed90743ebac4c04f149598429abe9e39e4f9
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0bc40c024c22b9e1b2186e8e7a4c2f3a500b35929b69715cfb5c19a89a4c4d18
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:fe071e3a4141e03a8b80672bfa60da43ca008145d34291daf61c0add4c059f42
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68335e3a2df2bfa81c56efcaffcbebb309c34002d558c616927dfc04b16713f8
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8d5012e7deb44193dda31bc4fdfea1bbb030ad14b9d44c8b1580d96723dc85dc
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4879c9f5c4842d67a20b9af021fee91168f94cb6afc4974b706950dcdaadbaf
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8b91b1c156683bf598c38137c0d098276e568097ee68a560b9aa59e3deb387a1
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9618c42244a6cbe7bd076cf638215b4d77a9b2f745ad26a237dc198183aef9ee
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -1104,3 +1104,243 @@
1104
  {"current_steps": 989, "total_steps": 1230, "loss": 0.1877, "lr": 4.498240773728859e-06, "epoch": 4.013164556962026, "percentage": 80.41, "elapsed_time": "4:31:10", "remaining_time": "1:06:04"}
1105
  {"current_steps": 990, "total_steps": 1230, "loss": 0.2029, "lr": 4.462440087699609e-06, "epoch": 4.017215189873418, "percentage": 80.49, "elapsed_time": "4:31:39", "remaining_time": "1:05:51"}
1106
  {"current_steps": 991, "total_steps": 1230, "loss": 0.195, "lr": 4.426764539041861e-06, "epoch": 4.02126582278481, "percentage": 80.57, "elapsed_time": "4:32:13", "remaining_time": "1:05:39"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1104
  {"current_steps": 989, "total_steps": 1230, "loss": 0.1877, "lr": 4.498240773728859e-06, "epoch": 4.013164556962026, "percentage": 80.41, "elapsed_time": "4:31:10", "remaining_time": "1:06:04"}
1105
  {"current_steps": 990, "total_steps": 1230, "loss": 0.2029, "lr": 4.462440087699609e-06, "epoch": 4.017215189873418, "percentage": 80.49, "elapsed_time": "4:31:39", "remaining_time": "1:05:51"}
1106
  {"current_steps": 991, "total_steps": 1230, "loss": 0.195, "lr": 4.426764539041861e-06, "epoch": 4.02126582278481, "percentage": 80.57, "elapsed_time": "4:32:13", "remaining_time": "1:05:39"}
1107
+ {"current_steps": 992, "total_steps": 1230, "loss": 0.1864, "lr": 4.391214415081582e-06, "epoch": 4.025316455696203, "percentage": 80.65, "elapsed_time": "4:32:40", "remaining_time": "1:05:25"}
1108
+ {"current_steps": 993, "total_steps": 1230, "loss": 0.2231, "lr": 4.355790002134579e-06, "epoch": 4.029367088607595, "percentage": 80.73, "elapsed_time": "4:33:09", "remaining_time": "1:05:11"}
1109
+ {"current_steps": 994, "total_steps": 1230, "loss": 0.2039, "lr": 4.320491585504207e-06, "epoch": 4.033417721518988, "percentage": 80.81, "elapsed_time": "4:33:41", "remaining_time": "1:04:58"}
1110
+ {"current_steps": 995, "total_steps": 1230, "loss": 0.1985, "lr": 4.2853194494790615e-06, "epoch": 4.03746835443038, "percentage": 80.89, "elapsed_time": "4:34:11", "remaining_time": "1:04:45"}
1111
+ {"current_steps": 996, "total_steps": 1230, "loss": 0.2108, "lr": 4.250273877330691e-06, "epoch": 4.041518987341772, "percentage": 80.98, "elapsed_time": "4:34:41", "remaining_time": "1:04:32"}
1112
+ {"current_steps": 997, "total_steps": 1230, "loss": 0.2019, "lr": 4.215355151311313e-06, "epoch": 4.045569620253165, "percentage": 81.06, "elapsed_time": "4:35:17", "remaining_time": "1:04:20"}
1113
+ {"current_steps": 998, "total_steps": 1230, "loss": 0.1935, "lr": 4.180563552651542e-06, "epoch": 4.049620253164557, "percentage": 81.14, "elapsed_time": "4:35:44", "remaining_time": "1:04:06"}
1114
+ {"current_steps": 999, "total_steps": 1230, "loss": 0.207, "lr": 4.145899361558147e-06, "epoch": 4.053670886075949, "percentage": 81.22, "elapsed_time": "4:36:20", "remaining_time": "1:03:53"}
1115
+ {"current_steps": 1000, "total_steps": 1230, "loss": 0.1902, "lr": 4.111362857211738e-06, "epoch": 4.057721518987342, "percentage": 81.3, "elapsed_time": "4:36:50", "remaining_time": "1:03:40"}
1116
+ {"current_steps": 1001, "total_steps": 1230, "loss": 0.196, "lr": 4.076954317764592e-06, "epoch": 4.061772151898734, "percentage": 81.38, "elapsed_time": "4:37:19", "remaining_time": "1:03:26"}
1117
+ {"current_steps": 1002, "total_steps": 1230, "loss": 0.1966, "lr": 4.042674020338335e-06, "epoch": 4.065822784810127, "percentage": 81.46, "elapsed_time": "4:37:46", "remaining_time": "1:03:12"}
1118
+ {"current_steps": 1003, "total_steps": 1230, "loss": 0.1959, "lr": 4.0085222410217835e-06, "epoch": 4.069873417721519, "percentage": 81.54, "elapsed_time": "4:38:17", "remaining_time": "1:02:59"}
1119
+ {"current_steps": 1004, "total_steps": 1230, "loss": 0.1975, "lr": 3.974499254868674e-06, "epoch": 4.073924050632911, "percentage": 81.63, "elapsed_time": "4:38:47", "remaining_time": "1:02:45"}
1120
+ {"current_steps": 1005, "total_steps": 1230, "loss": 0.1865, "lr": 3.940605335895451e-06, "epoch": 4.077974683544304, "percentage": 81.71, "elapsed_time": "4:39:18", "remaining_time": "1:02:31"}
1121
+ {"current_steps": 1006, "total_steps": 1230, "loss": 0.197, "lr": 3.90684075707908e-06, "epoch": 4.082025316455696, "percentage": 81.79, "elapsed_time": "4:39:51", "remaining_time": "1:02:18"}
1122
+ {"current_steps": 1007, "total_steps": 1230, "loss": 0.1662, "lr": 3.8732057903548505e-06, "epoch": 4.086075949367088, "percentage": 81.87, "elapsed_time": "4:40:25", "remaining_time": "1:02:06"}
1123
+ {"current_steps": 1008, "total_steps": 1230, "loss": 0.1888, "lr": 3.8397007066141375e-06, "epoch": 4.090126582278481, "percentage": 81.95, "elapsed_time": "4:40:56", "remaining_time": "1:01:52"}
1124
+ {"current_steps": 1009, "total_steps": 1230, "loss": 0.2056, "lr": 3.806325775702304e-06, "epoch": 4.094177215189873, "percentage": 82.03, "elapsed_time": "4:41:32", "remaining_time": "1:01:39"}
1125
+ {"current_steps": 1010, "total_steps": 1230, "loss": 0.1871, "lr": 3.773081266416434e-06, "epoch": 4.098227848101266, "percentage": 82.11, "elapsed_time": "4:42:03", "remaining_time": "1:01:26"}
1126
+ {"current_steps": 1011, "total_steps": 1230, "loss": 0.17, "lr": 3.739967446503245e-06, "epoch": 4.102278481012658, "percentage": 82.2, "elapsed_time": "4:42:29", "remaining_time": "1:01:11"}
1127
+ {"current_steps": 1012, "total_steps": 1230, "loss": 0.203, "lr": 3.706984582656894e-06, "epoch": 4.10632911392405, "percentage": 82.28, "elapsed_time": "4:42:58", "remaining_time": "1:00:57"}
1128
+ {"current_steps": 1013, "total_steps": 1230, "loss": 0.2059, "lr": 3.6741329405168237e-06, "epoch": 4.110379746835443, "percentage": 82.36, "elapsed_time": "4:43:35", "remaining_time": "1:00:44"}
1129
+ {"current_steps": 1014, "total_steps": 1230, "loss": 0.1833, "lr": 3.641412784665648e-06, "epoch": 4.114430379746835, "percentage": 82.44, "elapsed_time": "4:43:59", "remaining_time": "1:00:29"}
1130
+ {"current_steps": 1015, "total_steps": 1230, "loss": 0.1944, "lr": 3.608824378627005e-06, "epoch": 4.118481012658227, "percentage": 82.52, "elapsed_time": "4:44:32", "remaining_time": "1:00:16"}
1131
+ {"current_steps": 1016, "total_steps": 1230, "loss": 0.2076, "lr": 3.5763679848634337e-06, "epoch": 4.12253164556962, "percentage": 82.6, "elapsed_time": "4:45:00", "remaining_time": "1:00:01"}
1132
+ {"current_steps": 1017, "total_steps": 1230, "loss": 0.2121, "lr": 3.544043864774269e-06, "epoch": 4.1265822784810124, "percentage": 82.68, "elapsed_time": "4:45:34", "remaining_time": "0:59:48"}
1133
+ {"current_steps": 1018, "total_steps": 1230, "loss": 0.18, "lr": 3.5118522786935282e-06, "epoch": 4.130632911392405, "percentage": 82.76, "elapsed_time": "4:46:05", "remaining_time": "0:59:34"}
1134
+ {"current_steps": 1019, "total_steps": 1230, "loss": 0.1888, "lr": 3.479793485887819e-06, "epoch": 4.1346835443037975, "percentage": 82.85, "elapsed_time": "4:46:35", "remaining_time": "0:59:20"}
1135
+ {"current_steps": 1020, "total_steps": 1230, "loss": 0.2149, "lr": 3.4478677445542653e-06, "epoch": 4.1387341772151895, "percentage": 82.93, "elapsed_time": "4:47:09", "remaining_time": "0:59:07"}
1136
+ {"current_steps": 1021, "total_steps": 1230, "loss": 0.2118, "lr": 3.4160753118183767e-06, "epoch": 4.1427848101265825, "percentage": 83.01, "elapsed_time": "4:47:43", "remaining_time": "0:58:53"}
1137
+ {"current_steps": 1022, "total_steps": 1230, "loss": 0.1956, "lr": 3.3844164437320527e-06, "epoch": 4.146835443037975, "percentage": 83.09, "elapsed_time": "4:48:14", "remaining_time": "0:58:39"}
1138
+ {"current_steps": 1023, "total_steps": 1230, "loss": 0.2174, "lr": 3.3528913952714558e-06, "epoch": 4.1508860759493675, "percentage": 83.17, "elapsed_time": "4:48:52", "remaining_time": "0:58:27"}
1139
+ {"current_steps": 1024, "total_steps": 1230, "loss": 0.2098, "lr": 3.321500420335e-06, "epoch": 4.15493670886076, "percentage": 83.25, "elapsed_time": "4:49:22", "remaining_time": "0:58:12"}
1140
+ {"current_steps": 1025, "total_steps": 1230, "loss": 0.2208, "lr": 3.290243771741275e-06, "epoch": 4.158987341772152, "percentage": 83.33, "elapsed_time": "4:49:55", "remaining_time": "0:57:59"}
1141
+ {"current_steps": 1026, "total_steps": 1230, "loss": 0.2015, "lr": 3.2591217012270325e-06, "epoch": 4.163037974683545, "percentage": 83.41, "elapsed_time": "4:50:26", "remaining_time": "0:57:44"}
1142
+ {"current_steps": 1027, "total_steps": 1230, "loss": 0.2074, "lr": 3.228134459445149e-06, "epoch": 4.167088607594937, "percentage": 83.5, "elapsed_time": "4:50:54", "remaining_time": "0:57:30"}
1143
+ {"current_steps": 1028, "total_steps": 1230, "loss": 0.2044, "lr": 3.1972822959626205e-06, "epoch": 4.171139240506329, "percentage": 83.58, "elapsed_time": "4:51:26", "remaining_time": "0:57:16"}
1144
+ {"current_steps": 1029, "total_steps": 1230, "loss": 0.2073, "lr": 3.166565459258513e-06, "epoch": 4.175189873417722, "percentage": 83.66, "elapsed_time": "4:51:58", "remaining_time": "0:57:01"}
1145
+ {"current_steps": 1030, "total_steps": 1230, "loss": 0.1956, "lr": 3.1359841967220193e-06, "epoch": 4.179240506329114, "percentage": 83.74, "elapsed_time": "4:52:32", "remaining_time": "0:56:48"}
1146
+ {"current_steps": 1031, "total_steps": 1230, "loss": 0.2069, "lr": 3.105538754650419e-06, "epoch": 4.183291139240506, "percentage": 83.82, "elapsed_time": "4:53:05", "remaining_time": "0:56:34"}
1147
+ {"current_steps": 1032, "total_steps": 1230, "loss": 0.2114, "lr": 3.07522937824712e-06, "epoch": 4.187341772151899, "percentage": 83.9, "elapsed_time": "4:53:37", "remaining_time": "0:56:20"}
1148
+ {"current_steps": 1033, "total_steps": 1230, "loss": 0.2041, "lr": 3.0450563116196697e-06, "epoch": 4.191392405063291, "percentage": 83.98, "elapsed_time": "4:54:06", "remaining_time": "0:56:05"}
1149
+ {"current_steps": 1034, "total_steps": 1230, "loss": 0.2032, "lr": 3.0150197977778008e-06, "epoch": 4.195443037974684, "percentage": 84.07, "elapsed_time": "4:54:39", "remaining_time": "0:55:51"}
1150
+ {"current_steps": 1035, "total_steps": 1230, "loss": 0.1921, "lr": 2.985120078631465e-06, "epoch": 4.199493670886076, "percentage": 84.15, "elapsed_time": "4:55:08", "remaining_time": "0:55:36"}
1151
+ {"current_steps": 1036, "total_steps": 1230, "loss": 0.2032, "lr": 2.9553573949888893e-06, "epoch": 4.203544303797468, "percentage": 84.23, "elapsed_time": "4:55:40", "remaining_time": "0:55:22"}
1152
+ {"current_steps": 1037, "total_steps": 1230, "loss": 0.1647, "lr": 2.9257319865546384e-06, "epoch": 4.207594936708861, "percentage": 84.31, "elapsed_time": "4:56:10", "remaining_time": "0:55:07"}
1153
+ {"current_steps": 1038, "total_steps": 1230, "loss": 0.2037, "lr": 2.896244091927678e-06, "epoch": 4.211645569620253, "percentage": 84.39, "elapsed_time": "4:56:47", "remaining_time": "0:54:53"}
1154
+ {"current_steps": 1039, "total_steps": 1230, "loss": 0.2131, "lr": 2.8668939485994584e-06, "epoch": 4.215696202531646, "percentage": 84.47, "elapsed_time": "4:57:19", "remaining_time": "0:54:39"}
1155
+ {"current_steps": 1040, "total_steps": 1230, "loss": 0.224, "lr": 2.837681792951994e-06, "epoch": 4.219746835443038, "percentage": 84.55, "elapsed_time": "4:57:53", "remaining_time": "0:54:25"}
1156
+ {"current_steps": 1041, "total_steps": 1230, "loss": 0.2089, "lr": 2.808607860255981e-06, "epoch": 4.22379746835443, "percentage": 84.63, "elapsed_time": "4:58:27", "remaining_time": "0:54:11"}
1157
+ {"current_steps": 1042, "total_steps": 1230, "loss": 0.1984, "lr": 2.7796723846688634e-06, "epoch": 4.227848101265823, "percentage": 84.72, "elapsed_time": "4:58:59", "remaining_time": "0:53:56"}
1158
+ {"current_steps": 1043, "total_steps": 1230, "loss": 0.2199, "lr": 2.7508755992329937e-06, "epoch": 4.231898734177215, "percentage": 84.8, "elapsed_time": "4:59:30", "remaining_time": "0:53:41"}
1159
+ {"current_steps": 1044, "total_steps": 1230, "loss": 0.1929, "lr": 2.722217735873718e-06, "epoch": 4.235949367088607, "percentage": 84.88, "elapsed_time": "5:00:02", "remaining_time": "0:53:27"}
1160
+ {"current_steps": 1045, "total_steps": 1230, "loss": 0.2041, "lr": 2.6936990253975315e-06, "epoch": 4.24, "percentage": 84.96, "elapsed_time": "5:00:38", "remaining_time": "0:53:13"}
1161
+ {"current_steps": 1046, "total_steps": 1230, "loss": 0.198, "lr": 2.665319697490205e-06, "epoch": 4.244050632911392, "percentage": 85.04, "elapsed_time": "5:01:10", "remaining_time": "0:52:58"}
1162
+ {"current_steps": 1047, "total_steps": 1230, "loss": 0.1789, "lr": 2.637079980714945e-06, "epoch": 4.248101265822784, "percentage": 85.12, "elapsed_time": "5:01:40", "remaining_time": "0:52:43"}
1163
+ {"current_steps": 1048, "total_steps": 1230, "loss": 0.1651, "lr": 2.6089801025105453e-06, "epoch": 4.252151898734177, "percentage": 85.2, "elapsed_time": "5:02:12", "remaining_time": "0:52:28"}
1164
+ {"current_steps": 1049, "total_steps": 1230, "loss": 0.211, "lr": 2.581020289189571e-06, "epoch": 4.256202531645569, "percentage": 85.28, "elapsed_time": "5:02:47", "remaining_time": "0:52:14"}
1165
+ {"current_steps": 1050, "total_steps": 1230, "loss": 0.1999, "lr": 2.553200765936501e-06, "epoch": 4.260253164556962, "percentage": 85.37, "elapsed_time": "5:03:19", "remaining_time": "0:51:59"}
1166
+ {"current_steps": 1051, "total_steps": 1230, "loss": 0.1857, "lr": 2.525521756805962e-06, "epoch": 4.264303797468354, "percentage": 85.45, "elapsed_time": "5:03:50", "remaining_time": "0:51:44"}
1167
+ {"current_steps": 1052, "total_steps": 1230, "loss": 0.2093, "lr": 2.497983484720885e-06, "epoch": 4.2683544303797465, "percentage": 85.53, "elapsed_time": "5:04:21", "remaining_time": "0:51:29"}
1168
+ {"current_steps": 1053, "total_steps": 1230, "loss": 0.1901, "lr": 2.470586171470728e-06, "epoch": 4.2724050632911394, "percentage": 85.61, "elapsed_time": "5:04:57", "remaining_time": "0:51:15"}
1169
+ {"current_steps": 1054, "total_steps": 1230, "loss": 0.1942, "lr": 2.4433300377096836e-06, "epoch": 4.2764556962025315, "percentage": 85.69, "elapsed_time": "5:05:26", "remaining_time": "0:51:00"}
1170
+ {"current_steps": 1055, "total_steps": 1230, "loss": 0.2061, "lr": 2.4162153029549073e-06, "epoch": 4.2805063291139245, "percentage": 85.77, "elapsed_time": "5:05:57", "remaining_time": "0:50:45"}
1171
+ {"current_steps": 1056, "total_steps": 1230, "loss": 0.2018, "lr": 2.3892421855847458e-06, "epoch": 4.2845569620253166, "percentage": 85.85, "elapsed_time": "5:06:33", "remaining_time": "0:50:30"}
1172
+ {"current_steps": 1057, "total_steps": 1230, "loss": 0.2012, "lr": 2.362410902836978e-06, "epoch": 4.288607594936709, "percentage": 85.93, "elapsed_time": "5:07:06", "remaining_time": "0:50:15"}
1173
+ {"current_steps": 1058, "total_steps": 1230, "loss": 0.1946, "lr": 2.3357216708070653e-06, "epoch": 4.292658227848102, "percentage": 86.02, "elapsed_time": "5:07:40", "remaining_time": "0:50:01"}
1174
+ {"current_steps": 1059, "total_steps": 1230, "loss": 0.2088, "lr": 2.309174704446411e-06, "epoch": 4.296708860759494, "percentage": 86.1, "elapsed_time": "5:08:11", "remaining_time": "0:49:45"}
1175
+ {"current_steps": 1060, "total_steps": 1230, "loss": 0.211, "lr": 2.2827702175606437e-06, "epoch": 4.300759493670886, "percentage": 86.18, "elapsed_time": "5:08:45", "remaining_time": "0:49:31"}
1176
+ {"current_steps": 1061, "total_steps": 1230, "loss": 0.1951, "lr": 2.256508422807855e-06, "epoch": 4.304810126582279, "percentage": 86.26, "elapsed_time": "5:09:20", "remaining_time": "0:49:16"}
1177
+ {"current_steps": 1062, "total_steps": 1230, "loss": 0.1975, "lr": 2.230389531696946e-06, "epoch": 4.308860759493671, "percentage": 86.34, "elapsed_time": "5:09:54", "remaining_time": "0:49:01"}
1178
+ {"current_steps": 1063, "total_steps": 1230, "loss": 0.1904, "lr": 2.204413754585857e-06, "epoch": 4.312911392405063, "percentage": 86.42, "elapsed_time": "5:10:29", "remaining_time": "0:48:46"}
1179
+ {"current_steps": 1064, "total_steps": 1230, "loss": 0.1832, "lr": 2.1785813006799406e-06, "epoch": 4.316962025316456, "percentage": 86.5, "elapsed_time": "5:11:01", "remaining_time": "0:48:31"}
1180
+ {"current_steps": 1065, "total_steps": 1230, "loss": 0.2142, "lr": 2.1528923780302224e-06, "epoch": 4.321012658227848, "percentage": 86.59, "elapsed_time": "5:11:31", "remaining_time": "0:48:15"}
1181
+ {"current_steps": 1066, "total_steps": 1230, "loss": 0.2134, "lr": 2.127347193531757e-06, "epoch": 4.325063291139241, "percentage": 86.67, "elapsed_time": "5:12:06", "remaining_time": "0:48:01"}
1182
+ {"current_steps": 1067, "total_steps": 1230, "loss": 0.1849, "lr": 2.101945952921942e-06, "epoch": 4.329113924050633, "percentage": 86.75, "elapsed_time": "5:12:37", "remaining_time": "0:47:45"}
1183
+ {"current_steps": 1068, "total_steps": 1230, "loss": 0.2112, "lr": 2.0766888607788906e-06, "epoch": 4.333164556962025, "percentage": 86.83, "elapsed_time": "5:13:10", "remaining_time": "0:47:30"}
1184
+ {"current_steps": 1069, "total_steps": 1230, "loss": 0.218, "lr": 2.0515761205197337e-06, "epoch": 4.337215189873418, "percentage": 86.91, "elapsed_time": "5:13:40", "remaining_time": "0:47:14"}
1185
+ {"current_steps": 1070, "total_steps": 1230, "loss": 0.1909, "lr": 2.0266079343990453e-06, "epoch": 4.34126582278481, "percentage": 86.99, "elapsed_time": "5:14:12", "remaining_time": "0:46:59"}
1186
+ {"current_steps": 1071, "total_steps": 1230, "loss": 0.2187, "lr": 2.0017845035071494e-06, "epoch": 4.345316455696203, "percentage": 87.07, "elapsed_time": "5:14:48", "remaining_time": "0:46:44"}
1187
+ {"current_steps": 1072, "total_steps": 1230, "loss": 0.241, "lr": 1.9771060277685537e-06, "epoch": 4.349367088607595, "percentage": 87.15, "elapsed_time": "5:15:24", "remaining_time": "0:46:29"}
1188
+ {"current_steps": 1073, "total_steps": 1230, "loss": 0.235, "lr": 1.95257270594031e-06, "epoch": 4.353417721518987, "percentage": 87.24, "elapsed_time": "5:15:57", "remaining_time": "0:46:13"}
1189
+ {"current_steps": 1074, "total_steps": 1230, "loss": 0.1924, "lr": 1.9281847356104188e-06, "epoch": 4.35746835443038, "percentage": 87.32, "elapsed_time": "5:16:27", "remaining_time": "0:45:58"}
1190
+ {"current_steps": 1075, "total_steps": 1230, "loss": 0.2038, "lr": 1.9039423131962365e-06, "epoch": 4.361518987341772, "percentage": 87.4, "elapsed_time": "5:17:02", "remaining_time": "0:45:42"}
1191
+ {"current_steps": 1076, "total_steps": 1230, "loss": 0.2199, "lr": 1.8798456339429027e-06, "epoch": 4.365569620253164, "percentage": 87.48, "elapsed_time": "5:17:38", "remaining_time": "0:45:27"}
1192
+ {"current_steps": 1077, "total_steps": 1230, "loss": 0.1946, "lr": 1.8558948919217612e-06, "epoch": 4.369620253164557, "percentage": 87.56, "elapsed_time": "5:18:03", "remaining_time": "0:45:11"}
1193
+ {"current_steps": 1078, "total_steps": 1230, "loss": 0.2097, "lr": 1.8320902800287954e-06, "epoch": 4.373670886075949, "percentage": 87.64, "elapsed_time": "5:18:38", "remaining_time": "0:44:55"}
1194
+ {"current_steps": 1079, "total_steps": 1230, "loss": 0.1943, "lr": 1.8084319899830726e-06, "epoch": 4.377721518987342, "percentage": 87.72, "elapsed_time": "5:19:15", "remaining_time": "0:44:40"}
1195
+ {"current_steps": 1080, "total_steps": 1230, "loss": 0.214, "lr": 1.7849202123252097e-06, "epoch": 4.381772151898734, "percentage": 87.8, "elapsed_time": "5:19:46", "remaining_time": "0:44:24"}
1196
+ {"current_steps": 1081, "total_steps": 1230, "loss": 0.1921, "lr": 1.7615551364158401e-06, "epoch": 4.385822784810126, "percentage": 87.89, "elapsed_time": "5:20:20", "remaining_time": "0:44:09"}
1197
+ {"current_steps": 1082, "total_steps": 1230, "loss": 0.181, "lr": 1.738336950434061e-06, "epoch": 4.389873417721519, "percentage": 87.97, "elapsed_time": "5:20:51", "remaining_time": "0:43:53"}
1198
+ {"current_steps": 1083, "total_steps": 1230, "loss": 0.196, "lr": 1.715265841375957e-06, "epoch": 4.393924050632911, "percentage": 88.05, "elapsed_time": "5:21:21", "remaining_time": "0:43:37"}
1199
+ {"current_steps": 1084, "total_steps": 1230, "loss": 0.2044, "lr": 1.6923419950530684e-06, "epoch": 4.397974683544303, "percentage": 88.13, "elapsed_time": "5:21:59", "remaining_time": "0:43:22"}
1200
+ {"current_steps": 1085, "total_steps": 1230, "loss": 0.1902, "lr": 1.6695655960909008e-06, "epoch": 4.402025316455696, "percentage": 88.21, "elapsed_time": "5:22:28", "remaining_time": "0:43:05"}
1201
+ {"current_steps": 1086, "total_steps": 1230, "loss": 0.2025, "lr": 1.646936827927441e-06, "epoch": 4.4060759493670885, "percentage": 88.29, "elapsed_time": "5:23:01", "remaining_time": "0:42:49"}
1202
+ {"current_steps": 1087, "total_steps": 1230, "loss": 0.2047, "lr": 1.6244558728116766e-06, "epoch": 4.410126582278481, "percentage": 88.37, "elapsed_time": "5:23:32", "remaining_time": "0:42:33"}
1203
+ {"current_steps": 1088, "total_steps": 1230, "loss": 0.2165, "lr": 1.6021229118021265e-06, "epoch": 4.4141772151898735, "percentage": 88.46, "elapsed_time": "5:24:07", "remaining_time": "0:42:18"}
1204
+ {"current_steps": 1089, "total_steps": 1230, "loss": 0.1865, "lr": 1.5799381247653967e-06, "epoch": 4.418227848101266, "percentage": 88.54, "elapsed_time": "5:24:38", "remaining_time": "0:42:02"}
1205
+ {"current_steps": 1090, "total_steps": 1230, "loss": 0.1904, "lr": 1.5579016903747013e-06, "epoch": 4.4222784810126585, "percentage": 88.62, "elapsed_time": "5:25:06", "remaining_time": "0:41:45"}
1206
+ {"current_steps": 1091, "total_steps": 1230, "loss": 0.1986, "lr": 1.5360137861084656e-06, "epoch": 4.426329113924051, "percentage": 88.7, "elapsed_time": "5:25:36", "remaining_time": "0:41:29"}
1207
+ {"current_steps": 1092, "total_steps": 1230, "loss": 0.189, "lr": 1.5142745882488475e-06, "epoch": 4.430379746835443, "percentage": 88.78, "elapsed_time": "5:26:10", "remaining_time": "0:41:13"}
1208
+ {"current_steps": 1093, "total_steps": 1230, "loss": 0.2169, "lr": 1.4926842718803691e-06, "epoch": 4.434430379746836, "percentage": 88.86, "elapsed_time": "5:26:42", "remaining_time": "0:40:57"}
1209
+ {"current_steps": 1094, "total_steps": 1230, "loss": 0.197, "lr": 1.4712430108884657e-06, "epoch": 4.438481012658228, "percentage": 88.94, "elapsed_time": "5:27:19", "remaining_time": "0:40:41"}
1210
+ {"current_steps": 1095, "total_steps": 1230, "loss": 0.1936, "lr": 1.4499509779581078e-06, "epoch": 4.442531645569621, "percentage": 89.02, "elapsed_time": "5:27:51", "remaining_time": "0:40:25"}
1211
+ {"current_steps": 1096, "total_steps": 1230, "loss": 0.1842, "lr": 1.4288083445723988e-06, "epoch": 4.446582278481013, "percentage": 89.11, "elapsed_time": "5:28:18", "remaining_time": "0:40:08"}
1212
+ {"current_steps": 1097, "total_steps": 1230, "loss": 0.1854, "lr": 1.4078152810112045e-06, "epoch": 4.450632911392405, "percentage": 89.19, "elapsed_time": "5:28:45", "remaining_time": "0:39:51"}
1213
+ {"current_steps": 1098, "total_steps": 1230, "loss": 0.1934, "lr": 1.3869719563497697e-06, "epoch": 4.454683544303798, "percentage": 89.27, "elapsed_time": "5:29:09", "remaining_time": "0:39:34"}
1214
+ {"current_steps": 1099, "total_steps": 1230, "loss": 0.1868, "lr": 1.3662785384573663e-06, "epoch": 4.45873417721519, "percentage": 89.35, "elapsed_time": "5:29:42", "remaining_time": "0:39:18"}
1215
+ {"current_steps": 1100, "total_steps": 1230, "loss": 0.1969, "lr": 1.3457351939959383e-06, "epoch": 4.462784810126582, "percentage": 89.43, "elapsed_time": "5:30:09", "remaining_time": "0:39:01"}
1216
+ {"current_steps": 1101, "total_steps": 1230, "loss": 0.2034, "lr": 1.3253420884187551e-06, "epoch": 4.466835443037975, "percentage": 89.51, "elapsed_time": "5:30:42", "remaining_time": "0:38:44"}
1217
+ {"current_steps": 1102, "total_steps": 1230, "loss": 0.2288, "lr": 1.3050993859690953e-06, "epoch": 4.470886075949367, "percentage": 89.59, "elapsed_time": "5:31:21", "remaining_time": "0:38:29"}
1218
+ {"current_steps": 1103, "total_steps": 1230, "loss": 0.1841, "lr": 1.2850072496788869e-06, "epoch": 4.47493670886076, "percentage": 89.67, "elapsed_time": "5:31:56", "remaining_time": "0:38:13"}
1219
+ {"current_steps": 1104, "total_steps": 1230, "loss": 0.1811, "lr": 1.2650658413674434e-06, "epoch": 4.478987341772152, "percentage": 89.76, "elapsed_time": "5:32:23", "remaining_time": "0:37:56"}
1220
+ {"current_steps": 1105, "total_steps": 1230, "loss": 0.2032, "lr": 1.2452753216401226e-06, "epoch": 4.483037974683544, "percentage": 89.84, "elapsed_time": "5:32:52", "remaining_time": "0:37:39"}
1221
+ {"current_steps": 1106, "total_steps": 1230, "loss": 0.1965, "lr": 1.2256358498870503e-06, "epoch": 4.487088607594937, "percentage": 89.92, "elapsed_time": "5:33:29", "remaining_time": "0:37:23"}
1222
+ {"current_steps": 1107, "total_steps": 1230, "loss": 0.1669, "lr": 1.2061475842818337e-06, "epoch": 4.491139240506329, "percentage": 90.0, "elapsed_time": "5:34:02", "remaining_time": "0:37:06"}
1223
+ {"current_steps": 1108, "total_steps": 1230, "loss": 0.2028, "lr": 1.1868106817802816e-06, "epoch": 4.495189873417721, "percentage": 90.08, "elapsed_time": "5:34:39", "remaining_time": "0:36:50"}
1224
+ {"current_steps": 1109, "total_steps": 1230, "loss": 0.1979, "lr": 1.1676252981191482e-06, "epoch": 4.499240506329114, "percentage": 90.16, "elapsed_time": "5:35:14", "remaining_time": "0:36:34"}
1225
+ {"current_steps": 1110, "total_steps": 1230, "loss": 0.2312, "lr": 1.1485915878148823e-06, "epoch": 4.503291139240506, "percentage": 90.24, "elapsed_time": "5:35:44", "remaining_time": "0:36:17"}
1226
+ {"current_steps": 1111, "total_steps": 1230, "loss": 0.2053, "lr": 1.1297097041623584e-06, "epoch": 4.507341772151898, "percentage": 90.33, "elapsed_time": "5:36:21", "remaining_time": "0:36:01"}
1227
+ {"current_steps": 1112, "total_steps": 1230, "loss": 0.2275, "lr": 1.1109797992336847e-06, "epoch": 4.511392405063291, "percentage": 90.41, "elapsed_time": "5:36:55", "remaining_time": "0:35:45"}
1228
+ {"current_steps": 1113, "total_steps": 1230, "loss": 0.2044, "lr": 1.092402023876933e-06, "epoch": 4.515443037974683, "percentage": 90.49, "elapsed_time": "5:37:25", "remaining_time": "0:35:28"}
1229
+ {"current_steps": 1114, "total_steps": 1230, "loss": 0.2092, "lr": 1.0739765277149527e-06, "epoch": 4.519493670886076, "percentage": 90.57, "elapsed_time": "5:37:54", "remaining_time": "0:35:11"}
1230
+ {"current_steps": 1115, "total_steps": 1230, "loss": 0.1921, "lr": 1.0557034591441596e-06, "epoch": 4.523544303797468, "percentage": 90.65, "elapsed_time": "5:38:21", "remaining_time": "0:34:53"}
1231
+ {"current_steps": 1116, "total_steps": 1230, "loss": 0.2067, "lr": 1.0375829653333324e-06, "epoch": 4.52759493670886, "percentage": 90.73, "elapsed_time": "5:38:58", "remaining_time": "0:34:37"}
1232
+ {"current_steps": 1117, "total_steps": 1230, "loss": 0.1768, "lr": 1.0196151922224385e-06, "epoch": 4.531645569620253, "percentage": 90.81, "elapsed_time": "5:39:26", "remaining_time": "0:34:20"}
1233
+ {"current_steps": 1118, "total_steps": 1230, "loss": 0.1807, "lr": 1.0018002845214526e-06, "epoch": 4.535696202531645, "percentage": 90.89, "elapsed_time": "5:39:54", "remaining_time": "0:34:03"}
1234
+ {"current_steps": 1119, "total_steps": 1230, "loss": 0.1754, "lr": 9.841383857091947e-07, "epoch": 4.539746835443038, "percentage": 90.98, "elapsed_time": "5:40:19", "remaining_time": "0:33:45"}
1235
+ {"current_steps": 1120, "total_steps": 1230, "loss": 0.2092, "lr": 9.666296380321616e-07, "epoch": 4.54379746835443, "percentage": 91.06, "elapsed_time": "5:40:48", "remaining_time": "0:33:28"}
1236
+ {"current_steps": 1121, "total_steps": 1230, "loss": 0.1975, "lr": 9.492741825034124e-07, "epoch": 4.5478481012658225, "percentage": 91.14, "elapsed_time": "5:41:21", "remaining_time": "0:33:11"}
1237
+ {"current_steps": 1122, "total_steps": 1230, "loss": 0.192, "lr": 9.320721589013892e-07, "epoch": 4.5518987341772155, "percentage": 91.22, "elapsed_time": "5:41:47", "remaining_time": "0:32:53"}
1238
+ {"current_steps": 1123, "total_steps": 1230, "loss": 0.2098, "lr": 9.150237057688339e-07, "epoch": 4.5559493670886075, "percentage": 91.3, "elapsed_time": "5:42:22", "remaining_time": "0:32:37"}
1239
+ {"current_steps": 1124, "total_steps": 1230, "loss": 0.2117, "lr": 8.981289604116328e-07, "epoch": 4.5600000000000005, "percentage": 91.38, "elapsed_time": "5:42:50", "remaining_time": "0:32:19"}
1240
+ {"current_steps": 1125, "total_steps": 1230, "loss": 0.195, "lr": 8.813880588977542e-07, "epoch": 4.564050632911393, "percentage": 91.46, "elapsed_time": "5:43:23", "remaining_time": "0:32:03"}
1241
+ {"current_steps": 1126, "total_steps": 1230, "loss": 0.2008, "lr": 8.648011360561126e-07, "epoch": 4.568101265822785, "percentage": 91.54, "elapsed_time": "5:43:53", "remaining_time": "0:31:45"}
1242
+ {"current_steps": 1127, "total_steps": 1230, "loss": 0.2145, "lr": 8.483683254755037e-07, "epoch": 4.572151898734178, "percentage": 91.63, "elapsed_time": "5:44:27", "remaining_time": "0:31:28"}
1243
+ {"current_steps": 1128, "total_steps": 1230, "loss": 0.1843, "lr": 8.320897595035227e-07, "epoch": 4.57620253164557, "percentage": 91.71, "elapsed_time": "5:44:59", "remaining_time": "0:31:11"}
1244
+ {"current_steps": 1129, "total_steps": 1230, "loss": 0.1959, "lr": 8.159655692455093e-07, "epoch": 4.580253164556962, "percentage": 91.79, "elapsed_time": "5:45:35", "remaining_time": "0:30:54"}
1245
+ {"current_steps": 1130, "total_steps": 1230, "loss": 0.1847, "lr": 7.999958845634648e-07, "epoch": 4.584303797468355, "percentage": 91.87, "elapsed_time": "5:46:04", "remaining_time": "0:30:37"}
1246
+ {"current_steps": 1131, "total_steps": 1230, "loss": 0.2, "lr": 7.841808340750478e-07, "epoch": 4.588354430379747, "percentage": 91.95, "elapsed_time": "5:46:35", "remaining_time": "0:30:20"}
1247
+ {"current_steps": 1132, "total_steps": 1230, "loss": 0.1773, "lr": 7.685205451524869e-07, "epoch": 4.592405063291139, "percentage": 92.03, "elapsed_time": "5:47:08", "remaining_time": "0:30:03"}
1248
+ {"current_steps": 1133, "total_steps": 1230, "loss": 0.2055, "lr": 7.530151439216027e-07, "epoch": 4.596455696202532, "percentage": 92.11, "elapsed_time": "5:47:41", "remaining_time": "0:29:46"}
1249
+ {"current_steps": 1134, "total_steps": 1230, "loss": 0.2, "lr": 7.376647552607675e-07, "epoch": 4.600506329113924, "percentage": 92.2, "elapsed_time": "5:48:12", "remaining_time": "0:29:28"}
1250
+ {"current_steps": 1135, "total_steps": 1230, "loss": 0.1785, "lr": 7.224695027998963e-07, "epoch": 4.604556962025317, "percentage": 92.28, "elapsed_time": "5:48:44", "remaining_time": "0:29:11"}
1251
+ {"current_steps": 1136, "total_steps": 1230, "loss": 0.1957, "lr": 7.07429508919466e-07, "epoch": 4.608607594936709, "percentage": 92.36, "elapsed_time": "5:49:15", "remaining_time": "0:28:53"}
1252
+ {"current_steps": 1137, "total_steps": 1230, "loss": 0.2017, "lr": 6.925448947495206e-07, "epoch": 4.612658227848101, "percentage": 92.44, "elapsed_time": "5:49:47", "remaining_time": "0:28:36"}
1253
+ {"current_steps": 1138, "total_steps": 1230, "loss": 0.1751, "lr": 6.778157801686936e-07, "epoch": 4.616708860759494, "percentage": 92.52, "elapsed_time": "5:50:15", "remaining_time": "0:28:18"}
1254
+ {"current_steps": 1139, "total_steps": 1230, "loss": 0.2096, "lr": 6.632422838032515e-07, "epoch": 4.620759493670886, "percentage": 92.6, "elapsed_time": "5:50:47", "remaining_time": "0:28:01"}
1255
+ {"current_steps": 1140, "total_steps": 1230, "loss": 0.1802, "lr": 6.488245230261281e-07, "epoch": 4.624810126582279, "percentage": 92.68, "elapsed_time": "5:51:18", "remaining_time": "0:27:44"}
1256
+ {"current_steps": 1141, "total_steps": 1230, "loss": 0.1774, "lr": 6.345626139559868e-07, "epoch": 4.628860759493671, "percentage": 92.76, "elapsed_time": "5:51:51", "remaining_time": "0:27:26"}
1257
+ {"current_steps": 1142, "total_steps": 1230, "loss": 0.2175, "lr": 6.204566714562866e-07, "epoch": 4.632911392405063, "percentage": 92.85, "elapsed_time": "5:52:24", "remaining_time": "0:27:09"}
1258
+ {"current_steps": 1143, "total_steps": 1230, "loss": 0.2038, "lr": 6.06506809134344e-07, "epoch": 4.636962025316456, "percentage": 92.93, "elapsed_time": "5:52:54", "remaining_time": "0:26:51"}
1259
+ {"current_steps": 1144, "total_steps": 1230, "loss": 0.2144, "lr": 5.927131393404373e-07, "epoch": 4.641012658227848, "percentage": 93.01, "elapsed_time": "5:53:29", "remaining_time": "0:26:34"}
1260
+ {"current_steps": 1145, "total_steps": 1230, "loss": 0.2115, "lr": 5.790757731668817e-07, "epoch": 4.64506329113924, "percentage": 93.09, "elapsed_time": "5:54:00", "remaining_time": "0:26:16"}
1261
+ {"current_steps": 1146, "total_steps": 1230, "loss": 0.245, "lr": 5.655948204471507e-07, "epoch": 4.649113924050633, "percentage": 93.17, "elapsed_time": "5:54:37", "remaining_time": "0:25:59"}
1262
+ {"current_steps": 1147, "total_steps": 1230, "loss": 0.2089, "lr": 5.522703897549875e-07, "epoch": 4.653164556962025, "percentage": 93.25, "elapsed_time": "5:55:06", "remaining_time": "0:25:41"}
1263
+ {"current_steps": 1148, "total_steps": 1230, "loss": 0.1958, "lr": 5.391025884035239e-07, "epoch": 4.657215189873417, "percentage": 93.33, "elapsed_time": "5:55:33", "remaining_time": "0:25:23"}
1264
+ {"current_steps": 1149, "total_steps": 1230, "loss": 0.1844, "lr": 5.260915224444207e-07, "epoch": 4.66126582278481, "percentage": 93.41, "elapsed_time": "5:56:02", "remaining_time": "0:25:05"}
1265
+ {"current_steps": 1150, "total_steps": 1230, "loss": 0.2015, "lr": 5.132372966670129e-07, "epoch": 4.665316455696202, "percentage": 93.5, "elapsed_time": "5:56:29", "remaining_time": "0:24:47"}
1266
+ {"current_steps": 1151, "total_steps": 1230, "loss": 0.1815, "lr": 5.005400145974704e-07, "epoch": 4.669367088607595, "percentage": 93.58, "elapsed_time": "5:56:59", "remaining_time": "0:24:30"}
1267
+ {"current_steps": 1152, "total_steps": 1230, "loss": 0.2213, "lr": 4.879997784979562e-07, "epoch": 4.673417721518987, "percentage": 93.66, "elapsed_time": "5:57:34", "remaining_time": "0:24:12"}
1268
+ {"current_steps": 1153, "total_steps": 1230, "loss": 0.1924, "lr": 4.7561668936580984e-07, "epoch": 4.6774683544303794, "percentage": 93.74, "elapsed_time": "5:58:04", "remaining_time": "0:23:54"}
1269
+ {"current_steps": 1154, "total_steps": 1230, "loss": 0.214, "lr": 4.6339084693272306e-07, "epoch": 4.681518987341772, "percentage": 93.82, "elapsed_time": "5:58:41", "remaining_time": "0:23:37"}
1270
+ {"current_steps": 1155, "total_steps": 1230, "loss": 0.2059, "lr": 4.5132234966395847e-07, "epoch": 4.6855696202531645, "percentage": 93.9, "elapsed_time": "5:59:06", "remaining_time": "0:23:19"}
1271
+ {"current_steps": 1156, "total_steps": 1230, "loss": 0.1928, "lr": 4.3941129475752795e-07, "epoch": 4.689620253164557, "percentage": 93.98, "elapsed_time": "5:59:35", "remaining_time": "0:23:01"}
1272
+ {"current_steps": 1157, "total_steps": 1230, "loss": 0.2049, "lr": 4.27657778143431e-07, "epoch": 4.6936708860759495, "percentage": 94.07, "elapsed_time": "6:00:04", "remaining_time": "0:22:43"}
1273
+ {"current_steps": 1158, "total_steps": 1230, "loss": 0.2097, "lr": 4.1606189448287757e-07, "epoch": 4.697721518987342, "percentage": 94.15, "elapsed_time": "6:00:31", "remaining_time": "0:22:24"}
1274
+ {"current_steps": 1159, "total_steps": 1230, "loss": 0.2157, "lr": 4.046237371675177e-07, "epoch": 4.7017721518987345, "percentage": 94.23, "elapsed_time": "6:01:02", "remaining_time": "0:22:07"}
1275
+ {"current_steps": 1160, "total_steps": 1230, "loss": 0.2077, "lr": 3.9334339831869963e-07, "epoch": 4.705822784810127, "percentage": 94.31, "elapsed_time": "6:01:39", "remaining_time": "0:21:49"}
1276
+ {"current_steps": 1161, "total_steps": 1230, "loss": 0.1873, "lr": 3.8222096878671955e-07, "epoch": 4.709873417721519, "percentage": 94.39, "elapsed_time": "6:02:13", "remaining_time": "0:21:31"}
1277
+ {"current_steps": 1162, "total_steps": 1230, "loss": 0.2151, "lr": 3.7125653815009545e-07, "epoch": 4.713924050632912, "percentage": 94.47, "elapsed_time": "6:02:47", "remaining_time": "0:21:13"}
1278
+ {"current_steps": 1163, "total_steps": 1230, "loss": 0.1751, "lr": 3.6045019471484974e-07, "epoch": 4.717974683544304, "percentage": 94.55, "elapsed_time": "6:03:22", "remaining_time": "0:20:56"}
1279
+ {"current_steps": 1164, "total_steps": 1230, "loss": 0.2095, "lr": 3.498020255137813e-07, "epoch": 4.722025316455696, "percentage": 94.63, "elapsed_time": "6:03:58", "remaining_time": "0:20:38"}
1280
+ {"current_steps": 1165, "total_steps": 1230, "loss": 0.1659, "lr": 3.393121163057811e-07, "epoch": 4.726075949367089, "percentage": 94.72, "elapsed_time": "6:04:27", "remaining_time": "0:20:20"}
1281
+ {"current_steps": 1166, "total_steps": 1230, "loss": 0.1677, "lr": 3.289805515751399e-07, "epoch": 4.730126582278481, "percentage": 94.8, "elapsed_time": "6:04:59", "remaining_time": "0:20:02"}
1282
+ {"current_steps": 1167, "total_steps": 1230, "loss": 0.2036, "lr": 3.188074145308573e-07, "epoch": 4.734177215189874, "percentage": 94.88, "elapsed_time": "6:05:32", "remaining_time": "0:19:44"}
1283
+ {"current_steps": 1168, "total_steps": 1230, "loss": 0.2253, "lr": 3.087927871059804e-07, "epoch": 4.738227848101266, "percentage": 94.96, "elapsed_time": "6:06:06", "remaining_time": "0:19:26"}
1284
+ {"current_steps": 1169, "total_steps": 1230, "loss": 0.2024, "lr": 2.989367499569418e-07, "epoch": 4.742278481012658, "percentage": 95.04, "elapsed_time": "6:06:40", "remaining_time": "0:19:08"}
1285
+ {"current_steps": 1170, "total_steps": 1230, "loss": 0.2023, "lr": 2.8923938246290917e-07, "epoch": 4.746329113924051, "percentage": 95.12, "elapsed_time": "6:07:12", "remaining_time": "0:18:49"}
1286
+ {"current_steps": 1171, "total_steps": 1230, "loss": 0.178, "lr": 2.7970076272514804e-07, "epoch": 4.750379746835443, "percentage": 95.2, "elapsed_time": "6:07:39", "remaining_time": "0:18:31"}
1287
+ {"current_steps": 1172, "total_steps": 1230, "loss": 0.1892, "lr": 2.703209675663887e-07, "epoch": 4.754430379746836, "percentage": 95.28, "elapsed_time": "6:08:12", "remaining_time": "0:18:13"}
1288
+ {"current_steps": 1173, "total_steps": 1230, "loss": 0.1958, "lr": 2.6110007253021374e-07, "epoch": 4.758481012658228, "percentage": 95.37, "elapsed_time": "6:08:40", "remaining_time": "0:17:54"}
1289
+ {"current_steps": 1174, "total_steps": 1230, "loss": 0.2062, "lr": 2.520381518804471e-07, "epoch": 4.76253164556962, "percentage": 95.45, "elapsed_time": "6:09:20", "remaining_time": "0:17:37"}
1290
+ {"current_steps": 1175, "total_steps": 1230, "loss": 0.2087, "lr": 2.4313527860054585e-07, "epoch": 4.766582278481013, "percentage": 95.53, "elapsed_time": "6:09:54", "remaining_time": "0:17:18"}
1291
+ {"current_steps": 1176, "total_steps": 1230, "loss": 0.1903, "lr": 2.343915243930317e-07, "epoch": 4.770632911392405, "percentage": 95.61, "elapsed_time": "6:10:22", "remaining_time": "0:17:00"}
1292
+ {"current_steps": 1177, "total_steps": 1230, "loss": 0.187, "lr": 2.2580695967889367e-07, "epoch": 4.774683544303797, "percentage": 95.69, "elapsed_time": "6:10:49", "remaining_time": "0:16:41"}
1293
+ {"current_steps": 1178, "total_steps": 1230, "loss": 0.1971, "lr": 2.1738165359704189e-07, "epoch": 4.77873417721519, "percentage": 95.77, "elapsed_time": "6:11:20", "remaining_time": "0:16:23"}
1294
+ {"current_steps": 1179, "total_steps": 1230, "loss": 0.1995, "lr": 2.0911567400373257e-07, "epoch": 4.782784810126582, "percentage": 95.85, "elapsed_time": "6:11:54", "remaining_time": "0:16:05"}
1295
+ {"current_steps": 1180, "total_steps": 1230, "loss": 0.1545, "lr": 2.0100908747202607e-07, "epoch": 4.786835443037974, "percentage": 95.93, "elapsed_time": "6:12:27", "remaining_time": "0:15:46"}
1296
+ {"current_steps": 1181, "total_steps": 1230, "loss": 0.1779, "lr": 1.9306195929125638e-07, "epoch": 4.790886075949367, "percentage": 96.02, "elapsed_time": "6:13:00", "remaining_time": "0:15:28"}
1297
+ {"current_steps": 1182, "total_steps": 1230, "loss": 0.2106, "lr": 1.8527435346650247e-07, "epoch": 4.794936708860759, "percentage": 96.1, "elapsed_time": "6:13:30", "remaining_time": "0:15:10"}
1298
+ {"current_steps": 1183, "total_steps": 1230, "loss": 0.1826, "lr": 1.7764633271807108e-07, "epoch": 4.798987341772152, "percentage": 96.18, "elapsed_time": "6:14:01", "remaining_time": "0:14:51"}
1299
+ {"current_steps": 1184, "total_steps": 1230, "loss": 0.1737, "lr": 1.7017795848099262e-07, "epoch": 4.803037974683544, "percentage": 96.26, "elapsed_time": "6:14:35", "remaining_time": "0:14:33"}
1300
+ {"current_steps": 1185, "total_steps": 1230, "loss": 0.2046, "lr": 1.6286929090452596e-07, "epoch": 4.807088607594936, "percentage": 96.34, "elapsed_time": "6:15:03", "remaining_time": "0:14:14"}
1301
+ {"current_steps": 1186, "total_steps": 1230, "loss": 0.2067, "lr": 1.557203888516745e-07, "epoch": 4.811139240506329, "percentage": 96.42, "elapsed_time": "6:15:38", "remaining_time": "0:13:56"}
1302
+ {"current_steps": 1187, "total_steps": 1230, "loss": 0.2182, "lr": 1.487313098987131e-07, "epoch": 4.815189873417721, "percentage": 96.5, "elapsed_time": "6:16:13", "remaining_time": "0:13:37"}
1303
+ {"current_steps": 1188, "total_steps": 1230, "loss": 0.1979, "lr": 1.4190211033472402e-07, "epoch": 4.819240506329114, "percentage": 96.59, "elapsed_time": "6:16:46", "remaining_time": "0:13:19"}
1304
+ {"current_steps": 1189, "total_steps": 1230, "loss": 0.1934, "lr": 1.3523284516113955e-07, "epoch": 4.8232911392405065, "percentage": 96.67, "elapsed_time": "6:17:20", "remaining_time": "0:13:00"}
1305
+ {"current_steps": 1190, "total_steps": 1230, "loss": 0.1884, "lr": 1.2872356809130682e-07, "epoch": 4.8273417721518985, "percentage": 96.75, "elapsed_time": "6:17:49", "remaining_time": "0:12:41"}
1306
+ {"current_steps": 1191, "total_steps": 1230, "loss": 0.1814, "lr": 1.2237433155004807e-07, "epoch": 4.8313924050632915, "percentage": 96.83, "elapsed_time": "6:18:20", "remaining_time": "0:12:23"}
1307
+ {"current_steps": 1192, "total_steps": 1230, "loss": 0.1785, "lr": 1.1618518667323886e-07, "epoch": 4.8354430379746836, "percentage": 96.91, "elapsed_time": "6:18:51", "remaining_time": "0:12:04"}
1308
+ {"current_steps": 1193, "total_steps": 1230, "loss": 0.1957, "lr": 1.1015618330740385e-07, "epoch": 4.839493670886076, "percentage": 96.99, "elapsed_time": "6:19:21", "remaining_time": "0:11:45"}
1309
+ {"current_steps": 1194, "total_steps": 1230, "loss": 0.1798, "lr": 1.042873700093061e-07, "epoch": 4.843544303797469, "percentage": 97.07, "elapsed_time": "6:19:49", "remaining_time": "0:11:27"}
1310
+ {"current_steps": 1195, "total_steps": 1230, "loss": 0.2255, "lr": 9.857879404556291e-08, "epoch": 4.847594936708861, "percentage": 97.15, "elapsed_time": "6:20:22", "remaining_time": "0:11:08"}
1311
+ {"current_steps": 1196, "total_steps": 1230, "loss": 0.181, "lr": 9.303050139225722e-08, "epoch": 4.851645569620253, "percentage": 97.24, "elapsed_time": "6:20:57", "remaining_time": "0:10:49"}
1312
+ {"current_steps": 1197, "total_steps": 1230, "loss": 0.1971, "lr": 8.76425367345779e-08, "epoch": 4.855696202531646, "percentage": 97.32, "elapsed_time": "6:21:29", "remaining_time": "0:10:31"}
1313
+ {"current_steps": 1198, "total_steps": 1230, "loss": 0.1873, "lr": 8.241494346644897e-08, "epoch": 4.859746835443038, "percentage": 97.4, "elapsed_time": "6:21:59", "remaining_time": "0:10:12"}
1314
+ {"current_steps": 1199, "total_steps": 1230, "loss": 0.1872, "lr": 7.734776369019204e-08, "epoch": 4.863797468354431, "percentage": 97.48, "elapsed_time": "6:22:33", "remaining_time": "0:09:53"}
1315
+ {"current_steps": 1200, "total_steps": 1230, "loss": 0.203, "lr": 7.244103821617332e-08, "epoch": 4.867848101265823, "percentage": 97.56, "elapsed_time": "6:23:06", "remaining_time": "0:09:34"}
1316
+ {"current_steps": 1201, "total_steps": 1230, "loss": 0.204, "lr": 6.769480656248606e-08, "epoch": 4.871898734177215, "percentage": 97.64, "elapsed_time": "6:23:41", "remaining_time": "0:09:15"}
1317
+ {"current_steps": 1202, "total_steps": 1230, "loss": 0.1866, "lr": 6.310910695462635e-08, "epoch": 4.875949367088608, "percentage": 97.72, "elapsed_time": "6:24:14", "remaining_time": "0:08:57"}
1318
+ {"current_steps": 1203, "total_steps": 1230, "loss": 0.2102, "lr": 5.8683976325191185e-08, "epoch": 4.88, "percentage": 97.8, "elapsed_time": "6:24:49", "remaining_time": "0:08:38"}
1319
+ {"current_steps": 1204, "total_steps": 1230, "loss": 0.2046, "lr": 5.4419450313571984e-08, "epoch": 4.884050632911393, "percentage": 97.89, "elapsed_time": "6:25:22", "remaining_time": "0:08:19"}
1320
+ {"current_steps": 1205, "total_steps": 1230, "loss": 0.1912, "lr": 5.031556326567488e-08, "epoch": 4.888101265822785, "percentage": 97.97, "elapsed_time": "6:25:54", "remaining_time": "0:08:00"}
1321
+ {"current_steps": 1206, "total_steps": 1230, "loss": 0.2113, "lr": 4.637234823364312e-08, "epoch": 4.892151898734177, "percentage": 98.05, "elapsed_time": "6:26:26", "remaining_time": "0:07:41"}
1322
+ {"current_steps": 1207, "total_steps": 1230, "loss": 0.1992, "lr": 4.258983697558838e-08, "epoch": 4.89620253164557, "percentage": 98.13, "elapsed_time": "6:27:00", "remaining_time": "0:07:22"}
1323
+ {"current_steps": 1208, "total_steps": 1230, "loss": 0.2291, "lr": 3.896805995533548e-08, "epoch": 4.900253164556962, "percentage": 98.21, "elapsed_time": "6:27:32", "remaining_time": "0:07:03"}
1324
+ {"current_steps": 1209, "total_steps": 1230, "loss": 0.1823, "lr": 3.550704634218028e-08, "epoch": 4.904303797468354, "percentage": 98.29, "elapsed_time": "6:28:07", "remaining_time": "0:06:44"}
1325
+ {"current_steps": 1210, "total_steps": 1230, "loss": 0.1981, "lr": 3.2206824010647676e-08, "epoch": 4.908354430379747, "percentage": 98.37, "elapsed_time": "6:28:41", "remaining_time": "0:06:25"}
1326
+ {"current_steps": 1211, "total_steps": 1230, "loss": 0.1971, "lr": 2.9067419540278476e-08, "epoch": 4.912405063291139, "percentage": 98.46, "elapsed_time": "6:29:15", "remaining_time": "0:06:06"}
1327
+ {"current_steps": 1212, "total_steps": 1230, "loss": 0.1835, "lr": 2.6088858215400638e-08, "epoch": 4.916455696202531, "percentage": 98.54, "elapsed_time": "6:29:51", "remaining_time": "0:05:47"}
1328
+ {"current_steps": 1213, "total_steps": 1230, "loss": 0.2126, "lr": 2.3271164024940564e-08, "epoch": 4.920506329113924, "percentage": 98.62, "elapsed_time": "6:30:19", "remaining_time": "0:05:28"}
1329
+ {"current_steps": 1214, "total_steps": 1230, "loss": 0.1896, "lr": 2.061435966221881e-08, "epoch": 4.924556962025316, "percentage": 98.7, "elapsed_time": "6:30:46", "remaining_time": "0:05:09"}
1330
+ {"current_steps": 1215, "total_steps": 1230, "loss": 0.1832, "lr": 1.811846652477245e-08, "epoch": 4.928607594936709, "percentage": 98.78, "elapsed_time": "6:31:18", "remaining_time": "0:04:49"}
1331
+ {"current_steps": 1216, "total_steps": 1230, "loss": 0.1907, "lr": 1.5783504714184106e-08, "epoch": 4.932658227848101, "percentage": 98.86, "elapsed_time": "6:31:52", "remaining_time": "0:04:30"}
1332
+ {"current_steps": 1217, "total_steps": 1230, "loss": 0.2112, "lr": 1.360949303591097e-08, "epoch": 4.936708860759493, "percentage": 98.94, "elapsed_time": "6:32:29", "remaining_time": "0:04:11"}
1333
+ {"current_steps": 1218, "total_steps": 1230, "loss": 0.1974, "lr": 1.1596448999144916e-08, "epoch": 4.940759493670886, "percentage": 99.02, "elapsed_time": "6:33:00", "remaining_time": "0:03:52"}
1334
+ {"current_steps": 1219, "total_steps": 1230, "loss": 0.171, "lr": 9.744388816668172e-09, "epoch": 4.944810126582278, "percentage": 99.11, "elapsed_time": "6:33:29", "remaining_time": "0:03:33"}
1335
+ {"current_steps": 1220, "total_steps": 1230, "loss": 0.1857, "lr": 8.05332740472009e-09, "epoch": 4.948860759493671, "percentage": 99.19, "elapsed_time": "6:33:58", "remaining_time": "0:03:13"}
1336
+ {"current_steps": 1221, "total_steps": 1230, "loss": 0.1712, "lr": 6.523278382872811e-09, "epoch": 4.952911392405063, "percentage": 99.27, "elapsed_time": "6:34:28", "remaining_time": "0:02:54"}
1337
+ {"current_steps": 1222, "total_steps": 1230, "loss": 0.1959, "lr": 5.15425407393133e-09, "epoch": 4.9569620253164555, "percentage": 99.35, "elapsed_time": "6:34:58", "remaining_time": "0:02:35"}
1338
+ {"current_steps": 1223, "total_steps": 1230, "loss": 0.203, "lr": 3.94626550383137e-09, "epoch": 4.961012658227848, "percentage": 99.43, "elapsed_time": "6:35:36", "remaining_time": "0:02:15"}
1339
+ {"current_steps": 1224, "total_steps": 1230, "loss": 0.1804, "lr": 2.899322401546112e-09, "epoch": 4.9650632911392405, "percentage": 99.51, "elapsed_time": "6:36:01", "remaining_time": "0:01:56"}
1340
+ {"current_steps": 1225, "total_steps": 1230, "loss": 0.1995, "lr": 2.013433199010706e-09, "epoch": 4.969113924050633, "percentage": 99.59, "elapsed_time": "6:36:35", "remaining_time": "0:01:37"}
1341
+ {"current_steps": 1226, "total_steps": 1230, "loss": 0.2084, "lr": 1.2886050310556563e-09, "epoch": 4.9731645569620255, "percentage": 99.67, "elapsed_time": "6:37:09", "remaining_time": "0:01:17"}
1342
+ {"current_steps": 1227, "total_steps": 1230, "loss": 0.1996, "lr": 7.248437353468695e-10, "epoch": 4.977215189873418, "percentage": 99.76, "elapsed_time": "6:37:42", "remaining_time": "0:00:58"}
1343
+ {"current_steps": 1228, "total_steps": 1230, "loss": 0.1895, "lr": 3.221538523412449e-10, "epoch": 4.98126582278481, "percentage": 99.84, "elapsed_time": "6:38:15", "remaining_time": "0:00:38"}
1344
+ {"current_steps": 1229, "total_steps": 1230, "loss": 0.1732, "lr": 8.053862524670663e-11, "epoch": 4.985316455696203, "percentage": 99.92, "elapsed_time": "6:38:43", "remaining_time": "0:00:19"}
1345
+ {"current_steps": 1230, "total_steps": 1230, "loss": 0.1817, "lr": 0.0, "epoch": 4.989367088607595, "percentage": 100.0, "elapsed_time": "6:39:21", "remaining_time": "0:00:00"}
1346
+ {"current_steps": 1230, "total_steps": 1230, "epoch": 4.989367088607595, "percentage": 100.0, "elapsed_time": "6:42:41", "remaining_time": "0:00:00"}