neginr commited on
Commit
c2178ae
·
verified ·
1 Parent(s): 3bbd088

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 sha256:98aa1a6280509831c4b3f10b4941c4e12969cafa6400a1ff9b943f73cfc55df0
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc5902c156db27af37e818846aa7459c8064c395d31b53629bfcff86d392ebd2
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4b38eefed441b39ac0b80b072346fbe532f9fea8c2d2995650574b221d2f324a
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a0e2c4e381d1633c4f6b9dcbc57387758dd1df79c68f81cf8e618425f53cd4a
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:d29b2bef5dbb64f4f0b52b0f599c6d7649bd8754e3b3dc0a6ea0ca0a8a251259
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b7b0d8bb9c510336de536f29bc91d9750519003801a7410ccbf03f5e018aa36
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:15b1cbf36e61932fcfb78ee8f14ea97b3226894d2653dfaeca6fb9c629f236cc
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4756747320f51a10a3add4e08f7621159a79111371bd2052a0dd7c61648d9228
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -989,3 +989,435 @@
989
  {"current_steps": 989, "total_steps": 1230, "loss": 0.3504, "lr": 4.498240773728859e-06, "epoch": 4.006075949367089, "percentage": 80.41, "elapsed_time": "11:58:34", "remaining_time": "2:55:06"}
990
  {"current_steps": 990, "total_steps": 1230, "loss": 0.3564, "lr": 4.462440087699609e-06, "epoch": 4.010126582278481, "percentage": 80.49, "elapsed_time": "11:59:16", "remaining_time": "2:54:22"}
991
  {"current_steps": 991, "total_steps": 1230, "loss": 0.3295, "lr": 4.426764539041861e-06, "epoch": 4.014177215189873, "percentage": 80.57, "elapsed_time": "11:59:57", "remaining_time": "2:53:37"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
989
  {"current_steps": 989, "total_steps": 1230, "loss": 0.3504, "lr": 4.498240773728859e-06, "epoch": 4.006075949367089, "percentage": 80.41, "elapsed_time": "11:58:34", "remaining_time": "2:55:06"}
990
  {"current_steps": 990, "total_steps": 1230, "loss": 0.3564, "lr": 4.462440087699609e-06, "epoch": 4.010126582278481, "percentage": 80.49, "elapsed_time": "11:59:16", "remaining_time": "2:54:22"}
991
  {"current_steps": 991, "total_steps": 1230, "loss": 0.3295, "lr": 4.426764539041861e-06, "epoch": 4.014177215189873, "percentage": 80.57, "elapsed_time": "11:59:57", "remaining_time": "2:53:37"}
992
+ {"current_steps": 992, "total_steps": 1230, "loss": 0.3332, "lr": 4.391214415081582e-06, "epoch": 4.018227848101266, "percentage": 80.65, "elapsed_time": "12:00:37", "remaining_time": "2:52:53"}
993
+ {"current_steps": 993, "total_steps": 1230, "loss": 0.3255, "lr": 4.355790002134579e-06, "epoch": 4.022278481012658, "percentage": 80.73, "elapsed_time": "12:01:18", "remaining_time": "2:52:09"}
994
+ {"current_steps": 994, "total_steps": 1230, "loss": 0.3427, "lr": 4.320491585504207e-06, "epoch": 4.02632911392405, "percentage": 80.81, "elapsed_time": "12:02:02", "remaining_time": "2:51:25"}
995
+ {"current_steps": 995, "total_steps": 1230, "loss": 0.3367, "lr": 4.2853194494790615e-06, "epoch": 4.030379746835443, "percentage": 80.89, "elapsed_time": "12:02:47", "remaining_time": "2:50:42"}
996
+ {"current_steps": 996, "total_steps": 1230, "loss": 0.3279, "lr": 4.250273877330691e-06, "epoch": 4.034430379746835, "percentage": 80.98, "elapsed_time": "12:03:29", "remaining_time": "2:49:58"}
997
+ {"current_steps": 997, "total_steps": 1230, "loss": 0.3298, "lr": 4.215355151311313e-06, "epoch": 4.038481012658228, "percentage": 81.06, "elapsed_time": "12:04:13", "remaining_time": "2:49:15"}
998
+ {"current_steps": 998, "total_steps": 1230, "loss": 0.3446, "lr": 4.180563552651542e-06, "epoch": 4.04253164556962, "percentage": 81.14, "elapsed_time": "12:04:58", "remaining_time": "2:48:31"}
999
+ {"current_steps": 999, "total_steps": 1230, "loss": 0.3093, "lr": 4.145899361558147e-06, "epoch": 4.046582278481012, "percentage": 81.22, "elapsed_time": "12:05:38", "remaining_time": "2:47:47"}
1000
+ {"current_steps": 1000, "total_steps": 1230, "loss": 0.3394, "lr": 4.111362857211738e-06, "epoch": 4.050632911392405, "percentage": 81.3, "elapsed_time": "12:06:22", "remaining_time": "2:47:04"}
1001
+ {"current_steps": 1001, "total_steps": 1230, "loss": 0.3524, "lr": 4.076954317764592e-06, "epoch": 4.054683544303797, "percentage": 81.38, "elapsed_time": "12:07:05", "remaining_time": "2:46:20"}
1002
+ {"current_steps": 1002, "total_steps": 1230, "loss": 0.3478, "lr": 4.042674020338335e-06, "epoch": 4.0587341772151895, "percentage": 81.46, "elapsed_time": "12:07:49", "remaining_time": "2:45:36"}
1003
+ {"current_steps": 1003, "total_steps": 1230, "loss": 0.3189, "lr": 4.0085222410217835e-06, "epoch": 4.062784810126582, "percentage": 81.54, "elapsed_time": "12:08:31", "remaining_time": "2:44:52"}
1004
+ {"current_steps": 1004, "total_steps": 1230, "loss": 0.3361, "lr": 3.974499254868674e-06, "epoch": 4.0668354430379745, "percentage": 81.63, "elapsed_time": "12:09:16", "remaining_time": "2:44:09"}
1005
+ {"current_steps": 1005, "total_steps": 1230, "loss": 0.3191, "lr": 3.940605335895451e-06, "epoch": 4.0708860759493675, "percentage": 81.71, "elapsed_time": "12:09:56", "remaining_time": "2:43:25"}
1006
+ {"current_steps": 1006, "total_steps": 1230, "loss": 0.3523, "lr": 3.90684075707908e-06, "epoch": 4.0749367088607595, "percentage": 81.79, "elapsed_time": "12:10:40", "remaining_time": "2:42:41"}
1007
+ {"current_steps": 1007, "total_steps": 1230, "loss": 0.315, "lr": 3.8732057903548505e-06, "epoch": 4.078987341772152, "percentage": 81.87, "elapsed_time": "12:11:20", "remaining_time": "2:41:57"}
1008
+ {"current_steps": 1008, "total_steps": 1230, "loss": 0.3219, "lr": 3.8397007066141375e-06, "epoch": 4.083037974683545, "percentage": 81.95, "elapsed_time": "12:12:01", "remaining_time": "2:41:13"}
1009
+ {"current_steps": 1009, "total_steps": 1230, "loss": 0.3519, "lr": 3.806325775702304e-06, "epoch": 4.087088607594937, "percentage": 82.03, "elapsed_time": "12:12:40", "remaining_time": "2:40:28"}
1010
+ {"current_steps": 1010, "total_steps": 1230, "loss": 0.3284, "lr": 3.773081266416434e-06, "epoch": 4.091139240506329, "percentage": 82.11, "elapsed_time": "12:13:23", "remaining_time": "2:39:44"}
1011
+ {"current_steps": 1011, "total_steps": 1230, "loss": 0.3387, "lr": 3.739967446503245e-06, "epoch": 4.095189873417722, "percentage": 82.2, "elapsed_time": "12:14:08", "remaining_time": "2:39:01"}
1012
+ {"current_steps": 1012, "total_steps": 1230, "loss": 0.3306, "lr": 3.706984582656894e-06, "epoch": 4.099240506329114, "percentage": 82.28, "elapsed_time": "12:14:52", "remaining_time": "2:38:18"}
1013
+ {"current_steps": 1013, "total_steps": 1230, "loss": 0.3457, "lr": 3.6741329405168237e-06, "epoch": 4.103291139240507, "percentage": 82.36, "elapsed_time": "12:15:37", "remaining_time": "2:37:34"}
1014
+ {"current_steps": 1014, "total_steps": 1230, "loss": 0.3305, "lr": 3.641412784665648e-06, "epoch": 4.107341772151899, "percentage": 82.44, "elapsed_time": "12:16:20", "remaining_time": "2:36:51"}
1015
+ {"current_steps": 1015, "total_steps": 1230, "loss": 0.3456, "lr": 3.608824378627005e-06, "epoch": 4.111392405063291, "percentage": 82.52, "elapsed_time": "12:17:05", "remaining_time": "2:36:07"}
1016
+ {"current_steps": 1016, "total_steps": 1230, "loss": 0.3302, "lr": 3.5763679848634337e-06, "epoch": 4.115443037974684, "percentage": 82.6, "elapsed_time": "12:17:45", "remaining_time": "2:35:23"}
1017
+ {"current_steps": 1017, "total_steps": 1230, "loss": 0.3269, "lr": 3.544043864774269e-06, "epoch": 4.119493670886076, "percentage": 82.68, "elapsed_time": "12:18:29", "remaining_time": "2:34:40"}
1018
+ {"current_steps": 1018, "total_steps": 1230, "loss": 0.3251, "lr": 3.5118522786935282e-06, "epoch": 4.123544303797468, "percentage": 82.76, "elapsed_time": "12:19:12", "remaining_time": "2:33:56"}
1019
+ {"current_steps": 1019, "total_steps": 1230, "loss": 0.3244, "lr": 3.479793485887819e-06, "epoch": 4.127594936708861, "percentage": 82.85, "elapsed_time": "12:19:54", "remaining_time": "2:33:12"}
1020
+ {"current_steps": 1020, "total_steps": 1230, "loss": 0.3007, "lr": 3.4478677445542653e-06, "epoch": 4.131645569620253, "percentage": 82.93, "elapsed_time": "12:20:35", "remaining_time": "2:32:28"}
1021
+ {"current_steps": 1021, "total_steps": 1230, "loss": 0.336, "lr": 3.4160753118183767e-06, "epoch": 4.135696202531646, "percentage": 83.01, "elapsed_time": "12:21:16", "remaining_time": "2:31:44"}
1022
+ {"current_steps": 1022, "total_steps": 1230, "loss": 0.3117, "lr": 3.3844164437320527e-06, "epoch": 4.139746835443038, "percentage": 83.09, "elapsed_time": "12:21:58", "remaining_time": "2:31:00"}
1023
+ {"current_steps": 1023, "total_steps": 1230, "loss": 0.3519, "lr": 3.3528913952714558e-06, "epoch": 4.14379746835443, "percentage": 83.17, "elapsed_time": "12:22:41", "remaining_time": "2:30:16"}
1024
+ {"current_steps": 1024, "total_steps": 1230, "loss": 0.3002, "lr": 3.321500420335e-06, "epoch": 4.147848101265823, "percentage": 83.25, "elapsed_time": "12:23:26", "remaining_time": "2:29:33"}
1025
+ {"current_steps": 1025, "total_steps": 1230, "loss": 0.3307, "lr": 3.290243771741275e-06, "epoch": 4.151898734177215, "percentage": 83.33, "elapsed_time": "12:24:07", "remaining_time": "2:28:49"}
1026
+ {"current_steps": 1026, "total_steps": 1230, "loss": 0.3452, "lr": 3.2591217012270325e-06, "epoch": 4.155949367088607, "percentage": 83.41, "elapsed_time": "12:24:51", "remaining_time": "2:28:06"}
1027
+ {"current_steps": 1027, "total_steps": 1230, "loss": 0.326, "lr": 3.228134459445149e-06, "epoch": 4.16, "percentage": 83.5, "elapsed_time": "12:25:34", "remaining_time": "2:27:22"}
1028
+ {"current_steps": 1028, "total_steps": 1230, "loss": 0.3227, "lr": 3.1972822959626205e-06, "epoch": 4.164050632911392, "percentage": 83.58, "elapsed_time": "12:26:14", "remaining_time": "2:26:38"}
1029
+ {"current_steps": 1029, "total_steps": 1230, "loss": 0.3193, "lr": 3.166565459258513e-06, "epoch": 4.168101265822785, "percentage": 83.66, "elapsed_time": "12:26:55", "remaining_time": "2:25:53"}
1030
+ {"current_steps": 1030, "total_steps": 1230, "loss": 0.3413, "lr": 3.1359841967220193e-06, "epoch": 4.172151898734177, "percentage": 83.74, "elapsed_time": "12:27:34", "remaining_time": "2:25:09"}
1031
+ {"current_steps": 1031, "total_steps": 1230, "loss": 0.3227, "lr": 3.105538754650419e-06, "epoch": 4.176202531645569, "percentage": 83.82, "elapsed_time": "12:28:15", "remaining_time": "2:24:25"}
1032
+ {"current_steps": 1032, "total_steps": 1230, "loss": 0.3275, "lr": 3.07522937824712e-06, "epoch": 4.180253164556962, "percentage": 83.9, "elapsed_time": "12:28:55", "remaining_time": "2:23:41"}
1033
+ {"current_steps": 1033, "total_steps": 1230, "loss": 0.3183, "lr": 3.0450563116196697e-06, "epoch": 4.184303797468354, "percentage": 83.98, "elapsed_time": "12:29:36", "remaining_time": "2:22:57"}
1034
+ {"current_steps": 1034, "total_steps": 1230, "loss": 0.3545, "lr": 3.0150197977778008e-06, "epoch": 4.188354430379746, "percentage": 84.07, "elapsed_time": "12:30:22", "remaining_time": "2:22:14"}
1035
+ {"current_steps": 1035, "total_steps": 1230, "loss": 0.3325, "lr": 2.985120078631465e-06, "epoch": 4.192405063291139, "percentage": 84.15, "elapsed_time": "12:31:05", "remaining_time": "2:21:30"}
1036
+ {"current_steps": 1036, "total_steps": 1230, "loss": 0.3164, "lr": 2.9553573949888893e-06, "epoch": 4.1964556962025314, "percentage": 84.23, "elapsed_time": "12:31:48", "remaining_time": "2:20:46"}
1037
+ {"current_steps": 1037, "total_steps": 1230, "loss": 0.3366, "lr": 2.9257319865546384e-06, "epoch": 4.200506329113924, "percentage": 84.31, "elapsed_time": "12:32:31", "remaining_time": "2:20:03"}
1038
+ {"current_steps": 1038, "total_steps": 1230, "loss": 0.3573, "lr": 2.896244091927678e-06, "epoch": 4.2045569620253165, "percentage": 84.39, "elapsed_time": "12:33:16", "remaining_time": "2:19:19"}
1039
+ {"current_steps": 1039, "total_steps": 1230, "loss": 0.325, "lr": 2.8668939485994584e-06, "epoch": 4.2086075949367086, "percentage": 84.47, "elapsed_time": "12:33:56", "remaining_time": "2:18:35"}
1040
+ {"current_steps": 1040, "total_steps": 1230, "loss": 0.3281, "lr": 2.837681792951994e-06, "epoch": 4.2126582278481015, "percentage": 84.55, "elapsed_time": "12:34:39", "remaining_time": "2:17:52"}
1041
+ {"current_steps": 1041, "total_steps": 1230, "loss": 0.3282, "lr": 2.808607860255981e-06, "epoch": 4.216708860759494, "percentage": 84.63, "elapsed_time": "12:35:21", "remaining_time": "2:17:08"}
1042
+ {"current_steps": 1042, "total_steps": 1230, "loss": 0.3008, "lr": 2.7796723846688634e-06, "epoch": 4.220759493670886, "percentage": 84.72, "elapsed_time": "12:36:03", "remaining_time": "2:16:24"}
1043
+ {"current_steps": 1043, "total_steps": 1230, "loss": 0.3388, "lr": 2.7508755992329937e-06, "epoch": 4.224810126582279, "percentage": 84.8, "elapsed_time": "12:36:47", "remaining_time": "2:15:41"}
1044
+ {"current_steps": 1044, "total_steps": 1230, "loss": 0.3371, "lr": 2.722217735873718e-06, "epoch": 4.228860759493671, "percentage": 84.88, "elapsed_time": "12:37:29", "remaining_time": "2:14:57"}
1045
+ {"current_steps": 1045, "total_steps": 1230, "loss": 0.3529, "lr": 2.6936990253975315e-06, "epoch": 4.232911392405064, "percentage": 84.96, "elapsed_time": "12:38:13", "remaining_time": "2:14:13"}
1046
+ {"current_steps": 1046, "total_steps": 1230, "loss": 0.3286, "lr": 2.665319697490205e-06, "epoch": 4.236962025316456, "percentage": 85.04, "elapsed_time": "12:38:56", "remaining_time": "2:13:30"}
1047
+ {"current_steps": 1047, "total_steps": 1230, "loss": 0.3194, "lr": 2.637079980714945e-06, "epoch": 4.241012658227848, "percentage": 85.12, "elapsed_time": "12:39:40", "remaining_time": "2:12:46"}
1048
+ {"current_steps": 1048, "total_steps": 1230, "loss": 0.3359, "lr": 2.6089801025105453e-06, "epoch": 4.245063291139241, "percentage": 85.2, "elapsed_time": "12:40:20", "remaining_time": "2:12:02"}
1049
+ {"current_steps": 1049, "total_steps": 1230, "loss": 0.3482, "lr": 2.581020289189571e-06, "epoch": 4.249113924050633, "percentage": 85.28, "elapsed_time": "12:41:04", "remaining_time": "2:11:19"}
1050
+ {"current_steps": 1050, "total_steps": 1230, "loss": 0.3298, "lr": 2.553200765936501e-06, "epoch": 4.253164556962025, "percentage": 85.37, "elapsed_time": "12:41:49", "remaining_time": "2:10:35"}
1051
+ {"current_steps": 1051, "total_steps": 1230, "loss": 0.3423, "lr": 2.525521756805962e-06, "epoch": 4.257215189873418, "percentage": 85.45, "elapsed_time": "12:42:34", "remaining_time": "2:09:52"}
1052
+ {"current_steps": 1052, "total_steps": 1230, "loss": 0.3421, "lr": 2.497983484720885e-06, "epoch": 4.26126582278481, "percentage": 85.53, "elapsed_time": "12:43:16", "remaining_time": "2:09:08"}
1053
+ {"current_steps": 1053, "total_steps": 1230, "loss": 0.3326, "lr": 2.470586171470728e-06, "epoch": 4.265316455696203, "percentage": 85.61, "elapsed_time": "12:44:00", "remaining_time": "2:08:25"}
1054
+ {"current_steps": 1054, "total_steps": 1230, "loss": 0.339, "lr": 2.4433300377096836e-06, "epoch": 4.269367088607595, "percentage": 85.69, "elapsed_time": "12:44:44", "remaining_time": "2:07:41"}
1055
+ {"current_steps": 1055, "total_steps": 1230, "loss": 0.3548, "lr": 2.4162153029549073e-06, "epoch": 4.273417721518987, "percentage": 85.77, "elapsed_time": "12:45:28", "remaining_time": "2:06:58"}
1056
+ {"current_steps": 1056, "total_steps": 1230, "loss": 0.3293, "lr": 2.3892421855847458e-06, "epoch": 4.27746835443038, "percentage": 85.85, "elapsed_time": "12:46:12", "remaining_time": "2:06:15"}
1057
+ {"current_steps": 1057, "total_steps": 1230, "loss": 0.3209, "lr": 2.362410902836978e-06, "epoch": 4.281518987341772, "percentage": 85.93, "elapsed_time": "12:46:56", "remaining_time": "2:05:31"}
1058
+ {"current_steps": 1058, "total_steps": 1230, "loss": 0.3236, "lr": 2.3357216708070653e-06, "epoch": 4.285569620253165, "percentage": 86.02, "elapsed_time": "12:47:36", "remaining_time": "2:04:47"}
1059
+ {"current_steps": 1059, "total_steps": 1230, "loss": 0.3179, "lr": 2.309174704446411e-06, "epoch": 4.289620253164557, "percentage": 86.1, "elapsed_time": "12:48:21", "remaining_time": "2:04:04"}
1060
+ {"current_steps": 1060, "total_steps": 1230, "loss": 0.3885, "lr": 2.2827702175606437e-06, "epoch": 4.293670886075949, "percentage": 86.18, "elapsed_time": "12:49:04", "remaining_time": "2:03:20"}
1061
+ {"current_steps": 1061, "total_steps": 1230, "loss": 0.3165, "lr": 2.256508422807855e-06, "epoch": 4.297721518987342, "percentage": 86.26, "elapsed_time": "12:49:46", "remaining_time": "2:02:36"}
1062
+ {"current_steps": 1062, "total_steps": 1230, "loss": 0.3195, "lr": 2.230389531696946e-06, "epoch": 4.301772151898734, "percentage": 86.34, "elapsed_time": "12:50:28", "remaining_time": "2:01:52"}
1063
+ {"current_steps": 1063, "total_steps": 1230, "loss": 0.3312, "lr": 2.204413754585857e-06, "epoch": 4.305822784810126, "percentage": 86.42, "elapsed_time": "12:51:12", "remaining_time": "2:01:09"}
1064
+ {"current_steps": 1064, "total_steps": 1230, "loss": 0.3332, "lr": 2.1785813006799406e-06, "epoch": 4.309873417721519, "percentage": 86.5, "elapsed_time": "12:51:58", "remaining_time": "2:00:26"}
1065
+ {"current_steps": 1065, "total_steps": 1230, "loss": 0.3331, "lr": 2.1528923780302224e-06, "epoch": 4.313924050632911, "percentage": 86.59, "elapsed_time": "12:52:41", "remaining_time": "1:59:42"}
1066
+ {"current_steps": 1066, "total_steps": 1230, "loss": 0.333, "lr": 2.127347193531757e-06, "epoch": 4.317974683544303, "percentage": 86.67, "elapsed_time": "12:53:26", "remaining_time": "1:58:59"}
1067
+ {"current_steps": 1067, "total_steps": 1230, "loss": 0.3306, "lr": 2.101945952921942e-06, "epoch": 4.322025316455696, "percentage": 86.75, "elapsed_time": "12:54:11", "remaining_time": "1:58:16"}
1068
+ {"current_steps": 1068, "total_steps": 1230, "loss": 0.3461, "lr": 2.0766888607788906e-06, "epoch": 4.326075949367088, "percentage": 86.83, "elapsed_time": "12:54:53", "remaining_time": "1:57:32"}
1069
+ {"current_steps": 1069, "total_steps": 1230, "loss": 0.323, "lr": 2.0515761205197337e-06, "epoch": 4.330126582278481, "percentage": 86.91, "elapsed_time": "12:55:36", "remaining_time": "1:56:48"}
1070
+ {"current_steps": 1070, "total_steps": 1230, "loss": 0.3362, "lr": 2.0266079343990453e-06, "epoch": 4.334177215189873, "percentage": 86.99, "elapsed_time": "12:56:19", "remaining_time": "1:56:05"}
1071
+ {"current_steps": 1071, "total_steps": 1230, "loss": 0.3307, "lr": 2.0017845035071494e-06, "epoch": 4.3382278481012655, "percentage": 87.07, "elapsed_time": "12:57:01", "remaining_time": "1:55:21"}
1072
+ {"current_steps": 1072, "total_steps": 1230, "loss": 0.3314, "lr": 1.9771060277685537e-06, "epoch": 4.3422784810126585, "percentage": 87.15, "elapsed_time": "12:57:45", "remaining_time": "1:54:38"}
1073
+ {"current_steps": 1073, "total_steps": 1230, "loss": 0.3493, "lr": 1.95257270594031e-06, "epoch": 4.3463291139240505, "percentage": 87.24, "elapsed_time": "12:58:26", "remaining_time": "1:53:54"}
1074
+ {"current_steps": 1074, "total_steps": 1230, "loss": 0.3574, "lr": 1.9281847356104188e-06, "epoch": 4.3503797468354435, "percentage": 87.32, "elapsed_time": "12:59:10", "remaining_time": "1:53:10"}
1075
+ {"current_steps": 1075, "total_steps": 1230, "loss": 0.3328, "lr": 1.9039423131962365e-06, "epoch": 4.3544303797468356, "percentage": 87.4, "elapsed_time": "12:59:52", "remaining_time": "1:52:26"}
1076
+ {"current_steps": 1076, "total_steps": 1230, "loss": 0.3296, "lr": 1.8798456339429027e-06, "epoch": 4.358481012658228, "percentage": 87.48, "elapsed_time": "13:00:35", "remaining_time": "1:51:43"}
1077
+ {"current_steps": 1077, "total_steps": 1230, "loss": 0.3369, "lr": 1.8558948919217612e-06, "epoch": 4.362531645569621, "percentage": 87.56, "elapsed_time": "13:01:18", "remaining_time": "1:50:59"}
1078
+ {"current_steps": 1078, "total_steps": 1230, "loss": 0.3134, "lr": 1.8320902800287954e-06, "epoch": 4.366582278481013, "percentage": 87.64, "elapsed_time": "13:01:58", "remaining_time": "1:50:15"}
1079
+ {"current_steps": 1079, "total_steps": 1230, "loss": 0.3234, "lr": 1.8084319899830726e-06, "epoch": 4.370632911392405, "percentage": 87.72, "elapsed_time": "13:02:41", "remaining_time": "1:49:31"}
1080
+ {"current_steps": 1080, "total_steps": 1230, "loss": 0.3342, "lr": 1.7849202123252097e-06, "epoch": 4.374683544303798, "percentage": 87.8, "elapsed_time": "13:03:24", "remaining_time": "1:48:48"}
1081
+ {"current_steps": 1081, "total_steps": 1230, "loss": 0.3053, "lr": 1.7615551364158401e-06, "epoch": 4.37873417721519, "percentage": 87.89, "elapsed_time": "13:04:10", "remaining_time": "1:48:05"}
1082
+ {"current_steps": 1082, "total_steps": 1230, "loss": 0.3302, "lr": 1.738336950434061e-06, "epoch": 4.382784810126582, "percentage": 87.97, "elapsed_time": "13:04:54", "remaining_time": "1:47:21"}
1083
+ {"current_steps": 1083, "total_steps": 1230, "loss": 0.3338, "lr": 1.715265841375957e-06, "epoch": 4.386835443037975, "percentage": 88.05, "elapsed_time": "13:05:35", "remaining_time": "1:46:37"}
1084
+ {"current_steps": 1084, "total_steps": 1230, "loss": 0.3332, "lr": 1.6923419950530684e-06, "epoch": 4.390886075949367, "percentage": 88.13, "elapsed_time": "13:06:19", "remaining_time": "1:45:54"}
1085
+ {"current_steps": 1085, "total_steps": 1230, "loss": 0.3387, "lr": 1.6695655960909008e-06, "epoch": 4.39493670886076, "percentage": 88.21, "elapsed_time": "13:07:01", "remaining_time": "1:45:10"}
1086
+ {"current_steps": 1086, "total_steps": 1230, "loss": 0.3429, "lr": 1.646936827927441e-06, "epoch": 4.398987341772152, "percentage": 88.29, "elapsed_time": "13:07:45", "remaining_time": "1:44:27"}
1087
+ {"current_steps": 1087, "total_steps": 1230, "loss": 0.3324, "lr": 1.6244558728116766e-06, "epoch": 4.403037974683544, "percentage": 88.37, "elapsed_time": "13:08:27", "remaining_time": "1:43:43"}
1088
+ {"current_steps": 1088, "total_steps": 1230, "loss": 0.3412, "lr": 1.6021229118021265e-06, "epoch": 4.407088607594937, "percentage": 88.46, "elapsed_time": "13:09:07", "remaining_time": "1:42:59"}
1089
+ {"current_steps": 1089, "total_steps": 1230, "loss": 0.3326, "lr": 1.5799381247653967e-06, "epoch": 4.411139240506329, "percentage": 88.54, "elapsed_time": "13:09:51", "remaining_time": "1:42:16"}
1090
+ {"current_steps": 1090, "total_steps": 1230, "loss": 0.3375, "lr": 1.5579016903747013e-06, "epoch": 4.415189873417722, "percentage": 88.62, "elapsed_time": "13:10:32", "remaining_time": "1:41:32"}
1091
+ {"current_steps": 1091, "total_steps": 1230, "loss": 0.334, "lr": 1.5360137861084656e-06, "epoch": 4.419240506329114, "percentage": 88.7, "elapsed_time": "13:11:15", "remaining_time": "1:40:48"}
1092
+ {"current_steps": 1092, "total_steps": 1230, "loss": 0.3289, "lr": 1.5142745882488475e-06, "epoch": 4.423291139240506, "percentage": 88.78, "elapsed_time": "13:11:58", "remaining_time": "1:40:05"}
1093
+ {"current_steps": 1093, "total_steps": 1230, "loss": 0.3614, "lr": 1.4926842718803691e-06, "epoch": 4.427341772151899, "percentage": 88.86, "elapsed_time": "13:12:43", "remaining_time": "1:39:21"}
1094
+ {"current_steps": 1094, "total_steps": 1230, "loss": 0.3343, "lr": 1.4712430108884657e-06, "epoch": 4.431392405063291, "percentage": 88.94, "elapsed_time": "13:13:27", "remaining_time": "1:38:38"}
1095
+ {"current_steps": 1095, "total_steps": 1230, "loss": 0.3412, "lr": 1.4499509779581078e-06, "epoch": 4.435443037974683, "percentage": 89.02, "elapsed_time": "13:14:11", "remaining_time": "1:37:54"}
1096
+ {"current_steps": 1096, "total_steps": 1230, "loss": 0.3543, "lr": 1.4288083445723988e-06, "epoch": 4.439493670886076, "percentage": 89.11, "elapsed_time": "13:14:52", "remaining_time": "1:37:11"}
1097
+ {"current_steps": 1097, "total_steps": 1230, "loss": 0.3365, "lr": 1.4078152810112045e-06, "epoch": 4.443544303797468, "percentage": 89.19, "elapsed_time": "13:15:38", "remaining_time": "1:36:27"}
1098
+ {"current_steps": 1098, "total_steps": 1230, "loss": 0.3308, "lr": 1.3869719563497697e-06, "epoch": 4.44759493670886, "percentage": 89.27, "elapsed_time": "13:16:21", "remaining_time": "1:35:44"}
1099
+ {"current_steps": 1099, "total_steps": 1230, "loss": 0.3455, "lr": 1.3662785384573663e-06, "epoch": 4.451645569620253, "percentage": 89.35, "elapsed_time": "13:17:05", "remaining_time": "1:35:00"}
1100
+ {"current_steps": 1100, "total_steps": 1230, "loss": 0.328, "lr": 1.3457351939959383e-06, "epoch": 4.455696202531645, "percentage": 89.43, "elapsed_time": "13:17:44", "remaining_time": "1:34:16"}
1101
+ {"current_steps": 1101, "total_steps": 1230, "loss": 0.3309, "lr": 1.3253420884187551e-06, "epoch": 4.459746835443038, "percentage": 89.51, "elapsed_time": "13:18:27", "remaining_time": "1:33:33"}
1102
+ {"current_steps": 1102, "total_steps": 1230, "loss": 0.3026, "lr": 1.3050993859690953e-06, "epoch": 4.46379746835443, "percentage": 89.59, "elapsed_time": "13:19:11", "remaining_time": "1:32:49"}
1103
+ {"current_steps": 1103, "total_steps": 1230, "loss": 0.3171, "lr": 1.2850072496788869e-06, "epoch": 4.467848101265822, "percentage": 89.67, "elapsed_time": "13:19:54", "remaining_time": "1:32:06"}
1104
+ {"current_steps": 1104, "total_steps": 1230, "loss": 0.3456, "lr": 1.2650658413674434e-06, "epoch": 4.471898734177215, "percentage": 89.76, "elapsed_time": "13:20:38", "remaining_time": "1:31:22"}
1105
+ {"current_steps": 1105, "total_steps": 1230, "loss": 0.316, "lr": 1.2452753216401226e-06, "epoch": 4.4759493670886075, "percentage": 89.84, "elapsed_time": "13:21:20", "remaining_time": "1:30:38"}
1106
+ {"current_steps": 1106, "total_steps": 1230, "loss": 0.3408, "lr": 1.2256358498870503e-06, "epoch": 4.48, "percentage": 89.92, "elapsed_time": "13:22:02", "remaining_time": "1:29:55"}
1107
+ {"current_steps": 1107, "total_steps": 1230, "loss": 0.3305, "lr": 1.2061475842818337e-06, "epoch": 4.4840506329113925, "percentage": 90.0, "elapsed_time": "13:22:45", "remaining_time": "1:29:11"}
1108
+ {"current_steps": 1108, "total_steps": 1230, "loss": 0.3117, "lr": 1.1868106817802816e-06, "epoch": 4.488101265822785, "percentage": 90.08, "elapsed_time": "13:23:26", "remaining_time": "1:28:27"}
1109
+ {"current_steps": 1109, "total_steps": 1230, "loss": 0.3434, "lr": 1.1676252981191482e-06, "epoch": 4.4921518987341775, "percentage": 90.16, "elapsed_time": "13:24:08", "remaining_time": "1:27:44"}
1110
+ {"current_steps": 1110, "total_steps": 1230, "loss": 0.3368, "lr": 1.1485915878148823e-06, "epoch": 4.49620253164557, "percentage": 90.24, "elapsed_time": "13:24:49", "remaining_time": "1:27:00"}
1111
+ {"current_steps": 1111, "total_steps": 1230, "loss": 0.357, "lr": 1.1297097041623584e-06, "epoch": 4.500253164556962, "percentage": 90.33, "elapsed_time": "13:25:32", "remaining_time": "1:26:16"}
1112
+ {"current_steps": 1112, "total_steps": 1230, "loss": 0.3487, "lr": 1.1109797992336847e-06, "epoch": 4.504303797468355, "percentage": 90.41, "elapsed_time": "13:26:14", "remaining_time": "1:25:33"}
1113
+ {"current_steps": 1113, "total_steps": 1230, "loss": 0.3218, "lr": 1.092402023876933e-06, "epoch": 4.508354430379747, "percentage": 90.49, "elapsed_time": "13:26:55", "remaining_time": "1:24:49"}
1114
+ {"current_steps": 1114, "total_steps": 1230, "loss": 0.3307, "lr": 1.0739765277149527e-06, "epoch": 4.512405063291139, "percentage": 90.57, "elapsed_time": "13:27:39", "remaining_time": "1:24:06"}
1115
+ {"current_steps": 1115, "total_steps": 1230, "loss": 0.3444, "lr": 1.0557034591441596e-06, "epoch": 4.516455696202532, "percentage": 90.65, "elapsed_time": "13:28:21", "remaining_time": "1:23:22"}
1116
+ {"current_steps": 1116, "total_steps": 1230, "loss": 0.3463, "lr": 1.0375829653333324e-06, "epoch": 4.520506329113924, "percentage": 90.73, "elapsed_time": "13:29:04", "remaining_time": "1:22:38"}
1117
+ {"current_steps": 1117, "total_steps": 1230, "loss": 0.3386, "lr": 1.0196151922224385e-06, "epoch": 4.524556962025317, "percentage": 90.81, "elapsed_time": "13:32:35", "remaining_time": "1:22:12"}
1118
+ {"current_steps": 1118, "total_steps": 1230, "loss": 0.3227, "lr": 1.0018002845214526e-06, "epoch": 4.528607594936709, "percentage": 90.89, "elapsed_time": "13:33:19", "remaining_time": "1:21:28"}
1119
+ {"current_steps": 1119, "total_steps": 1230, "loss": 0.3372, "lr": 9.841383857091947e-07, "epoch": 4.532658227848101, "percentage": 90.98, "elapsed_time": "13:34:02", "remaining_time": "1:20:45"}
1120
+ {"current_steps": 1120, "total_steps": 1230, "loss": 0.3049, "lr": 9.666296380321616e-07, "epoch": 4.536708860759494, "percentage": 91.06, "elapsed_time": "13:34:44", "remaining_time": "1:20:01"}
1121
+ {"current_steps": 1121, "total_steps": 1230, "loss": 0.3264, "lr": 9.492741825034124e-07, "epoch": 4.540759493670886, "percentage": 91.14, "elapsed_time": "13:35:28", "remaining_time": "1:19:17"}
1122
+ {"current_steps": 1122, "total_steps": 1230, "loss": 0.3318, "lr": 9.320721589013892e-07, "epoch": 4.544810126582279, "percentage": 91.22, "elapsed_time": "13:36:08", "remaining_time": "1:18:33"}
1123
+ {"current_steps": 1123, "total_steps": 1230, "loss": 0.3179, "lr": 9.150237057688339e-07, "epoch": 4.548860759493671, "percentage": 91.3, "elapsed_time": "13:36:49", "remaining_time": "1:17:49"}
1124
+ {"current_steps": 1124, "total_steps": 1230, "loss": 0.3413, "lr": 8.981289604116328e-07, "epoch": 4.552911392405063, "percentage": 91.38, "elapsed_time": "13:37:34", "remaining_time": "1:17:06"}
1125
+ {"current_steps": 1125, "total_steps": 1230, "loss": 0.3484, "lr": 8.813880588977542e-07, "epoch": 4.556962025316456, "percentage": 91.46, "elapsed_time": "13:38:19", "remaining_time": "1:16:22"}
1126
+ {"current_steps": 1126, "total_steps": 1230, "loss": 0.3445, "lr": 8.648011360561126e-07, "epoch": 4.561012658227848, "percentage": 91.54, "elapsed_time": "13:39:03", "remaining_time": "1:15:38"}
1127
+ {"current_steps": 1127, "total_steps": 1230, "loss": 0.3391, "lr": 8.483683254755037e-07, "epoch": 4.56506329113924, "percentage": 91.63, "elapsed_time": "13:39:47", "remaining_time": "1:14:55"}
1128
+ {"current_steps": 1128, "total_steps": 1230, "loss": 0.3517, "lr": 8.320897595035227e-07, "epoch": 4.569113924050633, "percentage": 91.71, "elapsed_time": "13:40:31", "remaining_time": "1:14:11"}
1129
+ {"current_steps": 1129, "total_steps": 1230, "loss": 0.3407, "lr": 8.159655692455093e-07, "epoch": 4.573164556962025, "percentage": 91.79, "elapsed_time": "13:41:16", "remaining_time": "1:13:28"}
1130
+ {"current_steps": 1130, "total_steps": 1230, "loss": 0.3282, "lr": 7.999958845634648e-07, "epoch": 4.577215189873417, "percentage": 91.87, "elapsed_time": "13:42:02", "remaining_time": "1:12:44"}
1131
+ {"current_steps": 1131, "total_steps": 1230, "loss": 0.3353, "lr": 7.841808340750478e-07, "epoch": 4.58126582278481, "percentage": 91.95, "elapsed_time": "13:42:48", "remaining_time": "1:12:01"}
1132
+ {"current_steps": 1132, "total_steps": 1230, "loss": 0.327, "lr": 7.685205451524869e-07, "epoch": 4.585316455696202, "percentage": 92.03, "elapsed_time": "13:43:30", "remaining_time": "1:11:17"}
1133
+ {"current_steps": 1133, "total_steps": 1230, "loss": 0.3419, "lr": 7.530151439216027e-07, "epoch": 4.589367088607595, "percentage": 92.11, "elapsed_time": "13:44:14", "remaining_time": "1:10:33"}
1134
+ {"current_steps": 1134, "total_steps": 1230, "loss": 0.305, "lr": 7.376647552607675e-07, "epoch": 4.593417721518987, "percentage": 92.2, "elapsed_time": "13:45:00", "remaining_time": "1:09:50"}
1135
+ {"current_steps": 1135, "total_steps": 1230, "loss": 0.3235, "lr": 7.224695027998963e-07, "epoch": 4.597468354430379, "percentage": 92.28, "elapsed_time": "13:45:43", "remaining_time": "1:09:06"}
1136
+ {"current_steps": 1136, "total_steps": 1230, "loss": 0.3535, "lr": 7.07429508919466e-07, "epoch": 4.601518987341772, "percentage": 92.36, "elapsed_time": "13:46:26", "remaining_time": "1:08:23"}
1137
+ {"current_steps": 1137, "total_steps": 1230, "loss": 0.3306, "lr": 6.925448947495206e-07, "epoch": 4.605569620253164, "percentage": 92.44, "elapsed_time": "13:47:10", "remaining_time": "1:07:39"}
1138
+ {"current_steps": 1138, "total_steps": 1230, "loss": 0.2999, "lr": 6.778157801686936e-07, "epoch": 4.609620253164557, "percentage": 92.52, "elapsed_time": "13:47:53", "remaining_time": "1:06:55"}
1139
+ {"current_steps": 1139, "total_steps": 1230, "loss": 0.3464, "lr": 6.632422838032515e-07, "epoch": 4.613670886075949, "percentage": 92.6, "elapsed_time": "13:48:33", "remaining_time": "1:06:11"}
1140
+ {"current_steps": 1140, "total_steps": 1230, "loss": 0.3479, "lr": 6.488245230261281e-07, "epoch": 4.6177215189873415, "percentage": 92.68, "elapsed_time": "13:49:16", "remaining_time": "1:05:28"}
1141
+ {"current_steps": 1141, "total_steps": 1230, "loss": 0.3361, "lr": 6.345626139559868e-07, "epoch": 4.6217721518987345, "percentage": 92.76, "elapsed_time": "13:50:00", "remaining_time": "1:04:44"}
1142
+ {"current_steps": 1142, "total_steps": 1230, "loss": 0.3335, "lr": 6.204566714562866e-07, "epoch": 4.6258227848101265, "percentage": 92.85, "elapsed_time": "13:50:43", "remaining_time": "1:04:00"}
1143
+ {"current_steps": 1143, "total_steps": 1230, "loss": 0.3185, "lr": 6.06506809134344e-07, "epoch": 4.629873417721519, "percentage": 92.93, "elapsed_time": "13:51:22", "remaining_time": "1:03:16"}
1144
+ {"current_steps": 1144, "total_steps": 1230, "loss": 0.3517, "lr": 5.927131393404373e-07, "epoch": 4.633924050632912, "percentage": 93.01, "elapsed_time": "13:52:03", "remaining_time": "1:02:32"}
1145
+ {"current_steps": 1145, "total_steps": 1230, "loss": 0.3182, "lr": 5.790757731668817e-07, "epoch": 4.637974683544304, "percentage": 93.09, "elapsed_time": "13:52:45", "remaining_time": "1:01:49"}
1146
+ {"current_steps": 1146, "total_steps": 1230, "loss": 0.3398, "lr": 5.655948204471507e-07, "epoch": 4.642025316455696, "percentage": 93.17, "elapsed_time": "13:53:28", "remaining_time": "1:01:05"}
1147
+ {"current_steps": 1147, "total_steps": 1230, "loss": 0.3483, "lr": 5.522703897549875e-07, "epoch": 4.646075949367089, "percentage": 93.25, "elapsed_time": "13:54:15", "remaining_time": "1:00:22"}
1148
+ {"current_steps": 1148, "total_steps": 1230, "loss": 0.3273, "lr": 5.391025884035239e-07, "epoch": 4.650126582278481, "percentage": 93.33, "elapsed_time": "13:54:56", "remaining_time": "0:59:38"}
1149
+ {"current_steps": 1149, "total_steps": 1230, "loss": 0.3249, "lr": 5.260915224444207e-07, "epoch": 4.654177215189874, "percentage": 93.41, "elapsed_time": "13:55:37", "remaining_time": "0:58:54"}
1150
+ {"current_steps": 1150, "total_steps": 1230, "loss": 0.3434, "lr": 5.132372966670129e-07, "epoch": 4.658227848101266, "percentage": 93.5, "elapsed_time": "13:56:19", "remaining_time": "0:58:10"}
1151
+ {"current_steps": 1151, "total_steps": 1230, "loss": 0.3203, "lr": 5.005400145974704e-07, "epoch": 4.662278481012658, "percentage": 93.58, "elapsed_time": "13:57:03", "remaining_time": "0:57:27"}
1152
+ {"current_steps": 1152, "total_steps": 1230, "loss": 0.3222, "lr": 4.879997784979562e-07, "epoch": 4.666329113924051, "percentage": 93.66, "elapsed_time": "13:57:48", "remaining_time": "0:56:43"}
1153
+ {"current_steps": 1153, "total_steps": 1230, "loss": 0.3445, "lr": 4.7561668936580984e-07, "epoch": 4.670379746835443, "percentage": 93.74, "elapsed_time": "13:58:31", "remaining_time": "0:55:59"}
1154
+ {"current_steps": 1154, "total_steps": 1230, "loss": 0.3488, "lr": 4.6339084693272306e-07, "epoch": 4.674430379746836, "percentage": 93.82, "elapsed_time": "13:59:14", "remaining_time": "0:55:16"}
1155
+ {"current_steps": 1155, "total_steps": 1230, "loss": 0.3291, "lr": 4.5132234966395847e-07, "epoch": 4.678481012658228, "percentage": 93.9, "elapsed_time": "13:59:57", "remaining_time": "0:54:32"}
1156
+ {"current_steps": 1156, "total_steps": 1230, "loss": 0.3253, "lr": 4.3941129475752795e-07, "epoch": 4.68253164556962, "percentage": 93.98, "elapsed_time": "14:00:41", "remaining_time": "0:53:48"}
1157
+ {"current_steps": 1157, "total_steps": 1230, "loss": 0.3378, "lr": 4.27657778143431e-07, "epoch": 4.686582278481013, "percentage": 94.07, "elapsed_time": "14:01:21", "remaining_time": "0:53:05"}
1158
+ {"current_steps": 1158, "total_steps": 1230, "loss": 0.3268, "lr": 4.1606189448287757e-07, "epoch": 4.690632911392405, "percentage": 94.15, "elapsed_time": "14:02:06", "remaining_time": "0:52:21"}
1159
+ {"current_steps": 1159, "total_steps": 1230, "loss": 0.3405, "lr": 4.046237371675177e-07, "epoch": 4.694683544303797, "percentage": 94.23, "elapsed_time": "14:02:50", "remaining_time": "0:51:37"}
1160
+ {"current_steps": 1160, "total_steps": 1230, "loss": 0.3581, "lr": 3.9334339831869963e-07, "epoch": 4.69873417721519, "percentage": 94.31, "elapsed_time": "14:03:34", "remaining_time": "0:50:54"}
1161
+ {"current_steps": 1161, "total_steps": 1230, "loss": 0.3094, "lr": 3.8222096878671955e-07, "epoch": 4.702784810126582, "percentage": 94.39, "elapsed_time": "14:04:18", "remaining_time": "0:50:10"}
1162
+ {"current_steps": 1162, "total_steps": 1230, "loss": 0.3053, "lr": 3.7125653815009545e-07, "epoch": 4.706835443037974, "percentage": 94.47, "elapsed_time": "14:05:00", "remaining_time": "0:49:26"}
1163
+ {"current_steps": 1163, "total_steps": 1230, "loss": 0.3276, "lr": 3.6045019471484974e-07, "epoch": 4.710886075949367, "percentage": 94.55, "elapsed_time": "14:05:43", "remaining_time": "0:48:43"}
1164
+ {"current_steps": 1164, "total_steps": 1230, "loss": 0.3199, "lr": 3.498020255137813e-07, "epoch": 4.714936708860759, "percentage": 94.63, "elapsed_time": "14:06:28", "remaining_time": "0:47:59"}
1165
+ {"current_steps": 1165, "total_steps": 1230, "loss": 0.3359, "lr": 3.393121163057811e-07, "epoch": 4.718987341772152, "percentage": 94.72, "elapsed_time": "14:07:12", "remaining_time": "0:47:16"}
1166
+ {"current_steps": 1166, "total_steps": 1230, "loss": 0.3201, "lr": 3.289805515751399e-07, "epoch": 4.723037974683544, "percentage": 94.8, "elapsed_time": "14:07:52", "remaining_time": "0:46:32"}
1167
+ {"current_steps": 1167, "total_steps": 1230, "loss": 0.3253, "lr": 3.188074145308573e-07, "epoch": 4.727088607594936, "percentage": 94.88, "elapsed_time": "14:08:38", "remaining_time": "0:45:48"}
1168
+ {"current_steps": 1168, "total_steps": 1230, "loss": 0.3148, "lr": 3.087927871059804e-07, "epoch": 4.731139240506329, "percentage": 94.96, "elapsed_time": "14:09:21", "remaining_time": "0:45:05"}
1169
+ {"current_steps": 1169, "total_steps": 1230, "loss": 0.3339, "lr": 2.989367499569418e-07, "epoch": 4.735189873417721, "percentage": 95.04, "elapsed_time": "14:10:04", "remaining_time": "0:44:21"}
1170
+ {"current_steps": 1170, "total_steps": 1230, "loss": 0.3266, "lr": 2.8923938246290917e-07, "epoch": 4.739240506329114, "percentage": 95.12, "elapsed_time": "14:10:48", "remaining_time": "0:43:37"}
1171
+ {"current_steps": 1171, "total_steps": 1230, "loss": 0.344, "lr": 2.7970076272514804e-07, "epoch": 4.743291139240506, "percentage": 95.2, "elapsed_time": "14:11:34", "remaining_time": "0:42:54"}
1172
+ {"current_steps": 1172, "total_steps": 1230, "loss": 0.3444, "lr": 2.703209675663887e-07, "epoch": 4.7473417721518985, "percentage": 95.28, "elapsed_time": "14:12:20", "remaining_time": "0:42:10"}
1173
+ {"current_steps": 1173, "total_steps": 1230, "loss": 0.347, "lr": 2.6110007253021374e-07, "epoch": 4.751392405063291, "percentage": 95.37, "elapsed_time": "14:13:04", "remaining_time": "0:41:27"}
1174
+ {"current_steps": 1174, "total_steps": 1230, "loss": 0.3558, "lr": 2.520381518804471e-07, "epoch": 4.7554430379746835, "percentage": 95.45, "elapsed_time": "14:13:49", "remaining_time": "0:40:43"}
1175
+ {"current_steps": 1175, "total_steps": 1230, "loss": 0.3385, "lr": 2.4313527860054585e-07, "epoch": 4.759493670886076, "percentage": 95.53, "elapsed_time": "14:14:31", "remaining_time": "0:39:59"}
1176
+ {"current_steps": 1176, "total_steps": 1230, "loss": 0.3389, "lr": 2.343915243930317e-07, "epoch": 4.7635443037974685, "percentage": 95.61, "elapsed_time": "14:15:16", "remaining_time": "0:39:16"}
1177
+ {"current_steps": 1177, "total_steps": 1230, "loss": 0.2958, "lr": 2.2580695967889367e-07, "epoch": 4.767594936708861, "percentage": 95.69, "elapsed_time": "14:16:00", "remaining_time": "0:38:32"}
1178
+ {"current_steps": 1178, "total_steps": 1230, "loss": 0.3378, "lr": 2.1738165359704189e-07, "epoch": 4.7716455696202535, "percentage": 95.77, "elapsed_time": "14:16:45", "remaining_time": "0:37:49"}
1179
+ {"current_steps": 1179, "total_steps": 1230, "loss": 0.3353, "lr": 2.0911567400373257e-07, "epoch": 4.775696202531646, "percentage": 95.85, "elapsed_time": "14:17:23", "remaining_time": "0:37:05"}
1180
+ {"current_steps": 988, "total_steps": 1230, "loss": 0.3249, "lr": 4.534166308795815e-06, "epoch": 4.01620253164557, "percentage": 80.33, "elapsed_time": "0:00:44", "remaining_time": "0:00:10"}
1181
+ {"current_steps": 989, "total_steps": 1230, "loss": 0.3271, "lr": 4.498240773728859e-06, "epoch": 4.020253164556962, "percentage": 80.41, "elapsed_time": "0:01:26", "remaining_time": "0:00:21"}
1182
+ {"current_steps": 990, "total_steps": 1230, "loss": 0.3344, "lr": 4.462440087699609e-06, "epoch": 4.024303797468354, "percentage": 80.49, "elapsed_time": "0:02:10", "remaining_time": "0:00:31"}
1183
+ {"current_steps": 991, "total_steps": 1230, "loss": 0.3428, "lr": 4.426764539041861e-06, "epoch": 4.028354430379747, "percentage": 80.57, "elapsed_time": "0:02:55", "remaining_time": "0:00:42"}
1184
+ {"current_steps": 992, "total_steps": 1230, "loss": 0.3427, "lr": 4.391214415081582e-06, "epoch": 4.032405063291139, "percentage": 80.65, "elapsed_time": "0:03:40", "remaining_time": "0:00:52"}
1185
+ {"current_steps": 993, "total_steps": 1230, "loss": 0.319, "lr": 4.355790002134579e-06, "epoch": 4.036455696202531, "percentage": 80.73, "elapsed_time": "0:04:23", "remaining_time": "0:01:02"}
1186
+ {"current_steps": 994, "total_steps": 1230, "loss": 0.3454, "lr": 4.320491585504207e-06, "epoch": 4.040506329113924, "percentage": 80.81, "elapsed_time": "0:05:06", "remaining_time": "0:01:12"}
1187
+ {"current_steps": 995, "total_steps": 1230, "loss": 0.3326, "lr": 4.2853194494790615e-06, "epoch": 4.044556962025316, "percentage": 80.89, "elapsed_time": "0:05:48", "remaining_time": "0:01:22"}
1188
+ {"current_steps": 996, "total_steps": 1230, "loss": 0.3062, "lr": 4.250273877330691e-06, "epoch": 4.048607594936709, "percentage": 80.98, "elapsed_time": "0:06:28", "remaining_time": "0:01:31"}
1189
+ {"current_steps": 997, "total_steps": 1230, "loss": 0.3537, "lr": 4.215355151311313e-06, "epoch": 4.052658227848101, "percentage": 81.06, "elapsed_time": "0:07:10", "remaining_time": "0:01:40"}
1190
+ {"current_steps": 998, "total_steps": 1230, "loss": 0.3565, "lr": 4.180563552651542e-06, "epoch": 4.056708860759493, "percentage": 81.14, "elapsed_time": "0:07:54", "remaining_time": "0:01:50"}
1191
+ {"current_steps": 999, "total_steps": 1230, "loss": 0.3524, "lr": 4.145899361558147e-06, "epoch": 4.060759493670886, "percentage": 81.22, "elapsed_time": "0:08:37", "remaining_time": "0:01:59"}
1192
+ {"current_steps": 1000, "total_steps": 1230, "loss": 0.3031, "lr": 4.111362857211738e-06, "epoch": 4.0648101265822785, "percentage": 81.3, "elapsed_time": "0:09:22", "remaining_time": "0:02:09"}
1193
+ {"current_steps": 1001, "total_steps": 1230, "loss": 0.328, "lr": 4.076954317764592e-06, "epoch": 4.0688607594936705, "percentage": 81.38, "elapsed_time": "0:10:04", "remaining_time": "0:02:18"}
1194
+ {"current_steps": 1002, "total_steps": 1230, "loss": 0.3411, "lr": 4.042674020338335e-06, "epoch": 4.0729113924050635, "percentage": 81.46, "elapsed_time": "0:10:46", "remaining_time": "0:02:27"}
1195
+ {"current_steps": 1003, "total_steps": 1230, "loss": 0.3391, "lr": 4.0085222410217835e-06, "epoch": 4.076962025316456, "percentage": 81.54, "elapsed_time": "0:11:29", "remaining_time": "0:02:36"}
1196
+ {"current_steps": 1004, "total_steps": 1230, "loss": 0.3157, "lr": 3.974499254868674e-06, "epoch": 4.0810126582278485, "percentage": 81.63, "elapsed_time": "0:12:09", "remaining_time": "0:02:44"}
1197
+ {"current_steps": 1005, "total_steps": 1230, "loss": 0.3318, "lr": 3.940605335895451e-06, "epoch": 4.085063291139241, "percentage": 81.71, "elapsed_time": "0:12:48", "remaining_time": "0:02:51"}
1198
+ {"current_steps": 1006, "total_steps": 1230, "loss": 0.3555, "lr": 3.90684075707908e-06, "epoch": 4.089113924050633, "percentage": 81.79, "elapsed_time": "0:13:31", "remaining_time": "0:03:00"}
1199
+ {"current_steps": 1007, "total_steps": 1230, "loss": 0.3266, "lr": 3.8732057903548505e-06, "epoch": 4.093164556962026, "percentage": 81.87, "elapsed_time": "0:14:14", "remaining_time": "0:03:09"}
1200
+ {"current_steps": 1008, "total_steps": 1230, "loss": 0.3336, "lr": 3.8397007066141375e-06, "epoch": 4.097215189873418, "percentage": 81.95, "elapsed_time": "0:14:57", "remaining_time": "0:03:17"}
1201
+ {"current_steps": 1009, "total_steps": 1230, "loss": 0.3453, "lr": 3.806325775702304e-06, "epoch": 4.10126582278481, "percentage": 82.03, "elapsed_time": "0:15:42", "remaining_time": "0:03:26"}
1202
+ {"current_steps": 1010, "total_steps": 1230, "loss": 0.3284, "lr": 3.773081266416434e-06, "epoch": 4.105316455696203, "percentage": 82.11, "elapsed_time": "0:16:26", "remaining_time": "0:03:34"}
1203
+ {"current_steps": 1011, "total_steps": 1230, "loss": 0.3509, "lr": 3.739967446503245e-06, "epoch": 4.109367088607595, "percentage": 82.2, "elapsed_time": "0:17:10", "remaining_time": "0:03:43"}
1204
+ {"current_steps": 1012, "total_steps": 1230, "loss": 0.3203, "lr": 3.706984582656894e-06, "epoch": 4.113417721518988, "percentage": 82.28, "elapsed_time": "0:17:51", "remaining_time": "0:03:50"}
1205
+ {"current_steps": 1013, "total_steps": 1230, "loss": 0.3366, "lr": 3.6741329405168237e-06, "epoch": 4.11746835443038, "percentage": 82.36, "elapsed_time": "0:18:35", "remaining_time": "0:03:58"}
1206
+ {"current_steps": 1014, "total_steps": 1230, "loss": 0.3215, "lr": 3.641412784665648e-06, "epoch": 4.121518987341772, "percentage": 82.44, "elapsed_time": "0:19:18", "remaining_time": "0:04:06"}
1207
+ {"current_steps": 1015, "total_steps": 1230, "loss": 0.3113, "lr": 3.608824378627005e-06, "epoch": 4.125569620253165, "percentage": 82.52, "elapsed_time": "0:20:01", "remaining_time": "0:04:14"}
1208
+ {"current_steps": 1016, "total_steps": 1230, "loss": 0.3477, "lr": 3.5763679848634337e-06, "epoch": 4.129620253164557, "percentage": 82.6, "elapsed_time": "0:20:41", "remaining_time": "0:04:21"}
1209
+ {"current_steps": 1017, "total_steps": 1230, "loss": 0.3064, "lr": 3.544043864774269e-06, "epoch": 4.133670886075949, "percentage": 82.68, "elapsed_time": "0:21:24", "remaining_time": "0:04:29"}
1210
+ {"current_steps": 1018, "total_steps": 1230, "loss": 0.3235, "lr": 3.5118522786935282e-06, "epoch": 4.137721518987342, "percentage": 82.76, "elapsed_time": "0:22:04", "remaining_time": "0:04:35"}
1211
+ {"current_steps": 1019, "total_steps": 1230, "loss": 0.3199, "lr": 3.479793485887819e-06, "epoch": 4.141772151898734, "percentage": 82.85, "elapsed_time": "0:22:47", "remaining_time": "0:04:43"}
1212
+ {"current_steps": 1020, "total_steps": 1230, "loss": 0.3405, "lr": 3.4478677445542653e-06, "epoch": 4.145822784810127, "percentage": 82.93, "elapsed_time": "0:23:31", "remaining_time": "0:04:50"}
1213
+ {"current_steps": 1021, "total_steps": 1230, "loss": 0.3086, "lr": 3.4160753118183767e-06, "epoch": 4.149873417721519, "percentage": 83.01, "elapsed_time": "0:24:13", "remaining_time": "0:04:57"}
1214
+ {"current_steps": 1022, "total_steps": 1230, "loss": 0.3349, "lr": 3.3844164437320527e-06, "epoch": 4.153924050632911, "percentage": 83.09, "elapsed_time": "0:24:57", "remaining_time": "0:05:04"}
1215
+ {"current_steps": 1023, "total_steps": 1230, "loss": 0.3265, "lr": 3.3528913952714558e-06, "epoch": 4.157974683544304, "percentage": 83.17, "elapsed_time": "0:25:41", "remaining_time": "0:05:11"}
1216
+ {"current_steps": 1024, "total_steps": 1230, "loss": 0.3409, "lr": 3.321500420335e-06, "epoch": 4.162025316455696, "percentage": 83.25, "elapsed_time": "0:26:24", "remaining_time": "0:05:18"}
1217
+ {"current_steps": 1025, "total_steps": 1230, "loss": 0.3263, "lr": 3.290243771741275e-06, "epoch": 4.166075949367088, "percentage": 83.33, "elapsed_time": "0:27:03", "remaining_time": "0:05:24"}
1218
+ {"current_steps": 1026, "total_steps": 1230, "loss": 0.3192, "lr": 3.2591217012270325e-06, "epoch": 4.170126582278481, "percentage": 83.41, "elapsed_time": "0:27:44", "remaining_time": "0:05:30"}
1219
+ {"current_steps": 1027, "total_steps": 1230, "loss": 0.3333, "lr": 3.228134459445149e-06, "epoch": 4.174177215189873, "percentage": 83.5, "elapsed_time": "0:28:25", "remaining_time": "0:05:37"}
1220
+ {"current_steps": 1028, "total_steps": 1230, "loss": 0.3243, "lr": 3.1972822959626205e-06, "epoch": 4.178227848101266, "percentage": 83.58, "elapsed_time": "0:29:04", "remaining_time": "0:05:42"}
1221
+ {"current_steps": 1029, "total_steps": 1230, "loss": 0.3191, "lr": 3.166565459258513e-06, "epoch": 4.182278481012658, "percentage": 83.66, "elapsed_time": "0:29:44", "remaining_time": "0:05:48"}
1222
+ {"current_steps": 1030, "total_steps": 1230, "loss": 0.3499, "lr": 3.1359841967220193e-06, "epoch": 4.18632911392405, "percentage": 83.74, "elapsed_time": "0:30:28", "remaining_time": "0:05:55"}
1223
+ {"current_steps": 1031, "total_steps": 1230, "loss": 0.3364, "lr": 3.105538754650419e-06, "epoch": 4.190379746835443, "percentage": 83.82, "elapsed_time": "0:31:12", "remaining_time": "0:06:01"}
1224
+ {"current_steps": 1032, "total_steps": 1230, "loss": 0.3247, "lr": 3.07522937824712e-06, "epoch": 4.194430379746835, "percentage": 83.9, "elapsed_time": "0:31:57", "remaining_time": "0:06:07"}
1225
+ {"current_steps": 1033, "total_steps": 1230, "loss": 0.3371, "lr": 3.0450563116196697e-06, "epoch": 4.1984810126582275, "percentage": 83.98, "elapsed_time": "0:32:40", "remaining_time": "0:06:13"}
1226
+ {"current_steps": 1034, "total_steps": 1230, "loss": 0.3423, "lr": 3.0150197977778008e-06, "epoch": 4.2025316455696204, "percentage": 84.07, "elapsed_time": "0:33:22", "remaining_time": "0:06:19"}
1227
+ {"current_steps": 1035, "total_steps": 1230, "loss": 0.3463, "lr": 2.985120078631465e-06, "epoch": 4.2065822784810125, "percentage": 84.15, "elapsed_time": "0:34:04", "remaining_time": "0:06:25"}
1228
+ {"current_steps": 1036, "total_steps": 1230, "loss": 0.3122, "lr": 2.9553573949888893e-06, "epoch": 4.2106329113924055, "percentage": 84.23, "elapsed_time": "0:34:47", "remaining_time": "0:06:30"}
1229
+ {"current_steps": 1037, "total_steps": 1230, "loss": 0.3365, "lr": 2.9257319865546384e-06, "epoch": 4.2146835443037975, "percentage": 84.31, "elapsed_time": "0:35:30", "remaining_time": "0:06:36"}
1230
+ {"current_steps": 1038, "total_steps": 1230, "loss": 0.3079, "lr": 2.896244091927678e-06, "epoch": 4.21873417721519, "percentage": 84.39, "elapsed_time": "0:36:11", "remaining_time": "0:06:41"}
1231
+ {"current_steps": 1039, "total_steps": 1230, "loss": 0.3054, "lr": 2.8668939485994584e-06, "epoch": 4.222784810126583, "percentage": 84.47, "elapsed_time": "0:36:55", "remaining_time": "0:06:47"}
1232
+ {"current_steps": 1040, "total_steps": 1230, "loss": 0.354, "lr": 2.837681792951994e-06, "epoch": 4.226835443037975, "percentage": 84.55, "elapsed_time": "0:37:38", "remaining_time": "0:06:52"}
1233
+ {"current_steps": 1041, "total_steps": 1230, "loss": 0.3457, "lr": 2.808607860255981e-06, "epoch": 4.230886075949367, "percentage": 84.63, "elapsed_time": "0:38:21", "remaining_time": "0:06:57"}
1234
+ {"current_steps": 1042, "total_steps": 1230, "loss": 0.3309, "lr": 2.7796723846688634e-06, "epoch": 4.23493670886076, "percentage": 84.72, "elapsed_time": "0:39:03", "remaining_time": "0:07:02"}
1235
+ {"current_steps": 1043, "total_steps": 1230, "loss": 0.3377, "lr": 2.7508755992329937e-06, "epoch": 4.238987341772152, "percentage": 84.8, "elapsed_time": "0:39:49", "remaining_time": "0:07:08"}
1236
+ {"current_steps": 1044, "total_steps": 1230, "loss": 0.3254, "lr": 2.722217735873718e-06, "epoch": 4.243037974683545, "percentage": 84.88, "elapsed_time": "0:40:31", "remaining_time": "0:07:13"}
1237
+ {"current_steps": 1045, "total_steps": 1230, "loss": 0.3376, "lr": 2.6936990253975315e-06, "epoch": 4.247088607594937, "percentage": 84.96, "elapsed_time": "0:41:13", "remaining_time": "0:07:17"}
1238
+ {"current_steps": 1046, "total_steps": 1230, "loss": 0.3481, "lr": 2.665319697490205e-06, "epoch": 4.251139240506329, "percentage": 85.04, "elapsed_time": "0:41:58", "remaining_time": "0:07:23"}
1239
+ {"current_steps": 1047, "total_steps": 1230, "loss": 0.342, "lr": 2.637079980714945e-06, "epoch": 4.255189873417722, "percentage": 85.12, "elapsed_time": "0:42:43", "remaining_time": "0:07:28"}
1240
+ {"current_steps": 1048, "total_steps": 1230, "loss": 0.3288, "lr": 2.6089801025105453e-06, "epoch": 4.259240506329114, "percentage": 85.2, "elapsed_time": "0:43:27", "remaining_time": "0:07:32"}
1241
+ {"current_steps": 1049, "total_steps": 1230, "loss": 0.3393, "lr": 2.581020289189571e-06, "epoch": 4.263291139240506, "percentage": 85.28, "elapsed_time": "0:44:11", "remaining_time": "0:07:37"}
1242
+ {"current_steps": 1050, "total_steps": 1230, "loss": 0.3367, "lr": 2.553200765936501e-06, "epoch": 4.267341772151899, "percentage": 85.37, "elapsed_time": "0:44:54", "remaining_time": "0:07:41"}
1243
+ {"current_steps": 1051, "total_steps": 1230, "loss": 0.3496, "lr": 2.525521756805962e-06, "epoch": 4.271392405063291, "percentage": 85.45, "elapsed_time": "0:45:38", "remaining_time": "0:07:46"}
1244
+ {"current_steps": 1052, "total_steps": 1230, "loss": 0.3287, "lr": 2.497983484720885e-06, "epoch": 4.275443037974684, "percentage": 85.53, "elapsed_time": "0:46:22", "remaining_time": "0:07:50"}
1245
+ {"current_steps": 1053, "total_steps": 1230, "loss": 0.3411, "lr": 2.470586171470728e-06, "epoch": 4.279493670886076, "percentage": 85.61, "elapsed_time": "0:47:06", "remaining_time": "0:07:55"}
1246
+ {"current_steps": 1054, "total_steps": 1230, "loss": 0.3085, "lr": 2.4433300377096836e-06, "epoch": 4.283544303797468, "percentage": 85.69, "elapsed_time": "0:47:47", "remaining_time": "0:07:58"}
1247
+ {"current_steps": 1055, "total_steps": 1230, "loss": 0.3407, "lr": 2.4162153029549073e-06, "epoch": 4.287594936708861, "percentage": 85.77, "elapsed_time": "0:48:31", "remaining_time": "0:08:02"}
1248
+ {"current_steps": 1056, "total_steps": 1230, "loss": 0.3303, "lr": 2.3892421855847458e-06, "epoch": 4.291645569620253, "percentage": 85.85, "elapsed_time": "0:49:15", "remaining_time": "0:08:07"}
1249
+ {"current_steps": 1057, "total_steps": 1230, "loss": 0.351, "lr": 2.362410902836978e-06, "epoch": 4.295696202531645, "percentage": 85.93, "elapsed_time": "0:49:59", "remaining_time": "0:08:10"}
1250
+ {"current_steps": 1058, "total_steps": 1230, "loss": 0.3081, "lr": 2.3357216708070653e-06, "epoch": 4.299746835443038, "percentage": 86.02, "elapsed_time": "0:50:39", "remaining_time": "0:08:14"}
1251
+ {"current_steps": 1059, "total_steps": 1230, "loss": 0.3446, "lr": 2.309174704446411e-06, "epoch": 4.30379746835443, "percentage": 86.1, "elapsed_time": "0:51:24", "remaining_time": "0:08:18"}
1252
+ {"current_steps": 1060, "total_steps": 1230, "loss": 0.3177, "lr": 2.2827702175606437e-06, "epoch": 4.307848101265823, "percentage": 86.18, "elapsed_time": "0:52:08", "remaining_time": "0:08:21"}
1253
+ {"current_steps": 1061, "total_steps": 1230, "loss": 0.3417, "lr": 2.256508422807855e-06, "epoch": 4.311898734177215, "percentage": 86.26, "elapsed_time": "0:52:53", "remaining_time": "0:08:25"}
1254
+ {"current_steps": 1062, "total_steps": 1230, "loss": 0.322, "lr": 2.230389531696946e-06, "epoch": 4.315949367088607, "percentage": 86.34, "elapsed_time": "0:53:36", "remaining_time": "0:08:28"}
1255
+ {"current_steps": 1063, "total_steps": 1230, "loss": 0.3438, "lr": 2.204413754585857e-06, "epoch": 4.32, "percentage": 86.42, "elapsed_time": "0:54:21", "remaining_time": "0:08:32"}
1256
+ {"current_steps": 1064, "total_steps": 1230, "loss": 0.3387, "lr": 2.1785813006799406e-06, "epoch": 4.324050632911392, "percentage": 86.5, "elapsed_time": "0:55:05", "remaining_time": "0:08:35"}
1257
+ {"current_steps": 1065, "total_steps": 1230, "loss": 0.3327, "lr": 2.1528923780302224e-06, "epoch": 4.328101265822784, "percentage": 86.59, "elapsed_time": "0:55:48", "remaining_time": "0:08:38"}
1258
+ {"current_steps": 1066, "total_steps": 1230, "loss": 0.3264, "lr": 2.127347193531757e-06, "epoch": 4.332151898734177, "percentage": 86.67, "elapsed_time": "0:56:30", "remaining_time": "0:08:41"}
1259
+ {"current_steps": 1067, "total_steps": 1230, "loss": 0.3397, "lr": 2.101945952921942e-06, "epoch": 4.3362025316455695, "percentage": 86.75, "elapsed_time": "0:57:14", "remaining_time": "0:08:44"}
1260
+ {"current_steps": 1068, "total_steps": 1230, "loss": 0.3191, "lr": 2.0766888607788906e-06, "epoch": 4.340253164556962, "percentage": 86.83, "elapsed_time": "0:57:57", "remaining_time": "0:08:47"}
1261
+ {"current_steps": 1069, "total_steps": 1230, "loss": 0.356, "lr": 2.0515761205197337e-06, "epoch": 4.3443037974683545, "percentage": 86.91, "elapsed_time": "0:58:42", "remaining_time": "0:08:50"}
1262
+ {"current_steps": 1070, "total_steps": 1230, "loss": 0.3405, "lr": 2.0266079343990453e-06, "epoch": 4.348354430379747, "percentage": 86.99, "elapsed_time": "0:59:21", "remaining_time": "0:08:52"}
1263
+ {"current_steps": 1071, "total_steps": 1230, "loss": 0.3279, "lr": 2.0017845035071494e-06, "epoch": 4.3524050632911395, "percentage": 87.07, "elapsed_time": "1:00:05", "remaining_time": "0:08:55"}
1264
+ {"current_steps": 1072, "total_steps": 1230, "loss": 0.3643, "lr": 1.9771060277685537e-06, "epoch": 4.356455696202532, "percentage": 87.15, "elapsed_time": "1:00:50", "remaining_time": "0:08:57"}
1265
+ {"current_steps": 1073, "total_steps": 1230, "loss": 0.3297, "lr": 1.95257270594031e-06, "epoch": 4.360506329113924, "percentage": 87.24, "elapsed_time": "1:01:32", "remaining_time": "0:09:00"}
1266
+ {"current_steps": 1074, "total_steps": 1230, "loss": 0.3206, "lr": 1.9281847356104188e-06, "epoch": 4.364556962025317, "percentage": 87.32, "elapsed_time": "1:02:12", "remaining_time": "0:09:02"}
1267
+ {"current_steps": 1075, "total_steps": 1230, "loss": 0.3103, "lr": 1.9039423131962365e-06, "epoch": 4.368607594936709, "percentage": 87.4, "elapsed_time": "1:02:54", "remaining_time": "0:09:04"}
1268
+ {"current_steps": 1076, "total_steps": 1230, "loss": 0.334, "lr": 1.8798456339429027e-06, "epoch": 4.372658227848102, "percentage": 87.48, "elapsed_time": "1:03:36", "remaining_time": "0:09:06"}
1269
+ {"current_steps": 1077, "total_steps": 1230, "loss": 0.3213, "lr": 1.8558948919217612e-06, "epoch": 4.376708860759494, "percentage": 87.56, "elapsed_time": "1:04:22", "remaining_time": "0:09:08"}
1270
+ {"current_steps": 1078, "total_steps": 1230, "loss": 0.3197, "lr": 1.8320902800287954e-06, "epoch": 4.380759493670886, "percentage": 87.64, "elapsed_time": "1:05:08", "remaining_time": "0:09:11"}
1271
+ {"current_steps": 1079, "total_steps": 1230, "loss": 0.3323, "lr": 1.8084319899830726e-06, "epoch": 4.384810126582279, "percentage": 87.72, "elapsed_time": "1:05:52", "remaining_time": "0:09:13"}
1272
+ {"current_steps": 1080, "total_steps": 1230, "loss": 0.3299, "lr": 1.7849202123252097e-06, "epoch": 4.388860759493671, "percentage": 87.8, "elapsed_time": "1:06:34", "remaining_time": "0:09:14"}
1273
+ {"current_steps": 1081, "total_steps": 1230, "loss": 0.3298, "lr": 1.7615551364158401e-06, "epoch": 4.392911392405063, "percentage": 87.89, "elapsed_time": "1:07:16", "remaining_time": "0:09:16"}
1274
+ {"current_steps": 1082, "total_steps": 1230, "loss": 0.3363, "lr": 1.738336950434061e-06, "epoch": 4.396962025316456, "percentage": 87.97, "elapsed_time": "1:07:59", "remaining_time": "0:09:17"}
1275
+ {"current_steps": 1083, "total_steps": 1230, "loss": 0.3622, "lr": 1.715265841375957e-06, "epoch": 4.401012658227848, "percentage": 88.05, "elapsed_time": "1:08:44", "remaining_time": "0:09:19"}
1276
+ {"current_steps": 1084, "total_steps": 1230, "loss": 0.3297, "lr": 1.6923419950530684e-06, "epoch": 4.405063291139241, "percentage": 88.13, "elapsed_time": "1:09:24", "remaining_time": "0:09:20"}
1277
+ {"current_steps": 1085, "total_steps": 1230, "loss": 0.3397, "lr": 1.6695655960909008e-06, "epoch": 4.409113924050633, "percentage": 88.21, "elapsed_time": "1:10:07", "remaining_time": "0:09:22"}
1278
+ {"current_steps": 1086, "total_steps": 1230, "loss": 0.3216, "lr": 1.646936827927441e-06, "epoch": 4.413164556962025, "percentage": 88.29, "elapsed_time": "1:10:48", "remaining_time": "0:09:23"}
1279
+ {"current_steps": 1087, "total_steps": 1230, "loss": 0.3421, "lr": 1.6244558728116766e-06, "epoch": 4.417215189873418, "percentage": 88.37, "elapsed_time": "1:11:31", "remaining_time": "0:09:24"}
1280
+ {"current_steps": 1088, "total_steps": 1230, "loss": 0.3157, "lr": 1.6021229118021265e-06, "epoch": 4.42126582278481, "percentage": 88.46, "elapsed_time": "1:12:12", "remaining_time": "0:09:25"}
1281
+ {"current_steps": 1089, "total_steps": 1230, "loss": 0.3671, "lr": 1.5799381247653967e-06, "epoch": 4.425316455696202, "percentage": 88.54, "elapsed_time": "1:12:56", "remaining_time": "0:09:26"}
1282
+ {"current_steps": 1090, "total_steps": 1230, "loss": 0.3477, "lr": 1.5579016903747013e-06, "epoch": 4.429367088607595, "percentage": 88.62, "elapsed_time": "1:13:42", "remaining_time": "0:09:28"}
1283
+ {"current_steps": 1091, "total_steps": 1230, "loss": 0.32, "lr": 1.5360137861084656e-06, "epoch": 4.433417721518987, "percentage": 88.7, "elapsed_time": "1:14:26", "remaining_time": "0:09:29"}
1284
+ {"current_steps": 1092, "total_steps": 1230, "loss": 0.3701, "lr": 1.5142745882488475e-06, "epoch": 4.43746835443038, "percentage": 88.78, "elapsed_time": "1:15:07", "remaining_time": "0:09:29"}
1285
+ {"current_steps": 1093, "total_steps": 1230, "loss": 0.3372, "lr": 1.4926842718803691e-06, "epoch": 4.441518987341772, "percentage": 88.86, "elapsed_time": "1:15:52", "remaining_time": "0:09:30"}
1286
+ {"current_steps": 1094, "total_steps": 1230, "loss": 0.3364, "lr": 1.4712430108884657e-06, "epoch": 4.445569620253164, "percentage": 88.94, "elapsed_time": "1:16:35", "remaining_time": "0:09:31"}
1287
+ {"current_steps": 1095, "total_steps": 1230, "loss": 0.3233, "lr": 1.4499509779581078e-06, "epoch": 4.449620253164557, "percentage": 89.02, "elapsed_time": "1:17:21", "remaining_time": "0:09:32"}
1288
+ {"current_steps": 1096, "total_steps": 1230, "loss": 0.3497, "lr": 1.4288083445723988e-06, "epoch": 4.453670886075949, "percentage": 89.11, "elapsed_time": "1:18:03", "remaining_time": "0:09:32"}
1289
+ {"current_steps": 1097, "total_steps": 1230, "loss": 0.327, "lr": 1.4078152810112045e-06, "epoch": 4.457721518987341, "percentage": 89.19, "elapsed_time": "1:18:42", "remaining_time": "0:09:32"}
1290
+ {"current_steps": 1098, "total_steps": 1230, "loss": 0.3243, "lr": 1.3869719563497697e-06, "epoch": 4.461772151898734, "percentage": 89.27, "elapsed_time": "1:19:27", "remaining_time": "0:09:33"}
1291
+ {"current_steps": 1099, "total_steps": 1230, "loss": 0.31, "lr": 1.3662785384573663e-06, "epoch": 4.465822784810126, "percentage": 89.35, "elapsed_time": "1:20:11", "remaining_time": "0:09:33"}
1292
+ {"current_steps": 1100, "total_steps": 1230, "loss": 0.3103, "lr": 1.3457351939959383e-06, "epoch": 4.469873417721519, "percentage": 89.43, "elapsed_time": "1:20:54", "remaining_time": "0:09:33"}
1293
+ {"current_steps": 1101, "total_steps": 1230, "loss": 0.353, "lr": 1.3253420884187551e-06, "epoch": 4.473924050632911, "percentage": 89.51, "elapsed_time": "1:21:38", "remaining_time": "0:09:33"}
1294
+ {"current_steps": 1102, "total_steps": 1230, "loss": 0.3095, "lr": 1.3050993859690953e-06, "epoch": 4.4779746835443035, "percentage": 89.59, "elapsed_time": "1:22:21", "remaining_time": "0:09:33"}
1295
+ {"current_steps": 1103, "total_steps": 1230, "loss": 0.3364, "lr": 1.2850072496788869e-06, "epoch": 4.4820253164556965, "percentage": 89.67, "elapsed_time": "1:23:03", "remaining_time": "0:09:33"}
1296
+ {"current_steps": 1104, "total_steps": 1230, "loss": 0.3294, "lr": 1.2650658413674434e-06, "epoch": 4.4860759493670885, "percentage": 89.76, "elapsed_time": "1:23:46", "remaining_time": "0:09:33"}
1297
+ {"current_steps": 1105, "total_steps": 1230, "loss": 0.3294, "lr": 1.2452753216401226e-06, "epoch": 4.490126582278481, "percentage": 89.84, "elapsed_time": "1:24:26", "remaining_time": "0:09:33"}
1298
+ {"current_steps": 1106, "total_steps": 1230, "loss": 0.3461, "lr": 1.2256358498870503e-06, "epoch": 4.494177215189874, "percentage": 89.92, "elapsed_time": "1:25:07", "remaining_time": "0:09:32"}
1299
+ {"current_steps": 1107, "total_steps": 1230, "loss": 0.3425, "lr": 1.2061475842818337e-06, "epoch": 4.498227848101266, "percentage": 90.0, "elapsed_time": "1:25:49", "remaining_time": "0:09:32"}
1300
+ {"current_steps": 1108, "total_steps": 1230, "loss": 0.3489, "lr": 1.1868106817802816e-06, "epoch": 4.502278481012659, "percentage": 90.08, "elapsed_time": "1:26:31", "remaining_time": "0:09:31"}
1301
+ {"current_steps": 1109, "total_steps": 1230, "loss": 0.3308, "lr": 1.1676252981191482e-06, "epoch": 4.506329113924051, "percentage": 90.16, "elapsed_time": "1:27:12", "remaining_time": "0:09:30"}
1302
+ {"current_steps": 1110, "total_steps": 1230, "loss": 0.3275, "lr": 1.1485915878148823e-06, "epoch": 4.510379746835443, "percentage": 90.24, "elapsed_time": "1:27:56", "remaining_time": "0:09:30"}
1303
+ {"current_steps": 1111, "total_steps": 1230, "loss": 0.3394, "lr": 1.1297097041623584e-06, "epoch": 4.514430379746836, "percentage": 90.33, "elapsed_time": "1:28:38", "remaining_time": "0:09:29"}
1304
+ {"current_steps": 1112, "total_steps": 1230, "loss": 0.3474, "lr": 1.1109797992336847e-06, "epoch": 4.518481012658228, "percentage": 90.41, "elapsed_time": "1:29:23", "remaining_time": "0:09:29"}
1305
+ {"current_steps": 1113, "total_steps": 1230, "loss": 0.3501, "lr": 1.092402023876933e-06, "epoch": 4.52253164556962, "percentage": 90.49, "elapsed_time": "1:30:07", "remaining_time": "0:09:28"}
1306
+ {"current_steps": 1114, "total_steps": 1230, "loss": 0.3271, "lr": 1.0739765277149527e-06, "epoch": 4.526582278481013, "percentage": 90.57, "elapsed_time": "1:30:52", "remaining_time": "0:09:27"}
1307
+ {"current_steps": 1115, "total_steps": 1230, "loss": 0.3262, "lr": 1.0557034591441596e-06, "epoch": 4.530632911392405, "percentage": 90.65, "elapsed_time": "1:31:35", "remaining_time": "0:09:26"}
1308
+ {"current_steps": 1116, "total_steps": 1230, "loss": 0.3229, "lr": 1.0375829653333324e-06, "epoch": 4.534683544303798, "percentage": 90.73, "elapsed_time": "1:32:19", "remaining_time": "0:09:25"}
1309
+ {"current_steps": 1117, "total_steps": 1230, "loss": 0.3094, "lr": 1.0196151922224385e-06, "epoch": 4.53873417721519, "percentage": 90.81, "elapsed_time": "1:33:02", "remaining_time": "0:09:24"}
1310
+ {"current_steps": 1118, "total_steps": 1230, "loss": 0.3411, "lr": 1.0018002845214526e-06, "epoch": 4.542784810126582, "percentage": 90.89, "elapsed_time": "1:33:44", "remaining_time": "0:09:23"}
1311
+ {"current_steps": 1119, "total_steps": 1230, "loss": 0.3213, "lr": 9.841383857091947e-07, "epoch": 4.546835443037975, "percentage": 90.98, "elapsed_time": "1:34:23", "remaining_time": "0:09:21"}
1312
+ {"current_steps": 1120, "total_steps": 1230, "loss": 0.3345, "lr": 9.666296380321616e-07, "epoch": 4.550886075949367, "percentage": 91.06, "elapsed_time": "1:35:07", "remaining_time": "0:09:20"}
1313
+ {"current_steps": 1121, "total_steps": 1230, "loss": 0.3392, "lr": 9.492741825034124e-07, "epoch": 4.55493670886076, "percentage": 91.14, "elapsed_time": "1:35:51", "remaining_time": "0:09:19"}
1314
+ {"current_steps": 1122, "total_steps": 1230, "loss": 0.356, "lr": 9.320721589013892e-07, "epoch": 4.558987341772152, "percentage": 91.22, "elapsed_time": "1:36:35", "remaining_time": "0:09:17"}
1315
+ {"current_steps": 1123, "total_steps": 1230, "loss": 0.3346, "lr": 9.150237057688339e-07, "epoch": 4.563037974683544, "percentage": 91.3, "elapsed_time": "1:37:19", "remaining_time": "0:09:16"}
1316
+ {"current_steps": 1124, "total_steps": 1230, "loss": 0.3495, "lr": 8.981289604116328e-07, "epoch": 4.567088607594937, "percentage": 91.38, "elapsed_time": "1:38:04", "remaining_time": "0:09:14"}
1317
+ {"current_steps": 1125, "total_steps": 1230, "loss": 0.3318, "lr": 8.813880588977542e-07, "epoch": 4.571139240506329, "percentage": 91.46, "elapsed_time": "1:38:49", "remaining_time": "0:09:13"}
1318
+ {"current_steps": 1126, "total_steps": 1230, "loss": 0.3624, "lr": 8.648011360561126e-07, "epoch": 4.575189873417721, "percentage": 91.54, "elapsed_time": "1:39:36", "remaining_time": "0:09:11"}
1319
+ {"current_steps": 1127, "total_steps": 1230, "loss": 0.3135, "lr": 8.483683254755037e-07, "epoch": 4.579240506329114, "percentage": 91.63, "elapsed_time": "1:40:21", "remaining_time": "0:09:10"}
1320
+ {"current_steps": 1128, "total_steps": 1230, "loss": 0.3215, "lr": 8.320897595035227e-07, "epoch": 4.583291139240506, "percentage": 91.71, "elapsed_time": "1:41:04", "remaining_time": "0:09:08"}
1321
+ {"current_steps": 1129, "total_steps": 1230, "loss": 0.3442, "lr": 8.159655692455093e-07, "epoch": 4.587341772151898, "percentage": 91.79, "elapsed_time": "1:41:48", "remaining_time": "0:09:06"}
1322
+ {"current_steps": 1130, "total_steps": 1230, "loss": 0.3204, "lr": 7.999958845634648e-07, "epoch": 4.591392405063291, "percentage": 91.87, "elapsed_time": "1:42:33", "remaining_time": "0:09:04"}
1323
+ {"current_steps": 1131, "total_steps": 1230, "loss": 0.2999, "lr": 7.841808340750478e-07, "epoch": 4.595443037974683, "percentage": 91.95, "elapsed_time": "1:43:18", "remaining_time": "0:09:02"}
1324
+ {"current_steps": 1132, "total_steps": 1230, "loss": 0.3631, "lr": 7.685205451524869e-07, "epoch": 4.599493670886076, "percentage": 92.03, "elapsed_time": "1:44:01", "remaining_time": "0:09:00"}
1325
+ {"current_steps": 1133, "total_steps": 1230, "loss": 0.3299, "lr": 7.530151439216027e-07, "epoch": 4.603544303797468, "percentage": 92.11, "elapsed_time": "1:44:45", "remaining_time": "0:08:58"}
1326
+ {"current_steps": 1134, "total_steps": 1230, "loss": 0.3163, "lr": 7.376647552607675e-07, "epoch": 4.6075949367088604, "percentage": 92.2, "elapsed_time": "1:45:28", "remaining_time": "0:08:55"}
1327
+ {"current_steps": 1135, "total_steps": 1230, "loss": 0.3324, "lr": 7.224695027998963e-07, "epoch": 4.611645569620253, "percentage": 92.28, "elapsed_time": "1:46:10", "remaining_time": "0:08:53"}
1328
+ {"current_steps": 1136, "total_steps": 1230, "loss": 0.3414, "lr": 7.07429508919466e-07, "epoch": 4.6156962025316455, "percentage": 92.36, "elapsed_time": "1:46:52", "remaining_time": "0:08:50"}
1329
+ {"current_steps": 1137, "total_steps": 1230, "loss": 0.3373, "lr": 6.925448947495206e-07, "epoch": 4.619746835443038, "percentage": 92.44, "elapsed_time": "1:47:35", "remaining_time": "0:08:48"}
1330
+ {"current_steps": 1138, "total_steps": 1230, "loss": 0.3425, "lr": 6.778157801686936e-07, "epoch": 4.6237974683544305, "percentage": 92.52, "elapsed_time": "1:48:18", "remaining_time": "0:08:45"}
1331
+ {"current_steps": 1139, "total_steps": 1230, "loss": 0.3288, "lr": 6.632422838032515e-07, "epoch": 4.627848101265823, "percentage": 92.6, "elapsed_time": "1:49:02", "remaining_time": "0:08:42"}
1332
+ {"current_steps": 1140, "total_steps": 1230, "loss": 0.3247, "lr": 6.488245230261281e-07, "epoch": 4.6318987341772155, "percentage": 92.68, "elapsed_time": "1:49:38", "remaining_time": "0:08:39"}
1333
+ {"current_steps": 1141, "total_steps": 1230, "loss": 0.3374, "lr": 6.345626139559868e-07, "epoch": 4.635949367088608, "percentage": 92.76, "elapsed_time": "1:50:21", "remaining_time": "0:08:36"}
1334
+ {"current_steps": 1142, "total_steps": 1230, "loss": 0.3258, "lr": 6.204566714562866e-07, "epoch": 4.64, "percentage": 92.85, "elapsed_time": "1:51:06", "remaining_time": "0:08:33"}
1335
+ {"current_steps": 1143, "total_steps": 1230, "loss": 0.3424, "lr": 6.06506809134344e-07, "epoch": 4.644050632911393, "percentage": 92.93, "elapsed_time": "1:51:50", "remaining_time": "0:08:30"}
1336
+ {"current_steps": 1144, "total_steps": 1230, "loss": 0.3308, "lr": 5.927131393404373e-07, "epoch": 4.648101265822785, "percentage": 93.01, "elapsed_time": "1:52:34", "remaining_time": "0:08:27"}
1337
+ {"current_steps": 1145, "total_steps": 1230, "loss": 0.3465, "lr": 5.790757731668817e-07, "epoch": 4.652151898734177, "percentage": 93.09, "elapsed_time": "1:53:15", "remaining_time": "0:08:24"}
1338
+ {"current_steps": 1146, "total_steps": 1230, "loss": 0.3328, "lr": 5.655948204471507e-07, "epoch": 4.65620253164557, "percentage": 93.17, "elapsed_time": "1:53:56", "remaining_time": "0:08:21"}
1339
+ {"current_steps": 1147, "total_steps": 1230, "loss": 0.3186, "lr": 5.522703897549875e-07, "epoch": 4.660253164556962, "percentage": 93.25, "elapsed_time": "1:54:40", "remaining_time": "0:08:17"}
1340
+ {"current_steps": 1148, "total_steps": 1230, "loss": 0.333, "lr": 5.391025884035239e-07, "epoch": 4.664303797468355, "percentage": 93.33, "elapsed_time": "1:55:25", "remaining_time": "0:08:14"}
1341
+ {"current_steps": 1149, "total_steps": 1230, "loss": 0.3286, "lr": 5.260915224444207e-07, "epoch": 4.668354430379747, "percentage": 93.41, "elapsed_time": "1:56:07", "remaining_time": "0:08:11"}
1342
+ {"current_steps": 1150, "total_steps": 1230, "loss": 0.3502, "lr": 5.132372966670129e-07, "epoch": 4.672405063291139, "percentage": 93.5, "elapsed_time": "1:56:50", "remaining_time": "0:08:07"}
1343
+ {"current_steps": 1151, "total_steps": 1230, "loss": 0.3464, "lr": 5.005400145974704e-07, "epoch": 4.676455696202532, "percentage": 93.58, "elapsed_time": "1:57:34", "remaining_time": "0:08:04"}
1344
+ {"current_steps": 1152, "total_steps": 1230, "loss": 0.3131, "lr": 4.879997784979562e-07, "epoch": 4.680506329113924, "percentage": 93.66, "elapsed_time": "1:58:17", "remaining_time": "0:08:00"}
1345
+ {"current_steps": 1153, "total_steps": 1230, "loss": 0.3503, "lr": 4.7561668936580984e-07, "epoch": 4.684556962025317, "percentage": 93.74, "elapsed_time": "1:59:00", "remaining_time": "0:07:56"}
1346
+ {"current_steps": 1154, "total_steps": 1230, "loss": 0.3103, "lr": 4.6339084693272306e-07, "epoch": 4.688607594936709, "percentage": 93.82, "elapsed_time": "1:59:43", "remaining_time": "0:07:53"}
1347
+ {"current_steps": 1155, "total_steps": 1230, "loss": 0.3361, "lr": 4.5132234966395847e-07, "epoch": 4.692658227848101, "percentage": 93.9, "elapsed_time": "2:00:27", "remaining_time": "0:07:49"}
1348
+ {"current_steps": 1156, "total_steps": 1230, "loss": 0.3661, "lr": 4.3941129475752795e-07, "epoch": 4.696708860759494, "percentage": 93.98, "elapsed_time": "2:01:11", "remaining_time": "0:07:45"}
1349
+ {"current_steps": 1157, "total_steps": 1230, "loss": 0.3247, "lr": 4.27657778143431e-07, "epoch": 4.700759493670886, "percentage": 94.07, "elapsed_time": "2:01:55", "remaining_time": "0:07:41"}
1350
+ {"current_steps": 1158, "total_steps": 1230, "loss": 0.3139, "lr": 4.1606189448287757e-07, "epoch": 4.704810126582278, "percentage": 94.15, "elapsed_time": "2:02:39", "remaining_time": "0:07:37"}
1351
+ {"current_steps": 1159, "total_steps": 1230, "loss": 0.3139, "lr": 4.046237371675177e-07, "epoch": 4.708860759493671, "percentage": 94.23, "elapsed_time": "2:03:21", "remaining_time": "0:07:33"}
1352
+ {"current_steps": 1160, "total_steps": 1230, "loss": 0.3257, "lr": 3.9334339831869963e-07, "epoch": 4.712911392405063, "percentage": 94.31, "elapsed_time": "2:04:06", "remaining_time": "0:07:29"}
1353
+ {"current_steps": 1161, "total_steps": 1230, "loss": 0.3186, "lr": 3.8222096878671955e-07, "epoch": 4.716962025316455, "percentage": 94.39, "elapsed_time": "2:04:51", "remaining_time": "0:07:25"}
1354
+ {"current_steps": 1162, "total_steps": 1230, "loss": 0.331, "lr": 3.7125653815009545e-07, "epoch": 4.721012658227848, "percentage": 94.47, "elapsed_time": "2:05:30", "remaining_time": "0:07:20"}
1355
+ {"current_steps": 1163, "total_steps": 1230, "loss": 0.3163, "lr": 3.6045019471484974e-07, "epoch": 4.72506329113924, "percentage": 94.55, "elapsed_time": "2:06:16", "remaining_time": "0:07:16"}
1356
+ {"current_steps": 1164, "total_steps": 1230, "loss": 0.3297, "lr": 3.498020255137813e-07, "epoch": 4.729113924050633, "percentage": 94.63, "elapsed_time": "2:07:00", "remaining_time": "0:07:12"}
1357
+ {"current_steps": 1165, "total_steps": 1230, "loss": 0.3231, "lr": 3.393121163057811e-07, "epoch": 4.733164556962025, "percentage": 94.72, "elapsed_time": "2:07:41", "remaining_time": "0:07:07"}
1358
+ {"current_steps": 1166, "total_steps": 1230, "loss": 0.3305, "lr": 3.289805515751399e-07, "epoch": 4.737215189873417, "percentage": 94.8, "elapsed_time": "2:08:26", "remaining_time": "0:07:03"}
1359
+ {"current_steps": 1167, "total_steps": 1230, "loss": 0.3338, "lr": 3.188074145308573e-07, "epoch": 4.74126582278481, "percentage": 94.88, "elapsed_time": "2:09:10", "remaining_time": "0:06:58"}
1360
+ {"current_steps": 1168, "total_steps": 1230, "loss": 0.3428, "lr": 3.087927871059804e-07, "epoch": 4.745316455696202, "percentage": 94.96, "elapsed_time": "2:09:56", "remaining_time": "0:06:53"}
1361
+ {"current_steps": 1169, "total_steps": 1230, "loss": 0.3455, "lr": 2.989367499569418e-07, "epoch": 4.749367088607595, "percentage": 95.04, "elapsed_time": "2:10:41", "remaining_time": "0:06:49"}
1362
+ {"current_steps": 1170, "total_steps": 1230, "loss": 0.3588, "lr": 2.8923938246290917e-07, "epoch": 4.7534177215189874, "percentage": 95.12, "elapsed_time": "2:11:28", "remaining_time": "0:06:44"}
1363
+ {"current_steps": 1171, "total_steps": 1230, "loss": 0.3394, "lr": 2.7970076272514804e-07, "epoch": 4.7574683544303795, "percentage": 95.2, "elapsed_time": "2:12:10", "remaining_time": "0:06:39"}
1364
+ {"current_steps": 1172, "total_steps": 1230, "loss": 0.3425, "lr": 2.703209675663887e-07, "epoch": 4.7615189873417725, "percentage": 95.28, "elapsed_time": "2:12:55", "remaining_time": "0:06:34"}
1365
+ {"current_steps": 1173, "total_steps": 1230, "loss": 0.315, "lr": 2.6110007253021374e-07, "epoch": 4.7655696202531646, "percentage": 95.37, "elapsed_time": "2:13:38", "remaining_time": "0:06:29"}
1366
+ {"current_steps": 1174, "total_steps": 1230, "loss": 0.3119, "lr": 2.520381518804471e-07, "epoch": 4.769620253164557, "percentage": 95.45, "elapsed_time": "2:14:22", "remaining_time": "0:06:24"}
1367
+ {"current_steps": 1175, "total_steps": 1230, "loss": 0.3333, "lr": 2.4313527860054585e-07, "epoch": 4.77367088607595, "percentage": 95.53, "elapsed_time": "2:15:06", "remaining_time": "0:06:19"}
1368
+ {"current_steps": 1176, "total_steps": 1230, "loss": 0.3405, "lr": 2.343915243930317e-07, "epoch": 4.777721518987342, "percentage": 95.61, "elapsed_time": "2:15:42", "remaining_time": "0:06:13"}
1369
+ {"current_steps": 1177, "total_steps": 1230, "loss": 0.3236, "lr": 2.2580695967889367e-07, "epoch": 4.781772151898734, "percentage": 95.69, "elapsed_time": "2:16:29", "remaining_time": "0:06:08"}
1370
+ {"current_steps": 1178, "total_steps": 1230, "loss": 0.3361, "lr": 2.1738165359704189e-07, "epoch": 4.785822784810127, "percentage": 95.77, "elapsed_time": "2:17:13", "remaining_time": "0:06:03"}
1371
+ {"current_steps": 1179, "total_steps": 1230, "loss": 0.3086, "lr": 2.0911567400373257e-07, "epoch": 4.789873417721519, "percentage": 95.85, "elapsed_time": "2:17:57", "remaining_time": "0:05:58"}
1372
+ {"current_steps": 1180, "total_steps": 1230, "loss": 0.3285, "lr": 2.0100908747202607e-07, "epoch": 4.793924050632912, "percentage": 95.93, "elapsed_time": "2:18:39", "remaining_time": "0:05:52"}
1373
+ {"current_steps": 1181, "total_steps": 1230, "loss": 0.3322, "lr": 1.9306195929125638e-07, "epoch": 4.797974683544304, "percentage": 96.02, "elapsed_time": "2:19:20", "remaining_time": "0:05:46"}
1374
+ {"current_steps": 1182, "total_steps": 1230, "loss": 0.3304, "lr": 1.8527435346650247e-07, "epoch": 4.802025316455696, "percentage": 96.1, "elapsed_time": "2:20:03", "remaining_time": "0:05:41"}
1375
+ {"current_steps": 1183, "total_steps": 1230, "loss": 0.3293, "lr": 1.7764633271807108e-07, "epoch": 4.806075949367089, "percentage": 96.18, "elapsed_time": "2:20:46", "remaining_time": "0:05:35"}
1376
+ {"current_steps": 1184, "total_steps": 1230, "loss": 0.3321, "lr": 1.7017795848099262e-07, "epoch": 4.810126582278481, "percentage": 96.26, "elapsed_time": "2:21:32", "remaining_time": "0:05:29"}
1377
+ {"current_steps": 1185, "total_steps": 1230, "loss": 0.3367, "lr": 1.6286929090452596e-07, "epoch": 4.814177215189874, "percentage": 96.34, "elapsed_time": "2:22:17", "remaining_time": "0:05:24"}
1378
+ {"current_steps": 1186, "total_steps": 1230, "loss": 0.3364, "lr": 1.557203888516745e-07, "epoch": 4.818227848101266, "percentage": 96.42, "elapsed_time": "2:23:03", "remaining_time": "0:05:18"}
1379
+ {"current_steps": 1187, "total_steps": 1230, "loss": 0.3352, "lr": 1.487313098987131e-07, "epoch": 4.822278481012658, "percentage": 96.5, "elapsed_time": "2:23:46", "remaining_time": "0:05:12"}
1380
+ {"current_steps": 1188, "total_steps": 1230, "loss": 0.3206, "lr": 1.4190211033472402e-07, "epoch": 4.826329113924051, "percentage": 96.59, "elapsed_time": "2:24:27", "remaining_time": "0:05:06"}
1381
+ {"current_steps": 1189, "total_steps": 1230, "loss": 0.338, "lr": 1.3523284516113955e-07, "epoch": 4.830379746835443, "percentage": 96.67, "elapsed_time": "2:25:10", "remaining_time": "0:05:00"}
1382
+ {"current_steps": 1190, "total_steps": 1230, "loss": 0.345, "lr": 1.2872356809130682e-07, "epoch": 4.834430379746835, "percentage": 96.75, "elapsed_time": "2:25:55", "remaining_time": "0:04:54"}
1383
+ {"current_steps": 1191, "total_steps": 1230, "loss": 0.3443, "lr": 1.2237433155004807e-07, "epoch": 4.838481012658228, "percentage": 96.83, "elapsed_time": "2:26:39", "remaining_time": "0:04:48"}
1384
+ {"current_steps": 1192, "total_steps": 1230, "loss": 0.3469, "lr": 1.1618518667323886e-07, "epoch": 4.84253164556962, "percentage": 96.91, "elapsed_time": "2:27:19", "remaining_time": "0:04:41"}
1385
+ {"current_steps": 1193, "total_steps": 1230, "loss": 0.3297, "lr": 1.1015618330740385e-07, "epoch": 4.846582278481012, "percentage": 96.99, "elapsed_time": "2:28:01", "remaining_time": "0:04:35"}
1386
+ {"current_steps": 1194, "total_steps": 1230, "loss": 0.3427, "lr": 1.042873700093061e-07, "epoch": 4.850632911392405, "percentage": 97.07, "elapsed_time": "2:28:46", "remaining_time": "0:04:29"}
1387
+ {"current_steps": 1195, "total_steps": 1230, "loss": 0.3425, "lr": 9.857879404556291e-08, "epoch": 4.854683544303797, "percentage": 97.15, "elapsed_time": "2:29:30", "remaining_time": "0:04:22"}
1388
+ {"current_steps": 1196, "total_steps": 1230, "loss": 0.3219, "lr": 9.303050139225722e-08, "epoch": 4.85873417721519, "percentage": 97.24, "elapsed_time": "2:30:15", "remaining_time": "0:04:16"}
1389
+ {"current_steps": 1197, "total_steps": 1230, "loss": 0.3199, "lr": 8.76425367345779e-08, "epoch": 4.862784810126582, "percentage": 97.32, "elapsed_time": "2:30:59", "remaining_time": "0:04:09"}
1390
+ {"current_steps": 1198, "total_steps": 1230, "loss": 0.3365, "lr": 8.241494346644897e-08, "epoch": 4.866835443037974, "percentage": 97.4, "elapsed_time": "2:31:42", "remaining_time": "0:04:03"}
1391
+ {"current_steps": 1199, "total_steps": 1230, "loss": 0.2913, "lr": 7.734776369019204e-08, "epoch": 4.870886075949367, "percentage": 97.48, "elapsed_time": "2:32:28", "remaining_time": "0:03:56"}
1392
+ {"current_steps": 1200, "total_steps": 1230, "loss": 0.3212, "lr": 7.244103821617332e-08, "epoch": 4.874936708860759, "percentage": 97.56, "elapsed_time": "2:33:11", "remaining_time": "0:03:49"}
1393
+ {"current_steps": 1201, "total_steps": 1230, "loss": 0.3331, "lr": 6.769480656248606e-08, "epoch": 4.878987341772152, "percentage": 97.64, "elapsed_time": "2:33:57", "remaining_time": "0:03:43"}
1394
+ {"current_steps": 1202, "total_steps": 1230, "loss": 0.3272, "lr": 6.310910695462635e-08, "epoch": 4.883037974683544, "percentage": 97.72, "elapsed_time": "2:34:42", "remaining_time": "0:03:36"}
1395
+ {"current_steps": 1203, "total_steps": 1230, "loss": 0.3149, "lr": 5.8683976325191185e-08, "epoch": 4.8870886075949365, "percentage": 97.8, "elapsed_time": "2:35:24", "remaining_time": "0:03:29"}
1396
+ {"current_steps": 1204, "total_steps": 1230, "loss": 0.3104, "lr": 5.4419450313571984e-08, "epoch": 4.891139240506329, "percentage": 97.89, "elapsed_time": "2:36:06", "remaining_time": "0:03:22"}
1397
+ {"current_steps": 1205, "total_steps": 1230, "loss": 0.3166, "lr": 5.031556326567488e-08, "epoch": 4.8951898734177215, "percentage": 97.97, "elapsed_time": "2:36:50", "remaining_time": "0:03:15"}
1398
+ {"current_steps": 1206, "total_steps": 1230, "loss": 0.3272, "lr": 4.637234823364312e-08, "epoch": 4.899240506329114, "percentage": 98.05, "elapsed_time": "2:37:34", "remaining_time": "0:03:08"}
1399
+ {"current_steps": 1207, "total_steps": 1230, "loss": 0.325, "lr": 4.258983697558838e-08, "epoch": 4.9032911392405065, "percentage": 98.13, "elapsed_time": "2:38:18", "remaining_time": "0:03:01"}
1400
+ {"current_steps": 1208, "total_steps": 1230, "loss": 0.3486, "lr": 3.896805995533548e-08, "epoch": 4.907341772151899, "percentage": 98.21, "elapsed_time": "2:39:02", "remaining_time": "0:02:53"}
1401
+ {"current_steps": 1209, "total_steps": 1230, "loss": 0.3281, "lr": 3.550704634218028e-08, "epoch": 4.911392405063291, "percentage": 98.29, "elapsed_time": "2:39:44", "remaining_time": "0:02:46"}
1402
+ {"current_steps": 1210, "total_steps": 1230, "loss": 0.3465, "lr": 3.2206824010647676e-08, "epoch": 4.915443037974684, "percentage": 98.37, "elapsed_time": "2:40:25", "remaining_time": "0:02:39"}
1403
+ {"current_steps": 1211, "total_steps": 1230, "loss": 0.3453, "lr": 2.9067419540278476e-08, "epoch": 4.919493670886076, "percentage": 98.46, "elapsed_time": "2:41:05", "remaining_time": "0:02:31"}
1404
+ {"current_steps": 1212, "total_steps": 1230, "loss": 0.336, "lr": 2.6088858215400638e-08, "epoch": 4.923544303797469, "percentage": 98.54, "elapsed_time": "2:41:47", "remaining_time": "0:02:24"}
1405
+ {"current_steps": 1213, "total_steps": 1230, "loss": 0.3421, "lr": 2.3271164024940564e-08, "epoch": 4.927594936708861, "percentage": 98.62, "elapsed_time": "2:42:32", "remaining_time": "0:02:16"}
1406
+ {"current_steps": 1214, "total_steps": 1230, "loss": 0.3382, "lr": 2.061435966221881e-08, "epoch": 4.931645569620253, "percentage": 98.7, "elapsed_time": "2:43:14", "remaining_time": "0:02:09"}
1407
+ {"current_steps": 1215, "total_steps": 1230, "loss": 0.349, "lr": 1.811846652477245e-08, "epoch": 4.935696202531646, "percentage": 98.78, "elapsed_time": "2:43:59", "remaining_time": "0:02:01"}
1408
+ {"current_steps": 1216, "total_steps": 1230, "loss": 0.322, "lr": 1.5783504714184106e-08, "epoch": 4.939746835443038, "percentage": 98.86, "elapsed_time": "2:44:42", "remaining_time": "0:01:53"}
1409
+ {"current_steps": 1217, "total_steps": 1230, "loss": 0.3428, "lr": 1.360949303591097e-08, "epoch": 4.943797468354431, "percentage": 98.94, "elapsed_time": "2:45:28", "remaining_time": "0:01:46"}
1410
+ {"current_steps": 1218, "total_steps": 1230, "loss": 0.3276, "lr": 1.1596448999144916e-08, "epoch": 4.947848101265823, "percentage": 99.02, "elapsed_time": "2:46:12", "remaining_time": "0:01:38"}
1411
+ {"current_steps": 1219, "total_steps": 1230, "loss": 0.3412, "lr": 9.744388816668172e-09, "epoch": 4.951898734177215, "percentage": 99.11, "elapsed_time": "2:46:56", "remaining_time": "0:01:30"}
1412
+ {"current_steps": 1220, "total_steps": 1230, "loss": 0.3222, "lr": 8.05332740472009e-09, "epoch": 4.955949367088608, "percentage": 99.19, "elapsed_time": "2:47:40", "remaining_time": "0:01:22"}
1413
+ {"current_steps": 1221, "total_steps": 1230, "loss": 0.3378, "lr": 6.523278382872811e-09, "epoch": 4.96, "percentage": 99.27, "elapsed_time": "2:48:27", "remaining_time": "0:01:14"}
1414
+ {"current_steps": 1222, "total_steps": 1230, "loss": 0.3582, "lr": 5.15425407393133e-09, "epoch": 4.964050632911392, "percentage": 99.35, "elapsed_time": "2:49:09", "remaining_time": "0:01:06"}
1415
+ {"current_steps": 1223, "total_steps": 1230, "loss": 0.3433, "lr": 3.94626550383137e-09, "epoch": 4.968101265822785, "percentage": 99.43, "elapsed_time": "2:49:53", "remaining_time": "0:00:58"}
1416
+ {"current_steps": 1224, "total_steps": 1230, "loss": 0.3476, "lr": 2.899322401546112e-09, "epoch": 4.972151898734177, "percentage": 99.51, "elapsed_time": "2:50:37", "remaining_time": "0:00:50"}
1417
+ {"current_steps": 1225, "total_steps": 1230, "loss": 0.3591, "lr": 2.013433199010706e-09, "epoch": 4.976202531645569, "percentage": 99.59, "elapsed_time": "2:51:22", "remaining_time": "0:00:41"}
1418
+ {"current_steps": 1226, "total_steps": 1230, "loss": 0.3551, "lr": 1.2886050310556563e-09, "epoch": 4.980253164556962, "percentage": 99.67, "elapsed_time": "2:52:05", "remaining_time": "0:00:33"}
1419
+ {"current_steps": 1227, "total_steps": 1230, "loss": 0.351, "lr": 7.248437353468695e-10, "epoch": 4.984303797468354, "percentage": 99.76, "elapsed_time": "2:52:50", "remaining_time": "0:00:25"}
1420
+ {"current_steps": 1228, "total_steps": 1230, "loss": 0.3382, "lr": 3.221538523412449e-10, "epoch": 4.988354430379747, "percentage": 99.84, "elapsed_time": "2:53:33", "remaining_time": "0:00:16"}
1421
+ {"current_steps": 1229, "total_steps": 1230, "loss": 0.3235, "lr": 8.053862524670663e-11, "epoch": 4.992405063291139, "percentage": 99.92, "elapsed_time": "2:54:16", "remaining_time": "0:00:08"}
1422
+ {"current_steps": 1230, "total_steps": 1230, "loss": 0.3503, "lr": 0.0, "epoch": 4.996455696202531, "percentage": 100.0, "elapsed_time": "2:54:57", "remaining_time": "0:00:00"}
1423
+ {"current_steps": 1230, "total_steps": 1230, "epoch": 4.996455696202531, "percentage": 100.0, "elapsed_time": "2:59:34", "remaining_time": "0:00:00"}
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:314475a6ea347579c629a6d45f573604d06bd883db6e15463b89852401857313
3
- size 7288
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3d1d92cdea6e95ba3218ac829e75871a55daebd9eac6ce115c3feb2358adcdb
3
+ size 7352