neginr commited on
Commit
4434362
·
verified ·
1 Parent(s): f613f52

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 sha256:7e2d69bcf83f2e10f219765d3adf7003bdbd881a7604e77032dd44eb199f368e
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c352b53049da9e8266cfcd7489e4055b45dbfe49b0533ca4813ca43ca8dc5a8
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:d3c2d1feba198588458e95f59f56fb13dc8fd154c6e6e804a59c6b977b4aac5f
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52bedbe21da06499925634122defd925f6d545f1126a07152669e3f5c70ac38b
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:286d6f851139bb672a0669b0153bfe2014311bca2b93f1eb4477ed5996b2cf69
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8990ff7a878b9c14bdb1a7aea5e308df7d4e7c40cc6fe2e6a2d5f954a12b0042
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:a1b72aaec2a56dfb94b3ac5eab2fefe9f55a0b0fa4ab70abaff41e3af5cf35ec
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:acfa0057997313cecf022a33d14e98d43f47574043db24a2280753279763b3a1
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -1088,3 +1088,246 @@
1088
  {"current_steps": 986, "total_steps": 1230, "loss": 0.4058, "lr": 4.6063907676823474e-06, "epoch": 4.004556962025316, "percentage": 80.16, "elapsed_time": "3:05:56", "remaining_time": "0:46:00"}
1089
  {"current_steps": 987, "total_steps": 1230, "loss": 0.3731, "lr": 4.570216403561141e-06, "epoch": 4.008607594936709, "percentage": 80.24, "elapsed_time": "3:06:42", "remaining_time": "0:45:57"}
1090
  {"current_steps": 988, "total_steps": 1230, "loss": 0.3876, "lr": 4.534166308795815e-06, "epoch": 4.012658227848101, "percentage": 80.33, "elapsed_time": "3:07:27", "remaining_time": "0:45:54"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1088
  {"current_steps": 986, "total_steps": 1230, "loss": 0.4058, "lr": 4.6063907676823474e-06, "epoch": 4.004556962025316, "percentage": 80.16, "elapsed_time": "3:05:56", "remaining_time": "0:46:00"}
1089
  {"current_steps": 987, "total_steps": 1230, "loss": 0.3731, "lr": 4.570216403561141e-06, "epoch": 4.008607594936709, "percentage": 80.24, "elapsed_time": "3:06:42", "remaining_time": "0:45:57"}
1090
  {"current_steps": 988, "total_steps": 1230, "loss": 0.3876, "lr": 4.534166308795815e-06, "epoch": 4.012658227848101, "percentage": 80.33, "elapsed_time": "3:07:27", "remaining_time": "0:45:54"}
1091
+ {"current_steps": 989, "total_steps": 1230, "loss": 0.3815, "lr": 4.498240773728859e-06, "epoch": 4.016708860759493, "percentage": 80.41, "elapsed_time": "3:08:13", "remaining_time": "0:45:52"}
1092
+ {"current_steps": 990, "total_steps": 1230, "loss": 0.3915, "lr": 4.462440087699609e-06, "epoch": 4.020759493670886, "percentage": 80.49, "elapsed_time": "3:08:56", "remaining_time": "0:45:48"}
1093
+ {"current_steps": 991, "total_steps": 1230, "loss": 0.3726, "lr": 4.426764539041861e-06, "epoch": 4.024810126582278, "percentage": 80.57, "elapsed_time": "3:09:40", "remaining_time": "0:45:44"}
1094
+ {"current_steps": 992, "total_steps": 1230, "loss": 0.3674, "lr": 4.391214415081582e-06, "epoch": 4.0288607594936705, "percentage": 80.65, "elapsed_time": "3:10:26", "remaining_time": "0:45:41"}
1095
+ {"current_steps": 993, "total_steps": 1230, "loss": 0.3809, "lr": 4.355790002134579e-06, "epoch": 4.0329113924050635, "percentage": 80.73, "elapsed_time": "3:11:12", "remaining_time": "0:45:38"}
1096
+ {"current_steps": 994, "total_steps": 1230, "loss": 0.3694, "lr": 4.320491585504207e-06, "epoch": 4.0369620253164555, "percentage": 80.81, "elapsed_time": "3:11:59", "remaining_time": "0:45:34"}
1097
+ {"current_steps": 995, "total_steps": 1230, "loss": 0.39, "lr": 4.2853194494790615e-06, "epoch": 4.0410126582278485, "percentage": 80.89, "elapsed_time": "3:12:43", "remaining_time": "0:45:31"}
1098
+ {"current_steps": 996, "total_steps": 1230, "loss": 0.3785, "lr": 4.250273877330691e-06, "epoch": 4.045063291139241, "percentage": 80.98, "elapsed_time": "3:13:28", "remaining_time": "0:45:27"}
1099
+ {"current_steps": 997, "total_steps": 1230, "loss": 0.3865, "lr": 4.215355151311313e-06, "epoch": 4.049113924050633, "percentage": 81.06, "elapsed_time": "3:14:14", "remaining_time": "0:45:23"}
1100
+ {"current_steps": 998, "total_steps": 1230, "loss": 0.3882, "lr": 4.180563552651542e-06, "epoch": 4.053164556962026, "percentage": 81.14, "elapsed_time": "3:15:00", "remaining_time": "0:45:19"}
1101
+ {"current_steps": 999, "total_steps": 1230, "loss": 0.3944, "lr": 4.145899361558147e-06, "epoch": 4.057215189873418, "percentage": 81.22, "elapsed_time": "3:15:44", "remaining_time": "0:45:15"}
1102
+ {"current_steps": 1000, "total_steps": 1230, "loss": 0.369, "lr": 4.111362857211738e-06, "epoch": 4.06126582278481, "percentage": 81.3, "elapsed_time": "3:16:30", "remaining_time": "0:45:11"}
1103
+ {"current_steps": 1001, "total_steps": 1230, "loss": 0.3938, "lr": 4.076954317764592e-06, "epoch": 4.065316455696203, "percentage": 81.38, "elapsed_time": "3:17:13", "remaining_time": "0:45:07"}
1104
+ {"current_steps": 1002, "total_steps": 1230, "loss": 0.3779, "lr": 4.042674020338335e-06, "epoch": 4.069367088607595, "percentage": 81.46, "elapsed_time": "3:17:59", "remaining_time": "0:45:03"}
1105
+ {"current_steps": 1003, "total_steps": 1230, "loss": 0.3978, "lr": 4.0085222410217835e-06, "epoch": 4.073417721518988, "percentage": 81.54, "elapsed_time": "3:18:45", "remaining_time": "0:44:59"}
1106
+ {"current_steps": 1004, "total_steps": 1230, "loss": 0.3695, "lr": 3.974499254868674e-06, "epoch": 4.07746835443038, "percentage": 81.63, "elapsed_time": "3:19:31", "remaining_time": "0:44:54"}
1107
+ {"current_steps": 1005, "total_steps": 1230, "loss": 0.3905, "lr": 3.940605335895451e-06, "epoch": 4.081518987341772, "percentage": 81.71, "elapsed_time": "3:20:17", "remaining_time": "0:44:50"}
1108
+ {"current_steps": 1006, "total_steps": 1230, "loss": 0.3706, "lr": 3.90684075707908e-06, "epoch": 4.085569620253165, "percentage": 81.79, "elapsed_time": "3:21:01", "remaining_time": "0:44:45"}
1109
+ {"current_steps": 1007, "total_steps": 1230, "loss": 0.378, "lr": 3.8732057903548505e-06, "epoch": 4.089620253164557, "percentage": 81.87, "elapsed_time": "3:21:46", "remaining_time": "0:44:41"}
1110
+ {"current_steps": 1008, "total_steps": 1230, "loss": 0.3733, "lr": 3.8397007066141375e-06, "epoch": 4.093670886075949, "percentage": 81.95, "elapsed_time": "3:22:32", "remaining_time": "0:44:36"}
1111
+ {"current_steps": 1009, "total_steps": 1230, "loss": 0.3899, "lr": 3.806325775702304e-06, "epoch": 4.097721518987342, "percentage": 82.03, "elapsed_time": "3:23:16", "remaining_time": "0:44:31"}
1112
+ {"current_steps": 1010, "total_steps": 1230, "loss": 0.386, "lr": 3.773081266416434e-06, "epoch": 4.101772151898734, "percentage": 82.11, "elapsed_time": "3:24:00", "remaining_time": "0:44:26"}
1113
+ {"current_steps": 1011, "total_steps": 1230, "loss": 0.3738, "lr": 3.739967446503245e-06, "epoch": 4.105822784810127, "percentage": 82.2, "elapsed_time": "3:24:46", "remaining_time": "0:44:21"}
1114
+ {"current_steps": 1012, "total_steps": 1230, "loss": 0.3764, "lr": 3.706984582656894e-06, "epoch": 4.109873417721519, "percentage": 82.28, "elapsed_time": "3:25:31", "remaining_time": "0:44:16"}
1115
+ {"current_steps": 1013, "total_steps": 1230, "loss": 0.3857, "lr": 3.6741329405168237e-06, "epoch": 4.113924050632911, "percentage": 82.36, "elapsed_time": "3:26:17", "remaining_time": "0:44:11"}
1116
+ {"current_steps": 1014, "total_steps": 1230, "loss": 0.365, "lr": 3.641412784665648e-06, "epoch": 4.117974683544304, "percentage": 82.44, "elapsed_time": "3:27:03", "remaining_time": "0:44:06"}
1117
+ {"current_steps": 1015, "total_steps": 1230, "loss": 0.3601, "lr": 3.608824378627005e-06, "epoch": 4.122025316455696, "percentage": 82.52, "elapsed_time": "3:27:45", "remaining_time": "0:44:00"}
1118
+ {"current_steps": 1016, "total_steps": 1230, "loss": 0.4252, "lr": 3.5763679848634337e-06, "epoch": 4.126075949367088, "percentage": 82.6, "elapsed_time": "3:28:31", "remaining_time": "0:43:55"}
1119
+ {"current_steps": 1017, "total_steps": 1230, "loss": 0.3784, "lr": 3.544043864774269e-06, "epoch": 4.130126582278481, "percentage": 82.68, "elapsed_time": "3:29:18", "remaining_time": "0:43:50"}
1120
+ {"current_steps": 1018, "total_steps": 1230, "loss": 0.3796, "lr": 3.5118522786935282e-06, "epoch": 4.134177215189873, "percentage": 82.76, "elapsed_time": "3:30:04", "remaining_time": "0:43:44"}
1121
+ {"current_steps": 1019, "total_steps": 1230, "loss": 0.3894, "lr": 3.479793485887819e-06, "epoch": 4.138227848101266, "percentage": 82.85, "elapsed_time": "3:30:48", "remaining_time": "0:43:39"}
1122
+ {"current_steps": 1020, "total_steps": 1230, "loss": 0.3636, "lr": 3.4478677445542653e-06, "epoch": 4.142278481012658, "percentage": 82.93, "elapsed_time": "3:31:33", "remaining_time": "0:43:33"}
1123
+ {"current_steps": 1021, "total_steps": 1230, "loss": 0.3628, "lr": 3.4160753118183767e-06, "epoch": 4.14632911392405, "percentage": 83.01, "elapsed_time": "3:32:18", "remaining_time": "0:43:27"}
1124
+ {"current_steps": 1022, "total_steps": 1230, "loss": 0.3878, "lr": 3.3844164437320527e-06, "epoch": 4.150379746835443, "percentage": 83.09, "elapsed_time": "3:33:03", "remaining_time": "0:43:21"}
1125
+ {"current_steps": 1023, "total_steps": 1230, "loss": 0.373, "lr": 3.3528913952714558e-06, "epoch": 4.154430379746835, "percentage": 83.17, "elapsed_time": "3:33:50", "remaining_time": "0:43:16"}
1126
+ {"current_steps": 1024, "total_steps": 1230, "loss": 0.3789, "lr": 3.321500420335e-06, "epoch": 4.1584810126582274, "percentage": 83.25, "elapsed_time": "3:34:35", "remaining_time": "0:43:10"}
1127
+ {"current_steps": 1025, "total_steps": 1230, "loss": 0.3665, "lr": 3.290243771741275e-06, "epoch": 4.16253164556962, "percentage": 83.33, "elapsed_time": "3:35:17", "remaining_time": "0:43:03"}
1128
+ {"current_steps": 1026, "total_steps": 1230, "loss": 0.3559, "lr": 3.2591217012270325e-06, "epoch": 4.1665822784810125, "percentage": 83.41, "elapsed_time": "3:36:02", "remaining_time": "0:42:57"}
1129
+ {"current_steps": 1027, "total_steps": 1230, "loss": 0.3861, "lr": 3.228134459445149e-06, "epoch": 4.170632911392405, "percentage": 83.5, "elapsed_time": "3:36:47", "remaining_time": "0:42:51"}
1130
+ {"current_steps": 1028, "total_steps": 1230, "loss": 0.3843, "lr": 3.1972822959626205e-06, "epoch": 4.1746835443037975, "percentage": 83.58, "elapsed_time": "3:37:32", "remaining_time": "0:42:44"}
1131
+ {"current_steps": 1029, "total_steps": 1230, "loss": 0.376, "lr": 3.166565459258513e-06, "epoch": 4.17873417721519, "percentage": 83.66, "elapsed_time": "3:38:16", "remaining_time": "0:42:38"}
1132
+ {"current_steps": 1030, "total_steps": 1230, "loss": 0.3727, "lr": 3.1359841967220193e-06, "epoch": 4.1827848101265825, "percentage": 83.74, "elapsed_time": "3:39:01", "remaining_time": "0:42:31"}
1133
+ {"current_steps": 1031, "total_steps": 1230, "loss": 0.3817, "lr": 3.105538754650419e-06, "epoch": 4.186835443037975, "percentage": 83.82, "elapsed_time": "3:39:43", "remaining_time": "0:42:24"}
1134
+ {"current_steps": 1032, "total_steps": 1230, "loss": 0.3723, "lr": 3.07522937824712e-06, "epoch": 4.190886075949367, "percentage": 83.9, "elapsed_time": "3:40:28", "remaining_time": "0:42:18"}
1135
+ {"current_steps": 1033, "total_steps": 1230, "loss": 0.3719, "lr": 3.0450563116196697e-06, "epoch": 4.19493670886076, "percentage": 83.98, "elapsed_time": "3:41:13", "remaining_time": "0:42:11"}
1136
+ {"current_steps": 1034, "total_steps": 1230, "loss": 0.392, "lr": 3.0150197977778008e-06, "epoch": 4.198987341772152, "percentage": 84.07, "elapsed_time": "3:41:59", "remaining_time": "0:42:04"}
1137
+ {"current_steps": 1035, "total_steps": 1230, "loss": 0.4053, "lr": 2.985120078631465e-06, "epoch": 4.203037974683545, "percentage": 84.15, "elapsed_time": "3:42:46", "remaining_time": "0:41:58"}
1138
+ {"current_steps": 1036, "total_steps": 1230, "loss": 0.3889, "lr": 2.9553573949888893e-06, "epoch": 4.207088607594937, "percentage": 84.23, "elapsed_time": "3:43:33", "remaining_time": "0:41:51"}
1139
+ {"current_steps": 1037, "total_steps": 1230, "loss": 0.3767, "lr": 2.9257319865546384e-06, "epoch": 4.211139240506329, "percentage": 84.31, "elapsed_time": "3:44:19", "remaining_time": "0:41:45"}
1140
+ {"current_steps": 1038, "total_steps": 1230, "loss": 0.3781, "lr": 2.896244091927678e-06, "epoch": 4.215189873417722, "percentage": 84.39, "elapsed_time": "3:45:03", "remaining_time": "0:41:37"}
1141
+ {"current_steps": 1039, "total_steps": 1230, "loss": 0.382, "lr": 2.8668939485994584e-06, "epoch": 4.219240506329114, "percentage": 84.47, "elapsed_time": "3:45:47", "remaining_time": "0:41:30"}
1142
+ {"current_steps": 1040, "total_steps": 1230, "loss": 0.3647, "lr": 2.837681792951994e-06, "epoch": 4.223291139240506, "percentage": 84.55, "elapsed_time": "3:46:31", "remaining_time": "0:41:23"}
1143
+ {"current_steps": 1041, "total_steps": 1230, "loss": 0.3905, "lr": 2.808607860255981e-06, "epoch": 4.227341772151899, "percentage": 84.63, "elapsed_time": "3:47:15", "remaining_time": "0:41:15"}
1144
+ {"current_steps": 1042, "total_steps": 1230, "loss": 0.3872, "lr": 2.7796723846688634e-06, "epoch": 4.231392405063291, "percentage": 84.72, "elapsed_time": "3:48:00", "remaining_time": "0:41:08"}
1145
+ {"current_steps": 1043, "total_steps": 1230, "loss": 0.3805, "lr": 2.7508755992329937e-06, "epoch": 4.235443037974684, "percentage": 84.8, "elapsed_time": "3:48:44", "remaining_time": "0:41:00"}
1146
+ {"current_steps": 1044, "total_steps": 1230, "loss": 0.384, "lr": 2.722217735873718e-06, "epoch": 4.239493670886076, "percentage": 84.88, "elapsed_time": "3:49:28", "remaining_time": "0:40:53"}
1147
+ {"current_steps": 1045, "total_steps": 1230, "loss": 0.405, "lr": 2.6936990253975315e-06, "epoch": 4.243544303797468, "percentage": 84.96, "elapsed_time": "3:50:14", "remaining_time": "0:40:45"}
1148
+ {"current_steps": 1046, "total_steps": 1230, "loss": 0.3769, "lr": 2.665319697490205e-06, "epoch": 4.247594936708861, "percentage": 85.04, "elapsed_time": "3:50:59", "remaining_time": "0:40:37"}
1149
+ {"current_steps": 1047, "total_steps": 1230, "loss": 0.3884, "lr": 2.637079980714945e-06, "epoch": 4.251645569620253, "percentage": 85.12, "elapsed_time": "3:51:44", "remaining_time": "0:40:30"}
1150
+ {"current_steps": 1048, "total_steps": 1230, "loss": 0.3931, "lr": 2.6089801025105453e-06, "epoch": 4.255696202531645, "percentage": 85.2, "elapsed_time": "3:52:29", "remaining_time": "0:40:22"}
1151
+ {"current_steps": 1049, "total_steps": 1230, "loss": 0.3911, "lr": 2.581020289189571e-06, "epoch": 4.259746835443038, "percentage": 85.28, "elapsed_time": "3:53:13", "remaining_time": "0:40:14"}
1152
+ {"current_steps": 1050, "total_steps": 1230, "loss": 0.379, "lr": 2.553200765936501e-06, "epoch": 4.26379746835443, "percentage": 85.37, "elapsed_time": "3:53:59", "remaining_time": "0:40:06"}
1153
+ {"current_steps": 1051, "total_steps": 1230, "loss": 0.3693, "lr": 2.525521756805962e-06, "epoch": 4.267848101265823, "percentage": 85.45, "elapsed_time": "3:54:40", "remaining_time": "0:39:58"}
1154
+ {"current_steps": 1052, "total_steps": 1230, "loss": 0.4053, "lr": 2.497983484720885e-06, "epoch": 4.271898734177215, "percentage": 85.53, "elapsed_time": "3:55:24", "remaining_time": "0:39:49"}
1155
+ {"current_steps": 1053, "total_steps": 1230, "loss": 0.3757, "lr": 2.470586171470728e-06, "epoch": 4.275949367088607, "percentage": 85.61, "elapsed_time": "3:56:09", "remaining_time": "0:39:41"}
1156
+ {"current_steps": 1054, "total_steps": 1230, "loss": 0.3752, "lr": 2.4433300377096836e-06, "epoch": 4.28, "percentage": 85.69, "elapsed_time": "3:56:55", "remaining_time": "0:39:33"}
1157
+ {"current_steps": 1055, "total_steps": 1230, "loss": 0.3854, "lr": 2.4162153029549073e-06, "epoch": 4.284050632911392, "percentage": 85.77, "elapsed_time": "3:57:40", "remaining_time": "0:39:25"}
1158
+ {"current_steps": 1056, "total_steps": 1230, "loss": 0.3683, "lr": 2.3892421855847458e-06, "epoch": 4.288101265822785, "percentage": 85.85, "elapsed_time": "3:58:27", "remaining_time": "0:39:17"}
1159
+ {"current_steps": 1057, "total_steps": 1230, "loss": 0.3771, "lr": 2.362410902836978e-06, "epoch": 4.292151898734177, "percentage": 85.93, "elapsed_time": "3:59:11", "remaining_time": "0:39:08"}
1160
+ {"current_steps": 1058, "total_steps": 1230, "loss": 0.366, "lr": 2.3357216708070653e-06, "epoch": 4.296202531645569, "percentage": 86.02, "elapsed_time": "3:59:56", "remaining_time": "0:39:00"}
1161
+ {"current_steps": 1059, "total_steps": 1230, "loss": 0.3779, "lr": 2.309174704446411e-06, "epoch": 4.300253164556962, "percentage": 86.1, "elapsed_time": "4:00:37", "remaining_time": "0:38:51"}
1162
+ {"current_steps": 1060, "total_steps": 1230, "loss": 0.3767, "lr": 2.2827702175606437e-06, "epoch": 4.3043037974683545, "percentage": 86.18, "elapsed_time": "4:01:23", "remaining_time": "0:38:42"}
1163
+ {"current_steps": 1061, "total_steps": 1230, "loss": 0.3649, "lr": 2.256508422807855e-06, "epoch": 4.3083544303797465, "percentage": 86.26, "elapsed_time": "4:02:07", "remaining_time": "0:38:33"}
1164
+ {"current_steps": 1062, "total_steps": 1230, "loss": 0.3767, "lr": 2.230389531696946e-06, "epoch": 4.3124050632911395, "percentage": 86.34, "elapsed_time": "4:02:52", "remaining_time": "0:38:25"}
1165
+ {"current_steps": 1063, "total_steps": 1230, "loss": 0.3929, "lr": 2.204413754585857e-06, "epoch": 4.3164556962025316, "percentage": 86.42, "elapsed_time": "4:03:37", "remaining_time": "0:38:16"}
1166
+ {"current_steps": 1064, "total_steps": 1230, "loss": 0.3826, "lr": 2.1785813006799406e-06, "epoch": 4.320506329113924, "percentage": 86.5, "elapsed_time": "4:04:22", "remaining_time": "0:38:07"}
1167
+ {"current_steps": 1065, "total_steps": 1230, "loss": 0.384, "lr": 2.1528923780302224e-06, "epoch": 4.324556962025317, "percentage": 86.59, "elapsed_time": "4:05:07", "remaining_time": "0:37:58"}
1168
+ {"current_steps": 1066, "total_steps": 1230, "loss": 0.3808, "lr": 2.127347193531757e-06, "epoch": 4.328607594936709, "percentage": 86.67, "elapsed_time": "4:05:52", "remaining_time": "0:37:49"}
1169
+ {"current_steps": 1067, "total_steps": 1230, "loss": 0.3841, "lr": 2.101945952921942e-06, "epoch": 4.332658227848102, "percentage": 86.75, "elapsed_time": "4:06:36", "remaining_time": "0:37:40"}
1170
+ {"current_steps": 1068, "total_steps": 1230, "loss": 0.3718, "lr": 2.0766888607788906e-06, "epoch": 4.336708860759494, "percentage": 86.83, "elapsed_time": "4:07:22", "remaining_time": "0:37:31"}
1171
+ {"current_steps": 1069, "total_steps": 1230, "loss": 0.3889, "lr": 2.0515761205197337e-06, "epoch": 4.340759493670886, "percentage": 86.91, "elapsed_time": "4:08:08", "remaining_time": "0:37:22"}
1172
+ {"current_steps": 1070, "total_steps": 1230, "loss": 0.3831, "lr": 2.0266079343990453e-06, "epoch": 4.344810126582279, "percentage": 86.99, "elapsed_time": "4:08:53", "remaining_time": "0:37:13"}
1173
+ {"current_steps": 1071, "total_steps": 1230, "loss": 0.379, "lr": 2.0017845035071494e-06, "epoch": 4.348860759493671, "percentage": 87.07, "elapsed_time": "4:09:37", "remaining_time": "0:37:03"}
1174
+ {"current_steps": 1072, "total_steps": 1230, "loss": 0.3987, "lr": 1.9771060277685537e-06, "epoch": 4.352911392405064, "percentage": 87.15, "elapsed_time": "4:10:21", "remaining_time": "0:36:53"}
1175
+ {"current_steps": 1073, "total_steps": 1230, "loss": 0.3772, "lr": 1.95257270594031e-06, "epoch": 4.356962025316456, "percentage": 87.24, "elapsed_time": "4:11:04", "remaining_time": "0:36:44"}
1176
+ {"current_steps": 1074, "total_steps": 1230, "loss": 0.3764, "lr": 1.9281847356104188e-06, "epoch": 4.361012658227848, "percentage": 87.32, "elapsed_time": "4:11:50", "remaining_time": "0:36:34"}
1177
+ {"current_steps": 1075, "total_steps": 1230, "loss": 0.3762, "lr": 1.9039423131962365e-06, "epoch": 4.365063291139241, "percentage": 87.4, "elapsed_time": "4:12:36", "remaining_time": "0:36:25"}
1178
+ {"current_steps": 1076, "total_steps": 1230, "loss": 0.3804, "lr": 1.8798456339429027e-06, "epoch": 4.369113924050633, "percentage": 87.48, "elapsed_time": "4:13:19", "remaining_time": "0:36:15"}
1179
+ {"current_steps": 1077, "total_steps": 1230, "loss": 0.3836, "lr": 1.8558948919217612e-06, "epoch": 4.373164556962025, "percentage": 87.56, "elapsed_time": "4:14:02", "remaining_time": "0:36:05"}
1180
+ {"current_steps": 1078, "total_steps": 1230, "loss": 0.3837, "lr": 1.8320902800287954e-06, "epoch": 4.377215189873418, "percentage": 87.64, "elapsed_time": "4:14:46", "remaining_time": "0:35:55"}
1181
+ {"current_steps": 1079, "total_steps": 1230, "loss": 0.3694, "lr": 1.8084319899830726e-06, "epoch": 4.38126582278481, "percentage": 87.72, "elapsed_time": "4:15:32", "remaining_time": "0:35:45"}
1182
+ {"current_steps": 1080, "total_steps": 1230, "loss": 0.3813, "lr": 1.7849202123252097e-06, "epoch": 4.385316455696202, "percentage": 87.8, "elapsed_time": "4:16:16", "remaining_time": "0:35:35"}
1183
+ {"current_steps": 1081, "total_steps": 1230, "loss": 0.3959, "lr": 1.7615551364158401e-06, "epoch": 4.389367088607595, "percentage": 87.89, "elapsed_time": "4:17:03", "remaining_time": "0:35:25"}
1184
+ {"current_steps": 1082, "total_steps": 1230, "loss": 0.3828, "lr": 1.738336950434061e-06, "epoch": 4.393417721518987, "percentage": 87.97, "elapsed_time": "4:17:46", "remaining_time": "0:35:15"}
1185
+ {"current_steps": 1083, "total_steps": 1230, "loss": 0.3635, "lr": 1.715265841375957e-06, "epoch": 4.39746835443038, "percentage": 88.05, "elapsed_time": "4:18:31", "remaining_time": "0:35:05"}
1186
+ {"current_steps": 1084, "total_steps": 1230, "loss": 0.3876, "lr": 1.6923419950530684e-06, "epoch": 4.401518987341772, "percentage": 88.13, "elapsed_time": "4:19:18", "remaining_time": "0:34:55"}
1187
+ {"current_steps": 1085, "total_steps": 1230, "loss": 0.3785, "lr": 1.6695655960909008e-06, "epoch": 4.405569620253164, "percentage": 88.21, "elapsed_time": "4:20:01", "remaining_time": "0:34:45"}
1188
+ {"current_steps": 1086, "total_steps": 1230, "loss": 0.3883, "lr": 1.646936827927441e-06, "epoch": 4.409620253164557, "percentage": 88.29, "elapsed_time": "4:20:47", "remaining_time": "0:34:34"}
1189
+ {"current_steps": 1087, "total_steps": 1230, "loss": 0.3808, "lr": 1.6244558728116766e-06, "epoch": 4.413670886075949, "percentage": 88.37, "elapsed_time": "4:21:33", "remaining_time": "0:34:24"}
1190
+ {"current_steps": 1088, "total_steps": 1230, "loss": 0.3619, "lr": 1.6021229118021265e-06, "epoch": 4.417721518987342, "percentage": 88.46, "elapsed_time": "4:22:19", "remaining_time": "0:34:14"}
1191
+ {"current_steps": 1089, "total_steps": 1230, "loss": 0.3794, "lr": 1.5799381247653967e-06, "epoch": 4.421772151898734, "percentage": 88.54, "elapsed_time": "4:23:05", "remaining_time": "0:34:03"}
1192
+ {"current_steps": 1090, "total_steps": 1230, "loss": 0.3718, "lr": 1.5579016903747013e-06, "epoch": 4.425822784810126, "percentage": 88.62, "elapsed_time": "4:23:50", "remaining_time": "0:33:53"}
1193
+ {"current_steps": 1091, "total_steps": 1230, "loss": 0.3829, "lr": 1.5360137861084656e-06, "epoch": 4.429873417721519, "percentage": 88.7, "elapsed_time": "4:24:34", "remaining_time": "0:33:42"}
1194
+ {"current_steps": 1092, "total_steps": 1230, "loss": 0.397, "lr": 1.5142745882488475e-06, "epoch": 4.433924050632911, "percentage": 88.78, "elapsed_time": "4:25:21", "remaining_time": "0:33:32"}
1195
+ {"current_steps": 1093, "total_steps": 1230, "loss": 0.3773, "lr": 1.4926842718803691e-06, "epoch": 4.4379746835443035, "percentage": 88.86, "elapsed_time": "4:26:06", "remaining_time": "0:33:21"}
1196
+ {"current_steps": 1094, "total_steps": 1230, "loss": 0.38, "lr": 1.4712430108884657e-06, "epoch": 4.442025316455696, "percentage": 88.94, "elapsed_time": "4:26:51", "remaining_time": "0:33:10"}
1197
+ {"current_steps": 1095, "total_steps": 1230, "loss": 0.372, "lr": 1.4499509779581078e-06, "epoch": 4.4460759493670885, "percentage": 89.02, "elapsed_time": "4:27:35", "remaining_time": "0:32:59"}
1198
+ {"current_steps": 1096, "total_steps": 1230, "loss": 0.3815, "lr": 1.4288083445723988e-06, "epoch": 4.450126582278481, "percentage": 89.11, "elapsed_time": "4:28:20", "remaining_time": "0:32:48"}
1199
+ {"current_steps": 1097, "total_steps": 1230, "loss": 0.3655, "lr": 1.4078152810112045e-06, "epoch": 4.4541772151898735, "percentage": 89.19, "elapsed_time": "4:29:02", "remaining_time": "0:32:37"}
1200
+ {"current_steps": 1098, "total_steps": 1230, "loss": 0.3871, "lr": 1.3869719563497697e-06, "epoch": 4.458227848101266, "percentage": 89.27, "elapsed_time": "4:29:48", "remaining_time": "0:32:26"}
1201
+ {"current_steps": 1099, "total_steps": 1230, "loss": 0.3691, "lr": 1.3662785384573663e-06, "epoch": 4.462278481012659, "percentage": 89.35, "elapsed_time": "4:30:34", "remaining_time": "0:32:15"}
1202
+ {"current_steps": 1100, "total_steps": 1230, "loss": 0.3594, "lr": 1.3457351939959383e-06, "epoch": 4.466329113924051, "percentage": 89.43, "elapsed_time": "4:31:17", "remaining_time": "0:32:03"}
1203
+ {"current_steps": 1101, "total_steps": 1230, "loss": 0.3662, "lr": 1.3253420884187551e-06, "epoch": 4.470379746835443, "percentage": 89.51, "elapsed_time": "4:32:01", "remaining_time": "0:31:52"}
1204
+ {"current_steps": 1102, "total_steps": 1230, "loss": 0.3927, "lr": 1.3050993859690953e-06, "epoch": 4.474430379746836, "percentage": 89.59, "elapsed_time": "4:32:47", "remaining_time": "0:31:41"}
1205
+ {"current_steps": 1103, "total_steps": 1230, "loss": 0.3819, "lr": 1.2850072496788869e-06, "epoch": 4.478481012658228, "percentage": 89.67, "elapsed_time": "4:33:33", "remaining_time": "0:31:29"}
1206
+ {"current_steps": 1104, "total_steps": 1230, "loss": 0.3688, "lr": 1.2650658413674434e-06, "epoch": 4.482531645569621, "percentage": 89.76, "elapsed_time": "4:34:18", "remaining_time": "0:31:18"}
1207
+ {"current_steps": 1105, "total_steps": 1230, "loss": 0.374, "lr": 1.2452753216401226e-06, "epoch": 4.486582278481013, "percentage": 89.84, "elapsed_time": "4:35:02", "remaining_time": "0:31:06"}
1208
+ {"current_steps": 1106, "total_steps": 1230, "loss": 0.3664, "lr": 1.2256358498870503e-06, "epoch": 4.490632911392405, "percentage": 89.92, "elapsed_time": "4:35:46", "remaining_time": "0:30:55"}
1209
+ {"current_steps": 1107, "total_steps": 1230, "loss": 0.3946, "lr": 1.2061475842818337e-06, "epoch": 4.494683544303798, "percentage": 90.0, "elapsed_time": "4:36:30", "remaining_time": "0:30:43"}
1210
+ {"current_steps": 1108, "total_steps": 1230, "loss": 0.3797, "lr": 1.1868106817802816e-06, "epoch": 4.49873417721519, "percentage": 90.08, "elapsed_time": "4:37:15", "remaining_time": "0:30:31"}
1211
+ {"current_steps": 1109, "total_steps": 1230, "loss": 0.3667, "lr": 1.1676252981191482e-06, "epoch": 4.502784810126582, "percentage": 90.16, "elapsed_time": "4:38:00", "remaining_time": "0:30:19"}
1212
+ {"current_steps": 1110, "total_steps": 1230, "loss": 0.3878, "lr": 1.1485915878148823e-06, "epoch": 4.506835443037975, "percentage": 90.24, "elapsed_time": "4:38:45", "remaining_time": "0:30:08"}
1213
+ {"current_steps": 1111, "total_steps": 1230, "loss": 0.3967, "lr": 1.1297097041623584e-06, "epoch": 4.510886075949367, "percentage": 90.33, "elapsed_time": "4:39:31", "remaining_time": "0:29:56"}
1214
+ {"current_steps": 1112, "total_steps": 1230, "loss": 0.3741, "lr": 1.1109797992336847e-06, "epoch": 4.514936708860759, "percentage": 90.41, "elapsed_time": "4:40:16", "remaining_time": "0:29:44"}
1215
+ {"current_steps": 1113, "total_steps": 1230, "loss": 0.3751, "lr": 1.092402023876933e-06, "epoch": 4.518987341772152, "percentage": 90.49, "elapsed_time": "4:41:02", "remaining_time": "0:29:32"}
1216
+ {"current_steps": 1114, "total_steps": 1230, "loss": 0.3825, "lr": 1.0739765277149527e-06, "epoch": 4.523037974683544, "percentage": 90.57, "elapsed_time": "4:41:46", "remaining_time": "0:29:20"}
1217
+ {"current_steps": 1115, "total_steps": 1230, "loss": 0.378, "lr": 1.0557034591441596e-06, "epoch": 4.527088607594937, "percentage": 90.65, "elapsed_time": "4:42:32", "remaining_time": "0:29:08"}
1218
+ {"current_steps": 1116, "total_steps": 1230, "loss": 0.3787, "lr": 1.0375829653333324e-06, "epoch": 4.531139240506329, "percentage": 90.73, "elapsed_time": "4:43:16", "remaining_time": "0:28:56"}
1219
+ {"current_steps": 1117, "total_steps": 1230, "loss": 0.3603, "lr": 1.0196151922224385e-06, "epoch": 4.535189873417721, "percentage": 90.81, "elapsed_time": "4:44:02", "remaining_time": "0:28:44"}
1220
+ {"current_steps": 1118, "total_steps": 1230, "loss": 0.3878, "lr": 1.0018002845214526e-06, "epoch": 4.539240506329114, "percentage": 90.89, "elapsed_time": "4:44:48", "remaining_time": "0:28:31"}
1221
+ {"current_steps": 1119, "total_steps": 1230, "loss": 0.383, "lr": 9.841383857091947e-07, "epoch": 4.543291139240506, "percentage": 90.98, "elapsed_time": "4:45:33", "remaining_time": "0:28:19"}
1222
+ {"current_steps": 1120, "total_steps": 1230, "loss": 0.3769, "lr": 9.666296380321616e-07, "epoch": 4.547341772151899, "percentage": 91.06, "elapsed_time": "4:46:19", "remaining_time": "0:28:07"}
1223
+ {"current_steps": 1121, "total_steps": 1230, "loss": 0.3786, "lr": 9.492741825034124e-07, "epoch": 4.551392405063291, "percentage": 91.14, "elapsed_time": "4:47:03", "remaining_time": "0:27:54"}
1224
+ {"current_steps": 1122, "total_steps": 1230, "loss": 0.3746, "lr": 9.320721589013892e-07, "epoch": 4.555443037974683, "percentage": 91.22, "elapsed_time": "4:47:48", "remaining_time": "0:27:42"}
1225
+ {"current_steps": 1123, "total_steps": 1230, "loss": 0.3692, "lr": 9.150237057688339e-07, "epoch": 4.559493670886076, "percentage": 91.3, "elapsed_time": "4:48:34", "remaining_time": "0:27:29"}
1226
+ {"current_steps": 1124, "total_steps": 1230, "loss": 0.3794, "lr": 8.981289604116328e-07, "epoch": 4.563544303797468, "percentage": 91.38, "elapsed_time": "4:49:18", "remaining_time": "0:27:16"}
1227
+ {"current_steps": 1125, "total_steps": 1230, "loss": 0.391, "lr": 8.813880588977542e-07, "epoch": 4.56759493670886, "percentage": 91.46, "elapsed_time": "4:50:02", "remaining_time": "0:27:04"}
1228
+ {"current_steps": 1126, "total_steps": 1230, "loss": 0.3821, "lr": 8.648011360561126e-07, "epoch": 4.571645569620253, "percentage": 91.54, "elapsed_time": "4:50:48", "remaining_time": "0:26:51"}
1229
+ {"current_steps": 1127, "total_steps": 1230, "loss": 0.3812, "lr": 8.483683254755037e-07, "epoch": 4.575696202531645, "percentage": 91.63, "elapsed_time": "4:51:32", "remaining_time": "0:26:38"}
1230
+ {"current_steps": 1128, "total_steps": 1230, "loss": 0.3844, "lr": 8.320897595035227e-07, "epoch": 4.5797468354430375, "percentage": 91.71, "elapsed_time": "4:52:17", "remaining_time": "0:26:25"}
1231
+ {"current_steps": 1129, "total_steps": 1230, "loss": 0.3846, "lr": 8.159655692455093e-07, "epoch": 4.5837974683544305, "percentage": 91.79, "elapsed_time": "4:53:02", "remaining_time": "0:26:12"}
1232
+ {"current_steps": 1130, "total_steps": 1230, "loss": 0.3848, "lr": 7.999958845634648e-07, "epoch": 4.5878481012658225, "percentage": 91.87, "elapsed_time": "4:53:45", "remaining_time": "0:25:59"}
1233
+ {"current_steps": 1131, "total_steps": 1230, "loss": 0.3708, "lr": 7.841808340750478e-07, "epoch": 4.5918987341772155, "percentage": 91.95, "elapsed_time": "4:54:30", "remaining_time": "0:25:46"}
1234
+ {"current_steps": 1132, "total_steps": 1230, "loss": 0.3835, "lr": 7.685205451524869e-07, "epoch": 4.595949367088608, "percentage": 92.03, "elapsed_time": "4:55:15", "remaining_time": "0:25:33"}
1235
+ {"current_steps": 1133, "total_steps": 1230, "loss": 0.3881, "lr": 7.530151439216027e-07, "epoch": 4.6, "percentage": 92.11, "elapsed_time": "4:56:01", "remaining_time": "0:25:20"}
1236
+ {"current_steps": 1134, "total_steps": 1230, "loss": 0.3627, "lr": 7.376647552607675e-07, "epoch": 4.604050632911393, "percentage": 92.2, "elapsed_time": "4:56:44", "remaining_time": "0:25:07"}
1237
+ {"current_steps": 1135, "total_steps": 1230, "loss": 0.3726, "lr": 7.224695027998963e-07, "epoch": 4.608101265822785, "percentage": 92.28, "elapsed_time": "4:57:30", "remaining_time": "0:24:54"}
1238
+ {"current_steps": 1136, "total_steps": 1230, "loss": 0.3734, "lr": 7.07429508919466e-07, "epoch": 4.612151898734178, "percentage": 92.36, "elapsed_time": "4:58:14", "remaining_time": "0:24:40"}
1239
+ {"current_steps": 1137, "total_steps": 1230, "loss": 0.3781, "lr": 6.925448947495206e-07, "epoch": 4.61620253164557, "percentage": 92.44, "elapsed_time": "4:59:00", "remaining_time": "0:24:27"}
1240
+ {"current_steps": 1138, "total_steps": 1230, "loss": 0.3914, "lr": 6.778157801686936e-07, "epoch": 4.620253164556962, "percentage": 92.52, "elapsed_time": "4:59:44", "remaining_time": "0:24:13"}
1241
+ {"current_steps": 1139, "total_steps": 1230, "loss": 0.3855, "lr": 6.632422838032515e-07, "epoch": 4.624303797468355, "percentage": 92.6, "elapsed_time": "5:00:30", "remaining_time": "0:24:00"}
1242
+ {"current_steps": 1140, "total_steps": 1230, "loss": 0.3881, "lr": 6.488245230261281e-07, "epoch": 4.628354430379747, "percentage": 92.68, "elapsed_time": "5:01:12", "remaining_time": "0:23:46"}
1243
+ {"current_steps": 1141, "total_steps": 1230, "loss": 0.3649, "lr": 6.345626139559868e-07, "epoch": 4.632405063291139, "percentage": 92.76, "elapsed_time": "5:01:57", "remaining_time": "0:23:33"}
1244
+ {"current_steps": 1142, "total_steps": 1230, "loss": 0.3749, "lr": 6.204566714562866e-07, "epoch": 4.636455696202532, "percentage": 92.85, "elapsed_time": "5:02:40", "remaining_time": "0:23:19"}
1245
+ {"current_steps": 1143, "total_steps": 1230, "loss": 0.3909, "lr": 6.06506809134344e-07, "epoch": 4.640506329113924, "percentage": 92.93, "elapsed_time": "5:03:23", "remaining_time": "0:23:05"}
1246
+ {"current_steps": 1144, "total_steps": 1230, "loss": 0.3826, "lr": 5.927131393404373e-07, "epoch": 4.644556962025316, "percentage": 93.01, "elapsed_time": "5:04:08", "remaining_time": "0:22:51"}
1247
+ {"current_steps": 1145, "total_steps": 1230, "loss": 0.3749, "lr": 5.790757731668817e-07, "epoch": 4.648607594936709, "percentage": 93.09, "elapsed_time": "5:04:51", "remaining_time": "0:22:37"}
1248
+ {"current_steps": 1146, "total_steps": 1230, "loss": 0.3805, "lr": 5.655948204471507e-07, "epoch": 4.652658227848101, "percentage": 93.17, "elapsed_time": "5:05:38", "remaining_time": "0:22:24"}
1249
+ {"current_steps": 1147, "total_steps": 1230, "loss": 0.3808, "lr": 5.522703897549875e-07, "epoch": 4.656708860759494, "percentage": 93.25, "elapsed_time": "5:06:21", "remaining_time": "0:22:10"}
1250
+ {"current_steps": 1148, "total_steps": 1230, "loss": 0.3713, "lr": 5.391025884035239e-07, "epoch": 4.660759493670886, "percentage": 93.33, "elapsed_time": "5:07:06", "remaining_time": "0:21:56"}
1251
+ {"current_steps": 1149, "total_steps": 1230, "loss": 0.3785, "lr": 5.260915224444207e-07, "epoch": 4.664810126582278, "percentage": 93.41, "elapsed_time": "5:07:50", "remaining_time": "0:21:42"}
1252
+ {"current_steps": 1150, "total_steps": 1230, "loss": 0.3782, "lr": 5.132372966670129e-07, "epoch": 4.668860759493671, "percentage": 93.5, "elapsed_time": "5:08:35", "remaining_time": "0:21:28"}
1253
+ {"current_steps": 1151, "total_steps": 1230, "loss": 0.3855, "lr": 5.005400145974704e-07, "epoch": 4.672911392405063, "percentage": 93.58, "elapsed_time": "5:09:20", "remaining_time": "0:21:13"}
1254
+ {"current_steps": 1152, "total_steps": 1230, "loss": 0.3858, "lr": 4.879997784979562e-07, "epoch": 4.676962025316456, "percentage": 93.66, "elapsed_time": "5:10:04", "remaining_time": "0:20:59"}
1255
+ {"current_steps": 1153, "total_steps": 1230, "loss": 0.376, "lr": 4.7561668936580984e-07, "epoch": 4.681012658227848, "percentage": 93.74, "elapsed_time": "5:10:49", "remaining_time": "0:20:45"}
1256
+ {"current_steps": 1154, "total_steps": 1230, "loss": 0.3772, "lr": 4.6339084693272306e-07, "epoch": 4.68506329113924, "percentage": 93.82, "elapsed_time": "5:11:32", "remaining_time": "0:20:31"}
1257
+ {"current_steps": 1155, "total_steps": 1230, "loss": 0.3827, "lr": 4.5132234966395847e-07, "epoch": 4.689113924050633, "percentage": 93.9, "elapsed_time": "5:12:18", "remaining_time": "0:20:16"}
1258
+ {"current_steps": 1156, "total_steps": 1230, "loss": 0.3624, "lr": 4.3941129475752795e-07, "epoch": 4.693164556962025, "percentage": 93.98, "elapsed_time": "5:13:02", "remaining_time": "0:20:02"}
1259
+ {"current_steps": 1157, "total_steps": 1230, "loss": 0.3989, "lr": 4.27657778143431e-07, "epoch": 4.697215189873417, "percentage": 94.07, "elapsed_time": "5:13:47", "remaining_time": "0:19:47"}
1260
+ {"current_steps": 1158, "total_steps": 1230, "loss": 0.3681, "lr": 4.1606189448287757e-07, "epoch": 4.70126582278481, "percentage": 94.15, "elapsed_time": "5:14:33", "remaining_time": "0:19:33"}
1261
+ {"current_steps": 1159, "total_steps": 1230, "loss": 0.3602, "lr": 4.046237371675177e-07, "epoch": 4.705316455696202, "percentage": 94.23, "elapsed_time": "5:15:20", "remaining_time": "0:19:19"}
1262
+ {"current_steps": 1160, "total_steps": 1230, "loss": 0.376, "lr": 3.9334339831869963e-07, "epoch": 4.7093670886075945, "percentage": 94.31, "elapsed_time": "5:16:05", "remaining_time": "0:19:04"}
1263
+ {"current_steps": 1161, "total_steps": 1230, "loss": 0.396, "lr": 3.8222096878671955e-07, "epoch": 4.713417721518987, "percentage": 94.39, "elapsed_time": "5:16:51", "remaining_time": "0:18:49"}
1264
+ {"current_steps": 1162, "total_steps": 1230, "loss": 0.3921, "lr": 3.7125653815009545e-07, "epoch": 4.7174683544303795, "percentage": 94.47, "elapsed_time": "5:17:34", "remaining_time": "0:18:35"}
1265
+ {"current_steps": 1163, "total_steps": 1230, "loss": 0.3881, "lr": 3.6045019471484974e-07, "epoch": 4.7215189873417724, "percentage": 94.55, "elapsed_time": "5:18:21", "remaining_time": "0:18:20"}
1266
+ {"current_steps": 1164, "total_steps": 1230, "loss": 0.39, "lr": 3.498020255137813e-07, "epoch": 4.7255696202531645, "percentage": 94.63, "elapsed_time": "5:19:06", "remaining_time": "0:18:05"}
1267
+ {"current_steps": 1165, "total_steps": 1230, "loss": 0.3867, "lr": 3.393121163057811e-07, "epoch": 4.729620253164557, "percentage": 94.72, "elapsed_time": "5:19:48", "remaining_time": "0:17:50"}
1268
+ {"current_steps": 1166, "total_steps": 1230, "loss": 0.3884, "lr": 3.289805515751399e-07, "epoch": 4.7336708860759495, "percentage": 94.8, "elapsed_time": "5:20:31", "remaining_time": "0:17:35"}
1269
+ {"current_steps": 1167, "total_steps": 1230, "loss": 0.3739, "lr": 3.188074145308573e-07, "epoch": 4.737721518987342, "percentage": 94.88, "elapsed_time": "5:21:18", "remaining_time": "0:17:20"}
1270
+ {"current_steps": 1168, "total_steps": 1230, "loss": 0.3675, "lr": 3.087927871059804e-07, "epoch": 4.741772151898735, "percentage": 94.96, "elapsed_time": "5:22:02", "remaining_time": "0:17:05"}
1271
+ {"current_steps": 1169, "total_steps": 1230, "loss": 0.381, "lr": 2.989367499569418e-07, "epoch": 4.745822784810127, "percentage": 95.04, "elapsed_time": "5:22:46", "remaining_time": "0:16:50"}
1272
+ {"current_steps": 1170, "total_steps": 1230, "loss": 0.3781, "lr": 2.8923938246290917e-07, "epoch": 4.749873417721519, "percentage": 95.12, "elapsed_time": "5:23:30", "remaining_time": "0:16:35"}
1273
+ {"current_steps": 1171, "total_steps": 1230, "loss": 0.3784, "lr": 2.7970076272514804e-07, "epoch": 4.753924050632912, "percentage": 95.2, "elapsed_time": "5:24:16", "remaining_time": "0:16:20"}
1274
+ {"current_steps": 1172, "total_steps": 1230, "loss": 0.3831, "lr": 2.703209675663887e-07, "epoch": 4.757974683544304, "percentage": 95.28, "elapsed_time": "5:25:01", "remaining_time": "0:16:05"}
1275
+ {"current_steps": 1173, "total_steps": 1230, "loss": 0.3862, "lr": 2.6110007253021374e-07, "epoch": 4.762025316455696, "percentage": 95.37, "elapsed_time": "5:25:47", "remaining_time": "0:15:49"}
1276
+ {"current_steps": 1174, "total_steps": 1230, "loss": 0.3881, "lr": 2.520381518804471e-07, "epoch": 4.766075949367089, "percentage": 95.45, "elapsed_time": "5:26:32", "remaining_time": "0:15:34"}
1277
+ {"current_steps": 1175, "total_steps": 1230, "loss": 0.3791, "lr": 2.4313527860054585e-07, "epoch": 4.770126582278481, "percentage": 95.53, "elapsed_time": "5:27:18", "remaining_time": "0:15:19"}
1278
+ {"current_steps": 1176, "total_steps": 1230, "loss": 0.3881, "lr": 2.343915243930317e-07, "epoch": 4.774177215189873, "percentage": 95.61, "elapsed_time": "5:28:02", "remaining_time": "0:15:03"}
1279
+ {"current_steps": 1177, "total_steps": 1230, "loss": 0.3691, "lr": 2.2580695967889367e-07, "epoch": 4.778227848101266, "percentage": 95.69, "elapsed_time": "5:28:47", "remaining_time": "0:14:48"}
1280
+ {"current_steps": 1178, "total_steps": 1230, "loss": 0.3642, "lr": 2.1738165359704189e-07, "epoch": 4.782278481012658, "percentage": 95.77, "elapsed_time": "5:29:32", "remaining_time": "0:14:32"}
1281
+ {"current_steps": 1179, "total_steps": 1230, "loss": 0.385, "lr": 2.0911567400373257e-07, "epoch": 4.786329113924051, "percentage": 95.85, "elapsed_time": "5:30:15", "remaining_time": "0:14:17"}
1282
+ {"current_steps": 1180, "total_steps": 1230, "loss": 0.3894, "lr": 2.0100908747202607e-07, "epoch": 4.790379746835443, "percentage": 95.93, "elapsed_time": "5:31:00", "remaining_time": "0:14:01"}
1283
+ {"current_steps": 1181, "total_steps": 1230, "loss": 0.3838, "lr": 1.9306195929125638e-07, "epoch": 4.794430379746835, "percentage": 96.02, "elapsed_time": "5:31:46", "remaining_time": "0:13:45"}
1284
+ {"current_steps": 1182, "total_steps": 1230, "loss": 0.3894, "lr": 1.8527435346650247e-07, "epoch": 4.798481012658228, "percentage": 96.1, "elapsed_time": "5:32:28", "remaining_time": "0:13:30"}
1285
+ {"current_steps": 1183, "total_steps": 1230, "loss": 0.3819, "lr": 1.7764633271807108e-07, "epoch": 4.80253164556962, "percentage": 96.18, "elapsed_time": "5:33:12", "remaining_time": "0:13:14"}
1286
+ {"current_steps": 1184, "total_steps": 1230, "loss": 0.3805, "lr": 1.7017795848099262e-07, "epoch": 4.806582278481013, "percentage": 96.26, "elapsed_time": "5:33:59", "remaining_time": "0:12:58"}
1287
+ {"current_steps": 1185, "total_steps": 1230, "loss": 0.3844, "lr": 1.6286929090452596e-07, "epoch": 4.810632911392405, "percentage": 96.34, "elapsed_time": "5:34:45", "remaining_time": "0:12:42"}
1288
+ {"current_steps": 1186, "total_steps": 1230, "loss": 0.3899, "lr": 1.557203888516745e-07, "epoch": 4.814683544303797, "percentage": 96.42, "elapsed_time": "5:35:30", "remaining_time": "0:12:26"}
1289
+ {"current_steps": 1187, "total_steps": 1230, "loss": 0.3715, "lr": 1.487313098987131e-07, "epoch": 4.81873417721519, "percentage": 96.5, "elapsed_time": "5:36:17", "remaining_time": "0:12:10"}
1290
+ {"current_steps": 1188, "total_steps": 1230, "loss": 0.3768, "lr": 1.4190211033472402e-07, "epoch": 4.822784810126582, "percentage": 96.59, "elapsed_time": "5:37:02", "remaining_time": "0:11:54"}
1291
+ {"current_steps": 1189, "total_steps": 1230, "loss": 0.3776, "lr": 1.3523284516113955e-07, "epoch": 4.826835443037975, "percentage": 96.67, "elapsed_time": "5:37:48", "remaining_time": "0:11:38"}
1292
+ {"current_steps": 1190, "total_steps": 1230, "loss": 0.3746, "lr": 1.2872356809130682e-07, "epoch": 4.830886075949367, "percentage": 96.75, "elapsed_time": "5:38:31", "remaining_time": "0:11:22"}
1293
+ {"current_steps": 1191, "total_steps": 1230, "loss": 0.3835, "lr": 1.2237433155004807e-07, "epoch": 4.834936708860759, "percentage": 96.83, "elapsed_time": "5:39:15", "remaining_time": "0:11:06"}
1294
+ {"current_steps": 1192, "total_steps": 1230, "loss": 0.3916, "lr": 1.1618518667323886e-07, "epoch": 4.838987341772152, "percentage": 96.91, "elapsed_time": "5:40:00", "remaining_time": "0:10:50"}
1295
+ {"current_steps": 1193, "total_steps": 1230, "loss": 0.3876, "lr": 1.1015618330740385e-07, "epoch": 4.843037974683544, "percentage": 96.99, "elapsed_time": "5:40:45", "remaining_time": "0:10:34"}
1296
+ {"current_steps": 1194, "total_steps": 1230, "loss": 0.3858, "lr": 1.042873700093061e-07, "epoch": 4.847088607594936, "percentage": 97.07, "elapsed_time": "5:41:31", "remaining_time": "0:10:17"}
1297
+ {"current_steps": 1195, "total_steps": 1230, "loss": 0.3916, "lr": 9.857879404556291e-08, "epoch": 4.851139240506329, "percentage": 97.15, "elapsed_time": "5:42:17", "remaining_time": "0:10:01"}
1298
+ {"current_steps": 1196, "total_steps": 1230, "loss": 0.3805, "lr": 9.303050139225722e-08, "epoch": 4.8551898734177215, "percentage": 97.24, "elapsed_time": "5:43:00", "remaining_time": "0:09:45"}
1299
+ {"current_steps": 1197, "total_steps": 1230, "loss": 0.3729, "lr": 8.76425367345779e-08, "epoch": 4.8592405063291135, "percentage": 97.32, "elapsed_time": "5:43:45", "remaining_time": "0:09:28"}
1300
+ {"current_steps": 1198, "total_steps": 1230, "loss": 0.3894, "lr": 8.241494346644897e-08, "epoch": 4.8632911392405065, "percentage": 97.4, "elapsed_time": "5:44:29", "remaining_time": "0:09:12"}
1301
+ {"current_steps": 1199, "total_steps": 1230, "loss": 0.3632, "lr": 7.734776369019204e-08, "epoch": 4.867341772151899, "percentage": 97.48, "elapsed_time": "5:45:13", "remaining_time": "0:08:55"}
1302
+ {"current_steps": 1200, "total_steps": 1230, "loss": 0.385, "lr": 7.244103821617332e-08, "epoch": 4.8713924050632915, "percentage": 97.56, "elapsed_time": "5:45:57", "remaining_time": "0:08:38"}
1303
+ {"current_steps": 1201, "total_steps": 1230, "loss": 0.3652, "lr": 6.769480656248606e-08, "epoch": 4.875443037974684, "percentage": 97.64, "elapsed_time": "5:46:39", "remaining_time": "0:08:22"}
1304
+ {"current_steps": 1202, "total_steps": 1230, "loss": 0.3669, "lr": 6.310910695462635e-08, "epoch": 4.879493670886076, "percentage": 97.72, "elapsed_time": "5:47:24", "remaining_time": "0:08:05"}
1305
+ {"current_steps": 1203, "total_steps": 1230, "loss": 0.3799, "lr": 5.8683976325191185e-08, "epoch": 4.883544303797469, "percentage": 97.8, "elapsed_time": "5:48:09", "remaining_time": "0:07:48"}
1306
+ {"current_steps": 1204, "total_steps": 1230, "loss": 0.3703, "lr": 5.4419450313571984e-08, "epoch": 4.887594936708861, "percentage": 97.89, "elapsed_time": "5:48:51", "remaining_time": "0:07:32"}
1307
+ {"current_steps": 1205, "total_steps": 1230, "loss": 0.3903, "lr": 5.031556326567488e-08, "epoch": 4.891645569620254, "percentage": 97.97, "elapsed_time": "5:49:36", "remaining_time": "0:07:15"}
1308
+ {"current_steps": 1206, "total_steps": 1230, "loss": 0.3683, "lr": 4.637234823364312e-08, "epoch": 4.895696202531646, "percentage": 98.05, "elapsed_time": "5:50:21", "remaining_time": "0:06:58"}
1309
+ {"current_steps": 1207, "total_steps": 1230, "loss": 0.3647, "lr": 4.258983697558838e-08, "epoch": 4.899746835443038, "percentage": 98.13, "elapsed_time": "5:51:06", "remaining_time": "0:06:41"}
1310
+ {"current_steps": 1208, "total_steps": 1230, "loss": 0.3811, "lr": 3.896805995533548e-08, "epoch": 4.903797468354431, "percentage": 98.21, "elapsed_time": "5:51:50", "remaining_time": "0:06:24"}
1311
+ {"current_steps": 1209, "total_steps": 1230, "loss": 0.3778, "lr": 3.550704634218028e-08, "epoch": 4.907848101265823, "percentage": 98.29, "elapsed_time": "5:52:35", "remaining_time": "0:06:07"}
1312
+ {"current_steps": 1210, "total_steps": 1230, "loss": 0.3665, "lr": 3.2206824010647676e-08, "epoch": 4.911898734177215, "percentage": 98.37, "elapsed_time": "5:53:18", "remaining_time": "0:05:50"}
1313
+ {"current_steps": 1211, "total_steps": 1230, "loss": 0.3769, "lr": 2.9067419540278476e-08, "epoch": 4.915949367088608, "percentage": 98.46, "elapsed_time": "5:54:01", "remaining_time": "0:05:33"}
1314
+ {"current_steps": 1212, "total_steps": 1230, "loss": 0.3704, "lr": 2.6088858215400638e-08, "epoch": 4.92, "percentage": 98.54, "elapsed_time": "5:54:44", "remaining_time": "0:05:16"}
1315
+ {"current_steps": 1213, "total_steps": 1230, "loss": 0.3838, "lr": 2.3271164024940564e-08, "epoch": 4.924050632911392, "percentage": 98.62, "elapsed_time": "5:55:29", "remaining_time": "0:04:58"}
1316
+ {"current_steps": 1214, "total_steps": 1230, "loss": 0.3925, "lr": 2.061435966221881e-08, "epoch": 4.928101265822785, "percentage": 98.7, "elapsed_time": "5:56:15", "remaining_time": "0:04:41"}
1317
+ {"current_steps": 1215, "total_steps": 1230, "loss": 0.3867, "lr": 1.811846652477245e-08, "epoch": 4.932151898734177, "percentage": 98.78, "elapsed_time": "5:56:59", "remaining_time": "0:04:24"}
1318
+ {"current_steps": 1216, "total_steps": 1230, "loss": 0.3668, "lr": 1.5783504714184106e-08, "epoch": 4.93620253164557, "percentage": 98.86, "elapsed_time": "5:57:43", "remaining_time": "0:04:07"}
1319
+ {"current_steps": 1217, "total_steps": 1230, "loss": 0.3947, "lr": 1.360949303591097e-08, "epoch": 4.940253164556962, "percentage": 98.94, "elapsed_time": "5:58:29", "remaining_time": "0:03:49"}
1320
+ {"current_steps": 1218, "total_steps": 1230, "loss": 0.3705, "lr": 1.1596448999144916e-08, "epoch": 4.944303797468354, "percentage": 99.02, "elapsed_time": "5:59:14", "remaining_time": "0:03:32"}
1321
+ {"current_steps": 1219, "total_steps": 1230, "loss": 0.3622, "lr": 9.744388816668172e-09, "epoch": 4.948354430379747, "percentage": 99.11, "elapsed_time": "6:00:00", "remaining_time": "0:03:14"}
1322
+ {"current_steps": 1220, "total_steps": 1230, "loss": 0.3846, "lr": 8.05332740472009e-09, "epoch": 4.952405063291139, "percentage": 99.19, "elapsed_time": "6:00:45", "remaining_time": "0:02:57"}
1323
+ {"current_steps": 1221, "total_steps": 1230, "loss": 0.3693, "lr": 6.523278382872811e-09, "epoch": 4.956455696202532, "percentage": 99.27, "elapsed_time": "6:01:30", "remaining_time": "0:02:39"}
1324
+ {"current_steps": 1222, "total_steps": 1230, "loss": 0.3718, "lr": 5.15425407393133e-09, "epoch": 4.960506329113924, "percentage": 99.35, "elapsed_time": "6:02:14", "remaining_time": "0:02:22"}
1325
+ {"current_steps": 1223, "total_steps": 1230, "loss": 0.3755, "lr": 3.94626550383137e-09, "epoch": 4.964556962025316, "percentage": 99.43, "elapsed_time": "6:02:57", "remaining_time": "0:02:04"}
1326
+ {"current_steps": 1224, "total_steps": 1230, "loss": 0.3705, "lr": 2.899322401546112e-09, "epoch": 4.968607594936709, "percentage": 99.51, "elapsed_time": "6:03:43", "remaining_time": "0:01:46"}
1327
+ {"current_steps": 1225, "total_steps": 1230, "loss": 0.3667, "lr": 2.013433199010706e-09, "epoch": 4.972658227848101, "percentage": 99.59, "elapsed_time": "6:04:28", "remaining_time": "0:01:29"}
1328
+ {"current_steps": 1226, "total_steps": 1230, "loss": 0.3734, "lr": 1.2886050310556563e-09, "epoch": 4.976708860759493, "percentage": 99.67, "elapsed_time": "6:05:13", "remaining_time": "0:01:11"}
1329
+ {"current_steps": 1227, "total_steps": 1230, "loss": 0.3853, "lr": 7.248437353468695e-10, "epoch": 4.980759493670886, "percentage": 99.76, "elapsed_time": "6:05:58", "remaining_time": "0:00:53"}
1330
+ {"current_steps": 1228, "total_steps": 1230, "loss": 0.3755, "lr": 3.221538523412449e-10, "epoch": 4.984810126582278, "percentage": 99.84, "elapsed_time": "6:06:43", "remaining_time": "0:00:35"}
1331
+ {"current_steps": 1229, "total_steps": 1230, "loss": 0.3792, "lr": 8.053862524670663e-11, "epoch": 4.9888607594936705, "percentage": 99.92, "elapsed_time": "6:07:27", "remaining_time": "0:00:17"}
1332
+ {"current_steps": 1230, "total_steps": 1230, "loss": 0.3929, "lr": 0.0, "epoch": 4.992911392405063, "percentage": 100.0, "elapsed_time": "6:08:12", "remaining_time": "0:00:00"}
1333
+ {"current_steps": 1230, "total_steps": 1230, "epoch": 4.992911392405063, "percentage": 100.0, "elapsed_time": "6:11:50", "remaining_time": "0:00:00"}