diff --git "a/log/debug_0.log" "b/log/debug_0.log"
--- "a/log/debug_0.log"
+++ "b/log/debug_0.log"
@@ -15028,3 +15028,15007 @@ M	requirements.txt
 08/30/2021 15:48:24 - INFO - __main__ - Evaluating model checkpoint
 08/30/2021 15:57:02 - INFO - __main__ - Step 15000: {'loss/eval': 1.5676782131195068, 'perplexity': 4.795501232147217}
 08/30/2021 15:57:02 - INFO - __main__ - Saving model checkpoint
+08/30/2021 15:57:37 - INFO - __main__ - Step 15001: {'lr': 0.0004905416503522123, 'samples': 2880192, 'steps': 15000, 'loss/train': 0.08897807449102402}
+08/30/2021 15:57:37 - INFO - __main__ - Step 15002: {'lr': 0.0004905402044129162, 'samples': 2880384, 'steps': 15001, 'loss/train': 1.7169634103775024}
+08/30/2021 15:57:38 - INFO - __main__ - Step 15003: {'lr': 0.0004905387583652363, 'samples': 2880576, 'steps': 15002, 'loss/train': 2.079348564147949}
+08/30/2021 15:57:39 - INFO - __main__ - Step 15004: {'lr': 0.0004905373122091734, 'samples': 2880768, 'steps': 15003, 'loss/train': 1.7418956756591797}
+08/30/2021 15:57:40 - INFO - __main__ - Step 15005: {'lr': 0.0004905358659447281, 'samples': 2880960, 'steps': 15004, 'loss/train': 1.5207520723342896}
+08/30/2021 15:57:40 - INFO - __main__ - Step 15006: {'lr': 0.000490534419571901, 'samples': 2881152, 'steps': 15005, 'loss/train': 1.5853830575942993}
+08/30/2021 15:57:40 - INFO - __main__ - Step 15007: {'lr': 0.0004905329730906929, 'samples': 2881344, 'steps': 15006, 'loss/train': 1.8985745906829834}
+08/30/2021 15:57:41 - INFO - __main__ - Step 15008: {'lr': 0.0004905315265011043, 'samples': 2881536, 'steps': 15007, 'loss/train': 1.9557712078094482}
+08/30/2021 15:57:42 - INFO - __main__ - Step 15009: {'lr': 0.0004905300798031359, 'samples': 2881728, 'steps': 15008, 'loss/train': 1.9216936826705933}
+08/30/2021 15:57:43 - INFO - __main__ - Step 15010: {'lr': 0.0004905286329967883, 'samples': 2881920, 'steps': 15009, 'loss/train': 1.2003295421600342}
+08/30/2021 15:57:43 - INFO - __main__ - Step 15011: {'lr': 0.0004905271860820622, 'samples': 2882112, 'steps': 15010, 'loss/train': 2.3111867904663086}
+08/30/2021 15:57:43 - INFO - __main__ - Step 15012: {'lr': 0.0004905257390589585, 'samples': 2882304, 'steps': 15011, 'loss/train': 1.5301975011825562}
+08/30/2021 15:57:44 - INFO - __main__ - Step 15013: {'lr': 0.0004905242919274774, 'samples': 2882496, 'steps': 15012, 'loss/train': 1.2972427606582642}
+08/30/2021 15:57:45 - INFO - __main__ - Step 15014: {'lr': 0.0004905228446876197, 'samples': 2882688, 'steps': 15013, 'loss/train': 1.50941002368927}
+08/30/2021 15:57:46 - INFO - __main__ - Step 15015: {'lr': 0.0004905213973393863, 'samples': 2882880, 'steps': 15014, 'loss/train': 1.6621195077896118}
+08/30/2021 15:57:46 - INFO - __main__ - Step 15016: {'lr': 0.0004905199498827776, 'samples': 2883072, 'steps': 15015, 'loss/train': 1.812369704246521}
+08/30/2021 15:57:46 - INFO - __main__ - Step 15017: {'lr': 0.0004905185023177942, 'samples': 2883264, 'steps': 15016, 'loss/train': 1.7890472412109375}
+08/30/2021 15:57:47 - INFO - __main__ - Step 15018: {'lr': 0.0004905170546444371, 'samples': 2883456, 'steps': 15017, 'loss/train': 1.4666922092437744}
+08/30/2021 15:57:49 - INFO - __main__ - Step 15019: {'lr': 0.0004905156068627065, 'samples': 2883648, 'steps': 15018, 'loss/train': 1.536946177482605}
+08/30/2021 15:57:49 - INFO - __main__ - Step 15020: {'lr': 0.0004905141589726035, 'samples': 2883840, 'steps': 15019, 'loss/train': 1.8957767486572266}
+08/30/2021 15:57:50 - INFO - __main__ - Step 15021: {'lr': 0.0004905127109741284, 'samples': 2884032, 'steps': 15020, 'loss/train': 1.2258646488189697}
+08/30/2021 15:57:50 - INFO - __main__ - Step 15022: {'lr': 0.000490511262867282, 'samples': 2884224, 'steps': 15021, 'loss/train': 1.2116807699203491}
+08/30/2021 15:57:50 - INFO - __main__ - Step 15023: {'lr': 0.000490509814652065, 'samples': 2884416, 'steps': 15022, 'loss/train': 1.846852421760559}
+08/30/2021 15:57:52 - INFO - __main__ - Step 15024: {'lr': 0.0004905083663284779, 'samples': 2884608, 'steps': 15023, 'loss/train': 1.4833589792251587}
+08/30/2021 15:57:52 - INFO - __main__ - Step 15025: {'lr': 0.0004905069178965214, 'samples': 2884800, 'steps': 15024, 'loss/train': 1.6528632640838623}
+08/30/2021 15:57:53 - INFO - __main__ - Step 15026: {'lr': 0.0004905054693561963, 'samples': 2884992, 'steps': 15025, 'loss/train': 1.6975077390670776}
+08/30/2021 15:57:53 - INFO - __main__ - Step 15027: {'lr': 0.0004905040207075032, 'samples': 2885184, 'steps': 15026, 'loss/train': 1.3338165283203125}
+08/30/2021 15:57:53 - INFO - __main__ - Step 15028: {'lr': 0.0004905025719504426, 'samples': 2885376, 'steps': 15027, 'loss/train': 1.818396806716919}
+08/30/2021 15:57:54 - INFO - __main__ - Step 15029: {'lr': 0.0004905011230850152, 'samples': 2885568, 'steps': 15028, 'loss/train': 1.5168710947036743}
+08/30/2021 15:57:56 - INFO - __main__ - Step 15030: {'lr': 0.0004904996741112218, 'samples': 2885760, 'steps': 15029, 'loss/train': 1.5877747535705566}
+08/30/2021 15:57:56 - INFO - __main__ - Step 15031: {'lr': 0.0004904982250290629, 'samples': 2885952, 'steps': 15030, 'loss/train': 1.7008051872253418}
+08/30/2021 15:57:56 - INFO - __main__ - Step 15032: {'lr': 0.0004904967758385393, 'samples': 2886144, 'steps': 15031, 'loss/train': 1.7522859573364258}
+08/30/2021 15:57:57 - INFO - __main__ - Step 15033: {'lr': 0.0004904953265396515, 'samples': 2886336, 'steps': 15032, 'loss/train': 0.14056184887886047}
+08/30/2021 15:57:57 - INFO - __main__ - Step 15034: {'lr': 0.0004904938771324002, 'samples': 2886528, 'steps': 15033, 'loss/train': 1.7451437711715698}
+08/30/2021 15:57:59 - INFO - __main__ - Step 15035: {'lr': 0.0004904924276167861, 'samples': 2886720, 'steps': 15034, 'loss/train': 1.7355155944824219}
+08/30/2021 15:57:59 - INFO - __main__ - Step 15036: {'lr': 0.0004904909779928099, 'samples': 2886912, 'steps': 15035, 'loss/train': 1.4620782136917114}
+08/30/2021 15:57:59 - INFO - __main__ - Step 15037: {'lr': 0.000490489528260472, 'samples': 2887104, 'steps': 15036, 'loss/train': 0.44157060980796814}
+08/30/2021 15:58:00 - INFO - __main__ - Step 15038: {'lr': 0.0004904880784197734, 'samples': 2887296, 'steps': 15037, 'loss/train': 1.6056537628173828}
+08/30/2021 15:58:00 - INFO - __main__ - Step 15039: {'lr': 0.0004904866284707144, 'samples': 2887488, 'steps': 15038, 'loss/train': 2.031805992126465}
+08/30/2021 15:58:02 - INFO - __main__ - Step 15040: {'lr': 0.000490485178413296, 'samples': 2887680, 'steps': 15039, 'loss/train': 1.5526639223098755}
+08/30/2021 15:58:02 - INFO - __main__ - Step 15041: {'lr': 0.0004904837282475186, 'samples': 2887872, 'steps': 15040, 'loss/train': 2.158902406692505}
+08/30/2021 15:58:03 - INFO - __main__ - Step 15042: {'lr': 0.000490482277973383, 'samples': 2888064, 'steps': 15041, 'loss/train': 1.7040448188781738}
+08/30/2021 15:58:03 - INFO - __main__ - Step 15043: {'lr': 0.0004904808275908898, 'samples': 2888256, 'steps': 15042, 'loss/train': 0.609427809715271}
+08/30/2021 15:58:03 - INFO - __main__ - Step 15044: {'lr': 0.0004904793771000396, 'samples': 2888448, 'steps': 15043, 'loss/train': 1.9580683708190918}
+08/30/2021 15:58:05 - INFO - __main__ - Step 15045: {'lr': 0.0004904779265008331, 'samples': 2888640, 'steps': 15044, 'loss/train': 1.416972041130066}
+08/30/2021 15:58:05 - INFO - __main__ - Step 15046: {'lr': 0.000490476475793271, 'samples': 2888832, 'steps': 15045, 'loss/train': 1.914841890335083}
+08/30/2021 15:58:06 - INFO - __main__ - Step 15047: {'lr': 0.0004904750249773538, 'samples': 2889024, 'steps': 15046, 'loss/train': 1.60141122341156}
+08/30/2021 15:58:06 - INFO - __main__ - Step 15048: {'lr': 0.0004904735740530825, 'samples': 2889216, 'steps': 15047, 'loss/train': 1.4357203245162964}
+08/30/2021 15:58:06 - INFO - __main__ - Step 15049: {'lr': 0.0004904721230204573, 'samples': 2889408, 'steps': 15048, 'loss/train': 2.2410624027252197}
+08/30/2021 15:58:08 - INFO - __main__ - Step 15050: {'lr': 0.0004904706718794791, 'samples': 2889600, 'steps': 15049, 'loss/train': 1.1474930047988892}
+08/30/2021 15:58:09 - INFO - __main__ - Step 15051: {'lr': 0.0004904692206301487, 'samples': 2889792, 'steps': 15050, 'loss/train': 1.4560447931289673}
+08/30/2021 15:58:09 - INFO - __main__ - Step 15052: {'lr': 0.0004904677692724664, 'samples': 2889984, 'steps': 15051, 'loss/train': 1.4431084394454956}
+08/30/2021 15:58:09 - INFO - __main__ - Step 15053: {'lr': 0.000490466317806433, 'samples': 2890176, 'steps': 15052, 'loss/train': 1.6216411590576172}
+08/30/2021 15:58:10 - INFO - __main__ - Step 15054: {'lr': 0.0004904648662320493, 'samples': 2890368, 'steps': 15053, 'loss/train': 0.1565411537885666}
+08/30/2021 15:58:11 - INFO - __main__ - Step 15055: {'lr': 0.0004904634145493159, 'samples': 2890560, 'steps': 15054, 'loss/train': 1.1482092142105103}
+08/30/2021 15:58:12 - INFO - __main__ - Step 15056: {'lr': 0.0004904619627582332, 'samples': 2890752, 'steps': 15055, 'loss/train': 1.7334765195846558}
+08/30/2021 15:58:12 - INFO - __main__ - Step 15057: {'lr': 0.0004904605108588023, 'samples': 2890944, 'steps': 15056, 'loss/train': 1.4141312837600708}
+08/30/2021 15:58:12 - INFO - __main__ - Step 15058: {'lr': 0.0004904590588510234, 'samples': 2891136, 'steps': 15057, 'loss/train': 1.9265528917312622}
+08/30/2021 15:58:13 - INFO - __main__ - Step 15059: {'lr': 0.0004904576067348975, 'samples': 2891328, 'steps': 15058, 'loss/train': 2.2109851837158203}
+08/30/2021 15:58:13 - INFO - __main__ - Step 15060: {'lr': 0.000490456154510425, 'samples': 2891520, 'steps': 15059, 'loss/train': 2.0628292560577393}
+08/30/2021 15:58:15 - INFO - __main__ - Step 15061: {'lr': 0.0004904547021776067, 'samples': 2891712, 'steps': 15060, 'loss/train': 1.9347633123397827}
+08/30/2021 15:58:15 - INFO - __main__ - Step 15062: {'lr': 0.0004904532497364432, 'samples': 2891904, 'steps': 15061, 'loss/train': 1.5641708374023438}
+08/30/2021 15:58:15 - INFO - __main__ - Step 15063: {'lr': 0.0004904517971869352, 'samples': 2892096, 'steps': 15062, 'loss/train': 1.079559326171875}
+08/30/2021 15:58:16 - INFO - __main__ - Step 15064: {'lr': 0.0004904503445290833, 'samples': 2892288, 'steps': 15063, 'loss/train': 1.13528573513031}
+08/30/2021 15:58:16 - INFO - __main__ - Step 15065: {'lr': 0.0004904488917628882, 'samples': 2892480, 'steps': 15064, 'loss/train': 2.182119607925415}
+08/30/2021 15:58:18 - INFO - __main__ - Step 15066: {'lr': 0.0004904474388883507, 'samples': 2892672, 'steps': 15065, 'loss/train': 1.4964021444320679}
+08/30/2021 15:58:18 - INFO - __main__ - Step 15067: {'lr': 0.000490445985905471, 'samples': 2892864, 'steps': 15066, 'loss/train': 1.062370777130127}
+08/30/2021 15:58:18 - INFO - __main__ - Step 15068: {'lr': 0.0004904445328142503, 'samples': 2893056, 'steps': 15067, 'loss/train': 0.9581953287124634}
+08/30/2021 15:58:19 - INFO - __main__ - Step 15069: {'lr': 0.0004904430796146889, 'samples': 2893248, 'steps': 15068, 'loss/train': 1.8068184852600098}
+08/30/2021 15:58:19 - INFO - __main__ - Step 15070: {'lr': 0.0004904416263067876, 'samples': 2893440, 'steps': 15069, 'loss/train': 1.8006515502929688}
+08/30/2021 15:58:21 - INFO - __main__ - Step 15071: {'lr': 0.0004904401728905469, 'samples': 2893632, 'steps': 15070, 'loss/train': 1.647088646888733}
+08/30/2021 15:58:22 - INFO - __main__ - Step 15072: {'lr': 0.0004904387193659677, 'samples': 2893824, 'steps': 15071, 'loss/train': 1.7353768348693848}
+08/30/2021 15:58:22 - INFO - __main__ - Step 15073: {'lr': 0.0004904372657330504, 'samples': 2894016, 'steps': 15072, 'loss/train': 1.6333556175231934}
+08/30/2021 15:58:22 - INFO - __main__ - Step 15074: {'lr': 0.0004904358119917959, 'samples': 2894208, 'steps': 15073, 'loss/train': 1.9115346670150757}
+08/30/2021 15:58:23 - INFO - __main__ - Step 15075: {'lr': 0.0004904343581422047, 'samples': 2894400, 'steps': 15074, 'loss/train': 1.6262946128845215}
+08/30/2021 15:58:24 - INFO - __main__ - Step 15076: {'lr': 0.0004904329041842774, 'samples': 2894592, 'steps': 15075, 'loss/train': 2.36826229095459}
+08/30/2021 15:58:25 - INFO - __main__ - Step 15077: {'lr': 0.0004904314501180148, 'samples': 2894784, 'steps': 15076, 'loss/train': 1.9142673015594482}
+08/30/2021 15:58:25 - INFO - __main__ - Step 15078: {'lr': 0.0004904299959434175, 'samples': 2894976, 'steps': 15077, 'loss/train': 1.7328768968582153}
+08/30/2021 15:58:25 - INFO - __main__ - Step 15079: {'lr': 0.0004904285416604862, 'samples': 2895168, 'steps': 15078, 'loss/train': 1.6171680688858032}
+08/30/2021 15:58:26 - INFO - __main__ - Step 15080: {'lr': 0.0004904270872692215, 'samples': 2895360, 'steps': 15079, 'loss/train': 2.092799663543701}
+08/30/2021 15:58:27 - INFO - __main__ - Step 15081: {'lr': 0.0004904256327696241, 'samples': 2895552, 'steps': 15080, 'loss/train': 1.2302974462509155}
+08/30/2021 15:58:28 - INFO - __main__ - Step 15082: {'lr': 0.0004904241781616945, 'samples': 2895744, 'steps': 15081, 'loss/train': 1.1482905149459839}
+08/30/2021 15:58:28 - INFO - __main__ - Step 15083: {'lr': 0.0004904227234454335, 'samples': 2895936, 'steps': 15082, 'loss/train': 1.9209469556808472}
+08/30/2021 15:58:28 - INFO - __main__ - Step 15084: {'lr': 0.0004904212686208418, 'samples': 2896128, 'steps': 15083, 'loss/train': 2.028625011444092}
+08/30/2021 15:58:29 - INFO - __main__ - Step 15085: {'lr': 0.00049041981368792, 'samples': 2896320, 'steps': 15084, 'loss/train': 1.8900392055511475}
+08/30/2021 15:58:29 - INFO - __main__ - Step 15086: {'lr': 0.0004904183586466686, 'samples': 2896512, 'steps': 15085, 'loss/train': 2.02756404876709}
+08/30/2021 15:58:31 - INFO - __main__ - Step 15087: {'lr': 0.0004904169034970885, 'samples': 2896704, 'steps': 15086, 'loss/train': 1.0059603452682495}
+08/30/2021 15:58:31 - INFO - __main__ - Step 15088: {'lr': 0.0004904154482391803, 'samples': 2896896, 'steps': 15087, 'loss/train': 1.565056562423706}
+08/30/2021 15:58:31 - INFO - __main__ - Step 15089: {'lr': 0.0004904139928729445, 'samples': 2897088, 'steps': 15088, 'loss/train': 1.6708370447158813}
+08/30/2021 15:58:32 - INFO - __main__ - Step 15090: {'lr': 0.0004904125373983819, 'samples': 2897280, 'steps': 15089, 'loss/train': 1.9066559076309204}
+08/30/2021 15:58:32 - INFO - __main__ - Step 15091: {'lr': 0.0004904110818154931, 'samples': 2897472, 'steps': 15090, 'loss/train': 1.757454514503479}
+08/30/2021 15:58:33 - INFO - __main__ - Step 15092: {'lr': 0.0004904096261242789, 'samples': 2897664, 'steps': 15091, 'loss/train': 1.1484358310699463}
+08/30/2021 15:58:34 - INFO - __main__ - Step 15093: {'lr': 0.0004904081703247397, 'samples': 2897856, 'steps': 15092, 'loss/train': 1.4675343036651611}
+08/30/2021 15:58:34 - INFO - __main__ - Step 15094: {'lr': 0.0004904067144168763, 'samples': 2898048, 'steps': 15093, 'loss/train': 1.3540998697280884}
+08/30/2021 15:58:35 - INFO - __main__ - Step 15095: {'lr': 0.0004904052584006895, 'samples': 2898240, 'steps': 15094, 'loss/train': 2.115405321121216}
+08/30/2021 15:58:35 - INFO - __main__ - Step 15096: {'lr': 0.0004904038022761797, 'samples': 2898432, 'steps': 15095, 'loss/train': 1.7329566478729248}
+08/30/2021 15:58:36 - INFO - __main__ - Step 15097: {'lr': 0.0004904023460433475, 'samples': 2898624, 'steps': 15096, 'loss/train': 1.617341160774231}
+08/30/2021 15:58:37 - INFO - __main__ - Step 15098: {'lr': 0.0004904008897021939, 'samples': 2898816, 'steps': 15097, 'loss/train': 1.7051061391830444}
+08/30/2021 15:58:37 - INFO - __main__ - Step 15099: {'lr': 0.0004903994332527193, 'samples': 2899008, 'steps': 15098, 'loss/train': 1.9150274991989136}
+08/30/2021 15:58:38 - INFO - __main__ - Step 15100: {'lr': 0.0004903979766949244, 'samples': 2899200, 'steps': 15099, 'loss/train': 2.107600450515747}
+08/30/2021 15:58:38 - INFO - __main__ - Step 15101: {'lr': 0.00049039652002881, 'samples': 2899392, 'steps': 15100, 'loss/train': 2.323913335800171}
+08/30/2021 15:58:39 - INFO - __main__ - Step 15102: {'lr': 0.0004903950632543766, 'samples': 2899584, 'steps': 15101, 'loss/train': 1.8349885940551758}
+08/30/2021 15:58:40 - INFO - __main__ - Step 15103: {'lr': 0.0004903936063716248, 'samples': 2899776, 'steps': 15102, 'loss/train': 1.3465237617492676}
+08/30/2021 15:58:40 - INFO - __main__ - Step 15104: {'lr': 0.0004903921493805554, 'samples': 2899968, 'steps': 15103, 'loss/train': 1.4871973991394043}
+08/30/2021 15:58:41 - INFO - __main__ - Step 15105: {'lr': 0.000490390692281169, 'samples': 2900160, 'steps': 15104, 'loss/train': 1.7064441442489624}
+08/30/2021 15:58:41 - INFO - __main__ - Step 15106: {'lr': 0.0004903892350734663, 'samples': 2900352, 'steps': 15105, 'loss/train': 1.973088264465332}
+08/30/2021 15:58:43 - INFO - __main__ - Step 15107: {'lr': 0.0004903877777574479, 'samples': 2900544, 'steps': 15106, 'loss/train': 1.91025710105896}
+08/30/2021 15:58:43 - INFO - __main__ - Step 15108: {'lr': 0.0004903863203331145, 'samples': 2900736, 'steps': 15107, 'loss/train': 1.796217441558838}
+08/30/2021 15:58:43 - INFO - __main__ - Step 15109: {'lr': 0.0004903848628004667, 'samples': 2900928, 'steps': 15108, 'loss/train': 1.2699918746948242}
+08/30/2021 15:58:44 - INFO - __main__ - Step 15110: {'lr': 0.0004903834051595052, 'samples': 2901120, 'steps': 15109, 'loss/train': 1.7588151693344116}
+08/30/2021 15:58:44 - INFO - __main__ - Step 15111: {'lr': 0.0004903819474102306, 'samples': 2901312, 'steps': 15110, 'loss/train': 1.5148886442184448}
+08/30/2021 15:58:45 - INFO - __main__ - Step 15112: {'lr': 0.0004903804895526437, 'samples': 2901504, 'steps': 15111, 'loss/train': 1.8466156721115112}
+08/30/2021 15:58:46 - INFO - __main__ - Step 15113: {'lr': 0.0004903790315867449, 'samples': 2901696, 'steps': 15112, 'loss/train': 1.7272372245788574}
+08/30/2021 15:58:46 - INFO - __main__ - Step 15114: {'lr': 0.0004903775735125352, 'samples': 2901888, 'steps': 15113, 'loss/train': 1.9933096170425415}
+08/30/2021 15:58:47 - INFO - __main__ - Step 15115: {'lr': 0.0004903761153300149, 'samples': 2902080, 'steps': 15114, 'loss/train': 0.09477217495441437}
+08/30/2021 15:58:47 - INFO - __main__ - Step 15116: {'lr': 0.000490374657039185, 'samples': 2902272, 'steps': 15115, 'loss/train': 1.6263753175735474}
+08/30/2021 15:58:49 - INFO - __main__ - Step 15117: {'lr': 0.0004903731986400459, 'samples': 2902464, 'steps': 15116, 'loss/train': 1.6342326402664185}
+08/30/2021 15:58:50 - INFO - __main__ - Step 15118: {'lr': 0.0004903717401325983, 'samples': 2902656, 'steps': 15117, 'loss/train': 2.0062599182128906}
+08/30/2021 15:58:50 - INFO - __main__ - Step 15119: {'lr': 0.000490370281516843, 'samples': 2902848, 'steps': 15118, 'loss/train': 1.5492897033691406}
+08/30/2021 15:58:50 - INFO - __main__ - Step 15120: {'lr': 0.0004903688227927806, 'samples': 2903040, 'steps': 15119, 'loss/train': 1.9500274658203125}
+08/30/2021 15:58:51 - INFO - __main__ - Step 15121: {'lr': 0.0004903673639604116, 'samples': 2903232, 'steps': 15120, 'loss/train': 1.6372621059417725}
+08/30/2021 15:58:51 - INFO - __main__ - Step 15122: {'lr': 0.0004903659050197369, 'samples': 2903424, 'steps': 15121, 'loss/train': 2.0835390090942383}
+08/30/2021 15:58:51 - INFO - __main__ - Step 15123: {'lr': 0.0004903644459707569, 'samples': 2903616, 'steps': 15122, 'loss/train': 1.7659131288528442}
+08/30/2021 15:58:54 - INFO - __main__ - Step 15124: {'lr': 0.0004903629868134725, 'samples': 2903808, 'steps': 15123, 'loss/train': 1.7020103931427002}
+08/30/2021 15:58:54 - INFO - __main__ - Step 15125: {'lr': 0.0004903615275478841, 'samples': 2904000, 'steps': 15124, 'loss/train': 1.284178614616394}
+08/30/2021 15:58:55 - INFO - __main__ - Step 15126: {'lr': 0.0004903600681739926, 'samples': 2904192, 'steps': 15125, 'loss/train': 0.15328308939933777}
+08/30/2021 15:58:55 - INFO - __main__ - Step 15127: {'lr': 0.0004903586086917986, 'samples': 2904384, 'steps': 15126, 'loss/train': 1.4526680707931519}
+08/30/2021 15:58:55 - INFO - __main__ - Step 15128: {'lr': 0.0004903571491013027, 'samples': 2904576, 'steps': 15127, 'loss/train': 1.530230164527893}
+08/30/2021 15:58:56 - INFO - __main__ - Step 15129: {'lr': 0.0004903556894025055, 'samples': 2904768, 'steps': 15128, 'loss/train': 0.06229347363114357}
+08/30/2021 15:58:57 - INFO - __main__ - Step 15130: {'lr': 0.0004903542295954077, 'samples': 2904960, 'steps': 15129, 'loss/train': 1.8654475212097168}
+08/30/2021 15:58:58 - INFO - __main__ - Step 15131: {'lr': 0.0004903527696800102, 'samples': 2905152, 'steps': 15130, 'loss/train': 1.4783753156661987}
+08/30/2021 15:58:58 - INFO - __main__ - Step 15132: {'lr': 0.0004903513096563133, 'samples': 2905344, 'steps': 15131, 'loss/train': 0.13516157865524292}
+08/30/2021 15:58:59 - INFO - __main__ - Step 15133: {'lr': 0.0004903498495243178, 'samples': 2905536, 'steps': 15132, 'loss/train': 1.6506235599517822}
+08/30/2021 15:58:59 - INFO - __main__ - Step 15134: {'lr': 0.0004903483892840244, 'samples': 2905728, 'steps': 15133, 'loss/train': 4.622920513153076}
+08/30/2021 15:59:00 - INFO - __main__ - Step 15135: {'lr': 0.0004903469289354338, 'samples': 2905920, 'steps': 15134, 'loss/train': 1.3137805461883545}
+08/30/2021 15:59:01 - INFO - __main__ - Step 15136: {'lr': 0.0004903454684785465, 'samples': 2906112, 'steps': 15135, 'loss/train': 1.9431031942367554}
+08/30/2021 15:59:01 - INFO - __main__ - Step 15137: {'lr': 0.0004903440079133633, 'samples': 2906304, 'steps': 15136, 'loss/train': 2.1094818115234375}
+08/30/2021 15:59:02 - INFO - __main__ - Step 15138: {'lr': 0.0004903425472398846, 'samples': 2906496, 'steps': 15137, 'loss/train': 1.6039923429489136}
+08/30/2021 15:59:02 - INFO - __main__ - Step 15139: {'lr': 0.0004903410864581115, 'samples': 2906688, 'steps': 15138, 'loss/train': 2.016150951385498}
+08/30/2021 15:59:02 - INFO - __main__ - Step 15140: {'lr': 0.0004903396255680443, 'samples': 2906880, 'steps': 15139, 'loss/train': 1.7691010236740112}
+08/30/2021 15:59:04 - INFO - __main__ - Step 15141: {'lr': 0.0004903381645696838, 'samples': 2907072, 'steps': 15140, 'loss/train': 0.2667216360569}
+08/30/2021 15:59:04 - INFO - __main__ - Step 15142: {'lr': 0.0004903367034630307, 'samples': 2907264, 'steps': 15141, 'loss/train': 1.5593140125274658}
+08/30/2021 15:59:05 - INFO - __main__ - Step 15143: {'lr': 0.0004903352422480855, 'samples': 2907456, 'steps': 15142, 'loss/train': 1.4108080863952637}
+08/30/2021 15:59:05 - INFO - __main__ - Step 15144: {'lr': 0.000490333780924849, 'samples': 2907648, 'steps': 15143, 'loss/train': 1.7154890298843384}
+08/30/2021 15:59:05 - INFO - __main__ - Step 15145: {'lr': 0.0004903323194933218, 'samples': 2907840, 'steps': 15144, 'loss/train': 1.3250635862350464}
+08/30/2021 15:59:07 - INFO - __main__ - Step 15146: {'lr': 0.0004903308579535045, 'samples': 2908032, 'steps': 15145, 'loss/train': 1.4927868843078613}
+08/30/2021 15:59:07 - INFO - __main__ - Step 15147: {'lr': 0.0004903293963053979, 'samples': 2908224, 'steps': 15146, 'loss/train': 1.4518280029296875}
+08/30/2021 15:59:08 - INFO - __main__ - Step 15148: {'lr': 0.0004903279345490026, 'samples': 2908416, 'steps': 15147, 'loss/train': 1.5175867080688477}
+08/30/2021 15:59:08 - INFO - __main__ - Step 15149: {'lr': 0.0004903264726843191, 'samples': 2908608, 'steps': 15148, 'loss/train': 1.6642018556594849}
+08/30/2021 15:59:08 - INFO - __main__ - Step 15150: {'lr': 0.0004903250107113483, 'samples': 2908800, 'steps': 15149, 'loss/train': 1.3926502466201782}
+08/30/2021 15:59:10 - INFO - __main__ - Step 15151: {'lr': 0.0004903235486300908, 'samples': 2908992, 'steps': 15150, 'loss/train': 1.6689372062683105}
+08/30/2021 15:59:10 - INFO - __main__ - Step 15152: {'lr': 0.0004903220864405471, 'samples': 2909184, 'steps': 15151, 'loss/train': 1.4074832201004028}
+08/30/2021 15:59:11 - INFO - __main__ - Step 15153: {'lr': 0.000490320624142718, 'samples': 2909376, 'steps': 15152, 'loss/train': 1.8029906749725342}
+08/30/2021 15:59:11 - INFO - __main__ - Step 15154: {'lr': 0.0004903191617366043, 'samples': 2909568, 'steps': 15153, 'loss/train': 2.1712491512298584}
+08/30/2021 15:59:12 - INFO - __main__ - Step 15155: {'lr': 0.0004903176992222063, 'samples': 2909760, 'steps': 15154, 'loss/train': 1.6152732372283936}
+08/30/2021 15:59:13 - INFO - __main__ - Step 15156: {'lr': 0.000490316236599525, 'samples': 2909952, 'steps': 15155, 'loss/train': 1.0634926557540894}
+08/30/2021 15:59:14 - INFO - __main__ - Step 15157: {'lr': 0.0004903147738685609, 'samples': 2910144, 'steps': 15156, 'loss/train': 1.811274766921997}
+08/30/2021 15:59:14 - INFO - __main__ - Step 15158: {'lr': 0.0004903133110293145, 'samples': 2910336, 'steps': 15157, 'loss/train': 1.590394139289856}
+08/30/2021 15:59:14 - INFO - __main__ - Step 15159: {'lr': 0.0004903118480817868, 'samples': 2910528, 'steps': 15158, 'loss/train': 1.6736689805984497}
+08/30/2021 15:59:15 - INFO - __main__ - Step 15160: {'lr': 0.0004903103850259781, 'samples': 2910720, 'steps': 15159, 'loss/train': 1.409801721572876}
+08/30/2021 15:59:16 - INFO - __main__ - Step 15161: {'lr': 0.0004903089218618895, 'samples': 2910912, 'steps': 15160, 'loss/train': 1.5411909818649292}
+08/30/2021 15:59:16 - INFO - __main__ - Step 15162: {'lr': 0.0004903074585895212, 'samples': 2911104, 'steps': 15161, 'loss/train': 2.174487590789795}
+08/30/2021 15:59:17 - INFO - __main__ - Step 15163: {'lr': 0.0004903059952088742, 'samples': 2911296, 'steps': 15162, 'loss/train': 1.5213121175765991}
+08/30/2021 15:59:17 - INFO - __main__ - Step 15164: {'lr': 0.0004903045317199489, 'samples': 2911488, 'steps': 15163, 'loss/train': 1.627817153930664}
+08/30/2021 15:59:18 - INFO - __main__ - Step 15165: {'lr': 0.0004903030681227463, 'samples': 2911680, 'steps': 15164, 'loss/train': 1.5124437808990479}
+08/30/2021 15:59:19 - INFO - __main__ - Step 15166: {'lr': 0.0004903016044172666, 'samples': 2911872, 'steps': 15165, 'loss/train': 1.874131441116333}
+08/30/2021 15:59:19 - INFO - __main__ - Step 15167: {'lr': 0.0004903001406035109, 'samples': 2912064, 'steps': 15166, 'loss/train': 1.0103309154510498}
+08/30/2021 15:59:20 - INFO - __main__ - Step 15168: {'lr': 0.0004902986766814795, 'samples': 2912256, 'steps': 15167, 'loss/train': 1.9327702522277832}
+08/30/2021 15:59:20 - INFO - __main__ - Step 15169: {'lr': 0.0004902972126511734, 'samples': 2912448, 'steps': 15168, 'loss/train': 2.031543493270874}
+08/30/2021 15:59:20 - INFO - __main__ - Step 15170: {'lr': 0.0004902957485125929, 'samples': 2912640, 'steps': 15169, 'loss/train': 2.0452992916107178}
+08/30/2021 15:59:21 - INFO - __main__ - Step 15171: {'lr': 0.0004902942842657389, 'samples': 2912832, 'steps': 15170, 'loss/train': 1.6215959787368774}
+08/30/2021 15:59:22 - INFO - __main__ - Step 15172: {'lr': 0.0004902928199106121, 'samples': 2913024, 'steps': 15171, 'loss/train': 1.258383870124817}
+08/30/2021 15:59:23 - INFO - __main__ - Step 15173: {'lr': 0.000490291355447213, 'samples': 2913216, 'steps': 15172, 'loss/train': 1.4947481155395508}
+08/30/2021 15:59:23 - INFO - __main__ - Step 15174: {'lr': 0.0004902898908755424, 'samples': 2913408, 'steps': 15173, 'loss/train': 2.7635366916656494}
+08/30/2021 15:59:23 - INFO - __main__ - Step 15175: {'lr': 0.0004902884261956007, 'samples': 2913600, 'steps': 15174, 'loss/train': 1.5870851278305054}
+08/30/2021 15:59:24 - INFO - __main__ - Step 15176: {'lr': 0.0004902869614073889, 'samples': 2913792, 'steps': 15175, 'loss/train': 1.5923242568969727}
+08/30/2021 15:59:25 - INFO - __main__ - Step 15177: {'lr': 0.0004902854965109074, 'samples': 2913984, 'steps': 15176, 'loss/train': 1.8057106733322144}
+08/30/2021 15:59:26 - INFO - __main__ - Step 15178: {'lr': 0.0004902840315061571, 'samples': 2914176, 'steps': 15177, 'loss/train': 1.4928910732269287}
+08/30/2021 15:59:26 - INFO - __main__ - Step 15179: {'lr': 0.0004902825663931384, 'samples': 2914368, 'steps': 15178, 'loss/train': 1.6890974044799805}
+08/30/2021 15:59:27 - INFO - __main__ - Step 15180: {'lr': 0.0004902811011718521, 'samples': 2914560, 'steps': 15179, 'loss/train': 1.528063416481018}
+08/30/2021 15:59:27 - INFO - __main__ - Step 15181: {'lr': 0.0004902796358422989, 'samples': 2914752, 'steps': 15180, 'loss/train': 2.985886812210083}
+08/30/2021 15:59:27 - INFO - __main__ - Step 15182: {'lr': 0.0004902781704044793, 'samples': 2914944, 'steps': 15181, 'loss/train': 1.86506187915802}
+08/30/2021 15:59:29 - INFO - __main__ - Step 15183: {'lr': 0.0004902767048583942, 'samples': 2915136, 'steps': 15182, 'loss/train': 1.3643348217010498}
+08/30/2021 15:59:30 - INFO - __main__ - Step 15184: {'lr': 0.000490275239204044, 'samples': 2915328, 'steps': 15183, 'loss/train': 1.420096516609192}
+08/30/2021 15:59:30 - INFO - __main__ - Step 15185: {'lr': 0.0004902737734414296, 'samples': 2915520, 'steps': 15184, 'loss/train': 1.7147296667099}
+08/30/2021 15:59:31 - INFO - __main__ - Step 15186: {'lr': 0.0004902723075705514, 'samples': 2915712, 'steps': 15185, 'loss/train': 2.1276416778564453}
+08/30/2021 15:59:31 - INFO - __main__ - Step 15187: {'lr': 0.0004902708415914103, 'samples': 2915904, 'steps': 15186, 'loss/train': 0.7894248366355896}
+08/30/2021 15:59:32 - INFO - __main__ - Step 15188: {'lr': 0.0004902693755040069, 'samples': 2916096, 'steps': 15187, 'loss/train': 1.9741934537887573}
+08/30/2021 15:59:33 - INFO - __main__ - Step 15189: {'lr': 0.0004902679093083418, 'samples': 2916288, 'steps': 15188, 'loss/train': 1.7528294324874878}
+08/30/2021 15:59:33 - INFO - __main__ - Step 15190: {'lr': 0.0004902664430044156, 'samples': 2916480, 'steps': 15189, 'loss/train': 1.6628696918487549}
+08/30/2021 15:59:34 - INFO - __main__ - Step 15191: {'lr': 0.0004902649765922292, 'samples': 2916672, 'steps': 15190, 'loss/train': 1.560943841934204}
+08/30/2021 15:59:34 - INFO - __main__ - Step 15192: {'lr': 0.0004902635100717831, 'samples': 2916864, 'steps': 15191, 'loss/train': 1.5229425430297852}
+08/30/2021 15:59:36 - INFO - __main__ - Step 15193: {'lr': 0.0004902620434430778, 'samples': 2917056, 'steps': 15192, 'loss/train': 2.1835124492645264}
+08/30/2021 15:59:36 - INFO - __main__ - Step 15194: {'lr': 0.0004902605767061142, 'samples': 2917248, 'steps': 15193, 'loss/train': 1.9095793962478638}
+08/30/2021 15:59:36 - INFO - __main__ - Step 15195: {'lr': 0.000490259109860893, 'samples': 2917440, 'steps': 15194, 'loss/train': 1.4937175512313843}
+08/30/2021 15:59:37 - INFO - __main__ - Step 15196: {'lr': 0.0004902576429074146, 'samples': 2917632, 'steps': 15195, 'loss/train': 0.872139036655426}
+08/30/2021 15:59:37 - INFO - __main__ - Step 15197: {'lr': 0.0004902561758456799, 'samples': 2917824, 'steps': 15196, 'loss/train': 1.0893328189849854}
+08/30/2021 15:59:39 - INFO - __main__ - Step 15198: {'lr': 0.0004902547086756895, 'samples': 2918016, 'steps': 15197, 'loss/train': 1.9009952545166016}
+08/30/2021 15:59:39 - INFO - __main__ - Step 15199: {'lr': 0.000490253241397444, 'samples': 2918208, 'steps': 15198, 'loss/train': 1.7882243394851685}
+08/30/2021 15:59:39 - INFO - __main__ - Step 15200: {'lr': 0.0004902517740109441, 'samples': 2918400, 'steps': 15199, 'loss/train': 2.0170230865478516}
+08/30/2021 15:59:40 - INFO - __main__ - Step 15201: {'lr': 0.0004902503065161905, 'samples': 2918592, 'steps': 15200, 'loss/train': 1.1906795501708984}
+08/30/2021 15:59:40 - INFO - __main__ - Step 15202: {'lr': 0.0004902488389131837, 'samples': 2918784, 'steps': 15201, 'loss/train': 1.0520771741867065}
+08/30/2021 15:59:42 - INFO - __main__ - Step 15203: {'lr': 0.0004902473712019246, 'samples': 2918976, 'steps': 15202, 'loss/train': 1.7138489484786987}
+08/30/2021 15:59:42 - INFO - __main__ - Step 15204: {'lr': 0.0004902459033824137, 'samples': 2919168, 'steps': 15203, 'loss/train': 1.5838242769241333}
+08/30/2021 15:59:42 - INFO - __main__ - Step 15205: {'lr': 0.0004902444354546516, 'samples': 2919360, 'steps': 15204, 'loss/train': 1.8327378034591675}
+08/30/2021 15:59:43 - INFO - __main__ - Step 15206: {'lr': 0.0004902429674186392, 'samples': 2919552, 'steps': 15205, 'loss/train': 1.8911542892456055}
+08/30/2021 15:59:43 - INFO - __main__ - Step 15207: {'lr': 0.000490241499274377, 'samples': 2919744, 'steps': 15206, 'loss/train': 1.6966699361801147}
+08/30/2021 15:59:43 - INFO - __main__ - Step 15208: {'lr': 0.0004902400310218657, 'samples': 2919936, 'steps': 15207, 'loss/train': 1.6051431894302368}
+08/30/2021 15:59:45 - INFO - __main__ - Step 15209: {'lr': 0.0004902385626611059, 'samples': 2920128, 'steps': 15208, 'loss/train': 1.5678776502609253}
+08/30/2021 15:59:45 - INFO - __main__ - Step 15210: {'lr': 0.0004902370941920984, 'samples': 2920320, 'steps': 15209, 'loss/train': 1.2162106037139893}
+08/30/2021 15:59:46 - INFO - __main__ - Step 15211: {'lr': 0.0004902356256148437, 'samples': 2920512, 'steps': 15210, 'loss/train': 1.455880045890808}
+08/30/2021 15:59:46 - INFO - __main__ - Step 15212: {'lr': 0.0004902341569293425, 'samples': 2920704, 'steps': 15211, 'loss/train': 1.459934949874878}
+08/30/2021 15:59:46 - INFO - __main__ - Step 15213: {'lr': 0.0004902326881355955, 'samples': 2920896, 'steps': 15212, 'loss/train': 1.446386456489563}
+08/30/2021 15:59:48 - INFO - __main__ - Step 15214: {'lr': 0.0004902312192336034, 'samples': 2921088, 'steps': 15213, 'loss/train': 1.5584096908569336}
+08/30/2021 15:59:48 - INFO - __main__ - Step 15215: {'lr': 0.000490229750223367, 'samples': 2921280, 'steps': 15214, 'loss/train': 0.9233636260032654}
+08/30/2021 15:59:49 - INFO - __main__ - Step 15216: {'lr': 0.0004902282811048864, 'samples': 2921472, 'steps': 15215, 'loss/train': 1.0606367588043213}
+08/30/2021 15:59:49 - INFO - __main__ - Step 15217: {'lr': 0.000490226811878163, 'samples': 2921664, 'steps': 15216, 'loss/train': 1.704091191291809}
+08/30/2021 15:59:50 - INFO - __main__ - Step 15218: {'lr': 0.0004902253425431969, 'samples': 2921856, 'steps': 15217, 'loss/train': 1.7339808940887451}
+08/30/2021 15:59:51 - INFO - __main__ - Step 15219: {'lr': 0.000490223873099989, 'samples': 2922048, 'steps': 15218, 'loss/train': 2.1102333068847656}
+08/30/2021 15:59:51 - INFO - __main__ - Step 15220: {'lr': 0.00049022240354854, 'samples': 2922240, 'steps': 15219, 'loss/train': 1.6153285503387451}
+08/30/2021 15:59:52 - INFO - __main__ - Step 15221: {'lr': 0.0004902209338888503, 'samples': 2922432, 'steps': 15220, 'loss/train': 2.018859386444092}
+08/30/2021 15:59:52 - INFO - __main__ - Step 15222: {'lr': 0.000490219464120921, 'samples': 2922624, 'steps': 15221, 'loss/train': 0.7686914205551147}
+08/30/2021 15:59:53 - INFO - __main__ - Step 15223: {'lr': 0.0004902179942447524, 'samples': 2922816, 'steps': 15222, 'loss/train': 0.8456284999847412}
+08/30/2021 15:59:54 - INFO - __main__ - Step 15224: {'lr': 0.0004902165242603452, 'samples': 2923008, 'steps': 15223, 'loss/train': 1.8118358850479126}
+08/30/2021 15:59:54 - INFO - __main__ - Step 15225: {'lr': 0.0004902150541677003, 'samples': 2923200, 'steps': 15224, 'loss/train': 1.6165413856506348}
+08/30/2021 15:59:55 - INFO - __main__ - Step 15226: {'lr': 0.0004902135839668181, 'samples': 2923392, 'steps': 15225, 'loss/train': 1.4570969343185425}
+08/30/2021 15:59:55 - INFO - __main__ - Step 15227: {'lr': 0.0004902121136576994, 'samples': 2923584, 'steps': 15226, 'loss/train': 2.010981559753418}
+08/30/2021 15:59:55 - INFO - __main__ - Step 15228: {'lr': 0.0004902106432403448, 'samples': 2923776, 'steps': 15227, 'loss/train': 2.0917279720306396}
+08/30/2021 15:59:56 - INFO - __main__ - Step 15229: {'lr': 0.0004902091727147551, 'samples': 2923968, 'steps': 15228, 'loss/train': 1.145888090133667}
+08/30/2021 15:59:57 - INFO - __main__ - Step 15230: {'lr': 0.0004902077020809307, 'samples': 2924160, 'steps': 15229, 'loss/train': 1.5485759973526}
+08/30/2021 15:59:58 - INFO - __main__ - Step 15231: {'lr': 0.0004902062313388725, 'samples': 2924352, 'steps': 15230, 'loss/train': 1.5448799133300781}
+08/30/2021 15:59:58 - INFO - __main__ - Step 15232: {'lr': 0.0004902047604885811, 'samples': 2924544, 'steps': 15231, 'loss/train': 1.6722486019134521}
+08/30/2021 15:59:58 - INFO - __main__ - Step 15233: {'lr': 0.0004902032895300571, 'samples': 2924736, 'steps': 15232, 'loss/train': 1.3838722705841064}
+08/30/2021 15:59:59 - INFO - __main__ - Step 15234: {'lr': 0.0004902018184633012, 'samples': 2924928, 'steps': 15233, 'loss/train': 0.8554103374481201}
+08/30/2021 16:00:01 - INFO - __main__ - Step 15235: {'lr': 0.0004902003472883141, 'samples': 2925120, 'steps': 15234, 'loss/train': 1.9881125688552856}
+08/30/2021 16:00:01 - INFO - __main__ - Step 15236: {'lr': 0.0004901988760050964, 'samples': 2925312, 'steps': 15235, 'loss/train': 1.5846076011657715}
+08/30/2021 16:00:02 - INFO - __main__ - Step 15237: {'lr': 0.0004901974046136488, 'samples': 2925504, 'steps': 15236, 'loss/train': 2.070047378540039}
+08/30/2021 16:00:02 - INFO - __main__ - Step 15238: {'lr': 0.000490195933113972, 'samples': 2925696, 'steps': 15237, 'loss/train': 1.5535564422607422}
+08/30/2021 16:00:02 - INFO - __main__ - Step 15239: {'lr': 0.0004901944615060665, 'samples': 2925888, 'steps': 15238, 'loss/train': 1.2036014795303345}
+08/30/2021 16:00:04 - INFO - __main__ - Step 15240: {'lr': 0.0004901929897899331, 'samples': 2926080, 'steps': 15239, 'loss/train': 1.620802402496338}
+08/30/2021 16:00:05 - INFO - __main__ - Step 15241: {'lr': 0.0004901915179655726, 'samples': 2926272, 'steps': 15240, 'loss/train': 1.8651938438415527}
+08/30/2021 16:00:05 - INFO - __main__ - Step 15242: {'lr': 0.0004901900460329853, 'samples': 2926464, 'steps': 15241, 'loss/train': 1.6313143968582153}
+08/30/2021 16:00:05 - INFO - __main__ - Step 15243: {'lr': 0.0004901885739921723, 'samples': 2926656, 'steps': 15242, 'loss/train': 2.0313265323638916}
+08/30/2021 16:00:06 - INFO - __main__ - Step 15244: {'lr': 0.0004901871018431339, 'samples': 2926848, 'steps': 15243, 'loss/train': 1.65639066696167}
+08/30/2021 16:00:06 - INFO - __main__ - Step 15245: {'lr': 0.0004901856295858708, 'samples': 2927040, 'steps': 15244, 'loss/train': 1.7966381311416626}
+08/30/2021 16:00:08 - INFO - __main__ - Step 15246: {'lr': 0.0004901841572203839, 'samples': 2927232, 'steps': 15245, 'loss/train': 1.388607382774353}
+08/30/2021 16:00:08 - INFO - __main__ - Step 15247: {'lr': 0.0004901826847466738, 'samples': 2927424, 'steps': 15246, 'loss/train': 1.3225113153457642}
+08/30/2021 16:00:09 - INFO - __main__ - Step 15248: {'lr': 0.000490181212164741, 'samples': 2927616, 'steps': 15247, 'loss/train': 1.9013538360595703}
+08/30/2021 16:00:09 - INFO - __main__ - Step 15249: {'lr': 0.0004901797394745861, 'samples': 2927808, 'steps': 15248, 'loss/train': 1.9068899154663086}
+08/30/2021 16:00:09 - INFO - __main__ - Step 15250: {'lr': 0.0004901782666762102, 'samples': 2928000, 'steps': 15249, 'loss/train': 0.07610747218132019}
+08/30/2021 16:00:10 - INFO - __main__ - Step 15251: {'lr': 0.0004901767937696135, 'samples': 2928192, 'steps': 15250, 'loss/train': 1.5153677463531494}
+08/30/2021 16:00:11 - INFO - __main__ - Step 15252: {'lr': 0.0004901753207547969, 'samples': 2928384, 'steps': 15251, 'loss/train': 1.294348955154419}
+08/30/2021 16:00:11 - INFO - __main__ - Step 15253: {'lr': 0.000490173847631761, 'samples': 2928576, 'steps': 15252, 'loss/train': 1.6863707304000854}
+08/30/2021 16:00:12 - INFO - __main__ - Step 15254: {'lr': 0.0004901723744005065, 'samples': 2928768, 'steps': 15253, 'loss/train': 1.673261284828186}
+08/30/2021 16:00:12 - INFO - __main__ - Step 15255: {'lr': 0.0004901709010610339, 'samples': 2928960, 'steps': 15254, 'loss/train': 1.7124124765396118}
+08/30/2021 16:00:12 - INFO - __main__ - Step 15256: {'lr': 0.0004901694276133441, 'samples': 2929152, 'steps': 15255, 'loss/train': 2.0685617923736572}
+08/30/2021 16:00:14 - INFO - __main__ - Step 15257: {'lr': 0.0004901679540574377, 'samples': 2929344, 'steps': 15256, 'loss/train': 1.9410738945007324}
+08/30/2021 16:00:14 - INFO - __main__ - Step 15258: {'lr': 0.0004901664803933153, 'samples': 2929536, 'steps': 15257, 'loss/train': 2.0417656898498535}
+08/30/2021 16:00:15 - INFO - __main__ - Step 15259: {'lr': 0.0004901650066209775, 'samples': 2929728, 'steps': 15258, 'loss/train': 1.6134295463562012}
+08/30/2021 16:00:15 - INFO - __main__ - Step 15260: {'lr': 0.0004901635327404252, 'samples': 2929920, 'steps': 15259, 'loss/train': 1.9462106227874756}
+08/30/2021 16:00:15 - INFO - __main__ - Step 15261: {'lr': 0.0004901620587516587, 'samples': 2930112, 'steps': 15260, 'loss/train': 1.2231272459030151}
+08/30/2021 16:00:17 - INFO - __main__ - Step 15262: {'lr': 0.0004901605846546791, 'samples': 2930304, 'steps': 15261, 'loss/train': 1.6867084503173828}
+08/30/2021 16:00:18 - INFO - __main__ - Step 15263: {'lr': 0.0004901591104494868, 'samples': 2930496, 'steps': 15262, 'loss/train': 1.9147292375564575}
+08/30/2021 16:00:18 - INFO - __main__ - Step 15264: {'lr': 0.0004901576361360825, 'samples': 2930688, 'steps': 15263, 'loss/train': 2.208069086074829}
+08/30/2021 16:00:18 - INFO - __main__ - Step 15265: {'lr': 0.0004901561617144667, 'samples': 2930880, 'steps': 15264, 'loss/train': 1.3121311664581299}
+08/30/2021 16:00:19 - INFO - __main__ - Step 15266: {'lr': 0.0004901546871846405, 'samples': 2931072, 'steps': 15265, 'loss/train': 2.051281690597534}
+08/30/2021 16:00:20 - INFO - __main__ - Step 15267: {'lr': 0.0004901532125466041, 'samples': 2931264, 'steps': 15266, 'loss/train': 0.10278207808732986}
+08/30/2021 16:00:21 - INFO - __main__ - Step 15268: {'lr': 0.0004901517378003584, 'samples': 2931456, 'steps': 15267, 'loss/train': 1.8167712688446045}
+08/30/2021 16:00:21 - INFO - __main__ - Step 15269: {'lr': 0.0004901502629459042, 'samples': 2931648, 'steps': 15268, 'loss/train': 1.5532091856002808}
+08/30/2021 16:00:22 - INFO - __main__ - Step 15270: {'lr': 0.000490148787983242, 'samples': 2931840, 'steps': 15269, 'loss/train': 2.1325762271881104}
+08/30/2021 16:00:22 - INFO - __main__ - Step 15271: {'lr': 0.0004901473129123723, 'samples': 2932032, 'steps': 15270, 'loss/train': 1.9315848350524902}
+08/30/2021 16:00:22 - INFO - __main__ - Step 15272: {'lr': 0.0004901458377332959, 'samples': 2932224, 'steps': 15271, 'loss/train': 0.2822628319263458}
+08/30/2021 16:00:24 - INFO - __main__ - Step 15273: {'lr': 0.0004901443624460136, 'samples': 2932416, 'steps': 15272, 'loss/train': 1.6238374710083008}
+08/30/2021 16:00:24 - INFO - __main__ - Step 15274: {'lr': 0.000490142887050526, 'samples': 2932608, 'steps': 15273, 'loss/train': 2.0749807357788086}
+08/30/2021 16:00:25 - INFO - __main__ - Step 15275: {'lr': 0.0004901414115468335, 'samples': 2932800, 'steps': 15274, 'loss/train': 2.2964682579040527}
+08/30/2021 16:00:25 - INFO - __main__ - Step 15276: {'lr': 0.0004901399359349372, 'samples': 2932992, 'steps': 15275, 'loss/train': 1.9444867372512817}
+08/30/2021 16:00:25 - INFO - __main__ - Step 15277: {'lr': 0.0004901384602148376, 'samples': 2933184, 'steps': 15276, 'loss/train': 1.6872153282165527}
+08/30/2021 16:00:27 - INFO - __main__ - Step 15278: {'lr': 0.0004901369843865351, 'samples': 2933376, 'steps': 15277, 'loss/train': 1.8935812711715698}
+08/30/2021 16:00:27 - INFO - __main__ - Step 15279: {'lr': 0.0004901355084500307, 'samples': 2933568, 'steps': 15278, 'loss/train': 3.2335526943206787}
+08/30/2021 16:00:28 - INFO - __main__ - Step 15280: {'lr': 0.000490134032405325, 'samples': 2933760, 'steps': 15279, 'loss/train': 1.9136563539505005}
+08/30/2021 16:00:28 - INFO - __main__ - Step 15281: {'lr': 0.0004901325562524185, 'samples': 2933952, 'steps': 15280, 'loss/train': 1.8464934825897217}
+08/30/2021 16:00:28 - INFO - __main__ - Step 15282: {'lr': 0.0004901310799913121, 'samples': 2934144, 'steps': 15281, 'loss/train': 1.439648151397705}
+08/30/2021 16:00:30 - INFO - __main__ - Step 15283: {'lr': 0.0004901296036220062, 'samples': 2934336, 'steps': 15282, 'loss/train': 1.7032266855239868}
+08/30/2021 16:00:30 - INFO - __main__ - Step 15284: {'lr': 0.0004901281271445016, 'samples': 2934528, 'steps': 15283, 'loss/train': 1.8631856441497803}
+08/30/2021 16:00:31 - INFO - __main__ - Step 15285: {'lr': 0.000490126650558799, 'samples': 2934720, 'steps': 15284, 'loss/train': 2.1576526165008545}
+08/30/2021 16:00:31 - INFO - __main__ - Step 15286: {'lr': 0.000490125173864899, 'samples': 2934912, 'steps': 15285, 'loss/train': 1.8573395013809204}
+08/30/2021 16:00:31 - INFO - __main__ - Step 15287: {'lr': 0.0004901236970628024, 'samples': 2935104, 'steps': 15286, 'loss/train': 1.9123634099960327}
+08/30/2021 16:00:33 - INFO - __main__ - Step 15288: {'lr': 0.0004901222201525099, 'samples': 2935296, 'steps': 15287, 'loss/train': 2.1508285999298096}
+08/30/2021 16:00:34 - INFO - __main__ - Step 15289: {'lr': 0.0004901207431340218, 'samples': 2935488, 'steps': 15288, 'loss/train': 1.8390781879425049}
+08/30/2021 16:00:34 - INFO - __main__ - Step 15290: {'lr': 0.000490119266007339, 'samples': 2935680, 'steps': 15289, 'loss/train': 1.6442031860351562}
+08/30/2021 16:00:34 - INFO - __main__ - Step 15291: {'lr': 0.0004901177887724623, 'samples': 2935872, 'steps': 15290, 'loss/train': 2.0264084339141846}
+08/30/2021 16:00:35 - INFO - __main__ - Step 15292: {'lr': 0.0004901163114293921, 'samples': 2936064, 'steps': 15291, 'loss/train': 1.4709222316741943}
+08/30/2021 16:00:35 - INFO - __main__ - Step 15293: {'lr': 0.0004901148339781293, 'samples': 2936256, 'steps': 15292, 'loss/train': 1.3401129245758057}
+08/30/2021 16:00:37 - INFO - __main__ - Step 15294: {'lr': 0.0004901133564186744, 'samples': 2936448, 'steps': 15293, 'loss/train': 1.8701170682907104}
+08/30/2021 16:00:38 - INFO - __main__ - Step 15295: {'lr': 0.0004901118787510281, 'samples': 2936640, 'steps': 15294, 'loss/train': 1.311923861503601}
+08/30/2021 16:00:38 - INFO - __main__ - Step 15296: {'lr': 0.0004901104009751912, 'samples': 2936832, 'steps': 15295, 'loss/train': 1.8409775495529175}
+08/30/2021 16:00:39 - INFO - __main__ - Step 15297: {'lr': 0.0004901089230911642, 'samples': 2937024, 'steps': 15296, 'loss/train': 1.8538223505020142}
+08/30/2021 16:00:39 - INFO - __main__ - Step 15298: {'lr': 0.0004901074450989479, 'samples': 2937216, 'steps': 15297, 'loss/train': 1.9554061889648438}
+08/30/2021 16:00:41 - INFO - __main__ - Step 15299: {'lr': 0.0004901059669985427, 'samples': 2937408, 'steps': 15298, 'loss/train': 0.32535094022750854}
+08/30/2021 16:00:41 - INFO - __main__ - Step 15300: {'lr': 0.0004901044887899496, 'samples': 2937600, 'steps': 15299, 'loss/train': 1.4372743368148804}
+08/30/2021 16:00:41 - INFO - __main__ - Step 15301: {'lr': 0.0004901030104731691, 'samples': 2937792, 'steps': 15300, 'loss/train': 1.6454297304153442}
+08/30/2021 16:00:42 - INFO - __main__ - Step 15302: {'lr': 0.0004901015320482019, 'samples': 2937984, 'steps': 15301, 'loss/train': 2.1553637981414795}
+08/30/2021 16:00:42 - INFO - __main__ - Step 15303: {'lr': 0.0004901000535150486, 'samples': 2938176, 'steps': 15302, 'loss/train': 1.8293977975845337}
+08/30/2021 16:00:44 - INFO - __main__ - Step 15304: {'lr': 0.0004900985748737101, 'samples': 2938368, 'steps': 15303, 'loss/train': 2.0799834728240967}
+08/30/2021 16:00:44 - INFO - __main__ - Step 15305: {'lr': 0.0004900970961241866, 'samples': 2938560, 'steps': 15304, 'loss/train': 2.3479645252227783}
+08/30/2021 16:00:45 - INFO - __main__ - Step 15306: {'lr': 0.0004900956172664792, 'samples': 2938752, 'steps': 15305, 'loss/train': 1.979406714439392}
+08/30/2021 16:00:45 - INFO - __main__ - Step 15307: {'lr': 0.0004900941383005884, 'samples': 2938944, 'steps': 15306, 'loss/train': 2.0431814193725586}
+08/30/2021 16:00:45 - INFO - __main__ - Step 15308: {'lr': 0.0004900926592265149, 'samples': 2939136, 'steps': 15307, 'loss/train': 1.457631230354309}
+08/30/2021 16:00:47 - INFO - __main__ - Step 15309: {'lr': 0.0004900911800442593, 'samples': 2939328, 'steps': 15308, 'loss/train': 1.8405603170394897}
+08/30/2021 16:00:47 - INFO - __main__ - Step 15310: {'lr': 0.0004900897007538225, 'samples': 2939520, 'steps': 15309, 'loss/train': 1.909132480621338}
+08/30/2021 16:00:48 - INFO - __main__ - Step 15311: {'lr': 0.0004900882213552049, 'samples': 2939712, 'steps': 15310, 'loss/train': 2.91546893119812}
+08/30/2021 16:00:48 - INFO - __main__ - Step 15312: {'lr': 0.0004900867418484072, 'samples': 2939904, 'steps': 15311, 'loss/train': 1.8374571800231934}
+08/30/2021 16:00:48 - INFO - __main__ - Step 15313: {'lr': 0.0004900852622334301, 'samples': 2940096, 'steps': 15312, 'loss/train': 1.6467686891555786}
+08/30/2021 16:00:49 - INFO - __main__ - Step 15314: {'lr': 0.0004900837825102743, 'samples': 2940288, 'steps': 15313, 'loss/train': 0.1568973809480667}
+08/30/2021 16:00:50 - INFO - __main__ - Step 15315: {'lr': 0.0004900823026789405, 'samples': 2940480, 'steps': 15314, 'loss/train': 1.7074110507965088}
+08/30/2021 16:00:51 - INFO - __main__ - Step 15316: {'lr': 0.0004900808227394293, 'samples': 2940672, 'steps': 15315, 'loss/train': 1.5589522123336792}
+08/30/2021 16:00:51 - INFO - __main__ - Step 15317: {'lr': 0.0004900793426917412, 'samples': 2940864, 'steps': 15316, 'loss/train': 1.637278437614441}
+08/30/2021 16:00:52 - INFO - __main__ - Step 15318: {'lr': 0.0004900778625358774, 'samples': 2941056, 'steps': 15317, 'loss/train': 1.842742919921875}
+08/30/2021 16:00:52 - INFO - __main__ - Step 15319: {'lr': 0.000490076382271838, 'samples': 2941248, 'steps': 15318, 'loss/train': 1.6763697862625122}
+08/30/2021 16:00:53 - INFO - __main__ - Step 15320: {'lr': 0.0004900749018996238, 'samples': 2941440, 'steps': 15319, 'loss/train': 1.5344160795211792}
+08/30/2021 16:00:54 - INFO - __main__ - Step 15321: {'lr': 0.0004900734214192358, 'samples': 2941632, 'steps': 15320, 'loss/train': 2.8766956329345703}
+08/30/2021 16:00:54 - INFO - __main__ - Step 15322: {'lr': 0.0004900719408306743, 'samples': 2941824, 'steps': 15321, 'loss/train': 2.0137224197387695}
+08/30/2021 16:00:54 - INFO - __main__ - Step 15323: {'lr': 0.0004900704601339401, 'samples': 2942016, 'steps': 15322, 'loss/train': 2.109374761581421}
+08/30/2021 16:00:55 - INFO - __main__ - Step 15324: {'lr': 0.0004900689793290339, 'samples': 2942208, 'steps': 15323, 'loss/train': 1.5553075075149536}
+08/30/2021 16:00:56 - INFO - __main__ - Step 15325: {'lr': 0.0004900674984159562, 'samples': 2942400, 'steps': 15324, 'loss/train': 1.4952634572982788}
+08/30/2021 16:00:57 - INFO - __main__ - Step 15326: {'lr': 0.0004900660173947079, 'samples': 2942592, 'steps': 15325, 'loss/train': 0.48776811361312866}
+08/30/2021 16:00:57 - INFO - __main__ - Step 15327: {'lr': 0.0004900645362652895, 'samples': 2942784, 'steps': 15326, 'loss/train': 1.2803184986114502}
+08/30/2021 16:00:57 - INFO - __main__ - Step 15328: {'lr': 0.0004900630550277018, 'samples': 2942976, 'steps': 15327, 'loss/train': 1.2247620820999146}
+08/30/2021 16:00:58 - INFO - __main__ - Step 15329: {'lr': 0.0004900615736819452, 'samples': 2943168, 'steps': 15328, 'loss/train': 1.6304024457931519}
+08/30/2021 16:00:59 - INFO - __main__ - Step 15330: {'lr': 0.0004900600922280207, 'samples': 2943360, 'steps': 15329, 'loss/train': 1.6658141613006592}
+08/30/2021 16:01:00 - INFO - __main__ - Step 15331: {'lr': 0.0004900586106659289, 'samples': 2943552, 'steps': 15330, 'loss/train': 2.2869555950164795}
+08/30/2021 16:01:00 - INFO - __main__ - Step 15332: {'lr': 0.0004900571289956703, 'samples': 2943744, 'steps': 15331, 'loss/train': 1.738834023475647}
+08/30/2021 16:01:01 - INFO - __main__ - Step 15333: {'lr': 0.0004900556472172457, 'samples': 2943936, 'steps': 15332, 'loss/train': 1.7425967454910278}
+08/30/2021 16:01:01 - INFO - __main__ - Step 15334: {'lr': 0.0004900541653306557, 'samples': 2944128, 'steps': 15333, 'loss/train': 1.44273042678833}
+08/30/2021 16:01:02 - INFO - __main__ - Step 15335: {'lr': 0.0004900526833359009, 'samples': 2944320, 'steps': 15334, 'loss/train': 1.672918677330017}
+08/30/2021 16:01:03 - INFO - __main__ - Step 15336: {'lr': 0.0004900512012329822, 'samples': 2944512, 'steps': 15335, 'loss/train': 1.6832565069198608}
+08/30/2021 16:01:03 - INFO - __main__ - Step 15337: {'lr': 0.0004900497190219002, 'samples': 2944704, 'steps': 15336, 'loss/train': 1.8559441566467285}
+08/30/2021 16:01:04 - INFO - __main__ - Step 15338: {'lr': 0.0004900482367026554, 'samples': 2944896, 'steps': 15337, 'loss/train': 1.5720969438552856}
+08/30/2021 16:01:04 - INFO - __main__ - Step 15339: {'lr': 0.0004900467542752485, 'samples': 2945088, 'steps': 15338, 'loss/train': 2.4836173057556152}
+08/30/2021 16:01:04 - INFO - __main__ - Step 15340: {'lr': 0.0004900452717396803, 'samples': 2945280, 'steps': 15339, 'loss/train': 2.947153091430664}
+08/30/2021 16:01:06 - INFO - __main__ - Step 15341: {'lr': 0.0004900437890959515, 'samples': 2945472, 'steps': 15340, 'loss/train': 2.604426145553589}
+08/30/2021 16:01:07 - INFO - __main__ - Step 15342: {'lr': 0.0004900423063440625, 'samples': 2945664, 'steps': 15341, 'loss/train': 2.2659289836883545}
+08/30/2021 16:01:07 - INFO - __main__ - Step 15343: {'lr': 0.0004900408234840142, 'samples': 2945856, 'steps': 15342, 'loss/train': 0.302096426486969}
+08/30/2021 16:01:07 - INFO - __main__ - Step 15344: {'lr': 0.0004900393405158073, 'samples': 2946048, 'steps': 15343, 'loss/train': 1.3263083696365356}
+08/30/2021 16:01:08 - INFO - __main__ - Step 15345: {'lr': 0.0004900378574394423, 'samples': 2946240, 'steps': 15344, 'loss/train': 0.3805118203163147}
+08/30/2021 16:01:10 - INFO - __main__ - Step 15346: {'lr': 0.00049003637425492, 'samples': 2946432, 'steps': 15345, 'loss/train': 2.1891603469848633}
+08/30/2021 16:01:10 - INFO - __main__ - Step 15347: {'lr': 0.0004900348909622409, 'samples': 2946624, 'steps': 15346, 'loss/train': 1.907754898071289}
+08/30/2021 16:01:10 - INFO - __main__ - Step 15348: {'lr': 0.0004900334075614059, 'samples': 2946816, 'steps': 15347, 'loss/train': 2.2687036991119385}
+08/30/2021 16:01:11 - INFO - __main__ - Step 15349: {'lr': 0.0004900319240524155, 'samples': 2947008, 'steps': 15348, 'loss/train': 1.630103349685669}
+08/30/2021 16:01:11 - INFO - __main__ - Step 15350: {'lr': 0.0004900304404352704, 'samples': 2947200, 'steps': 15349, 'loss/train': 1.5954492092132568}
+08/30/2021 16:01:13 - INFO - __main__ - Step 15351: {'lr': 0.0004900289567099713, 'samples': 2947392, 'steps': 15350, 'loss/train': 0.9392467737197876}
+08/30/2021 16:01:13 - INFO - __main__ - Step 15352: {'lr': 0.000490027472876519, 'samples': 2947584, 'steps': 15351, 'loss/train': 1.7012474536895752}
+08/30/2021 16:01:13 - INFO - __main__ - Step 15353: {'lr': 0.0004900259889349138, 'samples': 2947776, 'steps': 15352, 'loss/train': 2.369603395462036}
+08/30/2021 16:01:14 - INFO - __main__ - Step 15354: {'lr': 0.0004900245048851567, 'samples': 2947968, 'steps': 15353, 'loss/train': 2.3797850608825684}
+08/30/2021 16:01:14 - INFO - __main__ - Step 15355: {'lr': 0.0004900230207272483, 'samples': 2948160, 'steps': 15354, 'loss/train': 1.4411885738372803}
+08/30/2021 16:01:16 - INFO - __main__ - Step 15356: {'lr': 0.000490021536461189, 'samples': 2948352, 'steps': 15355, 'loss/train': 1.212572455406189}
+08/30/2021 16:01:16 - INFO - __main__ - Step 15357: {'lr': 0.00049002005208698, 'samples': 2948544, 'steps': 15356, 'loss/train': 1.9965567588806152}
+08/30/2021 16:01:16 - INFO - __main__ - Step 15358: {'lr': 0.0004900185676046214, 'samples': 2948736, 'steps': 15357, 'loss/train': 1.5751240253448486}
+08/30/2021 16:01:17 - INFO - __main__ - Step 15359: {'lr': 0.0004900170830141144, 'samples': 2948928, 'steps': 15358, 'loss/train': 2.052021026611328}
+08/30/2021 16:01:17 - INFO - __main__ - Step 15360: {'lr': 0.0004900155983154592, 'samples': 2949120, 'steps': 15359, 'loss/train': 1.865669846534729}
+08/30/2021 16:01:19 - INFO - __main__ - Step 15361: {'lr': 0.0004900141135086569, 'samples': 2949312, 'steps': 15360, 'loss/train': 1.7544538974761963}
+08/30/2021 16:01:19 - INFO - __main__ - Step 15362: {'lr': 0.0004900126285937077, 'samples': 2949504, 'steps': 15361, 'loss/train': 1.7860257625579834}
+08/30/2021 16:01:19 - INFO - __main__ - Step 15363: {'lr': 0.0004900111435706127, 'samples': 2949696, 'steps': 15362, 'loss/train': 1.7874385118484497}
+08/30/2021 16:01:20 - INFO - __main__ - Step 15364: {'lr': 0.0004900096584393723, 'samples': 2949888, 'steps': 15363, 'loss/train': 2.277987241744995}
+08/30/2021 16:01:20 - INFO - __main__ - Step 15365: {'lr': 0.0004900081731999872, 'samples': 2950080, 'steps': 15364, 'loss/train': 1.8814116716384888}
+08/30/2021 16:01:23 - INFO - __main__ - Step 15366: {'lr': 0.0004900066878524582, 'samples': 2950272, 'steps': 15365, 'loss/train': 1.7960764169692993}
+08/30/2021 16:01:23 - INFO - __main__ - Step 15367: {'lr': 0.0004900052023967859, 'samples': 2950464, 'steps': 15366, 'loss/train': 1.2443969249725342}
+08/30/2021 16:01:23 - INFO - __main__ - Step 15368: {'lr': 0.0004900037168329709, 'samples': 2950656, 'steps': 15367, 'loss/train': 1.445622444152832}
+08/30/2021 16:01:24 - INFO - __main__ - Step 15369: {'lr': 0.000490002231161014, 'samples': 2950848, 'steps': 15368, 'loss/train': 2.6704702377319336}
+08/30/2021 16:01:24 - INFO - __main__ - Step 15370: {'lr': 0.0004900007453809157, 'samples': 2951040, 'steps': 15369, 'loss/train': 3.144233465194702}
+08/30/2021 16:01:25 - INFO - __main__ - Step 15371: {'lr': 0.0004899992594926769, 'samples': 2951232, 'steps': 15370, 'loss/train': 3.3713228702545166}
+08/30/2021 16:01:25 - INFO - __main__ - Step 15372: {'lr': 0.000489997773496298, 'samples': 2951424, 'steps': 15371, 'loss/train': 3.7108395099639893}
+08/30/2021 16:01:25 - INFO - __main__ - Step 15373: {'lr': 0.0004899962873917798, 'samples': 2951616, 'steps': 15372, 'loss/train': 2.2490532398223877}
+08/30/2021 16:01:27 - INFO - __main__ - Step 15374: {'lr': 0.000489994801179123, 'samples': 2951808, 'steps': 15373, 'loss/train': 1.7610284090042114}
+08/30/2021 16:01:27 - INFO - __main__ - Step 15375: {'lr': 0.0004899933148583284, 'samples': 2952000, 'steps': 15374, 'loss/train': 2.233377456665039}
+08/30/2021 16:01:27 - INFO - __main__ - Step 15376: {'lr': 0.0004899918284293964, 'samples': 2952192, 'steps': 15375, 'loss/train': 1.900270938873291}
+08/30/2021 16:01:28 - INFO - __main__ - Step 15377: {'lr': 0.0004899903418923278, 'samples': 2952384, 'steps': 15376, 'loss/train': 1.764028787612915}
+08/30/2021 16:01:28 - INFO - __main__ - Step 15378: {'lr': 0.0004899888552471232, 'samples': 2952576, 'steps': 15377, 'loss/train': 1.6459065675735474}
+08/30/2021 16:01:30 - INFO - __main__ - Step 15379: {'lr': 0.0004899873684937833, 'samples': 2952768, 'steps': 15378, 'loss/train': 1.967921257019043}
+08/30/2021 16:01:30 - INFO - __main__ - Step 15380: {'lr': 0.0004899858816323089, 'samples': 2952960, 'steps': 15379, 'loss/train': 1.7271283864974976}
+08/30/2021 16:01:30 - INFO - __main__ - Step 15381: {'lr': 0.0004899843946627006, 'samples': 2953152, 'steps': 15380, 'loss/train': 1.5563031435012817}
+08/30/2021 16:01:31 - INFO - __main__ - Step 15382: {'lr': 0.0004899829075849589, 'samples': 2953344, 'steps': 15381, 'loss/train': 1.7910250425338745}
+08/30/2021 16:01:31 - INFO - __main__ - Step 15383: {'lr': 0.0004899814203990847, 'samples': 2953536, 'steps': 15382, 'loss/train': 1.7405543327331543}
+08/30/2021 16:01:33 - INFO - __main__ - Step 15384: {'lr': 0.0004899799331050785, 'samples': 2953728, 'steps': 15383, 'loss/train': 2.0326998233795166}
+08/30/2021 16:01:33 - INFO - __main__ - Step 15385: {'lr': 0.0004899784457029411, 'samples': 2953920, 'steps': 15384, 'loss/train': 1.8632278442382812}
+08/30/2021 16:01:34 - INFO - __main__ - Step 15386: {'lr': 0.000489976958192673, 'samples': 2954112, 'steps': 15385, 'loss/train': 1.770098328590393}
+08/30/2021 16:01:34 - INFO - __main__ - Step 15387: {'lr': 0.0004899754705742752, 'samples': 2954304, 'steps': 15386, 'loss/train': 1.867549180984497}
+08/30/2021 16:01:34 - INFO - __main__ - Step 15388: {'lr': 0.0004899739828477481, 'samples': 2954496, 'steps': 15387, 'loss/train': 1.5787196159362793}
+08/30/2021 16:01:36 - INFO - __main__ - Step 15389: {'lr': 0.0004899724950130923, 'samples': 2954688, 'steps': 15388, 'loss/train': 1.854261040687561}
+08/30/2021 16:01:36 - INFO - __main__ - Step 15390: {'lr': 0.0004899710070703087, 'samples': 2954880, 'steps': 15389, 'loss/train': 4.427979946136475}
+08/30/2021 16:01:37 - INFO - __main__ - Step 15391: {'lr': 0.0004899695190193978, 'samples': 2955072, 'steps': 15390, 'loss/train': 1.817335605621338}
+08/30/2021 16:01:37 - INFO - __main__ - Step 15392: {'lr': 0.0004899680308603604, 'samples': 2955264, 'steps': 15391, 'loss/train': 1.8148187398910522}
+08/30/2021 16:01:37 - INFO - __main__ - Step 15393: {'lr': 0.000489966542593197, 'samples': 2955456, 'steps': 15392, 'loss/train': 1.0594487190246582}
+08/30/2021 16:01:39 - INFO - __main__ - Step 15394: {'lr': 0.0004899650542179085, 'samples': 2955648, 'steps': 15393, 'loss/train': 1.8477115631103516}
+08/30/2021 16:01:39 - INFO - __main__ - Step 15395: {'lr': 0.0004899635657344954, 'samples': 2955840, 'steps': 15394, 'loss/train': 0.6730448603630066}
+08/30/2021 16:01:40 - INFO - __main__ - Step 15396: {'lr': 0.0004899620771429585, 'samples': 2956032, 'steps': 15395, 'loss/train': 1.3027268648147583}
+08/30/2021 16:01:40 - INFO - __main__ - Step 15397: {'lr': 0.0004899605884432983, 'samples': 2956224, 'steps': 15396, 'loss/train': 2.2151174545288086}
+08/30/2021 16:01:40 - INFO - __main__ - Step 15398: {'lr': 0.0004899590996355155, 'samples': 2956416, 'steps': 15397, 'loss/train': 1.4743446111679077}
+08/30/2021 16:01:41 - INFO - __main__ - Step 15399: {'lr': 0.000489957610719611, 'samples': 2956608, 'steps': 15398, 'loss/train': 2.064164161682129}
+08/30/2021 16:01:43 - INFO - __main__ - Step 15400: {'lr': 0.0004899561216955852, 'samples': 2956800, 'steps': 15399, 'loss/train': 1.038681149482727}
+08/30/2021 16:01:43 - INFO - __main__ - Step 15401: {'lr': 0.0004899546325634388, 'samples': 2956992, 'steps': 15400, 'loss/train': 1.3875161409378052}
+08/30/2021 16:01:43 - INFO - __main__ - Step 15402: {'lr': 0.0004899531433231728, 'samples': 2957184, 'steps': 15401, 'loss/train': 2.049558639526367}
+08/30/2021 16:01:44 - INFO - __main__ - Step 15403: {'lr': 0.0004899516539747874, 'samples': 2957376, 'steps': 15402, 'loss/train': 2.8670461177825928}
+08/30/2021 16:01:44 - INFO - __main__ - Step 15404: {'lr': 0.0004899501645182835, 'samples': 2957568, 'steps': 15403, 'loss/train': 1.763898491859436}
+08/30/2021 16:01:47 - INFO - __main__ - Step 15405: {'lr': 0.0004899486749536618, 'samples': 2957760, 'steps': 15404, 'loss/train': 1.6202975511550903}
+08/30/2021 16:01:47 - INFO - __main__ - Step 15406: {'lr': 0.000489947185280923, 'samples': 2957952, 'steps': 15405, 'loss/train': 1.525149941444397}
+08/30/2021 16:01:47 - INFO - __main__ - Step 15407: {'lr': 0.0004899456955000676, 'samples': 2958144, 'steps': 15406, 'loss/train': 2.3715343475341797}
+08/30/2021 16:01:48 - INFO - __main__ - Step 15408: {'lr': 0.0004899442056110964, 'samples': 2958336, 'steps': 15407, 'loss/train': 0.917862057685852}
+08/30/2021 16:01:48 - INFO - __main__ - Step 15409: {'lr': 0.00048994271561401, 'samples': 2958528, 'steps': 15408, 'loss/train': 0.7670138478279114}
+08/30/2021 16:01:48 - INFO - __main__ - Step 15410: {'lr': 0.0004899412255088091, 'samples': 2958720, 'steps': 15409, 'loss/train': 0.6514217853546143}
+08/30/2021 16:01:50 - INFO - __main__ - Step 15411: {'lr': 0.0004899397352954945, 'samples': 2958912, 'steps': 15410, 'loss/train': 1.4594303369522095}
+08/30/2021 16:01:50 - INFO - __main__ - Step 15412: {'lr': 0.0004899382449740667, 'samples': 2959104, 'steps': 15411, 'loss/train': 1.6789549589157104}
+08/30/2021 16:01:51 - INFO - __main__ - Step 15413: {'lr': 0.0004899367545445264, 'samples': 2959296, 'steps': 15412, 'loss/train': 1.2324168682098389}
+08/30/2021 16:01:51 - INFO - __main__ - Step 15414: {'lr': 0.0004899352640068743, 'samples': 2959488, 'steps': 15413, 'loss/train': 1.689152717590332}
+08/30/2021 16:01:51 - INFO - __main__ - Step 15415: {'lr': 0.0004899337733611113, 'samples': 2959680, 'steps': 15414, 'loss/train': 2.1103951930999756}
+08/30/2021 16:01:53 - INFO - __main__ - Step 15416: {'lr': 0.0004899322826072375, 'samples': 2959872, 'steps': 15415, 'loss/train': 1.8710706233978271}
+08/30/2021 16:01:54 - INFO - __main__ - Step 15417: {'lr': 0.0004899307917452542, 'samples': 2960064, 'steps': 15416, 'loss/train': 2.642216205596924}
+08/30/2021 16:01:54 - INFO - __main__ - Step 15418: {'lr': 0.0004899293007751616, 'samples': 2960256, 'steps': 15417, 'loss/train': 1.8343582153320312}
+08/30/2021 16:01:54 - INFO - __main__ - Step 15419: {'lr': 0.0004899278096969605, 'samples': 2960448, 'steps': 15418, 'loss/train': 2.05309796333313}
+08/30/2021 16:01:55 - INFO - __main__ - Step 15420: {'lr': 0.0004899263185106518, 'samples': 2960640, 'steps': 15419, 'loss/train': 1.5433604717254639}
+08/30/2021 16:01:55 - INFO - __main__ - Step 15421: {'lr': 0.000489924827216236, 'samples': 2960832, 'steps': 15420, 'loss/train': 2.4911468029022217}
+08/30/2021 16:01:57 - INFO - __main__ - Step 15422: {'lr': 0.0004899233358137137, 'samples': 2961024, 'steps': 15421, 'loss/train': 2.5839223861694336}
+08/30/2021 16:01:57 - INFO - __main__ - Step 15423: {'lr': 0.0004899218443030857, 'samples': 2961216, 'steps': 15422, 'loss/train': 1.6599600315093994}
+08/30/2021 16:01:57 - INFO - __main__ - Step 15424: {'lr': 0.0004899203526843526, 'samples': 2961408, 'steps': 15423, 'loss/train': 2.8455517292022705}
+08/30/2021 16:01:58 - INFO - __main__ - Step 15425: {'lr': 0.000489918860957515, 'samples': 2961600, 'steps': 15424, 'loss/train': 1.2354341745376587}
+08/30/2021 16:01:58 - INFO - __main__ - Step 15426: {'lr': 0.0004899173691225737, 'samples': 2961792, 'steps': 15425, 'loss/train': 1.9968653917312622}
+08/30/2021 16:02:00 - INFO - __main__ - Step 15427: {'lr': 0.0004899158771795295, 'samples': 2961984, 'steps': 15426, 'loss/train': 1.388020634651184}
+08/30/2021 16:02:00 - INFO - __main__ - Step 15428: {'lr': 0.0004899143851283827, 'samples': 2962176, 'steps': 15427, 'loss/train': 1.0337297916412354}
+08/30/2021 16:02:01 - INFO - __main__ - Step 15429: {'lr': 0.0004899128929691343, 'samples': 2962368, 'steps': 15428, 'loss/train': 0.4183272421360016}
+08/30/2021 16:02:01 - INFO - __main__ - Step 15430: {'lr': 0.0004899114007017849, 'samples': 2962560, 'steps': 15429, 'loss/train': 1.970598578453064}
+08/30/2021 16:02:02 - INFO - __main__ - Step 15431: {'lr': 0.000489909908326335, 'samples': 2962752, 'steps': 15430, 'loss/train': 1.612714171409607}
+08/30/2021 16:02:03 - INFO - __main__ - Step 15432: {'lr': 0.0004899084158427855, 'samples': 2962944, 'steps': 15431, 'loss/train': 1.9569873809814453}
+08/30/2021 16:02:03 - INFO - __main__ - Step 15433: {'lr': 0.0004899069232511368, 'samples': 2963136, 'steps': 15432, 'loss/train': 1.9313437938690186}
+08/30/2021 16:02:04 - INFO - __main__ - Step 15434: {'lr': 0.0004899054305513899, 'samples': 2963328, 'steps': 15433, 'loss/train': 1.5398770570755005}
+08/30/2021 16:02:04 - INFO - __main__ - Step 15435: {'lr': 0.0004899039377435452, 'samples': 2963520, 'steps': 15434, 'loss/train': 1.5831071138381958}
+08/30/2021 16:02:04 - INFO - __main__ - Step 15436: {'lr': 0.0004899024448276036, 'samples': 2963712, 'steps': 15435, 'loss/train': 1.657619833946228}
+08/30/2021 16:02:06 - INFO - __main__ - Step 15437: {'lr': 0.0004899009518035657, 'samples': 2963904, 'steps': 15436, 'loss/train': 1.9374465942382812}
+08/30/2021 16:02:06 - INFO - __main__ - Step 15438: {'lr': 0.000489899458671432, 'samples': 2964096, 'steps': 15437, 'loss/train': 1.7268048524856567}
+08/30/2021 16:02:07 - INFO - __main__ - Step 15439: {'lr': 0.0004898979654312034, 'samples': 2964288, 'steps': 15438, 'loss/train': 2.1226131916046143}
+08/30/2021 16:02:07 - INFO - __main__ - Step 15440: {'lr': 0.0004898964720828804, 'samples': 2964480, 'steps': 15439, 'loss/train': 1.9830279350280762}
+08/30/2021 16:02:07 - INFO - __main__ - Step 15441: {'lr': 0.0004898949786264638, 'samples': 2964672, 'steps': 15440, 'loss/train': 1.5021300315856934}
+08/30/2021 16:02:08 - INFO - __main__ - Step 15442: {'lr': 0.0004898934850619542, 'samples': 2964864, 'steps': 15441, 'loss/train': 1.5217854976654053}
+08/30/2021 16:02:09 - INFO - __main__ - Step 15443: {'lr': 0.0004898919913893522, 'samples': 2965056, 'steps': 15442, 'loss/train': 1.356797456741333}
+08/30/2021 16:02:10 - INFO - __main__ - Step 15444: {'lr': 0.0004898904976086588, 'samples': 2965248, 'steps': 15443, 'loss/train': 1.2115391492843628}
+08/30/2021 16:02:10 - INFO - __main__ - Step 15445: {'lr': 0.0004898890037198743, 'samples': 2965440, 'steps': 15444, 'loss/train': 2.0368924140930176}
+08/30/2021 16:02:11 - INFO - __main__ - Step 15446: {'lr': 0.0004898875097229995, 'samples': 2965632, 'steps': 15445, 'loss/train': 1.4779425859451294}
+08/30/2021 16:02:11 - INFO - __main__ - Step 15447: {'lr': 0.0004898860156180351, 'samples': 2965824, 'steps': 15446, 'loss/train': 0.7495663166046143}
+08/30/2021 16:02:12 - INFO - __main__ - Step 15448: {'lr': 0.0004898845214049818, 'samples': 2966016, 'steps': 15447, 'loss/train': 1.6176329851150513}
+08/30/2021 16:02:13 - INFO - __main__ - Step 15449: {'lr': 0.0004898830270838403, 'samples': 2966208, 'steps': 15448, 'loss/train': 1.2131174802780151}
+08/30/2021 16:02:13 - INFO - __main__ - Step 15450: {'lr': 0.0004898815326546111, 'samples': 2966400, 'steps': 15449, 'loss/train': 1.6455386877059937}
+08/30/2021 16:02:14 - INFO - __main__ - Step 15451: {'lr': 0.0004898800381172951, 'samples': 2966592, 'steps': 15450, 'loss/train': 1.2084242105484009}
+08/30/2021 16:02:14 - INFO - __main__ - Step 15452: {'lr': 0.0004898785434718927, 'samples': 2966784, 'steps': 15451, 'loss/train': 1.802215337753296}
+08/30/2021 16:02:16 - INFO - __main__ - Step 15453: {'lr': 0.0004898770487184047, 'samples': 2966976, 'steps': 15452, 'loss/train': 1.7267192602157593}
+08/30/2021 16:02:16 - INFO - __main__ - Step 15454: {'lr': 0.000489875553856832, 'samples': 2967168, 'steps': 15453, 'loss/train': 2.06032133102417}
+08/30/2021 16:02:16 - INFO - __main__ - Step 15455: {'lr': 0.000489874058887175, 'samples': 2967360, 'steps': 15454, 'loss/train': 2.269136428833008}
+08/30/2021 16:02:17 - INFO - __main__ - Step 15456: {'lr': 0.0004898725638094345, 'samples': 2967552, 'steps': 15455, 'loss/train': 1.7237387895584106}
+08/30/2021 16:02:17 - INFO - __main__ - Step 15457: {'lr': 0.0004898710686236109, 'samples': 2967744, 'steps': 15456, 'loss/train': 2.390012264251709}
+08/30/2021 16:02:17 - INFO - __main__ - Step 15458: {'lr': 0.0004898695733297054, 'samples': 2967936, 'steps': 15457, 'loss/train': 1.067933201789856}
+08/30/2021 16:02:19 - INFO - __main__ - Step 15459: {'lr': 0.0004898680779277182, 'samples': 2968128, 'steps': 15458, 'loss/train': 1.0919665098190308}
+08/30/2021 16:02:20 - INFO - __main__ - Step 15460: {'lr': 0.0004898665824176502, 'samples': 2968320, 'steps': 15459, 'loss/train': 1.6166990995407104}
+08/30/2021 16:02:20 - INFO - __main__ - Step 15461: {'lr': 0.000489865086799502, 'samples': 2968512, 'steps': 15460, 'loss/train': 6.107758045196533}
+08/30/2021 16:02:21 - INFO - __main__ - Step 15462: {'lr': 0.0004898635910732743, 'samples': 2968704, 'steps': 15461, 'loss/train': 1.7005637884140015}
+08/30/2021 16:02:21 - INFO - __main__ - Step 15463: {'lr': 0.0004898620952389677, 'samples': 2968896, 'steps': 15462, 'loss/train': 1.6844971179962158}
+08/30/2021 16:02:22 - INFO - __main__ - Step 15464: {'lr': 0.000489860599296583, 'samples': 2969088, 'steps': 15463, 'loss/train': 1.0527204275131226}
+08/30/2021 16:02:23 - INFO - __main__ - Step 15465: {'lr': 0.0004898591032461208, 'samples': 2969280, 'steps': 15464, 'loss/train': 0.9791547060012817}
+08/30/2021 16:02:23 - INFO - __main__ - Step 15466: {'lr': 0.0004898576070875818, 'samples': 2969472, 'steps': 15465, 'loss/train': 1.6744648218154907}
+08/30/2021 16:02:24 - INFO - __main__ - Step 15467: {'lr': 0.0004898561108209667, 'samples': 2969664, 'steps': 15466, 'loss/train': 1.3549813032150269}
+08/30/2021 16:02:24 - INFO - __main__ - Step 15468: {'lr': 0.0004898546144462762, 'samples': 2969856, 'steps': 15467, 'loss/train': 1.7299755811691284}
+08/30/2021 16:02:25 - INFO - __main__ - Step 15469: {'lr': 0.0004898531179635108, 'samples': 2970048, 'steps': 15468, 'loss/train': 2.0573878288269043}
+08/30/2021 16:02:26 - INFO - __main__ - Step 15470: {'lr': 0.0004898516213726712, 'samples': 2970240, 'steps': 15469, 'loss/train': 1.1556767225265503}
+08/30/2021 16:02:26 - INFO - __main__ - Step 15471: {'lr': 0.0004898501246737583, 'samples': 2970432, 'steps': 15470, 'loss/train': 1.9659992456436157}
+08/30/2021 16:02:26 - INFO - __main__ - Step 15472: {'lr': 0.0004898486278667725, 'samples': 2970624, 'steps': 15471, 'loss/train': 2.3629324436187744}
+08/30/2021 16:02:27 - INFO - __main__ - Step 15473: {'lr': 0.0004898471309517148, 'samples': 2970816, 'steps': 15472, 'loss/train': 1.8187549114227295}
+08/30/2021 16:02:29 - INFO - __main__ - Step 15474: {'lr': 0.0004898456339285857, 'samples': 2971008, 'steps': 15473, 'loss/train': 1.479103446006775}
+08/30/2021 16:02:29 - INFO - __main__ - Step 15475: {'lr': 0.0004898441367973856, 'samples': 2971200, 'steps': 15474, 'loss/train': 1.9135509729385376}
+08/30/2021 16:02:30 - INFO - __main__ - Step 15476: {'lr': 0.0004898426395581156, 'samples': 2971392, 'steps': 15475, 'loss/train': 1.8636592626571655}
+08/30/2021 16:02:30 - INFO - __main__ - Step 15477: {'lr': 0.0004898411422107762, 'samples': 2971584, 'steps': 15476, 'loss/train': 1.3952314853668213}
+08/30/2021 16:02:31 - INFO - __main__ - Step 15478: {'lr': 0.0004898396447553681, 'samples': 2971776, 'steps': 15477, 'loss/train': 2.1136181354522705}
+08/30/2021 16:02:31 - INFO - __main__ - Step 15479: {'lr': 0.000489838147191892, 'samples': 2971968, 'steps': 15478, 'loss/train': 1.599002718925476}
+08/30/2021 16:02:31 - INFO - __main__ - Step 15480: {'lr': 0.0004898366495203483, 'samples': 2972160, 'steps': 15479, 'loss/train': 1.0923447608947754}
+08/30/2021 16:02:34 - INFO - __main__ - Step 15481: {'lr': 0.0004898351517407381, 'samples': 2972352, 'steps': 15480, 'loss/train': 0.9394541382789612}
+08/30/2021 16:02:35 - INFO - __main__ - Step 15482: {'lr': 0.0004898336538530619, 'samples': 2972544, 'steps': 15481, 'loss/train': 1.670491337776184}
+08/30/2021 16:02:35 - INFO - __main__ - Step 15483: {'lr': 0.0004898321558573203, 'samples': 2972736, 'steps': 15482, 'loss/train': 1.520904302597046}
+08/30/2021 16:02:35 - INFO - __main__ - Step 15484: {'lr': 0.000489830657753514, 'samples': 2972928, 'steps': 15483, 'loss/train': 0.9412619471549988}
+08/30/2021 16:02:36 - INFO - __main__ - Step 15485: {'lr': 0.0004898291595416438, 'samples': 2973120, 'steps': 15484, 'loss/train': 1.2993401288986206}
+08/30/2021 16:02:36 - INFO - __main__ - Step 15486: {'lr': 0.0004898276612217102, 'samples': 2973312, 'steps': 15485, 'loss/train': 3.5321402549743652}
+08/30/2021 16:02:36 - INFO - __main__ - Step 15487: {'lr': 0.0004898261627937139, 'samples': 2973504, 'steps': 15486, 'loss/train': 4.29628324508667}
+08/30/2021 16:02:37 - INFO - __main__ - Step 15488: {'lr': 0.0004898246642576559, 'samples': 2973696, 'steps': 15487, 'loss/train': 4.206449508666992}
+08/30/2021 16:02:38 - INFO - __main__ - Step 15489: {'lr': 0.0004898231656135362, 'samples': 2973888, 'steps': 15488, 'loss/train': 3.173597812652588}
+08/30/2021 16:02:39 - INFO - __main__ - Step 15490: {'lr': 0.0004898216668613562, 'samples': 2974080, 'steps': 15489, 'loss/train': 2.2753357887268066}
+08/30/2021 16:02:39 - INFO - __main__ - Step 15491: {'lr': 0.0004898201680011161, 'samples': 2974272, 'steps': 15490, 'loss/train': 1.9113277196884155}
+08/30/2021 16:02:39 - INFO - __main__ - Step 15492: {'lr': 0.0004898186690328168, 'samples': 2974464, 'steps': 15491, 'loss/train': 1.8918006420135498}
+08/30/2021 16:02:40 - INFO - __main__ - Step 15493: {'lr': 0.000489817169956459, 'samples': 2974656, 'steps': 15492, 'loss/train': 1.9345825910568237}
+08/30/2021 16:02:42 - INFO - __main__ - Step 15494: {'lr': 0.0004898156707720432, 'samples': 2974848, 'steps': 15493, 'loss/train': 2.1934449672698975}
+08/30/2021 16:02:42 - INFO - __main__ - Step 15495: {'lr': 0.0004898141714795701, 'samples': 2975040, 'steps': 15494, 'loss/train': 1.4573293924331665}
+08/30/2021 16:02:43 - INFO - __main__ - Step 15496: {'lr': 0.0004898126720790405, 'samples': 2975232, 'steps': 15495, 'loss/train': 2.0083725452423096}
+08/30/2021 16:02:43 - INFO - __main__ - Step 15497: {'lr': 0.0004898111725704549, 'samples': 2975424, 'steps': 15496, 'loss/train': 2.119008779525757}
+08/30/2021 16:02:43 - INFO - __main__ - Step 15498: {'lr': 0.0004898096729538142, 'samples': 2975616, 'steps': 15497, 'loss/train': 1.5298768281936646}
+08/30/2021 16:02:44 - INFO - __main__ - Step 15499: {'lr': 0.000489808173229119, 'samples': 2975808, 'steps': 15498, 'loss/train': 2.387995958328247}
+08/30/2021 16:02:44 - INFO - __main__ - Step 15500: {'lr': 0.0004898066733963699, 'samples': 2976000, 'steps': 15499, 'loss/train': 1.9597584009170532}
+08/30/2021 16:02:45 - INFO - __main__ - Step 15501: {'lr': 0.0004898051734555676, 'samples': 2976192, 'steps': 15500, 'loss/train': 2.040754795074463}
+08/30/2021 16:02:46 - INFO - __main__ - Step 15502: {'lr': 0.0004898036734067127, 'samples': 2976384, 'steps': 15501, 'loss/train': 1.9665862321853638}
+08/30/2021 16:02:46 - INFO - __main__ - Step 15503: {'lr': 0.000489802173249806, 'samples': 2976576, 'steps': 15502, 'loss/train': 1.9422433376312256}
+08/30/2021 16:02:47 - INFO - __main__ - Step 15504: {'lr': 0.0004898006729848482, 'samples': 2976768, 'steps': 15503, 'loss/train': 2.226653575897217}
+08/30/2021 16:02:47 - INFO - __main__ - Step 15505: {'lr': 0.0004897991726118399, 'samples': 2976960, 'steps': 15504, 'loss/train': 2.4603707790374756}
+08/30/2021 16:02:49 - INFO - __main__ - Step 15506: {'lr': 0.0004897976721307818, 'samples': 2977152, 'steps': 15505, 'loss/train': 1.1228480339050293}
+08/30/2021 16:02:49 - INFO - __main__ - Step 15507: {'lr': 0.0004897961715416746, 'samples': 2977344, 'steps': 15506, 'loss/train': 1.8973417282104492}
+08/30/2021 16:02:50 - INFO - __main__ - Step 15508: {'lr': 0.0004897946708445189, 'samples': 2977536, 'steps': 15507, 'loss/train': 4.241513729095459}
+08/30/2021 16:02:50 - INFO - __main__ - Step 15509: {'lr': 0.0004897931700393154, 'samples': 2977728, 'steps': 15508, 'loss/train': 2.953615665435791}
+08/30/2021 16:02:50 - INFO - __main__ - Step 15510: {'lr': 0.0004897916691260648, 'samples': 2977920, 'steps': 15509, 'loss/train': 2.6631486415863037}
+08/30/2021 16:02:51 - INFO - __main__ - Step 15511: {'lr': 0.0004897901681047679, 'samples': 2978112, 'steps': 15510, 'loss/train': 1.7656136751174927}
+08/30/2021 16:02:53 - INFO - __main__ - Step 15512: {'lr': 0.0004897886669754251, 'samples': 2978304, 'steps': 15511, 'loss/train': 1.8558725118637085}
+08/30/2021 16:02:53 - INFO - __main__ - Step 15513: {'lr': 0.0004897871657380373, 'samples': 2978496, 'steps': 15512, 'loss/train': 2.337657928466797}
+08/30/2021 16:02:54 - INFO - __main__ - Step 15514: {'lr': 0.0004897856643926051, 'samples': 2978688, 'steps': 15513, 'loss/train': 2.785068988800049}
+08/30/2021 16:02:54 - INFO - __main__ - Step 15515: {'lr': 0.0004897841629391291, 'samples': 2978880, 'steps': 15514, 'loss/train': 2.09179949760437}
+08/30/2021 16:02:54 - INFO - __main__ - Step 15516: {'lr': 0.0004897826613776101, 'samples': 2979072, 'steps': 15515, 'loss/train': 2.7315292358398438}
+08/30/2021 16:02:56 - INFO - __main__ - Step 15517: {'lr': 0.0004897811597080488, 'samples': 2979264, 'steps': 15516, 'loss/train': 2.242156744003296}
+08/30/2021 16:02:56 - INFO - __main__ - Step 15518: {'lr': 0.0004897796579304458, 'samples': 2979456, 'steps': 15517, 'loss/train': 2.1583588123321533}
+08/30/2021 16:02:57 - INFO - __main__ - Step 15519: {'lr': 0.0004897781560448017, 'samples': 2979648, 'steps': 15518, 'loss/train': 1.82471764087677}
+08/30/2021 16:02:57 - INFO - __main__ - Step 15520: {'lr': 0.0004897766540511173, 'samples': 2979840, 'steps': 15519, 'loss/train': 0.4177507758140564}
+08/30/2021 16:02:57 - INFO - __main__ - Step 15521: {'lr': 0.0004897751519493933, 'samples': 2980032, 'steps': 15520, 'loss/train': 2.0823662281036377}
+08/30/2021 16:02:58 - INFO - __main__ - Step 15522: {'lr': 0.0004897736497396303, 'samples': 2980224, 'steps': 15521, 'loss/train': 2.7419381141662598}
+08/30/2021 16:03:00 - INFO - __main__ - Step 15523: {'lr': 0.000489772147421829, 'samples': 2980416, 'steps': 15522, 'loss/train': 2.4459147453308105}
+08/30/2021 16:03:00 - INFO - __main__ - Step 15524: {'lr': 0.0004897706449959899, 'samples': 2980608, 'steps': 15523, 'loss/train': 2.3358840942382812}
+08/30/2021 16:03:00 - INFO - __main__ - Step 15525: {'lr': 0.000489769142462114, 'samples': 2980800, 'steps': 15524, 'loss/train': 1.6837490797042847}
+08/30/2021 16:03:01 - INFO - __main__ - Step 15526: {'lr': 0.0004897676398202018, 'samples': 2980992, 'steps': 15525, 'loss/train': 2.7207229137420654}
+08/30/2021 16:03:01 - INFO - __main__ - Step 15527: {'lr': 0.000489766137070254, 'samples': 2981184, 'steps': 15526, 'loss/train': 1.6504679918289185}
+08/30/2021 16:03:02 - INFO - __main__ - Step 15528: {'lr': 0.0004897646342122713, 'samples': 2981376, 'steps': 15527, 'loss/train': 0.8819839954376221}
+08/30/2021 16:03:03 - INFO - __main__ - Step 15529: {'lr': 0.0004897631312462544, 'samples': 2981568, 'steps': 15528, 'loss/train': 1.7353520393371582}
+08/30/2021 16:03:03 - INFO - __main__ - Step 15530: {'lr': 0.0004897616281722038, 'samples': 2981760, 'steps': 15529, 'loss/train': 2.0722784996032715}
+08/30/2021 16:03:04 - INFO - __main__ - Step 15531: {'lr': 0.0004897601249901204, 'samples': 2981952, 'steps': 15530, 'loss/train': 1.614208698272705}
+08/30/2021 16:03:04 - INFO - __main__ - Step 15532: {'lr': 0.0004897586217000047, 'samples': 2982144, 'steps': 15531, 'loss/train': 2.2137129306793213}
+08/30/2021 16:03:06 - INFO - __main__ - Step 15533: {'lr': 0.0004897571183018576, 'samples': 2982336, 'steps': 15532, 'loss/train': 2.5601062774658203}
+08/30/2021 16:03:06 - INFO - __main__ - Step 15534: {'lr': 0.0004897556147956796, 'samples': 2982528, 'steps': 15533, 'loss/train': 1.969010591506958}
+08/30/2021 16:03:06 - INFO - __main__ - Step 15535: {'lr': 0.0004897541111814714, 'samples': 2982720, 'steps': 15534, 'loss/train': 1.4815599918365479}
+08/30/2021 16:03:07 - INFO - __main__ - Step 15536: {'lr': 0.0004897526074592337, 'samples': 2982912, 'steps': 15535, 'loss/train': 2.658247470855713}
+08/30/2021 16:03:07 - INFO - __main__ - Step 15537: {'lr': 0.0004897511036289671, 'samples': 2983104, 'steps': 15536, 'loss/train': 1.8597320318222046}
+08/30/2021 16:03:09 - INFO - __main__ - Step 15538: {'lr': 0.0004897495996906725, 'samples': 2983296, 'steps': 15537, 'loss/train': 1.9959858655929565}
+08/30/2021 16:03:09 - INFO - __main__ - Step 15539: {'lr': 0.0004897480956443503, 'samples': 2983488, 'steps': 15538, 'loss/train': 1.9335285425186157}
+08/30/2021 16:03:10 - INFO - __main__ - Step 15540: {'lr': 0.0004897465914900013, 'samples': 2983680, 'steps': 15539, 'loss/train': 2.258700370788574}
+08/30/2021 16:03:10 - INFO - __main__ - Step 15541: {'lr': 0.0004897450872276263, 'samples': 2983872, 'steps': 15540, 'loss/train': 1.6229095458984375}
+08/30/2021 16:03:10 - INFO - __main__ - Step 15542: {'lr': 0.0004897435828572258, 'samples': 2984064, 'steps': 15541, 'loss/train': 1.8740934133529663}
+08/30/2021 16:03:11 - INFO - __main__ - Step 15543: {'lr': 0.0004897420783788006, 'samples': 2984256, 'steps': 15542, 'loss/train': 0.48658761382102966}
+08/30/2021 16:03:12 - INFO - __main__ - Step 15544: {'lr': 0.0004897405737923511, 'samples': 2984448, 'steps': 15543, 'loss/train': 1.3301993608474731}
+08/30/2021 16:03:13 - INFO - __main__ - Step 15545: {'lr': 0.0004897390690978785, 'samples': 2984640, 'steps': 15544, 'loss/train': 2.144516944885254}
+08/30/2021 16:03:13 - INFO - __main__ - Step 15546: {'lr': 0.000489737564295383, 'samples': 2984832, 'steps': 15545, 'loss/train': 1.8909426927566528}
+08/30/2021 16:03:13 - INFO - __main__ - Step 15547: {'lr': 0.0004897360593848655, 'samples': 2985024, 'steps': 15546, 'loss/train': 2.0608294010162354}
+08/30/2021 16:03:14 - INFO - __main__ - Step 15548: {'lr': 0.0004897345543663266, 'samples': 2985216, 'steps': 15547, 'loss/train': 1.966789722442627}
+08/30/2021 16:03:15 - INFO - __main__ - Step 15549: {'lr': 0.000489733049239767, 'samples': 2985408, 'steps': 15548, 'loss/train': 2.0603878498077393}
+08/30/2021 16:03:16 - INFO - __main__ - Step 15550: {'lr': 0.0004897315440051874, 'samples': 2985600, 'steps': 15549, 'loss/train': 1.5398551225662231}
+08/30/2021 16:03:16 - INFO - __main__ - Step 15551: {'lr': 0.0004897300386625885, 'samples': 2985792, 'steps': 15550, 'loss/train': 1.3343030214309692}
+08/30/2021 16:03:16 - INFO - __main__ - Step 15552: {'lr': 0.0004897285332119709, 'samples': 2985984, 'steps': 15551, 'loss/train': 1.5717535018920898}
+08/30/2021 16:03:17 - INFO - __main__ - Step 15553: {'lr': 0.0004897270276533355, 'samples': 2986176, 'steps': 15552, 'loss/train': 1.6205661296844482}
+08/30/2021 16:03:18 - INFO - __main__ - Step 15554: {'lr': 0.0004897255219866825, 'samples': 2986368, 'steps': 15553, 'loss/train': 1.9927802085876465}
+08/30/2021 16:03:19 - INFO - __main__ - Step 15555: {'lr': 0.000489724016212013, 'samples': 2986560, 'steps': 15554, 'loss/train': 2.115006446838379}
+08/30/2021 16:03:19 - INFO - __main__ - Step 15556: {'lr': 0.0004897225103293277, 'samples': 2986752, 'steps': 15555, 'loss/train': 1.4051820039749146}
+08/30/2021 16:03:19 - INFO - __main__ - Step 15557: {'lr': 0.0004897210043386269, 'samples': 2986944, 'steps': 15556, 'loss/train': 1.575562834739685}
+08/30/2021 16:03:20 - INFO - __main__ - Step 15558: {'lr': 0.0004897194982399117, 'samples': 2987136, 'steps': 15557, 'loss/train': 1.874578595161438}
+08/30/2021 16:03:21 - INFO - __main__ - Step 15559: {'lr': 0.0004897179920331826, 'samples': 2987328, 'steps': 15558, 'loss/train': 1.6472991704940796}
+08/30/2021 16:03:22 - INFO - __main__ - Step 15560: {'lr': 0.0004897164857184401, 'samples': 2987520, 'steps': 15559, 'loss/train': 1.7609413862228394}
+08/30/2021 16:03:22 - INFO - __main__ - Step 15561: {'lr': 0.0004897149792956852, 'samples': 2987712, 'steps': 15560, 'loss/train': 2.2637219429016113}
+08/30/2021 16:03:22 - INFO - __main__ - Step 15562: {'lr': 0.0004897134727649184, 'samples': 2987904, 'steps': 15561, 'loss/train': 1.636091947555542}
+08/30/2021 16:03:23 - INFO - __main__ - Step 15563: {'lr': 0.0004897119661261403, 'samples': 2988096, 'steps': 15562, 'loss/train': 1.4694645404815674}
+08/30/2021 16:03:24 - INFO - __main__ - Step 15564: {'lr': 0.0004897104593793518, 'samples': 2988288, 'steps': 15563, 'loss/train': 1.817311406135559}
+08/30/2021 16:03:25 - INFO - __main__ - Step 15565: {'lr': 0.0004897089525245535, 'samples': 2988480, 'steps': 15564, 'loss/train': 2.0266592502593994}
+08/30/2021 16:03:25 - INFO - __main__ - Step 15566: {'lr': 0.000489707445561746, 'samples': 2988672, 'steps': 15565, 'loss/train': 1.5361164808273315}
+08/30/2021 16:03:25 - INFO - __main__ - Step 15567: {'lr': 0.0004897059384909299, 'samples': 2988864, 'steps': 15566, 'loss/train': 2.2441718578338623}
+08/30/2021 16:03:26 - INFO - __main__ - Step 15568: {'lr': 0.0004897044313121061, 'samples': 2989056, 'steps': 15567, 'loss/train': 1.7525969743728638}
+08/30/2021 16:03:28 - INFO - __main__ - Step 15569: {'lr': 0.0004897029240252753, 'samples': 2989248, 'steps': 15568, 'loss/train': 2.4664337635040283}
+08/30/2021 16:03:28 - INFO - __main__ - Step 15570: {'lr': 0.000489701416630438, 'samples': 2989440, 'steps': 15569, 'loss/train': 1.9209808111190796}
+08/30/2021 16:03:29 - INFO - __main__ - Step 15571: {'lr': 0.0004896999091275948, 'samples': 2989632, 'steps': 15570, 'loss/train': 0.6832961440086365}
+08/30/2021 16:03:29 - INFO - __main__ - Step 15572: {'lr': 0.0004896984015167466, 'samples': 2989824, 'steps': 15571, 'loss/train': 1.6293202638626099}
+08/30/2021 16:03:29 - INFO - __main__ - Step 15573: {'lr': 0.0004896968937978941, 'samples': 2990016, 'steps': 15572, 'loss/train': 1.7801684141159058}
+08/30/2021 16:03:31 - INFO - __main__ - Step 15574: {'lr': 0.0004896953859710379, 'samples': 2990208, 'steps': 15573, 'loss/train': 1.8957176208496094}
+08/30/2021 16:03:31 - INFO - __main__ - Step 15575: {'lr': 0.0004896938780361784, 'samples': 2990400, 'steps': 15574, 'loss/train': 1.351629614830017}
+08/30/2021 16:03:32 - INFO - __main__ - Step 15576: {'lr': 0.0004896923699933167, 'samples': 2990592, 'steps': 15575, 'loss/train': 1.7757244110107422}
+08/30/2021 16:03:32 - INFO - __main__ - Step 15577: {'lr': 0.0004896908618424533, 'samples': 2990784, 'steps': 15576, 'loss/train': 0.904737651348114}
+08/30/2021 16:03:32 - INFO - __main__ - Step 15578: {'lr': 0.0004896893535835889, 'samples': 2990976, 'steps': 15577, 'loss/train': 1.9108182191848755}
+08/30/2021 16:03:34 - INFO - __main__ - Step 15579: {'lr': 0.0004896878452167241, 'samples': 2991168, 'steps': 15578, 'loss/train': 1.9039455652236938}
+08/30/2021 16:03:35 - INFO - __main__ - Step 15580: {'lr': 0.0004896863367418598, 'samples': 2991360, 'steps': 15579, 'loss/train': 1.4533703327178955}
+08/30/2021 16:03:35 - INFO - __main__ - Step 15581: {'lr': 0.0004896848281589966, 'samples': 2991552, 'steps': 15580, 'loss/train': 1.8411744832992554}
+08/30/2021 16:03:35 - INFO - __main__ - Step 15582: {'lr': 0.0004896833194681349, 'samples': 2991744, 'steps': 15581, 'loss/train': 1.028562307357788}
+08/30/2021 16:03:36 - INFO - __main__ - Step 15583: {'lr': 0.0004896818106692757, 'samples': 2991936, 'steps': 15582, 'loss/train': 1.3289109468460083}
+08/30/2021 16:03:36 - INFO - __main__ - Step 15584: {'lr': 0.0004896803017624196, 'samples': 2992128, 'steps': 15583, 'loss/train': 2.1643829345703125}
+08/30/2021 16:03:38 - INFO - __main__ - Step 15585: {'lr': 0.0004896787927475671, 'samples': 2992320, 'steps': 15584, 'loss/train': 1.8471970558166504}
+08/30/2021 16:03:38 - INFO - __main__ - Step 15586: {'lr': 0.0004896772836247192, 'samples': 2992512, 'steps': 15585, 'loss/train': 0.6814278960227966}
+08/30/2021 16:03:38 - INFO - __main__ - Step 15587: {'lr': 0.0004896757743938764, 'samples': 2992704, 'steps': 15586, 'loss/train': 1.236244559288025}
+08/30/2021 16:03:39 - INFO - __main__ - Step 15588: {'lr': 0.0004896742650550393, 'samples': 2992896, 'steps': 15587, 'loss/train': 0.9975184202194214}
+08/30/2021 16:03:39 - INFO - __main__ - Step 15589: {'lr': 0.0004896727556082086, 'samples': 2993088, 'steps': 15588, 'loss/train': 1.2266881465911865}
+08/30/2021 16:03:41 - INFO - __main__ - Step 15590: {'lr': 0.0004896712460533854, 'samples': 2993280, 'steps': 15589, 'loss/train': 1.6080315113067627}
+08/30/2021 16:03:41 - INFO - __main__ - Step 15591: {'lr': 0.0004896697363905697, 'samples': 2993472, 'steps': 15590, 'loss/train': 1.8571051359176636}
+08/30/2021 16:03:41 - INFO - __main__ - Step 15592: {'lr': 0.0004896682266197626, 'samples': 2993664, 'steps': 15591, 'loss/train': 1.597836971282959}
+08/30/2021 16:03:42 - INFO - __main__ - Step 15593: {'lr': 0.0004896667167409648, 'samples': 2993856, 'steps': 15592, 'loss/train': 1.7377614974975586}
+08/30/2021 16:03:42 - INFO - __main__ - Step 15594: {'lr': 0.0004896652067541767, 'samples': 2994048, 'steps': 15593, 'loss/train': 2.089097738265991}
+08/30/2021 16:03:44 - INFO - __main__ - Step 15595: {'lr': 0.0004896636966593993, 'samples': 2994240, 'steps': 15594, 'loss/train': 1.5005847215652466}
+08/30/2021 16:03:44 - INFO - __main__ - Step 15596: {'lr': 0.0004896621864566331, 'samples': 2994432, 'steps': 15595, 'loss/train': 1.8175733089447021}
+08/30/2021 16:03:44 - INFO - __main__ - Step 15597: {'lr': 0.0004896606761458788, 'samples': 2994624, 'steps': 15596, 'loss/train': 2.0225472450256348}
+08/30/2021 16:03:45 - INFO - __main__ - Step 15598: {'lr': 0.0004896591657271371, 'samples': 2994816, 'steps': 15597, 'loss/train': 1.8359782695770264}
+08/30/2021 16:03:45 - INFO - __main__ - Step 15599: {'lr': 0.0004896576552004087, 'samples': 2995008, 'steps': 15598, 'loss/train': 1.9440196752548218}
+08/30/2021 16:03:47 - INFO - __main__ - Step 15600: {'lr': 0.0004896561445656943, 'samples': 2995200, 'steps': 15599, 'loss/train': 1.7889635562896729}
+08/30/2021 16:03:47 - INFO - __main__ - Step 15601: {'lr': 0.0004896546338229945, 'samples': 2995392, 'steps': 15600, 'loss/train': 1.71900475025177}
+08/30/2021 16:03:47 - INFO - __main__ - Step 15602: {'lr': 0.00048965312297231, 'samples': 2995584, 'steps': 15601, 'loss/train': 1.3022347688674927}
+08/30/2021 16:03:48 - INFO - __main__ - Step 15603: {'lr': 0.0004896516120136415, 'samples': 2995776, 'steps': 15602, 'loss/train': 1.4900071620941162}
+08/30/2021 16:03:48 - INFO - __main__ - Step 15604: {'lr': 0.0004896501009469896, 'samples': 2995968, 'steps': 15603, 'loss/train': 1.9007580280303955}
+08/30/2021 16:03:50 - INFO - __main__ - Step 15605: {'lr': 0.0004896485897723552, 'samples': 2996160, 'steps': 15604, 'loss/train': 1.6240850687026978}
+08/30/2021 16:03:50 - INFO - __main__ - Step 15606: {'lr': 0.0004896470784897388, 'samples': 2996352, 'steps': 15605, 'loss/train': 1.648932933807373}
+08/30/2021 16:03:50 - INFO - __main__ - Step 15607: {'lr': 0.0004896455670991411, 'samples': 2996544, 'steps': 15606, 'loss/train': 2.3295695781707764}
+08/30/2021 16:03:51 - INFO - __main__ - Step 15608: {'lr': 0.0004896440556005628, 'samples': 2996736, 'steps': 15607, 'loss/train': 1.33921480178833}
+08/30/2021 16:03:51 - INFO - __main__ - Step 15609: {'lr': 0.0004896425439940047, 'samples': 2996928, 'steps': 15608, 'loss/train': 2.26648211479187}
+08/30/2021 16:03:52 - INFO - __main__ - Step 15610: {'lr': 0.0004896410322794673, 'samples': 2997120, 'steps': 15609, 'loss/train': 2.101055145263672}
+08/30/2021 16:03:53 - INFO - __main__ - Step 15611: {'lr': 0.0004896395204569512, 'samples': 2997312, 'steps': 15610, 'loss/train': 1.5403823852539062}
+08/30/2021 16:03:54 - INFO - __main__ - Step 15612: {'lr': 0.0004896380085264573, 'samples': 2997504, 'steps': 15611, 'loss/train': 1.9643793106079102}
+08/30/2021 16:03:54 - INFO - __main__ - Step 15613: {'lr': 0.0004896364964879864, 'samples': 2997696, 'steps': 15612, 'loss/train': 1.3354697227478027}
+08/30/2021 16:03:54 - INFO - __main__ - Step 15614: {'lr': 0.0004896349843415389, 'samples': 2997888, 'steps': 15613, 'loss/train': 1.8205819129943848}
+08/30/2021 16:03:55 - INFO - __main__ - Step 15615: {'lr': 0.0004896334720871156, 'samples': 2998080, 'steps': 15614, 'loss/train': 1.1578238010406494}
+08/30/2021 16:03:57 - INFO - __main__ - Step 15616: {'lr': 0.0004896319597247169, 'samples': 2998272, 'steps': 15615, 'loss/train': 1.310843586921692}
+08/30/2021 16:03:57 - INFO - __main__ - Step 15617: {'lr': 0.0004896304472543439, 'samples': 2998464, 'steps': 15616, 'loss/train': 1.4455901384353638}
+08/30/2021 16:03:57 - INFO - __main__ - Step 15618: {'lr': 0.0004896289346759973, 'samples': 2998656, 'steps': 15617, 'loss/train': 2.1688995361328125}
+08/30/2021 16:03:58 - INFO - __main__ - Step 15619: {'lr': 0.0004896274219896773, 'samples': 2998848, 'steps': 15618, 'loss/train': 1.1482386589050293}
+08/30/2021 16:03:58 - INFO - __main__ - Step 15620: {'lr': 0.000489625909195385, 'samples': 2999040, 'steps': 15619, 'loss/train': 1.9774795770645142}
+08/30/2021 16:04:00 - INFO - __main__ - Step 15621: {'lr': 0.0004896243962931211, 'samples': 2999232, 'steps': 15620, 'loss/train': 1.5860469341278076}
+08/30/2021 16:04:01 - INFO - __main__ - Step 15622: {'lr': 0.0004896228832828861, 'samples': 2999424, 'steps': 15621, 'loss/train': 1.7794502973556519}
+08/30/2021 16:04:01 - INFO - __main__ - Step 15623: {'lr': 0.0004896213701646806, 'samples': 2999616, 'steps': 15622, 'loss/train': 1.5514764785766602}
+08/30/2021 16:04:01 - INFO - __main__ - Step 15624: {'lr': 0.0004896198569385055, 'samples': 2999808, 'steps': 15623, 'loss/train': 1.6653560400009155}
+08/30/2021 16:04:02 - INFO - __main__ - Step 15625: {'lr': 0.0004896183436043613, 'samples': 3000000, 'steps': 15624, 'loss/train': 1.218605875968933}
+08/30/2021 16:04:03 - INFO - __main__ - Step 15626: {'lr': 0.0004896168301622488, 'samples': 3000192, 'steps': 15625, 'loss/train': 1.5329443216323853}
+08/30/2021 16:04:04 - INFO - __main__ - Step 15627: {'lr': 0.0004896153166121688, 'samples': 3000384, 'steps': 15626, 'loss/train': 2.0231528282165527}
+08/30/2021 16:04:04 - INFO - __main__ - Step 15628: {'lr': 0.0004896138029541217, 'samples': 3000576, 'steps': 15627, 'loss/train': 2.0275752544403076}
+08/30/2021 16:04:04 - INFO - __main__ - Step 15629: {'lr': 0.0004896122891881083, 'samples': 3000768, 'steps': 15628, 'loss/train': 1.9274102449417114}
+08/30/2021 16:04:05 - INFO - __main__ - Step 15630: {'lr': 0.0004896107753141293, 'samples': 3000960, 'steps': 15629, 'loss/train': 1.6786177158355713}
+08/30/2021 16:04:06 - INFO - __main__ - Step 15631: {'lr': 0.0004896092613321854, 'samples': 3001152, 'steps': 15630, 'loss/train': 1.7088583707809448}
+08/30/2021 16:04:07 - INFO - __main__ - Step 15632: {'lr': 0.0004896077472422773, 'samples': 3001344, 'steps': 15631, 'loss/train': 1.5837279558181763}
+08/30/2021 16:04:07 - INFO - __main__ - Step 15633: {'lr': 0.0004896062330444057, 'samples': 3001536, 'steps': 15632, 'loss/train': 1.5668208599090576}
+08/30/2021 16:04:07 - INFO - __main__ - Step 15634: {'lr': 0.0004896047187385711, 'samples': 3001728, 'steps': 15633, 'loss/train': 1.3298778533935547}
+08/30/2021 16:04:08 - INFO - __main__ - Step 15635: {'lr': 0.0004896032043247744, 'samples': 3001920, 'steps': 15634, 'loss/train': 1.4978915452957153}
+08/30/2021 16:04:09 - INFO - __main__ - Step 15636: {'lr': 0.0004896016898030161, 'samples': 3002112, 'steps': 15635, 'loss/train': 1.8773466348648071}
+08/30/2021 16:04:09 - INFO - __main__ - Step 15637: {'lr': 0.0004896001751732971, 'samples': 3002304, 'steps': 15636, 'loss/train': 1.8856909275054932}
+08/30/2021 16:04:10 - INFO - __main__ - Step 15638: {'lr': 0.0004895986604356178, 'samples': 3002496, 'steps': 15637, 'loss/train': 1.6762871742248535}
+08/30/2021 16:04:10 - INFO - __main__ - Step 15639: {'lr': 0.0004895971455899792, 'samples': 3002688, 'steps': 15638, 'loss/train': 1.5342628955841064}
+08/30/2021 16:04:10 - INFO - __main__ - Step 15640: {'lr': 0.0004895956306363818, 'samples': 3002880, 'steps': 15639, 'loss/train': 2.096414804458618}
+08/30/2021 16:04:11 - INFO - __main__ - Step 15641: {'lr': 0.0004895941155748263, 'samples': 3003072, 'steps': 15640, 'loss/train': 1.8845845460891724}
+08/30/2021 16:04:12 - INFO - __main__ - Step 15642: {'lr': 0.0004895926004053133, 'samples': 3003264, 'steps': 15641, 'loss/train': 1.309841275215149}
+08/30/2021 16:04:13 - INFO - __main__ - Step 15643: {'lr': 0.0004895910851278436, 'samples': 3003456, 'steps': 15642, 'loss/train': 1.4342775344848633}
+08/30/2021 16:04:13 - INFO - __main__ - Step 15644: {'lr': 0.0004895895697424179, 'samples': 3003648, 'steps': 15643, 'loss/train': 1.3895652294158936}
+08/30/2021 16:04:14 - INFO - __main__ - Step 15645: {'lr': 0.0004895880542490369, 'samples': 3003840, 'steps': 15644, 'loss/train': 1.7355033159255981}
+08/30/2021 16:04:14 - INFO - __main__ - Step 15646: {'lr': 0.0004895865386477011, 'samples': 3004032, 'steps': 15645, 'loss/train': 1.8758642673492432}
+08/30/2021 16:04:15 - INFO - __main__ - Step 15647: {'lr': 0.0004895850229384113, 'samples': 3004224, 'steps': 15646, 'loss/train': 1.4401111602783203}
+08/30/2021 16:04:16 - INFO - __main__ - Step 15648: {'lr': 0.0004895835071211682, 'samples': 3004416, 'steps': 15647, 'loss/train': 1.859441876411438}
+08/30/2021 16:04:16 - INFO - __main__ - Step 15649: {'lr': 0.0004895819911959725, 'samples': 3004608, 'steps': 15648, 'loss/train': 1.9605817794799805}
+08/30/2021 16:04:16 - INFO - __main__ - Step 15650: {'lr': 0.0004895804751628249, 'samples': 3004800, 'steps': 15649, 'loss/train': 2.3211185932159424}
+08/30/2021 16:04:17 - INFO - __main__ - Step 15651: {'lr': 0.0004895789590217259, 'samples': 3004992, 'steps': 15650, 'loss/train': 1.648622751235962}
+08/30/2021 16:04:18 - INFO - __main__ - Step 15652: {'lr': 0.0004895774427726764, 'samples': 3005184, 'steps': 15651, 'loss/train': 1.631855845451355}
+08/30/2021 16:04:19 - INFO - __main__ - Step 15653: {'lr': 0.000489575926415677, 'samples': 3005376, 'steps': 15652, 'loss/train': 1.496962070465088}
+08/30/2021 16:04:19 - INFO - __main__ - Step 15654: {'lr': 0.0004895744099507284, 'samples': 3005568, 'steps': 15653, 'loss/train': 1.2107460498809814}
+08/30/2021 16:04:20 - INFO - __main__ - Step 15655: {'lr': 0.0004895728933778313, 'samples': 3005760, 'steps': 15654, 'loss/train': 1.797992467880249}
+08/30/2021 16:04:20 - INFO - __main__ - Step 15656: {'lr': 0.0004895713766969863, 'samples': 3005952, 'steps': 15655, 'loss/train': 1.4545979499816895}
+08/30/2021 16:04:21 - INFO - __main__ - Step 15657: {'lr': 0.0004895698599081942, 'samples': 3006144, 'steps': 15656, 'loss/train': 1.5968542098999023}
+08/30/2021 16:04:22 - INFO - __main__ - Step 15658: {'lr': 0.0004895683430114555, 'samples': 3006336, 'steps': 15657, 'loss/train': 3.075434923171997}
+08/30/2021 16:04:22 - INFO - __main__ - Step 15659: {'lr': 0.0004895668260067711, 'samples': 3006528, 'steps': 15658, 'loss/train': 1.7385143041610718}
+08/30/2021 16:04:23 - INFO - __main__ - Step 15660: {'lr': 0.0004895653088941416, 'samples': 3006720, 'steps': 15659, 'loss/train': 1.9182649850845337}
+08/30/2021 16:04:23 - INFO - __main__ - Step 15661: {'lr': 0.0004895637916735675, 'samples': 3006912, 'steps': 15660, 'loss/train': 1.7979016304016113}
+08/30/2021 16:04:25 - INFO - __main__ - Step 15662: {'lr': 0.0004895622743450497, 'samples': 3007104, 'steps': 15661, 'loss/train': 1.7512699365615845}
+08/30/2021 16:04:25 - INFO - __main__ - Step 15663: {'lr': 0.000489560756908589, 'samples': 3007296, 'steps': 15662, 'loss/train': 0.8430560827255249}
+08/30/2021 16:04:25 - INFO - __main__ - Step 15664: {'lr': 0.0004895592393641858, 'samples': 3007488, 'steps': 15663, 'loss/train': 1.425565242767334}
+08/30/2021 16:04:26 - INFO - __main__ - Step 15665: {'lr': 0.0004895577217118408, 'samples': 3007680, 'steps': 15664, 'loss/train': 1.679845929145813}
+08/30/2021 16:04:26 - INFO - __main__ - Step 15666: {'lr': 0.000489556203951555, 'samples': 3007872, 'steps': 15665, 'loss/train': 1.8205928802490234}
+08/30/2021 16:04:26 - INFO - __main__ - Step 15667: {'lr': 0.0004895546860833287, 'samples': 3008064, 'steps': 15666, 'loss/train': 1.5674464702606201}
+08/30/2021 16:04:28 - INFO - __main__ - Step 15668: {'lr': 0.000489553168107163, 'samples': 3008256, 'steps': 15667, 'loss/train': 2.0820534229278564}
+08/30/2021 16:04:29 - INFO - __main__ - Step 15669: {'lr': 0.0004895516500230581, 'samples': 3008448, 'steps': 15668, 'loss/train': 1.8909108638763428}
+08/30/2021 16:04:29 - INFO - __main__ - Step 15670: {'lr': 0.000489550131831015, 'samples': 3008640, 'steps': 15669, 'loss/train': 1.6744166612625122}
+08/30/2021 16:04:29 - INFO - __main__ - Step 15671: {'lr': 0.0004895486135310343, 'samples': 3008832, 'steps': 15670, 'loss/train': 1.5791500806808472}
+08/30/2021 16:04:30 - INFO - __main__ - Step 15672: {'lr': 0.0004895470951231166, 'samples': 3009024, 'steps': 15671, 'loss/train': 1.5914665460586548}
+08/30/2021 16:04:31 - INFO - __main__ - Step 15673: {'lr': 0.0004895455766072629, 'samples': 3009216, 'steps': 15672, 'loss/train': 0.410793662071228}
+08/30/2021 16:04:32 - INFO - __main__ - Step 15674: {'lr': 0.0004895440579834736, 'samples': 3009408, 'steps': 15673, 'loss/train': 1.7942060232162476}
+08/30/2021 16:04:32 - INFO - __main__ - Step 15675: {'lr': 0.0004895425392517493, 'samples': 3009600, 'steps': 15674, 'loss/train': 1.6709843873977661}
+08/30/2021 16:04:32 - INFO - __main__ - Step 15676: {'lr': 0.0004895410204120909, 'samples': 3009792, 'steps': 15675, 'loss/train': 1.6655640602111816}
+08/30/2021 16:04:33 - INFO - __main__ - Step 15677: {'lr': 0.000489539501464499, 'samples': 3009984, 'steps': 15676, 'loss/train': 1.4968088865280151}
+08/30/2021 16:04:35 - INFO - __main__ - Step 15678: {'lr': 0.0004895379824089743, 'samples': 3010176, 'steps': 15677, 'loss/train': 2.078408718109131}
+08/30/2021 16:04:35 - INFO - __main__ - Step 15679: {'lr': 0.0004895364632455175, 'samples': 3010368, 'steps': 15678, 'loss/train': 1.7145956754684448}
+08/30/2021 16:04:36 - INFO - __main__ - Step 15680: {'lr': 0.0004895349439741292, 'samples': 3010560, 'steps': 15679, 'loss/train': 2.807765483856201}
+08/30/2021 16:04:36 - INFO - __main__ - Step 15681: {'lr': 0.0004895334245948103, 'samples': 3010752, 'steps': 15680, 'loss/train': 2.011272430419922}
+08/30/2021 16:04:36 - INFO - __main__ - Step 15682: {'lr': 0.0004895319051075612, 'samples': 3010944, 'steps': 15681, 'loss/train': 1.902477741241455}
+08/30/2021 16:04:38 - INFO - __main__ - Step 15683: {'lr': 0.0004895303855123828, 'samples': 3011136, 'steps': 15682, 'loss/train': 1.9463393688201904}
+08/30/2021 16:04:38 - INFO - __main__ - Step 15684: {'lr': 0.0004895288658092757, 'samples': 3011328, 'steps': 15683, 'loss/train': 1.6282411813735962}
+08/30/2021 16:04:39 - INFO - __main__ - Step 15685: {'lr': 0.0004895273459982406, 'samples': 3011520, 'steps': 15684, 'loss/train': 1.6483428478240967}
+08/30/2021 16:04:39 - INFO - __main__ - Step 15686: {'lr': 0.0004895258260792781, 'samples': 3011712, 'steps': 15685, 'loss/train': 1.8689420223236084}
+08/30/2021 16:04:39 - INFO - __main__ - Step 15687: {'lr': 0.0004895243060523889, 'samples': 3011904, 'steps': 15686, 'loss/train': 1.473405122756958}
+08/30/2021 16:04:41 - INFO - __main__ - Step 15688: {'lr': 0.0004895227859175739, 'samples': 3012096, 'steps': 15687, 'loss/train': 1.5170730352401733}
+08/30/2021 16:04:42 - INFO - __main__ - Step 15689: {'lr': 0.0004895212656748336, 'samples': 3012288, 'steps': 15688, 'loss/train': 0.24248376488685608}
+08/30/2021 16:04:42 - INFO - __main__ - Step 15690: {'lr': 0.0004895197453241687, 'samples': 3012480, 'steps': 15689, 'loss/train': 2.572460174560547}
+08/30/2021 16:04:43 - INFO - __main__ - Step 15691: {'lr': 0.0004895182248655798, 'samples': 3012672, 'steps': 15690, 'loss/train': 1.790162205696106}
+08/30/2021 16:04:43 - INFO - __main__ - Step 15692: {'lr': 0.0004895167042990678, 'samples': 3012864, 'steps': 15691, 'loss/train': 1.0607959032058716}
+08/30/2021 16:04:44 - INFO - __main__ - Step 15693: {'lr': 0.0004895151836246332, 'samples': 3013056, 'steps': 15692, 'loss/train': 1.7529367208480835}
+08/30/2021 16:04:45 - INFO - __main__ - Step 15694: {'lr': 0.0004895136628422767, 'samples': 3013248, 'steps': 15693, 'loss/train': 1.3572545051574707}
+08/30/2021 16:04:45 - INFO - __main__ - Step 15695: {'lr': 0.0004895121419519992, 'samples': 3013440, 'steps': 15694, 'loss/train': 1.9496676921844482}
+08/30/2021 16:04:45 - INFO - __main__ - Step 15696: {'lr': 0.0004895106209538011, 'samples': 3013632, 'steps': 15695, 'loss/train': 1.5155653953552246}
+08/30/2021 16:04:46 - INFO - __main__ - Step 15697: {'lr': 0.0004895090998476833, 'samples': 3013824, 'steps': 15696, 'loss/train': 1.7715060710906982}
+08/30/2021 16:04:47 - INFO - __main__ - Step 15698: {'lr': 0.0004895075786336463, 'samples': 3014016, 'steps': 15697, 'loss/train': 2.041308879852295}
+08/30/2021 16:04:48 - INFO - __main__ - Step 15699: {'lr': 0.000489506057311691, 'samples': 3014208, 'steps': 15698, 'loss/train': 1.2994133234024048}
+08/30/2021 16:04:48 - INFO - __main__ - Step 15700: {'lr': 0.0004895045358818179, 'samples': 3014400, 'steps': 15699, 'loss/train': 1.5458451509475708}
+08/30/2021 16:04:48 - INFO - __main__ - Step 15701: {'lr': 0.0004895030143440278, 'samples': 3014592, 'steps': 15700, 'loss/train': 2.004124164581299}
+08/30/2021 16:04:49 - INFO - __main__ - Step 15702: {'lr': 0.0004895014926983212, 'samples': 3014784, 'steps': 15701, 'loss/train': 1.2008405923843384}
+08/30/2021 16:04:49 - INFO - __main__ - Step 15703: {'lr': 0.0004894999709446991, 'samples': 3014976, 'steps': 15702, 'loss/train': 1.6882003545761108}
+08/30/2021 16:04:51 - INFO - __main__ - Step 15704: {'lr': 0.0004894984490831619, 'samples': 3015168, 'steps': 15703, 'loss/train': 1.5917606353759766}
+08/30/2021 16:04:51 - INFO - __main__ - Step 15705: {'lr': 0.0004894969271137104, 'samples': 3015360, 'steps': 15704, 'loss/train': 0.23126155138015747}
+08/30/2021 16:04:52 - INFO - __main__ - Step 15706: {'lr': 0.0004894954050363452, 'samples': 3015552, 'steps': 15705, 'loss/train': 1.0706652402877808}
+08/30/2021 16:04:52 - INFO - __main__ - Step 15707: {'lr': 0.0004894938828510672, 'samples': 3015744, 'steps': 15706, 'loss/train': 1.2698158025741577}
+08/30/2021 16:04:53 - INFO - __main__ - Step 15708: {'lr': 0.000489492360557877, 'samples': 3015936, 'steps': 15707, 'loss/train': 0.8350092768669128}
+08/30/2021 16:04:53 - INFO - __main__ - Step 15709: {'lr': 0.0004894908381567751, 'samples': 3016128, 'steps': 15708, 'loss/train': 2.3612992763519287}
+08/30/2021 16:04:54 - INFO - __main__ - Step 15710: {'lr': 0.0004894893156477623, 'samples': 3016320, 'steps': 15709, 'loss/train': 1.7201426029205322}
+08/30/2021 16:04:55 - INFO - __main__ - Step 15711: {'lr': 0.0004894877930308395, 'samples': 3016512, 'steps': 15710, 'loss/train': 1.4212003946304321}
+08/30/2021 16:04:55 - INFO - __main__ - Step 15712: {'lr': 0.0004894862703060071, 'samples': 3016704, 'steps': 15711, 'loss/train': 2.0885603427886963}
+08/30/2021 16:04:55 - INFO - __main__ - Step 15713: {'lr': 0.0004894847474732658, 'samples': 3016896, 'steps': 15712, 'loss/train': 2.1898651123046875}
+08/30/2021 16:04:56 - INFO - __main__ - Step 15714: {'lr': 0.0004894832245326165, 'samples': 3017088, 'steps': 15713, 'loss/train': 1.267521619796753}
+08/30/2021 16:04:57 - INFO - __main__ - Step 15715: {'lr': 0.0004894817014840597, 'samples': 3017280, 'steps': 15714, 'loss/train': 1.5059354305267334}
+08/30/2021 16:04:58 - INFO - __main__ - Step 15716: {'lr': 0.0004894801783275961, 'samples': 3017472, 'steps': 15715, 'loss/train': 1.5661461353302002}
+08/30/2021 16:04:58 - INFO - __main__ - Step 15717: {'lr': 0.0004894786550632264, 'samples': 3017664, 'steps': 15716, 'loss/train': 1.3200610876083374}
+08/30/2021 16:04:58 - INFO - __main__ - Step 15718: {'lr': 0.0004894771316909514, 'samples': 3017856, 'steps': 15717, 'loss/train': 1.5051206350326538}
+08/30/2021 16:04:59 - INFO - __main__ - Step 15719: {'lr': 0.0004894756082107717, 'samples': 3018048, 'steps': 15718, 'loss/train': 1.4719260931015015}
+08/30/2021 16:05:00 - INFO - __main__ - Step 15720: {'lr': 0.0004894740846226879, 'samples': 3018240, 'steps': 15719, 'loss/train': 1.7230294942855835}
+08/30/2021 16:05:01 - INFO - __main__ - Step 15721: {'lr': 0.0004894725609267009, 'samples': 3018432, 'steps': 15720, 'loss/train': 1.6836109161376953}
+08/30/2021 16:05:01 - INFO - __main__ - Step 15722: {'lr': 0.0004894710371228111, 'samples': 3018624, 'steps': 15721, 'loss/train': 2.2346858978271484}
+08/30/2021 16:05:02 - INFO - __main__ - Step 15723: {'lr': 0.0004894695132110196, 'samples': 3018816, 'steps': 15722, 'loss/train': 1.240833044052124}
+08/30/2021 16:05:02 - INFO - __main__ - Step 15724: {'lr': 0.0004894679891913266, 'samples': 3019008, 'steps': 15723, 'loss/train': 1.9928617477416992}
+08/30/2021 16:05:02 - INFO - __main__ - Step 15725: {'lr': 0.000489466465063733, 'samples': 3019200, 'steps': 15724, 'loss/train': 1.71743905544281}
+08/30/2021 16:05:04 - INFO - __main__ - Step 15726: {'lr': 0.0004894649408282396, 'samples': 3019392, 'steps': 15725, 'loss/train': 1.3347309827804565}
+08/30/2021 16:05:04 - INFO - __main__ - Step 15727: {'lr': 0.000489463416484847, 'samples': 3019584, 'steps': 15726, 'loss/train': 2.6286916732788086}
+08/30/2021 16:05:05 - INFO - __main__ - Step 15728: {'lr': 0.0004894618920335558, 'samples': 3019776, 'steps': 15727, 'loss/train': 1.3679033517837524}
+08/30/2021 16:05:05 - INFO - __main__ - Step 15729: {'lr': 0.0004894603674743668, 'samples': 3019968, 'steps': 15728, 'loss/train': 1.9781831502914429}
+08/30/2021 16:05:05 - INFO - __main__ - Step 15730: {'lr': 0.0004894588428072808, 'samples': 3020160, 'steps': 15729, 'loss/train': 2.1462972164154053}
+08/30/2021 16:05:07 - INFO - __main__ - Step 15731: {'lr': 0.0004894573180322982, 'samples': 3020352, 'steps': 15730, 'loss/train': 1.7896645069122314}
+08/30/2021 16:05:08 - INFO - __main__ - Step 15732: {'lr': 0.0004894557931494199, 'samples': 3020544, 'steps': 15731, 'loss/train': 1.843048334121704}
+08/30/2021 16:05:08 - INFO - __main__ - Step 15733: {'lr': 0.0004894542681586465, 'samples': 3020736, 'steps': 15732, 'loss/train': 1.7974251508712769}
+08/30/2021 16:05:09 - INFO - __main__ - Step 15734: {'lr': 0.0004894527430599786, 'samples': 3020928, 'steps': 15733, 'loss/train': 1.9471001625061035}
+08/30/2021 16:05:09 - INFO - __main__ - Step 15735: {'lr': 0.0004894512178534171, 'samples': 3021120, 'steps': 15734, 'loss/train': 1.8450522422790527}
+08/30/2021 16:05:10 - INFO - __main__ - Step 15736: {'lr': 0.0004894496925389625, 'samples': 3021312, 'steps': 15735, 'loss/train': 1.952476143836975}
+08/30/2021 16:05:11 - INFO - __main__ - Step 15737: {'lr': 0.0004894481671166155, 'samples': 3021504, 'steps': 15736, 'loss/train': 1.9185781478881836}
+08/30/2021 16:05:11 - INFO - __main__ - Step 15738: {'lr': 0.0004894466415863771, 'samples': 3021696, 'steps': 15737, 'loss/train': 1.8842803239822388}
+08/30/2021 16:05:12 - INFO - __main__ - Step 15739: {'lr': 0.0004894451159482476, 'samples': 3021888, 'steps': 15738, 'loss/train': 1.6598477363586426}
+08/30/2021 16:05:12 - INFO - __main__ - Step 15740: {'lr': 0.0004894435902022277, 'samples': 3022080, 'steps': 15739, 'loss/train': 2.236760139465332}
+08/30/2021 16:05:14 - INFO - __main__ - Step 15741: {'lr': 0.0004894420643483184, 'samples': 3022272, 'steps': 15740, 'loss/train': 1.7471964359283447}
+08/30/2021 16:05:14 - INFO - __main__ - Step 15742: {'lr': 0.0004894405383865201, 'samples': 3022464, 'steps': 15741, 'loss/train': 1.1105577945709229}
+08/30/2021 16:05:15 - INFO - __main__ - Step 15743: {'lr': 0.0004894390123168337, 'samples': 3022656, 'steps': 15742, 'loss/train': 1.852920413017273}
+08/30/2021 16:05:15 - INFO - __main__ - Step 15744: {'lr': 0.0004894374861392596, 'samples': 3022848, 'steps': 15743, 'loss/train': 1.7588038444519043}
+08/30/2021 16:05:15 - INFO - __main__ - Step 15745: {'lr': 0.0004894359598537987, 'samples': 3023040, 'steps': 15744, 'loss/train': 1.2188833951950073}
+08/30/2021 16:05:17 - INFO - __main__ - Step 15746: {'lr': 0.0004894344334604517, 'samples': 3023232, 'steps': 15745, 'loss/train': 1.872450590133667}
+08/30/2021 16:05:17 - INFO - __main__ - Step 15747: {'lr': 0.0004894329069592192, 'samples': 3023424, 'steps': 15746, 'loss/train': 1.7818655967712402}
+08/30/2021 16:05:18 - INFO - __main__ - Step 15748: {'lr': 0.000489431380350102, 'samples': 3023616, 'steps': 15747, 'loss/train': 1.5086807012557983}
+08/30/2021 16:05:18 - INFO - __main__ - Step 15749: {'lr': 0.0004894298536331007, 'samples': 3023808, 'steps': 15748, 'loss/train': 1.1315829753875732}
+08/30/2021 16:05:18 - INFO - __main__ - Step 15750: {'lr': 0.000489428326808216, 'samples': 3024000, 'steps': 15749, 'loss/train': 1.984466314315796}
+08/30/2021 16:05:20 - INFO - __main__ - Step 15751: {'lr': 0.0004894267998754486, 'samples': 3024192, 'steps': 15750, 'loss/train': 2.230523109436035}
+08/30/2021 16:05:20 - INFO - __main__ - Step 15752: {'lr': 0.0004894252728347992, 'samples': 3024384, 'steps': 15751, 'loss/train': 1.0668296813964844}
+08/30/2021 16:05:21 - INFO - __main__ - Step 15753: {'lr': 0.0004894237456862684, 'samples': 3024576, 'steps': 15752, 'loss/train': 2.916994333267212}
+08/30/2021 16:05:21 - INFO - __main__ - Step 15754: {'lr': 0.000489422218429857, 'samples': 3024768, 'steps': 15753, 'loss/train': 1.766281247138977}
+08/30/2021 16:05:21 - INFO - __main__ - Step 15755: {'lr': 0.0004894206910655656, 'samples': 3024960, 'steps': 15754, 'loss/train': 2.572554349899292}
+08/30/2021 16:05:23 - INFO - __main__ - Step 15756: {'lr': 0.0004894191635933949, 'samples': 3025152, 'steps': 15755, 'loss/train': 1.671134114265442}
+08/30/2021 16:05:23 - INFO - __main__ - Step 15757: {'lr': 0.0004894176360133456, 'samples': 3025344, 'steps': 15756, 'loss/train': 1.7096961736679077}
+08/30/2021 16:05:24 - INFO - __main__ - Step 15758: {'lr': 0.0004894161083254186, 'samples': 3025536, 'steps': 15757, 'loss/train': 1.6784322261810303}
+08/30/2021 16:05:24 - INFO - __main__ - Step 15759: {'lr': 0.0004894145805296143, 'samples': 3025728, 'steps': 15758, 'loss/train': 2.076785087585449}
+08/30/2021 16:05:24 - INFO - __main__ - Step 15760: {'lr': 0.0004894130526259334, 'samples': 3025920, 'steps': 15759, 'loss/train': 1.7659324407577515}
+08/30/2021 16:05:26 - INFO - __main__ - Step 15761: {'lr': 0.0004894115246143768, 'samples': 3026112, 'steps': 15760, 'loss/train': 0.3448126018047333}
+08/30/2021 16:05:26 - INFO - __main__ - Step 15762: {'lr': 0.0004894099964949449, 'samples': 3026304, 'steps': 15761, 'loss/train': 2.420470714569092}
+08/30/2021 16:05:27 - INFO - __main__ - Step 15763: {'lr': 0.0004894084682676387, 'samples': 3026496, 'steps': 15762, 'loss/train': 2.1055173873901367}
+08/30/2021 16:05:27 - INFO - __main__ - Step 15764: {'lr': 0.0004894069399324586, 'samples': 3026688, 'steps': 15763, 'loss/train': 1.9874101877212524}
+08/30/2021 16:05:27 - INFO - __main__ - Step 15765: {'lr': 0.0004894054114894055, 'samples': 3026880, 'steps': 15764, 'loss/train': 1.9154988527297974}
+08/30/2021 16:05:28 - INFO - __main__ - Step 15766: {'lr': 0.00048940388293848, 'samples': 3027072, 'steps': 15765, 'loss/train': 1.456554889678955}
+08/30/2021 16:05:29 - INFO - __main__ - Step 15767: {'lr': 0.000489402354279683, 'samples': 3027264, 'steps': 15766, 'loss/train': 1.8956642150878906}
+08/30/2021 16:05:30 - INFO - __main__ - Step 15768: {'lr': 0.0004894008255130147, 'samples': 3027456, 'steps': 15767, 'loss/train': 1.8803777694702148}
+08/30/2021 16:05:30 - INFO - __main__ - Step 15769: {'lr': 0.0004893992966384762, 'samples': 3027648, 'steps': 15768, 'loss/train': 1.9418342113494873}
+08/30/2021 16:05:30 - INFO - __main__ - Step 15770: {'lr': 0.0004893977676560682, 'samples': 3027840, 'steps': 15769, 'loss/train': 1.8949304819107056}
+08/30/2021 16:05:31 - INFO - __main__ - Step 15771: {'lr': 0.000489396238565791, 'samples': 3028032, 'steps': 15770, 'loss/train': 0.8951969146728516}
+08/30/2021 16:05:32 - INFO - __main__ - Step 15772: {'lr': 0.0004893947093676458, 'samples': 3028224, 'steps': 15771, 'loss/train': 1.8372505903244019}
+08/30/2021 16:05:33 - INFO - __main__ - Step 15773: {'lr': 0.0004893931800616329, 'samples': 3028416, 'steps': 15772, 'loss/train': 2.0663514137268066}
+08/30/2021 16:05:33 - INFO - __main__ - Step 15774: {'lr': 0.0004893916506477532, 'samples': 3028608, 'steps': 15773, 'loss/train': 1.3187042474746704}
+08/30/2021 16:05:33 - INFO - __main__ - Step 15775: {'lr': 0.0004893901211260073, 'samples': 3028800, 'steps': 15774, 'loss/train': 2.269486665725708}
+08/30/2021 16:05:34 - INFO - __main__ - Step 15776: {'lr': 0.0004893885914963958, 'samples': 3028992, 'steps': 15775, 'loss/train': 1.5242422819137573}
+08/30/2021 16:05:35 - INFO - __main__ - Step 15777: {'lr': 0.0004893870617589196, 'samples': 3029184, 'steps': 15776, 'loss/train': 1.0224928855895996}
+08/30/2021 16:05:36 - INFO - __main__ - Step 15778: {'lr': 0.0004893855319135791, 'samples': 3029376, 'steps': 15777, 'loss/train': 1.6880754232406616}
+08/30/2021 16:05:36 - INFO - __main__ - Step 15779: {'lr': 0.0004893840019603754, 'samples': 3029568, 'steps': 15778, 'loss/train': 1.4016624689102173}
+08/30/2021 16:05:36 - INFO - __main__ - Step 15780: {'lr': 0.0004893824718993088, 'samples': 3029760, 'steps': 15779, 'loss/train': 1.8057093620300293}
+08/30/2021 16:05:37 - INFO - __main__ - Step 15781: {'lr': 0.0004893809417303803, 'samples': 3029952, 'steps': 15780, 'loss/train': 1.8039134740829468}
+08/30/2021 16:05:39 - INFO - __main__ - Step 15782: {'lr': 0.0004893794114535905, 'samples': 3030144, 'steps': 15781, 'loss/train': 1.7117946147918701}
+08/30/2021 16:05:39 - INFO - __main__ - Step 15783: {'lr': 0.0004893778810689399, 'samples': 3030336, 'steps': 15782, 'loss/train': 1.8342255353927612}
+08/30/2021 16:05:39 - INFO - __main__ - Step 15784: {'lr': 0.0004893763505764292, 'samples': 3030528, 'steps': 15783, 'loss/train': 1.4451026916503906}
+08/30/2021 16:05:40 - INFO - __main__ - Step 15785: {'lr': 0.0004893748199760594, 'samples': 3030720, 'steps': 15784, 'loss/train': 0.1269480586051941}
+08/30/2021 16:05:40 - INFO - __main__ - Step 15786: {'lr': 0.0004893732892678309, 'samples': 3030912, 'steps': 15785, 'loss/train': 1.6834965944290161}
+08/30/2021 16:05:40 - INFO - __main__ - Step 15787: {'lr': 0.0004893717584517445, 'samples': 3031104, 'steps': 15786, 'loss/train': 0.7068189978599548}
+08/30/2021 16:05:42 - INFO - __main__ - Step 15788: {'lr': 0.000489370227527801, 'samples': 3031296, 'steps': 15787, 'loss/train': 0.6516126990318298}
+08/30/2021 16:05:43 - INFO - __main__ - Step 15789: {'lr': 0.0004893686964960009, 'samples': 3031488, 'steps': 15788, 'loss/train': 1.4837327003479004}
+08/30/2021 16:05:43 - INFO - __main__ - Step 15790: {'lr': 0.0004893671653563448, 'samples': 3031680, 'steps': 15789, 'loss/train': 2.016655445098877}
+08/30/2021 16:05:44 - INFO - __main__ - Step 15791: {'lr': 0.0004893656341088338, 'samples': 3031872, 'steps': 15790, 'loss/train': 1.369646430015564}
+08/30/2021 16:05:44 - INFO - __main__ - Step 15792: {'lr': 0.0004893641027534682, 'samples': 3032064, 'steps': 15791, 'loss/train': 1.9633276462554932}
+08/30/2021 16:05:46 - INFO - __main__ - Step 15793: {'lr': 0.0004893625712902489, 'samples': 3032256, 'steps': 15792, 'loss/train': 1.4365977048873901}
+08/30/2021 16:05:46 - INFO - __main__ - Step 15794: {'lr': 0.0004893610397191764, 'samples': 3032448, 'steps': 15793, 'loss/train': 1.6184943914413452}
+08/30/2021 16:05:46 - INFO - __main__ - Step 15795: {'lr': 0.0004893595080402517, 'samples': 3032640, 'steps': 15794, 'loss/train': 1.0569422245025635}
+08/30/2021 16:05:47 - INFO - __main__ - Step 15796: {'lr': 0.0004893579762534751, 'samples': 3032832, 'steps': 15795, 'loss/train': 1.966475486755371}
+08/30/2021 16:05:47 - INFO - __main__ - Step 15797: {'lr': 0.0004893564443588476, 'samples': 3033024, 'steps': 15796, 'loss/train': 1.7992537021636963}
+08/30/2021 16:05:49 - INFO - __main__ - Step 15798: {'lr': 0.0004893549123563697, 'samples': 3033216, 'steps': 15797, 'loss/train': 1.788185477256775}
+08/30/2021 16:05:49 - INFO - __main__ - Step 15799: {'lr': 0.0004893533802460422, 'samples': 3033408, 'steps': 15798, 'loss/train': 1.57007896900177}
+08/30/2021 16:05:49 - INFO - __main__ - Step 15800: {'lr': 0.0004893518480278658, 'samples': 3033600, 'steps': 15799, 'loss/train': 2.435354232788086}
+08/30/2021 16:05:50 - INFO - __main__ - Step 15801: {'lr': 0.0004893503157018412, 'samples': 3033792, 'steps': 15800, 'loss/train': 1.724379301071167}
+08/30/2021 16:05:50 - INFO - __main__ - Step 15802: {'lr': 0.000489348783267969, 'samples': 3033984, 'steps': 15801, 'loss/train': 1.6994962692260742}
+08/30/2021 16:05:50 - INFO - __main__ - Step 15803: {'lr': 0.0004893472507262499, 'samples': 3034176, 'steps': 15802, 'loss/train': 2.779169797897339}
+08/30/2021 16:05:52 - INFO - __main__ - Step 15804: {'lr': 0.0004893457180766846, 'samples': 3034368, 'steps': 15803, 'loss/train': 1.732416033744812}
+08/30/2021 16:05:53 - INFO - __main__ - Step 15805: {'lr': 0.0004893441853192739, 'samples': 3034560, 'steps': 15804, 'loss/train': 1.6029468774795532}
+08/30/2021 16:05:53 - INFO - __main__ - Step 15806: {'lr': 0.0004893426524540183, 'samples': 3034752, 'steps': 15805, 'loss/train': 2.099090099334717}
+08/30/2021 16:05:53 - INFO - __main__ - Step 15807: {'lr': 0.0004893411194809186, 'samples': 3034944, 'steps': 15806, 'loss/train': 1.7839194536209106}
+08/30/2021 16:05:54 - INFO - __main__ - Step 15808: {'lr': 0.0004893395863999755, 'samples': 3035136, 'steps': 15807, 'loss/train': 1.5603755712509155}
+08/30/2021 16:05:55 - INFO - __main__ - Step 15809: {'lr': 0.0004893380532111898, 'samples': 3035328, 'steps': 15808, 'loss/train': 1.5778244733810425}
+08/30/2021 16:05:56 - INFO - __main__ - Step 15810: {'lr': 0.0004893365199145619, 'samples': 3035520, 'steps': 15809, 'loss/train': 1.8768761157989502}
+08/30/2021 16:05:56 - INFO - __main__ - Step 15811: {'lr': 0.0004893349865100927, 'samples': 3035712, 'steps': 15810, 'loss/train': 1.9645310640335083}
+08/30/2021 16:05:56 - INFO - __main__ - Step 15812: {'lr': 0.0004893334529977828, 'samples': 3035904, 'steps': 15811, 'loss/train': 1.8728632926940918}
+08/30/2021 16:05:57 - INFO - __main__ - Step 15813: {'lr': 0.0004893319193776331, 'samples': 3036096, 'steps': 15812, 'loss/train': 1.7371985912322998}
+08/30/2021 16:05:58 - INFO - __main__ - Step 15814: {'lr': 0.000489330385649644, 'samples': 3036288, 'steps': 15813, 'loss/train': 1.9565091133117676}
+08/30/2021 16:05:59 - INFO - __main__ - Step 15815: {'lr': 0.0004893288518138163, 'samples': 3036480, 'steps': 15814, 'loss/train': 1.8143585920333862}
+08/30/2021 16:05:59 - INFO - __main__ - Step 15816: {'lr': 0.0004893273178701508, 'samples': 3036672, 'steps': 15815, 'loss/train': 1.7400017976760864}
+08/30/2021 16:05:59 - INFO - __main__ - Step 15817: {'lr': 0.0004893257838186481, 'samples': 3036864, 'steps': 15816, 'loss/train': 2.777813673019409}
+08/30/2021 16:06:00 - INFO - __main__ - Step 15818: {'lr': 0.0004893242496593089, 'samples': 3037056, 'steps': 15817, 'loss/train': 2.0366008281707764}
+08/30/2021 16:06:01 - INFO - __main__ - Step 15819: {'lr': 0.0004893227153921338, 'samples': 3037248, 'steps': 15818, 'loss/train': 1.7623364925384521}
+08/30/2021 16:06:02 - INFO - __main__ - Step 15820: {'lr': 0.0004893211810171237, 'samples': 3037440, 'steps': 15819, 'loss/train': 1.1324254274368286}
+08/30/2021 16:06:02 - INFO - __main__ - Step 15821: {'lr': 0.0004893196465342791, 'samples': 3037632, 'steps': 15820, 'loss/train': 2.2985141277313232}
+08/30/2021 16:06:02 - INFO - __main__ - Step 15822: {'lr': 0.0004893181119436007, 'samples': 3037824, 'steps': 15821, 'loss/train': 1.7648950815200806}
+08/30/2021 16:06:03 - INFO - __main__ - Step 15823: {'lr': 0.0004893165772450893, 'samples': 3038016, 'steps': 15822, 'loss/train': 1.7349241971969604}
+08/30/2021 16:06:04 - INFO - __main__ - Step 15824: {'lr': 0.0004893150424387456, 'samples': 3038208, 'steps': 15823, 'loss/train': 1.8271968364715576}
+08/30/2021 16:06:05 - INFO - __main__ - Step 15825: {'lr': 0.0004893135075245702, 'samples': 3038400, 'steps': 15824, 'loss/train': 1.7137402296066284}
+08/30/2021 16:06:05 - INFO - __main__ - Step 15826: {'lr': 0.0004893119725025639, 'samples': 3038592, 'steps': 15825, 'loss/train': 1.4959312677383423}
+08/30/2021 16:06:06 - INFO - __main__ - Step 15827: {'lr': 0.0004893104373727272, 'samples': 3038784, 'steps': 15826, 'loss/train': 1.7496213912963867}
+08/30/2021 16:06:06 - INFO - __main__ - Step 15828: {'lr': 0.0004893089021350609, 'samples': 3038976, 'steps': 15827, 'loss/train': 1.48745596408844}
+08/30/2021 16:06:07 - INFO - __main__ - Step 15829: {'lr': 0.0004893073667895658, 'samples': 3039168, 'steps': 15828, 'loss/train': 0.20793157815933228}
+08/30/2021 16:06:08 - INFO - __main__ - Step 15830: {'lr': 0.0004893058313362424, 'samples': 3039360, 'steps': 15829, 'loss/train': 2.057208776473999}
+08/30/2021 16:06:08 - INFO - __main__ - Step 15831: {'lr': 0.0004893042957750916, 'samples': 3039552, 'steps': 15830, 'loss/train': 1.514568567276001}
+08/30/2021 16:06:09 - INFO - __main__ - Step 15832: {'lr': 0.0004893027601061138, 'samples': 3039744, 'steps': 15831, 'loss/train': 1.5174131393432617}
+08/30/2021 16:06:09 - INFO - __main__ - Step 15833: {'lr': 0.00048930122432931, 'samples': 3039936, 'steps': 15832, 'loss/train': 1.8271756172180176}
+08/30/2021 16:06:09 - INFO - __main__ - Step 15834: {'lr': 0.0004892996884446807, 'samples': 3040128, 'steps': 15833, 'loss/train': 1.2590651512145996}
+08/30/2021 16:06:11 - INFO - __main__ - Step 15835: {'lr': 0.0004892981524522267, 'samples': 3040320, 'steps': 15834, 'loss/train': 1.8676629066467285}
+08/30/2021 16:06:12 - INFO - __main__ - Step 15836: {'lr': 0.0004892966163519487, 'samples': 3040512, 'steps': 15835, 'loss/train': 1.9099675416946411}
+08/30/2021 16:06:12 - INFO - __main__ - Step 15837: {'lr': 0.0004892950801438472, 'samples': 3040704, 'steps': 15836, 'loss/train': 1.5653126239776611}
+08/30/2021 16:06:12 - INFO - __main__ - Step 15838: {'lr': 0.0004892935438279231, 'samples': 3040896, 'steps': 15837, 'loss/train': 1.9078892469406128}
+08/30/2021 16:06:13 - INFO - __main__ - Step 15839: {'lr': 0.0004892920074041771, 'samples': 3041088, 'steps': 15838, 'loss/train': 1.8621835708618164}
+08/30/2021 16:06:13 - INFO - __main__ - Step 15840: {'lr': 0.0004892904708726096, 'samples': 3041280, 'steps': 15839, 'loss/train': 1.7209863662719727}
+08/30/2021 16:06:15 - INFO - __main__ - Step 15841: {'lr': 0.0004892889342332218, 'samples': 3041472, 'steps': 15840, 'loss/train': 1.2462749481201172}
+08/30/2021 16:06:16 - INFO - __main__ - Step 15842: {'lr': 0.000489287397486014, 'samples': 3041664, 'steps': 15841, 'loss/train': 1.5948426723480225}
+08/30/2021 16:06:16 - INFO - __main__ - Step 15843: {'lr': 0.0004892858606309868, 'samples': 3041856, 'steps': 15842, 'loss/train': 1.6169359683990479}
+08/30/2021 16:06:16 - INFO - __main__ - Step 15844: {'lr': 0.0004892843236681412, 'samples': 3042048, 'steps': 15843, 'loss/train': 1.8096169233322144}
+08/30/2021 16:06:17 - INFO - __main__ - Step 15845: {'lr': 0.0004892827865974779, 'samples': 3042240, 'steps': 15844, 'loss/train': 1.927626609802246}
+08/30/2021 16:06:18 - INFO - __main__ - Step 15846: {'lr': 0.0004892812494189973, 'samples': 3042432, 'steps': 15845, 'loss/train': 1.567002534866333}
+08/30/2021 16:06:19 - INFO - __main__ - Step 15847: {'lr': 0.0004892797121327003, 'samples': 3042624, 'steps': 15846, 'loss/train': 1.6373697519302368}
+08/30/2021 16:06:19 - INFO - __main__ - Step 15848: {'lr': 0.0004892781747385876, 'samples': 3042816, 'steps': 15847, 'loss/train': 1.892551064491272}
+08/30/2021 16:06:19 - INFO - __main__ - Step 15849: {'lr': 0.0004892766372366598, 'samples': 3043008, 'steps': 15848, 'loss/train': 2.0063562393188477}
+08/30/2021 16:06:20 - INFO - __main__ - Step 15850: {'lr': 0.0004892750996269177, 'samples': 3043200, 'steps': 15849, 'loss/train': 2.2678918838500977}
+08/30/2021 16:06:21 - INFO - __main__ - Step 15851: {'lr': 0.0004892735619093618, 'samples': 3043392, 'steps': 15850, 'loss/train': 2.7943601608276367}
+08/30/2021 16:06:22 - INFO - __main__ - Step 15852: {'lr': 0.0004892720240839931, 'samples': 3043584, 'steps': 15851, 'loss/train': 1.4127070903778076}
+08/30/2021 16:06:22 - INFO - __main__ - Step 15853: {'lr': 0.0004892704861508121, 'samples': 3043776, 'steps': 15852, 'loss/train': 2.1591296195983887}
+08/30/2021 16:06:22 - INFO - __main__ - Step 15854: {'lr': 0.0004892689481098193, 'samples': 3043968, 'steps': 15853, 'loss/train': 2.0167603492736816}
+08/30/2021 16:06:23 - INFO - __main__ - Step 15855: {'lr': 0.0004892674099610158, 'samples': 3044160, 'steps': 15854, 'loss/train': 1.6414259672164917}
+08/30/2021 16:06:24 - INFO - __main__ - Step 15856: {'lr': 0.000489265871704402, 'samples': 3044352, 'steps': 15855, 'loss/train': 6.075537204742432}
+08/30/2021 16:06:25 - INFO - __main__ - Step 15857: {'lr': 0.0004892643333399788, 'samples': 3044544, 'steps': 15856, 'loss/train': 1.768763780593872}
+08/30/2021 16:06:25 - INFO - __main__ - Step 15858: {'lr': 0.0004892627948677467, 'samples': 3044736, 'steps': 15857, 'loss/train': 1.0978754758834839}
+08/30/2021 16:06:26 - INFO - __main__ - Step 15859: {'lr': 0.0004892612562877066, 'samples': 3044928, 'steps': 15858, 'loss/train': 2.134469509124756}
+08/30/2021 16:06:26 - INFO - __main__ - Step 15860: {'lr': 0.0004892597175998589, 'samples': 3045120, 'steps': 15859, 'loss/train': 2.2281742095947266}
+08/30/2021 16:06:26 - INFO - __main__ - Step 15861: {'lr': 0.0004892581788042045, 'samples': 3045312, 'steps': 15860, 'loss/train': 1.843698263168335}
+08/30/2021 16:06:28 - INFO - __main__ - Step 15862: {'lr': 0.0004892566399007441, 'samples': 3045504, 'steps': 15861, 'loss/train': 0.2343396246433258}
+08/30/2021 16:06:28 - INFO - __main__ - Step 15863: {'lr': 0.0004892551008894784, 'samples': 3045696, 'steps': 15862, 'loss/train': 0.3301844000816345}
+08/30/2021 16:06:29 - INFO - __main__ - Step 15864: {'lr': 0.0004892535617704079, 'samples': 3045888, 'steps': 15863, 'loss/train': 1.5133025646209717}
+08/30/2021 16:06:29 - INFO - __main__ - Step 15865: {'lr': 0.0004892520225435336, 'samples': 3046080, 'steps': 15864, 'loss/train': 1.9222338199615479}
+08/30/2021 16:06:29 - INFO - __main__ - Step 15866: {'lr': 0.000489250483208856, 'samples': 3046272, 'steps': 15865, 'loss/train': 1.7021836042404175}
+08/30/2021 16:06:31 - INFO - __main__ - Step 15867: {'lr': 0.0004892489437663758, 'samples': 3046464, 'steps': 15866, 'loss/train': 0.7320907115936279}
+08/30/2021 16:06:31 - INFO - __main__ - Step 15868: {'lr': 0.0004892474042160936, 'samples': 3046656, 'steps': 15867, 'loss/train': 2.1231696605682373}
+08/30/2021 16:06:32 - INFO - __main__ - Step 15869: {'lr': 0.0004892458645580103, 'samples': 3046848, 'steps': 15868, 'loss/train': 1.857272982597351}
+08/30/2021 16:06:32 - INFO - __main__ - Step 15870: {'lr': 0.0004892443247921265, 'samples': 3047040, 'steps': 15869, 'loss/train': 1.4664748907089233}
+08/30/2021 16:06:33 - INFO - __main__ - Step 15871: {'lr': 0.0004892427849184428, 'samples': 3047232, 'steps': 15870, 'loss/train': 1.3892543315887451}
+08/30/2021 16:06:34 - INFO - __main__ - Step 15872: {'lr': 0.0004892412449369602, 'samples': 3047424, 'steps': 15871, 'loss/train': 0.11538084596395493}
+08/30/2021 16:06:34 - INFO - __main__ - Step 15873: {'lr': 0.0004892397048476791, 'samples': 3047616, 'steps': 15872, 'loss/train': 1.4485125541687012}
+08/30/2021 16:06:35 - INFO - __main__ - Step 15874: {'lr': 0.0004892381646506002, 'samples': 3047808, 'steps': 15873, 'loss/train': 2.0320661067962646}
+08/30/2021 16:06:35 - INFO - __main__ - Step 15875: {'lr': 0.0004892366243457244, 'samples': 3048000, 'steps': 15874, 'loss/train': 1.4326623678207397}
+08/30/2021 16:06:36 - INFO - __main__ - Step 15876: {'lr': 0.0004892350839330522, 'samples': 3048192, 'steps': 15875, 'loss/train': 1.6021592617034912}
+08/30/2021 16:06:37 - INFO - __main__ - Step 15877: {'lr': 0.0004892335434125844, 'samples': 3048384, 'steps': 15876, 'loss/train': 1.6339194774627686}
+08/30/2021 16:06:38 - INFO - __main__ - Step 15878: {'lr': 0.0004892320027843216, 'samples': 3048576, 'steps': 15877, 'loss/train': 1.673117756843567}
+08/30/2021 16:06:38 - INFO - __main__ - Step 15879: {'lr': 0.0004892304620482646, 'samples': 3048768, 'steps': 15878, 'loss/train': 1.6826636791229248}
+08/30/2021 16:06:38 - INFO - __main__ - Step 15880: {'lr': 0.000489228921204414, 'samples': 3048960, 'steps': 15879, 'loss/train': 1.749036192893982}
+08/30/2021 16:06:39 - INFO - __main__ - Step 15881: {'lr': 0.0004892273802527706, 'samples': 3049152, 'steps': 15880, 'loss/train': 0.9491150975227356}
+08/30/2021 16:06:40 - INFO - __main__ - Step 15882: {'lr': 0.000489225839193335, 'samples': 3049344, 'steps': 15881, 'loss/train': 2.020514488220215}
+08/30/2021 16:06:41 - INFO - __main__ - Step 15883: {'lr': 0.0004892242980261079, 'samples': 3049536, 'steps': 15882, 'loss/train': 1.8321619033813477}
+08/30/2021 16:06:41 - INFO - __main__ - Step 15884: {'lr': 0.0004892227567510901, 'samples': 3049728, 'steps': 15883, 'loss/train': 0.1489810347557068}
+08/30/2021 16:06:41 - INFO - __main__ - Step 15885: {'lr': 0.0004892212153682822, 'samples': 3049920, 'steps': 15884, 'loss/train': 1.6919065713882446}
+08/30/2021 16:06:42 - INFO - __main__ - Step 15886: {'lr': 0.0004892196738776848, 'samples': 3050112, 'steps': 15885, 'loss/train': 1.034507393836975}
+08/30/2021 16:06:43 - INFO - __main__ - Step 15887: {'lr': 0.0004892181322792989, 'samples': 3050304, 'steps': 15886, 'loss/train': 1.7606680393218994}
+08/30/2021 16:06:44 - INFO - __main__ - Step 15888: {'lr': 0.0004892165905731248, 'samples': 3050496, 'steps': 15887, 'loss/train': 1.3945250511169434}
+08/30/2021 16:06:44 - INFO - __main__ - Step 15889: {'lr': 0.0004892150487591635, 'samples': 3050688, 'steps': 15888, 'loss/train': 1.6292153596878052}
+08/30/2021 16:06:44 - INFO - __main__ - Step 15890: {'lr': 0.0004892135068374156, 'samples': 3050880, 'steps': 15889, 'loss/train': 1.4689536094665527}
+08/30/2021 16:06:45 - INFO - __main__ - Step 15891: {'lr': 0.0004892119648078817, 'samples': 3051072, 'steps': 15890, 'loss/train': 1.9595842361450195}
+08/30/2021 16:06:47 - INFO - __main__ - Step 15892: {'lr': 0.0004892104226705627, 'samples': 3051264, 'steps': 15891, 'loss/train': 1.322706937789917}
+08/30/2021 16:06:47 - INFO - __main__ - Step 15893: {'lr': 0.0004892088804254591, 'samples': 3051456, 'steps': 15892, 'loss/train': 1.619107961654663}
+08/30/2021 16:06:48 - INFO - __main__ - Step 15894: {'lr': 0.0004892073380725716, 'samples': 3051648, 'steps': 15893, 'loss/train': 1.9878965616226196}
+08/30/2021 16:06:48 - INFO - __main__ - Step 15895: {'lr': 0.0004892057956119012, 'samples': 3051840, 'steps': 15894, 'loss/train': 1.452697515487671}
+08/30/2021 16:06:48 - INFO - __main__ - Step 15896: {'lr': 0.0004892042530434482, 'samples': 3052032, 'steps': 15895, 'loss/train': 1.6216015815734863}
+08/30/2021 16:06:49 - INFO - __main__ - Step 15897: {'lr': 0.0004892027103672134, 'samples': 3052224, 'steps': 15896, 'loss/train': 1.6163655519485474}
+08/30/2021 16:06:50 - INFO - __main__ - Step 15898: {'lr': 0.0004892011675831976, 'samples': 3052416, 'steps': 15897, 'loss/train': 0.8906508684158325}
+08/30/2021 16:06:51 - INFO - __main__ - Step 15899: {'lr': 0.0004891996246914014, 'samples': 3052608, 'steps': 15898, 'loss/train': 1.6975879669189453}
+08/30/2021 16:06:51 - INFO - __main__ - Step 15900: {'lr': 0.0004891980816918257, 'samples': 3052800, 'steps': 15899, 'loss/train': 0.37823686003685}
+08/30/2021 16:06:51 - INFO - __main__ - Step 15901: {'lr': 0.0004891965385844709, 'samples': 3052992, 'steps': 15900, 'loss/train': 1.9129810333251953}
+08/30/2021 16:06:52 - INFO - __main__ - Step 15902: {'lr': 0.0004891949953693378, 'samples': 3053184, 'steps': 15901, 'loss/train': 1.1313961744308472}
+08/30/2021 16:06:53 - INFO - __main__ - Step 15903: {'lr': 0.0004891934520464273, 'samples': 3053376, 'steps': 15902, 'loss/train': 1.218643069267273}
+08/30/2021 16:06:54 - INFO - __main__ - Step 15904: {'lr': 0.0004891919086157398, 'samples': 3053568, 'steps': 15903, 'loss/train': 2.356090784072876}
+08/30/2021 16:06:54 - INFO - __main__ - Step 15905: {'lr': 0.000489190365077276, 'samples': 3053760, 'steps': 15904, 'loss/train': 1.6718299388885498}
+08/30/2021 16:06:54 - INFO - __main__ - Step 15906: {'lr': 0.0004891888214310369, 'samples': 3053952, 'steps': 15905, 'loss/train': 1.7623941898345947}
+08/30/2021 16:06:55 - INFO - __main__ - Step 15907: {'lr': 0.000489187277677023, 'samples': 3054144, 'steps': 15906, 'loss/train': 1.8284597396850586}
+08/30/2021 16:06:56 - INFO - __main__ - Step 15908: {'lr': 0.000489185733815235, 'samples': 3054336, 'steps': 15907, 'loss/train': 1.508117437362671}
+08/30/2021 16:06:57 - INFO - __main__ - Step 15909: {'lr': 0.0004891841898456735, 'samples': 3054528, 'steps': 15908, 'loss/train': 1.4869719743728638}
+08/30/2021 16:06:57 - INFO - __main__ - Step 15910: {'lr': 0.0004891826457683394, 'samples': 3054720, 'steps': 15909, 'loss/train': 1.608035683631897}
+08/30/2021 16:06:57 - INFO - __main__ - Step 15911: {'lr': 0.0004891811015832332, 'samples': 3054912, 'steps': 15910, 'loss/train': 1.6275404691696167}
+08/30/2021 16:06:58 - INFO - __main__ - Step 15912: {'lr': 0.0004891795572903557, 'samples': 3055104, 'steps': 15911, 'loss/train': 1.6273819208145142}
+08/30/2021 16:06:59 - INFO - __main__ - Step 15913: {'lr': 0.0004891780128897077, 'samples': 3055296, 'steps': 15912, 'loss/train': 1.4007941484451294}
+08/30/2021 16:07:00 - INFO - __main__ - Step 15914: {'lr': 0.0004891764683812896, 'samples': 3055488, 'steps': 15913, 'loss/train': 1.4682165384292603}
+08/30/2021 16:07:00 - INFO - __main__ - Step 15915: {'lr': 0.0004891749237651024, 'samples': 3055680, 'steps': 15914, 'loss/train': 1.6606872081756592}
+08/30/2021 16:07:00 - INFO - __main__ - Step 15916: {'lr': 0.0004891733790411466, 'samples': 3055872, 'steps': 15915, 'loss/train': 1.191284418106079}
+08/30/2021 16:07:01 - INFO - __main__ - Step 15917: {'lr': 0.000489171834209423, 'samples': 3056064, 'steps': 15916, 'loss/train': 1.778518557548523}
+08/30/2021 16:07:03 - INFO - __main__ - Step 15918: {'lr': 0.0004891702892699323, 'samples': 3056256, 'steps': 15917, 'loss/train': 1.8627073764801025}
+08/30/2021 16:07:03 - INFO - __main__ - Step 15919: {'lr': 0.0004891687442226751, 'samples': 3056448, 'steps': 15918, 'loss/train': 1.9882503747940063}
+08/30/2021 16:07:04 - INFO - __main__ - Step 15920: {'lr': 0.0004891671990676522, 'samples': 3056640, 'steps': 15919, 'loss/train': 2.7746639251708984}
+08/30/2021 16:07:04 - INFO - __main__ - Step 15921: {'lr': 0.0004891656538048642, 'samples': 3056832, 'steps': 15920, 'loss/train': 2.682562828063965}
+08/30/2021 16:07:04 - INFO - __main__ - Step 15922: {'lr': 0.0004891641084343118, 'samples': 3057024, 'steps': 15921, 'loss/train': 1.0898919105529785}
+08/30/2021 16:07:05 - INFO - __main__ - Step 15923: {'lr': 0.0004891625629559959, 'samples': 3057216, 'steps': 15922, 'loss/train': 1.7425451278686523}
+08/30/2021 16:07:05 - INFO - __main__ - Step 15924: {'lr': 0.0004891610173699169, 'samples': 3057408, 'steps': 15923, 'loss/train': 1.8265413045883179}
+08/30/2021 16:07:07 - INFO - __main__ - Step 15925: {'lr': 0.0004891594716760757, 'samples': 3057600, 'steps': 15924, 'loss/train': 2.081162214279175}
+08/30/2021 16:07:07 - INFO - __main__ - Step 15926: {'lr': 0.0004891579258744728, 'samples': 3057792, 'steps': 15925, 'loss/train': 1.856448769569397}
+08/30/2021 16:07:07 - INFO - __main__ - Step 15927: {'lr': 0.0004891563799651092, 'samples': 3057984, 'steps': 15926, 'loss/train': 2.0374579429626465}
+08/30/2021 16:07:08 - INFO - __main__ - Step 15928: {'lr': 0.0004891548339479854, 'samples': 3058176, 'steps': 15927, 'loss/train': 1.7977981567382812}
+08/30/2021 16:07:08 - INFO - __main__ - Step 15929: {'lr': 0.0004891532878231021, 'samples': 3058368, 'steps': 15928, 'loss/train': 1.543886423110962}
+08/30/2021 16:07:10 - INFO - __main__ - Step 15930: {'lr': 0.00048915174159046, 'samples': 3058560, 'steps': 15929, 'loss/train': 1.049500584602356}
+08/30/2021 16:07:10 - INFO - __main__ - Step 15931: {'lr': 0.0004891501952500599, 'samples': 3058752, 'steps': 15930, 'loss/train': 1.4056872129440308}
+08/30/2021 16:07:10 - INFO - __main__ - Step 15932: {'lr': 0.0004891486488019023, 'samples': 3058944, 'steps': 15931, 'loss/train': 1.9798353910446167}
+08/30/2021 16:07:11 - INFO - __main__ - Step 15933: {'lr': 0.000489147102245988, 'samples': 3059136, 'steps': 15932, 'loss/train': 0.31406834721565247}
+08/30/2021 16:07:11 - INFO - __main__ - Step 15934: {'lr': 0.0004891455555823179, 'samples': 3059328, 'steps': 15933, 'loss/train': 2.054659605026245}
+08/30/2021 16:07:13 - INFO - __main__ - Step 15935: {'lr': 0.0004891440088108923, 'samples': 3059520, 'steps': 15934, 'loss/train': 2.25657320022583}
+08/30/2021 16:07:13 - INFO - __main__ - Step 15936: {'lr': 0.0004891424619317121, 'samples': 3059712, 'steps': 15935, 'loss/train': 1.7731446027755737}
+08/30/2021 16:07:13 - INFO - __main__ - Step 15937: {'lr': 0.000489140914944778, 'samples': 3059904, 'steps': 15936, 'loss/train': 1.6978503465652466}
+08/30/2021 16:07:14 - INFO - __main__ - Step 15938: {'lr': 0.0004891393678500909, 'samples': 3060096, 'steps': 15937, 'loss/train': 1.7160401344299316}
+08/30/2021 16:07:14 - INFO - __main__ - Step 15939: {'lr': 0.0004891378206476511, 'samples': 3060288, 'steps': 15938, 'loss/train': 0.48282942175865173}
+08/30/2021 16:07:14 - INFO - __main__ - Step 15940: {'lr': 0.0004891362733374595, 'samples': 3060480, 'steps': 15939, 'loss/train': 1.8949224948883057}
+08/30/2021 16:07:17 - INFO - __main__ - Step 15941: {'lr': 0.0004891347259195168, 'samples': 3060672, 'steps': 15940, 'loss/train': 1.5520035028457642}
+08/30/2021 16:07:17 - INFO - __main__ - Step 15942: {'lr': 0.0004891331783938238, 'samples': 3060864, 'steps': 15941, 'loss/train': 1.6616119146347046}
+08/30/2021 16:07:18 - INFO - __main__ - Step 15943: {'lr': 0.000489131630760381, 'samples': 3061056, 'steps': 15942, 'loss/train': 1.7089266777038574}
+08/30/2021 16:07:18 - INFO - __main__ - Step 15944: {'lr': 0.000489130083019189, 'samples': 3061248, 'steps': 15943, 'loss/train': 2.1419475078582764}
+08/30/2021 16:07:18 - INFO - __main__ - Step 15945: {'lr': 0.000489128535170249, 'samples': 3061440, 'steps': 15944, 'loss/train': 1.6969479322433472}
+08/30/2021 16:07:19 - INFO - __main__ - Step 15946: {'lr': 0.0004891269872135611, 'samples': 3061632, 'steps': 15945, 'loss/train': 1.1622493267059326}
+08/30/2021 16:07:19 - INFO - __main__ - Step 15947: {'lr': 0.0004891254391491264, 'samples': 3061824, 'steps': 15946, 'loss/train': 1.6910468339920044}
+08/30/2021 16:07:21 - INFO - __main__ - Step 15948: {'lr': 0.0004891238909769454, 'samples': 3062016, 'steps': 15947, 'loss/train': 1.6272855997085571}
+08/30/2021 16:07:21 - INFO - __main__ - Step 15949: {'lr': 0.0004891223426970189, 'samples': 3062208, 'steps': 15948, 'loss/train': 1.7621570825576782}
+08/30/2021 16:07:21 - INFO - __main__ - Step 15950: {'lr': 0.0004891207943093476, 'samples': 3062400, 'steps': 15949, 'loss/train': 0.6291665434837341}
+08/30/2021 16:07:22 - INFO - __main__ - Step 15951: {'lr': 0.000489119245813932, 'samples': 3062592, 'steps': 15950, 'loss/train': 1.1066741943359375}
+08/30/2021 16:07:22 - INFO - __main__ - Step 15952: {'lr': 0.0004891176972107731, 'samples': 3062784, 'steps': 15951, 'loss/train': 1.4184036254882812}
+08/30/2021 16:07:24 - INFO - __main__ - Step 15953: {'lr': 0.0004891161484998715, 'samples': 3062976, 'steps': 15952, 'loss/train': 1.664896011352539}
+08/30/2021 16:07:25 - INFO - __main__ - Step 15954: {'lr': 0.0004891145996812279, 'samples': 3063168, 'steps': 15953, 'loss/train': 1.8335856199264526}
+08/30/2021 16:07:25 - INFO - __main__ - Step 15955: {'lr': 0.0004891130507548427, 'samples': 3063360, 'steps': 15954, 'loss/train': 1.547168254852295}
+08/30/2021 16:07:25 - INFO - __main__ - Step 15956: {'lr': 0.000489111501720717, 'samples': 3063552, 'steps': 15955, 'loss/train': 1.9942551851272583}
+08/30/2021 16:07:26 - INFO - __main__ - Step 15957: {'lr': 0.0004891099525788514, 'samples': 3063744, 'steps': 15956, 'loss/train': 1.791953206062317}
+08/30/2021 16:07:26 - INFO - __main__ - Step 15958: {'lr': 0.0004891084033292464, 'samples': 3063936, 'steps': 15957, 'loss/train': 1.6415573358535767}
+08/30/2021 16:07:28 - INFO - __main__ - Step 15959: {'lr': 0.0004891068539719031, 'samples': 3064128, 'steps': 15958, 'loss/train': 1.894308090209961}
+08/30/2021 16:07:28 - INFO - __main__ - Step 15960: {'lr': 0.0004891053045068217, 'samples': 3064320, 'steps': 15959, 'loss/train': 2.062399387359619}
+08/30/2021 16:07:28 - INFO - __main__ - Step 15961: {'lr': 0.0004891037549340032, 'samples': 3064512, 'steps': 15960, 'loss/train': 1.6622875928878784}
+08/30/2021 16:07:29 - INFO - __main__ - Step 15962: {'lr': 0.0004891022052534482, 'samples': 3064704, 'steps': 15961, 'loss/train': 1.6348267793655396}
+08/30/2021 16:07:29 - INFO - __main__ - Step 15963: {'lr': 0.0004891006554651574, 'samples': 3064896, 'steps': 15962, 'loss/train': 1.1106070280075073}
+08/30/2021 16:07:31 - INFO - __main__ - Step 15964: {'lr': 0.0004890991055691318, 'samples': 3065088, 'steps': 15963, 'loss/train': 1.455451488494873}
+08/30/2021 16:07:31 - INFO - __main__ - Step 15965: {'lr': 0.0004890975555653716, 'samples': 3065280, 'steps': 15964, 'loss/train': 1.4749478101730347}
+08/30/2021 16:07:31 - INFO - __main__ - Step 15966: {'lr': 0.0004890960054538778, 'samples': 3065472, 'steps': 15965, 'loss/train': 1.6150314807891846}
+08/30/2021 16:07:32 - INFO - __main__ - Step 15967: {'lr': 0.000489094455234651, 'samples': 3065664, 'steps': 15966, 'loss/train': 0.3192380368709564}
+08/30/2021 16:07:32 - INFO - __main__ - Step 15968: {'lr': 0.0004890929049076919, 'samples': 3065856, 'steps': 15967, 'loss/train': 1.7374497652053833}
+08/30/2021 16:07:34 - INFO - __main__ - Step 15969: {'lr': 0.0004890913544730013, 'samples': 3066048, 'steps': 15968, 'loss/train': 1.5663126707077026}
+08/30/2021 16:07:35 - INFO - __main__ - Step 15970: {'lr': 0.0004890898039305798, 'samples': 3066240, 'steps': 15969, 'loss/train': 1.9863234758377075}
+08/30/2021 16:07:35 - INFO - __main__ - Step 15971: {'lr': 0.000489088253280428, 'samples': 3066432, 'steps': 15970, 'loss/train': 1.812970519065857}
+08/30/2021 16:07:35 - INFO - __main__ - Step 15972: {'lr': 0.0004890867025225469, 'samples': 3066624, 'steps': 15971, 'loss/train': 1.6286590099334717}
+08/30/2021 16:07:36 - INFO - __main__ - Step 15973: {'lr': 0.000489085151656937, 'samples': 3066816, 'steps': 15972, 'loss/train': 2.0572667121887207}
+08/30/2021 16:07:37 - INFO - __main__ - Step 15974: {'lr': 0.000489083600683599, 'samples': 3067008, 'steps': 15973, 'loss/train': 0.20823699235916138}
+08/30/2021 16:07:37 - INFO - __main__ - Step 15975: {'lr': 0.0004890820496025335, 'samples': 3067200, 'steps': 15974, 'loss/train': 2.290116310119629}
+08/30/2021 16:07:38 - INFO - __main__ - Step 15976: {'lr': 0.0004890804984137415, 'samples': 3067392, 'steps': 15975, 'loss/train': 1.6490013599395752}
+08/30/2021 16:07:38 - INFO - __main__ - Step 15977: {'lr': 0.0004890789471172233, 'samples': 3067584, 'steps': 15976, 'loss/train': 1.6396937370300293}
+08/30/2021 16:07:38 - INFO - __main__ - Step 15978: {'lr': 0.00048907739571298, 'samples': 3067776, 'steps': 15977, 'loss/train': 1.9426047801971436}
+08/30/2021 16:07:39 - INFO - __main__ - Step 15979: {'lr': 0.000489075844201012, 'samples': 3067968, 'steps': 15978, 'loss/train': 1.6522164344787598}
+08/30/2021 16:07:40 - INFO - __main__ - Step 15980: {'lr': 0.0004890742925813202, 'samples': 3068160, 'steps': 15979, 'loss/train': 1.8167675733566284}
+08/30/2021 16:07:41 - INFO - __main__ - Step 15981: {'lr': 0.0004890727408539051, 'samples': 3068352, 'steps': 15980, 'loss/train': 1.2056710720062256}
+08/30/2021 16:07:41 - INFO - __main__ - Step 15982: {'lr': 0.0004890711890187676, 'samples': 3068544, 'steps': 15981, 'loss/train': 2.293987274169922}
+08/30/2021 16:07:42 - INFO - __main__ - Step 15983: {'lr': 0.0004890696370759085, 'samples': 3068736, 'steps': 15982, 'loss/train': 1.3528395891189575}
+08/30/2021 16:07:42 - INFO - __main__ - Step 15984: {'lr': 0.0004890680850253281, 'samples': 3068928, 'steps': 15983, 'loss/train': 1.4105851650238037}
+08/30/2021 16:07:43 - INFO - __main__ - Step 15985: {'lr': 0.0004890665328670273, 'samples': 3069120, 'steps': 15984, 'loss/train': 1.8543025255203247}
+08/30/2021 16:07:44 - INFO - __main__ - Step 15986: {'lr': 0.0004890649806010067, 'samples': 3069312, 'steps': 15985, 'loss/train': 0.3930068612098694}
+08/30/2021 16:07:44 - INFO - __main__ - Step 15987: {'lr': 0.0004890634282272673, 'samples': 3069504, 'steps': 15986, 'loss/train': 1.812916874885559}
+08/30/2021 16:07:45 - INFO - __main__ - Step 15988: {'lr': 0.0004890618757458096, 'samples': 3069696, 'steps': 15987, 'loss/train': 1.3969653844833374}
+08/30/2021 16:07:45 - INFO - __main__ - Step 15989: {'lr': 0.0004890603231566343, 'samples': 3069888, 'steps': 15988, 'loss/train': 1.9779038429260254}
+08/30/2021 16:07:47 - INFO - __main__ - Step 15990: {'lr': 0.000489058770459742, 'samples': 3070080, 'steps': 15989, 'loss/train': 1.6323916912078857}
+08/30/2021 16:07:47 - INFO - __main__ - Step 15991: {'lr': 0.0004890572176551337, 'samples': 3070272, 'steps': 15990, 'loss/train': 1.7052792310714722}
+08/30/2021 16:07:47 - INFO - __main__ - Step 15992: {'lr': 0.0004890556647428097, 'samples': 3070464, 'steps': 15991, 'loss/train': 1.92897629737854}
+08/30/2021 16:07:48 - INFO - __main__ - Step 15993: {'lr': 0.0004890541117227711, 'samples': 3070656, 'steps': 15992, 'loss/train': 1.7285797595977783}
+08/30/2021 16:07:48 - INFO - __main__ - Step 15994: {'lr': 0.0004890525585950181, 'samples': 3070848, 'steps': 15993, 'loss/train': 1.4235693216323853}
+08/30/2021 16:07:48 - INFO - __main__ - Step 15995: {'lr': 0.000489051005359552, 'samples': 3071040, 'steps': 15994, 'loss/train': 0.4631354510784149}
+08/30/2021 16:07:50 - INFO - __main__ - Step 15996: {'lr': 0.0004890494520163731, 'samples': 3071232, 'steps': 15995, 'loss/train': 4.9341912269592285}
+08/30/2021 16:07:50 - INFO - __main__ - Step 15997: {'lr': 0.0004890478985654823, 'samples': 3071424, 'steps': 15996, 'loss/train': 1.2674771547317505}
+08/30/2021 16:07:51 - INFO - __main__ - Step 15998: {'lr': 0.0004890463450068801, 'samples': 3071616, 'steps': 15997, 'loss/train': 1.4238637685775757}
+08/30/2021 16:07:51 - INFO - __main__ - Step 15999: {'lr': 0.0004890447913405673, 'samples': 3071808, 'steps': 15998, 'loss/train': 1.9229238033294678}
+08/30/2021 16:07:51 - INFO - __main__ - Step 16000: {'lr': 0.0004890432375665447, 'samples': 3072000, 'steps': 15999, 'loss/train': 2.1698992252349854}
+08/30/2021 16:07:53 - INFO - __main__ - Step 16001: {'lr': 0.0004890416836848127, 'samples': 3072192, 'steps': 16000, 'loss/train': 1.5063798427581787}
+08/30/2021 16:07:53 - INFO - __main__ - Step 16002: {'lr': 0.0004890401296953723, 'samples': 3072384, 'steps': 16001, 'loss/train': 1.455306887626648}
+08/30/2021 16:07:54 - INFO - __main__ - Step 16003: {'lr': 0.0004890385755982243, 'samples': 3072576, 'steps': 16002, 'loss/train': 1.368117094039917}
+08/30/2021 16:07:54 - INFO - __main__ - Step 16004: {'lr': 0.0004890370213933691, 'samples': 3072768, 'steps': 16003, 'loss/train': 1.1363060474395752}
+08/30/2021 16:07:54 - INFO - __main__ - Step 16005: {'lr': 0.0004890354670808074, 'samples': 3072960, 'steps': 16004, 'loss/train': 1.667634129524231}
+08/30/2021 16:07:57 - INFO - __main__ - Step 16006: {'lr': 0.0004890339126605401, 'samples': 3073152, 'steps': 16005, 'loss/train': 1.5886671543121338}
+08/30/2021 16:07:57 - INFO - __main__ - Step 16007: {'lr': 0.0004890323581325677, 'samples': 3073344, 'steps': 16006, 'loss/train': 1.4568320512771606}
+08/30/2021 16:07:57 - INFO - __main__ - Step 16008: {'lr': 0.0004890308034968911, 'samples': 3073536, 'steps': 16007, 'loss/train': 1.618986964225769}
+08/30/2021 16:07:58 - INFO - __main__ - Step 16009: {'lr': 0.0004890292487535108, 'samples': 3073728, 'steps': 16008, 'loss/train': 1.9119718074798584}
+08/30/2021 16:07:58 - INFO - __main__ - Step 16010: {'lr': 0.0004890276939024278, 'samples': 3073920, 'steps': 16009, 'loss/train': 2.1318917274475098}
+08/30/2021 16:08:00 - INFO - __main__ - Step 16011: {'lr': 0.0004890261389436424, 'samples': 3074112, 'steps': 16010, 'loss/train': 1.9940615892410278}
+08/30/2021 16:08:01 - INFO - __main__ - Step 16012: {'lr': 0.0004890245838771557, 'samples': 3074304, 'steps': 16011, 'loss/train': 0.35355421900749207}
+08/30/2021 16:08:01 - INFO - __main__ - Step 16013: {'lr': 0.0004890230287029681, 'samples': 3074496, 'steps': 16012, 'loss/train': 0.5573104023933411}
+08/30/2021 16:08:01 - INFO - __main__ - Step 16014: {'lr': 0.0004890214734210805, 'samples': 3074688, 'steps': 16013, 'loss/train': 1.2571091651916504}
+08/30/2021 16:08:02 - INFO - __main__ - Step 16015: {'lr': 0.0004890199180314935, 'samples': 3074880, 'steps': 16014, 'loss/train': 1.6820523738861084}
+08/30/2021 16:08:02 - INFO - __main__ - Step 16016: {'lr': 0.0004890183625342078, 'samples': 3075072, 'steps': 16015, 'loss/train': 1.702893614768982}
+08/30/2021 16:08:03 - INFO - __main__ - Step 16017: {'lr': 0.0004890168069292241, 'samples': 3075264, 'steps': 16016, 'loss/train': 1.690147876739502}
+08/30/2021 16:08:04 - INFO - __main__ - Step 16018: {'lr': 0.000489015251216543, 'samples': 3075456, 'steps': 16017, 'loss/train': 1.5505287647247314}
+08/30/2021 16:08:04 - INFO - __main__ - Step 16019: {'lr': 0.0004890136953961654, 'samples': 3075648, 'steps': 16018, 'loss/train': 1.1830521821975708}
+08/30/2021 16:08:05 - INFO - __main__ - Step 16020: {'lr': 0.000489012139468092, 'samples': 3075840, 'steps': 16019, 'loss/train': 1.4839494228363037}
+08/30/2021 16:08:05 - INFO - __main__ - Step 16021: {'lr': 0.0004890105834323233, 'samples': 3076032, 'steps': 16020, 'loss/train': 1.502497673034668}
+08/30/2021 16:08:06 - INFO - __main__ - Step 16022: {'lr': 0.0004890090272888602, 'samples': 3076224, 'steps': 16021, 'loss/train': 1.6627182960510254}
+08/30/2021 16:08:07 - INFO - __main__ - Step 16023: {'lr': 0.0004890074710377033, 'samples': 3076416, 'steps': 16022, 'loss/train': 1.9242879152297974}
+08/30/2021 16:08:07 - INFO - __main__ - Step 16024: {'lr': 0.0004890059146788532, 'samples': 3076608, 'steps': 16023, 'loss/train': 1.4171985387802124}
+08/30/2021 16:08:08 - INFO - __main__ - Step 16025: {'lr': 0.000489004358212311, 'samples': 3076800, 'steps': 16024, 'loss/train': 2.0105652809143066}
+08/30/2021 16:08:08 - INFO - __main__ - Step 16026: {'lr': 0.0004890028016380769, 'samples': 3076992, 'steps': 16025, 'loss/train': 1.8932466506958008}
+08/30/2021 16:08:10 - INFO - __main__ - Step 16027: {'lr': 0.0004890012449561518, 'samples': 3077184, 'steps': 16026, 'loss/train': 1.5929791927337646}
+08/30/2021 16:08:10 - INFO - __main__ - Step 16028: {'lr': 0.0004889996881665366, 'samples': 3077376, 'steps': 16027, 'loss/train': 1.5297855138778687}
+08/30/2021 16:08:10 - INFO - __main__ - Step 16029: {'lr': 0.0004889981312692317, 'samples': 3077568, 'steps': 16028, 'loss/train': 1.4741088151931763}
+08/30/2021 16:08:11 - INFO - __main__ - Step 16030: {'lr': 0.000488996574264238, 'samples': 3077760, 'steps': 16029, 'loss/train': 0.3136903941631317}
+08/30/2021 16:08:11 - INFO - __main__ - Step 16031: {'lr': 0.000488995017151556, 'samples': 3077952, 'steps': 16030, 'loss/train': 1.9275661706924438}
+08/30/2021 16:08:13 - INFO - __main__ - Step 16032: {'lr': 0.0004889934599311867, 'samples': 3078144, 'steps': 16031, 'loss/train': 1.510998010635376}
+08/30/2021 16:08:13 - INFO - __main__ - Step 16033: {'lr': 0.0004889919026031306, 'samples': 3078336, 'steps': 16032, 'loss/train': 1.4501458406448364}
+08/30/2021 16:08:13 - INFO - __main__ - Step 16034: {'lr': 0.0004889903451673884, 'samples': 3078528, 'steps': 16033, 'loss/train': 1.6799242496490479}
+08/30/2021 16:08:14 - INFO - __main__ - Step 16035: {'lr': 0.0004889887876239608, 'samples': 3078720, 'steps': 16034, 'loss/train': 1.4250009059906006}
+08/30/2021 16:08:14 - INFO - __main__ - Step 16036: {'lr': 0.0004889872299728486, 'samples': 3078912, 'steps': 16035, 'loss/train': 1.598712682723999}
+08/30/2021 16:08:15 - INFO - __main__ - Step 16037: {'lr': 0.0004889856722140525, 'samples': 3079104, 'steps': 16036, 'loss/train': 0.8378870487213135}
+08/30/2021 16:08:16 - INFO - __main__ - Step 16038: {'lr': 0.000488984114347573, 'samples': 3079296, 'steps': 16037, 'loss/train': 1.6544798612594604}
+08/30/2021 16:08:16 - INFO - __main__ - Step 16039: {'lr': 0.000488982556373411, 'samples': 3079488, 'steps': 16038, 'loss/train': 0.9884001612663269}
+08/30/2021 16:08:17 - INFO - __main__ - Step 16040: {'lr': 0.0004889809982915672, 'samples': 3079680, 'steps': 16039, 'loss/train': 1.8656682968139648}
+08/30/2021 16:08:17 - INFO - __main__ - Step 16041: {'lr': 0.0004889794401020422, 'samples': 3079872, 'steps': 16040, 'loss/train': 1.5121309757232666}
+08/30/2021 16:08:18 - INFO - __main__ - Step 16042: {'lr': 0.0004889778818048368, 'samples': 3080064, 'steps': 16041, 'loss/train': 1.3341726064682007}
+08/30/2021 16:08:19 - INFO - __main__ - Step 16043: {'lr': 0.0004889763233999516, 'samples': 3080256, 'steps': 16042, 'loss/train': 1.7305001020431519}
+08/30/2021 16:08:19 - INFO - __main__ - Step 16044: {'lr': 0.0004889747648873874, 'samples': 3080448, 'steps': 16043, 'loss/train': 2.1049811840057373}
+08/30/2021 16:08:19 - INFO - __main__ - Step 16045: {'lr': 0.0004889732062671448, 'samples': 3080640, 'steps': 16044, 'loss/train': 1.8849035501480103}
+08/30/2021 16:08:20 - INFO - __main__ - Step 16046: {'lr': 0.0004889716475392247, 'samples': 3080832, 'steps': 16045, 'loss/train': 1.5957787036895752}
+08/30/2021 16:08:21 - INFO - __main__ - Step 16047: {'lr': 0.0004889700887036275, 'samples': 3081024, 'steps': 16046, 'loss/train': 1.4747272729873657}
+08/30/2021 16:08:22 - INFO - __main__ - Step 16048: {'lr': 0.0004889685297603541, 'samples': 3081216, 'steps': 16047, 'loss/train': 1.2768683433532715}
+08/30/2021 16:08:22 - INFO - __main__ - Step 16049: {'lr': 0.0004889669707094052, 'samples': 3081408, 'steps': 16048, 'loss/train': 1.3526276350021362}
+08/30/2021 16:08:23 - INFO - __main__ - Step 16050: {'lr': 0.0004889654115507815, 'samples': 3081600, 'steps': 16049, 'loss/train': 2.011629343032837}
+08/30/2021 16:08:23 - INFO - __main__ - Step 16051: {'lr': 0.0004889638522844836, 'samples': 3081792, 'steps': 16050, 'loss/train': 1.3644627332687378}
+08/30/2021 16:08:24 - INFO - __main__ - Step 16052: {'lr': 0.0004889622929105123, 'samples': 3081984, 'steps': 16051, 'loss/train': 1.5981725454330444}
+08/30/2021 16:08:25 - INFO - __main__ - Step 16053: {'lr': 0.0004889607334288683, 'samples': 3082176, 'steps': 16052, 'loss/train': 1.5981335639953613}
+08/30/2021 16:08:25 - INFO - __main__ - Step 16054: {'lr': 0.0004889591738395522, 'samples': 3082368, 'steps': 16053, 'loss/train': 1.9253791570663452}
+08/30/2021 16:08:25 - INFO - __main__ - Step 16055: {'lr': 0.0004889576141425649, 'samples': 3082560, 'steps': 16054, 'loss/train': 1.7079644203186035}
+08/30/2021 16:08:26 - INFO - __main__ - Step 16056: {'lr': 0.0004889560543379069, 'samples': 3082752, 'steps': 16055, 'loss/train': 1.6662176847457886}
+08/30/2021 16:08:28 - INFO - __main__ - Step 16057: {'lr': 0.000488954494425579, 'samples': 3082944, 'steps': 16056, 'loss/train': 1.7057243585586548}
+08/30/2021 16:08:28 - INFO - __main__ - Step 16058: {'lr': 0.000488952934405582, 'samples': 3083136, 'steps': 16057, 'loss/train': 2.2320845127105713}
+08/30/2021 16:08:29 - INFO - __main__ - Step 16059: {'lr': 0.0004889513742779164, 'samples': 3083328, 'steps': 16058, 'loss/train': 1.759162425994873}
+08/30/2021 16:08:29 - INFO - __main__ - Step 16060: {'lr': 0.0004889498140425829, 'samples': 3083520, 'steps': 16059, 'loss/train': 0.5264279246330261}
+08/30/2021 16:08:29 - INFO - __main__ - Step 16061: {'lr': 0.0004889482536995825, 'samples': 3083712, 'steps': 16060, 'loss/train': 1.7540335655212402}
+08/30/2021 16:08:30 - INFO - __main__ - Step 16062: {'lr': 0.0004889466932489157, 'samples': 3083904, 'steps': 16061, 'loss/train': 1.7482750415802002}
+08/30/2021 16:08:31 - INFO - __main__ - Step 16063: {'lr': 0.0004889451326905831, 'samples': 3084096, 'steps': 16062, 'loss/train': 1.2973772287368774}
+08/30/2021 16:08:32 - INFO - __main__ - Step 16064: {'lr': 0.0004889435720245855, 'samples': 3084288, 'steps': 16063, 'loss/train': 1.0407685041427612}
+08/30/2021 16:08:32 - INFO - __main__ - Step 16065: {'lr': 0.0004889420112509237, 'samples': 3084480, 'steps': 16064, 'loss/train': 0.8719043135643005}
+08/30/2021 16:08:33 - INFO - __main__ - Step 16066: {'lr': 0.0004889404503695983, 'samples': 3084672, 'steps': 16065, 'loss/train': 0.8405120372772217}
+08/30/2021 16:08:33 - INFO - __main__ - Step 16067: {'lr': 0.0004889388893806099, 'samples': 3084864, 'steps': 16066, 'loss/train': 1.693964958190918}
+08/30/2021 16:08:34 - INFO - __main__ - Step 16068: {'lr': 0.0004889373282839594, 'samples': 3085056, 'steps': 16067, 'loss/train': 1.8568710088729858}
+08/30/2021 16:08:35 - INFO - __main__ - Step 16069: {'lr': 0.0004889357670796474, 'samples': 3085248, 'steps': 16068, 'loss/train': 2.2184221744537354}
+08/30/2021 16:08:35 - INFO - __main__ - Step 16070: {'lr': 0.0004889342057676748, 'samples': 3085440, 'steps': 16069, 'loss/train': 1.2420254945755005}
+08/30/2021 16:08:36 - INFO - __main__ - Step 16071: {'lr': 0.000488932644348042, 'samples': 3085632, 'steps': 16070, 'loss/train': 1.8536574840545654}
+08/30/2021 16:08:36 - INFO - __main__ - Step 16072: {'lr': 0.0004889310828207498, 'samples': 3085824, 'steps': 16071, 'loss/train': 1.2023687362670898}
+08/30/2021 16:08:37 - INFO - __main__ - Step 16073: {'lr': 0.000488929521185799, 'samples': 3086016, 'steps': 16072, 'loss/train': 1.577937126159668}
+08/30/2021 16:08:38 - INFO - __main__ - Step 16074: {'lr': 0.0004889279594431903, 'samples': 3086208, 'steps': 16073, 'loss/train': 1.64153254032135}
+08/30/2021 16:08:38 - INFO - __main__ - Step 16075: {'lr': 0.0004889263975929242, 'samples': 3086400, 'steps': 16074, 'loss/train': 1.453249454498291}
+08/30/2021 16:08:39 - INFO - __main__ - Step 16076: {'lr': 0.0004889248356350016, 'samples': 3086592, 'steps': 16075, 'loss/train': 1.5572229623794556}
+08/30/2021 16:08:39 - INFO - __main__ - Step 16077: {'lr': 0.0004889232735694232, 'samples': 3086784, 'steps': 16076, 'loss/train': 1.7651371955871582}
+08/30/2021 16:08:41 - INFO - __main__ - Step 16078: {'lr': 0.0004889217113961896, 'samples': 3086976, 'steps': 16077, 'loss/train': 1.8475475311279297}
+08/30/2021 16:08:41 - INFO - __main__ - Step 16079: {'lr': 0.0004889201491153016, 'samples': 3087168, 'steps': 16078, 'loss/train': 2.020800828933716}
+08/30/2021 16:08:42 - INFO - __main__ - Step 16080: {'lr': 0.0004889185867267599, 'samples': 3087360, 'steps': 16079, 'loss/train': 2.3029513359069824}
+08/30/2021 16:08:42 - INFO - __main__ - Step 16081: {'lr': 0.0004889170242305652, 'samples': 3087552, 'steps': 16080, 'loss/train': 0.11970590054988861}
+08/30/2021 16:08:42 - INFO - __main__ - Step 16082: {'lr': 0.0004889154616267181, 'samples': 3087744, 'steps': 16081, 'loss/train': 1.6496000289916992}
+08/30/2021 16:08:43 - INFO - __main__ - Step 16083: {'lr': 0.0004889138989152194, 'samples': 3087936, 'steps': 16082, 'loss/train': 1.455633282661438}
+08/30/2021 16:08:44 - INFO - __main__ - Step 16084: {'lr': 0.0004889123360960698, 'samples': 3088128, 'steps': 16083, 'loss/train': 1.4459062814712524}
+08/30/2021 16:08:45 - INFO - __main__ - Step 16085: {'lr': 0.0004889107731692699, 'samples': 3088320, 'steps': 16084, 'loss/train': 1.3344615697860718}
+08/30/2021 16:08:45 - INFO - __main__ - Step 16086: {'lr': 0.0004889092101348206, 'samples': 3088512, 'steps': 16085, 'loss/train': 1.3583908081054688}
+08/30/2021 16:08:45 - INFO - __main__ - Step 16087: {'lr': 0.0004889076469927225, 'samples': 3088704, 'steps': 16086, 'loss/train': 1.5506062507629395}
+08/30/2021 16:08:46 - INFO - __main__ - Step 16088: {'lr': 0.0004889060837429762, 'samples': 3088896, 'steps': 16087, 'loss/train': 1.8411803245544434}
+08/30/2021 16:08:47 - INFO - __main__ - Step 16089: {'lr': 0.0004889045203855826, 'samples': 3089088, 'steps': 16088, 'loss/train': 1.8212236166000366}
+08/30/2021 16:08:48 - INFO - __main__ - Step 16090: {'lr': 0.0004889029569205423, 'samples': 3089280, 'steps': 16089, 'loss/train': 1.8571813106536865}
+08/30/2021 16:08:48 - INFO - __main__ - Step 16091: {'lr': 0.0004889013933478559, 'samples': 3089472, 'steps': 16090, 'loss/train': 1.8308440446853638}
+08/30/2021 16:08:48 - INFO - __main__ - Step 16092: {'lr': 0.0004888998296675243, 'samples': 3089664, 'steps': 16091, 'loss/train': 1.9102141857147217}
+08/30/2021 16:08:49 - INFO - __main__ - Step 16093: {'lr': 0.0004888982658795482, 'samples': 3089856, 'steps': 16092, 'loss/train': 1.6870355606079102}
+08/30/2021 16:08:49 - INFO - __main__ - Step 16094: {'lr': 0.0004888967019839282, 'samples': 3090048, 'steps': 16093, 'loss/train': 1.6751246452331543}
+08/30/2021 16:08:51 - INFO - __main__ - Step 16095: {'lr': 0.000488895137980665, 'samples': 3090240, 'steps': 16094, 'loss/train': 1.1235871315002441}
+08/30/2021 16:08:51 - INFO - __main__ - Step 16096: {'lr': 0.0004888935738697593, 'samples': 3090432, 'steps': 16095, 'loss/train': 0.3828321099281311}
+08/30/2021 16:08:52 - INFO - __main__ - Step 16097: {'lr': 0.0004888920096512118, 'samples': 3090624, 'steps': 16096, 'loss/train': 1.1133627891540527}
+08/30/2021 16:08:52 - INFO - __main__ - Step 16098: {'lr': 0.0004888904453250233, 'samples': 3090816, 'steps': 16097, 'loss/train': 1.6914875507354736}
+08/30/2021 16:08:52 - INFO - __main__ - Step 16099: {'lr': 0.0004888888808911946, 'samples': 3091008, 'steps': 16098, 'loss/train': 1.1670382022857666}
+08/30/2021 16:08:54 - INFO - __main__ - Step 16100: {'lr': 0.0004888873163497261, 'samples': 3091200, 'steps': 16099, 'loss/train': 2.175337076187134}
+08/30/2021 16:08:54 - INFO - __main__ - Step 16101: {'lr': 0.0004888857517006186, 'samples': 3091392, 'steps': 16100, 'loss/train': 1.7574958801269531}
+08/30/2021 16:08:55 - INFO - __main__ - Step 16102: {'lr': 0.000488884186943873, 'samples': 3091584, 'steps': 16101, 'loss/train': 1.4863200187683105}
+08/30/2021 16:08:55 - INFO - __main__ - Step 16103: {'lr': 0.0004888826220794899, 'samples': 3091776, 'steps': 16102, 'loss/train': 1.8977420330047607}
+08/30/2021 16:08:56 - INFO - __main__ - Step 16104: {'lr': 0.0004888810571074698, 'samples': 3091968, 'steps': 16103, 'loss/train': 1.5029984712600708}
+08/30/2021 16:08:56 - INFO - __main__ - Step 16105: {'lr': 0.0004888794920278137, 'samples': 3092160, 'steps': 16104, 'loss/train': 1.0788410902023315}
+08/30/2021 16:08:57 - INFO - __main__ - Step 16106: {'lr': 0.0004888779268405223, 'samples': 3092352, 'steps': 16105, 'loss/train': 2.3209078311920166}
+08/30/2021 16:08:58 - INFO - __main__ - Step 16107: {'lr': 0.0004888763615455959, 'samples': 3092544, 'steps': 16106, 'loss/train': 0.9094582200050354}
+08/30/2021 16:08:58 - INFO - __main__ - Step 16108: {'lr': 0.0004888747961430358, 'samples': 3092736, 'steps': 16107, 'loss/train': 2.0828287601470947}
+08/30/2021 16:08:59 - INFO - __main__ - Step 16109: {'lr': 0.0004888732306328422, 'samples': 3092928, 'steps': 16108, 'loss/train': 1.569623589515686}
+08/30/2021 16:08:59 - INFO - __main__ - Step 16110: {'lr': 0.000488871665015016, 'samples': 3093120, 'steps': 16109, 'loss/train': 1.9902257919311523}
+08/30/2021 16:09:01 - INFO - __main__ - Step 16111: {'lr': 0.0004888700992895581, 'samples': 3093312, 'steps': 16110, 'loss/train': 1.6226801872253418}
+08/30/2021 16:09:01 - INFO - __main__ - Step 16112: {'lr': 0.0004888685334564688, 'samples': 3093504, 'steps': 16111, 'loss/train': 1.4757969379425049}
+08/30/2021 16:09:02 - INFO - __main__ - Step 16113: {'lr': 0.0004888669675157492, 'samples': 3093696, 'steps': 16112, 'loss/train': 1.684322476387024}
+08/30/2021 16:09:02 - INFO - __main__ - Step 16114: {'lr': 0.0004888654014673998, 'samples': 3093888, 'steps': 16113, 'loss/train': 0.572607696056366}
+08/30/2021 16:09:02 - INFO - __main__ - Step 16115: {'lr': 0.0004888638353114212, 'samples': 3094080, 'steps': 16114, 'loss/train': 3.351923704147339}
+08/30/2021 16:09:04 - INFO - __main__ - Step 16116: {'lr': 0.0004888622690478144, 'samples': 3094272, 'steps': 16115, 'loss/train': 2.2719335556030273}
+08/30/2021 16:09:05 - INFO - __main__ - Step 16117: {'lr': 0.0004888607026765799, 'samples': 3094464, 'steps': 16116, 'loss/train': 1.4435566663742065}
+08/30/2021 16:09:05 - INFO - __main__ - Step 16118: {'lr': 0.0004888591361977184, 'samples': 3094656, 'steps': 16117, 'loss/train': 2.0642950534820557}
+08/30/2021 16:09:05 - INFO - __main__ - Step 16119: {'lr': 0.0004888575696112308, 'samples': 3094848, 'steps': 16118, 'loss/train': 1.451029658317566}
+08/30/2021 16:09:06 - INFO - __main__ - Step 16120: {'lr': 0.0004888560029171175, 'samples': 3095040, 'steps': 16119, 'loss/train': 0.7746983766555786}
+08/30/2021 16:09:07 - INFO - __main__ - Step 16121: {'lr': 0.0004888544361153794, 'samples': 3095232, 'steps': 16120, 'loss/train': 2.073786973953247}
+08/30/2021 16:09:08 - INFO - __main__ - Step 16122: {'lr': 0.0004888528692060173, 'samples': 3095424, 'steps': 16121, 'loss/train': 1.788468837738037}
+08/30/2021 16:09:08 - INFO - __main__ - Step 16123: {'lr': 0.0004888513021890316, 'samples': 3095616, 'steps': 16122, 'loss/train': 1.5074615478515625}
+08/30/2021 16:09:08 - INFO - __main__ - Step 16124: {'lr': 0.0004888497350644234, 'samples': 3095808, 'steps': 16123, 'loss/train': 1.744973063468933}
+08/30/2021 16:09:09 - INFO - __main__ - Step 16125: {'lr': 0.000488848167832193, 'samples': 3096000, 'steps': 16124, 'loss/train': 1.935605764389038}
+08/30/2021 16:09:09 - INFO - __main__ - Step 16126: {'lr': 0.0004888466004923413, 'samples': 3096192, 'steps': 16125, 'loss/train': 1.6238654851913452}
+08/30/2021 16:09:10 - INFO - __main__ - Step 16127: {'lr': 0.0004888450330448692, 'samples': 3096384, 'steps': 16126, 'loss/train': 1.3200464248657227}
+08/30/2021 16:09:11 - INFO - __main__ - Step 16128: {'lr': 0.000488843465489777, 'samples': 3096576, 'steps': 16127, 'loss/train': 2.069633960723877}
+08/30/2021 16:09:11 - INFO - __main__ - Step 16129: {'lr': 0.0004888418978270658, 'samples': 3096768, 'steps': 16128, 'loss/train': 1.963121771812439}
+08/30/2021 16:09:12 - INFO - __main__ - Step 16130: {'lr': 0.000488840330056736, 'samples': 3096960, 'steps': 16129, 'loss/train': 0.6227633953094482}
+08/30/2021 16:09:12 - INFO - __main__ - Step 16131: {'lr': 0.0004888387621787885, 'samples': 3097152, 'steps': 16130, 'loss/train': 1.151824712753296}
+08/30/2021 16:09:14 - INFO - __main__ - Step 16132: {'lr': 0.0004888371941932239, 'samples': 3097344, 'steps': 16131, 'loss/train': 1.8692610263824463}
+08/30/2021 16:09:14 - INFO - __main__ - Step 16133: {'lr': 0.000488835626100043, 'samples': 3097536, 'steps': 16132, 'loss/train': 2.0648441314697266}
+08/30/2021 16:09:15 - INFO - __main__ - Step 16134: {'lr': 0.0004888340578992464, 'samples': 3097728, 'steps': 16133, 'loss/train': 1.5093820095062256}
+08/30/2021 16:09:15 - INFO - __main__ - Step 16135: {'lr': 0.0004888324895908349, 'samples': 3097920, 'steps': 16134, 'loss/train': 0.14670990407466888}
+08/30/2021 16:09:15 - INFO - __main__ - Step 16136: {'lr': 0.0004888309211748091, 'samples': 3098112, 'steps': 16135, 'loss/train': 2.1670074462890625}
+08/30/2021 16:09:17 - INFO - __main__ - Step 16137: {'lr': 0.0004888293526511697, 'samples': 3098304, 'steps': 16136, 'loss/train': 1.357384204864502}
+08/30/2021 16:09:18 - INFO - __main__ - Step 16138: {'lr': 0.0004888277840199177, 'samples': 3098496, 'steps': 16137, 'loss/train': 2.0959296226501465}
+08/30/2021 16:09:18 - INFO - __main__ - Step 16139: {'lr': 0.0004888262152810534, 'samples': 3098688, 'steps': 16138, 'loss/train': 1.4581689834594727}
+08/30/2021 16:09:19 - INFO - __main__ - Step 16140: {'lr': 0.0004888246464345779, 'samples': 3098880, 'steps': 16139, 'loss/train': 1.218555212020874}
+08/30/2021 16:09:19 - INFO - __main__ - Step 16141: {'lr': 0.0004888230774804915, 'samples': 3099072, 'steps': 16140, 'loss/train': 2.924306631088257}
+08/30/2021 16:09:19 - INFO - __main__ - Step 16142: {'lr': 0.0004888215084187952, 'samples': 3099264, 'steps': 16141, 'loss/train': 1.1649971008300781}
+08/30/2021 16:09:20 - INFO - __main__ - Step 16143: {'lr': 0.0004888199392494896, 'samples': 3099456, 'steps': 16142, 'loss/train': 1.8804823160171509}
+08/30/2021 16:09:21 - INFO - __main__ - Step 16144: {'lr': 0.0004888183699725755, 'samples': 3099648, 'steps': 16143, 'loss/train': 1.9456937313079834}
+08/30/2021 16:09:22 - INFO - __main__ - Step 16145: {'lr': 0.0004888168005880533, 'samples': 3099840, 'steps': 16144, 'loss/train': 1.3489423990249634}
+08/30/2021 16:09:22 - INFO - __main__ - Step 16146: {'lr': 0.0004888152310959242, 'samples': 3100032, 'steps': 16145, 'loss/train': 2.2964887619018555}
+08/30/2021 16:09:23 - INFO - __main__ - Step 16147: {'lr': 0.0004888136614961885, 'samples': 3100224, 'steps': 16146, 'loss/train': 1.5480968952178955}
+08/30/2021 16:09:23 - INFO - __main__ - Step 16148: {'lr': 0.000488812091788847, 'samples': 3100416, 'steps': 16147, 'loss/train': 1.7133764028549194}
+08/30/2021 16:09:23 - INFO - __main__ - Step 16149: {'lr': 0.0004888105219739005, 'samples': 3100608, 'steps': 16148, 'loss/train': 1.5252094268798828}
+08/30/2021 16:09:25 - INFO - __main__ - Step 16150: {'lr': 0.0004888089520513497, 'samples': 3100800, 'steps': 16149, 'loss/train': 2.347001314163208}
+08/30/2021 16:09:25 - INFO - __main__ - Step 16151: {'lr': 0.0004888073820211952, 'samples': 3100992, 'steps': 16150, 'loss/train': 1.6128660440444946}
+08/30/2021 16:09:26 - INFO - __main__ - Step 16152: {'lr': 0.0004888058118834379, 'samples': 3101184, 'steps': 16151, 'loss/train': 1.2262918949127197}
+08/30/2021 16:09:26 - INFO - __main__ - Step 16153: {'lr': 0.0004888042416380784, 'samples': 3101376, 'steps': 16152, 'loss/train': 1.3816686868667603}
+08/30/2021 16:09:26 - INFO - __main__ - Step 16154: {'lr': 0.0004888026712851172, 'samples': 3101568, 'steps': 16153, 'loss/train': 1.3808690309524536}
+08/30/2021 16:09:28 - INFO - __main__ - Step 16155: {'lr': 0.0004888011008245554, 'samples': 3101760, 'steps': 16154, 'loss/train': 2.342851400375366}
+08/30/2021 16:09:28 - INFO - __main__ - Step 16156: {'lr': 0.0004887995302563934, 'samples': 3101952, 'steps': 16155, 'loss/train': 1.524072527885437}
+08/30/2021 16:09:29 - INFO - __main__ - Step 16157: {'lr': 0.000488797959580632, 'samples': 3102144, 'steps': 16156, 'loss/train': 1.9407135248184204}
+08/30/2021 16:09:29 - INFO - __main__ - Step 16158: {'lr': 0.000488796388797272, 'samples': 3102336, 'steps': 16157, 'loss/train': 1.8427869081497192}
+08/30/2021 16:09:29 - INFO - __main__ - Step 16159: {'lr': 0.0004887948179063139, 'samples': 3102528, 'steps': 16158, 'loss/train': 1.2670528888702393}
+08/30/2021 16:09:31 - INFO - __main__ - Step 16160: {'lr': 0.0004887932469077587, 'samples': 3102720, 'steps': 16159, 'loss/train': 1.7608425617218018}
+08/30/2021 16:09:32 - INFO - __main__ - Step 16161: {'lr': 0.0004887916758016069, 'samples': 3102912, 'steps': 16160, 'loss/train': 1.6997241973876953}
+08/30/2021 16:09:32 - INFO - __main__ - Step 16162: {'lr': 0.0004887901045878592, 'samples': 3103104, 'steps': 16161, 'loss/train': 1.8640961647033691}
+08/30/2021 16:09:33 - INFO - __main__ - Step 16163: {'lr': 0.0004887885332665165, 'samples': 3103296, 'steps': 16162, 'loss/train': 1.8507424592971802}
+08/30/2021 16:09:33 - INFO - __main__ - Step 16164: {'lr': 0.0004887869618375793, 'samples': 3103488, 'steps': 16163, 'loss/train': 1.8012827634811401}
+08/30/2021 16:09:34 - INFO - __main__ - Step 16165: {'lr': 0.0004887853903010483, 'samples': 3103680, 'steps': 16164, 'loss/train': 1.77405846118927}
+08/30/2021 16:09:35 - INFO - __main__ - Step 16166: {'lr': 0.0004887838186569244, 'samples': 3103872, 'steps': 16165, 'loss/train': 1.9588273763656616}
+08/30/2021 16:09:35 - INFO - __main__ - Step 16167: {'lr': 0.0004887822469052081, 'samples': 3104064, 'steps': 16166, 'loss/train': 1.5669358968734741}
+08/30/2021 16:09:35 - INFO - __main__ - Step 16168: {'lr': 0.0004887806750459002, 'samples': 3104256, 'steps': 16167, 'loss/train': 1.1243661642074585}
+08/30/2021 16:09:36 - INFO - __main__ - Step 16169: {'lr': 0.0004887791030790016, 'samples': 3104448, 'steps': 16168, 'loss/train': 0.7587945461273193}
+08/30/2021 16:09:37 - INFO - __main__ - Step 16170: {'lr': 0.0004887775310045126, 'samples': 3104640, 'steps': 16169, 'loss/train': 1.7444339990615845}
+08/30/2021 16:09:38 - INFO - __main__ - Step 16171: {'lr': 0.0004887759588224342, 'samples': 3104832, 'steps': 16170, 'loss/train': 1.7415778636932373}
+08/30/2021 16:09:38 - INFO - __main__ - Step 16172: {'lr': 0.000488774386532767, 'samples': 3105024, 'steps': 16171, 'loss/train': 1.9292267560958862}
+08/30/2021 16:09:39 - INFO - __main__ - Step 16173: {'lr': 0.0004887728141355118, 'samples': 3105216, 'steps': 16172, 'loss/train': 1.68677818775177}
+08/30/2021 16:09:39 - INFO - __main__ - Step 16174: {'lr': 0.0004887712416306693, 'samples': 3105408, 'steps': 16173, 'loss/train': 1.582221269607544}
+08/30/2021 16:09:39 - INFO - __main__ - Step 16175: {'lr': 0.00048876966901824, 'samples': 3105600, 'steps': 16174, 'loss/train': 3.0712389945983887}
+08/30/2021 16:09:41 - INFO - __main__ - Step 16176: {'lr': 0.0004887680962982249, 'samples': 3105792, 'steps': 16175, 'loss/train': 1.2103501558303833}
+08/30/2021 16:09:41 - INFO - __main__ - Step 16177: {'lr': 0.0004887665234706247, 'samples': 3105984, 'steps': 16176, 'loss/train': 0.9753164052963257}
+08/30/2021 16:09:42 - INFO - __main__ - Step 16178: {'lr': 0.0004887649505354398, 'samples': 3106176, 'steps': 16177, 'loss/train': 1.9455859661102295}
+08/30/2021 16:09:42 - INFO - __main__ - Step 16179: {'lr': 0.000488763377492671, 'samples': 3106368, 'steps': 16178, 'loss/train': 2.0331685543060303}
+08/30/2021 16:09:42 - INFO - __main__ - Step 16180: {'lr': 0.0004887618043423194, 'samples': 3106560, 'steps': 16179, 'loss/train': 1.3366820812225342}
+08/30/2021 16:09:44 - INFO - __main__ - Step 16181: {'lr': 0.0004887602310843852, 'samples': 3106752, 'steps': 16180, 'loss/train': 1.2191157341003418}
+08/30/2021 16:09:44 - INFO - __main__ - Step 16182: {'lr': 0.0004887586577188694, 'samples': 3106944, 'steps': 16181, 'loss/train': 1.6067984104156494}
+08/30/2021 16:09:45 - INFO - __main__ - Step 16183: {'lr': 0.0004887570842457726, 'samples': 3107136, 'steps': 16182, 'loss/train': 1.8974665403366089}
+08/30/2021 16:09:45 - INFO - __main__ - Step 16184: {'lr': 0.0004887555106650956, 'samples': 3107328, 'steps': 16183, 'loss/train': 1.5397377014160156}
+08/30/2021 16:09:46 - INFO - __main__ - Step 16185: {'lr': 0.000488753936976839, 'samples': 3107520, 'steps': 16184, 'loss/train': 1.5278619527816772}
+08/30/2021 16:09:47 - INFO - __main__ - Step 16186: {'lr': 0.0004887523631810036, 'samples': 3107712, 'steps': 16185, 'loss/train': 1.9503189325332642}
+08/30/2021 16:09:48 - INFO - __main__ - Step 16187: {'lr': 0.00048875078927759, 'samples': 3107904, 'steps': 16186, 'loss/train': 1.579522967338562}
+08/30/2021 16:09:48 - INFO - __main__ - Step 16188: {'lr': 0.000488749215266599, 'samples': 3108096, 'steps': 16187, 'loss/train': 1.55048406124115}
+08/30/2021 16:09:48 - INFO - __main__ - Step 16189: {'lr': 0.0004887476411480314, 'samples': 3108288, 'steps': 16188, 'loss/train': 1.6580860614776611}
+08/30/2021 16:09:49 - INFO - __main__ - Step 16190: {'lr': 0.0004887460669218877, 'samples': 3108480, 'steps': 16189, 'loss/train': 2.1892404556274414}
+08/30/2021 16:09:49 - INFO - __main__ - Step 16191: {'lr': 0.0004887444925881688, 'samples': 3108672, 'steps': 16190, 'loss/train': 1.9593427181243896}
+08/30/2021 16:09:50 - INFO - __main__ - Step 16192: {'lr': 0.0004887429181468752, 'samples': 3108864, 'steps': 16191, 'loss/train': 1.5536094903945923}
+08/30/2021 16:09:51 - INFO - __main__ - Step 16193: {'lr': 0.0004887413435980077, 'samples': 3109056, 'steps': 16192, 'loss/train': 1.3946034908294678}
+08/30/2021 16:09:51 - INFO - __main__ - Step 16194: {'lr': 0.0004887397689415672, 'samples': 3109248, 'steps': 16193, 'loss/train': 1.8941177129745483}
+08/30/2021 16:09:52 - INFO - __main__ - Step 16195: {'lr': 0.0004887381941775541, 'samples': 3109440, 'steps': 16194, 'loss/train': 1.5038566589355469}
+08/30/2021 16:09:52 - INFO - __main__ - Step 16196: {'lr': 0.0004887366193059693, 'samples': 3109632, 'steps': 16195, 'loss/train': 2.350515127182007}
+08/30/2021 16:09:54 - INFO - __main__ - Step 16197: {'lr': 0.0004887350443268134, 'samples': 3109824, 'steps': 16196, 'loss/train': 2.0816149711608887}
+08/30/2021 16:09:54 - INFO - __main__ - Step 16198: {'lr': 0.0004887334692400872, 'samples': 3110016, 'steps': 16197, 'loss/train': 2.001119375228882}
+08/30/2021 16:09:54 - INFO - __main__ - Step 16199: {'lr': 0.0004887318940457915, 'samples': 3110208, 'steps': 16198, 'loss/train': 2.252450466156006}
+08/30/2021 16:09:55 - INFO - __main__ - Step 16200: {'lr': 0.0004887303187439267, 'samples': 3110400, 'steps': 16199, 'loss/train': 1.8264209032058716}
+08/30/2021 16:09:55 - INFO - __main__ - Step 16201: {'lr': 0.0004887287433344939, 'samples': 3110592, 'steps': 16200, 'loss/train': 2.057054281234741}
+08/30/2021 16:09:57 - INFO - __main__ - Step 16202: {'lr': 0.0004887271678174935, 'samples': 3110784, 'steps': 16201, 'loss/train': 1.7432345151901245}
+08/30/2021 16:09:57 - INFO - __main__ - Step 16203: {'lr': 0.0004887255921929264, 'samples': 3110976, 'steps': 16202, 'loss/train': 1.7855374813079834}
+08/30/2021 16:09:57 - INFO - __main__ - Step 16204: {'lr': 0.0004887240164607931, 'samples': 3111168, 'steps': 16203, 'loss/train': 1.6861077547073364}
+08/30/2021 16:09:58 - INFO - __main__ - Step 16205: {'lr': 0.0004887224406210945, 'samples': 3111360, 'steps': 16204, 'loss/train': 1.757550597190857}
+08/30/2021 16:09:58 - INFO - __main__ - Step 16206: {'lr': 0.0004887208646738312, 'samples': 3111552, 'steps': 16205, 'loss/train': 1.7205955982208252}
+08/30/2021 16:10:00 - INFO - __main__ - Step 16207: {'lr': 0.000488719288619004, 'samples': 3111744, 'steps': 16206, 'loss/train': 1.0609853267669678}
+08/30/2021 16:10:00 - INFO - __main__ - Step 16208: {'lr': 0.0004887177124566136, 'samples': 3111936, 'steps': 16207, 'loss/train': 1.9943522214889526}
+08/30/2021 16:10:01 - INFO - __main__ - Step 16209: {'lr': 0.0004887161361866607, 'samples': 3112128, 'steps': 16208, 'loss/train': 2.03987455368042}
+08/30/2021 16:10:01 - INFO - __main__ - Step 16210: {'lr': 0.000488714559809146, 'samples': 3112320, 'steps': 16209, 'loss/train': 1.0090466737747192}
+08/30/2021 16:10:01 - INFO - __main__ - Step 16211: {'lr': 0.0004887129833240703, 'samples': 3112512, 'steps': 16210, 'loss/train': 2.009734630584717}
+08/30/2021 16:10:02 - INFO - __main__ - Step 16212: {'lr': 0.000488711406731434, 'samples': 3112704, 'steps': 16211, 'loss/train': 2.1733686923980713}
+08/30/2021 16:10:04 - INFO - __main__ - Step 16213: {'lr': 0.0004887098300312381, 'samples': 3112896, 'steps': 16212, 'loss/train': 2.4037039279937744}
+08/30/2021 16:10:04 - INFO - __main__ - Step 16214: {'lr': 0.0004887082532234832, 'samples': 3113088, 'steps': 16213, 'loss/train': 1.0594024658203125}
+08/30/2021 16:10:05 - INFO - __main__ - Step 16215: {'lr': 0.0004887066763081702, 'samples': 3113280, 'steps': 16214, 'loss/train': 1.5682018995285034}
+08/30/2021 16:10:05 - INFO - __main__ - Step 16216: {'lr': 0.0004887050992852995, 'samples': 3113472, 'steps': 16215, 'loss/train': 2.072334051132202}
+08/30/2021 16:10:05 - INFO - __main__ - Step 16217: {'lr': 0.000488703522154872, 'samples': 3113664, 'steps': 16216, 'loss/train': 1.8428153991699219}
+08/30/2021 16:10:07 - INFO - __main__ - Step 16218: {'lr': 0.0004887019449168884, 'samples': 3113856, 'steps': 16217, 'loss/train': 1.2231703996658325}
+08/30/2021 16:10:08 - INFO - __main__ - Step 16219: {'lr': 0.0004887003675713493, 'samples': 3114048, 'steps': 16218, 'loss/train': 1.609653115272522}
+08/30/2021 16:10:08 - INFO - __main__ - Step 16220: {'lr': 0.0004886987901182556, 'samples': 3114240, 'steps': 16219, 'loss/train': 0.17627251148223877}
+08/30/2021 16:10:08 - INFO - __main__ - Step 16221: {'lr': 0.0004886972125576079, 'samples': 3114432, 'steps': 16220, 'loss/train': 0.09967661648988724}
+08/30/2021 16:10:09 - INFO - __main__ - Step 16222: {'lr': 0.0004886956348894069, 'samples': 3114624, 'steps': 16221, 'loss/train': 1.9792263507843018}
+08/30/2021 16:10:09 - INFO - __main__ - Step 16223: {'lr': 0.0004886940571136533, 'samples': 3114816, 'steps': 16222, 'loss/train': 1.4621689319610596}
+08/30/2021 16:10:11 - INFO - __main__ - Step 16224: {'lr': 0.0004886924792303479, 'samples': 3115008, 'steps': 16223, 'loss/train': 1.6258628368377686}
+08/30/2021 16:10:11 - INFO - __main__ - Step 16225: {'lr': 0.0004886909012394913, 'samples': 3115200, 'steps': 16224, 'loss/train': 1.3522077798843384}
+08/30/2021 16:10:11 - INFO - __main__ - Step 16226: {'lr': 0.0004886893231410844, 'samples': 3115392, 'steps': 16225, 'loss/train': 2.247959613800049}
+08/30/2021 16:10:12 - INFO - __main__ - Step 16227: {'lr': 0.0004886877449351276, 'samples': 3115584, 'steps': 16226, 'loss/train': 1.8723901510238647}
+08/30/2021 16:10:12 - INFO - __main__ - Step 16228: {'lr': 0.0004886861666216219, 'samples': 3115776, 'steps': 16227, 'loss/train': 1.1099066734313965}
+08/30/2021 16:10:14 - INFO - __main__ - Step 16229: {'lr': 0.0004886845882005679, 'samples': 3115968, 'steps': 16228, 'loss/train': 1.552213191986084}
+08/30/2021 16:10:14 - INFO - __main__ - Step 16230: {'lr': 0.0004886830096719662, 'samples': 3116160, 'steps': 16229, 'loss/train': 1.9366902112960815}
+08/30/2021 16:10:14 - INFO - __main__ - Step 16231: {'lr': 0.0004886814310358176, 'samples': 3116352, 'steps': 16230, 'loss/train': 1.5782767534255981}
+08/30/2021 16:10:15 - INFO - __main__ - Step 16232: {'lr': 0.000488679852292123, 'samples': 3116544, 'steps': 16231, 'loss/train': 1.4731717109680176}
+08/30/2021 16:10:15 - INFO - __main__ - Step 16233: {'lr': 0.0004886782734408828, 'samples': 3116736, 'steps': 16232, 'loss/train': 2.0903234481811523}
+08/30/2021 16:10:17 - INFO - __main__ - Step 16234: {'lr': 0.0004886766944820979, 'samples': 3116928, 'steps': 16233, 'loss/train': 0.8610385060310364}
+08/30/2021 16:10:17 - INFO - __main__ - Step 16235: {'lr': 0.0004886751154157689, 'samples': 3117120, 'steps': 16234, 'loss/train': 1.0175727605819702}
+08/30/2021 16:10:17 - INFO - __main__ - Step 16236: {'lr': 0.0004886735362418967, 'samples': 3117312, 'steps': 16235, 'loss/train': 1.5067758560180664}
+08/30/2021 16:10:18 - INFO - __main__ - Step 16237: {'lr': 0.0004886719569604818, 'samples': 3117504, 'steps': 16236, 'loss/train': 1.7044957876205444}
+08/30/2021 16:10:18 - INFO - __main__ - Step 16238: {'lr': 0.000488670377571525, 'samples': 3117696, 'steps': 16237, 'loss/train': 3.1742258071899414}
+08/30/2021 16:10:19 - INFO - __main__ - Step 16239: {'lr': 0.0004886687980750271, 'samples': 3117888, 'steps': 16238, 'loss/train': 2.278348684310913}
+08/30/2021 16:10:20 - INFO - __main__ - Step 16240: {'lr': 0.0004886672184709886, 'samples': 3118080, 'steps': 16239, 'loss/train': 1.5339815616607666}
+08/30/2021 16:10:20 - INFO - __main__ - Step 16241: {'lr': 0.0004886656387594104, 'samples': 3118272, 'steps': 16240, 'loss/train': 0.7528780698776245}
+08/30/2021 16:10:21 - INFO - __main__ - Step 16242: {'lr': 0.0004886640589402932, 'samples': 3118464, 'steps': 16241, 'loss/train': 1.4154741764068604}
+08/30/2021 16:10:21 - INFO - __main__ - Step 16243: {'lr': 0.0004886624790136375, 'samples': 3118656, 'steps': 16242, 'loss/train': 1.8899236917495728}
+08/30/2021 16:10:22 - INFO - __main__ - Step 16244: {'lr': 0.0004886608989794443, 'samples': 3118848, 'steps': 16243, 'loss/train': 1.998671293258667}
+08/30/2021 16:10:23 - INFO - __main__ - Step 16245: {'lr': 0.0004886593188377142, 'samples': 3119040, 'steps': 16244, 'loss/train': 1.9466640949249268}
+08/30/2021 16:10:23 - INFO - __main__ - Step 16246: {'lr': 0.0004886577385884478, 'samples': 3119232, 'steps': 16245, 'loss/train': 1.231416940689087}
+08/30/2021 16:10:24 - INFO - __main__ - Step 16247: {'lr': 0.0004886561582316458, 'samples': 3119424, 'steps': 16246, 'loss/train': 1.6249898672103882}
+08/30/2021 16:10:24 - INFO - __main__ - Step 16248: {'lr': 0.0004886545777673093, 'samples': 3119616, 'steps': 16247, 'loss/train': 1.663931131362915}
+08/30/2021 16:10:26 - INFO - __main__ - Step 16249: {'lr': 0.0004886529971954385, 'samples': 3119808, 'steps': 16248, 'loss/train': 1.503287672996521}
+08/30/2021 16:10:26 - INFO - __main__ - Step 16250: {'lr': 0.0004886514165160345, 'samples': 3120000, 'steps': 16249, 'loss/train': 0.7937673330307007}
+08/30/2021 16:10:26 - INFO - __main__ - Step 16251: {'lr': 0.0004886498357290979, 'samples': 3120192, 'steps': 16250, 'loss/train': 3.2912514209747314}
+08/30/2021 16:10:27 - INFO - __main__ - Step 16252: {'lr': 0.0004886482548346291, 'samples': 3120384, 'steps': 16251, 'loss/train': 0.1299923211336136}
+08/30/2021 16:10:27 - INFO - __main__ - Step 16253: {'lr': 0.0004886466738326293, 'samples': 3120576, 'steps': 16252, 'loss/train': 0.14120961725711823}
+08/30/2021 16:10:27 - INFO - __main__ - Step 16254: {'lr': 0.000488645092723099, 'samples': 3120768, 'steps': 16253, 'loss/train': 1.906154990196228}
+08/30/2021 16:10:29 - INFO - __main__ - Step 16255: {'lr': 0.0004886435115060388, 'samples': 3120960, 'steps': 16254, 'loss/train': 1.6424577236175537}
+08/30/2021 16:10:29 - INFO - __main__ - Step 16256: {'lr': 0.0004886419301814495, 'samples': 3121152, 'steps': 16255, 'loss/train': 1.7797577381134033}
+08/30/2021 16:10:30 - INFO - __main__ - Step 16257: {'lr': 0.0004886403487493319, 'samples': 3121344, 'steps': 16256, 'loss/train': 1.8279746770858765}
+08/30/2021 16:10:30 - INFO - __main__ - Step 16258: {'lr': 0.0004886387672096866, 'samples': 3121536, 'steps': 16257, 'loss/train': 0.8470008969306946}
+08/30/2021 16:10:30 - INFO - __main__ - Step 16259: {'lr': 0.0004886371855625143, 'samples': 3121728, 'steps': 16258, 'loss/train': 1.8683289289474487}
+08/30/2021 16:10:32 - INFO - __main__ - Step 16260: {'lr': 0.0004886356038078159, 'samples': 3121920, 'steps': 16259, 'loss/train': 1.5578852891921997}
+08/30/2021 16:10:32 - INFO - __main__ - Step 16261: {'lr': 0.0004886340219455919, 'samples': 3122112, 'steps': 16260, 'loss/train': 1.034650444984436}
+08/30/2021 16:10:33 - INFO - __main__ - Step 16262: {'lr': 0.0004886324399758431, 'samples': 3122304, 'steps': 16261, 'loss/train': 1.6897884607315063}
+08/30/2021 16:10:33 - INFO - __main__ - Step 16263: {'lr': 0.0004886308578985702, 'samples': 3122496, 'steps': 16262, 'loss/train': 1.7113878726959229}
+08/30/2021 16:10:33 - INFO - __main__ - Step 16264: {'lr': 0.0004886292757137739, 'samples': 3122688, 'steps': 16263, 'loss/train': 2.0861010551452637}
+08/30/2021 16:10:34 - INFO - __main__ - Step 16265: {'lr': 0.0004886276934214551, 'samples': 3122880, 'steps': 16264, 'loss/train': 1.7308111190795898}
+08/30/2021 16:10:35 - INFO - __main__ - Step 16266: {'lr': 0.0004886261110216141, 'samples': 3123072, 'steps': 16265, 'loss/train': 1.7342652082443237}
+08/30/2021 16:10:36 - INFO - __main__ - Step 16267: {'lr': 0.000488624528514252, 'samples': 3123264, 'steps': 16266, 'loss/train': 1.5815978050231934}
+08/30/2021 16:10:36 - INFO - __main__ - Step 16268: {'lr': 0.0004886229458993693, 'samples': 3123456, 'steps': 16267, 'loss/train': 1.6773253679275513}
+08/30/2021 16:10:36 - INFO - __main__ - Step 16269: {'lr': 0.0004886213631769669, 'samples': 3123648, 'steps': 16268, 'loss/train': 1.8577414751052856}
+08/30/2021 16:10:37 - INFO - __main__ - Step 16270: {'lr': 0.0004886197803470453, 'samples': 3123840, 'steps': 16269, 'loss/train': 1.8149452209472656}
+08/30/2021 16:10:39 - INFO - __main__ - Step 16271: {'lr': 0.0004886181974096052, 'samples': 3124032, 'steps': 16270, 'loss/train': 1.1607913970947266}
+08/30/2021 16:10:39 - INFO - __main__ - Step 16272: {'lr': 0.0004886166143646476, 'samples': 3124224, 'steps': 16271, 'loss/train': 1.8695080280303955}
+08/30/2021 16:10:40 - INFO - __main__ - Step 16273: {'lr': 0.000488615031212173, 'samples': 3124416, 'steps': 16272, 'loss/train': 1.834064245223999}
+08/30/2021 16:10:40 - INFO - __main__ - Step 16274: {'lr': 0.0004886134479521821, 'samples': 3124608, 'steps': 16273, 'loss/train': 1.9997714757919312}
+08/30/2021 16:10:40 - INFO - __main__ - Step 16275: {'lr': 0.0004886118645846757, 'samples': 3124800, 'steps': 16274, 'loss/train': 1.942400574684143}
+08/30/2021 16:10:42 - INFO - __main__ - Step 16276: {'lr': 0.0004886102811096544, 'samples': 3124992, 'steps': 16275, 'loss/train': 1.6288559436798096}
+08/30/2021 16:10:42 - INFO - __main__ - Step 16277: {'lr': 0.0004886086975271191, 'samples': 3125184, 'steps': 16276, 'loss/train': 1.7238287925720215}
+08/30/2021 16:10:43 - INFO - __main__ - Step 16278: {'lr': 0.0004886071138370704, 'samples': 3125376, 'steps': 16277, 'loss/train': 1.8636168241500854}
+08/30/2021 16:10:43 - INFO - __main__ - Step 16279: {'lr': 0.000488605530039509, 'samples': 3125568, 'steps': 16278, 'loss/train': 1.5248596668243408}
+08/30/2021 16:10:43 - INFO - __main__ - Step 16280: {'lr': 0.0004886039461344356, 'samples': 3125760, 'steps': 16279, 'loss/train': 1.7116458415985107}
+08/30/2021 16:10:45 - INFO - __main__ - Step 16281: {'lr': 0.0004886023621218509, 'samples': 3125952, 'steps': 16280, 'loss/train': 1.7959003448486328}
+08/30/2021 16:10:45 - INFO - __main__ - Step 16282: {'lr': 0.0004886007780017557, 'samples': 3126144, 'steps': 16281, 'loss/train': 1.5302084684371948}
+08/30/2021 16:10:46 - INFO - __main__ - Step 16283: {'lr': 0.0004885991937741506, 'samples': 3126336, 'steps': 16282, 'loss/train': 1.8500771522521973}
+08/30/2021 16:10:46 - INFO - __main__ - Step 16284: {'lr': 0.0004885976094390366, 'samples': 3126528, 'steps': 16283, 'loss/train': 1.7807413339614868}
+08/30/2021 16:10:46 - INFO - __main__ - Step 16285: {'lr': 0.000488596024996414, 'samples': 3126720, 'steps': 16284, 'loss/train': 1.6970168352127075}
+08/30/2021 16:10:47 - INFO - __main__ - Step 16286: {'lr': 0.0004885944404462838, 'samples': 3126912, 'steps': 16285, 'loss/train': 1.7380517721176147}
+08/30/2021 16:10:49 - INFO - __main__ - Step 16287: {'lr': 0.0004885928557886466, 'samples': 3127104, 'steps': 16286, 'loss/train': 1.9905680418014526}
+08/30/2021 16:10:49 - INFO - __main__ - Step 16288: {'lr': 0.0004885912710235031, 'samples': 3127296, 'steps': 16287, 'loss/train': 1.461103916168213}
+08/30/2021 16:10:49 - INFO - __main__ - Step 16289: {'lr': 0.0004885896861508541, 'samples': 3127488, 'steps': 16288, 'loss/train': 2.0694077014923096}
+08/30/2021 16:10:50 - INFO - __main__ - Step 16290: {'lr': 0.0004885881011707003, 'samples': 3127680, 'steps': 16289, 'loss/train': 1.1995704174041748}
+08/30/2021 16:10:50 - INFO - __main__ - Step 16291: {'lr': 0.0004885865160830422, 'samples': 3127872, 'steps': 16290, 'loss/train': 1.7522541284561157}
+08/30/2021 16:10:51 - INFO - __main__ - Step 16292: {'lr': 0.0004885849308878809, 'samples': 3128064, 'steps': 16291, 'loss/train': 1.6052396297454834}
+08/30/2021 16:10:52 - INFO - __main__ - Step 16293: {'lr': 0.0004885833455852169, 'samples': 3128256, 'steps': 16292, 'loss/train': 1.8246219158172607}
+08/30/2021 16:10:52 - INFO - __main__ - Step 16294: {'lr': 0.0004885817601750509, 'samples': 3128448, 'steps': 16293, 'loss/train': 1.7759073972702026}
+08/30/2021 16:10:53 - INFO - __main__ - Step 16295: {'lr': 0.0004885801746573836, 'samples': 3128640, 'steps': 16294, 'loss/train': 1.4780112504959106}
+08/30/2021 16:10:53 - INFO - __main__ - Step 16296: {'lr': 0.0004885785890322158, 'samples': 3128832, 'steps': 16295, 'loss/train': 1.8578686714172363}
+08/30/2021 16:10:54 - INFO - __main__ - Step 16297: {'lr': 0.0004885770032995482, 'samples': 3129024, 'steps': 16296, 'loss/train': 1.973870873451233}
+08/30/2021 16:10:55 - INFO - __main__ - Step 16298: {'lr': 0.0004885754174593814, 'samples': 3129216, 'steps': 16297, 'loss/train': 1.013839602470398}
+08/30/2021 16:10:55 - INFO - __main__ - Step 16299: {'lr': 0.0004885738315117162, 'samples': 3129408, 'steps': 16298, 'loss/train': 1.2680706977844238}
+08/30/2021 16:10:56 - INFO - __main__ - Step 16300: {'lr': 0.0004885722454565534, 'samples': 3129600, 'steps': 16299, 'loss/train': 1.2194448709487915}
+08/30/2021 16:10:56 - INFO - __main__ - Step 16301: {'lr': 0.0004885706592938936, 'samples': 3129792, 'steps': 16300, 'loss/train': 1.9567265510559082}
+08/30/2021 16:10:58 - INFO - __main__ - Step 16302: {'lr': 0.0004885690730237375, 'samples': 3129984, 'steps': 16301, 'loss/train': 1.841776967048645}
+08/30/2021 16:10:58 - INFO - __main__ - Step 16303: {'lr': 0.0004885674866460858, 'samples': 3130176, 'steps': 16302, 'loss/train': 2.2307300567626953}
+08/30/2021 16:10:58 - INFO - __main__ - Step 16304: {'lr': 0.0004885659001609393, 'samples': 3130368, 'steps': 16303, 'loss/train': 1.4630793333053589}
+08/30/2021 16:10:59 - INFO - __main__ - Step 16305: {'lr': 0.0004885643135682987, 'samples': 3130560, 'steps': 16304, 'loss/train': 1.1288224458694458}
+08/30/2021 16:10:59 - INFO - __main__ - Step 16306: {'lr': 0.0004885627268681648, 'samples': 3130752, 'steps': 16305, 'loss/train': 5.890904903411865}
+08/30/2021 16:10:59 - INFO - __main__ - Step 16307: {'lr': 0.0004885611400605381, 'samples': 3130944, 'steps': 16306, 'loss/train': 1.1502996683120728}
+08/30/2021 16:11:01 - INFO - __main__ - Step 16308: {'lr': 0.0004885595531454195, 'samples': 3131136, 'steps': 16307, 'loss/train': 2.030357837677002}
+08/30/2021 16:11:01 - INFO - __main__ - Step 16309: {'lr': 0.0004885579661228097, 'samples': 3131328, 'steps': 16308, 'loss/train': 2.012671947479248}
+08/30/2021 16:11:02 - INFO - __main__ - Step 16310: {'lr': 0.0004885563789927092, 'samples': 3131520, 'steps': 16309, 'loss/train': 1.4014322757720947}
+08/30/2021 16:11:02 - INFO - __main__ - Step 16311: {'lr': 0.0004885547917551189, 'samples': 3131712, 'steps': 16310, 'loss/train': 1.609916090965271}
+08/30/2021 16:11:02 - INFO - __main__ - Step 16312: {'lr': 0.0004885532044100396, 'samples': 3131904, 'steps': 16311, 'loss/train': 1.7045129537582397}
+08/30/2021 16:11:04 - INFO - __main__ - Step 16313: {'lr': 0.0004885516169574719, 'samples': 3132096, 'steps': 16312, 'loss/train': 1.6659396886825562}
+08/30/2021 16:11:05 - INFO - __main__ - Step 16314: {'lr': 0.0004885500293974165, 'samples': 3132288, 'steps': 16313, 'loss/train': 1.6932291984558105}
+08/30/2021 16:11:05 - INFO - __main__ - Step 16315: {'lr': 0.0004885484417298741, 'samples': 3132480, 'steps': 16314, 'loss/train': 1.825520396232605}
+08/30/2021 16:11:05 - INFO - __main__ - Step 16316: {'lr': 0.0004885468539548455, 'samples': 3132672, 'steps': 16315, 'loss/train': 0.23717674612998962}
+08/30/2021 16:11:06 - INFO - __main__ - Step 16317: {'lr': 0.0004885452660723313, 'samples': 3132864, 'steps': 16316, 'loss/train': 1.829975962638855}
+08/30/2021 16:11:07 - INFO - __main__ - Step 16318: {'lr': 0.0004885436780823324, 'samples': 3133056, 'steps': 16317, 'loss/train': 1.3374109268188477}
+08/30/2021 16:11:08 - INFO - __main__ - Step 16319: {'lr': 0.0004885420899848492, 'samples': 3133248, 'steps': 16318, 'loss/train': 0.565299928188324}
+08/30/2021 16:11:08 - INFO - __main__ - Step 16320: {'lr': 0.0004885405017798828, 'samples': 3133440, 'steps': 16319, 'loss/train': 1.8940999507904053}
+08/30/2021 16:11:08 - INFO - __main__ - Step 16321: {'lr': 0.0004885389134674337, 'samples': 3133632, 'steps': 16320, 'loss/train': 1.845708966255188}
+08/30/2021 16:11:09 - INFO - __main__ - Step 16322: {'lr': 0.0004885373250475026, 'samples': 3133824, 'steps': 16321, 'loss/train': 1.7308459281921387}
+08/30/2021 16:11:11 - INFO - __main__ - Step 16323: {'lr': 0.0004885357365200903, 'samples': 3134016, 'steps': 16322, 'loss/train': 1.538646936416626}
+08/30/2021 16:11:11 - INFO - __main__ - Step 16324: {'lr': 0.0004885341478851975, 'samples': 3134208, 'steps': 16323, 'loss/train': 1.763047695159912}
+08/30/2021 16:11:12 - INFO - __main__ - Step 16325: {'lr': 0.0004885325591428248, 'samples': 3134400, 'steps': 16324, 'loss/train': 1.3690780401229858}
+08/30/2021 16:11:12 - INFO - __main__ - Step 16326: {'lr': 0.0004885309702929731, 'samples': 3134592, 'steps': 16325, 'loss/train': 1.5660958290100098}
+08/30/2021 16:11:12 - INFO - __main__ - Step 16327: {'lr': 0.000488529381335643, 'samples': 3134784, 'steps': 16326, 'loss/train': 1.7297216653823853}
+08/30/2021 16:11:14 - INFO - __main__ - Step 16328: {'lr': 0.0004885277922708352, 'samples': 3134976, 'steps': 16327, 'loss/train': 1.8478820323944092}
+08/30/2021 16:11:14 - INFO - __main__ - Step 16329: {'lr': 0.0004885262030985504, 'samples': 3135168, 'steps': 16328, 'loss/train': 1.6181265115737915}
+08/30/2021 16:11:15 - INFO - __main__ - Step 16330: {'lr': 0.0004885246138187896, 'samples': 3135360, 'steps': 16329, 'loss/train': 1.5884735584259033}
+08/30/2021 16:11:15 - INFO - __main__ - Step 16331: {'lr': 0.0004885230244315531, 'samples': 3135552, 'steps': 16330, 'loss/train': 1.2228111028671265}
+08/30/2021 16:11:15 - INFO - __main__ - Step 16332: {'lr': 0.0004885214349368419, 'samples': 3135744, 'steps': 16331, 'loss/train': 2.0802552700042725}
+08/30/2021 16:11:16 - INFO - __main__ - Step 16333: {'lr': 0.0004885198453346565, 'samples': 3135936, 'steps': 16332, 'loss/train': 1.9758137464523315}
+08/30/2021 16:11:18 - INFO - __main__ - Step 16334: {'lr': 0.0004885182556249978, 'samples': 3136128, 'steps': 16333, 'loss/train': 2.045431137084961}
+08/30/2021 16:11:18 - INFO - __main__ - Step 16335: {'lr': 0.0004885166658078666, 'samples': 3136320, 'steps': 16334, 'loss/train': 1.4344342947006226}
+08/30/2021 16:11:18 - INFO - __main__ - Step 16336: {'lr': 0.0004885150758832632, 'samples': 3136512, 'steps': 16335, 'loss/train': 1.4791133403778076}
+08/30/2021 16:11:19 - INFO - __main__ - Step 16337: {'lr': 0.0004885134858511888, 'samples': 3136704, 'steps': 16336, 'loss/train': 1.6670126914978027}
+08/30/2021 16:11:19 - INFO - __main__ - Step 16338: {'lr': 0.0004885118957116438, 'samples': 3136896, 'steps': 16337, 'loss/train': 1.0015093088150024}
+08/30/2021 16:11:21 - INFO - __main__ - Step 16339: {'lr': 0.000488510305464629, 'samples': 3137088, 'steps': 16338, 'loss/train': 2.0380828380584717}
+08/30/2021 16:11:21 - INFO - __main__ - Step 16340: {'lr': 0.0004885087151101453, 'samples': 3137280, 'steps': 16339, 'loss/train': 1.8990954160690308}
+08/30/2021 16:11:21 - INFO - __main__ - Step 16341: {'lr': 0.0004885071246481931, 'samples': 3137472, 'steps': 16340, 'loss/train': 1.7942309379577637}
+08/30/2021 16:11:22 - INFO - __main__ - Step 16342: {'lr': 0.0004885055340787733, 'samples': 3137664, 'steps': 16341, 'loss/train': 1.1840516328811646}
+08/30/2021 16:11:22 - INFO - __main__ - Step 16343: {'lr': 0.0004885039434018866, 'samples': 3137856, 'steps': 16342, 'loss/train': 1.8106180429458618}
+08/30/2021 16:11:24 - INFO - __main__ - Step 16344: {'lr': 0.0004885023526175337, 'samples': 3138048, 'steps': 16343, 'loss/train': 1.5840362310409546}
+08/30/2021 16:11:24 - INFO - __main__ - Step 16345: {'lr': 0.0004885007617257154, 'samples': 3138240, 'steps': 16344, 'loss/train': 1.4874635934829712}
+08/30/2021 16:11:25 - INFO - __main__ - Step 16346: {'lr': 0.0004884991707264322, 'samples': 3138432, 'steps': 16345, 'loss/train': 0.11009877920150757}
+08/30/2021 16:11:25 - INFO - __main__ - Step 16347: {'lr': 0.000488497579619685, 'samples': 3138624, 'steps': 16346, 'loss/train': 1.738002061843872}
+08/30/2021 16:11:25 - INFO - __main__ - Step 16348: {'lr': 0.0004884959884054745, 'samples': 3138816, 'steps': 16347, 'loss/train': 1.8687289953231812}
+08/30/2021 16:11:26 - INFO - __main__ - Step 16349: {'lr': 0.0004884943970838014, 'samples': 3139008, 'steps': 16348, 'loss/train': 1.5455678701400757}
+08/30/2021 16:11:27 - INFO - __main__ - Step 16350: {'lr': 0.0004884928056546663, 'samples': 3139200, 'steps': 16349, 'loss/train': 1.8006826639175415}
+08/30/2021 16:11:28 - INFO - __main__ - Step 16351: {'lr': 0.0004884912141180701, 'samples': 3139392, 'steps': 16350, 'loss/train': 1.7931283712387085}
+08/30/2021 16:11:28 - INFO - __main__ - Step 16352: {'lr': 0.0004884896224740136, 'samples': 3139584, 'steps': 16351, 'loss/train': 1.4437652826309204}
+08/30/2021 16:11:28 - INFO - __main__ - Step 16353: {'lr': 0.0004884880307224972, 'samples': 3139776, 'steps': 16352, 'loss/train': 2.056745767593384}
+08/30/2021 16:11:29 - INFO - __main__ - Step 16354: {'lr': 0.0004884864388635217, 'samples': 3139968, 'steps': 16353, 'loss/train': 1.7429823875427246}
+08/30/2021 16:11:30 - INFO - __main__ - Step 16355: {'lr': 0.0004884848468970879, 'samples': 3140160, 'steps': 16354, 'loss/train': 1.7310128211975098}
+08/30/2021 16:11:31 - INFO - __main__ - Step 16356: {'lr': 0.0004884832548231966, 'samples': 3140352, 'steps': 16355, 'loss/train': 1.6515498161315918}
+08/30/2021 16:11:31 - INFO - __main__ - Step 16357: {'lr': 0.0004884816626418484, 'samples': 3140544, 'steps': 16356, 'loss/train': 1.6642929315567017}
+08/30/2021 16:11:31 - INFO - __main__ - Step 16358: {'lr': 0.000488480070353044, 'samples': 3140736, 'steps': 16357, 'loss/train': 1.6606919765472412}
+08/30/2021 16:11:32 - INFO - __main__ - Step 16359: {'lr': 0.0004884784779567843, 'samples': 3140928, 'steps': 16358, 'loss/train': 1.5081998109817505}
+08/30/2021 16:11:34 - INFO - __main__ - Step 16360: {'lr': 0.0004884768854530696, 'samples': 3141120, 'steps': 16359, 'loss/train': 1.4753029346466064}
+08/30/2021 16:11:34 - INFO - __main__ - Step 16361: {'lr': 0.0004884752928419012, 'samples': 3141312, 'steps': 16360, 'loss/train': 1.6934443712234497}
+08/30/2021 16:11:35 - INFO - __main__ - Step 16362: {'lr': 0.0004884737001232793, 'samples': 3141504, 'steps': 16361, 'loss/train': 1.7826738357543945}
+08/30/2021 16:11:35 - INFO - __main__ - Step 16363: {'lr': 0.000488472107297205, 'samples': 3141696, 'steps': 16362, 'loss/train': 0.815053403377533}
+08/30/2021 16:11:35 - INFO - __main__ - Step 16364: {'lr': 0.0004884705143636788, 'samples': 3141888, 'steps': 16363, 'loss/train': 1.4334876537322998}
+08/30/2021 16:11:36 - INFO - __main__ - Step 16365: {'lr': 0.0004884689213227013, 'samples': 3142080, 'steps': 16364, 'loss/train': 1.7051260471343994}
+08/30/2021 16:11:36 - INFO - __main__ - Step 16366: {'lr': 0.0004884673281742736, 'samples': 3142272, 'steps': 16365, 'loss/train': 0.10288375616073608}
+08/30/2021 16:11:38 - INFO - __main__ - Step 16367: {'lr': 0.0004884657349183961, 'samples': 3142464, 'steps': 16366, 'loss/train': 0.10311628878116608}
+08/30/2021 16:11:38 - INFO - __main__ - Step 16368: {'lr': 0.0004884641415550696, 'samples': 3142656, 'steps': 16367, 'loss/train': 1.4080204963684082}
+08/30/2021 16:11:38 - INFO - __main__ - Step 16369: {'lr': 0.0004884625480842949, 'samples': 3142848, 'steps': 16368, 'loss/train': 1.8912681341171265}
+08/30/2021 16:11:39 - INFO - __main__ - Step 16370: {'lr': 0.0004884609545060726, 'samples': 3143040, 'steps': 16369, 'loss/train': 1.391222596168518}
+08/30/2021 16:11:39 - INFO - __main__ - Step 16371: {'lr': 0.0004884593608204035, 'samples': 3143232, 'steps': 16370, 'loss/train': 1.6049600839614868}
+08/30/2021 16:11:41 - INFO - __main__ - Step 16372: {'lr': 0.0004884577670272882, 'samples': 3143424, 'steps': 16371, 'loss/train': 1.399133563041687}
+08/30/2021 16:11:41 - INFO - __main__ - Step 16373: {'lr': 0.0004884561731267278, 'samples': 3143616, 'steps': 16372, 'loss/train': 1.9584330320358276}
+08/30/2021 16:11:41 - INFO - __main__ - Step 16374: {'lr': 0.0004884545791187224, 'samples': 3143808, 'steps': 16373, 'loss/train': 1.2325204610824585}
+08/30/2021 16:11:42 - INFO - __main__ - Step 16375: {'lr': 0.0004884529850032732, 'samples': 3144000, 'steps': 16374, 'loss/train': 1.823428988456726}
+08/30/2021 16:11:42 - INFO - __main__ - Step 16376: {'lr': 0.0004884513907803808, 'samples': 3144192, 'steps': 16375, 'loss/train': 2.0254604816436768}
+08/30/2021 16:11:44 - INFO - __main__ - Step 16377: {'lr': 0.0004884497964500457, 'samples': 3144384, 'steps': 16376, 'loss/train': 1.838220238685608}
+08/30/2021 16:11:44 - INFO - __main__ - Step 16378: {'lr': 0.000488448202012269, 'samples': 3144576, 'steps': 16377, 'loss/train': 1.714113473892212}
+08/30/2021 16:11:45 - INFO - __main__ - Step 16379: {'lr': 0.0004884466074670512, 'samples': 3144768, 'steps': 16378, 'loss/train': 1.836683988571167}
+08/30/2021 16:11:45 - INFO - __main__ - Step 16380: {'lr': 0.0004884450128143929, 'samples': 3144960, 'steps': 16379, 'loss/train': 1.4216639995574951}
+08/30/2021 16:11:45 - INFO - __main__ - Step 16381: {'lr': 0.000488443418054295, 'samples': 3145152, 'steps': 16380, 'loss/train': 1.983205795288086}
+08/30/2021 16:11:47 - INFO - __main__ - Step 16382: {'lr': 0.0004884418231867583, 'samples': 3145344, 'steps': 16381, 'loss/train': 1.8755842447280884}
+08/30/2021 16:11:48 - INFO - __main__ - Step 16383: {'lr': 0.0004884402282117833, 'samples': 3145536, 'steps': 16382, 'loss/train': 1.6494497060775757}
+08/30/2021 16:11:48 - INFO - __main__ - Step 16384: {'lr': 0.0004884386331293708, 'samples': 3145728, 'steps': 16383, 'loss/train': 0.07024643570184708}
+08/30/2021 16:11:49 - INFO - __main__ - Step 16385: {'lr': 0.0004884370379395215, 'samples': 3145920, 'steps': 16384, 'loss/train': 1.9015545845031738}
+08/30/2021 16:11:49 - INFO - __main__ - Step 16386: {'lr': 0.0004884354426422363, 'samples': 3146112, 'steps': 16385, 'loss/train': 0.16112719476222992}
+08/30/2021 16:11:49 - INFO - __main__ - Step 16387: {'lr': 0.0004884338472375156, 'samples': 3146304, 'steps': 16386, 'loss/train': 1.2409710884094238}
+08/30/2021 16:11:51 - INFO - __main__ - Step 16388: {'lr': 0.0004884322517253604, 'samples': 3146496, 'steps': 16387, 'loss/train': 1.0356227159500122}
+08/30/2021 16:11:51 - INFO - __main__ - Step 16389: {'lr': 0.0004884306561057713, 'samples': 3146688, 'steps': 16388, 'loss/train': 1.4719094038009644}
+08/30/2021 16:11:52 - INFO - __main__ - Step 16390: {'lr': 0.000488429060378749, 'samples': 3146880, 'steps': 16389, 'loss/train': 1.825208306312561}
+08/30/2021 16:11:52 - INFO - __main__ - Step 16391: {'lr': 0.0004884274645442942, 'samples': 3147072, 'steps': 16390, 'loss/train': 1.7455666065216064}
+08/30/2021 16:11:52 - INFO - __main__ - Step 16392: {'lr': 0.0004884258686024077, 'samples': 3147264, 'steps': 16391, 'loss/train': 1.788954734802246}
+08/30/2021 16:11:54 - INFO - __main__ - Step 16393: {'lr': 0.0004884242725530902, 'samples': 3147456, 'steps': 16392, 'loss/train': 1.6024516820907593}
+08/30/2021 16:11:54 - INFO - __main__ - Step 16394: {'lr': 0.0004884226763963423, 'samples': 3147648, 'steps': 16393, 'loss/train': 1.8891571760177612}
+08/30/2021 16:11:55 - INFO - __main__ - Step 16395: {'lr': 0.000488421080132165, 'samples': 3147840, 'steps': 16394, 'loss/train': 1.7516354322433472}
+08/30/2021 16:11:55 - INFO - __main__ - Step 16396: {'lr': 0.0004884194837605587, 'samples': 3148032, 'steps': 16395, 'loss/train': 1.6981509923934937}
+08/30/2021 16:11:55 - INFO - __main__ - Step 16397: {'lr': 0.0004884178872815243, 'samples': 3148224, 'steps': 16396, 'loss/train': 1.2616357803344727}
+08/30/2021 16:11:57 - INFO - __main__ - Step 16398: {'lr': 0.0004884162906950624, 'samples': 3148416, 'steps': 16397, 'loss/train': 0.14406365156173706}
+08/30/2021 16:11:58 - INFO - __main__ - Step 16399: {'lr': 0.000488414694001174, 'samples': 3148608, 'steps': 16398, 'loss/train': 2.0568366050720215}
+08/30/2021 16:11:58 - INFO - __main__ - Step 16400: {'lr': 0.0004884130971998595, 'samples': 3148800, 'steps': 16399, 'loss/train': 2.191758871078491}
+08/30/2021 16:11:58 - INFO - __main__ - Step 16401: {'lr': 0.0004884115002911197, 'samples': 3148992, 'steps': 16400, 'loss/train': 1.3861243724822998}
+08/30/2021 16:11:59 - INFO - __main__ - Step 16402: {'lr': 0.0004884099032749554, 'samples': 3149184, 'steps': 16401, 'loss/train': 0.0903669074177742}
+08/30/2021 16:12:00 - INFO - __main__ - Step 16403: {'lr': 0.0004884083061513672, 'samples': 3149376, 'steps': 16402, 'loss/train': 2.5146679878234863}
+08/30/2021 16:12:00 - INFO - __main__ - Step 16404: {'lr': 0.0004884067089203559, 'samples': 3149568, 'steps': 16403, 'loss/train': 1.8538411855697632}
+08/30/2021 16:12:01 - INFO - __main__ - Step 16405: {'lr': 0.0004884051115819224, 'samples': 3149760, 'steps': 16404, 'loss/train': 2.032058000564575}
+08/30/2021 16:12:01 - INFO - __main__ - Step 16406: {'lr': 0.000488403514136067, 'samples': 3149952, 'steps': 16405, 'loss/train': 1.4845865964889526}
+08/30/2021 16:12:01 - INFO - __main__ - Step 16407: {'lr': 0.0004884019165827909, 'samples': 3150144, 'steps': 16406, 'loss/train': 1.7833247184753418}
+08/30/2021 16:12:03 - INFO - __main__ - Step 16408: {'lr': 0.0004884003189220945, 'samples': 3150336, 'steps': 16407, 'loss/train': 1.4036445617675781}
+08/30/2021 16:12:03 - INFO - __main__ - Step 16409: {'lr': 0.0004883987211539785, 'samples': 3150528, 'steps': 16408, 'loss/train': 2.021967649459839}
+08/30/2021 16:12:04 - INFO - __main__ - Step 16410: {'lr': 0.0004883971232784438, 'samples': 3150720, 'steps': 16409, 'loss/train': 1.841018557548523}
+08/30/2021 16:12:04 - INFO - __main__ - Step 16411: {'lr': 0.0004883955252954909, 'samples': 3150912, 'steps': 16410, 'loss/train': 2.0723958015441895}
+08/30/2021 16:12:04 - INFO - __main__ - Step 16412: {'lr': 0.0004883939272051208, 'samples': 3151104, 'steps': 16411, 'loss/train': 1.7425384521484375}
+08/30/2021 16:12:05 - INFO - __main__ - Step 16413: {'lr': 0.000488392329007334, 'samples': 3151296, 'steps': 16412, 'loss/train': 1.697700023651123}
+08/30/2021 16:12:07 - INFO - __main__ - Step 16414: {'lr': 0.0004883907307021314, 'samples': 3151488, 'steps': 16413, 'loss/train': 2.5796310901641846}
+08/30/2021 16:12:07 - INFO - __main__ - Step 16415: {'lr': 0.0004883891322895134, 'samples': 3151680, 'steps': 16414, 'loss/train': 2.1869726181030273}
+08/30/2021 16:12:07 - INFO - __main__ - Step 16416: {'lr': 0.000488387533769481, 'samples': 3151872, 'steps': 16415, 'loss/train': 1.569940209388733}
+08/30/2021 16:12:08 - INFO - __main__ - Step 16417: {'lr': 0.000488385935142035, 'samples': 3152064, 'steps': 16416, 'loss/train': 1.4833344221115112}
+08/30/2021 16:12:08 - INFO - __main__ - Step 16418: {'lr': 0.0004883843364071759, 'samples': 3152256, 'steps': 16417, 'loss/train': 1.2835125923156738}
+08/30/2021 16:12:09 - INFO - __main__ - Step 16419: {'lr': 0.0004883827375649045, 'samples': 3152448, 'steps': 16418, 'loss/train': 1.0750722885131836}
+08/30/2021 16:12:10 - INFO - __main__ - Step 16420: {'lr': 0.0004883811386152216, 'samples': 3152640, 'steps': 16419, 'loss/train': 1.722716212272644}
+08/30/2021 16:12:10 - INFO - __main__ - Step 16421: {'lr': 0.0004883795395581277, 'samples': 3152832, 'steps': 16420, 'loss/train': 0.47888919711112976}
+08/30/2021 16:12:11 - INFO - __main__ - Step 16422: {'lr': 0.0004883779403936237, 'samples': 3153024, 'steps': 16421, 'loss/train': 1.4829291105270386}
+08/30/2021 16:12:11 - INFO - __main__ - Step 16423: {'lr': 0.0004883763411217103, 'samples': 3153216, 'steps': 16422, 'loss/train': 1.7919137477874756}
+08/30/2021 16:12:12 - INFO - __main__ - Step 16424: {'lr': 0.0004883747417423882, 'samples': 3153408, 'steps': 16423, 'loss/train': 1.6080315113067627}
+08/30/2021 16:12:13 - INFO - __main__ - Step 16425: {'lr': 0.000488373142255658, 'samples': 3153600, 'steps': 16424, 'loss/train': 1.644591212272644}
+08/30/2021 16:12:13 - INFO - __main__ - Step 16426: {'lr': 0.0004883715426615207, 'samples': 3153792, 'steps': 16425, 'loss/train': 1.6483370065689087}
+08/30/2021 16:12:14 - INFO - __main__ - Step 16427: {'lr': 0.0004883699429599768, 'samples': 3153984, 'steps': 16426, 'loss/train': 1.8033820390701294}
+08/30/2021 16:12:14 - INFO - __main__ - Step 16428: {'lr': 0.0004883683431510272, 'samples': 3154176, 'steps': 16427, 'loss/train': 1.4099290370941162}
+08/30/2021 16:12:16 - INFO - __main__ - Step 16429: {'lr': 0.0004883667432346723, 'samples': 3154368, 'steps': 16428, 'loss/train': 0.9474764466285706}
+08/30/2021 16:12:16 - INFO - __main__ - Step 16430: {'lr': 0.0004883651432109132, 'samples': 3154560, 'steps': 16429, 'loss/train': 2.8283019065856934}
+08/30/2021 16:12:17 - INFO - __main__ - Step 16431: {'lr': 0.0004883635430797502, 'samples': 3154752, 'steps': 16430, 'loss/train': 2.3652114868164062}
+08/30/2021 16:12:17 - INFO - __main__ - Step 16432: {'lr': 0.0004883619428411846, 'samples': 3154944, 'steps': 16431, 'loss/train': 1.80955171585083}
+08/30/2021 16:12:17 - INFO - __main__ - Step 16433: {'lr': 0.0004883603424952165, 'samples': 3155136, 'steps': 16432, 'loss/train': 1.612752914428711}
+08/30/2021 16:12:19 - INFO - __main__ - Step 16434: {'lr': 0.0004883587420418471, 'samples': 3155328, 'steps': 16433, 'loss/train': 1.9555912017822266}
+08/30/2021 16:12:20 - INFO - __main__ - Step 16435: {'lr': 0.0004883571414810769, 'samples': 3155520, 'steps': 16434, 'loss/train': 1.5818567276000977}
+08/30/2021 16:12:20 - INFO - __main__ - Step 16436: {'lr': 0.0004883555408129066, 'samples': 3155712, 'steps': 16435, 'loss/train': 1.2745782136917114}
+08/30/2021 16:12:20 - INFO - __main__ - Step 16437: {'lr': 0.0004883539400373369, 'samples': 3155904, 'steps': 16436, 'loss/train': 1.8561028242111206}
+08/30/2021 16:12:21 - INFO - __main__ - Step 16438: {'lr': 0.0004883523391543687, 'samples': 3156096, 'steps': 16437, 'loss/train': 1.5114132165908813}
+08/30/2021 16:12:22 - INFO - __main__ - Step 16439: {'lr': 0.0004883507381640026, 'samples': 3156288, 'steps': 16438, 'loss/train': 1.323274850845337}
+08/30/2021 16:12:23 - INFO - __main__ - Step 16440: {'lr': 0.0004883491370662393, 'samples': 3156480, 'steps': 16439, 'loss/train': 0.6661016941070557}
+08/30/2021 16:12:23 - INFO - __main__ - Step 16441: {'lr': 0.0004883475358610794, 'samples': 3156672, 'steps': 16440, 'loss/train': 1.3470076322555542}
+08/30/2021 16:12:24 - INFO - __main__ - Step 16442: {'lr': 0.000488345934548524, 'samples': 3156864, 'steps': 16441, 'loss/train': 1.2103748321533203}
+08/30/2021 16:12:24 - INFO - __main__ - Step 16443: {'lr': 0.0004883443331285736, 'samples': 3157056, 'steps': 16442, 'loss/train': 1.5097126960754395}
+08/30/2021 16:12:24 - INFO - __main__ - Step 16444: {'lr': 0.0004883427316012289, 'samples': 3157248, 'steps': 16443, 'loss/train': 1.5376880168914795}
+08/30/2021 16:12:26 - INFO - __main__ - Step 16445: {'lr': 0.0004883411299664906, 'samples': 3157440, 'steps': 16444, 'loss/train': 3.0078248977661133}
+08/30/2021 16:12:27 - INFO - __main__ - Step 16446: {'lr': 0.0004883395282243595, 'samples': 3157632, 'steps': 16445, 'loss/train': 0.14940780401229858}
+08/30/2021 16:12:27 - INFO - __main__ - Step 16447: {'lr': 0.0004883379263748363, 'samples': 3157824, 'steps': 16446, 'loss/train': 2.0638163089752197}
+08/30/2021 16:12:27 - INFO - __main__ - Step 16448: {'lr': 0.0004883363244179217, 'samples': 3158016, 'steps': 16447, 'loss/train': 1.5818711519241333}
+08/30/2021 16:12:28 - INFO - __main__ - Step 16449: {'lr': 0.0004883347223536164, 'samples': 3158208, 'steps': 16448, 'loss/train': 1.8282077312469482}
+08/30/2021 16:12:28 - INFO - __main__ - Step 16450: {'lr': 0.0004883331201819211, 'samples': 3158400, 'steps': 16449, 'loss/train': 0.11230821907520294}
+08/30/2021 16:12:30 - INFO - __main__ - Step 16451: {'lr': 0.0004883315179028366, 'samples': 3158592, 'steps': 16450, 'loss/train': 0.17662116885185242}
+08/30/2021 16:12:30 - INFO - __main__ - Step 16452: {'lr': 0.0004883299155163636, 'samples': 3158784, 'steps': 16451, 'loss/train': 1.5383926630020142}
+08/30/2021 16:12:30 - INFO - __main__ - Step 16453: {'lr': 0.0004883283130225029, 'samples': 3158976, 'steps': 16452, 'loss/train': 2.2520840167999268}
+08/30/2021 16:12:31 - INFO - __main__ - Step 16454: {'lr': 0.0004883267104212551, 'samples': 3159168, 'steps': 16453, 'loss/train': 0.7508336901664734}
+08/30/2021 16:12:31 - INFO - __main__ - Step 16455: {'lr': 0.0004883251077126209, 'samples': 3159360, 'steps': 16454, 'loss/train': 2.7111029624938965}
+08/30/2021 16:12:31 - INFO - __main__ - Step 16456: {'lr': 0.0004883235048966011, 'samples': 3159552, 'steps': 16455, 'loss/train': 1.7357203960418701}
+08/30/2021 16:12:33 - INFO - __main__ - Step 16457: {'lr': 0.0004883219019731964, 'samples': 3159744, 'steps': 16456, 'loss/train': 2.1748054027557373}
+08/30/2021 16:12:34 - INFO - __main__ - Step 16458: {'lr': 0.0004883202989424076, 'samples': 3159936, 'steps': 16457, 'loss/train': 1.9947377443313599}
+08/30/2021 16:12:34 - INFO - __main__ - Step 16459: {'lr': 0.0004883186958042354, 'samples': 3160128, 'steps': 16458, 'loss/train': 0.9799297451972961}
+08/30/2021 16:12:34 - INFO - __main__ - Step 16460: {'lr': 0.0004883170925586804, 'samples': 3160320, 'steps': 16459, 'loss/train': 1.2041651010513306}
+08/30/2021 16:12:35 - INFO - __main__ - Step 16461: {'lr': 0.0004883154892057433, 'samples': 3160512, 'steps': 16460, 'loss/train': 1.4210397005081177}
+08/30/2021 16:12:36 - INFO - __main__ - Step 16462: {'lr': 0.000488313885745425, 'samples': 3160704, 'steps': 16461, 'loss/train': 1.7475907802581787}
+08/30/2021 16:12:37 - INFO - __main__ - Step 16463: {'lr': 0.0004883122821777261, 'samples': 3160896, 'steps': 16462, 'loss/train': 1.7158664464950562}
+08/30/2021 16:12:37 - INFO - __main__ - Step 16464: {'lr': 0.0004883106785026475, 'samples': 3161088, 'steps': 16463, 'loss/train': 1.3037594556808472}
+08/30/2021 16:12:37 - INFO - __main__ - Step 16465: {'lr': 0.0004883090747201897, 'samples': 3161280, 'steps': 16464, 'loss/train': 1.3759013414382935}
+08/30/2021 16:12:38 - INFO - __main__ - Step 16466: {'lr': 0.0004883074708303534, 'samples': 3161472, 'steps': 16465, 'loss/train': 1.0900455713272095}
+08/30/2021 16:12:39 - INFO - __main__ - Step 16467: {'lr': 0.0004883058668331396, 'samples': 3161664, 'steps': 16466, 'loss/train': 1.6898516416549683}
+08/30/2021 16:12:40 - INFO - __main__ - Step 16468: {'lr': 0.0004883042627285488, 'samples': 3161856, 'steps': 16467, 'loss/train': 1.8191605806350708}
+08/30/2021 16:12:40 - INFO - __main__ - Step 16469: {'lr': 0.0004883026585165817, 'samples': 3162048, 'steps': 16468, 'loss/train': 1.6544195413589478}
+08/30/2021 16:12:41 - INFO - __main__ - Step 16470: {'lr': 0.0004883010541972392, 'samples': 3162240, 'steps': 16469, 'loss/train': 1.6518362760543823}
+08/30/2021 16:12:41 - INFO - __main__ - Step 16471: {'lr': 0.0004882994497705219, 'samples': 3162432, 'steps': 16470, 'loss/train': 2.0174849033355713}
+08/30/2021 16:12:42 - INFO - __main__ - Step 16472: {'lr': 0.0004882978452364305, 'samples': 3162624, 'steps': 16471, 'loss/train': 1.4940745830535889}
+08/30/2021 16:12:43 - INFO - __main__ - Step 16473: {'lr': 0.0004882962405949658, 'samples': 3162816, 'steps': 16472, 'loss/train': 1.7469748258590698}
+08/30/2021 16:12:43 - INFO - __main__ - Step 16474: {'lr': 0.0004882946358461285, 'samples': 3163008, 'steps': 16473, 'loss/train': 1.8230326175689697}
+08/30/2021 16:12:44 - INFO - __main__ - Step 16475: {'lr': 0.0004882930309899192, 'samples': 3163200, 'steps': 16474, 'loss/train': 1.4943701028823853}
+08/30/2021 16:12:44 - INFO - __main__ - Step 16476: {'lr': 0.000488291426026339, 'samples': 3163392, 'steps': 16475, 'loss/train': 1.4653288125991821}
+08/30/2021 16:12:44 - INFO - __main__ - Step 16477: {'lr': 0.0004882898209553881, 'samples': 3163584, 'steps': 16476, 'loss/train': 1.550358533859253}
+08/30/2021 16:12:46 - INFO - __main__ - Step 16478: {'lr': 0.0004882882157770676, 'samples': 3163776, 'steps': 16477, 'loss/train': 1.679360270500183}
+08/30/2021 16:12:47 - INFO - __main__ - Step 16479: {'lr': 0.000488286610491378, 'samples': 3163968, 'steps': 16478, 'loss/train': 1.8442274332046509}
+08/30/2021 16:12:47 - INFO - __main__ - Step 16480: {'lr': 0.0004882850050983203, 'samples': 3164160, 'steps': 16479, 'loss/train': 1.6017777919769287}
+08/30/2021 16:12:47 - INFO - __main__ - Step 16481: {'lr': 0.0004882833995978949, 'samples': 3164352, 'steps': 16480, 'loss/train': 1.884262204170227}
+08/30/2021 16:12:48 - INFO - __main__ - Step 16482: {'lr': 0.0004882817939901027, 'samples': 3164544, 'steps': 16481, 'loss/train': 0.0743497759103775}
+08/30/2021 16:12:48 - INFO - __main__ - Step 16483: {'lr': 0.0004882801882749445, 'samples': 3164736, 'steps': 16482, 'loss/train': 0.18168054521083832}
+08/30/2021 16:12:50 - INFO - __main__ - Step 16484: {'lr': 0.0004882785824524209, 'samples': 3164928, 'steps': 16483, 'loss/train': 1.5538021326065063}
+08/30/2021 16:12:50 - INFO - __main__ - Step 16485: {'lr': 0.0004882769765225326, 'samples': 3165120, 'steps': 16484, 'loss/train': 2.0989391803741455}
+08/30/2021 16:12:50 - INFO - __main__ - Step 16486: {'lr': 0.00048827537048528035, 'samples': 3165312, 'steps': 16485, 'loss/train': 1.651032567024231}
+08/30/2021 16:12:51 - INFO - __main__ - Step 16487: {'lr': 0.00048827376434066493, 'samples': 3165504, 'steps': 16486, 'loss/train': 1.2024333477020264}
+08/30/2021 16:12:51 - INFO - __main__ - Step 16488: {'lr': 0.0004882721580886871, 'samples': 3165696, 'steps': 16487, 'loss/train': 1.6652101278305054}
+08/30/2021 16:12:53 - INFO - __main__ - Step 16489: {'lr': 0.00048827055172934744, 'samples': 3165888, 'steps': 16488, 'loss/train': 1.4172935485839844}
+08/30/2021 16:12:54 - INFO - __main__ - Step 16490: {'lr': 0.0004882689452626468, 'samples': 3166080, 'steps': 16489, 'loss/train': 1.1986442804336548}
+08/30/2021 16:12:54 - INFO - __main__ - Step 16491: {'lr': 0.00048826733868858577, 'samples': 3166272, 'steps': 16490, 'loss/train': 1.8039789199829102}
+08/30/2021 16:12:55 - INFO - __main__ - Step 16492: {'lr': 0.00048826573200716516, 'samples': 3166464, 'steps': 16491, 'loss/train': 1.7548322677612305}
+08/30/2021 16:12:55 - INFO - __main__ - Step 16493: {'lr': 0.0004882641252183857, 'samples': 3166656, 'steps': 16492, 'loss/train': 1.9020053148269653}
+08/30/2021 16:12:55 - INFO - __main__ - Step 16494: {'lr': 0.0004882625183222481, 'samples': 3166848, 'steps': 16493, 'loss/train': 1.7261946201324463}
+08/30/2021 16:12:57 - INFO - __main__ - Step 16495: {'lr': 0.00048826091131875317, 'samples': 3167040, 'steps': 16494, 'loss/train': 1.968366265296936}
+08/30/2021 16:12:57 - INFO - __main__ - Step 16496: {'lr': 0.00048825930420790144, 'samples': 3167232, 'steps': 16495, 'loss/train': 1.53008234500885}
+08/30/2021 16:12:58 - INFO - __main__ - Step 16497: {'lr': 0.0004882576969896938, 'samples': 3167424, 'steps': 16496, 'loss/train': 1.7781314849853516}
+08/30/2021 16:12:58 - INFO - __main__ - Step 16498: {'lr': 0.00048825608966413095, 'samples': 3167616, 'steps': 16497, 'loss/train': 1.7661806344985962}
+08/30/2021 16:12:58 - INFO - __main__ - Step 16499: {'lr': 0.0004882544822312135, 'samples': 3167808, 'steps': 16498, 'loss/train': 1.7144266366958618}
+08/30/2021 16:13:00 - INFO - __main__ - Step 16500: {'lr': 0.00048825287469094224, 'samples': 3168000, 'steps': 16499, 'loss/train': 2.3831145763397217}
+08/30/2021 16:13:00 - INFO - __main__ - Step 16501: {'lr': 0.000488251267043318, 'samples': 3168192, 'steps': 16500, 'loss/train': 1.950164794921875}
+08/30/2021 16:13:01 - INFO - __main__ - Step 16502: {'lr': 0.00048824965928834143, 'samples': 3168384, 'steps': 16501, 'loss/train': 1.650948405265808}
+08/30/2021 16:13:01 - INFO - __main__ - Step 16503: {'lr': 0.0004882480514260131, 'samples': 3168576, 'steps': 16502, 'loss/train': 1.506259560585022}
+08/30/2021 16:13:01 - INFO - __main__ - Step 16504: {'lr': 0.000488246443456334, 'samples': 3168768, 'steps': 16503, 'loss/train': 0.11784862726926804}
+08/30/2021 16:13:03 - INFO - __main__ - Step 16505: {'lr': 0.0004882448353793048, 'samples': 3168960, 'steps': 16504, 'loss/train': 2.259474039077759}
+08/30/2021 16:13:03 - INFO - __main__ - Step 16506: {'lr': 0.000488243227194926, 'samples': 3169152, 'steps': 16505, 'loss/train': 1.8807767629623413}
+08/30/2021 16:13:04 - INFO - __main__ - Step 16507: {'lr': 0.00048824161890319854, 'samples': 3169344, 'steps': 16506, 'loss/train': 1.8212604522705078}
+08/30/2021 16:13:04 - INFO - __main__ - Step 16508: {'lr': 0.00048824001050412304, 'samples': 3169536, 'steps': 16507, 'loss/train': 1.6447376012802124}
+08/30/2021 16:13:04 - INFO - __main__ - Step 16509: {'lr': 0.0004882384019977003, 'samples': 3169728, 'steps': 16508, 'loss/train': 1.7541759014129639}
+08/30/2021 16:13:06 - INFO - __main__ - Step 16510: {'lr': 0.000488236793383931, 'samples': 3169920, 'steps': 16509, 'loss/train': 1.5085219144821167}
+08/30/2021 16:13:07 - INFO - __main__ - Step 16511: {'lr': 0.00048823518466281586, 'samples': 3170112, 'steps': 16510, 'loss/train': 1.641247034072876}
+08/30/2021 16:13:07 - INFO - __main__ - Step 16512: {'lr': 0.0004882335758343557, 'samples': 3170304, 'steps': 16511, 'loss/train': 1.3721646070480347}
+08/30/2021 16:13:07 - INFO - __main__ - Step 16513: {'lr': 0.0004882319668985511, 'samples': 3170496, 'steps': 16512, 'loss/train': 0.09264480322599411}
+08/30/2021 16:13:08 - INFO - __main__ - Step 16514: {'lr': 0.00048823035785540284, 'samples': 3170688, 'steps': 16513, 'loss/train': 1.4933146238327026}
+08/30/2021 16:13:09 - INFO - __main__ - Step 16515: {'lr': 0.0004882287487049117, 'samples': 3170880, 'steps': 16514, 'loss/train': 2.5302674770355225}
+08/30/2021 16:13:10 - INFO - __main__ - Step 16516: {'lr': 0.00048822713944707833, 'samples': 3171072, 'steps': 16515, 'loss/train': 1.7074077129364014}
+08/30/2021 16:13:10 - INFO - __main__ - Step 16517: {'lr': 0.0004882255300819035, 'samples': 3171264, 'steps': 16516, 'loss/train': 2.1281604766845703}
+08/30/2021 16:13:10 - INFO - __main__ - Step 16518: {'lr': 0.0004882239206093879, 'samples': 3171456, 'steps': 16517, 'loss/train': 0.7898990511894226}
+08/30/2021 16:13:11 - INFO - __main__ - Step 16519: {'lr': 0.0004882223110295323, 'samples': 3171648, 'steps': 16518, 'loss/train': 1.6536293029785156}
+08/30/2021 16:13:12 - INFO - __main__ - Step 16520: {'lr': 0.00048822070134233743, 'samples': 3171840, 'steps': 16519, 'loss/train': 2.1504950523376465}
+08/30/2021 16:13:13 - INFO - __main__ - Step 16521: {'lr': 0.000488219091547804, 'samples': 3172032, 'steps': 16520, 'loss/train': 1.400365948677063}
+08/30/2021 16:13:13 - INFO - __main__ - Step 16522: {'lr': 0.0004882174816459326, 'samples': 3172224, 'steps': 16521, 'loss/train': 2.339890480041504}
+08/30/2021 16:13:13 - INFO - __main__ - Step 16523: {'lr': 0.0004882158716367242, 'samples': 3172416, 'steps': 16522, 'loss/train': 1.9823507070541382}
+08/30/2021 16:13:14 - INFO - __main__ - Step 16524: {'lr': 0.0004882142615201793, 'samples': 3172608, 'steps': 16523, 'loss/train': 1.4485024213790894}
+08/30/2021 16:13:14 - INFO - __main__ - Step 16525: {'lr': 0.00048821265129629887, 'samples': 3172800, 'steps': 16524, 'loss/train': 1.3576749563217163}
+08/30/2021 16:13:16 - INFO - __main__ - Step 16526: {'lr': 0.0004882110409650834, 'samples': 3172992, 'steps': 16525, 'loss/train': 1.6916894912719727}
+08/30/2021 16:13:16 - INFO - __main__ - Step 16527: {'lr': 0.0004882094305265338, 'samples': 3173184, 'steps': 16526, 'loss/train': 1.6859670877456665}
+08/30/2021 16:13:16 - INFO - __main__ - Step 16528: {'lr': 0.00048820781998065054, 'samples': 3173376, 'steps': 16527, 'loss/train': 1.3498218059539795}
+08/30/2021 16:13:17 - INFO - __main__ - Step 16529: {'lr': 0.00048820620932743465, 'samples': 3173568, 'steps': 16528, 'loss/train': 1.842890977859497}
+08/30/2021 16:13:17 - INFO - __main__ - Step 16530: {'lr': 0.0004882045985668867, 'samples': 3173760, 'steps': 16529, 'loss/train': 1.518268346786499}
+08/30/2021 16:13:18 - INFO - __main__ - Step 16531: {'lr': 0.0004882029876990074, 'samples': 3173952, 'steps': 16530, 'loss/train': 2.1686899662017822}
+08/30/2021 16:13:19 - INFO - __main__ - Step 16532: {'lr': 0.0004882013767237975, 'samples': 3174144, 'steps': 16531, 'loss/train': 1.8740262985229492}
+08/30/2021 16:13:19 - INFO - __main__ - Step 16533: {'lr': 0.0004881997656412578, 'samples': 3174336, 'steps': 16532, 'loss/train': 1.9127898216247559}
+08/30/2021 16:13:20 - INFO - __main__ - Step 16534: {'lr': 0.0004881981544513889, 'samples': 3174528, 'steps': 16533, 'loss/train': 1.4909237623214722}
+08/30/2021 16:13:20 - INFO - __main__ - Step 16535: {'lr': 0.0004881965431541916, 'samples': 3174720, 'steps': 16534, 'loss/train': 1.2026665210723877}
+08/30/2021 16:13:21 - INFO - __main__ - Step 16536: {'lr': 0.0004881949317496667, 'samples': 3174912, 'steps': 16535, 'loss/train': 1.699640154838562}
+08/30/2021 16:13:22 - INFO - __main__ - Step 16537: {'lr': 0.0004881933202378147, 'samples': 3175104, 'steps': 16536, 'loss/train': 1.465736746788025}
+08/30/2021 16:13:22 - INFO - __main__ - Step 16538: {'lr': 0.0004881917086186365, 'samples': 3175296, 'steps': 16537, 'loss/train': 2.144170045852661}
+08/30/2021 16:13:23 - INFO - __main__ - Step 16539: {'lr': 0.0004881900968921328, 'samples': 3175488, 'steps': 16538, 'loss/train': 1.691697597503662}
+08/30/2021 16:13:23 - INFO - __main__ - Step 16540: {'lr': 0.00048818848505830436, 'samples': 3175680, 'steps': 16539, 'loss/train': 1.9390833377838135}
+08/30/2021 16:13:24 - INFO - __main__ - Step 16541: {'lr': 0.0004881868731171518, 'samples': 3175872, 'steps': 16540, 'loss/train': 1.9974125623703003}
+08/30/2021 16:13:25 - INFO - __main__ - Step 16542: {'lr': 0.000488185261068676, 'samples': 3176064, 'steps': 16541, 'loss/train': 2.561133623123169}
+08/30/2021 16:13:25 - INFO - __main__ - Step 16543: {'lr': 0.0004881836489128776, 'samples': 3176256, 'steps': 16542, 'loss/train': 1.8090492486953735}
+08/30/2021 16:13:26 - INFO - __main__ - Step 16544: {'lr': 0.00048818203664975727, 'samples': 3176448, 'steps': 16543, 'loss/train': 1.488569736480713}
+08/30/2021 16:13:26 - INFO - __main__ - Step 16545: {'lr': 0.00048818042427931573, 'samples': 3176640, 'steps': 16544, 'loss/train': 1.1984081268310547}
+08/30/2021 16:13:28 - INFO - __main__ - Step 16546: {'lr': 0.00048817881180155385, 'samples': 3176832, 'steps': 16545, 'loss/train': 1.8053693771362305}
+08/30/2021 16:13:29 - INFO - __main__ - Step 16547: {'lr': 0.0004881771992164722, 'samples': 3177024, 'steps': 16546, 'loss/train': 1.8906036615371704}
+08/30/2021 16:13:29 - INFO - __main__ - Step 16548: {'lr': 0.0004881755865240717, 'samples': 3177216, 'steps': 16547, 'loss/train': 1.862004280090332}
+08/30/2021 16:13:29 - INFO - __main__ - Step 16549: {'lr': 0.0004881739737243528, 'samples': 3177408, 'steps': 16548, 'loss/train': 1.5678037405014038}
+08/30/2021 16:13:30 - INFO - __main__ - Step 16550: {'lr': 0.00048817236081731655, 'samples': 3177600, 'steps': 16549, 'loss/train': 1.2787948846817017}
+08/30/2021 16:13:30 - INFO - __main__ - Step 16551: {'lr': 0.0004881707478029634, 'samples': 3177792, 'steps': 16550, 'loss/train': 1.0139423608779907}
+08/30/2021 16:13:32 - INFO - __main__ - Step 16552: {'lr': 0.0004881691346812942, 'samples': 3177984, 'steps': 16551, 'loss/train': 1.6228530406951904}
+08/30/2021 16:13:32 - INFO - __main__ - Step 16553: {'lr': 0.0004881675214523097, 'samples': 3178176, 'steps': 16552, 'loss/train': 1.7885985374450684}
+08/30/2021 16:13:33 - INFO - __main__ - Step 16554: {'lr': 0.00048816590811601054, 'samples': 3178368, 'steps': 16553, 'loss/train': 1.4082645177841187}
+08/30/2021 16:13:33 - INFO - __main__ - Step 16555: {'lr': 0.0004881642946723975, 'samples': 3178560, 'steps': 16554, 'loss/train': 0.08122952282428741}
+08/30/2021 16:13:33 - INFO - __main__ - Step 16556: {'lr': 0.00048816268112147134, 'samples': 3178752, 'steps': 16555, 'loss/train': 1.641249656677246}
+08/30/2021 16:13:35 - INFO - __main__ - Step 16557: {'lr': 0.00048816106746323273, 'samples': 3178944, 'steps': 16556, 'loss/train': 1.8160207271575928}
+08/30/2021 16:13:35 - INFO - __main__ - Step 16558: {'lr': 0.00048815945369768245, 'samples': 3179136, 'steps': 16557, 'loss/train': 1.1699459552764893}
+08/30/2021 16:13:36 - INFO - __main__ - Step 16559: {'lr': 0.00048815783982482115, 'samples': 3179328, 'steps': 16558, 'loss/train': 1.8620539903640747}
+08/30/2021 16:13:36 - INFO - __main__ - Step 16560: {'lr': 0.0004881562258446496, 'samples': 3179520, 'steps': 16559, 'loss/train': 1.6518065929412842}
+08/30/2021 16:13:36 - INFO - __main__ - Step 16561: {'lr': 0.00048815461175716855, 'samples': 3179712, 'steps': 16560, 'loss/train': 1.3696002960205078}
+08/30/2021 16:13:37 - INFO - __main__ - Step 16562: {'lr': 0.00048815299756237873, 'samples': 3179904, 'steps': 16561, 'loss/train': 1.7370407581329346}
+08/30/2021 16:13:38 - INFO - __main__ - Step 16563: {'lr': 0.0004881513832602808, 'samples': 3180096, 'steps': 16562, 'loss/train': 1.635070562362671}
+08/30/2021 16:13:38 - INFO - __main__ - Step 16564: {'lr': 0.0004881497688508756, 'samples': 3180288, 'steps': 16563, 'loss/train': 1.273830771446228}
+08/30/2021 16:13:39 - INFO - __main__ - Step 16565: {'lr': 0.0004881481543341637, 'samples': 3180480, 'steps': 16564, 'loss/train': 1.7977510690689087}
+08/30/2021 16:13:39 - INFO - __main__ - Step 16566: {'lr': 0.000488146539710146, 'samples': 3180672, 'steps': 16565, 'loss/train': 2.0253050327301025}
+08/30/2021 16:13:40 - INFO - __main__ - Step 16567: {'lr': 0.00048814492497882306, 'samples': 3180864, 'steps': 16566, 'loss/train': 1.941239833831787}
+08/30/2021 16:13:41 - INFO - __main__ - Step 16568: {'lr': 0.00048814331014019577, 'samples': 3181056, 'steps': 16567, 'loss/train': 1.6758822202682495}
+08/30/2021 16:13:41 - INFO - __main__ - Step 16569: {'lr': 0.0004881416951942647, 'samples': 3181248, 'steps': 16568, 'loss/train': 2.201371431350708}
+08/30/2021 16:13:42 - INFO - __main__ - Step 16570: {'lr': 0.0004881400801410307, 'samples': 3181440, 'steps': 16569, 'loss/train': 1.941340684890747}
+08/30/2021 16:13:42 - INFO - __main__ - Step 16571: {'lr': 0.0004881384649804945, 'samples': 3181632, 'steps': 16570, 'loss/train': 2.0682497024536133}
+08/30/2021 16:13:43 - INFO - __main__ - Step 16572: {'lr': 0.0004881368497126567, 'samples': 3181824, 'steps': 16571, 'loss/train': 1.958207368850708}
+08/30/2021 16:13:44 - INFO - __main__ - Step 16573: {'lr': 0.00048813523433751814, 'samples': 3182016, 'steps': 16572, 'loss/train': 1.3708523511886597}
+08/30/2021 16:13:45 - INFO - __main__ - Step 16574: {'lr': 0.00048813361885507956, 'samples': 3182208, 'steps': 16573, 'loss/train': 1.3560123443603516}
+08/30/2021 16:13:45 - INFO - __main__ - Step 16575: {'lr': 0.00048813200326534156, 'samples': 3182400, 'steps': 16574, 'loss/train': 1.6077187061309814}
+08/30/2021 16:13:45 - INFO - __main__ - Step 16576: {'lr': 0.00048813038756830506, 'samples': 3182592, 'steps': 16575, 'loss/train': 1.6748696565628052}
+08/30/2021 16:13:46 - INFO - __main__ - Step 16577: {'lr': 0.00048812877176397066, 'samples': 3182784, 'steps': 16576, 'loss/train': 0.4968474507331848}
+08/30/2021 16:13:47 - INFO - __main__ - Step 16578: {'lr': 0.00048812715585233905, 'samples': 3182976, 'steps': 16577, 'loss/train': 1.143213152885437}
+08/30/2021 16:13:48 - INFO - __main__ - Step 16579: {'lr': 0.000488125539833411, 'samples': 3183168, 'steps': 16578, 'loss/train': 1.5067323446273804}
+08/30/2021 16:13:48 - INFO - __main__ - Step 16580: {'lr': 0.0004881239237071873, 'samples': 3183360, 'steps': 16579, 'loss/train': 0.1325390636920929}
+08/30/2021 16:13:49 - INFO - __main__ - Step 16581: {'lr': 0.0004881223074736687, 'samples': 3183552, 'steps': 16580, 'loss/train': 1.699009895324707}
+08/30/2021 16:13:49 - INFO - __main__ - Step 16582: {'lr': 0.00048812069113285573, 'samples': 3183744, 'steps': 16581, 'loss/train': 0.08957020193338394}
+08/30/2021 16:13:49 - INFO - __main__ - Step 16583: {'lr': 0.00048811907468474934, 'samples': 3183936, 'steps': 16582, 'loss/train': 1.3878061771392822}
+08/30/2021 16:13:51 - INFO - __main__ - Step 16584: {'lr': 0.00048811745812935015, 'samples': 3184128, 'steps': 16583, 'loss/train': 0.20824885368347168}
+08/30/2021 16:13:51 - INFO - __main__ - Step 16585: {'lr': 0.00048811584146665895, 'samples': 3184320, 'steps': 16584, 'loss/train': 1.6124420166015625}
+08/30/2021 16:13:52 - INFO - __main__ - Step 16586: {'lr': 0.0004881142246966763, 'samples': 3184512, 'steps': 16585, 'loss/train': 1.8895361423492432}
+08/30/2021 16:13:52 - INFO - __main__ - Step 16587: {'lr': 0.00048811260781940317, 'samples': 3184704, 'steps': 16586, 'loss/train': 1.4383306503295898}
+08/30/2021 16:13:52 - INFO - __main__ - Step 16588: {'lr': 0.00048811099083484016, 'samples': 3184896, 'steps': 16587, 'loss/train': 1.6250507831573486}
+08/30/2021 16:13:54 - INFO - __main__ - Step 16589: {'lr': 0.000488109373742988, 'samples': 3185088, 'steps': 16588, 'loss/train': 1.5738410949707031}
+08/30/2021 16:13:54 - INFO - __main__ - Step 16590: {'lr': 0.0004881077565438474, 'samples': 3185280, 'steps': 16589, 'loss/train': 1.6363602876663208}
+08/30/2021 16:13:55 - INFO - __main__ - Step 16591: {'lr': 0.0004881061392374192, 'samples': 3185472, 'steps': 16590, 'loss/train': 1.9625236988067627}
+08/30/2021 16:13:55 - INFO - __main__ - Step 16592: {'lr': 0.000488104521823704, 'samples': 3185664, 'steps': 16591, 'loss/train': 1.8436386585235596}
+08/30/2021 16:13:55 - INFO - __main__ - Step 16593: {'lr': 0.00048810290430270257, 'samples': 3185856, 'steps': 16592, 'loss/train': 2.055682420730591}
+08/30/2021 16:13:56 - INFO - __main__ - Step 16594: {'lr': 0.0004881012866744156, 'samples': 3186048, 'steps': 16593, 'loss/train': 1.7000099420547485}
+08/30/2021 16:13:57 - INFO - __main__ - Step 16595: {'lr': 0.00048809966893884396, 'samples': 3186240, 'steps': 16594, 'loss/train': 1.7137199640274048}
+08/30/2021 16:13:58 - INFO - __main__ - Step 16596: {'lr': 0.00048809805109598813, 'samples': 3186432, 'steps': 16595, 'loss/train': 1.7170580625534058}
+08/30/2021 16:13:58 - INFO - __main__ - Step 16597: {'lr': 0.0004880964331458492, 'samples': 3186624, 'steps': 16596, 'loss/train': 1.5858354568481445}
+08/30/2021 16:13:59 - INFO - __main__ - Step 16598: {'lr': 0.0004880948150884276, 'samples': 3186816, 'steps': 16597, 'loss/train': 1.4752651453018188}
+08/30/2021 16:13:59 - INFO - __main__ - Step 16599: {'lr': 0.00048809319692372406, 'samples': 3187008, 'steps': 16598, 'loss/train': 1.3279571533203125}
+08/30/2021 16:14:01 - INFO - __main__ - Step 16600: {'lr': 0.0004880915786517395, 'samples': 3187200, 'steps': 16599, 'loss/train': 2.0533125400543213}
+08/30/2021 16:14:01 - INFO - __main__ - Step 16601: {'lr': 0.00048808996027247453, 'samples': 3187392, 'steps': 16600, 'loss/train': 2.0156710147857666}
+08/30/2021 16:14:02 - INFO - __main__ - Step 16602: {'lr': 0.0004880883417859299, 'samples': 3187584, 'steps': 16601, 'loss/train': 1.2864296436309814}
+08/30/2021 16:14:02 - INFO - __main__ - Step 16603: {'lr': 0.0004880867231921063, 'samples': 3187776, 'steps': 16602, 'loss/train': 1.0905944108963013}
+08/30/2021 16:14:03 - INFO - __main__ - Step 16604: {'lr': 0.0004880851044910045, 'samples': 3187968, 'steps': 16603, 'loss/train': 1.7267661094665527}
+08/30/2021 16:14:04 - INFO - __main__ - Step 16605: {'lr': 0.0004880834856826253, 'samples': 3188160, 'steps': 16604, 'loss/train': 1.4709233045578003}
+08/30/2021 16:14:04 - INFO - __main__ - Step 16606: {'lr': 0.0004880818667669693, 'samples': 3188352, 'steps': 16605, 'loss/train': 2.203814744949341}
+08/30/2021 16:14:05 - INFO - __main__ - Step 16607: {'lr': 0.00048808024774403726, 'samples': 3188544, 'steps': 16606, 'loss/train': 1.5960253477096558}
+08/30/2021 16:14:05 - INFO - __main__ - Step 16608: {'lr': 0.00048807862861382996, 'samples': 3188736, 'steps': 16607, 'loss/train': 1.7516332864761353}
+08/30/2021 16:14:05 - INFO - __main__ - Step 16609: {'lr': 0.0004880770093763481, 'samples': 3188928, 'steps': 16608, 'loss/train': 2.1294281482696533}
+08/30/2021 16:14:07 - INFO - __main__ - Step 16610: {'lr': 0.0004880753900315924, 'samples': 3189120, 'steps': 16609, 'loss/train': 1.4692928791046143}
+08/30/2021 16:14:07 - INFO - __main__ - Step 16611: {'lr': 0.00048807377057956365, 'samples': 3189312, 'steps': 16610, 'loss/train': 1.856947422027588}
+08/30/2021 16:14:08 - INFO - __main__ - Step 16612: {'lr': 0.00048807215102026247, 'samples': 3189504, 'steps': 16611, 'loss/train': 1.485852837562561}
+08/30/2021 16:14:08 - INFO - __main__ - Step 16613: {'lr': 0.00048807053135368973, 'samples': 3189696, 'steps': 16612, 'loss/train': 2.0284597873687744}
+08/30/2021 16:14:08 - INFO - __main__ - Step 16614: {'lr': 0.00048806891157984604, 'samples': 3189888, 'steps': 16613, 'loss/train': 1.6739753484725952}
+08/30/2021 16:14:10 - INFO - __main__ - Step 16615: {'lr': 0.0004880672916987322, 'samples': 3190080, 'steps': 16614, 'loss/train': 0.4266573488712311}
+08/30/2021 16:14:11 - INFO - __main__ - Step 16616: {'lr': 0.0004880656717103489, 'samples': 3190272, 'steps': 16615, 'loss/train': 1.585524320602417}
+08/30/2021 16:14:11 - INFO - __main__ - Step 16617: {'lr': 0.0004880640516146968, 'samples': 3190464, 'steps': 16616, 'loss/train': 1.5404939651489258}
+08/30/2021 16:14:11 - INFO - __main__ - Step 16618: {'lr': 0.0004880624314117768, 'samples': 3190656, 'steps': 16617, 'loss/train': 1.2139486074447632}
+08/30/2021 16:14:12 - INFO - __main__ - Step 16619: {'lr': 0.0004880608111015895, 'samples': 3190848, 'steps': 16618, 'loss/train': 1.6645313501358032}
+08/30/2021 16:14:13 - INFO - __main__ - Step 16620: {'lr': 0.00048805919068413574, 'samples': 3191040, 'steps': 16619, 'loss/train': 0.14072319865226746}
+08/30/2021 16:14:14 - INFO - __main__ - Step 16621: {'lr': 0.0004880575701594161, 'samples': 3191232, 'steps': 16620, 'loss/train': 2.3166964054107666}
+08/30/2021 16:14:14 - INFO - __main__ - Step 16622: {'lr': 0.0004880559495274315, 'samples': 3191424, 'steps': 16621, 'loss/train': 1.9499908685684204}
+08/30/2021 16:14:15 - INFO - __main__ - Step 16623: {'lr': 0.00048805432878818247, 'samples': 3191616, 'steps': 16622, 'loss/train': 1.9381393194198608}
+08/30/2021 16:14:15 - INFO - __main__ - Step 16624: {'lr': 0.0004880527079416698, 'samples': 3191808, 'steps': 16623, 'loss/train': 1.55039381980896}
+08/30/2021 16:14:15 - INFO - __main__ - Step 16625: {'lr': 0.00048805108698789435, 'samples': 3192000, 'steps': 16624, 'loss/train': 1.7067677974700928}
+08/30/2021 16:14:17 - INFO - __main__ - Step 16626: {'lr': 0.00048804946592685667, 'samples': 3192192, 'steps': 16625, 'loss/train': 0.2757457494735718}
+08/30/2021 16:14:17 - INFO - __main__ - Step 16627: {'lr': 0.0004880478447585576, 'samples': 3192384, 'steps': 16626, 'loss/train': 0.9581832885742188}
+08/30/2021 16:14:18 - INFO - __main__ - Step 16628: {'lr': 0.00048804622348299785, 'samples': 3192576, 'steps': 16627, 'loss/train': 1.693848729133606}
+08/30/2021 16:14:18 - INFO - __main__ - Step 16629: {'lr': 0.0004880446021001782, 'samples': 3192768, 'steps': 16628, 'loss/train': 1.7661103010177612}
+08/30/2021 16:14:18 - INFO - __main__ - Step 16630: {'lr': 0.00048804298061009925, 'samples': 3192960, 'steps': 16629, 'loss/train': 2.469510078430176}
+08/30/2021 16:14:20 - INFO - __main__ - Step 16631: {'lr': 0.0004880413590127619, 'samples': 3193152, 'steps': 16630, 'loss/train': 1.0144615173339844}
+08/30/2021 16:14:20 - INFO - __main__ - Step 16632: {'lr': 0.0004880397373081666, 'samples': 3193344, 'steps': 16631, 'loss/train': 1.9545166492462158}
+08/30/2021 16:14:21 - INFO - __main__ - Step 16633: {'lr': 0.0004880381154963145, 'samples': 3193536, 'steps': 16632, 'loss/train': 1.8227757215499878}
+08/30/2021 16:14:21 - INFO - __main__ - Step 16634: {'lr': 0.0004880364935772059, 'samples': 3193728, 'steps': 16633, 'loss/train': 1.6634933948516846}
+08/30/2021 16:14:21 - INFO - __main__ - Step 16635: {'lr': 0.00048803487155084184, 'samples': 3193920, 'steps': 16634, 'loss/train': 1.8381518125534058}
+08/30/2021 16:14:23 - INFO - __main__ - Step 16636: {'lr': 0.00048803324941722295, 'samples': 3194112, 'steps': 16635, 'loss/train': 1.544309377670288}
+08/30/2021 16:14:23 - INFO - __main__ - Step 16637: {'lr': 0.0004880316271763499, 'samples': 3194304, 'steps': 16636, 'loss/train': 0.11979955434799194}
+08/30/2021 16:14:24 - INFO - __main__ - Step 16638: {'lr': 0.0004880300048282235, 'samples': 3194496, 'steps': 16637, 'loss/train': 1.9168736934661865}
+08/30/2021 16:14:24 - INFO - __main__ - Step 16639: {'lr': 0.00048802838237284443, 'samples': 3194688, 'steps': 16638, 'loss/train': 2.0347630977630615}
+08/30/2021 16:14:24 - INFO - __main__ - Step 16640: {'lr': 0.0004880267598102135, 'samples': 3194880, 'steps': 16639, 'loss/train': 1.0156313180923462}
+08/30/2021 16:14:25 - INFO - __main__ - Step 16641: {'lr': 0.0004880251371403313, 'samples': 3195072, 'steps': 16640, 'loss/train': 1.5347892045974731}
+08/30/2021 16:14:26 - INFO - __main__ - Step 16642: {'lr': 0.0004880235143631987, 'samples': 3195264, 'steps': 16641, 'loss/train': 1.6933704614639282}
+08/30/2021 16:14:27 - INFO - __main__ - Step 16643: {'lr': 0.0004880218914788164, 'samples': 3195456, 'steps': 16642, 'loss/train': 1.696418285369873}
+08/30/2021 16:14:27 - INFO - __main__ - Step 16644: {'lr': 0.00048802026848718505, 'samples': 3195648, 'steps': 16643, 'loss/train': 1.2272576093673706}
+08/30/2021 16:14:28 - INFO - __main__ - Step 16645: {'lr': 0.0004880186453883054, 'samples': 3195840, 'steps': 16644, 'loss/train': 1.1475294828414917}
+08/30/2021 16:14:28 - INFO - __main__ - Step 16646: {'lr': 0.00048801702218217834, 'samples': 3196032, 'steps': 16645, 'loss/train': 1.7064080238342285}
+08/30/2021 16:14:29 - INFO - __main__ - Step 16647: {'lr': 0.0004880153988688044, 'samples': 3196224, 'steps': 16646, 'loss/train': 0.5632283687591553}
+08/30/2021 16:14:30 - INFO - __main__ - Step 16648: {'lr': 0.0004880137754481845, 'samples': 3196416, 'steps': 16647, 'loss/train': 1.7644410133361816}
+08/30/2021 16:14:30 - INFO - __main__ - Step 16649: {'lr': 0.0004880121519203191, 'samples': 3196608, 'steps': 16648, 'loss/train': 1.4228501319885254}
+08/30/2021 16:14:31 - INFO - __main__ - Step 16650: {'lr': 0.0004880105282852092, 'samples': 3196800, 'steps': 16649, 'loss/train': 1.9696342945098877}
+08/30/2021 16:14:31 - INFO - __main__ - Step 16651: {'lr': 0.0004880089045428554, 'samples': 3196992, 'steps': 16650, 'loss/train': 1.603187918663025}
+08/30/2021 16:14:33 - INFO - __main__ - Step 16652: {'lr': 0.0004880072806932585, 'samples': 3197184, 'steps': 16651, 'loss/train': 1.5181456804275513}
+08/30/2021 16:14:33 - INFO - __main__ - Step 16653: {'lr': 0.00048800565673641917, 'samples': 3197376, 'steps': 16652, 'loss/train': 1.427760362625122}
+08/30/2021 16:14:34 - INFO - __main__ - Step 16654: {'lr': 0.0004880040326723382, 'samples': 3197568, 'steps': 16653, 'loss/train': 1.944973349571228}
+08/30/2021 16:14:34 - INFO - __main__ - Step 16655: {'lr': 0.0004880024085010162, 'samples': 3197760, 'steps': 16654, 'loss/train': 1.6088995933532715}
+08/30/2021 16:14:34 - INFO - __main__ - Step 16656: {'lr': 0.00048800078422245406, 'samples': 3197952, 'steps': 16655, 'loss/train': 1.9604657888412476}
+08/30/2021 16:14:36 - INFO - __main__ - Step 16657: {'lr': 0.0004879991598366524, 'samples': 3198144, 'steps': 16656, 'loss/train': 1.8557242155075073}
+08/30/2021 16:14:37 - INFO - __main__ - Step 16658: {'lr': 0.000487997535343612, 'samples': 3198336, 'steps': 16657, 'loss/train': 2.594700336456299}
+08/30/2021 16:14:37 - INFO - __main__ - Step 16659: {'lr': 0.0004879959107433336, 'samples': 3198528, 'steps': 16658, 'loss/train': 1.4913543462753296}
+08/30/2021 16:14:37 - INFO - __main__ - Step 16660: {'lr': 0.00048799428603581786, 'samples': 3198720, 'steps': 16659, 'loss/train': 1.9455454349517822}
+08/30/2021 16:14:38 - INFO - __main__ - Step 16661: {'lr': 0.0004879926612210656, 'samples': 3198912, 'steps': 16660, 'loss/train': 0.6294904947280884}
+08/30/2021 16:14:38 - INFO - __main__ - Step 16662: {'lr': 0.0004879910362990775, 'samples': 3199104, 'steps': 16661, 'loss/train': 1.3812592029571533}
+08/30/2021 16:14:38 - INFO - __main__ - Step 16663: {'lr': 0.0004879894112698544, 'samples': 3199296, 'steps': 16662, 'loss/train': 1.2141501903533936}
+08/30/2021 16:14:40 - INFO - __main__ - Step 16664: {'lr': 0.0004879877861333969, 'samples': 3199488, 'steps': 16663, 'loss/train': 0.5333452224731445}
+08/30/2021 16:14:40 - INFO - __main__ - Step 16665: {'lr': 0.00048798616088970573, 'samples': 3199680, 'steps': 16664, 'loss/train': 0.5689380168914795}
+08/30/2021 16:14:41 - INFO - __main__ - Step 16666: {'lr': 0.0004879845355387817, 'samples': 3199872, 'steps': 16665, 'loss/train': 1.3376206159591675}
+08/30/2021 16:14:41 - INFO - __main__ - Step 16667: {'lr': 0.00048798291008062553, 'samples': 3200064, 'steps': 16666, 'loss/train': 2.0341899394989014}
+08/30/2021 16:14:41 - INFO - __main__ - Step 16668: {'lr': 0.0004879812845152379, 'samples': 3200256, 'steps': 16667, 'loss/train': 2.0121335983276367}
+08/30/2021 16:14:43 - INFO - __main__ - Step 16669: {'lr': 0.0004879796588426195, 'samples': 3200448, 'steps': 16668, 'loss/train': 1.902250051498413}
+08/30/2021 16:14:44 - INFO - __main__ - Step 16670: {'lr': 0.0004879780330627713, 'samples': 3200640, 'steps': 16669, 'loss/train': 1.7941910028457642}
+08/30/2021 16:14:44 - INFO - __main__ - Step 16671: {'lr': 0.0004879764071756938, 'samples': 3200832, 'steps': 16670, 'loss/train': 0.3390023708343506}
+08/30/2021 16:14:44 - INFO - __main__ - Step 16672: {'lr': 0.00048797478118138777, 'samples': 3201024, 'steps': 16671, 'loss/train': 1.7030514478683472}
+08/30/2021 16:14:45 - INFO - __main__ - Step 16673: {'lr': 0.000487973155079854, 'samples': 3201216, 'steps': 16672, 'loss/train': 1.5212053060531616}
+08/30/2021 16:14:46 - INFO - __main__ - Step 16674: {'lr': 0.0004879715288710932, 'samples': 3201408, 'steps': 16673, 'loss/train': 1.762177586555481}
+08/30/2021 16:14:47 - INFO - __main__ - Step 16675: {'lr': 0.0004879699025551061, 'samples': 3201600, 'steps': 16674, 'loss/train': 1.2488783597946167}
+08/30/2021 16:14:47 - INFO - __main__ - Step 16676: {'lr': 0.0004879682761318934, 'samples': 3201792, 'steps': 16675, 'loss/train': 1.6335327625274658}
+08/30/2021 16:14:47 - INFO - __main__ - Step 16677: {'lr': 0.00048796664960145596, 'samples': 3201984, 'steps': 16676, 'loss/train': 0.05811972916126251}
+08/30/2021 16:14:48 - INFO - __main__ - Step 16678: {'lr': 0.00048796502296379437, 'samples': 3202176, 'steps': 16677, 'loss/train': 1.8747398853302002}
+08/30/2021 16:14:49 - INFO - __main__ - Step 16679: {'lr': 0.0004879633962189094, 'samples': 3202368, 'steps': 16678, 'loss/train': 1.61774742603302}
+08/30/2021 16:14:50 - INFO - __main__ - Step 16680: {'lr': 0.0004879617693668018, 'samples': 3202560, 'steps': 16679, 'loss/train': 2.108137607574463}
+08/30/2021 16:14:50 - INFO - __main__ - Step 16681: {'lr': 0.00048796014240747227, 'samples': 3202752, 'steps': 16680, 'loss/train': 1.5128915309906006}
+08/30/2021 16:14:50 - INFO - __main__ - Step 16682: {'lr': 0.0004879585153409216, 'samples': 3202944, 'steps': 16681, 'loss/train': 1.926310420036316}
+08/30/2021 16:14:51 - INFO - __main__ - Step 16683: {'lr': 0.0004879568881671505, 'samples': 3203136, 'steps': 16682, 'loss/train': 1.9453061819076538}
+08/30/2021 16:14:52 - INFO - __main__ - Step 16684: {'lr': 0.0004879552608861597, 'samples': 3203328, 'steps': 16683, 'loss/train': 1.6820000410079956}
+08/30/2021 16:14:53 - INFO - __main__ - Step 16685: {'lr': 0.00048795363349794996, 'samples': 3203520, 'steps': 16684, 'loss/train': 1.78916335105896}
+08/30/2021 16:14:53 - INFO - __main__ - Step 16686: {'lr': 0.00048795200600252193, 'samples': 3203712, 'steps': 16685, 'loss/train': 1.3662347793579102}
+08/30/2021 16:14:54 - INFO - __main__ - Step 16687: {'lr': 0.00048795037839987644, 'samples': 3203904, 'steps': 16686, 'loss/train': 1.3548601865768433}
+08/30/2021 16:14:54 - INFO - __main__ - Step 16688: {'lr': 0.0004879487506900141, 'samples': 3204096, 'steps': 16687, 'loss/train': 1.7290133237838745}
+08/30/2021 16:14:55 - INFO - __main__ - Step 16689: {'lr': 0.0004879471228729358, 'samples': 3204288, 'steps': 16688, 'loss/train': 0.3155171871185303}
+08/30/2021 16:14:56 - INFO - __main__ - Step 16690: {'lr': 0.0004879454949486422, 'samples': 3204480, 'steps': 16689, 'loss/train': 1.1663745641708374}
+08/30/2021 16:14:56 - INFO - __main__ - Step 16691: {'lr': 0.000487943866917134, 'samples': 3204672, 'steps': 16690, 'loss/train': 1.5553964376449585}
+08/30/2021 16:14:57 - INFO - __main__ - Step 16692: {'lr': 0.00048794223877841197, 'samples': 3204864, 'steps': 16691, 'loss/train': 1.8806887865066528}
+08/30/2021 16:14:57 - INFO - __main__ - Step 16693: {'lr': 0.00048794061053247686, 'samples': 3205056, 'steps': 16692, 'loss/train': 1.5888007879257202}
+08/30/2021 16:14:58 - INFO - __main__ - Step 16694: {'lr': 0.0004879389821793294, 'samples': 3205248, 'steps': 16693, 'loss/train': 1.103945016860962}
+08/30/2021 16:14:59 - INFO - __main__ - Step 16695: {'lr': 0.00048793735371897027, 'samples': 3205440, 'steps': 16694, 'loss/train': 1.3188711404800415}
+08/30/2021 16:14:59 - INFO - __main__ - Step 16696: {'lr': 0.00048793572515140024, 'samples': 3205632, 'steps': 16695, 'loss/train': 1.5159010887145996}
+08/30/2021 16:15:00 - INFO - __main__ - Step 16697: {'lr': 0.00048793409647662, 'samples': 3205824, 'steps': 16696, 'loss/train': 2.130124092102051}
+08/30/2021 16:15:00 - INFO - __main__ - Step 16698: {'lr': 0.0004879324676946304, 'samples': 3206016, 'steps': 16697, 'loss/train': 1.5905779600143433}
+08/30/2021 16:15:00 - INFO - __main__ - Step 16699: {'lr': 0.0004879308388054321, 'samples': 3206208, 'steps': 16698, 'loss/train': 1.96693754196167}
+08/30/2021 16:15:03 - INFO - __main__ - Step 16700: {'lr': 0.0004879292098090258, 'samples': 3206400, 'steps': 16699, 'loss/train': 1.7866253852844238}
+08/30/2021 16:15:03 - INFO - __main__ - Step 16701: {'lr': 0.00048792758070541234, 'samples': 3206592, 'steps': 16700, 'loss/train': 1.3016022443771362}
+08/30/2021 16:15:04 - INFO - __main__ - Step 16702: {'lr': 0.00048792595149459226, 'samples': 3206784, 'steps': 16701, 'loss/train': 0.7525354623794556}
+08/30/2021 16:15:04 - INFO - __main__ - Step 16703: {'lr': 0.0004879243221765665, 'samples': 3206976, 'steps': 16702, 'loss/train': 0.6439904570579529}
+08/30/2021 16:15:04 - INFO - __main__ - Step 16704: {'lr': 0.00048792269275133574, 'samples': 3207168, 'steps': 16703, 'loss/train': 0.6069667935371399}
+08/30/2021 16:15:05 - INFO - __main__ - Step 16705: {'lr': 0.0004879210632189006, 'samples': 3207360, 'steps': 16704, 'loss/train': 1.6717065572738647}
+08/30/2021 16:15:06 - INFO - __main__ - Step 16706: {'lr': 0.0004879194335792619, 'samples': 3207552, 'steps': 16705, 'loss/train': 1.686883807182312}
+08/30/2021 16:15:07 - INFO - __main__ - Step 16707: {'lr': 0.0004879178038324205, 'samples': 3207744, 'steps': 16706, 'loss/train': 0.46764278411865234}
+08/30/2021 16:15:07 - INFO - __main__ - Step 16708: {'lr': 0.0004879161739783769, 'samples': 3207936, 'steps': 16707, 'loss/train': 1.4054722785949707}
+08/30/2021 16:15:07 - INFO - __main__ - Step 16709: {'lr': 0.00048791454401713195, 'samples': 3208128, 'steps': 16708, 'loss/train': 1.715261697769165}
+08/30/2021 16:15:08 - INFO - __main__ - Step 16710: {'lr': 0.00048791291394868644, 'samples': 3208320, 'steps': 16709, 'loss/train': 1.0365930795669556}
+08/30/2021 16:15:10 - INFO - __main__ - Step 16711: {'lr': 0.000487911283773041, 'samples': 3208512, 'steps': 16710, 'loss/train': 0.22322697937488556}
+08/30/2021 16:15:10 - INFO - __main__ - Step 16712: {'lr': 0.0004879096534901964, 'samples': 3208704, 'steps': 16711, 'loss/train': 1.6091737747192383}
+08/30/2021 16:15:11 - INFO - __main__ - Step 16713: {'lr': 0.00048790802310015336, 'samples': 3208896, 'steps': 16712, 'loss/train': 1.3067803382873535}
+08/30/2021 16:15:11 - INFO - __main__ - Step 16714: {'lr': 0.0004879063926029127, 'samples': 3209088, 'steps': 16713, 'loss/train': 0.07299730181694031}
+08/30/2021 16:15:11 - INFO - __main__ - Step 16715: {'lr': 0.00048790476199847506, 'samples': 3209280, 'steps': 16714, 'loss/train': 1.7180428504943848}
+08/30/2021 16:15:13 - INFO - __main__ - Step 16716: {'lr': 0.0004879031312868412, 'samples': 3209472, 'steps': 16715, 'loss/train': 1.3390231132507324}
+08/30/2021 16:15:13 - INFO - __main__ - Step 16717: {'lr': 0.00048790150046801187, 'samples': 3209664, 'steps': 16716, 'loss/train': 1.1674901247024536}
+08/30/2021 16:15:14 - INFO - __main__ - Step 16718: {'lr': 0.0004878998695419877, 'samples': 3209856, 'steps': 16717, 'loss/train': 1.949594259262085}
+08/30/2021 16:15:14 - INFO - __main__ - Step 16719: {'lr': 0.0004878982385087697, 'samples': 3210048, 'steps': 16718, 'loss/train': 1.2132210731506348}
+08/30/2021 16:15:15 - INFO - __main__ - Step 16720: {'lr': 0.0004878966073683583, 'samples': 3210240, 'steps': 16719, 'loss/train': 1.2069034576416016}
+08/30/2021 16:15:15 - INFO - __main__ - Step 16721: {'lr': 0.0004878949761207544, 'samples': 3210432, 'steps': 16720, 'loss/train': 1.6156997680664062}
+08/30/2021 16:15:16 - INFO - __main__ - Step 16722: {'lr': 0.0004878933447659587, 'samples': 3210624, 'steps': 16721, 'loss/train': 2.123835325241089}
+08/30/2021 16:15:17 - INFO - __main__ - Step 16723: {'lr': 0.0004878917133039719, 'samples': 3210816, 'steps': 16722, 'loss/train': 1.9504806995391846}
+08/30/2021 16:15:17 - INFO - __main__ - Step 16724: {'lr': 0.00048789008173479476, 'samples': 3211008, 'steps': 16723, 'loss/train': 1.1853959560394287}
+08/30/2021 16:15:17 - INFO - __main__ - Step 16725: {'lr': 0.0004878884500584281, 'samples': 3211200, 'steps': 16724, 'loss/train': 1.256620168685913}
+08/30/2021 16:15:18 - INFO - __main__ - Step 16726: {'lr': 0.0004878868182748725, 'samples': 3211392, 'steps': 16725, 'loss/train': 1.831167459487915}
+08/30/2021 16:15:19 - INFO - __main__ - Step 16727: {'lr': 0.0004878851863841287, 'samples': 3211584, 'steps': 16726, 'loss/train': 1.5383081436157227}
+08/30/2021 16:15:20 - INFO - __main__ - Step 16728: {'lr': 0.00048788355438619764, 'samples': 3211776, 'steps': 16727, 'loss/train': 1.5069228410720825}
+08/30/2021 16:15:20 - INFO - __main__ - Step 16729: {'lr': 0.00048788192228107986, 'samples': 3211968, 'steps': 16728, 'loss/train': 1.9376816749572754}
+08/30/2021 16:15:20 - INFO - __main__ - Step 16730: {'lr': 0.00048788029006877623, 'samples': 3212160, 'steps': 16729, 'loss/train': 1.933656096458435}
+08/30/2021 16:15:21 - INFO - __main__ - Step 16731: {'lr': 0.0004878786577492873, 'samples': 3212352, 'steps': 16730, 'loss/train': 1.6945432424545288}
+08/30/2021 16:15:22 - INFO - __main__ - Step 16732: {'lr': 0.00048787702532261396, 'samples': 3212544, 'steps': 16731, 'loss/train': 1.8733289241790771}
+08/30/2021 16:15:23 - INFO - __main__ - Step 16733: {'lr': 0.0004878753927887569, 'samples': 3212736, 'steps': 16732, 'loss/train': 1.5571599006652832}
+08/30/2021 16:15:23 - INFO - __main__ - Step 16734: {'lr': 0.0004878737601477169, 'samples': 3212928, 'steps': 16733, 'loss/train': 1.8006837368011475}
+08/30/2021 16:15:23 - INFO - __main__ - Step 16735: {'lr': 0.0004878721273994946, 'samples': 3213120, 'steps': 16734, 'loss/train': 1.913068175315857}
+08/30/2021 16:15:24 - INFO - __main__ - Step 16736: {'lr': 0.00048787049454409085, 'samples': 3213312, 'steps': 16735, 'loss/train': 1.6572901010513306}
+08/30/2021 16:15:25 - INFO - __main__ - Step 16737: {'lr': 0.0004878688615815063, 'samples': 3213504, 'steps': 16736, 'loss/train': 1.5615729093551636}
+08/30/2021 16:15:26 - INFO - __main__ - Step 16738: {'lr': 0.0004878672285117417, 'samples': 3213696, 'steps': 16737, 'loss/train': 1.1859101057052612}
+08/30/2021 16:15:26 - INFO - __main__ - Step 16739: {'lr': 0.0004878655953347978, 'samples': 3213888, 'steps': 16738, 'loss/train': 1.5913857221603394}
+08/30/2021 16:15:26 - INFO - __main__ - Step 16740: {'lr': 0.0004878639620506753, 'samples': 3214080, 'steps': 16739, 'loss/train': 1.3443471193313599}
+08/30/2021 16:15:27 - INFO - __main__ - Step 16741: {'lr': 0.00048786232865937504, 'samples': 3214272, 'steps': 16740, 'loss/train': 0.7952996492385864}
+08/30/2021 16:15:28 - INFO - __main__ - Step 16742: {'lr': 0.0004878606951608976, 'samples': 3214464, 'steps': 16741, 'loss/train': 1.502210021018982}
+08/30/2021 16:15:29 - INFO - __main__ - Step 16743: {'lr': 0.00048785906155524386, 'samples': 3214656, 'steps': 16742, 'loss/train': 1.5023962259292603}
+08/30/2021 16:15:29 - INFO - __main__ - Step 16744: {'lr': 0.0004878574278424145, 'samples': 3214848, 'steps': 16743, 'loss/train': 2.827465295791626}
+08/30/2021 16:15:30 - INFO - __main__ - Step 16745: {'lr': 0.0004878557940224102, 'samples': 3215040, 'steps': 16744, 'loss/train': 1.257771611213684}
+08/30/2021 16:15:30 - INFO - __main__ - Step 16746: {'lr': 0.0004878541600952318, 'samples': 3215232, 'steps': 16745, 'loss/train': 1.6157188415527344}
+08/30/2021 16:15:30 - INFO - __main__ - Step 16747: {'lr': 0.00048785252606087996, 'samples': 3215424, 'steps': 16746, 'loss/train': 1.7678358554840088}
+08/30/2021 16:15:32 - INFO - __main__ - Step 16748: {'lr': 0.0004878508919193555, 'samples': 3215616, 'steps': 16747, 'loss/train': 1.8955780267715454}
+08/30/2021 16:15:33 - INFO - __main__ - Step 16749: {'lr': 0.000487849257670659, 'samples': 3215808, 'steps': 16748, 'loss/train': 1.434479832649231}
+08/30/2021 16:15:33 - INFO - __main__ - Step 16750: {'lr': 0.0004878476233147914, 'samples': 3216000, 'steps': 16749, 'loss/train': 1.400259256362915}
+08/30/2021 16:15:33 - INFO - __main__ - Step 16751: {'lr': 0.00048784598885175324, 'samples': 3216192, 'steps': 16750, 'loss/train': 1.5084441900253296}
+08/30/2021 16:15:34 - INFO - __main__ - Step 16752: {'lr': 0.00048784435428154537, 'samples': 3216384, 'steps': 16751, 'loss/train': 1.7930991649627686}
+08/30/2021 16:15:34 - INFO - __main__ - Step 16753: {'lr': 0.0004878427196041686, 'samples': 3216576, 'steps': 16752, 'loss/train': 1.52134370803833}
+08/30/2021 16:15:35 - INFO - __main__ - Step 16754: {'lr': 0.00048784108481962347, 'samples': 3216768, 'steps': 16753, 'loss/train': 0.8323087096214294}
+08/30/2021 16:15:36 - INFO - __main__ - Step 16755: {'lr': 0.00048783944992791085, 'samples': 3216960, 'steps': 16754, 'loss/train': 1.7217965126037598}
+08/30/2021 16:15:36 - INFO - __main__ - Step 16756: {'lr': 0.00048783781492903145, 'samples': 3217152, 'steps': 16755, 'loss/train': 1.1818318367004395}
+08/30/2021 16:15:36 - INFO - __main__ - Step 16757: {'lr': 0.00048783617982298594, 'samples': 3217344, 'steps': 16756, 'loss/train': 1.7665915489196777}
+08/30/2021 16:15:37 - INFO - __main__ - Step 16758: {'lr': 0.00048783454460977517, 'samples': 3217536, 'steps': 16757, 'loss/train': 2.1646244525909424}
+08/30/2021 16:15:38 - INFO - __main__ - Step 16759: {'lr': 0.00048783290928939985, 'samples': 3217728, 'steps': 16758, 'loss/train': 1.5340540409088135}
+08/30/2021 16:15:39 - INFO - __main__ - Step 16760: {'lr': 0.00048783127386186064, 'samples': 3217920, 'steps': 16759, 'loss/train': 2.2429051399230957}
+08/30/2021 16:15:39 - INFO - __main__ - Step 16761: {'lr': 0.00048782963832715834, 'samples': 3218112, 'steps': 16760, 'loss/train': 2.0270144939422607}
+08/30/2021 16:15:39 - INFO - __main__ - Step 16762: {'lr': 0.0004878280026852937, 'samples': 3218304, 'steps': 16761, 'loss/train': 1.3143175840377808}
+08/30/2021 16:15:40 - INFO - __main__ - Step 16763: {'lr': 0.00048782636693626736, 'samples': 3218496, 'steps': 16762, 'loss/train': 1.7576345205307007}
+08/30/2021 16:15:42 - INFO - __main__ - Step 16764: {'lr': 0.0004878247310800802, 'samples': 3218688, 'steps': 16763, 'loss/train': 0.20639830827713013}
+08/30/2021 16:15:43 - INFO - __main__ - Step 16765: {'lr': 0.0004878230951167328, 'samples': 3218880, 'steps': 16764, 'loss/train': 0.18535570800304413}
+08/30/2021 16:15:43 - INFO - __main__ - Step 16766: {'lr': 0.0004878214590462261, 'samples': 3219072, 'steps': 16765, 'loss/train': 0.671101987361908}
+08/30/2021 16:15:44 - INFO - __main__ - Step 16767: {'lr': 0.0004878198228685607, 'samples': 3219264, 'steps': 16766, 'loss/train': 1.7018426656723022}
+08/30/2021 16:15:44 - INFO - __main__ - Step 16768: {'lr': 0.00048781818658373734, 'samples': 3219456, 'steps': 16767, 'loss/train': 1.3425238132476807}
+08/30/2021 16:15:44 - INFO - __main__ - Step 16769: {'lr': 0.00048781655019175676, 'samples': 3219648, 'steps': 16768, 'loss/train': 1.5089943408966064}
+08/30/2021 16:15:46 - INFO - __main__ - Step 16770: {'lr': 0.00048781491369261965, 'samples': 3219840, 'steps': 16769, 'loss/train': 1.4512887001037598}
+08/30/2021 16:15:46 - INFO - __main__ - Step 16771: {'lr': 0.00048781327708632695, 'samples': 3220032, 'steps': 16770, 'loss/train': 0.9616290926933289}
+08/30/2021 16:15:47 - INFO - __main__ - Step 16772: {'lr': 0.0004878116403728792, 'samples': 3220224, 'steps': 16771, 'loss/train': 1.8094511032104492}
+08/30/2021 16:15:47 - INFO - __main__ - Step 16773: {'lr': 0.0004878100035522771, 'samples': 3220416, 'steps': 16772, 'loss/train': 1.944799542427063}
+08/30/2021 16:15:47 - INFO - __main__ - Step 16774: {'lr': 0.00048780836662452154, 'samples': 3220608, 'steps': 16773, 'loss/train': 1.8739910125732422}
+08/30/2021 16:15:49 - INFO - __main__ - Step 16775: {'lr': 0.00048780672958961325, 'samples': 3220800, 'steps': 16774, 'loss/train': 2.0597751140594482}
+08/30/2021 16:15:49 - INFO - __main__ - Step 16776: {'lr': 0.0004878050924475529, 'samples': 3220992, 'steps': 16775, 'loss/train': 1.400397777557373}
+08/30/2021 16:15:50 - INFO - __main__ - Step 16777: {'lr': 0.00048780345519834124, 'samples': 3221184, 'steps': 16776, 'loss/train': 1.1562952995300293}
+08/30/2021 16:15:50 - INFO - __main__ - Step 16778: {'lr': 0.000487801817841979, 'samples': 3221376, 'steps': 16777, 'loss/train': 0.9177966117858887}
+08/30/2021 16:15:50 - INFO - __main__ - Step 16779: {'lr': 0.0004878001803784669, 'samples': 3221568, 'steps': 16778, 'loss/train': 1.7204710245132446}
+08/30/2021 16:15:51 - INFO - __main__ - Step 16780: {'lr': 0.00048779854280780576, 'samples': 3221760, 'steps': 16779, 'loss/train': 1.5911046266555786}
+08/30/2021 16:15:52 - INFO - __main__ - Step 16781: {'lr': 0.00048779690512999627, 'samples': 3221952, 'steps': 16780, 'loss/train': 1.4506856203079224}
+08/30/2021 16:15:53 - INFO - __main__ - Step 16782: {'lr': 0.0004877952673450391, 'samples': 3222144, 'steps': 16781, 'loss/train': 1.4995564222335815}
+08/30/2021 16:15:53 - INFO - __main__ - Step 16783: {'lr': 0.0004877936294529351, 'samples': 3222336, 'steps': 16782, 'loss/train': 0.9332077503204346}
+08/30/2021 16:15:53 - INFO - __main__ - Step 16784: {'lr': 0.00048779199145368494, 'samples': 3222528, 'steps': 16783, 'loss/train': 1.4664751291275024}
+08/30/2021 16:15:54 - INFO - __main__ - Step 16785: {'lr': 0.0004877903533472894, 'samples': 3222720, 'steps': 16784, 'loss/train': 1.3890423774719238}
+08/30/2021 16:15:55 - INFO - __main__ - Step 16786: {'lr': 0.0004877887151337492, 'samples': 3222912, 'steps': 16785, 'loss/train': 0.972080409526825}
+08/30/2021 16:15:56 - INFO - __main__ - Step 16787: {'lr': 0.0004877870768130651, 'samples': 3223104, 'steps': 16786, 'loss/train': 1.5679256916046143}
+08/30/2021 16:15:56 - INFO - __main__ - Step 16788: {'lr': 0.0004877854383852377, 'samples': 3223296, 'steps': 16787, 'loss/train': 1.64675772190094}
+08/30/2021 16:15:57 - INFO - __main__ - Step 16789: {'lr': 0.000487783799850268, 'samples': 3223488, 'steps': 16788, 'loss/train': 1.936020016670227}
+08/30/2021 16:15:57 - INFO - __main__ - Step 16790: {'lr': 0.00048778216120815644, 'samples': 3223680, 'steps': 16789, 'loss/train': 1.426086187362671}
+08/30/2021 16:15:58 - INFO - __main__ - Step 16791: {'lr': 0.00048778052245890404, 'samples': 3223872, 'steps': 16790, 'loss/train': 1.7422831058502197}
+08/30/2021 16:15:59 - INFO - __main__ - Step 16792: {'lr': 0.0004877788836025113, 'samples': 3224064, 'steps': 16791, 'loss/train': 1.311118245124817}
+08/30/2021 16:15:59 - INFO - __main__ - Step 16793: {'lr': 0.0004877772446389791, 'samples': 3224256, 'steps': 16792, 'loss/train': 1.623799204826355}
+08/30/2021 16:16:00 - INFO - __main__ - Step 16794: {'lr': 0.0004877756055683082, 'samples': 3224448, 'steps': 16793, 'loss/train': 2.0339138507843018}
+08/30/2021 16:16:00 - INFO - __main__ - Step 16795: {'lr': 0.0004877739663904992, 'samples': 3224640, 'steps': 16794, 'loss/train': 1.47018301486969}
+08/30/2021 16:16:02 - INFO - __main__ - Step 16796: {'lr': 0.00048777232710555296, 'samples': 3224832, 'steps': 16795, 'loss/train': 1.961258888244629}
+08/30/2021 16:16:02 - INFO - __main__ - Step 16797: {'lr': 0.0004877706877134702, 'samples': 3225024, 'steps': 16796, 'loss/train': 1.7934300899505615}
+08/30/2021 16:16:03 - INFO - __main__ - Step 16798: {'lr': 0.0004877690482142516, 'samples': 3225216, 'steps': 16797, 'loss/train': 1.6483789682388306}
+08/30/2021 16:16:03 - INFO - __main__ - Step 16799: {'lr': 0.0004877674086078979, 'samples': 3225408, 'steps': 16798, 'loss/train': 1.7061437368392944}
+08/30/2021 16:16:03 - INFO - __main__ - Step 16800: {'lr': 0.0004877657688944099, 'samples': 3225600, 'steps': 16799, 'loss/train': 1.4893561601638794}
+08/30/2021 16:16:04 - INFO - __main__ - Step 16801: {'lr': 0.0004877641290737884, 'samples': 3225792, 'steps': 16800, 'loss/train': 1.5711534023284912}
+08/30/2021 16:16:05 - INFO - __main__ - Step 16802: {'lr': 0.000487762489146034, 'samples': 3225984, 'steps': 16801, 'loss/train': 0.10147201269865036}
+08/30/2021 16:16:06 - INFO - __main__ - Step 16803: {'lr': 0.0004877608491111475, 'samples': 3226176, 'steps': 16802, 'loss/train': 1.5733031034469604}
+08/30/2021 16:16:06 - INFO - __main__ - Step 16804: {'lr': 0.0004877592089691296, 'samples': 3226368, 'steps': 16803, 'loss/train': 1.1071979999542236}
+08/30/2021 16:16:06 - INFO - __main__ - Step 16805: {'lr': 0.00048775756871998106, 'samples': 3226560, 'steps': 16804, 'loss/train': 1.2677621841430664}
+08/30/2021 16:16:07 - INFO - __main__ - Step 16806: {'lr': 0.0004877559283637026, 'samples': 3226752, 'steps': 16805, 'loss/train': 1.9323376417160034}
+08/30/2021 16:16:08 - INFO - __main__ - Step 16807: {'lr': 0.0004877542879002951, 'samples': 3226944, 'steps': 16806, 'loss/train': 1.47136390209198}
+08/30/2021 16:16:09 - INFO - __main__ - Step 16808: {'lr': 0.0004877526473297591, 'samples': 3227136, 'steps': 16807, 'loss/train': 1.6244699954986572}
+08/30/2021 16:16:09 - INFO - __main__ - Step 16809: {'lr': 0.0004877510066520954, 'samples': 3227328, 'steps': 16808, 'loss/train': 1.7713903188705444}
+08/30/2021 16:16:09 - INFO - __main__ - Step 16810: {'lr': 0.0004877493658673048, 'samples': 3227520, 'steps': 16809, 'loss/train': 2.050170660018921}
+08/30/2021 16:16:10 - INFO - __main__ - Step 16811: {'lr': 0.00048774772497538806, 'samples': 3227712, 'steps': 16810, 'loss/train': 2.4477641582489014}
+08/30/2021 16:16:11 - INFO - __main__ - Step 16812: {'lr': 0.0004877460839763458, 'samples': 3227904, 'steps': 16811, 'loss/train': 1.2472822666168213}
+08/30/2021 16:16:12 - INFO - __main__ - Step 16813: {'lr': 0.0004877444428701788, 'samples': 3228096, 'steps': 16812, 'loss/train': 1.5294315814971924}
+08/30/2021 16:16:12 - INFO - __main__ - Step 16814: {'lr': 0.0004877428016568879, 'samples': 3228288, 'steps': 16813, 'loss/train': 2.1093595027923584}
+08/30/2021 16:16:13 - INFO - __main__ - Step 16815: {'lr': 0.00048774116033647373, 'samples': 3228480, 'steps': 16814, 'loss/train': 1.6045103073120117}
+08/30/2021 16:16:13 - INFO - __main__ - Step 16816: {'lr': 0.0004877395189089371, 'samples': 3228672, 'steps': 16815, 'loss/train': 2.525740146636963}
+08/30/2021 16:16:15 - INFO - __main__ - Step 16817: {'lr': 0.00048773787737427867, 'samples': 3228864, 'steps': 16816, 'loss/train': 1.4167840480804443}
+08/30/2021 16:16:16 - INFO - __main__ - Step 16818: {'lr': 0.0004877362357324992, 'samples': 3229056, 'steps': 16817, 'loss/train': 2.2660722732543945}
+08/30/2021 16:16:16 - INFO - __main__ - Step 16819: {'lr': 0.0004877345939835995, 'samples': 3229248, 'steps': 16818, 'loss/train': 1.4358583688735962}
+08/30/2021 16:16:16 - INFO - __main__ - Step 16820: {'lr': 0.0004877329521275802, 'samples': 3229440, 'steps': 16819, 'loss/train': 1.6625192165374756}
+08/30/2021 16:16:17 - INFO - __main__ - Step 16821: {'lr': 0.0004877313101644422, 'samples': 3229632, 'steps': 16820, 'loss/train': 1.6703619956970215}
+08/30/2021 16:16:17 - INFO - __main__ - Step 16822: {'lr': 0.000487729668094186, 'samples': 3229824, 'steps': 16821, 'loss/train': 2.0354955196380615}
+08/30/2021 16:16:18 - INFO - __main__ - Step 16823: {'lr': 0.0004877280259168125, 'samples': 3230016, 'steps': 16822, 'loss/train': 1.4470092058181763}
+08/30/2021 16:16:19 - INFO - __main__ - Step 16824: {'lr': 0.0004877263836323226, 'samples': 3230208, 'steps': 16823, 'loss/train': 1.4930732250213623}
+08/30/2021 16:16:19 - INFO - __main__ - Step 16825: {'lr': 0.00048772474124071663, 'samples': 3230400, 'steps': 16824, 'loss/train': 1.8102967739105225}
+08/30/2021 16:16:20 - INFO - __main__ - Step 16826: {'lr': 0.0004877230987419957, 'samples': 3230592, 'steps': 16825, 'loss/train': 1.7201083898544312}
+08/30/2021 16:16:20 - INFO - __main__ - Step 16827: {'lr': 0.00048772145613616035, 'samples': 3230784, 'steps': 16826, 'loss/train': 1.827391505241394}
+08/30/2021 16:16:22 - INFO - __main__ - Step 16828: {'lr': 0.00048771981342321145, 'samples': 3230976, 'steps': 16827, 'loss/train': 1.4888100624084473}
+08/30/2021 16:16:22 - INFO - __main__ - Step 16829: {'lr': 0.0004877181706031496, 'samples': 3231168, 'steps': 16828, 'loss/train': 1.685758352279663}
+08/30/2021 16:16:23 - INFO - __main__ - Step 16830: {'lr': 0.00048771652767597563, 'samples': 3231360, 'steps': 16829, 'loss/train': 1.369916558265686}
+08/30/2021 16:16:23 - INFO - __main__ - Step 16831: {'lr': 0.0004877148846416903, 'samples': 3231552, 'steps': 16830, 'loss/train': 1.7621418237686157}
+08/30/2021 16:16:23 - INFO - __main__ - Step 16832: {'lr': 0.0004877132415002943, 'samples': 3231744, 'steps': 16831, 'loss/train': 1.6573519706726074}
+08/30/2021 16:16:25 - INFO - __main__ - Step 16833: {'lr': 0.00048771159825178827, 'samples': 3231936, 'steps': 16832, 'loss/train': 1.4401060342788696}
+08/30/2021 16:16:26 - INFO - __main__ - Step 16834: {'lr': 0.0004877099548961732, 'samples': 3232128, 'steps': 16833, 'loss/train': 1.8510234355926514}
+08/30/2021 16:16:26 - INFO - __main__ - Step 16835: {'lr': 0.0004877083114334496, 'samples': 3232320, 'steps': 16834, 'loss/train': 1.7695484161376953}
+08/30/2021 16:16:27 - INFO - __main__ - Step 16836: {'lr': 0.0004877066678636184, 'samples': 3232512, 'steps': 16835, 'loss/train': 1.2076002359390259}
+08/30/2021 16:16:27 - INFO - __main__ - Step 16837: {'lr': 0.00048770502418668017, 'samples': 3232704, 'steps': 16836, 'loss/train': 1.9213272333145142}
+08/30/2021 16:16:27 - INFO - __main__ - Step 16838: {'lr': 0.00048770338040263574, 'samples': 3232896, 'steps': 16837, 'loss/train': 1.7977879047393799}
+08/30/2021 16:16:28 - INFO - __main__ - Step 16839: {'lr': 0.00048770173651148586, 'samples': 3233088, 'steps': 16838, 'loss/train': 1.4382543563842773}
+08/30/2021 16:16:29 - INFO - __main__ - Step 16840: {'lr': 0.0004877000925132312, 'samples': 3233280, 'steps': 16839, 'loss/train': 1.8501614332199097}
+08/30/2021 16:16:30 - INFO - __main__ - Step 16841: {'lr': 0.0004876984484078726, 'samples': 3233472, 'steps': 16840, 'loss/train': 2.0979394912719727}
+08/30/2021 16:16:30 - INFO - __main__ - Step 16842: {'lr': 0.0004876968041954107, 'samples': 3233664, 'steps': 16841, 'loss/train': 1.6127644777297974}
+08/30/2021 16:16:30 - INFO - __main__ - Step 16843: {'lr': 0.00048769515987584624, 'samples': 3233856, 'steps': 16842, 'loss/train': 1.70716392993927}
+08/30/2021 16:16:31 - INFO - __main__ - Step 16844: {'lr': 0.0004876935154491801, 'samples': 3234048, 'steps': 16843, 'loss/train': 1.579373836517334}
+08/30/2021 16:16:32 - INFO - __main__ - Step 16845: {'lr': 0.00048769187091541287, 'samples': 3234240, 'steps': 16844, 'loss/train': 2.0687344074249268}
+08/30/2021 16:16:33 - INFO - __main__ - Step 16846: {'lr': 0.0004876902262745454, 'samples': 3234432, 'steps': 16845, 'loss/train': 1.246543288230896}
+08/30/2021 16:16:33 - INFO - __main__ - Step 16847: {'lr': 0.00048768858152657837, 'samples': 3234624, 'steps': 16846, 'loss/train': 1.0815016031265259}
+08/30/2021 16:16:33 - INFO - __main__ - Step 16848: {'lr': 0.0004876869366715125, 'samples': 3234816, 'steps': 16847, 'loss/train': 2.131363868713379}
+08/30/2021 16:16:34 - INFO - __main__ - Step 16849: {'lr': 0.0004876852917093486, 'samples': 3235008, 'steps': 16848, 'loss/train': 1.6099157333374023}
+08/30/2021 16:16:35 - INFO - __main__ - Step 16850: {'lr': 0.0004876836466400874, 'samples': 3235200, 'steps': 16849, 'loss/train': 1.794905185699463}
+08/30/2021 16:16:36 - INFO - __main__ - Step 16851: {'lr': 0.00048768200146372955, 'samples': 3235392, 'steps': 16850, 'loss/train': 1.6487356424331665}
+08/30/2021 16:16:36 - INFO - __main__ - Step 16852: {'lr': 0.00048768035618027597, 'samples': 3235584, 'steps': 16851, 'loss/train': 1.405745506286621}
+08/30/2021 16:16:37 - INFO - __main__ - Step 16853: {'lr': 0.00048767871078972717, 'samples': 3235776, 'steps': 16852, 'loss/train': 0.655771791934967}
+08/30/2021 16:16:37 - INFO - __main__ - Step 16854: {'lr': 0.000487677065292084, 'samples': 3235968, 'steps': 16853, 'loss/train': 0.8521744012832642}
+08/30/2021 16:16:38 - INFO - __main__ - Step 16855: {'lr': 0.0004876754196873473, 'samples': 3236160, 'steps': 16854, 'loss/train': 1.6467833518981934}
+08/30/2021 16:16:39 - INFO - __main__ - Step 16856: {'lr': 0.00048767377397551773, 'samples': 3236352, 'steps': 16855, 'loss/train': 1.3419854640960693}
+08/30/2021 16:16:39 - INFO - __main__ - Step 16857: {'lr': 0.00048767212815659593, 'samples': 3236544, 'steps': 16856, 'loss/train': 1.296749234199524}
+08/30/2021 16:16:39 - INFO - __main__ - Step 16858: {'lr': 0.0004876704822305828, 'samples': 3236736, 'steps': 16857, 'loss/train': 1.3770450353622437}
+08/30/2021 16:16:40 - INFO - __main__ - Step 16859: {'lr': 0.00048766883619747906, 'samples': 3236928, 'steps': 16858, 'loss/train': 1.717189908027649}
+08/30/2021 16:16:40 - INFO - __main__ - Step 16860: {'lr': 0.00048766719005728534, 'samples': 3237120, 'steps': 16859, 'loss/train': 1.4536820650100708}
+08/30/2021 16:16:42 - INFO - __main__ - Step 16861: {'lr': 0.0004876655438100024, 'samples': 3237312, 'steps': 16860, 'loss/train': 1.5952472686767578}
+08/30/2021 16:16:42 - INFO - __main__ - Step 16862: {'lr': 0.00048766389745563113, 'samples': 3237504, 'steps': 16861, 'loss/train': 1.6588070392608643}
+08/30/2021 16:16:43 - INFO - __main__ - Step 16863: {'lr': 0.00048766225099417215, 'samples': 3237696, 'steps': 16862, 'loss/train': 2.1189510822296143}
+08/30/2021 16:16:43 - INFO - __main__ - Step 16864: {'lr': 0.0004876606044256262, 'samples': 3237888, 'steps': 16863, 'loss/train': 1.515399694442749}
+08/30/2021 16:16:43 - INFO - __main__ - Step 16865: {'lr': 0.0004876589577499941, 'samples': 3238080, 'steps': 16864, 'loss/train': 1.8756680488586426}
+08/30/2021 16:16:45 - INFO - __main__ - Step 16866: {'lr': 0.0004876573109672765, 'samples': 3238272, 'steps': 16865, 'loss/train': 1.465890645980835}
+08/30/2021 16:16:45 - INFO - __main__ - Step 16867: {'lr': 0.0004876556640774742, 'samples': 3238464, 'steps': 16866, 'loss/train': 0.9735254049301147}
+08/30/2021 16:16:45 - INFO - __main__ - Step 16868: {'lr': 0.0004876540170805879, 'samples': 3238656, 'steps': 16867, 'loss/train': 1.6697684526443481}
+08/30/2021 16:16:46 - INFO - __main__ - Step 16869: {'lr': 0.00048765236997661845, 'samples': 3238848, 'steps': 16868, 'loss/train': 1.7975212335586548}
+08/30/2021 16:16:46 - INFO - __main__ - Step 16870: {'lr': 0.0004876507227655664, 'samples': 3239040, 'steps': 16869, 'loss/train': 2.108999252319336}
+08/30/2021 16:16:48 - INFO - __main__ - Step 16871: {'lr': 0.00048764907544743264, 'samples': 3239232, 'steps': 16870, 'loss/train': 1.7371759414672852}
+08/30/2021 16:16:49 - INFO - __main__ - Step 16872: {'lr': 0.0004876474280222179, 'samples': 3239424, 'steps': 16871, 'loss/train': 1.6256959438323975}
+08/30/2021 16:16:49 - INFO - __main__ - Step 16873: {'lr': 0.00048764578048992284, 'samples': 3239616, 'steps': 16872, 'loss/train': 1.8462085723876953}
+08/30/2021 16:16:49 - INFO - __main__ - Step 16874: {'lr': 0.0004876441328505483, 'samples': 3239808, 'steps': 16873, 'loss/train': 1.6450989246368408}
+08/30/2021 16:16:50 - INFO - __main__ - Step 16875: {'lr': 0.000487642485104095, 'samples': 3240000, 'steps': 16874, 'loss/train': 1.564517617225647}
+08/30/2021 16:16:50 - INFO - __main__ - Step 16876: {'lr': 0.00048764083725056365, 'samples': 3240192, 'steps': 16875, 'loss/train': 1.8679288625717163}
+08/30/2021 16:16:52 - INFO - __main__ - Step 16877: {'lr': 0.00048763918928995496, 'samples': 3240384, 'steps': 16876, 'loss/train': 0.08533859252929688}
+08/30/2021 16:16:53 - INFO - __main__ - Step 16878: {'lr': 0.00048763754122226977, 'samples': 3240576, 'steps': 16877, 'loss/train': 0.792040228843689}
+08/30/2021 16:16:53 - INFO - __main__ - Step 16879: {'lr': 0.00048763589304750876, 'samples': 3240768, 'steps': 16878, 'loss/train': 1.5878849029541016}
+08/30/2021 16:16:53 - INFO - __main__ - Step 16880: {'lr': 0.0004876342447656727, 'samples': 3240960, 'steps': 16879, 'loss/train': 1.5004578828811646}
+08/30/2021 16:16:54 - INFO - __main__ - Step 16881: {'lr': 0.00048763259637676226, 'samples': 3241152, 'steps': 16880, 'loss/train': 0.9142868518829346}
+08/30/2021 16:16:54 - INFO - __main__ - Step 16882: {'lr': 0.00048763094788077834, 'samples': 3241344, 'steps': 16881, 'loss/train': 2.1745200157165527}
+08/30/2021 16:16:56 - INFO - __main__ - Step 16883: {'lr': 0.0004876292992777215, 'samples': 3241536, 'steps': 16882, 'loss/train': 0.9276759624481201}
+08/30/2021 16:16:56 - INFO - __main__ - Step 16884: {'lr': 0.00048762765056759255, 'samples': 3241728, 'steps': 16883, 'loss/train': 1.70012366771698}
+08/30/2021 16:16:56 - INFO - __main__ - Step 16885: {'lr': 0.00048762600175039227, 'samples': 3241920, 'steps': 16884, 'loss/train': 1.8063913583755493}
+08/30/2021 16:16:57 - INFO - __main__ - Step 16886: {'lr': 0.0004876243528261214, 'samples': 3242112, 'steps': 16885, 'loss/train': 1.6086015701293945}
+08/30/2021 16:16:57 - INFO - __main__ - Step 16887: {'lr': 0.0004876227037947807, 'samples': 3242304, 'steps': 16886, 'loss/train': 1.947364091873169}
+08/30/2021 16:16:59 - INFO - __main__ - Step 16888: {'lr': 0.0004876210546563707, 'samples': 3242496, 'steps': 16887, 'loss/train': 1.076502799987793}
+08/30/2021 16:16:59 - INFO - __main__ - Step 16889: {'lr': 0.0004876194054108926, 'samples': 3242688, 'steps': 16888, 'loss/train': 1.7061368227005005}
+08/30/2021 16:16:59 - INFO - __main__ - Step 16890: {'lr': 0.0004876177560583466, 'samples': 3242880, 'steps': 16889, 'loss/train': 1.4884884357452393}
+08/30/2021 16:17:00 - INFO - __main__ - Step 16891: {'lr': 0.00048761610659873387, 'samples': 3243072, 'steps': 16890, 'loss/train': 1.8173021078109741}
+08/30/2021 16:17:00 - INFO - __main__ - Step 16892: {'lr': 0.0004876144570320549, 'samples': 3243264, 'steps': 16891, 'loss/train': 1.4878637790679932}
+08/30/2021 16:17:01 - INFO - __main__ - Step 16893: {'lr': 0.0004876128073583106, 'samples': 3243456, 'steps': 16892, 'loss/train': 1.981358289718628}
+08/30/2021 16:17:02 - INFO - __main__ - Step 16894: {'lr': 0.00048761115757750155, 'samples': 3243648, 'steps': 16893, 'loss/train': 1.865716814994812}
+08/30/2021 16:17:02 - INFO - __main__ - Step 16895: {'lr': 0.00048760950768962863, 'samples': 3243840, 'steps': 16894, 'loss/train': 1.4976617097854614}
+08/30/2021 16:17:03 - INFO - __main__ - Step 16896: {'lr': 0.00048760785769469254, 'samples': 3244032, 'steps': 16895, 'loss/train': 1.4995694160461426}
+08/30/2021 16:17:03 - INFO - __main__ - Step 16897: {'lr': 0.00048760620759269403, 'samples': 3244224, 'steps': 16896, 'loss/train': 1.84534752368927}
+08/30/2021 16:17:04 - INFO - __main__ - Step 16898: {'lr': 0.00048760455738363376, 'samples': 3244416, 'steps': 16897, 'loss/train': 1.0716979503631592}
+08/30/2021 16:17:05 - INFO - __main__ - Step 16899: {'lr': 0.0004876029070675126, 'samples': 3244608, 'steps': 16898, 'loss/train': 1.7161740064620972}
+08/30/2021 16:17:05 - INFO - __main__ - Step 16900: {'lr': 0.0004876012566443312, 'samples': 3244800, 'steps': 16899, 'loss/train': 1.3478282690048218}
+08/30/2021 16:17:06 - INFO - __main__ - Step 16901: {'lr': 0.00048759960611409036, 'samples': 3244992, 'steps': 16900, 'loss/train': 1.9062011241912842}
+08/30/2021 16:17:06 - INFO - __main__ - Step 16902: {'lr': 0.00048759795547679083, 'samples': 3245184, 'steps': 16901, 'loss/train': 2.2854104042053223}
+08/30/2021 16:17:06 - INFO - __main__ - Step 16903: {'lr': 0.00048759630473243327, 'samples': 3245376, 'steps': 16902, 'loss/train': 1.3685877323150635}
+08/30/2021 16:17:08 - INFO - __main__ - Step 16904: {'lr': 0.00048759465388101855, 'samples': 3245568, 'steps': 16903, 'loss/train': 1.9079225063323975}
+08/30/2021 16:17:08 - INFO - __main__ - Step 16905: {'lr': 0.0004875930029225473, 'samples': 3245760, 'steps': 16904, 'loss/train': 0.7501497864723206}
+08/30/2021 16:17:09 - INFO - __main__ - Step 16906: {'lr': 0.0004875913518570203, 'samples': 3245952, 'steps': 16905, 'loss/train': 1.463302493095398}
+08/30/2021 16:17:09 - INFO - __main__ - Step 16907: {'lr': 0.0004875897006844383, 'samples': 3246144, 'steps': 16906, 'loss/train': 2.013986825942993}
+08/30/2021 16:17:09 - INFO - __main__ - Step 16908: {'lr': 0.00048758804940480203, 'samples': 3246336, 'steps': 16907, 'loss/train': 1.6306395530700684}
+08/30/2021 16:17:11 - INFO - __main__ - Step 16909: {'lr': 0.0004875863980181123, 'samples': 3246528, 'steps': 16908, 'loss/train': 0.6218293309211731}
+08/30/2021 16:17:11 - INFO - __main__ - Step 16910: {'lr': 0.0004875847465243698, 'samples': 3246720, 'steps': 16909, 'loss/train': 2.3276655673980713}
+08/30/2021 16:17:12 - INFO - __main__ - Step 16911: {'lr': 0.00048758309492357533, 'samples': 3246912, 'steps': 16910, 'loss/train': 3.1968994140625}
+08/30/2021 16:17:12 - INFO - __main__ - Step 16912: {'lr': 0.0004875814432157295, 'samples': 3247104, 'steps': 16911, 'loss/train': 1.6495847702026367}
+08/30/2021 16:17:12 - INFO - __main__ - Step 16913: {'lr': 0.0004875797914008332, 'samples': 3247296, 'steps': 16912, 'loss/train': 2.0352587699890137}
+08/30/2021 16:17:14 - INFO - __main__ - Step 16914: {'lr': 0.00048757813947888706, 'samples': 3247488, 'steps': 16913, 'loss/train': 1.3868038654327393}
+08/30/2021 16:17:14 - INFO - __main__ - Step 16915: {'lr': 0.0004875764874498919, 'samples': 3247680, 'steps': 16914, 'loss/train': 1.3998552560806274}
+08/30/2021 16:17:15 - INFO - __main__ - Step 16916: {'lr': 0.00048757483531384837, 'samples': 3247872, 'steps': 16915, 'loss/train': 1.9597069025039673}
+08/30/2021 16:17:15 - INFO - __main__ - Step 16917: {'lr': 0.0004875731830707574, 'samples': 3248064, 'steps': 16916, 'loss/train': 1.2749173641204834}
+08/30/2021 16:17:15 - INFO - __main__ - Step 16918: {'lr': 0.00048757153072061954, 'samples': 3248256, 'steps': 16917, 'loss/train': 1.8954534530639648}
+08/30/2021 16:17:17 - INFO - __main__ - Step 16919: {'lr': 0.0004875698782634357, 'samples': 3248448, 'steps': 16918, 'loss/train': 2.011024236679077}
+08/30/2021 16:17:17 - INFO - __main__ - Step 16920: {'lr': 0.00048756822569920647, 'samples': 3248640, 'steps': 16919, 'loss/train': 1.3850997686386108}
+08/30/2021 16:17:18 - INFO - __main__ - Step 16921: {'lr': 0.0004875665730279326, 'samples': 3248832, 'steps': 16920, 'loss/train': 1.5362807512283325}
+08/30/2021 16:17:18 - INFO - __main__ - Step 16922: {'lr': 0.000487564920249615, 'samples': 3249024, 'steps': 16921, 'loss/train': 1.6729166507720947}
+08/30/2021 16:17:18 - INFO - __main__ - Step 16923: {'lr': 0.00048756326736425427, 'samples': 3249216, 'steps': 16922, 'loss/train': 1.3989808559417725}
+08/30/2021 16:17:20 - INFO - __main__ - Step 16924: {'lr': 0.00048756161437185126, 'samples': 3249408, 'steps': 16923, 'loss/train': 1.8012539148330688}
+08/30/2021 16:17:20 - INFO - __main__ - Step 16925: {'lr': 0.0004875599612724066, 'samples': 3249600, 'steps': 16924, 'loss/train': 1.931175947189331}
+08/30/2021 16:17:21 - INFO - __main__ - Step 16926: {'lr': 0.00048755830806592105, 'samples': 3249792, 'steps': 16925, 'loss/train': 1.0830150842666626}
+08/30/2021 16:17:21 - INFO - __main__ - Step 16927: {'lr': 0.00048755665475239547, 'samples': 3249984, 'steps': 16926, 'loss/train': 1.3054875135421753}
+08/30/2021 16:17:21 - INFO - __main__ - Step 16928: {'lr': 0.0004875550013318305, 'samples': 3250176, 'steps': 16927, 'loss/train': 1.578044056892395}
+08/30/2021 16:17:22 - INFO - __main__ - Step 16929: {'lr': 0.0004875533478042269, 'samples': 3250368, 'steps': 16928, 'loss/train': 1.6108318567276}
+08/30/2021 16:17:24 - INFO - __main__ - Step 16930: {'lr': 0.00048755169416958544, 'samples': 3250560, 'steps': 16929, 'loss/train': 1.500242829322815}
+08/30/2021 16:17:24 - INFO - __main__ - Step 16931: {'lr': 0.00048755004042790685, 'samples': 3250752, 'steps': 16930, 'loss/train': 1.882196307182312}
+08/30/2021 16:17:25 - INFO - __main__ - Step 16932: {'lr': 0.00048754838657919186, 'samples': 3250944, 'steps': 16931, 'loss/train': 1.561686635017395}
+08/30/2021 16:17:25 - INFO - __main__ - Step 16933: {'lr': 0.00048754673262344124, 'samples': 3251136, 'steps': 16932, 'loss/train': 0.8742133975028992}
+08/30/2021 16:17:25 - INFO - __main__ - Step 16934: {'lr': 0.00048754507856065574, 'samples': 3251328, 'steps': 16933, 'loss/train': 1.7597050666809082}
+08/30/2021 16:17:27 - INFO - __main__ - Step 16935: {'lr': 0.0004875434243908361, 'samples': 3251520, 'steps': 16934, 'loss/train': 5.917540550231934}
+08/30/2021 16:17:27 - INFO - __main__ - Step 16936: {'lr': 0.00048754177011398303, 'samples': 3251712, 'steps': 16935, 'loss/train': 1.3282630443572998}
+08/30/2021 16:17:28 - INFO - __main__ - Step 16937: {'lr': 0.0004875401157300973, 'samples': 3251904, 'steps': 16936, 'loss/train': 1.3805826902389526}
+08/30/2021 16:17:28 - INFO - __main__ - Step 16938: {'lr': 0.00048753846123917964, 'samples': 3252096, 'steps': 16937, 'loss/train': 1.926552414894104}
+08/30/2021 16:17:28 - INFO - __main__ - Step 16939: {'lr': 0.0004875368066412309, 'samples': 3252288, 'steps': 16938, 'loss/train': 1.5819123983383179}
+08/30/2021 16:17:30 - INFO - __main__ - Step 16940: {'lr': 0.00048753515193625165, 'samples': 3252480, 'steps': 16939, 'loss/train': 1.2893445491790771}
+08/30/2021 16:17:30 - INFO - __main__ - Step 16941: {'lr': 0.00048753349712424277, 'samples': 3252672, 'steps': 16940, 'loss/train': 0.8502808809280396}
+08/30/2021 16:17:31 - INFO - __main__ - Step 16942: {'lr': 0.00048753184220520497, 'samples': 3252864, 'steps': 16941, 'loss/train': 1.6763042211532593}
+08/30/2021 16:17:31 - INFO - __main__ - Step 16943: {'lr': 0.000487530187179139, 'samples': 3253056, 'steps': 16942, 'loss/train': 0.5161139369010925}
+08/30/2021 16:17:31 - INFO - __main__ - Step 16944: {'lr': 0.00048752853204604555, 'samples': 3253248, 'steps': 16943, 'loss/train': 1.5600448846817017}
+08/30/2021 16:17:33 - INFO - __main__ - Step 16945: {'lr': 0.00048752687680592545, 'samples': 3253440, 'steps': 16944, 'loss/train': 1.602253794670105}
+08/30/2021 16:17:33 - INFO - __main__ - Step 16946: {'lr': 0.00048752522145877937, 'samples': 3253632, 'steps': 16945, 'loss/train': 1.7223378419876099}
+08/30/2021 16:17:34 - INFO - __main__ - Step 16947: {'lr': 0.0004875235660046081, 'samples': 3253824, 'steps': 16946, 'loss/train': 0.6119934320449829}
+08/30/2021 16:17:34 - INFO - __main__ - Step 16948: {'lr': 0.0004875219104434124, 'samples': 3254016, 'steps': 16947, 'loss/train': 1.73008131980896}
+08/30/2021 16:17:34 - INFO - __main__ - Step 16949: {'lr': 0.0004875202547751929, 'samples': 3254208, 'steps': 16948, 'loss/train': 1.3419551849365234}
+08/30/2021 16:17:35 - INFO - __main__ - Step 16950: {'lr': 0.00048751859899995054, 'samples': 3254400, 'steps': 16949, 'loss/train': 1.8059403896331787}
+08/30/2021 16:17:36 - INFO - __main__ - Step 16951: {'lr': 0.0004875169431176859, 'samples': 3254592, 'steps': 16950, 'loss/train': 2.4468488693237305}
+08/30/2021 16:17:37 - INFO - __main__ - Step 16952: {'lr': 0.0004875152871283999, 'samples': 3254784, 'steps': 16951, 'loss/train': 1.3676382303237915}
+08/30/2021 16:17:37 - INFO - __main__ - Step 16953: {'lr': 0.0004875136310320931, 'samples': 3254976, 'steps': 16952, 'loss/train': 0.8390756845474243}
+08/30/2021 16:17:37 - INFO - __main__ - Step 16954: {'lr': 0.0004875119748287663, 'samples': 3255168, 'steps': 16953, 'loss/train': 1.3089519739151}
+08/30/2021 16:17:38 - INFO - __main__ - Step 16955: {'lr': 0.0004875103185184203, 'samples': 3255360, 'steps': 16954, 'loss/train': 1.563284158706665}
+08/30/2021 16:17:39 - INFO - __main__ - Step 16956: {'lr': 0.00048750866210105583, 'samples': 3255552, 'steps': 16955, 'loss/train': 1.4730861186981201}
+08/30/2021 16:17:40 - INFO - __main__ - Step 16957: {'lr': 0.0004875070055766736, 'samples': 3255744, 'steps': 16956, 'loss/train': 1.0444947481155396}
+08/30/2021 16:17:40 - INFO - __main__ - Step 16958: {'lr': 0.0004875053489452743, 'samples': 3255936, 'steps': 16957, 'loss/train': 1.472135066986084}
+08/30/2021 16:17:40 - INFO - __main__ - Step 16959: {'lr': 0.00048750369220685886, 'samples': 3256128, 'steps': 16958, 'loss/train': 1.045244812965393}
+08/30/2021 16:17:41 - INFO - __main__ - Step 16960: {'lr': 0.0004875020353614279, 'samples': 3256320, 'steps': 16959, 'loss/train': 2.2059497833251953}
+08/30/2021 16:17:42 - INFO - __main__ - Step 16961: {'lr': 0.0004875003784089822, 'samples': 3256512, 'steps': 16960, 'loss/train': 1.6468404531478882}
+08/30/2021 16:17:43 - INFO - __main__ - Step 16962: {'lr': 0.00048749872134952243, 'samples': 3256704, 'steps': 16961, 'loss/train': 1.4637099504470825}
+08/30/2021 16:17:43 - INFO - __main__ - Step 16963: {'lr': 0.0004874970641830495, 'samples': 3256896, 'steps': 16962, 'loss/train': 1.3961182832717896}
+08/30/2021 16:17:43 - INFO - __main__ - Step 16964: {'lr': 0.000487495406909564, 'samples': 3257088, 'steps': 16963, 'loss/train': 1.7496854066848755}
+08/30/2021 16:17:44 - INFO - __main__ - Step 16965: {'lr': 0.00048749374952906677, 'samples': 3257280, 'steps': 16964, 'loss/train': 1.5075517892837524}
+08/30/2021 16:17:46 - INFO - __main__ - Step 16966: {'lr': 0.0004874920920415584, 'samples': 3257472, 'steps': 16965, 'loss/train': 1.5595650672912598}
+08/30/2021 16:17:46 - INFO - __main__ - Step 16967: {'lr': 0.0004874904344470399, 'samples': 3257664, 'steps': 16966, 'loss/train': 1.7632176876068115}
+08/30/2021 16:17:46 - INFO - __main__ - Step 16968: {'lr': 0.00048748877674551183, 'samples': 3257856, 'steps': 16967, 'loss/train': 1.9016896486282349}
+08/30/2021 16:17:47 - INFO - __main__ - Step 16969: {'lr': 0.00048748711893697495, 'samples': 3258048, 'steps': 16968, 'loss/train': 1.3011797666549683}
+08/30/2021 16:17:47 - INFO - __main__ - Step 16970: {'lr': 0.0004874854610214301, 'samples': 3258240, 'steps': 16969, 'loss/train': 0.07831119745969772}
+08/30/2021 16:17:48 - INFO - __main__ - Step 16971: {'lr': 0.00048748380299887793, 'samples': 3258432, 'steps': 16970, 'loss/train': 1.6787441968917847}
+08/30/2021 16:17:48 - INFO - __main__ - Step 16972: {'lr': 0.0004874821448693192, 'samples': 3258624, 'steps': 16971, 'loss/train': 1.504599928855896}
+08/30/2021 16:17:49 - INFO - __main__ - Step 16973: {'lr': 0.00048748048663275475, 'samples': 3258816, 'steps': 16972, 'loss/train': 1.9052436351776123}
+08/30/2021 16:17:50 - INFO - __main__ - Step 16974: {'lr': 0.00048747882828918524, 'samples': 3259008, 'steps': 16973, 'loss/train': 1.4593864679336548}
+08/30/2021 16:17:50 - INFO - __main__ - Step 16975: {'lr': 0.0004874771698386113, 'samples': 3259200, 'steps': 16974, 'loss/train': 1.39486563205719}
+08/30/2021 16:17:51 - INFO - __main__ - Step 16976: {'lr': 0.00048747551128103397, 'samples': 3259392, 'steps': 16975, 'loss/train': 1.2716879844665527}
+08/30/2021 16:17:51 - INFO - __main__ - Step 16977: {'lr': 0.00048747385261645377, 'samples': 3259584, 'steps': 16976, 'loss/train': 1.0684585571289062}
+08/30/2021 16:17:52 - INFO - __main__ - Step 16978: {'lr': 0.0004874721938448715, 'samples': 3259776, 'steps': 16977, 'loss/train': 2.4069674015045166}
+08/30/2021 16:17:53 - INFO - __main__ - Step 16979: {'lr': 0.000487470534966288, 'samples': 3259968, 'steps': 16978, 'loss/train': 1.359895944595337}
+08/30/2021 16:17:53 - INFO - __main__ - Step 16980: {'lr': 0.0004874688759807039, 'samples': 3260160, 'steps': 16979, 'loss/train': 1.7185837030410767}
+08/30/2021 16:17:53 - INFO - __main__ - Step 16981: {'lr': 0.00048746721688812004, 'samples': 3260352, 'steps': 16980, 'loss/train': 1.7675763368606567}
+08/30/2021 16:17:54 - INFO - __main__ - Step 16982: {'lr': 0.00048746555768853703, 'samples': 3260544, 'steps': 16981, 'loss/train': 2.0602288246154785}
+08/30/2021 16:17:56 - INFO - __main__ - Step 16983: {'lr': 0.00048746389838195573, 'samples': 3260736, 'steps': 16982, 'loss/train': 1.249222755432129}
+08/30/2021 16:17:57 - INFO - __main__ - Step 16984: {'lr': 0.0004874622389683768, 'samples': 3260928, 'steps': 16983, 'loss/train': 1.7813916206359863}
+08/30/2021 16:17:57 - INFO - __main__ - Step 16985: {'lr': 0.0004874605794478012, 'samples': 3261120, 'steps': 16984, 'loss/train': 1.7750695943832397}
+08/30/2021 16:17:57 - INFO - __main__ - Step 16986: {'lr': 0.0004874589198202294, 'samples': 3261312, 'steps': 16985, 'loss/train': 2.1372036933898926}
+08/30/2021 16:17:58 - INFO - __main__ - Step 16987: {'lr': 0.0004874572600856624, 'samples': 3261504, 'steps': 16986, 'loss/train': 1.801600456237793}
+08/30/2021 16:17:59 - INFO - __main__ - Step 16988: {'lr': 0.0004874556002441007, 'samples': 3261696, 'steps': 16987, 'loss/train': 1.3790847063064575}
+08/30/2021 16:18:00 - INFO - __main__ - Step 16989: {'lr': 0.0004874539402955452, 'samples': 3261888, 'steps': 16988, 'loss/train': 2.015305519104004}
+08/30/2021 16:18:00 - INFO - __main__ - Step 16990: {'lr': 0.00048745228023999666, 'samples': 3262080, 'steps': 16989, 'loss/train': 1.1904144287109375}
+08/30/2021 16:18:00 - INFO - __main__ - Step 16991: {'lr': 0.0004874506200774557, 'samples': 3262272, 'steps': 16990, 'loss/train': 1.6295344829559326}
+08/30/2021 16:18:01 - INFO - __main__ - Step 16992: {'lr': 0.00048744895980792327, 'samples': 3262464, 'steps': 16991, 'loss/train': 1.7436455488204956}
+08/30/2021 16:18:02 - INFO - __main__ - Step 16993: {'lr': 0.00048744729943139993, 'samples': 3262656, 'steps': 16992, 'loss/train': 1.2896414995193481}
+08/30/2021 16:18:03 - INFO - __main__ - Step 16994: {'lr': 0.0004874456389478865, 'samples': 3262848, 'steps': 16993, 'loss/train': 1.5997600555419922}
+08/30/2021 16:18:03 - INFO - __main__ - Step 16995: {'lr': 0.00048744397835738377, 'samples': 3263040, 'steps': 16994, 'loss/train': 1.8420839309692383}
+08/30/2021 16:18:03 - INFO - __main__ - Step 16996: {'lr': 0.00048744231765989246, 'samples': 3263232, 'steps': 16995, 'loss/train': 1.8090988397598267}
+08/30/2021 16:18:04 - INFO - __main__ - Step 16997: {'lr': 0.0004874406568554132, 'samples': 3263424, 'steps': 16996, 'loss/train': 1.8278638124465942}
+08/30/2021 16:18:05 - INFO - __main__ - Step 16998: {'lr': 0.0004874389959439469, 'samples': 3263616, 'steps': 16997, 'loss/train': 1.401595950126648}
+08/30/2021 16:18:06 - INFO - __main__ - Step 16999: {'lr': 0.0004874373349254943, 'samples': 3263808, 'steps': 16998, 'loss/train': 1.4432423114776611}
+08/30/2021 16:18:06 - INFO - __main__ - Step 17000: {'lr': 0.00048743567380005604, 'samples': 3264000, 'steps': 16999, 'loss/train': 1.7033408880233765}
+08/30/2021 16:18:06 - INFO - __main__ - Step 17001: {'lr': 0.000487434012567633, 'samples': 3264192, 'steps': 17000, 'loss/train': 0.7083486318588257}
+08/30/2021 16:18:07 - INFO - __main__ - Step 17002: {'lr': 0.0004874323512282258, 'samples': 3264384, 'steps': 17001, 'loss/train': 1.2216070890426636}
+08/30/2021 16:18:08 - INFO - __main__ - Step 17003: {'lr': 0.00048743068978183523, 'samples': 3264576, 'steps': 17002, 'loss/train': 1.9648942947387695}
+08/30/2021 16:18:09 - INFO - __main__ - Step 17004: {'lr': 0.00048742902822846215, 'samples': 3264768, 'steps': 17003, 'loss/train': 1.9739830493927002}
+08/30/2021 16:18:09 - INFO - __main__ - Step 17005: {'lr': 0.0004874273665681071, 'samples': 3264960, 'steps': 17004, 'loss/train': 1.4854813814163208}
+08/30/2021 16:18:09 - INFO - __main__ - Step 17006: {'lr': 0.00048742570480077096, 'samples': 3265152, 'steps': 17005, 'loss/train': 1.954255223274231}
+08/30/2021 16:18:10 - INFO - __main__ - Step 17007: {'lr': 0.0004874240429264545, 'samples': 3265344, 'steps': 17006, 'loss/train': 1.6127092838287354}
+08/30/2021 16:18:10 - INFO - __main__ - Step 17008: {'lr': 0.00048742238094515844, 'samples': 3265536, 'steps': 17007, 'loss/train': 1.5501658916473389}
+08/30/2021 16:18:11 - INFO - __main__ - Step 17009: {'lr': 0.00048742071885688354, 'samples': 3265728, 'steps': 17008, 'loss/train': 1.9240108728408813}
+08/30/2021 16:18:12 - INFO - __main__ - Step 17010: {'lr': 0.00048741905666163047, 'samples': 3265920, 'steps': 17009, 'loss/train': 2.3126652240753174}
+08/30/2021 16:18:12 - INFO - __main__ - Step 17011: {'lr': 0.00048741739435940003, 'samples': 3266112, 'steps': 17010, 'loss/train': 1.563551664352417}
+08/30/2021 16:18:13 - INFO - __main__ - Step 17012: {'lr': 0.000487415731950193, 'samples': 3266304, 'steps': 17011, 'loss/train': 1.6391255855560303}
+08/30/2021 16:18:13 - INFO - __main__ - Step 17013: {'lr': 0.0004874140694340101, 'samples': 3266496, 'steps': 17012, 'loss/train': 1.1839629411697388}
+08/30/2021 16:18:15 - INFO - __main__ - Step 17014: {'lr': 0.0004874124068108521, 'samples': 3266688, 'steps': 17013, 'loss/train': 1.763357162475586}
+08/30/2021 16:18:15 - INFO - __main__ - Step 17015: {'lr': 0.00048741074408071975, 'samples': 3266880, 'steps': 17014, 'loss/train': 1.1405329704284668}
+08/30/2021 16:18:16 - INFO - __main__ - Step 17016: {'lr': 0.00048740908124361373, 'samples': 3267072, 'steps': 17015, 'loss/train': 1.4558064937591553}
+08/30/2021 16:18:16 - INFO - __main__ - Step 17017: {'lr': 0.0004874074182995349, 'samples': 3267264, 'steps': 17016, 'loss/train': 0.0474298894405365}
+08/30/2021 16:18:16 - INFO - __main__ - Step 17018: {'lr': 0.0004874057552484839, 'samples': 3267456, 'steps': 17017, 'loss/train': 1.5617492198944092}
+08/30/2021 16:18:17 - INFO - __main__ - Step 17019: {'lr': 0.00048740409209046154, 'samples': 3267648, 'steps': 17018, 'loss/train': 1.7178077697753906}
+08/30/2021 16:18:18 - INFO - __main__ - Step 17020: {'lr': 0.0004874024288254686, 'samples': 3267840, 'steps': 17019, 'loss/train': 1.9327551126480103}
+08/30/2021 16:18:18 - INFO - __main__ - Step 17021: {'lr': 0.00048740076545350573, 'samples': 3268032, 'steps': 17020, 'loss/train': 1.848136067390442}
+08/30/2021 16:18:19 - INFO - __main__ - Step 17022: {'lr': 0.00048739910197457376, 'samples': 3268224, 'steps': 17021, 'loss/train': 1.6528129577636719}
+08/30/2021 16:18:19 - INFO - __main__ - Step 17023: {'lr': 0.00048739743838867344, 'samples': 3268416, 'steps': 17022, 'loss/train': 2.532574415206909}
+08/30/2021 16:18:19 - INFO - __main__ - Step 17024: {'lr': 0.00048739577469580545, 'samples': 3268608, 'steps': 17023, 'loss/train': 1.4743624925613403}
+08/30/2021 16:18:22 - INFO - __main__ - Step 17025: {'lr': 0.0004873941108959706, 'samples': 3268800, 'steps': 17024, 'loss/train': 1.819540023803711}
+08/30/2021 16:18:22 - INFO - __main__ - Step 17026: {'lr': 0.0004873924469891697, 'samples': 3268992, 'steps': 17025, 'loss/train': 1.5908654928207397}
+08/30/2021 16:18:23 - INFO - __main__ - Step 17027: {'lr': 0.00048739078297540335, 'samples': 3269184, 'steps': 17026, 'loss/train': 1.6285433769226074}
+08/30/2021 16:18:23 - INFO - __main__ - Step 17028: {'lr': 0.00048738911885467243, 'samples': 3269376, 'steps': 17027, 'loss/train': 1.983981966972351}
+08/30/2021 16:18:23 - INFO - __main__ - Step 17029: {'lr': 0.00048738745462697754, 'samples': 3269568, 'steps': 17028, 'loss/train': 1.3978523015975952}
+08/30/2021 16:18:24 - INFO - __main__ - Step 17030: {'lr': 0.0004873857902923196, 'samples': 3269760, 'steps': 17029, 'loss/train': 1.835018515586853}
+08/30/2021 16:18:24 - INFO - __main__ - Step 17031: {'lr': 0.00048738412585069927, 'samples': 3269952, 'steps': 17030, 'loss/train': 1.1982173919677734}
+08/30/2021 16:18:26 - INFO - __main__ - Step 17032: {'lr': 0.00048738246130211734, 'samples': 3270144, 'steps': 17031, 'loss/train': 0.9439342617988586}
+08/30/2021 16:18:26 - INFO - __main__ - Step 17033: {'lr': 0.00048738079664657454, 'samples': 3270336, 'steps': 17032, 'loss/train': 1.631165623664856}
+08/30/2021 16:18:26 - INFO - __main__ - Step 17034: {'lr': 0.00048737913188407156, 'samples': 3270528, 'steps': 17033, 'loss/train': 1.7660175561904907}
+08/30/2021 16:18:27 - INFO - __main__ - Step 17035: {'lr': 0.00048737746701460927, 'samples': 3270720, 'steps': 17034, 'loss/train': 2.2325189113616943}
+08/30/2021 16:18:27 - INFO - __main__ - Step 17036: {'lr': 0.0004873758020381883, 'samples': 3270912, 'steps': 17035, 'loss/train': 2.220383882522583}
+08/30/2021 16:18:29 - INFO - __main__ - Step 17037: {'lr': 0.00048737413695480947, 'samples': 3271104, 'steps': 17036, 'loss/train': 1.8013945817947388}
+08/30/2021 16:18:30 - INFO - __main__ - Step 17038: {'lr': 0.00048737247176447354, 'samples': 3271296, 'steps': 17037, 'loss/train': 2.1499481201171875}
+08/30/2021 16:18:30 - INFO - __main__ - Step 17039: {'lr': 0.0004873708064671812, 'samples': 3271488, 'steps': 17038, 'loss/train': 1.095421314239502}
+08/30/2021 16:18:30 - INFO - __main__ - Step 17040: {'lr': 0.0004873691410629333, 'samples': 3271680, 'steps': 17039, 'loss/train': 1.4788717031478882}
+08/30/2021 16:18:31 - INFO - __main__ - Step 17041: {'lr': 0.0004873674755517304, 'samples': 3271872, 'steps': 17040, 'loss/train': 1.1645203828811646}
+08/30/2021 16:18:32 - INFO - __main__ - Step 17042: {'lr': 0.00048736580993357357, 'samples': 3272064, 'steps': 17041, 'loss/train': 0.893046498298645}
+08/30/2021 16:18:33 - INFO - __main__ - Step 17043: {'lr': 0.0004873641442084632, 'samples': 3272256, 'steps': 17042, 'loss/train': 1.681810736656189}
+08/30/2021 16:18:33 - INFO - __main__ - Step 17044: {'lr': 0.00048736247837640037, 'samples': 3272448, 'steps': 17043, 'loss/train': 1.2126652002334595}
+08/30/2021 16:18:33 - INFO - __main__ - Step 17045: {'lr': 0.0004873608124373855, 'samples': 3272640, 'steps': 17044, 'loss/train': 1.578004240989685}
+08/30/2021 16:18:34 - INFO - __main__ - Step 17046: {'lr': 0.00048735914639141964, 'samples': 3272832, 'steps': 17045, 'loss/train': 1.7768607139587402}
+08/30/2021 16:18:35 - INFO - __main__ - Step 17047: {'lr': 0.00048735748023850337, 'samples': 3273024, 'steps': 17046, 'loss/train': 1.973023772239685}
+08/30/2021 16:18:36 - INFO - __main__ - Step 17048: {'lr': 0.00048735581397863745, 'samples': 3273216, 'steps': 17047, 'loss/train': 1.459733247756958}
+08/30/2021 16:18:36 - INFO - __main__ - Step 17049: {'lr': 0.0004873541476118227, 'samples': 3273408, 'steps': 17048, 'loss/train': 1.3695586919784546}
+08/30/2021 16:18:37 - INFO - __main__ - Step 17050: {'lr': 0.00048735248113805976, 'samples': 3273600, 'steps': 17049, 'loss/train': 1.7251688241958618}
+08/30/2021 16:18:37 - INFO - __main__ - Step 17051: {'lr': 0.0004873508145573495, 'samples': 3273792, 'steps': 17050, 'loss/train': 1.272658109664917}
+08/30/2021 16:18:37 - INFO - __main__ - Step 17052: {'lr': 0.00048734914786969266, 'samples': 3273984, 'steps': 17051, 'loss/train': 1.9978035688400269}
+08/30/2021 16:18:39 - INFO - __main__ - Step 17053: {'lr': 0.00048734748107509, 'samples': 3274176, 'steps': 17052, 'loss/train': 1.6371781826019287}
+08/30/2021 16:18:39 - INFO - __main__ - Step 17054: {'lr': 0.0004873458141735421, 'samples': 3274368, 'steps': 17053, 'loss/train': 1.8606921434402466}
+08/30/2021 16:18:39 - INFO - __main__ - Step 17055: {'lr': 0.0004873441471650499, 'samples': 3274560, 'steps': 17054, 'loss/train': 1.903680682182312}
+08/30/2021 16:18:40 - INFO - __main__ - Step 17056: {'lr': 0.00048734248004961414, 'samples': 3274752, 'steps': 17055, 'loss/train': 1.8469626903533936}
+08/30/2021 16:18:40 - INFO - __main__ - Step 17057: {'lr': 0.00048734081282723543, 'samples': 3274944, 'steps': 17056, 'loss/train': 1.2959022521972656}
+08/30/2021 16:18:42 - INFO - __main__ - Step 17058: {'lr': 0.00048733914549791465, 'samples': 3275136, 'steps': 17057, 'loss/train': 0.8788344860076904}
+08/30/2021 16:18:42 - INFO - __main__ - Step 17059: {'lr': 0.0004873374780616525, 'samples': 3275328, 'steps': 17058, 'loss/train': 1.9548438787460327}
+08/30/2021 16:18:42 - INFO - __main__ - Step 17060: {'lr': 0.00048733581051844976, 'samples': 3275520, 'steps': 17059, 'loss/train': 1.576919674873352}
+08/30/2021 16:18:43 - INFO - __main__ - Step 17061: {'lr': 0.00048733414286830716, 'samples': 3275712, 'steps': 17060, 'loss/train': 1.4760609865188599}
+08/30/2021 16:18:43 - INFO - __main__ - Step 17062: {'lr': 0.00048733247511122547, 'samples': 3275904, 'steps': 17061, 'loss/train': 1.4664009809494019}
+08/30/2021 16:18:45 - INFO - __main__ - Step 17063: {'lr': 0.00048733080724720545, 'samples': 3276096, 'steps': 17062, 'loss/train': 1.7509276866912842}
+08/30/2021 16:18:46 - INFO - __main__ - Step 17064: {'lr': 0.00048732913927624776, 'samples': 3276288, 'steps': 17063, 'loss/train': 1.422742247581482}
+08/30/2021 16:18:46 - INFO - __main__ - Step 17065: {'lr': 0.0004873274711983533, 'samples': 3276480, 'steps': 17064, 'loss/train': 1.491871953010559}
+08/30/2021 16:18:47 - INFO - __main__ - Step 17066: {'lr': 0.0004873258030135227, 'samples': 3276672, 'steps': 17065, 'loss/train': 1.6416592597961426}
+08/30/2021 16:18:47 - INFO - __main__ - Step 17067: {'lr': 0.0004873241347217567, 'samples': 3276864, 'steps': 17066, 'loss/train': 2.1945347785949707}
+08/30/2021 16:18:47 - INFO - __main__ - Step 17068: {'lr': 0.0004873224663230562, 'samples': 3277056, 'steps': 17067, 'loss/train': 3.0288026332855225}
+08/30/2021 16:18:49 - INFO - __main__ - Step 17069: {'lr': 0.0004873207978174219, 'samples': 3277248, 'steps': 17068, 'loss/train': 3.829235792160034}
+08/30/2021 16:18:49 - INFO - __main__ - Step 17070: {'lr': 0.00048731912920485444, 'samples': 3277440, 'steps': 17069, 'loss/train': 2.0071985721588135}
+08/30/2021 16:18:50 - INFO - __main__ - Step 17071: {'lr': 0.0004873174604853546, 'samples': 3277632, 'steps': 17070, 'loss/train': 1.8288429975509644}
+08/30/2021 16:18:50 - INFO - __main__ - Step 17072: {'lr': 0.00048731579165892325, 'samples': 3277824, 'steps': 17071, 'loss/train': 1.354732871055603}
+08/30/2021 16:18:50 - INFO - __main__ - Step 17073: {'lr': 0.000487314122725561, 'samples': 3278016, 'steps': 17072, 'loss/train': 1.5520434379577637}
+08/30/2021 16:18:52 - INFO - __main__ - Step 17074: {'lr': 0.00048731245368526877, 'samples': 3278208, 'steps': 17073, 'loss/train': 1.3054972887039185}
+08/30/2021 16:18:53 - INFO - __main__ - Step 17075: {'lr': 0.0004873107845380471, 'samples': 3278400, 'steps': 17074, 'loss/train': 2.0592572689056396}
+08/30/2021 16:18:53 - INFO - __main__ - Step 17076: {'lr': 0.00048730911528389686, 'samples': 3278592, 'steps': 17075, 'loss/train': 2.3109729290008545}
+08/30/2021 16:18:53 - INFO - __main__ - Step 17077: {'lr': 0.0004873074459228188, 'samples': 3278784, 'steps': 17076, 'loss/train': 1.7390919923782349}
+08/30/2021 16:18:54 - INFO - __main__ - Step 17078: {'lr': 0.0004873057764548138, 'samples': 3278976, 'steps': 17077, 'loss/train': 1.2778682708740234}
+08/30/2021 16:18:54 - INFO - __main__ - Step 17079: {'lr': 0.00048730410687988237, 'samples': 3279168, 'steps': 17078, 'loss/train': 1.43776535987854}
+08/30/2021 16:18:55 - INFO - __main__ - Step 17080: {'lr': 0.00048730243719802535, 'samples': 3279360, 'steps': 17079, 'loss/train': 1.517069935798645}
+08/30/2021 16:18:56 - INFO - __main__ - Step 17081: {'lr': 0.00048730076740924355, 'samples': 3279552, 'steps': 17080, 'loss/train': 1.8498196601867676}
+08/30/2021 16:18:56 - INFO - __main__ - Step 17082: {'lr': 0.0004872990975135377, 'samples': 3279744, 'steps': 17081, 'loss/train': 1.755913496017456}
+08/30/2021 16:18:57 - INFO - __main__ - Step 17083: {'lr': 0.0004872974275109085, 'samples': 3279936, 'steps': 17082, 'loss/train': 1.8197604417800903}
+08/30/2021 16:18:57 - INFO - __main__ - Step 17084: {'lr': 0.00048729575740135675, 'samples': 3280128, 'steps': 17083, 'loss/train': 2.2922885417938232}
+08/30/2021 16:18:59 - INFO - __main__ - Step 17085: {'lr': 0.0004872940871848832, 'samples': 3280320, 'steps': 17084, 'loss/train': 1.6462880373001099}
+08/30/2021 16:18:59 - INFO - __main__ - Step 17086: {'lr': 0.00048729241686148864, 'samples': 3280512, 'steps': 17085, 'loss/train': 1.4661798477172852}
+08/30/2021 16:18:59 - INFO - __main__ - Step 17087: {'lr': 0.0004872907464311737, 'samples': 3280704, 'steps': 17086, 'loss/train': 1.6990941762924194}
+08/30/2021 16:19:00 - INFO - __main__ - Step 17088: {'lr': 0.0004872890758939392, 'samples': 3280896, 'steps': 17087, 'loss/train': 1.6704976558685303}
+08/30/2021 16:19:00 - INFO - __main__ - Step 17089: {'lr': 0.00048728740524978597, 'samples': 3281088, 'steps': 17088, 'loss/train': 2.290745973587036}
+08/30/2021 16:19:03 - INFO - __main__ - Step 17090: {'lr': 0.00048728573449871473, 'samples': 3281280, 'steps': 17089, 'loss/train': 1.4036996364593506}
+08/30/2021 16:19:03 - INFO - __main__ - Step 17091: {'lr': 0.0004872840636407261, 'samples': 3281472, 'steps': 17090, 'loss/train': 1.581344723701477}
+08/30/2021 16:19:03 - INFO - __main__ - Step 17092: {'lr': 0.00048728239267582096, 'samples': 3281664, 'steps': 17091, 'loss/train': 1.573412537574768}
+08/30/2021 16:19:04 - INFO - __main__ - Step 17093: {'lr': 0.00048728072160400006, 'samples': 3281856, 'steps': 17092, 'loss/train': 0.24032923579216003}
+08/30/2021 16:19:04 - INFO - __main__ - Step 17094: {'lr': 0.0004872790504252641, 'samples': 3282048, 'steps': 17093, 'loss/train': 0.16618132591247559}
+08/30/2021 16:19:04 - INFO - __main__ - Step 17095: {'lr': 0.0004872773791396139, 'samples': 3282240, 'steps': 17094, 'loss/train': 1.9471571445465088}
+08/30/2021 16:19:05 - INFO - __main__ - Step 17096: {'lr': 0.0004872757077470502, 'samples': 3282432, 'steps': 17095, 'loss/train': 0.5481041669845581}
+08/30/2021 16:19:05 - INFO - __main__ - Step 17097: {'lr': 0.0004872740362475737, 'samples': 3282624, 'steps': 17096, 'loss/train': 0.5585260987281799}
+08/30/2021 16:19:07 - INFO - __main__ - Step 17098: {'lr': 0.0004872723646411851, 'samples': 3282816, 'steps': 17097, 'loss/train': 1.5546623468399048}
+08/30/2021 16:19:08 - INFO - __main__ - Step 17099: {'lr': 0.0004872706929278853, 'samples': 3283008, 'steps': 17098, 'loss/train': 1.0834232568740845}
+08/30/2021 16:19:08 - INFO - __main__ - Step 17100: {'lr': 0.000487269021107675, 'samples': 3283200, 'steps': 17099, 'loss/train': 1.696337103843689}
+08/30/2021 16:19:08 - INFO - __main__ - Step 17101: {'lr': 0.0004872673491805549, 'samples': 3283392, 'steps': 17100, 'loss/train': 1.5764994621276855}
+08/30/2021 16:19:09 - INFO - __main__ - Step 17102: {'lr': 0.0004872656771465259, 'samples': 3283584, 'steps': 17101, 'loss/train': 1.586539387702942}
+08/30/2021 16:19:10 - INFO - __main__ - Step 17103: {'lr': 0.00048726400500558856, 'samples': 3283776, 'steps': 17102, 'loss/train': 1.5957640409469604}
+08/30/2021 16:19:11 - INFO - __main__ - Step 17104: {'lr': 0.0004872623327577437, 'samples': 3283968, 'steps': 17103, 'loss/train': 2.2525582313537598}
+08/30/2021 16:19:11 - INFO - __main__ - Step 17105: {'lr': 0.0004872606604029921, 'samples': 3284160, 'steps': 17104, 'loss/train': 1.8458601236343384}
+08/30/2021 16:19:11 - INFO - __main__ - Step 17106: {'lr': 0.00048725898794133455, 'samples': 3284352, 'steps': 17105, 'loss/train': 1.9900256395339966}
+08/30/2021 16:19:12 - INFO - __main__ - Step 17107: {'lr': 0.00048725731537277173, 'samples': 3284544, 'steps': 17106, 'loss/train': 1.4694170951843262}
+08/30/2021 16:19:13 - INFO - __main__ - Step 17108: {'lr': 0.0004872556426973044, 'samples': 3284736, 'steps': 17107, 'loss/train': 1.8389586210250854}
+08/30/2021 16:19:14 - INFO - __main__ - Step 17109: {'lr': 0.0004872539699149334, 'samples': 3284928, 'steps': 17108, 'loss/train': 1.6983451843261719}
+08/30/2021 16:19:14 - INFO - __main__ - Step 17110: {'lr': 0.0004872522970256594, 'samples': 3285120, 'steps': 17109, 'loss/train': 1.7530301809310913}
+08/30/2021 16:19:15 - INFO - __main__ - Step 17111: {'lr': 0.00048725062402948314, 'samples': 3285312, 'steps': 17110, 'loss/train': 0.3163411319255829}
+08/30/2021 16:19:15 - INFO - __main__ - Step 17112: {'lr': 0.00048724895092640546, 'samples': 3285504, 'steps': 17111, 'loss/train': 1.2892173528671265}
+08/30/2021 16:19:17 - INFO - __main__ - Step 17113: {'lr': 0.00048724727771642706, 'samples': 3285696, 'steps': 17112, 'loss/train': 1.6487714052200317}
+08/30/2021 16:19:17 - INFO - __main__ - Step 17114: {'lr': 0.00048724560439954867, 'samples': 3285888, 'steps': 17113, 'loss/train': 1.8985477685928345}
+08/30/2021 16:19:18 - INFO - __main__ - Step 17115: {'lr': 0.00048724393097577113, 'samples': 3286080, 'steps': 17114, 'loss/train': 0.21476341784000397}
+08/30/2021 16:19:18 - INFO - __main__ - Step 17116: {'lr': 0.0004872422574450951, 'samples': 3286272, 'steps': 17115, 'loss/train': 1.6858916282653809}
+08/30/2021 16:19:18 - INFO - __main__ - Step 17117: {'lr': 0.0004872405838075213, 'samples': 3286464, 'steps': 17116, 'loss/train': 1.4407038688659668}
+08/30/2021 16:19:20 - INFO - __main__ - Step 17118: {'lr': 0.00048723891006305066, 'samples': 3286656, 'steps': 17117, 'loss/train': 1.684228539466858}
+08/30/2021 16:19:20 - INFO - __main__ - Step 17119: {'lr': 0.0004872372362116838, 'samples': 3286848, 'steps': 17118, 'loss/train': 1.4467246532440186}
+08/30/2021 16:19:21 - INFO - __main__ - Step 17120: {'lr': 0.0004872355622534215, 'samples': 3287040, 'steps': 17119, 'loss/train': 1.9959315061569214}
+08/30/2021 16:19:21 - INFO - __main__ - Step 17121: {'lr': 0.0004872338881882644, 'samples': 3287232, 'steps': 17120, 'loss/train': 1.707873821258545}
+08/30/2021 16:19:21 - INFO - __main__ - Step 17122: {'lr': 0.00048723221401621354, 'samples': 3287424, 'steps': 17121, 'loss/train': 2.1110117435455322}
+08/30/2021 16:19:23 - INFO - __main__ - Step 17123: {'lr': 0.0004872305397372694, 'samples': 3287616, 'steps': 17122, 'loss/train': 0.8126787543296814}
+08/30/2021 16:19:23 - INFO - __main__ - Step 17124: {'lr': 0.0004872288653514329, 'samples': 3287808, 'steps': 17123, 'loss/train': 1.9742519855499268}
+08/30/2021 16:19:24 - INFO - __main__ - Step 17125: {'lr': 0.0004872271908587047, 'samples': 3288000, 'steps': 17124, 'loss/train': 1.7569471597671509}
+08/30/2021 16:19:24 - INFO - __main__ - Step 17126: {'lr': 0.0004872255162590856, 'samples': 3288192, 'steps': 17125, 'loss/train': 1.9443386793136597}
+08/30/2021 16:19:25 - INFO - __main__ - Step 17127: {'lr': 0.0004872238415525764, 'samples': 3288384, 'steps': 17126, 'loss/train': 0.16956979036331177}
+08/30/2021 16:19:25 - INFO - __main__ - Step 17128: {'lr': 0.0004872221667391777, 'samples': 3288576, 'steps': 17127, 'loss/train': 2.152531623840332}
+08/30/2021 16:19:27 - INFO - __main__ - Step 17129: {'lr': 0.00048722049181889037, 'samples': 3288768, 'steps': 17128, 'loss/train': 1.5011897087097168}
+08/30/2021 16:19:27 - INFO - __main__ - Step 17130: {'lr': 0.0004872188167917152, 'samples': 3288960, 'steps': 17129, 'loss/train': 1.6086961030960083}
+08/30/2021 16:19:27 - INFO - __main__ - Step 17131: {'lr': 0.00048721714165765286, 'samples': 3289152, 'steps': 17130, 'loss/train': 1.6895132064819336}
+08/30/2021 16:19:28 - INFO - __main__ - Step 17132: {'lr': 0.00048721546641670413, 'samples': 3289344, 'steps': 17131, 'loss/train': 1.262113332748413}
+08/30/2021 16:19:28 - INFO - __main__ - Step 17133: {'lr': 0.00048721379106886976, 'samples': 3289536, 'steps': 17132, 'loss/train': 1.8208268880844116}
+08/30/2021 16:19:29 - INFO - __main__ - Step 17134: {'lr': 0.0004872121156141506, 'samples': 3289728, 'steps': 17133, 'loss/train': 1.3156644105911255}
+08/30/2021 16:19:30 - INFO - __main__ - Step 17135: {'lr': 0.0004872104400525472, 'samples': 3289920, 'steps': 17134, 'loss/train': 1.5294270515441895}
+08/30/2021 16:19:30 - INFO - __main__ - Step 17136: {'lr': 0.0004872087643840605, 'samples': 3290112, 'steps': 17135, 'loss/train': 1.184144139289856}
+08/30/2021 16:19:31 - INFO - __main__ - Step 17137: {'lr': 0.00048720708860869116, 'samples': 3290304, 'steps': 17136, 'loss/train': 1.7141838073730469}
+08/30/2021 16:19:31 - INFO - __main__ - Step 17138: {'lr': 0.00048720541272644004, 'samples': 3290496, 'steps': 17137, 'loss/train': 0.6089520454406738}
+08/30/2021 16:19:32 - INFO - __main__ - Step 17139: {'lr': 0.00048720373673730773, 'samples': 3290688, 'steps': 17138, 'loss/train': 1.5148826837539673}
+08/30/2021 16:19:33 - INFO - __main__ - Step 17140: {'lr': 0.00048720206064129516, 'samples': 3290880, 'steps': 17139, 'loss/train': 1.9033597707748413}
+08/30/2021 16:19:33 - INFO - __main__ - Step 17141: {'lr': 0.0004872003844384029, 'samples': 3291072, 'steps': 17140, 'loss/train': 1.4932576417922974}
+08/30/2021 16:19:33 - INFO - __main__ - Step 17142: {'lr': 0.0004871987081286319, 'samples': 3291264, 'steps': 17141, 'loss/train': 0.6825220584869385}
+08/30/2021 16:19:34 - INFO - __main__ - Step 17143: {'lr': 0.0004871970317119828, 'samples': 3291456, 'steps': 17142, 'loss/train': 1.1307752132415771}
+08/30/2021 16:19:35 - INFO - __main__ - Step 17144: {'lr': 0.00048719535518845634, 'samples': 3291648, 'steps': 17143, 'loss/train': 1.6785632371902466}
+08/30/2021 16:19:36 - INFO - __main__ - Step 17145: {'lr': 0.0004871936785580533, 'samples': 3291840, 'steps': 17144, 'loss/train': 1.5717003345489502}
+08/30/2021 16:19:36 - INFO - __main__ - Step 17146: {'lr': 0.0004871920018207745, 'samples': 3292032, 'steps': 17145, 'loss/train': 1.947385549545288}
+08/30/2021 16:19:37 - INFO - __main__ - Step 17147: {'lr': 0.0004871903249766206, 'samples': 3292224, 'steps': 17146, 'loss/train': 0.9774880409240723}
+08/30/2021 16:19:37 - INFO - __main__ - Step 17148: {'lr': 0.0004871886480255925, 'samples': 3292416, 'steps': 17147, 'loss/train': 1.7427949905395508}
+08/30/2021 16:19:39 - INFO - __main__ - Step 17149: {'lr': 0.0004871869709676907, 'samples': 3292608, 'steps': 17148, 'loss/train': 1.4562371969223022}
+08/30/2021 16:19:39 - INFO - __main__ - Step 17150: {'lr': 0.0004871852938029162, 'samples': 3292800, 'steps': 17149, 'loss/train': 1.6578058004379272}
+08/30/2021 16:19:40 - INFO - __main__ - Step 17151: {'lr': 0.00048718361653126975, 'samples': 3292992, 'steps': 17150, 'loss/train': 1.7739109992980957}
+08/30/2021 16:19:40 - INFO - __main__ - Step 17152: {'lr': 0.0004871819391527519, 'samples': 3293184, 'steps': 17151, 'loss/train': 1.5501478910446167}
+08/30/2021 16:19:40 - INFO - __main__ - Step 17153: {'lr': 0.0004871802616673636, 'samples': 3293376, 'steps': 17152, 'loss/train': 1.8780291080474854}
+08/30/2021 16:19:41 - INFO - __main__ - Step 17154: {'lr': 0.00048717858407510545, 'samples': 3293568, 'steps': 17153, 'loss/train': 1.376879096031189}
+08/30/2021 16:19:42 - INFO - __main__ - Step 17155: {'lr': 0.0004871769063759783, 'samples': 3293760, 'steps': 17154, 'loss/train': 1.3158879280090332}
+08/30/2021 16:19:43 - INFO - __main__ - Step 17156: {'lr': 0.000487175228569983, 'samples': 3293952, 'steps': 17155, 'loss/train': 1.6738362312316895}
+08/30/2021 16:19:43 - INFO - __main__ - Step 17157: {'lr': 0.0004871735506571201, 'samples': 3294144, 'steps': 17156, 'loss/train': 1.697090744972229}
+08/30/2021 16:19:43 - INFO - __main__ - Step 17158: {'lr': 0.00048717187263739046, 'samples': 3294336, 'steps': 17157, 'loss/train': 1.677499532699585}
+08/30/2021 16:19:44 - INFO - __main__ - Step 17159: {'lr': 0.00048717019451079493, 'samples': 3294528, 'steps': 17158, 'loss/train': 1.9471052885055542}
+08/30/2021 16:19:45 - INFO - __main__ - Step 17160: {'lr': 0.00048716851627733404, 'samples': 3294720, 'steps': 17159, 'loss/train': 2.3192944526672363}
+08/30/2021 16:19:46 - INFO - __main__ - Step 17161: {'lr': 0.00048716683793700876, 'samples': 3294912, 'steps': 17160, 'loss/train': 1.8594112396240234}
+08/30/2021 16:19:46 - INFO - __main__ - Step 17162: {'lr': 0.00048716515948981975, 'samples': 3295104, 'steps': 17161, 'loss/train': 1.7230446338653564}
+08/30/2021 16:19:46 - INFO - __main__ - Step 17163: {'lr': 0.0004871634809357678, 'samples': 3295296, 'steps': 17162, 'loss/train': 1.4229161739349365}
+08/30/2021 16:19:47 - INFO - __main__ - Step 17164: {'lr': 0.00048716180227485365, 'samples': 3295488, 'steps': 17163, 'loss/train': 1.7989989519119263}
+08/30/2021 16:19:48 - INFO - __main__ - Step 17165: {'lr': 0.000487160123507078, 'samples': 3295680, 'steps': 17164, 'loss/train': 1.8469843864440918}
+08/30/2021 16:19:49 - INFO - __main__ - Step 17166: {'lr': 0.00048715844463244166, 'samples': 3295872, 'steps': 17165, 'loss/train': 1.6918755769729614}
+08/30/2021 16:19:49 - INFO - __main__ - Step 17167: {'lr': 0.0004871567656509454, 'samples': 3296064, 'steps': 17166, 'loss/train': 1.916261076927185}
+08/30/2021 16:19:49 - INFO - __main__ - Step 17168: {'lr': 0.00048715508656259, 'samples': 3296256, 'steps': 17167, 'loss/train': 1.7329760789871216}
+08/30/2021 16:19:50 - INFO - __main__ - Step 17169: {'lr': 0.00048715340736737615, 'samples': 3296448, 'steps': 17168, 'loss/train': 1.7122958898544312}
+08/30/2021 16:19:51 - INFO - __main__ - Step 17170: {'lr': 0.0004871517280653046, 'samples': 3296640, 'steps': 17169, 'loss/train': 2.1107749938964844}
+08/30/2021 16:19:52 - INFO - __main__ - Step 17171: {'lr': 0.0004871500486563761, 'samples': 3296832, 'steps': 17170, 'loss/train': 1.417673945426941}
+08/30/2021 16:19:52 - INFO - __main__ - Step 17172: {'lr': 0.0004871483691405916, 'samples': 3297024, 'steps': 17171, 'loss/train': 1.558638095855713}
+08/30/2021 16:19:52 - INFO - __main__ - Step 17173: {'lr': 0.0004871466895179516, 'samples': 3297216, 'steps': 17172, 'loss/train': 1.9435893297195435}
+08/30/2021 16:19:53 - INFO - __main__ - Step 17174: {'lr': 0.000487145009788457, 'samples': 3297408, 'steps': 17173, 'loss/train': 1.5993436574935913}
+08/30/2021 16:19:55 - INFO - __main__ - Step 17175: {'lr': 0.0004871433299521085, 'samples': 3297600, 'steps': 17174, 'loss/train': 1.9466005563735962}
+08/30/2021 16:19:55 - INFO - __main__ - Step 17176: {'lr': 0.00048714165000890685, 'samples': 3297792, 'steps': 17175, 'loss/train': 1.5319772958755493}
+08/30/2021 16:19:55 - INFO - __main__ - Step 17177: {'lr': 0.00048713996995885286, 'samples': 3297984, 'steps': 17176, 'loss/train': 0.8693053722381592}
+08/30/2021 16:19:56 - INFO - __main__ - Step 17178: {'lr': 0.0004871382898019472, 'samples': 3298176, 'steps': 17177, 'loss/train': 2.826000928878784}
+08/30/2021 16:19:56 - INFO - __main__ - Step 17179: {'lr': 0.0004871366095381908, 'samples': 3298368, 'steps': 17178, 'loss/train': 1.463893175125122}
+08/30/2021 16:19:56 - INFO - __main__ - Step 17180: {'lr': 0.00048713492916758425, 'samples': 3298560, 'steps': 17179, 'loss/train': 1.4658360481262207}
+08/30/2021 16:19:58 - INFO - __main__ - Step 17181: {'lr': 0.00048713324869012833, 'samples': 3298752, 'steps': 17180, 'loss/train': 0.9056485891342163}
+08/30/2021 16:19:59 - INFO - __main__ - Step 17182: {'lr': 0.0004871315681058238, 'samples': 3298944, 'steps': 17181, 'loss/train': 1.3314779996871948}
+08/30/2021 16:19:59 - INFO - __main__ - Step 17183: {'lr': 0.0004871298874146716, 'samples': 3299136, 'steps': 17182, 'loss/train': 0.2603258192539215}
+08/30/2021 16:19:59 - INFO - __main__ - Step 17184: {'lr': 0.00048712820661667215, 'samples': 3299328, 'steps': 17183, 'loss/train': 1.1811299324035645}
+08/30/2021 16:20:00 - INFO - __main__ - Step 17185: {'lr': 0.0004871265257118265, 'samples': 3299520, 'steps': 17184, 'loss/train': 0.7493991255760193}
+08/30/2021 16:20:01 - INFO - __main__ - Step 17186: {'lr': 0.0004871248447001352, 'samples': 3299712, 'steps': 17185, 'loss/train': 1.7395381927490234}
+08/30/2021 16:20:02 - INFO - __main__ - Step 17187: {'lr': 0.0004871231635815992, 'samples': 3299904, 'steps': 17186, 'loss/train': 1.6505751609802246}
+08/30/2021 16:20:02 - INFO - __main__ - Step 17188: {'lr': 0.0004871214823562191, 'samples': 3300096, 'steps': 17187, 'loss/train': 1.7045437097549438}
+08/30/2021 16:20:02 - INFO - __main__ - Step 17189: {'lr': 0.0004871198010239958, 'samples': 3300288, 'steps': 17188, 'loss/train': 1.5755842924118042}
+08/30/2021 16:20:03 - INFO - __main__ - Step 17190: {'lr': 0.0004871181195849299, 'samples': 3300480, 'steps': 17189, 'loss/train': 1.3983370065689087}
+08/30/2021 16:20:04 - INFO - __main__ - Step 17191: {'lr': 0.00048711643803902227, 'samples': 3300672, 'steps': 17190, 'loss/train': 1.941197156906128}
+08/30/2021 16:20:05 - INFO - __main__ - Step 17192: {'lr': 0.00048711475638627363, 'samples': 3300864, 'steps': 17191, 'loss/train': 1.90217125415802}
+08/30/2021 16:20:05 - INFO - __main__ - Step 17193: {'lr': 0.0004871130746266847, 'samples': 3301056, 'steps': 17192, 'loss/train': 1.3400033712387085}
+08/30/2021 16:20:05 - INFO - __main__ - Step 17194: {'lr': 0.00048711139276025626, 'samples': 3301248, 'steps': 17193, 'loss/train': 1.4913097620010376}
+08/30/2021 16:20:06 - INFO - __main__ - Step 17195: {'lr': 0.00048710971078698916, 'samples': 3301440, 'steps': 17194, 'loss/train': 2.4068617820739746}
+08/30/2021 16:20:07 - INFO - __main__ - Step 17196: {'lr': 0.0004871080287068841, 'samples': 3301632, 'steps': 17195, 'loss/train': 1.3379743099212646}
+08/30/2021 16:20:08 - INFO - __main__ - Step 17197: {'lr': 0.00048710634651994176, 'samples': 3301824, 'steps': 17196, 'loss/train': 2.3184237480163574}
+08/30/2021 16:20:08 - INFO - __main__ - Step 17198: {'lr': 0.0004871046642261629, 'samples': 3302016, 'steps': 17197, 'loss/train': 1.6905794143676758}
+08/30/2021 16:20:09 - INFO - __main__ - Step 17199: {'lr': 0.0004871029818255485, 'samples': 3302208, 'steps': 17198, 'loss/train': 1.668904423713684}
+08/30/2021 16:20:09 - INFO - __main__ - Step 17200: {'lr': 0.0004871012993180991, 'samples': 3302400, 'steps': 17199, 'loss/train': 1.8536714315414429}
+08/30/2021 16:20:09 - INFO - __main__ - Step 17201: {'lr': 0.0004870996167038154, 'samples': 3302592, 'steps': 17200, 'loss/train': 0.12117816507816315}
+08/30/2021 16:20:11 - INFO - __main__ - Step 17202: {'lr': 0.0004870979339826984, 'samples': 3302784, 'steps': 17201, 'loss/train': 1.790168285369873}
+08/30/2021 16:20:11 - INFO - __main__ - Step 17203: {'lr': 0.00048709625115474865, 'samples': 3302976, 'steps': 17202, 'loss/train': 1.631544828414917}
+08/30/2021 16:20:11 - INFO - __main__ - Step 17204: {'lr': 0.00048709456821996705, 'samples': 3303168, 'steps': 17203, 'loss/train': 1.6139225959777832}
+08/30/2021 16:20:12 - INFO - __main__ - Step 17205: {'lr': 0.0004870928851783543, 'samples': 3303360, 'steps': 17204, 'loss/train': 1.7055037021636963}
+08/30/2021 16:20:12 - INFO - __main__ - Step 17206: {'lr': 0.00048709120202991107, 'samples': 3303552, 'steps': 17205, 'loss/train': 1.8445712327957153}
+08/30/2021 16:20:14 - INFO - __main__ - Step 17207: {'lr': 0.0004870895187746383, 'samples': 3303744, 'steps': 17206, 'loss/train': 1.7481948137283325}
+08/30/2021 16:20:15 - INFO - __main__ - Step 17208: {'lr': 0.00048708783541253655, 'samples': 3303936, 'steps': 17207, 'loss/train': 1.8356598615646362}
+08/30/2021 16:20:15 - INFO - __main__ - Step 17209: {'lr': 0.00048708615194360675, 'samples': 3304128, 'steps': 17208, 'loss/train': 1.4905062913894653}
+08/30/2021 16:20:15 - INFO - __main__ - Step 17210: {'lr': 0.0004870844683678496, 'samples': 3304320, 'steps': 17209, 'loss/train': 2.038738965988159}
+08/30/2021 16:20:16 - INFO - __main__ - Step 17211: {'lr': 0.0004870827846852658, 'samples': 3304512, 'steps': 17210, 'loss/train': 1.8041356801986694}
+08/30/2021 16:20:17 - INFO - __main__ - Step 17212: {'lr': 0.00048708110089585617, 'samples': 3304704, 'steps': 17211, 'loss/train': 1.6887880563735962}
+08/30/2021 16:20:18 - INFO - __main__ - Step 17213: {'lr': 0.00048707941699962143, 'samples': 3304896, 'steps': 17212, 'loss/train': 1.7832515239715576}
+08/30/2021 16:20:18 - INFO - __main__ - Step 17214: {'lr': 0.0004870777329965624, 'samples': 3305088, 'steps': 17213, 'loss/train': 1.9115080833435059}
+08/30/2021 16:20:18 - INFO - __main__ - Step 17215: {'lr': 0.00048707604888667983, 'samples': 3305280, 'steps': 17214, 'loss/train': 1.2715325355529785}
+08/30/2021 16:20:19 - INFO - __main__ - Step 17216: {'lr': 0.0004870743646699744, 'samples': 3305472, 'steps': 17215, 'loss/train': 1.3081682920455933}
+08/30/2021 16:20:20 - INFO - __main__ - Step 17217: {'lr': 0.0004870726803464469, 'samples': 3305664, 'steps': 17216, 'loss/train': 1.637826919555664}
+08/30/2021 16:20:21 - INFO - __main__ - Step 17218: {'lr': 0.00048707099591609816, 'samples': 3305856, 'steps': 17217, 'loss/train': 1.9086990356445312}
+08/30/2021 16:20:21 - INFO - __main__ - Step 17219: {'lr': 0.0004870693113789289, 'samples': 3306048, 'steps': 17218, 'loss/train': 1.7289403676986694}
+08/30/2021 16:20:21 - INFO - __main__ - Step 17220: {'lr': 0.00048706762673493987, 'samples': 3306240, 'steps': 17219, 'loss/train': 1.3607165813446045}
+08/30/2021 16:20:22 - INFO - __main__ - Step 17221: {'lr': 0.00048706594198413177, 'samples': 3306432, 'steps': 17220, 'loss/train': 1.6289743185043335}
+08/30/2021 16:20:23 - INFO - __main__ - Step 17222: {'lr': 0.0004870642571265054, 'samples': 3306624, 'steps': 17221, 'loss/train': 1.3383699655532837}
+08/30/2021 16:20:24 - INFO - __main__ - Step 17223: {'lr': 0.0004870625721620616, 'samples': 3306816, 'steps': 17222, 'loss/train': 1.5149602890014648}
+08/30/2021 16:20:24 - INFO - __main__ - Step 17224: {'lr': 0.00048706088709080103, 'samples': 3307008, 'steps': 17223, 'loss/train': 2.0026845932006836}
+08/30/2021 16:20:24 - INFO - __main__ - Step 17225: {'lr': 0.00048705920191272447, 'samples': 3307200, 'steps': 17224, 'loss/train': 1.5719797611236572}
+08/30/2021 16:20:25 - INFO - __main__ - Step 17226: {'lr': 0.0004870575166278327, 'samples': 3307392, 'steps': 17225, 'loss/train': 1.1763685941696167}
+08/30/2021 16:20:26 - INFO - __main__ - Step 17227: {'lr': 0.0004870558312361265, 'samples': 3307584, 'steps': 17226, 'loss/train': 1.4753894805908203}
+08/30/2021 16:20:27 - INFO - __main__ - Step 17228: {'lr': 0.0004870541457376066, 'samples': 3307776, 'steps': 17227, 'loss/train': 1.3628004789352417}
+08/30/2021 16:20:27 - INFO - __main__ - Step 17229: {'lr': 0.0004870524601322737, 'samples': 3307968, 'steps': 17228, 'loss/train': 1.4777752161026}
+08/30/2021 16:20:27 - INFO - __main__ - Step 17230: {'lr': 0.00048705077442012866, 'samples': 3308160, 'steps': 17229, 'loss/train': 1.9251604080200195}
+08/30/2021 16:20:28 - INFO - __main__ - Step 17231: {'lr': 0.0004870490886011723, 'samples': 3308352, 'steps': 17230, 'loss/train': 1.7312031984329224}
+08/30/2021 16:20:29 - INFO - __main__ - Step 17232: {'lr': 0.0004870474026754051, 'samples': 3308544, 'steps': 17231, 'loss/train': 1.7540390491485596}
+08/30/2021 16:20:30 - INFO - __main__ - Step 17233: {'lr': 0.00048704571664282806, 'samples': 3308736, 'steps': 17232, 'loss/train': 1.5850716829299927}
+08/30/2021 16:20:30 - INFO - __main__ - Step 17234: {'lr': 0.0004870440305034419, 'samples': 3308928, 'steps': 17233, 'loss/train': 0.14398325979709625}
+08/30/2021 16:20:30 - INFO - __main__ - Step 17235: {'lr': 0.00048704234425724736, 'samples': 3309120, 'steps': 17234, 'loss/train': 1.5970796346664429}
+08/30/2021 16:20:31 - INFO - __main__ - Step 17236: {'lr': 0.0004870406579042452, 'samples': 3309312, 'steps': 17235, 'loss/train': 2.115356206893921}
+08/30/2021 16:20:32 - INFO - __main__ - Step 17237: {'lr': 0.00048703897144443615, 'samples': 3309504, 'steps': 17236, 'loss/train': 1.9717119932174683}
+08/30/2021 16:20:33 - INFO - __main__ - Step 17238: {'lr': 0.000487037284877821, 'samples': 3309696, 'steps': 17237, 'loss/train': 1.8846182823181152}
+08/30/2021 16:20:33 - INFO - __main__ - Step 17239: {'lr': 0.00048703559820440054, 'samples': 3309888, 'steps': 17238, 'loss/train': 0.8971735239028931}
+08/30/2021 16:20:34 - INFO - __main__ - Step 17240: {'lr': 0.0004870339114241755, 'samples': 3310080, 'steps': 17239, 'loss/train': 1.6554961204528809}
+08/30/2021 16:20:34 - INFO - __main__ - Step 17241: {'lr': 0.00048703222453714656, 'samples': 3310272, 'steps': 17240, 'loss/train': 1.9984480142593384}
+08/30/2021 16:20:35 - INFO - __main__ - Step 17242: {'lr': 0.0004870305375433146, 'samples': 3310464, 'steps': 17241, 'loss/train': 0.11705752462148666}
+08/30/2021 16:20:36 - INFO - __main__ - Step 17243: {'lr': 0.0004870288504426804, 'samples': 3310656, 'steps': 17242, 'loss/train': 1.8031328916549683}
+08/30/2021 16:20:36 - INFO - __main__ - Step 17244: {'lr': 0.0004870271632352446, 'samples': 3310848, 'steps': 17243, 'loss/train': 1.4639816284179688}
+08/30/2021 16:20:37 - INFO - __main__ - Step 17245: {'lr': 0.000487025475921008, 'samples': 3311040, 'steps': 17244, 'loss/train': 1.7096904516220093}
+08/30/2021 16:20:37 - INFO - __main__ - Step 17246: {'lr': 0.00048702378849997143, 'samples': 3311232, 'steps': 17245, 'loss/train': 1.751753330230713}
+08/30/2021 16:20:38 - INFO - __main__ - Step 17247: {'lr': 0.0004870221009721356, 'samples': 3311424, 'steps': 17246, 'loss/train': 1.6622823476791382}
+08/30/2021 16:20:39 - INFO - __main__ - Step 17248: {'lr': 0.00048702041333750117, 'samples': 3311616, 'steps': 17247, 'loss/train': 1.5522351264953613}
+08/30/2021 16:20:39 - INFO - __main__ - Step 17249: {'lr': 0.0004870187255960691, 'samples': 3311808, 'steps': 17248, 'loss/train': 1.5034717321395874}
+08/30/2021 16:20:39 - INFO - __main__ - Step 17250: {'lr': 0.00048701703774784, 'samples': 3312000, 'steps': 17249, 'loss/train': 1.4204462766647339}
+08/30/2021 16:20:40 - INFO - __main__ - Step 17251: {'lr': 0.0004870153497928147, 'samples': 3312192, 'steps': 17250, 'loss/train': 1.531490683555603}
+08/30/2021 16:20:41 - INFO - __main__ - Step 17252: {'lr': 0.00048701366173099396, 'samples': 3312384, 'steps': 17251, 'loss/train': 1.433632254600525}
+08/30/2021 16:20:42 - INFO - __main__ - Step 17253: {'lr': 0.0004870119735623785, 'samples': 3312576, 'steps': 17252, 'loss/train': 1.6299384832382202}
+08/30/2021 16:20:42 - INFO - __main__ - Step 17254: {'lr': 0.00048701028528696914, 'samples': 3312768, 'steps': 17253, 'loss/train': 1.7262139320373535}
+08/30/2021 16:20:42 - INFO - __main__ - Step 17255: {'lr': 0.0004870085969047665, 'samples': 3312960, 'steps': 17254, 'loss/train': 1.7061408758163452}
+08/30/2021 16:20:43 - INFO - __main__ - Step 17256: {'lr': 0.00048700690841577154, 'samples': 3313152, 'steps': 17255, 'loss/train': 0.7340334057807922}
+08/30/2021 16:20:45 - INFO - __main__ - Step 17257: {'lr': 0.0004870052198199849, 'samples': 3313344, 'steps': 17256, 'loss/train': 1.5008362531661987}
+08/30/2021 16:20:45 - INFO - __main__ - Step 17258: {'lr': 0.00048700353111740734, 'samples': 3313536, 'steps': 17257, 'loss/train': 0.9157738089561462}
+08/30/2021 16:20:46 - INFO - __main__ - Step 17259: {'lr': 0.0004870018423080397, 'samples': 3313728, 'steps': 17258, 'loss/train': 1.6854766607284546}
+08/30/2021 16:20:46 - INFO - __main__ - Step 17260: {'lr': 0.00048700015339188266, 'samples': 3313920, 'steps': 17259, 'loss/train': 1.5270642042160034}
+08/30/2021 16:20:46 - INFO - __main__ - Step 17261: {'lr': 0.0004869984643689369, 'samples': 3314112, 'steps': 17260, 'loss/train': 1.520378589630127}
+08/30/2021 16:20:47 - INFO - __main__ - Step 17262: {'lr': 0.00048699677523920346, 'samples': 3314304, 'steps': 17261, 'loss/train': 1.5046796798706055}
+08/30/2021 16:20:48 - INFO - __main__ - Step 17263: {'lr': 0.00048699508600268284, 'samples': 3314496, 'steps': 17262, 'loss/train': 1.4834710359573364}
+08/30/2021 16:20:49 - INFO - __main__ - Step 17264: {'lr': 0.00048699339665937594, 'samples': 3314688, 'steps': 17263, 'loss/train': 2.0987493991851807}
+08/30/2021 16:20:49 - INFO - __main__ - Step 17265: {'lr': 0.0004869917072092834, 'samples': 3314880, 'steps': 17264, 'loss/train': 1.4187264442443848}
+08/30/2021 16:20:49 - INFO - __main__ - Step 17266: {'lr': 0.00048699001765240615, 'samples': 3315072, 'steps': 17265, 'loss/train': 1.3038651943206787}
+08/30/2021 16:20:50 - INFO - __main__ - Step 17267: {'lr': 0.00048698832798874477, 'samples': 3315264, 'steps': 17266, 'loss/train': 1.9730043411254883}
+08/30/2021 16:20:51 - INFO - __main__ - Step 17268: {'lr': 0.0004869866382183001, 'samples': 3315456, 'steps': 17267, 'loss/train': 1.1494001150131226}
+08/30/2021 16:20:52 - INFO - __main__ - Step 17269: {'lr': 0.00048698494834107297, 'samples': 3315648, 'steps': 17268, 'loss/train': 1.7524253129959106}
+08/30/2021 16:20:52 - INFO - __main__ - Step 17270: {'lr': 0.000486983258357064, 'samples': 3315840, 'steps': 17269, 'loss/train': 1.5027101039886475}
+08/30/2021 16:20:53 - INFO - __main__ - Step 17271: {'lr': 0.00048698156826627414, 'samples': 3316032, 'steps': 17270, 'loss/train': 1.9209132194519043}
+08/30/2021 16:20:53 - INFO - __main__ - Step 17272: {'lr': 0.00048697987806870397, 'samples': 3316224, 'steps': 17271, 'loss/train': 1.8910088539123535}
+08/30/2021 16:20:54 - INFO - __main__ - Step 17273: {'lr': 0.0004869781877643543, 'samples': 3316416, 'steps': 17272, 'loss/train': 1.5945838689804077}
+08/30/2021 16:20:55 - INFO - __main__ - Step 17274: {'lr': 0.000486976497353226, 'samples': 3316608, 'steps': 17273, 'loss/train': 0.6928431987762451}
+08/30/2021 16:20:55 - INFO - __main__ - Step 17275: {'lr': 0.0004869748068353197, 'samples': 3316800, 'steps': 17274, 'loss/train': 1.5734776258468628}
+08/30/2021 16:20:56 - INFO - __main__ - Step 17276: {'lr': 0.00048697311621063625, 'samples': 3316992, 'steps': 17275, 'loss/train': 1.3791122436523438}
+08/30/2021 16:20:56 - INFO - __main__ - Step 17277: {'lr': 0.0004869714254791763, 'samples': 3317184, 'steps': 17276, 'loss/train': 2.1521201133728027}
+08/30/2021 16:20:58 - INFO - __main__ - Step 17278: {'lr': 0.00048696973464094076, 'samples': 3317376, 'steps': 17277, 'loss/train': 1.322631597518921}
+08/30/2021 16:20:59 - INFO - __main__ - Step 17279: {'lr': 0.00048696804369593023, 'samples': 3317568, 'steps': 17278, 'loss/train': 1.4515596628189087}
+08/30/2021 16:20:59 - INFO - __main__ - Step 17280: {'lr': 0.0004869663526441456, 'samples': 3317760, 'steps': 17279, 'loss/train': 1.5458523035049438}
+08/30/2021 16:20:59 - INFO - __main__ - Step 17281: {'lr': 0.0004869646614855876, 'samples': 3317952, 'steps': 17280, 'loss/train': 0.6698225140571594}
+08/30/2021 16:21:00 - INFO - __main__ - Step 17282: {'lr': 0.0004869629702202569, 'samples': 3318144, 'steps': 17281, 'loss/train': 0.613684892654419}
+08/30/2021 16:21:00 - INFO - __main__ - Step 17283: {'lr': 0.0004869612788481544, 'samples': 3318336, 'steps': 17282, 'loss/train': 0.5401663184165955}
+08/30/2021 16:21:01 - INFO - __main__ - Step 17284: {'lr': 0.00048695958736928084, 'samples': 3318528, 'steps': 17283, 'loss/train': 2.1009950637817383}
+08/30/2021 16:21:02 - INFO - __main__ - Step 17285: {'lr': 0.00048695789578363693, 'samples': 3318720, 'steps': 17284, 'loss/train': 1.6466425657272339}
+08/30/2021 16:21:02 - INFO - __main__ - Step 17286: {'lr': 0.00048695620409122345, 'samples': 3318912, 'steps': 17285, 'loss/train': 1.2270723581314087}
+08/30/2021 16:21:03 - INFO - __main__ - Step 17287: {'lr': 0.00048695451229204115, 'samples': 3319104, 'steps': 17286, 'loss/train': 1.5756330490112305}
+08/30/2021 16:21:03 - INFO - __main__ - Step 17288: {'lr': 0.0004869528203860908, 'samples': 3319296, 'steps': 17287, 'loss/train': 1.4684290885925293}
+08/30/2021 16:21:04 - INFO - __main__ - Step 17289: {'lr': 0.0004869511283733732, 'samples': 3319488, 'steps': 17288, 'loss/train': 1.3921698331832886}
+08/30/2021 16:21:05 - INFO - __main__ - Step 17290: {'lr': 0.000486949436253889, 'samples': 3319680, 'steps': 17289, 'loss/train': 1.5589308738708496}
+08/30/2021 16:21:05 - INFO - __main__ - Step 17291: {'lr': 0.0004869477440276391, 'samples': 3319872, 'steps': 17290, 'loss/train': 1.8033311367034912}
+08/30/2021 16:21:06 - INFO - __main__ - Step 17292: {'lr': 0.00048694605169462415, 'samples': 3320064, 'steps': 17291, 'loss/train': 1.333516001701355}
+08/30/2021 16:21:06 - INFO - __main__ - Step 17293: {'lr': 0.00048694435925484506, 'samples': 3320256, 'steps': 17292, 'loss/train': 1.8079005479812622}
+08/30/2021 16:21:08 - INFO - __main__ - Step 17294: {'lr': 0.0004869426667083024, 'samples': 3320448, 'steps': 17293, 'loss/train': 2.0321059226989746}
+08/30/2021 16:21:08 - INFO - __main__ - Step 17295: {'lr': 0.00048694097405499703, 'samples': 3320640, 'steps': 17294, 'loss/train': 1.420762538909912}
+08/30/2021 16:21:09 - INFO - __main__ - Step 17296: {'lr': 0.0004869392812949298, 'samples': 3320832, 'steps': 17295, 'loss/train': 0.06690653413534164}
+08/30/2021 16:21:09 - INFO - __main__ - Step 17297: {'lr': 0.00048693758842810133, 'samples': 3321024, 'steps': 17296, 'loss/train': 1.6953409910202026}
+08/30/2021 16:21:09 - INFO - __main__ - Step 17298: {'lr': 0.00048693589545451243, 'samples': 3321216, 'steps': 17297, 'loss/train': 1.5967339277267456}
+08/30/2021 16:21:10 - INFO - __main__ - Step 17299: {'lr': 0.00048693420237416393, 'samples': 3321408, 'steps': 17298, 'loss/train': 1.582407832145691}
+08/30/2021 16:21:11 - INFO - __main__ - Step 17300: {'lr': 0.00048693250918705643, 'samples': 3321600, 'steps': 17299, 'loss/train': 1.3376667499542236}
+08/30/2021 16:21:12 - INFO - __main__ - Step 17301: {'lr': 0.0004869308158931909, 'samples': 3321792, 'steps': 17300, 'loss/train': 2.073134660720825}
+08/30/2021 16:21:12 - INFO - __main__ - Step 17302: {'lr': 0.00048692912249256794, 'samples': 3321984, 'steps': 17301, 'loss/train': 1.2439717054367065}
+08/30/2021 16:21:12 - INFO - __main__ - Step 17303: {'lr': 0.00048692742898518836, 'samples': 3322176, 'steps': 17302, 'loss/train': 1.4036697149276733}
+08/30/2021 16:21:13 - INFO - __main__ - Step 17304: {'lr': 0.000486925735371053, 'samples': 3322368, 'steps': 17303, 'loss/train': 1.7767975330352783}
+08/30/2021 16:21:14 - INFO - __main__ - Step 17305: {'lr': 0.00048692404165016256, 'samples': 3322560, 'steps': 17304, 'loss/train': 1.9546399116516113}
+08/30/2021 16:21:15 - INFO - __main__ - Step 17306: {'lr': 0.0004869223478225178, 'samples': 3322752, 'steps': 17305, 'loss/train': 1.1804614067077637}
+08/30/2021 16:21:15 - INFO - __main__ - Step 17307: {'lr': 0.00048692065388811944, 'samples': 3322944, 'steps': 17306, 'loss/train': 1.7170722484588623}
+08/30/2021 16:21:15 - INFO - __main__ - Step 17308: {'lr': 0.0004869189598469683, 'samples': 3323136, 'steps': 17307, 'loss/train': 1.4930357933044434}
+08/30/2021 16:21:16 - INFO - __main__ - Step 17309: {'lr': 0.00048691726569906514, 'samples': 3323328, 'steps': 17308, 'loss/train': 1.680724024772644}
+08/30/2021 16:21:19 - INFO - __main__ - Step 17310: {'lr': 0.0004869155714444107, 'samples': 3323520, 'steps': 17309, 'loss/train': 1.571215271949768}
+08/30/2021 16:21:19 - INFO - __main__ - Step 17311: {'lr': 0.00048691387708300584, 'samples': 3323712, 'steps': 17310, 'loss/train': 1.4766267538070679}
+08/30/2021 16:21:19 - INFO - __main__ - Step 17312: {'lr': 0.00048691218261485113, 'samples': 3323904, 'steps': 17311, 'loss/train': 1.329664945602417}
+08/30/2021 16:21:20 - INFO - __main__ - Step 17313: {'lr': 0.00048691048803994755, 'samples': 3324096, 'steps': 17312, 'loss/train': 1.7416303157806396}
+08/30/2021 16:21:20 - INFO - __main__ - Step 17314: {'lr': 0.00048690879335829565, 'samples': 3324288, 'steps': 17313, 'loss/train': 1.323940634727478}
+08/30/2021 16:21:20 - INFO - __main__ - Step 17315: {'lr': 0.00048690709856989635, 'samples': 3324480, 'steps': 17314, 'loss/train': 2.468637228012085}
+08/30/2021 16:21:21 - INFO - __main__ - Step 17316: {'lr': 0.00048690540367475046, 'samples': 3324672, 'steps': 17315, 'loss/train': 0.28997504711151123}
+08/30/2021 16:21:22 - INFO - __main__ - Step 17317: {'lr': 0.00048690370867285847, 'samples': 3324864, 'steps': 17316, 'loss/train': 0.3503378927707672}
+08/30/2021 16:21:23 - INFO - __main__ - Step 17318: {'lr': 0.00048690201356422146, 'samples': 3325056, 'steps': 17317, 'loss/train': 1.3354766368865967}
+08/30/2021 16:21:23 - INFO - __main__ - Step 17319: {'lr': 0.00048690031834884004, 'samples': 3325248, 'steps': 17318, 'loss/train': 0.25356781482696533}
+08/30/2021 16:21:24 - INFO - __main__ - Step 17320: {'lr': 0.00048689862302671495, 'samples': 3325440, 'steps': 17319, 'loss/train': 1.2663406133651733}
+08/30/2021 16:21:24 - INFO - __main__ - Step 17321: {'lr': 0.000486896927597847, 'samples': 3325632, 'steps': 17320, 'loss/train': 2.2433221340179443}
+08/30/2021 16:21:25 - INFO - __main__ - Step 17322: {'lr': 0.00048689523206223693, 'samples': 3325824, 'steps': 17321, 'loss/train': 1.3755285739898682}
+08/30/2021 16:21:26 - INFO - __main__ - Step 17323: {'lr': 0.00048689353641988563, 'samples': 3326016, 'steps': 17322, 'loss/train': 1.7116140127182007}
+08/30/2021 16:21:26 - INFO - __main__ - Step 17324: {'lr': 0.0004868918406707937, 'samples': 3326208, 'steps': 17323, 'loss/train': 1.3808372020721436}
+08/30/2021 16:21:27 - INFO - __main__ - Step 17325: {'lr': 0.00048689014481496197, 'samples': 3326400, 'steps': 17324, 'loss/train': 1.2138450145721436}
+08/30/2021 16:21:27 - INFO - __main__ - Step 17326: {'lr': 0.0004868884488523911, 'samples': 3326592, 'steps': 17325, 'loss/train': 1.6475673913955688}
+08/30/2021 16:21:29 - INFO - __main__ - Step 17327: {'lr': 0.0004868867527830821, 'samples': 3326784, 'steps': 17326, 'loss/train': 1.5045684576034546}
+08/30/2021 16:21:29 - INFO - __main__ - Step 17328: {'lr': 0.0004868850566070355, 'samples': 3326976, 'steps': 17327, 'loss/train': 0.6110200881958008}
+08/30/2021 16:21:29 - INFO - __main__ - Step 17329: {'lr': 0.00048688336032425217, 'samples': 3327168, 'steps': 17328, 'loss/train': 2.3573122024536133}
+08/30/2021 16:21:30 - INFO - __main__ - Step 17330: {'lr': 0.0004868816639347328, 'samples': 3327360, 'steps': 17329, 'loss/train': 1.7974035739898682}
+08/30/2021 16:21:30 - INFO - __main__ - Step 17331: {'lr': 0.0004868799674384783, 'samples': 3327552, 'steps': 17330, 'loss/train': 2.2172374725341797}
+08/30/2021 16:21:30 - INFO - __main__ - Step 17332: {'lr': 0.0004868782708354893, 'samples': 3327744, 'steps': 17331, 'loss/train': 1.334261178970337}
+08/30/2021 16:21:32 - INFO - __main__ - Step 17333: {'lr': 0.0004868765741257666, 'samples': 3327936, 'steps': 17332, 'loss/train': 1.588341236114502}
+08/30/2021 16:21:32 - INFO - __main__ - Step 17334: {'lr': 0.00048687487730931096, 'samples': 3328128, 'steps': 17333, 'loss/train': 2.2034811973571777}
+08/30/2021 16:21:33 - INFO - __main__ - Step 17335: {'lr': 0.00048687318038612317, 'samples': 3328320, 'steps': 17334, 'loss/train': 1.5304841995239258}
+08/30/2021 16:21:33 - INFO - __main__ - Step 17336: {'lr': 0.000486871483356204, 'samples': 3328512, 'steps': 17335, 'loss/train': 1.9972132444381714}
+08/30/2021 16:21:34 - INFO - __main__ - Step 17337: {'lr': 0.00048686978621955416, 'samples': 3328704, 'steps': 17336, 'loss/train': 1.6155893802642822}
+08/30/2021 16:21:35 - INFO - __main__ - Step 17338: {'lr': 0.00048686808897617447, 'samples': 3328896, 'steps': 17337, 'loss/train': 2.1802656650543213}
+08/30/2021 16:21:35 - INFO - __main__ - Step 17339: {'lr': 0.00048686639162606564, 'samples': 3329088, 'steps': 17338, 'loss/train': 1.9840431213378906}
+08/30/2021 16:21:36 - INFO - __main__ - Step 17340: {'lr': 0.0004868646941692285, 'samples': 3329280, 'steps': 17339, 'loss/train': 1.7624295949935913}
+08/30/2021 16:21:36 - INFO - __main__ - Step 17341: {'lr': 0.0004868629966056638, 'samples': 3329472, 'steps': 17340, 'loss/train': 1.2280787229537964}
+08/30/2021 16:21:36 - INFO - __main__ - Step 17342: {'lr': 0.0004868612989353722, 'samples': 3329664, 'steps': 17341, 'loss/train': 1.5077310800552368}
+08/30/2021 16:21:38 - INFO - __main__ - Step 17343: {'lr': 0.0004868596011583547, 'samples': 3329856, 'steps': 17342, 'loss/train': 0.6439254879951477}
+08/30/2021 16:21:39 - INFO - __main__ - Step 17344: {'lr': 0.00048685790327461184, 'samples': 3330048, 'steps': 17343, 'loss/train': 1.9081764221191406}
+08/30/2021 16:21:39 - INFO - __main__ - Step 17345: {'lr': 0.0004868562052841444, 'samples': 3330240, 'steps': 17344, 'loss/train': 1.3459018468856812}
+08/30/2021 16:21:39 - INFO - __main__ - Step 17346: {'lr': 0.00048685450718695335, 'samples': 3330432, 'steps': 17345, 'loss/train': 0.2580951750278473}
+08/30/2021 16:21:40 - INFO - __main__ - Step 17347: {'lr': 0.00048685280898303916, 'samples': 3330624, 'steps': 17346, 'loss/train': 1.4930943250656128}
+08/30/2021 16:21:40 - INFO - __main__ - Step 17348: {'lr': 0.00048685111067240283, 'samples': 3330816, 'steps': 17347, 'loss/train': 1.3986310958862305}
+08/30/2021 16:21:42 - INFO - __main__ - Step 17349: {'lr': 0.00048684941225504507, 'samples': 3331008, 'steps': 17348, 'loss/train': 1.661223292350769}
+08/30/2021 16:21:42 - INFO - __main__ - Step 17350: {'lr': 0.0004868477137309666, 'samples': 3331200, 'steps': 17349, 'loss/train': 2.1348724365234375}
+08/30/2021 16:21:43 - INFO - __main__ - Step 17351: {'lr': 0.00048684601510016817, 'samples': 3331392, 'steps': 17350, 'loss/train': 2.4937057495117188}
+08/30/2021 16:21:43 - INFO - __main__ - Step 17352: {'lr': 0.00048684431636265065, 'samples': 3331584, 'steps': 17351, 'loss/train': 1.2339820861816406}
+08/30/2021 16:21:43 - INFO - __main__ - Step 17353: {'lr': 0.00048684261751841463, 'samples': 3331776, 'steps': 17352, 'loss/train': 1.6313081979751587}
+08/30/2021 16:21:45 - INFO - __main__ - Step 17354: {'lr': 0.000486840918567461, 'samples': 3331968, 'steps': 17353, 'loss/train': 1.693860411643982}
+08/30/2021 16:21:45 - INFO - __main__ - Step 17355: {'lr': 0.0004868392195097906, 'samples': 3332160, 'steps': 17354, 'loss/train': 1.7639496326446533}
+08/30/2021 16:21:46 - INFO - __main__ - Step 17356: {'lr': 0.0004868375203454041, 'samples': 3332352, 'steps': 17355, 'loss/train': 1.3028088808059692}
+08/30/2021 16:21:46 - INFO - __main__ - Step 17357: {'lr': 0.00048683582107430227, 'samples': 3332544, 'steps': 17356, 'loss/train': 0.4325411319732666}
+08/30/2021 16:21:46 - INFO - __main__ - Step 17358: {'lr': 0.0004868341216964858, 'samples': 3332736, 'steps': 17357, 'loss/train': 1.8419189453125}
+08/30/2021 16:21:48 - INFO - __main__ - Step 17359: {'lr': 0.00048683242221195553, 'samples': 3332928, 'steps': 17358, 'loss/train': 1.6655195951461792}
+08/30/2021 16:21:48 - INFO - __main__ - Step 17360: {'lr': 0.00048683072262071224, 'samples': 3333120, 'steps': 17359, 'loss/train': 0.29443657398223877}
+08/30/2021 16:21:49 - INFO - __main__ - Step 17361: {'lr': 0.00048682902292275667, 'samples': 3333312, 'steps': 17360, 'loss/train': 1.6831555366516113}
+08/30/2021 16:21:49 - INFO - __main__ - Step 17362: {'lr': 0.00048682732311808964, 'samples': 3333504, 'steps': 17361, 'loss/train': 1.497959017753601}
+08/30/2021 16:21:49 - INFO - __main__ - Step 17363: {'lr': 0.00048682562320671185, 'samples': 3333696, 'steps': 17362, 'loss/train': 1.7417789697647095}
+08/30/2021 16:21:51 - INFO - __main__ - Step 17364: {'lr': 0.00048682392318862407, 'samples': 3333888, 'steps': 17363, 'loss/train': 1.3795396089553833}
+08/30/2021 16:21:52 - INFO - __main__ - Step 17365: {'lr': 0.00048682222306382705, 'samples': 3334080, 'steps': 17364, 'loss/train': 1.7262126207351685}
+08/30/2021 16:21:52 - INFO - __main__ - Step 17366: {'lr': 0.0004868205228323217, 'samples': 3334272, 'steps': 17365, 'loss/train': 1.6140670776367188}
+08/30/2021 16:21:53 - INFO - __main__ - Step 17367: {'lr': 0.0004868188224941086, 'samples': 3334464, 'steps': 17366, 'loss/train': 2.37587308883667}
+08/30/2021 16:21:53 - INFO - __main__ - Step 17368: {'lr': 0.0004868171220491886, 'samples': 3334656, 'steps': 17367, 'loss/train': 2.0379302501678467}
+08/30/2021 16:21:54 - INFO - __main__ - Step 17369: {'lr': 0.00048681542149756253, 'samples': 3334848, 'steps': 17368, 'loss/train': 1.8309261798858643}
+08/30/2021 16:21:55 - INFO - __main__ - Step 17370: {'lr': 0.00048681372083923103, 'samples': 3335040, 'steps': 17369, 'loss/train': 1.9486777782440186}
+08/30/2021 16:21:55 - INFO - __main__ - Step 17371: {'lr': 0.0004868120200741949, 'samples': 3335232, 'steps': 17370, 'loss/train': 2.133272886276245}
+08/30/2021 16:21:56 - INFO - __main__ - Step 17372: {'lr': 0.0004868103192024549, 'samples': 3335424, 'steps': 17371, 'loss/train': 1.6345919370651245}
+08/30/2021 16:21:56 - INFO - __main__ - Step 17373: {'lr': 0.0004868086182240119, 'samples': 3335616, 'steps': 17372, 'loss/train': 1.309005618095398}
+08/30/2021 16:21:58 - INFO - __main__ - Step 17374: {'lr': 0.00048680691713886653, 'samples': 3335808, 'steps': 17373, 'loss/train': 1.9788750410079956}
+08/30/2021 16:21:58 - INFO - __main__ - Step 17375: {'lr': 0.00048680521594701964, 'samples': 3336000, 'steps': 17374, 'loss/train': 1.8031384944915771}
+08/30/2021 16:21:59 - INFO - __main__ - Step 17376: {'lr': 0.00048680351464847207, 'samples': 3336192, 'steps': 17375, 'loss/train': 1.7543350458145142}
+08/30/2021 16:21:59 - INFO - __main__ - Step 17377: {'lr': 0.00048680181324322437, 'samples': 3336384, 'steps': 17376, 'loss/train': 1.9475842714309692}
+08/30/2021 16:21:59 - INFO - __main__ - Step 17378: {'lr': 0.00048680011173127746, 'samples': 3336576, 'steps': 17377, 'loss/train': 1.0543763637542725}
+08/30/2021 16:22:00 - INFO - __main__ - Step 17379: {'lr': 0.00048679841011263204, 'samples': 3336768, 'steps': 17378, 'loss/train': 3.990530252456665}
+08/30/2021 16:22:01 - INFO - __main__ - Step 17380: {'lr': 0.00048679670838728894, 'samples': 3336960, 'steps': 17379, 'loss/train': 0.1678185611963272}
+08/30/2021 16:22:02 - INFO - __main__ - Step 17381: {'lr': 0.0004867950065552489, 'samples': 3337152, 'steps': 17380, 'loss/train': 1.7439442873001099}
+08/30/2021 16:22:02 - INFO - __main__ - Step 17382: {'lr': 0.00048679330461651275, 'samples': 3337344, 'steps': 17381, 'loss/train': 1.6377366781234741}
+08/30/2021 16:22:03 - INFO - __main__ - Step 17383: {'lr': 0.00048679160257108107, 'samples': 3337536, 'steps': 17382, 'loss/train': 2.1917710304260254}
+08/30/2021 16:22:03 - INFO - __main__ - Step 17384: {'lr': 0.00048678990041895484, 'samples': 3337728, 'steps': 17383, 'loss/train': 1.8279938697814941}
+08/30/2021 16:22:05 - INFO - __main__ - Step 17385: {'lr': 0.00048678819816013467, 'samples': 3337920, 'steps': 17384, 'loss/train': 0.23291407525539398}
+08/30/2021 16:22:05 - INFO - __main__ - Step 17386: {'lr': 0.0004867864957946214, 'samples': 3338112, 'steps': 17385, 'loss/train': 1.5302484035491943}
+08/30/2021 16:22:05 - INFO - __main__ - Step 17387: {'lr': 0.0004867847933224158, 'samples': 3338304, 'steps': 17386, 'loss/train': 1.5825395584106445}
+08/30/2021 16:22:06 - INFO - __main__ - Step 17388: {'lr': 0.0004867830907435187, 'samples': 3338496, 'steps': 17387, 'loss/train': 1.4746028184890747}
+08/30/2021 16:22:06 - INFO - __main__ - Step 17389: {'lr': 0.0004867813880579307, 'samples': 3338688, 'steps': 17388, 'loss/train': 1.6257576942443848}
+08/30/2021 16:22:06 - INFO - __main__ - Step 17390: {'lr': 0.0004867796852656527, 'samples': 3338880, 'steps': 17389, 'loss/train': 1.0585116147994995}
+08/30/2021 16:22:08 - INFO - __main__ - Step 17391: {'lr': 0.00048677798236668537, 'samples': 3339072, 'steps': 17390, 'loss/train': 1.5680699348449707}
+08/30/2021 16:22:08 - INFO - __main__ - Step 17392: {'lr': 0.00048677627936102966, 'samples': 3339264, 'steps': 17391, 'loss/train': 2.17177414894104}
+08/30/2021 16:22:09 - INFO - __main__ - Step 17393: {'lr': 0.0004867745762486861, 'samples': 3339456, 'steps': 17392, 'loss/train': 2.0008177757263184}
+08/30/2021 16:22:09 - INFO - __main__ - Step 17394: {'lr': 0.0004867728730296556, 'samples': 3339648, 'steps': 17393, 'loss/train': 1.4614367485046387}
+08/30/2021 16:22:09 - INFO - __main__ - Step 17395: {'lr': 0.0004867711697039389, 'samples': 3339840, 'steps': 17394, 'loss/train': 1.858125925064087}
+08/30/2021 16:22:11 - INFO - __main__ - Step 17396: {'lr': 0.00048676946627153675, 'samples': 3340032, 'steps': 17395, 'loss/train': 1.4392808675765991}
+08/30/2021 16:22:11 - INFO - __main__ - Step 17397: {'lr': 0.00048676776273244994, 'samples': 3340224, 'steps': 17396, 'loss/train': 1.8327624797821045}
+08/30/2021 16:22:12 - INFO - __main__ - Step 17398: {'lr': 0.00048676605908667926, 'samples': 3340416, 'steps': 17397, 'loss/train': 2.5532779693603516}
+08/30/2021 16:22:12 - INFO - __main__ - Step 17399: {'lr': 0.00048676435533422536, 'samples': 3340608, 'steps': 17398, 'loss/train': 1.3023334741592407}
+08/30/2021 16:22:12 - INFO - __main__ - Step 17400: {'lr': 0.00048676265147508917, 'samples': 3340800, 'steps': 17399, 'loss/train': 1.5067830085754395}
+08/30/2021 16:22:14 - INFO - __main__ - Step 17401: {'lr': 0.00048676094750927144, 'samples': 3340992, 'steps': 17400, 'loss/train': 1.7027322053909302}
+08/30/2021 16:22:14 - INFO - __main__ - Step 17402: {'lr': 0.0004867592434367728, 'samples': 3341184, 'steps': 17401, 'loss/train': 1.6238844394683838}
+08/30/2021 16:22:15 - INFO - __main__ - Step 17403: {'lr': 0.0004867575392575941, 'samples': 3341376, 'steps': 17402, 'loss/train': 1.6029798984527588}
+08/30/2021 16:22:15 - INFO - __main__ - Step 17404: {'lr': 0.0004867558349717361, 'samples': 3341568, 'steps': 17403, 'loss/train': 1.3958392143249512}
+08/30/2021 16:22:15 - INFO - __main__ - Step 17405: {'lr': 0.0004867541305791996, 'samples': 3341760, 'steps': 17404, 'loss/train': 1.8233625888824463}
+08/30/2021 16:22:17 - INFO - __main__ - Step 17406: {'lr': 0.00048675242607998533, 'samples': 3341952, 'steps': 17405, 'loss/train': 1.6665757894515991}
+08/30/2021 16:22:17 - INFO - __main__ - Step 17407: {'lr': 0.00048675072147409405, 'samples': 3342144, 'steps': 17406, 'loss/train': 1.259602665901184}
+08/30/2021 16:22:18 - INFO - __main__ - Step 17408: {'lr': 0.0004867490167615266, 'samples': 3342336, 'steps': 17407, 'loss/train': 2.2457082271575928}
+08/30/2021 16:22:18 - INFO - __main__ - Step 17409: {'lr': 0.0004867473119422837, 'samples': 3342528, 'steps': 17408, 'loss/train': 1.7272624969482422}
+08/30/2021 16:22:18 - INFO - __main__ - Step 17410: {'lr': 0.00048674560701636606, 'samples': 3342720, 'steps': 17409, 'loss/train': 1.9000693559646606}
+08/30/2021 16:22:20 - INFO - __main__ - Step 17411: {'lr': 0.0004867439019837745, 'samples': 3342912, 'steps': 17410, 'loss/train': 2.7054336071014404}
+08/30/2021 16:22:20 - INFO - __main__ - Step 17412: {'lr': 0.00048674219684450985, 'samples': 3343104, 'steps': 17411, 'loss/train': 1.8756489753723145}
+08/30/2021 16:22:21 - INFO - __main__ - Step 17413: {'lr': 0.00048674049159857277, 'samples': 3343296, 'steps': 17412, 'loss/train': 0.689872682094574}
+08/30/2021 16:22:21 - INFO - __main__ - Step 17414: {'lr': 0.0004867387862459641, 'samples': 3343488, 'steps': 17413, 'loss/train': 1.6381309032440186}
+08/30/2021 16:22:21 - INFO - __main__ - Step 17415: {'lr': 0.0004867370807866845, 'samples': 3343680, 'steps': 17414, 'loss/train': 1.8539162874221802}
+08/30/2021 16:22:24 - INFO - __main__ - Step 17416: {'lr': 0.000486735375220735, 'samples': 3343872, 'steps': 17415, 'loss/train': 2.4776206016540527}
+08/30/2021 16:22:24 - INFO - __main__ - Step 17417: {'lr': 0.00048673366954811605, 'samples': 3344064, 'steps': 17416, 'loss/train': 1.5945243835449219}
+08/30/2021 16:22:24 - INFO - __main__ - Step 17418: {'lr': 0.0004867319637688286, 'samples': 3344256, 'steps': 17417, 'loss/train': 1.1917868852615356}
+08/30/2021 16:22:25 - INFO - __main__ - Step 17419: {'lr': 0.0004867302578828734, 'samples': 3344448, 'steps': 17418, 'loss/train': 1.623712182044983}
+08/30/2021 16:22:25 - INFO - __main__ - Step 17420: {'lr': 0.0004867285518902512, 'samples': 3344640, 'steps': 17419, 'loss/train': 2.194242477416992}
+08/30/2021 16:22:25 - INFO - __main__ - Step 17421: {'lr': 0.0004867268457909627, 'samples': 3344832, 'steps': 17420, 'loss/train': 1.349695086479187}
+08/30/2021 16:22:28 - INFO - __main__ - Step 17422: {'lr': 0.0004867251395850088, 'samples': 3345024, 'steps': 17421, 'loss/train': 0.17078430950641632}
+08/30/2021 16:22:29 - INFO - __main__ - Step 17423: {'lr': 0.00048672343327239024, 'samples': 3345216, 'steps': 17422, 'loss/train': 1.512771725654602}
+08/30/2021 16:22:29 - INFO - __main__ - Step 17424: {'lr': 0.00048672172685310767, 'samples': 3345408, 'steps': 17423, 'loss/train': 1.4440419673919678}
+08/30/2021 16:22:29 - INFO - __main__ - Step 17425: {'lr': 0.000486720020327162, 'samples': 3345600, 'steps': 17424, 'loss/train': 1.7390447854995728}
+08/30/2021 16:22:30 - INFO - __main__ - Step 17426: {'lr': 0.00048671831369455386, 'samples': 3345792, 'steps': 17425, 'loss/train': 0.44793176651000977}
+08/30/2021 16:22:30 - INFO - __main__ - Step 17427: {'lr': 0.0004867166069552842, 'samples': 3345984, 'steps': 17426, 'loss/train': 2.000828266143799}
+08/30/2021 16:22:30 - INFO - __main__ - Step 17428: {'lr': 0.00048671490010935366, 'samples': 3346176, 'steps': 17427, 'loss/train': 1.1772760152816772}
+08/30/2021 16:22:31 - INFO - __main__ - Step 17429: {'lr': 0.00048671319315676305, 'samples': 3346368, 'steps': 17428, 'loss/train': 2.734375}
+08/30/2021 16:22:32 - INFO - __main__ - Step 17430: {'lr': 0.00048671148609751307, 'samples': 3346560, 'steps': 17429, 'loss/train': 1.5546437501907349}
+08/30/2021 16:22:33 - INFO - __main__ - Step 17431: {'lr': 0.0004867097789316046, 'samples': 3346752, 'steps': 17430, 'loss/train': 2.1142067909240723}
+08/30/2021 16:22:33 - INFO - __main__ - Step 17432: {'lr': 0.0004867080716590384, 'samples': 3346944, 'steps': 17431, 'loss/train': 1.9760955572128296}
+08/30/2021 16:22:33 - INFO - __main__ - Step 17433: {'lr': 0.0004867063642798151, 'samples': 3347136, 'steps': 17432, 'loss/train': 1.793282389640808}
+08/30/2021 16:22:34 - INFO - __main__ - Step 17434: {'lr': 0.0004867046567939356, 'samples': 3347328, 'steps': 17433, 'loss/train': 1.8897130489349365}
+08/30/2021 16:22:35 - INFO - __main__ - Step 17435: {'lr': 0.00048670294920140063, 'samples': 3347520, 'steps': 17434, 'loss/train': 2.087878465652466}
+08/30/2021 16:22:36 - INFO - __main__ - Step 17436: {'lr': 0.00048670124150221094, 'samples': 3347712, 'steps': 17435, 'loss/train': 1.708673357963562}
+08/30/2021 16:22:36 - INFO - __main__ - Step 17437: {'lr': 0.00048669953369636737, 'samples': 3347904, 'steps': 17436, 'loss/train': 1.349056601524353}
+08/30/2021 16:22:36 - INFO - __main__ - Step 17438: {'lr': 0.00048669782578387067, 'samples': 3348096, 'steps': 17437, 'loss/train': 0.8885194063186646}
+08/30/2021 16:22:37 - INFO - __main__ - Step 17439: {'lr': 0.00048669611776472153, 'samples': 3348288, 'steps': 17438, 'loss/train': 1.7635525465011597}
+08/30/2021 16:22:37 - INFO - __main__ - Step 17440: {'lr': 0.00048669440963892074, 'samples': 3348480, 'steps': 17439, 'loss/train': 2.1269845962524414}
+08/30/2021 16:22:39 - INFO - __main__ - Step 17441: {'lr': 0.00048669270140646914, 'samples': 3348672, 'steps': 17440, 'loss/train': 1.8065775632858276}
+08/30/2021 16:22:39 - INFO - __main__ - Step 17442: {'lr': 0.0004866909930673675, 'samples': 3348864, 'steps': 17441, 'loss/train': 2.5166263580322266}
+08/30/2021 16:22:39 - INFO - __main__ - Step 17443: {'lr': 0.00048668928462161653, 'samples': 3349056, 'steps': 17442, 'loss/train': 2.0788023471832275}
+08/30/2021 16:22:40 - INFO - __main__ - Step 17444: {'lr': 0.000486687576069217, 'samples': 3349248, 'steps': 17443, 'loss/train': 5.522563934326172}
+08/30/2021 16:22:40 - INFO - __main__ - Step 17445: {'lr': 0.00048668586741016967, 'samples': 3349440, 'steps': 17444, 'loss/train': 2.367457866668701}
+08/30/2021 16:22:42 - INFO - __main__ - Step 17446: {'lr': 0.0004866841586444754, 'samples': 3349632, 'steps': 17445, 'loss/train': 1.866705060005188}
+08/30/2021 16:22:43 - INFO - __main__ - Step 17447: {'lr': 0.0004866824497721349, 'samples': 3349824, 'steps': 17446, 'loss/train': 1.8990633487701416}
+08/30/2021 16:22:43 - INFO - __main__ - Step 17448: {'lr': 0.0004866807407931489, 'samples': 3350016, 'steps': 17447, 'loss/train': 1.7508528232574463}
+08/30/2021 16:22:43 - INFO - __main__ - Step 17449: {'lr': 0.0004866790317075182, 'samples': 3350208, 'steps': 17448, 'loss/train': 1.650154709815979}
+08/30/2021 16:22:44 - INFO - __main__ - Step 17450: {'lr': 0.00048667732251524365, 'samples': 3350400, 'steps': 17449, 'loss/train': 1.7136389017105103}
+08/30/2021 16:22:44 - INFO - __main__ - Step 17451: {'lr': 0.0004866756132163259, 'samples': 3350592, 'steps': 17450, 'loss/train': 1.9944013357162476}
+08/30/2021 16:22:45 - INFO - __main__ - Step 17452: {'lr': 0.0004866739038107658, 'samples': 3350784, 'steps': 17451, 'loss/train': 0.36397862434387207}
+08/30/2021 16:22:46 - INFO - __main__ - Step 17453: {'lr': 0.000486672194298564, 'samples': 3350976, 'steps': 17452, 'loss/train': 1.371496558189392}
+08/30/2021 16:22:46 - INFO - __main__ - Step 17454: {'lr': 0.00048667048467972146, 'samples': 3351168, 'steps': 17453, 'loss/train': 2.206498384475708}
+08/30/2021 16:22:47 - INFO - __main__ - Step 17455: {'lr': 0.00048666877495423885, 'samples': 3351360, 'steps': 17454, 'loss/train': 2.2213566303253174}
+08/30/2021 16:22:47 - INFO - __main__ - Step 17456: {'lr': 0.0004866670651221169, 'samples': 3351552, 'steps': 17455, 'loss/train': 1.8459641933441162}
+08/30/2021 16:22:48 - INFO - __main__ - Step 17457: {'lr': 0.0004866653551833564, 'samples': 3351744, 'steps': 17456, 'loss/train': 2.0397403240203857}
+08/30/2021 16:22:49 - INFO - __main__ - Step 17458: {'lr': 0.00048666364513795816, 'samples': 3351936, 'steps': 17457, 'loss/train': 1.4646025896072388}
+08/30/2021 16:22:49 - INFO - __main__ - Step 17459: {'lr': 0.00048666193498592304, 'samples': 3352128, 'steps': 17458, 'loss/train': 1.1593598127365112}
+08/30/2021 16:22:50 - INFO - __main__ - Step 17460: {'lr': 0.0004866602247272516, 'samples': 3352320, 'steps': 17459, 'loss/train': 0.906301736831665}
+08/30/2021 16:22:50 - INFO - __main__ - Step 17461: {'lr': 0.0004866585143619447, 'samples': 3352512, 'steps': 17460, 'loss/train': 1.827962875366211}
+08/30/2021 16:22:51 - INFO - __main__ - Step 17462: {'lr': 0.00048665680389000315, 'samples': 3352704, 'steps': 17461, 'loss/train': 2.0785582065582275}
+08/30/2021 16:22:52 - INFO - __main__ - Step 17463: {'lr': 0.0004866550933114277, 'samples': 3352896, 'steps': 17462, 'loss/train': 1.6082682609558105}
+08/30/2021 16:22:52 - INFO - __main__ - Step 17464: {'lr': 0.00048665338262621915, 'samples': 3353088, 'steps': 17463, 'loss/train': 1.9932937622070312}
+08/30/2021 16:22:53 - INFO - __main__ - Step 17465: {'lr': 0.00048665167183437817, 'samples': 3353280, 'steps': 17464, 'loss/train': 1.7249715328216553}
+08/30/2021 16:22:53 - INFO - __main__ - Step 17466: {'lr': 0.00048664996093590563, 'samples': 3353472, 'steps': 17465, 'loss/train': 2.252119302749634}
+08/30/2021 16:22:54 - INFO - __main__ - Step 17467: {'lr': 0.0004866482499308023, 'samples': 3353664, 'steps': 17466, 'loss/train': 2.0502357482910156}
+08/30/2021 16:22:55 - INFO - __main__ - Step 17468: {'lr': 0.0004866465388190689, 'samples': 3353856, 'steps': 17467, 'loss/train': 1.966733694076538}
+08/30/2021 16:22:55 - INFO - __main__ - Step 17469: {'lr': 0.0004866448276007062, 'samples': 3354048, 'steps': 17468, 'loss/train': 1.647402048110962}
+08/30/2021 16:22:55 - INFO - __main__ - Step 17470: {'lr': 0.000486643116275715, 'samples': 3354240, 'steps': 17469, 'loss/train': 3.549617290496826}
+08/30/2021 16:22:56 - INFO - __main__ - Step 17471: {'lr': 0.00048664140484409613, 'samples': 3354432, 'steps': 17470, 'loss/train': 1.3118197917938232}
+08/30/2021 16:22:57 - INFO - __main__ - Step 17472: {'lr': 0.0004866396933058502, 'samples': 3354624, 'steps': 17471, 'loss/train': 1.5544676780700684}
+08/30/2021 16:22:58 - INFO - __main__ - Step 17473: {'lr': 0.00048663798166097814, 'samples': 3354816, 'steps': 17472, 'loss/train': 2.0812900066375732}
+08/30/2021 16:22:58 - INFO - __main__ - Step 17474: {'lr': 0.0004866362699094806, 'samples': 3355008, 'steps': 17473, 'loss/train': 1.616500973701477}
+08/30/2021 16:22:58 - INFO - __main__ - Step 17475: {'lr': 0.0004866345580513585, 'samples': 3355200, 'steps': 17474, 'loss/train': 1.8247954845428467}
+08/30/2021 16:22:59 - INFO - __main__ - Step 17476: {'lr': 0.0004866328460866124, 'samples': 3355392, 'steps': 17475, 'loss/train': 1.255110740661621}
+08/30/2021 16:22:59 - INFO - __main__ - Step 17477: {'lr': 0.0004866311340152433, 'samples': 3355584, 'steps': 17476, 'loss/train': 1.3190022706985474}
+08/30/2021 16:23:01 - INFO - __main__ - Step 17478: {'lr': 0.0004866294218372518, 'samples': 3355776, 'steps': 17477, 'loss/train': 1.7746151685714722}
+08/30/2021 16:23:02 - INFO - __main__ - Step 17479: {'lr': 0.0004866277095526387, 'samples': 3355968, 'steps': 17478, 'loss/train': 2.225783348083496}
+08/30/2021 16:23:02 - INFO - __main__ - Step 17480: {'lr': 0.00048662599716140485, 'samples': 3356160, 'steps': 17479, 'loss/train': 1.618331789970398}
+08/30/2021 16:23:03 - INFO - __main__ - Step 17481: {'lr': 0.00048662428466355104, 'samples': 3356352, 'steps': 17480, 'loss/train': 1.8510490655899048}
+08/30/2021 16:23:03 - INFO - __main__ - Step 17482: {'lr': 0.0004866225720590779, 'samples': 3356544, 'steps': 17481, 'loss/train': 3.352268695831299}
+08/30/2021 16:23:05 - INFO - __main__ - Step 17483: {'lr': 0.00048662085934798627, 'samples': 3356736, 'steps': 17482, 'loss/train': 1.5689951181411743}
+08/30/2021 16:23:05 - INFO - __main__ - Step 17484: {'lr': 0.00048661914653027694, 'samples': 3356928, 'steps': 17483, 'loss/train': 1.9016592502593994}
+08/30/2021 16:23:05 - INFO - __main__ - Step 17485: {'lr': 0.0004866174336059507, 'samples': 3357120, 'steps': 17484, 'loss/train': 0.360641211271286}
+08/30/2021 16:23:06 - INFO - __main__ - Step 17486: {'lr': 0.00048661572057500833, 'samples': 3357312, 'steps': 17485, 'loss/train': 0.2026984840631485}
+08/30/2021 16:23:06 - INFO - __main__ - Step 17487: {'lr': 0.00048661400743745057, 'samples': 3357504, 'steps': 17486, 'loss/train': 1.749847412109375}
+08/30/2021 16:23:08 - INFO - __main__ - Step 17488: {'lr': 0.00048661229419327806, 'samples': 3357696, 'steps': 17487, 'loss/train': 1.402083158493042}
+08/30/2021 16:23:08 - INFO - __main__ - Step 17489: {'lr': 0.0004866105808424918, 'samples': 3357888, 'steps': 17488, 'loss/train': 1.8154724836349487}
+08/30/2021 16:23:09 - INFO - __main__ - Step 17490: {'lr': 0.0004866088673850925, 'samples': 3358080, 'steps': 17489, 'loss/train': 1.7261987924575806}
+08/30/2021 16:23:09 - INFO - __main__ - Step 17491: {'lr': 0.0004866071538210808, 'samples': 3358272, 'steps': 17490, 'loss/train': 1.573549747467041}
+08/30/2021 16:23:09 - INFO - __main__ - Step 17492: {'lr': 0.0004866054401504576, 'samples': 3358464, 'steps': 17491, 'loss/train': 2.3931453227996826}
+08/30/2021 16:23:11 - INFO - __main__ - Step 17493: {'lr': 0.0004866037263732237, 'samples': 3358656, 'steps': 17492, 'loss/train': 1.9802180528640747}
+08/30/2021 16:23:12 - INFO - __main__ - Step 17494: {'lr': 0.00048660201248937974, 'samples': 3358848, 'steps': 17493, 'loss/train': 1.6586722135543823}
+08/30/2021 16:23:12 - INFO - __main__ - Step 17495: {'lr': 0.0004866002984989266, 'samples': 3359040, 'steps': 17494, 'loss/train': 1.571513056755066}
+08/30/2021 16:23:12 - INFO - __main__ - Step 17496: {'lr': 0.000486598584401865, 'samples': 3359232, 'steps': 17495, 'loss/train': 2.110097646713257}
+08/30/2021 16:23:13 - INFO - __main__ - Step 17497: {'lr': 0.0004865968701981958, 'samples': 3359424, 'steps': 17496, 'loss/train': 1.8144365549087524}
+08/30/2021 16:23:13 - INFO - __main__ - Step 17498: {'lr': 0.0004865951558879196, 'samples': 3359616, 'steps': 17497, 'loss/train': 1.760158896446228}
+08/30/2021 16:23:15 - INFO - __main__ - Step 17499: {'lr': 0.00048659344147103725, 'samples': 3359808, 'steps': 17498, 'loss/train': 0.44034385681152344}
+08/30/2021 16:23:15 - INFO - __main__ - Step 17500: {'lr': 0.0004865917269475496, 'samples': 3360000, 'steps': 17499, 'loss/train': 1.6851074695587158}
+08/30/2021 16:23:15 - INFO - __main__ - Step 17501: {'lr': 0.00048659001231745734, 'samples': 3360192, 'steps': 17500, 'loss/train': 1.7847763299942017}
+08/30/2021 16:23:16 - INFO - __main__ - Step 17502: {'lr': 0.0004865882975807614, 'samples': 3360384, 'steps': 17501, 'loss/train': 1.5666096210479736}
+08/30/2021 16:23:16 - INFO - __main__ - Step 17503: {'lr': 0.00048658658273746224, 'samples': 3360576, 'steps': 17502, 'loss/train': 1.6288776397705078}
+08/30/2021 16:23:18 - INFO - __main__ - Step 17504: {'lr': 0.00048658486778756097, 'samples': 3360768, 'steps': 17503, 'loss/train': 1.1607974767684937}
+08/30/2021 16:23:18 - INFO - __main__ - Step 17505: {'lr': 0.0004865831527310581, 'samples': 3360960, 'steps': 17504, 'loss/train': 1.639221429824829}
+08/30/2021 16:23:18 - INFO - __main__ - Step 17506: {'lr': 0.00048658143756795456, 'samples': 3361152, 'steps': 17505, 'loss/train': 1.5825897455215454}
+08/30/2021 16:23:19 - INFO - __main__ - Step 17507: {'lr': 0.0004865797222982511, 'samples': 3361344, 'steps': 17506, 'loss/train': 1.4309252500534058}
+08/30/2021 16:23:19 - INFO - __main__ - Step 17508: {'lr': 0.0004865780069219484, 'samples': 3361536, 'steps': 17507, 'loss/train': 1.031682014465332}
+08/30/2021 16:23:21 - INFO - __main__ - Step 17509: {'lr': 0.00048657629143904733, 'samples': 3361728, 'steps': 17508, 'loss/train': 1.5543208122253418}
+08/30/2021 16:23:21 - INFO - __main__ - Step 17510: {'lr': 0.0004865745758495487, 'samples': 3361920, 'steps': 17509, 'loss/train': 2.160651206970215}
+08/30/2021 16:23:22 - INFO - __main__ - Step 17511: {'lr': 0.00048657286015345313, 'samples': 3362112, 'steps': 17510, 'loss/train': 2.1131794452667236}
+08/30/2021 16:23:22 - INFO - __main__ - Step 17512: {'lr': 0.00048657114435076153, 'samples': 3362304, 'steps': 17511, 'loss/train': 1.8827873468399048}
+08/30/2021 16:23:22 - INFO - __main__ - Step 17513: {'lr': 0.00048656942844147464, 'samples': 3362496, 'steps': 17512, 'loss/train': 1.306170105934143}
+08/30/2021 16:23:24 - INFO - __main__ - Step 17514: {'lr': 0.00048656771242559316, 'samples': 3362688, 'steps': 17513, 'loss/train': 1.6868219375610352}
+08/30/2021 16:23:24 - INFO - __main__ - Step 17515: {'lr': 0.0004865659963031179, 'samples': 3362880, 'steps': 17514, 'loss/train': 1.9404577016830444}
+08/30/2021 16:23:24 - INFO - __main__ - Step 17516: {'lr': 0.0004865642800740497, 'samples': 3363072, 'steps': 17515, 'loss/train': 1.8532264232635498}
+08/30/2021 16:23:25 - INFO - __main__ - Step 17517: {'lr': 0.0004865625637383893, 'samples': 3363264, 'steps': 17516, 'loss/train': 1.0725972652435303}
+08/30/2021 16:23:25 - INFO - __main__ - Step 17518: {'lr': 0.00048656084729613747, 'samples': 3363456, 'steps': 17517, 'loss/train': 1.7218142747879028}
+08/30/2021 16:23:27 - INFO - __main__ - Step 17519: {'lr': 0.0004865591307472949, 'samples': 3363648, 'steps': 17518, 'loss/train': 1.6953128576278687}
+08/30/2021 16:23:27 - INFO - __main__ - Step 17520: {'lr': 0.0004865574140918625, 'samples': 3363840, 'steps': 17519, 'loss/train': 1.5887824296951294}
+08/30/2021 16:23:27 - INFO - __main__ - Step 17521: {'lr': 0.00048655569732984096, 'samples': 3364032, 'steps': 17520, 'loss/train': 1.7230455875396729}
+08/30/2021 16:23:28 - INFO - __main__ - Step 17522: {'lr': 0.000486553980461231, 'samples': 3364224, 'steps': 17521, 'loss/train': 1.970909833908081}
+08/30/2021 16:23:28 - INFO - __main__ - Step 17523: {'lr': 0.0004865522634860335, 'samples': 3364416, 'steps': 17522, 'loss/train': 1.807120442390442}
+08/30/2021 16:23:30 - INFO - __main__ - Step 17524: {'lr': 0.00048655054640424936, 'samples': 3364608, 'steps': 17523, 'loss/train': 1.5671602487564087}
+08/30/2021 16:23:30 - INFO - __main__ - Step 17525: {'lr': 0.00048654882921587907, 'samples': 3364800, 'steps': 17524, 'loss/train': 2.561570882797241}
+08/30/2021 16:23:30 - INFO - __main__ - Step 17526: {'lr': 0.00048654711192092347, 'samples': 3364992, 'steps': 17525, 'loss/train': 0.830582857131958}
+08/30/2021 16:23:31 - INFO - __main__ - Step 17527: {'lr': 0.0004865453945193835, 'samples': 3365184, 'steps': 17526, 'loss/train': 1.5798051357269287}
+08/30/2021 16:23:31 - INFO - __main__ - Step 17528: {'lr': 0.00048654367701125975, 'samples': 3365376, 'steps': 17527, 'loss/train': 1.8259228467941284}
+08/30/2021 16:23:33 - INFO - __main__ - Step 17529: {'lr': 0.0004865419593965531, 'samples': 3365568, 'steps': 17528, 'loss/train': 2.335393190383911}
+08/30/2021 16:23:34 - INFO - __main__ - Step 17530: {'lr': 0.0004865402416752642, 'samples': 3365760, 'steps': 17529, 'loss/train': 1.5797656774520874}
+08/30/2021 16:23:34 - INFO - __main__ - Step 17531: {'lr': 0.0004865385238473941, 'samples': 3365952, 'steps': 17530, 'loss/train': 1.0944950580596924}
+08/30/2021 16:23:34 - INFO - __main__ - Step 17532: {'lr': 0.00048653680591294324, 'samples': 3366144, 'steps': 17531, 'loss/train': 1.232177972793579}
+08/30/2021 16:23:35 - INFO - __main__ - Step 17533: {'lr': 0.00048653508787191256, 'samples': 3366336, 'steps': 17532, 'loss/train': 2.8243906497955322}
+08/30/2021 16:23:37 - INFO - __main__ - Step 17534: {'lr': 0.00048653336972430297, 'samples': 3366528, 'steps': 17533, 'loss/train': 2.401196241378784}
+08/30/2021 16:23:37 - INFO - __main__ - Step 17535: {'lr': 0.0004865316514701149, 'samples': 3366720, 'steps': 17534, 'loss/train': 1.4661340713500977}
+08/30/2021 16:23:38 - INFO - __main__ - Step 17536: {'lr': 0.0004865299331093495, 'samples': 3366912, 'steps': 17535, 'loss/train': 1.7392544746398926}
+08/30/2021 16:23:38 - INFO - __main__ - Step 17537: {'lr': 0.0004865282146420072, 'samples': 3367104, 'steps': 17536, 'loss/train': 1.827589988708496}
+08/30/2021 16:23:38 - INFO - __main__ - Step 17538: {'lr': 0.000486526496068089, 'samples': 3367296, 'steps': 17537, 'loss/train': 1.1134750843048096}
+08/30/2021 16:23:39 - INFO - __main__ - Step 17539: {'lr': 0.0004865247773875956, 'samples': 3367488, 'steps': 17538, 'loss/train': 1.734523892402649}
+08/30/2021 16:23:39 - INFO - __main__ - Step 17540: {'lr': 0.0004865230586005278, 'samples': 3367680, 'steps': 17539, 'loss/train': 0.24024170637130737}
+08/30/2021 16:23:41 - INFO - __main__ - Step 17541: {'lr': 0.00048652133970688633, 'samples': 3367872, 'steps': 17540, 'loss/train': 0.15640875697135925}
+08/30/2021 16:23:41 - INFO - __main__ - Step 17542: {'lr': 0.00048651962070667197, 'samples': 3368064, 'steps': 17541, 'loss/train': 1.7502667903900146}
+08/30/2021 16:23:41 - INFO - __main__ - Step 17543: {'lr': 0.00048651790159988563, 'samples': 3368256, 'steps': 17542, 'loss/train': 0.8552508354187012}
+08/30/2021 16:23:42 - INFO - __main__ - Step 17544: {'lr': 0.0004865161823865279, 'samples': 3368448, 'steps': 17543, 'loss/train': 1.3909282684326172}
+08/30/2021 16:23:42 - INFO - __main__ - Step 17545: {'lr': 0.0004865144630665996, 'samples': 3368640, 'steps': 17544, 'loss/train': 1.7435178756713867}
+08/30/2021 16:23:44 - INFO - __main__ - Step 17546: {'lr': 0.0004865127436401016, 'samples': 3368832, 'steps': 17545, 'loss/train': 1.4475579261779785}
+08/30/2021 16:23:44 - INFO - __main__ - Step 17547: {'lr': 0.00048651102410703464, 'samples': 3369024, 'steps': 17546, 'loss/train': 1.4390286207199097}
+08/30/2021 16:23:44 - INFO - __main__ - Step 17548: {'lr': 0.00048650930446739936, 'samples': 3369216, 'steps': 17547, 'loss/train': 1.4975570440292358}
+08/30/2021 16:23:45 - INFO - __main__ - Step 17549: {'lr': 0.00048650758472119666, 'samples': 3369408, 'steps': 17548, 'loss/train': 1.786547303199768}
+08/30/2021 16:23:45 - INFO - __main__ - Step 17550: {'lr': 0.0004865058648684273, 'samples': 3369600, 'steps': 17549, 'loss/train': 1.720345139503479}
+08/30/2021 16:23:46 - INFO - __main__ - Step 17551: {'lr': 0.00048650414490909207, 'samples': 3369792, 'steps': 17550, 'loss/train': 1.4965839385986328}
+08/30/2021 16:23:47 - INFO - __main__ - Step 17552: {'lr': 0.00048650242484319175, 'samples': 3369984, 'steps': 17551, 'loss/train': 1.6356937885284424}
+08/30/2021 16:23:47 - INFO - __main__ - Step 17553: {'lr': 0.000486500704670727, 'samples': 3370176, 'steps': 17552, 'loss/train': 1.6092661619186401}
+08/30/2021 16:23:48 - INFO - __main__ - Step 17554: {'lr': 0.0004864989843916987, 'samples': 3370368, 'steps': 17553, 'loss/train': 1.1740132570266724}
+08/30/2021 16:23:48 - INFO - __main__ - Step 17555: {'lr': 0.0004864972640061077, 'samples': 3370560, 'steps': 17554, 'loss/train': 1.7153794765472412}
+08/30/2021 16:23:49 - INFO - __main__ - Step 17556: {'lr': 0.00048649554351395453, 'samples': 3370752, 'steps': 17555, 'loss/train': 2.135126829147339}
+08/30/2021 16:23:50 - INFO - __main__ - Step 17557: {'lr': 0.00048649382291524024, 'samples': 3370944, 'steps': 17556, 'loss/train': 1.6388752460479736}
+08/30/2021 16:23:50 - INFO - __main__ - Step 17558: {'lr': 0.0004864921022099654, 'samples': 3371136, 'steps': 17557, 'loss/train': 1.245361328125}
+08/30/2021 16:23:51 - INFO - __main__ - Step 17559: {'lr': 0.00048649038139813097, 'samples': 3371328, 'steps': 17558, 'loss/train': 0.5165625214576721}
+08/30/2021 16:23:51 - INFO - __main__ - Step 17560: {'lr': 0.00048648866047973756, 'samples': 3371520, 'steps': 17559, 'loss/train': 1.52119779586792}
+08/30/2021 16:23:52 - INFO - __main__ - Step 17561: {'lr': 0.000486486939454786, 'samples': 3371712, 'steps': 17560, 'loss/train': 1.4700878858566284}
+08/30/2021 16:23:53 - INFO - __main__ - Step 17562: {'lr': 0.0004864852183232771, 'samples': 3371904, 'steps': 17561, 'loss/train': 1.4670953750610352}
+08/30/2021 16:23:53 - INFO - __main__ - Step 17563: {'lr': 0.0004864834970852116, 'samples': 3372096, 'steps': 17562, 'loss/train': 1.9046157598495483}
+08/30/2021 16:23:54 - INFO - __main__ - Step 17564: {'lr': 0.0004864817757405903, 'samples': 3372288, 'steps': 17563, 'loss/train': 0.10192663967609406}
+08/30/2021 16:23:54 - INFO - __main__ - Step 17565: {'lr': 0.0004864800542894139, 'samples': 3372480, 'steps': 17564, 'loss/train': 1.6360749006271362}
+08/30/2021 16:23:56 - INFO - __main__ - Step 17566: {'lr': 0.0004864783327316833, 'samples': 3372672, 'steps': 17565, 'loss/train': 2.031972885131836}
+08/30/2021 16:23:57 - INFO - __main__ - Step 17567: {'lr': 0.0004864766110673992, 'samples': 3372864, 'steps': 17566, 'loss/train': 1.7081667184829712}
+08/30/2021 16:23:57 - INFO - __main__ - Step 17568: {'lr': 0.00048647488929656237, 'samples': 3373056, 'steps': 17567, 'loss/train': 1.829378604888916}
+08/30/2021 16:23:57 - INFO - __main__ - Step 17569: {'lr': 0.00048647316741917365, 'samples': 3373248, 'steps': 17568, 'loss/train': 0.38812997937202454}
+08/30/2021 16:23:58 - INFO - __main__ - Step 17570: {'lr': 0.0004864714454352337, 'samples': 3373440, 'steps': 17569, 'loss/train': 1.7490671873092651}
+08/30/2021 16:23:59 - INFO - __main__ - Step 17571: {'lr': 0.00048646972334474343, 'samples': 3373632, 'steps': 17570, 'loss/train': 2.08906888961792}
+08/30/2021 16:24:00 - INFO - __main__ - Step 17572: {'lr': 0.0004864680011477035, 'samples': 3373824, 'steps': 17571, 'loss/train': 1.4270910024642944}
+08/30/2021 16:24:00 - INFO - __main__ - Step 17573: {'lr': 0.00048646627884411475, 'samples': 3374016, 'steps': 17572, 'loss/train': 1.5729337930679321}
+08/30/2021 16:24:01 - INFO - __main__ - Step 17574: {'lr': 0.00048646455643397803, 'samples': 3374208, 'steps': 17573, 'loss/train': 1.4936065673828125}
+08/30/2021 16:24:01 - INFO - __main__ - Step 17575: {'lr': 0.0004864628339172939, 'samples': 3374400, 'steps': 17574, 'loss/train': 2.0495150089263916}
+08/30/2021 16:24:01 - INFO - __main__ - Step 17576: {'lr': 0.00048646111129406336, 'samples': 3374592, 'steps': 17575, 'loss/train': 1.1590380668640137}
+08/30/2021 16:24:03 - INFO - __main__ - Step 17577: {'lr': 0.00048645938856428704, 'samples': 3374784, 'steps': 17576, 'loss/train': 1.0573232173919678}
+08/30/2021 16:24:03 - INFO - __main__ - Step 17578: {'lr': 0.0004864576657279658, 'samples': 3374976, 'steps': 17577, 'loss/train': 1.2430789470672607}
+08/30/2021 16:24:03 - INFO - __main__ - Step 17579: {'lr': 0.0004864559427851003, 'samples': 3375168, 'steps': 17578, 'loss/train': 1.875684142112732}
+08/30/2021 16:24:04 - INFO - __main__ - Step 17580: {'lr': 0.0004864542197356915, 'samples': 3375360, 'steps': 17579, 'loss/train': 1.5721102952957153}
+08/30/2021 16:24:04 - INFO - __main__ - Step 17581: {'lr': 0.00048645249657974007, 'samples': 3375552, 'steps': 17580, 'loss/train': 1.1137334108352661}
+08/30/2021 16:24:06 - INFO - __main__ - Step 17582: {'lr': 0.00048645077331724675, 'samples': 3375744, 'steps': 17581, 'loss/train': 2.0492448806762695}
+08/30/2021 16:24:06 - INFO - __main__ - Step 17583: {'lr': 0.00048644904994821236, 'samples': 3375936, 'steps': 17582, 'loss/train': 1.9140725135803223}
+08/30/2021 16:24:06 - INFO - __main__ - Step 17584: {'lr': 0.0004864473264726377, 'samples': 3376128, 'steps': 17583, 'loss/train': 1.8759957551956177}
+08/30/2021 16:24:07 - INFO - __main__ - Step 17585: {'lr': 0.00048644560289052354, 'samples': 3376320, 'steps': 17584, 'loss/train': 1.6567912101745605}
+08/30/2021 16:24:07 - INFO - __main__ - Step 17586: {'lr': 0.0004864438792018706, 'samples': 3376512, 'steps': 17585, 'loss/train': 1.447975993156433}
+08/30/2021 16:24:08 - INFO - __main__ - Step 17587: {'lr': 0.0004864421554066797, 'samples': 3376704, 'steps': 17586, 'loss/train': 1.0083297491073608}
+08/30/2021 16:24:09 - INFO - __main__ - Step 17588: {'lr': 0.00048644043150495165, 'samples': 3376896, 'steps': 17587, 'loss/train': 1.7974839210510254}
+08/30/2021 16:24:10 - INFO - __main__ - Step 17589: {'lr': 0.00048643870749668717, 'samples': 3377088, 'steps': 17588, 'loss/train': 1.3072870969772339}
+08/30/2021 16:24:10 - INFO - __main__ - Step 17590: {'lr': 0.000486436983381887, 'samples': 3377280, 'steps': 17589, 'loss/train': 1.7835060358047485}
+08/30/2021 16:24:11 - INFO - __main__ - Step 17591: {'lr': 0.0004864352591605521, 'samples': 3377472, 'steps': 17590, 'loss/train': 1.905362844467163}
+08/30/2021 16:24:11 - INFO - __main__ - Step 17592: {'lr': 0.00048643353483268306, 'samples': 3377664, 'steps': 17591, 'loss/train': 1.7080096006393433}
+08/30/2021 16:24:13 - INFO - __main__ - Step 17593: {'lr': 0.00048643181039828066, 'samples': 3377856, 'steps': 17592, 'loss/train': 1.9489187002182007}
+08/30/2021 16:24:13 - INFO - __main__ - Step 17594: {'lr': 0.00048643008585734575, 'samples': 3378048, 'steps': 17593, 'loss/train': 0.11998263746500015}
+08/30/2021 16:24:14 - INFO - __main__ - Step 17595: {'lr': 0.00048642836120987913, 'samples': 3378240, 'steps': 17594, 'loss/train': 2.023465156555176}
+08/30/2021 16:24:14 - INFO - __main__ - Step 17596: {'lr': 0.0004864266364558816, 'samples': 3378432, 'steps': 17595, 'loss/train': 1.4682003259658813}
+08/30/2021 16:24:14 - INFO - __main__ - Step 17597: {'lr': 0.00048642491159535373, 'samples': 3378624, 'steps': 17596, 'loss/train': 1.3541736602783203}
+08/30/2021 16:24:15 - INFO - __main__ - Step 17598: {'lr': 0.0004864231866282965, 'samples': 3378816, 'steps': 17597, 'loss/train': 2.111245632171631}
+08/30/2021 16:24:16 - INFO - __main__ - Step 17599: {'lr': 0.0004864214615547107, 'samples': 3379008, 'steps': 17598, 'loss/train': 1.268403172492981}
+08/30/2021 16:24:16 - INFO - __main__ - Step 17600: {'lr': 0.000486419736374597, 'samples': 3379200, 'steps': 17599, 'loss/train': 1.5935360193252563}
+08/30/2021 16:24:17 - INFO - __main__ - Step 17601: {'lr': 0.0004864180110879562, 'samples': 3379392, 'steps': 17600, 'loss/train': 1.3745697736740112}
+08/30/2021 16:24:17 - INFO - __main__ - Step 17602: {'lr': 0.00048641628569478916, 'samples': 3379584, 'steps': 17601, 'loss/train': 1.301063895225525}
+08/30/2021 16:24:18 - INFO - __main__ - Step 17603: {'lr': 0.00048641456019509643, 'samples': 3379776, 'steps': 17602, 'loss/train': 1.8030059337615967}
+08/30/2021 16:24:19 - INFO - __main__ - Step 17604: {'lr': 0.0004864128345888791, 'samples': 3379968, 'steps': 17603, 'loss/train': 1.6895872354507446}
+08/30/2021 16:24:20 - INFO - __main__ - Step 17605: {'lr': 0.0004864111088761377, 'samples': 3380160, 'steps': 17604, 'loss/train': 1.3598532676696777}
+08/30/2021 16:24:20 - INFO - __main__ - Step 17606: {'lr': 0.00048640938305687315, 'samples': 3380352, 'steps': 17605, 'loss/train': 0.15379035472869873}
+08/30/2021 16:24:21 - INFO - __main__ - Step 17607: {'lr': 0.00048640765713108615, 'samples': 3380544, 'steps': 17606, 'loss/train': 1.9393595457077026}
+08/30/2021 16:24:21 - INFO - __main__ - Step 17608: {'lr': 0.00048640593109877754, 'samples': 3380736, 'steps': 17607, 'loss/train': 0.3218410015106201}
+08/30/2021 16:24:21 - INFO - __main__ - Step 17609: {'lr': 0.00048640420495994806, 'samples': 3380928, 'steps': 17608, 'loss/train': 1.898372769355774}
+08/30/2021 16:24:23 - INFO - __main__ - Step 17610: {'lr': 0.0004864024787145985, 'samples': 3381120, 'steps': 17609, 'loss/train': 1.7394880056381226}
+08/30/2021 16:24:23 - INFO - __main__ - Step 17611: {'lr': 0.00048640075236272963, 'samples': 3381312, 'steps': 17610, 'loss/train': 1.656727910041809}
+08/30/2021 16:24:24 - INFO - __main__ - Step 17612: {'lr': 0.00048639902590434214, 'samples': 3381504, 'steps': 17611, 'loss/train': 1.1785953044891357}
+08/30/2021 16:24:24 - INFO - __main__ - Step 17613: {'lr': 0.000486397299339437, 'samples': 3381696, 'steps': 17612, 'loss/train': 1.621639609336853}
+08/30/2021 16:24:24 - INFO - __main__ - Step 17614: {'lr': 0.0004863955726680149, 'samples': 3381888, 'steps': 17613, 'loss/train': 1.469756007194519}
+08/30/2021 16:24:26 - INFO - __main__ - Step 17615: {'lr': 0.0004863938458900765, 'samples': 3382080, 'steps': 17614, 'loss/train': 1.897817611694336}
+08/30/2021 16:24:27 - INFO - __main__ - Step 17616: {'lr': 0.0004863921190056227, 'samples': 3382272, 'steps': 17615, 'loss/train': 1.5590382814407349}
+08/30/2021 16:24:27 - INFO - __main__ - Step 17617: {'lr': 0.0004863903920146544, 'samples': 3382464, 'steps': 17616, 'loss/train': 1.265742540359497}
+08/30/2021 16:24:28 - INFO - __main__ - Step 17618: {'lr': 0.00048638866491717214, 'samples': 3382656, 'steps': 17617, 'loss/train': 2.574831247329712}
+08/30/2021 16:24:28 - INFO - __main__ - Step 17619: {'lr': 0.00048638693771317675, 'samples': 3382848, 'steps': 17618, 'loss/train': 1.6485815048217773}
+08/30/2021 16:24:28 - INFO - __main__ - Step 17620: {'lr': 0.0004863852104026691, 'samples': 3383040, 'steps': 17619, 'loss/train': 1.6006711721420288}
+08/30/2021 16:24:30 - INFO - __main__ - Step 17621: {'lr': 0.00048638348298564996, 'samples': 3383232, 'steps': 17620, 'loss/train': 1.7198574542999268}
+08/30/2021 16:24:31 - INFO - __main__ - Step 17622: {'lr': 0.00048638175546212, 'samples': 3383424, 'steps': 17621, 'loss/train': 2.257721424102783}
+08/30/2021 16:24:31 - INFO - __main__ - Step 17623: {'lr': 0.00048638002783208013, 'samples': 3383616, 'steps': 17622, 'loss/train': 1.4844609498977661}
+08/30/2021 16:24:31 - INFO - __main__ - Step 17624: {'lr': 0.000486378300095531, 'samples': 3383808, 'steps': 17623, 'loss/train': 1.7797285318374634}
+08/30/2021 16:24:32 - INFO - __main__ - Step 17625: {'lr': 0.0004863765722524735, 'samples': 3384000, 'steps': 17624, 'loss/train': 1.936982274055481}
+08/30/2021 16:24:33 - INFO - __main__ - Step 17626: {'lr': 0.0004863748443029083, 'samples': 3384192, 'steps': 17625, 'loss/train': 1.141573190689087}
+08/30/2021 16:24:34 - INFO - __main__ - Step 17627: {'lr': 0.00048637311624683634, 'samples': 3384384, 'steps': 17626, 'loss/train': 1.7004591226577759}
+08/30/2021 16:24:34 - INFO - __main__ - Step 17628: {'lr': 0.0004863713880842583, 'samples': 3384576, 'steps': 17627, 'loss/train': 1.8569802045822144}
+08/30/2021 16:24:34 - INFO - __main__ - Step 17629: {'lr': 0.0004863696598151749, 'samples': 3384768, 'steps': 17628, 'loss/train': 1.8134541511535645}
+08/30/2021 16:24:35 - INFO - __main__ - Step 17630: {'lr': 0.00048636793143958695, 'samples': 3384960, 'steps': 17629, 'loss/train': 1.7280523777008057}
+08/30/2021 16:24:35 - INFO - __main__ - Step 17631: {'lr': 0.00048636620295749533, 'samples': 3385152, 'steps': 17630, 'loss/train': 1.4507464170455933}
+08/30/2021 16:24:36 - INFO - __main__ - Step 17632: {'lr': 0.00048636447436890075, 'samples': 3385344, 'steps': 17631, 'loss/train': 1.9362410306930542}
+08/30/2021 16:24:37 - INFO - __main__ - Step 17633: {'lr': 0.0004863627456738039, 'samples': 3385536, 'steps': 17632, 'loss/train': 2.50399112701416}
+08/30/2021 16:24:37 - INFO - __main__ - Step 17634: {'lr': 0.00048636101687220566, 'samples': 3385728, 'steps': 17633, 'loss/train': 0.6674114465713501}
+08/30/2021 16:24:38 - INFO - __main__ - Step 17635: {'lr': 0.0004863592879641069, 'samples': 3385920, 'steps': 17634, 'loss/train': 2.0079925060272217}
+08/30/2021 16:24:38 - INFO - __main__ - Step 17636: {'lr': 0.0004863575589495082, 'samples': 3386112, 'steps': 17635, 'loss/train': 1.5300225019454956}
+08/30/2021 16:24:40 - INFO - __main__ - Step 17637: {'lr': 0.00048635582982841047, 'samples': 3386304, 'steps': 17636, 'loss/train': 2.4551563262939453}
+08/30/2021 16:24:41 - INFO - __main__ - Step 17638: {'lr': 0.0004863541006008144, 'samples': 3386496, 'steps': 17637, 'loss/train': 1.9068865776062012}
+08/30/2021 16:24:41 - INFO - __main__ - Step 17639: {'lr': 0.0004863523712667209, 'samples': 3386688, 'steps': 17638, 'loss/train': 1.994493007659912}
+08/30/2021 16:24:41 - INFO - __main__ - Step 17640: {'lr': 0.00048635064182613063, 'samples': 3386880, 'steps': 17639, 'loss/train': 1.995773196220398}
+08/30/2021 16:24:42 - INFO - __main__ - Step 17641: {'lr': 0.00048634891227904435, 'samples': 3387072, 'steps': 17640, 'loss/train': 1.3929442167282104}
+08/30/2021 16:24:43 - INFO - __main__ - Step 17642: {'lr': 0.00048634718262546297, 'samples': 3387264, 'steps': 17641, 'loss/train': 1.0950262546539307}
+08/30/2021 16:24:44 - INFO - __main__ - Step 17643: {'lr': 0.0004863454528653872, 'samples': 3387456, 'steps': 17642, 'loss/train': 1.6616877317428589}
+08/30/2021 16:24:44 - INFO - __main__ - Step 17644: {'lr': 0.0004863437229988178, 'samples': 3387648, 'steps': 17643, 'loss/train': 1.6589170694351196}
+08/30/2021 16:24:44 - INFO - __main__ - Step 17645: {'lr': 0.00048634199302575554, 'samples': 3387840, 'steps': 17644, 'loss/train': 1.4650273323059082}
+08/30/2021 16:24:45 - INFO - __main__ - Step 17646: {'lr': 0.00048634026294620125, 'samples': 3388032, 'steps': 17645, 'loss/train': 1.4868621826171875}
+08/30/2021 16:24:46 - INFO - __main__ - Step 17647: {'lr': 0.00048633853276015566, 'samples': 3388224, 'steps': 17646, 'loss/train': 2.0076630115509033}
+08/30/2021 16:24:47 - INFO - __main__ - Step 17648: {'lr': 0.00048633680246761956, 'samples': 3388416, 'steps': 17647, 'loss/train': 1.830798864364624}
+08/30/2021 16:24:47 - INFO - __main__ - Step 17649: {'lr': 0.00048633507206859383, 'samples': 3388608, 'steps': 17648, 'loss/train': 2.4800283908843994}
+08/30/2021 16:24:47 - INFO - __main__ - Step 17650: {'lr': 0.00048633334156307907, 'samples': 3388800, 'steps': 17649, 'loss/train': 1.6565618515014648}
+08/30/2021 16:24:48 - INFO - __main__ - Step 17651: {'lr': 0.0004863316109510762, 'samples': 3388992, 'steps': 17650, 'loss/train': 1.6478811502456665}
+08/30/2021 16:24:49 - INFO - __main__ - Step 17652: {'lr': 0.00048632988023258596, 'samples': 3389184, 'steps': 17651, 'loss/train': 1.6498517990112305}
+08/30/2021 16:24:50 - INFO - __main__ - Step 17653: {'lr': 0.00048632814940760907, 'samples': 3389376, 'steps': 17652, 'loss/train': 1.7267106771469116}
+08/30/2021 16:24:50 - INFO - __main__ - Step 17654: {'lr': 0.00048632641847614645, 'samples': 3389568, 'steps': 17653, 'loss/train': 1.8104838132858276}
+08/30/2021 16:24:50 - INFO - __main__ - Step 17655: {'lr': 0.0004863246874381987, 'samples': 3389760, 'steps': 17654, 'loss/train': 0.7106810808181763}
+08/30/2021 16:24:51 - INFO - __main__ - Step 17656: {'lr': 0.00048632295629376675, 'samples': 3389952, 'steps': 17655, 'loss/train': 1.741978406906128}
+08/30/2021 16:24:52 - INFO - __main__ - Step 17657: {'lr': 0.00048632122504285133, 'samples': 3390144, 'steps': 17656, 'loss/train': 1.5844680070877075}
+08/30/2021 16:24:53 - INFO - __main__ - Step 17658: {'lr': 0.0004863194936854531, 'samples': 3390336, 'steps': 17657, 'loss/train': 1.7016268968582153}
+08/30/2021 16:24:53 - INFO - __main__ - Step 17659: {'lr': 0.0004863177622215731, 'samples': 3390528, 'steps': 17658, 'loss/train': 1.6292468309402466}
+08/30/2021 16:24:54 - INFO - __main__ - Step 17660: {'lr': 0.00048631603065121186, 'samples': 3390720, 'steps': 17659, 'loss/train': 1.6936275959014893}
+08/30/2021 16:24:54 - INFO - __main__ - Step 17661: {'lr': 0.00048631429897437033, 'samples': 3390912, 'steps': 17660, 'loss/train': 0.9331439733505249}
+08/30/2021 16:24:54 - INFO - __main__ - Step 17662: {'lr': 0.0004863125671910492, 'samples': 3391104, 'steps': 17661, 'loss/train': 6.046341896057129}
+08/30/2021 16:24:55 - INFO - __main__ - Step 17663: {'lr': 0.00048631083530124934, 'samples': 3391296, 'steps': 17662, 'loss/train': 1.7382398843765259}
+08/30/2021 16:24:56 - INFO - __main__ - Step 17664: {'lr': 0.00048630910330497133, 'samples': 3391488, 'steps': 17663, 'loss/train': 1.9881970882415771}
+08/30/2021 16:24:57 - INFO - __main__ - Step 17665: {'lr': 0.0004863073712022162, 'samples': 3391680, 'steps': 17664, 'loss/train': 1.7396708726882935}
+08/30/2021 16:24:57 - INFO - __main__ - Step 17666: {'lr': 0.00048630563899298453, 'samples': 3391872, 'steps': 17665, 'loss/train': 1.8456741571426392}
+08/30/2021 16:24:57 - INFO - __main__ - Step 17667: {'lr': 0.00048630390667727725, 'samples': 3392064, 'steps': 17666, 'loss/train': 1.488634467124939}
+08/30/2021 16:24:58 - INFO - __main__ - Step 17668: {'lr': 0.00048630217425509503, 'samples': 3392256, 'steps': 17667, 'loss/train': 1.8691930770874023}
+08/30/2021 16:24:59 - INFO - __main__ - Step 17669: {'lr': 0.00048630044172643874, 'samples': 3392448, 'steps': 17668, 'loss/train': 1.8067786693572998}
+08/30/2021 16:25:00 - INFO - __main__ - Step 17670: {'lr': 0.0004862987090913091, 'samples': 3392640, 'steps': 17669, 'loss/train': 1.7889330387115479}
+08/30/2021 16:25:00 - INFO - __main__ - Step 17671: {'lr': 0.0004862969763497069, 'samples': 3392832, 'steps': 17670, 'loss/train': 1.8399053812026978}
+08/30/2021 16:25:01 - INFO - __main__ - Step 17672: {'lr': 0.0004862952435016329, 'samples': 3393024, 'steps': 17671, 'loss/train': 1.7011256217956543}
+08/30/2021 16:25:01 - INFO - __main__ - Step 17673: {'lr': 0.00048629351054708795, 'samples': 3393216, 'steps': 17672, 'loss/train': 1.8765562772750854}
+08/30/2021 16:25:02 - INFO - __main__ - Step 17674: {'lr': 0.0004862917774860728, 'samples': 3393408, 'steps': 17673, 'loss/train': 0.143140971660614}
+08/30/2021 16:25:03 - INFO - __main__ - Step 17675: {'lr': 0.0004862900443185882, 'samples': 3393600, 'steps': 17674, 'loss/train': 0.4153665006160736}
+08/30/2021 16:25:03 - INFO - __main__ - Step 17676: {'lr': 0.00048628831104463496, 'samples': 3393792, 'steps': 17675, 'loss/train': 1.7494155168533325}
+08/30/2021 16:25:04 - INFO - __main__ - Step 17677: {'lr': 0.0004862865776642138, 'samples': 3393984, 'steps': 17676, 'loss/train': 1.814841389656067}
+08/30/2021 16:25:04 - INFO - __main__ - Step 17678: {'lr': 0.00048628484417732567, 'samples': 3394176, 'steps': 17677, 'loss/train': 1.5618295669555664}
+08/30/2021 16:25:06 - INFO - __main__ - Step 17679: {'lr': 0.00048628311058397113, 'samples': 3394368, 'steps': 17678, 'loss/train': 0.9141178727149963}
+08/30/2021 16:25:06 - INFO - __main__ - Step 17680: {'lr': 0.0004862813768841511, 'samples': 3394560, 'steps': 17679, 'loss/train': 1.3781713247299194}
+08/30/2021 16:25:06 - INFO - __main__ - Step 17681: {'lr': 0.0004862796430778663, 'samples': 3394752, 'steps': 17680, 'loss/train': 1.9683810472488403}
+08/30/2021 16:25:07 - INFO - __main__ - Step 17682: {'lr': 0.0004862779091651176, 'samples': 3394944, 'steps': 17681, 'loss/train': 2.0991878509521484}
+08/30/2021 16:25:07 - INFO - __main__ - Step 17683: {'lr': 0.0004862761751459057, 'samples': 3395136, 'steps': 17682, 'loss/train': 2.1489808559417725}
+08/30/2021 16:25:09 - INFO - __main__ - Step 17684: {'lr': 0.0004862744410202314, 'samples': 3395328, 'steps': 17683, 'loss/train': 1.5708801746368408}
+08/30/2021 16:25:09 - INFO - __main__ - Step 17685: {'lr': 0.00048627270678809544, 'samples': 3395520, 'steps': 17684, 'loss/train': 1.5949734449386597}
+08/30/2021 16:25:09 - INFO - __main__ - Step 17686: {'lr': 0.0004862709724494987, 'samples': 3395712, 'steps': 17685, 'loss/train': 1.6808841228485107}
+08/30/2021 16:25:10 - INFO - __main__ - Step 17687: {'lr': 0.0004862692380044419, 'samples': 3395904, 'steps': 17686, 'loss/train': 1.69366455078125}
+08/30/2021 16:25:10 - INFO - __main__ - Step 17688: {'lr': 0.0004862675034529258, 'samples': 3396096, 'steps': 17687, 'loss/train': 1.183712124824524}
+08/30/2021 16:25:12 - INFO - __main__ - Step 17689: {'lr': 0.0004862657687949512, 'samples': 3396288, 'steps': 17688, 'loss/train': 1.6497210264205933}
+08/30/2021 16:25:12 - INFO - __main__ - Step 17690: {'lr': 0.00048626403403051894, 'samples': 3396480, 'steps': 17689, 'loss/train': 1.8684240579605103}
+08/30/2021 16:25:13 - INFO - __main__ - Step 17691: {'lr': 0.00048626229915962974, 'samples': 3396672, 'steps': 17690, 'loss/train': 0.08506304025650024}
+08/30/2021 16:25:13 - INFO - __main__ - Step 17692: {'lr': 0.00048626056418228436, 'samples': 3396864, 'steps': 17691, 'loss/train': 2.190805435180664}
+08/30/2021 16:25:13 - INFO - __main__ - Step 17693: {'lr': 0.0004862588290984836, 'samples': 3397056, 'steps': 17692, 'loss/train': 1.9205013513565063}
+08/30/2021 16:25:14 - INFO - __main__ - Step 17694: {'lr': 0.0004862570939082283, 'samples': 3397248, 'steps': 17693, 'loss/train': 1.5624686479568481}
+08/30/2021 16:25:16 - INFO - __main__ - Step 17695: {'lr': 0.0004862553586115192, 'samples': 3397440, 'steps': 17694, 'loss/train': 1.7238426208496094}
+08/30/2021 16:25:16 - INFO - __main__ - Step 17696: {'lr': 0.00048625362320835707, 'samples': 3397632, 'steps': 17695, 'loss/train': 1.9803744554519653}
+08/30/2021 16:25:17 - INFO - __main__ - Step 17697: {'lr': 0.00048625188769874274, 'samples': 3397824, 'steps': 17696, 'loss/train': 1.5344154834747314}
+08/30/2021 16:25:17 - INFO - __main__ - Step 17698: {'lr': 0.0004862501520826769, 'samples': 3398016, 'steps': 17697, 'loss/train': 0.9941984415054321}
+08/30/2021 16:25:17 - INFO - __main__ - Step 17699: {'lr': 0.0004862484163601604, 'samples': 3398208, 'steps': 17698, 'loss/train': 0.08878421783447266}
+08/30/2021 16:25:19 - INFO - __main__ - Step 17700: {'lr': 0.000486246680531194, 'samples': 3398400, 'steps': 17699, 'loss/train': 1.453533411026001}
+08/30/2021 16:25:19 - INFO - __main__ - Step 17701: {'lr': 0.0004862449445957785, 'samples': 3398592, 'steps': 17700, 'loss/train': 1.675041913986206}
+08/30/2021 16:25:20 - INFO - __main__ - Step 17702: {'lr': 0.00048624320855391467, 'samples': 3398784, 'steps': 17701, 'loss/train': 1.457558035850525}
+08/30/2021 16:25:20 - INFO - __main__ - Step 17703: {'lr': 0.00048624147240560335, 'samples': 3398976, 'steps': 17702, 'loss/train': 1.555201530456543}
+08/30/2021 16:25:20 - INFO - __main__ - Step 17704: {'lr': 0.00048623973615084516, 'samples': 3399168, 'steps': 17703, 'loss/train': 1.6829344034194946}
+08/30/2021 16:25:22 - INFO - __main__ - Step 17705: {'lr': 0.0004862379997896411, 'samples': 3399360, 'steps': 17704, 'loss/train': 1.406872272491455}
+08/30/2021 16:25:22 - INFO - __main__ - Step 17706: {'lr': 0.0004862362633219918, 'samples': 3399552, 'steps': 17705, 'loss/train': 1.8866908550262451}
+08/30/2021 16:25:23 - INFO - __main__ - Step 17707: {'lr': 0.000486234526747898, 'samples': 3399744, 'steps': 17706, 'loss/train': 1.6731010675430298}
+08/30/2021 16:25:23 - INFO - __main__ - Step 17708: {'lr': 0.0004862327900673607, 'samples': 3399936, 'steps': 17707, 'loss/train': 2.172962188720703}
+08/30/2021 16:25:23 - INFO - __main__ - Step 17709: {'lr': 0.00048623105328038054, 'samples': 3400128, 'steps': 17708, 'loss/train': 1.1505485773086548}
+08/30/2021 16:25:25 - INFO - __main__ - Step 17710: {'lr': 0.0004862293163869582, 'samples': 3400320, 'steps': 17709, 'loss/train': 1.3676457405090332}
+08/30/2021 16:25:25 - INFO - __main__ - Step 17711: {'lr': 0.00048622757938709466, 'samples': 3400512, 'steps': 17710, 'loss/train': 0.37289196252822876}
+08/30/2021 16:25:26 - INFO - __main__ - Step 17712: {'lr': 0.0004862258422807906, 'samples': 3400704, 'steps': 17711, 'loss/train': 1.7323291301727295}
+08/30/2021 16:25:26 - INFO - __main__ - Step 17713: {'lr': 0.0004862241050680468, 'samples': 3400896, 'steps': 17712, 'loss/train': 2.248530864715576}
+08/30/2021 16:25:26 - INFO - __main__ - Step 17714: {'lr': 0.00048622236774886415, 'samples': 3401088, 'steps': 17713, 'loss/train': 0.818747878074646}
+08/30/2021 16:25:28 - INFO - __main__ - Step 17715: {'lr': 0.00048622063032324324, 'samples': 3401280, 'steps': 17714, 'loss/train': 1.9397470951080322}
+08/30/2021 16:25:28 - INFO - __main__ - Step 17716: {'lr': 0.000486218892791185, 'samples': 3401472, 'steps': 17715, 'loss/train': 3.122344493865967}
+08/30/2021 16:25:29 - INFO - __main__ - Step 17717: {'lr': 0.00048621715515269017, 'samples': 3401664, 'steps': 17716, 'loss/train': 1.2338253259658813}
+08/30/2021 16:25:29 - INFO - __main__ - Step 17718: {'lr': 0.0004862154174077595, 'samples': 3401856, 'steps': 17717, 'loss/train': 1.7586365938186646}
+08/30/2021 16:25:29 - INFO - __main__ - Step 17719: {'lr': 0.00048621367955639395, 'samples': 3402048, 'steps': 17718, 'loss/train': 1.6339696645736694}
+08/30/2021 16:25:31 - INFO - __main__ - Step 17720: {'lr': 0.00048621194159859403, 'samples': 3402240, 'steps': 17719, 'loss/train': 1.7732384204864502}
+08/30/2021 16:25:31 - INFO - __main__ - Step 17721: {'lr': 0.0004862102035343607, 'samples': 3402432, 'steps': 17720, 'loss/train': 2.0181620121002197}
+08/30/2021 16:25:32 - INFO - __main__ - Step 17722: {'lr': 0.0004862084653636947, 'samples': 3402624, 'steps': 17721, 'loss/train': 2.088188886642456}
+08/30/2021 16:25:32 - INFO - __main__ - Step 17723: {'lr': 0.00048620672708659675, 'samples': 3402816, 'steps': 17722, 'loss/train': 2.3807716369628906}
+08/30/2021 16:25:32 - INFO - __main__ - Step 17724: {'lr': 0.0004862049887030677, 'samples': 3403008, 'steps': 17723, 'loss/train': 1.3474513292312622}
+08/30/2021 16:25:34 - INFO - __main__ - Step 17725: {'lr': 0.0004862032502131084, 'samples': 3403200, 'steps': 17724, 'loss/train': 1.401879072189331}
+08/30/2021 16:25:34 - INFO - __main__ - Step 17726: {'lr': 0.00048620151161671955, 'samples': 3403392, 'steps': 17725, 'loss/train': 1.8139903545379639}
+08/30/2021 16:25:35 - INFO - __main__ - Step 17727: {'lr': 0.00048619977291390186, 'samples': 3403584, 'steps': 17726, 'loss/train': 2.8312020301818848}
+08/30/2021 16:25:35 - INFO - __main__ - Step 17728: {'lr': 0.00048619803410465624, 'samples': 3403776, 'steps': 17727, 'loss/train': 1.4648650884628296}
+08/30/2021 16:25:36 - INFO - __main__ - Step 17729: {'lr': 0.00048619629518898344, 'samples': 3403968, 'steps': 17728, 'loss/train': 2.1914825439453125}
+08/30/2021 16:25:36 - INFO - __main__ - Step 17730: {'lr': 0.00048619455616688426, 'samples': 3404160, 'steps': 17729, 'loss/train': 1.0621435642242432}
+08/30/2021 16:25:37 - INFO - __main__ - Step 17731: {'lr': 0.0004861928170383594, 'samples': 3404352, 'steps': 17730, 'loss/train': 1.7239242792129517}
+08/30/2021 16:25:38 - INFO - __main__ - Step 17732: {'lr': 0.0004861910778034098, 'samples': 3404544, 'steps': 17731, 'loss/train': 1.5181375741958618}
+08/30/2021 16:25:38 - INFO - __main__ - Step 17733: {'lr': 0.00048618933846203606, 'samples': 3404736, 'steps': 17732, 'loss/train': 1.8347440958023071}
+08/30/2021 16:25:38 - INFO - __main__ - Step 17734: {'lr': 0.00048618759901423905, 'samples': 3404928, 'steps': 17733, 'loss/train': 1.5305198431015015}
+08/30/2021 16:25:39 - INFO - __main__ - Step 17735: {'lr': 0.0004861858594600196, 'samples': 3405120, 'steps': 17734, 'loss/train': 1.7854728698730469}
+08/30/2021 16:25:40 - INFO - __main__ - Step 17736: {'lr': 0.0004861841197993784, 'samples': 3405312, 'steps': 17735, 'loss/train': 1.6548168659210205}
+08/30/2021 16:25:41 - INFO - __main__ - Step 17737: {'lr': 0.0004861823800323163, 'samples': 3405504, 'steps': 17736, 'loss/train': 1.2652748823165894}
+08/30/2021 16:25:41 - INFO - __main__ - Step 17738: {'lr': 0.00048618064015883405, 'samples': 3405696, 'steps': 17737, 'loss/train': 1.4637962579727173}
+08/30/2021 16:25:41 - INFO - __main__ - Step 17739: {'lr': 0.0004861789001789325, 'samples': 3405888, 'steps': 17738, 'loss/train': 1.7666879892349243}
+08/30/2021 16:25:42 - INFO - __main__ - Step 17740: {'lr': 0.00048617716009261236, 'samples': 3406080, 'steps': 17739, 'loss/train': 1.6758126020431519}
+08/30/2021 16:25:43 - INFO - __main__ - Step 17741: {'lr': 0.00048617541989987435, 'samples': 3406272, 'steps': 17740, 'loss/train': 1.4668971300125122}
+08/30/2021 16:25:44 - INFO - __main__ - Step 17742: {'lr': 0.00048617367960071946, 'samples': 3406464, 'steps': 17741, 'loss/train': 1.4784157276153564}
+08/30/2021 16:25:44 - INFO - __main__ - Step 17743: {'lr': 0.0004861719391951483, 'samples': 3406656, 'steps': 17742, 'loss/train': 1.6684218645095825}
+08/30/2021 16:25:44 - INFO - __main__ - Step 17744: {'lr': 0.0004861701986831617, 'samples': 3406848, 'steps': 17743, 'loss/train': 1.5837866067886353}
+08/30/2021 16:25:45 - INFO - __main__ - Step 17745: {'lr': 0.0004861684580647605, 'samples': 3407040, 'steps': 17744, 'loss/train': 1.8455150127410889}
+08/30/2021 16:25:47 - INFO - __main__ - Step 17746: {'lr': 0.0004861667173399453, 'samples': 3407232, 'steps': 17745, 'loss/train': 1.2570794820785522}
+08/30/2021 16:25:48 - INFO - __main__ - Step 17747: {'lr': 0.0004861649765087172, 'samples': 3407424, 'steps': 17746, 'loss/train': 2.085454225540161}
+08/30/2021 16:25:48 - INFO - __main__ - Step 17748: {'lr': 0.0004861632355710767, 'samples': 3407616, 'steps': 17747, 'loss/train': 1.643376350402832}
+08/30/2021 16:25:48 - INFO - __main__ - Step 17749: {'lr': 0.00048616149452702473, 'samples': 3407808, 'steps': 17748, 'loss/train': 2.5802743434906006}
+08/30/2021 16:25:49 - INFO - __main__ - Step 17750: {'lr': 0.00048615975337656204, 'samples': 3408000, 'steps': 17749, 'loss/train': 1.4473512172698975}
+08/30/2021 16:25:49 - INFO - __main__ - Step 17751: {'lr': 0.00048615801211968936, 'samples': 3408192, 'steps': 17750, 'loss/train': 1.7644591331481934}
+08/30/2021 16:25:51 - INFO - __main__ - Step 17752: {'lr': 0.00048615627075640754, 'samples': 3408384, 'steps': 17751, 'loss/train': 1.8071231842041016}
+08/30/2021 16:25:51 - INFO - __main__ - Step 17753: {'lr': 0.00048615452928671746, 'samples': 3408576, 'steps': 17752, 'loss/train': 2.0351507663726807}
+08/30/2021 16:25:51 - INFO - __main__ - Step 17754: {'lr': 0.00048615278771061966, 'samples': 3408768, 'steps': 17753, 'loss/train': 0.9494560360908508}
+08/30/2021 16:25:52 - INFO - __main__ - Step 17755: {'lr': 0.0004861510460281151, 'samples': 3408960, 'steps': 17754, 'loss/train': 6.22068977355957}
+08/30/2021 16:25:52 - INFO - __main__ - Step 17756: {'lr': 0.0004861493042392045, 'samples': 3409152, 'steps': 17755, 'loss/train': 2.4171478748321533}
+08/30/2021 16:25:54 - INFO - __main__ - Step 17757: {'lr': 0.00048614756234388866, 'samples': 3409344, 'steps': 17756, 'loss/train': 1.8834068775177002}
+08/30/2021 16:25:54 - INFO - __main__ - Step 17758: {'lr': 0.00048614582034216844, 'samples': 3409536, 'steps': 17757, 'loss/train': 1.4243308305740356}
+08/30/2021 16:25:54 - INFO - __main__ - Step 17759: {'lr': 0.0004861440782340445, 'samples': 3409728, 'steps': 17758, 'loss/train': 1.5687111616134644}
+08/30/2021 16:25:55 - INFO - __main__ - Step 17760: {'lr': 0.0004861423360195177, 'samples': 3409920, 'steps': 17759, 'loss/train': 1.073167324066162}
+08/30/2021 16:25:55 - INFO - __main__ - Step 17761: {'lr': 0.0004861405936985888, 'samples': 3410112, 'steps': 17760, 'loss/train': 1.616040587425232}
+08/30/2021 16:25:57 - INFO - __main__ - Step 17762: {'lr': 0.0004861388512712586, 'samples': 3410304, 'steps': 17761, 'loss/train': 1.6898744106292725}
+08/30/2021 16:25:57 - INFO - __main__ - Step 17763: {'lr': 0.0004861371087375279, 'samples': 3410496, 'steps': 17762, 'loss/train': 2.581831693649292}
+08/30/2021 16:25:58 - INFO - __main__ - Step 17764: {'lr': 0.0004861353660973974, 'samples': 3410688, 'steps': 17763, 'loss/train': 1.838334560394287}
+08/30/2021 16:25:58 - INFO - __main__ - Step 17765: {'lr': 0.00048613362335086797, 'samples': 3410880, 'steps': 17764, 'loss/train': 1.6511179208755493}
+08/30/2021 16:25:58 - INFO - __main__ - Step 17766: {'lr': 0.00048613188049794045, 'samples': 3411072, 'steps': 17765, 'loss/train': 1.6235308647155762}
+08/30/2021 16:25:59 - INFO - __main__ - Step 17767: {'lr': 0.00048613013753861546, 'samples': 3411264, 'steps': 17766, 'loss/train': 1.9086244106292725}
+08/30/2021 16:26:00 - INFO - __main__ - Step 17768: {'lr': 0.0004861283944728939, 'samples': 3411456, 'steps': 17767, 'loss/train': 1.6346663236618042}
+08/30/2021 16:26:00 - INFO - __main__ - Step 17769: {'lr': 0.0004861266513007765, 'samples': 3411648, 'steps': 17768, 'loss/train': 1.9003173112869263}
+08/30/2021 16:26:01 - INFO - __main__ - Step 17770: {'lr': 0.00048612490802226415, 'samples': 3411840, 'steps': 17769, 'loss/train': 1.941716194152832}
+08/30/2021 16:26:01 - INFO - __main__ - Step 17771: {'lr': 0.0004861231646373575, 'samples': 3412032, 'steps': 17770, 'loss/train': 2.2606074810028076}
+08/30/2021 16:26:02 - INFO - __main__ - Step 17772: {'lr': 0.0004861214211460574, 'samples': 3412224, 'steps': 17771, 'loss/train': 1.241268515586853}
+08/30/2021 16:26:03 - INFO - __main__ - Step 17773: {'lr': 0.00048611967754836466, 'samples': 3412416, 'steps': 17772, 'loss/train': 1.577620506286621}
+08/30/2021 16:26:03 - INFO - __main__ - Step 17774: {'lr': 0.00048611793384428006, 'samples': 3412608, 'steps': 17773, 'loss/train': 1.2940549850463867}
+08/30/2021 16:26:04 - INFO - __main__ - Step 17775: {'lr': 0.00048611619003380426, 'samples': 3412800, 'steps': 17774, 'loss/train': 1.457544207572937}
+08/30/2021 16:26:04 - INFO - __main__ - Step 17776: {'lr': 0.0004861144461169382, 'samples': 3412992, 'steps': 17775, 'loss/train': 1.60025155544281}
+08/30/2021 16:26:04 - INFO - __main__ - Step 17777: {'lr': 0.00048611270209368264, 'samples': 3413184, 'steps': 17776, 'loss/train': 1.5212907791137695}
+08/30/2021 16:26:06 - INFO - __main__ - Step 17778: {'lr': 0.0004861109579640384, 'samples': 3413376, 'steps': 17777, 'loss/train': 1.9214051961898804}
+08/30/2021 16:26:07 - INFO - __main__ - Step 17779: {'lr': 0.0004861092137280061, 'samples': 3413568, 'steps': 17778, 'loss/train': 1.3035353422164917}
+08/30/2021 16:26:07 - INFO - __main__ - Step 17780: {'lr': 0.00048610746938558666, 'samples': 3413760, 'steps': 17779, 'loss/train': 1.7488807439804077}
+08/30/2021 16:26:07 - INFO - __main__ - Step 17781: {'lr': 0.0004861057249367808, 'samples': 3413952, 'steps': 17780, 'loss/train': 0.3444135785102844}
+08/30/2021 16:26:08 - INFO - __main__ - Step 17782: {'lr': 0.00048610398038158943, 'samples': 3414144, 'steps': 17781, 'loss/train': 0.3180020749568939}
+08/30/2021 16:26:08 - INFO - __main__ - Step 17783: {'lr': 0.00048610223572001315, 'samples': 3414336, 'steps': 17782, 'loss/train': 1.867020606994629}
+08/30/2021 16:26:09 - INFO - __main__ - Step 17784: {'lr': 0.0004861004909520529, 'samples': 3414528, 'steps': 17783, 'loss/train': 1.1937071084976196}
+08/30/2021 16:26:10 - INFO - __main__ - Step 17785: {'lr': 0.00048609874607770945, 'samples': 3414720, 'steps': 17784, 'loss/train': 2.2578063011169434}
+08/30/2021 16:26:10 - INFO - __main__ - Step 17786: {'lr': 0.0004860970010969835, 'samples': 3414912, 'steps': 17785, 'loss/train': 1.9325724840164185}
+08/30/2021 16:26:11 - INFO - __main__ - Step 17787: {'lr': 0.0004860952560098759, 'samples': 3415104, 'steps': 17786, 'loss/train': 2.0252583026885986}
+08/30/2021 16:26:11 - INFO - __main__ - Step 17788: {'lr': 0.0004860935108163874, 'samples': 3415296, 'steps': 17787, 'loss/train': 1.694702386856079}
+08/30/2021 16:26:12 - INFO - __main__ - Step 17789: {'lr': 0.0004860917655165188, 'samples': 3415488, 'steps': 17788, 'loss/train': 1.336488962173462}
+08/30/2021 16:26:13 - INFO - __main__ - Step 17790: {'lr': 0.00048609002011027093, 'samples': 3415680, 'steps': 17789, 'loss/train': 1.6751717329025269}
+08/30/2021 16:26:13 - INFO - __main__ - Step 17791: {'lr': 0.0004860882745976445, 'samples': 3415872, 'steps': 17790, 'loss/train': 1.6190760135650635}
+08/30/2021 16:26:14 - INFO - __main__ - Step 17792: {'lr': 0.00048608652897864034, 'samples': 3416064, 'steps': 17791, 'loss/train': 2.0488550662994385}
+08/30/2021 16:26:14 - INFO - __main__ - Step 17793: {'lr': 0.0004860847832532593, 'samples': 3416256, 'steps': 17792, 'loss/train': 1.6386748552322388}
+08/30/2021 16:26:15 - INFO - __main__ - Step 17794: {'lr': 0.00048608303742150204, 'samples': 3416448, 'steps': 17793, 'loss/train': 1.3178482055664062}
+08/30/2021 16:26:16 - INFO - __main__ - Step 17795: {'lr': 0.0004860812914833694, 'samples': 3416640, 'steps': 17794, 'loss/train': 1.6896860599517822}
+08/30/2021 16:26:16 - INFO - __main__ - Step 17796: {'lr': 0.00048607954543886225, 'samples': 3416832, 'steps': 17795, 'loss/train': 1.564070701599121}
+08/30/2021 16:26:17 - INFO - __main__ - Step 17797: {'lr': 0.00048607779928798125, 'samples': 3417024, 'steps': 17796, 'loss/train': 1.4566324949264526}
+08/30/2021 16:26:17 - INFO - __main__ - Step 17798: {'lr': 0.0004860760530307272, 'samples': 3417216, 'steps': 17797, 'loss/train': 2.0166878700256348}
+08/30/2021 16:26:19 - INFO - __main__ - Step 17799: {'lr': 0.00048607430666710097, 'samples': 3417408, 'steps': 17798, 'loss/train': 2.282393217086792}
+08/30/2021 16:26:19 - INFO - __main__ - Step 17800: {'lr': 0.00048607256019710327, 'samples': 3417600, 'steps': 17799, 'loss/train': 1.350229024887085}
+08/30/2021 16:26:19 - INFO - __main__ - Step 17801: {'lr': 0.0004860708136207349, 'samples': 3417792, 'steps': 17800, 'loss/train': 1.3988617658615112}
+08/30/2021 16:26:20 - INFO - __main__ - Step 17802: {'lr': 0.0004860690669379967, 'samples': 3417984, 'steps': 17801, 'loss/train': 1.5887693166732788}
+08/30/2021 16:26:20 - INFO - __main__ - Step 17803: {'lr': 0.00048606732014888946, 'samples': 3418176, 'steps': 17802, 'loss/train': 0.10701005905866623}
+08/30/2021 16:26:23 - INFO - __main__ - Step 17804: {'lr': 0.0004860655732534138, 'samples': 3418368, 'steps': 17803, 'loss/train': 1.9331892728805542}
+08/30/2021 16:26:23 - INFO - __main__ - Step 17805: {'lr': 0.00048606382625157075, 'samples': 3418560, 'steps': 17804, 'loss/train': 1.2968308925628662}
+08/30/2021 16:26:23 - INFO - __main__ - Step 17806: {'lr': 0.00048606207914336097, 'samples': 3418752, 'steps': 17805, 'loss/train': 0.0958833396434784}
+08/30/2021 16:26:24 - INFO - __main__ - Step 17807: {'lr': 0.0004860603319287853, 'samples': 3418944, 'steps': 17806, 'loss/train': 1.3931435346603394}
+08/30/2021 16:26:24 - INFO - __main__ - Step 17808: {'lr': 0.0004860585846078444, 'samples': 3419136, 'steps': 17807, 'loss/train': 2.507514238357544}
+08/30/2021 16:26:24 - INFO - __main__ - Step 17809: {'lr': 0.00048605683718053915, 'samples': 3419328, 'steps': 17808, 'loss/train': 1.7126376628875732}
+08/30/2021 16:26:25 - INFO - __main__ - Step 17810: {'lr': 0.0004860550896468704, 'samples': 3419520, 'steps': 17809, 'loss/train': 1.714233636856079}
+08/30/2021 16:26:26 - INFO - __main__ - Step 17811: {'lr': 0.00048605334200683883, 'samples': 3419712, 'steps': 17810, 'loss/train': 1.740059733390808}
+08/30/2021 16:26:27 - INFO - __main__ - Step 17812: {'lr': 0.0004860515942604452, 'samples': 3419904, 'steps': 17811, 'loss/train': 1.2822657823562622}
+08/30/2021 16:26:27 - INFO - __main__ - Step 17813: {'lr': 0.00048604984640769047, 'samples': 3420096, 'steps': 17812, 'loss/train': 1.1805046796798706}
+08/30/2021 16:26:27 - INFO - __main__ - Step 17814: {'lr': 0.00048604809844857524, 'samples': 3420288, 'steps': 17813, 'loss/train': 3.061659097671509}
+08/30/2021 16:26:28 - INFO - __main__ - Step 17815: {'lr': 0.0004860463503831004, 'samples': 3420480, 'steps': 17814, 'loss/train': 1.9420151710510254}
+08/30/2021 16:26:29 - INFO - __main__ - Step 17816: {'lr': 0.0004860446022112668, 'samples': 3420672, 'steps': 17815, 'loss/train': 1.388025164604187}
+08/30/2021 16:26:30 - INFO - __main__ - Step 17817: {'lr': 0.00048604285393307503, 'samples': 3420864, 'steps': 17816, 'loss/train': 1.9964635372161865}
+08/30/2021 16:26:30 - INFO - __main__ - Step 17818: {'lr': 0.000486041105548526, 'samples': 3421056, 'steps': 17817, 'loss/train': 0.955362856388092}
+08/30/2021 16:26:30 - INFO - __main__ - Step 17819: {'lr': 0.00048603935705762057, 'samples': 3421248, 'steps': 17818, 'loss/train': 1.5427345037460327}
+08/30/2021 16:26:31 - INFO - __main__ - Step 17820: {'lr': 0.0004860376084603594, 'samples': 3421440, 'steps': 17819, 'loss/train': 1.8449162244796753}
+08/30/2021 16:26:32 - INFO - __main__ - Step 17821: {'lr': 0.00048603585975674334, 'samples': 3421632, 'steps': 17820, 'loss/train': 1.494202971458435}
+08/30/2021 16:26:33 - INFO - __main__ - Step 17822: {'lr': 0.0004860341109467732, 'samples': 3421824, 'steps': 17821, 'loss/train': 1.6064958572387695}
+08/30/2021 16:26:33 - INFO - __main__ - Step 17823: {'lr': 0.00048603236203044963, 'samples': 3422016, 'steps': 17822, 'loss/train': 1.8284484148025513}
+08/30/2021 16:26:34 - INFO - __main__ - Step 17824: {'lr': 0.00048603061300777365, 'samples': 3422208, 'steps': 17823, 'loss/train': 1.8893921375274658}
+08/30/2021 16:26:34 - INFO - __main__ - Step 17825: {'lr': 0.0004860288638787458, 'samples': 3422400, 'steps': 17824, 'loss/train': 1.239871621131897}
+08/30/2021 16:26:34 - INFO - __main__ - Step 17826: {'lr': 0.000486027114643367, 'samples': 3422592, 'steps': 17825, 'loss/train': 1.517728328704834}
+08/30/2021 16:26:36 - INFO - __main__ - Step 17827: {'lr': 0.0004860253653016381, 'samples': 3422784, 'steps': 17826, 'loss/train': 0.07044032216072083}
+08/30/2021 16:26:36 - INFO - __main__ - Step 17828: {'lr': 0.00048602361585355975, 'samples': 3422976, 'steps': 17827, 'loss/train': 1.964586853981018}
+08/30/2021 16:26:36 - INFO - __main__ - Step 17829: {'lr': 0.0004860218662991328, 'samples': 3423168, 'steps': 17828, 'loss/train': 1.9995909929275513}
+08/30/2021 16:26:37 - INFO - __main__ - Step 17830: {'lr': 0.0004860201166383581, 'samples': 3423360, 'steps': 17829, 'loss/train': 1.5352898836135864}
+08/30/2021 16:26:37 - INFO - __main__ - Step 17831: {'lr': 0.00048601836687123636, 'samples': 3423552, 'steps': 17830, 'loss/train': 1.1319940090179443}
+08/30/2021 16:26:39 - INFO - __main__ - Step 17832: {'lr': 0.00048601661699776834, 'samples': 3423744, 'steps': 17831, 'loss/train': 1.645721197128296}
+08/30/2021 16:26:39 - INFO - __main__ - Step 17833: {'lr': 0.0004860148670179549, 'samples': 3423936, 'steps': 17832, 'loss/train': 1.8793554306030273}
+08/30/2021 16:26:40 - INFO - __main__ - Step 17834: {'lr': 0.0004860131169317968, 'samples': 3424128, 'steps': 17833, 'loss/train': 2.120166778564453}
+08/30/2021 16:26:40 - INFO - __main__ - Step 17835: {'lr': 0.0004860113667392948, 'samples': 3424320, 'steps': 17834, 'loss/train': 0.14136287569999695}
+08/30/2021 16:26:40 - INFO - __main__ - Step 17836: {'lr': 0.00048600961644044977, 'samples': 3424512, 'steps': 17835, 'loss/train': 1.4645096063613892}
+08/30/2021 16:26:42 - INFO - __main__ - Step 17837: {'lr': 0.0004860078660352625, 'samples': 3424704, 'steps': 17836, 'loss/train': 0.9518241286277771}
+08/30/2021 16:26:42 - INFO - __main__ - Step 17838: {'lr': 0.0004860061155237336, 'samples': 3424896, 'steps': 17837, 'loss/train': 1.8600260019302368}
+08/30/2021 16:26:43 - INFO - __main__ - Step 17839: {'lr': 0.0004860043649058641, 'samples': 3425088, 'steps': 17838, 'loss/train': 1.0962424278259277}
+08/30/2021 16:26:43 - INFO - __main__ - Step 17840: {'lr': 0.00048600261418165456, 'samples': 3425280, 'steps': 17839, 'loss/train': 1.6016703844070435}
+08/30/2021 16:26:44 - INFO - __main__ - Step 17841: {'lr': 0.00048600086335110593, 'samples': 3425472, 'steps': 17840, 'loss/train': 1.4285876750946045}
+08/30/2021 16:26:45 - INFO - __main__ - Step 17842: {'lr': 0.000485999112414219, 'samples': 3425664, 'steps': 17841, 'loss/train': 1.2479573488235474}
+08/30/2021 16:26:46 - INFO - __main__ - Step 17843: {'lr': 0.0004859973613709945, 'samples': 3425856, 'steps': 17842, 'loss/train': 1.5413181781768799}
+08/30/2021 16:26:46 - INFO - __main__ - Step 17844: {'lr': 0.0004859956102214332, 'samples': 3426048, 'steps': 17843, 'loss/train': 1.8095704317092896}
+08/30/2021 16:26:46 - INFO - __main__ - Step 17845: {'lr': 0.00048599385896553595, 'samples': 3426240, 'steps': 17844, 'loss/train': 1.3200632333755493}
+08/30/2021 16:26:47 - INFO - __main__ - Step 17846: {'lr': 0.0004859921076033034, 'samples': 3426432, 'steps': 17845, 'loss/train': 2.3370091915130615}
+08/30/2021 16:26:48 - INFO - __main__ - Step 17847: {'lr': 0.00048599035613473656, 'samples': 3426624, 'steps': 17846, 'loss/train': 1.3648688793182373}
+08/30/2021 16:26:49 - INFO - __main__ - Step 17848: {'lr': 0.0004859886045598361, 'samples': 3426816, 'steps': 17847, 'loss/train': 1.6096360683441162}
+08/30/2021 16:26:49 - INFO - __main__ - Step 17849: {'lr': 0.0004859868528786028, 'samples': 3427008, 'steps': 17848, 'loss/train': 0.8248007297515869}
+08/30/2021 16:26:50 - INFO - __main__ - Step 17850: {'lr': 0.0004859851010910374, 'samples': 3427200, 'steps': 17849, 'loss/train': 2.027937889099121}
+08/30/2021 16:26:50 - INFO - __main__ - Step 17851: {'lr': 0.0004859833491971409, 'samples': 3427392, 'steps': 17850, 'loss/train': 2.022143602371216}
+08/30/2021 16:26:50 - INFO - __main__ - Step 17852: {'lr': 0.0004859815971969138, 'samples': 3427584, 'steps': 17851, 'loss/train': 1.8337533473968506}
+08/30/2021 16:26:52 - INFO - __main__ - Step 17853: {'lr': 0.0004859798450903571, 'samples': 3427776, 'steps': 17852, 'loss/train': 2.1065738201141357}
+08/30/2021 16:26:52 - INFO - __main__ - Step 17854: {'lr': 0.00048597809287747153, 'samples': 3427968, 'steps': 17853, 'loss/train': 1.8997302055358887}
+08/30/2021 16:26:53 - INFO - __main__ - Step 17855: {'lr': 0.0004859763405582579, 'samples': 3428160, 'steps': 17854, 'loss/train': 1.2824190855026245}
+08/30/2021 16:26:53 - INFO - __main__ - Step 17856: {'lr': 0.00048597458813271686, 'samples': 3428352, 'steps': 17855, 'loss/train': 1.6876394748687744}
+08/30/2021 16:26:53 - INFO - __main__ - Step 17857: {'lr': 0.0004859728356008494, 'samples': 3428544, 'steps': 17856, 'loss/train': 1.5995029211044312}
+08/30/2021 16:26:55 - INFO - __main__ - Step 17858: {'lr': 0.00048597108296265625, 'samples': 3428736, 'steps': 17857, 'loss/train': 0.4544801414012909}
+08/30/2021 16:26:56 - INFO - __main__ - Step 17859: {'lr': 0.00048596933021813815, 'samples': 3428928, 'steps': 17858, 'loss/train': 1.3313671350479126}
+08/30/2021 16:26:56 - INFO - __main__ - Step 17860: {'lr': 0.0004859675773672959, 'samples': 3429120, 'steps': 17859, 'loss/train': 1.9243196249008179}
+08/30/2021 16:26:57 - INFO - __main__ - Step 17861: {'lr': 0.00048596582441013026, 'samples': 3429312, 'steps': 17860, 'loss/train': 1.6134884357452393}
+08/30/2021 16:26:57 - INFO - __main__ - Step 17862: {'lr': 0.0004859640713466421, 'samples': 3429504, 'steps': 17861, 'loss/train': 1.5414246320724487}
+08/30/2021 16:26:59 - INFO - __main__ - Step 17863: {'lr': 0.0004859623181768321, 'samples': 3429696, 'steps': 17862, 'loss/train': 1.0997945070266724}
+08/30/2021 16:26:59 - INFO - __main__ - Step 17864: {'lr': 0.0004859605649007012, 'samples': 3429888, 'steps': 17863, 'loss/train': 0.7047229409217834}
+08/30/2021 16:26:59 - INFO - __main__ - Step 17865: {'lr': 0.00048595881151825015, 'samples': 3430080, 'steps': 17864, 'loss/train': 1.7464097738265991}
+08/30/2021 16:27:00 - INFO - __main__ - Step 17866: {'lr': 0.00048595705802947963, 'samples': 3430272, 'steps': 17865, 'loss/train': 1.578861117362976}
+08/30/2021 16:27:00 - INFO - __main__ - Step 17867: {'lr': 0.0004859553044343905, 'samples': 3430464, 'steps': 17866, 'loss/train': 1.4532793760299683}
+08/30/2021 16:27:00 - INFO - __main__ - Step 17868: {'lr': 0.0004859535507329836, 'samples': 3430656, 'steps': 17867, 'loss/train': 2.017756938934326}
+08/30/2021 16:27:02 - INFO - __main__ - Step 17869: {'lr': 0.0004859517969252596, 'samples': 3430848, 'steps': 17868, 'loss/train': 1.7452476024627686}
+08/30/2021 16:27:02 - INFO - __main__ - Step 17870: {'lr': 0.0004859500430112194, 'samples': 3431040, 'steps': 17869, 'loss/train': 1.0578614473342896}
+08/30/2021 16:27:03 - INFO - __main__ - Step 17871: {'lr': 0.0004859482889908637, 'samples': 3431232, 'steps': 17870, 'loss/train': 1.5763440132141113}
+08/30/2021 16:27:03 - INFO - __main__ - Step 17872: {'lr': 0.0004859465348641934, 'samples': 3431424, 'steps': 17871, 'loss/train': 1.7885918617248535}
+08/30/2021 16:27:03 - INFO - __main__ - Step 17873: {'lr': 0.0004859447806312093, 'samples': 3431616, 'steps': 17872, 'loss/train': 1.7694075107574463}
+08/30/2021 16:27:05 - INFO - __main__ - Step 17874: {'lr': 0.000485943026291912, 'samples': 3431808, 'steps': 17873, 'loss/train': 1.6329407691955566}
+08/30/2021 16:27:05 - INFO - __main__ - Step 17875: {'lr': 0.0004859412718463025, 'samples': 3432000, 'steps': 17874, 'loss/train': 0.8633098602294922}
+08/30/2021 16:27:06 - INFO - __main__ - Step 17876: {'lr': 0.00048593951729438144, 'samples': 3432192, 'steps': 17875, 'loss/train': 1.3485416173934937}
+08/30/2021 16:27:06 - INFO - __main__ - Step 17877: {'lr': 0.0004859377626361497, 'samples': 3432384, 'steps': 17876, 'loss/train': 1.8221259117126465}
+08/30/2021 16:27:06 - INFO - __main__ - Step 17878: {'lr': 0.00048593600787160806, 'samples': 3432576, 'steps': 17877, 'loss/train': 0.9330003261566162}
+08/30/2021 16:27:08 - INFO - __main__ - Step 17879: {'lr': 0.0004859342530007572, 'samples': 3432768, 'steps': 17878, 'loss/train': 1.376065969467163}
+08/30/2021 16:27:08 - INFO - __main__ - Step 17880: {'lr': 0.0004859324980235982, 'samples': 3432960, 'steps': 17879, 'loss/train': 1.5842962265014648}
+08/30/2021 16:27:09 - INFO - __main__ - Step 17881: {'lr': 0.0004859307429401315, 'samples': 3433152, 'steps': 17880, 'loss/train': 1.2794156074523926}
+08/30/2021 16:27:09 - INFO - __main__ - Step 17882: {'lr': 0.0004859289877503581, 'samples': 3433344, 'steps': 17881, 'loss/train': 1.737648367881775}
+08/30/2021 16:27:09 - INFO - __main__ - Step 17883: {'lr': 0.00048592723245427874, 'samples': 3433536, 'steps': 17882, 'loss/train': 0.8127500414848328}
+08/30/2021 16:27:11 - INFO - __main__ - Step 17884: {'lr': 0.00048592547705189414, 'samples': 3433728, 'steps': 17883, 'loss/train': 1.9721065759658813}
+08/30/2021 16:27:11 - INFO - __main__ - Step 17885: {'lr': 0.00048592372154320526, 'samples': 3433920, 'steps': 17884, 'loss/train': 1.3245036602020264}
+08/30/2021 16:27:12 - INFO - __main__ - Step 17886: {'lr': 0.0004859219659282127, 'samples': 3434112, 'steps': 17885, 'loss/train': 2.183135986328125}
+08/30/2021 16:27:12 - INFO - __main__ - Step 17887: {'lr': 0.00048592021020691745, 'samples': 3434304, 'steps': 17886, 'loss/train': 1.2190138101577759}
+08/30/2021 16:27:12 - INFO - __main__ - Step 17888: {'lr': 0.00048591845437932014, 'samples': 3434496, 'steps': 17887, 'loss/train': 1.4049583673477173}
+08/30/2021 16:27:14 - INFO - __main__ - Step 17889: {'lr': 0.0004859166984454216, 'samples': 3434688, 'steps': 17888, 'loss/train': 1.5307166576385498}
+08/30/2021 16:27:14 - INFO - __main__ - Step 17890: {'lr': 0.0004859149424052226, 'samples': 3434880, 'steps': 17889, 'loss/train': 1.7316594123840332}
+08/30/2021 16:27:15 - INFO - __main__ - Step 17891: {'lr': 0.00048591318625872403, 'samples': 3435072, 'steps': 17890, 'loss/train': 2.1398332118988037}
+08/30/2021 16:27:15 - INFO - __main__ - Step 17892: {'lr': 0.00048591143000592665, 'samples': 3435264, 'steps': 17891, 'loss/train': 1.8469187021255493}
+08/30/2021 16:27:15 - INFO - __main__ - Step 17893: {'lr': 0.00048590967364683116, 'samples': 3435456, 'steps': 17892, 'loss/train': 2.175302505493164}
+08/30/2021 16:27:17 - INFO - __main__ - Step 17894: {'lr': 0.0004859079171814384, 'samples': 3435648, 'steps': 17893, 'loss/train': 1.7110624313354492}
+08/30/2021 16:27:17 - INFO - __main__ - Step 17895: {'lr': 0.00048590616060974917, 'samples': 3435840, 'steps': 17894, 'loss/train': 0.8588742017745972}
+08/30/2021 16:27:18 - INFO - __main__ - Step 17896: {'lr': 0.00048590440393176434, 'samples': 3436032, 'steps': 17895, 'loss/train': 1.4952541589736938}
+08/30/2021 16:27:18 - INFO - __main__ - Step 17897: {'lr': 0.00048590264714748455, 'samples': 3436224, 'steps': 17896, 'loss/train': 1.6051567792892456}
+08/30/2021 16:27:18 - INFO - __main__ - Step 17898: {'lr': 0.0004859008902569107, 'samples': 3436416, 'steps': 17897, 'loss/train': 1.8908735513687134}
+08/30/2021 16:27:20 - INFO - __main__ - Step 17899: {'lr': 0.00048589913326004355, 'samples': 3436608, 'steps': 17898, 'loss/train': 1.6623704433441162}
+08/30/2021 16:27:20 - INFO - __main__ - Step 17900: {'lr': 0.0004858973761568839, 'samples': 3436800, 'steps': 17899, 'loss/train': 1.1768349409103394}
+08/30/2021 16:27:21 - INFO - __main__ - Step 17901: {'lr': 0.0004858956189474325, 'samples': 3436992, 'steps': 17900, 'loss/train': 1.343118667602539}
+08/30/2021 16:27:21 - INFO - __main__ - Step 17902: {'lr': 0.0004858938616316902, 'samples': 3437184, 'steps': 17901, 'loss/train': 3.308218240737915}
+08/30/2021 16:27:21 - INFO - __main__ - Step 17903: {'lr': 0.00048589210420965775, 'samples': 3437376, 'steps': 17902, 'loss/train': 1.6797643899917603}
+08/30/2021 16:27:22 - INFO - __main__ - Step 17904: {'lr': 0.0004858903466813359, 'samples': 3437568, 'steps': 17903, 'loss/train': 1.4640237092971802}
+08/30/2021 16:27:23 - INFO - __main__ - Step 17905: {'lr': 0.0004858885890467256, 'samples': 3437760, 'steps': 17904, 'loss/train': 0.6652421355247498}
+08/30/2021 16:27:24 - INFO - __main__ - Step 17906: {'lr': 0.00048588683130582755, 'samples': 3437952, 'steps': 17905, 'loss/train': 1.5127453804016113}
+08/30/2021 16:27:24 - INFO - __main__ - Step 17907: {'lr': 0.00048588507345864246, 'samples': 3438144, 'steps': 17906, 'loss/train': 1.1763780117034912}
+08/30/2021 16:27:24 - INFO - __main__ - Step 17908: {'lr': 0.00048588331550517125, 'samples': 3438336, 'steps': 17907, 'loss/train': 1.3862305879592896}
+08/30/2021 16:27:25 - INFO - __main__ - Step 17909: {'lr': 0.0004858815574454146, 'samples': 3438528, 'steps': 17908, 'loss/train': 1.5857625007629395}
+08/30/2021 16:27:27 - INFO - __main__ - Step 17910: {'lr': 0.0004858797992793734, 'samples': 3438720, 'steps': 17909, 'loss/train': 1.6279613971710205}
+08/30/2021 16:27:27 - INFO - __main__ - Step 17911: {'lr': 0.0004858780410070484, 'samples': 3438912, 'steps': 17910, 'loss/train': 2.0002217292785645}
+08/30/2021 16:27:28 - INFO - __main__ - Step 17912: {'lr': 0.0004858762826284404, 'samples': 3439104, 'steps': 17911, 'loss/train': 1.3232227563858032}
+08/30/2021 16:27:28 - INFO - __main__ - Step 17913: {'lr': 0.00048587452414355014, 'samples': 3439296, 'steps': 17912, 'loss/train': 1.5202692747116089}
+08/30/2021 16:27:28 - INFO - __main__ - Step 17914: {'lr': 0.00048587276555237853, 'samples': 3439488, 'steps': 17913, 'loss/train': 1.5702459812164307}
+08/30/2021 16:27:30 - INFO - __main__ - Step 17915: {'lr': 0.00048587100685492626, 'samples': 3439680, 'steps': 17914, 'loss/train': 1.5571792125701904}
+08/30/2021 16:27:30 - INFO - __main__ - Step 17916: {'lr': 0.00048586924805119416, 'samples': 3439872, 'steps': 17915, 'loss/train': 1.0138022899627686}
+08/30/2021 16:27:31 - INFO - __main__ - Step 17917: {'lr': 0.00048586748914118303, 'samples': 3440064, 'steps': 17916, 'loss/train': 1.2218353748321533}
+08/30/2021 16:27:31 - INFO - __main__ - Step 17918: {'lr': 0.0004858657301248936, 'samples': 3440256, 'steps': 17917, 'loss/train': 1.5009742975234985}
+08/30/2021 16:27:32 - INFO - __main__ - Step 17919: {'lr': 0.00048586397100232673, 'samples': 3440448, 'steps': 17918, 'loss/train': 1.6131455898284912}
+08/30/2021 16:27:33 - INFO - __main__ - Step 17920: {'lr': 0.00048586221177348323, 'samples': 3440640, 'steps': 17919, 'loss/train': 1.9276503324508667}
+08/30/2021 16:27:33 - INFO - __main__ - Step 17921: {'lr': 0.00048586045243836386, 'samples': 3440832, 'steps': 17920, 'loss/train': 1.802316427230835}
+08/30/2021 16:27:34 - INFO - __main__ - Step 17922: {'lr': 0.0004858586929969693, 'samples': 3441024, 'steps': 17921, 'loss/train': 1.4100080728530884}
+08/30/2021 16:27:34 - INFO - __main__ - Step 17923: {'lr': 0.0004858569334493006, 'samples': 3441216, 'steps': 17922, 'loss/train': 1.6916251182556152}
+08/30/2021 16:27:34 - INFO - __main__ - Step 17924: {'lr': 0.0004858551737953583, 'samples': 3441408, 'steps': 17923, 'loss/train': 1.9449329376220703}
+08/30/2021 16:27:36 - INFO - __main__ - Step 17925: {'lr': 0.00048585341403514337, 'samples': 3441600, 'steps': 17924, 'loss/train': 2.312624931335449}
+08/30/2021 16:27:36 - INFO - __main__ - Step 17926: {'lr': 0.0004858516541686565, 'samples': 3441792, 'steps': 17925, 'loss/train': 1.7189046144485474}
+08/30/2021 16:27:37 - INFO - __main__ - Step 17927: {'lr': 0.0004858498941958985, 'samples': 3441984, 'steps': 17926, 'loss/train': 1.7091323137283325}
+08/30/2021 16:27:37 - INFO - __main__ - Step 17928: {'lr': 0.00048584813411687016, 'samples': 3442176, 'steps': 17927, 'loss/train': 1.7522549629211426}
+08/30/2021 16:27:37 - INFO - __main__ - Step 17929: {'lr': 0.00048584637393157235, 'samples': 3442368, 'steps': 17928, 'loss/train': 2.142777442932129}
+08/30/2021 16:27:39 - INFO - __main__ - Step 17930: {'lr': 0.00048584461364000576, 'samples': 3442560, 'steps': 17929, 'loss/train': 1.5607608556747437}
+08/30/2021 16:27:40 - INFO - __main__ - Step 17931: {'lr': 0.00048584285324217125, 'samples': 3442752, 'steps': 17930, 'loss/train': 0.613991379737854}
+08/30/2021 16:27:40 - INFO - __main__ - Step 17932: {'lr': 0.00048584109273806954, 'samples': 3442944, 'steps': 17931, 'loss/train': 1.3197829723358154}
+08/30/2021 16:27:40 - INFO - __main__ - Step 17933: {'lr': 0.00048583933212770154, 'samples': 3443136, 'steps': 17932, 'loss/train': 1.585553765296936}
+08/30/2021 16:27:41 - INFO - __main__ - Step 17934: {'lr': 0.00048583757141106796, 'samples': 3443328, 'steps': 17933, 'loss/train': 1.2175897359848022}
+08/30/2021 16:27:42 - INFO - __main__ - Step 17935: {'lr': 0.00048583581058816956, 'samples': 3443520, 'steps': 17934, 'loss/train': 1.8148592710494995}
+08/30/2021 16:27:42 - INFO - __main__ - Step 17936: {'lr': 0.00048583404965900725, 'samples': 3443712, 'steps': 17935, 'loss/train': 1.5685232877731323}
+08/30/2021 16:27:43 - INFO - __main__ - Step 17937: {'lr': 0.0004858322886235817, 'samples': 3443904, 'steps': 17936, 'loss/train': 1.5733325481414795}
+08/30/2021 16:27:43 - INFO - __main__ - Step 17938: {'lr': 0.0004858305274818938, 'samples': 3444096, 'steps': 17937, 'loss/train': 1.5058397054672241}
+08/30/2021 16:27:44 - INFO - __main__ - Step 17939: {'lr': 0.0004858287662339443, 'samples': 3444288, 'steps': 17938, 'loss/train': 1.559350609779358}
+08/30/2021 16:27:45 - INFO - __main__ - Step 17940: {'lr': 0.00048582700487973397, 'samples': 3444480, 'steps': 17939, 'loss/train': 1.7616230249404907}
+08/30/2021 16:27:45 - INFO - __main__ - Step 17941: {'lr': 0.00048582524341926365, 'samples': 3444672, 'steps': 17940, 'loss/train': 1.6359294652938843}
+08/30/2021 16:27:46 - INFO - __main__ - Step 17942: {'lr': 0.0004858234818525341, 'samples': 3444864, 'steps': 17941, 'loss/train': 1.1140216588974}
+08/30/2021 16:27:46 - INFO - __main__ - Step 17943: {'lr': 0.0004858217201795462, 'samples': 3445056, 'steps': 17942, 'loss/train': 1.5846662521362305}
+08/30/2021 16:27:46 - INFO - __main__ - Step 17944: {'lr': 0.0004858199584003006, 'samples': 3445248, 'steps': 17943, 'loss/train': 1.5004762411117554}
+08/30/2021 16:27:47 - INFO - __main__ - Step 17945: {'lr': 0.00048581819651479814, 'samples': 3445440, 'steps': 17944, 'loss/train': 1.7346022129058838}
+08/30/2021 16:27:48 - INFO - __main__ - Step 17946: {'lr': 0.0004858164345230397, 'samples': 3445632, 'steps': 17945, 'loss/train': 1.4551098346710205}
+08/30/2021 16:27:49 - INFO - __main__ - Step 17947: {'lr': 0.000485814672425026, 'samples': 3445824, 'steps': 17946, 'loss/train': 1.748676061630249}
+08/30/2021 16:27:49 - INFO - __main__ - Step 17948: {'lr': 0.0004858129102207578, 'samples': 3446016, 'steps': 17947, 'loss/train': 1.8068292140960693}
+08/30/2021 16:27:50 - INFO - __main__ - Step 17949: {'lr': 0.0004858111479102359, 'samples': 3446208, 'steps': 17948, 'loss/train': 1.6488761901855469}
+08/30/2021 16:27:50 - INFO - __main__ - Step 17950: {'lr': 0.00048580938549346134, 'samples': 3446400, 'steps': 17949, 'loss/train': 1.5202116966247559}
+08/30/2021 16:27:51 - INFO - __main__ - Step 17951: {'lr': 0.00048580762297043456, 'samples': 3446592, 'steps': 17950, 'loss/train': 1.6269984245300293}
+08/30/2021 16:27:52 - INFO - __main__ - Step 17952: {'lr': 0.00048580586034115646, 'samples': 3446784, 'steps': 17951, 'loss/train': 0.8832659125328064}
+08/30/2021 16:27:52 - INFO - __main__ - Step 17953: {'lr': 0.000485804097605628, 'samples': 3446976, 'steps': 17952, 'loss/train': 0.5102223753929138}
+08/30/2021 16:27:53 - INFO - __main__ - Step 17954: {'lr': 0.00048580233476384975, 'samples': 3447168, 'steps': 17953, 'loss/train': 1.293516993522644}
+08/30/2021 16:27:53 - INFO - __main__ - Step 17955: {'lr': 0.0004858005718158227, 'samples': 3447360, 'steps': 17954, 'loss/train': 0.8091772794723511}
+08/30/2021 16:27:55 - INFO - __main__ - Step 17956: {'lr': 0.0004857988087615475, 'samples': 3447552, 'steps': 17955, 'loss/train': 1.6286166906356812}
+08/30/2021 16:27:55 - INFO - __main__ - Step 17957: {'lr': 0.000485797045601025, 'samples': 3447744, 'steps': 17956, 'loss/train': 1.5255802869796753}
+08/30/2021 16:27:55 - INFO - __main__ - Step 17958: {'lr': 0.000485795282334256, 'samples': 3447936, 'steps': 17957, 'loss/train': 0.8993553519248962}
+08/30/2021 16:27:56 - INFO - __main__ - Step 17959: {'lr': 0.00048579351896124127, 'samples': 3448128, 'steps': 17958, 'loss/train': 1.3962647914886475}
+08/30/2021 16:27:56 - INFO - __main__ - Step 17960: {'lr': 0.0004857917554819816, 'samples': 3448320, 'steps': 17959, 'loss/train': 1.6764079332351685}
+08/30/2021 16:27:58 - INFO - __main__ - Step 17961: {'lr': 0.00048578999189647786, 'samples': 3448512, 'steps': 17960, 'loss/train': 1.4923226833343506}
+08/30/2021 16:27:59 - INFO - __main__ - Step 17962: {'lr': 0.00048578822820473074, 'samples': 3448704, 'steps': 17961, 'loss/train': 1.8143463134765625}
+08/30/2021 16:27:59 - INFO - __main__ - Step 17963: {'lr': 0.00048578646440674113, 'samples': 3448896, 'steps': 17962, 'loss/train': 2.056778907775879}
+08/30/2021 16:27:59 - INFO - __main__ - Step 17964: {'lr': 0.0004857847005025097, 'samples': 3449088, 'steps': 17963, 'loss/train': 1.4036874771118164}
+08/30/2021 16:28:00 - INFO - __main__ - Step 17965: {'lr': 0.0004857829364920374, 'samples': 3449280, 'steps': 17964, 'loss/train': 1.3317981958389282}
+08/30/2021 16:28:01 - INFO - __main__ - Step 17966: {'lr': 0.0004857811723753249, 'samples': 3449472, 'steps': 17965, 'loss/train': 1.7080540657043457}
+08/30/2021 16:28:02 - INFO - __main__ - Step 17967: {'lr': 0.00048577940815237305, 'samples': 3449664, 'steps': 17966, 'loss/train': 1.4190630912780762}
+08/30/2021 16:28:02 - INFO - __main__ - Step 17968: {'lr': 0.00048577764382318265, 'samples': 3449856, 'steps': 17967, 'loss/train': 1.4978206157684326}
+08/30/2021 16:28:02 - INFO - __main__ - Step 17969: {'lr': 0.0004857758793877545, 'samples': 3450048, 'steps': 17968, 'loss/train': 1.8247748613357544}
+08/30/2021 16:28:03 - INFO - __main__ - Step 17970: {'lr': 0.00048577411484608936, 'samples': 3450240, 'steps': 17969, 'loss/train': 1.8087624311447144}
+08/30/2021 16:28:04 - INFO - __main__ - Step 17971: {'lr': 0.000485772350198188, 'samples': 3450432, 'steps': 17970, 'loss/train': 1.5536245107650757}
+08/30/2021 16:28:05 - INFO - __main__ - Step 17972: {'lr': 0.00048577058544405126, 'samples': 3450624, 'steps': 17971, 'loss/train': 1.661061406135559}
+08/30/2021 16:28:05 - INFO - __main__ - Step 17973: {'lr': 0.00048576882058368, 'samples': 3450816, 'steps': 17972, 'loss/train': 1.5742443799972534}
+08/30/2021 16:28:05 - INFO - __main__ - Step 17974: {'lr': 0.0004857670556170749, 'samples': 3451008, 'steps': 17973, 'loss/train': 1.044863224029541}
+08/30/2021 16:28:06 - INFO - __main__ - Step 17975: {'lr': 0.0004857652905442368, 'samples': 3451200, 'steps': 17974, 'loss/train': 2.287400484085083}
+08/30/2021 16:28:07 - INFO - __main__ - Step 17976: {'lr': 0.0004857635253651665, 'samples': 3451392, 'steps': 17975, 'loss/train': 1.5925867557525635}
+08/30/2021 16:28:08 - INFO - __main__ - Step 17977: {'lr': 0.00048576176007986485, 'samples': 3451584, 'steps': 17976, 'loss/train': 1.464400053024292}
+08/30/2021 16:28:08 - INFO - __main__ - Step 17978: {'lr': 0.00048575999468833256, 'samples': 3451776, 'steps': 17977, 'loss/train': 1.465862512588501}
+08/30/2021 16:28:08 - INFO - __main__ - Step 17979: {'lr': 0.0004857582291905704, 'samples': 3451968, 'steps': 17978, 'loss/train': 1.49838387966156}
+08/30/2021 16:28:09 - INFO - __main__ - Step 17980: {'lr': 0.00048575646358657934, 'samples': 3452160, 'steps': 17979, 'loss/train': 1.0039933919906616}
+08/30/2021 16:28:10 - INFO - __main__ - Step 17981: {'lr': 0.00048575469787635997, 'samples': 3452352, 'steps': 17980, 'loss/train': 1.6469841003417969}
+08/30/2021 16:28:11 - INFO - __main__ - Step 17982: {'lr': 0.00048575293205991313, 'samples': 3452544, 'steps': 17981, 'loss/train': 1.6953777074813843}
+08/30/2021 16:28:11 - INFO - __main__ - Step 17983: {'lr': 0.0004857511661372397, 'samples': 3452736, 'steps': 17982, 'loss/train': 1.6324660778045654}
+08/30/2021 16:28:11 - INFO - __main__ - Step 17984: {'lr': 0.00048574940010834045, 'samples': 3452928, 'steps': 17983, 'loss/train': 1.3473966121673584}
+08/30/2021 16:28:12 - INFO - __main__ - Step 17985: {'lr': 0.0004857476339732161, 'samples': 3453120, 'steps': 17984, 'loss/train': 1.9128919839859009}
+08/30/2021 16:28:12 - INFO - __main__ - Step 17986: {'lr': 0.0004857458677318676, 'samples': 3453312, 'steps': 17985, 'loss/train': 1.7540589570999146}
+08/30/2021 16:28:14 - INFO - __main__ - Step 17987: {'lr': 0.0004857441013842956, 'samples': 3453504, 'steps': 17986, 'loss/train': 1.6961069107055664}
+08/30/2021 16:28:14 - INFO - __main__ - Step 17988: {'lr': 0.0004857423349305009, 'samples': 3453696, 'steps': 17987, 'loss/train': 1.6407495737075806}
+08/30/2021 16:28:15 - INFO - __main__ - Step 17989: {'lr': 0.00048574056837048443, 'samples': 3453888, 'steps': 17988, 'loss/train': 1.7343302965164185}
+08/30/2021 16:28:15 - INFO - __main__ - Step 17990: {'lr': 0.0004857388017042468, 'samples': 3454080, 'steps': 17989, 'loss/train': 0.266526997089386}
+08/30/2021 16:28:15 - INFO - __main__ - Step 17991: {'lr': 0.000485737034931789, 'samples': 3454272, 'steps': 17990, 'loss/train': 1.5119613409042358}
+08/30/2021 16:28:17 - INFO - __main__ - Step 17992: {'lr': 0.00048573526805311166, 'samples': 3454464, 'steps': 17991, 'loss/train': 1.3970911502838135}
+08/30/2021 16:28:17 - INFO - __main__ - Step 17993: {'lr': 0.0004857335010682157, 'samples': 3454656, 'steps': 17992, 'loss/train': 2.1763477325439453}
+08/30/2021 16:28:18 - INFO - __main__ - Step 17994: {'lr': 0.0004857317339771018, 'samples': 3454848, 'steps': 17993, 'loss/train': 5.6309027671813965}
+08/30/2021 16:28:18 - INFO - __main__ - Step 17995: {'lr': 0.0004857299667797709, 'samples': 3455040, 'steps': 17994, 'loss/train': 1.6603909730911255}
+08/30/2021 16:28:18 - INFO - __main__ - Step 17996: {'lr': 0.0004857281994762236, 'samples': 3455232, 'steps': 17995, 'loss/train': 1.3990861177444458}
+08/30/2021 16:28:20 - INFO - __main__ - Step 17997: {'lr': 0.00048572643206646097, 'samples': 3455424, 'steps': 17996, 'loss/train': 1.095388412475586}
+08/30/2021 16:28:21 - INFO - __main__ - Step 17998: {'lr': 0.0004857246645504835, 'samples': 3455616, 'steps': 17997, 'loss/train': 1.5710792541503906}
+08/30/2021 16:28:21 - INFO - __main__ - Step 17999: {'lr': 0.00048572289692829217, 'samples': 3455808, 'steps': 17998, 'loss/train': 1.4027560949325562}
+08/30/2021 16:28:21 - INFO - __main__ - Step 18000: {'lr': 0.00048572112919988776, 'samples': 3456000, 'steps': 17999, 'loss/train': 1.682323694229126}
+08/30/2021 16:28:22 - INFO - __main__ - Step 18001: {'lr': 0.00048571936136527106, 'samples': 3456192, 'steps': 18000, 'loss/train': 1.7628370523452759}
+08/30/2021 16:28:22 - INFO - __main__ - Step 18002: {'lr': 0.0004857175934244428, 'samples': 3456384, 'steps': 18001, 'loss/train': 1.5482879877090454}
+08/30/2021 16:28:23 - INFO - __main__ - Step 18003: {'lr': 0.0004857158253774039, 'samples': 3456576, 'steps': 18002, 'loss/train': 0.09714821726083755}
+08/30/2021 16:28:24 - INFO - __main__ - Step 18004: {'lr': 0.0004857140572241551, 'samples': 3456768, 'steps': 18003, 'loss/train': 0.06454353779554367}
+08/30/2021 16:28:25 - INFO - __main__ - Step 18005: {'lr': 0.00048571228896469713, 'samples': 3456960, 'steps': 18004, 'loss/train': 1.6359314918518066}
+08/30/2021 16:28:25 - INFO - __main__ - Step 18006: {'lr': 0.0004857105205990308, 'samples': 3457152, 'steps': 18005, 'loss/train': 1.7537561655044556}
+08/30/2021 16:28:26 - INFO - __main__ - Step 18007: {'lr': 0.00048570875212715706, 'samples': 3457344, 'steps': 18006, 'loss/train': 1.392996907234192}
+08/30/2021 16:28:26 - INFO - __main__ - Step 18008: {'lr': 0.0004857069835490765, 'samples': 3457536, 'steps': 18007, 'loss/train': 1.7586145401000977}
+08/30/2021 16:28:26 - INFO - __main__ - Step 18009: {'lr': 0.00048570521486479004, 'samples': 3457728, 'steps': 18008, 'loss/train': 2.623910903930664}
+08/30/2021 16:28:28 - INFO - __main__ - Step 18010: {'lr': 0.0004857034460742984, 'samples': 3457920, 'steps': 18009, 'loss/train': 1.8344008922576904}
+08/30/2021 16:28:29 - INFO - __main__ - Step 18011: {'lr': 0.0004857016771776025, 'samples': 3458112, 'steps': 18010, 'loss/train': 2.376192092895508}
+08/30/2021 16:28:29 - INFO - __main__ - Step 18012: {'lr': 0.000485699908174703, 'samples': 3458304, 'steps': 18011, 'loss/train': 2.1674773693084717}
+08/30/2021 16:28:29 - INFO - __main__ - Step 18013: {'lr': 0.0004856981390656008, 'samples': 3458496, 'steps': 18012, 'loss/train': 1.5568349361419678}
+08/30/2021 16:28:30 - INFO - __main__ - Step 18014: {'lr': 0.00048569636985029664, 'samples': 3458688, 'steps': 18013, 'loss/train': 2.163891077041626}
+08/30/2021 16:28:31 - INFO - __main__ - Step 18015: {'lr': 0.00048569460052879136, 'samples': 3458880, 'steps': 18014, 'loss/train': 1.916684627532959}
+08/30/2021 16:28:32 - INFO - __main__ - Step 18016: {'lr': 0.0004856928311010857, 'samples': 3459072, 'steps': 18015, 'loss/train': 1.7760971784591675}
+08/30/2021 16:28:32 - INFO - __main__ - Step 18017: {'lr': 0.00048569106156718045, 'samples': 3459264, 'steps': 18016, 'loss/train': 1.3841313123703003}
+08/30/2021 16:28:32 - INFO - __main__ - Step 18018: {'lr': 0.00048568929192707657, 'samples': 3459456, 'steps': 18017, 'loss/train': 1.5409024953842163}
+08/30/2021 16:28:33 - INFO - __main__ - Step 18019: {'lr': 0.0004856875221807746, 'samples': 3459648, 'steps': 18018, 'loss/train': 1.7263318300247192}
+08/30/2021 16:28:35 - INFO - __main__ - Step 18020: {'lr': 0.0004856857523282755, 'samples': 3459840, 'steps': 18019, 'loss/train': 0.9564329385757446}
+08/30/2021 16:28:35 - INFO - __main__ - Step 18021: {'lr': 0.0004856839823695801, 'samples': 3460032, 'steps': 18020, 'loss/train': 1.9314879179000854}
+08/30/2021 16:28:36 - INFO - __main__ - Step 18022: {'lr': 0.00048568221230468905, 'samples': 3460224, 'steps': 18021, 'loss/train': 1.7067102193832397}
+08/30/2021 16:28:36 - INFO - __main__ - Step 18023: {'lr': 0.0004856804421336033, 'samples': 3460416, 'steps': 18022, 'loss/train': 2.0386927127838135}
+08/30/2021 16:28:36 - INFO - __main__ - Step 18024: {'lr': 0.0004856786718563235, 'samples': 3460608, 'steps': 18023, 'loss/train': 1.5910874605178833}
+08/30/2021 16:28:38 - INFO - __main__ - Step 18025: {'lr': 0.0004856769014728506, 'samples': 3460800, 'steps': 18024, 'loss/train': 1.4760442972183228}
+08/30/2021 16:28:38 - INFO - __main__ - Step 18026: {'lr': 0.0004856751309831853, 'samples': 3460992, 'steps': 18025, 'loss/train': 1.577941656112671}
+08/30/2021 16:28:38 - INFO - __main__ - Step 18027: {'lr': 0.00048567336038732843, 'samples': 3461184, 'steps': 18026, 'loss/train': 1.6862093210220337}
+08/30/2021 16:28:39 - INFO - __main__ - Step 18028: {'lr': 0.0004856715896852808, 'samples': 3461376, 'steps': 18027, 'loss/train': 1.8757396936416626}
+08/30/2021 16:28:39 - INFO - __main__ - Step 18029: {'lr': 0.0004856698188770432, 'samples': 3461568, 'steps': 18028, 'loss/train': 1.694564700126648}
+08/30/2021 16:28:41 - INFO - __main__ - Step 18030: {'lr': 0.0004856680479626163, 'samples': 3461760, 'steps': 18029, 'loss/train': 1.5136922597885132}
+08/30/2021 16:28:41 - INFO - __main__ - Step 18031: {'lr': 0.0004856662769420012, 'samples': 3461952, 'steps': 18030, 'loss/train': 1.7104381322860718}
+08/30/2021 16:28:41 - INFO - __main__ - Step 18032: {'lr': 0.0004856645058151984, 'samples': 3462144, 'steps': 18031, 'loss/train': 0.833308219909668}
+08/30/2021 16:28:42 - INFO - __main__ - Step 18033: {'lr': 0.0004856627345822088, 'samples': 3462336, 'steps': 18032, 'loss/train': 0.7060480117797852}
+08/30/2021 16:28:42 - INFO - __main__ - Step 18034: {'lr': 0.0004856609632430332, 'samples': 3462528, 'steps': 18033, 'loss/train': 1.5961253643035889}
+08/30/2021 16:28:42 - INFO - __main__ - Step 18035: {'lr': 0.00048565919179767246, 'samples': 3462720, 'steps': 18034, 'loss/train': 1.7715524435043335}
+08/30/2021 16:28:44 - INFO - __main__ - Step 18036: {'lr': 0.0004856574202461273, 'samples': 3462912, 'steps': 18035, 'loss/train': 0.9656311273574829}
+08/30/2021 16:28:45 - INFO - __main__ - Step 18037: {'lr': 0.0004856556485883985, 'samples': 3463104, 'steps': 18036, 'loss/train': 1.2984038591384888}
+08/30/2021 16:28:45 - INFO - __main__ - Step 18038: {'lr': 0.000485653876824487, 'samples': 3463296, 'steps': 18037, 'loss/train': 2.0501441955566406}
+08/30/2021 16:28:45 - INFO - __main__ - Step 18039: {'lr': 0.00048565210495439337, 'samples': 3463488, 'steps': 18038, 'loss/train': 1.552443265914917}
+08/30/2021 16:28:46 - INFO - __main__ - Step 18040: {'lr': 0.00048565033297811867, 'samples': 3463680, 'steps': 18039, 'loss/train': 1.5536558628082275}
+08/30/2021 16:28:47 - INFO - __main__ - Step 18041: {'lr': 0.0004856485608956635, 'samples': 3463872, 'steps': 18040, 'loss/train': 1.036659836769104}
+08/30/2021 16:28:48 - INFO - __main__ - Step 18042: {'lr': 0.00048564678870702873, 'samples': 3464064, 'steps': 18041, 'loss/train': 1.7979850769042969}
+08/30/2021 16:28:48 - INFO - __main__ - Step 18043: {'lr': 0.00048564501641221516, 'samples': 3464256, 'steps': 18042, 'loss/train': 1.3544678688049316}
+08/30/2021 16:28:48 - INFO - __main__ - Step 18044: {'lr': 0.00048564324401122357, 'samples': 3464448, 'steps': 18043, 'loss/train': 1.6906307935714722}
+08/30/2021 16:28:49 - INFO - __main__ - Step 18045: {'lr': 0.0004856414715040548, 'samples': 3464640, 'steps': 18044, 'loss/train': 1.0748234987258911}
+08/30/2021 16:28:50 - INFO - __main__ - Step 18046: {'lr': 0.0004856396988907096, 'samples': 3464832, 'steps': 18045, 'loss/train': 1.5081632137298584}
+08/30/2021 16:28:51 - INFO - __main__ - Step 18047: {'lr': 0.00048563792617118876, 'samples': 3465024, 'steps': 18046, 'loss/train': 1.872005820274353}
+08/30/2021 16:28:51 - INFO - __main__ - Step 18048: {'lr': 0.00048563615334549316, 'samples': 3465216, 'steps': 18047, 'loss/train': 2.1396422386169434}
+08/30/2021 16:28:51 - INFO - __main__ - Step 18049: {'lr': 0.0004856343804136235, 'samples': 3465408, 'steps': 18048, 'loss/train': 1.707249641418457}
+08/30/2021 16:28:52 - INFO - __main__ - Step 18050: {'lr': 0.0004856326073755806, 'samples': 3465600, 'steps': 18049, 'loss/train': 1.3193695545196533}
+08/30/2021 16:28:53 - INFO - __main__ - Step 18051: {'lr': 0.0004856308342313653, 'samples': 3465792, 'steps': 18050, 'loss/train': 0.984358549118042}
+08/30/2021 16:28:54 - INFO - __main__ - Step 18052: {'lr': 0.00048562906098097847, 'samples': 3465984, 'steps': 18051, 'loss/train': 1.6047166585922241}
+08/30/2021 16:28:54 - INFO - __main__ - Step 18053: {'lr': 0.0004856272876244208, 'samples': 3466176, 'steps': 18052, 'loss/train': 1.973154902458191}
+08/30/2021 16:28:54 - INFO - __main__ - Step 18054: {'lr': 0.000485625514161693, 'samples': 3466368, 'steps': 18053, 'loss/train': 1.4109480381011963}
+08/30/2021 16:28:55 - INFO - __main__ - Step 18055: {'lr': 0.00048562374059279604, 'samples': 3466560, 'steps': 18054, 'loss/train': 1.571926474571228}
+08/30/2021 16:28:56 - INFO - __main__ - Step 18056: {'lr': 0.00048562196691773066, 'samples': 3466752, 'steps': 18055, 'loss/train': 1.6709606647491455}
+08/30/2021 16:28:57 - INFO - __main__ - Step 18057: {'lr': 0.00048562019313649766, 'samples': 3466944, 'steps': 18056, 'loss/train': 0.5680364370346069}
+08/30/2021 16:28:57 - INFO - __main__ - Step 18058: {'lr': 0.0004856184192490979, 'samples': 3467136, 'steps': 18057, 'loss/train': 1.7736974954605103}
+08/30/2021 16:28:57 - INFO - __main__ - Step 18059: {'lr': 0.000485616645255532, 'samples': 3467328, 'steps': 18058, 'loss/train': 1.9981396198272705}
+08/30/2021 16:28:58 - INFO - __main__ - Step 18060: {'lr': 0.0004856148711558009, 'samples': 3467520, 'steps': 18059, 'loss/train': 1.743849754333496}
+08/30/2021 16:28:58 - INFO - __main__ - Step 18061: {'lr': 0.00048561309694990543, 'samples': 3467712, 'steps': 18060, 'loss/train': 1.9952452182769775}
+08/30/2021 16:29:00 - INFO - __main__ - Step 18062: {'lr': 0.00048561132263784634, 'samples': 3467904, 'steps': 18061, 'loss/train': 1.6193169355392456}
+08/30/2021 16:29:00 - INFO - __main__ - Step 18063: {'lr': 0.00048560954821962434, 'samples': 3468096, 'steps': 18062, 'loss/train': 1.4820996522903442}
+08/30/2021 16:29:01 - INFO - __main__ - Step 18064: {'lr': 0.0004856077736952404, 'samples': 3468288, 'steps': 18063, 'loss/train': 0.35932403802871704}
+08/30/2021 16:29:01 - INFO - __main__ - Step 18065: {'lr': 0.00048560599906469513, 'samples': 3468480, 'steps': 18064, 'loss/train': 0.5257107615470886}
+08/30/2021 16:29:01 - INFO - __main__ - Step 18066: {'lr': 0.00048560422432798956, 'samples': 3468672, 'steps': 18065, 'loss/train': 2.516770124435425}
+08/30/2021 16:29:02 - INFO - __main__ - Step 18067: {'lr': 0.0004856024494851243, 'samples': 3468864, 'steps': 18066, 'loss/train': 1.6919971704483032}
+08/30/2021 16:29:03 - INFO - __main__ - Step 18068: {'lr': 0.00048560067453610025, 'samples': 3469056, 'steps': 18067, 'loss/train': 1.546239972114563}
+08/30/2021 16:29:04 - INFO - __main__ - Step 18069: {'lr': 0.00048559889948091814, 'samples': 3469248, 'steps': 18068, 'loss/train': 1.52725088596344}
+08/30/2021 16:29:04 - INFO - __main__ - Step 18070: {'lr': 0.0004855971243195788, 'samples': 3469440, 'steps': 18069, 'loss/train': 1.8115290403366089}
+08/30/2021 16:29:04 - INFO - __main__ - Step 18071: {'lr': 0.00048559534905208304, 'samples': 3469632, 'steps': 18070, 'loss/train': 1.6920514106750488}
+08/30/2021 16:29:05 - INFO - __main__ - Step 18072: {'lr': 0.0004855935736784316, 'samples': 3469824, 'steps': 18071, 'loss/train': 1.7712047100067139}
+08/30/2021 16:29:07 - INFO - __main__ - Step 18073: {'lr': 0.00048559179819862537, 'samples': 3470016, 'steps': 18072, 'loss/train': 1.6060940027236938}
+08/30/2021 16:29:07 - INFO - __main__ - Step 18074: {'lr': 0.0004855900226126651, 'samples': 3470208, 'steps': 18073, 'loss/train': 1.5529301166534424}
+08/30/2021 16:29:08 - INFO - __main__ - Step 18075: {'lr': 0.00048558824692055156, 'samples': 3470400, 'steps': 18074, 'loss/train': 1.69679594039917}
+08/30/2021 16:29:08 - INFO - __main__ - Step 18076: {'lr': 0.0004855864711222857, 'samples': 3470592, 'steps': 18075, 'loss/train': 1.4229506254196167}
+08/30/2021 16:29:09 - INFO - __main__ - Step 18077: {'lr': 0.0004855846952178682, 'samples': 3470784, 'steps': 18076, 'loss/train': 1.3505346775054932}
+08/30/2021 16:29:09 - INFO - __main__ - Step 18078: {'lr': 0.0004855829192072998, 'samples': 3470976, 'steps': 18077, 'loss/train': 1.947479009628296}
+08/30/2021 16:29:10 - INFO - __main__ - Step 18079: {'lr': 0.00048558114309058144, 'samples': 3471168, 'steps': 18078, 'loss/train': 2.2514586448669434}
+08/30/2021 16:29:11 - INFO - __main__ - Step 18080: {'lr': 0.00048557936686771376, 'samples': 3471360, 'steps': 18079, 'loss/train': 1.5654730796813965}
+08/30/2021 16:29:11 - INFO - __main__ - Step 18081: {'lr': 0.0004855775905386977, 'samples': 3471552, 'steps': 18080, 'loss/train': 1.4146381616592407}
+08/30/2021 16:29:11 - INFO - __main__ - Step 18082: {'lr': 0.000485575814103534, 'samples': 3471744, 'steps': 18081, 'loss/train': 1.4612665176391602}
+08/30/2021 16:29:12 - INFO - __main__ - Step 18083: {'lr': 0.0004855740375622235, 'samples': 3471936, 'steps': 18082, 'loss/train': 1.6697293519973755}
+08/30/2021 16:29:13 - INFO - __main__ - Step 18084: {'lr': 0.00048557226091476704, 'samples': 3472128, 'steps': 18083, 'loss/train': 1.5470685958862305}
+08/30/2021 16:29:14 - INFO - __main__ - Step 18085: {'lr': 0.0004855704841611652, 'samples': 3472320, 'steps': 18084, 'loss/train': 1.0351128578186035}
+08/30/2021 16:29:14 - INFO - __main__ - Step 18086: {'lr': 0.00048556870730141906, 'samples': 3472512, 'steps': 18085, 'loss/train': 1.4645930528640747}
+08/30/2021 16:29:15 - INFO - __main__ - Step 18087: {'lr': 0.00048556693033552926, 'samples': 3472704, 'steps': 18086, 'loss/train': 1.5588650703430176}
+08/30/2021 16:29:15 - INFO - __main__ - Step 18088: {'lr': 0.0004855651532634966, 'samples': 3472896, 'steps': 18087, 'loss/train': 1.4824671745300293}
+08/30/2021 16:29:17 - INFO - __main__ - Step 18089: {'lr': 0.00048556337608532196, 'samples': 3473088, 'steps': 18088, 'loss/train': 1.5125601291656494}
+08/30/2021 16:29:17 - INFO - __main__ - Step 18090: {'lr': 0.00048556159880100604, 'samples': 3473280, 'steps': 18089, 'loss/train': 1.5799002647399902}
+08/30/2021 16:29:17 - INFO - __main__ - Step 18091: {'lr': 0.00048555982141054976, 'samples': 3473472, 'steps': 18090, 'loss/train': 1.3235498666763306}
+08/30/2021 16:29:18 - INFO - __main__ - Step 18092: {'lr': 0.0004855580439139539, 'samples': 3473664, 'steps': 18091, 'loss/train': 1.2626641988754272}
+08/30/2021 16:29:18 - INFO - __main__ - Step 18093: {'lr': 0.00048555626631121906, 'samples': 3473856, 'steps': 18092, 'loss/train': 1.4647942781448364}
+08/30/2021 16:29:20 - INFO - __main__ - Step 18094: {'lr': 0.0004855544886023463, 'samples': 3474048, 'steps': 18093, 'loss/train': 1.4743677377700806}
+08/30/2021 16:29:20 - INFO - __main__ - Step 18095: {'lr': 0.00048555271078733637, 'samples': 3474240, 'steps': 18094, 'loss/train': 1.375719666481018}
+08/30/2021 16:29:20 - INFO - __main__ - Step 18096: {'lr': 0.00048555093286618996, 'samples': 3474432, 'steps': 18095, 'loss/train': 2.1218225955963135}
+08/30/2021 16:29:21 - INFO - __main__ - Step 18097: {'lr': 0.0004855491548389079, 'samples': 3474624, 'steps': 18096, 'loss/train': 1.4977178573608398}
+08/30/2021 16:29:21 - INFO - __main__ - Step 18098: {'lr': 0.0004855473767054911, 'samples': 3474816, 'steps': 18097, 'loss/train': 1.7799386978149414}
+08/30/2021 16:29:23 - INFO - __main__ - Step 18099: {'lr': 0.00048554559846594026, 'samples': 3475008, 'steps': 18098, 'loss/train': 1.7905550003051758}
+08/30/2021 16:29:23 - INFO - __main__ - Step 18100: {'lr': 0.0004855438201202562, 'samples': 3475200, 'steps': 18099, 'loss/train': 1.3962756395339966}
+08/30/2021 16:29:23 - INFO - __main__ - Step 18101: {'lr': 0.0004855420416684398, 'samples': 3475392, 'steps': 18100, 'loss/train': 1.8041163682937622}
+08/30/2021 16:29:24 - INFO - __main__ - Step 18102: {'lr': 0.0004855402631104917, 'samples': 3475584, 'steps': 18101, 'loss/train': 0.3637233376502991}
+08/30/2021 16:29:24 - INFO - __main__ - Step 18103: {'lr': 0.0004855384844464128, 'samples': 3475776, 'steps': 18102, 'loss/train': 1.7341152429580688}
+08/30/2021 16:29:24 - INFO - __main__ - Step 18104: {'lr': 0.00048553670567620395, 'samples': 3475968, 'steps': 18103, 'loss/train': 1.2765697240829468}
+08/30/2021 16:29:26 - INFO - __main__ - Step 18105: {'lr': 0.0004855349267998659, 'samples': 3476160, 'steps': 18104, 'loss/train': 1.5414867401123047}
+08/30/2021 16:29:26 - INFO - __main__ - Step 18106: {'lr': 0.0004855331478173994, 'samples': 3476352, 'steps': 18105, 'loss/train': 2.287764310836792}
+08/30/2021 16:29:27 - INFO - __main__ - Step 18107: {'lr': 0.0004855313687288053, 'samples': 3476544, 'steps': 18106, 'loss/train': 1.6214512586593628}
+08/30/2021 16:29:27 - INFO - __main__ - Step 18108: {'lr': 0.00048552958953408437, 'samples': 3476736, 'steps': 18107, 'loss/train': 1.9014850854873657}
+08/30/2021 16:29:28 - INFO - __main__ - Step 18109: {'lr': 0.0004855278102332375, 'samples': 3476928, 'steps': 18108, 'loss/train': 1.979744791984558}
+08/30/2021 16:29:29 - INFO - __main__ - Step 18110: {'lr': 0.0004855260308262654, 'samples': 3477120, 'steps': 18109, 'loss/train': 1.468855857849121}
+08/30/2021 16:29:30 - INFO - __main__ - Step 18111: {'lr': 0.00048552425131316893, 'samples': 3477312, 'steps': 18110, 'loss/train': 2.183777093887329}
+08/30/2021 16:29:30 - INFO - __main__ - Step 18112: {'lr': 0.0004855224716939488, 'samples': 3477504, 'steps': 18111, 'loss/train': 1.2424217462539673}
+08/30/2021 16:29:30 - INFO - __main__ - Step 18113: {'lr': 0.0004855206919686059, 'samples': 3477696, 'steps': 18112, 'loss/train': 1.9680477380752563}
+08/30/2021 16:29:31 - INFO - __main__ - Step 18114: {'lr': 0.0004855189121371411, 'samples': 3477888, 'steps': 18113, 'loss/train': 1.4735645055770874}
+08/30/2021 16:29:32 - INFO - __main__ - Step 18115: {'lr': 0.00048551713219955505, 'samples': 3478080, 'steps': 18114, 'loss/train': 1.5061053037643433}
+08/30/2021 16:29:32 - INFO - __main__ - Step 18116: {'lr': 0.00048551535215584865, 'samples': 3478272, 'steps': 18115, 'loss/train': 1.6229461431503296}
+08/30/2021 16:29:33 - INFO - __main__ - Step 18117: {'lr': 0.00048551357200602265, 'samples': 3478464, 'steps': 18116, 'loss/train': 0.8685430288314819}
+08/30/2021 16:29:33 - INFO - __main__ - Step 18118: {'lr': 0.0004855117917500778, 'samples': 3478656, 'steps': 18117, 'loss/train': 1.8633511066436768}
+08/30/2021 16:29:34 - INFO - __main__ - Step 18119: {'lr': 0.000485510011388015, 'samples': 3478848, 'steps': 18118, 'loss/train': 1.6058130264282227}
+08/30/2021 16:29:35 - INFO - __main__ - Step 18120: {'lr': 0.00048550823091983507, 'samples': 3479040, 'steps': 18119, 'loss/train': 0.5264639258384705}
+08/30/2021 16:29:36 - INFO - __main__ - Step 18121: {'lr': 0.00048550645034553877, 'samples': 3479232, 'steps': 18120, 'loss/train': 1.413364052772522}
+08/30/2021 16:29:36 - INFO - __main__ - Step 18122: {'lr': 0.00048550466966512684, 'samples': 3479424, 'steps': 18121, 'loss/train': 1.579680323600769}
+08/30/2021 16:29:36 - INFO - __main__ - Step 18123: {'lr': 0.0004855028888786002, 'samples': 3479616, 'steps': 18122, 'loss/train': 1.9736636877059937}
+08/30/2021 16:29:37 - INFO - __main__ - Step 18124: {'lr': 0.00048550110798595953, 'samples': 3479808, 'steps': 18123, 'loss/train': 1.5097899436950684}
+08/30/2021 16:29:39 - INFO - __main__ - Step 18125: {'lr': 0.0004854993269872057, 'samples': 3480000, 'steps': 18124, 'loss/train': 1.5835509300231934}
+08/30/2021 16:29:39 - INFO - __main__ - Step 18126: {'lr': 0.0004854975458823396, 'samples': 3480192, 'steps': 18125, 'loss/train': 2.423356056213379}
+08/30/2021 16:29:39 - INFO - __main__ - Step 18127: {'lr': 0.0004854957646713618, 'samples': 3480384, 'steps': 18126, 'loss/train': 1.6631091833114624}
+08/30/2021 16:29:40 - INFO - __main__ - Step 18128: {'lr': 0.00048549398335427337, 'samples': 3480576, 'steps': 18127, 'loss/train': 1.527232050895691}
+08/30/2021 16:29:40 - INFO - __main__ - Step 18129: {'lr': 0.0004854922019310749, 'samples': 3480768, 'steps': 18128, 'loss/train': 1.6804276704788208}
+08/30/2021 16:29:42 - INFO - __main__ - Step 18130: {'lr': 0.0004854904204017673, 'samples': 3480960, 'steps': 18129, 'loss/train': 1.1936918497085571}
+08/30/2021 16:29:43 - INFO - __main__ - Step 18131: {'lr': 0.0004854886387663514, 'samples': 3481152, 'steps': 18130, 'loss/train': 2.179919481277466}
+08/30/2021 16:29:43 - INFO - __main__ - Step 18132: {'lr': 0.0004854868570248279, 'samples': 3481344, 'steps': 18131, 'loss/train': 1.3007756471633911}
+08/30/2021 16:29:43 - INFO - __main__ - Step 18133: {'lr': 0.00048548507517719766, 'samples': 3481536, 'steps': 18132, 'loss/train': 1.2625625133514404}
+08/30/2021 16:29:44 - INFO - __main__ - Step 18134: {'lr': 0.0004854832932234615, 'samples': 3481728, 'steps': 18133, 'loss/train': 1.6213260889053345}
+08/30/2021 16:29:44 - INFO - __main__ - Step 18135: {'lr': 0.0004854815111636202, 'samples': 3481920, 'steps': 18134, 'loss/train': 1.7813739776611328}
+08/30/2021 16:29:45 - INFO - __main__ - Step 18136: {'lr': 0.00048547972899767454, 'samples': 3482112, 'steps': 18135, 'loss/train': 1.9012194871902466}
+08/30/2021 16:29:46 - INFO - __main__ - Step 18137: {'lr': 0.0004854779467256254, 'samples': 3482304, 'steps': 18136, 'loss/train': 1.1619831323623657}
+08/30/2021 16:29:46 - INFO - __main__ - Step 18138: {'lr': 0.00048547616434747344, 'samples': 3482496, 'steps': 18137, 'loss/train': 1.0694165229797363}
+08/30/2021 16:29:47 - INFO - __main__ - Step 18139: {'lr': 0.0004854743818632196, 'samples': 3482688, 'steps': 18138, 'loss/train': 0.7140091061592102}
+08/30/2021 16:29:47 - INFO - __main__ - Step 18140: {'lr': 0.0004854725992728647, 'samples': 3482880, 'steps': 18139, 'loss/train': 1.559740424156189}
+08/30/2021 16:29:48 - INFO - __main__ - Step 18141: {'lr': 0.00048547081657640935, 'samples': 3483072, 'steps': 18140, 'loss/train': 1.8245887756347656}
+08/30/2021 16:29:49 - INFO - __main__ - Step 18142: {'lr': 0.00048546903377385457, 'samples': 3483264, 'steps': 18141, 'loss/train': 0.4078364372253418}
+08/30/2021 16:29:49 - INFO - __main__ - Step 18143: {'lr': 0.00048546725086520107, 'samples': 3483456, 'steps': 18142, 'loss/train': 2.0865206718444824}
+08/30/2021 16:29:50 - INFO - __main__ - Step 18144: {'lr': 0.00048546546785044965, 'samples': 3483648, 'steps': 18143, 'loss/train': 1.1922963857650757}
+08/30/2021 16:29:50 - INFO - __main__ - Step 18145: {'lr': 0.00048546368472960114, 'samples': 3483840, 'steps': 18144, 'loss/train': 1.7791651487350464}
+08/30/2021 16:29:51 - INFO - __main__ - Step 18146: {'lr': 0.00048546190150265634, 'samples': 3484032, 'steps': 18145, 'loss/train': 1.6271249055862427}
+08/30/2021 16:29:52 - INFO - __main__ - Step 18147: {'lr': 0.00048546011816961597, 'samples': 3484224, 'steps': 18146, 'loss/train': 1.6857608556747437}
+08/30/2021 16:29:52 - INFO - __main__ - Step 18148: {'lr': 0.00048545833473048094, 'samples': 3484416, 'steps': 18147, 'loss/train': 1.4611496925354004}
+08/30/2021 16:29:52 - INFO - __main__ - Step 18149: {'lr': 0.00048545655118525206, 'samples': 3484608, 'steps': 18148, 'loss/train': 1.7676684856414795}
+08/30/2021 16:29:53 - INFO - __main__ - Step 18150: {'lr': 0.00048545476753393004, 'samples': 3484800, 'steps': 18149, 'loss/train': 1.7006365060806274}
+08/30/2021 16:29:55 - INFO - __main__ - Step 18151: {'lr': 0.0004854529837765158, 'samples': 3484992, 'steps': 18150, 'loss/train': 2.1798832416534424}
+08/30/2021 16:29:55 - INFO - __main__ - Step 18152: {'lr': 0.00048545119991301, 'samples': 3485184, 'steps': 18151, 'loss/train': 0.24442991614341736}
+08/30/2021 16:29:55 - INFO - __main__ - Step 18153: {'lr': 0.0004854494159434135, 'samples': 3485376, 'steps': 18152, 'loss/train': 0.07093805074691772}
+08/30/2021 16:29:56 - INFO - __main__ - Step 18154: {'lr': 0.0004854476318677272, 'samples': 3485568, 'steps': 18153, 'loss/train': 2.1398026943206787}
+08/30/2021 16:29:56 - INFO - __main__ - Step 18155: {'lr': 0.00048544584768595185, 'samples': 3485760, 'steps': 18154, 'loss/train': 1.5284425020217896}
+08/30/2021 16:29:56 - INFO - __main__ - Step 18156: {'lr': 0.00048544406339808823, 'samples': 3485952, 'steps': 18155, 'loss/train': 1.9047931432724}
+08/30/2021 16:29:58 - INFO - __main__ - Step 18157: {'lr': 0.00048544227900413706, 'samples': 3486144, 'steps': 18156, 'loss/train': 1.0087835788726807}
+08/30/2021 16:29:58 - INFO - __main__ - Step 18158: {'lr': 0.0004854404945040993, 'samples': 3486336, 'steps': 18157, 'loss/train': 1.7160950899124146}
+08/30/2021 16:29:59 - INFO - __main__ - Step 18159: {'lr': 0.0004854387098979757, 'samples': 3486528, 'steps': 18158, 'loss/train': 2.1456117630004883}
+08/30/2021 16:29:59 - INFO - __main__ - Step 18160: {'lr': 0.000485436925185767, 'samples': 3486720, 'steps': 18159, 'loss/train': 1.3853322267532349}
+08/30/2021 16:29:59 - INFO - __main__ - Step 18161: {'lr': 0.00048543514036747404, 'samples': 3486912, 'steps': 18160, 'loss/train': 2.0687689781188965}
+08/30/2021 16:30:01 - INFO - __main__ - Step 18162: {'lr': 0.00048543335544309776, 'samples': 3487104, 'steps': 18161, 'loss/train': 1.7371457815170288}
+08/30/2021 16:30:02 - INFO - __main__ - Step 18163: {'lr': 0.00048543157041263876, 'samples': 3487296, 'steps': 18162, 'loss/train': 1.9401506185531616}
+08/30/2021 16:30:02 - INFO - __main__ - Step 18164: {'lr': 0.0004854297852760979, 'samples': 3487488, 'steps': 18163, 'loss/train': 1.199976921081543}
+08/30/2021 16:30:03 - INFO - __main__ - Step 18165: {'lr': 0.000485428000033476, 'samples': 3487680, 'steps': 18164, 'loss/train': 1.9119760990142822}
+08/30/2021 16:30:03 - INFO - __main__ - Step 18166: {'lr': 0.00048542621468477393, 'samples': 3487872, 'steps': 18165, 'loss/train': 1.1560609340667725}
+08/30/2021 16:30:03 - INFO - __main__ - Step 18167: {'lr': 0.0004854244292299924, 'samples': 3488064, 'steps': 18166, 'loss/train': 1.251025676727295}
+08/30/2021 16:30:04 - INFO - __main__ - Step 18168: {'lr': 0.0004854226436691323, 'samples': 3488256, 'steps': 18167, 'loss/train': 0.1865871548652649}
+08/30/2021 16:30:05 - INFO - __main__ - Step 18169: {'lr': 0.0004854208580021944, 'samples': 3488448, 'steps': 18168, 'loss/train': 0.15591633319854736}
+08/30/2021 16:30:06 - INFO - __main__ - Step 18170: {'lr': 0.00048541907222917946, 'samples': 3488640, 'steps': 18169, 'loss/train': 2.0507378578186035}
+08/30/2021 16:30:06 - INFO - __main__ - Step 18171: {'lr': 0.0004854172863500883, 'samples': 3488832, 'steps': 18170, 'loss/train': 1.788221001625061}
+08/30/2021 16:30:06 - INFO - __main__ - Step 18172: {'lr': 0.00048541550036492175, 'samples': 3489024, 'steps': 18171, 'loss/train': 2.480135679244995}
+08/30/2021 16:30:07 - INFO - __main__ - Step 18173: {'lr': 0.00048541371427368064, 'samples': 3489216, 'steps': 18172, 'loss/train': 2.4320027828216553}
+08/30/2021 16:30:08 - INFO - __main__ - Step 18174: {'lr': 0.0004854119280763657, 'samples': 3489408, 'steps': 18173, 'loss/train': 1.6566660404205322}
+08/30/2021 16:30:09 - INFO - __main__ - Step 18175: {'lr': 0.00048541014177297783, 'samples': 3489600, 'steps': 18174, 'loss/train': 1.9397094249725342}
+08/30/2021 16:30:09 - INFO - __main__ - Step 18176: {'lr': 0.0004854083553635178, 'samples': 3489792, 'steps': 18175, 'loss/train': 1.500089406967163}
+08/30/2021 16:30:10 - INFO - __main__ - Step 18177: {'lr': 0.00048540656884798626, 'samples': 3489984, 'steps': 18176, 'loss/train': 1.5683972835540771}
+08/30/2021 16:30:10 - INFO - __main__ - Step 18178: {'lr': 0.0004854047822263843, 'samples': 3490176, 'steps': 18177, 'loss/train': 1.6979554891586304}
+08/30/2021 16:30:10 - INFO - __main__ - Step 18179: {'lr': 0.00048540299549871256, 'samples': 3490368, 'steps': 18178, 'loss/train': 0.07497352361679077}
+08/30/2021 16:30:11 - INFO - __main__ - Step 18180: {'lr': 0.0004854012086649718, 'samples': 3490560, 'steps': 18179, 'loss/train': 0.6716282367706299}
+08/30/2021 16:30:12 - INFO - __main__ - Step 18181: {'lr': 0.00048539942172516295, 'samples': 3490752, 'steps': 18180, 'loss/train': 0.06318680942058563}
+08/30/2021 16:30:13 - INFO - __main__ - Step 18182: {'lr': 0.00048539763467928665, 'samples': 3490944, 'steps': 18181, 'loss/train': 1.983986496925354}
+08/30/2021 16:30:13 - INFO - __main__ - Step 18183: {'lr': 0.0004853958475273439, 'samples': 3491136, 'steps': 18182, 'loss/train': 1.9680562019348145}
+08/30/2021 16:30:13 - INFO - __main__ - Step 18184: {'lr': 0.0004853940602693354, 'samples': 3491328, 'steps': 18183, 'loss/train': 1.910803198814392}
+08/30/2021 16:30:14 - INFO - __main__ - Step 18185: {'lr': 0.00048539227290526194, 'samples': 3491520, 'steps': 18184, 'loss/train': 1.7229681015014648}
+08/30/2021 16:30:16 - INFO - __main__ - Step 18186: {'lr': 0.00048539048543512443, 'samples': 3491712, 'steps': 18185, 'loss/train': 1.7122142314910889}
+08/30/2021 16:30:17 - INFO - __main__ - Step 18187: {'lr': 0.0004853886978589235, 'samples': 3491904, 'steps': 18186, 'loss/train': 1.6136554479599}
+08/30/2021 16:30:17 - INFO - __main__ - Step 18188: {'lr': 0.0004853869101766601, 'samples': 3492096, 'steps': 18187, 'loss/train': 1.744834303855896}
+08/30/2021 16:30:17 - INFO - __main__ - Step 18189: {'lr': 0.000485385122388335, 'samples': 3492288, 'steps': 18188, 'loss/train': 1.8125004768371582}
+08/30/2021 16:30:18 - INFO - __main__ - Step 18190: {'lr': 0.000485383334493949, 'samples': 3492480, 'steps': 18189, 'loss/train': 0.11176054179668427}
+08/30/2021 16:30:19 - INFO - __main__ - Step 18191: {'lr': 0.00048538154649350286, 'samples': 3492672, 'steps': 18190, 'loss/train': 1.5933929681777954}
+08/30/2021 16:30:20 - INFO - __main__ - Step 18192: {'lr': 0.00048537975838699744, 'samples': 3492864, 'steps': 18191, 'loss/train': 1.4787840843200684}
+08/30/2021 16:30:20 - INFO - __main__ - Step 18193: {'lr': 0.0004853779701744335, 'samples': 3493056, 'steps': 18192, 'loss/train': 1.5653127431869507}
+08/30/2021 16:30:20 - INFO - __main__ - Step 18194: {'lr': 0.000485376181855812, 'samples': 3493248, 'steps': 18193, 'loss/train': 1.5043683052062988}
+08/30/2021 16:30:21 - INFO - __main__ - Step 18195: {'lr': 0.00048537439343113354, 'samples': 3493440, 'steps': 18194, 'loss/train': 1.4824970960617065}
+08/30/2021 16:30:21 - INFO - __main__ - Step 18196: {'lr': 0.000485372604900399, 'samples': 3493632, 'steps': 18195, 'loss/train': 1.315542459487915}
+08/30/2021 16:30:22 - INFO - __main__ - Step 18197: {'lr': 0.0004853708162636092, 'samples': 3493824, 'steps': 18196, 'loss/train': 1.5427913665771484}
+08/30/2021 16:30:23 - INFO - __main__ - Step 18198: {'lr': 0.00048536902752076494, 'samples': 3494016, 'steps': 18197, 'loss/train': 1.4136998653411865}
+08/30/2021 16:30:23 - INFO - __main__ - Step 18199: {'lr': 0.00048536723867186705, 'samples': 3494208, 'steps': 18198, 'loss/train': 2.3811869621276855}
+08/30/2021 16:30:24 - INFO - __main__ - Step 18200: {'lr': 0.0004853654497169163, 'samples': 3494400, 'steps': 18199, 'loss/train': 1.7197117805480957}
+08/30/2021 16:30:24 - INFO - __main__ - Step 18201: {'lr': 0.00048536366065591354, 'samples': 3494592, 'steps': 18200, 'loss/train': 1.966328740119934}
+08/30/2021 16:30:25 - INFO - __main__ - Step 18202: {'lr': 0.00048536187148885956, 'samples': 3494784, 'steps': 18201, 'loss/train': 1.398764729499817}
+08/30/2021 16:30:26 - INFO - __main__ - Step 18203: {'lr': 0.0004853600822157551, 'samples': 3494976, 'steps': 18202, 'loss/train': 1.0334347486495972}
+08/30/2021 16:30:26 - INFO - __main__ - Step 18204: {'lr': 0.000485358292836601, 'samples': 3495168, 'steps': 18203, 'loss/train': 2.1281890869140625}
+08/30/2021 16:30:27 - INFO - __main__ - Step 18205: {'lr': 0.0004853565033513982, 'samples': 3495360, 'steps': 18204, 'loss/train': 0.22665266692638397}
+08/30/2021 16:30:27 - INFO - __main__ - Step 18206: {'lr': 0.0004853547137601473, 'samples': 3495552, 'steps': 18205, 'loss/train': 1.2151612043380737}
+08/30/2021 16:30:29 - INFO - __main__ - Step 18207: {'lr': 0.0004853529240628493, 'samples': 3495744, 'steps': 18206, 'loss/train': 1.48349928855896}
+08/30/2021 16:30:29 - INFO - __main__ - Step 18208: {'lr': 0.00048535113425950474, 'samples': 3495936, 'steps': 18207, 'loss/train': 1.808370590209961}
+08/30/2021 16:30:29 - INFO - __main__ - Step 18209: {'lr': 0.0004853493443501147, 'samples': 3496128, 'steps': 18208, 'loss/train': 0.945346474647522}
+08/30/2021 16:30:30 - INFO - __main__ - Step 18210: {'lr': 0.0004853475543346798, 'samples': 3496320, 'steps': 18209, 'loss/train': 1.5416520833969116}
+08/30/2021 16:30:30 - INFO - __main__ - Step 18211: {'lr': 0.000485345764213201, 'samples': 3496512, 'steps': 18210, 'loss/train': 1.618773102760315}
+08/30/2021 16:30:30 - INFO - __main__ - Step 18212: {'lr': 0.00048534397398567895, 'samples': 3496704, 'steps': 18211, 'loss/train': 1.5082675218582153}
+08/30/2021 16:30:32 - INFO - __main__ - Step 18213: {'lr': 0.00048534218365211456, 'samples': 3496896, 'steps': 18212, 'loss/train': 0.14711081981658936}
+08/30/2021 16:30:32 - INFO - __main__ - Step 18214: {'lr': 0.0004853403932125087, 'samples': 3497088, 'steps': 18213, 'loss/train': 1.564862608909607}
+08/30/2021 16:30:33 - INFO - __main__ - Step 18215: {'lr': 0.00048533860266686203, 'samples': 3497280, 'steps': 18214, 'loss/train': 2.049409866333008}
+08/30/2021 16:30:33 - INFO - __main__ - Step 18216: {'lr': 0.0004853368120151754, 'samples': 3497472, 'steps': 18215, 'loss/train': 1.8001041412353516}
+08/30/2021 16:30:33 - INFO - __main__ - Step 18217: {'lr': 0.00048533502125744967, 'samples': 3497664, 'steps': 18216, 'loss/train': 1.8892565965652466}
+08/30/2021 16:30:35 - INFO - __main__ - Step 18218: {'lr': 0.0004853332303936856, 'samples': 3497856, 'steps': 18217, 'loss/train': 1.4445117712020874}
+08/30/2021 16:30:35 - INFO - __main__ - Step 18219: {'lr': 0.000485331439423884, 'samples': 3498048, 'steps': 18218, 'loss/train': 1.5056453943252563}
+08/30/2021 16:30:36 - INFO - __main__ - Step 18220: {'lr': 0.00048532964834804566, 'samples': 3498240, 'steps': 18219, 'loss/train': 0.9864267706871033}
+08/30/2021 16:30:36 - INFO - __main__ - Step 18221: {'lr': 0.00048532785716617145, 'samples': 3498432, 'steps': 18220, 'loss/train': 1.4905229806900024}
+08/30/2021 16:30:37 - INFO - __main__ - Step 18222: {'lr': 0.0004853260658782621, 'samples': 3498624, 'steps': 18221, 'loss/train': 1.4205816984176636}
+08/30/2021 16:30:38 - INFO - __main__ - Step 18223: {'lr': 0.0004853242744843185, 'samples': 3498816, 'steps': 18222, 'loss/train': 2.076859712600708}
+08/30/2021 16:30:38 - INFO - __main__ - Step 18224: {'lr': 0.0004853224829843414, 'samples': 3499008, 'steps': 18223, 'loss/train': 2.2336368560791016}
+08/30/2021 16:30:39 - INFO - __main__ - Step 18225: {'lr': 0.00048532069137833156, 'samples': 3499200, 'steps': 18224, 'loss/train': 1.8242483139038086}
+08/30/2021 16:30:39 - INFO - __main__ - Step 18226: {'lr': 0.00048531889966628997, 'samples': 3499392, 'steps': 18225, 'loss/train': 1.3434109687805176}
+08/30/2021 16:30:40 - INFO - __main__ - Step 18227: {'lr': 0.00048531710784821726, 'samples': 3499584, 'steps': 18226, 'loss/train': 1.7954832315444946}
+08/30/2021 16:30:41 - INFO - __main__ - Step 18228: {'lr': 0.0004853153159241143, 'samples': 3499776, 'steps': 18227, 'loss/train': 1.3241018056869507}
+08/30/2021 16:30:41 - INFO - __main__ - Step 18229: {'lr': 0.0004853135238939818, 'samples': 3499968, 'steps': 18228, 'loss/train': 1.6579416990280151}
+08/30/2021 16:30:42 - INFO - __main__ - Step 18230: {'lr': 0.0004853117317578207, 'samples': 3500160, 'steps': 18229, 'loss/train': 2.469796657562256}
+08/30/2021 16:30:42 - INFO - __main__ - Step 18231: {'lr': 0.00048530993951563186, 'samples': 3500352, 'steps': 18230, 'loss/train': 1.4420359134674072}
+08/30/2021 16:30:42 - INFO - __main__ - Step 18232: {'lr': 0.0004853081471674159, 'samples': 3500544, 'steps': 18231, 'loss/train': 1.3792097568511963}
+08/30/2021 16:30:43 - INFO - __main__ - Step 18233: {'lr': 0.00048530635471317373, 'samples': 3500736, 'steps': 18232, 'loss/train': 1.8431075811386108}
+08/30/2021 16:30:45 - INFO - __main__ - Step 18234: {'lr': 0.0004853045621529062, 'samples': 3500928, 'steps': 18233, 'loss/train': 0.8953320980072021}
+08/30/2021 16:30:45 - INFO - __main__ - Step 18235: {'lr': 0.000485302769486614, 'samples': 3501120, 'steps': 18234, 'loss/train': 1.5394054651260376}
+08/30/2021 16:30:45 - INFO - __main__ - Step 18236: {'lr': 0.000485300976714298, 'samples': 3501312, 'steps': 18235, 'loss/train': 1.4558779001235962}
+08/30/2021 16:30:46 - INFO - __main__ - Step 18237: {'lr': 0.00048529918383595906, 'samples': 3501504, 'steps': 18236, 'loss/train': 1.3067607879638672}
+08/30/2021 16:30:46 - INFO - __main__ - Step 18238: {'lr': 0.0004852973908515979, 'samples': 3501696, 'steps': 18237, 'loss/train': 0.7174292802810669}
+08/30/2021 16:30:48 - INFO - __main__ - Step 18239: {'lr': 0.0004852955977612154, 'samples': 3501888, 'steps': 18238, 'loss/train': 1.5812405347824097}
+08/30/2021 16:30:49 - INFO - __main__ - Step 18240: {'lr': 0.0004852938045648123, 'samples': 3502080, 'steps': 18239, 'loss/train': 1.4285887479782104}
+08/30/2021 16:30:49 - INFO - __main__ - Step 18241: {'lr': 0.0004852920112623895, 'samples': 3502272, 'steps': 18240, 'loss/train': 2.0259315967559814}
+08/30/2021 16:30:49 - INFO - __main__ - Step 18242: {'lr': 0.00048529021785394765, 'samples': 3502464, 'steps': 18241, 'loss/train': 1.8416999578475952}
+08/30/2021 16:30:50 - INFO - __main__ - Step 18243: {'lr': 0.00048528842433948776, 'samples': 3502656, 'steps': 18242, 'loss/train': 1.518181324005127}
+08/30/2021 16:30:52 - INFO - __main__ - Step 18244: {'lr': 0.00048528663071901047, 'samples': 3502848, 'steps': 18243, 'loss/train': 1.5467149019241333}
+08/30/2021 16:30:52 - INFO - __main__ - Step 18245: {'lr': 0.0004852848369925167, 'samples': 3503040, 'steps': 18244, 'loss/train': 2.726255416870117}
+08/30/2021 16:30:53 - INFO - __main__ - Step 18246: {'lr': 0.00048528304316000723, 'samples': 3503232, 'steps': 18245, 'loss/train': 1.824460744857788}
+08/30/2021 16:30:53 - INFO - __main__ - Step 18247: {'lr': 0.0004852812492214828, 'samples': 3503424, 'steps': 18246, 'loss/train': 1.953322172164917}
+08/30/2021 16:30:53 - INFO - __main__ - Step 18248: {'lr': 0.0004852794551769443, 'samples': 3503616, 'steps': 18247, 'loss/train': 2.5393340587615967}
+08/30/2021 16:30:54 - INFO - __main__ - Step 18249: {'lr': 0.0004852776610263925, 'samples': 3503808, 'steps': 18248, 'loss/train': 2.7364838123321533}
+08/30/2021 16:30:54 - INFO - __main__ - Step 18250: {'lr': 0.0004852758667698282, 'samples': 3504000, 'steps': 18249, 'loss/train': 1.9968701601028442}
+08/30/2021 16:30:56 - INFO - __main__ - Step 18251: {'lr': 0.00048527407240725223, 'samples': 3504192, 'steps': 18250, 'loss/train': 2.165238618850708}
+08/30/2021 16:30:56 - INFO - __main__ - Step 18252: {'lr': 0.0004852722779386654, 'samples': 3504384, 'steps': 18251, 'loss/train': 2.3952183723449707}
+08/30/2021 16:30:57 - INFO - __main__ - Step 18253: {'lr': 0.00048527048336406855, 'samples': 3504576, 'steps': 18252, 'loss/train': 2.9041616916656494}
+08/30/2021 16:30:57 - INFO - __main__ - Step 18254: {'lr': 0.00048526868868346243, 'samples': 3504768, 'steps': 18253, 'loss/train': 2.2178878784179688}
+08/30/2021 16:30:57 - INFO - __main__ - Step 18255: {'lr': 0.0004852668938968478, 'samples': 3504960, 'steps': 18254, 'loss/train': 2.0800187587738037}
+08/30/2021 16:30:59 - INFO - __main__ - Step 18256: {'lr': 0.0004852650990042256, 'samples': 3505152, 'steps': 18255, 'loss/train': 1.8880712985992432}
+08/30/2021 16:31:00 - INFO - __main__ - Step 18257: {'lr': 0.0004852633040055966, 'samples': 3505344, 'steps': 18256, 'loss/train': 2.0610196590423584}
+08/30/2021 16:31:00 - INFO - __main__ - Step 18258: {'lr': 0.00048526150890096153, 'samples': 3505536, 'steps': 18257, 'loss/train': 1.6383503675460815}
+08/30/2021 16:31:00 - INFO - __main__ - Step 18259: {'lr': 0.0004852597136903213, 'samples': 3505728, 'steps': 18258, 'loss/train': 0.2615097165107727}
+08/30/2021 16:31:01 - INFO - __main__ - Step 18260: {'lr': 0.0004852579183736766, 'samples': 3505920, 'steps': 18259, 'loss/train': 1.326377511024475}
+08/30/2021 16:31:01 - INFO - __main__ - Step 18261: {'lr': 0.00048525612295102836, 'samples': 3506112, 'steps': 18260, 'loss/train': 2.922910213470459}
+08/30/2021 16:31:02 - INFO - __main__ - Step 18262: {'lr': 0.00048525432742237736, 'samples': 3506304, 'steps': 18261, 'loss/train': 0.17876708507537842}
+08/30/2021 16:31:03 - INFO - __main__ - Step 18263: {'lr': 0.00048525253178772435, 'samples': 3506496, 'steps': 18262, 'loss/train': 1.77130925655365}
+08/30/2021 16:31:03 - INFO - __main__ - Step 18264: {'lr': 0.0004852507360470702, 'samples': 3506688, 'steps': 18263, 'loss/train': 1.9590058326721191}
+08/30/2021 16:31:04 - INFO - __main__ - Step 18265: {'lr': 0.0004852489402004157, 'samples': 3506880, 'steps': 18264, 'loss/train': 1.867340087890625}
+08/30/2021 16:31:04 - INFO - __main__ - Step 18266: {'lr': 0.0004852471442477617, 'samples': 3507072, 'steps': 18265, 'loss/train': 1.7032133340835571}
+08/30/2021 16:31:06 - INFO - __main__ - Step 18267: {'lr': 0.0004852453481891089, 'samples': 3507264, 'steps': 18266, 'loss/train': 1.5362731218338013}
+08/30/2021 16:31:06 - INFO - __main__ - Step 18268: {'lr': 0.00048524355202445827, 'samples': 3507456, 'steps': 18267, 'loss/train': 2.047058343887329}
+08/30/2021 16:31:06 - INFO - __main__ - Step 18269: {'lr': 0.0004852417557538104, 'samples': 3507648, 'steps': 18268, 'loss/train': 1.3270645141601562}
+08/30/2021 16:31:07 - INFO - __main__ - Step 18270: {'lr': 0.00048523995937716625, 'samples': 3507840, 'steps': 18269, 'loss/train': 1.3608251810073853}
+08/30/2021 16:31:07 - INFO - __main__ - Step 18271: {'lr': 0.0004852381628945267, 'samples': 3508032, 'steps': 18270, 'loss/train': 2.296241521835327}
+08/30/2021 16:31:09 - INFO - __main__ - Step 18272: {'lr': 0.0004852363663058924, 'samples': 3508224, 'steps': 18271, 'loss/train': 1.6583689451217651}
+08/30/2021 16:31:09 - INFO - __main__ - Step 18273: {'lr': 0.0004852345696112642, 'samples': 3508416, 'steps': 18272, 'loss/train': 1.4764230251312256}
+08/30/2021 16:31:09 - INFO - __main__ - Step 18274: {'lr': 0.00048523277281064295, 'samples': 3508608, 'steps': 18273, 'loss/train': 1.6788078546524048}
+08/30/2021 16:31:10 - INFO - __main__ - Step 18275: {'lr': 0.0004852309759040294, 'samples': 3508800, 'steps': 18274, 'loss/train': 1.5933668613433838}
+08/30/2021 16:31:10 - INFO - __main__ - Step 18276: {'lr': 0.00048522917889142446, 'samples': 3508992, 'steps': 18275, 'loss/train': 1.636905550956726}
+08/30/2021 16:31:10 - INFO - __main__ - Step 18277: {'lr': 0.00048522738177282887, 'samples': 3509184, 'steps': 18276, 'loss/train': 1.4415043592453003}
+08/30/2021 16:31:12 - INFO - __main__ - Step 18278: {'lr': 0.0004852255845482435, 'samples': 3509376, 'steps': 18277, 'loss/train': 1.8900659084320068}
+08/30/2021 16:31:13 - INFO - __main__ - Step 18279: {'lr': 0.0004852237872176691, 'samples': 3509568, 'steps': 18278, 'loss/train': 0.18102802336215973}
+08/30/2021 16:31:13 - INFO - __main__ - Step 18280: {'lr': 0.00048522198978110645, 'samples': 3509760, 'steps': 18279, 'loss/train': 1.3858753442764282}
+08/30/2021 16:31:13 - INFO - __main__ - Step 18281: {'lr': 0.0004852201922385564, 'samples': 3509952, 'steps': 18280, 'loss/train': 1.6936274766921997}
+08/30/2021 16:31:14 - INFO - __main__ - Step 18282: {'lr': 0.00048521839459001977, 'samples': 3510144, 'steps': 18281, 'loss/train': 1.615212082862854}
+08/30/2021 16:31:15 - INFO - __main__ - Step 18283: {'lr': 0.0004852165968354973, 'samples': 3510336, 'steps': 18282, 'loss/train': 1.8196706771850586}
+08/30/2021 16:31:16 - INFO - __main__ - Step 18284: {'lr': 0.00048521479897499, 'samples': 3510528, 'steps': 18283, 'loss/train': 1.353030800819397}
+08/30/2021 16:31:16 - INFO - __main__ - Step 18285: {'lr': 0.0004852130010084984, 'samples': 3510720, 'steps': 18284, 'loss/train': 1.5243914127349854}
+08/30/2021 16:31:16 - INFO - __main__ - Step 18286: {'lr': 0.0004852112029360235, 'samples': 3510912, 'steps': 18285, 'loss/train': 1.9026896953582764}
+08/30/2021 16:31:17 - INFO - __main__ - Step 18287: {'lr': 0.0004852094047575661, 'samples': 3511104, 'steps': 18286, 'loss/train': 2.0276737213134766}
+08/30/2021 16:31:17 - INFO - __main__ - Step 18288: {'lr': 0.00048520760647312696, 'samples': 3511296, 'steps': 18287, 'loss/train': 1.7218397855758667}
+08/30/2021 16:31:19 - INFO - __main__ - Step 18289: {'lr': 0.00048520580808270687, 'samples': 3511488, 'steps': 18288, 'loss/train': 1.6105717420578003}
+08/30/2021 16:31:19 - INFO - __main__ - Step 18290: {'lr': 0.0004852040095863067, 'samples': 3511680, 'steps': 18289, 'loss/train': 1.9469579458236694}
+08/30/2021 16:31:19 - INFO - __main__ - Step 18291: {'lr': 0.0004852022109839273, 'samples': 3511872, 'steps': 18290, 'loss/train': 0.3960586488246918}
+08/30/2021 16:31:20 - INFO - __main__ - Step 18292: {'lr': 0.0004852004122755693, 'samples': 3512064, 'steps': 18291, 'loss/train': 2.3295421600341797}
+08/30/2021 16:31:20 - INFO - __main__ - Step 18293: {'lr': 0.00048519861346123363, 'samples': 3512256, 'steps': 18292, 'loss/train': 1.4214847087860107}
+08/30/2021 16:31:22 - INFO - __main__ - Step 18294: {'lr': 0.0004851968145409211, 'samples': 3512448, 'steps': 18293, 'loss/train': 1.611711025238037}
+08/30/2021 16:31:22 - INFO - __main__ - Step 18295: {'lr': 0.00048519501551463255, 'samples': 3512640, 'steps': 18294, 'loss/train': 2.0002479553222656}
+08/30/2021 16:31:22 - INFO - __main__ - Step 18296: {'lr': 0.0004851932163823688, 'samples': 3512832, 'steps': 18295, 'loss/train': 1.2055373191833496}
+08/30/2021 16:31:23 - INFO - __main__ - Step 18297: {'lr': 0.0004851914171441305, 'samples': 3513024, 'steps': 18296, 'loss/train': 1.1820570230484009}
+08/30/2021 16:31:23 - INFO - __main__ - Step 18298: {'lr': 0.00048518961779991866, 'samples': 3513216, 'steps': 18297, 'loss/train': 2.120363235473633}
+08/30/2021 16:31:26 - INFO - __main__ - Step 18299: {'lr': 0.00048518781834973405, 'samples': 3513408, 'steps': 18298, 'loss/train': 1.4115668535232544}
+08/30/2021 16:31:26 - INFO - __main__ - Step 18300: {'lr': 0.0004851860187935773, 'samples': 3513600, 'steps': 18299, 'loss/train': 1.4641038179397583}
+08/30/2021 16:31:27 - INFO - __main__ - Step 18301: {'lr': 0.0004851842191314494, 'samples': 3513792, 'steps': 18300, 'loss/train': 2.2291409969329834}
+08/30/2021 16:31:27 - INFO - __main__ - Step 18302: {'lr': 0.0004851824193633512, 'samples': 3513984, 'steps': 18301, 'loss/train': 1.5605565309524536}
+08/30/2021 16:31:27 - INFO - __main__ - Step 18303: {'lr': 0.00048518061948928337, 'samples': 3514176, 'steps': 18302, 'loss/train': 1.9699370861053467}
+08/30/2021 16:31:28 - INFO - __main__ - Step 18304: {'lr': 0.0004851788195092468, 'samples': 3514368, 'steps': 18303, 'loss/train': 0.10047666728496552}
+08/30/2021 16:31:28 - INFO - __main__ - Step 18305: {'lr': 0.00048517701942324225, 'samples': 3514560, 'steps': 18304, 'loss/train': 1.6972315311431885}
+08/30/2021 16:31:29 - INFO - __main__ - Step 18306: {'lr': 0.00048517521923127063, 'samples': 3514752, 'steps': 18305, 'loss/train': 1.4234768152236938}
+08/30/2021 16:31:30 - INFO - __main__ - Step 18307: {'lr': 0.00048517341893333267, 'samples': 3514944, 'steps': 18306, 'loss/train': 1.5142172574996948}
+08/30/2021 16:31:30 - INFO - __main__ - Step 18308: {'lr': 0.0004851716185294291, 'samples': 3515136, 'steps': 18307, 'loss/train': 2.0314602851867676}
+08/30/2021 16:31:31 - INFO - __main__ - Step 18309: {'lr': 0.00048516981801956097, 'samples': 3515328, 'steps': 18308, 'loss/train': 1.5293121337890625}
+08/30/2021 16:31:31 - INFO - __main__ - Step 18310: {'lr': 0.00048516801740372886, 'samples': 3515520, 'steps': 18309, 'loss/train': 1.6754064559936523}
+08/30/2021 16:31:33 - INFO - __main__ - Step 18311: {'lr': 0.0004851662166819337, 'samples': 3515712, 'steps': 18310, 'loss/train': 1.343644618988037}
+08/30/2021 16:31:33 - INFO - __main__ - Step 18312: {'lr': 0.00048516441585417624, 'samples': 3515904, 'steps': 18311, 'loss/train': 1.9953339099884033}
+08/30/2021 16:31:33 - INFO - __main__ - Step 18313: {'lr': 0.0004851626149204573, 'samples': 3516096, 'steps': 18312, 'loss/train': 1.207190990447998}
+08/30/2021 16:31:34 - INFO - __main__ - Step 18314: {'lr': 0.0004851608138807778, 'samples': 3516288, 'steps': 18313, 'loss/train': 1.730093002319336}
+08/30/2021 16:31:34 - INFO - __main__ - Step 18315: {'lr': 0.0004851590127351384, 'samples': 3516480, 'steps': 18314, 'loss/train': 2.054384708404541}
+08/30/2021 16:31:36 - INFO - __main__ - Step 18316: {'lr': 0.0004851572114835401, 'samples': 3516672, 'steps': 18315, 'loss/train': 2.286177158355713}
+08/30/2021 16:31:36 - INFO - __main__ - Step 18317: {'lr': 0.0004851554101259834, 'samples': 3516864, 'steps': 18316, 'loss/train': 1.541135311126709}
+08/30/2021 16:31:37 - INFO - __main__ - Step 18318: {'lr': 0.00048515360866246943, 'samples': 3517056, 'steps': 18317, 'loss/train': 1.7443363666534424}
+08/30/2021 16:31:37 - INFO - __main__ - Step 18319: {'lr': 0.00048515180709299884, 'samples': 3517248, 'steps': 18318, 'loss/train': 3.8915019035339355}
+08/30/2021 16:31:37 - INFO - __main__ - Step 18320: {'lr': 0.0004851500054175725, 'samples': 3517440, 'steps': 18319, 'loss/train': 1.7440677881240845}
+08/30/2021 16:31:39 - INFO - __main__ - Step 18321: {'lr': 0.00048514820363619116, 'samples': 3517632, 'steps': 18320, 'loss/train': 0.1379471719264984}
+08/30/2021 16:31:39 - INFO - __main__ - Step 18322: {'lr': 0.0004851464017488556, 'samples': 3517824, 'steps': 18321, 'loss/train': 0.9234429597854614}
+08/30/2021 16:31:40 - INFO - __main__ - Step 18323: {'lr': 0.0004851445997555668, 'samples': 3518016, 'steps': 18322, 'loss/train': 2.0152969360351562}
+08/30/2021 16:31:40 - INFO - __main__ - Step 18324: {'lr': 0.00048514279765632547, 'samples': 3518208, 'steps': 18323, 'loss/train': 1.6747567653656006}
+08/30/2021 16:31:40 - INFO - __main__ - Step 18325: {'lr': 0.0004851409954511324, 'samples': 3518400, 'steps': 18324, 'loss/train': 1.8239686489105225}
+08/30/2021 16:31:42 - INFO - __main__ - Step 18326: {'lr': 0.0004851391931399884, 'samples': 3518592, 'steps': 18325, 'loss/train': 1.2097152471542358}
+08/30/2021 16:31:42 - INFO - __main__ - Step 18327: {'lr': 0.0004851373907228943, 'samples': 3518784, 'steps': 18326, 'loss/train': 1.3782691955566406}
+08/30/2021 16:31:43 - INFO - __main__ - Step 18328: {'lr': 0.00048513558819985106, 'samples': 3518976, 'steps': 18327, 'loss/train': 1.735744595527649}
+08/30/2021 16:31:43 - INFO - __main__ - Step 18329: {'lr': 0.0004851337855708592, 'samples': 3519168, 'steps': 18328, 'loss/train': 1.9939866065979004}
+08/30/2021 16:31:43 - INFO - __main__ - Step 18330: {'lr': 0.0004851319828359198, 'samples': 3519360, 'steps': 18329, 'loss/train': 1.025618076324463}
+08/30/2021 16:31:45 - INFO - __main__ - Step 18331: {'lr': 0.0004851301799950334, 'samples': 3519552, 'steps': 18330, 'loss/train': 2.0228524208068848}
+08/30/2021 16:31:45 - INFO - __main__ - Step 18332: {'lr': 0.00048512837704820107, 'samples': 3519744, 'steps': 18331, 'loss/train': 1.407360315322876}
+08/30/2021 16:31:46 - INFO - __main__ - Step 18333: {'lr': 0.00048512657399542346, 'samples': 3519936, 'steps': 18332, 'loss/train': 1.6591839790344238}
+08/30/2021 16:31:46 - INFO - __main__ - Step 18334: {'lr': 0.0004851247708367015, 'samples': 3520128, 'steps': 18333, 'loss/train': 5.407085418701172}
+08/30/2021 16:31:46 - INFO - __main__ - Step 18335: {'lr': 0.000485122967572036, 'samples': 3520320, 'steps': 18334, 'loss/train': 1.739969253540039}
+08/30/2021 16:31:47 - INFO - __main__ - Step 18336: {'lr': 0.0004851211642014276, 'samples': 3520512, 'steps': 18335, 'loss/train': 1.5402262210845947}
+08/30/2021 16:31:48 - INFO - __main__ - Step 18337: {'lr': 0.0004851193607248773, 'samples': 3520704, 'steps': 18336, 'loss/train': 2.23903489112854}
+08/30/2021 16:31:49 - INFO - __main__ - Step 18338: {'lr': 0.00048511755714238585, 'samples': 3520896, 'steps': 18337, 'loss/train': 1.6420117616653442}
+08/30/2021 16:31:49 - INFO - __main__ - Step 18339: {'lr': 0.0004851157534539541, 'samples': 3521088, 'steps': 18338, 'loss/train': 2.079241991043091}
+08/30/2021 16:31:49 - INFO - __main__ - Step 18340: {'lr': 0.0004851139496595827, 'samples': 3521280, 'steps': 18339, 'loss/train': 1.5721169710159302}
+08/30/2021 16:31:50 - INFO - __main__ - Step 18341: {'lr': 0.00048511214575927265, 'samples': 3521472, 'steps': 18340, 'loss/train': 2.0448737144470215}
+08/30/2021 16:31:51 - INFO - __main__ - Step 18342: {'lr': 0.0004851103417530247, 'samples': 3521664, 'steps': 18341, 'loss/train': 1.964516282081604}
+08/30/2021 16:31:52 - INFO - __main__ - Step 18343: {'lr': 0.0004851085376408396, 'samples': 3521856, 'steps': 18342, 'loss/train': 1.792725920677185}
+08/30/2021 16:31:52 - INFO - __main__ - Step 18344: {'lr': 0.0004851067334227183, 'samples': 3522048, 'steps': 18343, 'loss/train': 1.1735317707061768}
+08/30/2021 16:31:52 - INFO - __main__ - Step 18345: {'lr': 0.0004851049290986615, 'samples': 3522240, 'steps': 18344, 'loss/train': 2.0181925296783447}
+08/30/2021 16:31:53 - INFO - __main__ - Step 18346: {'lr': 0.00048510312466867, 'samples': 3522432, 'steps': 18345, 'loss/train': 1.9342454671859741}
+08/30/2021 16:31:54 - INFO - __main__ - Step 18347: {'lr': 0.0004851013201327448, 'samples': 3522624, 'steps': 18346, 'loss/train': 1.4876445531845093}
+08/30/2021 16:31:55 - INFO - __main__ - Step 18348: {'lr': 0.0004850995154908864, 'samples': 3522816, 'steps': 18347, 'loss/train': 1.9688720703125}
+08/30/2021 16:31:55 - INFO - __main__ - Step 18349: {'lr': 0.0004850977107430959, 'samples': 3523008, 'steps': 18348, 'loss/train': 1.1184128522872925}
+08/30/2021 16:31:55 - INFO - __main__ - Step 18350: {'lr': 0.000485095905889374, 'samples': 3523200, 'steps': 18349, 'loss/train': 1.152635097503662}
+08/30/2021 16:31:56 - INFO - __main__ - Step 18351: {'lr': 0.00048509410092972144, 'samples': 3523392, 'steps': 18350, 'loss/train': 1.8936458826065063}
+08/30/2021 16:31:58 - INFO - __main__ - Step 18352: {'lr': 0.0004850922958641392, 'samples': 3523584, 'steps': 18351, 'loss/train': 1.6338152885437012}
+08/30/2021 16:31:58 - INFO - __main__ - Step 18353: {'lr': 0.0004850904906926279, 'samples': 3523776, 'steps': 18352, 'loss/train': 1.175215721130371}
+08/30/2021 16:31:58 - INFO - __main__ - Step 18354: {'lr': 0.0004850886854151885, 'samples': 3523968, 'steps': 18353, 'loss/train': 1.374414086341858}
+08/30/2021 16:31:59 - INFO - __main__ - Step 18355: {'lr': 0.0004850868800318218, 'samples': 3524160, 'steps': 18354, 'loss/train': 1.856572151184082}
+08/30/2021 16:31:59 - INFO - __main__ - Step 18356: {'lr': 0.00048508507454252846, 'samples': 3524352, 'steps': 18355, 'loss/train': 1.1230909824371338}
+08/30/2021 16:31:59 - INFO - __main__ - Step 18357: {'lr': 0.00048508326894730955, 'samples': 3524544, 'steps': 18356, 'loss/train': 2.62599515914917}
+08/30/2021 16:32:01 - INFO - __main__ - Step 18358: {'lr': 0.00048508146324616566, 'samples': 3524736, 'steps': 18357, 'loss/train': 1.2977162599563599}
+08/30/2021 16:32:01 - INFO - __main__ - Step 18359: {'lr': 0.0004850796574390977, 'samples': 3524928, 'steps': 18358, 'loss/train': 1.9402198791503906}
+08/30/2021 16:32:02 - INFO - __main__ - Step 18360: {'lr': 0.0004850778515261065, 'samples': 3525120, 'steps': 18359, 'loss/train': 1.5444425344467163}
+08/30/2021 16:32:02 - INFO - __main__ - Step 18361: {'lr': 0.0004850760455071929, 'samples': 3525312, 'steps': 18360, 'loss/train': 1.594689965248108}
+08/30/2021 16:32:02 - INFO - __main__ - Step 18362: {'lr': 0.0004850742393823576, 'samples': 3525504, 'steps': 18361, 'loss/train': 0.8999673128128052}
+08/30/2021 16:32:04 - INFO - __main__ - Step 18363: {'lr': 0.0004850724331516014, 'samples': 3525696, 'steps': 18362, 'loss/train': 1.3309015035629272}
+08/30/2021 16:32:04 - INFO - __main__ - Step 18364: {'lr': 0.0004850706268149253, 'samples': 3525888, 'steps': 18363, 'loss/train': 1.3089945316314697}
+08/30/2021 16:32:05 - INFO - __main__ - Step 18365: {'lr': 0.00048506882037233, 'samples': 3526080, 'steps': 18364, 'loss/train': 1.3521586656570435}
+08/30/2021 16:32:05 - INFO - __main__ - Step 18366: {'lr': 0.0004850670138238162, 'samples': 3526272, 'steps': 18365, 'loss/train': 1.974701166152954}
+08/30/2021 16:32:06 - INFO - __main__ - Step 18367: {'lr': 0.00048506520716938496, 'samples': 3526464, 'steps': 18366, 'loss/train': 1.5892881155014038}
+08/30/2021 16:32:07 - INFO - __main__ - Step 18368: {'lr': 0.00048506340040903697, 'samples': 3526656, 'steps': 18367, 'loss/train': 1.944163203239441}
+08/30/2021 16:32:08 - INFO - __main__ - Step 18369: {'lr': 0.00048506159354277294, 'samples': 3526848, 'steps': 18368, 'loss/train': 2.3988265991210938}
+08/30/2021 16:32:08 - INFO - __main__ - Step 18370: {'lr': 0.00048505978657059385, 'samples': 3527040, 'steps': 18369, 'loss/train': 1.93350350856781}
+08/30/2021 16:32:08 - INFO - __main__ - Step 18371: {'lr': 0.0004850579794925004, 'samples': 3527232, 'steps': 18370, 'loss/train': 2.4299449920654297}
+08/30/2021 16:32:09 - INFO - __main__ - Step 18372: {'lr': 0.0004850561723084935, 'samples': 3527424, 'steps': 18371, 'loss/train': 1.7484010457992554}
+08/30/2021 16:32:10 - INFO - __main__ - Step 18373: {'lr': 0.0004850543650185739, 'samples': 3527616, 'steps': 18372, 'loss/train': 1.9789292812347412}
+08/30/2021 16:32:11 - INFO - __main__ - Step 18374: {'lr': 0.0004850525576227425, 'samples': 3527808, 'steps': 18373, 'loss/train': 1.1833218336105347}
+08/30/2021 16:32:11 - INFO - __main__ - Step 18375: {'lr': 0.000485050750121, 'samples': 3528000, 'steps': 18374, 'loss/train': 1.0919058322906494}
+08/30/2021 16:32:11 - INFO - __main__ - Step 18376: {'lr': 0.0004850489425133472, 'samples': 3528192, 'steps': 18375, 'loss/train': 1.805298089981079}
+08/30/2021 16:32:12 - INFO - __main__ - Step 18377: {'lr': 0.000485047134799785, 'samples': 3528384, 'steps': 18376, 'loss/train': 1.5543766021728516}
+08/30/2021 16:32:14 - INFO - __main__ - Step 18378: {'lr': 0.00048504532698031416, 'samples': 3528576, 'steps': 18377, 'loss/train': 1.73404061794281}
+08/30/2021 16:32:14 - INFO - __main__ - Step 18379: {'lr': 0.0004850435190549356, 'samples': 3528768, 'steps': 18378, 'loss/train': 1.9069091081619263}
+08/30/2021 16:32:14 - INFO - __main__ - Step 18380: {'lr': 0.00048504171102365, 'samples': 3528960, 'steps': 18379, 'loss/train': 1.5401171445846558}
+08/30/2021 16:32:15 - INFO - __main__ - Step 18381: {'lr': 0.0004850399028864583, 'samples': 3529152, 'steps': 18380, 'loss/train': 0.7602036595344543}
+08/30/2021 16:32:15 - INFO - __main__ - Step 18382: {'lr': 0.0004850380946433611, 'samples': 3529344, 'steps': 18381, 'loss/train': 2.0335865020751953}
+08/30/2021 16:32:15 - INFO - __main__ - Step 18383: {'lr': 0.00048503628629435947, 'samples': 3529536, 'steps': 18382, 'loss/train': 1.367948055267334}
+08/30/2021 16:32:17 - INFO - __main__ - Step 18384: {'lr': 0.0004850344778394541, 'samples': 3529728, 'steps': 18383, 'loss/train': 1.0850682258605957}
+08/30/2021 16:32:18 - INFO - __main__ - Step 18385: {'lr': 0.0004850326692786459, 'samples': 3529920, 'steps': 18384, 'loss/train': 2.2030513286590576}
+08/30/2021 16:32:18 - INFO - __main__ - Step 18386: {'lr': 0.00048503086061193546, 'samples': 3530112, 'steps': 18385, 'loss/train': 2.3353638648986816}
+08/30/2021 16:32:18 - INFO - __main__ - Step 18387: {'lr': 0.0004850290518393238, 'samples': 3530304, 'steps': 18386, 'loss/train': 1.7692161798477173}
+08/30/2021 16:32:19 - INFO - __main__ - Step 18388: {'lr': 0.0004850272429608117, 'samples': 3530496, 'steps': 18387, 'loss/train': 1.059675693511963}
+08/30/2021 16:32:20 - INFO - __main__ - Step 18389: {'lr': 0.0004850254339764, 'samples': 3530688, 'steps': 18388, 'loss/train': 1.7607570886611938}
+08/30/2021 16:32:21 - INFO - __main__ - Step 18390: {'lr': 0.00048502362488608933, 'samples': 3530880, 'steps': 18389, 'loss/train': 1.701917290687561}
+08/30/2021 16:32:21 - INFO - __main__ - Step 18391: {'lr': 0.0004850218156898807, 'samples': 3531072, 'steps': 18390, 'loss/train': 1.5931764841079712}
+08/30/2021 16:32:21 - INFO - __main__ - Step 18392: {'lr': 0.00048502000638777487, 'samples': 3531264, 'steps': 18391, 'loss/train': 2.0616695880889893}
+08/30/2021 16:32:22 - INFO - __main__ - Step 18393: {'lr': 0.0004850181969797727, 'samples': 3531456, 'steps': 18392, 'loss/train': 0.8655185103416443}
+08/30/2021 16:32:23 - INFO - __main__ - Step 18394: {'lr': 0.00048501638746587493, 'samples': 3531648, 'steps': 18393, 'loss/train': 1.868634819984436}
+08/30/2021 16:32:24 - INFO - __main__ - Step 18395: {'lr': 0.0004850145778460824, 'samples': 3531840, 'steps': 18394, 'loss/train': 1.9058949947357178}
+08/30/2021 16:32:24 - INFO - __main__ - Step 18396: {'lr': 0.00048501276812039585, 'samples': 3532032, 'steps': 18395, 'loss/train': 1.474753737449646}
+08/30/2021 16:32:24 - INFO - __main__ - Step 18397: {'lr': 0.00048501095828881627, 'samples': 3532224, 'steps': 18396, 'loss/train': 1.768510103225708}
+08/30/2021 16:32:25 - INFO - __main__ - Step 18398: {'lr': 0.00048500914835134434, 'samples': 3532416, 'steps': 18397, 'loss/train': 1.8040025234222412}
+08/30/2021 16:32:25 - INFO - __main__ - Step 18399: {'lr': 0.00048500733830798094, 'samples': 3532608, 'steps': 18398, 'loss/train': 1.8621283769607544}
+08/30/2021 16:32:26 - INFO - __main__ - Step 18400: {'lr': 0.00048500552815872687, 'samples': 3532800, 'steps': 18399, 'loss/train': 1.68860924243927}
+08/30/2021 16:32:27 - INFO - __main__ - Step 18401: {'lr': 0.0004850037179035829, 'samples': 3532992, 'steps': 18400, 'loss/train': 2.0445046424865723}
+08/30/2021 16:32:27 - INFO - __main__ - Step 18402: {'lr': 0.00048500190754254994, 'samples': 3533184, 'steps': 18401, 'loss/train': 1.752744197845459}
+08/30/2021 16:32:28 - INFO - __main__ - Step 18403: {'lr': 0.00048500009707562865, 'samples': 3533376, 'steps': 18402, 'loss/train': 1.315450668334961}
+08/30/2021 16:32:28 - INFO - __main__ - Step 18404: {'lr': 0.00048499828650281994, 'samples': 3533568, 'steps': 18403, 'loss/train': 0.9854258894920349}
+08/30/2021 16:32:30 - INFO - __main__ - Step 18405: {'lr': 0.00048499647582412475, 'samples': 3533760, 'steps': 18404, 'loss/train': 2.5694668292999268}
+08/30/2021 16:32:30 - INFO - __main__ - Step 18406: {'lr': 0.0004849946650395437, 'samples': 3533952, 'steps': 18405, 'loss/train': 1.2151046991348267}
+08/30/2021 16:32:30 - INFO - __main__ - Step 18407: {'lr': 0.0004849928541490777, 'samples': 3534144, 'steps': 18406, 'loss/train': 0.6300547122955322}
+08/30/2021 16:32:31 - INFO - __main__ - Step 18408: {'lr': 0.0004849910431527275, 'samples': 3534336, 'steps': 18407, 'loss/train': 1.6237766742706299}
+08/30/2021 16:32:31 - INFO - __main__ - Step 18409: {'lr': 0.000484989232050494, 'samples': 3534528, 'steps': 18408, 'loss/train': 1.6840767860412598}
+08/30/2021 16:32:33 - INFO - __main__ - Step 18410: {'lr': 0.00048498742084237796, 'samples': 3534720, 'steps': 18409, 'loss/train': 1.428397536277771}
+08/30/2021 16:32:34 - INFO - __main__ - Step 18411: {'lr': 0.00048498560952838025, 'samples': 3534912, 'steps': 18410, 'loss/train': 1.7967861890792847}
+08/30/2021 16:32:34 - INFO - __main__ - Step 18412: {'lr': 0.00048498379810850157, 'samples': 3535104, 'steps': 18411, 'loss/train': 1.5502450466156006}
+08/30/2021 16:32:34 - INFO - __main__ - Step 18413: {'lr': 0.0004849819865827429, 'samples': 3535296, 'steps': 18412, 'loss/train': 1.7416106462478638}
+08/30/2021 16:32:35 - INFO - __main__ - Step 18414: {'lr': 0.0004849801749511049, 'samples': 3535488, 'steps': 18413, 'loss/train': 2.118992805480957}
+08/30/2021 16:32:36 - INFO - __main__ - Step 18415: {'lr': 0.00048497836321358855, 'samples': 3535680, 'steps': 18414, 'loss/train': 1.533248782157898}
+08/30/2021 16:32:37 - INFO - __main__ - Step 18416: {'lr': 0.00048497655137019454, 'samples': 3535872, 'steps': 18415, 'loss/train': 1.6962758302688599}
+08/30/2021 16:32:37 - INFO - __main__ - Step 18417: {'lr': 0.0004849747394209237, 'samples': 3536064, 'steps': 18416, 'loss/train': 1.527657151222229}
+08/30/2021 16:32:37 - INFO - __main__ - Step 18418: {'lr': 0.00048497292736577685, 'samples': 3536256, 'steps': 18417, 'loss/train': 1.5346958637237549}
+08/30/2021 16:32:38 - INFO - __main__ - Step 18419: {'lr': 0.0004849711152047549, 'samples': 3536448, 'steps': 18418, 'loss/train': 1.7111904621124268}
+08/30/2021 16:32:38 - INFO - __main__ - Step 18420: {'lr': 0.0004849693029378585, 'samples': 3536640, 'steps': 18419, 'loss/train': 1.6931809186935425}
+08/30/2021 16:32:39 - INFO - __main__ - Step 18421: {'lr': 0.0004849674905650886, 'samples': 3536832, 'steps': 18420, 'loss/train': 1.9758563041687012}
+08/30/2021 16:32:40 - INFO - __main__ - Step 18422: {'lr': 0.000484965678086446, 'samples': 3537024, 'steps': 18421, 'loss/train': 1.5684478282928467}
+08/30/2021 16:32:40 - INFO - __main__ - Step 18423: {'lr': 0.0004849638655019315, 'samples': 3537216, 'steps': 18422, 'loss/train': 1.285486102104187}
+08/30/2021 16:32:41 - INFO - __main__ - Step 18424: {'lr': 0.0004849620528115458, 'samples': 3537408, 'steps': 18423, 'loss/train': 1.4267280101776123}
+08/30/2021 16:32:41 - INFO - __main__ - Step 18425: {'lr': 0.0004849602400152899, 'samples': 3537600, 'steps': 18424, 'loss/train': 1.044335126876831}
+08/30/2021 16:32:42 - INFO - __main__ - Step 18426: {'lr': 0.0004849584271131646, 'samples': 3537792, 'steps': 18425, 'loss/train': 1.9281814098358154}
+08/30/2021 16:32:43 - INFO - __main__ - Step 18427: {'lr': 0.00048495661410517056, 'samples': 3537984, 'steps': 18426, 'loss/train': 1.8135710954666138}
+08/30/2021 16:32:43 - INFO - __main__ - Step 18428: {'lr': 0.0004849548009913087, 'samples': 3538176, 'steps': 18427, 'loss/train': 3.7530477046966553}
+08/30/2021 16:32:44 - INFO - __main__ - Step 18429: {'lr': 0.00048495298777157994, 'samples': 3538368, 'steps': 18428, 'loss/train': 1.0768924951553345}
+08/30/2021 16:32:44 - INFO - __main__ - Step 18430: {'lr': 0.0004849511744459849, 'samples': 3538560, 'steps': 18429, 'loss/train': 1.7873797416687012}
+08/30/2021 16:32:45 - INFO - __main__ - Step 18431: {'lr': 0.00048494936101452446, 'samples': 3538752, 'steps': 18430, 'loss/train': 1.1974409818649292}
+08/30/2021 16:32:46 - INFO - __main__ - Step 18432: {'lr': 0.00048494754747719954, 'samples': 3538944, 'steps': 18431, 'loss/train': 2.0334620475769043}
+08/30/2021 16:32:46 - INFO - __main__ - Step 18433: {'lr': 0.00048494573383401084, 'samples': 3539136, 'steps': 18432, 'loss/train': 1.6517343521118164}
+08/30/2021 16:32:47 - INFO - __main__ - Step 18434: {'lr': 0.0004849439200849592, 'samples': 3539328, 'steps': 18433, 'loss/train': 1.7558435201644897}
+08/30/2021 16:32:47 - INFO - __main__ - Step 18435: {'lr': 0.0004849421062300455, 'samples': 3539520, 'steps': 18434, 'loss/train': 1.7587658166885376}
+08/30/2021 16:32:48 - INFO - __main__ - Step 18436: {'lr': 0.0004849402922692705, 'samples': 3539712, 'steps': 18435, 'loss/train': 2.0340306758880615}
+08/30/2021 16:32:49 - INFO - __main__ - Step 18437: {'lr': 0.000484938478202635, 'samples': 3539904, 'steps': 18436, 'loss/train': 1.9905076026916504}
+08/30/2021 16:32:49 - INFO - __main__ - Step 18438: {'lr': 0.0004849366640301399, 'samples': 3540096, 'steps': 18437, 'loss/train': 1.4739770889282227}
+08/30/2021 16:32:50 - INFO - __main__ - Step 18439: {'lr': 0.00048493484975178593, 'samples': 3540288, 'steps': 18438, 'loss/train': 1.9535123109817505}
+08/30/2021 16:32:50 - INFO - __main__ - Step 18440: {'lr': 0.00048493303536757394, 'samples': 3540480, 'steps': 18439, 'loss/train': 1.733303427696228}
+08/30/2021 16:32:52 - INFO - __main__ - Step 18441: {'lr': 0.00048493122087750473, 'samples': 3540672, 'steps': 18440, 'loss/train': 1.183138370513916}
+08/30/2021 16:32:52 - INFO - __main__ - Step 18442: {'lr': 0.0004849294062815792, 'samples': 3540864, 'steps': 18441, 'loss/train': 1.2568312883377075}
+08/30/2021 16:32:52 - INFO - __main__ - Step 18443: {'lr': 0.000484927591579798, 'samples': 3541056, 'steps': 18442, 'loss/train': 1.481009840965271}
+08/30/2021 16:32:53 - INFO - __main__ - Step 18444: {'lr': 0.0004849257767721622, 'samples': 3541248, 'steps': 18443, 'loss/train': 1.2963892221450806}
+08/30/2021 16:32:53 - INFO - __main__ - Step 18445: {'lr': 0.00048492396185867236, 'samples': 3541440, 'steps': 18444, 'loss/train': 1.720694899559021}
+08/30/2021 16:32:53 - INFO - __main__ - Step 18446: {'lr': 0.0004849221468393294, 'samples': 3541632, 'steps': 18445, 'loss/train': 1.6941791772842407}
+08/30/2021 16:32:55 - INFO - __main__ - Step 18447: {'lr': 0.00048492033171413425, 'samples': 3541824, 'steps': 18446, 'loss/train': 1.7716199159622192}
+08/30/2021 16:32:55 - INFO - __main__ - Step 18448: {'lr': 0.00048491851648308756, 'samples': 3542016, 'steps': 18447, 'loss/train': 1.8997448682785034}
+08/30/2021 16:32:56 - INFO - __main__ - Step 18449: {'lr': 0.00048491670114619026, 'samples': 3542208, 'steps': 18448, 'loss/train': 0.9838755130767822}
+08/30/2021 16:32:56 - INFO - __main__ - Step 18450: {'lr': 0.000484914885703443, 'samples': 3542400, 'steps': 18449, 'loss/train': 1.8256545066833496}
+08/30/2021 16:32:56 - INFO - __main__ - Step 18451: {'lr': 0.00048491307015484684, 'samples': 3542592, 'steps': 18450, 'loss/train': 2.717716693878174}
+08/30/2021 16:32:58 - INFO - __main__ - Step 18452: {'lr': 0.0004849112545004024, 'samples': 3542784, 'steps': 18451, 'loss/train': 1.6457176208496094}
+08/30/2021 16:32:59 - INFO - __main__ - Step 18453: {'lr': 0.00048490943874011054, 'samples': 3542976, 'steps': 18452, 'loss/train': 1.8555002212524414}
+08/30/2021 16:32:59 - INFO - __main__ - Step 18454: {'lr': 0.00048490762287397215, 'samples': 3543168, 'steps': 18453, 'loss/train': 0.8818188309669495}
+08/30/2021 16:32:59 - INFO - __main__ - Step 18455: {'lr': 0.00048490580690198804, 'samples': 3543360, 'steps': 18454, 'loss/train': 1.917466163635254}
+08/30/2021 16:33:00 - INFO - __main__ - Step 18456: {'lr': 0.000484903990824159, 'samples': 3543552, 'steps': 18455, 'loss/train': 1.6682443618774414}
+08/30/2021 16:33:01 - INFO - __main__ - Step 18457: {'lr': 0.0004849021746404859, 'samples': 3543744, 'steps': 18456, 'loss/train': 1.5969135761260986}
+08/30/2021 16:33:02 - INFO - __main__ - Step 18458: {'lr': 0.00048490035835096936, 'samples': 3543936, 'steps': 18457, 'loss/train': 1.598833441734314}
+08/30/2021 16:33:02 - INFO - __main__ - Step 18459: {'lr': 0.0004848985419556104, 'samples': 3544128, 'steps': 18458, 'loss/train': 1.4627039432525635}
+08/30/2021 16:33:03 - INFO - __main__ - Step 18460: {'lr': 0.0004848967254544099, 'samples': 3544320, 'steps': 18459, 'loss/train': 1.282549500465393}
+08/30/2021 16:33:03 - INFO - __main__ - Step 18461: {'lr': 0.00048489490884736844, 'samples': 3544512, 'steps': 18460, 'loss/train': 1.6859853267669678}
+08/30/2021 16:33:03 - INFO - __main__ - Step 18462: {'lr': 0.00048489309213448696, 'samples': 3544704, 'steps': 18461, 'loss/train': 0.12266451865434647}
+08/30/2021 16:33:05 - INFO - __main__ - Step 18463: {'lr': 0.00048489127531576627, 'samples': 3544896, 'steps': 18462, 'loss/train': 2.86110258102417}
+08/30/2021 16:33:06 - INFO - __main__ - Step 18464: {'lr': 0.0004848894583912072, 'samples': 3545088, 'steps': 18463, 'loss/train': 1.9362525939941406}
+08/30/2021 16:33:06 - INFO - __main__ - Step 18465: {'lr': 0.00048488764136081063, 'samples': 3545280, 'steps': 18464, 'loss/train': 1.3914740085601807}
+08/30/2021 16:33:07 - INFO - __main__ - Step 18466: {'lr': 0.00048488582422457726, 'samples': 3545472, 'steps': 18465, 'loss/train': 1.8300514221191406}
+08/30/2021 16:33:07 - INFO - __main__ - Step 18467: {'lr': 0.000484884006982508, 'samples': 3545664, 'steps': 18466, 'loss/train': 1.2591675519943237}
+08/30/2021 16:33:09 - INFO - __main__ - Step 18468: {'lr': 0.0004848821896346036, 'samples': 3545856, 'steps': 18467, 'loss/train': 1.572219967842102}
+08/30/2021 16:33:09 - INFO - __main__ - Step 18469: {'lr': 0.0004848803721808649, 'samples': 3546048, 'steps': 18468, 'loss/train': 1.520451307296753}
+08/30/2021 16:33:10 - INFO - __main__ - Step 18470: {'lr': 0.0004848785546212927, 'samples': 3546240, 'steps': 18469, 'loss/train': 1.6013100147247314}
+08/30/2021 16:33:10 - INFO - __main__ - Step 18471: {'lr': 0.00048487673695588794, 'samples': 3546432, 'steps': 18470, 'loss/train': 0.8847469091415405}
+08/30/2021 16:33:10 - INFO - __main__ - Step 18472: {'lr': 0.00048487491918465135, 'samples': 3546624, 'steps': 18471, 'loss/train': 1.629996418952942}
+08/30/2021 16:33:11 - INFO - __main__ - Step 18473: {'lr': 0.00048487310130758366, 'samples': 3546816, 'steps': 18472, 'loss/train': 1.4766883850097656}
+08/30/2021 16:33:12 - INFO - __main__ - Step 18474: {'lr': 0.00048487128332468576, 'samples': 3547008, 'steps': 18473, 'loss/train': 1.941003680229187}
+08/30/2021 16:33:13 - INFO - __main__ - Step 18475: {'lr': 0.00048486946523595856, 'samples': 3547200, 'steps': 18474, 'loss/train': 1.760926604270935}
+08/30/2021 16:33:13 - INFO - __main__ - Step 18476: {'lr': 0.00048486764704140276, 'samples': 3547392, 'steps': 18475, 'loss/train': 1.8866465091705322}
+08/30/2021 16:33:13 - INFO - __main__ - Step 18477: {'lr': 0.00048486582874101924, 'samples': 3547584, 'steps': 18476, 'loss/train': 1.8096379041671753}
+08/30/2021 16:33:14 - INFO - __main__ - Step 18478: {'lr': 0.0004848640103348088, 'samples': 3547776, 'steps': 18477, 'loss/train': 1.8322175741195679}
+08/30/2021 16:33:15 - INFO - __main__ - Step 18479: {'lr': 0.00048486219182277226, 'samples': 3547968, 'steps': 18478, 'loss/train': 1.4215279817581177}
+08/30/2021 16:33:15 - INFO - __main__ - Step 18480: {'lr': 0.00048486037320491043, 'samples': 3548160, 'steps': 18479, 'loss/train': 2.114464044570923}
+08/30/2021 16:33:16 - INFO - __main__ - Step 18481: {'lr': 0.0004848585544812242, 'samples': 3548352, 'steps': 18480, 'loss/train': 2.0277700424194336}
+08/30/2021 16:33:16 - INFO - __main__ - Step 18482: {'lr': 0.0004848567356517143, 'samples': 3548544, 'steps': 18481, 'loss/train': 1.935502290725708}
+08/30/2021 16:33:17 - INFO - __main__ - Step 18483: {'lr': 0.00048485491671638146, 'samples': 3548736, 'steps': 18482, 'loss/train': 1.707394003868103}
+08/30/2021 16:33:18 - INFO - __main__ - Step 18484: {'lr': 0.0004848530976752268, 'samples': 3548928, 'steps': 18483, 'loss/train': 1.799896001815796}
+08/30/2021 16:33:19 - INFO - __main__ - Step 18485: {'lr': 0.0004848512785282508, 'samples': 3549120, 'steps': 18484, 'loss/train': 2.754084348678589}
+08/30/2021 16:33:19 - INFO - __main__ - Step 18486: {'lr': 0.00048484945927545456, 'samples': 3549312, 'steps': 18485, 'loss/train': 1.213364601135254}
+08/30/2021 16:33:19 - INFO - __main__ - Step 18487: {'lr': 0.0004848476399168387, 'samples': 3549504, 'steps': 18486, 'loss/train': 1.6225429773330688}
+08/30/2021 16:33:20 - INFO - __main__ - Step 18488: {'lr': 0.0004848458204524042, 'samples': 3549696, 'steps': 18487, 'loss/train': 2.1874027252197266}
+08/30/2021 16:33:21 - INFO - __main__ - Step 18489: {'lr': 0.00048484400088215173, 'samples': 3549888, 'steps': 18488, 'loss/train': 1.7116848230361938}
+08/30/2021 16:33:22 - INFO - __main__ - Step 18490: {'lr': 0.0004848421812060821, 'samples': 3550080, 'steps': 18489, 'loss/train': 1.7499696016311646}
+08/30/2021 16:33:22 - INFO - __main__ - Step 18491: {'lr': 0.0004848403614241964, 'samples': 3550272, 'steps': 18490, 'loss/train': 0.8672402501106262}
+08/30/2021 16:33:23 - INFO - __main__ - Step 18492: {'lr': 0.00048483854153649514, 'samples': 3550464, 'steps': 18491, 'loss/train': 1.9149320125579834}
+08/30/2021 16:33:23 - INFO - __main__ - Step 18493: {'lr': 0.0004848367215429793, 'samples': 3550656, 'steps': 18492, 'loss/train': 1.3062007427215576}
+08/30/2021 16:33:23 - INFO - __main__ - Step 18494: {'lr': 0.0004848349014436496, 'samples': 3550848, 'steps': 18493, 'loss/train': 1.0269335508346558}
+08/30/2021 16:33:24 - INFO - __main__ - Step 18495: {'lr': 0.00048483308123850697, 'samples': 3551040, 'steps': 18494, 'loss/train': 0.1711260974407196}
+08/30/2021 16:33:25 - INFO - __main__ - Step 18496: {'lr': 0.00048483126092755215, 'samples': 3551232, 'steps': 18495, 'loss/train': 0.07490824162960052}
+08/30/2021 16:33:26 - INFO - __main__ - Step 18497: {'lr': 0.000484829440510786, 'samples': 3551424, 'steps': 18496, 'loss/train': 0.0846533253788948}
+08/30/2021 16:33:26 - INFO - __main__ - Step 18498: {'lr': 0.0004848276199882093, 'samples': 3551616, 'steps': 18497, 'loss/train': 0.7802138328552246}
+08/30/2021 16:33:27 - INFO - __main__ - Step 18499: {'lr': 0.0004848257993598229, 'samples': 3551808, 'steps': 18498, 'loss/train': 1.7126972675323486}
+08/30/2021 16:33:27 - INFO - __main__ - Step 18500: {'lr': 0.00048482397862562764, 'samples': 3552000, 'steps': 18499, 'loss/train': 4.151735782623291}
+08/30/2021 16:33:29 - INFO - __main__ - Step 18501: {'lr': 0.00048482215778562434, 'samples': 3552192, 'steps': 18500, 'loss/train': 1.5678753852844238}
+08/30/2021 16:33:29 - INFO - __main__ - Step 18502: {'lr': 0.00048482033683981376, 'samples': 3552384, 'steps': 18501, 'loss/train': 0.20393653213977814}
+08/30/2021 16:33:30 - INFO - __main__ - Step 18503: {'lr': 0.0004848185157881968, 'samples': 3552576, 'steps': 18502, 'loss/train': 1.5224156379699707}
+08/30/2021 16:33:30 - INFO - __main__ - Step 18504: {'lr': 0.0004848166946307742, 'samples': 3552768, 'steps': 18503, 'loss/train': 1.5995322465896606}
+08/30/2021 16:33:31 - INFO - __main__ - Step 18505: {'lr': 0.0004848148733675468, 'samples': 3552960, 'steps': 18504, 'loss/train': 1.0265933275222778}
+08/30/2021 16:33:31 - INFO - __main__ - Step 18506: {'lr': 0.0004848130519985155, 'samples': 3553152, 'steps': 18505, 'loss/train': 1.430309534072876}
+08/30/2021 16:33:31 - INFO - __main__ - Step 18507: {'lr': 0.000484811230523681, 'samples': 3553344, 'steps': 18506, 'loss/train': 1.8822970390319824}
+08/30/2021 16:33:33 - INFO - __main__ - Step 18508: {'lr': 0.00048480940894304425, 'samples': 3553536, 'steps': 18507, 'loss/train': 1.445253610610962}
+08/30/2021 16:33:33 - INFO - __main__ - Step 18509: {'lr': 0.000484807587256606, 'samples': 3553728, 'steps': 18508, 'loss/train': 1.4174604415893555}
+08/30/2021 16:33:34 - INFO - __main__ - Step 18510: {'lr': 0.00048480576546436707, 'samples': 3553920, 'steps': 18509, 'loss/train': 1.7771098613739014}
+08/30/2021 16:33:34 - INFO - __main__ - Step 18511: {'lr': 0.0004848039435663282, 'samples': 3554112, 'steps': 18510, 'loss/train': 1.7104212045669556}
+08/30/2021 16:33:34 - INFO - __main__ - Step 18512: {'lr': 0.0004848021215624904, 'samples': 3554304, 'steps': 18511, 'loss/train': 1.7735743522644043}
+08/30/2021 16:33:36 - INFO - __main__ - Step 18513: {'lr': 0.0004848002994528543, 'samples': 3554496, 'steps': 18512, 'loss/train': 2.0425238609313965}
+08/30/2021 16:33:36 - INFO - __main__ - Step 18514: {'lr': 0.0004847984772374209, 'samples': 3554688, 'steps': 18513, 'loss/train': 0.3305189907550812}
+08/30/2021 16:33:37 - INFO - __main__ - Step 18515: {'lr': 0.0004847966549161909, 'samples': 3554880, 'steps': 18514, 'loss/train': 1.1372885704040527}
+08/30/2021 16:33:37 - INFO - __main__ - Step 18516: {'lr': 0.0004847948324891651, 'samples': 3555072, 'steps': 18515, 'loss/train': 1.6787761449813843}
+08/30/2021 16:33:37 - INFO - __main__ - Step 18517: {'lr': 0.00048479300995634447, 'samples': 3555264, 'steps': 18516, 'loss/train': 1.302175521850586}
+08/30/2021 16:33:39 - INFO - __main__ - Step 18518: {'lr': 0.0004847911873177296, 'samples': 3555456, 'steps': 18517, 'loss/train': 2.0490682125091553}
+08/30/2021 16:33:40 - INFO - __main__ - Step 18519: {'lr': 0.0004847893645733216, 'samples': 3555648, 'steps': 18518, 'loss/train': 2.500790596008301}
+08/30/2021 16:33:40 - INFO - __main__ - Step 18520: {'lr': 0.000484787541723121, 'samples': 3555840, 'steps': 18519, 'loss/train': 0.8049459457397461}
+08/30/2021 16:33:40 - INFO - __main__ - Step 18521: {'lr': 0.0004847857187671288, 'samples': 3556032, 'steps': 18520, 'loss/train': 2.2276804447174072}
+08/30/2021 16:33:41 - INFO - __main__ - Step 18522: {'lr': 0.00048478389570534575, 'samples': 3556224, 'steps': 18521, 'loss/train': 1.3165028095245361}
+08/30/2021 16:33:42 - INFO - __main__ - Step 18523: {'lr': 0.0004847820725377728, 'samples': 3556416, 'steps': 18522, 'loss/train': 1.5506622791290283}
+08/30/2021 16:33:43 - INFO - __main__ - Step 18524: {'lr': 0.0004847802492644106, 'samples': 3556608, 'steps': 18523, 'loss/train': 1.2318246364593506}
+08/30/2021 16:33:43 - INFO - __main__ - Step 18525: {'lr': 0.00048477842588526, 'samples': 3556800, 'steps': 18524, 'loss/train': 1.4588223695755005}
+08/30/2021 16:33:43 - INFO - __main__ - Step 18526: {'lr': 0.000484776602400322, 'samples': 3556992, 'steps': 18525, 'loss/train': 1.276929259300232}
+08/30/2021 16:33:44 - INFO - __main__ - Step 18527: {'lr': 0.00048477477880959715, 'samples': 3557184, 'steps': 18526, 'loss/train': 1.384444236755371}
+08/30/2021 16:33:45 - INFO - __main__ - Step 18528: {'lr': 0.00048477295511308645, 'samples': 3557376, 'steps': 18527, 'loss/train': 1.8755440711975098}
+08/30/2021 16:33:46 - INFO - __main__ - Step 18529: {'lr': 0.0004847711313107907, 'samples': 3557568, 'steps': 18528, 'loss/train': 2.0067262649536133}
+08/30/2021 16:33:46 - INFO - __main__ - Step 18530: {'lr': 0.0004847693074027106, 'samples': 3557760, 'steps': 18529, 'loss/train': 1.3764686584472656}
+08/30/2021 16:33:46 - INFO - __main__ - Step 18531: {'lr': 0.0004847674833888472, 'samples': 3557952, 'steps': 18530, 'loss/train': 1.5434719324111938}
+08/30/2021 16:33:47 - INFO - __main__ - Step 18532: {'lr': 0.0004847656592692012, 'samples': 3558144, 'steps': 18531, 'loss/train': 1.7961565256118774}
+08/30/2021 16:33:47 - INFO - __main__ - Step 18533: {'lr': 0.00048476383504377337, 'samples': 3558336, 'steps': 18532, 'loss/train': 0.9700822234153748}
+08/30/2021 16:33:49 - INFO - __main__ - Step 18534: {'lr': 0.00048476201071256453, 'samples': 3558528, 'steps': 18533, 'loss/train': 1.6476198434829712}
+08/30/2021 16:33:49 - INFO - __main__ - Step 18535: {'lr': 0.0004847601862755756, 'samples': 3558720, 'steps': 18534, 'loss/train': 1.9694432020187378}
+08/30/2021 16:33:49 - INFO - __main__ - Step 18536: {'lr': 0.0004847583617328074, 'samples': 3558912, 'steps': 18535, 'loss/train': 2.1525583267211914}
+08/30/2021 16:33:50 - INFO - __main__ - Step 18537: {'lr': 0.00048475653708426067, 'samples': 3559104, 'steps': 18536, 'loss/train': 1.294746994972229}
+08/30/2021 16:33:50 - INFO - __main__ - Step 18538: {'lr': 0.00048475471232993625, 'samples': 3559296, 'steps': 18537, 'loss/train': 1.3839820623397827}
+08/30/2021 16:33:52 - INFO - __main__ - Step 18539: {'lr': 0.000484752887469835, 'samples': 3559488, 'steps': 18538, 'loss/train': 0.8167545795440674}
+08/30/2021 16:33:52 - INFO - __main__ - Step 18540: {'lr': 0.0004847510625039577, 'samples': 3559680, 'steps': 18539, 'loss/train': 2.311332941055298}
+08/30/2021 16:33:52 - INFO - __main__ - Step 18541: {'lr': 0.00048474923743230513, 'samples': 3559872, 'steps': 18540, 'loss/train': 1.7084465026855469}
+08/30/2021 16:33:53 - INFO - __main__ - Step 18542: {'lr': 0.0004847474122548783, 'samples': 3560064, 'steps': 18541, 'loss/train': 1.2706105709075928}
+08/30/2021 16:33:53 - INFO - __main__ - Step 18543: {'lr': 0.00048474558697167783, 'samples': 3560256, 'steps': 18542, 'loss/train': 1.7960759401321411}
+08/30/2021 16:33:54 - INFO - __main__ - Step 18544: {'lr': 0.0004847437615827046, 'samples': 3560448, 'steps': 18543, 'loss/train': 1.3301351070404053}
+08/30/2021 16:33:55 - INFO - __main__ - Step 18545: {'lr': 0.0004847419360879596, 'samples': 3560640, 'steps': 18544, 'loss/train': 1.4916123151779175}
+08/30/2021 16:33:55 - INFO - __main__ - Step 18546: {'lr': 0.00048474011048744336, 'samples': 3560832, 'steps': 18545, 'loss/train': 1.7456555366516113}
+08/30/2021 16:33:56 - INFO - __main__ - Step 18547: {'lr': 0.0004847382847811569, 'samples': 3561024, 'steps': 18546, 'loss/train': 1.4895341396331787}
+08/30/2021 16:33:56 - INFO - __main__ - Step 18548: {'lr': 0.00048473645896910094, 'samples': 3561216, 'steps': 18547, 'loss/train': 2.0263867378234863}
+08/30/2021 16:33:58 - INFO - __main__ - Step 18549: {'lr': 0.0004847346330512764, 'samples': 3561408, 'steps': 18548, 'loss/train': 1.640236496925354}
+08/30/2021 16:33:58 - INFO - __main__ - Step 18550: {'lr': 0.0004847328070276841, 'samples': 3561600, 'steps': 18549, 'loss/train': 1.829225778579712}
+08/30/2021 16:33:58 - INFO - __main__ - Step 18551: {'lr': 0.00048473098089832475, 'samples': 3561792, 'steps': 18550, 'loss/train': 1.2299416065216064}
+08/30/2021 16:33:59 - INFO - __main__ - Step 18552: {'lr': 0.0004847291546631992, 'samples': 3561984, 'steps': 18551, 'loss/train': 0.17121967673301697}
+08/30/2021 16:33:59 - INFO - __main__ - Step 18553: {'lr': 0.0004847273283223084, 'samples': 3562176, 'steps': 18552, 'loss/train': 1.252171277999878}
+08/30/2021 16:34:01 - INFO - __main__ - Step 18554: {'lr': 0.0004847255018756531, 'samples': 3562368, 'steps': 18553, 'loss/train': 1.419908046722412}
+08/30/2021 16:34:01 - INFO - __main__ - Step 18555: {'lr': 0.0004847236753232341, 'samples': 3562560, 'steps': 18554, 'loss/train': 1.4968973398208618}
+08/30/2021 16:34:01 - INFO - __main__ - Step 18556: {'lr': 0.0004847218486650522, 'samples': 3562752, 'steps': 18555, 'loss/train': 2.253539562225342}
+08/30/2021 16:34:02 - INFO - __main__ - Step 18557: {'lr': 0.00048472002190110827, 'samples': 3562944, 'steps': 18556, 'loss/train': 1.9014835357666016}
+08/30/2021 16:34:02 - INFO - __main__ - Step 18558: {'lr': 0.0004847181950314031, 'samples': 3563136, 'steps': 18557, 'loss/train': 1.7548178434371948}
+08/30/2021 16:34:04 - INFO - __main__ - Step 18559: {'lr': 0.00048471636805593756, 'samples': 3563328, 'steps': 18558, 'loss/train': 1.438714861869812}
+08/30/2021 16:34:04 - INFO - __main__ - Step 18560: {'lr': 0.0004847145409747125, 'samples': 3563520, 'steps': 18559, 'loss/train': 1.4307847023010254}
+08/30/2021 16:34:04 - INFO - __main__ - Step 18561: {'lr': 0.00048471271378772857, 'samples': 3563712, 'steps': 18560, 'loss/train': 1.4135974645614624}
+08/30/2021 16:34:05 - INFO - __main__ - Step 18562: {'lr': 0.00048471088649498675, 'samples': 3563904, 'steps': 18561, 'loss/train': 1.8708280324935913}
+08/30/2021 16:34:05 - INFO - __main__ - Step 18563: {'lr': 0.0004847090590964879, 'samples': 3564096, 'steps': 18562, 'loss/train': 2.121454954147339}
+08/30/2021 16:34:07 - INFO - __main__ - Step 18564: {'lr': 0.00048470723159223266, 'samples': 3564288, 'steps': 18563, 'loss/train': 1.6470462083816528}
+08/30/2021 16:34:07 - INFO - __main__ - Step 18565: {'lr': 0.00048470540398222207, 'samples': 3564480, 'steps': 18564, 'loss/train': 2.0197346210479736}
+08/30/2021 16:34:07 - INFO - __main__ - Step 18566: {'lr': 0.00048470357626645676, 'samples': 3564672, 'steps': 18565, 'loss/train': 1.9334089756011963}
+08/30/2021 16:34:08 - INFO - __main__ - Step 18567: {'lr': 0.0004847017484449377, 'samples': 3564864, 'steps': 18566, 'loss/train': 1.6592752933502197}
+08/30/2021 16:34:08 - INFO - __main__ - Step 18568: {'lr': 0.0004846999205176657, 'samples': 3565056, 'steps': 18567, 'loss/train': 1.9945423603057861}
+08/30/2021 16:34:10 - INFO - __main__ - Step 18569: {'lr': 0.00048469809248464135, 'samples': 3565248, 'steps': 18568, 'loss/train': 1.9166946411132812}
+08/30/2021 16:34:11 - INFO - __main__ - Step 18570: {'lr': 0.0004846962643458658, 'samples': 3565440, 'steps': 18569, 'loss/train': 1.3833893537521362}
+08/30/2021 16:34:11 - INFO - __main__ - Step 18571: {'lr': 0.00048469443610133975, 'samples': 3565632, 'steps': 18570, 'loss/train': 1.9449726343154907}
+08/30/2021 16:34:12 - INFO - __main__ - Step 18572: {'lr': 0.00048469260775106394, 'samples': 3565824, 'steps': 18571, 'loss/train': 0.8559990525245667}
+08/30/2021 16:34:12 - INFO - __main__ - Step 18573: {'lr': 0.0004846907792950393, 'samples': 3566016, 'steps': 18572, 'loss/train': 1.033095121383667}
+08/30/2021 16:34:12 - INFO - __main__ - Step 18574: {'lr': 0.00048468895073326663, 'samples': 3566208, 'steps': 18573, 'loss/train': 1.4956058263778687}
+08/30/2021 16:34:14 - INFO - __main__ - Step 18575: {'lr': 0.0004846871220657467, 'samples': 3566400, 'steps': 18574, 'loss/train': 1.2601957321166992}
+08/30/2021 16:34:14 - INFO - __main__ - Step 18576: {'lr': 0.0004846852932924804, 'samples': 3566592, 'steps': 18575, 'loss/train': 1.1903382539749146}
+08/30/2021 16:34:15 - INFO - __main__ - Step 18577: {'lr': 0.00048468346441346853, 'samples': 3566784, 'steps': 18576, 'loss/train': 1.7406201362609863}
+08/30/2021 16:34:15 - INFO - __main__ - Step 18578: {'lr': 0.0004846816354287119, 'samples': 3566976, 'steps': 18577, 'loss/train': 1.6070871353149414}
+08/30/2021 16:34:15 - INFO - __main__ - Step 18579: {'lr': 0.0004846798063382114, 'samples': 3567168, 'steps': 18578, 'loss/train': 1.9260528087615967}
+08/30/2021 16:34:17 - INFO - __main__ - Step 18580: {'lr': 0.0004846779771419677, 'samples': 3567360, 'steps': 18579, 'loss/train': 1.7920345067977905}
+08/30/2021 16:34:17 - INFO - __main__ - Step 18581: {'lr': 0.0004846761478399818, 'samples': 3567552, 'steps': 18580, 'loss/train': 1.483244776725769}
+08/30/2021 16:34:18 - INFO - __main__ - Step 18582: {'lr': 0.0004846743184322544, 'samples': 3567744, 'steps': 18581, 'loss/train': 1.7939437627792358}
+08/30/2021 16:34:18 - INFO - __main__ - Step 18583: {'lr': 0.00048467248891878644, 'samples': 3567936, 'steps': 18582, 'loss/train': 1.690280795097351}
+08/30/2021 16:34:18 - INFO - __main__ - Step 18584: {'lr': 0.00048467065929957867, 'samples': 3568128, 'steps': 18583, 'loss/train': 1.767741084098816}
+08/30/2021 16:34:20 - INFO - __main__ - Step 18585: {'lr': 0.00048466882957463186, 'samples': 3568320, 'steps': 18584, 'loss/train': 0.10865940153598785}
+08/30/2021 16:34:21 - INFO - __main__ - Step 18586: {'lr': 0.0004846669997439469, 'samples': 3568512, 'steps': 18585, 'loss/train': 1.2697912454605103}
+08/30/2021 16:34:21 - INFO - __main__ - Step 18587: {'lr': 0.0004846651698075246, 'samples': 3568704, 'steps': 18586, 'loss/train': 1.837859869003296}
+08/30/2021 16:34:22 - INFO - __main__ - Step 18588: {'lr': 0.00048466333976536594, 'samples': 3568896, 'steps': 18587, 'loss/train': 1.3561391830444336}
+08/30/2021 16:34:22 - INFO - __main__ - Step 18589: {'lr': 0.0004846615096174715, 'samples': 3569088, 'steps': 18588, 'loss/train': 1.76717209815979}
+08/30/2021 16:34:22 - INFO - __main__ - Step 18590: {'lr': 0.00048465967936384217, 'samples': 3569280, 'steps': 18589, 'loss/train': 1.7219301462173462}
+08/30/2021 16:34:23 - INFO - __main__ - Step 18591: {'lr': 0.00048465784900447885, 'samples': 3569472, 'steps': 18590, 'loss/train': 5.92577600479126}
+08/30/2021 16:34:24 - INFO - __main__ - Step 18592: {'lr': 0.00048465601853938224, 'samples': 3569664, 'steps': 18591, 'loss/train': 5.849154472351074}
+08/30/2021 16:34:25 - INFO - __main__ - Step 18593: {'lr': 0.0004846541879685533, 'samples': 3569856, 'steps': 18592, 'loss/train': 1.7809295654296875}
+08/30/2021 16:34:25 - INFO - __main__ - Step 18594: {'lr': 0.0004846523572919929, 'samples': 3570048, 'steps': 18593, 'loss/train': 1.50161874294281}
+08/30/2021 16:34:25 - INFO - __main__ - Step 18595: {'lr': 0.00048465052650970166, 'samples': 3570240, 'steps': 18594, 'loss/train': 1.2964003086090088}
+08/30/2021 16:34:26 - INFO - __main__ - Step 18596: {'lr': 0.00048464869562168055, 'samples': 3570432, 'steps': 18595, 'loss/train': 1.6343309879302979}
+08/30/2021 16:34:27 - INFO - __main__ - Step 18597: {'lr': 0.0004846468646279304, 'samples': 3570624, 'steps': 18596, 'loss/train': 1.6104968786239624}
+08/30/2021 16:34:28 - INFO - __main__ - Step 18598: {'lr': 0.0004846450335284519, 'samples': 3570816, 'steps': 18597, 'loss/train': 0.6221204400062561}
+08/30/2021 16:34:28 - INFO - __main__ - Step 18599: {'lr': 0.00048464320232324604, 'samples': 3571008, 'steps': 18598, 'loss/train': 2.2074191570281982}
+08/30/2021 16:34:28 - INFO - __main__ - Step 18600: {'lr': 0.00048464137101231355, 'samples': 3571200, 'steps': 18599, 'loss/train': 1.2850799560546875}
+08/30/2021 16:34:29 - INFO - __main__ - Step 18601: {'lr': 0.0004846395395956553, 'samples': 3571392, 'steps': 18600, 'loss/train': 1.0383111238479614}
+08/30/2021 16:34:30 - INFO - __main__ - Step 18602: {'lr': 0.00048463770807327206, 'samples': 3571584, 'steps': 18601, 'loss/train': 1.3161869049072266}
+08/30/2021 16:34:30 - INFO - __main__ - Step 18603: {'lr': 0.00048463587644516473, 'samples': 3571776, 'steps': 18602, 'loss/train': 1.3902069330215454}
+08/30/2021 16:34:31 - INFO - __main__ - Step 18604: {'lr': 0.00048463404471133404, 'samples': 3571968, 'steps': 18603, 'loss/train': 1.687749981880188}
+08/30/2021 16:34:31 - INFO - __main__ - Step 18605: {'lr': 0.00048463221287178094, 'samples': 3572160, 'steps': 18604, 'loss/train': 1.7741122245788574}
+08/30/2021 16:34:32 - INFO - __main__ - Step 18606: {'lr': 0.0004846303809265061, 'samples': 3572352, 'steps': 18605, 'loss/train': 1.8821640014648438}
+08/30/2021 16:34:33 - INFO - __main__ - Step 18607: {'lr': 0.00048462854887551044, 'samples': 3572544, 'steps': 18606, 'loss/train': 1.5964727401733398}
+08/30/2021 16:34:33 - INFO - __main__ - Step 18608: {'lr': 0.0004846267167187949, 'samples': 3572736, 'steps': 18607, 'loss/train': 1.278092861175537}
+08/30/2021 16:34:34 - INFO - __main__ - Step 18609: {'lr': 0.00048462488445636005, 'samples': 3572928, 'steps': 18608, 'loss/train': 1.5015875101089478}
+08/30/2021 16:34:34 - INFO - __main__ - Step 18610: {'lr': 0.0004846230520882069, 'samples': 3573120, 'steps': 18609, 'loss/train': 1.857212781906128}
+08/30/2021 16:34:34 - INFO - __main__ - Step 18611: {'lr': 0.00048462121961433623, 'samples': 3573312, 'steps': 18610, 'loss/train': 1.809973120689392}
+08/30/2021 16:34:35 - INFO - __main__ - Step 18612: {'lr': 0.00048461938703474886, 'samples': 3573504, 'steps': 18611, 'loss/train': 1.3722333908081055}
+08/30/2021 16:34:36 - INFO - __main__ - Step 18613: {'lr': 0.00048461755434944554, 'samples': 3573696, 'steps': 18612, 'loss/train': 1.4379137754440308}
+08/30/2021 16:34:37 - INFO - __main__ - Step 18614: {'lr': 0.00048461572155842725, 'samples': 3573888, 'steps': 18613, 'loss/train': 2.0803561210632324}
+08/30/2021 16:34:37 - INFO - __main__ - Step 18615: {'lr': 0.00048461388866169474, 'samples': 3574080, 'steps': 18614, 'loss/train': 2.1274871826171875}
+08/30/2021 16:34:38 - INFO - __main__ - Step 18616: {'lr': 0.00048461205565924884, 'samples': 3574272, 'steps': 18615, 'loss/train': 1.253926396369934}
+08/30/2021 16:34:38 - INFO - __main__ - Step 18617: {'lr': 0.0004846102225510903, 'samples': 3574464, 'steps': 18616, 'loss/train': 1.4275085926055908}
+08/30/2021 16:34:39 - INFO - __main__ - Step 18618: {'lr': 0.00048460838933722005, 'samples': 3574656, 'steps': 18617, 'loss/train': 1.5730656385421753}
+08/30/2021 16:34:40 - INFO - __main__ - Step 18619: {'lr': 0.0004846065560176389, 'samples': 3574848, 'steps': 18618, 'loss/train': 1.208412528038025}
+08/30/2021 16:34:40 - INFO - __main__ - Step 18620: {'lr': 0.00048460472259234764, 'samples': 3575040, 'steps': 18619, 'loss/train': 1.4797141551971436}
+08/30/2021 16:34:41 - INFO - __main__ - Step 18621: {'lr': 0.0004846028890613471, 'samples': 3575232, 'steps': 18620, 'loss/train': 1.6955381631851196}
+08/30/2021 16:34:41 - INFO - __main__ - Step 18622: {'lr': 0.00048460105542463805, 'samples': 3575424, 'steps': 18621, 'loss/train': 1.2728599309921265}
+08/30/2021 16:34:42 - INFO - __main__ - Step 18623: {'lr': 0.00048459922168222146, 'samples': 3575616, 'steps': 18622, 'loss/train': 1.4494702816009521}
+08/30/2021 16:34:43 - INFO - __main__ - Step 18624: {'lr': 0.00048459738783409814, 'samples': 3575808, 'steps': 18623, 'loss/train': 1.8204737901687622}
+08/30/2021 16:34:43 - INFO - __main__ - Step 18625: {'lr': 0.0004845955538802688, 'samples': 3576000, 'steps': 18624, 'loss/train': 1.6453754901885986}
+08/30/2021 16:34:44 - INFO - __main__ - Step 18626: {'lr': 0.0004845937198207343, 'samples': 3576192, 'steps': 18625, 'loss/train': 1.7081118822097778}
+08/30/2021 16:34:44 - INFO - __main__ - Step 18627: {'lr': 0.0004845918856554955, 'samples': 3576384, 'steps': 18626, 'loss/train': 1.1042102575302124}
+08/30/2021 16:34:46 - INFO - __main__ - Step 18628: {'lr': 0.00048459005138455326, 'samples': 3576576, 'steps': 18627, 'loss/train': 1.6801420450210571}
+08/30/2021 16:34:46 - INFO - __main__ - Step 18629: {'lr': 0.0004845882170079083, 'samples': 3576768, 'steps': 18628, 'loss/train': 2.0579943656921387}
+08/30/2021 16:34:47 - INFO - __main__ - Step 18630: {'lr': 0.00048458638252556153, 'samples': 3576960, 'steps': 18629, 'loss/train': 1.502411127090454}
+08/30/2021 16:34:47 - INFO - __main__ - Step 18631: {'lr': 0.0004845845479375138, 'samples': 3577152, 'steps': 18630, 'loss/train': 1.7819527387619019}
+08/30/2021 16:34:47 - INFO - __main__ - Step 18632: {'lr': 0.00048458271324376586, 'samples': 3577344, 'steps': 18631, 'loss/train': 1.3876886367797852}
+08/30/2021 16:34:49 - INFO - __main__ - Step 18633: {'lr': 0.0004845808784443185, 'samples': 3577536, 'steps': 18632, 'loss/train': 1.173553466796875}
+08/30/2021 16:34:49 - INFO - __main__ - Step 18634: {'lr': 0.00048457904353917277, 'samples': 3577728, 'steps': 18633, 'loss/train': 2.2251369953155518}
+08/30/2021 16:34:50 - INFO - __main__ - Step 18635: {'lr': 0.0004845772085283292, 'samples': 3577920, 'steps': 18634, 'loss/train': 1.0557796955108643}
+08/30/2021 16:34:50 - INFO - __main__ - Step 18636: {'lr': 0.00048457537341178885, 'samples': 3578112, 'steps': 18635, 'loss/train': 1.8288823366165161}
+08/30/2021 16:34:51 - INFO - __main__ - Step 18637: {'lr': 0.0004845735381895524, 'samples': 3578304, 'steps': 18636, 'loss/train': 1.7181144952774048}
+08/30/2021 16:34:52 - INFO - __main__ - Step 18638: {'lr': 0.0004845717028616208, 'samples': 3578496, 'steps': 18637, 'loss/train': 0.7587200999259949}
+08/30/2021 16:34:53 - INFO - __main__ - Step 18639: {'lr': 0.00048456986742799474, 'samples': 3578688, 'steps': 18638, 'loss/train': 1.7869253158569336}
+08/30/2021 16:34:53 - INFO - __main__ - Step 18640: {'lr': 0.00048456803188867513, 'samples': 3578880, 'steps': 18639, 'loss/train': 1.3770478963851929}
+08/30/2021 16:34:53 - INFO - __main__ - Step 18641: {'lr': 0.00048456619624366284, 'samples': 3579072, 'steps': 18640, 'loss/train': 1.5366994142532349}
+08/30/2021 16:34:54 - INFO - __main__ - Step 18642: {'lr': 0.0004845643604929586, 'samples': 3579264, 'steps': 18641, 'loss/train': 1.6829020977020264}
+08/30/2021 16:34:55 - INFO - __main__ - Step 18643: {'lr': 0.00048456252463656326, 'samples': 3579456, 'steps': 18642, 'loss/train': 1.63473379611969}
+08/30/2021 16:34:56 - INFO - __main__ - Step 18644: {'lr': 0.00048456068867447767, 'samples': 3579648, 'steps': 18643, 'loss/train': 1.4576683044433594}
+08/30/2021 16:34:56 - INFO - __main__ - Step 18645: {'lr': 0.0004845588526067027, 'samples': 3579840, 'steps': 18644, 'loss/train': 1.4982426166534424}
+08/30/2021 16:34:56 - INFO - __main__ - Step 18646: {'lr': 0.00048455701643323914, 'samples': 3580032, 'steps': 18645, 'loss/train': 1.80778169631958}
+08/30/2021 16:34:57 - INFO - __main__ - Step 18647: {'lr': 0.00048455518015408773, 'samples': 3580224, 'steps': 18646, 'loss/train': 1.5563485622406006}
+08/30/2021 16:34:59 - INFO - __main__ - Step 18648: {'lr': 0.00048455334376924943, 'samples': 3580416, 'steps': 18647, 'loss/train': 1.4022586345672607}
+08/30/2021 16:34:59 - INFO - __main__ - Step 18649: {'lr': 0.000484551507278725, 'samples': 3580608, 'steps': 18648, 'loss/train': 1.4820568561553955}
+08/30/2021 16:35:00 - INFO - __main__ - Step 18650: {'lr': 0.0004845496706825152, 'samples': 3580800, 'steps': 18649, 'loss/train': 0.0739121288061142}
+08/30/2021 16:35:00 - INFO - __main__ - Step 18651: {'lr': 0.0004845478339806211, 'samples': 3580992, 'steps': 18650, 'loss/train': 0.09882553666830063}
+08/30/2021 16:35:00 - INFO - __main__ - Step 18652: {'lr': 0.00048454599717304327, 'samples': 3581184, 'steps': 18651, 'loss/train': 1.7683773040771484}
+08/30/2021 16:35:01 - INFO - __main__ - Step 18653: {'lr': 0.0004845441602597826, 'samples': 3581376, 'steps': 18652, 'loss/train': 2.580165386199951}
+08/30/2021 16:35:01 - INFO - __main__ - Step 18654: {'lr': 0.00048454232324084004, 'samples': 3581568, 'steps': 18653, 'loss/train': 2.1176917552948}
+08/30/2021 16:35:03 - INFO - __main__ - Step 18655: {'lr': 0.0004845404861162163, 'samples': 3581760, 'steps': 18654, 'loss/train': 2.0859687328338623}
+08/30/2021 16:35:03 - INFO - __main__ - Step 18656: {'lr': 0.00048453864888591214, 'samples': 3581952, 'steps': 18655, 'loss/train': 2.2482786178588867}
+08/30/2021 16:35:04 - INFO - __main__ - Step 18657: {'lr': 0.0004845368115499286, 'samples': 3582144, 'steps': 18656, 'loss/train': 1.875685214996338}
+08/30/2021 16:35:04 - INFO - __main__ - Step 18658: {'lr': 0.0004845349741082663, 'samples': 3582336, 'steps': 18657, 'loss/train': 1.0968303680419922}
+08/30/2021 16:35:04 - INFO - __main__ - Step 18659: {'lr': 0.00048453313656092624, 'samples': 3582528, 'steps': 18658, 'loss/train': 1.6515830755233765}
+08/30/2021 16:35:05 - INFO - __main__ - Step 18660: {'lr': 0.0004845312989079091, 'samples': 3582720, 'steps': 18659, 'loss/train': 1.2533869743347168}
+08/30/2021 16:35:06 - INFO - __main__ - Step 18661: {'lr': 0.0004845294611492158, 'samples': 3582912, 'steps': 18660, 'loss/train': 0.9937903881072998}
+08/30/2021 16:35:07 - INFO - __main__ - Step 18662: {'lr': 0.00048452762328484724, 'samples': 3583104, 'steps': 18661, 'loss/train': 0.3184073567390442}
+08/30/2021 16:35:07 - INFO - __main__ - Step 18663: {'lr': 0.000484525785314804, 'samples': 3583296, 'steps': 18662, 'loss/train': 1.3504564762115479}
+08/30/2021 16:35:07 - INFO - __main__ - Step 18664: {'lr': 0.0004845239472390872, 'samples': 3583488, 'steps': 18663, 'loss/train': 1.2113533020019531}
+08/30/2021 16:35:08 - INFO - __main__ - Step 18665: {'lr': 0.0004845221090576974, 'samples': 3583680, 'steps': 18664, 'loss/train': 1.6577436923980713}
+08/30/2021 16:35:09 - INFO - __main__ - Step 18666: {'lr': 0.0004845202707706356, 'samples': 3583872, 'steps': 18665, 'loss/train': 2.0766139030456543}
+08/30/2021 16:35:09 - INFO - __main__ - Step 18667: {'lr': 0.0004845184323779026, 'samples': 3584064, 'steps': 18666, 'loss/train': 1.9564974308013916}
+08/30/2021 16:35:10 - INFO - __main__ - Step 18668: {'lr': 0.0004845165938794992, 'samples': 3584256, 'steps': 18667, 'loss/train': 1.630800485610962}
+08/30/2021 16:35:10 - INFO - __main__ - Step 18669: {'lr': 0.0004845147552754263, 'samples': 3584448, 'steps': 18668, 'loss/train': 1.7552801370620728}
+08/30/2021 16:35:10 - INFO - __main__ - Step 18670: {'lr': 0.0004845129165656846, 'samples': 3584640, 'steps': 18669, 'loss/train': 1.6562836170196533}
+08/30/2021 16:35:12 - INFO - __main__ - Step 18671: {'lr': 0.00048451107775027505, 'samples': 3584832, 'steps': 18670, 'loss/train': 1.9035931825637817}
+08/30/2021 16:35:12 - INFO - __main__ - Step 18672: {'lr': 0.0004845092388291984, 'samples': 3585024, 'steps': 18671, 'loss/train': 1.4335185289382935}
+08/30/2021 16:35:13 - INFO - __main__ - Step 18673: {'lr': 0.0004845073998024555, 'samples': 3585216, 'steps': 18672, 'loss/train': 1.2621657848358154}
+08/30/2021 16:35:13 - INFO - __main__ - Step 18674: {'lr': 0.0004845055606700472, 'samples': 3585408, 'steps': 18673, 'loss/train': 1.5613656044006348}
+08/30/2021 16:35:13 - INFO - __main__ - Step 18675: {'lr': 0.0004845037214319743, 'samples': 3585600, 'steps': 18674, 'loss/train': 1.5874727964401245}
+08/30/2021 16:35:15 - INFO - __main__ - Step 18676: {'lr': 0.00048450188208823766, 'samples': 3585792, 'steps': 18675, 'loss/train': 0.40764713287353516}
+08/30/2021 16:35:15 - INFO - __main__ - Step 18677: {'lr': 0.00048450004263883806, 'samples': 3585984, 'steps': 18676, 'loss/train': 1.5625742673873901}
+08/30/2021 16:35:16 - INFO - __main__ - Step 18678: {'lr': 0.00048449820308377634, 'samples': 3586176, 'steps': 18677, 'loss/train': 1.9346193075180054}
+08/30/2021 16:35:16 - INFO - __main__ - Step 18679: {'lr': 0.00048449636342305343, 'samples': 3586368, 'steps': 18678, 'loss/train': 1.4314703941345215}
+08/30/2021 16:35:16 - INFO - __main__ - Step 18680: {'lr': 0.00048449452365667003, 'samples': 3586560, 'steps': 18679, 'loss/train': 1.5792099237442017}
+08/30/2021 16:35:19 - INFO - __main__ - Step 18681: {'lr': 0.00048449268378462695, 'samples': 3586752, 'steps': 18680, 'loss/train': 1.8770092725753784}
+08/30/2021 16:35:20 - INFO - __main__ - Step 18682: {'lr': 0.00048449084380692523, 'samples': 3586944, 'steps': 18681, 'loss/train': 1.610478162765503}
+08/30/2021 16:35:20 - INFO - __main__ - Step 18683: {'lr': 0.0004844890037235654, 'samples': 3587136, 'steps': 18682, 'loss/train': 1.8821977376937866}
+08/30/2021 16:35:20 - INFO - __main__ - Step 18684: {'lr': 0.00048448716353454856, 'samples': 3587328, 'steps': 18683, 'loss/train': 3.1390202045440674}
+08/30/2021 16:35:21 - INFO - __main__ - Step 18685: {'lr': 0.0004844853232398754, 'samples': 3587520, 'steps': 18684, 'loss/train': 3.5587410926818848}
+08/30/2021 16:35:21 - INFO - __main__ - Step 18686: {'lr': 0.00048448348283954674, 'samples': 3587712, 'steps': 18685, 'loss/train': 1.690757155418396}
+08/30/2021 16:35:22 - INFO - __main__ - Step 18687: {'lr': 0.00048448164233356344, 'samples': 3587904, 'steps': 18686, 'loss/train': 2.143714427947998}
+08/30/2021 16:35:23 - INFO - __main__ - Step 18688: {'lr': 0.0004844798017219264, 'samples': 3588096, 'steps': 18687, 'loss/train': 1.801722764968872}
+08/30/2021 16:35:23 - INFO - __main__ - Step 18689: {'lr': 0.00048447796100463625, 'samples': 3588288, 'steps': 18688, 'loss/train': 2.230644941329956}
+08/30/2021 16:35:24 - INFO - __main__ - Step 18690: {'lr': 0.0004844761201816941, 'samples': 3588480, 'steps': 18689, 'loss/train': 1.5586072206497192}
+08/30/2021 16:35:24 - INFO - __main__ - Step 18691: {'lr': 0.0004844742792531005, 'samples': 3588672, 'steps': 18690, 'loss/train': 1.4849650859832764}
+08/30/2021 16:35:24 - INFO - __main__ - Step 18692: {'lr': 0.00048447243821885644, 'samples': 3588864, 'steps': 18691, 'loss/train': 1.0598472356796265}
+08/30/2021 16:35:26 - INFO - __main__ - Step 18693: {'lr': 0.0004844705970789628, 'samples': 3589056, 'steps': 18692, 'loss/train': 1.4825066328048706}
+08/30/2021 16:35:26 - INFO - __main__ - Step 18694: {'lr': 0.0004844687558334202, 'samples': 3589248, 'steps': 18693, 'loss/train': 1.6356847286224365}
+08/30/2021 16:35:27 - INFO - __main__ - Step 18695: {'lr': 0.0004844669144822297, 'samples': 3589440, 'steps': 18694, 'loss/train': 2.0778491497039795}
+08/30/2021 16:35:27 - INFO - __main__ - Step 18696: {'lr': 0.000484465073025392, 'samples': 3589632, 'steps': 18695, 'loss/train': 1.254042148590088}
+08/30/2021 16:35:27 - INFO - __main__ - Step 18697: {'lr': 0.00048446323146290795, 'samples': 3589824, 'steps': 18696, 'loss/train': 2.0559182167053223}
+08/30/2021 16:35:29 - INFO - __main__ - Step 18698: {'lr': 0.0004844613897947784, 'samples': 3590016, 'steps': 18697, 'loss/train': 1.9842222929000854}
+08/30/2021 16:35:29 - INFO - __main__ - Step 18699: {'lr': 0.00048445954802100414, 'samples': 3590208, 'steps': 18698, 'loss/train': 1.610824704170227}
+08/30/2021 16:35:30 - INFO - __main__ - Step 18700: {'lr': 0.000484457706141586, 'samples': 3590400, 'steps': 18699, 'loss/train': 1.5430368185043335}
+08/30/2021 16:35:30 - INFO - __main__ - Step 18701: {'lr': 0.0004844558641565249, 'samples': 3590592, 'steps': 18700, 'loss/train': 1.5543664693832397}
+08/30/2021 16:35:30 - INFO - __main__ - Step 18702: {'lr': 0.00048445402206582155, 'samples': 3590784, 'steps': 18701, 'loss/train': 1.8709467649459839}
+08/30/2021 16:35:32 - INFO - __main__ - Step 18703: {'lr': 0.0004844521798694768, 'samples': 3590976, 'steps': 18702, 'loss/train': 1.660312294960022}
+08/30/2021 16:35:32 - INFO - __main__ - Step 18704: {'lr': 0.0004844503375674916, 'samples': 3591168, 'steps': 18703, 'loss/train': 1.8360676765441895}
+08/30/2021 16:35:33 - INFO - __main__ - Step 18705: {'lr': 0.0004844484951598667, 'samples': 3591360, 'steps': 18704, 'loss/train': 1.815129280090332}
+08/30/2021 16:35:33 - INFO - __main__ - Step 18706: {'lr': 0.00048444665264660286, 'samples': 3591552, 'steps': 18705, 'loss/train': 0.14327189326286316}
+08/30/2021 16:35:33 - INFO - __main__ - Step 18707: {'lr': 0.000484444810027701, 'samples': 3591744, 'steps': 18706, 'loss/train': 1.789504051208496}
+08/30/2021 16:35:35 - INFO - __main__ - Step 18708: {'lr': 0.00048444296730316196, 'samples': 3591936, 'steps': 18707, 'loss/train': 1.9275892972946167}
+08/30/2021 16:35:35 - INFO - __main__ - Step 18709: {'lr': 0.0004844411244729865, 'samples': 3592128, 'steps': 18708, 'loss/train': 2.6028988361358643}
+08/30/2021 16:35:36 - INFO - __main__ - Step 18710: {'lr': 0.00048443928153717555, 'samples': 3592320, 'steps': 18709, 'loss/train': 1.8521556854248047}
+08/30/2021 16:35:36 - INFO - __main__ - Step 18711: {'lr': 0.00048443743849572974, 'samples': 3592512, 'steps': 18710, 'loss/train': 1.3215727806091309}
+08/30/2021 16:35:36 - INFO - __main__ - Step 18712: {'lr': 0.00048443559534865017, 'samples': 3592704, 'steps': 18711, 'loss/train': 1.9808443784713745}
+08/30/2021 16:35:37 - INFO - __main__ - Step 18713: {'lr': 0.0004844337520959375, 'samples': 3592896, 'steps': 18712, 'loss/train': 1.8047269582748413}
+08/30/2021 16:35:39 - INFO - __main__ - Step 18714: {'lr': 0.00048443190873759256, 'samples': 3593088, 'steps': 18713, 'loss/train': 1.957062005996704}
+08/30/2021 16:35:39 - INFO - __main__ - Step 18715: {'lr': 0.00048443006527361626, 'samples': 3593280, 'steps': 18714, 'loss/train': 1.7376261949539185}
+08/30/2021 16:35:40 - INFO - __main__ - Step 18716: {'lr': 0.0004844282217040094, 'samples': 3593472, 'steps': 18715, 'loss/train': 1.8164899349212646}
+08/30/2021 16:35:40 - INFO - __main__ - Step 18717: {'lr': 0.00048442637802877277, 'samples': 3593664, 'steps': 18716, 'loss/train': 0.22864291071891785}
+08/30/2021 16:35:40 - INFO - __main__ - Step 18718: {'lr': 0.0004844245342479072, 'samples': 3593856, 'steps': 18717, 'loss/train': 1.6635072231292725}
+08/30/2021 16:35:41 - INFO - __main__ - Step 18719: {'lr': 0.00048442269036141363, 'samples': 3594048, 'steps': 18718, 'loss/train': 1.2503526210784912}
+08/30/2021 16:35:42 - INFO - __main__ - Step 18720: {'lr': 0.0004844208463692928, 'samples': 3594240, 'steps': 18719, 'loss/train': 0.14091970026493073}
+08/30/2021 16:35:43 - INFO - __main__ - Step 18721: {'lr': 0.00048441900227154557, 'samples': 3594432, 'steps': 18720, 'loss/train': 1.1688940525054932}
+08/30/2021 16:35:43 - INFO - __main__ - Step 18722: {'lr': 0.00048441715806817265, 'samples': 3594624, 'steps': 18721, 'loss/train': 1.5595972537994385}
+08/30/2021 16:35:43 - INFO - __main__ - Step 18723: {'lr': 0.0004844153137591751, 'samples': 3594816, 'steps': 18722, 'loss/train': 2.0275187492370605}
+08/30/2021 16:35:44 - INFO - __main__ - Step 18724: {'lr': 0.00048441346934455356, 'samples': 3595008, 'steps': 18723, 'loss/train': 1.7118854522705078}
+08/30/2021 16:35:45 - INFO - __main__ - Step 18725: {'lr': 0.0004844116248243089, 'samples': 3595200, 'steps': 18724, 'loss/train': 1.8899564743041992}
+08/30/2021 16:35:46 - INFO - __main__ - Step 18726: {'lr': 0.0004844097801984421, 'samples': 3595392, 'steps': 18725, 'loss/train': 1.701796054840088}
+08/30/2021 16:35:46 - INFO - __main__ - Step 18727: {'lr': 0.0004844079354669537, 'samples': 3595584, 'steps': 18726, 'loss/train': 1.674830675125122}
+08/30/2021 16:35:46 - INFO - __main__ - Step 18728: {'lr': 0.0004844060906298448, 'samples': 3595776, 'steps': 18727, 'loss/train': 2.0198514461517334}
+08/30/2021 16:35:47 - INFO - __main__ - Step 18729: {'lr': 0.0004844042456871162, 'samples': 3595968, 'steps': 18728, 'loss/train': 1.8553674221038818}
+08/30/2021 16:35:48 - INFO - __main__ - Step 18730: {'lr': 0.0004844024006387685, 'samples': 3596160, 'steps': 18729, 'loss/train': 1.6953486204147339}
+08/30/2021 16:35:49 - INFO - __main__ - Step 18731: {'lr': 0.00048440055548480275, 'samples': 3596352, 'steps': 18730, 'loss/train': 1.5249199867248535}
+08/30/2021 16:35:49 - INFO - __main__ - Step 18732: {'lr': 0.0004843987102252198, 'samples': 3596544, 'steps': 18731, 'loss/train': 1.6466822624206543}
+08/30/2021 16:35:49 - INFO - __main__ - Step 18733: {'lr': 0.0004843968648600204, 'samples': 3596736, 'steps': 18732, 'loss/train': 1.4004868268966675}
+08/30/2021 16:35:50 - INFO - __main__ - Step 18734: {'lr': 0.00048439501938920534, 'samples': 3596928, 'steps': 18733, 'loss/train': 1.815832495689392}
+08/30/2021 16:35:51 - INFO - __main__ - Step 18735: {'lr': 0.0004843931738127755, 'samples': 3597120, 'steps': 18734, 'loss/train': 1.5569733381271362}
+08/30/2021 16:35:52 - INFO - __main__ - Step 18736: {'lr': 0.0004843913281307317, 'samples': 3597312, 'steps': 18735, 'loss/train': 1.4122766256332397}
+08/30/2021 16:35:52 - INFO - __main__ - Step 18737: {'lr': 0.0004843894823430749, 'samples': 3597504, 'steps': 18736, 'loss/train': 1.5067040920257568}
+08/30/2021 16:35:52 - INFO - __main__ - Step 18738: {'lr': 0.00048438763644980564, 'samples': 3597696, 'steps': 18737, 'loss/train': 1.0526565313339233}
+08/30/2021 16:35:53 - INFO - __main__ - Step 18739: {'lr': 0.0004843857904509251, 'samples': 3597888, 'steps': 18738, 'loss/train': 1.0327776670455933}
+08/30/2021 16:35:55 - INFO - __main__ - Step 18740: {'lr': 0.00048438394434643386, 'samples': 3598080, 'steps': 18739, 'loss/train': 2.21777081489563}
+08/30/2021 16:35:55 - INFO - __main__ - Step 18741: {'lr': 0.0004843820981363328, 'samples': 3598272, 'steps': 18740, 'loss/train': 1.4588394165039062}
+08/30/2021 16:35:55 - INFO - __main__ - Step 18742: {'lr': 0.00048438025182062286, 'samples': 3598464, 'steps': 18741, 'loss/train': 1.724167823791504}
+08/30/2021 16:35:56 - INFO - __main__ - Step 18743: {'lr': 0.00048437840539930466, 'samples': 3598656, 'steps': 18742, 'loss/train': 1.81268310546875}
+08/30/2021 16:35:56 - INFO - __main__ - Step 18744: {'lr': 0.0004843765588723793, 'samples': 3598848, 'steps': 18743, 'loss/train': 1.3539683818817139}
+08/30/2021 16:35:57 - INFO - __main__ - Step 18745: {'lr': 0.00048437471223984743, 'samples': 3599040, 'steps': 18744, 'loss/train': 2.382828712463379}
+08/30/2021 16:35:58 - INFO - __main__ - Step 18746: {'lr': 0.00048437286550170996, 'samples': 3599232, 'steps': 18745, 'loss/train': 2.2191319465637207}
+08/30/2021 16:35:58 - INFO - __main__ - Step 18747: {'lr': 0.00048437101865796763, 'samples': 3599424, 'steps': 18746, 'loss/train': 1.140054702758789}
+08/30/2021 16:35:59 - INFO - __main__ - Step 18748: {'lr': 0.0004843691717086214, 'samples': 3599616, 'steps': 18747, 'loss/train': 1.7695509195327759}
+08/30/2021 16:35:59 - INFO - __main__ - Step 18749: {'lr': 0.000484367324653672, 'samples': 3599808, 'steps': 18748, 'loss/train': 1.8163909912109375}
+08/30/2021 16:36:00 - INFO - __main__ - Step 18750: {'lr': 0.0004843654774931203, 'samples': 3600000, 'steps': 18749, 'loss/train': 1.4683212041854858}
+08/30/2021 16:36:01 - INFO - __main__ - Step 18751: {'lr': 0.00048436363022696715, 'samples': 3600192, 'steps': 18750, 'loss/train': 1.4695026874542236}
+08/30/2021 16:36:01 - INFO - __main__ - Step 18752: {'lr': 0.0004843617828552134, 'samples': 3600384, 'steps': 18751, 'loss/train': 2.245600938796997}
+08/30/2021 16:36:02 - INFO - __main__ - Step 18753: {'lr': 0.00048435993537785976, 'samples': 3600576, 'steps': 18752, 'loss/train': 2.03971266746521}
+08/30/2021 16:36:02 - INFO - __main__ - Step 18754: {'lr': 0.0004843580877949072, 'samples': 3600768, 'steps': 18753, 'loss/train': 1.674576997756958}
+08/30/2021 16:36:02 - INFO - __main__ - Step 18755: {'lr': 0.0004843562401063565, 'samples': 3600960, 'steps': 18754, 'loss/train': 1.3875715732574463}
+08/30/2021 16:36:04 - INFO - __main__ - Step 18756: {'lr': 0.0004843543923122085, 'samples': 3601152, 'steps': 18755, 'loss/train': 1.7169502973556519}
+08/30/2021 16:36:04 - INFO - __main__ - Step 18757: {'lr': 0.000484352544412464, 'samples': 3601344, 'steps': 18756, 'loss/train': 2.0435969829559326}
+08/30/2021 16:36:05 - INFO - __main__ - Step 18758: {'lr': 0.0004843506964071239, 'samples': 3601536, 'steps': 18757, 'loss/train': 1.4638701677322388}
+08/30/2021 16:36:05 - INFO - __main__ - Step 18759: {'lr': 0.000484348848296189, 'samples': 3601728, 'steps': 18758, 'loss/train': 1.5171616077423096}
+08/30/2021 16:36:05 - INFO - __main__ - Step 18760: {'lr': 0.00048434700007966006, 'samples': 3601920, 'steps': 18759, 'loss/train': 1.8144410848617554}
+08/30/2021 16:36:07 - INFO - __main__ - Step 18761: {'lr': 0.000484345151757538, 'samples': 3602112, 'steps': 18760, 'loss/train': 1.88290536403656}
+08/30/2021 16:36:08 - INFO - __main__ - Step 18762: {'lr': 0.0004843433033298237, 'samples': 3602304, 'steps': 18761, 'loss/train': 1.8810815811157227}
+08/30/2021 16:36:08 - INFO - __main__ - Step 18763: {'lr': 0.00048434145479651783, 'samples': 3602496, 'steps': 18762, 'loss/train': 1.4046201705932617}
+08/30/2021 16:36:08 - INFO - __main__ - Step 18764: {'lr': 0.00048433960615762136, 'samples': 3602688, 'steps': 18763, 'loss/train': 1.8820677995681763}
+08/30/2021 16:36:09 - INFO - __main__ - Step 18765: {'lr': 0.0004843377574131351, 'samples': 3602880, 'steps': 18764, 'loss/train': 1.4780255556106567}
+08/30/2021 16:36:10 - INFO - __main__ - Step 18766: {'lr': 0.0004843359085630598, 'samples': 3603072, 'steps': 18765, 'loss/train': 1.659212350845337}
+08/30/2021 16:36:11 - INFO - __main__ - Step 18767: {'lr': 0.0004843340596073964, 'samples': 3603264, 'steps': 18766, 'loss/train': 1.403775691986084}
+08/30/2021 16:36:11 - INFO - __main__ - Step 18768: {'lr': 0.0004843322105461457, 'samples': 3603456, 'steps': 18767, 'loss/train': 1.7835924625396729}
+08/30/2021 16:36:11 - INFO - __main__ - Step 18769: {'lr': 0.0004843303613793085, 'samples': 3603648, 'steps': 18768, 'loss/train': 1.0598496198654175}
+08/30/2021 16:36:12 - INFO - __main__ - Step 18770: {'lr': 0.00048432851210688567, 'samples': 3603840, 'steps': 18769, 'loss/train': 1.6672589778900146}
+08/30/2021 16:36:13 - INFO - __main__ - Step 18771: {'lr': 0.00048432666272887805, 'samples': 3604032, 'steps': 18770, 'loss/train': 2.340057849884033}
+08/30/2021 16:36:13 - INFO - __main__ - Step 18772: {'lr': 0.0004843248132452864, 'samples': 3604224, 'steps': 18771, 'loss/train': 1.585218071937561}
+08/30/2021 16:36:14 - INFO - __main__ - Step 18773: {'lr': 0.0004843229636561116, 'samples': 3604416, 'steps': 18772, 'loss/train': 1.4477012157440186}
+08/30/2021 16:36:14 - INFO - __main__ - Step 18774: {'lr': 0.00048432111396135447, 'samples': 3604608, 'steps': 18773, 'loss/train': 1.6103549003601074}
+08/30/2021 16:36:15 - INFO - __main__ - Step 18775: {'lr': 0.0004843192641610159, 'samples': 3604800, 'steps': 18774, 'loss/train': 1.2788995504379272}
+08/30/2021 16:36:16 - INFO - __main__ - Step 18776: {'lr': 0.00048431741425509676, 'samples': 3604992, 'steps': 18775, 'loss/train': 1.5461417436599731}
+08/30/2021 16:36:16 - INFO - __main__ - Step 18777: {'lr': 0.0004843155642435977, 'samples': 3605184, 'steps': 18776, 'loss/train': 2.0165276527404785}
+08/30/2021 16:36:17 - INFO - __main__ - Step 18778: {'lr': 0.0004843137141265197, 'samples': 3605376, 'steps': 18777, 'loss/train': 1.8745001554489136}
+08/30/2021 16:36:17 - INFO - __main__ - Step 18779: {'lr': 0.00048431186390386356, 'samples': 3605568, 'steps': 18778, 'loss/train': 1.5030087232589722}
+08/30/2021 16:36:18 - INFO - __main__ - Step 18780: {'lr': 0.0004843100135756301, 'samples': 3605760, 'steps': 18779, 'loss/train': 2.11687970161438}
+08/30/2021 16:36:18 - INFO - __main__ - Step 18781: {'lr': 0.0004843081631418202, 'samples': 3605952, 'steps': 18780, 'loss/train': 2.195359945297241}
+08/30/2021 16:36:19 - INFO - __main__ - Step 18782: {'lr': 0.00048430631260243465, 'samples': 3606144, 'steps': 18781, 'loss/train': 1.9703930616378784}
+08/30/2021 16:36:20 - INFO - __main__ - Step 18783: {'lr': 0.00048430446195747424, 'samples': 3606336, 'steps': 18782, 'loss/train': 1.436973214149475}
+08/30/2021 16:36:20 - INFO - __main__ - Step 18784: {'lr': 0.00048430261120693986, 'samples': 3606528, 'steps': 18783, 'loss/train': 1.4219201803207397}
+08/30/2021 16:36:21 - INFO - __main__ - Step 18785: {'lr': 0.0004843007603508324, 'samples': 3606720, 'steps': 18784, 'loss/train': 1.6902960538864136}
+08/30/2021 16:36:21 - INFO - __main__ - Step 18786: {'lr': 0.00048429890938915255, 'samples': 3606912, 'steps': 18785, 'loss/train': 1.467069387435913}
+08/30/2021 16:36:22 - INFO - __main__ - Step 18787: {'lr': 0.0004842970583219013, 'samples': 3607104, 'steps': 18786, 'loss/train': 1.503032922744751}
+08/30/2021 16:36:23 - INFO - __main__ - Step 18788: {'lr': 0.0004842952071490794, 'samples': 3607296, 'steps': 18787, 'loss/train': 1.3325965404510498}
+08/30/2021 16:36:23 - INFO - __main__ - Step 18789: {'lr': 0.0004842933558706877, 'samples': 3607488, 'steps': 18788, 'loss/train': 1.8448175191879272}
+08/30/2021 16:36:24 - INFO - __main__ - Step 18790: {'lr': 0.000484291504486727, 'samples': 3607680, 'steps': 18789, 'loss/train': 1.696388602256775}
+08/30/2021 16:36:24 - INFO - __main__ - Step 18791: {'lr': 0.0004842896529971982, 'samples': 3607872, 'steps': 18790, 'loss/train': 1.762611746788025}
+08/30/2021 16:36:26 - INFO - __main__ - Step 18792: {'lr': 0.00048428780140210204, 'samples': 3608064, 'steps': 18791, 'loss/train': 1.8964207172393799}
+08/30/2021 16:36:27 - INFO - __main__ - Step 18793: {'lr': 0.0004842859497014394, 'samples': 3608256, 'steps': 18792, 'loss/train': 1.6959890127182007}
+08/30/2021 16:36:27 - INFO - __main__ - Step 18794: {'lr': 0.0004842840978952112, 'samples': 3608448, 'steps': 18793, 'loss/train': 0.7731893658638}
+08/30/2021 16:36:27 - INFO - __main__ - Step 18795: {'lr': 0.00048428224598341815, 'samples': 3608640, 'steps': 18794, 'loss/train': 1.503921389579773}
+08/30/2021 16:36:28 - INFO - __main__ - Step 18796: {'lr': 0.0004842803939660612, 'samples': 3608832, 'steps': 18795, 'loss/train': 1.7576403617858887}
+08/30/2021 16:36:29 - INFO - __main__ - Step 18797: {'lr': 0.00048427854184314103, 'samples': 3609024, 'steps': 18796, 'loss/train': 1.324228286743164}
+08/30/2021 16:36:30 - INFO - __main__ - Step 18798: {'lr': 0.0004842766896146586, 'samples': 3609216, 'steps': 18797, 'loss/train': 1.5051244497299194}
+08/30/2021 16:36:30 - INFO - __main__ - Step 18799: {'lr': 0.0004842748372806147, 'samples': 3609408, 'steps': 18798, 'loss/train': 1.8872275352478027}
+08/30/2021 16:36:30 - INFO - __main__ - Step 18800: {'lr': 0.00048427298484101023, 'samples': 3609600, 'steps': 18799, 'loss/train': 1.111180067062378}
+08/30/2021 16:36:31 - INFO - __main__ - Step 18801: {'lr': 0.0004842711322958459, 'samples': 3609792, 'steps': 18800, 'loss/train': 1.7275948524475098}
+08/30/2021 16:36:33 - INFO - __main__ - Step 18802: {'lr': 0.0004842692796451226, 'samples': 3609984, 'steps': 18801, 'loss/train': 1.684067726135254}
+08/30/2021 16:36:33 - INFO - __main__ - Step 18803: {'lr': 0.0004842674268888413, 'samples': 3610176, 'steps': 18802, 'loss/train': 1.430519938468933}
+08/30/2021 16:36:33 - INFO - __main__ - Step 18804: {'lr': 0.0004842655740270026, 'samples': 3610368, 'steps': 18803, 'loss/train': 1.34248948097229}
+08/30/2021 16:36:34 - INFO - __main__ - Step 18805: {'lr': 0.0004842637210596075, 'samples': 3610560, 'steps': 18804, 'loss/train': 1.3173251152038574}
+08/30/2021 16:36:34 - INFO - __main__ - Step 18806: {'lr': 0.0004842618679866567, 'samples': 3610752, 'steps': 18805, 'loss/train': 1.451834797859192}
+08/30/2021 16:36:36 - INFO - __main__ - Step 18807: {'lr': 0.0004842600148081512, 'samples': 3610944, 'steps': 18806, 'loss/train': 1.028164029121399}
+08/30/2021 16:36:36 - INFO - __main__ - Step 18808: {'lr': 0.00048425816152409173, 'samples': 3611136, 'steps': 18807, 'loss/train': 2.2420125007629395}
+08/30/2021 16:36:36 - INFO - __main__ - Step 18809: {'lr': 0.00048425630813447916, 'samples': 3611328, 'steps': 18808, 'loss/train': 1.931848406791687}
+08/30/2021 16:36:37 - INFO - __main__ - Step 18810: {'lr': 0.0004842544546393143, 'samples': 3611520, 'steps': 18809, 'loss/train': 1.5243005752563477}
+08/30/2021 16:36:37 - INFO - __main__ - Step 18811: {'lr': 0.00048425260103859797, 'samples': 3611712, 'steps': 18810, 'loss/train': 2.062664270401001}
+08/30/2021 16:36:39 - INFO - __main__ - Step 18812: {'lr': 0.0004842507473323311, 'samples': 3611904, 'steps': 18811, 'loss/train': 1.3754416704177856}
+08/30/2021 16:36:39 - INFO - __main__ - Step 18813: {'lr': 0.00048424889352051436, 'samples': 3612096, 'steps': 18812, 'loss/train': 1.0482581853866577}
+08/30/2021 16:36:39 - INFO - __main__ - Step 18814: {'lr': 0.00048424703960314876, 'samples': 3612288, 'steps': 18813, 'loss/train': 1.5366097688674927}
+08/30/2021 16:36:40 - INFO - __main__ - Step 18815: {'lr': 0.00048424518558023505, 'samples': 3612480, 'steps': 18814, 'loss/train': 1.6471534967422485}
+08/30/2021 16:36:40 - INFO - __main__ - Step 18816: {'lr': 0.00048424333145177405, 'samples': 3612672, 'steps': 18815, 'loss/train': 2.2628097534179688}
+08/30/2021 16:36:40 - INFO - __main__ - Step 18817: {'lr': 0.00048424147721776666, 'samples': 3612864, 'steps': 18816, 'loss/train': 1.8539897203445435}
+08/30/2021 16:36:42 - INFO - __main__ - Step 18818: {'lr': 0.00048423962287821366, 'samples': 3613056, 'steps': 18817, 'loss/train': 1.4543426036834717}
+08/30/2021 16:36:43 - INFO - __main__ - Step 18819: {'lr': 0.00048423776843311585, 'samples': 3613248, 'steps': 18818, 'loss/train': 1.724756121635437}
+08/30/2021 16:36:43 - INFO - __main__ - Step 18820: {'lr': 0.00048423591388247416, 'samples': 3613440, 'steps': 18819, 'loss/train': 1.831925392150879}
+08/30/2021 16:36:44 - INFO - __main__ - Step 18821: {'lr': 0.0004842340592262894, 'samples': 3613632, 'steps': 18820, 'loss/train': 1.9668060541152954}
+08/30/2021 16:36:44 - INFO - __main__ - Step 18822: {'lr': 0.00048423220446456233, 'samples': 3613824, 'steps': 18821, 'loss/train': 1.4850150346755981}
+08/30/2021 16:36:44 - INFO - __main__ - Step 18823: {'lr': 0.0004842303495972939, 'samples': 3614016, 'steps': 18822, 'loss/train': 1.7642061710357666}
+08/30/2021 16:36:46 - INFO - __main__ - Step 18824: {'lr': 0.00048422849462448483, 'samples': 3614208, 'steps': 18823, 'loss/train': 2.1004860401153564}
+08/30/2021 16:36:47 - INFO - __main__ - Step 18825: {'lr': 0.0004842266395461361, 'samples': 3614400, 'steps': 18824, 'loss/train': 1.674424409866333}
+08/30/2021 16:36:47 - INFO - __main__ - Step 18826: {'lr': 0.0004842247843622484, 'samples': 3614592, 'steps': 18825, 'loss/train': 1.7505078315734863}
+08/30/2021 16:36:47 - INFO - __main__ - Step 18827: {'lr': 0.0004842229290728226, 'samples': 3614784, 'steps': 18826, 'loss/train': 1.1835781335830688}
+08/30/2021 16:36:48 - INFO - __main__ - Step 18828: {'lr': 0.0004842210736778596, 'samples': 3614976, 'steps': 18827, 'loss/train': 2.0453503131866455}
+08/30/2021 16:36:48 - INFO - __main__ - Step 18829: {'lr': 0.0004842192181773602, 'samples': 3615168, 'steps': 18828, 'loss/train': 1.901028037071228}
+08/30/2021 16:36:48 - INFO - __main__ - Step 18830: {'lr': 0.0004842173625713252, 'samples': 3615360, 'steps': 18829, 'loss/train': 1.8921504020690918}
+08/30/2021 16:36:50 - INFO - __main__ - Step 18831: {'lr': 0.0004842155068597556, 'samples': 3615552, 'steps': 18830, 'loss/train': 2.693031072616577}
+08/30/2021 16:36:50 - INFO - __main__ - Step 18832: {'lr': 0.0004842136510426519, 'samples': 3615744, 'steps': 18831, 'loss/train': 1.7852935791015625}
+08/30/2021 16:36:51 - INFO - __main__ - Step 18833: {'lr': 0.00048421179512001536, 'samples': 3615936, 'steps': 18832, 'loss/train': 1.0270863771438599}
+08/30/2021 16:36:51 - INFO - __main__ - Step 18834: {'lr': 0.0004842099390918464, 'samples': 3616128, 'steps': 18833, 'loss/train': 1.476439356803894}
+08/30/2021 16:36:51 - INFO - __main__ - Step 18835: {'lr': 0.00048420808295814624, 'samples': 3616320, 'steps': 18834, 'loss/train': 1.4553825855255127}
+08/30/2021 16:36:53 - INFO - __main__ - Step 18836: {'lr': 0.00048420622671891533, 'samples': 3616512, 'steps': 18835, 'loss/train': 1.8982298374176025}
+08/30/2021 16:36:53 - INFO - __main__ - Step 18837: {'lr': 0.00048420437037415486, 'samples': 3616704, 'steps': 18836, 'loss/train': 1.5830507278442383}
+08/30/2021 16:36:54 - INFO - __main__ - Step 18838: {'lr': 0.00048420251392386547, 'samples': 3616896, 'steps': 18837, 'loss/train': 2.066307544708252}
+08/30/2021 16:36:54 - INFO - __main__ - Step 18839: {'lr': 0.0004842006573680481, 'samples': 3617088, 'steps': 18838, 'loss/train': 1.865342617034912}
+08/30/2021 16:36:54 - INFO - __main__ - Step 18840: {'lr': 0.0004841988007067034, 'samples': 3617280, 'steps': 18839, 'loss/train': 1.5887759923934937}
+08/30/2021 16:36:56 - INFO - __main__ - Step 18841: {'lr': 0.00048419694393983244, 'samples': 3617472, 'steps': 18840, 'loss/train': 1.801106572151184}
+08/30/2021 16:36:56 - INFO - __main__ - Step 18842: {'lr': 0.00048419508706743587, 'samples': 3617664, 'steps': 18841, 'loss/train': 1.5339930057525635}
+08/30/2021 16:36:57 - INFO - __main__ - Step 18843: {'lr': 0.00048419323008951467, 'samples': 3617856, 'steps': 18842, 'loss/train': 1.4506832361221313}
+08/30/2021 16:36:57 - INFO - __main__ - Step 18844: {'lr': 0.00048419137300606963, 'samples': 3618048, 'steps': 18843, 'loss/train': 1.8783767223358154}
+08/30/2021 16:36:57 - INFO - __main__ - Step 18845: {'lr': 0.00048418951581710154, 'samples': 3618240, 'steps': 18844, 'loss/train': 1.9886521100997925}
+08/30/2021 16:37:00 - INFO - __main__ - Step 18846: {'lr': 0.00048418765852261124, 'samples': 3618432, 'steps': 18845, 'loss/train': 1.754531979560852}
+08/30/2021 16:37:00 - INFO - __main__ - Step 18847: {'lr': 0.0004841858011225996, 'samples': 3618624, 'steps': 18846, 'loss/train': 1.5919480323791504}
+08/30/2021 16:37:00 - INFO - __main__ - Step 18848: {'lr': 0.0004841839436170675, 'samples': 3618816, 'steps': 18847, 'loss/train': 1.814907193183899}
+08/30/2021 16:37:01 - INFO - __main__ - Step 18849: {'lr': 0.0004841820860060157, 'samples': 3619008, 'steps': 18848, 'loss/train': 1.5920826196670532}
+08/30/2021 16:37:01 - INFO - __main__ - Step 18850: {'lr': 0.0004841802282894451, 'samples': 3619200, 'steps': 18849, 'loss/train': 2.005141496658325}
+08/30/2021 16:37:01 - INFO - __main__ - Step 18851: {'lr': 0.0004841783704673565, 'samples': 3619392, 'steps': 18850, 'loss/train': 2.8705596923828125}
+08/30/2021 16:37:03 - INFO - __main__ - Step 18852: {'lr': 0.00048417651253975067, 'samples': 3619584, 'steps': 18851, 'loss/train': 1.971785545349121}
+08/30/2021 16:37:04 - INFO - __main__ - Step 18853: {'lr': 0.00048417465450662856, 'samples': 3619776, 'steps': 18852, 'loss/train': 1.8574641942977905}
+08/30/2021 16:37:04 - INFO - __main__ - Step 18854: {'lr': 0.0004841727963679909, 'samples': 3619968, 'steps': 18853, 'loss/train': 1.6750909090042114}
+08/30/2021 16:37:04 - INFO - __main__ - Step 18855: {'lr': 0.0004841709381238387, 'samples': 3620160, 'steps': 18854, 'loss/train': 1.5622586011886597}
+08/30/2021 16:37:05 - INFO - __main__ - Step 18856: {'lr': 0.0004841690797741726, 'samples': 3620352, 'steps': 18855, 'loss/train': 1.5276461839675903}
+08/30/2021 16:37:06 - INFO - __main__ - Step 18857: {'lr': 0.0004841672213189936, 'samples': 3620544, 'steps': 18856, 'loss/train': 1.2764571905136108}
+08/30/2021 16:37:06 - INFO - __main__ - Step 18858: {'lr': 0.00048416536275830245, 'samples': 3620736, 'steps': 18857, 'loss/train': 1.8183342218399048}
+08/30/2021 16:37:07 - INFO - __main__ - Step 18859: {'lr': 0.00048416350409209995, 'samples': 3620928, 'steps': 18858, 'loss/train': 1.6793569326400757}
+08/30/2021 16:37:07 - INFO - __main__ - Step 18860: {'lr': 0.000484161645320387, 'samples': 3621120, 'steps': 18859, 'loss/train': 1.5738416910171509}
+08/30/2021 16:37:08 - INFO - __main__ - Step 18861: {'lr': 0.0004841597864431645, 'samples': 3621312, 'steps': 18860, 'loss/train': 1.579481840133667}
+08/30/2021 16:37:09 - INFO - __main__ - Step 18862: {'lr': 0.00048415792746043314, 'samples': 3621504, 'steps': 18861, 'loss/train': 1.9011242389678955}
+08/30/2021 16:37:10 - INFO - __main__ - Step 18863: {'lr': 0.00048415606837219383, 'samples': 3621696, 'steps': 18862, 'loss/train': 2.1082510948181152}
+08/30/2021 16:37:10 - INFO - __main__ - Step 18864: {'lr': 0.00048415420917844744, 'samples': 3621888, 'steps': 18863, 'loss/train': 2.0008208751678467}
+08/30/2021 16:37:10 - INFO - __main__ - Step 18865: {'lr': 0.00048415234987919474, 'samples': 3622080, 'steps': 18864, 'loss/train': 0.12366552650928497}
+08/30/2021 16:37:11 - INFO - __main__ - Step 18866: {'lr': 0.0004841504904744367, 'samples': 3622272, 'steps': 18865, 'loss/train': 1.6811604499816895}
+08/30/2021 16:37:11 - INFO - __main__ - Step 18867: {'lr': 0.0004841486309641739, 'samples': 3622464, 'steps': 18866, 'loss/train': 1.8319847583770752}
+08/30/2021 16:37:13 - INFO - __main__ - Step 18868: {'lr': 0.00048414677134840753, 'samples': 3622656, 'steps': 18867, 'loss/train': 1.8587208986282349}
+08/30/2021 16:37:13 - INFO - __main__ - Step 18869: {'lr': 0.00048414491162713814, 'samples': 3622848, 'steps': 18868, 'loss/train': 1.55882728099823}
+08/30/2021 16:37:13 - INFO - __main__ - Step 18870: {'lr': 0.00048414305180036665, 'samples': 3623040, 'steps': 18869, 'loss/train': 1.6058638095855713}
+08/30/2021 16:37:14 - INFO - __main__ - Step 18871: {'lr': 0.0004841411918680939, 'samples': 3623232, 'steps': 18870, 'loss/train': 1.3894546031951904}
+08/30/2021 16:37:14 - INFO - __main__ - Step 18872: {'lr': 0.0004841393318303208, 'samples': 3623424, 'steps': 18871, 'loss/train': 1.9317538738250732}
+08/30/2021 16:37:16 - INFO - __main__ - Step 18873: {'lr': 0.0004841374716870481, 'samples': 3623616, 'steps': 18872, 'loss/train': 2.1624057292938232}
+08/30/2021 16:37:16 - INFO - __main__ - Step 18874: {'lr': 0.00048413561143827665, 'samples': 3623808, 'steps': 18873, 'loss/train': 4.072031497955322}
+08/30/2021 16:37:17 - INFO - __main__ - Step 18875: {'lr': 0.00048413375108400736, 'samples': 3624000, 'steps': 18874, 'loss/train': 1.3719980716705322}
+08/30/2021 16:37:17 - INFO - __main__ - Step 18876: {'lr': 0.000484131890624241, 'samples': 3624192, 'steps': 18875, 'loss/train': 2.0993733406066895}
+08/30/2021 16:37:17 - INFO - __main__ - Step 18877: {'lr': 0.00048413003005897835, 'samples': 3624384, 'steps': 18876, 'loss/train': 1.4373953342437744}
+08/30/2021 16:37:19 - INFO - __main__ - Step 18878: {'lr': 0.0004841281693882204, 'samples': 3624576, 'steps': 18877, 'loss/train': 1.7812221050262451}
+08/30/2021 16:37:19 - INFO - __main__ - Step 18879: {'lr': 0.0004841263086119679, 'samples': 3624768, 'steps': 18878, 'loss/train': 1.3264883756637573}
+08/30/2021 16:37:20 - INFO - __main__ - Step 18880: {'lr': 0.00048412444773022166, 'samples': 3624960, 'steps': 18879, 'loss/train': 1.821436882019043}
+08/30/2021 16:37:20 - INFO - __main__ - Step 18881: {'lr': 0.0004841225867429826, 'samples': 3625152, 'steps': 18880, 'loss/train': 0.1224297508597374}
+08/30/2021 16:37:20 - INFO - __main__ - Step 18882: {'lr': 0.0004841207256502515, 'samples': 3625344, 'steps': 18881, 'loss/train': 1.7958325147628784}
+08/30/2021 16:37:22 - INFO - __main__ - Step 18883: {'lr': 0.0004841188644520292, 'samples': 3625536, 'steps': 18882, 'loss/train': 1.6555604934692383}
+08/30/2021 16:37:22 - INFO - __main__ - Step 18884: {'lr': 0.0004841170031483165, 'samples': 3625728, 'steps': 18883, 'loss/train': 1.895039439201355}
+08/30/2021 16:37:23 - INFO - __main__ - Step 18885: {'lr': 0.0004841151417391144, 'samples': 3625920, 'steps': 18884, 'loss/train': 1.6589775085449219}
+08/30/2021 16:37:23 - INFO - __main__ - Step 18886: {'lr': 0.00048411328022442357, 'samples': 3626112, 'steps': 18885, 'loss/train': 2.0037918090820312}
+08/30/2021 16:37:23 - INFO - __main__ - Step 18887: {'lr': 0.000484111418604245, 'samples': 3626304, 'steps': 18886, 'loss/train': 0.38222405314445496}
+08/30/2021 16:37:24 - INFO - __main__ - Step 18888: {'lr': 0.00048410955687857926, 'samples': 3626496, 'steps': 18887, 'loss/train': 0.8166512846946716}
+08/30/2021 16:37:25 - INFO - __main__ - Step 18889: {'lr': 0.0004841076950474275, 'samples': 3626688, 'steps': 18888, 'loss/train': 1.5573936700820923}
+08/30/2021 16:37:26 - INFO - __main__ - Step 18890: {'lr': 0.0004841058331107904, 'samples': 3626880, 'steps': 18889, 'loss/train': 1.5806729793548584}
+08/30/2021 16:37:26 - INFO - __main__ - Step 18891: {'lr': 0.00048410397106866883, 'samples': 3627072, 'steps': 18890, 'loss/train': 1.5310070514678955}
+08/30/2021 16:37:26 - INFO - __main__ - Step 18892: {'lr': 0.0004841021089210636, 'samples': 3627264, 'steps': 18891, 'loss/train': 1.0836338996887207}
+08/30/2021 16:37:27 - INFO - __main__ - Step 18893: {'lr': 0.0004841002466679756, 'samples': 3627456, 'steps': 18892, 'loss/train': 1.0207998752593994}
+08/30/2021 16:37:28 - INFO - __main__ - Step 18894: {'lr': 0.00048409838430940556, 'samples': 3627648, 'steps': 18893, 'loss/train': 1.770282506942749}
+08/30/2021 16:37:29 - INFO - __main__ - Step 18895: {'lr': 0.00048409652184535447, 'samples': 3627840, 'steps': 18894, 'loss/train': 2.0498998165130615}
+08/30/2021 16:37:29 - INFO - __main__ - Step 18896: {'lr': 0.0004840946592758231, 'samples': 3628032, 'steps': 18895, 'loss/train': 1.9854480028152466}
+08/30/2021 16:37:29 - INFO - __main__ - Step 18897: {'lr': 0.00048409279660081226, 'samples': 3628224, 'steps': 18896, 'loss/train': 1.1680973768234253}
+08/30/2021 16:37:30 - INFO - __main__ - Step 18898: {'lr': 0.0004840909338203229, 'samples': 3628416, 'steps': 18897, 'loss/train': 1.9105874300003052}
+08/30/2021 16:37:31 - INFO - __main__ - Step 18899: {'lr': 0.0004840890709343557, 'samples': 3628608, 'steps': 18898, 'loss/train': 1.7854198217391968}
+08/30/2021 16:37:32 - INFO - __main__ - Step 18900: {'lr': 0.0004840872079429116, 'samples': 3628800, 'steps': 18899, 'loss/train': 1.3159809112548828}
+08/30/2021 16:37:32 - INFO - __main__ - Step 18901: {'lr': 0.00048408534484599143, 'samples': 3628992, 'steps': 18900, 'loss/train': 1.999829888343811}
+08/30/2021 16:37:32 - INFO - __main__ - Step 18902: {'lr': 0.00048408348164359594, 'samples': 3629184, 'steps': 18901, 'loss/train': 1.5713098049163818}
+08/30/2021 16:37:33 - INFO - __main__ - Step 18903: {'lr': 0.00048408161833572613, 'samples': 3629376, 'steps': 18902, 'loss/train': 1.4454656839370728}
+08/30/2021 16:37:35 - INFO - __main__ - Step 18904: {'lr': 0.0004840797549223827, 'samples': 3629568, 'steps': 18903, 'loss/train': 1.9976674318313599}
+08/30/2021 16:37:35 - INFO - __main__ - Step 18905: {'lr': 0.00048407789140356654, 'samples': 3629760, 'steps': 18904, 'loss/train': 1.8277145624160767}
+08/30/2021 16:37:36 - INFO - __main__ - Step 18906: {'lr': 0.00048407602777927856, 'samples': 3629952, 'steps': 18905, 'loss/train': 1.0211728811264038}
+08/30/2021 16:37:36 - INFO - __main__ - Step 18907: {'lr': 0.0004840741640495195, 'samples': 3630144, 'steps': 18906, 'loss/train': 1.4919006824493408}
+08/30/2021 16:37:36 - INFO - __main__ - Step 18908: {'lr': 0.0004840723002142902, 'samples': 3630336, 'steps': 18907, 'loss/train': 1.4708335399627686}
+08/30/2021 16:37:37 - INFO - __main__ - Step 18909: {'lr': 0.0004840704362735916, 'samples': 3630528, 'steps': 18908, 'loss/train': 1.542413592338562}
+08/30/2021 16:37:39 - INFO - __main__ - Step 18910: {'lr': 0.0004840685722274244, 'samples': 3630720, 'steps': 18909, 'loss/train': 0.1078791692852974}
+08/30/2021 16:37:39 - INFO - __main__ - Step 18911: {'lr': 0.0004840667080757896, 'samples': 3630912, 'steps': 18910, 'loss/train': 1.592965006828308}
+08/30/2021 16:37:40 - INFO - __main__ - Step 18912: {'lr': 0.00048406484381868786, 'samples': 3631104, 'steps': 18911, 'loss/train': 0.6894677877426147}
+08/30/2021 16:37:40 - INFO - __main__ - Step 18913: {'lr': 0.0004840629794561202, 'samples': 3631296, 'steps': 18912, 'loss/train': 0.5969001054763794}
+08/30/2021 16:37:41 - INFO - __main__ - Step 18914: {'lr': 0.0004840611149880873, 'samples': 3631488, 'steps': 18913, 'loss/train': 0.5913561582565308}
+08/30/2021 16:37:41 - INFO - __main__ - Step 18915: {'lr': 0.0004840592504145901, 'samples': 3631680, 'steps': 18914, 'loss/train': 1.8101297616958618}
+08/30/2021 16:37:42 - INFO - __main__ - Step 18916: {'lr': 0.0004840573857356294, 'samples': 3631872, 'steps': 18915, 'loss/train': 0.9657647609710693}
+08/30/2021 16:37:43 - INFO - __main__ - Step 18917: {'lr': 0.0004840555209512061, 'samples': 3632064, 'steps': 18916, 'loss/train': 1.3331830501556396}
+08/30/2021 16:37:43 - INFO - __main__ - Step 18918: {'lr': 0.00048405365606132096, 'samples': 3632256, 'steps': 18917, 'loss/train': 1.512233018875122}
+08/30/2021 16:37:43 - INFO - __main__ - Step 18919: {'lr': 0.00048405179106597487, 'samples': 3632448, 'steps': 18918, 'loss/train': 1.2156389951705933}
+08/30/2021 16:37:44 - INFO - __main__ - Step 18920: {'lr': 0.0004840499259651686, 'samples': 3632640, 'steps': 18919, 'loss/train': 1.3688234090805054}
+08/30/2021 16:37:45 - INFO - __main__ - Step 18921: {'lr': 0.0004840480607589031, 'samples': 3632832, 'steps': 18920, 'loss/train': 2.3019397258758545}
+08/30/2021 16:37:46 - INFO - __main__ - Step 18922: {'lr': 0.0004840461954471792, 'samples': 3633024, 'steps': 18921, 'loss/train': 1.5780038833618164}
+08/30/2021 16:37:46 - INFO - __main__ - Step 18923: {'lr': 0.00048404433002999757, 'samples': 3633216, 'steps': 18922, 'loss/train': 1.473617434501648}
+08/30/2021 16:37:46 - INFO - __main__ - Step 18924: {'lr': 0.0004840424645073593, 'samples': 3633408, 'steps': 18923, 'loss/train': 1.555058479309082}
+08/30/2021 16:37:47 - INFO - __main__ - Step 18925: {'lr': 0.000484040598879265, 'samples': 3633600, 'steps': 18924, 'loss/train': 1.5462207794189453}
+08/30/2021 16:37:48 - INFO - __main__ - Step 18926: {'lr': 0.0004840387331457157, 'samples': 3633792, 'steps': 18925, 'loss/train': 1.7636566162109375}
+08/30/2021 16:37:49 - INFO - __main__ - Step 18927: {'lr': 0.00048403686730671215, 'samples': 3633984, 'steps': 18926, 'loss/train': 1.7328298091888428}
+08/30/2021 16:37:49 - INFO - __main__ - Step 18928: {'lr': 0.0004840350013622552, 'samples': 3634176, 'steps': 18927, 'loss/train': 1.6066393852233887}
+08/30/2021 16:37:49 - INFO - __main__ - Step 18929: {'lr': 0.0004840331353123456, 'samples': 3634368, 'steps': 18928, 'loss/train': 1.3455466032028198}
+08/30/2021 16:37:50 - INFO - __main__ - Step 18930: {'lr': 0.00048403126915698435, 'samples': 3634560, 'steps': 18929, 'loss/train': 1.7716022729873657}
+08/30/2021 16:37:51 - INFO - __main__ - Step 18931: {'lr': 0.00048402940289617223, 'samples': 3634752, 'steps': 18930, 'loss/train': 1.5083965063095093}
+08/30/2021 16:37:52 - INFO - __main__ - Step 18932: {'lr': 0.00048402753652991007, 'samples': 3634944, 'steps': 18931, 'loss/train': 1.6436960697174072}
+08/30/2021 16:37:52 - INFO - __main__ - Step 18933: {'lr': 0.0004840256700581988, 'samples': 3635136, 'steps': 18932, 'loss/train': 1.7264306545257568}
+08/30/2021 16:37:52 - INFO - __main__ - Step 18934: {'lr': 0.000484023803481039, 'samples': 3635328, 'steps': 18933, 'loss/train': 2.0844295024871826}
+08/30/2021 16:37:53 - INFO - __main__ - Step 18935: {'lr': 0.00048402193679843175, 'samples': 3635520, 'steps': 18934, 'loss/train': 2.012082815170288}
+08/30/2021 16:37:54 - INFO - __main__ - Step 18936: {'lr': 0.00048402007001037786, 'samples': 3635712, 'steps': 18935, 'loss/train': 1.2280157804489136}
+08/30/2021 16:37:55 - INFO - __main__ - Step 18937: {'lr': 0.0004840182031168781, 'samples': 3635904, 'steps': 18936, 'loss/train': 1.131327509880066}
+08/30/2021 16:37:55 - INFO - __main__ - Step 18938: {'lr': 0.0004840163361179334, 'samples': 3636096, 'steps': 18937, 'loss/train': 2.4972782135009766}
+08/30/2021 16:37:56 - INFO - __main__ - Step 18939: {'lr': 0.00048401446901354453, 'samples': 3636288, 'steps': 18938, 'loss/train': 1.8392916917800903}
+08/30/2021 16:37:56 - INFO - __main__ - Step 18940: {'lr': 0.0004840126018037123, 'samples': 3636480, 'steps': 18939, 'loss/train': 1.055567979812622}
+08/30/2021 16:37:56 - INFO - __main__ - Step 18941: {'lr': 0.0004840107344884377, 'samples': 3636672, 'steps': 18940, 'loss/train': 1.5509389638900757}
+08/30/2021 16:37:58 - INFO - __main__ - Step 18942: {'lr': 0.0004840088670677214, 'samples': 3636864, 'steps': 18941, 'loss/train': 1.7684361934661865}
+08/30/2021 16:37:58 - INFO - __main__ - Step 18943: {'lr': 0.0004840069995415643, 'samples': 3637056, 'steps': 18942, 'loss/train': 1.6116442680358887}
+08/30/2021 16:37:58 - INFO - __main__ - Step 18944: {'lr': 0.0004840051319099673, 'samples': 3637248, 'steps': 18943, 'loss/train': 1.3261322975158691}
+08/30/2021 16:37:59 - INFO - __main__ - Step 18945: {'lr': 0.0004840032641729312, 'samples': 3637440, 'steps': 18944, 'loss/train': 1.5126307010650635}
+08/30/2021 16:37:59 - INFO - __main__ - Step 18946: {'lr': 0.0004840013963304568, 'samples': 3637632, 'steps': 18945, 'loss/train': 1.330876350402832}
+08/30/2021 16:38:01 - INFO - __main__ - Step 18947: {'lr': 0.000483999528382545, 'samples': 3637824, 'steps': 18946, 'loss/train': 1.518810510635376}
+08/30/2021 16:38:01 - INFO - __main__ - Step 18948: {'lr': 0.00048399766032919666, 'samples': 3638016, 'steps': 18947, 'loss/train': 1.6638489961624146}
+08/30/2021 16:38:02 - INFO - __main__ - Step 18949: {'lr': 0.0004839957921704126, 'samples': 3638208, 'steps': 18948, 'loss/train': 1.2972757816314697}
+08/30/2021 16:38:02 - INFO - __main__ - Step 18950: {'lr': 0.0004839939239061936, 'samples': 3638400, 'steps': 18949, 'loss/train': 1.5717649459838867}
+08/30/2021 16:38:02 - INFO - __main__ - Step 18951: {'lr': 0.00048399205553654046, 'samples': 3638592, 'steps': 18950, 'loss/train': 2.0166611671447754}
+08/30/2021 16:38:04 - INFO - __main__ - Step 18952: {'lr': 0.0004839901870614543, 'samples': 3638784, 'steps': 18951, 'loss/train': 2.096992254257202}
+08/30/2021 16:38:05 - INFO - __main__ - Step 18953: {'lr': 0.0004839883184809356, 'samples': 3638976, 'steps': 18952, 'loss/train': 1.51292884349823}
+08/30/2021 16:38:05 - INFO - __main__ - Step 18954: {'lr': 0.00048398644979498543, 'samples': 3639168, 'steps': 18953, 'loss/train': 1.4720566272735596}
+08/30/2021 16:38:05 - INFO - __main__ - Step 18955: {'lr': 0.0004839845810036047, 'samples': 3639360, 'steps': 18954, 'loss/train': 1.8984678983688354}
+08/30/2021 16:38:06 - INFO - __main__ - Step 18956: {'lr': 0.00048398271210679393, 'samples': 3639552, 'steps': 18955, 'loss/train': 1.601037621498108}
+08/30/2021 16:38:06 - INFO - __main__ - Step 18957: {'lr': 0.0004839808431045543, 'samples': 3639744, 'steps': 18956, 'loss/train': 2.0644285678863525}
+08/30/2021 16:38:08 - INFO - __main__ - Step 18958: {'lr': 0.00048397897399688643, 'samples': 3639936, 'steps': 18957, 'loss/train': 0.19773952662944794}
+08/30/2021 16:38:09 - INFO - __main__ - Step 18959: {'lr': 0.0004839771047837913, 'samples': 3640128, 'steps': 18958, 'loss/train': 2.199984550476074}
+08/30/2021 16:38:09 - INFO - __main__ - Step 18960: {'lr': 0.00048397523546526966, 'samples': 3640320, 'steps': 18959, 'loss/train': 1.8648544549942017}
+08/30/2021 16:38:10 - INFO - __main__ - Step 18961: {'lr': 0.0004839733660413224, 'samples': 3640512, 'steps': 18960, 'loss/train': 0.8826211094856262}
+08/30/2021 16:38:10 - INFO - __main__ - Step 18962: {'lr': 0.0004839714965119504, 'samples': 3640704, 'steps': 18961, 'loss/train': 1.3562123775482178}
+08/30/2021 16:38:11 - INFO - __main__ - Step 18963: {'lr': 0.0004839696268771544, 'samples': 3640896, 'steps': 18962, 'loss/train': 1.1805273294448853}
+08/30/2021 16:38:12 - INFO - __main__ - Step 18964: {'lr': 0.0004839677571369353, 'samples': 3641088, 'steps': 18963, 'loss/train': 1.6383274793624878}
+08/30/2021 16:38:12 - INFO - __main__ - Step 18965: {'lr': 0.000483965887291294, 'samples': 3641280, 'steps': 18964, 'loss/train': 1.8031878471374512}
+08/30/2021 16:38:13 - INFO - __main__ - Step 18966: {'lr': 0.0004839640173402312, 'samples': 3641472, 'steps': 18965, 'loss/train': 1.878609538078308}
+08/30/2021 16:38:13 - INFO - __main__ - Step 18967: {'lr': 0.00048396214728374786, 'samples': 3641664, 'steps': 18966, 'loss/train': 1.4588313102722168}
+08/30/2021 16:38:15 - INFO - __main__ - Step 18968: {'lr': 0.00048396027712184475, 'samples': 3641856, 'steps': 18967, 'loss/train': 1.53431236743927}
+08/30/2021 16:38:15 - INFO - __main__ - Step 18969: {'lr': 0.0004839584068545228, 'samples': 3642048, 'steps': 18968, 'loss/train': 1.6313693523406982}
+08/30/2021 16:38:16 - INFO - __main__ - Step 18970: {'lr': 0.0004839565364817828, 'samples': 3642240, 'steps': 18969, 'loss/train': 2.1428191661834717}
+08/30/2021 16:38:16 - INFO - __main__ - Step 18971: {'lr': 0.0004839546660036256, 'samples': 3642432, 'steps': 18970, 'loss/train': 1.717660903930664}
+08/30/2021 16:38:16 - INFO - __main__ - Step 18972: {'lr': 0.000483952795420052, 'samples': 3642624, 'steps': 18971, 'loss/train': 2.3953351974487305}
+08/30/2021 16:38:19 - INFO - __main__ - Step 18973: {'lr': 0.0004839509247310629, 'samples': 3642816, 'steps': 18972, 'loss/train': 2.4619195461273193}
+08/30/2021 16:38:19 - INFO - __main__ - Step 18974: {'lr': 0.00048394905393665913, 'samples': 3643008, 'steps': 18973, 'loss/train': 1.441680908203125}
+08/30/2021 16:38:19 - INFO - __main__ - Step 18975: {'lr': 0.00048394718303684147, 'samples': 3643200, 'steps': 18974, 'loss/train': 1.2632781267166138}
+08/30/2021 16:38:20 - INFO - __main__ - Step 18976: {'lr': 0.00048394531203161084, 'samples': 3643392, 'steps': 18975, 'loss/train': 1.9469889402389526}
+08/30/2021 16:38:20 - INFO - __main__ - Step 18977: {'lr': 0.00048394344092096816, 'samples': 3643584, 'steps': 18976, 'loss/train': 1.5366647243499756}
+08/30/2021 16:38:21 - INFO - __main__ - Step 18978: {'lr': 0.0004839415697049141, 'samples': 3643776, 'steps': 18977, 'loss/train': 1.3638979196548462}
+08/30/2021 16:38:21 - INFO - __main__ - Step 18979: {'lr': 0.00048393969838344956, 'samples': 3643968, 'steps': 18978, 'loss/train': 1.0342578887939453}
+08/30/2021 16:38:22 - INFO - __main__ - Step 18980: {'lr': 0.0004839378269565754, 'samples': 3644160, 'steps': 18979, 'loss/train': 0.22066383063793182}
+08/30/2021 16:38:23 - INFO - __main__ - Step 18981: {'lr': 0.00048393595542429253, 'samples': 3644352, 'steps': 18980, 'loss/train': 1.4377784729003906}
+08/30/2021 16:38:23 - INFO - __main__ - Step 18982: {'lr': 0.0004839340837866016, 'samples': 3644544, 'steps': 18981, 'loss/train': 1.9067206382751465}
+08/30/2021 16:38:24 - INFO - __main__ - Step 18983: {'lr': 0.00048393221204350376, 'samples': 3644736, 'steps': 18982, 'loss/train': 1.786861777305603}
+08/30/2021 16:38:24 - INFO - __main__ - Step 18984: {'lr': 0.0004839303401949996, 'samples': 3644928, 'steps': 18983, 'loss/train': 2.1087722778320312}
+08/30/2021 16:38:25 - INFO - __main__ - Step 18985: {'lr': 0.00048392846824109, 'samples': 3645120, 'steps': 18984, 'loss/train': 1.2350329160690308}
+08/30/2021 16:38:26 - INFO - __main__ - Step 18986: {'lr': 0.00048392659618177585, 'samples': 3645312, 'steps': 18985, 'loss/train': 1.221070408821106}
+08/30/2021 16:38:26 - INFO - __main__ - Step 18987: {'lr': 0.000483924724017058, 'samples': 3645504, 'steps': 18986, 'loss/train': 1.5440654754638672}
+08/30/2021 16:38:27 - INFO - __main__ - Step 18988: {'lr': 0.00048392285174693727, 'samples': 3645696, 'steps': 18987, 'loss/train': 1.292403221130371}
+08/30/2021 16:38:27 - INFO - __main__ - Step 18989: {'lr': 0.0004839209793714146, 'samples': 3645888, 'steps': 18988, 'loss/train': 1.4480961561203003}
+08/30/2021 16:38:28 - INFO - __main__ - Step 18990: {'lr': 0.00048391910689049057, 'samples': 3646080, 'steps': 18989, 'loss/train': 1.1235562562942505}
+08/30/2021 16:38:29 - INFO - __main__ - Step 18991: {'lr': 0.00048391723430416634, 'samples': 3646272, 'steps': 18990, 'loss/train': 1.2940679788589478}
+08/30/2021 16:38:29 - INFO - __main__ - Step 18992: {'lr': 0.00048391536161244254, 'samples': 3646464, 'steps': 18991, 'loss/train': 1.7962981462478638}
+08/30/2021 16:38:29 - INFO - __main__ - Step 18993: {'lr': 0.0004839134888153202, 'samples': 3646656, 'steps': 18992, 'loss/train': 1.6466200351715088}
+08/30/2021 16:38:30 - INFO - __main__ - Step 18994: {'lr': 0.00048391161591279994, 'samples': 3646848, 'steps': 18993, 'loss/train': 1.578004240989685}
+08/30/2021 16:38:32 - INFO - __main__ - Step 18995: {'lr': 0.0004839097429048827, 'samples': 3647040, 'steps': 18994, 'loss/train': 1.8380944728851318}
+08/30/2021 16:38:32 - INFO - __main__ - Step 18996: {'lr': 0.00048390786979156944, 'samples': 3647232, 'steps': 18995, 'loss/train': 1.4364378452301025}
+08/30/2021 16:38:32 - INFO - __main__ - Step 18997: {'lr': 0.0004839059965728608, 'samples': 3647424, 'steps': 18996, 'loss/train': 3.3598239421844482}
+08/30/2021 16:38:33 - INFO - __main__ - Step 18998: {'lr': 0.0004839041232487578, 'samples': 3647616, 'steps': 18997, 'loss/train': 2.0735983848571777}
+08/30/2021 16:38:33 - INFO - __main__ - Step 18999: {'lr': 0.0004839022498192612, 'samples': 3647808, 'steps': 18998, 'loss/train': 1.5744572877883911}
+08/30/2021 16:38:33 - INFO - __main__ - Step 19000: {'lr': 0.0004839003762843718, 'samples': 3648000, 'steps': 18999, 'loss/train': 1.8879928588867188}
+08/30/2021 16:38:35 - INFO - __main__ - Step 19001: {'lr': 0.00048389850264409054, 'samples': 3648192, 'steps': 19000, 'loss/train': 0.9014919996261597}
+08/30/2021 16:38:35 - INFO - __main__ - Step 19002: {'lr': 0.00048389662889841825, 'samples': 3648384, 'steps': 19001, 'loss/train': 2.4000437259674072}
+08/30/2021 16:38:36 - INFO - __main__ - Step 19003: {'lr': 0.0004838947550473557, 'samples': 3648576, 'steps': 19002, 'loss/train': 1.8039371967315674}
+08/30/2021 16:38:36 - INFO - __main__ - Step 19004: {'lr': 0.00048389288109090383, 'samples': 3648768, 'steps': 19003, 'loss/train': 2.0567820072174072}
+08/30/2021 16:38:36 - INFO - __main__ - Step 19005: {'lr': 0.0004838910070290634, 'samples': 3648960, 'steps': 19004, 'loss/train': 1.4886016845703125}
+08/30/2021 16:38:38 - INFO - __main__ - Step 19006: {'lr': 0.00048388913286183535, 'samples': 3649152, 'steps': 19005, 'loss/train': 2.1133718490600586}
+08/30/2021 16:38:39 - INFO - __main__ - Step 19007: {'lr': 0.0004838872585892204, 'samples': 3649344, 'steps': 19006, 'loss/train': 1.2090160846710205}
+08/30/2021 16:38:39 - INFO - __main__ - Step 19008: {'lr': 0.00048388538421121946, 'samples': 3649536, 'steps': 19007, 'loss/train': 2.146662473678589}
+08/30/2021 16:38:40 - INFO - __main__ - Step 19009: {'lr': 0.00048388350972783346, 'samples': 3649728, 'steps': 19008, 'loss/train': 2.1458070278167725}
+08/30/2021 16:38:40 - INFO - __main__ - Step 19010: {'lr': 0.000483881635139063, 'samples': 3649920, 'steps': 19009, 'loss/train': 1.6581511497497559}
+08/30/2021 16:38:40 - INFO - __main__ - Step 19011: {'lr': 0.00048387976044490924, 'samples': 3650112, 'steps': 19010, 'loss/train': 1.9609956741333008}
+08/30/2021 16:38:41 - INFO - __main__ - Step 19012: {'lr': 0.0004838778856453728, 'samples': 3650304, 'steps': 19011, 'loss/train': 1.3583651781082153}
+08/30/2021 16:38:43 - INFO - __main__ - Step 19013: {'lr': 0.00048387601074045464, 'samples': 3650496, 'steps': 19012, 'loss/train': 1.2468626499176025}
+08/30/2021 16:38:43 - INFO - __main__ - Step 19014: {'lr': 0.0004838741357301555, 'samples': 3650688, 'steps': 19013, 'loss/train': 1.5498229265213013}
+08/30/2021 16:38:44 - INFO - __main__ - Step 19015: {'lr': 0.00048387226061447633, 'samples': 3650880, 'steps': 19014, 'loss/train': 1.8786801099777222}
+08/30/2021 16:38:44 - INFO - __main__ - Step 19016: {'lr': 0.0004838703853934179, 'samples': 3651072, 'steps': 19015, 'loss/train': 1.5610238313674927}
+08/30/2021 16:38:44 - INFO - __main__ - Step 19017: {'lr': 0.0004838685100669811, 'samples': 3651264, 'steps': 19016, 'loss/train': 1.8917293548583984}
+08/30/2021 16:38:46 - INFO - __main__ - Step 19018: {'lr': 0.0004838666346351667, 'samples': 3651456, 'steps': 19017, 'loss/train': 2.051845073699951}
+08/30/2021 16:38:46 - INFO - __main__ - Step 19019: {'lr': 0.0004838647590979757, 'samples': 3651648, 'steps': 19018, 'loss/train': 1.5275967121124268}
+08/30/2021 16:38:47 - INFO - __main__ - Step 19020: {'lr': 0.00048386288345540876, 'samples': 3651840, 'steps': 19019, 'loss/train': 2.161799907684326}
+08/30/2021 16:38:47 - INFO - __main__ - Step 19021: {'lr': 0.00048386100770746686, 'samples': 3652032, 'steps': 19020, 'loss/train': 1.8600828647613525}
+08/30/2021 16:38:47 - INFO - __main__ - Step 19022: {'lr': 0.00048385913185415076, 'samples': 3652224, 'steps': 19021, 'loss/train': 1.7161812782287598}
+08/30/2021 16:38:49 - INFO - __main__ - Step 19023: {'lr': 0.00048385725589546137, 'samples': 3652416, 'steps': 19022, 'loss/train': 1.2950397729873657}
+08/30/2021 16:38:50 - INFO - __main__ - Step 19024: {'lr': 0.0004838553798313995, 'samples': 3652608, 'steps': 19023, 'loss/train': 1.843496561050415}
+08/30/2021 16:38:50 - INFO - __main__ - Step 19025: {'lr': 0.000483853503661966, 'samples': 3652800, 'steps': 19024, 'loss/train': 1.6987963914871216}
+08/30/2021 16:38:50 - INFO - __main__ - Step 19026: {'lr': 0.00048385162738716174, 'samples': 3652992, 'steps': 19025, 'loss/train': 1.9262787103652954}
+08/30/2021 16:38:51 - INFO - __main__ - Step 19027: {'lr': 0.00048384975100698756, 'samples': 3653184, 'steps': 19026, 'loss/train': 1.5370110273361206}
+08/30/2021 16:38:51 - INFO - __main__ - Step 19028: {'lr': 0.0004838478745214443, 'samples': 3653376, 'steps': 19027, 'loss/train': 0.09243328869342804}
+08/30/2021 16:38:53 - INFO - __main__ - Step 19029: {'lr': 0.00048384599793053275, 'samples': 3653568, 'steps': 19028, 'loss/train': 2.0480871200561523}
+08/30/2021 16:38:53 - INFO - __main__ - Step 19030: {'lr': 0.0004838441212342538, 'samples': 3653760, 'steps': 19029, 'loss/train': 1.5750621557235718}
+08/30/2021 16:38:54 - INFO - __main__ - Step 19031: {'lr': 0.0004838422444326084, 'samples': 3653952, 'steps': 19030, 'loss/train': 3.643911361694336}
+08/30/2021 16:38:54 - INFO - __main__ - Step 19032: {'lr': 0.0004838403675255971, 'samples': 3654144, 'steps': 19031, 'loss/train': 1.4532514810562134}
+08/30/2021 16:38:54 - INFO - __main__ - Step 19033: {'lr': 0.0004838384905132211, 'samples': 3654336, 'steps': 19032, 'loss/train': 1.6092004776000977}
+08/30/2021 16:38:55 - INFO - __main__ - Step 19034: {'lr': 0.000483836613395481, 'samples': 3654528, 'steps': 19033, 'loss/train': 1.7530258893966675}
+08/30/2021 16:38:56 - INFO - __main__ - Step 19035: {'lr': 0.0004838347361723778, 'samples': 3654720, 'steps': 19034, 'loss/train': 0.6507481932640076}
+08/30/2021 16:38:57 - INFO - __main__ - Step 19036: {'lr': 0.0004838328588439123, 'samples': 3654912, 'steps': 19035, 'loss/train': 1.0046108961105347}
+08/30/2021 16:38:57 - INFO - __main__ - Step 19037: {'lr': 0.0004838309814100852, 'samples': 3655104, 'steps': 19036, 'loss/train': 2.8187057971954346}
+08/30/2021 16:38:57 - INFO - __main__ - Step 19038: {'lr': 0.0004838291038708975, 'samples': 3655296, 'steps': 19037, 'loss/train': 2.971289873123169}
+08/30/2021 16:38:58 - INFO - __main__ - Step 19039: {'lr': 0.00048382722622635014, 'samples': 3655488, 'steps': 19038, 'loss/train': 1.3843629360198975}
+08/30/2021 16:38:59 - INFO - __main__ - Step 19040: {'lr': 0.0004838253484764437, 'samples': 3655680, 'steps': 19039, 'loss/train': 1.6307727098464966}
+08/30/2021 16:39:00 - INFO - __main__ - Step 19041: {'lr': 0.0004838234706211792, 'samples': 3655872, 'steps': 19040, 'loss/train': 1.6135318279266357}
+08/30/2021 16:39:00 - INFO - __main__ - Step 19042: {'lr': 0.00048382159266055746, 'samples': 3656064, 'steps': 19041, 'loss/train': 0.16198968887329102}
+08/30/2021 16:39:00 - INFO - __main__ - Step 19043: {'lr': 0.0004838197145945793, 'samples': 3656256, 'steps': 19042, 'loss/train': 1.6448854207992554}
+08/30/2021 16:39:01 - INFO - __main__ - Step 19044: {'lr': 0.0004838178364232456, 'samples': 3656448, 'steps': 19043, 'loss/train': 2.0197489261627197}
+08/30/2021 16:39:02 - INFO - __main__ - Step 19045: {'lr': 0.00048381595814655723, 'samples': 3656640, 'steps': 19044, 'loss/train': 1.3987911939620972}
+08/30/2021 16:39:03 - INFO - __main__ - Step 19046: {'lr': 0.000483814079764515, 'samples': 3656832, 'steps': 19045, 'loss/train': 1.6451157331466675}
+08/30/2021 16:39:03 - INFO - __main__ - Step 19047: {'lr': 0.00048381220127711967, 'samples': 3657024, 'steps': 19046, 'loss/train': 2.3354761600494385}
+08/30/2021 16:39:03 - INFO - __main__ - Step 19048: {'lr': 0.0004838103226843722, 'samples': 3657216, 'steps': 19047, 'loss/train': 1.6441980600357056}
+08/30/2021 16:39:04 - INFO - __main__ - Step 19049: {'lr': 0.00048380844398627343, 'samples': 3657408, 'steps': 19048, 'loss/train': 1.3039494752883911}
+08/30/2021 16:39:04 - INFO - __main__ - Step 19050: {'lr': 0.0004838065651828242, 'samples': 3657600, 'steps': 19049, 'loss/train': 1.348453402519226}
+08/30/2021 16:39:06 - INFO - __main__ - Step 19051: {'lr': 0.0004838046862740253, 'samples': 3657792, 'steps': 19050, 'loss/train': 1.6213575601577759}
+08/30/2021 16:39:06 - INFO - __main__ - Step 19052: {'lr': 0.0004838028072598777, 'samples': 3657984, 'steps': 19051, 'loss/train': 1.3830773830413818}
+08/30/2021 16:39:06 - INFO - __main__ - Step 19053: {'lr': 0.00048380092814038204, 'samples': 3658176, 'steps': 19052, 'loss/train': 1.631980299949646}
+08/30/2021 16:39:07 - INFO - __main__ - Step 19054: {'lr': 0.0004837990489155394, 'samples': 3658368, 'steps': 19053, 'loss/train': 1.7626631259918213}
+08/30/2021 16:39:07 - INFO - __main__ - Step 19055: {'lr': 0.00048379716958535043, 'samples': 3658560, 'steps': 19054, 'loss/train': 1.5269496440887451}
+08/30/2021 16:39:09 - INFO - __main__ - Step 19056: {'lr': 0.00048379529014981604, 'samples': 3658752, 'steps': 19055, 'loss/train': 0.27664247155189514}
+08/30/2021 16:39:09 - INFO - __main__ - Step 19057: {'lr': 0.0004837934106089372, 'samples': 3658944, 'steps': 19056, 'loss/train': 1.5194077491760254}
+08/30/2021 16:39:09 - INFO - __main__ - Step 19058: {'lr': 0.0004837915309627146, 'samples': 3659136, 'steps': 19057, 'loss/train': 1.365946650505066}
+08/30/2021 16:39:10 - INFO - __main__ - Step 19059: {'lr': 0.00048378965121114917, 'samples': 3659328, 'steps': 19058, 'loss/train': 1.3631266355514526}
+08/30/2021 16:39:10 - INFO - __main__ - Step 19060: {'lr': 0.00048378777135424166, 'samples': 3659520, 'steps': 19059, 'loss/train': 1.2037910223007202}
+08/30/2021 16:39:12 - INFO - __main__ - Step 19061: {'lr': 0.0004837858913919931, 'samples': 3659712, 'steps': 19060, 'loss/train': 1.6297072172164917}
+08/30/2021 16:39:12 - INFO - __main__ - Step 19062: {'lr': 0.0004837840113244042, 'samples': 3659904, 'steps': 19061, 'loss/train': 1.5092374086380005}
+08/30/2021 16:39:12 - INFO - __main__ - Step 19063: {'lr': 0.00048378213115147573, 'samples': 3660096, 'steps': 19062, 'loss/train': 1.9230157136917114}
+08/30/2021 16:39:13 - INFO - __main__ - Step 19064: {'lr': 0.00048378025087320877, 'samples': 3660288, 'steps': 19063, 'loss/train': 1.9381505250930786}
+08/30/2021 16:39:13 - INFO - __main__ - Step 19065: {'lr': 0.0004837783704896039, 'samples': 3660480, 'steps': 19064, 'loss/train': 0.7553221583366394}
+08/30/2021 16:39:15 - INFO - __main__ - Step 19066: {'lr': 0.0004837764900006623, 'samples': 3660672, 'steps': 19065, 'loss/train': 1.3389997482299805}
+08/30/2021 16:39:15 - INFO - __main__ - Step 19067: {'lr': 0.0004837746094063844, 'samples': 3660864, 'steps': 19066, 'loss/train': 1.5995224714279175}
+08/30/2021 16:39:16 - INFO - __main__ - Step 19068: {'lr': 0.00048377272870677135, 'samples': 3661056, 'steps': 19067, 'loss/train': 1.7355479001998901}
+08/30/2021 16:39:16 - INFO - __main__ - Step 19069: {'lr': 0.000483770847901824, 'samples': 3661248, 'steps': 19068, 'loss/train': 2.67655611038208}
+08/30/2021 16:39:16 - INFO - __main__ - Step 19070: {'lr': 0.000483768966991543, 'samples': 3661440, 'steps': 19069, 'loss/train': 1.287881851196289}
+08/30/2021 16:39:18 - INFO - __main__ - Step 19071: {'lr': 0.0004837670859759294, 'samples': 3661632, 'steps': 19070, 'loss/train': 1.5589580535888672}
+08/30/2021 16:39:18 - INFO - __main__ - Step 19072: {'lr': 0.0004837652048549839, 'samples': 3661824, 'steps': 19071, 'loss/train': 1.855506181716919}
+08/30/2021 16:39:19 - INFO - __main__ - Step 19073: {'lr': 0.00048376332362870745, 'samples': 3662016, 'steps': 19072, 'loss/train': 1.6589117050170898}
+08/30/2021 16:39:19 - INFO - __main__ - Step 19074: {'lr': 0.00048376144229710083, 'samples': 3662208, 'steps': 19073, 'loss/train': 1.7377173900604248}
+08/30/2021 16:39:19 - INFO - __main__ - Step 19075: {'lr': 0.00048375956086016495, 'samples': 3662400, 'steps': 19074, 'loss/train': 0.11043886095285416}
+08/30/2021 16:39:21 - INFO - __main__ - Step 19076: {'lr': 0.0004837576793179005, 'samples': 3662592, 'steps': 19075, 'loss/train': 2.205615997314453}
+08/30/2021 16:39:22 - INFO - __main__ - Step 19077: {'lr': 0.00048375579767030854, 'samples': 3662784, 'steps': 19076, 'loss/train': 1.613686203956604}
+08/30/2021 16:39:22 - INFO - __main__ - Step 19078: {'lr': 0.0004837539159173898, 'samples': 3662976, 'steps': 19077, 'loss/train': 1.8518331050872803}
+08/30/2021 16:39:22 - INFO - __main__ - Step 19079: {'lr': 0.00048375203405914515, 'samples': 3663168, 'steps': 19078, 'loss/train': 0.1458100527524948}
+08/30/2021 16:39:23 - INFO - __main__ - Step 19080: {'lr': 0.00048375015209557547, 'samples': 3663360, 'steps': 19079, 'loss/train': 1.805875301361084}
+08/30/2021 16:39:24 - INFO - __main__ - Step 19081: {'lr': 0.00048374827002668156, 'samples': 3663552, 'steps': 19080, 'loss/train': 1.8509334325790405}
+08/30/2021 16:39:25 - INFO - __main__ - Step 19082: {'lr': 0.0004837463878524643, 'samples': 3663744, 'steps': 19081, 'loss/train': 1.6861164569854736}
+08/30/2021 16:39:25 - INFO - __main__ - Step 19083: {'lr': 0.0004837445055729245, 'samples': 3663936, 'steps': 19082, 'loss/train': 1.4038214683532715}
+08/30/2021 16:39:25 - INFO - __main__ - Step 19084: {'lr': 0.00048374262318806306, 'samples': 3664128, 'steps': 19083, 'loss/train': 1.2989164590835571}
+08/30/2021 16:39:26 - INFO - __main__ - Step 19085: {'lr': 0.00048374074069788077, 'samples': 3664320, 'steps': 19084, 'loss/train': 0.9655818939208984}
+08/30/2021 16:39:27 - INFO - __main__ - Step 19086: {'lr': 0.0004837388581023785, 'samples': 3664512, 'steps': 19085, 'loss/train': 1.4404168128967285}
+08/30/2021 16:39:28 - INFO - __main__ - Step 19087: {'lr': 0.0004837369754015571, 'samples': 3664704, 'steps': 19086, 'loss/train': 1.8048416376113892}
+08/30/2021 16:39:28 - INFO - __main__ - Step 19088: {'lr': 0.0004837350925954175, 'samples': 3664896, 'steps': 19087, 'loss/train': 2.047614336013794}
+08/30/2021 16:39:28 - INFO - __main__ - Step 19089: {'lr': 0.00048373320968396043, 'samples': 3665088, 'steps': 19088, 'loss/train': 0.8277368545532227}
+08/30/2021 16:39:29 - INFO - __main__ - Step 19090: {'lr': 0.0004837313266671868, 'samples': 3665280, 'steps': 19089, 'loss/train': 1.7643955945968628}
+08/30/2021 16:39:29 - INFO - __main__ - Step 19091: {'lr': 0.0004837294435450974, 'samples': 3665472, 'steps': 19090, 'loss/train': 1.066404104232788}
+08/30/2021 16:39:31 - INFO - __main__ - Step 19092: {'lr': 0.00048372756031769316, 'samples': 3665664, 'steps': 19091, 'loss/train': 0.10456026345491409}
+08/30/2021 16:39:31 - INFO - __main__ - Step 19093: {'lr': 0.00048372567698497487, 'samples': 3665856, 'steps': 19092, 'loss/train': 1.5527896881103516}
+08/30/2021 16:39:32 - INFO - __main__ - Step 19094: {'lr': 0.0004837237935469434, 'samples': 3666048, 'steps': 19093, 'loss/train': 1.5800169706344604}
+08/30/2021 16:39:32 - INFO - __main__ - Step 19095: {'lr': 0.00048372191000359955, 'samples': 3666240, 'steps': 19094, 'loss/train': 1.4646916389465332}
+08/30/2021 16:39:32 - INFO - __main__ - Step 19096: {'lr': 0.00048372002635494425, 'samples': 3666432, 'steps': 19095, 'loss/train': 1.577537178993225}
+08/30/2021 16:39:34 - INFO - __main__ - Step 19097: {'lr': 0.00048371814260097834, 'samples': 3666624, 'steps': 19096, 'loss/train': 1.6097098588943481}
+08/30/2021 16:39:34 - INFO - __main__ - Step 19098: {'lr': 0.0004837162587417027, 'samples': 3666816, 'steps': 19097, 'loss/train': 1.6733466386795044}
+08/30/2021 16:39:35 - INFO - __main__ - Step 19099: {'lr': 0.000483714374777118, 'samples': 3667008, 'steps': 19098, 'loss/train': 1.3653650283813477}
+08/30/2021 16:39:35 - INFO - __main__ - Step 19100: {'lr': 0.00048371249070722525, 'samples': 3667200, 'steps': 19099, 'loss/train': 1.6094400882720947}
+08/30/2021 16:39:35 - INFO - __main__ - Step 19101: {'lr': 0.0004837106065320253, 'samples': 3667392, 'steps': 19100, 'loss/train': 1.5213968753814697}
+08/30/2021 16:39:37 - INFO - __main__ - Step 19102: {'lr': 0.00048370872225151886, 'samples': 3667584, 'steps': 19101, 'loss/train': 1.5737665891647339}
+08/30/2021 16:39:37 - INFO - __main__ - Step 19103: {'lr': 0.0004837068378657069, 'samples': 3667776, 'steps': 19102, 'loss/train': 0.6638611555099487}
+08/30/2021 16:39:38 - INFO - __main__ - Step 19104: {'lr': 0.0004837049533745903, 'samples': 3667968, 'steps': 19103, 'loss/train': 1.7117505073547363}
+08/30/2021 16:39:38 - INFO - __main__ - Step 19105: {'lr': 0.00048370306877816983, 'samples': 3668160, 'steps': 19104, 'loss/train': 2.4603612422943115}
+08/30/2021 16:39:38 - INFO - __main__ - Step 19106: {'lr': 0.00048370118407644637, 'samples': 3668352, 'steps': 19105, 'loss/train': 1.5029852390289307}
+08/30/2021 16:39:40 - INFO - __main__ - Step 19107: {'lr': 0.0004836992992694208, 'samples': 3668544, 'steps': 19106, 'loss/train': 1.1753807067871094}
+08/30/2021 16:39:40 - INFO - __main__ - Step 19108: {'lr': 0.00048369741435709383, 'samples': 3668736, 'steps': 19107, 'loss/train': 1.6933237314224243}
+08/30/2021 16:39:41 - INFO - __main__ - Step 19109: {'lr': 0.0004836955293394665, 'samples': 3668928, 'steps': 19108, 'loss/train': 1.3555686473846436}
+08/30/2021 16:39:41 - INFO - __main__ - Step 19110: {'lr': 0.00048369364421653953, 'samples': 3669120, 'steps': 19109, 'loss/train': 1.6328330039978027}
+08/30/2021 16:39:41 - INFO - __main__ - Step 19111: {'lr': 0.00048369175898831384, 'samples': 3669312, 'steps': 19110, 'loss/train': 1.8126920461654663}
+08/30/2021 16:39:43 - INFO - __main__ - Step 19112: {'lr': 0.0004836898736547902, 'samples': 3669504, 'steps': 19111, 'loss/train': 1.669182538986206}
+08/30/2021 16:39:44 - INFO - __main__ - Step 19113: {'lr': 0.0004836879882159696, 'samples': 3669696, 'steps': 19112, 'loss/train': 1.6478606462478638}
+08/30/2021 16:39:44 - INFO - __main__ - Step 19114: {'lr': 0.0004836861026718527, 'samples': 3669888, 'steps': 19113, 'loss/train': 2.1226742267608643}
+08/30/2021 16:39:44 - INFO - __main__ - Step 19115: {'lr': 0.00048368421702244045, 'samples': 3670080, 'steps': 19114, 'loss/train': 1.5584373474121094}
+08/30/2021 16:39:45 - INFO - __main__ - Step 19116: {'lr': 0.00048368233126773377, 'samples': 3670272, 'steps': 19115, 'loss/train': 1.6307731866836548}
+08/30/2021 16:39:45 - INFO - __main__ - Step 19117: {'lr': 0.0004836804454077334, 'samples': 3670464, 'steps': 19116, 'loss/train': 1.074960470199585}
+08/30/2021 16:39:47 - INFO - __main__ - Step 19118: {'lr': 0.0004836785594424402, 'samples': 3670656, 'steps': 19117, 'loss/train': 1.7020268440246582}
+08/30/2021 16:39:47 - INFO - __main__ - Step 19119: {'lr': 0.0004836766733718551, 'samples': 3670848, 'steps': 19118, 'loss/train': 1.8478784561157227}
+08/30/2021 16:39:48 - INFO - __main__ - Step 19120: {'lr': 0.0004836747871959789, 'samples': 3671040, 'steps': 19119, 'loss/train': 1.623666763305664}
+08/30/2021 16:39:48 - INFO - __main__ - Step 19121: {'lr': 0.0004836729009148124, 'samples': 3671232, 'steps': 19120, 'loss/train': 1.8176316022872925}
+08/30/2021 16:39:48 - INFO - __main__ - Step 19122: {'lr': 0.0004836710145283565, 'samples': 3671424, 'steps': 19121, 'loss/train': 4.032705783843994}
+08/30/2021 16:39:50 - INFO - __main__ - Step 19123: {'lr': 0.0004836691280366121, 'samples': 3671616, 'steps': 19122, 'loss/train': 1.6686691045761108}
+08/30/2021 16:39:51 - INFO - __main__ - Step 19124: {'lr': 0.00048366724143958, 'samples': 3671808, 'steps': 19123, 'loss/train': 1.7045818567276}
+08/30/2021 16:39:51 - INFO - __main__ - Step 19125: {'lr': 0.0004836653547372609, 'samples': 3672000, 'steps': 19124, 'loss/train': 1.033792495727539}
+08/30/2021 16:39:52 - INFO - __main__ - Step 19126: {'lr': 0.00048366346792965597, 'samples': 3672192, 'steps': 19125, 'loss/train': 1.7519725561141968}
+08/30/2021 16:39:52 - INFO - __main__ - Step 19127: {'lr': 0.0004836615810167658, 'samples': 3672384, 'steps': 19126, 'loss/train': 1.4983408451080322}
+08/30/2021 16:39:52 - INFO - __main__ - Step 19128: {'lr': 0.00048365969399859134, 'samples': 3672576, 'steps': 19127, 'loss/train': 1.1733825206756592}
+08/30/2021 16:39:54 - INFO - __main__ - Step 19129: {'lr': 0.00048365780687513346, 'samples': 3672768, 'steps': 19128, 'loss/train': 0.09725673496723175}
+08/30/2021 16:39:54 - INFO - __main__ - Step 19130: {'lr': 0.00048365591964639294, 'samples': 3672960, 'steps': 19129, 'loss/train': 1.7708055973052979}
+08/30/2021 16:39:54 - INFO - __main__ - Step 19131: {'lr': 0.0004836540323123707, 'samples': 3673152, 'steps': 19130, 'loss/train': 1.1902272701263428}
+08/30/2021 16:39:55 - INFO - __main__ - Step 19132: {'lr': 0.00048365214487306753, 'samples': 3673344, 'steps': 19131, 'loss/train': 1.6898306608200073}
+08/30/2021 16:39:55 - INFO - __main__ - Step 19133: {'lr': 0.00048365025732848433, 'samples': 3673536, 'steps': 19132, 'loss/train': 1.5089027881622314}
+08/30/2021 16:39:57 - INFO - __main__ - Step 19134: {'lr': 0.0004836483696786219, 'samples': 3673728, 'steps': 19133, 'loss/train': 1.7575311660766602}
+08/30/2021 16:39:57 - INFO - __main__ - Step 19135: {'lr': 0.00048364648192348117, 'samples': 3673920, 'steps': 19134, 'loss/train': 2.394428253173828}
+08/30/2021 16:39:58 - INFO - __main__ - Step 19136: {'lr': 0.0004836445940630629, 'samples': 3674112, 'steps': 19135, 'loss/train': 1.6285349130630493}
+08/30/2021 16:39:58 - INFO - __main__ - Step 19137: {'lr': 0.0004836427060973679, 'samples': 3674304, 'steps': 19136, 'loss/train': 1.4491521120071411}
+08/30/2021 16:39:58 - INFO - __main__ - Step 19138: {'lr': 0.00048364081802639724, 'samples': 3674496, 'steps': 19137, 'loss/train': 1.5877060890197754}
+08/30/2021 16:40:00 - INFO - __main__ - Step 19139: {'lr': 0.00048363892985015157, 'samples': 3674688, 'steps': 19138, 'loss/train': 1.4455280303955078}
+08/30/2021 16:40:00 - INFO - __main__ - Step 19140: {'lr': 0.00048363704156863187, 'samples': 3674880, 'steps': 19139, 'loss/train': 1.3501614332199097}
+08/30/2021 16:40:01 - INFO - __main__ - Step 19141: {'lr': 0.0004836351531818388, 'samples': 3675072, 'steps': 19140, 'loss/train': 1.4317426681518555}
+08/30/2021 16:40:01 - INFO - __main__ - Step 19142: {'lr': 0.00048363326468977343, 'samples': 3675264, 'steps': 19141, 'loss/train': 1.8610998392105103}
+08/30/2021 16:40:01 - INFO - __main__ - Step 19143: {'lr': 0.00048363137609243654, 'samples': 3675456, 'steps': 19142, 'loss/train': 1.4787158966064453}
+08/30/2021 16:40:03 - INFO - __main__ - Step 19144: {'lr': 0.0004836294873898289, 'samples': 3675648, 'steps': 19143, 'loss/train': 1.950890064239502}
+08/30/2021 16:40:03 - INFO - __main__ - Step 19145: {'lr': 0.00048362759858195146, 'samples': 3675840, 'steps': 19144, 'loss/train': 1.7649948596954346}
+08/30/2021 16:40:04 - INFO - __main__ - Step 19146: {'lr': 0.0004836257096688049, 'samples': 3676032, 'steps': 19145, 'loss/train': 1.7138363122940063}
+08/30/2021 16:40:04 - INFO - __main__ - Step 19147: {'lr': 0.00048362382065039034, 'samples': 3676224, 'steps': 19146, 'loss/train': 1.4875048398971558}
+08/30/2021 16:40:04 - INFO - __main__ - Step 19148: {'lr': 0.00048362193152670847, 'samples': 3676416, 'steps': 19147, 'loss/train': 1.2919530868530273}
+08/30/2021 16:40:06 - INFO - __main__ - Step 19149: {'lr': 0.0004836200422977601, 'samples': 3676608, 'steps': 19148, 'loss/train': 1.6786713600158691}
+08/30/2021 16:40:06 - INFO - __main__ - Step 19150: {'lr': 0.00048361815296354624, 'samples': 3676800, 'steps': 19149, 'loss/train': 1.4627530574798584}
+08/30/2021 16:40:07 - INFO - __main__ - Step 19151: {'lr': 0.00048361626352406756, 'samples': 3676992, 'steps': 19150, 'loss/train': 1.4496657848358154}
+08/30/2021 16:40:07 - INFO - __main__ - Step 19152: {'lr': 0.00048361437397932504, 'samples': 3677184, 'steps': 19151, 'loss/train': 1.9575152397155762}
+08/30/2021 16:40:07 - INFO - __main__ - Step 19153: {'lr': 0.0004836124843293195, 'samples': 3677376, 'steps': 19152, 'loss/train': 1.3367133140563965}
+08/30/2021 16:40:08 - INFO - __main__ - Step 19154: {'lr': 0.00048361059457405176, 'samples': 3677568, 'steps': 19153, 'loss/train': 1.7624095678329468}
+08/30/2021 16:40:09 - INFO - __main__ - Step 19155: {'lr': 0.0004836087047135227, 'samples': 3677760, 'steps': 19154, 'loss/train': 1.8370709419250488}
+08/30/2021 16:40:10 - INFO - __main__ - Step 19156: {'lr': 0.0004836068147477331, 'samples': 3677952, 'steps': 19155, 'loss/train': 1.474143385887146}
+08/30/2021 16:40:10 - INFO - __main__ - Step 19157: {'lr': 0.0004836049246766839, 'samples': 3678144, 'steps': 19156, 'loss/train': 0.8988378643989563}
+08/30/2021 16:40:10 - INFO - __main__ - Step 19158: {'lr': 0.000483603034500376, 'samples': 3678336, 'steps': 19157, 'loss/train': 1.754389762878418}
+08/30/2021 16:40:11 - INFO - __main__ - Step 19159: {'lr': 0.0004836011442188101, 'samples': 3678528, 'steps': 19158, 'loss/train': 0.9265342950820923}
+08/30/2021 16:40:12 - INFO - __main__ - Step 19160: {'lr': 0.00048359925383198714, 'samples': 3678720, 'steps': 19159, 'loss/train': 1.2509101629257202}
+08/30/2021 16:40:13 - INFO - __main__ - Step 19161: {'lr': 0.000483597363339908, 'samples': 3678912, 'steps': 19160, 'loss/train': 1.1521157026290894}
+08/30/2021 16:40:13 - INFO - __main__ - Step 19162: {'lr': 0.0004835954727425734, 'samples': 3679104, 'steps': 19161, 'loss/train': 2.0359926223754883}
+08/30/2021 16:40:13 - INFO - __main__ - Step 19163: {'lr': 0.0004835935820399844, 'samples': 3679296, 'steps': 19162, 'loss/train': 1.5492124557495117}
+08/30/2021 16:40:14 - INFO - __main__ - Step 19164: {'lr': 0.0004835916912321417, 'samples': 3679488, 'steps': 19163, 'loss/train': 1.642147421836853}
+08/30/2021 16:40:15 - INFO - __main__ - Step 19165: {'lr': 0.0004835898003190462, 'samples': 3679680, 'steps': 19164, 'loss/train': 1.559041142463684}
+08/30/2021 16:40:16 - INFO - __main__ - Step 19166: {'lr': 0.00048358790930069876, 'samples': 3679872, 'steps': 19165, 'loss/train': 1.1350476741790771}
+08/30/2021 16:40:16 - INFO - __main__ - Step 19167: {'lr': 0.0004835860181771001, 'samples': 3680064, 'steps': 19166, 'loss/train': 1.5662000179290771}
+08/30/2021 16:40:17 - INFO - __main__ - Step 19168: {'lr': 0.0004835841269482513, 'samples': 3680256, 'steps': 19167, 'loss/train': 0.23353731632232666}
+08/30/2021 16:40:17 - INFO - __main__ - Step 19169: {'lr': 0.00048358223561415306, 'samples': 3680448, 'steps': 19168, 'loss/train': 2.1290228366851807}
+08/30/2021 16:40:18 - INFO - __main__ - Step 19170: {'lr': 0.0004835803441748062, 'samples': 3680640, 'steps': 19169, 'loss/train': 2.134377956390381}
+08/30/2021 16:40:19 - INFO - __main__ - Step 19171: {'lr': 0.0004835784526302117, 'samples': 3680832, 'steps': 19170, 'loss/train': 1.7741402387619019}
+08/30/2021 16:40:19 - INFO - __main__ - Step 19172: {'lr': 0.0004835765609803704, 'samples': 3681024, 'steps': 19171, 'loss/train': 1.4562523365020752}
+08/30/2021 16:40:20 - INFO - __main__ - Step 19173: {'lr': 0.00048357466922528306, 'samples': 3681216, 'steps': 19172, 'loss/train': 1.050406813621521}
+08/30/2021 16:40:20 - INFO - __main__ - Step 19174: {'lr': 0.00048357277736495055, 'samples': 3681408, 'steps': 19173, 'loss/train': 1.797304391860962}
+08/30/2021 16:40:22 - INFO - __main__ - Step 19175: {'lr': 0.0004835708853993738, 'samples': 3681600, 'steps': 19174, 'loss/train': 1.1651562452316284}
+08/30/2021 16:40:22 - INFO - __main__ - Step 19176: {'lr': 0.0004835689933285536, 'samples': 3681792, 'steps': 19175, 'loss/train': 1.6475266218185425}
+08/30/2021 16:40:22 - INFO - __main__ - Step 19177: {'lr': 0.0004835671011524908, 'samples': 3681984, 'steps': 19176, 'loss/train': 1.2482472658157349}
+08/30/2021 16:40:23 - INFO - __main__ - Step 19178: {'lr': 0.0004835652088711863, 'samples': 3682176, 'steps': 19177, 'loss/train': 1.5967295169830322}
+08/30/2021 16:40:23 - INFO - __main__ - Step 19179: {'lr': 0.0004835633164846409, 'samples': 3682368, 'steps': 19178, 'loss/train': 1.1644779443740845}
+08/30/2021 16:40:23 - INFO - __main__ - Step 19180: {'lr': 0.00048356142399285545, 'samples': 3682560, 'steps': 19179, 'loss/train': 0.6553381085395813}
+08/30/2021 16:40:25 - INFO - __main__ - Step 19181: {'lr': 0.00048355953139583087, 'samples': 3682752, 'steps': 19180, 'loss/train': 2.0194222927093506}
+08/30/2021 16:40:26 - INFO - __main__ - Step 19182: {'lr': 0.00048355763869356794, 'samples': 3682944, 'steps': 19181, 'loss/train': 1.7708877325057983}
+08/30/2021 16:40:26 - INFO - __main__ - Step 19183: {'lr': 0.0004835557458860675, 'samples': 3683136, 'steps': 19182, 'loss/train': 2.164074659347534}
+08/30/2021 16:40:27 - INFO - __main__ - Step 19184: {'lr': 0.00048355385297333054, 'samples': 3683328, 'steps': 19183, 'loss/train': 2.01297926902771}
+08/30/2021 16:40:27 - INFO - __main__ - Step 19185: {'lr': 0.0004835519599553578, 'samples': 3683520, 'steps': 19184, 'loss/train': 0.9082038402557373}
+08/30/2021 16:40:28 - INFO - __main__ - Step 19186: {'lr': 0.0004835500668321501, 'samples': 3683712, 'steps': 19185, 'loss/train': 1.8561290502548218}
+08/30/2021 16:40:29 - INFO - __main__ - Step 19187: {'lr': 0.0004835481736037084, 'samples': 3683904, 'steps': 19186, 'loss/train': 1.6833256483078003}
+08/30/2021 16:40:29 - INFO - __main__ - Step 19188: {'lr': 0.0004835462802700334, 'samples': 3684096, 'steps': 19187, 'loss/train': 0.865152895450592}
+08/30/2021 16:40:30 - INFO - __main__ - Step 19189: {'lr': 0.00048354438683112614, 'samples': 3684288, 'steps': 19188, 'loss/train': 1.5439050197601318}
+08/30/2021 16:40:30 - INFO - __main__ - Step 19190: {'lr': 0.00048354249328698743, 'samples': 3684480, 'steps': 19189, 'loss/train': 1.1552523374557495}
+08/30/2021 16:40:32 - INFO - __main__ - Step 19191: {'lr': 0.000483540599637618, 'samples': 3684672, 'steps': 19190, 'loss/train': 1.3549734354019165}
+08/30/2021 16:40:32 - INFO - __main__ - Step 19192: {'lr': 0.00048353870588301875, 'samples': 3684864, 'steps': 19191, 'loss/train': 1.8058332204818726}
+08/30/2021 16:40:32 - INFO - __main__ - Step 19193: {'lr': 0.00048353681202319056, 'samples': 3685056, 'steps': 19192, 'loss/train': 1.5506209135055542}
+08/30/2021 16:40:33 - INFO - __main__ - Step 19194: {'lr': 0.0004835349180581343, 'samples': 3685248, 'steps': 19193, 'loss/train': 1.9190616607666016}
+08/30/2021 16:40:33 - INFO - __main__ - Step 19195: {'lr': 0.0004835330239878509, 'samples': 3685440, 'steps': 19194, 'loss/train': 1.884497880935669}
+08/30/2021 16:40:34 - INFO - __main__ - Step 19196: {'lr': 0.00048353112981234104, 'samples': 3685632, 'steps': 19195, 'loss/train': 2.119391441345215}
+08/30/2021 16:40:35 - INFO - __main__ - Step 19197: {'lr': 0.0004835292355316057, 'samples': 3685824, 'steps': 19196, 'loss/train': 1.1468201875686646}
+08/30/2021 16:40:35 - INFO - __main__ - Step 19198: {'lr': 0.0004835273411456456, 'samples': 3686016, 'steps': 19197, 'loss/train': 1.3540319204330444}
+08/30/2021 16:40:36 - INFO - __main__ - Step 19199: {'lr': 0.00048352544665446174, 'samples': 3686208, 'steps': 19198, 'loss/train': 1.6521283388137817}
+08/30/2021 16:40:36 - INFO - __main__ - Step 19200: {'lr': 0.000483523552058055, 'samples': 3686400, 'steps': 19199, 'loss/train': 1.589746117591858}
+08/30/2021 16:40:37 - INFO - __main__ - Step 19201: {'lr': 0.00048352165735642607, 'samples': 3686592, 'steps': 19200, 'loss/train': 1.7299714088439941}
+08/30/2021 16:40:38 - INFO - __main__ - Step 19202: {'lr': 0.00048351976254957585, 'samples': 3686784, 'steps': 19201, 'loss/train': 1.8458266258239746}
+08/30/2021 16:40:38 - INFO - __main__ - Step 19203: {'lr': 0.0004835178676375053, 'samples': 3686976, 'steps': 19202, 'loss/train': 1.3130806684494019}
+08/30/2021 16:40:39 - INFO - __main__ - Step 19204: {'lr': 0.0004835159726202151, 'samples': 3687168, 'steps': 19203, 'loss/train': 0.9123445153236389}
+08/30/2021 16:40:39 - INFO - __main__ - Step 19205: {'lr': 0.0004835140774977063, 'samples': 3687360, 'steps': 19204, 'loss/train': 2.004091739654541}
+08/30/2021 16:40:41 - INFO - __main__ - Step 19206: {'lr': 0.0004835121822699796, 'samples': 3687552, 'steps': 19205, 'loss/train': 1.6181484460830688}
+08/30/2021 16:40:41 - INFO - __main__ - Step 19207: {'lr': 0.000483510286937036, 'samples': 3687744, 'steps': 19206, 'loss/train': 1.237630844116211}
+08/30/2021 16:40:42 - INFO - __main__ - Step 19208: {'lr': 0.0004835083914988762, 'samples': 3687936, 'steps': 19207, 'loss/train': 1.074430227279663}
+08/30/2021 16:40:42 - INFO - __main__ - Step 19209: {'lr': 0.0004835064959555011, 'samples': 3688128, 'steps': 19208, 'loss/train': 1.427473783493042}
+08/30/2021 16:40:42 - INFO - __main__ - Step 19210: {'lr': 0.00048350460030691165, 'samples': 3688320, 'steps': 19209, 'loss/train': 1.7300118207931519}
+08/30/2021 16:40:43 - INFO - __main__ - Step 19211: {'lr': 0.00048350270455310864, 'samples': 3688512, 'steps': 19210, 'loss/train': 1.803452730178833}
+08/30/2021 16:40:44 - INFO - __main__ - Step 19212: {'lr': 0.00048350080869409285, 'samples': 3688704, 'steps': 19211, 'loss/train': 1.4562078714370728}
+08/30/2021 16:40:45 - INFO - __main__ - Step 19213: {'lr': 0.0004834989127298652, 'samples': 3688896, 'steps': 19212, 'loss/train': 1.6275389194488525}
+08/30/2021 16:40:45 - INFO - __main__ - Step 19214: {'lr': 0.00048349701666042656, 'samples': 3689088, 'steps': 19213, 'loss/train': 2.423234462738037}
+08/30/2021 16:40:45 - INFO - __main__ - Step 19215: {'lr': 0.00048349512048577784, 'samples': 3689280, 'steps': 19214, 'loss/train': 0.1250191479921341}
+08/30/2021 16:40:46 - INFO - __main__ - Step 19216: {'lr': 0.00048349322420591966, 'samples': 3689472, 'steps': 19215, 'loss/train': 1.613912582397461}
+08/30/2021 16:40:47 - INFO - __main__ - Step 19217: {'lr': 0.00048349132782085316, 'samples': 3689664, 'steps': 19216, 'loss/train': 1.6297813653945923}
+08/30/2021 16:40:48 - INFO - __main__ - Step 19218: {'lr': 0.00048348943133057903, 'samples': 3689856, 'steps': 19217, 'loss/train': 1.4121403694152832}
+08/30/2021 16:40:48 - INFO - __main__ - Step 19219: {'lr': 0.0004834875347350982, 'samples': 3690048, 'steps': 19218, 'loss/train': 1.678435206413269}
+08/30/2021 16:40:48 - INFO - __main__ - Step 19220: {'lr': 0.00048348563803441146, 'samples': 3690240, 'steps': 19219, 'loss/train': 1.1719179153442383}
+08/30/2021 16:40:49 - INFO - __main__ - Step 19221: {'lr': 0.0004834837412285197, 'samples': 3690432, 'steps': 19220, 'loss/train': 1.373894453048706}
+08/30/2021 16:40:50 - INFO - __main__ - Step 19222: {'lr': 0.00048348184431742377, 'samples': 3690624, 'steps': 19221, 'loss/train': 1.4711549282073975}
+08/30/2021 16:40:51 - INFO - __main__ - Step 19223: {'lr': 0.00048347994730112457, 'samples': 3690816, 'steps': 19222, 'loss/train': 1.4518851041793823}
+08/30/2021 16:40:51 - INFO - __main__ - Step 19224: {'lr': 0.00048347805017962274, 'samples': 3691008, 'steps': 19223, 'loss/train': 1.7468440532684326}
+08/30/2021 16:40:51 - INFO - __main__ - Step 19225: {'lr': 0.00048347615295291947, 'samples': 3691200, 'steps': 19224, 'loss/train': 1.2006101608276367}
+08/30/2021 16:40:52 - INFO - __main__ - Step 19226: {'lr': 0.0004834742556210154, 'samples': 3691392, 'steps': 19225, 'loss/train': 1.5260684490203857}
+08/30/2021 16:40:53 - INFO - __main__ - Step 19227: {'lr': 0.00048347235818391144, 'samples': 3691584, 'steps': 19226, 'loss/train': 1.6461853981018066}
+08/30/2021 16:40:54 - INFO - __main__ - Step 19228: {'lr': 0.0004834704606416084, 'samples': 3691776, 'steps': 19227, 'loss/train': 1.7791305780410767}
+08/30/2021 16:40:54 - INFO - __main__ - Step 19229: {'lr': 0.00048346856299410725, 'samples': 3691968, 'steps': 19228, 'loss/train': 1.5573664903640747}
+08/30/2021 16:40:54 - INFO - __main__ - Step 19230: {'lr': 0.0004834666652414087, 'samples': 3692160, 'steps': 19229, 'loss/train': 1.4086616039276123}
+08/30/2021 16:40:55 - INFO - __main__ - Step 19231: {'lr': 0.0004834647673835137, 'samples': 3692352, 'steps': 19230, 'loss/train': 1.5888431072235107}
+08/30/2021 16:40:57 - INFO - __main__ - Step 19232: {'lr': 0.00048346286942042307, 'samples': 3692544, 'steps': 19231, 'loss/train': 1.8565961122512817}
+08/30/2021 16:40:57 - INFO - __main__ - Step 19233: {'lr': 0.0004834609713521377, 'samples': 3692736, 'steps': 19232, 'loss/train': 1.3755172491073608}
+08/30/2021 16:40:58 - INFO - __main__ - Step 19234: {'lr': 0.0004834590731786584, 'samples': 3692928, 'steps': 19233, 'loss/train': 2.0674779415130615}
+08/30/2021 16:40:58 - INFO - __main__ - Step 19235: {'lr': 0.000483457174899986, 'samples': 3693120, 'steps': 19234, 'loss/train': 1.592346429824829}
+08/30/2021 16:40:58 - INFO - __main__ - Step 19236: {'lr': 0.00048345527651612145, 'samples': 3693312, 'steps': 19235, 'loss/train': 1.53139066696167}
+08/30/2021 16:41:00 - INFO - __main__ - Step 19237: {'lr': 0.00048345337802706555, 'samples': 3693504, 'steps': 19236, 'loss/train': 1.984649419784546}
+08/30/2021 16:41:00 - INFO - __main__ - Step 19238: {'lr': 0.0004834514794328192, 'samples': 3693696, 'steps': 19237, 'loss/train': 1.4567769765853882}
+08/30/2021 16:41:01 - INFO - __main__ - Step 19239: {'lr': 0.00048344958073338315, 'samples': 3693888, 'steps': 19238, 'loss/train': 1.2409563064575195}
+08/30/2021 16:41:01 - INFO - __main__ - Step 19240: {'lr': 0.00048344768192875833, 'samples': 3694080, 'steps': 19239, 'loss/train': 1.451059341430664}
+08/30/2021 16:41:01 - INFO - __main__ - Step 19241: {'lr': 0.00048344578301894557, 'samples': 3694272, 'steps': 19240, 'loss/train': 1.528473973274231}
+08/30/2021 16:41:03 - INFO - __main__ - Step 19242: {'lr': 0.0004834438840039458, 'samples': 3694464, 'steps': 19241, 'loss/train': 1.8752729892730713}
+08/30/2021 16:41:03 - INFO - __main__ - Step 19243: {'lr': 0.0004834419848837598, 'samples': 3694656, 'steps': 19242, 'loss/train': 1.4833667278289795}
+08/30/2021 16:41:03 - INFO - __main__ - Step 19244: {'lr': 0.00048344008565838844, 'samples': 3694848, 'steps': 19243, 'loss/train': 1.3282593488693237}
+08/30/2021 16:41:04 - INFO - __main__ - Step 19245: {'lr': 0.00048343818632783255, 'samples': 3695040, 'steps': 19244, 'loss/train': 1.71040678024292}
+08/30/2021 16:41:04 - INFO - __main__ - Step 19246: {'lr': 0.00048343628689209305, 'samples': 3695232, 'steps': 19245, 'loss/train': 1.2799099683761597}
+08/30/2021 16:41:06 - INFO - __main__ - Step 19247: {'lr': 0.00048343438735117076, 'samples': 3695424, 'steps': 19246, 'loss/train': 1.4637094736099243}
+08/30/2021 16:41:06 - INFO - __main__ - Step 19248: {'lr': 0.00048343248770506655, 'samples': 3695616, 'steps': 19247, 'loss/train': 1.267026424407959}
+08/30/2021 16:41:06 - INFO - __main__ - Step 19249: {'lr': 0.0004834305879537812, 'samples': 3695808, 'steps': 19248, 'loss/train': 1.6086654663085938}
+08/30/2021 16:41:07 - INFO - __main__ - Step 19250: {'lr': 0.00048342868809731567, 'samples': 3696000, 'steps': 19249, 'loss/train': 1.593589425086975}
+08/30/2021 16:41:07 - INFO - __main__ - Step 19251: {'lr': 0.0004834267881356708, 'samples': 3696192, 'steps': 19250, 'loss/train': 2.4772422313690186}
+08/30/2021 16:41:09 - INFO - __main__ - Step 19252: {'lr': 0.0004834248880688474, 'samples': 3696384, 'steps': 19251, 'loss/train': 1.9250917434692383}
+08/30/2021 16:41:09 - INFO - __main__ - Step 19253: {'lr': 0.00048342298789684637, 'samples': 3696576, 'steps': 19252, 'loss/train': 0.587297797203064}
+08/30/2021 16:41:10 - INFO - __main__ - Step 19254: {'lr': 0.0004834210876196685, 'samples': 3696768, 'steps': 19253, 'loss/train': 0.7421675324440002}
+08/30/2021 16:41:10 - INFO - __main__ - Step 19255: {'lr': 0.0004834191872373147, 'samples': 3696960, 'steps': 19254, 'loss/train': 1.430770993232727}
+08/30/2021 16:41:10 - INFO - __main__ - Step 19256: {'lr': 0.0004834172867497858, 'samples': 3697152, 'steps': 19255, 'loss/train': 1.7474435567855835}
+08/30/2021 16:41:11 - INFO - __main__ - Step 19257: {'lr': 0.0004834153861570827, 'samples': 3697344, 'steps': 19256, 'loss/train': 1.3884469270706177}
+08/30/2021 16:41:12 - INFO - __main__ - Step 19258: {'lr': 0.00048341348545920623, 'samples': 3697536, 'steps': 19257, 'loss/train': 1.7233219146728516}
+08/30/2021 16:41:13 - INFO - __main__ - Step 19259: {'lr': 0.0004834115846561572, 'samples': 3697728, 'steps': 19258, 'loss/train': 1.4816497564315796}
+08/30/2021 16:41:13 - INFO - __main__ - Step 19260: {'lr': 0.0004834096837479366, 'samples': 3697920, 'steps': 19259, 'loss/train': 1.445310115814209}
+08/30/2021 16:41:13 - INFO - __main__ - Step 19261: {'lr': 0.00048340778273454514, 'samples': 3698112, 'steps': 19260, 'loss/train': 1.3448522090911865}
+08/30/2021 16:41:14 - INFO - __main__ - Step 19262: {'lr': 0.00048340588161598373, 'samples': 3698304, 'steps': 19261, 'loss/train': 1.6510472297668457}
+08/30/2021 16:41:15 - INFO - __main__ - Step 19263: {'lr': 0.00048340398039225325, 'samples': 3698496, 'steps': 19262, 'loss/train': 1.1248397827148438}
+08/30/2021 16:41:16 - INFO - __main__ - Step 19264: {'lr': 0.0004834020790633545, 'samples': 3698688, 'steps': 19263, 'loss/train': 1.4149553775787354}
+08/30/2021 16:41:16 - INFO - __main__ - Step 19265: {'lr': 0.00048340017762928843, 'samples': 3698880, 'steps': 19264, 'loss/train': 1.1894426345825195}
+08/30/2021 16:41:16 - INFO - __main__ - Step 19266: {'lr': 0.00048339827609005583, 'samples': 3699072, 'steps': 19265, 'loss/train': 1.9458779096603394}
+08/30/2021 16:41:17 - INFO - __main__ - Step 19267: {'lr': 0.00048339637444565756, 'samples': 3699264, 'steps': 19266, 'loss/train': 1.5638084411621094}
+08/30/2021 16:41:18 - INFO - __main__ - Step 19268: {'lr': 0.0004833944726960945, 'samples': 3699456, 'steps': 19267, 'loss/train': 1.2100439071655273}
+08/30/2021 16:41:19 - INFO - __main__ - Step 19269: {'lr': 0.00048339257084136747, 'samples': 3699648, 'steps': 19268, 'loss/train': 1.7518751621246338}
+08/30/2021 16:41:19 - INFO - __main__ - Step 19270: {'lr': 0.0004833906688814774, 'samples': 3699840, 'steps': 19269, 'loss/train': 1.656874179840088}
+08/30/2021 16:41:19 - INFO - __main__ - Step 19271: {'lr': 0.00048338876681642504, 'samples': 3700032, 'steps': 19270, 'loss/train': 1.2396714687347412}
+08/30/2021 16:41:20 - INFO - __main__ - Step 19272: {'lr': 0.0004833868646462113, 'samples': 3700224, 'steps': 19271, 'loss/train': 1.0070147514343262}
+08/30/2021 16:41:21 - INFO - __main__ - Step 19273: {'lr': 0.00048338496237083705, 'samples': 3700416, 'steps': 19272, 'loss/train': 1.6314671039581299}
+08/30/2021 16:41:22 - INFO - __main__ - Step 19274: {'lr': 0.00048338305999030313, 'samples': 3700608, 'steps': 19273, 'loss/train': 1.4817777872085571}
+08/30/2021 16:41:22 - INFO - __main__ - Step 19275: {'lr': 0.00048338115750461044, 'samples': 3700800, 'steps': 19274, 'loss/train': 1.095033049583435}
+08/30/2021 16:41:22 - INFO - __main__ - Step 19276: {'lr': 0.0004833792549137598, 'samples': 3700992, 'steps': 19275, 'loss/train': 1.7891143560409546}
+08/30/2021 16:41:23 - INFO - __main__ - Step 19277: {'lr': 0.00048337735221775204, 'samples': 3701184, 'steps': 19276, 'loss/train': 1.3591951131820679}
+08/30/2021 16:41:23 - INFO - __main__ - Step 19278: {'lr': 0.000483375449416588, 'samples': 3701376, 'steps': 19277, 'loss/train': 1.4019490480422974}
+08/30/2021 16:41:25 - INFO - __main__ - Step 19279: {'lr': 0.0004833735465102687, 'samples': 3701568, 'steps': 19278, 'loss/train': 2.0010457038879395}
+08/30/2021 16:41:25 - INFO - __main__ - Step 19280: {'lr': 0.0004833716434987948, 'samples': 3701760, 'steps': 19279, 'loss/train': 1.1725772619247437}
+08/30/2021 16:41:25 - INFO - __main__ - Step 19281: {'lr': 0.0004833697403821672, 'samples': 3701952, 'steps': 19280, 'loss/train': 1.2886343002319336}
+08/30/2021 16:41:26 - INFO - __main__ - Step 19282: {'lr': 0.0004833678371603869, 'samples': 3702144, 'steps': 19281, 'loss/train': 1.4475995302200317}
+08/30/2021 16:41:26 - INFO - __main__ - Step 19283: {'lr': 0.0004833659338334546, 'samples': 3702336, 'steps': 19282, 'loss/train': 1.569151520729065}
+08/30/2021 16:41:28 - INFO - __main__ - Step 19284: {'lr': 0.0004833640304013712, 'samples': 3702528, 'steps': 19283, 'loss/train': 1.0333819389343262}
+08/30/2021 16:41:28 - INFO - __main__ - Step 19285: {'lr': 0.0004833621268641376, 'samples': 3702720, 'steps': 19284, 'loss/train': 1.674288272857666}
+08/30/2021 16:41:28 - INFO - __main__ - Step 19286: {'lr': 0.0004833602232217546, 'samples': 3702912, 'steps': 19285, 'loss/train': 1.4194025993347168}
+08/30/2021 16:41:29 - INFO - __main__ - Step 19287: {'lr': 0.0004833583194742231, 'samples': 3703104, 'steps': 19286, 'loss/train': 1.5545814037322998}
+08/30/2021 16:41:29 - INFO - __main__ - Step 19288: {'lr': 0.00048335641562154396, 'samples': 3703296, 'steps': 19287, 'loss/train': 1.0568838119506836}
+08/30/2021 16:41:31 - INFO - __main__ - Step 19289: {'lr': 0.00048335451166371803, 'samples': 3703488, 'steps': 19288, 'loss/train': 2.0425543785095215}
+08/30/2021 16:41:32 - INFO - __main__ - Step 19290: {'lr': 0.0004833526076007461, 'samples': 3703680, 'steps': 19289, 'loss/train': 1.287030816078186}
+08/30/2021 16:41:32 - INFO - __main__ - Step 19291: {'lr': 0.0004833507034326291, 'samples': 3703872, 'steps': 19290, 'loss/train': 1.7177244424819946}
+08/30/2021 16:41:32 - INFO - __main__ - Step 19292: {'lr': 0.0004833487991593679, 'samples': 3704064, 'steps': 19291, 'loss/train': 1.2387974262237549}
+08/30/2021 16:41:33 - INFO - __main__ - Step 19293: {'lr': 0.0004833468947809633, 'samples': 3704256, 'steps': 19292, 'loss/train': 1.8201804161071777}
+08/30/2021 16:41:34 - INFO - __main__ - Step 19294: {'lr': 0.0004833449902974162, 'samples': 3704448, 'steps': 19293, 'loss/train': 1.149401068687439}
+08/30/2021 16:41:35 - INFO - __main__ - Step 19295: {'lr': 0.00048334308570872745, 'samples': 3704640, 'steps': 19294, 'loss/train': 2.3005709648132324}
+08/30/2021 16:41:35 - INFO - __main__ - Step 19296: {'lr': 0.00048334118101489793, 'samples': 3704832, 'steps': 19295, 'loss/train': 1.070224642753601}
+08/30/2021 16:41:35 - INFO - __main__ - Step 19297: {'lr': 0.00048333927621592844, 'samples': 3705024, 'steps': 19296, 'loss/train': 1.6150513887405396}
+08/30/2021 16:41:36 - INFO - __main__ - Step 19298: {'lr': 0.00048333737131181986, 'samples': 3705216, 'steps': 19297, 'loss/train': 1.8145430088043213}
+08/30/2021 16:41:36 - INFO - __main__ - Step 19299: {'lr': 0.00048333546630257315, 'samples': 3705408, 'steps': 19298, 'loss/train': 1.3970966339111328}
+08/30/2021 16:41:38 - INFO - __main__ - Step 19300: {'lr': 0.000483333561188189, 'samples': 3705600, 'steps': 19299, 'loss/train': 0.6124410033226013}
+08/30/2021 16:41:38 - INFO - __main__ - Step 19301: {'lr': 0.00048333165596866837, 'samples': 3705792, 'steps': 19300, 'loss/train': 1.4383171796798706}
+08/30/2021 16:41:38 - INFO - __main__ - Step 19302: {'lr': 0.00048332975064401207, 'samples': 3705984, 'steps': 19301, 'loss/train': 1.7804783582687378}
+08/30/2021 16:41:39 - INFO - __main__ - Step 19303: {'lr': 0.000483327845214221, 'samples': 3706176, 'steps': 19302, 'loss/train': 1.6774909496307373}
+08/30/2021 16:41:39 - INFO - __main__ - Step 19304: {'lr': 0.00048332593967929607, 'samples': 3706368, 'steps': 19303, 'loss/train': 2.2327358722686768}
+08/30/2021 16:41:40 - INFO - __main__ - Step 19305: {'lr': 0.000483324034039238, 'samples': 3706560, 'steps': 19304, 'loss/train': 1.806740403175354}
+08/30/2021 16:41:41 - INFO - __main__ - Step 19306: {'lr': 0.00048332212829404775, 'samples': 3706752, 'steps': 19305, 'loss/train': 1.667768120765686}
+08/30/2021 16:41:41 - INFO - __main__ - Step 19307: {'lr': 0.0004833202224437261, 'samples': 3706944, 'steps': 19306, 'loss/train': 1.2210687398910522}
+08/30/2021 16:41:42 - INFO - __main__ - Step 19308: {'lr': 0.000483318316488274, 'samples': 3707136, 'steps': 19307, 'loss/train': 2.147545337677002}
+08/30/2021 16:41:42 - INFO - __main__ - Step 19309: {'lr': 0.00048331641042769223, 'samples': 3707328, 'steps': 19308, 'loss/train': 1.5021699666976929}
+08/30/2021 16:41:43 - INFO - __main__ - Step 19310: {'lr': 0.00048331450426198177, 'samples': 3707520, 'steps': 19309, 'loss/train': 1.634742259979248}
+08/30/2021 16:41:44 - INFO - __main__ - Step 19311: {'lr': 0.0004833125979911434, 'samples': 3707712, 'steps': 19310, 'loss/train': 1.7047052383422852}
+08/30/2021 16:41:44 - INFO - __main__ - Step 19312: {'lr': 0.0004833106916151778, 'samples': 3707904, 'steps': 19311, 'loss/train': 1.4949703216552734}
+08/30/2021 16:41:45 - INFO - __main__ - Step 19313: {'lr': 0.00048330878513408616, 'samples': 3708096, 'steps': 19312, 'loss/train': 1.2732231616973877}
+08/30/2021 16:41:45 - INFO - __main__ - Step 19314: {'lr': 0.00048330687854786914, 'samples': 3708288, 'steps': 19313, 'loss/train': 1.2981466054916382}
+08/30/2021 16:41:47 - INFO - __main__ - Step 19315: {'lr': 0.00048330497185652765, 'samples': 3708480, 'steps': 19314, 'loss/train': 1.2048128843307495}
+08/30/2021 16:41:47 - INFO - __main__ - Step 19316: {'lr': 0.00048330306506006257, 'samples': 3708672, 'steps': 19315, 'loss/train': 1.9277514219284058}
+08/30/2021 16:41:48 - INFO - __main__ - Step 19317: {'lr': 0.00048330115815847465, 'samples': 3708864, 'steps': 19316, 'loss/train': 1.4384599924087524}
+08/30/2021 16:41:48 - INFO - __main__ - Step 19318: {'lr': 0.0004832992511517649, 'samples': 3709056, 'steps': 19317, 'loss/train': 0.2641623318195343}
+08/30/2021 16:41:48 - INFO - __main__ - Step 19319: {'lr': 0.00048329734403993406, 'samples': 3709248, 'steps': 19318, 'loss/train': 1.6658275127410889}
+08/30/2021 16:41:49 - INFO - __main__ - Step 19320: {'lr': 0.00048329543682298307, 'samples': 3709440, 'steps': 19319, 'loss/train': 1.0207011699676514}
+08/30/2021 16:41:50 - INFO - __main__ - Step 19321: {'lr': 0.0004832935295009127, 'samples': 3709632, 'steps': 19320, 'loss/train': 0.1176118329167366}
+08/30/2021 16:41:51 - INFO - __main__ - Step 19322: {'lr': 0.0004832916220737239, 'samples': 3709824, 'steps': 19321, 'loss/train': 1.34175443649292}
+08/30/2021 16:41:51 - INFO - __main__ - Step 19323: {'lr': 0.0004832897145414175, 'samples': 3710016, 'steps': 19322, 'loss/train': 1.9319572448730469}
+08/30/2021 16:41:52 - INFO - __main__ - Step 19324: {'lr': 0.0004832878069039943, 'samples': 3710208, 'steps': 19323, 'loss/train': 1.999365210533142}
+08/30/2021 16:41:52 - INFO - __main__ - Step 19325: {'lr': 0.0004832858991614553, 'samples': 3710400, 'steps': 19324, 'loss/train': 1.1017085313796997}
+08/30/2021 16:41:53 - INFO - __main__ - Step 19326: {'lr': 0.00048328399131380127, 'samples': 3710592, 'steps': 19325, 'loss/train': 0.11377518624067307}
+08/30/2021 16:41:54 - INFO - __main__ - Step 19327: {'lr': 0.00048328208336103305, 'samples': 3710784, 'steps': 19326, 'loss/train': 1.020818829536438}
+08/30/2021 16:41:54 - INFO - __main__ - Step 19328: {'lr': 0.0004832801753031515, 'samples': 3710976, 'steps': 19327, 'loss/train': 0.6918624639511108}
+08/30/2021 16:41:55 - INFO - __main__ - Step 19329: {'lr': 0.00048327826714015756, 'samples': 3711168, 'steps': 19328, 'loss/train': 1.8891956806182861}
+08/30/2021 16:41:55 - INFO - __main__ - Step 19330: {'lr': 0.00048327635887205196, 'samples': 3711360, 'steps': 19329, 'loss/train': 1.7779945135116577}
+08/30/2021 16:41:56 - INFO - __main__ - Step 19331: {'lr': 0.00048327445049883567, 'samples': 3711552, 'steps': 19330, 'loss/train': 1.7812371253967285}
+08/30/2021 16:41:57 - INFO - __main__ - Step 19332: {'lr': 0.0004832725420205095, 'samples': 3711744, 'steps': 19331, 'loss/train': 2.511662006378174}
+08/30/2021 16:41:57 - INFO - __main__ - Step 19333: {'lr': 0.00048327063343707433, 'samples': 3711936, 'steps': 19332, 'loss/train': 1.664101004600525}
+08/30/2021 16:41:57 - INFO - __main__ - Step 19334: {'lr': 0.000483268724748531, 'samples': 3712128, 'steps': 19333, 'loss/train': 1.742770791053772}
+08/30/2021 16:41:58 - INFO - __main__ - Step 19335: {'lr': 0.0004832668159548804, 'samples': 3712320, 'steps': 19334, 'loss/train': 1.5348186492919922}
+08/30/2021 16:41:59 - INFO - __main__ - Step 19336: {'lr': 0.00048326490705612337, 'samples': 3712512, 'steps': 19335, 'loss/train': 1.2737853527069092}
+08/30/2021 16:42:00 - INFO - __main__ - Step 19337: {'lr': 0.0004832629980522608, 'samples': 3712704, 'steps': 19336, 'loss/train': 1.415540099143982}
+08/30/2021 16:42:00 - INFO - __main__ - Step 19338: {'lr': 0.00048326108894329345, 'samples': 3712896, 'steps': 19337, 'loss/train': 1.4279959201812744}
+08/30/2021 16:42:00 - INFO - __main__ - Step 19339: {'lr': 0.00048325917972922227, 'samples': 3713088, 'steps': 19338, 'loss/train': 1.3825029134750366}
+08/30/2021 16:42:01 - INFO - __main__ - Step 19340: {'lr': 0.00048325727041004815, 'samples': 3713280, 'steps': 19339, 'loss/train': 2.0216457843780518}
+08/30/2021 16:42:01 - INFO - __main__ - Step 19341: {'lr': 0.0004832553609857719, 'samples': 3713472, 'steps': 19340, 'loss/train': 0.8572243452072144}
+08/30/2021 16:42:03 - INFO - __main__ - Step 19342: {'lr': 0.0004832534514563943, 'samples': 3713664, 'steps': 19341, 'loss/train': 1.5212790966033936}
+08/30/2021 16:42:04 - INFO - __main__ - Step 19343: {'lr': 0.0004832515418219164, 'samples': 3713856, 'steps': 19342, 'loss/train': 3.0543317794799805}
+08/30/2021 16:42:04 - INFO - __main__ - Step 19344: {'lr': 0.0004832496320823389, 'samples': 3714048, 'steps': 19343, 'loss/train': 1.8511292934417725}
+08/30/2021 16:42:05 - INFO - __main__ - Step 19345: {'lr': 0.0004832477222376627, 'samples': 3714240, 'steps': 19344, 'loss/train': 1.4760186672210693}
+08/30/2021 16:42:05 - INFO - __main__ - Step 19346: {'lr': 0.0004832458122878888, 'samples': 3714432, 'steps': 19345, 'loss/train': 1.3504347801208496}
+08/30/2021 16:42:05 - INFO - __main__ - Step 19347: {'lr': 0.0004832439022330178, 'samples': 3714624, 'steps': 19346, 'loss/train': 1.0208516120910645}
+08/30/2021 16:42:07 - INFO - __main__ - Step 19348: {'lr': 0.00048324199207305075, 'samples': 3714816, 'steps': 19347, 'loss/train': 1.5862152576446533}
+08/30/2021 16:42:07 - INFO - __main__ - Step 19349: {'lr': 0.0004832400818079884, 'samples': 3715008, 'steps': 19348, 'loss/train': 0.6771523952484131}
+08/30/2021 16:42:07 - INFO - __main__ - Step 19350: {'lr': 0.00048323817143783174, 'samples': 3715200, 'steps': 19349, 'loss/train': 1.9784314632415771}
+08/30/2021 16:42:08 - INFO - __main__ - Step 19351: {'lr': 0.0004832362609625815, 'samples': 3715392, 'steps': 19350, 'loss/train': 1.5952527523040771}
+08/30/2021 16:42:08 - INFO - __main__ - Step 19352: {'lr': 0.0004832343503822386, 'samples': 3715584, 'steps': 19351, 'loss/train': 1.8875341415405273}
+08/30/2021 16:42:10 - INFO - __main__ - Step 19353: {'lr': 0.000483232439696804, 'samples': 3715776, 'steps': 19352, 'loss/train': 1.3885711431503296}
+08/30/2021 16:42:10 - INFO - __main__ - Step 19354: {'lr': 0.0004832305289062784, 'samples': 3715968, 'steps': 19353, 'loss/train': 0.8795766830444336}
+08/30/2021 16:42:10 - INFO - __main__ - Step 19355: {'lr': 0.00048322861801066265, 'samples': 3716160, 'steps': 19354, 'loss/train': 1.794315218925476}
+08/30/2021 16:42:11 - INFO - __main__ - Step 19356: {'lr': 0.00048322670700995775, 'samples': 3716352, 'steps': 19355, 'loss/train': 2.2336206436157227}
+08/30/2021 16:42:11 - INFO - __main__ - Step 19357: {'lr': 0.0004832247959041645, 'samples': 3716544, 'steps': 19356, 'loss/train': 1.6674057245254517}
+08/30/2021 16:42:13 - INFO - __main__ - Step 19358: {'lr': 0.0004832228846932838, 'samples': 3716736, 'steps': 19357, 'loss/train': 1.828009843826294}
+08/30/2021 16:42:13 - INFO - __main__ - Step 19359: {'lr': 0.0004832209733773164, 'samples': 3716928, 'steps': 19358, 'loss/train': 2.1200366020202637}
+08/30/2021 16:42:13 - INFO - __main__ - Step 19360: {'lr': 0.0004832190619562632, 'samples': 3717120, 'steps': 19359, 'loss/train': 2.2332732677459717}
+08/30/2021 16:42:14 - INFO - __main__ - Step 19361: {'lr': 0.00048321715043012515, 'samples': 3717312, 'steps': 19360, 'loss/train': 1.1754701137542725}
+08/30/2021 16:42:14 - INFO - __main__ - Step 19362: {'lr': 0.00048321523879890307, 'samples': 3717504, 'steps': 19361, 'loss/train': 1.480566143989563}
+08/30/2021 16:42:16 - INFO - __main__ - Step 19363: {'lr': 0.00048321332706259773, 'samples': 3717696, 'steps': 19362, 'loss/train': 0.8196985125541687}
+08/30/2021 16:42:16 - INFO - __main__ - Step 19364: {'lr': 0.0004832114152212101, 'samples': 3717888, 'steps': 19363, 'loss/train': 1.7934433221817017}
+08/30/2021 16:42:16 - INFO - __main__ - Step 19365: {'lr': 0.000483209503274741, 'samples': 3718080, 'steps': 19364, 'loss/train': 1.9399924278259277}
+08/30/2021 16:42:17 - INFO - __main__ - Step 19366: {'lr': 0.0004832075912231913, 'samples': 3718272, 'steps': 19365, 'loss/train': 1.6247559785842896}
+08/30/2021 16:42:17 - INFO - __main__ - Step 19367: {'lr': 0.0004832056790665619, 'samples': 3718464, 'steps': 19366, 'loss/train': 1.808705449104309}
+08/30/2021 16:42:19 - INFO - __main__ - Step 19368: {'lr': 0.0004832037668048536, 'samples': 3718656, 'steps': 19367, 'loss/train': 0.978150486946106}
+08/30/2021 16:42:19 - INFO - __main__ - Step 19369: {'lr': 0.00048320185443806717, 'samples': 3718848, 'steps': 19368, 'loss/train': 1.0606640577316284}
+08/30/2021 16:42:19 - INFO - __main__ - Step 19370: {'lr': 0.0004831999419662037, 'samples': 3719040, 'steps': 19369, 'loss/train': 1.6687099933624268}
+08/30/2021 16:42:20 - INFO - __main__ - Step 19371: {'lr': 0.0004831980293892639, 'samples': 3719232, 'steps': 19370, 'loss/train': 1.8510860204696655}
+08/30/2021 16:42:20 - INFO - __main__ - Step 19372: {'lr': 0.0004831961167072487, 'samples': 3719424, 'steps': 19371, 'loss/train': 1.5339409112930298}
+08/30/2021 16:42:22 - INFO - __main__ - Step 19373: {'lr': 0.0004831942039201589, 'samples': 3719616, 'steps': 19372, 'loss/train': 1.3339210748672485}
+08/30/2021 16:42:22 - INFO - __main__ - Step 19374: {'lr': 0.0004831922910279954, 'samples': 3719808, 'steps': 19373, 'loss/train': 1.6575361490249634}
+08/30/2021 16:42:23 - INFO - __main__ - Step 19375: {'lr': 0.000483190378030759, 'samples': 3720000, 'steps': 19374, 'loss/train': 0.06456669420003891}
+08/30/2021 16:42:23 - INFO - __main__ - Step 19376: {'lr': 0.0004831884649284507, 'samples': 3720192, 'steps': 19375, 'loss/train': 0.7960783839225769}
+08/30/2021 16:42:23 - INFO - __main__ - Step 19377: {'lr': 0.00048318655172107126, 'samples': 3720384, 'steps': 19376, 'loss/train': 4.159504413604736}
+08/30/2021 16:42:25 - INFO - __main__ - Step 19378: {'lr': 0.0004831846384086215, 'samples': 3720576, 'steps': 19377, 'loss/train': 1.4446724653244019}
+08/30/2021 16:42:25 - INFO - __main__ - Step 19379: {'lr': 0.0004831827249911024, 'samples': 3720768, 'steps': 19378, 'loss/train': 1.2134758234024048}
+08/30/2021 16:42:26 - INFO - __main__ - Step 19380: {'lr': 0.0004831808114685147, 'samples': 3720960, 'steps': 19379, 'loss/train': 1.2609055042266846}
+08/30/2021 16:42:26 - INFO - __main__ - Step 19381: {'lr': 0.00048317889784085935, 'samples': 3721152, 'steps': 19380, 'loss/train': 0.6011592149734497}
+08/30/2021 16:42:26 - INFO - __main__ - Step 19382: {'lr': 0.0004831769841081372, 'samples': 3721344, 'steps': 19381, 'loss/train': 2.1070375442504883}
+08/30/2021 16:42:27 - INFO - __main__ - Step 19383: {'lr': 0.00048317507027034913, 'samples': 3721536, 'steps': 19382, 'loss/train': 1.7769204378128052}
+08/30/2021 16:42:28 - INFO - __main__ - Step 19384: {'lr': 0.0004831731563274959, 'samples': 3721728, 'steps': 19383, 'loss/train': 1.5864990949630737}
+08/30/2021 16:42:29 - INFO - __main__ - Step 19385: {'lr': 0.0004831712422795785, 'samples': 3721920, 'steps': 19384, 'loss/train': 1.2622509002685547}
+08/30/2021 16:42:29 - INFO - __main__ - Step 19386: {'lr': 0.00048316932812659776, 'samples': 3722112, 'steps': 19385, 'loss/train': 1.7974189519882202}
+08/30/2021 16:42:30 - INFO - __main__ - Step 19387: {'lr': 0.00048316741386855445, 'samples': 3722304, 'steps': 19386, 'loss/train': 0.48866257071495056}
+08/30/2021 16:42:30 - INFO - __main__ - Step 19388: {'lr': 0.0004831654995054495, 'samples': 3722496, 'steps': 19387, 'loss/train': 1.4563623666763306}
+08/30/2021 16:42:32 - INFO - __main__ - Step 19389: {'lr': 0.0004831635850372838, 'samples': 3722688, 'steps': 19388, 'loss/train': 1.7257275581359863}
+08/30/2021 16:42:32 - INFO - __main__ - Step 19390: {'lr': 0.00048316167046405826, 'samples': 3722880, 'steps': 19389, 'loss/train': 0.7319338917732239}
+08/30/2021 16:42:32 - INFO - __main__ - Step 19391: {'lr': 0.0004831597557857735, 'samples': 3723072, 'steps': 19390, 'loss/train': 1.5165249109268188}
+08/30/2021 16:42:33 - INFO - __main__ - Step 19392: {'lr': 0.00048315784100243063, 'samples': 3723264, 'steps': 19391, 'loss/train': 1.9773688316345215}
+08/30/2021 16:42:33 - INFO - __main__ - Step 19393: {'lr': 0.0004831559261140305, 'samples': 3723456, 'steps': 19392, 'loss/train': 1.6093653440475464}
+08/30/2021 16:42:35 - INFO - __main__ - Step 19394: {'lr': 0.0004831540111205739, 'samples': 3723648, 'steps': 19393, 'loss/train': 1.6279922723770142}
+08/30/2021 16:42:35 - INFO - __main__ - Step 19395: {'lr': 0.00048315209602206165, 'samples': 3723840, 'steps': 19394, 'loss/train': 1.7154209613800049}
+08/30/2021 16:42:36 - INFO - __main__ - Step 19396: {'lr': 0.0004831501808184947, 'samples': 3724032, 'steps': 19395, 'loss/train': 1.2043235301971436}
+08/30/2021 16:42:36 - INFO - __main__ - Step 19397: {'lr': 0.0004831482655098738, 'samples': 3724224, 'steps': 19396, 'loss/train': 1.9871405363082886}
+08/30/2021 16:42:36 - INFO - __main__ - Step 19398: {'lr': 0.00048314635009619997, 'samples': 3724416, 'steps': 19397, 'loss/train': 1.6793252229690552}
+08/30/2021 16:42:37 - INFO - __main__ - Step 19399: {'lr': 0.0004831444345774739, 'samples': 3724608, 'steps': 19398, 'loss/train': 0.517352283000946}
+08/30/2021 16:42:39 - INFO - __main__ - Step 19400: {'lr': 0.00048314251895369663, 'samples': 3724800, 'steps': 19399, 'loss/train': 1.0613000392913818}
+08/30/2021 16:42:39 - INFO - __main__ - Step 19401: {'lr': 0.000483140603224869, 'samples': 3724992, 'steps': 19400, 'loss/train': 1.8209928274154663}
+08/30/2021 16:42:40 - INFO - __main__ - Step 19402: {'lr': 0.00048313868739099166, 'samples': 3725184, 'steps': 19401, 'loss/train': 1.1783801317214966}
+08/30/2021 16:42:40 - INFO - __main__ - Step 19403: {'lr': 0.0004831367714520657, 'samples': 3725376, 'steps': 19402, 'loss/train': 1.5873388051986694}
+08/30/2021 16:42:40 - INFO - __main__ - Step 19404: {'lr': 0.0004831348554080919, 'samples': 3725568, 'steps': 19403, 'loss/train': 2.2661373615264893}
+08/30/2021 16:42:42 - INFO - __main__ - Step 19405: {'lr': 0.0004831329392590711, 'samples': 3725760, 'steps': 19404, 'loss/train': 0.8620322346687317}
+08/30/2021 16:42:42 - INFO - __main__ - Step 19406: {'lr': 0.00048313102300500424, 'samples': 3725952, 'steps': 19405, 'loss/train': 1.3002861738204956}
+08/30/2021 16:42:42 - INFO - __main__ - Step 19407: {'lr': 0.00048312910664589215, 'samples': 3726144, 'steps': 19406, 'loss/train': 1.7104800939559937}
+08/30/2021 16:42:43 - INFO - __main__ - Step 19408: {'lr': 0.0004831271901817357, 'samples': 3726336, 'steps': 19407, 'loss/train': 1.7206051349639893}
+08/30/2021 16:42:43 - INFO - __main__ - Step 19409: {'lr': 0.00048312527361253567, 'samples': 3726528, 'steps': 19408, 'loss/train': 0.7446151971817017}
+08/30/2021 16:42:45 - INFO - __main__ - Step 19410: {'lr': 0.000483123356938293, 'samples': 3726720, 'steps': 19409, 'loss/train': 1.662960410118103}
+08/30/2021 16:42:45 - INFO - __main__ - Step 19411: {'lr': 0.00048312144015900856, 'samples': 3726912, 'steps': 19410, 'loss/train': 2.022324323654175}
+08/30/2021 16:42:46 - INFO - __main__ - Step 19412: {'lr': 0.00048311952327468325, 'samples': 3727104, 'steps': 19411, 'loss/train': 1.5919524431228638}
+08/30/2021 16:42:46 - INFO - __main__ - Step 19413: {'lr': 0.00048311760628531777, 'samples': 3727296, 'steps': 19412, 'loss/train': 0.9535502195358276}
+08/30/2021 16:42:46 - INFO - __main__ - Step 19414: {'lr': 0.00048311568919091316, 'samples': 3727488, 'steps': 19413, 'loss/train': 1.7854655981063843}
+08/30/2021 16:42:48 - INFO - __main__ - Step 19415: {'lr': 0.00048311377199147023, 'samples': 3727680, 'steps': 19414, 'loss/train': 1.4093464612960815}
+08/30/2021 16:42:48 - INFO - __main__ - Step 19416: {'lr': 0.00048311185468698974, 'samples': 3727872, 'steps': 19415, 'loss/train': 1.5233309268951416}
+08/30/2021 16:42:49 - INFO - __main__ - Step 19417: {'lr': 0.00048310993727747277, 'samples': 3728064, 'steps': 19416, 'loss/train': 1.3573007583618164}
+08/30/2021 16:42:49 - INFO - __main__ - Step 19418: {'lr': 0.00048310801976292, 'samples': 3728256, 'steps': 19417, 'loss/train': 0.570035994052887}
+08/30/2021 16:42:49 - INFO - __main__ - Step 19419: {'lr': 0.0004831061021433323, 'samples': 3728448, 'steps': 19418, 'loss/train': 0.9198406338691711}
+08/30/2021 16:42:51 - INFO - __main__ - Step 19420: {'lr': 0.00048310418441871065, 'samples': 3728640, 'steps': 19419, 'loss/train': 1.227281928062439}
+08/30/2021 16:42:51 - INFO - __main__ - Step 19421: {'lr': 0.00048310226658905585, 'samples': 3728832, 'steps': 19420, 'loss/train': 1.704697608947754}
+08/30/2021 16:42:52 - INFO - __main__ - Step 19422: {'lr': 0.00048310034865436876, 'samples': 3729024, 'steps': 19421, 'loss/train': 1.689162254333496}
+08/30/2021 16:42:52 - INFO - __main__ - Step 19423: {'lr': 0.0004830984306146503, 'samples': 3729216, 'steps': 19422, 'loss/train': 1.5913020372390747}
+08/30/2021 16:42:52 - INFO - __main__ - Step 19424: {'lr': 0.0004830965124699012, 'samples': 3729408, 'steps': 19423, 'loss/train': 2.141072988510132}
+08/30/2021 16:42:53 - INFO - __main__ - Step 19425: {'lr': 0.00048309459422012243, 'samples': 3729600, 'steps': 19424, 'loss/train': 1.4321925640106201}
+08/30/2021 16:42:54 - INFO - __main__ - Step 19426: {'lr': 0.0004830926758653148, 'samples': 3729792, 'steps': 19425, 'loss/train': 1.5611809492111206}
+08/30/2021 16:42:55 - INFO - __main__ - Step 19427: {'lr': 0.00048309075740547925, 'samples': 3729984, 'steps': 19426, 'loss/train': 0.10041192173957825}
+08/30/2021 16:42:55 - INFO - __main__ - Step 19428: {'lr': 0.0004830888388406166, 'samples': 3730176, 'steps': 19427, 'loss/train': 1.552420973777771}
+08/30/2021 16:42:56 - INFO - __main__ - Step 19429: {'lr': 0.00048308692017072773, 'samples': 3730368, 'steps': 19428, 'loss/train': 2.0706841945648193}
+08/30/2021 16:42:56 - INFO - __main__ - Step 19430: {'lr': 0.00048308500139581344, 'samples': 3730560, 'steps': 19429, 'loss/train': 1.984182596206665}
+08/30/2021 16:42:57 - INFO - __main__ - Step 19431: {'lr': 0.00048308308251587476, 'samples': 3730752, 'steps': 19430, 'loss/train': 1.6536108255386353}
+08/30/2021 16:42:58 - INFO - __main__ - Step 19432: {'lr': 0.00048308116353091234, 'samples': 3730944, 'steps': 19431, 'loss/train': 1.4992344379425049}
+08/30/2021 16:42:58 - INFO - __main__ - Step 19433: {'lr': 0.00048307924444092716, 'samples': 3731136, 'steps': 19432, 'loss/train': 1.4667798280715942}
+08/30/2021 16:42:58 - INFO - __main__ - Step 19434: {'lr': 0.0004830773252459201, 'samples': 3731328, 'steps': 19433, 'loss/train': 1.0226434469223022}
+08/30/2021 16:42:59 - INFO - __main__ - Step 19435: {'lr': 0.00048307540594589194, 'samples': 3731520, 'steps': 19434, 'loss/train': 1.4328798055648804}
+08/30/2021 16:43:00 - INFO - __main__ - Step 19436: {'lr': 0.0004830734865408437, 'samples': 3731712, 'steps': 19435, 'loss/train': 1.447022795677185}
+08/30/2021 16:43:01 - INFO - __main__ - Step 19437: {'lr': 0.000483071567030776, 'samples': 3731904, 'steps': 19436, 'loss/train': 1.696250557899475}
+08/30/2021 16:43:01 - INFO - __main__ - Step 19438: {'lr': 0.00048306964741568994, 'samples': 3732096, 'steps': 19437, 'loss/train': 1.3995155096054077}
+08/30/2021 16:43:01 - INFO - __main__ - Step 19439: {'lr': 0.00048306772769558624, 'samples': 3732288, 'steps': 19438, 'loss/train': 1.395381212234497}
+08/30/2021 16:43:02 - INFO - __main__ - Step 19440: {'lr': 0.0004830658078704659, 'samples': 3732480, 'steps': 19439, 'loss/train': 1.5541294813156128}
+08/30/2021 16:43:04 - INFO - __main__ - Step 19441: {'lr': 0.0004830638879403296, 'samples': 3732672, 'steps': 19440, 'loss/train': 1.2075867652893066}
+08/30/2021 16:43:04 - INFO - __main__ - Step 19442: {'lr': 0.00048306196790517844, 'samples': 3732864, 'steps': 19441, 'loss/train': 1.0280719995498657}
+08/30/2021 16:43:04 - INFO - __main__ - Step 19443: {'lr': 0.0004830600477650131, 'samples': 3733056, 'steps': 19442, 'loss/train': 0.19573047757148743}
+08/30/2021 16:43:05 - INFO - __main__ - Step 19444: {'lr': 0.0004830581275198344, 'samples': 3733248, 'steps': 19443, 'loss/train': 0.19728131592273712}
+08/30/2021 16:43:05 - INFO - __main__ - Step 19445: {'lr': 0.00048305620716964336, 'samples': 3733440, 'steps': 19444, 'loss/train': 1.397684931755066}
+08/30/2021 16:43:05 - INFO - __main__ - Step 19446: {'lr': 0.00048305428671444083, 'samples': 3733632, 'steps': 19445, 'loss/train': 1.491231083869934}
+08/30/2021 16:43:07 - INFO - __main__ - Step 19447: {'lr': 0.00048305236615422763, 'samples': 3733824, 'steps': 19446, 'loss/train': 1.369369387626648}
+08/30/2021 16:43:08 - INFO - __main__ - Step 19448: {'lr': 0.00048305044548900463, 'samples': 3734016, 'steps': 19447, 'loss/train': 1.5268791913986206}
+08/30/2021 16:43:08 - INFO - __main__ - Step 19449: {'lr': 0.0004830485247187727, 'samples': 3734208, 'steps': 19448, 'loss/train': 1.5801888704299927}
+08/30/2021 16:43:08 - INFO - __main__ - Step 19450: {'lr': 0.0004830466038435327, 'samples': 3734400, 'steps': 19449, 'loss/train': 1.4094716310501099}
+08/30/2021 16:43:09 - INFO - __main__ - Step 19451: {'lr': 0.0004830446828632854, 'samples': 3734592, 'steps': 19450, 'loss/train': 0.9922022223472595}
+08/30/2021 16:43:09 - INFO - __main__ - Step 19452: {'lr': 0.00048304276177803186, 'samples': 3734784, 'steps': 19451, 'loss/train': 1.7343542575836182}
+08/30/2021 16:43:11 - INFO - __main__ - Step 19453: {'lr': 0.00048304084058777285, 'samples': 3734976, 'steps': 19452, 'loss/train': 1.4883506298065186}
+08/30/2021 16:43:11 - INFO - __main__ - Step 19454: {'lr': 0.00048303891929250923, 'samples': 3735168, 'steps': 19453, 'loss/train': 2.03281831741333}
+08/30/2021 16:43:12 - INFO - __main__ - Step 19455: {'lr': 0.0004830369978922418, 'samples': 3735360, 'steps': 19454, 'loss/train': 1.4497188329696655}
+08/30/2021 16:43:12 - INFO - __main__ - Step 19456: {'lr': 0.00048303507638697155, 'samples': 3735552, 'steps': 19455, 'loss/train': 1.403900384902954}
+08/30/2021 16:43:12 - INFO - __main__ - Step 19457: {'lr': 0.0004830331547766993, 'samples': 3735744, 'steps': 19456, 'loss/train': 1.4013632535934448}
+08/30/2021 16:43:14 - INFO - __main__ - Step 19458: {'lr': 0.0004830312330614259, 'samples': 3735936, 'steps': 19457, 'loss/train': 1.2117112874984741}
+08/30/2021 16:43:15 - INFO - __main__ - Step 19459: {'lr': 0.00048302931124115226, 'samples': 3736128, 'steps': 19458, 'loss/train': 0.4895917773246765}
+08/30/2021 16:43:15 - INFO - __main__ - Step 19460: {'lr': 0.0004830273893158791, 'samples': 3736320, 'steps': 19459, 'loss/train': 1.79667329788208}
+08/30/2021 16:43:15 - INFO - __main__ - Step 19461: {'lr': 0.0004830254672856075, 'samples': 3736512, 'steps': 19460, 'loss/train': 1.1802961826324463}
+08/30/2021 16:43:16 - INFO - __main__ - Step 19462: {'lr': 0.00048302354515033813, 'samples': 3736704, 'steps': 19461, 'loss/train': 1.596136212348938}
+08/30/2021 16:43:16 - INFO - __main__ - Step 19463: {'lr': 0.00048302162291007203, 'samples': 3736896, 'steps': 19462, 'loss/train': 1.3673269748687744}
+08/30/2021 16:43:17 - INFO - __main__ - Step 19464: {'lr': 0.00048301970056480994, 'samples': 3737088, 'steps': 19463, 'loss/train': 1.8032881021499634}
+08/30/2021 16:43:18 - INFO - __main__ - Step 19465: {'lr': 0.00048301777811455274, 'samples': 3737280, 'steps': 19464, 'loss/train': 1.113150954246521}
+08/30/2021 16:43:18 - INFO - __main__ - Step 19466: {'lr': 0.0004830158555593014, 'samples': 3737472, 'steps': 19465, 'loss/train': 1.349056601524353}
+08/30/2021 16:43:19 - INFO - __main__ - Step 19467: {'lr': 0.00048301393289905663, 'samples': 3737664, 'steps': 19466, 'loss/train': 1.4769805669784546}
+08/30/2021 16:43:19 - INFO - __main__ - Step 19468: {'lr': 0.00048301201013381946, 'samples': 3737856, 'steps': 19467, 'loss/train': 1.7169746160507202}
+08/30/2021 16:43:20 - INFO - __main__ - Step 19469: {'lr': 0.00048301008726359064, 'samples': 3738048, 'steps': 19468, 'loss/train': 1.3549416065216064}
+08/30/2021 16:43:21 - INFO - __main__ - Step 19470: {'lr': 0.00048300816428837104, 'samples': 3738240, 'steps': 19469, 'loss/train': 1.4819215536117554}
+08/30/2021 16:43:21 - INFO - __main__ - Step 19471: {'lr': 0.00048300624120816153, 'samples': 3738432, 'steps': 19470, 'loss/train': 1.624529242515564}
+08/30/2021 16:43:22 - INFO - __main__ - Step 19472: {'lr': 0.0004830043180229631, 'samples': 3738624, 'steps': 19471, 'loss/train': 1.4806876182556152}
+08/30/2021 16:43:22 - INFO - __main__ - Step 19473: {'lr': 0.0004830023947327764, 'samples': 3738816, 'steps': 19472, 'loss/train': 1.8842469453811646}
+08/30/2021 16:43:24 - INFO - __main__ - Step 19474: {'lr': 0.0004830004713376025, 'samples': 3739008, 'steps': 19473, 'loss/train': 0.922451913356781}
+08/30/2021 16:43:24 - INFO - __main__ - Step 19475: {'lr': 0.00048299854783744224, 'samples': 3739200, 'steps': 19474, 'loss/train': 1.7893987894058228}
+08/30/2021 16:43:24 - INFO - __main__ - Step 19476: {'lr': 0.0004829966242322963, 'samples': 3739392, 'steps': 19475, 'loss/train': 1.2062294483184814}
+08/30/2021 16:43:25 - INFO - __main__ - Step 19477: {'lr': 0.00048299470052216576, 'samples': 3739584, 'steps': 19476, 'loss/train': 1.5458911657333374}
+08/30/2021 16:43:25 - INFO - __main__ - Step 19478: {'lr': 0.0004829927767070514, 'samples': 3739776, 'steps': 19477, 'loss/train': 1.5041776895523071}
+08/30/2021 16:43:27 - INFO - __main__ - Step 19479: {'lr': 0.0004829908527869541, 'samples': 3739968, 'steps': 19478, 'loss/train': 2.5316600799560547}
+08/30/2021 16:43:27 - INFO - __main__ - Step 19480: {'lr': 0.0004829889287618746, 'samples': 3740160, 'steps': 19479, 'loss/train': 1.558606743812561}
+08/30/2021 16:43:27 - INFO - __main__ - Step 19481: {'lr': 0.000482987004631814, 'samples': 3740352, 'steps': 19480, 'loss/train': 1.1558796167373657}
+08/30/2021 16:43:28 - INFO - __main__ - Step 19482: {'lr': 0.000482985080396773, 'samples': 3740544, 'steps': 19481, 'loss/train': 1.0911834239959717}
+08/30/2021 16:43:28 - INFO - __main__ - Step 19483: {'lr': 0.00048298315605675257, 'samples': 3740736, 'steps': 19482, 'loss/train': 2.164764404296875}
+08/30/2021 16:43:28 - INFO - __main__ - Step 19484: {'lr': 0.0004829812316117535, 'samples': 3740928, 'steps': 19483, 'loss/train': 1.5163272619247437}
+08/30/2021 16:43:30 - INFO - __main__ - Step 19485: {'lr': 0.0004829793070617767, 'samples': 3741120, 'steps': 19484, 'loss/train': 0.15662556886672974}
+08/30/2021 16:43:31 - INFO - __main__ - Step 19486: {'lr': 0.000482977382406823, 'samples': 3741312, 'steps': 19485, 'loss/train': 2.4153854846954346}
+08/30/2021 16:43:31 - INFO - __main__ - Step 19487: {'lr': 0.00048297545764689327, 'samples': 3741504, 'steps': 19486, 'loss/train': 1.7778544425964355}
+08/30/2021 16:43:31 - INFO - __main__ - Step 19488: {'lr': 0.00048297353278198843, 'samples': 3741696, 'steps': 19487, 'loss/train': 2.195345640182495}
+08/30/2021 16:43:32 - INFO - __main__ - Step 19489: {'lr': 0.00048297160781210925, 'samples': 3741888, 'steps': 19488, 'loss/train': 1.1673959493637085}
+08/30/2021 16:43:33 - INFO - __main__ - Step 19490: {'lr': 0.00048296968273725673, 'samples': 3742080, 'steps': 19489, 'loss/train': 1.3847583532333374}
+08/30/2021 16:43:33 - INFO - __main__ - Step 19491: {'lr': 0.0004829677575574316, 'samples': 3742272, 'steps': 19490, 'loss/train': 1.5721217393875122}
+08/30/2021 16:43:34 - INFO - __main__ - Step 19492: {'lr': 0.0004829658322726348, 'samples': 3742464, 'steps': 19491, 'loss/train': 2.139817476272583}
+08/30/2021 16:43:34 - INFO - __main__ - Step 19493: {'lr': 0.00048296390688286724, 'samples': 3742656, 'steps': 19492, 'loss/train': 1.1478424072265625}
+08/30/2021 16:43:35 - INFO - __main__ - Step 19494: {'lr': 0.00048296198138812974, 'samples': 3742848, 'steps': 19493, 'loss/train': 1.6474329233169556}
+08/30/2021 16:43:36 - INFO - __main__ - Step 19495: {'lr': 0.00048296005578842314, 'samples': 3743040, 'steps': 19494, 'loss/train': 1.5222991704940796}
+08/30/2021 16:43:37 - INFO - __main__ - Step 19496: {'lr': 0.0004829581300837483, 'samples': 3743232, 'steps': 19495, 'loss/train': 1.2511401176452637}
+08/30/2021 16:43:37 - INFO - __main__ - Step 19497: {'lr': 0.00048295620427410614, 'samples': 3743424, 'steps': 19496, 'loss/train': 2.0683276653289795}
+08/30/2021 16:43:38 - INFO - __main__ - Step 19498: {'lr': 0.00048295427835949757, 'samples': 3743616, 'steps': 19497, 'loss/train': 0.14382371306419373}
+08/30/2021 16:43:38 - INFO - __main__ - Step 19499: {'lr': 0.0004829523523399233, 'samples': 3743808, 'steps': 19498, 'loss/train': 1.646743655204773}
+08/30/2021 16:43:39 - INFO - __main__ - Step 19500: {'lr': 0.0004829504262153844, 'samples': 3744000, 'steps': 19499, 'loss/train': 1.6095962524414062}
+08/30/2021 16:43:40 - INFO - __main__ - Step 19501: {'lr': 0.00048294849998588155, 'samples': 3744192, 'steps': 19500, 'loss/train': 1.597055196762085}
+08/30/2021 16:43:40 - INFO - __main__ - Step 19502: {'lr': 0.0004829465736514157, 'samples': 3744384, 'steps': 19501, 'loss/train': 1.6863080263137817}
+08/30/2021 16:43:40 - INFO - __main__ - Step 19503: {'lr': 0.0004829446472119878, 'samples': 3744576, 'steps': 19502, 'loss/train': 1.519710659980774}
+08/30/2021 16:43:41 - INFO - __main__ - Step 19504: {'lr': 0.0004829427206675986, 'samples': 3744768, 'steps': 19503, 'loss/train': 1.3485311269760132}
+08/30/2021 16:43:43 - INFO - __main__ - Step 19505: {'lr': 0.000482940794018249, 'samples': 3744960, 'steps': 19504, 'loss/train': 1.680020809173584}
+08/30/2021 16:43:44 - INFO - __main__ - Step 19506: {'lr': 0.00048293886726393984, 'samples': 3745152, 'steps': 19505, 'loss/train': 1.2845860719680786}
+08/30/2021 16:43:44 - INFO - __main__ - Step 19507: {'lr': 0.00048293694040467205, 'samples': 3745344, 'steps': 19506, 'loss/train': 1.7753819227218628}
+08/30/2021 16:43:44 - INFO - __main__ - Step 19508: {'lr': 0.00048293501344044644, 'samples': 3745536, 'steps': 19507, 'loss/train': 1.3423000574111938}
+08/30/2021 16:43:45 - INFO - __main__ - Step 19509: {'lr': 0.00048293308637126393, 'samples': 3745728, 'steps': 19508, 'loss/train': 0.06995130330324173}
+08/30/2021 16:43:45 - INFO - __main__ - Step 19510: {'lr': 0.0004829311591971254, 'samples': 3745920, 'steps': 19509, 'loss/train': 1.3867766857147217}
+08/30/2021 16:43:46 - INFO - __main__ - Step 19511: {'lr': 0.0004829292319180316, 'samples': 3746112, 'steps': 19510, 'loss/train': 1.5491560697555542}
+08/30/2021 16:43:47 - INFO - __main__ - Step 19512: {'lr': 0.00048292730453398355, 'samples': 3746304, 'steps': 19511, 'loss/train': 2.0232818126678467}
+08/30/2021 16:43:47 - INFO - __main__ - Step 19513: {'lr': 0.00048292537704498203, 'samples': 3746496, 'steps': 19512, 'loss/train': 0.7678455114364624}
+08/30/2021 16:43:48 - INFO - __main__ - Step 19514: {'lr': 0.00048292344945102795, 'samples': 3746688, 'steps': 19513, 'loss/train': 1.5709292888641357}
+08/30/2021 16:43:48 - INFO - __main__ - Step 19515: {'lr': 0.0004829215217521221, 'samples': 3746880, 'steps': 19514, 'loss/train': 1.579296350479126}
+08/30/2021 16:43:49 - INFO - __main__ - Step 19516: {'lr': 0.00048291959394826546, 'samples': 3747072, 'steps': 19515, 'loss/train': 1.4513450860977173}
+08/30/2021 16:43:50 - INFO - __main__ - Step 19517: {'lr': 0.00048291766603945885, 'samples': 3747264, 'steps': 19516, 'loss/train': 1.569222331047058}
+08/30/2021 16:43:50 - INFO - __main__ - Step 19518: {'lr': 0.0004829157380257031, 'samples': 3747456, 'steps': 19517, 'loss/train': 0.45005112886428833}
+08/30/2021 16:43:51 - INFO - __main__ - Step 19519: {'lr': 0.0004829138099069991, 'samples': 3747648, 'steps': 19518, 'loss/train': 2.1218044757843018}
+08/30/2021 16:43:51 - INFO - __main__ - Step 19520: {'lr': 0.0004829118816833478, 'samples': 3747840, 'steps': 19519, 'loss/train': 1.4196314811706543}
+08/30/2021 16:43:51 - INFO - __main__ - Step 19521: {'lr': 0.00048290995335474997, 'samples': 3748032, 'steps': 19520, 'loss/train': 1.3461363315582275}
+08/30/2021 16:43:53 - INFO - __main__ - Step 19522: {'lr': 0.0004829080249212064, 'samples': 3748224, 'steps': 19521, 'loss/train': 1.23183012008667}
+08/30/2021 16:43:53 - INFO - __main__ - Step 19523: {'lr': 0.00048290609638271823, 'samples': 3748416, 'steps': 19522, 'loss/train': 0.9542306661605835}
+08/30/2021 16:43:54 - INFO - __main__ - Step 19524: {'lr': 0.00048290416773928615, 'samples': 3748608, 'steps': 19523, 'loss/train': 1.4460543394088745}
+08/30/2021 16:43:54 - INFO - __main__ - Step 19525: {'lr': 0.00048290223899091094, 'samples': 3748800, 'steps': 19524, 'loss/train': 1.4835989475250244}
+08/30/2021 16:43:54 - INFO - __main__ - Step 19526: {'lr': 0.0004829003101375937, 'samples': 3748992, 'steps': 19525, 'loss/train': 1.1736853122711182}
+08/30/2021 16:43:56 - INFO - __main__ - Step 19527: {'lr': 0.00048289838117933505, 'samples': 3749184, 'steps': 19526, 'loss/train': 1.1716976165771484}
+08/30/2021 16:43:56 - INFO - __main__ - Step 19528: {'lr': 0.0004828964521161361, 'samples': 3749376, 'steps': 19527, 'loss/train': 1.5114786624908447}
+08/30/2021 16:43:57 - INFO - __main__ - Step 19529: {'lr': 0.0004828945229479975, 'samples': 3749568, 'steps': 19528, 'loss/train': 1.2109297513961792}
+08/30/2021 16:43:57 - INFO - __main__ - Step 19530: {'lr': 0.0004828925936749202, 'samples': 3749760, 'steps': 19529, 'loss/train': 1.4926478862762451}
+08/30/2021 16:43:57 - INFO - __main__ - Step 19531: {'lr': 0.0004828906642969052, 'samples': 3749952, 'steps': 19530, 'loss/train': 1.70020592212677}
+08/30/2021 16:43:59 - INFO - __main__ - Step 19532: {'lr': 0.00048288873481395323, 'samples': 3750144, 'steps': 19531, 'loss/train': 2.006854295730591}
+08/30/2021 16:43:59 - INFO - __main__ - Step 19533: {'lr': 0.0004828868052260652, 'samples': 3750336, 'steps': 19532, 'loss/train': 1.75969398021698}
+08/30/2021 16:44:00 - INFO - __main__ - Step 19534: {'lr': 0.0004828848755332419, 'samples': 3750528, 'steps': 19533, 'loss/train': 1.984788179397583}
+08/30/2021 16:44:00 - INFO - __main__ - Step 19535: {'lr': 0.0004828829457354843, 'samples': 3750720, 'steps': 19534, 'loss/train': 1.0613036155700684}
+08/30/2021 16:44:01 - INFO - __main__ - Step 19536: {'lr': 0.0004828810158327933, 'samples': 3750912, 'steps': 19535, 'loss/train': 1.3652853965759277}
+08/30/2021 16:44:01 - INFO - __main__ - Step 19537: {'lr': 0.00048287908582516964, 'samples': 3751104, 'steps': 19536, 'loss/train': 1.3489757776260376}
+08/30/2021 16:44:02 - INFO - __main__ - Step 19538: {'lr': 0.00048287715571261424, 'samples': 3751296, 'steps': 19537, 'loss/train': 1.5740211009979248}
+08/30/2021 16:44:03 - INFO - __main__ - Step 19539: {'lr': 0.00048287522549512806, 'samples': 3751488, 'steps': 19538, 'loss/train': 1.7897087335586548}
+08/30/2021 16:44:03 - INFO - __main__ - Step 19540: {'lr': 0.0004828732951727119, 'samples': 3751680, 'steps': 19539, 'loss/train': 1.388185977935791}
+08/30/2021 16:44:04 - INFO - __main__ - Step 19541: {'lr': 0.00048287136474536657, 'samples': 3751872, 'steps': 19540, 'loss/train': 1.5125842094421387}
+08/30/2021 16:44:04 - INFO - __main__ - Step 19542: {'lr': 0.000482869434213093, 'samples': 3752064, 'steps': 19541, 'loss/train': 1.222025990486145}
+08/30/2021 16:44:05 - INFO - __main__ - Step 19543: {'lr': 0.0004828675035758921, 'samples': 3752256, 'steps': 19542, 'loss/train': 0.8148073554039001}
+08/30/2021 16:44:06 - INFO - __main__ - Step 19544: {'lr': 0.00048286557283376465, 'samples': 3752448, 'steps': 19543, 'loss/train': 1.2790478467941284}
+08/30/2021 16:44:06 - INFO - __main__ - Step 19545: {'lr': 0.0004828636419867116, 'samples': 3752640, 'steps': 19544, 'loss/train': 0.9558858871459961}
+08/30/2021 16:44:07 - INFO - __main__ - Step 19546: {'lr': 0.00048286171103473376, 'samples': 3752832, 'steps': 19545, 'loss/train': 1.670215368270874}
+08/30/2021 16:44:07 - INFO - __main__ - Step 19547: {'lr': 0.00048285977997783203, 'samples': 3753024, 'steps': 19546, 'loss/train': 2.879312515258789}
+08/30/2021 16:44:09 - INFO - __main__ - Step 19548: {'lr': 0.0004828578488160073, 'samples': 3753216, 'steps': 19547, 'loss/train': 1.5151432752609253}
+08/30/2021 16:44:09 - INFO - __main__ - Step 19549: {'lr': 0.0004828559175492604, 'samples': 3753408, 'steps': 19548, 'loss/train': 1.454259991645813}
+08/30/2021 16:44:09 - INFO - __main__ - Step 19550: {'lr': 0.0004828539861775922, 'samples': 3753600, 'steps': 19549, 'loss/train': 1.4162417650222778}
+08/30/2021 16:44:10 - INFO - __main__ - Step 19551: {'lr': 0.0004828520547010036, 'samples': 3753792, 'steps': 19550, 'loss/train': 2.0042665004730225}
+08/30/2021 16:44:10 - INFO - __main__ - Step 19552: {'lr': 0.0004828501231194955, 'samples': 3753984, 'steps': 19551, 'loss/train': 1.8019202947616577}
+08/30/2021 16:44:10 - INFO - __main__ - Step 19553: {'lr': 0.0004828481914330687, 'samples': 3754176, 'steps': 19552, 'loss/train': 1.7917029857635498}
+08/30/2021 16:44:13 - INFO - __main__ - Step 19554: {'lr': 0.000482846259641724, 'samples': 3754368, 'steps': 19553, 'loss/train': 0.7208302617073059}
+08/30/2021 16:44:13 - INFO - __main__ - Step 19555: {'lr': 0.0004828443277454625, 'samples': 3754560, 'steps': 19554, 'loss/train': 1.9223098754882812}
+08/30/2021 16:44:13 - INFO - __main__ - Step 19556: {'lr': 0.0004828423957442849, 'samples': 3754752, 'steps': 19555, 'loss/train': 1.1059141159057617}
+08/30/2021 16:44:14 - INFO - __main__ - Step 19557: {'lr': 0.00048284046363819213, 'samples': 3754944, 'steps': 19556, 'loss/train': 1.0503833293914795}
+08/30/2021 16:44:14 - INFO - __main__ - Step 19558: {'lr': 0.000482838531427185, 'samples': 3755136, 'steps': 19557, 'loss/train': 0.42678242921829224}
+08/30/2021 16:44:14 - INFO - __main__ - Step 19559: {'lr': 0.00048283659911126445, 'samples': 3755328, 'steps': 19558, 'loss/train': 1.0968704223632812}
+08/30/2021 16:44:17 - INFO - __main__ - Step 19560: {'lr': 0.0004828346666904313, 'samples': 3755520, 'steps': 19559, 'loss/train': 1.1777867078781128}
+08/30/2021 16:44:18 - INFO - __main__ - Step 19561: {'lr': 0.00048283273416468644, 'samples': 3755712, 'steps': 19560, 'loss/train': 1.7494573593139648}
+08/30/2021 16:44:18 - INFO - __main__ - Step 19562: {'lr': 0.0004828308015340307, 'samples': 3755904, 'steps': 19561, 'loss/train': 1.6501796245574951}
+08/30/2021 16:44:18 - INFO - __main__ - Step 19563: {'lr': 0.0004828288687984651, 'samples': 3756096, 'steps': 19562, 'loss/train': 1.9800878763198853}
+08/30/2021 16:44:19 - INFO - __main__ - Step 19564: {'lr': 0.0004828269359579903, 'samples': 3756288, 'steps': 19563, 'loss/train': 1.352666974067688}
+08/30/2021 16:44:19 - INFO - __main__ - Step 19565: {'lr': 0.00048282500301260735, 'samples': 3756480, 'steps': 19564, 'loss/train': 1.8031508922576904}
+08/30/2021 16:44:21 - INFO - __main__ - Step 19566: {'lr': 0.000482823069962317, 'samples': 3756672, 'steps': 19565, 'loss/train': 1.3478760719299316}
+08/30/2021 16:44:21 - INFO - __main__ - Step 19567: {'lr': 0.0004828211368071202, 'samples': 3756864, 'steps': 19566, 'loss/train': 1.795411229133606}
+08/30/2021 16:44:21 - INFO - __main__ - Step 19568: {'lr': 0.0004828192035470178, 'samples': 3757056, 'steps': 19567, 'loss/train': 1.5540285110473633}
+08/30/2021 16:44:22 - INFO - __main__ - Step 19569: {'lr': 0.00048281727018201063, 'samples': 3757248, 'steps': 19568, 'loss/train': 0.5638701915740967}
+08/30/2021 16:44:22 - INFO - __main__ - Step 19570: {'lr': 0.00048281533671209955, 'samples': 3757440, 'steps': 19569, 'loss/train': 1.6570943593978882}
+08/30/2021 16:44:24 - INFO - __main__ - Step 19571: {'lr': 0.0004828134031372855, 'samples': 3757632, 'steps': 19570, 'loss/train': 1.484034538269043}
+08/30/2021 16:44:24 - INFO - __main__ - Step 19572: {'lr': 0.00048281146945756937, 'samples': 3757824, 'steps': 19571, 'loss/train': 2.0269041061401367}
+08/30/2021 16:44:25 - INFO - __main__ - Step 19573: {'lr': 0.00048280953567295196, 'samples': 3758016, 'steps': 19572, 'loss/train': 1.5945733785629272}
+08/30/2021 16:44:25 - INFO - __main__ - Step 19574: {'lr': 0.0004828076017834342, 'samples': 3758208, 'steps': 19573, 'loss/train': 1.7511272430419922}
+08/30/2021 16:44:25 - INFO - __main__ - Step 19575: {'lr': 0.00048280566778901684, 'samples': 3758400, 'steps': 19574, 'loss/train': 1.7083972692489624}
+08/30/2021 16:44:26 - INFO - __main__ - Step 19576: {'lr': 0.00048280373368970086, 'samples': 3758592, 'steps': 19575, 'loss/train': 0.8600512742996216}
+08/30/2021 16:44:27 - INFO - __main__ - Step 19577: {'lr': 0.0004828017994854872, 'samples': 3758784, 'steps': 19576, 'loss/train': 5.872617244720459}
+08/30/2021 16:44:28 - INFO - __main__ - Step 19578: {'lr': 0.0004827998651763765, 'samples': 3758976, 'steps': 19577, 'loss/train': 1.3304845094680786}
+08/30/2021 16:44:28 - INFO - __main__ - Step 19579: {'lr': 0.0004827979307623699, 'samples': 3759168, 'steps': 19578, 'loss/train': 1.8319852352142334}
+08/30/2021 16:44:29 - INFO - __main__ - Step 19580: {'lr': 0.0004827959962434681, 'samples': 3759360, 'steps': 19579, 'loss/train': 1.463954210281372}
+08/30/2021 16:44:29 - INFO - __main__ - Step 19581: {'lr': 0.00048279406161967197, 'samples': 3759552, 'steps': 19580, 'loss/train': 1.9977972507476807}
+08/30/2021 16:44:29 - INFO - __main__ - Step 19582: {'lr': 0.0004827921268909825, 'samples': 3759744, 'steps': 19581, 'loss/train': 1.2031890153884888}
+08/30/2021 16:44:31 - INFO - __main__ - Step 19583: {'lr': 0.0004827901920574005, 'samples': 3759936, 'steps': 19582, 'loss/train': 4.179448127746582}
+08/30/2021 16:44:31 - INFO - __main__ - Step 19584: {'lr': 0.0004827882571189268, 'samples': 3760128, 'steps': 19583, 'loss/train': 1.2608264684677124}
+08/30/2021 16:44:32 - INFO - __main__ - Step 19585: {'lr': 0.00048278632207556226, 'samples': 3760320, 'steps': 19584, 'loss/train': 1.7685452699661255}
+08/30/2021 16:44:32 - INFO - __main__ - Step 19586: {'lr': 0.00048278438692730784, 'samples': 3760512, 'steps': 19585, 'loss/train': 1.4851990938186646}
+08/30/2021 16:44:32 - INFO - __main__ - Step 19587: {'lr': 0.00048278245167416434, 'samples': 3760704, 'steps': 19586, 'loss/train': 1.9291446208953857}
+08/30/2021 16:44:34 - INFO - __main__ - Step 19588: {'lr': 0.0004827805163161327, 'samples': 3760896, 'steps': 19587, 'loss/train': 1.251665472984314}
+08/30/2021 16:44:34 - INFO - __main__ - Step 19589: {'lr': 0.0004827785808532137, 'samples': 3761088, 'steps': 19588, 'loss/train': 1.1816458702087402}
+08/30/2021 16:44:35 - INFO - __main__ - Step 19590: {'lr': 0.0004827766452854083, 'samples': 3761280, 'steps': 19589, 'loss/train': 1.5434032678604126}
+08/30/2021 16:44:35 - INFO - __main__ - Step 19591: {'lr': 0.0004827747096127173, 'samples': 3761472, 'steps': 19590, 'loss/train': 1.9463564157485962}
+08/30/2021 16:44:35 - INFO - __main__ - Step 19592: {'lr': 0.00048277277383514165, 'samples': 3761664, 'steps': 19591, 'loss/train': 1.7181123495101929}
+08/30/2021 16:44:37 - INFO - __main__ - Step 19593: {'lr': 0.00048277083795268216, 'samples': 3761856, 'steps': 19592, 'loss/train': 1.314265251159668}
+08/30/2021 16:44:37 - INFO - __main__ - Step 19594: {'lr': 0.0004827689019653397, 'samples': 3762048, 'steps': 19593, 'loss/train': 2.241570234298706}
+08/30/2021 16:44:38 - INFO - __main__ - Step 19595: {'lr': 0.00048276696587311525, 'samples': 3762240, 'steps': 19594, 'loss/train': 2.594907283782959}
+08/30/2021 16:44:38 - INFO - __main__ - Step 19596: {'lr': 0.00048276502967600955, 'samples': 3762432, 'steps': 19595, 'loss/train': 1.2087441682815552}
+08/30/2021 16:44:38 - INFO - __main__ - Step 19597: {'lr': 0.00048276309337402345, 'samples': 3762624, 'steps': 19596, 'loss/train': 1.221699833869934}
+08/30/2021 16:44:40 - INFO - __main__ - Step 19598: {'lr': 0.000482761156967158, 'samples': 3762816, 'steps': 19597, 'loss/train': 0.21570028364658356}
+08/30/2021 16:44:40 - INFO - __main__ - Step 19599: {'lr': 0.0004827592204554139, 'samples': 3763008, 'steps': 19598, 'loss/train': 1.727426290512085}
+08/30/2021 16:44:41 - INFO - __main__ - Step 19600: {'lr': 0.00048275728383879215, 'samples': 3763200, 'steps': 19599, 'loss/train': 2.093048572540283}
+08/30/2021 16:44:41 - INFO - __main__ - Step 19601: {'lr': 0.0004827553471172935, 'samples': 3763392, 'steps': 19600, 'loss/train': 1.3071701526641846}
+08/30/2021 16:44:41 - INFO - __main__ - Step 19602: {'lr': 0.00048275341029091885, 'samples': 3763584, 'steps': 19601, 'loss/train': 1.304287075996399}
+08/30/2021 16:44:42 - INFO - __main__ - Step 19603: {'lr': 0.0004827514733596692, 'samples': 3763776, 'steps': 19602, 'loss/train': 1.56734037399292}
+08/30/2021 16:44:43 - INFO - __main__ - Step 19604: {'lr': 0.00048274953632354524, 'samples': 3763968, 'steps': 19603, 'loss/train': 1.830305814743042}
+08/30/2021 16:44:44 - INFO - __main__ - Step 19605: {'lr': 0.000482747599182548, 'samples': 3764160, 'steps': 19604, 'loss/train': 1.419538140296936}
+08/30/2021 16:44:44 - INFO - __main__ - Step 19606: {'lr': 0.00048274566193667824, 'samples': 3764352, 'steps': 19605, 'loss/train': 1.2372103929519653}
+08/30/2021 16:44:45 - INFO - __main__ - Step 19607: {'lr': 0.0004827437245859369, 'samples': 3764544, 'steps': 19606, 'loss/train': 1.2850303649902344}
+08/30/2021 16:44:45 - INFO - __main__ - Step 19608: {'lr': 0.0004827417871303248, 'samples': 3764736, 'steps': 19607, 'loss/train': 0.9325003027915955}
+08/30/2021 16:44:47 - INFO - __main__ - Step 19609: {'lr': 0.00048273984956984285, 'samples': 3764928, 'steps': 19608, 'loss/train': 1.6945222616195679}
+08/30/2021 16:44:47 - INFO - __main__ - Step 19610: {'lr': 0.0004827379119044919, 'samples': 3765120, 'steps': 19609, 'loss/train': 2.009012460708618}
+08/30/2021 16:44:47 - INFO - __main__ - Step 19611: {'lr': 0.00048273597413427284, 'samples': 3765312, 'steps': 19610, 'loss/train': 0.20731039345264435}
+08/30/2021 16:44:48 - INFO - __main__ - Step 19612: {'lr': 0.00048273403625918653, 'samples': 3765504, 'steps': 19611, 'loss/train': 1.801841139793396}
+08/30/2021 16:44:48 - INFO - __main__ - Step 19613: {'lr': 0.0004827320982792339, 'samples': 3765696, 'steps': 19612, 'loss/train': 1.930281639099121}
+08/30/2021 16:44:50 - INFO - __main__ - Step 19614: {'lr': 0.00048273016019441585, 'samples': 3765888, 'steps': 19613, 'loss/train': 2.790879487991333}
+08/30/2021 16:44:50 - INFO - __main__ - Step 19615: {'lr': 0.00048272822200473304, 'samples': 3766080, 'steps': 19614, 'loss/train': 0.7464519739151001}
+08/30/2021 16:44:51 - INFO - __main__ - Step 19616: {'lr': 0.0004827262837101866, 'samples': 3766272, 'steps': 19615, 'loss/train': 1.577192783355713}
+08/30/2021 16:44:51 - INFO - __main__ - Step 19617: {'lr': 0.0004827243453107772, 'samples': 3766464, 'steps': 19616, 'loss/train': 1.2627135515213013}
+08/30/2021 16:44:51 - INFO - __main__ - Step 19618: {'lr': 0.0004827224068065058, 'samples': 3766656, 'steps': 19617, 'loss/train': 2.4496021270751953}
+08/30/2021 16:44:53 - INFO - __main__ - Step 19619: {'lr': 0.0004827204681973733, 'samples': 3766848, 'steps': 19618, 'loss/train': 1.3852035999298096}
+08/30/2021 16:44:54 - INFO - __main__ - Step 19620: {'lr': 0.00048271852948338057, 'samples': 3767040, 'steps': 19619, 'loss/train': 2.0666980743408203}
+08/30/2021 16:44:54 - INFO - __main__ - Step 19621: {'lr': 0.00048271659066452847, 'samples': 3767232, 'steps': 19620, 'loss/train': 6.3381547927856445}
+08/30/2021 16:44:55 - INFO - __main__ - Step 19622: {'lr': 0.0004827146517408178, 'samples': 3767424, 'steps': 19621, 'loss/train': 1.6556847095489502}
+08/30/2021 16:44:55 - INFO - __main__ - Step 19623: {'lr': 0.0004827127127122495, 'samples': 3767616, 'steps': 19622, 'loss/train': 1.4426981210708618}
+08/30/2021 16:44:55 - INFO - __main__ - Step 19624: {'lr': 0.00048271077357882455, 'samples': 3767808, 'steps': 19623, 'loss/train': 0.5524057745933533}
+08/30/2021 16:44:57 - INFO - __main__ - Step 19625: {'lr': 0.00048270883434054364, 'samples': 3768000, 'steps': 19624, 'loss/train': 1.514841914176941}
+08/30/2021 16:44:57 - INFO - __main__ - Step 19626: {'lr': 0.00048270689499740774, 'samples': 3768192, 'steps': 19625, 'loss/train': 1.9654330015182495}
+08/30/2021 16:44:58 - INFO - __main__ - Step 19627: {'lr': 0.0004827049555494176, 'samples': 3768384, 'steps': 19626, 'loss/train': 1.2500262260437012}
+08/30/2021 16:44:58 - INFO - __main__ - Step 19628: {'lr': 0.00048270301599657436, 'samples': 3768576, 'steps': 19627, 'loss/train': 1.5800343751907349}
+08/30/2021 16:44:58 - INFO - __main__ - Step 19629: {'lr': 0.0004827010763388786, 'samples': 3768768, 'steps': 19628, 'loss/train': 1.7905545234680176}
+08/30/2021 16:44:59 - INFO - __main__ - Step 19630: {'lr': 0.00048269913657633147, 'samples': 3768960, 'steps': 19629, 'loss/train': 1.5206153392791748}
+08/30/2021 16:45:00 - INFO - __main__ - Step 19631: {'lr': 0.00048269719670893357, 'samples': 3769152, 'steps': 19630, 'loss/train': 1.2802495956420898}
+08/30/2021 16:45:01 - INFO - __main__ - Step 19632: {'lr': 0.00048269525673668595, 'samples': 3769344, 'steps': 19631, 'loss/train': 1.1612682342529297}
+08/30/2021 16:45:01 - INFO - __main__ - Step 19633: {'lr': 0.00048269331665958947, 'samples': 3769536, 'steps': 19632, 'loss/train': 1.210286021232605}
+08/30/2021 16:45:02 - INFO - __main__ - Step 19634: {'lr': 0.00048269137647764495, 'samples': 3769728, 'steps': 19633, 'loss/train': 1.4296683073043823}
+08/30/2021 16:45:02 - INFO - __main__ - Step 19635: {'lr': 0.00048268943619085325, 'samples': 3769920, 'steps': 19634, 'loss/train': 2.321168899536133}
+08/30/2021 16:45:04 - INFO - __main__ - Step 19636: {'lr': 0.00048268749579921536, 'samples': 3770112, 'steps': 19635, 'loss/train': 1.4415132999420166}
+08/30/2021 16:45:04 - INFO - __main__ - Step 19637: {'lr': 0.00048268555530273197, 'samples': 3770304, 'steps': 19636, 'loss/train': 0.2824762761592865}
+08/30/2021 16:45:04 - INFO - __main__ - Step 19638: {'lr': 0.0004826836147014041, 'samples': 3770496, 'steps': 19637, 'loss/train': 1.977523922920227}
+08/30/2021 16:45:05 - INFO - __main__ - Step 19639: {'lr': 0.0004826816739952326, 'samples': 3770688, 'steps': 19638, 'loss/train': 1.6820950508117676}
+08/30/2021 16:45:05 - INFO - __main__ - Step 19640: {'lr': 0.0004826797331842183, 'samples': 3770880, 'steps': 19639, 'loss/train': 2.1210596561431885}
+08/30/2021 16:45:07 - INFO - __main__ - Step 19641: {'lr': 0.0004826777922683622, 'samples': 3771072, 'steps': 19640, 'loss/train': 1.9992430210113525}
+08/30/2021 16:45:07 - INFO - __main__ - Step 19642: {'lr': 0.0004826758512476649, 'samples': 3771264, 'steps': 19641, 'loss/train': 2.0058212280273438}
+08/30/2021 16:45:08 - INFO - __main__ - Step 19643: {'lr': 0.0004826739101221276, 'samples': 3771456, 'steps': 19642, 'loss/train': 1.8318320512771606}
+08/30/2021 16:45:08 - INFO - __main__ - Step 19644: {'lr': 0.000482671968891751, 'samples': 3771648, 'steps': 19643, 'loss/train': 1.7951756715774536}
+08/30/2021 16:45:08 - INFO - __main__ - Step 19645: {'lr': 0.000482670027556536, 'samples': 3771840, 'steps': 19644, 'loss/train': 1.7677150964736938}
+08/30/2021 16:45:09 - INFO - __main__ - Step 19646: {'lr': 0.0004826680861164834, 'samples': 3772032, 'steps': 19645, 'loss/train': 1.8392150402069092}
+08/30/2021 16:45:10 - INFO - __main__ - Step 19647: {'lr': 0.00048266614457159426, 'samples': 3772224, 'steps': 19646, 'loss/train': 1.3000612258911133}
+08/30/2021 16:45:11 - INFO - __main__ - Step 19648: {'lr': 0.0004826642029218693, 'samples': 3772416, 'steps': 19647, 'loss/train': 1.3055709600448608}
+08/30/2021 16:45:11 - INFO - __main__ - Step 19649: {'lr': 0.00048266226116730937, 'samples': 3772608, 'steps': 19648, 'loss/train': 1.7779978513717651}
+08/30/2021 16:45:11 - INFO - __main__ - Step 19650: {'lr': 0.00048266031930791555, 'samples': 3772800, 'steps': 19649, 'loss/train': 1.8078025579452515}
+08/30/2021 16:45:12 - INFO - __main__ - Step 19651: {'lr': 0.0004826583773436884, 'samples': 3772992, 'steps': 19650, 'loss/train': 1.2400726079940796}
+08/30/2021 16:45:13 - INFO - __main__ - Step 19652: {'lr': 0.00048265643527462915, 'samples': 3773184, 'steps': 19651, 'loss/train': 1.1456602811813354}
+08/30/2021 16:45:14 - INFO - __main__ - Step 19653: {'lr': 0.00048265449310073847, 'samples': 3773376, 'steps': 19652, 'loss/train': 1.620891809463501}
+08/30/2021 16:45:14 - INFO - __main__ - Step 19654: {'lr': 0.0004826525508220172, 'samples': 3773568, 'steps': 19653, 'loss/train': 1.7850602865219116}
+08/30/2021 16:45:15 - INFO - __main__ - Step 19655: {'lr': 0.0004826506084384663, 'samples': 3773760, 'steps': 19654, 'loss/train': 0.13912451267242432}
+08/30/2021 16:45:15 - INFO - __main__ - Step 19656: {'lr': 0.00048264866595008665, 'samples': 3773952, 'steps': 19655, 'loss/train': 1.826074481010437}
+08/30/2021 16:45:17 - INFO - __main__ - Step 19657: {'lr': 0.0004826467233568791, 'samples': 3774144, 'steps': 19656, 'loss/train': 1.2786715030670166}
+08/30/2021 16:45:17 - INFO - __main__ - Step 19658: {'lr': 0.00048264478065884454, 'samples': 3774336, 'steps': 19657, 'loss/train': 1.6209207773208618}
+08/30/2021 16:45:18 - INFO - __main__ - Step 19659: {'lr': 0.0004826428378559838, 'samples': 3774528, 'steps': 19658, 'loss/train': 1.7213256359100342}
+08/30/2021 16:45:18 - INFO - __main__ - Step 19660: {'lr': 0.00048264089494829776, 'samples': 3774720, 'steps': 19659, 'loss/train': 0.07078750431537628}
+08/30/2021 16:45:18 - INFO - __main__ - Step 19661: {'lr': 0.0004826389519357874, 'samples': 3774912, 'steps': 19660, 'loss/train': 1.532974362373352}
+08/30/2021 16:45:19 - INFO - __main__ - Step 19662: {'lr': 0.00048263700881845346, 'samples': 3775104, 'steps': 19661, 'loss/train': 1.3122813701629639}
+08/30/2021 16:45:20 - INFO - __main__ - Step 19663: {'lr': 0.00048263506559629687, 'samples': 3775296, 'steps': 19662, 'loss/train': 1.125578761100769}
+08/30/2021 16:45:21 - INFO - __main__ - Step 19664: {'lr': 0.00048263312226931853, 'samples': 3775488, 'steps': 19663, 'loss/train': 2.198880434036255}
+08/30/2021 16:45:21 - INFO - __main__ - Step 19665: {'lr': 0.0004826311788375193, 'samples': 3775680, 'steps': 19664, 'loss/train': 1.7454428672790527}
+08/30/2021 16:45:21 - INFO - __main__ - Step 19666: {'lr': 0.00048262923530090007, 'samples': 3775872, 'steps': 19665, 'loss/train': 1.5772764682769775}
+08/30/2021 16:45:22 - INFO - __main__ - Step 19667: {'lr': 0.0004826272916594616, 'samples': 3776064, 'steps': 19666, 'loss/train': 1.87223482131958}
+08/30/2021 16:45:23 - INFO - __main__ - Step 19668: {'lr': 0.000482625347913205, 'samples': 3776256, 'steps': 19667, 'loss/train': 1.2227168083190918}
+08/30/2021 16:45:23 - INFO - __main__ - Step 19669: {'lr': 0.0004826234040621309, 'samples': 3776448, 'steps': 19668, 'loss/train': 0.7310164570808411}
+08/30/2021 16:45:24 - INFO - __main__ - Step 19670: {'lr': 0.00048262146010624035, 'samples': 3776640, 'steps': 19669, 'loss/train': 0.8155099749565125}
+08/30/2021 16:45:24 - INFO - __main__ - Step 19671: {'lr': 0.0004826195160455341, 'samples': 3776832, 'steps': 19670, 'loss/train': 1.195999264717102}
+08/30/2021 16:45:25 - INFO - __main__ - Step 19672: {'lr': 0.00048261757188001314, 'samples': 3777024, 'steps': 19671, 'loss/train': 1.8243367671966553}
+08/30/2021 16:45:25 - INFO - __main__ - Step 19673: {'lr': 0.00048261562760967824, 'samples': 3777216, 'steps': 19672, 'loss/train': 1.3731988668441772}
+08/30/2021 16:45:27 - INFO - __main__ - Step 19674: {'lr': 0.0004826136832345304, 'samples': 3777408, 'steps': 19673, 'loss/train': 1.8078889846801758}
+08/30/2021 16:45:27 - INFO - __main__ - Step 19675: {'lr': 0.00048261173875457035, 'samples': 3777600, 'steps': 19674, 'loss/train': 1.550720453262329}
+08/30/2021 16:45:28 - INFO - __main__ - Step 19676: {'lr': 0.0004826097941697991, 'samples': 3777792, 'steps': 19675, 'loss/train': 1.763080358505249}
+08/30/2021 16:45:28 - INFO - __main__ - Step 19677: {'lr': 0.0004826078494802174, 'samples': 3777984, 'steps': 19676, 'loss/train': 0.2705342173576355}
+08/30/2021 16:45:28 - INFO - __main__ - Step 19678: {'lr': 0.00048260590468582624, 'samples': 3778176, 'steps': 19677, 'loss/train': 1.0702122449874878}
+08/30/2021 16:45:30 - INFO - __main__ - Step 19679: {'lr': 0.0004826039597866265, 'samples': 3778368, 'steps': 19678, 'loss/train': 1.5734738111495972}
+08/30/2021 16:45:31 - INFO - __main__ - Step 19680: {'lr': 0.00048260201478261887, 'samples': 3778560, 'steps': 19679, 'loss/train': 1.3631218671798706}
+08/30/2021 16:45:31 - INFO - __main__ - Step 19681: {'lr': 0.0004826000696738045, 'samples': 3778752, 'steps': 19680, 'loss/train': 1.1993298530578613}
+08/30/2021 16:45:31 - INFO - __main__ - Step 19682: {'lr': 0.000482598124460184, 'samples': 3778944, 'steps': 19681, 'loss/train': 1.9589277505874634}
+08/30/2021 16:45:32 - INFO - __main__ - Step 19683: {'lr': 0.00048259617914175846, 'samples': 3779136, 'steps': 19682, 'loss/train': 1.520262360572815}
+08/30/2021 16:45:33 - INFO - __main__ - Step 19684: {'lr': 0.00048259423371852867, 'samples': 3779328, 'steps': 19683, 'loss/train': 1.4517934322357178}
+08/30/2021 16:45:34 - INFO - __main__ - Step 19685: {'lr': 0.0004825922881904955, 'samples': 3779520, 'steps': 19684, 'loss/train': 1.9209898710250854}
+08/30/2021 16:45:34 - INFO - __main__ - Step 19686: {'lr': 0.00048259034255765984, 'samples': 3779712, 'steps': 19685, 'loss/train': 1.4244006872177124}
+08/30/2021 16:45:34 - INFO - __main__ - Step 19687: {'lr': 0.00048258839682002253, 'samples': 3779904, 'steps': 19686, 'loss/train': 1.7588123083114624}
+08/30/2021 16:45:35 - INFO - __main__ - Step 19688: {'lr': 0.00048258645097758445, 'samples': 3780096, 'steps': 19687, 'loss/train': 1.736598014831543}
+08/30/2021 16:45:36 - INFO - __main__ - Step 19689: {'lr': 0.0004825845050303466, 'samples': 3780288, 'steps': 19688, 'loss/train': 1.4805346727371216}
+08/30/2021 16:45:37 - INFO - __main__ - Step 19690: {'lr': 0.00048258255897830967, 'samples': 3780480, 'steps': 19689, 'loss/train': 1.5934196710586548}
+08/30/2021 16:45:37 - INFO - __main__ - Step 19691: {'lr': 0.0004825806128214747, 'samples': 3780672, 'steps': 19690, 'loss/train': 1.61527419090271}
+08/30/2021 16:45:37 - INFO - __main__ - Step 19692: {'lr': 0.00048257866655984237, 'samples': 3780864, 'steps': 19691, 'loss/train': 1.6771128177642822}
+08/30/2021 16:45:38 - INFO - __main__ - Step 19693: {'lr': 0.0004825767201934138, 'samples': 3781056, 'steps': 19692, 'loss/train': 1.5107687711715698}
+08/30/2021 16:45:39 - INFO - __main__ - Step 19694: {'lr': 0.0004825747737221897, 'samples': 3781248, 'steps': 19693, 'loss/train': 1.7452632188796997}
+08/30/2021 16:45:40 - INFO - __main__ - Step 19695: {'lr': 0.000482572827146171, 'samples': 3781440, 'steps': 19694, 'loss/train': 1.260412335395813}
+08/30/2021 16:45:40 - INFO - __main__ - Step 19696: {'lr': 0.00048257088046535864, 'samples': 3781632, 'steps': 19695, 'loss/train': 1.8159458637237549}
+08/30/2021 16:45:41 - INFO - __main__ - Step 19697: {'lr': 0.0004825689336797534, 'samples': 3781824, 'steps': 19696, 'loss/train': 1.7496967315673828}
+08/30/2021 16:45:41 - INFO - __main__ - Step 19698: {'lr': 0.00048256698678935615, 'samples': 3782016, 'steps': 19697, 'loss/train': 6.348109245300293}
+08/30/2021 16:45:41 - INFO - __main__ - Step 19699: {'lr': 0.00048256503979416776, 'samples': 3782208, 'steps': 19698, 'loss/train': 2.1363143920898438}
+08/30/2021 16:45:43 - INFO - __main__ - Step 19700: {'lr': 0.0004825630926941892, 'samples': 3782400, 'steps': 19699, 'loss/train': 0.06274674832820892}
+08/30/2021 16:45:43 - INFO - __main__ - Step 19701: {'lr': 0.0004825611454894213, 'samples': 3782592, 'steps': 19700, 'loss/train': 1.3938616514205933}
+08/30/2021 16:45:44 - INFO - __main__ - Step 19702: {'lr': 0.000482559198179865, 'samples': 3782784, 'steps': 19701, 'loss/train': 1.8158903121948242}
+08/30/2021 16:45:44 - INFO - __main__ - Step 19703: {'lr': 0.00048255725076552103, 'samples': 3782976, 'steps': 19702, 'loss/train': 1.9675157070159912}
+08/30/2021 16:45:44 - INFO - __main__ - Step 19704: {'lr': 0.0004825553032463904, 'samples': 3783168, 'steps': 19703, 'loss/train': 1.5207316875457764}
+08/30/2021 16:45:45 - INFO - __main__ - Step 19705: {'lr': 0.00048255335562247395, 'samples': 3783360, 'steps': 19704, 'loss/train': 1.7516065835952759}
+08/30/2021 16:45:46 - INFO - __main__ - Step 19706: {'lr': 0.0004825514078937725, 'samples': 3783552, 'steps': 19705, 'loss/train': 1.459518313407898}
+08/30/2021 16:45:47 - INFO - __main__ - Step 19707: {'lr': 0.000482549460060287, 'samples': 3783744, 'steps': 19706, 'loss/train': 1.0809588432312012}
+08/30/2021 16:45:47 - INFO - __main__ - Step 19708: {'lr': 0.0004825475121220183, 'samples': 3783936, 'steps': 19707, 'loss/train': 1.7737821340560913}
+08/30/2021 16:45:47 - INFO - __main__ - Step 19709: {'lr': 0.0004825455640789672, 'samples': 3784128, 'steps': 19708, 'loss/train': 1.630860447883606}
+08/30/2021 16:45:48 - INFO - __main__ - Step 19710: {'lr': 0.00048254361593113475, 'samples': 3784320, 'steps': 19709, 'loss/train': 1.9221594333648682}
+08/30/2021 16:45:49 - INFO - __main__ - Step 19711: {'lr': 0.0004825416676785217, 'samples': 3784512, 'steps': 19710, 'loss/train': 2.125366687774658}
+08/30/2021 16:45:50 - INFO - __main__ - Step 19712: {'lr': 0.000482539719321129, 'samples': 3784704, 'steps': 19711, 'loss/train': 1.2897369861602783}
+08/30/2021 16:45:50 - INFO - __main__ - Step 19713: {'lr': 0.00048253777085895745, 'samples': 3784896, 'steps': 19712, 'loss/train': 1.3967864513397217}
+08/30/2021 16:45:50 - INFO - __main__ - Step 19714: {'lr': 0.000482535822292008, 'samples': 3785088, 'steps': 19713, 'loss/train': 1.3750593662261963}
+08/30/2021 16:45:51 - INFO - __main__ - Step 19715: {'lr': 0.0004825338736202815, 'samples': 3785280, 'steps': 19714, 'loss/train': 1.3700599670410156}
+08/30/2021 16:45:52 - INFO - __main__ - Step 19716: {'lr': 0.00048253192484377884, 'samples': 3785472, 'steps': 19715, 'loss/train': 1.6668800115585327}
+08/30/2021 16:45:53 - INFO - __main__ - Step 19717: {'lr': 0.0004825299759625008, 'samples': 3785664, 'steps': 19716, 'loss/train': 1.5117876529693604}
+08/30/2021 16:45:53 - INFO - __main__ - Step 19718: {'lr': 0.0004825280269764484, 'samples': 3785856, 'steps': 19717, 'loss/train': 1.9901987314224243}
+08/30/2021 16:45:53 - INFO - __main__ - Step 19719: {'lr': 0.0004825260778856224, 'samples': 3786048, 'steps': 19718, 'loss/train': 1.9022563695907593}
+08/30/2021 16:45:54 - INFO - __main__ - Step 19720: {'lr': 0.0004825241286900238, 'samples': 3786240, 'steps': 19719, 'loss/train': 1.249380111694336}
+08/30/2021 16:45:55 - INFO - __main__ - Step 19721: {'lr': 0.0004825221793896535, 'samples': 3786432, 'steps': 19720, 'loss/train': 2.0074994564056396}
+08/30/2021 16:45:56 - INFO - __main__ - Step 19722: {'lr': 0.0004825202299845122, 'samples': 3786624, 'steps': 19721, 'loss/train': 2.1659655570983887}
+08/30/2021 16:45:56 - INFO - __main__ - Step 19723: {'lr': 0.00048251828047460077, 'samples': 3786816, 'steps': 19722, 'loss/train': 1.6186447143554688}
+08/30/2021 16:45:56 - INFO - __main__ - Step 19724: {'lr': 0.0004825163308599203, 'samples': 3787008, 'steps': 19723, 'loss/train': 1.5282928943634033}
+08/30/2021 16:45:57 - INFO - __main__ - Step 19725: {'lr': 0.0004825143811404716, 'samples': 3787200, 'steps': 19724, 'loss/train': 1.08818519115448}
+08/30/2021 16:45:59 - INFO - __main__ - Step 19726: {'lr': 0.00048251243131625543, 'samples': 3787392, 'steps': 19725, 'loss/train': 1.213646411895752}
+08/30/2021 16:45:59 - INFO - __main__ - Step 19727: {'lr': 0.0004825104813872728, 'samples': 3787584, 'steps': 19726, 'loss/train': 1.608264446258545}
+08/30/2021 16:46:00 - INFO - __main__ - Step 19728: {'lr': 0.0004825085313535245, 'samples': 3787776, 'steps': 19727, 'loss/train': 1.5605945587158203}
+08/30/2021 16:46:00 - INFO - __main__ - Step 19729: {'lr': 0.00048250658121501145, 'samples': 3787968, 'steps': 19728, 'loss/train': 2.1500375270843506}
+08/30/2021 16:46:00 - INFO - __main__ - Step 19730: {'lr': 0.00048250463097173447, 'samples': 3788160, 'steps': 19729, 'loss/train': 1.2001900672912598}
+08/30/2021 16:46:02 - INFO - __main__ - Step 19731: {'lr': 0.0004825026806236946, 'samples': 3788352, 'steps': 19730, 'loss/train': 1.7775330543518066}
+08/30/2021 16:46:02 - INFO - __main__ - Step 19732: {'lr': 0.00048250073017089257, 'samples': 3788544, 'steps': 19731, 'loss/train': 1.0759825706481934}
+08/30/2021 16:46:03 - INFO - __main__ - Step 19733: {'lr': 0.00048249877961332923, 'samples': 3788736, 'steps': 19732, 'loss/train': 2.6747982501983643}
+08/30/2021 16:46:03 - INFO - __main__ - Step 19734: {'lr': 0.0004824968289510056, 'samples': 3788928, 'steps': 19733, 'loss/train': 1.3608564138412476}
+08/30/2021 16:46:03 - INFO - __main__ - Step 19735: {'lr': 0.0004824948781839225, 'samples': 3789120, 'steps': 19734, 'loss/train': 1.852820873260498}
+08/30/2021 16:46:05 - INFO - __main__ - Step 19736: {'lr': 0.0004824929273120807, 'samples': 3789312, 'steps': 19735, 'loss/train': 1.777243971824646}
+08/30/2021 16:46:05 - INFO - __main__ - Step 19737: {'lr': 0.0004824909763354813, 'samples': 3789504, 'steps': 19736, 'loss/train': 1.8846819400787354}
+08/30/2021 16:46:06 - INFO - __main__ - Step 19738: {'lr': 0.00048248902525412497, 'samples': 3789696, 'steps': 19737, 'loss/train': 1.4429880380630493}
+08/30/2021 16:46:06 - INFO - __main__ - Step 19739: {'lr': 0.0004824870740680127, 'samples': 3789888, 'steps': 19738, 'loss/train': 1.995111107826233}
+08/30/2021 16:46:07 - INFO - __main__ - Step 19740: {'lr': 0.0004824851227771453, 'samples': 3790080, 'steps': 19739, 'loss/train': 1.3590061664581299}
+08/30/2021 16:46:07 - INFO - __main__ - Step 19741: {'lr': 0.00048248317138152374, 'samples': 3790272, 'steps': 19740, 'loss/train': 1.6957652568817139}
+08/30/2021 16:46:08 - INFO - __main__ - Step 19742: {'lr': 0.00048248121988114887, 'samples': 3790464, 'steps': 19741, 'loss/train': 2.3059370517730713}
+08/30/2021 16:46:09 - INFO - __main__ - Step 19743: {'lr': 0.00048247926827602153, 'samples': 3790656, 'steps': 19742, 'loss/train': 1.349485158920288}
+08/30/2021 16:46:09 - INFO - __main__ - Step 19744: {'lr': 0.0004824773165661426, 'samples': 3790848, 'steps': 19743, 'loss/train': 1.3163179159164429}
+08/30/2021 16:46:10 - INFO - __main__ - Step 19745: {'lr': 0.000482475364751513, 'samples': 3791040, 'steps': 19744, 'loss/train': 1.5471094846725464}
+08/30/2021 16:46:10 - INFO - __main__ - Step 19746: {'lr': 0.0004824734128321335, 'samples': 3791232, 'steps': 19745, 'loss/train': 1.1037479639053345}
+08/30/2021 16:46:11 - INFO - __main__ - Step 19747: {'lr': 0.0004824714608080052, 'samples': 3791424, 'steps': 19746, 'loss/train': 1.6759765148162842}
+08/30/2021 16:46:12 - INFO - __main__ - Step 19748: {'lr': 0.00048246950867912873, 'samples': 3791616, 'steps': 19747, 'loss/train': 1.7748245000839233}
+08/30/2021 16:46:12 - INFO - __main__ - Step 19749: {'lr': 0.0004824675564455052, 'samples': 3791808, 'steps': 19748, 'loss/train': 1.7343673706054688}
+08/30/2021 16:46:13 - INFO - __main__ - Step 19750: {'lr': 0.0004824656041071353, 'samples': 3792000, 'steps': 19749, 'loss/train': 1.4536768198013306}
+08/30/2021 16:46:13 - INFO - __main__ - Step 19751: {'lr': 0.00048246365166402003, 'samples': 3792192, 'steps': 19750, 'loss/train': 1.4853363037109375}
+08/30/2021 16:46:14 - INFO - __main__ - Step 19752: {'lr': 0.00048246169911616015, 'samples': 3792384, 'steps': 19751, 'loss/train': 2.1229076385498047}
+08/30/2021 16:46:15 - INFO - __main__ - Step 19753: {'lr': 0.00048245974646355673, 'samples': 3792576, 'steps': 19752, 'loss/train': 1.5881577730178833}
+08/30/2021 16:46:15 - INFO - __main__ - Step 19754: {'lr': 0.00048245779370621045, 'samples': 3792768, 'steps': 19753, 'loss/train': 0.0828220397233963}
+08/30/2021 16:46:16 - INFO - __main__ - Step 19755: {'lr': 0.0004824558408441223, 'samples': 3792960, 'steps': 19754, 'loss/train': 1.7623757123947144}
+08/30/2021 16:46:16 - INFO - __main__ - Step 19756: {'lr': 0.00048245388787729316, 'samples': 3793152, 'steps': 19755, 'loss/train': 1.5343509912490845}
+08/30/2021 16:46:18 - INFO - __main__ - Step 19757: {'lr': 0.00048245193480572383, 'samples': 3793344, 'steps': 19756, 'loss/train': 1.145225167274475}
+08/30/2021 16:46:18 - INFO - __main__ - Step 19758: {'lr': 0.0004824499816294152, 'samples': 3793536, 'steps': 19757, 'loss/train': 1.65183424949646}
+08/30/2021 16:46:18 - INFO - __main__ - Step 19759: {'lr': 0.0004824480283483683, 'samples': 3793728, 'steps': 19758, 'loss/train': 1.3957730531692505}
+08/30/2021 16:46:19 - INFO - __main__ - Step 19760: {'lr': 0.0004824460749625839, 'samples': 3793920, 'steps': 19759, 'loss/train': 0.8056812286376953}
+08/30/2021 16:46:19 - INFO - __main__ - Step 19761: {'lr': 0.00048244412147206283, 'samples': 3794112, 'steps': 19760, 'loss/train': 1.4695429801940918}
+08/30/2021 16:46:21 - INFO - __main__ - Step 19762: {'lr': 0.00048244216787680607, 'samples': 3794304, 'steps': 19761, 'loss/train': 1.407184362411499}
+08/30/2021 16:46:21 - INFO - __main__ - Step 19763: {'lr': 0.0004824402141768145, 'samples': 3794496, 'steps': 19762, 'loss/train': 1.706057071685791}
+08/30/2021 16:46:21 - INFO - __main__ - Step 19764: {'lr': 0.0004824382603720888, 'samples': 3794688, 'steps': 19763, 'loss/train': 1.8974753618240356}
+08/30/2021 16:46:22 - INFO - __main__ - Step 19765: {'lr': 0.00048243630646263016, 'samples': 3794880, 'steps': 19764, 'loss/train': 1.7434874773025513}
+08/30/2021 16:46:22 - INFO - __main__ - Step 19766: {'lr': 0.00048243435244843926, 'samples': 3795072, 'steps': 19765, 'loss/train': 1.6711057424545288}
+08/30/2021 16:46:22 - INFO - __main__ - Step 19767: {'lr': 0.000482432398329517, 'samples': 3795264, 'steps': 19766, 'loss/train': 1.4974653720855713}
+08/30/2021 16:46:24 - INFO - __main__ - Step 19768: {'lr': 0.00048243044410586433, 'samples': 3795456, 'steps': 19767, 'loss/train': 1.5653835535049438}
+08/30/2021 16:46:24 - INFO - __main__ - Step 19769: {'lr': 0.00048242848977748205, 'samples': 3795648, 'steps': 19768, 'loss/train': 0.8201896548271179}
+08/30/2021 16:46:25 - INFO - __main__ - Step 19770: {'lr': 0.0004824265353443711, 'samples': 3795840, 'steps': 19769, 'loss/train': 1.5632750988006592}
+08/30/2021 16:46:25 - INFO - __main__ - Step 19771: {'lr': 0.00048242458080653233, 'samples': 3796032, 'steps': 19770, 'loss/train': 1.306421160697937}
+08/30/2021 16:46:26 - INFO - __main__ - Step 19772: {'lr': 0.0004824226261639666, 'samples': 3796224, 'steps': 19771, 'loss/train': 1.869511604309082}
+08/30/2021 16:46:27 - INFO - __main__ - Step 19773: {'lr': 0.00048242067141667487, 'samples': 3796416, 'steps': 19772, 'loss/train': 1.3827139139175415}
+08/30/2021 16:46:28 - INFO - __main__ - Step 19774: {'lr': 0.00048241871656465795, 'samples': 3796608, 'steps': 19773, 'loss/train': 0.756730854511261}
+08/30/2021 16:46:28 - INFO - __main__ - Step 19775: {'lr': 0.0004824167616079168, 'samples': 3796800, 'steps': 19774, 'loss/train': 1.6832746267318726}
+08/30/2021 16:46:28 - INFO - __main__ - Step 19776: {'lr': 0.0004824148065464522, 'samples': 3796992, 'steps': 19775, 'loss/train': 1.5018789768218994}
+08/30/2021 16:46:29 - INFO - __main__ - Step 19777: {'lr': 0.00048241285138026505, 'samples': 3797184, 'steps': 19776, 'loss/train': 1.9354379177093506}
+08/30/2021 16:46:30 - INFO - __main__ - Step 19778: {'lr': 0.00048241089610935627, 'samples': 3797376, 'steps': 19777, 'loss/train': 1.5387619733810425}
+08/30/2021 16:46:31 - INFO - __main__ - Step 19779: {'lr': 0.0004824089407337267, 'samples': 3797568, 'steps': 19778, 'loss/train': 1.7963557243347168}
+08/30/2021 16:46:31 - INFO - __main__ - Step 19780: {'lr': 0.00048240698525337726, 'samples': 3797760, 'steps': 19779, 'loss/train': 1.811444878578186}
+08/30/2021 16:46:31 - INFO - __main__ - Step 19781: {'lr': 0.0004824050296683089, 'samples': 3797952, 'steps': 19780, 'loss/train': 1.7149640321731567}
+08/30/2021 16:46:32 - INFO - __main__ - Step 19782: {'lr': 0.0004824030739785223, 'samples': 3798144, 'steps': 19781, 'loss/train': 1.2311028242111206}
+08/30/2021 16:46:32 - INFO - __main__ - Step 19783: {'lr': 0.00048240111818401854, 'samples': 3798336, 'steps': 19782, 'loss/train': 1.7671340703964233}
+08/30/2021 16:46:34 - INFO - __main__ - Step 19784: {'lr': 0.0004823991622847984, 'samples': 3798528, 'steps': 19783, 'loss/train': 1.5080082416534424}
+08/30/2021 16:46:35 - INFO - __main__ - Step 19785: {'lr': 0.0004823972062808628, 'samples': 3798720, 'steps': 19784, 'loss/train': 1.4996699094772339}
+08/30/2021 16:46:35 - INFO - __main__ - Step 19786: {'lr': 0.0004823952501722126, 'samples': 3798912, 'steps': 19785, 'loss/train': 1.8464879989624023}
+08/30/2021 16:46:35 - INFO - __main__ - Step 19787: {'lr': 0.00048239329395884865, 'samples': 3799104, 'steps': 19786, 'loss/train': 1.6811447143554688}
+08/30/2021 16:46:36 - INFO - __main__ - Step 19788: {'lr': 0.00048239133764077193, 'samples': 3799296, 'steps': 19787, 'loss/train': 1.9512839317321777}
+08/30/2021 16:46:37 - INFO - __main__ - Step 19789: {'lr': 0.00048238938121798313, 'samples': 3799488, 'steps': 19788, 'loss/train': 1.5324562788009644}
+08/30/2021 16:46:38 - INFO - __main__ - Step 19790: {'lr': 0.00048238742469048344, 'samples': 3799680, 'steps': 19789, 'loss/train': 1.4485249519348145}
+08/30/2021 16:46:38 - INFO - __main__ - Step 19791: {'lr': 0.00048238546805827345, 'samples': 3799872, 'steps': 19790, 'loss/train': 1.9327707290649414}
+08/30/2021 16:46:39 - INFO - __main__ - Step 19792: {'lr': 0.00048238351132135415, 'samples': 3800064, 'steps': 19791, 'loss/train': 1.6438424587249756}
+08/30/2021 16:46:39 - INFO - __main__ - Step 19793: {'lr': 0.0004823815544797265, 'samples': 3800256, 'steps': 19792, 'loss/train': 1.512700080871582}
+08/30/2021 16:46:40 - INFO - __main__ - Step 19794: {'lr': 0.0004823795975333912, 'samples': 3800448, 'steps': 19793, 'loss/train': 1.6888874769210815}
+08/30/2021 16:46:41 - INFO - __main__ - Step 19795: {'lr': 0.0004823776404823493, 'samples': 3800640, 'steps': 19794, 'loss/train': 1.5916376113891602}
+08/30/2021 16:46:41 - INFO - __main__ - Step 19796: {'lr': 0.00048237568332660163, 'samples': 3800832, 'steps': 19795, 'loss/train': 2.0096867084503174}
+08/30/2021 16:46:41 - INFO - __main__ - Step 19797: {'lr': 0.0004823737260661491, 'samples': 3801024, 'steps': 19796, 'loss/train': 1.7896571159362793}
+08/30/2021 16:46:42 - INFO - __main__ - Step 19798: {'lr': 0.00048237176870099256, 'samples': 3801216, 'steps': 19797, 'loss/train': 1.7274136543273926}
+08/30/2021 16:46:43 - INFO - __main__ - Step 19799: {'lr': 0.0004823698112311328, 'samples': 3801408, 'steps': 19798, 'loss/train': 1.4035961627960205}
+08/30/2021 16:46:44 - INFO - __main__ - Step 19800: {'lr': 0.00048236785365657076, 'samples': 3801600, 'steps': 19799, 'loss/train': 0.17131058871746063}
+08/30/2021 16:46:44 - INFO - __main__ - Step 19801: {'lr': 0.00048236589597730744, 'samples': 3801792, 'steps': 19800, 'loss/train': 1.7156814336776733}
+08/30/2021 16:46:45 - INFO - __main__ - Step 19802: {'lr': 0.00048236393819334363, 'samples': 3801984, 'steps': 19801, 'loss/train': 1.3876007795333862}
+08/30/2021 16:46:45 - INFO - __main__ - Step 19803: {'lr': 0.0004823619803046802, 'samples': 3802176, 'steps': 19802, 'loss/train': 0.6160278916358948}
+08/30/2021 16:46:47 - INFO - __main__ - Step 19804: {'lr': 0.00048236002231131803, 'samples': 3802368, 'steps': 19803, 'loss/train': 1.3296622037887573}
+08/30/2021 16:46:47 - INFO - __main__ - Step 19805: {'lr': 0.00048235806421325803, 'samples': 3802560, 'steps': 19804, 'loss/train': 1.531077265739441}
+08/30/2021 16:46:47 - INFO - __main__ - Step 19806: {'lr': 0.0004823561060105011, 'samples': 3802752, 'steps': 19805, 'loss/train': 1.6807235479354858}
+08/30/2021 16:46:48 - INFO - __main__ - Step 19807: {'lr': 0.00048235414770304803, 'samples': 3802944, 'steps': 19806, 'loss/train': 1.673302173614502}
+08/30/2021 16:46:48 - INFO - __main__ - Step 19808: {'lr': 0.00048235218929089987, 'samples': 3803136, 'steps': 19807, 'loss/train': 1.5240333080291748}
+08/30/2021 16:46:49 - INFO - __main__ - Step 19809: {'lr': 0.00048235023077405724, 'samples': 3803328, 'steps': 19808, 'loss/train': 1.59073805809021}
+08/30/2021 16:46:50 - INFO - __main__ - Step 19810: {'lr': 0.0004823482721525213, 'samples': 3803520, 'steps': 19809, 'loss/train': 1.7584518194198608}
+08/30/2021 16:46:50 - INFO - __main__ - Step 19811: {'lr': 0.0004823463134262928, 'samples': 3803712, 'steps': 19810, 'loss/train': 1.5256023406982422}
+08/30/2021 16:46:51 - INFO - __main__ - Step 19812: {'lr': 0.00048234435459537265, 'samples': 3803904, 'steps': 19811, 'loss/train': 1.4290350675582886}
+08/30/2021 16:46:51 - INFO - __main__ - Step 19813: {'lr': 0.0004823423956597617, 'samples': 3804096, 'steps': 19812, 'loss/train': 1.2690590620040894}
+08/30/2021 16:46:52 - INFO - __main__ - Step 19814: {'lr': 0.0004823404366194608, 'samples': 3804288, 'steps': 19813, 'loss/train': 1.546666145324707}
+08/30/2021 16:46:53 - INFO - __main__ - Step 19815: {'lr': 0.0004823384774744709, 'samples': 3804480, 'steps': 19814, 'loss/train': 1.6375718116760254}
+08/30/2021 16:46:53 - INFO - __main__ - Step 19816: {'lr': 0.000482336518224793, 'samples': 3804672, 'steps': 19815, 'loss/train': 0.07490232586860657}
+08/30/2021 16:46:54 - INFO - __main__ - Step 19817: {'lr': 0.00048233455887042764, 'samples': 3804864, 'steps': 19816, 'loss/train': 1.213105320930481}
+08/30/2021 16:46:54 - INFO - __main__ - Step 19818: {'lr': 0.0004823325994113761, 'samples': 3805056, 'steps': 19817, 'loss/train': 1.383909821510315}
+08/30/2021 16:46:56 - INFO - __main__ - Step 19819: {'lr': 0.00048233063984763895, 'samples': 3805248, 'steps': 19818, 'loss/train': 1.2611336708068848}
+08/30/2021 16:46:56 - INFO - __main__ - Step 19820: {'lr': 0.0004823286801792173, 'samples': 3805440, 'steps': 19819, 'loss/train': 1.7871754169464111}
+08/30/2021 16:46:56 - INFO - __main__ - Step 19821: {'lr': 0.0004823267204061118, 'samples': 3805632, 'steps': 19820, 'loss/train': 2.1539313793182373}
+08/30/2021 16:46:57 - INFO - __main__ - Step 19822: {'lr': 0.0004823247605283236, 'samples': 3805824, 'steps': 19821, 'loss/train': 0.15021799504756927}
+08/30/2021 16:46:57 - INFO - __main__ - Step 19823: {'lr': 0.0004823228005458534, 'samples': 3806016, 'steps': 19822, 'loss/train': 1.92867112159729}
+08/30/2021 16:46:59 - INFO - __main__ - Step 19824: {'lr': 0.00048232084045870204, 'samples': 3806208, 'steps': 19823, 'loss/train': 0.8178573250770569}
+08/30/2021 16:46:59 - INFO - __main__ - Step 19825: {'lr': 0.00048231888026687065, 'samples': 3806400, 'steps': 19824, 'loss/train': 1.4814424514770508}
+08/30/2021 16:46:59 - INFO - __main__ - Step 19826: {'lr': 0.00048231691997035987, 'samples': 3806592, 'steps': 19825, 'loss/train': 1.6040164232254028}
+08/30/2021 16:47:00 - INFO - __main__ - Step 19827: {'lr': 0.00048231495956917067, 'samples': 3806784, 'steps': 19826, 'loss/train': 1.462829351425171}
+08/30/2021 16:47:00 - INFO - __main__ - Step 19828: {'lr': 0.00048231299906330397, 'samples': 3806976, 'steps': 19827, 'loss/train': 1.1462972164154053}
+08/30/2021 16:47:02 - INFO - __main__ - Step 19829: {'lr': 0.0004823110384527606, 'samples': 3807168, 'steps': 19828, 'loss/train': 1.4257042407989502}
+08/30/2021 16:47:02 - INFO - __main__ - Step 19830: {'lr': 0.0004823090777375414, 'samples': 3807360, 'steps': 19829, 'loss/train': 1.8113360404968262}
+08/30/2021 16:47:02 - INFO - __main__ - Step 19831: {'lr': 0.0004823071169176474, 'samples': 3807552, 'steps': 19830, 'loss/train': 2.2109315395355225}
+08/30/2021 16:47:03 - INFO - __main__ - Step 19832: {'lr': 0.00048230515599307933, 'samples': 3807744, 'steps': 19831, 'loss/train': 1.2028950452804565}
+08/30/2021 16:47:03 - INFO - __main__ - Step 19833: {'lr': 0.0004823031949638382, 'samples': 3807936, 'steps': 19832, 'loss/train': 1.6282076835632324}
+08/30/2021 16:47:03 - INFO - __main__ - Step 19834: {'lr': 0.0004823012338299248, 'samples': 3808128, 'steps': 19833, 'loss/train': 1.61159348487854}
+08/30/2021 16:47:06 - INFO - __main__ - Step 19835: {'lr': 0.0004822992725913401, 'samples': 3808320, 'steps': 19834, 'loss/train': 1.688277244567871}
+08/30/2021 16:47:06 - INFO - __main__ - Step 19836: {'lr': 0.00048229731124808484, 'samples': 3808512, 'steps': 19835, 'loss/train': 1.5510793924331665}
+08/30/2021 16:47:07 - INFO - __main__ - Step 19837: {'lr': 0.00048229534980016007, 'samples': 3808704, 'steps': 19836, 'loss/train': 1.5770598649978638}
+08/30/2021 16:47:07 - INFO - __main__ - Step 19838: {'lr': 0.0004822933882475666, 'samples': 3808896, 'steps': 19837, 'loss/train': 1.6042286157608032}
+08/30/2021 16:47:07 - INFO - __main__ - Step 19839: {'lr': 0.00048229142659030527, 'samples': 3809088, 'steps': 19838, 'loss/train': 1.6330395936965942}
+08/30/2021 16:47:08 - INFO - __main__ - Step 19840: {'lr': 0.000482289464828377, 'samples': 3809280, 'steps': 19839, 'loss/train': 0.057610705494880676}
+08/30/2021 16:47:09 - INFO - __main__ - Step 19841: {'lr': 0.00048228750296178276, 'samples': 3809472, 'steps': 19840, 'loss/train': 1.5284667015075684}
+08/30/2021 16:47:10 - INFO - __main__ - Step 19842: {'lr': 0.0004822855409905233, 'samples': 3809664, 'steps': 19841, 'loss/train': 1.4956417083740234}
+08/30/2021 16:47:10 - INFO - __main__ - Step 19843: {'lr': 0.00048228357891459954, 'samples': 3809856, 'steps': 19842, 'loss/train': 2.1752610206604004}
+08/30/2021 16:47:11 - INFO - __main__ - Step 19844: {'lr': 0.0004822816167340124, 'samples': 3810048, 'steps': 19843, 'loss/train': 0.914184033870697}
+08/30/2021 16:47:11 - INFO - __main__ - Step 19845: {'lr': 0.00048227965444876277, 'samples': 3810240, 'steps': 19844, 'loss/train': 2.04819655418396}
+08/30/2021 16:47:12 - INFO - __main__ - Step 19846: {'lr': 0.0004822776920588515, 'samples': 3810432, 'steps': 19845, 'loss/train': 1.589402437210083}
+08/30/2021 16:47:13 - INFO - __main__ - Step 19847: {'lr': 0.0004822757295642795, 'samples': 3810624, 'steps': 19846, 'loss/train': 1.5684795379638672}
+08/30/2021 16:47:13 - INFO - __main__ - Step 19848: {'lr': 0.00048227376696504765, 'samples': 3810816, 'steps': 19847, 'loss/train': 1.812343955039978}
+08/30/2021 16:47:14 - INFO - __main__ - Step 19849: {'lr': 0.0004822718042611568, 'samples': 3811008, 'steps': 19848, 'loss/train': 1.5832816362380981}
+08/30/2021 16:47:14 - INFO - __main__ - Step 19850: {'lr': 0.0004822698414526079, 'samples': 3811200, 'steps': 19849, 'loss/train': 1.8289332389831543}
+08/30/2021 16:47:16 - INFO - __main__ - Step 19851: {'lr': 0.0004822678785394017, 'samples': 3811392, 'steps': 19850, 'loss/train': 1.7046853303909302}
+08/30/2021 16:47:16 - INFO - __main__ - Step 19852: {'lr': 0.0004822659155215393, 'samples': 3811584, 'steps': 19851, 'loss/train': 0.8314381837844849}
+08/30/2021 16:47:17 - INFO - __main__ - Step 19853: {'lr': 0.00048226395239902133, 'samples': 3811776, 'steps': 19852, 'loss/train': 1.683605670928955}
+08/30/2021 16:47:17 - INFO - __main__ - Step 19854: {'lr': 0.00048226198917184886, 'samples': 3811968, 'steps': 19853, 'loss/train': 1.5703904628753662}
+08/30/2021 16:47:17 - INFO - __main__ - Step 19855: {'lr': 0.00048226002584002276, 'samples': 3812160, 'steps': 19854, 'loss/train': 0.059553273022174835}
+08/30/2021 16:47:18 - INFO - __main__ - Step 19856: {'lr': 0.00048225806240354387, 'samples': 3812352, 'steps': 19855, 'loss/train': 0.06528206169605255}
+08/30/2021 16:47:19 - INFO - __main__ - Step 19857: {'lr': 0.0004822560988624131, 'samples': 3812544, 'steps': 19856, 'loss/train': 2.0399603843688965}
+08/30/2021 16:47:20 - INFO - __main__ - Step 19858: {'lr': 0.0004822541352166312, 'samples': 3812736, 'steps': 19857, 'loss/train': 1.376532793045044}
+08/30/2021 16:47:20 - INFO - __main__ - Step 19859: {'lr': 0.0004822521714661993, 'samples': 3812928, 'steps': 19858, 'loss/train': 1.4827698469161987}
+08/30/2021 16:47:20 - INFO - __main__ - Step 19860: {'lr': 0.0004822502076111181, 'samples': 3813120, 'steps': 19859, 'loss/train': 1.3917800188064575}
+08/30/2021 16:47:21 - INFO - __main__ - Step 19861: {'lr': 0.0004822482436513885, 'samples': 3813312, 'steps': 19860, 'loss/train': 0.8752621412277222}
+08/30/2021 16:47:21 - INFO - __main__ - Step 19862: {'lr': 0.0004822462795870115, 'samples': 3813504, 'steps': 19861, 'loss/train': 0.5461375713348389}
+08/30/2021 16:47:23 - INFO - __main__ - Step 19863: {'lr': 0.00048224431541798784, 'samples': 3813696, 'steps': 19862, 'loss/train': 1.2158832550048828}
+08/30/2021 16:47:23 - INFO - __main__ - Step 19864: {'lr': 0.00048224235114431856, 'samples': 3813888, 'steps': 19863, 'loss/train': 2.0124335289001465}
+08/30/2021 16:47:23 - INFO - __main__ - Step 19865: {'lr': 0.0004822403867660044, 'samples': 3814080, 'steps': 19864, 'loss/train': 1.2959673404693604}
+08/30/2021 16:47:24 - INFO - __main__ - Step 19866: {'lr': 0.0004822384222830463, 'samples': 3814272, 'steps': 19865, 'loss/train': 2.120906352996826}
+08/30/2021 16:47:24 - INFO - __main__ - Step 19867: {'lr': 0.0004822364576954452, 'samples': 3814464, 'steps': 19866, 'loss/train': 1.5623080730438232}
+08/30/2021 16:47:26 - INFO - __main__ - Step 19868: {'lr': 0.0004822344930032019, 'samples': 3814656, 'steps': 19867, 'loss/train': 1.6022862195968628}
+08/30/2021 16:47:26 - INFO - __main__ - Step 19869: {'lr': 0.00048223252820631736, 'samples': 3814848, 'steps': 19868, 'loss/train': 1.5811340808868408}
+08/30/2021 16:47:26 - INFO - __main__ - Step 19870: {'lr': 0.00048223056330479235, 'samples': 3815040, 'steps': 19869, 'loss/train': 0.598106324672699}
+08/30/2021 16:47:27 - INFO - __main__ - Step 19871: {'lr': 0.00048222859829862784, 'samples': 3815232, 'steps': 19870, 'loss/train': 1.6351191997528076}
+08/30/2021 16:47:27 - INFO - __main__ - Step 19872: {'lr': 0.0004822266331878248, 'samples': 3815424, 'steps': 19871, 'loss/train': 1.4950696229934692}
+08/30/2021 16:47:29 - INFO - __main__ - Step 19873: {'lr': 0.00048222466797238396, 'samples': 3815616, 'steps': 19872, 'loss/train': 1.8534035682678223}
+08/30/2021 16:47:29 - INFO - __main__ - Step 19874: {'lr': 0.00048222270265230627, 'samples': 3815808, 'steps': 19873, 'loss/train': 2.3191308975219727}
+08/30/2021 16:47:30 - INFO - __main__ - Step 19875: {'lr': 0.0004822207372275926, 'samples': 3816000, 'steps': 19874, 'loss/train': 0.8441720008850098}
+08/30/2021 16:47:30 - INFO - __main__ - Step 19876: {'lr': 0.0004822187716982439, 'samples': 3816192, 'steps': 19875, 'loss/train': 1.893140435218811}
+08/30/2021 16:47:30 - INFO - __main__ - Step 19877: {'lr': 0.000482216806064261, 'samples': 3816384, 'steps': 19876, 'loss/train': 1.9657264947891235}
+08/30/2021 16:47:32 - INFO - __main__ - Step 19878: {'lr': 0.0004822148403256447, 'samples': 3816576, 'steps': 19877, 'loss/train': 1.5532938241958618}
+08/30/2021 16:47:33 - INFO - __main__ - Step 19879: {'lr': 0.00048221287448239604, 'samples': 3816768, 'steps': 19878, 'loss/train': 2.102879047393799}
+08/30/2021 16:47:33 - INFO - __main__ - Step 19880: {'lr': 0.00048221090853451586, 'samples': 3816960, 'steps': 19879, 'loss/train': 1.3816614151000977}
+08/30/2021 16:47:33 - INFO - __main__ - Step 19881: {'lr': 0.000482208942482005, 'samples': 3817152, 'steps': 19880, 'loss/train': 1.6331406831741333}
+08/30/2021 16:47:34 - INFO - __main__ - Step 19882: {'lr': 0.00048220697632486443, 'samples': 3817344, 'steps': 19881, 'loss/train': 1.5460662841796875}
+08/30/2021 16:47:35 - INFO - __main__ - Step 19883: {'lr': 0.0004822050100630949, 'samples': 3817536, 'steps': 19882, 'loss/train': 1.1174434423446655}
+08/30/2021 16:47:36 - INFO - __main__ - Step 19884: {'lr': 0.0004822030436966974, 'samples': 3817728, 'steps': 19883, 'loss/train': 1.226914644241333}
+08/30/2021 16:47:36 - INFO - __main__ - Step 19885: {'lr': 0.0004822010772256728, 'samples': 3817920, 'steps': 19884, 'loss/train': 1.0844295024871826}
+08/30/2021 16:47:37 - INFO - __main__ - Step 19886: {'lr': 0.00048219911065002196, 'samples': 3818112, 'steps': 19885, 'loss/train': 0.13883930444717407}
+08/30/2021 16:47:37 - INFO - __main__ - Step 19887: {'lr': 0.00048219714396974587, 'samples': 3818304, 'steps': 19886, 'loss/train': 0.388445645570755}
+08/30/2021 16:47:37 - INFO - __main__ - Step 19888: {'lr': 0.0004821951771848452, 'samples': 3818496, 'steps': 19887, 'loss/train': 1.543168544769287}
+08/30/2021 16:47:39 - INFO - __main__ - Step 19889: {'lr': 0.00048219321029532104, 'samples': 3818688, 'steps': 19888, 'loss/train': 1.3442749977111816}
+08/30/2021 16:47:39 - INFO - __main__ - Step 19890: {'lr': 0.0004821912433011742, 'samples': 3818880, 'steps': 19889, 'loss/train': 2.1364612579345703}
+08/30/2021 16:47:39 - INFO - __main__ - Step 19891: {'lr': 0.00048218927620240557, 'samples': 3819072, 'steps': 19890, 'loss/train': 1.3614708185195923}
+08/30/2021 16:47:40 - INFO - __main__ - Step 19892: {'lr': 0.00048218730899901596, 'samples': 3819264, 'steps': 19891, 'loss/train': 1.7762341499328613}
+08/30/2021 16:47:40 - INFO - __main__ - Step 19893: {'lr': 0.0004821853416910065, 'samples': 3819456, 'steps': 19892, 'loss/train': 2.399401903152466}
+08/30/2021 16:47:42 - INFO - __main__ - Step 19894: {'lr': 0.0004821833742783778, 'samples': 3819648, 'steps': 19893, 'loss/train': 1.5506436824798584}
+08/30/2021 16:47:43 - INFO - __main__ - Step 19895: {'lr': 0.0004821814067611308, 'samples': 3819840, 'steps': 19894, 'loss/train': 1.3862872123718262}
+08/30/2021 16:47:43 - INFO - __main__ - Step 19896: {'lr': 0.00048217943913926646, 'samples': 3820032, 'steps': 19895, 'loss/train': 1.5992727279663086}
+08/30/2021 16:47:43 - INFO - __main__ - Step 19897: {'lr': 0.00048217747141278574, 'samples': 3820224, 'steps': 19896, 'loss/train': 1.7001378536224365}
+08/30/2021 16:47:44 - INFO - __main__ - Step 19898: {'lr': 0.00048217550358168937, 'samples': 3820416, 'steps': 19897, 'loss/train': 1.771938443183899}
+08/30/2021 16:47:44 - INFO - __main__ - Step 19899: {'lr': 0.00048217353564597833, 'samples': 3820608, 'steps': 19898, 'loss/train': 0.980220377445221}
+08/30/2021 16:47:46 - INFO - __main__ - Step 19900: {'lr': 0.0004821715676056534, 'samples': 3820800, 'steps': 19899, 'loss/train': 1.2470473051071167}
+08/30/2021 16:47:46 - INFO - __main__ - Step 19901: {'lr': 0.0004821695994607156, 'samples': 3820992, 'steps': 19900, 'loss/train': 1.54640793800354}
+08/30/2021 16:47:46 - INFO - __main__ - Step 19902: {'lr': 0.0004821676312111658, 'samples': 3821184, 'steps': 19901, 'loss/train': 1.4011132717132568}
+08/30/2021 16:47:47 - INFO - __main__ - Step 19903: {'lr': 0.0004821656628570048, 'samples': 3821376, 'steps': 19902, 'loss/train': 1.692028522491455}
+08/30/2021 16:47:47 - INFO - __main__ - Step 19904: {'lr': 0.00048216369439823355, 'samples': 3821568, 'steps': 19903, 'loss/train': 1.0948528051376343}
+08/30/2021 16:47:49 - INFO - __main__ - Step 19905: {'lr': 0.0004821617258348529, 'samples': 3821760, 'steps': 19904, 'loss/train': 1.3367528915405273}
+08/30/2021 16:47:49 - INFO - __main__ - Step 19906: {'lr': 0.0004821597571668638, 'samples': 3821952, 'steps': 19905, 'loss/train': 1.7913727760314941}
+08/30/2021 16:47:50 - INFO - __main__ - Step 19907: {'lr': 0.00048215778839426706, 'samples': 3822144, 'steps': 19906, 'loss/train': 1.740395426750183}
+08/30/2021 16:47:50 - INFO - __main__ - Step 19908: {'lr': 0.0004821558195170636, 'samples': 3822336, 'steps': 19907, 'loss/train': 1.95854651927948}
+08/30/2021 16:47:51 - INFO - __main__ - Step 19909: {'lr': 0.00048215385053525434, 'samples': 3822528, 'steps': 19908, 'loss/train': 1.7856106758117676}
+08/30/2021 16:47:52 - INFO - __main__ - Step 19910: {'lr': 0.00048215188144884013, 'samples': 3822720, 'steps': 19909, 'loss/train': 1.7378044128417969}
+08/30/2021 16:47:52 - INFO - __main__ - Step 19911: {'lr': 0.0004821499122578218, 'samples': 3822912, 'steps': 19910, 'loss/train': 1.4063925743103027}
+08/30/2021 16:47:53 - INFO - __main__ - Step 19912: {'lr': 0.00048214794296220045, 'samples': 3823104, 'steps': 19911, 'loss/train': 2.181438684463501}
+08/30/2021 16:47:53 - INFO - __main__ - Step 19913: {'lr': 0.00048214597356197665, 'samples': 3823296, 'steps': 19912, 'loss/train': 1.8075560331344604}
+08/30/2021 16:47:53 - INFO - __main__ - Step 19914: {'lr': 0.00048214400405715153, 'samples': 3823488, 'steps': 19913, 'loss/train': 1.2732000350952148}
+08/30/2021 16:47:55 - INFO - __main__ - Step 19915: {'lr': 0.000482142034447726, 'samples': 3823680, 'steps': 19914, 'loss/train': 2.2317516803741455}
+08/30/2021 16:47:55 - INFO - __main__ - Step 19916: {'lr': 0.0004821400647337007, 'samples': 3823872, 'steps': 19915, 'loss/train': 1.7764110565185547}
+08/30/2021 16:47:56 - INFO - __main__ - Step 19917: {'lr': 0.0004821380949150768, 'samples': 3824064, 'steps': 19916, 'loss/train': 1.7857691049575806}
+08/30/2021 16:47:56 - INFO - __main__ - Step 19918: {'lr': 0.0004821361249918549, 'samples': 3824256, 'steps': 19917, 'loss/train': 2.807133197784424}
+08/30/2021 16:47:56 - INFO - __main__ - Step 19919: {'lr': 0.0004821341549640361, 'samples': 3824448, 'steps': 19918, 'loss/train': 1.948252558708191}
+08/30/2021 16:47:57 - INFO - __main__ - Step 19920: {'lr': 0.00048213218483162133, 'samples': 3824640, 'steps': 19919, 'loss/train': 1.578928828239441}
+08/30/2021 16:47:58 - INFO - __main__ - Step 19921: {'lr': 0.0004821302145946113, 'samples': 3824832, 'steps': 19920, 'loss/train': 1.0670801401138306}
+08/30/2021 16:47:59 - INFO - __main__ - Step 19922: {'lr': 0.00048212824425300694, 'samples': 3825024, 'steps': 19921, 'loss/train': 1.6731804609298706}
+08/30/2021 16:47:59 - INFO - __main__ - Step 19923: {'lr': 0.0004821262738068093, 'samples': 3825216, 'steps': 19922, 'loss/train': 0.26068222522735596}
+08/30/2021 16:48:00 - INFO - __main__ - Step 19924: {'lr': 0.00048212430325601905, 'samples': 3825408, 'steps': 19923, 'loss/train': 1.7669562101364136}
+08/30/2021 16:48:00 - INFO - __main__ - Step 19925: {'lr': 0.0004821223326006372, 'samples': 3825600, 'steps': 19924, 'loss/train': 1.3206557035446167}
+08/30/2021 16:48:01 - INFO - __main__ - Step 19926: {'lr': 0.0004821203618406645, 'samples': 3825792, 'steps': 19925, 'loss/train': 1.6502186059951782}
+08/30/2021 16:48:02 - INFO - __main__ - Step 19927: {'lr': 0.0004821183909761021, 'samples': 3825984, 'steps': 19926, 'loss/train': 1.5708249807357788}
+08/30/2021 16:48:02 - INFO - __main__ - Step 19928: {'lr': 0.00048211642000695065, 'samples': 3826176, 'steps': 19927, 'loss/train': 1.6866652965545654}
+08/30/2021 16:48:03 - INFO - __main__ - Step 19929: {'lr': 0.0004821144489332112, 'samples': 3826368, 'steps': 19928, 'loss/train': 1.0631749629974365}
+08/30/2021 16:48:03 - INFO - __main__ - Step 19930: {'lr': 0.0004821124777548845, 'samples': 3826560, 'steps': 19929, 'loss/train': 1.2046526670455933}
+08/30/2021 16:48:05 - INFO - __main__ - Step 19931: {'lr': 0.0004821105064719715, 'samples': 3826752, 'steps': 19930, 'loss/train': 1.9138237237930298}
+08/30/2021 16:48:05 - INFO - __main__ - Step 19932: {'lr': 0.0004821085350844731, 'samples': 3826944, 'steps': 19931, 'loss/train': 0.1442057490348816}
+08/30/2021 16:48:05 - INFO - __main__ - Step 19933: {'lr': 0.0004821065635923902, 'samples': 3827136, 'steps': 19932, 'loss/train': 1.5246555805206299}
+08/30/2021 16:48:06 - INFO - __main__ - Step 19934: {'lr': 0.0004821045919957237, 'samples': 3827328, 'steps': 19933, 'loss/train': 1.7617788314819336}
+08/30/2021 16:48:06 - INFO - __main__ - Step 19935: {'lr': 0.00048210262029447425, 'samples': 3827520, 'steps': 19934, 'loss/train': 1.624178409576416}
+08/30/2021 16:48:08 - INFO - __main__ - Step 19936: {'lr': 0.0004821006484886431, 'samples': 3827712, 'steps': 19935, 'loss/train': 1.6159640550613403}
+08/30/2021 16:48:08 - INFO - __main__ - Step 19937: {'lr': 0.000482098676578231, 'samples': 3827904, 'steps': 19936, 'loss/train': 1.2737667560577393}
+08/30/2021 16:48:09 - INFO - __main__ - Step 19938: {'lr': 0.0004820967045632388, 'samples': 3828096, 'steps': 19937, 'loss/train': 1.4769971370697021}
+08/30/2021 16:48:09 - INFO - __main__ - Step 19939: {'lr': 0.00048209473244366737, 'samples': 3828288, 'steps': 19938, 'loss/train': 0.9654390811920166}
+08/30/2021 16:48:09 - INFO - __main__ - Step 19940: {'lr': 0.00048209276021951765, 'samples': 3828480, 'steps': 19939, 'loss/train': 1.6610724925994873}
+08/30/2021 16:48:11 - INFO - __main__ - Step 19941: {'lr': 0.00048209078789079055, 'samples': 3828672, 'steps': 19940, 'loss/train': 1.4529668092727661}
+08/30/2021 16:48:11 - INFO - __main__ - Step 19942: {'lr': 0.00048208881545748684, 'samples': 3828864, 'steps': 19941, 'loss/train': 2.073242664337158}
+08/30/2021 16:48:12 - INFO - __main__ - Step 19943: {'lr': 0.00048208684291960755, 'samples': 3829056, 'steps': 19942, 'loss/train': 1.3615379333496094}
+08/30/2021 16:48:12 - INFO - __main__ - Step 19944: {'lr': 0.0004820848702771535, 'samples': 3829248, 'steps': 19943, 'loss/train': 1.5603870153427124}
+08/30/2021 16:48:12 - INFO - __main__ - Step 19945: {'lr': 0.0004820828975301256, 'samples': 3829440, 'steps': 19944, 'loss/train': 1.638757348060608}
+08/30/2021 16:48:14 - INFO - __main__ - Step 19946: {'lr': 0.0004820809246785247, 'samples': 3829632, 'steps': 19945, 'loss/train': 1.8357417583465576}
+08/30/2021 16:48:15 - INFO - __main__ - Step 19947: {'lr': 0.00048207895172235174, 'samples': 3829824, 'steps': 19946, 'loss/train': 0.8339240550994873}
+08/30/2021 16:48:15 - INFO - __main__ - Step 19948: {'lr': 0.00048207697866160755, 'samples': 3830016, 'steps': 19947, 'loss/train': 0.9164642691612244}
+08/30/2021 16:48:15 - INFO - __main__ - Step 19949: {'lr': 0.0004820750054962931, 'samples': 3830208, 'steps': 19948, 'loss/train': 1.6671268939971924}
+08/30/2021 16:48:16 - INFO - __main__ - Step 19950: {'lr': 0.00048207303222640917, 'samples': 3830400, 'steps': 19949, 'loss/train': 1.640650749206543}
+08/30/2021 16:48:17 - INFO - __main__ - Step 19951: {'lr': 0.00048207105885195677, 'samples': 3830592, 'steps': 19950, 'loss/train': 1.5497727394104004}
+08/30/2021 16:48:18 - INFO - __main__ - Step 19952: {'lr': 0.0004820690853729367, 'samples': 3830784, 'steps': 19951, 'loss/train': 0.19414319097995758}
+08/30/2021 16:48:18 - INFO - __main__ - Step 19953: {'lr': 0.00048206711178934994, 'samples': 3830976, 'steps': 19952, 'loss/train': 1.789297342300415}
+08/30/2021 16:48:19 - INFO - __main__ - Step 19954: {'lr': 0.00048206513810119725, 'samples': 3831168, 'steps': 19953, 'loss/train': 1.8761667013168335}
+08/30/2021 16:48:19 - INFO - __main__ - Step 19955: {'lr': 0.0004820631643084796, 'samples': 3831360, 'steps': 19954, 'loss/train': 1.4396812915802002}
+08/30/2021 16:48:19 - INFO - __main__ - Step 19956: {'lr': 0.00048206119041119787, 'samples': 3831552, 'steps': 19955, 'loss/train': 1.5129131078720093}
+08/30/2021 16:48:21 - INFO - __main__ - Step 19957: {'lr': 0.000482059216409353, 'samples': 3831744, 'steps': 19956, 'loss/train': 1.8082789182662964}
+08/30/2021 16:48:22 - INFO - __main__ - Step 19958: {'lr': 0.0004820572423029458, 'samples': 3831936, 'steps': 19957, 'loss/train': 1.9943994283676147}
+08/30/2021 16:48:22 - INFO - __main__ - Step 19959: {'lr': 0.00048205526809197717, 'samples': 3832128, 'steps': 19958, 'loss/train': 1.5847307443618774}
+08/30/2021 16:48:22 - INFO - __main__ - Step 19960: {'lr': 0.000482053293776448, 'samples': 3832320, 'steps': 19959, 'loss/train': 1.7793534994125366}
+08/30/2021 16:48:23 - INFO - __main__ - Step 19961: {'lr': 0.0004820513193563593, 'samples': 3832512, 'steps': 19960, 'loss/train': 0.25694942474365234}
+08/30/2021 16:48:24 - INFO - __main__ - Step 19962: {'lr': 0.00048204934483171176, 'samples': 3832704, 'steps': 19961, 'loss/train': 1.4777239561080933}
+08/30/2021 16:48:25 - INFO - __main__ - Step 19963: {'lr': 0.0004820473702025064, 'samples': 3832896, 'steps': 19962, 'loss/train': 1.6857661008834839}
+08/30/2021 16:48:25 - INFO - __main__ - Step 19964: {'lr': 0.000482045395468744, 'samples': 3833088, 'steps': 19963, 'loss/train': 0.335319459438324}
+08/30/2021 16:48:26 - INFO - __main__ - Step 19965: {'lr': 0.0004820434206304256, 'samples': 3833280, 'steps': 19964, 'loss/train': 1.5853749513626099}
+08/30/2021 16:48:26 - INFO - __main__ - Step 19966: {'lr': 0.000482041445687552, 'samples': 3833472, 'steps': 19965, 'loss/train': 2.2551088333129883}
+08/30/2021 16:48:27 - INFO - __main__ - Step 19967: {'lr': 0.0004820394706401242, 'samples': 3833664, 'steps': 19966, 'loss/train': 0.075727179646492}
+08/30/2021 16:48:28 - INFO - __main__ - Step 19968: {'lr': 0.0004820374954881429, 'samples': 3833856, 'steps': 19967, 'loss/train': 1.5370581150054932}
+08/30/2021 16:48:28 - INFO - __main__ - Step 19969: {'lr': 0.000482035520231609, 'samples': 3834048, 'steps': 19968, 'loss/train': 1.8862011432647705}
+08/30/2021 16:48:29 - INFO - __main__ - Step 19970: {'lr': 0.00048203354487052363, 'samples': 3834240, 'steps': 19969, 'loss/train': 1.4049559831619263}
+08/30/2021 16:48:29 - INFO - __main__ - Step 19971: {'lr': 0.00048203156940488745, 'samples': 3834432, 'steps': 19970, 'loss/train': 1.6679749488830566}
+08/30/2021 16:48:29 - INFO - __main__ - Step 19972: {'lr': 0.00048202959383470144, 'samples': 3834624, 'steps': 19971, 'loss/train': 0.8248991966247559}
+08/30/2021 16:48:31 - INFO - __main__ - Step 19973: {'lr': 0.00048202761815996646, 'samples': 3834816, 'steps': 19972, 'loss/train': 1.5690691471099854}
+08/30/2021 16:48:31 - INFO - __main__ - Step 19974: {'lr': 0.0004820256423806835, 'samples': 3835008, 'steps': 19973, 'loss/train': 1.0361708402633667}
+08/30/2021 16:48:32 - INFO - __main__ - Step 19975: {'lr': 0.00048202366649685325, 'samples': 3835200, 'steps': 19974, 'loss/train': 1.9095230102539062}
+08/30/2021 16:48:32 - INFO - __main__ - Step 19976: {'lr': 0.0004820216905084768, 'samples': 3835392, 'steps': 19975, 'loss/train': 2.128371238708496}
+08/30/2021 16:48:32 - INFO - __main__ - Step 19977: {'lr': 0.00048201971441555485, 'samples': 3835584, 'steps': 19976, 'loss/train': 1.6646312475204468}
+08/30/2021 16:48:34 - INFO - __main__ - Step 19978: {'lr': 0.0004820177382180885, 'samples': 3835776, 'steps': 19977, 'loss/train': 1.3691110610961914}
+08/30/2021 16:48:34 - INFO - __main__ - Step 19979: {'lr': 0.00048201576191607843, 'samples': 3835968, 'steps': 19978, 'loss/train': 0.21969597041606903}
+08/30/2021 16:48:35 - INFO - __main__ - Step 19980: {'lr': 0.00048201378550952575, 'samples': 3836160, 'steps': 19979, 'loss/train': 1.217984914779663}
+08/30/2021 16:48:35 - INFO - __main__ - Step 19981: {'lr': 0.0004820118089984312, 'samples': 3836352, 'steps': 19980, 'loss/train': 1.7248014211654663}
+08/30/2021 16:48:35 - INFO - __main__ - Step 19982: {'lr': 0.0004820098323827957, 'samples': 3836544, 'steps': 19981, 'loss/train': 1.9163602590560913}
+08/30/2021 16:48:37 - INFO - __main__ - Step 19983: {'lr': 0.0004820078556626202, 'samples': 3836736, 'steps': 19982, 'loss/train': 1.093578815460205}
+08/30/2021 16:48:37 - INFO - __main__ - Step 19984: {'lr': 0.0004820058788379055, 'samples': 3836928, 'steps': 19983, 'loss/train': 1.651665449142456}
+08/30/2021 16:48:38 - INFO - __main__ - Step 19985: {'lr': 0.0004820039019086525, 'samples': 3837120, 'steps': 19984, 'loss/train': 1.1406774520874023}
+08/30/2021 16:48:38 - INFO - __main__ - Step 19986: {'lr': 0.00048200192487486216, 'samples': 3837312, 'steps': 19985, 'loss/train': 1.5559415817260742}
+08/30/2021 16:48:38 - INFO - __main__ - Step 19987: {'lr': 0.00048199994773653535, 'samples': 3837504, 'steps': 19986, 'loss/train': 1.3614102602005005}
+08/30/2021 16:48:40 - INFO - __main__ - Step 19988: {'lr': 0.0004819979704936729, 'samples': 3837696, 'steps': 19987, 'loss/train': 1.2424564361572266}
+08/30/2021 16:48:40 - INFO - __main__ - Step 19989: {'lr': 0.00048199599314627576, 'samples': 3837888, 'steps': 19988, 'loss/train': 1.5290501117706299}
+08/30/2021 16:48:41 - INFO - __main__ - Step 19990: {'lr': 0.00048199401569434477, 'samples': 3838080, 'steps': 19989, 'loss/train': 2.1153290271759033}
+08/30/2021 16:48:41 - INFO - __main__ - Step 19991: {'lr': 0.00048199203813788086, 'samples': 3838272, 'steps': 19990, 'loss/train': 1.7672927379608154}
+08/30/2021 16:48:42 - INFO - __main__ - Step 19992: {'lr': 0.00048199006047688496, 'samples': 3838464, 'steps': 19991, 'loss/train': 1.7383555173873901}
+08/30/2021 16:48:43 - INFO - __main__ - Step 19993: {'lr': 0.0004819880827113579, 'samples': 3838656, 'steps': 19992, 'loss/train': 1.8264869451522827}
+08/30/2021 16:48:44 - INFO - __main__ - Step 19994: {'lr': 0.0004819861048413006, 'samples': 3838848, 'steps': 19993, 'loss/train': 1.6042386293411255}
+08/30/2021 16:48:44 - INFO - __main__ - Step 19995: {'lr': 0.00048198412686671394, 'samples': 3839040, 'steps': 19994, 'loss/train': 0.16026639938354492}
+08/30/2021 16:48:45 - INFO - __main__ - Step 19996: {'lr': 0.0004819821487875988, 'samples': 3839232, 'steps': 19995, 'loss/train': 0.062003571540117264}
+08/30/2021 16:48:45 - INFO - __main__ - Step 19997: {'lr': 0.0004819801706039561, 'samples': 3839424, 'steps': 19996, 'loss/train': 1.302549123764038}
+08/30/2021 16:48:45 - INFO - __main__ - Step 19998: {'lr': 0.0004819781923157867, 'samples': 3839616, 'steps': 19997, 'loss/train': 1.3895676136016846}
+08/30/2021 16:48:47 - INFO - __main__ - Step 19999: {'lr': 0.00048197621392309154, 'samples': 3839808, 'steps': 19998, 'loss/train': 1.644120454788208}
+08/30/2021 16:48:47 - INFO - __main__ - Step 20000: {'lr': 0.00048197423542587143, 'samples': 3840000, 'steps': 19999, 'loss/train': 1.5134613513946533}
+08/30/2021 16:48:48 - INFO - __main__ - Step 20001: {'lr': 0.0004819722568241274, 'samples': 3840192, 'steps': 20000, 'loss/train': 0.9177433848381042}
+08/30/2021 16:48:48 - INFO - __main__ - Step 20002: {'lr': 0.0004819702781178601, 'samples': 3840384, 'steps': 20001, 'loss/train': 1.7758409976959229}
+08/30/2021 16:48:48 - INFO - __main__ - Step 20003: {'lr': 0.00048196829930707066, 'samples': 3840576, 'steps': 20002, 'loss/train': 1.3711930513381958}
+08/30/2021 16:48:50 - INFO - __main__ - Step 20004: {'lr': 0.0004819663203917599, 'samples': 3840768, 'steps': 20003, 'loss/train': 1.7435840368270874}
+08/30/2021 16:48:51 - INFO - __main__ - Step 20005: {'lr': 0.0004819643413719287, 'samples': 3840960, 'steps': 20004, 'loss/train': 1.8693407773971558}
+08/30/2021 16:48:51 - INFO - __main__ - Step 20006: {'lr': 0.0004819623622475779, 'samples': 3841152, 'steps': 20005, 'loss/train': 1.7306019067764282}
+08/30/2021 16:48:51 - INFO - __main__ - Step 20007: {'lr': 0.00048196038301870847, 'samples': 3841344, 'steps': 20006, 'loss/train': 1.9947823286056519}
+08/30/2021 16:48:52 - INFO - __main__ - Step 20008: {'lr': 0.0004819584036853212, 'samples': 3841536, 'steps': 20007, 'loss/train': 1.286116123199463}
+08/30/2021 16:48:52 - INFO - __main__ - Step 20009: {'lr': 0.00048195642424741716, 'samples': 3841728, 'steps': 20008, 'loss/train': 1.6496145725250244}
+08/30/2021 16:48:54 - INFO - __main__ - Step 20010: {'lr': 0.00048195444470499704, 'samples': 3841920, 'steps': 20009, 'loss/train': 1.3488520383834839}
+08/30/2021 16:48:54 - INFO - __main__ - Step 20011: {'lr': 0.0004819524650580619, 'samples': 3842112, 'steps': 20010, 'loss/train': 1.5523463487625122}
+08/30/2021 16:48:54 - INFO - __main__ - Step 20012: {'lr': 0.0004819504853066126, 'samples': 3842304, 'steps': 20011, 'loss/train': 2.034449577331543}
+08/30/2021 16:48:55 - INFO - __main__ - Step 20013: {'lr': 0.0004819485054506498, 'samples': 3842496, 'steps': 20012, 'loss/train': 1.734606146812439}
+08/30/2021 16:48:55 - INFO - __main__ - Step 20014: {'lr': 0.00048194652549017484, 'samples': 3842688, 'steps': 20013, 'loss/train': 1.9898678064346313}
+08/30/2021 16:48:57 - INFO - __main__ - Step 20015: {'lr': 0.0004819445454251882, 'samples': 3842880, 'steps': 20014, 'loss/train': 0.9438971877098083}
+08/30/2021 16:48:57 - INFO - __main__ - Step 20016: {'lr': 0.0004819425652556909, 'samples': 3843072, 'steps': 20015, 'loss/train': 2.579280376434326}
+08/30/2021 16:48:58 - INFO - __main__ - Step 20017: {'lr': 0.0004819405849816839, 'samples': 3843264, 'steps': 20016, 'loss/train': 1.5702136754989624}
+08/30/2021 16:48:58 - INFO - __main__ - Step 20018: {'lr': 0.00048193860460316805, 'samples': 3843456, 'steps': 20017, 'loss/train': 0.5301432609558105}
+08/30/2021 16:48:58 - INFO - __main__ - Step 20019: {'lr': 0.00048193662412014427, 'samples': 3843648, 'steps': 20018, 'loss/train': 1.7974170446395874}
+08/30/2021 16:49:00 - INFO - __main__ - Step 20020: {'lr': 0.0004819346435326134, 'samples': 3843840, 'steps': 20019, 'loss/train': 1.2705624103546143}
+08/30/2021 16:49:00 - INFO - __main__ - Step 20021: {'lr': 0.00048193266284057634, 'samples': 3844032, 'steps': 20020, 'loss/train': 1.3145122528076172}
+08/30/2021 16:49:01 - INFO - __main__ - Step 20022: {'lr': 0.0004819306820440341, 'samples': 3844224, 'steps': 20021, 'loss/train': 1.5394717454910278}
+08/30/2021 16:49:01 - INFO - __main__ - Step 20023: {'lr': 0.0004819287011429874, 'samples': 3844416, 'steps': 20022, 'loss/train': 1.6912767887115479}
+08/30/2021 16:49:01 - INFO - __main__ - Step 20024: {'lr': 0.0004819267201374372, 'samples': 3844608, 'steps': 20023, 'loss/train': 1.8691939115524292}
+08/30/2021 16:49:03 - INFO - __main__ - Step 20025: {'lr': 0.0004819247390273844, 'samples': 3844800, 'steps': 20024, 'loss/train': 1.7553164958953857}
+08/30/2021 16:49:03 - INFO - __main__ - Step 20026: {'lr': 0.00048192275781282993, 'samples': 3844992, 'steps': 20025, 'loss/train': 1.6538194417953491}
+08/30/2021 16:49:04 - INFO - __main__ - Step 20027: {'lr': 0.00048192077649377455, 'samples': 3845184, 'steps': 20026, 'loss/train': 2.2352724075317383}
+08/30/2021 16:49:04 - INFO - __main__ - Step 20028: {'lr': 0.0004819187950702193, 'samples': 3845376, 'steps': 20027, 'loss/train': 1.1791073083877563}
+08/30/2021 16:49:04 - INFO - __main__ - Step 20029: {'lr': 0.00048191681354216504, 'samples': 3845568, 'steps': 20028, 'loss/train': 1.2517369985580444}
+08/30/2021 16:49:06 - INFO - __main__ - Step 20030: {'lr': 0.0004819148319096126, 'samples': 3845760, 'steps': 20029, 'loss/train': 1.0241451263427734}
+08/30/2021 16:49:06 - INFO - __main__ - Step 20031: {'lr': 0.00048191285017256297, 'samples': 3845952, 'steps': 20030, 'loss/train': 1.7977837324142456}
+08/30/2021 16:49:07 - INFO - __main__ - Step 20032: {'lr': 0.00048191086833101695, 'samples': 3846144, 'steps': 20031, 'loss/train': 1.4658101797103882}
+08/30/2021 16:49:07 - INFO - __main__ - Step 20033: {'lr': 0.00048190888638497553, 'samples': 3846336, 'steps': 20032, 'loss/train': 1.695029616355896}
+08/30/2021 16:49:07 - INFO - __main__ - Step 20034: {'lr': 0.00048190690433443946, 'samples': 3846528, 'steps': 20033, 'loss/train': 1.1877739429473877}
+08/30/2021 16:49:08 - INFO - __main__ - Step 20035: {'lr': 0.0004819049221794097, 'samples': 3846720, 'steps': 20034, 'loss/train': 0.08224710822105408}
+08/30/2021 16:49:09 - INFO - __main__ - Step 20036: {'lr': 0.0004819029399198873, 'samples': 3846912, 'steps': 20035, 'loss/train': 1.4298524856567383}
+08/30/2021 16:49:10 - INFO - __main__ - Step 20037: {'lr': 0.0004819009575558729, 'samples': 3847104, 'steps': 20036, 'loss/train': 1.6943835020065308}
+08/30/2021 16:49:10 - INFO - __main__ - Step 20038: {'lr': 0.0004818989750873676, 'samples': 3847296, 'steps': 20037, 'loss/train': 0.03754433989524841}
+08/30/2021 16:49:11 - INFO - __main__ - Step 20039: {'lr': 0.00048189699251437206, 'samples': 3847488, 'steps': 20038, 'loss/train': 1.9434560537338257}
+08/30/2021 16:49:11 - INFO - __main__ - Step 20040: {'lr': 0.0004818950098368874, 'samples': 3847680, 'steps': 20039, 'loss/train': 1.8073323965072632}
+08/30/2021 16:49:11 - INFO - __main__ - Step 20041: {'lr': 0.00048189302705491446, 'samples': 3847872, 'steps': 20040, 'loss/train': 1.7424969673156738}
+08/30/2021 16:49:13 - INFO - __main__ - Step 20042: {'lr': 0.000481891044168454, 'samples': 3848064, 'steps': 20041, 'loss/train': 1.8437080383300781}
+08/30/2021 16:49:13 - INFO - __main__ - Step 20043: {'lr': 0.00048188906117750706, 'samples': 3848256, 'steps': 20042, 'loss/train': 0.10665156692266464}
+08/30/2021 16:49:14 - INFO - __main__ - Step 20044: {'lr': 0.00048188707808207457, 'samples': 3848448, 'steps': 20043, 'loss/train': 1.8833436965942383}
+08/30/2021 16:49:14 - INFO - __main__ - Step 20045: {'lr': 0.00048188509488215724, 'samples': 3848640, 'steps': 20044, 'loss/train': 1.396911859512329}
+08/30/2021 16:49:14 - INFO - __main__ - Step 20046: {'lr': 0.0004818831115777561, 'samples': 3848832, 'steps': 20045, 'loss/train': 1.676553726196289}
+08/30/2021 16:49:16 - INFO - __main__ - Step 20047: {'lr': 0.00048188112816887203, 'samples': 3849024, 'steps': 20046, 'loss/train': 1.7872953414916992}
+08/30/2021 16:49:16 - INFO - __main__ - Step 20048: {'lr': 0.0004818791446555059, 'samples': 3849216, 'steps': 20047, 'loss/train': 1.4919394254684448}
+08/30/2021 16:49:17 - INFO - __main__ - Step 20049: {'lr': 0.00048187716103765854, 'samples': 3849408, 'steps': 20048, 'loss/train': 0.8091785311698914}
+08/30/2021 16:49:17 - INFO - __main__ - Step 20050: {'lr': 0.0004818751773153309, 'samples': 3849600, 'steps': 20049, 'loss/train': 0.6129899621009827}
+08/30/2021 16:49:17 - INFO - __main__ - Step 20051: {'lr': 0.000481873193488524, 'samples': 3849792, 'steps': 20050, 'loss/train': 1.6006039381027222}
+08/30/2021 16:49:19 - INFO - __main__ - Step 20052: {'lr': 0.0004818712095572385, 'samples': 3849984, 'steps': 20051, 'loss/train': 1.1631252765655518}
+08/30/2021 16:49:19 - INFO - __main__ - Step 20053: {'lr': 0.0004818692255214755, 'samples': 3850176, 'steps': 20052, 'loss/train': 1.6821677684783936}
+08/30/2021 16:49:20 - INFO - __main__ - Step 20054: {'lr': 0.00048186724138123577, 'samples': 3850368, 'steps': 20053, 'loss/train': 1.827529788017273}
+08/30/2021 16:49:20 - INFO - __main__ - Step 20055: {'lr': 0.00048186525713652024, 'samples': 3850560, 'steps': 20054, 'loss/train': 1.3900905847549438}
+08/30/2021 16:49:20 - INFO - __main__ - Step 20056: {'lr': 0.0004818632727873298, 'samples': 3850752, 'steps': 20055, 'loss/train': 1.4969857931137085}
+08/30/2021 16:49:22 - INFO - __main__ - Step 20057: {'lr': 0.00048186128833366536, 'samples': 3850944, 'steps': 20056, 'loss/train': 1.184066653251648}
+08/30/2021 16:49:23 - INFO - __main__ - Step 20058: {'lr': 0.0004818593037755278, 'samples': 3851136, 'steps': 20057, 'loss/train': 1.6948479413986206}
+08/30/2021 16:49:23 - INFO - __main__ - Step 20059: {'lr': 0.000481857319112918, 'samples': 3851328, 'steps': 20058, 'loss/train': 1.9170730113983154}
+08/30/2021 16:49:23 - INFO - __main__ - Step 20060: {'lr': 0.0004818553343458368, 'samples': 3851520, 'steps': 20059, 'loss/train': 1.23885178565979}
+08/30/2021 16:49:24 - INFO - __main__ - Step 20061: {'lr': 0.00048185334947428525, 'samples': 3851712, 'steps': 20060, 'loss/train': 2.0625462532043457}
+08/30/2021 16:49:24 - INFO - __main__ - Step 20062: {'lr': 0.0004818513644982642, 'samples': 3851904, 'steps': 20061, 'loss/train': 1.9079039096832275}
+08/30/2021 16:49:26 - INFO - __main__ - Step 20063: {'lr': 0.0004818493794177744, 'samples': 3852096, 'steps': 20062, 'loss/train': 1.435896635055542}
+08/30/2021 16:49:26 - INFO - __main__ - Step 20064: {'lr': 0.00048184739423281695, 'samples': 3852288, 'steps': 20063, 'loss/train': 1.9172650575637817}
+08/30/2021 16:49:27 - INFO - __main__ - Step 20065: {'lr': 0.00048184540894339256, 'samples': 3852480, 'steps': 20064, 'loss/train': 0.9635215401649475}
+08/30/2021 16:49:27 - INFO - __main__ - Step 20066: {'lr': 0.00048184342354950225, 'samples': 3852672, 'steps': 20065, 'loss/train': 1.7241082191467285}
+08/30/2021 16:49:27 - INFO - __main__ - Step 20067: {'lr': 0.00048184143805114684, 'samples': 3852864, 'steps': 20066, 'loss/train': 1.6395256519317627}
+08/30/2021 16:49:29 - INFO - __main__ - Step 20068: {'lr': 0.00048183945244832725, 'samples': 3853056, 'steps': 20067, 'loss/train': 1.6814159154891968}
+08/30/2021 16:49:29 - INFO - __main__ - Step 20069: {'lr': 0.00048183746674104446, 'samples': 3853248, 'steps': 20068, 'loss/train': 1.5684231519699097}
+08/30/2021 16:49:29 - INFO - __main__ - Step 20070: {'lr': 0.00048183548092929916, 'samples': 3853440, 'steps': 20069, 'loss/train': 1.3256232738494873}
+08/30/2021 16:49:30 - INFO - __main__ - Step 20071: {'lr': 0.0004818334950130925, 'samples': 3853632, 'steps': 20070, 'loss/train': 1.4391560554504395}
+08/30/2021 16:49:30 - INFO - __main__ - Step 20072: {'lr': 0.00048183150899242514, 'samples': 3853824, 'steps': 20071, 'loss/train': 1.5120980739593506}
+08/30/2021 16:49:32 - INFO - __main__ - Step 20073: {'lr': 0.0004818295228672981, 'samples': 3854016, 'steps': 20072, 'loss/train': 1.8095577955245972}
+08/30/2021 16:49:32 - INFO - __main__ - Step 20074: {'lr': 0.0004818275366377123, 'samples': 3854208, 'steps': 20073, 'loss/train': 1.1560922861099243}
+08/30/2021 16:49:32 - INFO - __main__ - Step 20075: {'lr': 0.00048182555030366854, 'samples': 3854400, 'steps': 20074, 'loss/train': 1.2336541414260864}
+08/30/2021 16:49:33 - INFO - __main__ - Step 20076: {'lr': 0.0004818235638651678, 'samples': 3854592, 'steps': 20075, 'loss/train': 1.116799235343933}
+08/30/2021 16:49:33 - INFO - __main__ - Step 20077: {'lr': 0.0004818215773222109, 'samples': 3854784, 'steps': 20076, 'loss/train': 0.4001154601573944}
+08/30/2021 16:49:35 - INFO - __main__ - Step 20078: {'lr': 0.0004818195906747988, 'samples': 3854976, 'steps': 20077, 'loss/train': 2.4976325035095215}
+08/30/2021 16:49:35 - INFO - __main__ - Step 20079: {'lr': 0.0004818176039229324, 'samples': 3855168, 'steps': 20078, 'loss/train': 1.6350609064102173}
+08/30/2021 16:49:35 - INFO - __main__ - Step 20080: {'lr': 0.0004818156170666125, 'samples': 3855360, 'steps': 20079, 'loss/train': 1.3892173767089844}
+08/30/2021 16:49:36 - INFO - __main__ - Step 20081: {'lr': 0.0004818136301058401, 'samples': 3855552, 'steps': 20080, 'loss/train': 1.1264094114303589}
+08/30/2021 16:49:36 - INFO - __main__ - Step 20082: {'lr': 0.0004818116430406161, 'samples': 3855744, 'steps': 20081, 'loss/train': 2.3538107872009277}
+08/30/2021 16:49:36 - INFO - __main__ - Step 20083: {'lr': 0.00048180965587094125, 'samples': 3855936, 'steps': 20082, 'loss/train': 1.9352130889892578}
+08/30/2021 16:49:38 - INFO - __main__ - Step 20084: {'lr': 0.00048180766859681664, 'samples': 3856128, 'steps': 20083, 'loss/train': 1.302859902381897}
+08/30/2021 16:49:39 - INFO - __main__ - Step 20085: {'lr': 0.000481805681218243, 'samples': 3856320, 'steps': 20084, 'loss/train': 1.5741057395935059}
+08/30/2021 16:49:39 - INFO - __main__ - Step 20086: {'lr': 0.0004818036937352214, 'samples': 3856512, 'steps': 20085, 'loss/train': 2.0826728343963623}
+08/30/2021 16:49:39 - INFO - __main__ - Step 20087: {'lr': 0.0004818017061477525, 'samples': 3856704, 'steps': 20086, 'loss/train': 1.552943468093872}
+08/30/2021 16:49:40 - INFO - __main__ - Step 20088: {'lr': 0.00048179971845583734, 'samples': 3856896, 'steps': 20087, 'loss/train': 1.6637585163116455}
+08/30/2021 16:49:42 - INFO - __main__ - Step 20089: {'lr': 0.00048179773065947683, 'samples': 3857088, 'steps': 20088, 'loss/train': 1.3537242412567139}
+08/30/2021 16:49:42 - INFO - __main__ - Step 20090: {'lr': 0.0004817957427586719, 'samples': 3857280, 'steps': 20089, 'loss/train': 0.22368521988391876}
+08/30/2021 16:49:42 - INFO - __main__ - Step 20091: {'lr': 0.00048179375475342333, 'samples': 3857472, 'steps': 20090, 'loss/train': 0.22531534731388092}
+08/30/2021 16:49:43 - INFO - __main__ - Step 20092: {'lr': 0.00048179176664373214, 'samples': 3857664, 'steps': 20091, 'loss/train': 1.5876214504241943}
+08/30/2021 16:49:43 - INFO - __main__ - Step 20093: {'lr': 0.0004817897784295991, 'samples': 3857856, 'steps': 20092, 'loss/train': 1.9929802417755127}
+08/30/2021 16:49:43 - INFO - __main__ - Step 20094: {'lr': 0.0004817877901110251, 'samples': 3858048, 'steps': 20093, 'loss/train': 1.6999971866607666}
+08/30/2021 16:49:45 - INFO - __main__ - Step 20095: {'lr': 0.0004817858016880112, 'samples': 3858240, 'steps': 20094, 'loss/train': 1.4086908102035522}
+08/30/2021 16:49:45 - INFO - __main__ - Step 20096: {'lr': 0.0004817838131605582, 'samples': 3858432, 'steps': 20095, 'loss/train': 1.7002785205841064}
+08/30/2021 16:49:46 - INFO - __main__ - Step 20097: {'lr': 0.00048178182452866694, 'samples': 3858624, 'steps': 20096, 'loss/train': 0.9283069968223572}
+08/30/2021 16:49:46 - INFO - __main__ - Step 20098: {'lr': 0.0004817798357923384, 'samples': 3858816, 'steps': 20097, 'loss/train': 1.4377996921539307}
+08/30/2021 16:49:46 - INFO - __main__ - Step 20099: {'lr': 0.00048177784695157335, 'samples': 3859008, 'steps': 20098, 'loss/train': 1.0285416841506958}
+08/30/2021 16:49:48 - INFO - __main__ - Step 20100: {'lr': 0.00048177585800637286, 'samples': 3859200, 'steps': 20099, 'loss/train': 0.9273505210876465}
+08/30/2021 16:49:48 - INFO - __main__ - Step 20101: {'lr': 0.00048177386895673774, 'samples': 3859392, 'steps': 20100, 'loss/train': 1.3331303596496582}
+08/30/2021 16:49:49 - INFO - __main__ - Step 20102: {'lr': 0.0004817718798026689, 'samples': 3859584, 'steps': 20101, 'loss/train': 1.147251844406128}
+08/30/2021 16:49:49 - INFO - __main__ - Step 20103: {'lr': 0.0004817698905441672, 'samples': 3859776, 'steps': 20102, 'loss/train': 1.8079439401626587}
+08/30/2021 16:49:50 - INFO - __main__ - Step 20104: {'lr': 0.0004817679011812336, 'samples': 3859968, 'steps': 20103, 'loss/train': 2.1963179111480713}
+08/30/2021 16:49:50 - INFO - __main__ - Step 20105: {'lr': 0.00048176591171386884, 'samples': 3860160, 'steps': 20104, 'loss/train': 1.6470838785171509}
+08/30/2021 16:49:51 - INFO - __main__ - Step 20106: {'lr': 0.0004817639221420741, 'samples': 3860352, 'steps': 20105, 'loss/train': 1.1575138568878174}
+08/30/2021 16:49:52 - INFO - __main__ - Step 20107: {'lr': 0.00048176193246585, 'samples': 3860544, 'steps': 20106, 'loss/train': 1.32097327709198}
+08/30/2021 16:49:52 - INFO - __main__ - Step 20108: {'lr': 0.00048175994268519765, 'samples': 3860736, 'steps': 20107, 'loss/train': 1.5724048614501953}
+08/30/2021 16:49:52 - INFO - __main__ - Step 20109: {'lr': 0.00048175795280011775, 'samples': 3860928, 'steps': 20108, 'loss/train': 2.2219698429107666}
+08/30/2021 16:49:53 - INFO - __main__ - Step 20110: {'lr': 0.00048175596281061135, 'samples': 3861120, 'steps': 20109, 'loss/train': 1.98557448387146}
+08/30/2021 16:49:55 - INFO - __main__ - Step 20111: {'lr': 0.00048175397271667925, 'samples': 3861312, 'steps': 20110, 'loss/train': 1.6294634342193604}
+08/30/2021 16:49:55 - INFO - __main__ - Step 20112: {'lr': 0.00048175198251832244, 'samples': 3861504, 'steps': 20111, 'loss/train': 1.6430479288101196}
+08/30/2021 16:49:56 - INFO - __main__ - Step 20113: {'lr': 0.00048174999221554173, 'samples': 3861696, 'steps': 20112, 'loss/train': 1.6404865980148315}
+08/30/2021 16:49:56 - INFO - __main__ - Step 20114: {'lr': 0.000481748001808338, 'samples': 3861888, 'steps': 20113, 'loss/train': 1.6970770359039307}
+08/30/2021 16:49:56 - INFO - __main__ - Step 20115: {'lr': 0.00048174601129671223, 'samples': 3862080, 'steps': 20114, 'loss/train': 1.7774577140808105}
+08/30/2021 16:49:58 - INFO - __main__ - Step 20116: {'lr': 0.00048174402068066534, 'samples': 3862272, 'steps': 20115, 'loss/train': 1.4758708477020264}
+08/30/2021 16:49:58 - INFO - __main__ - Step 20117: {'lr': 0.0004817420299601981, 'samples': 3862464, 'steps': 20116, 'loss/train': 1.9957894086837769}
+08/30/2021 16:49:59 - INFO - __main__ - Step 20118: {'lr': 0.0004817400391353115, 'samples': 3862656, 'steps': 20117, 'loss/train': 1.3740090131759644}
+08/30/2021 16:49:59 - INFO - __main__ - Step 20119: {'lr': 0.00048173804820600646, 'samples': 3862848, 'steps': 20118, 'loss/train': 2.055910110473633}
+08/30/2021 16:49:59 - INFO - __main__ - Step 20120: {'lr': 0.0004817360571722838, 'samples': 3863040, 'steps': 20119, 'loss/train': 1.3270663022994995}
+08/30/2021 16:50:01 - INFO - __main__ - Step 20121: {'lr': 0.00048173406603414445, 'samples': 3863232, 'steps': 20120, 'loss/train': 1.580013632774353}
+08/30/2021 16:50:01 - INFO - __main__ - Step 20122: {'lr': 0.00048173207479158933, 'samples': 3863424, 'steps': 20121, 'loss/train': 1.3592381477355957}
+08/30/2021 16:50:02 - INFO - __main__ - Step 20123: {'lr': 0.0004817300834446192, 'samples': 3863616, 'steps': 20122, 'loss/train': 1.9252469539642334}
+08/30/2021 16:50:02 - INFO - __main__ - Step 20124: {'lr': 0.0004817280919932352, 'samples': 3863808, 'steps': 20123, 'loss/train': 1.3935565948486328}
+08/30/2021 16:50:02 - INFO - __main__ - Step 20125: {'lr': 0.000481726100437438, 'samples': 3864000, 'steps': 20124, 'loss/train': 1.8088167905807495}
+08/30/2021 16:50:04 - INFO - __main__ - Step 20126: {'lr': 0.00048172410877722865, 'samples': 3864192, 'steps': 20125, 'loss/train': 1.7946019172668457}
+08/30/2021 16:50:04 - INFO - __main__ - Step 20127: {'lr': 0.00048172211701260807, 'samples': 3864384, 'steps': 20126, 'loss/train': 0.818877100944519}
+08/30/2021 16:50:05 - INFO - __main__ - Step 20128: {'lr': 0.0004817201251435769, 'samples': 3864576, 'steps': 20127, 'loss/train': 1.384813666343689}
+08/30/2021 16:50:05 - INFO - __main__ - Step 20129: {'lr': 0.00048171813317013633, 'samples': 3864768, 'steps': 20128, 'loss/train': 1.5953658819198608}
+08/30/2021 16:50:05 - INFO - __main__ - Step 20130: {'lr': 0.00048171614109228714, 'samples': 3864960, 'steps': 20129, 'loss/train': 1.6424446105957031}
+08/30/2021 16:50:07 - INFO - __main__ - Step 20131: {'lr': 0.0004817141489100302, 'samples': 3865152, 'steps': 20130, 'loss/train': 1.778563141822815}
+08/30/2021 16:50:07 - INFO - __main__ - Step 20132: {'lr': 0.0004817121566233665, 'samples': 3865344, 'steps': 20131, 'loss/train': 1.9810020923614502}
+08/30/2021 16:50:08 - INFO - __main__ - Step 20133: {'lr': 0.0004817101642322968, 'samples': 3865536, 'steps': 20132, 'loss/train': 0.08221045136451721}
+08/30/2021 16:50:08 - INFO - __main__ - Step 20134: {'lr': 0.00048170817173682215, 'samples': 3865728, 'steps': 20133, 'loss/train': 1.5096927881240845}
+08/30/2021 16:50:08 - INFO - __main__ - Step 20135: {'lr': 0.00048170617913694333, 'samples': 3865920, 'steps': 20134, 'loss/train': 2.2990646362304688}
+08/30/2021 16:50:10 - INFO - __main__ - Step 20136: {'lr': 0.00048170418643266125, 'samples': 3866112, 'steps': 20135, 'loss/train': 1.6849663257598877}
+08/30/2021 16:50:10 - INFO - __main__ - Step 20137: {'lr': 0.00048170219362397685, 'samples': 3866304, 'steps': 20136, 'loss/train': 1.553839921951294}
+08/30/2021 16:50:11 - INFO - __main__ - Step 20138: {'lr': 0.00048170020071089105, 'samples': 3866496, 'steps': 20137, 'loss/train': 1.7705405950546265}
+08/30/2021 16:50:11 - INFO - __main__ - Step 20139: {'lr': 0.00048169820769340476, 'samples': 3866688, 'steps': 20138, 'loss/train': 0.19859115779399872}
+08/30/2021 16:50:11 - INFO - __main__ - Step 20140: {'lr': 0.0004816962145715188, 'samples': 3866880, 'steps': 20139, 'loss/train': 1.2331286668777466}
+08/30/2021 16:50:13 - INFO - __main__ - Step 20141: {'lr': 0.00048169422134523404, 'samples': 3867072, 'steps': 20140, 'loss/train': 1.1087123155593872}
+08/30/2021 16:50:13 - INFO - __main__ - Step 20142: {'lr': 0.0004816922280145515, 'samples': 3867264, 'steps': 20141, 'loss/train': 1.4092648029327393}
+08/30/2021 16:50:14 - INFO - __main__ - Step 20143: {'lr': 0.00048169023457947195, 'samples': 3867456, 'steps': 20142, 'loss/train': 1.1133297681808472}
+08/30/2021 16:50:14 - INFO - __main__ - Step 20144: {'lr': 0.0004816882410399964, 'samples': 3867648, 'steps': 20143, 'loss/train': 1.3509678840637207}
+08/30/2021 16:50:14 - INFO - __main__ - Step 20145: {'lr': 0.00048168624739612577, 'samples': 3867840, 'steps': 20144, 'loss/train': 1.8391437530517578}
+08/30/2021 16:50:16 - INFO - __main__ - Step 20146: {'lr': 0.0004816842536478608, 'samples': 3868032, 'steps': 20145, 'loss/train': 3.161020517349243}
+08/30/2021 16:50:16 - INFO - __main__ - Step 20147: {'lr': 0.00048168225979520254, 'samples': 3868224, 'steps': 20146, 'loss/train': 2.0961363315582275}
+08/30/2021 16:50:17 - INFO - __main__ - Step 20148: {'lr': 0.0004816802658381518, 'samples': 3868416, 'steps': 20147, 'loss/train': 1.7573124170303345}
+08/30/2021 16:50:17 - INFO - __main__ - Step 20149: {'lr': 0.00048167827177670946, 'samples': 3868608, 'steps': 20148, 'loss/train': 1.8705545663833618}
+08/30/2021 16:50:18 - INFO - __main__ - Step 20150: {'lr': 0.0004816762776108765, 'samples': 3868800, 'steps': 20149, 'loss/train': 1.470387578010559}
+08/30/2021 16:50:18 - INFO - __main__ - Step 20151: {'lr': 0.0004816742833406538, 'samples': 3868992, 'steps': 20150, 'loss/train': 2.1693620681762695}
+08/30/2021 16:50:19 - INFO - __main__ - Step 20152: {'lr': 0.0004816722889660423, 'samples': 3869184, 'steps': 20151, 'loss/train': 1.0245689153671265}
+08/30/2021 16:50:20 - INFO - __main__ - Step 20153: {'lr': 0.00048167029448704273, 'samples': 3869376, 'steps': 20152, 'loss/train': 1.4094831943511963}
+08/30/2021 16:50:20 - INFO - __main__ - Step 20154: {'lr': 0.00048166829990365615, 'samples': 3869568, 'steps': 20153, 'loss/train': 1.484419822692871}
+08/30/2021 16:50:20 - INFO - __main__ - Step 20155: {'lr': 0.0004816663052158834, 'samples': 3869760, 'steps': 20154, 'loss/train': 1.6280980110168457}
+08/30/2021 16:50:21 - INFO - __main__ - Step 20156: {'lr': 0.0004816643104237254, 'samples': 3869952, 'steps': 20155, 'loss/train': 1.244726538658142}
+08/30/2021 16:50:22 - INFO - __main__ - Step 20157: {'lr': 0.00048166231552718305, 'samples': 3870144, 'steps': 20156, 'loss/train': 1.5656678676605225}
+08/30/2021 16:50:23 - INFO - __main__ - Step 20158: {'lr': 0.0004816603205262572, 'samples': 3870336, 'steps': 20157, 'loss/train': 1.7199552059173584}
+08/30/2021 16:50:23 - INFO - __main__ - Step 20159: {'lr': 0.0004816583254209488, 'samples': 3870528, 'steps': 20158, 'loss/train': 1.8591266870498657}
+08/30/2021 16:50:23 - INFO - __main__ - Step 20160: {'lr': 0.00048165633021125874, 'samples': 3870720, 'steps': 20159, 'loss/train': 1.7345173358917236}
+08/30/2021 16:50:24 - INFO - __main__ - Step 20161: {'lr': 0.0004816543348971879, 'samples': 3870912, 'steps': 20160, 'loss/train': 1.5919828414916992}
+08/30/2021 16:50:25 - INFO - __main__ - Step 20162: {'lr': 0.0004816523394787372, 'samples': 3871104, 'steps': 20161, 'loss/train': 1.9427335262298584}
+08/30/2021 16:50:26 - INFO - __main__ - Step 20163: {'lr': 0.00048165034395590756, 'samples': 3871296, 'steps': 20162, 'loss/train': 2.0290613174438477}
+08/30/2021 16:50:26 - INFO - __main__ - Step 20164: {'lr': 0.0004816483483286998, 'samples': 3871488, 'steps': 20163, 'loss/train': 0.8475186228752136}
+08/30/2021 16:50:26 - INFO - __main__ - Step 20165: {'lr': 0.0004816463525971149, 'samples': 3871680, 'steps': 20164, 'loss/train': 1.5292781591415405}
+08/30/2021 16:50:27 - INFO - __main__ - Step 20166: {'lr': 0.0004816443567611537, 'samples': 3871872, 'steps': 20165, 'loss/train': 1.7337758541107178}
+08/30/2021 16:50:29 - INFO - __main__ - Step 20167: {'lr': 0.00048164236082081713, 'samples': 3872064, 'steps': 20166, 'loss/train': 1.8352793455123901}
+08/30/2021 16:50:29 - INFO - __main__ - Step 20168: {'lr': 0.00048164036477610616, 'samples': 3872256, 'steps': 20167, 'loss/train': 1.8482677936553955}
+08/30/2021 16:50:30 - INFO - __main__ - Step 20169: {'lr': 0.00048163836862702154, 'samples': 3872448, 'steps': 20168, 'loss/train': 0.8686457276344299}
+08/30/2021 16:50:30 - INFO - __main__ - Step 20170: {'lr': 0.0004816363723735643, 'samples': 3872640, 'steps': 20169, 'loss/train': 1.7034279108047485}
+08/30/2021 16:50:30 - INFO - __main__ - Step 20171: {'lr': 0.00048163437601573525, 'samples': 3872832, 'steps': 20170, 'loss/train': 0.10003358125686646}
+08/30/2021 16:50:32 - INFO - __main__ - Step 20172: {'lr': 0.00048163237955353526, 'samples': 3873024, 'steps': 20171, 'loss/train': 1.6900075674057007}
+08/30/2021 16:50:32 - INFO - __main__ - Step 20173: {'lr': 0.00048163038298696537, 'samples': 3873216, 'steps': 20172, 'loss/train': 1.5002872943878174}
+08/30/2021 16:50:33 - INFO - __main__ - Step 20174: {'lr': 0.00048162838631602643, 'samples': 3873408, 'steps': 20173, 'loss/train': 1.8476632833480835}
+08/30/2021 16:50:33 - INFO - __main__ - Step 20175: {'lr': 0.00048162638954071926, 'samples': 3873600, 'steps': 20174, 'loss/train': 1.378610372543335}
+08/30/2021 16:50:33 - INFO - __main__ - Step 20176: {'lr': 0.0004816243926610448, 'samples': 3873792, 'steps': 20175, 'loss/train': 1.5293242931365967}
+08/30/2021 16:50:35 - INFO - __main__ - Step 20177: {'lr': 0.000481622395677004, 'samples': 3873984, 'steps': 20176, 'loss/train': 1.675130844116211}
+08/30/2021 16:50:35 - INFO - __main__ - Step 20178: {'lr': 0.0004816203985885977, 'samples': 3874176, 'steps': 20177, 'loss/train': 1.2655019760131836}
+08/30/2021 16:50:36 - INFO - __main__ - Step 20179: {'lr': 0.0004816184013958268, 'samples': 3874368, 'steps': 20178, 'loss/train': 0.8092939257621765}
+08/30/2021 16:50:36 - INFO - __main__ - Step 20180: {'lr': 0.0004816164040986923, 'samples': 3874560, 'steps': 20179, 'loss/train': 1.2360841035842896}
+08/30/2021 16:50:36 - INFO - __main__ - Step 20181: {'lr': 0.00048161440669719496, 'samples': 3874752, 'steps': 20180, 'loss/train': 1.3704040050506592}
+08/30/2021 16:50:37 - INFO - __main__ - Step 20182: {'lr': 0.00048161240919133573, 'samples': 3874944, 'steps': 20181, 'loss/train': 1.7986598014831543}
+08/30/2021 16:50:39 - INFO - __main__ - Step 20183: {'lr': 0.00048161041158111564, 'samples': 3875136, 'steps': 20182, 'loss/train': 1.7684286832809448}
+08/30/2021 16:50:39 - INFO - __main__ - Step 20184: {'lr': 0.0004816084138665353, 'samples': 3875328, 'steps': 20183, 'loss/train': 2.0559840202331543}
+08/30/2021 16:50:40 - INFO - __main__ - Step 20185: {'lr': 0.00048160641604759593, 'samples': 3875520, 'steps': 20184, 'loss/train': 1.800355315208435}
+08/30/2021 16:50:40 - INFO - __main__ - Step 20186: {'lr': 0.0004816044181242982, 'samples': 3875712, 'steps': 20185, 'loss/train': 1.0849143266677856}
+08/30/2021 16:50:40 - INFO - __main__ - Step 20187: {'lr': 0.0004816024200966431, 'samples': 3875904, 'steps': 20186, 'loss/train': 1.4484061002731323}
+08/30/2021 16:50:41 - INFO - __main__ - Step 20188: {'lr': 0.00048160042196463153, 'samples': 3876096, 'steps': 20187, 'loss/train': 1.6775819063186646}
+08/30/2021 16:50:43 - INFO - __main__ - Step 20189: {'lr': 0.00048159842372826446, 'samples': 3876288, 'steps': 20188, 'loss/train': 0.43652939796447754}
+08/30/2021 16:50:43 - INFO - __main__ - Step 20190: {'lr': 0.0004815964253875426, 'samples': 3876480, 'steps': 20189, 'loss/train': 1.82103431224823}
+08/30/2021 16:50:44 - INFO - __main__ - Step 20191: {'lr': 0.000481594426942467, 'samples': 3876672, 'steps': 20190, 'loss/train': 1.695461630821228}
+08/30/2021 16:50:44 - INFO - __main__ - Step 20192: {'lr': 0.0004815924283930385, 'samples': 3876864, 'steps': 20191, 'loss/train': 0.7486909031867981}
+08/30/2021 16:50:45 - INFO - __main__ - Step 20193: {'lr': 0.0004815904297392582, 'samples': 3877056, 'steps': 20192, 'loss/train': 1.5004451274871826}
+08/30/2021 16:50:45 - INFO - __main__ - Step 20194: {'lr': 0.00048158843098112657, 'samples': 3877248, 'steps': 20193, 'loss/train': 0.9767536520957947}
+08/30/2021 16:50:45 - INFO - __main__ - Step 20195: {'lr': 0.00048158643211864495, 'samples': 3877440, 'steps': 20194, 'loss/train': 0.047608163207769394}
+08/30/2021 16:50:47 - INFO - __main__ - Step 20196: {'lr': 0.000481584433151814, 'samples': 3877632, 'steps': 20195, 'loss/train': 0.05013556405901909}
+08/30/2021 16:50:47 - INFO - __main__ - Step 20197: {'lr': 0.00048158243408063465, 'samples': 3877824, 'steps': 20196, 'loss/train': 1.9597336053848267}
+08/30/2021 16:50:47 - INFO - __main__ - Step 20198: {'lr': 0.0004815804349051078, 'samples': 3878016, 'steps': 20197, 'loss/train': 1.4055026769638062}
+08/30/2021 16:50:48 - INFO - __main__ - Step 20199: {'lr': 0.0004815784356252344, 'samples': 3878208, 'steps': 20198, 'loss/train': 1.3472555875778198}
+08/30/2021 16:50:48 - INFO - __main__ - Step 20200: {'lr': 0.0004815764362410154, 'samples': 3878400, 'steps': 20199, 'loss/train': 2.0765771865844727}
+08/30/2021 16:50:50 - INFO - __main__ - Step 20201: {'lr': 0.0004815744367524516, 'samples': 3878592, 'steps': 20200, 'loss/train': 1.5773504972457886}
+08/30/2021 16:50:50 - INFO - __main__ - Step 20202: {'lr': 0.0004815724371595439, 'samples': 3878784, 'steps': 20201, 'loss/train': 2.0365428924560547}
+08/30/2021 16:50:51 - INFO - __main__ - Step 20203: {'lr': 0.00048157043746229324, 'samples': 3878976, 'steps': 20202, 'loss/train': 1.6232331991195679}
+08/30/2021 16:50:51 - INFO - __main__ - Step 20204: {'lr': 0.0004815684376607006, 'samples': 3879168, 'steps': 20203, 'loss/train': 1.6831016540527344}
+08/30/2021 16:50:52 - INFO - __main__ - Step 20205: {'lr': 0.0004815664377547667, 'samples': 3879360, 'steps': 20204, 'loss/train': 1.1959266662597656}
+08/30/2021 16:50:52 - INFO - __main__ - Step 20206: {'lr': 0.00048156443774449254, 'samples': 3879552, 'steps': 20205, 'loss/train': 1.4080724716186523}
+08/30/2021 16:50:53 - INFO - __main__ - Step 20207: {'lr': 0.00048156243762987905, 'samples': 3879744, 'steps': 20206, 'loss/train': 0.19121168553829193}
+08/30/2021 16:50:54 - INFO - __main__ - Step 20208: {'lr': 0.00048156043741092705, 'samples': 3879936, 'steps': 20207, 'loss/train': 1.7060894966125488}
+08/30/2021 16:50:54 - INFO - __main__ - Step 20209: {'lr': 0.00048155843708763755, 'samples': 3880128, 'steps': 20208, 'loss/train': 1.4156874418258667}
+08/30/2021 16:50:54 - INFO - __main__ - Step 20210: {'lr': 0.0004815564366600114, 'samples': 3880320, 'steps': 20209, 'loss/train': 1.5062568187713623}
+08/30/2021 16:50:55 - INFO - __main__ - Step 20211: {'lr': 0.0004815544361280494, 'samples': 3880512, 'steps': 20210, 'loss/train': 1.4830186367034912}
+08/30/2021 16:50:56 - INFO - __main__ - Step 20212: {'lr': 0.00048155243549175263, 'samples': 3880704, 'steps': 20211, 'loss/train': 1.079834222793579}
+08/30/2021 16:50:57 - INFO - __main__ - Step 20213: {'lr': 0.00048155043475112184, 'samples': 3880896, 'steps': 20212, 'loss/train': 2.0521597862243652}
+08/30/2021 16:50:57 - INFO - __main__ - Step 20214: {'lr': 0.0004815484339061581, 'samples': 3881088, 'steps': 20213, 'loss/train': 1.731704831123352}
+08/30/2021 16:50:58 - INFO - __main__ - Step 20215: {'lr': 0.0004815464329568621, 'samples': 3881280, 'steps': 20214, 'loss/train': 1.4401785135269165}
+08/30/2021 16:50:58 - INFO - __main__ - Step 20216: {'lr': 0.00048154443190323495, 'samples': 3881472, 'steps': 20215, 'loss/train': 1.3341749906539917}
+08/30/2021 16:51:00 - INFO - __main__ - Step 20217: {'lr': 0.0004815424307452774, 'samples': 3881664, 'steps': 20216, 'loss/train': 1.637634515762329}
+08/30/2021 16:51:00 - INFO - __main__ - Step 20218: {'lr': 0.0004815404294829904, 'samples': 3881856, 'steps': 20217, 'loss/train': 1.7783867120742798}
+08/30/2021 16:51:01 - INFO - __main__ - Step 20219: {'lr': 0.0004815384281163748, 'samples': 3882048, 'steps': 20218, 'loss/train': 1.814454436302185}
+08/30/2021 16:51:01 - INFO - __main__ - Step 20220: {'lr': 0.0004815364266454316, 'samples': 3882240, 'steps': 20219, 'loss/train': 1.4207069873809814}
+08/30/2021 16:51:01 - INFO - __main__ - Step 20221: {'lr': 0.00048153442507016173, 'samples': 3882432, 'steps': 20220, 'loss/train': 1.6495163440704346}
+08/30/2021 16:51:03 - INFO - __main__ - Step 20222: {'lr': 0.00048153242339056594, 'samples': 3882624, 'steps': 20221, 'loss/train': 1.6814595460891724}
+08/30/2021 16:51:04 - INFO - __main__ - Step 20223: {'lr': 0.0004815304216066453, 'samples': 3882816, 'steps': 20222, 'loss/train': 0.20040147006511688}
+08/30/2021 16:51:04 - INFO - __main__ - Step 20224: {'lr': 0.0004815284197184005, 'samples': 3883008, 'steps': 20223, 'loss/train': 1.9685205221176147}
+08/30/2021 16:51:04 - INFO - __main__ - Step 20225: {'lr': 0.0004815264177258326, 'samples': 3883200, 'steps': 20224, 'loss/train': 1.3303196430206299}
+08/30/2021 16:51:05 - INFO - __main__ - Step 20226: {'lr': 0.00048152441562894255, 'samples': 3883392, 'steps': 20225, 'loss/train': 1.6731454133987427}
+08/30/2021 16:51:06 - INFO - __main__ - Step 20227: {'lr': 0.0004815224134277311, 'samples': 3883584, 'steps': 20226, 'loss/train': 1.7326157093048096}
+08/30/2021 16:51:07 - INFO - __main__ - Step 20228: {'lr': 0.00048152041112219926, 'samples': 3883776, 'steps': 20227, 'loss/train': 1.5589109659194946}
+08/30/2021 16:51:07 - INFO - __main__ - Step 20229: {'lr': 0.0004815184087123479, 'samples': 3883968, 'steps': 20228, 'loss/train': 0.0714040994644165}
+08/30/2021 16:51:07 - INFO - __main__ - Step 20230: {'lr': 0.0004815164061981778, 'samples': 3884160, 'steps': 20229, 'loss/train': 1.3627091646194458}
+08/30/2021 16:51:08 - INFO - __main__ - Step 20231: {'lr': 0.0004815144035796901, 'samples': 3884352, 'steps': 20230, 'loss/train': 1.625974178314209}
+08/30/2021 16:51:09 - INFO - __main__ - Step 20232: {'lr': 0.0004815124008568856, 'samples': 3884544, 'steps': 20231, 'loss/train': 1.6093692779541016}
+08/30/2021 16:51:10 - INFO - __main__ - Step 20233: {'lr': 0.00048151039802976517, 'samples': 3884736, 'steps': 20232, 'loss/train': 1.4500622749328613}
+08/30/2021 16:51:10 - INFO - __main__ - Step 20234: {'lr': 0.00048150839509832966, 'samples': 3884928, 'steps': 20233, 'loss/train': 1.9628890752792358}
+08/30/2021 16:51:10 - INFO - __main__ - Step 20235: {'lr': 0.0004815063920625801, 'samples': 3885120, 'steps': 20234, 'loss/train': 1.5627418756484985}
+08/30/2021 16:51:11 - INFO - __main__ - Step 20236: {'lr': 0.00048150438892251724, 'samples': 3885312, 'steps': 20235, 'loss/train': 1.7016435861587524}
+08/30/2021 16:51:11 - INFO - __main__ - Step 20237: {'lr': 0.00048150238567814217, 'samples': 3885504, 'steps': 20236, 'loss/train': 2.050870418548584}
+08/30/2021 16:51:13 - INFO - __main__ - Step 20238: {'lr': 0.0004815003823294557, 'samples': 3885696, 'steps': 20237, 'loss/train': 1.4891928434371948}
+08/30/2021 16:51:13 - INFO - __main__ - Step 20239: {'lr': 0.0004814983788764587, 'samples': 3885888, 'steps': 20238, 'loss/train': 1.7690858840942383}
+08/30/2021 16:51:13 - INFO - __main__ - Step 20240: {'lr': 0.00048149637531915215, 'samples': 3886080, 'steps': 20239, 'loss/train': 1.8192404508590698}
+08/30/2021 16:51:14 - INFO - __main__ - Step 20241: {'lr': 0.00048149437165753684, 'samples': 3886272, 'steps': 20240, 'loss/train': 1.5038063526153564}
+08/30/2021 16:51:14 - INFO - __main__ - Step 20242: {'lr': 0.00048149236789161374, 'samples': 3886464, 'steps': 20241, 'loss/train': 1.7118151187896729}
+08/30/2021 16:51:16 - INFO - __main__ - Step 20243: {'lr': 0.0004814903640213838, 'samples': 3886656, 'steps': 20242, 'loss/train': 1.7593092918395996}
+08/30/2021 16:51:16 - INFO - __main__ - Step 20244: {'lr': 0.0004814883600468478, 'samples': 3886848, 'steps': 20243, 'loss/train': 1.4841561317443848}
+08/30/2021 16:51:16 - INFO - __main__ - Step 20245: {'lr': 0.0004814863559680068, 'samples': 3887040, 'steps': 20244, 'loss/train': 1.5900686979293823}
+08/30/2021 16:51:17 - INFO - __main__ - Step 20246: {'lr': 0.00048148435178486156, 'samples': 3887232, 'steps': 20245, 'loss/train': 1.7600446939468384}
+08/30/2021 16:51:17 - INFO - __main__ - Step 20247: {'lr': 0.00048148234749741304, 'samples': 3887424, 'steps': 20246, 'loss/train': 1.2677690982818604}
+08/30/2021 16:51:19 - INFO - __main__ - Step 20248: {'lr': 0.0004814803431056622, 'samples': 3887616, 'steps': 20247, 'loss/train': 0.11285198479890823}
+08/30/2021 16:51:19 - INFO - __main__ - Step 20249: {'lr': 0.0004814783386096099, 'samples': 3887808, 'steps': 20248, 'loss/train': 1.5451240539550781}
+08/30/2021 16:51:19 - INFO - __main__ - Step 20250: {'lr': 0.00048147633400925693, 'samples': 3888000, 'steps': 20249, 'loss/train': 1.4259566068649292}
+08/30/2021 16:51:20 - INFO - __main__ - Step 20251: {'lr': 0.00048147432930460433, 'samples': 3888192, 'steps': 20250, 'loss/train': 1.0979019403457642}
+08/30/2021 16:51:20 - INFO - __main__ - Step 20252: {'lr': 0.00048147232449565305, 'samples': 3888384, 'steps': 20251, 'loss/train': 1.3598960638046265}
+08/30/2021 16:51:22 - INFO - __main__ - Step 20253: {'lr': 0.00048147031958240384, 'samples': 3888576, 'steps': 20252, 'loss/train': 1.4012603759765625}
+08/30/2021 16:51:22 - INFO - __main__ - Step 20254: {'lr': 0.00048146831456485776, 'samples': 3888768, 'steps': 20253, 'loss/train': 1.9264036417007446}
+08/30/2021 16:51:22 - INFO - __main__ - Step 20255: {'lr': 0.0004814663094430155, 'samples': 3888960, 'steps': 20254, 'loss/train': 1.0462913513183594}
+08/30/2021 16:51:23 - INFO - __main__ - Step 20256: {'lr': 0.00048146430421687817, 'samples': 3889152, 'steps': 20255, 'loss/train': 2.1124379634857178}
+08/30/2021 16:51:23 - INFO - __main__ - Step 20257: {'lr': 0.00048146229888644656, 'samples': 3889344, 'steps': 20256, 'loss/train': 1.7220581769943237}
+08/30/2021 16:51:24 - INFO - __main__ - Step 20258: {'lr': 0.00048146029345172165, 'samples': 3889536, 'steps': 20257, 'loss/train': 2.0938880443573}
+08/30/2021 16:51:25 - INFO - __main__ - Step 20259: {'lr': 0.0004814582879127043, 'samples': 3889728, 'steps': 20258, 'loss/train': 1.6154398918151855}
+08/30/2021 16:51:25 - INFO - __main__ - Step 20260: {'lr': 0.0004814562822693954, 'samples': 3889920, 'steps': 20259, 'loss/train': 1.5098820924758911}
+08/30/2021 16:51:26 - INFO - __main__ - Step 20261: {'lr': 0.00048145427652179583, 'samples': 3890112, 'steps': 20260, 'loss/train': 1.702278733253479}
+08/30/2021 16:51:26 - INFO - __main__ - Step 20262: {'lr': 0.0004814522706699066, 'samples': 3890304, 'steps': 20261, 'loss/train': 2.050403356552124}
+08/30/2021 16:51:27 - INFO - __main__ - Step 20263: {'lr': 0.00048145026471372855, 'samples': 3890496, 'steps': 20262, 'loss/train': 1.369707703590393}
+08/30/2021 16:51:28 - INFO - __main__ - Step 20264: {'lr': 0.0004814482586532626, 'samples': 3890688, 'steps': 20263, 'loss/train': 1.726524829864502}
+08/30/2021 16:51:28 - INFO - __main__ - Step 20265: {'lr': 0.00048144625248850955, 'samples': 3890880, 'steps': 20264, 'loss/train': 1.3683204650878906}
+08/30/2021 16:51:29 - INFO - __main__ - Step 20266: {'lr': 0.0004814442462194704, 'samples': 3891072, 'steps': 20265, 'loss/train': 1.4735925197601318}
+08/30/2021 16:51:29 - INFO - __main__ - Step 20267: {'lr': 0.0004814422398461461, 'samples': 3891264, 'steps': 20266, 'loss/train': 1.1498258113861084}
+08/30/2021 16:51:29 - INFO - __main__ - Step 20268: {'lr': 0.00048144023336853746, 'samples': 3891456, 'steps': 20267, 'loss/train': 1.1298660039901733}
+08/30/2021 16:51:31 - INFO - __main__ - Step 20269: {'lr': 0.00048143822678664545, 'samples': 3891648, 'steps': 20268, 'loss/train': 1.6574901342391968}
+08/30/2021 16:51:31 - INFO - __main__ - Step 20270: {'lr': 0.00048143622010047096, 'samples': 3891840, 'steps': 20269, 'loss/train': 1.2668615579605103}
+08/30/2021 16:51:32 - INFO - __main__ - Step 20271: {'lr': 0.0004814342133100149, 'samples': 3892032, 'steps': 20270, 'loss/train': 1.652359962463379}
+08/30/2021 16:51:32 - INFO - __main__ - Step 20272: {'lr': 0.00048143220641527805, 'samples': 3892224, 'steps': 20271, 'loss/train': 0.955489456653595}
+08/30/2021 16:51:32 - INFO - __main__ - Step 20273: {'lr': 0.0004814301994162615, 'samples': 3892416, 'steps': 20272, 'loss/train': 1.2216873168945312}
+08/30/2021 16:51:34 - INFO - __main__ - Step 20274: {'lr': 0.000481428192312966, 'samples': 3892608, 'steps': 20273, 'loss/train': 0.6006215214729309}
+08/30/2021 16:51:35 - INFO - __main__ - Step 20275: {'lr': 0.0004814261851053926, 'samples': 3892800, 'steps': 20274, 'loss/train': 2.2969014644622803}
+08/30/2021 16:51:35 - INFO - __main__ - Step 20276: {'lr': 0.00048142417779354214, 'samples': 3892992, 'steps': 20275, 'loss/train': 1.3134269714355469}
+08/30/2021 16:51:35 - INFO - __main__ - Step 20277: {'lr': 0.0004814221703774155, 'samples': 3893184, 'steps': 20276, 'loss/train': 1.9949308633804321}
+08/30/2021 16:51:36 - INFO - __main__ - Step 20278: {'lr': 0.00048142016285701356, 'samples': 3893376, 'steps': 20277, 'loss/train': 0.6431128978729248}
+08/30/2021 16:51:37 - INFO - __main__ - Step 20279: {'lr': 0.00048141815523233735, 'samples': 3893568, 'steps': 20278, 'loss/train': 1.374727487564087}
+08/30/2021 16:51:38 - INFO - __main__ - Step 20280: {'lr': 0.00048141614750338757, 'samples': 3893760, 'steps': 20279, 'loss/train': 1.5767276287078857}
+08/30/2021 16:51:38 - INFO - __main__ - Step 20281: {'lr': 0.00048141413967016535, 'samples': 3893952, 'steps': 20280, 'loss/train': 2.1855556964874268}
+08/30/2021 16:51:38 - INFO - __main__ - Step 20282: {'lr': 0.00048141213173267145, 'samples': 3894144, 'steps': 20281, 'loss/train': 1.0905746221542358}
+08/30/2021 16:51:39 - INFO - __main__ - Step 20283: {'lr': 0.0004814101236909068, 'samples': 3894336, 'steps': 20282, 'loss/train': 1.8638893365859985}
+08/30/2021 16:51:40 - INFO - __main__ - Step 20284: {'lr': 0.00048140811554487234, 'samples': 3894528, 'steps': 20283, 'loss/train': 1.758457064628601}
+08/30/2021 16:51:41 - INFO - __main__ - Step 20285: {'lr': 0.000481406107294569, 'samples': 3894720, 'steps': 20284, 'loss/train': 1.4025347232818604}
+08/30/2021 16:51:41 - INFO - __main__ - Step 20286: {'lr': 0.0004814040989399975, 'samples': 3894912, 'steps': 20285, 'loss/train': 1.8196550607681274}
+08/30/2021 16:51:41 - INFO - __main__ - Step 20287: {'lr': 0.000481402090481159, 'samples': 3895104, 'steps': 20286, 'loss/train': 1.3624060153961182}
+08/30/2021 16:51:42 - INFO - __main__ - Step 20288: {'lr': 0.0004814000819180543, 'samples': 3895296, 'steps': 20287, 'loss/train': 0.644443929195404}
+08/30/2021 16:51:42 - INFO - __main__ - Step 20289: {'lr': 0.00048139807325068423, 'samples': 3895488, 'steps': 20288, 'loss/train': 1.156691074371338}
+08/30/2021 16:51:44 - INFO - __main__ - Step 20290: {'lr': 0.0004813960644790498, 'samples': 3895680, 'steps': 20289, 'loss/train': 1.8000234365463257}
+08/30/2021 16:51:44 - INFO - __main__ - Step 20291: {'lr': 0.00048139405560315186, 'samples': 3895872, 'steps': 20290, 'loss/train': 1.5448402166366577}
+08/30/2021 16:51:44 - INFO - __main__ - Step 20292: {'lr': 0.0004813920466229913, 'samples': 3896064, 'steps': 20291, 'loss/train': 2.0204708576202393}
+08/30/2021 16:51:45 - INFO - __main__ - Step 20293: {'lr': 0.0004813900375385691, 'samples': 3896256, 'steps': 20292, 'loss/train': 1.535262107849121}
+08/30/2021 16:51:45 - INFO - __main__ - Step 20294: {'lr': 0.0004813880283498861, 'samples': 3896448, 'steps': 20293, 'loss/train': 1.7797614336013794}
+08/30/2021 16:51:47 - INFO - __main__ - Step 20295: {'lr': 0.00048138601905694324, 'samples': 3896640, 'steps': 20294, 'loss/train': 1.4918376207351685}
+08/30/2021 16:51:47 - INFO - __main__ - Step 20296: {'lr': 0.0004813840096597414, 'samples': 3896832, 'steps': 20295, 'loss/train': 1.7750217914581299}
+08/30/2021 16:51:47 - INFO - __main__ - Step 20297: {'lr': 0.00048138200015828146, 'samples': 3897024, 'steps': 20296, 'loss/train': 0.6045969724655151}
+08/30/2021 16:51:48 - INFO - __main__ - Step 20298: {'lr': 0.00048137999055256444, 'samples': 3897216, 'steps': 20297, 'loss/train': 1.321756362915039}
+08/30/2021 16:51:48 - INFO - __main__ - Step 20299: {'lr': 0.0004813779808425911, 'samples': 3897408, 'steps': 20298, 'loss/train': 2.277691125869751}
+08/30/2021 16:51:50 - INFO - __main__ - Step 20300: {'lr': 0.0004813759710283624, 'samples': 3897600, 'steps': 20299, 'loss/train': 1.074888825416565}
+08/30/2021 16:51:51 - INFO - __main__ - Step 20301: {'lr': 0.0004813739611098793, 'samples': 3897792, 'steps': 20300, 'loss/train': 1.1064374446868896}
+08/30/2021 16:51:51 - INFO - __main__ - Step 20302: {'lr': 0.00048137195108714266, 'samples': 3897984, 'steps': 20301, 'loss/train': 1.246031641960144}
+08/30/2021 16:51:51 - INFO - __main__ - Step 20303: {'lr': 0.00048136994096015343, 'samples': 3898176, 'steps': 20302, 'loss/train': 2.2300167083740234}
+08/30/2021 16:51:52 - INFO - __main__ - Step 20304: {'lr': 0.00048136793072891236, 'samples': 3898368, 'steps': 20303, 'loss/train': 0.9699680805206299}
+08/30/2021 16:51:52 - INFO - __main__ - Step 20305: {'lr': 0.00048136592039342053, 'samples': 3898560, 'steps': 20304, 'loss/train': 0.25588709115982056}
+08/30/2021 16:51:54 - INFO - __main__ - Step 20306: {'lr': 0.0004813639099536789, 'samples': 3898752, 'steps': 20305, 'loss/train': 0.08922585099935532}
+08/30/2021 16:51:54 - INFO - __main__ - Step 20307: {'lr': 0.0004813618994096881, 'samples': 3898944, 'steps': 20306, 'loss/train': 1.9414191246032715}
+08/30/2021 16:51:54 - INFO - __main__ - Step 20308: {'lr': 0.0004813598887614492, 'samples': 3899136, 'steps': 20307, 'loss/train': 2.3342318534851074}
+08/30/2021 16:51:55 - INFO - __main__ - Step 20309: {'lr': 0.0004813578780089632, 'samples': 3899328, 'steps': 20308, 'loss/train': 1.780541181564331}
+08/30/2021 16:51:55 - INFO - __main__ - Step 20310: {'lr': 0.00048135586715223087, 'samples': 3899520, 'steps': 20309, 'loss/train': 1.5144213438034058}
+08/30/2021 16:51:56 - INFO - __main__ - Step 20311: {'lr': 0.00048135385619125316, 'samples': 3899712, 'steps': 20310, 'loss/train': 1.6306337118148804}
+08/30/2021 16:51:57 - INFO - __main__ - Step 20312: {'lr': 0.00048135184512603093, 'samples': 3899904, 'steps': 20311, 'loss/train': 1.8974195718765259}
+08/30/2021 16:51:57 - INFO - __main__ - Step 20313: {'lr': 0.00048134983395656516, 'samples': 3900096, 'steps': 20312, 'loss/train': 1.349603533744812}
+08/30/2021 16:51:58 - INFO - __main__ - Step 20314: {'lr': 0.00048134782268285676, 'samples': 3900288, 'steps': 20313, 'loss/train': 1.4073094129562378}
+08/30/2021 16:51:58 - INFO - __main__ - Step 20315: {'lr': 0.00048134581130490655, 'samples': 3900480, 'steps': 20314, 'loss/train': 0.14571332931518555}
+08/30/2021 16:51:59 - INFO - __main__ - Step 20316: {'lr': 0.0004813437998227155, 'samples': 3900672, 'steps': 20315, 'loss/train': 1.4282830953598022}
+08/30/2021 16:52:00 - INFO - __main__ - Step 20317: {'lr': 0.00048134178823628455, 'samples': 3900864, 'steps': 20316, 'loss/train': 0.07498446106910706}
+08/30/2021 16:52:00 - INFO - __main__ - Step 20318: {'lr': 0.0004813397765456145, 'samples': 3901056, 'steps': 20317, 'loss/train': 1.475098729133606}
+08/30/2021 16:52:01 - INFO - __main__ - Step 20319: {'lr': 0.00048133776475070637, 'samples': 3901248, 'steps': 20318, 'loss/train': 1.4537569284439087}
+08/30/2021 16:52:01 - INFO - __main__ - Step 20320: {'lr': 0.00048133575285156093, 'samples': 3901440, 'steps': 20319, 'loss/train': 1.7889646291732788}
+08/30/2021 16:52:03 - INFO - __main__ - Step 20321: {'lr': 0.00048133374084817927, 'samples': 3901632, 'steps': 20320, 'loss/train': 1.2979167699813843}
+08/30/2021 16:52:03 - INFO - __main__ - Step 20322: {'lr': 0.00048133172874056213, 'samples': 3901824, 'steps': 20321, 'loss/train': 1.4164572954177856}
+08/30/2021 16:52:04 - INFO - __main__ - Step 20323: {'lr': 0.0004813297165287105, 'samples': 3902016, 'steps': 20322, 'loss/train': 0.38410359621047974}
+08/30/2021 16:52:04 - INFO - __main__ - Step 20324: {'lr': 0.00048132770421262526, 'samples': 3902208, 'steps': 20323, 'loss/train': 1.6559373140335083}
+08/30/2021 16:52:04 - INFO - __main__ - Step 20325: {'lr': 0.00048132569179230736, 'samples': 3902400, 'steps': 20324, 'loss/train': 1.012794852256775}
+08/30/2021 16:52:06 - INFO - __main__ - Step 20326: {'lr': 0.0004813236792677577, 'samples': 3902592, 'steps': 20325, 'loss/train': 1.9623057842254639}
+08/30/2021 16:52:07 - INFO - __main__ - Step 20327: {'lr': 0.00048132166663897703, 'samples': 3902784, 'steps': 20326, 'loss/train': 1.7337126731872559}
+08/30/2021 16:52:07 - INFO - __main__ - Step 20328: {'lr': 0.0004813196539059665, 'samples': 3902976, 'steps': 20327, 'loss/train': 1.6525582075119019}
+08/30/2021 16:52:08 - INFO - __main__ - Step 20329: {'lr': 0.0004813176410687269, 'samples': 3903168, 'steps': 20328, 'loss/train': 1.8098485469818115}
+08/30/2021 16:52:08 - INFO - __main__ - Step 20330: {'lr': 0.00048131562812725904, 'samples': 3903360, 'steps': 20329, 'loss/train': 1.4743527173995972}
+08/30/2021 16:52:09 - INFO - __main__ - Step 20331: {'lr': 0.000481313615081564, 'samples': 3903552, 'steps': 20330, 'loss/train': 0.7975194454193115}
+08/30/2021 16:52:10 - INFO - __main__ - Step 20332: {'lr': 0.00048131160193164266, 'samples': 3903744, 'steps': 20331, 'loss/train': 1.6436889171600342}
+08/30/2021 16:52:10 - INFO - __main__ - Step 20333: {'lr': 0.0004813095886774958, 'samples': 3903936, 'steps': 20332, 'loss/train': 1.3344805240631104}
+08/30/2021 16:52:11 - INFO - __main__ - Step 20334: {'lr': 0.00048130757531912447, 'samples': 3904128, 'steps': 20333, 'loss/train': 1.0350271463394165}
+08/30/2021 16:52:11 - INFO - __main__ - Step 20335: {'lr': 0.00048130556185652947, 'samples': 3904320, 'steps': 20334, 'loss/train': 1.1588261127471924}
+08/30/2021 16:52:13 - INFO - __main__ - Step 20336: {'lr': 0.0004813035482897118, 'samples': 3904512, 'steps': 20335, 'loss/train': 0.1003037616610527}
+08/30/2021 16:52:13 - INFO - __main__ - Step 20337: {'lr': 0.00048130153461867225, 'samples': 3904704, 'steps': 20336, 'loss/train': 1.3650394678115845}
+08/30/2021 16:52:13 - INFO - __main__ - Step 20338: {'lr': 0.0004812995208434119, 'samples': 3904896, 'steps': 20337, 'loss/train': 1.2996113300323486}
+08/30/2021 16:52:14 - INFO - __main__ - Step 20339: {'lr': 0.00048129750696393144, 'samples': 3905088, 'steps': 20338, 'loss/train': 0.38042551279067993}
+08/30/2021 16:52:14 - INFO - __main__ - Step 20340: {'lr': 0.00048129549298023196, 'samples': 3905280, 'steps': 20339, 'loss/train': 2.639559745788574}
+08/30/2021 16:52:16 - INFO - __main__ - Step 20341: {'lr': 0.0004812934788923143, 'samples': 3905472, 'steps': 20340, 'loss/train': 2.066987991333008}
+08/30/2021 16:52:16 - INFO - __main__ - Step 20342: {'lr': 0.00048129146470017933, 'samples': 3905664, 'steps': 20341, 'loss/train': 1.4800901412963867}
+08/30/2021 16:52:16 - INFO - __main__ - Step 20343: {'lr': 0.000481289450403828, 'samples': 3905856, 'steps': 20342, 'loss/train': 1.8806313276290894}
+08/30/2021 16:52:17 - INFO - __main__ - Step 20344: {'lr': 0.0004812874360032613, 'samples': 3906048, 'steps': 20343, 'loss/train': 0.0669122040271759}
+08/30/2021 16:52:17 - INFO - __main__ - Step 20345: {'lr': 0.0004812854214984799, 'samples': 3906240, 'steps': 20344, 'loss/train': 1.2670842409133911}
+08/30/2021 16:52:19 - INFO - __main__ - Step 20346: {'lr': 0.000481283406889485, 'samples': 3906432, 'steps': 20345, 'loss/train': 1.4036363363265991}
+08/30/2021 16:52:19 - INFO - __main__ - Step 20347: {'lr': 0.00048128139217627725, 'samples': 3906624, 'steps': 20346, 'loss/train': 1.4741283655166626}
+08/30/2021 16:52:20 - INFO - __main__ - Step 20348: {'lr': 0.00048127937735885774, 'samples': 3906816, 'steps': 20347, 'loss/train': 1.190222978591919}
+08/30/2021 16:52:20 - INFO - __main__ - Step 20349: {'lr': 0.0004812773624372273, 'samples': 3907008, 'steps': 20348, 'loss/train': 1.4741625785827637}
+08/30/2021 16:52:20 - INFO - __main__ - Step 20350: {'lr': 0.0004812753474113869, 'samples': 3907200, 'steps': 20349, 'loss/train': 0.13493667542934418}
+08/30/2021 16:52:21 - INFO - __main__ - Step 20351: {'lr': 0.0004812733322813373, 'samples': 3907392, 'steps': 20350, 'loss/train': 1.3247870206832886}
+08/30/2021 16:52:22 - INFO - __main__ - Step 20352: {'lr': 0.00048127131704707953, 'samples': 3907584, 'steps': 20351, 'loss/train': 1.2110882997512817}
+08/30/2021 16:52:23 - INFO - __main__ - Step 20353: {'lr': 0.0004812693017086145, 'samples': 3907776, 'steps': 20352, 'loss/train': 1.2169265747070312}
+08/30/2021 16:52:23 - INFO - __main__ - Step 20354: {'lr': 0.00048126728626594315, 'samples': 3907968, 'steps': 20353, 'loss/train': 1.8783468008041382}
+08/30/2021 16:52:24 - INFO - __main__ - Step 20355: {'lr': 0.00048126527071906623, 'samples': 3908160, 'steps': 20354, 'loss/train': 1.3172804117202759}
+08/30/2021 16:52:24 - INFO - __main__ - Step 20356: {'lr': 0.0004812632550679848, 'samples': 3908352, 'steps': 20355, 'loss/train': 1.304091215133667}
+08/30/2021 16:52:25 - INFO - __main__ - Step 20357: {'lr': 0.00048126123931269973, 'samples': 3908544, 'steps': 20356, 'loss/train': 2.1128251552581787}
+08/30/2021 16:52:26 - INFO - __main__ - Step 20358: {'lr': 0.0004812592234532118, 'samples': 3908736, 'steps': 20357, 'loss/train': 1.362840175628662}
+08/30/2021 16:52:26 - INFO - __main__ - Step 20359: {'lr': 0.00048125720748952216, 'samples': 3908928, 'steps': 20358, 'loss/train': 1.3950108289718628}
+08/30/2021 16:52:27 - INFO - __main__ - Step 20360: {'lr': 0.00048125519142163157, 'samples': 3909120, 'steps': 20359, 'loss/train': 1.794309139251709}
+08/30/2021 16:52:27 - INFO - __main__ - Step 20361: {'lr': 0.0004812531752495409, 'samples': 3909312, 'steps': 20360, 'loss/train': 1.2508519887924194}
+08/30/2021 16:52:28 - INFO - __main__ - Step 20362: {'lr': 0.00048125115897325115, 'samples': 3909504, 'steps': 20361, 'loss/train': 1.7729012966156006}
+08/30/2021 16:52:29 - INFO - __main__ - Step 20363: {'lr': 0.0004812491425927632, 'samples': 3909696, 'steps': 20362, 'loss/train': 1.9157298803329468}
+08/30/2021 16:52:29 - INFO - __main__ - Step 20364: {'lr': 0.000481247126108078, 'samples': 3909888, 'steps': 20363, 'loss/train': 0.7351324558258057}
+08/30/2021 16:52:29 - INFO - __main__ - Step 20365: {'lr': 0.00048124510951919633, 'samples': 3910080, 'steps': 20364, 'loss/train': 1.759158968925476}
+08/30/2021 16:52:30 - INFO - __main__ - Step 20366: {'lr': 0.0004812430928261192, 'samples': 3910272, 'steps': 20365, 'loss/train': 1.376376748085022}
+08/30/2021 16:52:30 - INFO - __main__ - Step 20367: {'lr': 0.00048124107602884753, 'samples': 3910464, 'steps': 20366, 'loss/train': 0.8080965876579285}
+08/30/2021 16:52:32 - INFO - __main__ - Step 20368: {'lr': 0.0004812390591273822, 'samples': 3910656, 'steps': 20367, 'loss/train': 2.2293286323547363}
+08/30/2021 16:52:32 - INFO - __main__ - Step 20369: {'lr': 0.00048123704212172416, 'samples': 3910848, 'steps': 20368, 'loss/train': 1.5028109550476074}
+08/30/2021 16:52:32 - INFO - __main__ - Step 20370: {'lr': 0.0004812350250118742, 'samples': 3911040, 'steps': 20369, 'loss/train': 1.318708896636963}
+08/30/2021 16:52:33 - INFO - __main__ - Step 20371: {'lr': 0.0004812330077978333, 'samples': 3911232, 'steps': 20370, 'loss/train': 1.5189670324325562}
+08/30/2021 16:52:33 - INFO - __main__ - Step 20372: {'lr': 0.0004812309904796024, 'samples': 3911424, 'steps': 20371, 'loss/train': 2.112004518508911}
+08/30/2021 16:52:35 - INFO - __main__ - Step 20373: {'lr': 0.0004812289730571824, 'samples': 3911616, 'steps': 20372, 'loss/train': 1.28286612033844}
+08/30/2021 16:52:35 - INFO - __main__ - Step 20374: {'lr': 0.00048122695553057417, 'samples': 3911808, 'steps': 20373, 'loss/train': 0.4064999222755432}
+08/30/2021 16:52:35 - INFO - __main__ - Step 20375: {'lr': 0.00048122493789977866, 'samples': 3912000, 'steps': 20374, 'loss/train': 0.8093968033790588}
+08/30/2021 16:52:36 - INFO - __main__ - Step 20376: {'lr': 0.00048122292016479674, 'samples': 3912192, 'steps': 20375, 'loss/train': 1.5330499410629272}
+08/30/2021 16:52:36 - INFO - __main__ - Step 20377: {'lr': 0.0004812209023256294, 'samples': 3912384, 'steps': 20376, 'loss/train': 1.7736256122589111}
+08/30/2021 16:52:38 - INFO - __main__ - Step 20378: {'lr': 0.0004812188843822775, 'samples': 3912576, 'steps': 20377, 'loss/train': 1.1705150604248047}
+08/30/2021 16:52:38 - INFO - __main__ - Step 20379: {'lr': 0.0004812168663347418, 'samples': 3912768, 'steps': 20378, 'loss/train': 1.4795498847961426}
+08/30/2021 16:52:38 - INFO - __main__ - Step 20380: {'lr': 0.00048121484818302343, 'samples': 3912960, 'steps': 20379, 'loss/train': 1.5681957006454468}
+08/30/2021 16:52:39 - INFO - __main__ - Step 20381: {'lr': 0.00048121282992712324, 'samples': 3913152, 'steps': 20380, 'loss/train': 1.891641616821289}
+08/30/2021 16:52:39 - INFO - __main__ - Step 20382: {'lr': 0.00048121081156704207, 'samples': 3913344, 'steps': 20381, 'loss/train': 1.8444931507110596}
+08/30/2021 16:52:39 - INFO - __main__ - Step 20383: {'lr': 0.00048120879310278094, 'samples': 3913536, 'steps': 20382, 'loss/train': 1.2242088317871094}
+08/30/2021 16:52:41 - INFO - __main__ - Step 20384: {'lr': 0.00048120677453434066, 'samples': 3913728, 'steps': 20383, 'loss/train': 1.4907710552215576}
+08/30/2021 16:52:42 - INFO - __main__ - Step 20385: {'lr': 0.00048120475586172217, 'samples': 3913920, 'steps': 20384, 'loss/train': 2.6739895343780518}
+08/30/2021 16:52:42 - INFO - __main__ - Step 20386: {'lr': 0.00048120273708492637, 'samples': 3914112, 'steps': 20385, 'loss/train': 1.0332735776901245}
+08/30/2021 16:52:43 - INFO - __main__ - Step 20387: {'lr': 0.0004812007182039542, 'samples': 3914304, 'steps': 20386, 'loss/train': 1.4726247787475586}
+08/30/2021 16:52:43 - INFO - __main__ - Step 20388: {'lr': 0.00048119869921880656, 'samples': 3914496, 'steps': 20387, 'loss/train': 2.6740262508392334}
+08/30/2021 16:52:44 - INFO - __main__ - Step 20389: {'lr': 0.00048119668012948434, 'samples': 3914688, 'steps': 20388, 'loss/train': 1.3015917539596558}
+08/30/2021 16:52:45 - INFO - __main__ - Step 20390: {'lr': 0.0004811946609359885, 'samples': 3914880, 'steps': 20389, 'loss/train': 1.6949397325515747}
+08/30/2021 16:52:45 - INFO - __main__ - Step 20391: {'lr': 0.00048119264163831987, 'samples': 3915072, 'steps': 20390, 'loss/train': 1.654359221458435}
+08/30/2021 16:52:46 - INFO - __main__ - Step 20392: {'lr': 0.0004811906222364794, 'samples': 3915264, 'steps': 20391, 'loss/train': 2.69132924079895}
+08/30/2021 16:52:46 - INFO - __main__ - Step 20393: {'lr': 0.00048118860273046804, 'samples': 3915456, 'steps': 20392, 'loss/train': 1.7485592365264893}
+08/30/2021 16:52:47 - INFO - __main__ - Step 20394: {'lr': 0.00048118658312028663, 'samples': 3915648, 'steps': 20393, 'loss/train': 1.83722984790802}
+08/30/2021 16:52:48 - INFO - __main__ - Step 20395: {'lr': 0.0004811845634059361, 'samples': 3915840, 'steps': 20394, 'loss/train': 1.4899861812591553}
+08/30/2021 16:52:48 - INFO - __main__ - Step 20396: {'lr': 0.0004811825435874174, 'samples': 3916032, 'steps': 20395, 'loss/train': 1.6030021905899048}
+08/30/2021 16:52:49 - INFO - __main__ - Step 20397: {'lr': 0.0004811805236647314, 'samples': 3916224, 'steps': 20396, 'loss/train': 1.620742917060852}
+08/30/2021 16:52:49 - INFO - __main__ - Step 20398: {'lr': 0.0004811785036378791, 'samples': 3916416, 'steps': 20397, 'loss/train': 1.9796329736709595}
+08/30/2021 16:52:50 - INFO - __main__ - Step 20399: {'lr': 0.0004811764835068613, 'samples': 3916608, 'steps': 20398, 'loss/train': 1.9112696647644043}
+08/30/2021 16:52:51 - INFO - __main__ - Step 20400: {'lr': 0.0004811744632716789, 'samples': 3916800, 'steps': 20399, 'loss/train': 2.097015142440796}
+08/30/2021 16:52:51 - INFO - __main__ - Step 20401: {'lr': 0.0004811724429323329, 'samples': 3916992, 'steps': 20400, 'loss/train': 1.3521363735198975}
+08/30/2021 16:52:52 - INFO - __main__ - Step 20402: {'lr': 0.0004811704224888241, 'samples': 3917184, 'steps': 20401, 'loss/train': 0.9783707857131958}
+08/30/2021 16:52:52 - INFO - __main__ - Step 20403: {'lr': 0.0004811684019411535, 'samples': 3917376, 'steps': 20402, 'loss/train': 1.3182331323623657}
+08/30/2021 16:52:54 - INFO - __main__ - Step 20404: {'lr': 0.000481166381289322, 'samples': 3917568, 'steps': 20403, 'loss/train': 1.7120299339294434}
+08/30/2021 16:52:54 - INFO - __main__ - Step 20405: {'lr': 0.0004811643605333305, 'samples': 3917760, 'steps': 20404, 'loss/train': 1.4472341537475586}
+08/30/2021 16:52:55 - INFO - __main__ - Step 20406: {'lr': 0.0004811623396731799, 'samples': 3917952, 'steps': 20405, 'loss/train': 1.9274582862854004}
+08/30/2021 16:52:55 - INFO - __main__ - Step 20407: {'lr': 0.0004811603187088711, 'samples': 3918144, 'steps': 20406, 'loss/train': 2.011478900909424}
+08/30/2021 16:52:55 - INFO - __main__ - Step 20408: {'lr': 0.00048115829764040503, 'samples': 3918336, 'steps': 20407, 'loss/train': 1.7389706373214722}
+08/30/2021 16:52:56 - INFO - __main__ - Step 20409: {'lr': 0.0004811562764677826, 'samples': 3918528, 'steps': 20408, 'loss/train': 1.454147219657898}
+08/30/2021 16:52:57 - INFO - __main__ - Step 20410: {'lr': 0.00048115425519100474, 'samples': 3918720, 'steps': 20409, 'loss/train': 0.04675471782684326}
+08/30/2021 16:52:58 - INFO - __main__ - Step 20411: {'lr': 0.0004811522338100723, 'samples': 3918912, 'steps': 20410, 'loss/train': 1.6382688283920288}
+08/30/2021 16:52:58 - INFO - __main__ - Step 20412: {'lr': 0.0004811502123249862, 'samples': 3919104, 'steps': 20411, 'loss/train': 0.9834139347076416}
+08/30/2021 16:52:58 - INFO - __main__ - Step 20413: {'lr': 0.0004811481907357475, 'samples': 3919296, 'steps': 20412, 'loss/train': 1.166786789894104}
+08/30/2021 16:52:59 - INFO - __main__ - Step 20414: {'lr': 0.000481146169042357, 'samples': 3919488, 'steps': 20413, 'loss/train': 1.9236106872558594}
+08/30/2021 16:53:00 - INFO - __main__ - Step 20415: {'lr': 0.0004811441472448155, 'samples': 3919680, 'steps': 20414, 'loss/train': 1.2484660148620605}
+08/30/2021 16:53:01 - INFO - __main__ - Step 20416: {'lr': 0.000481142125343124, 'samples': 3919872, 'steps': 20415, 'loss/train': 0.8506363034248352}
+08/30/2021 16:53:01 - INFO - __main__ - Step 20417: {'lr': 0.0004811401033372835, 'samples': 3920064, 'steps': 20416, 'loss/train': 1.2502920627593994}
+08/30/2021 16:53:01 - INFO - __main__ - Step 20418: {'lr': 0.0004811380812272948, 'samples': 3920256, 'steps': 20417, 'loss/train': 1.8344799280166626}
+08/30/2021 16:53:02 - INFO - __main__ - Step 20419: {'lr': 0.0004811360590131589, 'samples': 3920448, 'steps': 20418, 'loss/train': 1.6395113468170166}
+08/30/2021 16:53:02 - INFO - __main__ - Step 20420: {'lr': 0.00048113403669487655, 'samples': 3920640, 'steps': 20419, 'loss/train': 1.2615171670913696}
+08/30/2021 16:53:04 - INFO - __main__ - Step 20421: {'lr': 0.0004811320142724489, 'samples': 3920832, 'steps': 20420, 'loss/train': 1.563582181930542}
+08/30/2021 16:53:04 - INFO - __main__ - Step 20422: {'lr': 0.0004811299917458766, 'samples': 3921024, 'steps': 20421, 'loss/train': 1.7724220752716064}
+08/30/2021 16:53:04 - INFO - __main__ - Step 20423: {'lr': 0.00048112796911516076, 'samples': 3921216, 'steps': 20422, 'loss/train': 1.7514982223510742}
+08/30/2021 16:53:05 - INFO - __main__ - Step 20424: {'lr': 0.00048112594638030225, 'samples': 3921408, 'steps': 20423, 'loss/train': 1.2668033838272095}
+08/30/2021 16:53:05 - INFO - __main__ - Step 20425: {'lr': 0.00048112392354130194, 'samples': 3921600, 'steps': 20424, 'loss/train': 1.2459012269973755}
+08/30/2021 16:53:07 - INFO - __main__ - Step 20426: {'lr': 0.00048112190059816076, 'samples': 3921792, 'steps': 20425, 'loss/train': 1.2621666193008423}
+08/30/2021 16:53:07 - INFO - __main__ - Step 20427: {'lr': 0.0004811198775508796, 'samples': 3921984, 'steps': 20426, 'loss/train': 1.5181001424789429}
+08/30/2021 16:53:07 - INFO - __main__ - Step 20428: {'lr': 0.0004811178543994593, 'samples': 3922176, 'steps': 20427, 'loss/train': 1.673447847366333}
+08/30/2021 16:53:08 - INFO - __main__ - Step 20429: {'lr': 0.000481115831143901, 'samples': 3922368, 'steps': 20428, 'loss/train': 1.9533108472824097}
+08/30/2021 16:53:08 - INFO - __main__ - Step 20430: {'lr': 0.00048111380778420544, 'samples': 3922560, 'steps': 20429, 'loss/train': 1.0703402757644653}
+08/30/2021 16:53:10 - INFO - __main__ - Step 20431: {'lr': 0.0004811117843203735, 'samples': 3922752, 'steps': 20430, 'loss/train': 1.6772987842559814}
+08/30/2021 16:53:10 - INFO - __main__ - Step 20432: {'lr': 0.00048110976075240624, 'samples': 3922944, 'steps': 20431, 'loss/train': 1.4068084955215454}
+08/30/2021 16:53:11 - INFO - __main__ - Step 20433: {'lr': 0.00048110773708030444, 'samples': 3923136, 'steps': 20432, 'loss/train': 0.09284914284944534}
+08/30/2021 16:53:11 - INFO - __main__ - Step 20434: {'lr': 0.00048110571330406903, 'samples': 3923328, 'steps': 20433, 'loss/train': 2.2277603149414062}
+08/30/2021 16:53:11 - INFO - __main__ - Step 20435: {'lr': 0.0004811036894237011, 'samples': 3923520, 'steps': 20434, 'loss/train': 1.6527063846588135}
+08/30/2021 16:53:13 - INFO - __main__ - Step 20436: {'lr': 0.00048110166543920125, 'samples': 3923712, 'steps': 20435, 'loss/train': 0.29340869188308716}
+08/30/2021 16:53:14 - INFO - __main__ - Step 20437: {'lr': 0.0004810996413505706, 'samples': 3923904, 'steps': 20436, 'loss/train': 1.0672272443771362}
+08/30/2021 16:53:14 - INFO - __main__ - Step 20438: {'lr': 0.0004810976171578101, 'samples': 3924096, 'steps': 20437, 'loss/train': 1.6259253025054932}
+08/30/2021 16:53:15 - INFO - __main__ - Step 20439: {'lr': 0.00048109559286092047, 'samples': 3924288, 'steps': 20438, 'loss/train': 1.3832546472549438}
+08/30/2021 16:53:15 - INFO - __main__ - Step 20440: {'lr': 0.0004810935684599028, 'samples': 3924480, 'steps': 20439, 'loss/train': 0.8807126879692078}
+08/30/2021 16:53:16 - INFO - __main__ - Step 20441: {'lr': 0.00048109154395475787, 'samples': 3924672, 'steps': 20440, 'loss/train': 1.526767373085022}
+08/30/2021 16:53:17 - INFO - __main__ - Step 20442: {'lr': 0.00048108951934548673, 'samples': 3924864, 'steps': 20441, 'loss/train': 1.0425728559494019}
+08/30/2021 16:53:17 - INFO - __main__ - Step 20443: {'lr': 0.0004810874946320901, 'samples': 3925056, 'steps': 20442, 'loss/train': 1.772262692451477}
+08/30/2021 16:53:18 - INFO - __main__ - Step 20444: {'lr': 0.00048108546981456916, 'samples': 3925248, 'steps': 20443, 'loss/train': 1.2528482675552368}
+08/30/2021 16:53:18 - INFO - __main__ - Step 20445: {'lr': 0.0004810834448929246, 'samples': 3925440, 'steps': 20444, 'loss/train': 2.1821045875549316}
+08/30/2021 16:53:18 - INFO - __main__ - Step 20446: {'lr': 0.0004810814198671574, 'samples': 3925632, 'steps': 20445, 'loss/train': 1.8502366542816162}
+08/30/2021 16:53:20 - INFO - __main__ - Step 20447: {'lr': 0.00048107939473726846, 'samples': 3925824, 'steps': 20446, 'loss/train': 1.2826957702636719}
+08/30/2021 16:53:20 - INFO - __main__ - Step 20448: {'lr': 0.0004810773695032588, 'samples': 3926016, 'steps': 20447, 'loss/train': 2.0178780555725098}
+08/30/2021 16:53:21 - INFO - __main__ - Step 20449: {'lr': 0.00048107534416512915, 'samples': 3926208, 'steps': 20448, 'loss/train': 0.7107794880867004}
+08/30/2021 16:53:21 - INFO - __main__ - Step 20450: {'lr': 0.00048107331872288055, 'samples': 3926400, 'steps': 20449, 'loss/train': 1.8956117630004883}
+08/30/2021 16:53:21 - INFO - __main__ - Step 20451: {'lr': 0.0004810712931765139, 'samples': 3926592, 'steps': 20450, 'loss/train': 1.7767422199249268}
+08/30/2021 16:53:23 - INFO - __main__ - Step 20452: {'lr': 0.00048106926752603007, 'samples': 3926784, 'steps': 20451, 'loss/train': 1.5847138166427612}
+08/30/2021 16:53:23 - INFO - __main__ - Step 20453: {'lr': 0.00048106724177143, 'samples': 3926976, 'steps': 20452, 'loss/train': 1.5756040811538696}
+08/30/2021 16:53:24 - INFO - __main__ - Step 20454: {'lr': 0.00048106521591271455, 'samples': 3927168, 'steps': 20453, 'loss/train': 1.307875633239746}
+08/30/2021 16:53:24 - INFO - __main__ - Step 20455: {'lr': 0.00048106318994988476, 'samples': 3927360, 'steps': 20454, 'loss/train': 1.1496918201446533}
+08/30/2021 16:53:24 - INFO - __main__ - Step 20456: {'lr': 0.0004810611638829414, 'samples': 3927552, 'steps': 20455, 'loss/train': 1.597902536392212}
+08/30/2021 16:53:26 - INFO - __main__ - Step 20457: {'lr': 0.00048105913771188545, 'samples': 3927744, 'steps': 20456, 'loss/train': 1.5206817388534546}
+08/30/2021 16:53:26 - INFO - __main__ - Step 20458: {'lr': 0.00048105711143671783, 'samples': 3927936, 'steps': 20457, 'loss/train': 1.676174283027649}
+08/30/2021 16:53:27 - INFO - __main__ - Step 20459: {'lr': 0.0004810550850574394, 'samples': 3928128, 'steps': 20458, 'loss/train': 0.932281494140625}
+08/30/2021 16:53:27 - INFO - __main__ - Step 20460: {'lr': 0.0004810530585740512, 'samples': 3928320, 'steps': 20459, 'loss/train': 1.3992466926574707}
+08/30/2021 16:53:27 - INFO - __main__ - Step 20461: {'lr': 0.00048105103198655406, 'samples': 3928512, 'steps': 20460, 'loss/train': 1.2533982992172241}
+08/30/2021 16:53:29 - INFO - __main__ - Step 20462: {'lr': 0.0004810490052949488, 'samples': 3928704, 'steps': 20461, 'loss/train': 1.4120899438858032}
+08/30/2021 16:53:29 - INFO - __main__ - Step 20463: {'lr': 0.0004810469784992365, 'samples': 3928896, 'steps': 20462, 'loss/train': 1.0651419162750244}
+08/30/2021 16:53:30 - INFO - __main__ - Step 20464: {'lr': 0.00048104495159941794, 'samples': 3929088, 'steps': 20463, 'loss/train': 1.827168583869934}
+08/30/2021 16:53:30 - INFO - __main__ - Step 20465: {'lr': 0.00048104292459549413, 'samples': 3929280, 'steps': 20464, 'loss/train': 1.2470966577529907}
+08/30/2021 16:53:30 - INFO - __main__ - Step 20466: {'lr': 0.0004810408974874659, 'samples': 3929472, 'steps': 20465, 'loss/train': 1.5338815450668335}
+08/30/2021 16:53:32 - INFO - __main__ - Step 20467: {'lr': 0.0004810388702753342, 'samples': 3929664, 'steps': 20466, 'loss/train': 1.6177653074264526}
+08/30/2021 16:53:32 - INFO - __main__ - Step 20468: {'lr': 0.0004810368429591, 'samples': 3929856, 'steps': 20467, 'loss/train': 1.5753872394561768}
+08/30/2021 16:53:33 - INFO - __main__ - Step 20469: {'lr': 0.00048103481553876415, 'samples': 3930048, 'steps': 20468, 'loss/train': 1.6142983436584473}
+08/30/2021 16:53:33 - INFO - __main__ - Step 20470: {'lr': 0.0004810327880143276, 'samples': 3930240, 'steps': 20469, 'loss/train': 1.7200350761413574}
+08/30/2021 16:53:33 - INFO - __main__ - Step 20471: {'lr': 0.00048103076038579125, 'samples': 3930432, 'steps': 20470, 'loss/train': 1.4600830078125}
+08/30/2021 16:53:35 - INFO - __main__ - Step 20472: {'lr': 0.00048102873265315596, 'samples': 3930624, 'steps': 20471, 'loss/train': 1.7758893966674805}
+08/30/2021 16:53:36 - INFO - __main__ - Step 20473: {'lr': 0.0004810267048164227, 'samples': 3930816, 'steps': 20472, 'loss/train': 1.8201944828033447}
+08/30/2021 16:53:36 - INFO - __main__ - Step 20474: {'lr': 0.0004810246768755924, 'samples': 3931008, 'steps': 20473, 'loss/train': 1.5521976947784424}
+08/30/2021 16:53:37 - INFO - __main__ - Step 20475: {'lr': 0.0004810226488306659, 'samples': 3931200, 'steps': 20474, 'loss/train': 1.2664735317230225}
+08/30/2021 16:53:37 - INFO - __main__ - Step 20476: {'lr': 0.00048102062068164413, 'samples': 3931392, 'steps': 20475, 'loss/train': 1.3742451667785645}
+08/30/2021 16:53:38 - INFO - __main__ - Step 20477: {'lr': 0.0004810185924285281, 'samples': 3931584, 'steps': 20476, 'loss/train': 0.20455193519592285}
+08/30/2021 16:53:39 - INFO - __main__ - Step 20478: {'lr': 0.00048101656407131864, 'samples': 3931776, 'steps': 20477, 'loss/train': 1.7805805206298828}
+08/30/2021 16:53:39 - INFO - __main__ - Step 20479: {'lr': 0.00048101453561001667, 'samples': 3931968, 'steps': 20478, 'loss/train': 1.5799874067306519}
+08/30/2021 16:53:40 - INFO - __main__ - Step 20480: {'lr': 0.00048101250704462315, 'samples': 3932160, 'steps': 20479, 'loss/train': 1.4885618686676025}
+08/30/2021 16:53:40 - INFO - __main__ - Step 20481: {'lr': 0.0004810104783751389, 'samples': 3932352, 'steps': 20480, 'loss/train': 1.9872725009918213}
+08/30/2021 16:53:40 - INFO - __main__ - Step 20482: {'lr': 0.00048100844960156496, 'samples': 3932544, 'steps': 20481, 'loss/train': 0.8941634893417358}
+08/30/2021 16:53:42 - INFO - __main__ - Step 20483: {'lr': 0.0004810064207239021, 'samples': 3932736, 'steps': 20482, 'loss/train': 1.4970029592514038}
+08/30/2021 16:53:42 - INFO - __main__ - Step 20484: {'lr': 0.0004810043917421514, 'samples': 3932928, 'steps': 20483, 'loss/train': 1.6084808111190796}
+08/30/2021 16:53:43 - INFO - __main__ - Step 20485: {'lr': 0.0004810023626563136, 'samples': 3933120, 'steps': 20484, 'loss/train': 1.541935682296753}
+08/30/2021 16:53:43 - INFO - __main__ - Step 20486: {'lr': 0.0004810003334663898, 'samples': 3933312, 'steps': 20485, 'loss/train': 1.511197566986084}
+08/30/2021 16:53:43 - INFO - __main__ - Step 20487: {'lr': 0.0004809983041723807, 'samples': 3933504, 'steps': 20486, 'loss/train': 1.2819828987121582}
+08/30/2021 16:53:46 - INFO - __main__ - Step 20488: {'lr': 0.00048099627477428744, 'samples': 3933696, 'steps': 20487, 'loss/train': 1.2189552783966064}
+08/30/2021 16:53:47 - INFO - __main__ - Step 20489: {'lr': 0.0004809942452721107, 'samples': 3933888, 'steps': 20488, 'loss/train': 1.914501667022705}
+08/30/2021 16:53:47 - INFO - __main__ - Step 20490: {'lr': 0.0004809922156658516, 'samples': 3934080, 'steps': 20489, 'loss/train': 1.2167168855667114}
+08/30/2021 16:53:48 - INFO - __main__ - Step 20491: {'lr': 0.00048099018595551096, 'samples': 3934272, 'steps': 20490, 'loss/train': 1.6059019565582275}
+08/30/2021 16:53:48 - INFO - __main__ - Step 20492: {'lr': 0.0004809881561410897, 'samples': 3934464, 'steps': 20491, 'loss/train': 1.2520502805709839}
+08/30/2021 16:53:48 - INFO - __main__ - Step 20493: {'lr': 0.00048098612622258873, 'samples': 3934656, 'steps': 20492, 'loss/train': 5.677497863769531}
+08/30/2021 16:53:49 - INFO - __main__ - Step 20494: {'lr': 0.00048098409620000906, 'samples': 3934848, 'steps': 20493, 'loss/train': 5.572636127471924}
+08/30/2021 16:53:50 - INFO - __main__ - Step 20495: {'lr': 0.00048098206607335135, 'samples': 3935040, 'steps': 20494, 'loss/train': 5.476930141448975}
+08/30/2021 16:53:51 - INFO - __main__ - Step 20496: {'lr': 0.00048098003584261684, 'samples': 3935232, 'steps': 20495, 'loss/train': 1.538805365562439}
+08/30/2021 16:53:51 - INFO - __main__ - Step 20497: {'lr': 0.00048097800550780625, 'samples': 3935424, 'steps': 20496, 'loss/train': 0.8303343057632446}
+08/30/2021 16:53:52 - INFO - __main__ - Step 20498: {'lr': 0.0004809759750689205, 'samples': 3935616, 'steps': 20497, 'loss/train': 1.6164000034332275}
+08/30/2021 16:53:52 - INFO - __main__ - Step 20499: {'lr': 0.00048097394452596053, 'samples': 3935808, 'steps': 20498, 'loss/train': 1.4405229091644287}
+08/30/2021 16:53:52 - INFO - __main__ - Step 20500: {'lr': 0.0004809719138789273, 'samples': 3936000, 'steps': 20499, 'loss/train': 1.1235699653625488}
+08/30/2021 16:53:54 - INFO - __main__ - Step 20501: {'lr': 0.0004809698831278217, 'samples': 3936192, 'steps': 20500, 'loss/train': 1.742831826210022}
+08/30/2021 16:53:54 - INFO - __main__ - Step 20502: {'lr': 0.0004809678522726446, 'samples': 3936384, 'steps': 20501, 'loss/train': 1.0082358121871948}
+08/30/2021 16:53:55 - INFO - __main__ - Step 20503: {'lr': 0.000480965821313397, 'samples': 3936576, 'steps': 20502, 'loss/train': 1.5180387496948242}
+08/30/2021 16:53:55 - INFO - __main__ - Step 20504: {'lr': 0.0004809637902500797, 'samples': 3936768, 'steps': 20503, 'loss/train': 1.0592870712280273}
+08/30/2021 16:53:55 - INFO - __main__ - Step 20505: {'lr': 0.00048096175908269375, 'samples': 3936960, 'steps': 20504, 'loss/train': 1.5597378015518188}
+08/30/2021 16:53:57 - INFO - __main__ - Step 20506: {'lr': 0.00048095972781124, 'samples': 3937152, 'steps': 20505, 'loss/train': 1.4473786354064941}
+08/30/2021 16:53:58 - INFO - __main__ - Step 20507: {'lr': 0.00048095769643571927, 'samples': 3937344, 'steps': 20506, 'loss/train': 1.6616387367248535}
+08/30/2021 16:53:58 - INFO - __main__ - Step 20508: {'lr': 0.0004809556649561326, 'samples': 3937536, 'steps': 20507, 'loss/train': 1.440677285194397}
+08/30/2021 16:53:58 - INFO - __main__ - Step 20509: {'lr': 0.0004809536333724809, 'samples': 3937728, 'steps': 20508, 'loss/train': 1.7490971088409424}
+08/30/2021 16:53:59 - INFO - __main__ - Step 20510: {'lr': 0.000480951601684765, 'samples': 3937920, 'steps': 20509, 'loss/train': 0.3238224983215332}
+08/30/2021 16:54:00 - INFO - __main__ - Step 20511: {'lr': 0.00048094956989298593, 'samples': 3938112, 'steps': 20510, 'loss/train': 0.40685346722602844}
+08/30/2021 16:54:00 - INFO - __main__ - Step 20512: {'lr': 0.0004809475379971445, 'samples': 3938304, 'steps': 20511, 'loss/train': 1.6993385553359985}
+08/30/2021 16:54:01 - INFO - __main__ - Step 20513: {'lr': 0.00048094550599724176, 'samples': 3938496, 'steps': 20512, 'loss/train': 0.4886229634284973}
+08/30/2021 16:54:01 - INFO - __main__ - Step 20514: {'lr': 0.0004809434738932785, 'samples': 3938688, 'steps': 20513, 'loss/train': 2.4234566688537598}
+08/30/2021 16:54:01 - INFO - __main__ - Step 20515: {'lr': 0.0004809414416852557, 'samples': 3938880, 'steps': 20514, 'loss/train': 1.7882490158081055}
+08/30/2021 16:54:03 - INFO - __main__ - Step 20516: {'lr': 0.00048093940937317414, 'samples': 3939072, 'steps': 20515, 'loss/train': 1.388883352279663}
+08/30/2021 16:54:03 - INFO - __main__ - Step 20517: {'lr': 0.00048093737695703494, 'samples': 3939264, 'steps': 20516, 'loss/train': 1.4843791723251343}
+08/30/2021 16:54:04 - INFO - __main__ - Step 20518: {'lr': 0.0004809353444368389, 'samples': 3939456, 'steps': 20517, 'loss/train': 1.5473222732543945}
+08/30/2021 16:54:04 - INFO - __main__ - Step 20519: {'lr': 0.00048093331181258694, 'samples': 3939648, 'steps': 20518, 'loss/train': 1.5043143033981323}
+08/30/2021 16:54:04 - INFO - __main__ - Step 20520: {'lr': 0.00048093127908428, 'samples': 3939840, 'steps': 20519, 'loss/train': 0.6837820410728455}
+08/30/2021 16:54:06 - INFO - __main__ - Step 20521: {'lr': 0.00048092924625191903, 'samples': 3940032, 'steps': 20520, 'loss/train': 1.4310814142227173}
+08/30/2021 16:54:06 - INFO - __main__ - Step 20522: {'lr': 0.0004809272133155048, 'samples': 3940224, 'steps': 20521, 'loss/train': 1.9825042486190796}
+08/30/2021 16:54:07 - INFO - __main__ - Step 20523: {'lr': 0.00048092518027503844, 'samples': 3940416, 'steps': 20522, 'loss/train': 1.2254289388656616}
+08/30/2021 16:54:07 - INFO - __main__ - Step 20524: {'lr': 0.0004809231471305208, 'samples': 3940608, 'steps': 20523, 'loss/train': 1.680452585220337}
+08/30/2021 16:54:07 - INFO - __main__ - Step 20525: {'lr': 0.0004809211138819526, 'samples': 3940800, 'steps': 20524, 'loss/train': 1.5076162815093994}
+08/30/2021 16:54:09 - INFO - __main__ - Step 20526: {'lr': 0.000480919080529335, 'samples': 3940992, 'steps': 20525, 'loss/train': 0.3464648127555847}
+08/30/2021 16:54:09 - INFO - __main__ - Step 20527: {'lr': 0.0004809170470726688, 'samples': 3941184, 'steps': 20526, 'loss/train': 1.5762031078338623}
+08/30/2021 16:54:10 - INFO - __main__ - Step 20528: {'lr': 0.00048091501351195495, 'samples': 3941376, 'steps': 20527, 'loss/train': 1.6600455045700073}
+08/30/2021 16:54:10 - INFO - __main__ - Step 20529: {'lr': 0.00048091297984719433, 'samples': 3941568, 'steps': 20528, 'loss/train': 1.404067873954773}
+08/30/2021 16:54:10 - INFO - __main__ - Step 20530: {'lr': 0.0004809109460783879, 'samples': 3941760, 'steps': 20529, 'loss/train': 0.9669828414916992}
+08/30/2021 16:54:11 - INFO - __main__ - Step 20531: {'lr': 0.0004809089122055366, 'samples': 3941952, 'steps': 20530, 'loss/train': 1.045242190361023}
+08/30/2021 16:54:12 - INFO - __main__ - Step 20532: {'lr': 0.00048090687822864125, 'samples': 3942144, 'steps': 20531, 'loss/train': 1.9114315509796143}
+08/30/2021 16:54:13 - INFO - __main__ - Step 20533: {'lr': 0.00048090484414770284, 'samples': 3942336, 'steps': 20532, 'loss/train': 1.3316726684570312}
+08/30/2021 16:54:13 - INFO - __main__ - Step 20534: {'lr': 0.00048090280996272234, 'samples': 3942528, 'steps': 20533, 'loss/train': 0.9302244782447815}
+08/30/2021 16:54:13 - INFO - __main__ - Step 20535: {'lr': 0.0004809007756737005, 'samples': 3942720, 'steps': 20534, 'loss/train': 1.5411350727081299}
+08/30/2021 16:54:14 - INFO - __main__ - Step 20536: {'lr': 0.0004808987412806384, 'samples': 3942912, 'steps': 20535, 'loss/train': 1.745179533958435}
+08/30/2021 16:54:15 - INFO - __main__ - Step 20537: {'lr': 0.0004808967067835369, 'samples': 3943104, 'steps': 20536, 'loss/train': 1.4986993074417114}
+08/30/2021 16:54:16 - INFO - __main__ - Step 20538: {'lr': 0.00048089467218239687, 'samples': 3943296, 'steps': 20537, 'loss/train': 1.336204171180725}
+08/30/2021 16:54:16 - INFO - __main__ - Step 20539: {'lr': 0.00048089263747721925, 'samples': 3943488, 'steps': 20538, 'loss/train': 1.4198871850967407}
+08/30/2021 16:54:17 - INFO - __main__ - Step 20540: {'lr': 0.000480890602668005, 'samples': 3943680, 'steps': 20539, 'loss/train': 1.5905554294586182}
+08/30/2021 16:54:17 - INFO - __main__ - Step 20541: {'lr': 0.000480888567754755, 'samples': 3943872, 'steps': 20540, 'loss/train': 0.6319172382354736}
+08/30/2021 16:54:19 - INFO - __main__ - Step 20542: {'lr': 0.0004808865327374701, 'samples': 3944064, 'steps': 20541, 'loss/train': 1.8303757905960083}
+08/30/2021 16:54:19 - INFO - __main__ - Step 20543: {'lr': 0.0004808844976161514, 'samples': 3944256, 'steps': 20542, 'loss/train': 1.858598232269287}
+08/30/2021 16:54:19 - INFO - __main__ - Step 20544: {'lr': 0.0004808824623907997, 'samples': 3944448, 'steps': 20543, 'loss/train': 1.625712275505066}
+08/30/2021 16:54:20 - INFO - __main__ - Step 20545: {'lr': 0.0004808804270614159, 'samples': 3944640, 'steps': 20544, 'loss/train': 1.5935778617858887}
+08/30/2021 16:54:20 - INFO - __main__ - Step 20546: {'lr': 0.0004808783916280008, 'samples': 3944832, 'steps': 20545, 'loss/train': 1.4860432147979736}
+08/30/2021 16:54:22 - INFO - __main__ - Step 20547: {'lr': 0.0004808763560905557, 'samples': 3945024, 'steps': 20546, 'loss/train': 1.3092674016952515}
+08/30/2021 16:54:22 - INFO - __main__ - Step 20548: {'lr': 0.0004808743204490811, 'samples': 3945216, 'steps': 20547, 'loss/train': 1.6856248378753662}
+08/30/2021 16:54:23 - INFO - __main__ - Step 20549: {'lr': 0.00048087228470357823, 'samples': 3945408, 'steps': 20548, 'loss/train': 1.1017231941223145}
+08/30/2021 16:54:23 - INFO - __main__ - Step 20550: {'lr': 0.00048087024885404777, 'samples': 3945600, 'steps': 20549, 'loss/train': 1.039155125617981}
+08/30/2021 16:54:24 - INFO - __main__ - Step 20551: {'lr': 0.00048086821290049077, 'samples': 3945792, 'steps': 20550, 'loss/train': 1.5275973081588745}
+08/30/2021 16:54:25 - INFO - __main__ - Step 20552: {'lr': 0.00048086617684290814, 'samples': 3945984, 'steps': 20551, 'loss/train': 1.4478583335876465}
+08/30/2021 16:54:25 - INFO - __main__ - Step 20553: {'lr': 0.00048086414068130077, 'samples': 3946176, 'steps': 20552, 'loss/train': 1.6303349733352661}
+08/30/2021 16:54:26 - INFO - __main__ - Step 20554: {'lr': 0.00048086210441566956, 'samples': 3946368, 'steps': 20553, 'loss/train': 1.3500038385391235}
+08/30/2021 16:54:26 - INFO - __main__ - Step 20555: {'lr': 0.00048086006804601544, 'samples': 3946560, 'steps': 20554, 'loss/train': 1.5991129875183105}
+08/30/2021 16:54:26 - INFO - __main__ - Step 20556: {'lr': 0.00048085803157233933, 'samples': 3946752, 'steps': 20555, 'loss/train': 1.458549976348877}
+08/30/2021 16:54:28 - INFO - __main__ - Step 20557: {'lr': 0.00048085599499464216, 'samples': 3946944, 'steps': 20556, 'loss/train': 1.3403385877609253}
+08/30/2021 16:54:28 - INFO - __main__ - Step 20558: {'lr': 0.0004808539583129249, 'samples': 3947136, 'steps': 20557, 'loss/train': 0.9676722288131714}
+08/30/2021 16:54:29 - INFO - __main__ - Step 20559: {'lr': 0.0004808519215271884, 'samples': 3947328, 'steps': 20558, 'loss/train': 1.908630609512329}
+08/30/2021 16:54:29 - INFO - __main__ - Step 20560: {'lr': 0.0004808498846374335, 'samples': 3947520, 'steps': 20559, 'loss/train': 1.5557866096496582}
+08/30/2021 16:54:29 - INFO - __main__ - Step 20561: {'lr': 0.0004808478476436612, 'samples': 3947712, 'steps': 20560, 'loss/train': 1.6522068977355957}
+08/30/2021 16:54:30 - INFO - __main__ - Step 20562: {'lr': 0.00048084581054587253, 'samples': 3947904, 'steps': 20561, 'loss/train': 1.812275767326355}
+08/30/2021 16:54:31 - INFO - __main__ - Step 20563: {'lr': 0.0004808437733440682, 'samples': 3948096, 'steps': 20562, 'loss/train': 1.1599609851837158}
+08/30/2021 16:54:32 - INFO - __main__ - Step 20564: {'lr': 0.0004808417360382493, 'samples': 3948288, 'steps': 20563, 'loss/train': 1.241487979888916}
+08/30/2021 16:54:32 - INFO - __main__ - Step 20565: {'lr': 0.00048083969862841667, 'samples': 3948480, 'steps': 20564, 'loss/train': 1.663413405418396}
+08/30/2021 16:54:32 - INFO - __main__ - Step 20566: {'lr': 0.00048083766111457115, 'samples': 3948672, 'steps': 20565, 'loss/train': 1.9653089046478271}
+08/30/2021 16:54:33 - INFO - __main__ - Step 20567: {'lr': 0.0004808356234967138, 'samples': 3948864, 'steps': 20566, 'loss/train': 1.7561421394348145}
+08/30/2021 16:54:34 - INFO - __main__ - Step 20568: {'lr': 0.00048083358577484547, 'samples': 3949056, 'steps': 20567, 'loss/train': 2.359469175338745}
+08/30/2021 16:54:35 - INFO - __main__ - Step 20569: {'lr': 0.0004808315479489671, 'samples': 3949248, 'steps': 20568, 'loss/train': 1.3442726135253906}
+08/30/2021 16:54:35 - INFO - __main__ - Step 20570: {'lr': 0.00048082951001907965, 'samples': 3949440, 'steps': 20569, 'loss/train': 1.7343682050704956}
+08/30/2021 16:54:35 - INFO - __main__ - Step 20571: {'lr': 0.0004808274719851839, 'samples': 3949632, 'steps': 20570, 'loss/train': 1.5264581441879272}
+08/30/2021 16:54:36 - INFO - __main__ - Step 20572: {'lr': 0.0004808254338472809, 'samples': 3949824, 'steps': 20571, 'loss/train': 1.246448278427124}
+08/30/2021 16:54:36 - INFO - __main__ - Step 20573: {'lr': 0.00048082339560537145, 'samples': 3950016, 'steps': 20572, 'loss/train': 1.5132750272750854}
+08/30/2021 16:54:38 - INFO - __main__ - Step 20574: {'lr': 0.00048082135725945665, 'samples': 3950208, 'steps': 20573, 'loss/train': 1.9364030361175537}
+08/30/2021 16:54:38 - INFO - __main__ - Step 20575: {'lr': 0.0004808193188095372, 'samples': 3950400, 'steps': 20574, 'loss/train': 1.4878729581832886}
+08/30/2021 16:54:38 - INFO - __main__ - Step 20576: {'lr': 0.0004808172802556142, 'samples': 3950592, 'steps': 20575, 'loss/train': 1.508954644203186}
+08/30/2021 16:54:39 - INFO - __main__ - Step 20577: {'lr': 0.0004808152415976885, 'samples': 3950784, 'steps': 20576, 'loss/train': 1.4431802034378052}
+08/30/2021 16:54:39 - INFO - __main__ - Step 20578: {'lr': 0.000480813202835761, 'samples': 3950976, 'steps': 20577, 'loss/train': 1.0431770086288452}
+08/30/2021 16:54:41 - INFO - __main__ - Step 20579: {'lr': 0.0004808111639698326, 'samples': 3951168, 'steps': 20578, 'loss/train': 1.4277130365371704}
+08/30/2021 16:54:41 - INFO - __main__ - Step 20580: {'lr': 0.0004808091249999043, 'samples': 3951360, 'steps': 20579, 'loss/train': 1.4637948274612427}
+08/30/2021 16:54:41 - INFO - __main__ - Step 20581: {'lr': 0.0004808070859259769, 'samples': 3951552, 'steps': 20580, 'loss/train': 2.0352847576141357}
+08/30/2021 16:54:42 - INFO - __main__ - Step 20582: {'lr': 0.0004808050467480515, 'samples': 3951744, 'steps': 20581, 'loss/train': 1.7960317134857178}
+08/30/2021 16:54:42 - INFO - __main__ - Step 20583: {'lr': 0.0004808030074661288, 'samples': 3951936, 'steps': 20582, 'loss/train': 1.302974820137024}
+08/30/2021 16:54:44 - INFO - __main__ - Step 20584: {'lr': 0.0004808009680802099, 'samples': 3952128, 'steps': 20583, 'loss/train': 1.623962640762329}
+08/30/2021 16:54:44 - INFO - __main__ - Step 20585: {'lr': 0.00048079892859029564, 'samples': 3952320, 'steps': 20584, 'loss/train': 1.8166264295578003}
+08/30/2021 16:54:45 - INFO - __main__ - Step 20586: {'lr': 0.00048079688899638684, 'samples': 3952512, 'steps': 20585, 'loss/train': 2.028949022293091}
+08/30/2021 16:54:45 - INFO - __main__ - Step 20587: {'lr': 0.0004807948492984846, 'samples': 3952704, 'steps': 20586, 'loss/train': 2.6005401611328125}
+08/30/2021 16:54:45 - INFO - __main__ - Step 20588: {'lr': 0.0004807928094965898, 'samples': 3952896, 'steps': 20587, 'loss/train': 1.4047460556030273}
+08/30/2021 16:54:47 - INFO - __main__ - Step 20589: {'lr': 0.0004807907695907032, 'samples': 3953088, 'steps': 20588, 'loss/train': 1.6047488451004028}
+08/30/2021 16:54:48 - INFO - __main__ - Step 20590: {'lr': 0.000480788729580826, 'samples': 3953280, 'steps': 20589, 'loss/train': 1.1475815773010254}
+08/30/2021 16:54:48 - INFO - __main__ - Step 20591: {'lr': 0.00048078668946695887, 'samples': 3953472, 'steps': 20590, 'loss/train': 1.7670137882232666}
+08/30/2021 16:54:49 - INFO - __main__ - Step 20592: {'lr': 0.0004807846492491028, 'samples': 3953664, 'steps': 20591, 'loss/train': 2.0738556385040283}
+08/30/2021 16:54:49 - INFO - __main__ - Step 20593: {'lr': 0.0004807826089272588, 'samples': 3953856, 'steps': 20592, 'loss/train': 0.7206501960754395}
+08/30/2021 16:54:50 - INFO - __main__ - Step 20594: {'lr': 0.0004807805685014277, 'samples': 3954048, 'steps': 20593, 'loss/train': 1.4145188331604004}
+08/30/2021 16:54:51 - INFO - __main__ - Step 20595: {'lr': 0.00048077852797161034, 'samples': 3954240, 'steps': 20594, 'loss/train': 1.3185465335845947}
+08/30/2021 16:54:51 - INFO - __main__ - Step 20596: {'lr': 0.0004807764873378079, 'samples': 3954432, 'steps': 20595, 'loss/train': 1.6892168521881104}
+08/30/2021 16:54:52 - INFO - __main__ - Step 20597: {'lr': 0.000480774446600021, 'samples': 3954624, 'steps': 20596, 'loss/train': 0.9227716326713562}
+08/30/2021 16:54:52 - INFO - __main__ - Step 20598: {'lr': 0.00048077240575825075, 'samples': 3954816, 'steps': 20597, 'loss/train': 1.5762578248977661}
+08/30/2021 16:54:54 - INFO - __main__ - Step 20599: {'lr': 0.000480770364812498, 'samples': 3955008, 'steps': 20598, 'loss/train': 1.6765204668045044}
+08/30/2021 16:54:55 - INFO - __main__ - Step 20600: {'lr': 0.0004807683237627637, 'samples': 3955200, 'steps': 20599, 'loss/train': 1.3946428298950195}
+08/30/2021 16:54:55 - INFO - __main__ - Step 20601: {'lr': 0.0004807662826090488, 'samples': 3955392, 'steps': 20600, 'loss/train': 1.2109757661819458}
+08/30/2021 16:54:55 - INFO - __main__ - Step 20602: {'lr': 0.00048076424135135406, 'samples': 3955584, 'steps': 20601, 'loss/train': 1.6038706302642822}
+08/30/2021 16:54:56 - INFO - __main__ - Step 20603: {'lr': 0.00048076219998968055, 'samples': 3955776, 'steps': 20602, 'loss/train': 0.7600698471069336}
+08/30/2021 16:54:56 - INFO - __main__ - Step 20604: {'lr': 0.0004807601585240292, 'samples': 3955968, 'steps': 20603, 'loss/train': 1.781967282295227}
+08/30/2021 16:54:58 - INFO - __main__ - Step 20605: {'lr': 0.0004807581169544009, 'samples': 3956160, 'steps': 20604, 'loss/train': 0.2823835611343384}
+08/30/2021 16:54:58 - INFO - __main__ - Step 20606: {'lr': 0.00048075607528079645, 'samples': 3956352, 'steps': 20605, 'loss/train': 1.9294631481170654}
+08/30/2021 16:54:58 - INFO - __main__ - Step 20607: {'lr': 0.0004807540335032169, 'samples': 3956544, 'steps': 20606, 'loss/train': 1.2828264236450195}
+08/30/2021 16:54:59 - INFO - __main__ - Step 20608: {'lr': 0.0004807519916216633, 'samples': 3956736, 'steps': 20607, 'loss/train': 0.6966751217842102}
+08/30/2021 16:54:59 - INFO - __main__ - Step 20609: {'lr': 0.0004807499496361362, 'samples': 3956928, 'steps': 20608, 'loss/train': 1.4355417490005493}
+08/30/2021 16:55:00 - INFO - __main__ - Step 20610: {'lr': 0.00048074790754663686, 'samples': 3957120, 'steps': 20609, 'loss/train': 1.3458967208862305}
+08/30/2021 16:55:01 - INFO - __main__ - Step 20611: {'lr': 0.000480745865353166, 'samples': 3957312, 'steps': 20610, 'loss/train': 1.2405227422714233}
+08/30/2021 16:55:01 - INFO - __main__ - Step 20612: {'lr': 0.0004807438230557247, 'samples': 3957504, 'steps': 20611, 'loss/train': 1.2547762393951416}
+08/30/2021 16:55:02 - INFO - __main__ - Step 20613: {'lr': 0.00048074178065431373, 'samples': 3957696, 'steps': 20612, 'loss/train': 1.6068294048309326}
+08/30/2021 16:55:02 - INFO - __main__ - Step 20614: {'lr': 0.0004807397381489341, 'samples': 3957888, 'steps': 20613, 'loss/train': 1.6361725330352783}
+08/30/2021 16:55:04 - INFO - __main__ - Step 20615: {'lr': 0.00048073769553958666, 'samples': 3958080, 'steps': 20614, 'loss/train': 1.3007580041885376}
+08/30/2021 16:55:04 - INFO - __main__ - Step 20616: {'lr': 0.00048073565282627246, 'samples': 3958272, 'steps': 20615, 'loss/train': 1.7681808471679688}
+08/30/2021 16:55:05 - INFO - __main__ - Step 20617: {'lr': 0.0004807336100089923, 'samples': 3958464, 'steps': 20616, 'loss/train': 2.222637414932251}
+08/30/2021 16:55:05 - INFO - __main__ - Step 20618: {'lr': 0.0004807315670877471, 'samples': 3958656, 'steps': 20617, 'loss/train': 1.2972687482833862}
+08/30/2021 16:55:05 - INFO - __main__ - Step 20619: {'lr': 0.00048072952406253783, 'samples': 3958848, 'steps': 20618, 'loss/train': 1.7866398096084595}
+08/30/2021 16:55:06 - INFO - __main__ - Step 20620: {'lr': 0.00048072748093336536, 'samples': 3959040, 'steps': 20619, 'loss/train': 1.496514081954956}
+08/30/2021 16:55:07 - INFO - __main__ - Step 20621: {'lr': 0.00048072543770023076, 'samples': 3959232, 'steps': 20620, 'loss/train': 0.11282919347286224}
+08/30/2021 16:55:08 - INFO - __main__ - Step 20622: {'lr': 0.0004807233943631347, 'samples': 3959424, 'steps': 20621, 'loss/train': 1.8915866613388062}
+08/30/2021 16:55:08 - INFO - __main__ - Step 20623: {'lr': 0.0004807213509220784, 'samples': 3959616, 'steps': 20622, 'loss/train': 1.8186583518981934}
+08/30/2021 16:55:09 - INFO - __main__ - Step 20624: {'lr': 0.0004807193073770625, 'samples': 3959808, 'steps': 20623, 'loss/train': 1.4623253345489502}
+08/30/2021 16:55:09 - INFO - __main__ - Step 20625: {'lr': 0.0004807172637280881, 'samples': 3960000, 'steps': 20624, 'loss/train': 2.0191798210144043}
+08/30/2021 16:55:09 - INFO - __main__ - Step 20626: {'lr': 0.000480715219975156, 'samples': 3960192, 'steps': 20625, 'loss/train': 1.9373518228530884}
+08/30/2021 16:55:11 - INFO - __main__ - Step 20627: {'lr': 0.0004807131761182672, 'samples': 3960384, 'steps': 20626, 'loss/train': 0.041183751076459885}
+08/30/2021 16:55:12 - INFO - __main__ - Step 20628: {'lr': 0.00048071113215742263, 'samples': 3960576, 'steps': 20627, 'loss/train': 1.5153496265411377}
+08/30/2021 16:55:12 - INFO - __main__ - Step 20629: {'lr': 0.00048070908809262316, 'samples': 3960768, 'steps': 20628, 'loss/train': 1.4794275760650635}
+08/30/2021 16:55:12 - INFO - __main__ - Step 20630: {'lr': 0.0004807070439238698, 'samples': 3960960, 'steps': 20629, 'loss/train': 1.4660319089889526}
+08/30/2021 16:55:13 - INFO - __main__ - Step 20631: {'lr': 0.0004807049996511633, 'samples': 3961152, 'steps': 20630, 'loss/train': 1.8759181499481201}
+08/30/2021 16:55:13 - INFO - __main__ - Step 20632: {'lr': 0.00048070295527450474, 'samples': 3961344, 'steps': 20631, 'loss/train': 0.585408091545105}
+08/30/2021 16:55:14 - INFO - __main__ - Step 20633: {'lr': 0.000480700910793895, 'samples': 3961536, 'steps': 20632, 'loss/train': 1.9259815216064453}
+08/30/2021 16:55:15 - INFO - __main__ - Step 20634: {'lr': 0.000480698866209335, 'samples': 3961728, 'steps': 20633, 'loss/train': 1.8975882530212402}
+08/30/2021 16:55:15 - INFO - __main__ - Step 20635: {'lr': 0.0004806968215208256, 'samples': 3961920, 'steps': 20634, 'loss/train': 1.6896079778671265}
+08/30/2021 16:55:16 - INFO - __main__ - Step 20636: {'lr': 0.0004806947767283678, 'samples': 3962112, 'steps': 20635, 'loss/train': 1.4961246252059937}
+08/30/2021 16:55:16 - INFO - __main__ - Step 20637: {'lr': 0.0004806927318319625, 'samples': 3962304, 'steps': 20636, 'loss/train': 1.7835643291473389}
+08/30/2021 16:55:18 - INFO - __main__ - Step 20638: {'lr': 0.0004806906868316106, 'samples': 3962496, 'steps': 20637, 'loss/train': 1.540489673614502}
+08/30/2021 16:55:18 - INFO - __main__ - Step 20639: {'lr': 0.000480688641727313, 'samples': 3962688, 'steps': 20638, 'loss/train': 1.471384048461914}
+08/30/2021 16:55:19 - INFO - __main__ - Step 20640: {'lr': 0.00048068659651907076, 'samples': 3962880, 'steps': 20639, 'loss/train': 2.1339805126190186}
+08/30/2021 16:55:19 - INFO - __main__ - Step 20641: {'lr': 0.0004806845512068846, 'samples': 3963072, 'steps': 20640, 'loss/train': 1.4799166917800903}
+08/30/2021 16:55:19 - INFO - __main__ - Step 20642: {'lr': 0.00048068250579075554, 'samples': 3963264, 'steps': 20641, 'loss/train': 1.211970329284668}
+08/30/2021 16:55:21 - INFO - __main__ - Step 20643: {'lr': 0.00048068046027068456, 'samples': 3963456, 'steps': 20642, 'loss/train': 1.1890201568603516}
+08/30/2021 16:55:22 - INFO - __main__ - Step 20644: {'lr': 0.0004806784146466726, 'samples': 3963648, 'steps': 20643, 'loss/train': 1.6303956508636475}
+08/30/2021 16:55:22 - INFO - __main__ - Step 20645: {'lr': 0.00048067636891872036, 'samples': 3963840, 'steps': 20644, 'loss/train': 2.086669921875}
+08/30/2021 16:55:22 - INFO - __main__ - Step 20646: {'lr': 0.00048067432308682894, 'samples': 3964032, 'steps': 20645, 'loss/train': 1.1525413990020752}
+08/30/2021 16:55:23 - INFO - __main__ - Step 20647: {'lr': 0.0004806722771509993, 'samples': 3964224, 'steps': 20646, 'loss/train': 1.4894037246704102}
+08/30/2021 16:55:24 - INFO - __main__ - Step 20648: {'lr': 0.0004806702311112322, 'samples': 3964416, 'steps': 20647, 'loss/train': 1.3572239875793457}
+08/30/2021 16:55:25 - INFO - __main__ - Step 20649: {'lr': 0.0004806681849675287, 'samples': 3964608, 'steps': 20648, 'loss/train': 1.565950632095337}
+08/30/2021 16:55:25 - INFO - __main__ - Step 20650: {'lr': 0.00048066613871988967, 'samples': 3964800, 'steps': 20649, 'loss/train': 1.4098584651947021}
+08/30/2021 16:55:25 - INFO - __main__ - Step 20651: {'lr': 0.00048066409236831607, 'samples': 3964992, 'steps': 20650, 'loss/train': 1.4266493320465088}
+08/30/2021 16:55:26 - INFO - __main__ - Step 20652: {'lr': 0.0004806620459128087, 'samples': 3965184, 'steps': 20651, 'loss/train': 1.2918858528137207}
+08/30/2021 16:55:26 - INFO - __main__ - Step 20653: {'lr': 0.0004806599993533687, 'samples': 3965376, 'steps': 20652, 'loss/train': 1.5336929559707642}
+08/30/2021 16:55:28 - INFO - __main__ - Step 20654: {'lr': 0.00048065795268999677, 'samples': 3965568, 'steps': 20653, 'loss/train': 1.3345450162887573}
+08/30/2021 16:55:28 - INFO - __main__ - Step 20655: {'lr': 0.00048065590592269393, 'samples': 3965760, 'steps': 20654, 'loss/train': 2.247145652770996}
+08/30/2021 16:55:28 - INFO - __main__ - Step 20656: {'lr': 0.00048065385905146114, 'samples': 3965952, 'steps': 20655, 'loss/train': 1.7187037467956543}
+08/30/2021 16:55:29 - INFO - __main__ - Step 20657: {'lr': 0.0004806518120762993, 'samples': 3966144, 'steps': 20656, 'loss/train': 1.3709335327148438}
+08/30/2021 16:55:29 - INFO - __main__ - Step 20658: {'lr': 0.00048064976499720923, 'samples': 3966336, 'steps': 20657, 'loss/train': 2.0189366340637207}
+08/30/2021 16:55:31 - INFO - __main__ - Step 20659: {'lr': 0.000480647717814192, 'samples': 3966528, 'steps': 20658, 'loss/train': 1.8227946758270264}
+08/30/2021 16:55:31 - INFO - __main__ - Step 20660: {'lr': 0.0004806456705272484, 'samples': 3966720, 'steps': 20659, 'loss/train': 1.3422613143920898}
+08/30/2021 16:55:31 - INFO - __main__ - Step 20661: {'lr': 0.0004806436231363795, 'samples': 3966912, 'steps': 20660, 'loss/train': 1.457248568534851}
+08/30/2021 16:55:32 - INFO - __main__ - Step 20662: {'lr': 0.00048064157564158607, 'samples': 3967104, 'steps': 20661, 'loss/train': 1.3451411724090576}
+08/30/2021 16:55:32 - INFO - __main__ - Step 20663: {'lr': 0.00048063952804286913, 'samples': 3967296, 'steps': 20662, 'loss/train': 2.052534341812134}
+08/30/2021 16:55:34 - INFO - __main__ - Step 20664: {'lr': 0.0004806374803402296, 'samples': 3967488, 'steps': 20663, 'loss/train': 0.9287270307540894}
+08/30/2021 16:55:35 - INFO - __main__ - Step 20665: {'lr': 0.00048063543253366837, 'samples': 3967680, 'steps': 20664, 'loss/train': 1.0546422004699707}
+08/30/2021 16:55:35 - INFO - __main__ - Step 20666: {'lr': 0.0004806333846231864, 'samples': 3967872, 'steps': 20665, 'loss/train': 0.13127905130386353}
+08/30/2021 16:55:35 - INFO - __main__ - Step 20667: {'lr': 0.00048063133660878455, 'samples': 3968064, 'steps': 20666, 'loss/train': 1.5059527158737183}
+08/30/2021 16:55:36 - INFO - __main__ - Step 20668: {'lr': 0.00048062928849046377, 'samples': 3968256, 'steps': 20667, 'loss/train': 1.7320287227630615}
+08/30/2021 16:55:36 - INFO - __main__ - Step 20669: {'lr': 0.00048062724026822504, 'samples': 3968448, 'steps': 20668, 'loss/train': 0.11046398431062698}
+08/30/2021 16:55:38 - INFO - __main__ - Step 20670: {'lr': 0.00048062519194206916, 'samples': 3968640, 'steps': 20669, 'loss/train': 0.32149767875671387}
+08/30/2021 16:55:38 - INFO - __main__ - Step 20671: {'lr': 0.0004806231435119972, 'samples': 3968832, 'steps': 20670, 'loss/train': 1.7202013731002808}
+08/30/2021 16:55:38 - INFO - __main__ - Step 20672: {'lr': 0.00048062109497800997, 'samples': 3969024, 'steps': 20671, 'loss/train': 1.3532297611236572}
+08/30/2021 16:55:39 - INFO - __main__ - Step 20673: {'lr': 0.00048061904634010845, 'samples': 3969216, 'steps': 20672, 'loss/train': 1.7341771125793457}
+08/30/2021 16:55:39 - INFO - __main__ - Step 20674: {'lr': 0.0004806169975982935, 'samples': 3969408, 'steps': 20673, 'loss/train': 1.6083941459655762}
+08/30/2021 16:55:41 - INFO - __main__ - Step 20675: {'lr': 0.0004806149487525662, 'samples': 3969600, 'steps': 20674, 'loss/train': 1.7800225019454956}
+08/30/2021 16:55:41 - INFO - __main__ - Step 20676: {'lr': 0.0004806128998029272, 'samples': 3969792, 'steps': 20675, 'loss/train': 2.0995993614196777}
+08/30/2021 16:55:41 - INFO - __main__ - Step 20677: {'lr': 0.0004806108507493777, 'samples': 3969984, 'steps': 20676, 'loss/train': 1.972775936126709}
+08/30/2021 16:55:42 - INFO - __main__ - Step 20678: {'lr': 0.0004806088015919185, 'samples': 3970176, 'steps': 20677, 'loss/train': 5.629034996032715}
+08/30/2021 16:55:42 - INFO - __main__ - Step 20679: {'lr': 0.0004806067523305505, 'samples': 3970368, 'steps': 20678, 'loss/train': 2.0154056549072266}
+08/30/2021 16:55:43 - INFO - __main__ - Step 20680: {'lr': 0.0004806047029652747, 'samples': 3970560, 'steps': 20679, 'loss/train': 1.756956696510315}
+08/30/2021 16:55:44 - INFO - __main__ - Step 20681: {'lr': 0.00048060265349609193, 'samples': 3970752, 'steps': 20680, 'loss/train': 1.3318066596984863}
+08/30/2021 16:55:44 - INFO - __main__ - Step 20682: {'lr': 0.0004806006039230032, 'samples': 3970944, 'steps': 20681, 'loss/train': 1.3747334480285645}
+08/30/2021 16:55:45 - INFO - __main__ - Step 20683: {'lr': 0.0004805985542460094, 'samples': 3971136, 'steps': 20682, 'loss/train': 1.322189450263977}
+08/30/2021 16:55:45 - INFO - __main__ - Step 20684: {'lr': 0.00048059650446511136, 'samples': 3971328, 'steps': 20683, 'loss/train': 0.8517647981643677}
+08/30/2021 16:55:46 - INFO - __main__ - Step 20685: {'lr': 0.00048059445458031023, 'samples': 3971520, 'steps': 20684, 'loss/train': 1.3851511478424072}
+08/30/2021 16:55:47 - INFO - __main__ - Step 20686: {'lr': 0.0004805924045916067, 'samples': 3971712, 'steps': 20685, 'loss/train': 1.5475938320159912}
+08/30/2021 16:55:48 - INFO - __main__ - Step 20687: {'lr': 0.00048059035449900185, 'samples': 3971904, 'steps': 20686, 'loss/train': 1.7559659481048584}
+08/30/2021 16:55:48 - INFO - __main__ - Step 20688: {'lr': 0.0004805883043024965, 'samples': 3972096, 'steps': 20687, 'loss/train': 0.40264657139778137}
+08/30/2021 16:55:48 - INFO - __main__ - Step 20689: {'lr': 0.0004805862540020917, 'samples': 3972288, 'steps': 20688, 'loss/train': 0.4182220697402954}
+08/30/2021 16:55:49 - INFO - __main__ - Step 20690: {'lr': 0.0004805842035977882, 'samples': 3972480, 'steps': 20689, 'loss/train': 1.4698597192764282}
+08/30/2021 16:55:49 - INFO - __main__ - Step 20691: {'lr': 0.00048058215308958703, 'samples': 3972672, 'steps': 20690, 'loss/train': 1.8014353513717651}
+08/30/2021 16:55:51 - INFO - __main__ - Step 20692: {'lr': 0.00048058010247748904, 'samples': 3972864, 'steps': 20691, 'loss/train': 0.4119693338871002}
+08/30/2021 16:55:51 - INFO - __main__ - Step 20693: {'lr': 0.0004805780517614954, 'samples': 3973056, 'steps': 20692, 'loss/train': 1.5545519590377808}
+08/30/2021 16:55:52 - INFO - __main__ - Step 20694: {'lr': 0.0004805760009416067, 'samples': 3973248, 'steps': 20693, 'loss/train': 2.980133056640625}
+08/30/2021 16:55:52 - INFO - __main__ - Step 20695: {'lr': 0.000480573950017824, 'samples': 3973440, 'steps': 20694, 'loss/train': 0.15593315660953522}
+08/30/2021 16:55:52 - INFO - __main__ - Step 20696: {'lr': 0.0004805718989901483, 'samples': 3973632, 'steps': 20695, 'loss/train': 1.651999592781067}
+08/30/2021 16:55:54 - INFO - __main__ - Step 20697: {'lr': 0.00048056984785858046, 'samples': 3973824, 'steps': 20696, 'loss/train': 0.1327599734067917}
+08/30/2021 16:55:55 - INFO - __main__ - Step 20698: {'lr': 0.0004805677966231214, 'samples': 3974016, 'steps': 20697, 'loss/train': 1.5303266048431396}
+08/30/2021 16:55:55 - INFO - __main__ - Step 20699: {'lr': 0.00048056574528377205, 'samples': 3974208, 'steps': 20698, 'loss/train': 1.2969508171081543}
+08/30/2021 16:55:55 - INFO - __main__ - Step 20700: {'lr': 0.00048056369384053335, 'samples': 3974400, 'steps': 20699, 'loss/train': 1.381152629852295}
+08/30/2021 16:55:56 - INFO - __main__ - Step 20701: {'lr': 0.00048056164229340613, 'samples': 3974592, 'steps': 20700, 'loss/train': 1.2419464588165283}
+08/30/2021 16:55:57 - INFO - __main__ - Step 20702: {'lr': 0.0004805595906423914, 'samples': 3974784, 'steps': 20701, 'loss/train': 1.3216350078582764}
+08/30/2021 16:55:58 - INFO - __main__ - Step 20703: {'lr': 0.00048055753888749013, 'samples': 3974976, 'steps': 20702, 'loss/train': 2.056077480316162}
+08/30/2021 16:55:58 - INFO - __main__ - Step 20704: {'lr': 0.0004805554870287032, 'samples': 3975168, 'steps': 20703, 'loss/train': 1.2361171245574951}
+08/30/2021 16:55:58 - INFO - __main__ - Step 20705: {'lr': 0.0004805534350660315, 'samples': 3975360, 'steps': 20704, 'loss/train': 1.7923864126205444}
+08/30/2021 16:55:59 - INFO - __main__ - Step 20706: {'lr': 0.000480551382999476, 'samples': 3975552, 'steps': 20705, 'loss/train': 1.4378912448883057}
+08/30/2021 16:56:00 - INFO - __main__ - Step 20707: {'lr': 0.00048054933082903754, 'samples': 3975744, 'steps': 20706, 'loss/train': 1.7227957248687744}
+08/30/2021 16:56:01 - INFO - __main__ - Step 20708: {'lr': 0.00048054727855471717, 'samples': 3975936, 'steps': 20707, 'loss/train': 1.7430933713912964}
+08/30/2021 16:56:01 - INFO - __main__ - Step 20709: {'lr': 0.00048054522617651575, 'samples': 3976128, 'steps': 20708, 'loss/train': 1.4573649168014526}
+08/30/2021 16:56:01 - INFO - __main__ - Step 20710: {'lr': 0.0004805431736944342, 'samples': 3976320, 'steps': 20709, 'loss/train': 1.2537758350372314}
+08/30/2021 16:56:02 - INFO - __main__ - Step 20711: {'lr': 0.0004805411211084735, 'samples': 3976512, 'steps': 20710, 'loss/train': 0.9819672703742981}
+08/30/2021 16:56:03 - INFO - __main__ - Step 20712: {'lr': 0.0004805390684186344, 'samples': 3976704, 'steps': 20711, 'loss/train': 2.3263676166534424}
+08/30/2021 16:56:04 - INFO - __main__ - Step 20713: {'lr': 0.00048053701562491804, 'samples': 3976896, 'steps': 20712, 'loss/train': 1.2889982461929321}
+08/30/2021 16:56:04 - INFO - __main__ - Step 20714: {'lr': 0.0004805349627273253, 'samples': 3977088, 'steps': 20713, 'loss/train': 1.423947811126709}
+08/30/2021 16:56:05 - INFO - __main__ - Step 20715: {'lr': 0.00048053290972585697, 'samples': 3977280, 'steps': 20714, 'loss/train': 1.1521159410476685}
+08/30/2021 16:56:05 - INFO - __main__ - Step 20716: {'lr': 0.0004805308566205141, 'samples': 3977472, 'steps': 20715, 'loss/train': 1.5645651817321777}
+08/30/2021 16:56:05 - INFO - __main__ - Step 20717: {'lr': 0.00048052880341129764, 'samples': 3977664, 'steps': 20716, 'loss/train': 0.8094602823257446}
+08/30/2021 16:56:07 - INFO - __main__ - Step 20718: {'lr': 0.00048052675009820837, 'samples': 3977856, 'steps': 20717, 'loss/train': 1.7630436420440674}
+08/30/2021 16:56:07 - INFO - __main__ - Step 20719: {'lr': 0.0004805246966812474, 'samples': 3978048, 'steps': 20718, 'loss/train': 2.433021068572998}
+08/30/2021 16:56:07 - INFO - __main__ - Step 20720: {'lr': 0.0004805226431604155, 'samples': 3978240, 'steps': 20719, 'loss/train': 1.4015146493911743}
+08/30/2021 16:56:08 - INFO - __main__ - Step 20721: {'lr': 0.00048052058953571366, 'samples': 3978432, 'steps': 20720, 'loss/train': 1.4894248247146606}
+08/30/2021 16:56:08 - INFO - __main__ - Step 20722: {'lr': 0.0004805185358071428, 'samples': 3978624, 'steps': 20721, 'loss/train': 1.6452594995498657}
+08/30/2021 16:56:10 - INFO - __main__ - Step 20723: {'lr': 0.0004805164819747038, 'samples': 3978816, 'steps': 20722, 'loss/train': 1.3686636686325073}
+08/30/2021 16:56:10 - INFO - __main__ - Step 20724: {'lr': 0.0004805144280383977, 'samples': 3979008, 'steps': 20723, 'loss/train': 1.8824739456176758}
+08/30/2021 16:56:11 - INFO - __main__ - Step 20725: {'lr': 0.00048051237399822534, 'samples': 3979200, 'steps': 20724, 'loss/train': 1.6183282136917114}
+08/30/2021 16:56:11 - INFO - __main__ - Step 20726: {'lr': 0.00048051031985418764, 'samples': 3979392, 'steps': 20725, 'loss/train': 1.4658023118972778}
+08/30/2021 16:56:11 - INFO - __main__ - Step 20727: {'lr': 0.0004805082656062856, 'samples': 3979584, 'steps': 20726, 'loss/train': 1.5528312921524048}
+08/30/2021 16:56:13 - INFO - __main__ - Step 20728: {'lr': 0.00048050621125451996, 'samples': 3979776, 'steps': 20727, 'loss/train': 1.1035397052764893}
+08/30/2021 16:56:13 - INFO - __main__ - Step 20729: {'lr': 0.00048050415679889194, 'samples': 3979968, 'steps': 20728, 'loss/train': 2.0017354488372803}
+08/30/2021 16:56:14 - INFO - __main__ - Step 20730: {'lr': 0.0004805021022394022, 'samples': 3980160, 'steps': 20729, 'loss/train': 1.5923737287521362}
+08/30/2021 16:56:14 - INFO - __main__ - Step 20731: {'lr': 0.0004805000475760518, 'samples': 3980352, 'steps': 20730, 'loss/train': 1.7138861417770386}
+08/30/2021 16:56:14 - INFO - __main__ - Step 20732: {'lr': 0.0004804979928088417, 'samples': 3980544, 'steps': 20731, 'loss/train': 1.8164052963256836}
+08/30/2021 16:56:16 - INFO - __main__ - Step 20733: {'lr': 0.0004804959379377727, 'samples': 3980736, 'steps': 20732, 'loss/train': 1.570721983909607}
+08/30/2021 16:56:16 - INFO - __main__ - Step 20734: {'lr': 0.00048049388296284576, 'samples': 3980928, 'steps': 20733, 'loss/train': 0.9652804136276245}
+08/30/2021 16:56:17 - INFO - __main__ - Step 20735: {'lr': 0.00048049182788406186, 'samples': 3981120, 'steps': 20734, 'loss/train': 1.8427886962890625}
+08/30/2021 16:56:17 - INFO - __main__ - Step 20736: {'lr': 0.0004804897727014219, 'samples': 3981312, 'steps': 20735, 'loss/train': 2.443028688430786}
+08/30/2021 16:56:17 - INFO - __main__ - Step 20737: {'lr': 0.0004804877174149268, 'samples': 3981504, 'steps': 20736, 'loss/train': 0.9933156967163086}
+08/30/2021 16:56:18 - INFO - __main__ - Step 20738: {'lr': 0.00048048566202457747, 'samples': 3981696, 'steps': 20737, 'loss/train': 1.6103301048278809}
+08/30/2021 16:56:19 - INFO - __main__ - Step 20739: {'lr': 0.00048048360653037494, 'samples': 3981888, 'steps': 20738, 'loss/train': 1.3910224437713623}
+08/30/2021 16:56:20 - INFO - __main__ - Step 20740: {'lr': 0.00048048155093231994, 'samples': 3982080, 'steps': 20739, 'loss/train': 1.2703614234924316}
+08/30/2021 16:56:20 - INFO - __main__ - Step 20741: {'lr': 0.00048047949523041355, 'samples': 3982272, 'steps': 20740, 'loss/train': 0.5967580676078796}
+08/30/2021 16:56:21 - INFO - __main__ - Step 20742: {'lr': 0.0004804774394246567, 'samples': 3982464, 'steps': 20741, 'loss/train': 1.376112461090088}
+08/30/2021 16:56:21 - INFO - __main__ - Step 20743: {'lr': 0.0004804753835150503, 'samples': 3982656, 'steps': 20742, 'loss/train': 1.4000831842422485}
+08/30/2021 16:56:23 - INFO - __main__ - Step 20744: {'lr': 0.0004804733275015951, 'samples': 3982848, 'steps': 20743, 'loss/train': 1.4413738250732422}
+08/30/2021 16:56:24 - INFO - __main__ - Step 20745: {'lr': 0.0004804712713842923, 'samples': 3983040, 'steps': 20744, 'loss/train': 1.568382740020752}
+08/30/2021 16:56:24 - INFO - __main__ - Step 20746: {'lr': 0.0004804692151631427, 'samples': 3983232, 'steps': 20745, 'loss/train': 1.5668437480926514}
+08/30/2021 16:56:24 - INFO - __main__ - Step 20747: {'lr': 0.00048046715883814716, 'samples': 3983424, 'steps': 20746, 'loss/train': 1.9023722410202026}
+08/30/2021 16:56:25 - INFO - __main__ - Step 20748: {'lr': 0.00048046510240930674, 'samples': 3983616, 'steps': 20747, 'loss/train': 0.3020634055137634}
+08/30/2021 16:56:27 - INFO - __main__ - Step 20749: {'lr': 0.00048046304587662225, 'samples': 3983808, 'steps': 20748, 'loss/train': 1.6442160606384277}
+08/30/2021 16:56:27 - INFO - __main__ - Step 20750: {'lr': 0.00048046098924009467, 'samples': 3984000, 'steps': 20749, 'loss/train': 1.6216952800750732}
+08/30/2021 16:56:27 - INFO - __main__ - Step 20751: {'lr': 0.00048045893249972497, 'samples': 3984192, 'steps': 20750, 'loss/train': 1.441290259361267}
+08/30/2021 16:56:28 - INFO - __main__ - Step 20752: {'lr': 0.000480456875655514, 'samples': 3984384, 'steps': 20751, 'loss/train': 1.5465011596679688}
+08/30/2021 16:56:28 - INFO - __main__ - Step 20753: {'lr': 0.0004804548187074628, 'samples': 3984576, 'steps': 20752, 'loss/train': 1.6776716709136963}
+08/30/2021 16:56:28 - INFO - __main__ - Step 20754: {'lr': 0.0004804527616555721, 'samples': 3984768, 'steps': 20753, 'loss/train': 1.7566523551940918}
+08/30/2021 16:56:30 - INFO - __main__ - Step 20755: {'lr': 0.00048045070449984295, 'samples': 3984960, 'steps': 20754, 'loss/train': 1.4441533088684082}
+08/30/2021 16:56:30 - INFO - __main__ - Step 20756: {'lr': 0.0004804486472402763, 'samples': 3985152, 'steps': 20755, 'loss/train': 1.2981563806533813}
+08/30/2021 16:56:31 - INFO - __main__ - Step 20757: {'lr': 0.0004804465898768731, 'samples': 3985344, 'steps': 20756, 'loss/train': 2.227184772491455}
+08/30/2021 16:56:31 - INFO - __main__ - Step 20758: {'lr': 0.00048044453240963413, 'samples': 3985536, 'steps': 20757, 'loss/train': 2.007504463195801}
+08/30/2021 16:56:31 - INFO - __main__ - Step 20759: {'lr': 0.00048044247483856043, 'samples': 3985728, 'steps': 20758, 'loss/train': 2.0310137271881104}
+08/30/2021 16:56:33 - INFO - __main__ - Step 20760: {'lr': 0.00048044041716365296, 'samples': 3985920, 'steps': 20759, 'loss/train': 0.8354974985122681}
+08/30/2021 16:56:33 - INFO - __main__ - Step 20761: {'lr': 0.00048043835938491253, 'samples': 3986112, 'steps': 20760, 'loss/train': 1.1922798156738281}
+08/30/2021 16:56:34 - INFO - __main__ - Step 20762: {'lr': 0.0004804363015023402, 'samples': 3986304, 'steps': 20761, 'loss/train': 1.7823498249053955}
+08/30/2021 16:56:34 - INFO - __main__ - Step 20763: {'lr': 0.00048043424351593676, 'samples': 3986496, 'steps': 20762, 'loss/train': 2.0763256549835205}
+08/30/2021 16:56:34 - INFO - __main__ - Step 20764: {'lr': 0.0004804321854257032, 'samples': 3986688, 'steps': 20763, 'loss/train': 1.223707914352417}
+08/30/2021 16:56:36 - INFO - __main__ - Step 20765: {'lr': 0.0004804301272316405, 'samples': 3986880, 'steps': 20764, 'loss/train': 0.4089663326740265}
+08/30/2021 16:56:36 - INFO - __main__ - Step 20766: {'lr': 0.0004804280689337496, 'samples': 3987072, 'steps': 20765, 'loss/train': 1.802085280418396}
+08/30/2021 16:56:37 - INFO - __main__ - Step 20767: {'lr': 0.00048042601053203125, 'samples': 3987264, 'steps': 20766, 'loss/train': 1.5809887647628784}
+08/30/2021 16:56:37 - INFO - __main__ - Step 20768: {'lr': 0.00048042395202648646, 'samples': 3987456, 'steps': 20767, 'loss/train': 1.6898623704910278}
+08/30/2021 16:56:37 - INFO - __main__ - Step 20769: {'lr': 0.00048042189341711636, 'samples': 3987648, 'steps': 20768, 'loss/train': 1.701935052871704}
+08/30/2021 16:56:38 - INFO - __main__ - Step 20770: {'lr': 0.0004804198347039216, 'samples': 3987840, 'steps': 20769, 'loss/train': 2.0882790088653564}
+08/30/2021 16:56:39 - INFO - __main__ - Step 20771: {'lr': 0.0004804177758869032, 'samples': 3988032, 'steps': 20770, 'loss/train': 1.356032133102417}
+08/30/2021 16:56:40 - INFO - __main__ - Step 20772: {'lr': 0.0004804157169660622, 'samples': 3988224, 'steps': 20771, 'loss/train': 2.3334457874298096}
+08/30/2021 16:56:40 - INFO - __main__ - Step 20773: {'lr': 0.00048041365794139934, 'samples': 3988416, 'steps': 20772, 'loss/train': 0.2663647532463074}
+08/30/2021 16:56:41 - INFO - __main__ - Step 20774: {'lr': 0.00048041159881291574, 'samples': 3988608, 'steps': 20773, 'loss/train': 1.5477395057678223}
+08/30/2021 16:56:41 - INFO - __main__ - Step 20775: {'lr': 0.0004804095395806122, 'samples': 3988800, 'steps': 20774, 'loss/train': 1.612539529800415}
+08/30/2021 16:56:43 - INFO - __main__ - Step 20776: {'lr': 0.00048040748024448954, 'samples': 3988992, 'steps': 20775, 'loss/train': 1.688582420349121}
+08/30/2021 16:56:43 - INFO - __main__ - Step 20777: {'lr': 0.00048040542080454897, 'samples': 3989184, 'steps': 20776, 'loss/train': 1.3352688550949097}
+08/30/2021 16:56:44 - INFO - __main__ - Step 20778: {'lr': 0.0004804033612607912, 'samples': 3989376, 'steps': 20777, 'loss/train': 1.4921340942382812}
+08/30/2021 16:56:44 - INFO - __main__ - Step 20779: {'lr': 0.00048040130161321724, 'samples': 3989568, 'steps': 20778, 'loss/train': 1.7791802883148193}
+08/30/2021 16:56:44 - INFO - __main__ - Step 20780: {'lr': 0.0004803992418618281, 'samples': 3989760, 'steps': 20779, 'loss/train': 1.817274808883667}
+08/30/2021 16:56:46 - INFO - __main__ - Step 20781: {'lr': 0.00048039718200662454, 'samples': 3989952, 'steps': 20780, 'loss/train': 0.6666374206542969}
+08/30/2021 16:56:47 - INFO - __main__ - Step 20782: {'lr': 0.0004803951220476076, 'samples': 3990144, 'steps': 20781, 'loss/train': 2.2849414348602295}
+08/30/2021 16:56:47 - INFO - __main__ - Step 20783: {'lr': 0.00048039306198477817, 'samples': 3990336, 'steps': 20782, 'loss/train': 1.2788106203079224}
+08/30/2021 16:56:47 - INFO - __main__ - Step 20784: {'lr': 0.0004803910018181371, 'samples': 3990528, 'steps': 20783, 'loss/train': 1.457331895828247}
+08/30/2021 16:56:48 - INFO - __main__ - Step 20785: {'lr': 0.0004803889415476855, 'samples': 3990720, 'steps': 20784, 'loss/train': 1.5049031972885132}
+08/30/2021 16:56:50 - INFO - __main__ - Step 20786: {'lr': 0.0004803868811734242, 'samples': 3990912, 'steps': 20785, 'loss/train': 0.9126980304718018}
+08/30/2021 16:56:50 - INFO - __main__ - Step 20787: {'lr': 0.00048038482069535406, 'samples': 3991104, 'steps': 20786, 'loss/train': 0.9489515423774719}
+08/30/2021 16:56:50 - INFO - __main__ - Step 20788: {'lr': 0.000480382760113476, 'samples': 3991296, 'steps': 20787, 'loss/train': 1.571537733078003}
+08/30/2021 16:56:51 - INFO - __main__ - Step 20789: {'lr': 0.00048038069942779116, 'samples': 3991488, 'steps': 20788, 'loss/train': 1.521704912185669}
+08/30/2021 16:56:51 - INFO - __main__ - Step 20790: {'lr': 0.00048037863863830034, 'samples': 3991680, 'steps': 20789, 'loss/train': 1.4000773429870605}
+08/30/2021 16:56:51 - INFO - __main__ - Step 20791: {'lr': 0.0004803765777450044, 'samples': 3991872, 'steps': 20790, 'loss/train': 1.6413817405700684}
+08/30/2021 16:56:53 - INFO - __main__ - Step 20792: {'lr': 0.00048037451674790433, 'samples': 3992064, 'steps': 20791, 'loss/train': 0.200750470161438}
+08/30/2021 16:56:53 - INFO - __main__ - Step 20793: {'lr': 0.0004803724556470011, 'samples': 3992256, 'steps': 20792, 'loss/train': 1.843687653541565}
+08/30/2021 16:56:54 - INFO - __main__ - Step 20794: {'lr': 0.0004803703944422956, 'samples': 3992448, 'steps': 20793, 'loss/train': 1.8204582929611206}
+08/30/2021 16:56:54 - INFO - __main__ - Step 20795: {'lr': 0.0004803683331337887, 'samples': 3992640, 'steps': 20794, 'loss/train': 1.6987535953521729}
+08/30/2021 16:56:54 - INFO - __main__ - Step 20796: {'lr': 0.0004803662717214814, 'samples': 3992832, 'steps': 20795, 'loss/train': 1.7447631359100342}
+08/30/2021 16:56:56 - INFO - __main__ - Step 20797: {'lr': 0.00048036421020537464, 'samples': 3993024, 'steps': 20796, 'loss/train': 1.2406423091888428}
+08/30/2021 16:56:56 - INFO - __main__ - Step 20798: {'lr': 0.0004803621485854693, 'samples': 3993216, 'steps': 20797, 'loss/train': 1.7606385946273804}
+08/30/2021 16:56:57 - INFO - __main__ - Step 20799: {'lr': 0.00048036008686176636, 'samples': 3993408, 'steps': 20798, 'loss/train': 2.0389721393585205}
+08/30/2021 16:56:57 - INFO - __main__ - Step 20800: {'lr': 0.0004803580250342666, 'samples': 3993600, 'steps': 20799, 'loss/train': 0.8765015006065369}
+08/30/2021 16:56:57 - INFO - __main__ - Step 20801: {'lr': 0.00048035596310297125, 'samples': 3993792, 'steps': 20800, 'loss/train': 1.6353588104248047}
+08/30/2021 16:56:58 - INFO - __main__ - Step 20802: {'lr': 0.0004803539010678809, 'samples': 3993984, 'steps': 20801, 'loss/train': 1.1891461610794067}
+08/30/2021 16:57:00 - INFO - __main__ - Step 20803: {'lr': 0.00048035183892899676, 'samples': 3994176, 'steps': 20802, 'loss/train': 1.509429931640625}
+08/30/2021 16:57:00 - INFO - __main__ - Step 20804: {'lr': 0.0004803497766863195, 'samples': 3994368, 'steps': 20803, 'loss/train': 1.8290326595306396}
+08/30/2021 16:57:01 - INFO - __main__ - Step 20805: {'lr': 0.00048034771433985035, 'samples': 3994560, 'steps': 20804, 'loss/train': 1.8175963163375854}
+08/30/2021 16:57:01 - INFO - __main__ - Step 20806: {'lr': 0.00048034565188959, 'samples': 3994752, 'steps': 20805, 'loss/train': 1.915069341659546}
+08/30/2021 16:57:01 - INFO - __main__ - Step 20807: {'lr': 0.0004803435893355394, 'samples': 3994944, 'steps': 20806, 'loss/train': 1.5590801239013672}
+08/30/2021 16:57:03 - INFO - __main__ - Step 20808: {'lr': 0.00048034152667769957, 'samples': 3995136, 'steps': 20807, 'loss/train': 1.4858994483947754}
+08/30/2021 16:57:03 - INFO - __main__ - Step 20809: {'lr': 0.0004803394639160714, 'samples': 3995328, 'steps': 20808, 'loss/train': 1.0625766515731812}
+08/30/2021 16:57:04 - INFO - __main__ - Step 20810: {'lr': 0.00048033740105065585, 'samples': 3995520, 'steps': 20809, 'loss/train': 0.7241296768188477}
+08/30/2021 16:57:04 - INFO - __main__ - Step 20811: {'lr': 0.0004803353380814538, 'samples': 3995712, 'steps': 20810, 'loss/train': 1.686326503753662}
+08/30/2021 16:57:04 - INFO - __main__ - Step 20812: {'lr': 0.00048033327500846625, 'samples': 3995904, 'steps': 20811, 'loss/train': 1.425820231437683}
+08/30/2021 16:57:06 - INFO - __main__ - Step 20813: {'lr': 0.000480331211831694, 'samples': 3996096, 'steps': 20812, 'loss/train': 0.8603524565696716}
+08/30/2021 16:57:06 - INFO - __main__ - Step 20814: {'lr': 0.00048032914855113807, 'samples': 3996288, 'steps': 20813, 'loss/train': 1.022192120552063}
+08/30/2021 16:57:06 - INFO - __main__ - Step 20815: {'lr': 0.00048032708516679946, 'samples': 3996480, 'steps': 20814, 'loss/train': 0.7716886401176453}
+08/30/2021 16:57:07 - INFO - __main__ - Step 20816: {'lr': 0.00048032502167867896, 'samples': 3996672, 'steps': 20815, 'loss/train': 1.5297855138778687}
+08/30/2021 16:57:07 - INFO - __main__ - Step 20817: {'lr': 0.0004803229580867775, 'samples': 3996864, 'steps': 20816, 'loss/train': 1.4987337589263916}
+08/30/2021 16:57:09 - INFO - __main__ - Step 20818: {'lr': 0.0004803208943910962, 'samples': 3997056, 'steps': 20817, 'loss/train': 1.2595634460449219}
+08/30/2021 16:57:09 - INFO - __main__ - Step 20819: {'lr': 0.00048031883059163576, 'samples': 3997248, 'steps': 20818, 'loss/train': 1.42384934425354}
+08/30/2021 16:57:09 - INFO - __main__ - Step 20820: {'lr': 0.00048031676668839723, 'samples': 3997440, 'steps': 20819, 'loss/train': 1.623425006866455}
+08/30/2021 16:57:10 - INFO - __main__ - Step 20821: {'lr': 0.00048031470268138153, 'samples': 3997632, 'steps': 20820, 'loss/train': 1.529524564743042}
+08/30/2021 16:57:10 - INFO - __main__ - Step 20822: {'lr': 0.00048031263857058957, 'samples': 3997824, 'steps': 20821, 'loss/train': 1.398085355758667}
+08/30/2021 16:57:12 - INFO - __main__ - Step 20823: {'lr': 0.00048031057435602234, 'samples': 3998016, 'steps': 20822, 'loss/train': 0.6544572710990906}
+08/30/2021 16:57:12 - INFO - __main__ - Step 20824: {'lr': 0.0004803085100376807, 'samples': 3998208, 'steps': 20823, 'loss/train': 1.5054800510406494}
+08/30/2021 16:57:12 - INFO - __main__ - Step 20825: {'lr': 0.00048030644561556556, 'samples': 3998400, 'steps': 20824, 'loss/train': 2.384716749191284}
+08/30/2021 16:57:13 - INFO - __main__ - Step 20826: {'lr': 0.0004803043810896779, 'samples': 3998592, 'steps': 20825, 'loss/train': 1.834130883216858}
+08/30/2021 16:57:13 - INFO - __main__ - Step 20827: {'lr': 0.00048030231646001867, 'samples': 3998784, 'steps': 20826, 'loss/train': 1.5747114419937134}
+08/30/2021 16:57:15 - INFO - __main__ - Step 20828: {'lr': 0.0004803002517265887, 'samples': 3998976, 'steps': 20827, 'loss/train': 1.1097772121429443}
+08/30/2021 16:57:15 - INFO - __main__ - Step 20829: {'lr': 0.0004802981868893891, 'samples': 3999168, 'steps': 20828, 'loss/train': 1.3051564693450928}
+08/30/2021 16:57:16 - INFO - __main__ - Step 20830: {'lr': 0.00048029612194842056, 'samples': 3999360, 'steps': 20829, 'loss/train': 1.3877121210098267}
+08/30/2021 16:57:16 - INFO - __main__ - Step 20831: {'lr': 0.0004802940569036842, 'samples': 3999552, 'steps': 20830, 'loss/train': 1.4898688793182373}
+08/30/2021 16:57:16 - INFO - __main__ - Step 20832: {'lr': 0.0004802919917551809, 'samples': 3999744, 'steps': 20831, 'loss/train': 1.796456217765808}
+08/30/2021 16:57:18 - INFO - __main__ - Step 20833: {'lr': 0.00048028992650291156, 'samples': 3999936, 'steps': 20832, 'loss/train': 1.4047584533691406}
+08/30/2021 16:57:18 - INFO - __main__ - Step 20834: {'lr': 0.00048028786114687715, 'samples': 4000128, 'steps': 20833, 'loss/train': 0.3299529552459717}
+08/30/2021 16:57:18 - INFO - __main__ - Step 20835: {'lr': 0.0004802857956870786, 'samples': 4000320, 'steps': 20834, 'loss/train': 1.3085787296295166}
+08/30/2021 16:57:19 - INFO - __main__ - Step 20836: {'lr': 0.00048028373012351684, 'samples': 4000512, 'steps': 20835, 'loss/train': 1.2915829420089722}
+08/30/2021 16:57:19 - INFO - __main__ - Step 20837: {'lr': 0.00048028166445619275, 'samples': 4000704, 'steps': 20836, 'loss/train': 1.332929015159607}
+08/30/2021 16:57:21 - INFO - __main__ - Step 20838: {'lr': 0.0004802795986851073, 'samples': 4000896, 'steps': 20837, 'loss/train': 1.5033856630325317}
+08/30/2021 16:57:21 - INFO - __main__ - Step 20839: {'lr': 0.00048027753281026144, 'samples': 4001088, 'steps': 20838, 'loss/train': 1.496140956878662}
+08/30/2021 16:57:21 - INFO - __main__ - Step 20840: {'lr': 0.000480275466831656, 'samples': 4001280, 'steps': 20839, 'loss/train': 1.7681258916854858}
+08/30/2021 16:57:22 - INFO - __main__ - Step 20841: {'lr': 0.00048027340074929207, 'samples': 4001472, 'steps': 20840, 'loss/train': 1.8449194431304932}
+08/30/2021 16:57:22 - INFO - __main__ - Step 20842: {'lr': 0.0004802713345631705, 'samples': 4001664, 'steps': 20841, 'loss/train': 1.9577341079711914}
+08/30/2021 16:57:23 - INFO - __main__ - Step 20843: {'lr': 0.0004802692682732922, 'samples': 4001856, 'steps': 20842, 'loss/train': 1.7500014305114746}
+08/30/2021 16:57:24 - INFO - __main__ - Step 20844: {'lr': 0.0004802672018796581, 'samples': 4002048, 'steps': 20843, 'loss/train': 0.7694911360740662}
+08/30/2021 16:57:25 - INFO - __main__ - Step 20845: {'lr': 0.0004802651353822691, 'samples': 4002240, 'steps': 20844, 'loss/train': 1.3434566259384155}
+08/30/2021 16:57:25 - INFO - __main__ - Step 20846: {'lr': 0.0004802630687811263, 'samples': 4002432, 'steps': 20845, 'loss/train': 0.157589390873909}
+08/30/2021 16:57:25 - INFO - __main__ - Step 20847: {'lr': 0.00048026100207623047, 'samples': 4002624, 'steps': 20846, 'loss/train': 1.613234281539917}
+08/30/2021 16:57:26 - INFO - __main__ - Step 20848: {'lr': 0.0004802589352675826, 'samples': 4002816, 'steps': 20847, 'loss/train': 5.843477725982666}
+08/30/2021 16:57:27 - INFO - __main__ - Step 20849: {'lr': 0.0004802568683551836, 'samples': 4003008, 'steps': 20848, 'loss/train': 1.3360764980316162}
+08/30/2021 16:57:28 - INFO - __main__ - Step 20850: {'lr': 0.0004802548013390343, 'samples': 4003200, 'steps': 20849, 'loss/train': 1.213433027267456}
+08/30/2021 16:57:28 - INFO - __main__ - Step 20851: {'lr': 0.00048025273421913587, 'samples': 4003392, 'steps': 20850, 'loss/train': 1.7084523439407349}
+08/30/2021 16:57:28 - INFO - __main__ - Step 20852: {'lr': 0.0004802506669954891, 'samples': 4003584, 'steps': 20851, 'loss/train': 1.7778393030166626}
+08/30/2021 16:57:29 - INFO - __main__ - Step 20853: {'lr': 0.00048024859966809487, 'samples': 4003776, 'steps': 20852, 'loss/train': 2.043734550476074}
+08/30/2021 16:57:30 - INFO - __main__ - Step 20854: {'lr': 0.00048024653223695425, 'samples': 4003968, 'steps': 20853, 'loss/train': 1.2937445640563965}
+08/30/2021 16:57:31 - INFO - __main__ - Step 20855: {'lr': 0.00048024446470206806, 'samples': 4004160, 'steps': 20854, 'loss/train': 0.8848605155944824}
+08/30/2021 16:57:31 - INFO - __main__ - Step 20856: {'lr': 0.0004802423970634373, 'samples': 4004352, 'steps': 20855, 'loss/train': 1.7068744897842407}
+08/30/2021 16:57:31 - INFO - __main__ - Step 20857: {'lr': 0.00048024032932106277, 'samples': 4004544, 'steps': 20856, 'loss/train': 1.936099648475647}
+08/30/2021 16:57:32 - INFO - __main__ - Step 20858: {'lr': 0.00048023826147494556, 'samples': 4004736, 'steps': 20857, 'loss/train': 1.530527949333191}
+08/30/2021 16:57:32 - INFO - __main__ - Step 20859: {'lr': 0.0004802361935250865, 'samples': 4004928, 'steps': 20858, 'loss/train': 1.242943525314331}
+08/30/2021 16:57:34 - INFO - __main__ - Step 20860: {'lr': 0.0004802341254714867, 'samples': 4005120, 'steps': 20859, 'loss/train': 1.5698579549789429}
+08/30/2021 16:57:35 - INFO - __main__ - Step 20861: {'lr': 0.00048023205731414684, 'samples': 4005312, 'steps': 20860, 'loss/train': 1.8995860815048218}
+08/30/2021 16:57:35 - INFO - __main__ - Step 20862: {'lr': 0.00048022998905306795, 'samples': 4005504, 'steps': 20861, 'loss/train': 0.5663987994194031}
+08/30/2021 16:57:35 - INFO - __main__ - Step 20863: {'lr': 0.00048022792068825107, 'samples': 4005696, 'steps': 20862, 'loss/train': 1.5970838069915771}
+08/30/2021 16:57:36 - INFO - __main__ - Step 20864: {'lr': 0.00048022585221969697, 'samples': 4005888, 'steps': 20863, 'loss/train': 0.8861684799194336}
+08/30/2021 16:57:38 - INFO - __main__ - Step 20865: {'lr': 0.00048022378364740673, 'samples': 4006080, 'steps': 20864, 'loss/train': 1.7130883932113647}
+08/30/2021 16:57:38 - INFO - __main__ - Step 20866: {'lr': 0.0004802217149713811, 'samples': 4006272, 'steps': 20865, 'loss/train': 1.4740095138549805}
+08/30/2021 16:57:39 - INFO - __main__ - Step 20867: {'lr': 0.0004802196461916212, 'samples': 4006464, 'steps': 20866, 'loss/train': 1.6010992527008057}
+08/30/2021 16:57:39 - INFO - __main__ - Step 20868: {'lr': 0.0004802175773081278, 'samples': 4006656, 'steps': 20867, 'loss/train': 1.6782881021499634}
+08/30/2021 16:57:39 - INFO - __main__ - Step 20869: {'lr': 0.000480215508320902, 'samples': 4006848, 'steps': 20868, 'loss/train': 0.167189359664917}
+08/30/2021 16:57:41 - INFO - __main__ - Step 20870: {'lr': 0.0004802134392299446, 'samples': 4007040, 'steps': 20869, 'loss/train': 1.6451122760772705}
+08/30/2021 16:57:41 - INFO - __main__ - Step 20871: {'lr': 0.0004802113700352566, 'samples': 4007232, 'steps': 20870, 'loss/train': 1.909308910369873}
+08/30/2021 16:57:42 - INFO - __main__ - Step 20872: {'lr': 0.00048020930073683886, 'samples': 4007424, 'steps': 20871, 'loss/train': 1.7468796968460083}
+08/30/2021 16:57:42 - INFO - __main__ - Step 20873: {'lr': 0.0004802072313346924, 'samples': 4007616, 'steps': 20872, 'loss/train': 1.462784767150879}
+08/30/2021 16:57:42 - INFO - __main__ - Step 20874: {'lr': 0.00048020516182881813, 'samples': 4007808, 'steps': 20873, 'loss/train': 1.947792410850525}
+08/30/2021 16:57:44 - INFO - __main__ - Step 20875: {'lr': 0.00048020309221921686, 'samples': 4008000, 'steps': 20874, 'loss/train': 1.4549416303634644}
+08/30/2021 16:57:44 - INFO - __main__ - Step 20876: {'lr': 0.00048020102250588976, 'samples': 4008192, 'steps': 20875, 'loss/train': 1.3103128671646118}
+08/30/2021 16:57:45 - INFO - __main__ - Step 20877: {'lr': 0.00048019895268883764, 'samples': 4008384, 'steps': 20876, 'loss/train': 1.1322263479232788}
+08/30/2021 16:57:45 - INFO - __main__ - Step 20878: {'lr': 0.0004801968827680613, 'samples': 4008576, 'steps': 20877, 'loss/train': 1.3397971391677856}
+08/30/2021 16:57:45 - INFO - __main__ - Step 20879: {'lr': 0.00048019481274356194, 'samples': 4008768, 'steps': 20878, 'loss/train': 1.1345170736312866}
+08/30/2021 16:57:47 - INFO - __main__ - Step 20880: {'lr': 0.0004801927426153402, 'samples': 4008960, 'steps': 20879, 'loss/train': 1.5402135848999023}
+08/30/2021 16:57:48 - INFO - __main__ - Step 20881: {'lr': 0.00048019067238339725, 'samples': 4009152, 'steps': 20880, 'loss/train': 1.3619599342346191}
+08/30/2021 16:57:48 - INFO - __main__ - Step 20882: {'lr': 0.000480188602047734, 'samples': 4009344, 'steps': 20881, 'loss/train': 1.7267178297042847}
+08/30/2021 16:57:49 - INFO - __main__ - Step 20883: {'lr': 0.0004801865316083512, 'samples': 4009536, 'steps': 20882, 'loss/train': 2.110841989517212}
+08/30/2021 16:57:49 - INFO - __main__ - Step 20884: {'lr': 0.0004801844610652499, 'samples': 4009728, 'steps': 20883, 'loss/train': 1.598005771636963}
+08/30/2021 16:57:49 - INFO - __main__ - Step 20885: {'lr': 0.0004801823904184311, 'samples': 4009920, 'steps': 20884, 'loss/train': 1.4082896709442139}
+08/30/2021 16:57:51 - INFO - __main__ - Step 20886: {'lr': 0.00048018031966789564, 'samples': 4010112, 'steps': 20885, 'loss/train': 0.14600832760334015}
+08/30/2021 16:57:52 - INFO - __main__ - Step 20887: {'lr': 0.0004801782488136445, 'samples': 4010304, 'steps': 20886, 'loss/train': 1.7309308052062988}
+08/30/2021 16:57:52 - INFO - __main__ - Step 20888: {'lr': 0.00048017617785567855, 'samples': 4010496, 'steps': 20887, 'loss/train': 0.1437617540359497}
+08/30/2021 16:57:52 - INFO - __main__ - Step 20889: {'lr': 0.00048017410679399876, 'samples': 4010688, 'steps': 20888, 'loss/train': 1.4162567853927612}
+08/30/2021 16:57:53 - INFO - __main__ - Step 20890: {'lr': 0.00048017203562860614, 'samples': 4010880, 'steps': 20889, 'loss/train': 2.313275098800659}
+08/30/2021 16:57:53 - INFO - __main__ - Step 20891: {'lr': 0.0004801699643595015, 'samples': 4011072, 'steps': 20890, 'loss/train': 1.5743414163589478}
+08/30/2021 16:57:54 - INFO - __main__ - Step 20892: {'lr': 0.00048016789298668583, 'samples': 4011264, 'steps': 20891, 'loss/train': 0.7836162447929382}
+08/30/2021 16:57:55 - INFO - __main__ - Step 20893: {'lr': 0.0004801658215101601, 'samples': 4011456, 'steps': 20892, 'loss/train': 1.8106706142425537}
+08/30/2021 16:57:55 - INFO - __main__ - Step 20894: {'lr': 0.00048016374992992516, 'samples': 4011648, 'steps': 20893, 'loss/train': 1.6870431900024414}
+08/30/2021 16:57:56 - INFO - __main__ - Step 20895: {'lr': 0.000480161678245982, 'samples': 4011840, 'steps': 20894, 'loss/train': 1.6460051536560059}
+08/30/2021 16:57:57 - INFO - __main__ - Step 20896: {'lr': 0.0004801596064583315, 'samples': 4012032, 'steps': 20895, 'loss/train': 1.2648009061813354}
+08/30/2021 16:57:58 - INFO - __main__ - Step 20897: {'lr': 0.00048015753456697466, 'samples': 4012224, 'steps': 20896, 'loss/train': 1.7518366575241089}
+08/30/2021 16:57:58 - INFO - __main__ - Step 20898: {'lr': 0.00048015546257191243, 'samples': 4012416, 'steps': 20897, 'loss/train': 1.0268855094909668}
+08/30/2021 16:57:58 - INFO - __main__ - Step 20899: {'lr': 0.00048015339047314566, 'samples': 4012608, 'steps': 20898, 'loss/train': 1.3595432043075562}
+08/30/2021 16:57:59 - INFO - __main__ - Step 20900: {'lr': 0.00048015131827067534, 'samples': 4012800, 'steps': 20899, 'loss/train': 0.8023666739463806}
+08/30/2021 16:57:59 - INFO - __main__ - Step 20901: {'lr': 0.0004801492459645024, 'samples': 4012992, 'steps': 20900, 'loss/train': 1.5363144874572754}
+08/30/2021 16:58:00 - INFO - __main__ - Step 20902: {'lr': 0.0004801471735546277, 'samples': 4013184, 'steps': 20901, 'loss/train': 1.5872712135314941}
+08/30/2021 16:58:01 - INFO - __main__ - Step 20903: {'lr': 0.0004801451010410522, 'samples': 4013376, 'steps': 20902, 'loss/train': 1.7590477466583252}
+08/30/2021 16:58:01 - INFO - __main__ - Step 20904: {'lr': 0.000480143028423777, 'samples': 4013568, 'steps': 20903, 'loss/train': 1.8734040260314941}
+08/30/2021 16:58:02 - INFO - __main__ - Step 20905: {'lr': 0.0004801409557028028, 'samples': 4013760, 'steps': 20904, 'loss/train': 1.6589394807815552}
+08/30/2021 16:58:02 - INFO - __main__ - Step 20906: {'lr': 0.0004801388828781307, 'samples': 4013952, 'steps': 20905, 'loss/train': 1.5599116086959839}
+08/30/2021 16:58:04 - INFO - __main__ - Step 20907: {'lr': 0.00048013680994976154, 'samples': 4014144, 'steps': 20906, 'loss/train': 1.3931597471237183}
+08/30/2021 16:58:05 - INFO - __main__ - Step 20908: {'lr': 0.0004801347369176963, 'samples': 4014336, 'steps': 20907, 'loss/train': 1.6757256984710693}
+08/30/2021 16:58:05 - INFO - __main__ - Step 20909: {'lr': 0.00048013266378193586, 'samples': 4014528, 'steps': 20908, 'loss/train': 1.1520507335662842}
+08/30/2021 16:58:05 - INFO - __main__ - Step 20910: {'lr': 0.00048013059054248134, 'samples': 4014720, 'steps': 20909, 'loss/train': 1.6782448291778564}
+08/30/2021 16:58:06 - INFO - __main__ - Step 20911: {'lr': 0.00048012851719933335, 'samples': 4014912, 'steps': 20910, 'loss/train': 1.9210513830184937}
+08/30/2021 16:58:06 - INFO - __main__ - Step 20912: {'lr': 0.000480126443752493, 'samples': 4015104, 'steps': 20911, 'loss/train': 5.031146049499512}
+08/30/2021 16:58:08 - INFO - __main__ - Step 20913: {'lr': 0.0004801243702019614, 'samples': 4015296, 'steps': 20912, 'loss/train': 1.5334185361862183}
+08/30/2021 16:58:08 - INFO - __main__ - Step 20914: {'lr': 0.00048012229654773915, 'samples': 4015488, 'steps': 20913, 'loss/train': 1.430576205253601}
+08/30/2021 16:58:08 - INFO - __main__ - Step 20915: {'lr': 0.0004801202227898274, 'samples': 4015680, 'steps': 20914, 'loss/train': 1.8230525255203247}
+08/30/2021 16:58:09 - INFO - __main__ - Step 20916: {'lr': 0.00048011814892822704, 'samples': 4015872, 'steps': 20915, 'loss/train': 1.590773105621338}
+08/30/2021 16:58:09 - INFO - __main__ - Step 20917: {'lr': 0.00048011607496293896, 'samples': 4016064, 'steps': 20916, 'loss/train': 1.8072232007980347}
+08/30/2021 16:58:11 - INFO - __main__ - Step 20918: {'lr': 0.0004801140008939642, 'samples': 4016256, 'steps': 20917, 'loss/train': 1.6074912548065186}
+08/30/2021 16:58:11 - INFO - __main__ - Step 20919: {'lr': 0.00048011192672130356, 'samples': 4016448, 'steps': 20918, 'loss/train': 1.6177542209625244}
+08/30/2021 16:58:11 - INFO - __main__ - Step 20920: {'lr': 0.000480109852444958, 'samples': 4016640, 'steps': 20919, 'loss/train': 0.4326907992362976}
+08/30/2021 16:58:12 - INFO - __main__ - Step 20921: {'lr': 0.0004801077780649286, 'samples': 4016832, 'steps': 20920, 'loss/train': 1.431039571762085}
+08/30/2021 16:58:12 - INFO - __main__ - Step 20922: {'lr': 0.00048010570358121606, 'samples': 4017024, 'steps': 20921, 'loss/train': 1.421709418296814}
+08/30/2021 16:58:14 - INFO - __main__ - Step 20923: {'lr': 0.0004801036289938215, 'samples': 4017216, 'steps': 20922, 'loss/train': 1.3588948249816895}
+08/30/2021 16:58:14 - INFO - __main__ - Step 20924: {'lr': 0.0004801015543027458, 'samples': 4017408, 'steps': 20923, 'loss/train': 1.118821144104004}
+08/30/2021 16:58:15 - INFO - __main__ - Step 20925: {'lr': 0.0004800994795079899, 'samples': 4017600, 'steps': 20924, 'loss/train': 1.0915248394012451}
+08/30/2021 16:58:15 - INFO - __main__ - Step 20926: {'lr': 0.00048009740460955465, 'samples': 4017792, 'steps': 20925, 'loss/train': 1.7997756004333496}
+08/30/2021 16:58:16 - INFO - __main__ - Step 20927: {'lr': 0.00048009532960744116, 'samples': 4017984, 'steps': 20926, 'loss/train': 1.7789839506149292}
+08/30/2021 16:58:17 - INFO - __main__ - Step 20928: {'lr': 0.0004800932545016502, 'samples': 4018176, 'steps': 20927, 'loss/train': 2.1777122020721436}
+08/30/2021 16:58:18 - INFO - __main__ - Step 20929: {'lr': 0.0004800911792921828, 'samples': 4018368, 'steps': 20928, 'loss/train': 0.8171807527542114}
+08/30/2021 16:58:18 - INFO - __main__ - Step 20930: {'lr': 0.0004800891039790399, 'samples': 4018560, 'steps': 20929, 'loss/train': 2.5374791622161865}
+08/30/2021 16:58:18 - INFO - __main__ - Step 20931: {'lr': 0.00048008702856222233, 'samples': 4018752, 'steps': 20930, 'loss/train': 0.07208096235990524}
+08/30/2021 16:58:19 - INFO - __main__ - Step 20932: {'lr': 0.0004800849530417312, 'samples': 4018944, 'steps': 20931, 'loss/train': 0.8734824657440186}
+08/30/2021 16:58:20 - INFO - __main__ - Step 20933: {'lr': 0.00048008287741756715, 'samples': 4019136, 'steps': 20932, 'loss/train': 1.5740123987197876}
+08/30/2021 16:58:20 - INFO - __main__ - Step 20934: {'lr': 0.00048008080168973144, 'samples': 4019328, 'steps': 20933, 'loss/train': 1.2088955640792847}
+08/30/2021 16:58:21 - INFO - __main__ - Step 20935: {'lr': 0.00048007872585822486, 'samples': 4019520, 'steps': 20934, 'loss/train': 2.1600000858306885}
+08/30/2021 16:58:21 - INFO - __main__ - Step 20936: {'lr': 0.00048007664992304834, 'samples': 4019712, 'steps': 20935, 'loss/train': 1.962638020515442}
+08/30/2021 16:58:22 - INFO - __main__ - Step 20937: {'lr': 0.0004800745738842029, 'samples': 4019904, 'steps': 20936, 'loss/train': 1.4366098642349243}
+08/30/2021 16:58:23 - INFO - __main__ - Step 20938: {'lr': 0.0004800724977416894, 'samples': 4020096, 'steps': 20937, 'loss/train': 1.3570092916488647}
+08/30/2021 16:58:23 - INFO - __main__ - Step 20939: {'lr': 0.00048007042149550866, 'samples': 4020288, 'steps': 20938, 'loss/train': 2.136103868484497}
+08/30/2021 16:58:24 - INFO - __main__ - Step 20940: {'lr': 0.00048006834514566183, 'samples': 4020480, 'steps': 20939, 'loss/train': 1.2310088872909546}
+08/30/2021 16:58:24 - INFO - __main__ - Step 20941: {'lr': 0.00048006626869214977, 'samples': 4020672, 'steps': 20940, 'loss/train': 1.283164620399475}
+08/30/2021 16:58:24 - INFO - __main__ - Step 20942: {'lr': 0.00048006419213497334, 'samples': 4020864, 'steps': 20941, 'loss/train': 1.5024957656860352}
+08/30/2021 16:58:25 - INFO - __main__ - Step 20943: {'lr': 0.0004800621154741335, 'samples': 4021056, 'steps': 20942, 'loss/train': 1.8647565841674805}
+08/30/2021 16:58:27 - INFO - __main__ - Step 20944: {'lr': 0.00048006003870963135, 'samples': 4021248, 'steps': 20943, 'loss/train': 1.7144920825958252}
+08/30/2021 16:58:28 - INFO - __main__ - Step 20945: {'lr': 0.0004800579618414676, 'samples': 4021440, 'steps': 20944, 'loss/train': 0.9009919762611389}
+08/30/2021 16:58:28 - INFO - __main__ - Step 20946: {'lr': 0.0004800558848696433, 'samples': 4021632, 'steps': 20945, 'loss/train': 1.5119132995605469}
+08/30/2021 16:58:28 - INFO - __main__ - Step 20947: {'lr': 0.0004800538077941594, 'samples': 4021824, 'steps': 20946, 'loss/train': 1.3563536405563354}
+08/30/2021 16:58:29 - INFO - __main__ - Step 20948: {'lr': 0.00048005173061501673, 'samples': 4022016, 'steps': 20947, 'loss/train': 0.7356158494949341}
+08/30/2021 16:58:29 - INFO - __main__ - Step 20949: {'lr': 0.0004800496533322164, 'samples': 4022208, 'steps': 20948, 'loss/train': 0.7174288034439087}
+08/30/2021 16:58:31 - INFO - __main__ - Step 20950: {'lr': 0.00048004757594575923, 'samples': 4022400, 'steps': 20949, 'loss/train': 0.5843749046325684}
+08/30/2021 16:58:31 - INFO - __main__ - Step 20951: {'lr': 0.0004800454984556461, 'samples': 4022592, 'steps': 20950, 'loss/train': 1.7752432823181152}
+08/30/2021 16:58:31 - INFO - __main__ - Step 20952: {'lr': 0.00048004342086187805, 'samples': 4022784, 'steps': 20951, 'loss/train': 1.4212886095046997}
+08/30/2021 16:58:32 - INFO - __main__ - Step 20953: {'lr': 0.000480041343164456, 'samples': 4022976, 'steps': 20952, 'loss/train': 1.3968759775161743}
+08/30/2021 16:58:32 - INFO - __main__ - Step 20954: {'lr': 0.0004800392653633808, 'samples': 4023168, 'steps': 20953, 'loss/train': 1.6341660022735596}
+08/30/2021 16:58:34 - INFO - __main__ - Step 20955: {'lr': 0.0004800371874586535, 'samples': 4023360, 'steps': 20954, 'loss/train': 0.8786346912384033}
+08/30/2021 16:58:34 - INFO - __main__ - Step 20956: {'lr': 0.0004800351094502751, 'samples': 4023552, 'steps': 20955, 'loss/train': 1.3521685600280762}
+08/30/2021 16:58:34 - INFO - __main__ - Step 20957: {'lr': 0.00048003303133824633, 'samples': 4023744, 'steps': 20956, 'loss/train': 1.648524522781372}
+08/30/2021 16:58:35 - INFO - __main__ - Step 20958: {'lr': 0.0004800309531225683, 'samples': 4023936, 'steps': 20957, 'loss/train': 1.6984584331512451}
+08/30/2021 16:58:35 - INFO - __main__ - Step 20959: {'lr': 0.00048002887480324175, 'samples': 4024128, 'steps': 20958, 'loss/train': 1.4897602796554565}
+08/30/2021 16:58:37 - INFO - __main__ - Step 20960: {'lr': 0.0004800267963802678, 'samples': 4024320, 'steps': 20959, 'loss/train': 1.420543909072876}
+08/30/2021 16:58:38 - INFO - __main__ - Step 20961: {'lr': 0.0004800247178536473, 'samples': 4024512, 'steps': 20960, 'loss/train': 1.5173707008361816}
+08/30/2021 16:58:38 - INFO - __main__ - Step 20962: {'lr': 0.0004800226392233813, 'samples': 4024704, 'steps': 20961, 'loss/train': 1.550585389137268}
+08/30/2021 16:58:38 - INFO - __main__ - Step 20963: {'lr': 0.00048002056048947054, 'samples': 4024896, 'steps': 20962, 'loss/train': 1.3969539403915405}
+08/30/2021 16:58:39 - INFO - __main__ - Step 20964: {'lr': 0.0004800184816519161, 'samples': 4025088, 'steps': 20963, 'loss/train': 1.7827870845794678}
+08/30/2021 16:58:39 - INFO - __main__ - Step 20965: {'lr': 0.0004800164027107189, 'samples': 4025280, 'steps': 20964, 'loss/train': 0.1982184797525406}
+08/30/2021 16:58:41 - INFO - __main__ - Step 20966: {'lr': 0.0004800143236658798, 'samples': 4025472, 'steps': 20965, 'loss/train': 1.8056644201278687}
+08/30/2021 16:58:41 - INFO - __main__ - Step 20967: {'lr': 0.0004800122445173999, 'samples': 4025664, 'steps': 20966, 'loss/train': 1.2438685894012451}
+08/30/2021 16:58:42 - INFO - __main__ - Step 20968: {'lr': 0.00048001016526528, 'samples': 4025856, 'steps': 20967, 'loss/train': 1.4209654331207275}
+08/30/2021 16:58:42 - INFO - __main__ - Step 20969: {'lr': 0.00048000808590952106, 'samples': 4026048, 'steps': 20968, 'loss/train': 1.1624550819396973}
+08/30/2021 16:58:42 - INFO - __main__ - Step 20970: {'lr': 0.0004800060064501239, 'samples': 4026240, 'steps': 20969, 'loss/train': 1.373073935508728}
+08/30/2021 16:58:44 - INFO - __main__ - Step 20971: {'lr': 0.00048000392688708976, 'samples': 4026432, 'steps': 20970, 'loss/train': 1.401117205619812}
+08/30/2021 16:58:44 - INFO - __main__ - Step 20972: {'lr': 0.00048000184722041934, 'samples': 4026624, 'steps': 20971, 'loss/train': 1.7493475675582886}
+08/30/2021 16:58:45 - INFO - __main__ - Step 20973: {'lr': 0.00047999976745011366, 'samples': 4026816, 'steps': 20972, 'loss/train': 1.0928475856781006}
+08/30/2021 16:58:45 - INFO - __main__ - Step 20974: {'lr': 0.0004799976875761736, 'samples': 4027008, 'steps': 20973, 'loss/train': 2.1853578090667725}
+08/30/2021 16:58:45 - INFO - __main__ - Step 20975: {'lr': 0.00047999560759860006, 'samples': 4027200, 'steps': 20974, 'loss/train': 2.230820894241333}
+08/30/2021 16:58:47 - INFO - __main__ - Step 20976: {'lr': 0.00047999352751739414, 'samples': 4027392, 'steps': 20975, 'loss/train': 1.414308786392212}
+08/30/2021 16:58:48 - INFO - __main__ - Step 20977: {'lr': 0.0004799914473325567, 'samples': 4027584, 'steps': 20976, 'loss/train': 1.6380691528320312}
+08/30/2021 16:58:48 - INFO - __main__ - Step 20978: {'lr': 0.00047998936704408865, 'samples': 4027776, 'steps': 20977, 'loss/train': 1.5667731761932373}
+08/30/2021 16:58:48 - INFO - __main__ - Step 20979: {'lr': 0.00047998728665199085, 'samples': 4027968, 'steps': 20978, 'loss/train': 0.7598178386688232}
+08/30/2021 16:58:49 - INFO - __main__ - Step 20980: {'lr': 0.00047998520615626447, 'samples': 4028160, 'steps': 20979, 'loss/train': 0.548076331615448}
+08/30/2021 16:58:49 - INFO - __main__ - Step 20981: {'lr': 0.0004799831255569102, 'samples': 4028352, 'steps': 20980, 'loss/train': 3.950775384902954}
+08/30/2021 16:58:51 - INFO - __main__ - Step 20982: {'lr': 0.00047998104485392915, 'samples': 4028544, 'steps': 20981, 'loss/train': 1.2458995580673218}
+08/30/2021 16:58:51 - INFO - __main__ - Step 20983: {'lr': 0.0004799789640473221, 'samples': 4028736, 'steps': 20982, 'loss/train': 3.2928640842437744}
+08/30/2021 16:58:51 - INFO - __main__ - Step 20984: {'lr': 0.0004799768831370902, 'samples': 4028928, 'steps': 20983, 'loss/train': 1.4735898971557617}
+08/30/2021 16:58:52 - INFO - __main__ - Step 20985: {'lr': 0.0004799748021232342, 'samples': 4029120, 'steps': 20984, 'loss/train': 1.8679158687591553}
+08/30/2021 16:58:52 - INFO - __main__ - Step 20986: {'lr': 0.00047997272100575505, 'samples': 4029312, 'steps': 20985, 'loss/train': 2.7078568935394287}
+08/30/2021 16:58:54 - INFO - __main__ - Step 20987: {'lr': 0.00047997063978465383, 'samples': 4029504, 'steps': 20986, 'loss/train': 1.5304360389709473}
+08/30/2021 16:58:54 - INFO - __main__ - Step 20988: {'lr': 0.0004799685584599313, 'samples': 4029696, 'steps': 20987, 'loss/train': 1.5792006254196167}
+08/30/2021 16:58:54 - INFO - __main__ - Step 20989: {'lr': 0.00047996647703158857, 'samples': 4029888, 'steps': 20988, 'loss/train': 2.113802433013916}
+08/30/2021 16:58:55 - INFO - __main__ - Step 20990: {'lr': 0.00047996439549962647, 'samples': 4030080, 'steps': 20989, 'loss/train': 1.8476831912994385}
+08/30/2021 16:58:55 - INFO - __main__ - Step 20991: {'lr': 0.00047996231386404593, 'samples': 4030272, 'steps': 20990, 'loss/train': 1.592795729637146}
+08/30/2021 16:58:57 - INFO - __main__ - Step 20992: {'lr': 0.00047996023212484797, 'samples': 4030464, 'steps': 20991, 'loss/train': 1.5453822612762451}
+08/30/2021 16:58:57 - INFO - __main__ - Step 20993: {'lr': 0.00047995815028203346, 'samples': 4030656, 'steps': 20992, 'loss/train': 2.155550003051758}
+08/30/2021 16:58:58 - INFO - __main__ - Step 20994: {'lr': 0.00047995606833560337, 'samples': 4030848, 'steps': 20993, 'loss/train': 3.0335333347320557}
+08/30/2021 16:58:58 - INFO - __main__ - Step 20995: {'lr': 0.0004799539862855585, 'samples': 4031040, 'steps': 20994, 'loss/train': 1.8598829507827759}
+08/30/2021 16:58:58 - INFO - __main__ - Step 20996: {'lr': 0.00047995190413190004, 'samples': 4031232, 'steps': 20995, 'loss/train': 0.11773476749658585}
+08/30/2021 16:58:59 - INFO - __main__ - Step 20997: {'lr': 0.00047994982187462876, 'samples': 4031424, 'steps': 20996, 'loss/train': 1.9217010736465454}
+08/30/2021 16:59:00 - INFO - __main__ - Step 20998: {'lr': 0.0004799477395137457, 'samples': 4031616, 'steps': 20997, 'loss/train': 2.0599071979522705}
+08/30/2021 16:59:01 - INFO - __main__ - Step 20999: {'lr': 0.00047994565704925166, 'samples': 4031808, 'steps': 20998, 'loss/train': 1.5909682512283325}
+08/30/2021 16:59:01 - INFO - __main__ - Step 21000: {'lr': 0.0004799435744811477, 'samples': 4032000, 'steps': 20999, 'loss/train': 1.0935367345809937}
+08/30/2021 16:59:01 - INFO - __main__ - Step 21001: {'lr': 0.0004799414918094347, 'samples': 4032192, 'steps': 21000, 'loss/train': 1.9355828762054443}
+08/30/2021 16:59:02 - INFO - __main__ - Step 21002: {'lr': 0.0004799394090341136, 'samples': 4032384, 'steps': 21001, 'loss/train': 1.5669392347335815}
+08/30/2021 16:59:03 - INFO - __main__ - Step 21003: {'lr': 0.0004799373261551854, 'samples': 4032576, 'steps': 21002, 'loss/train': 1.6707897186279297}
+08/30/2021 16:59:04 - INFO - __main__ - Step 21004: {'lr': 0.0004799352431726509, 'samples': 4032768, 'steps': 21003, 'loss/train': 1.8671692609786987}
+08/30/2021 16:59:04 - INFO - __main__ - Step 21005: {'lr': 0.0004799331600865112, 'samples': 4032960, 'steps': 21004, 'loss/train': 1.4355348348617554}
+08/30/2021 16:59:04 - INFO - __main__ - Step 21006: {'lr': 0.0004799310768967671, 'samples': 4033152, 'steps': 21005, 'loss/train': 1.6290297508239746}
+08/30/2021 16:59:05 - INFO - __main__ - Step 21007: {'lr': 0.00047992899360341966, 'samples': 4033344, 'steps': 21006, 'loss/train': 1.5777473449707031}
+08/30/2021 16:59:06 - INFO - __main__ - Step 21008: {'lr': 0.0004799269102064698, 'samples': 4033536, 'steps': 21007, 'loss/train': 1.8052923679351807}
+08/30/2021 16:59:06 - INFO - __main__ - Step 21009: {'lr': 0.0004799248267059183, 'samples': 4033728, 'steps': 21008, 'loss/train': 1.715876579284668}
+08/30/2021 16:59:07 - INFO - __main__ - Step 21010: {'lr': 0.0004799227431017663, 'samples': 4033920, 'steps': 21009, 'loss/train': 1.5748149156570435}
+08/30/2021 16:59:07 - INFO - __main__ - Step 21011: {'lr': 0.0004799206593940147, 'samples': 4034112, 'steps': 21010, 'loss/train': 1.6504967212677002}
+08/30/2021 16:59:08 - INFO - __main__ - Step 21012: {'lr': 0.0004799185755826644, 'samples': 4034304, 'steps': 21011, 'loss/train': 1.7354111671447754}
+08/30/2021 16:59:09 - INFO - __main__ - Step 21013: {'lr': 0.00047991649166771624, 'samples': 4034496, 'steps': 21012, 'loss/train': 1.6346644163131714}
+08/30/2021 16:59:10 - INFO - __main__ - Step 21014: {'lr': 0.00047991440764917127, 'samples': 4034688, 'steps': 21013, 'loss/train': 2.4204812049865723}
+08/30/2021 16:59:10 - INFO - __main__ - Step 21015: {'lr': 0.0004799123235270305, 'samples': 4034880, 'steps': 21014, 'loss/train': 1.6461856365203857}
+08/30/2021 16:59:10 - INFO - __main__ - Step 21016: {'lr': 0.0004799102393012947, 'samples': 4035072, 'steps': 21015, 'loss/train': 1.6606346368789673}
+08/30/2021 16:59:11 - INFO - __main__ - Step 21017: {'lr': 0.0004799081549719649, 'samples': 4035264, 'steps': 21016, 'loss/train': 1.1760226488113403}
+08/30/2021 16:59:12 - INFO - __main__ - Step 21018: {'lr': 0.0004799060705390421, 'samples': 4035456, 'steps': 21017, 'loss/train': 2.0579817295074463}
+08/30/2021 16:59:12 - INFO - __main__ - Step 21019: {'lr': 0.00047990398600252713, 'samples': 4035648, 'steps': 21018, 'loss/train': 1.7861557006835938}
+08/30/2021 16:59:13 - INFO - __main__ - Step 21020: {'lr': 0.00047990190136242103, 'samples': 4035840, 'steps': 21019, 'loss/train': 1.7574015855789185}
+08/30/2021 16:59:13 - INFO - __main__ - Step 21021: {'lr': 0.0004798998166187246, 'samples': 4036032, 'steps': 21020, 'loss/train': 1.1989426612854004}
+08/30/2021 16:59:14 - INFO - __main__ - Step 21022: {'lr': 0.0004798977317714389, 'samples': 4036224, 'steps': 21021, 'loss/train': 1.8363909721374512}
+08/30/2021 16:59:16 - INFO - __main__ - Step 21023: {'lr': 0.00047989564682056487, 'samples': 4036416, 'steps': 21022, 'loss/train': 1.7746086120605469}
+08/30/2021 16:59:16 - INFO - __main__ - Step 21024: {'lr': 0.0004798935617661033, 'samples': 4036608, 'steps': 21023, 'loss/train': 1.5361837148666382}
+08/30/2021 16:59:16 - INFO - __main__ - Step 21025: {'lr': 0.0004798914766080553, 'samples': 4036800, 'steps': 21024, 'loss/train': 2.529196262359619}
+08/30/2021 16:59:17 - INFO - __main__ - Step 21026: {'lr': 0.00047988939134642174, 'samples': 4036992, 'steps': 21025, 'loss/train': 1.467066764831543}
+08/30/2021 16:59:17 - INFO - __main__ - Step 21027: {'lr': 0.00047988730598120356, 'samples': 4037184, 'steps': 21026, 'loss/train': 1.8944923877716064}
+08/30/2021 16:59:19 - INFO - __main__ - Step 21028: {'lr': 0.00047988522051240173, 'samples': 4037376, 'steps': 21027, 'loss/train': 0.8948488831520081}
+08/30/2021 16:59:19 - INFO - __main__ - Step 21029: {'lr': 0.0004798831349400172, 'samples': 4037568, 'steps': 21028, 'loss/train': 2.0099880695343018}
+08/30/2021 16:59:19 - INFO - __main__ - Step 21030: {'lr': 0.0004798810492640508, 'samples': 4037760, 'steps': 21029, 'loss/train': 1.7088042497634888}
+08/30/2021 16:59:20 - INFO - __main__ - Step 21031: {'lr': 0.00047987896348450354, 'samples': 4037952, 'steps': 21030, 'loss/train': 1.5720404386520386}
+08/30/2021 16:59:20 - INFO - __main__ - Step 21032: {'lr': 0.00047987687760137646, 'samples': 4038144, 'steps': 21031, 'loss/train': 1.5632773637771606}
+08/30/2021 16:59:21 - INFO - __main__ - Step 21033: {'lr': 0.00047987479161467033, 'samples': 4038336, 'steps': 21032, 'loss/train': 1.9008517265319824}
+08/30/2021 16:59:22 - INFO - __main__ - Step 21034: {'lr': 0.0004798727055243862, 'samples': 4038528, 'steps': 21033, 'loss/train': 1.5379389524459839}
+08/30/2021 16:59:23 - INFO - __main__ - Step 21035: {'lr': 0.000479870619330525, 'samples': 4038720, 'steps': 21034, 'loss/train': 0.876471757888794}
+08/30/2021 16:59:23 - INFO - __main__ - Step 21036: {'lr': 0.0004798685330330876, 'samples': 4038912, 'steps': 21035, 'loss/train': 1.7168902158737183}
+08/30/2021 16:59:23 - INFO - __main__ - Step 21037: {'lr': 0.000479866446632075, 'samples': 4039104, 'steps': 21036, 'loss/train': 1.406392216682434}
+08/30/2021 16:59:24 - INFO - __main__ - Step 21038: {'lr': 0.00047986436012748815, 'samples': 4039296, 'steps': 21037, 'loss/train': 1.267569661140442}
+08/30/2021 16:59:25 - INFO - __main__ - Step 21039: {'lr': 0.00047986227351932785, 'samples': 4039488, 'steps': 21038, 'loss/train': 1.684775710105896}
+08/30/2021 16:59:26 - INFO - __main__ - Step 21040: {'lr': 0.00047986018680759525, 'samples': 4039680, 'steps': 21039, 'loss/train': 1.8256009817123413}
+08/30/2021 16:59:26 - INFO - __main__ - Step 21041: {'lr': 0.00047985809999229125, 'samples': 4039872, 'steps': 21040, 'loss/train': 1.766939640045166}
+08/30/2021 16:59:26 - INFO - __main__ - Step 21042: {'lr': 0.00047985601307341667, 'samples': 4040064, 'steps': 21041, 'loss/train': 1.1235382556915283}
+08/30/2021 16:59:27 - INFO - __main__ - Step 21043: {'lr': 0.0004798539260509725, 'samples': 4040256, 'steps': 21042, 'loss/train': 1.7099907398223877}
+08/30/2021 16:59:28 - INFO - __main__ - Step 21044: {'lr': 0.00047985183892495977, 'samples': 4040448, 'steps': 21043, 'loss/train': 1.3469377756118774}
+08/30/2021 16:59:29 - INFO - __main__ - Step 21045: {'lr': 0.00047984975169537925, 'samples': 4040640, 'steps': 21044, 'loss/train': 0.8599517941474915}
+08/30/2021 16:59:29 - INFO - __main__ - Step 21046: {'lr': 0.00047984766436223205, 'samples': 4040832, 'steps': 21045, 'loss/train': 1.3645668029785156}
+08/30/2021 16:59:29 - INFO - __main__ - Step 21047: {'lr': 0.000479845576925519, 'samples': 4041024, 'steps': 21046, 'loss/train': 1.9667969942092896}
+08/30/2021 16:59:30 - INFO - __main__ - Step 21048: {'lr': 0.00047984348938524113, 'samples': 4041216, 'steps': 21047, 'loss/train': 1.1815723180770874}
+08/30/2021 16:59:31 - INFO - __main__ - Step 21049: {'lr': 0.00047984140174139926, 'samples': 4041408, 'steps': 21048, 'loss/train': 1.5975016355514526}
+08/30/2021 16:59:32 - INFO - __main__ - Step 21050: {'lr': 0.0004798393139939945, 'samples': 4041600, 'steps': 21049, 'loss/train': 1.9904526472091675}
+08/30/2021 16:59:32 - INFO - __main__ - Step 21051: {'lr': 0.0004798372261430276, 'samples': 4041792, 'steps': 21050, 'loss/train': 2.2192118167877197}
+08/30/2021 16:59:33 - INFO - __main__ - Step 21052: {'lr': 0.00047983513818849967, 'samples': 4041984, 'steps': 21051, 'loss/train': 1.5575976371765137}
+08/30/2021 16:59:33 - INFO - __main__ - Step 21053: {'lr': 0.0004798330501304115, 'samples': 4042176, 'steps': 21052, 'loss/train': 1.6344659328460693}
+08/30/2021 16:59:34 - INFO - __main__ - Step 21054: {'lr': 0.00047983096196876413, 'samples': 4042368, 'steps': 21053, 'loss/train': 1.3212599754333496}
+08/30/2021 16:59:35 - INFO - __main__ - Step 21055: {'lr': 0.00047982887370355846, 'samples': 4042560, 'steps': 21054, 'loss/train': 1.4824053049087524}
+08/30/2021 16:59:35 - INFO - __main__ - Step 21056: {'lr': 0.0004798267853347955, 'samples': 4042752, 'steps': 21055, 'loss/train': 1.472094178199768}
+08/30/2021 16:59:36 - INFO - __main__ - Step 21057: {'lr': 0.0004798246968624761, 'samples': 4042944, 'steps': 21056, 'loss/train': 1.0333106517791748}
+08/30/2021 16:59:36 - INFO - __main__ - Step 21058: {'lr': 0.00047982260828660124, 'samples': 4043136, 'steps': 21057, 'loss/train': 1.8350293636322021}
+08/30/2021 16:59:37 - INFO - __main__ - Step 21059: {'lr': 0.0004798205196071719, 'samples': 4043328, 'steps': 21058, 'loss/train': 1.284170150756836}
+08/30/2021 16:59:38 - INFO - __main__ - Step 21060: {'lr': 0.00047981843082418884, 'samples': 4043520, 'steps': 21059, 'loss/train': 1.7510058879852295}
+08/30/2021 16:59:38 - INFO - __main__ - Step 21061: {'lr': 0.0004798163419376533, 'samples': 4043712, 'steps': 21060, 'loss/train': 1.8825178146362305}
+08/30/2021 16:59:39 - INFO - __main__ - Step 21062: {'lr': 0.00047981425294756595, 'samples': 4043904, 'steps': 21061, 'loss/train': 1.579464316368103}
+08/30/2021 16:59:39 - INFO - __main__ - Step 21063: {'lr': 0.00047981216385392796, 'samples': 4044096, 'steps': 21062, 'loss/train': 1.7650657892227173}
+08/30/2021 16:59:39 - INFO - __main__ - Step 21064: {'lr': 0.0004798100746567401, 'samples': 4044288, 'steps': 21063, 'loss/train': 1.6939369440078735}
+08/30/2021 16:59:41 - INFO - __main__ - Step 21065: {'lr': 0.00047980798535600334, 'samples': 4044480, 'steps': 21064, 'loss/train': 1.627752661705017}
+08/30/2021 16:59:41 - INFO - __main__ - Step 21066: {'lr': 0.00047980589595171866, 'samples': 4044672, 'steps': 21065, 'loss/train': 1.8847434520721436}
+08/30/2021 16:59:42 - INFO - __main__ - Step 21067: {'lr': 0.000479803806443887, 'samples': 4044864, 'steps': 21066, 'loss/train': 1.7405376434326172}
+08/30/2021 16:59:42 - INFO - __main__ - Step 21068: {'lr': 0.0004798017168325093, 'samples': 4045056, 'steps': 21067, 'loss/train': 1.945316195487976}
+08/30/2021 16:59:42 - INFO - __main__ - Step 21069: {'lr': 0.0004797996271175865, 'samples': 4045248, 'steps': 21068, 'loss/train': 2.127417802810669}
+08/30/2021 16:59:44 - INFO - __main__ - Step 21070: {'lr': 0.00047979753729911944, 'samples': 4045440, 'steps': 21069, 'loss/train': 1.282895803451538}
+08/30/2021 16:59:44 - INFO - __main__ - Step 21071: {'lr': 0.00047979544737710925, 'samples': 4045632, 'steps': 21070, 'loss/train': 1.419189691543579}
+08/30/2021 16:59:45 - INFO - __main__ - Step 21072: {'lr': 0.00047979335735155677, 'samples': 4045824, 'steps': 21071, 'loss/train': 1.1895549297332764}
+08/30/2021 16:59:45 - INFO - __main__ - Step 21073: {'lr': 0.00047979126722246294, 'samples': 4046016, 'steps': 21072, 'loss/train': 1.095531940460205}
+08/30/2021 16:59:45 - INFO - __main__ - Step 21074: {'lr': 0.0004797891769898287, 'samples': 4046208, 'steps': 21073, 'loss/train': 1.6173202991485596}
+08/30/2021 16:59:47 - INFO - __main__ - Step 21075: {'lr': 0.00047978708665365503, 'samples': 4046400, 'steps': 21074, 'loss/train': 0.8989821672439575}
+08/30/2021 16:59:48 - INFO - __main__ - Step 21076: {'lr': 0.0004797849962139428, 'samples': 4046592, 'steps': 21075, 'loss/train': 1.6845216751098633}
+08/30/2021 16:59:48 - INFO - __main__ - Step 21077: {'lr': 0.00047978290567069306, 'samples': 4046784, 'steps': 21076, 'loss/train': 1.3722569942474365}
+08/30/2021 16:59:49 - INFO - __main__ - Step 21078: {'lr': 0.00047978081502390656, 'samples': 4046976, 'steps': 21077, 'loss/train': 1.6358416080474854}
+08/30/2021 16:59:49 - INFO - __main__ - Step 21079: {'lr': 0.0004797787242735845, 'samples': 4047168, 'steps': 21078, 'loss/train': 0.790678083896637}
+08/30/2021 16:59:49 - INFO - __main__ - Step 21080: {'lr': 0.00047977663341972765, 'samples': 4047360, 'steps': 21079, 'loss/train': 2.2479915618896484}
+08/30/2021 16:59:51 - INFO - __main__ - Step 21081: {'lr': 0.00047977454246233696, 'samples': 4047552, 'steps': 21080, 'loss/train': 1.709816575050354}
+08/30/2021 16:59:51 - INFO - __main__ - Step 21082: {'lr': 0.00047977245140141354, 'samples': 4047744, 'steps': 21081, 'loss/train': 1.2808079719543457}
+08/30/2021 16:59:52 - INFO - __main__ - Step 21083: {'lr': 0.00047977036023695807, 'samples': 4047936, 'steps': 21082, 'loss/train': 1.2697173357009888}
+08/30/2021 16:59:52 - INFO - __main__ - Step 21084: {'lr': 0.00047976826896897165, 'samples': 4048128, 'steps': 21083, 'loss/train': 1.6275309324264526}
+08/30/2021 16:59:52 - INFO - __main__ - Step 21085: {'lr': 0.0004797661775974552, 'samples': 4048320, 'steps': 21084, 'loss/train': 1.8187636137008667}
+08/30/2021 16:59:54 - INFO - __main__ - Step 21086: {'lr': 0.00047976408612240964, 'samples': 4048512, 'steps': 21085, 'loss/train': 1.1905463933944702}
+08/30/2021 16:59:54 - INFO - __main__ - Step 21087: {'lr': 0.00047976199454383595, 'samples': 4048704, 'steps': 21086, 'loss/train': 2.2994184494018555}
+08/30/2021 16:59:55 - INFO - __main__ - Step 21088: {'lr': 0.00047975990286173504, 'samples': 4048896, 'steps': 21087, 'loss/train': 1.679661512374878}
+08/30/2021 16:59:55 - INFO - __main__ - Step 21089: {'lr': 0.00047975781107610784, 'samples': 4049088, 'steps': 21088, 'loss/train': 0.8422901034355164}
+08/30/2021 16:59:56 - INFO - __main__ - Step 21090: {'lr': 0.0004797557191869554, 'samples': 4049280, 'steps': 21089, 'loss/train': 1.6706513166427612}
+08/30/2021 16:59:57 - INFO - __main__ - Step 21091: {'lr': 0.0004797536271942785, 'samples': 4049472, 'steps': 21090, 'loss/train': 1.8182177543640137}
+08/30/2021 16:59:57 - INFO - __main__ - Step 21092: {'lr': 0.00047975153509807815, 'samples': 4049664, 'steps': 21091, 'loss/train': 1.387774109840393}
+08/30/2021 16:59:58 - INFO - __main__ - Step 21093: {'lr': 0.0004797494428983553, 'samples': 4049856, 'steps': 21092, 'loss/train': 1.8198074102401733}
+08/30/2021 16:59:58 - INFO - __main__ - Step 21094: {'lr': 0.000479747350595111, 'samples': 4050048, 'steps': 21093, 'loss/train': 1.0651737451553345}
+08/30/2021 16:59:58 - INFO - __main__ - Step 21095: {'lr': 0.00047974525818834604, 'samples': 4050240, 'steps': 21094, 'loss/train': 1.5520455837249756}
+08/30/2021 17:00:00 - INFO - __main__ - Step 21096: {'lr': 0.0004797431656780613, 'samples': 4050432, 'steps': 21095, 'loss/train': 1.5461673736572266}
+08/30/2021 17:00:00 - INFO - __main__ - Step 21097: {'lr': 0.000479741073064258, 'samples': 4050624, 'steps': 21096, 'loss/train': 1.611256718635559}
+08/30/2021 17:00:01 - INFO - __main__ - Step 21098: {'lr': 0.0004797389803469369, 'samples': 4050816, 'steps': 21097, 'loss/train': 1.0551233291625977}
+08/30/2021 17:00:01 - INFO - __main__ - Step 21099: {'lr': 0.0004797368875260988, 'samples': 4051008, 'steps': 21098, 'loss/train': 0.49395498633384705}
+08/30/2021 17:00:01 - INFO - __main__ - Step 21100: {'lr': 0.00047973479460174497, 'samples': 4051200, 'steps': 21099, 'loss/train': 1.0994573831558228}
+08/30/2021 17:00:03 - INFO - __main__ - Step 21101: {'lr': 0.00047973270157387605, 'samples': 4051392, 'steps': 21100, 'loss/train': 1.73939847946167}
+08/30/2021 17:00:04 - INFO - __main__ - Step 21102: {'lr': 0.0004797306084424932, 'samples': 4051584, 'steps': 21101, 'loss/train': 1.246307611465454}
+08/30/2021 17:00:04 - INFO - __main__ - Step 21103: {'lr': 0.0004797285152075973, 'samples': 4051776, 'steps': 21102, 'loss/train': 1.6441198587417603}
+08/30/2021 17:00:04 - INFO - __main__ - Step 21104: {'lr': 0.00047972642186918925, 'samples': 4051968, 'steps': 21103, 'loss/train': 1.1580528020858765}
+08/30/2021 17:00:05 - INFO - __main__ - Step 21105: {'lr': 0.00047972432842727003, 'samples': 4052160, 'steps': 21104, 'loss/train': 2.2623374462127686}
+08/30/2021 17:00:06 - INFO - __main__ - Step 21106: {'lr': 0.0004797222348818405, 'samples': 4052352, 'steps': 21105, 'loss/train': 2.3679537773132324}
+08/30/2021 17:00:07 - INFO - __main__ - Step 21107: {'lr': 0.00047972014123290183, 'samples': 4052544, 'steps': 21106, 'loss/train': 1.9266010522842407}
+08/30/2021 17:00:07 - INFO - __main__ - Step 21108: {'lr': 0.00047971804748045464, 'samples': 4052736, 'steps': 21107, 'loss/train': 1.6839982271194458}
+08/30/2021 17:00:07 - INFO - __main__ - Step 21109: {'lr': 0.00047971595362450014, 'samples': 4052928, 'steps': 21108, 'loss/train': 1.119568109512329}
+08/30/2021 17:00:08 - INFO - __main__ - Step 21110: {'lr': 0.00047971385966503923, 'samples': 4053120, 'steps': 21109, 'loss/train': 1.3776720762252808}
+08/30/2021 17:00:08 - INFO - __main__ - Step 21111: {'lr': 0.0004797117656020727, 'samples': 4053312, 'steps': 21110, 'loss/train': 2.06646728515625}
+08/30/2021 17:00:09 - INFO - __main__ - Step 21112: {'lr': 0.0004797096714356016, 'samples': 4053504, 'steps': 21111, 'loss/train': 1.4350123405456543}
+08/30/2021 17:00:10 - INFO - __main__ - Step 21113: {'lr': 0.0004797075771656269, 'samples': 4053696, 'steps': 21112, 'loss/train': 6.5142292976379395}
+08/30/2021 17:00:10 - INFO - __main__ - Step 21114: {'lr': 0.0004797054827921495, 'samples': 4053888, 'steps': 21113, 'loss/train': 1.6243597269058228}
+08/30/2021 17:00:11 - INFO - __main__ - Step 21115: {'lr': 0.0004797033883151703, 'samples': 4054080, 'steps': 21114, 'loss/train': 1.6746667623519897}
+08/30/2021 17:00:11 - INFO - __main__ - Step 21116: {'lr': 0.0004797012937346904, 'samples': 4054272, 'steps': 21115, 'loss/train': 1.171312928199768}
+08/30/2021 17:00:12 - INFO - __main__ - Step 21117: {'lr': 0.0004796991990507106, 'samples': 4054464, 'steps': 21116, 'loss/train': 1.5629198551177979}
+08/30/2021 17:00:13 - INFO - __main__ - Step 21118: {'lr': 0.00047969710426323185, 'samples': 4054656, 'steps': 21117, 'loss/train': 1.9510616064071655}
+08/30/2021 17:00:13 - INFO - __main__ - Step 21119: {'lr': 0.0004796950093722552, 'samples': 4054848, 'steps': 21118, 'loss/train': 1.6718730926513672}
+08/30/2021 17:00:14 - INFO - __main__ - Step 21120: {'lr': 0.00047969291437778143, 'samples': 4055040, 'steps': 21119, 'loss/train': 1.4792535305023193}
+08/30/2021 17:00:14 - INFO - __main__ - Step 21121: {'lr': 0.00047969081927981165, 'samples': 4055232, 'steps': 21120, 'loss/train': 1.7120091915130615}
+08/30/2021 17:00:15 - INFO - __main__ - Step 21122: {'lr': 0.0004796887240783467, 'samples': 4055424, 'steps': 21121, 'loss/train': 1.5738706588745117}
+08/30/2021 17:00:16 - INFO - __main__ - Step 21123: {'lr': 0.0004796866287733875, 'samples': 4055616, 'steps': 21122, 'loss/train': 1.5310466289520264}
+08/30/2021 17:00:16 - INFO - __main__ - Step 21124: {'lr': 0.0004796845333649352, 'samples': 4055808, 'steps': 21123, 'loss/train': 1.5130800008773804}
+08/30/2021 17:00:17 - INFO - __main__ - Step 21125: {'lr': 0.00047968243785299046, 'samples': 4056000, 'steps': 21124, 'loss/train': 1.5441941022872925}
+08/30/2021 17:00:17 - INFO - __main__ - Step 21126: {'lr': 0.0004796803422375544, 'samples': 4056192, 'steps': 21125, 'loss/train': 1.8245644569396973}
+08/30/2021 17:00:17 - INFO - __main__ - Step 21127: {'lr': 0.0004796782465186279, 'samples': 4056384, 'steps': 21126, 'loss/train': 1.6191391944885254}
+08/30/2021 17:00:19 - INFO - __main__ - Step 21128: {'lr': 0.00047967615069621197, 'samples': 4056576, 'steps': 21127, 'loss/train': 1.7516992092132568}
+08/30/2021 17:00:19 - INFO - __main__ - Step 21129: {'lr': 0.0004796740547703075, 'samples': 4056768, 'steps': 21128, 'loss/train': 1.7212977409362793}
+08/30/2021 17:00:20 - INFO - __main__ - Step 21130: {'lr': 0.00047967195874091547, 'samples': 4056960, 'steps': 21129, 'loss/train': 1.614676833152771}
+08/30/2021 17:00:20 - INFO - __main__ - Step 21131: {'lr': 0.00047966986260803676, 'samples': 4057152, 'steps': 21130, 'loss/train': 0.2862565517425537}
+08/30/2021 17:00:20 - INFO - __main__ - Step 21132: {'lr': 0.0004796677663716723, 'samples': 4057344, 'steps': 21131, 'loss/train': 1.4826680421829224}
+08/30/2021 17:00:22 - INFO - __main__ - Step 21133: {'lr': 0.00047966567003182315, 'samples': 4057536, 'steps': 21132, 'loss/train': 1.4634411334991455}
+08/30/2021 17:00:23 - INFO - __main__ - Step 21134: {'lr': 0.0004796635735884902, 'samples': 4057728, 'steps': 21133, 'loss/train': 1.0680818557739258}
+08/30/2021 17:00:23 - INFO - __main__ - Step 21135: {'lr': 0.0004796614770416744, 'samples': 4057920, 'steps': 21134, 'loss/train': 1.6191478967666626}
+08/30/2021 17:00:23 - INFO - __main__ - Step 21136: {'lr': 0.00047965938039137666, 'samples': 4058112, 'steps': 21135, 'loss/train': 1.191550850868225}
+08/30/2021 17:00:24 - INFO - __main__ - Step 21137: {'lr': 0.000479657283637598, 'samples': 4058304, 'steps': 21136, 'loss/train': 1.3693060874938965}
+08/30/2021 17:00:25 - INFO - __main__ - Step 21138: {'lr': 0.00047965518678033924, 'samples': 4058496, 'steps': 21137, 'loss/train': 0.7484496235847473}
+08/30/2021 17:00:26 - INFO - __main__ - Step 21139: {'lr': 0.00047965308981960143, 'samples': 4058688, 'steps': 21138, 'loss/train': 1.3798872232437134}
+08/30/2021 17:00:26 - INFO - __main__ - Step 21140: {'lr': 0.0004796509927553854, 'samples': 4058880, 'steps': 21139, 'loss/train': 1.4580025672912598}
+08/30/2021 17:00:26 - INFO - __main__ - Step 21141: {'lr': 0.00047964889558769233, 'samples': 4059072, 'steps': 21140, 'loss/train': 2.0219380855560303}
+08/30/2021 17:00:27 - INFO - __main__ - Step 21142: {'lr': 0.00047964679831652294, 'samples': 4059264, 'steps': 21141, 'loss/train': 1.180588960647583}
+08/30/2021 17:00:28 - INFO - __main__ - Step 21143: {'lr': 0.00047964470094187815, 'samples': 4059456, 'steps': 21142, 'loss/train': 1.8486741781234741}
+08/30/2021 17:00:29 - INFO - __main__ - Step 21144: {'lr': 0.0004796426034637591, 'samples': 4059648, 'steps': 21143, 'loss/train': 2.0078158378601074}
+08/30/2021 17:00:29 - INFO - __main__ - Step 21145: {'lr': 0.0004796405058821666, 'samples': 4059840, 'steps': 21144, 'loss/train': 1.6045961380004883}
+08/30/2021 17:00:30 - INFO - __main__ - Step 21146: {'lr': 0.0004796384081971017, 'samples': 4060032, 'steps': 21145, 'loss/train': 1.570224404335022}
+08/30/2021 17:00:30 - INFO - __main__ - Step 21147: {'lr': 0.0004796363104085652, 'samples': 4060224, 'steps': 21146, 'loss/train': 2.0301578044891357}
+08/30/2021 17:00:31 - INFO - __main__ - Step 21148: {'lr': 0.00047963421251655817, 'samples': 4060416, 'steps': 21147, 'loss/train': 1.9047797918319702}
+08/30/2021 17:00:32 - INFO - __main__ - Step 21149: {'lr': 0.00047963211452108144, 'samples': 4060608, 'steps': 21148, 'loss/train': 1.92880380153656}
+08/30/2021 17:00:32 - INFO - __main__ - Step 21150: {'lr': 0.0004796300164221361, 'samples': 4060800, 'steps': 21149, 'loss/train': 1.8172188997268677}
+08/30/2021 17:00:33 - INFO - __main__ - Step 21151: {'lr': 0.00047962791821972296, 'samples': 4060992, 'steps': 21150, 'loss/train': 2.119884967803955}
+08/30/2021 17:00:33 - INFO - __main__ - Step 21152: {'lr': 0.00047962581991384305, 'samples': 4061184, 'steps': 21151, 'loss/train': 1.7036997079849243}
+08/30/2021 17:00:33 - INFO - __main__ - Step 21153: {'lr': 0.0004796237215044973, 'samples': 4061376, 'steps': 21152, 'loss/train': 1.6930289268493652}
+08/30/2021 17:00:35 - INFO - __main__ - Step 21154: {'lr': 0.0004796216229916867, 'samples': 4061568, 'steps': 21153, 'loss/train': 1.6659579277038574}
+08/30/2021 17:00:35 - INFO - __main__ - Step 21155: {'lr': 0.000479619524375412, 'samples': 4061760, 'steps': 21154, 'loss/train': 1.9712690114974976}
+08/30/2021 17:00:36 - INFO - __main__ - Step 21156: {'lr': 0.0004796174256556744, 'samples': 4061952, 'steps': 21155, 'loss/train': 1.701959252357483}
+08/30/2021 17:00:36 - INFO - __main__ - Step 21157: {'lr': 0.0004796153268324747, 'samples': 4062144, 'steps': 21156, 'loss/train': 1.6595348119735718}
+08/30/2021 17:00:36 - INFO - __main__ - Step 21158: {'lr': 0.00047961322790581384, 'samples': 4062336, 'steps': 21157, 'loss/train': 1.7811648845672607}
+08/30/2021 17:00:38 - INFO - __main__ - Step 21159: {'lr': 0.00047961112887569285, 'samples': 4062528, 'steps': 21158, 'loss/train': 1.2896312475204468}
+08/30/2021 17:00:38 - INFO - __main__ - Step 21160: {'lr': 0.0004796090297421126, 'samples': 4062720, 'steps': 21159, 'loss/train': 1.0237380266189575}
+08/30/2021 17:00:39 - INFO - __main__ - Step 21161: {'lr': 0.0004796069305050741, 'samples': 4062912, 'steps': 21160, 'loss/train': 1.6675056219100952}
+08/30/2021 17:00:39 - INFO - __main__ - Step 21162: {'lr': 0.0004796048311645782, 'samples': 4063104, 'steps': 21161, 'loss/train': 1.378087043762207}
+08/30/2021 17:00:39 - INFO - __main__ - Step 21163: {'lr': 0.00047960273172062596, 'samples': 4063296, 'steps': 21162, 'loss/train': 1.5852527618408203}
+08/30/2021 17:00:41 - INFO - __main__ - Step 21164: {'lr': 0.00047960063217321824, 'samples': 4063488, 'steps': 21163, 'loss/train': 1.6329618692398071}
+08/30/2021 17:00:41 - INFO - __main__ - Step 21165: {'lr': 0.0004795985325223561, 'samples': 4063680, 'steps': 21164, 'loss/train': 6.379885673522949}
+08/30/2021 17:00:41 - INFO - __main__ - Step 21166: {'lr': 0.00047959643276804026, 'samples': 4063872, 'steps': 21165, 'loss/train': 1.1205564737319946}
+08/30/2021 17:00:42 - INFO - __main__ - Step 21167: {'lr': 0.0004795943329102719, 'samples': 4064064, 'steps': 21166, 'loss/train': 1.3630781173706055}
+08/30/2021 17:00:42 - INFO - __main__ - Step 21168: {'lr': 0.00047959223294905185, 'samples': 4064256, 'steps': 21167, 'loss/train': 1.8570128679275513}
+08/30/2021 17:00:44 - INFO - __main__ - Step 21169: {'lr': 0.00047959013288438113, 'samples': 4064448, 'steps': 21168, 'loss/train': 1.3203643560409546}
+08/30/2021 17:00:45 - INFO - __main__ - Step 21170: {'lr': 0.0004795880327162606, 'samples': 4064640, 'steps': 21169, 'loss/train': 1.1915868520736694}
+08/30/2021 17:00:45 - INFO - __main__ - Step 21171: {'lr': 0.0004795859324446912, 'samples': 4064832, 'steps': 21170, 'loss/train': 0.10693927109241486}
+08/30/2021 17:00:45 - INFO - __main__ - Step 21172: {'lr': 0.000479583832069674, 'samples': 4065024, 'steps': 21171, 'loss/train': 0.39779266715049744}
+08/30/2021 17:00:46 - INFO - __main__ - Step 21173: {'lr': 0.00047958173159120984, 'samples': 4065216, 'steps': 21172, 'loss/train': 1.258679986000061}
+08/30/2021 17:00:47 - INFO - __main__ - Step 21174: {'lr': 0.0004795796310092997, 'samples': 4065408, 'steps': 21173, 'loss/train': 1.0735141038894653}
+08/30/2021 17:00:48 - INFO - __main__ - Step 21175: {'lr': 0.00047957753032394445, 'samples': 4065600, 'steps': 21174, 'loss/train': 1.6297802925109863}
+08/30/2021 17:00:48 - INFO - __main__ - Step 21176: {'lr': 0.00047957542953514523, 'samples': 4065792, 'steps': 21175, 'loss/train': 1.7633613348007202}
+08/30/2021 17:00:48 - INFO - __main__ - Step 21177: {'lr': 0.00047957332864290283, 'samples': 4065984, 'steps': 21176, 'loss/train': 2.5928258895874023}
+08/30/2021 17:00:49 - INFO - __main__ - Step 21178: {'lr': 0.00047957122764721817, 'samples': 4066176, 'steps': 21177, 'loss/train': 1.5828711986541748}
+08/30/2021 17:00:50 - INFO - __main__ - Step 21179: {'lr': 0.00047956912654809227, 'samples': 4066368, 'steps': 21178, 'loss/train': 1.8395119905471802}
+08/30/2021 17:00:51 - INFO - __main__ - Step 21180: {'lr': 0.0004795670253455261, 'samples': 4066560, 'steps': 21179, 'loss/train': 1.6991662979125977}
+08/30/2021 17:00:51 - INFO - __main__ - Step 21181: {'lr': 0.00047956492403952055, 'samples': 4066752, 'steps': 21180, 'loss/train': 2.4299497604370117}
+08/30/2021 17:00:51 - INFO - __main__ - Step 21182: {'lr': 0.00047956282263007663, 'samples': 4066944, 'steps': 21181, 'loss/train': 1.1073206663131714}
+08/30/2021 17:00:52 - INFO - __main__ - Step 21183: {'lr': 0.00047956072111719517, 'samples': 4067136, 'steps': 21182, 'loss/train': 0.08222738653421402}
+08/30/2021 17:00:52 - INFO - __main__ - Step 21184: {'lr': 0.00047955861950087724, 'samples': 4067328, 'steps': 21183, 'loss/train': 1.4232593774795532}
+08/30/2021 17:00:54 - INFO - __main__ - Step 21185: {'lr': 0.00047955651778112376, 'samples': 4067520, 'steps': 21184, 'loss/train': 1.5396087169647217}
+08/30/2021 17:00:55 - INFO - __main__ - Step 21186: {'lr': 0.00047955441595793556, 'samples': 4067712, 'steps': 21185, 'loss/train': 1.8421236276626587}
+08/30/2021 17:00:55 - INFO - __main__ - Step 21187: {'lr': 0.0004795523140313138, 'samples': 4067904, 'steps': 21186, 'loss/train': 1.4485394954681396}
+08/30/2021 17:00:56 - INFO - __main__ - Step 21188: {'lr': 0.00047955021200125924, 'samples': 4068096, 'steps': 21187, 'loss/train': 1.758474349975586}
+08/30/2021 17:00:56 - INFO - __main__ - Step 21189: {'lr': 0.0004795481098677729, 'samples': 4068288, 'steps': 21188, 'loss/train': 1.2918554544448853}
+08/30/2021 17:00:57 - INFO - __main__ - Step 21190: {'lr': 0.00047954600763085577, 'samples': 4068480, 'steps': 21189, 'loss/train': 3.0587217807769775}
+08/30/2021 17:00:58 - INFO - __main__ - Step 21191: {'lr': 0.0004795439052905087, 'samples': 4068672, 'steps': 21190, 'loss/train': 1.4779027700424194}
+08/30/2021 17:00:58 - INFO - __main__ - Step 21192: {'lr': 0.0004795418028467327, 'samples': 4068864, 'steps': 21191, 'loss/train': 1.567817211151123}
+08/30/2021 17:00:59 - INFO - __main__ - Step 21193: {'lr': 0.0004795397002995288, 'samples': 4069056, 'steps': 21192, 'loss/train': 1.5164625644683838}
+08/30/2021 17:00:59 - INFO - __main__ - Step 21194: {'lr': 0.0004795375976488977, 'samples': 4069248, 'steps': 21193, 'loss/train': 1.7314308881759644}
+08/30/2021 17:01:00 - INFO - __main__ - Step 21195: {'lr': 0.00047953549489484056, 'samples': 4069440, 'steps': 21194, 'loss/train': 1.236986756324768}
+08/30/2021 17:01:01 - INFO - __main__ - Step 21196: {'lr': 0.0004795333920373583, 'samples': 4069632, 'steps': 21195, 'loss/train': 1.9612573385238647}
+08/30/2021 17:01:01 - INFO - __main__ - Step 21197: {'lr': 0.00047953128907645185, 'samples': 4069824, 'steps': 21196, 'loss/train': 1.5197736024856567}
+08/30/2021 17:01:02 - INFO - __main__ - Step 21198: {'lr': 0.000479529186012122, 'samples': 4070016, 'steps': 21197, 'loss/train': 1.5771238803863525}
+08/30/2021 17:01:02 - INFO - __main__ - Step 21199: {'lr': 0.00047952708284437, 'samples': 4070208, 'steps': 21198, 'loss/train': 1.7781250476837158}
+08/30/2021 17:01:02 - INFO - __main__ - Step 21200: {'lr': 0.0004795249795731966, 'samples': 4070400, 'steps': 21199, 'loss/train': 2.0518839359283447}
+08/30/2021 17:01:04 - INFO - __main__ - Step 21201: {'lr': 0.00047952287619860273, 'samples': 4070592, 'steps': 21200, 'loss/train': 1.9785789251327515}
+08/30/2021 17:01:04 - INFO - __main__ - Step 21202: {'lr': 0.0004795207727205895, 'samples': 4070784, 'steps': 21201, 'loss/train': 2.0732979774475098}
+08/30/2021 17:01:05 - INFO - __main__ - Step 21203: {'lr': 0.00047951866913915767, 'samples': 4070976, 'steps': 21202, 'loss/train': 1.606500506401062}
+08/30/2021 17:01:05 - INFO - __main__ - Step 21204: {'lr': 0.0004795165654543082, 'samples': 4071168, 'steps': 21203, 'loss/train': 0.6346612572669983}
+08/30/2021 17:01:05 - INFO - __main__ - Step 21205: {'lr': 0.0004795144616660422, 'samples': 4071360, 'steps': 21204, 'loss/train': 1.6594130992889404}
+08/30/2021 17:01:07 - INFO - __main__ - Step 21206: {'lr': 0.0004795123577743605, 'samples': 4071552, 'steps': 21205, 'loss/train': 1.4455301761627197}
+08/30/2021 17:01:07 - INFO - __main__ - Step 21207: {'lr': 0.0004795102537792641, 'samples': 4071744, 'steps': 21206, 'loss/train': 1.718607783317566}
+08/30/2021 17:01:08 - INFO - __main__ - Step 21208: {'lr': 0.000479508149680754, 'samples': 4071936, 'steps': 21207, 'loss/train': 2.245089530944824}
+08/30/2021 17:01:08 - INFO - __main__ - Step 21209: {'lr': 0.0004795060454788309, 'samples': 4072128, 'steps': 21208, 'loss/train': 1.3547050952911377}
+08/30/2021 17:01:08 - INFO - __main__ - Step 21210: {'lr': 0.000479503941173496, 'samples': 4072320, 'steps': 21209, 'loss/train': 1.5988857746124268}
+08/30/2021 17:01:10 - INFO - __main__ - Step 21211: {'lr': 0.0004795018367647501, 'samples': 4072512, 'steps': 21210, 'loss/train': 1.6448431015014648}
+08/30/2021 17:01:11 - INFO - __main__ - Step 21212: {'lr': 0.0004794997322525944, 'samples': 4072704, 'steps': 21211, 'loss/train': 1.3287367820739746}
+08/30/2021 17:01:11 - INFO - __main__ - Step 21213: {'lr': 0.0004794976276370295, 'samples': 4072896, 'steps': 21212, 'loss/train': 1.5425965785980225}
+08/30/2021 17:01:11 - INFO - __main__ - Step 21214: {'lr': 0.00047949552291805654, 'samples': 4073088, 'steps': 21213, 'loss/train': 1.610379934310913}
+08/30/2021 17:01:12 - INFO - __main__ - Step 21215: {'lr': 0.0004794934180956764, 'samples': 4073280, 'steps': 21214, 'loss/train': 1.6742967367172241}
+08/30/2021 17:01:13 - INFO - __main__ - Step 21216: {'lr': 0.00047949131316989016, 'samples': 4073472, 'steps': 21215, 'loss/train': 1.3280588388442993}
+08/30/2021 17:01:14 - INFO - __main__ - Step 21217: {'lr': 0.0004794892081406986, 'samples': 4073664, 'steps': 21216, 'loss/train': 1.492698073387146}
+08/30/2021 17:01:14 - INFO - __main__ - Step 21218: {'lr': 0.00047948710300810276, 'samples': 4073856, 'steps': 21217, 'loss/train': 0.12345721572637558}
+08/30/2021 17:01:14 - INFO - __main__ - Step 21219: {'lr': 0.0004794849977721036, 'samples': 4074048, 'steps': 21218, 'loss/train': 0.09284964948892593}
+08/30/2021 17:01:15 - INFO - __main__ - Step 21220: {'lr': 0.00047948289243270205, 'samples': 4074240, 'steps': 21219, 'loss/train': 0.8473216891288757}
+08/30/2021 17:01:16 - INFO - __main__ - Step 21221: {'lr': 0.000479480786989899, 'samples': 4074432, 'steps': 21220, 'loss/train': 0.8647047877311707}
+08/30/2021 17:01:17 - INFO - __main__ - Step 21222: {'lr': 0.0004794786814436955, 'samples': 4074624, 'steps': 21221, 'loss/train': 1.4903291463851929}
+08/30/2021 17:01:17 - INFO - __main__ - Step 21223: {'lr': 0.0004794765757940924, 'samples': 4074816, 'steps': 21222, 'loss/train': 1.6796345710754395}
+08/30/2021 17:01:17 - INFO - __main__ - Step 21224: {'lr': 0.00047947447004109066, 'samples': 4075008, 'steps': 21223, 'loss/train': 1.7726914882659912}
+08/30/2021 17:01:18 - INFO - __main__ - Step 21225: {'lr': 0.0004794723641846914, 'samples': 4075200, 'steps': 21224, 'loss/train': 1.5440503358840942}
+08/30/2021 17:01:19 - INFO - __main__ - Step 21226: {'lr': 0.0004794702582248953, 'samples': 4075392, 'steps': 21225, 'loss/train': 1.757509708404541}
+08/30/2021 17:01:20 - INFO - __main__ - Step 21227: {'lr': 0.0004794681521617035, 'samples': 4075584, 'steps': 21226, 'loss/train': 1.6705842018127441}
+08/30/2021 17:01:20 - INFO - __main__ - Step 21228: {'lr': 0.0004794660459951169, 'samples': 4075776, 'steps': 21227, 'loss/train': 1.9040278196334839}
+08/30/2021 17:01:20 - INFO - __main__ - Step 21229: {'lr': 0.0004794639397251365, 'samples': 4075968, 'steps': 21228, 'loss/train': 2.0275213718414307}
+08/30/2021 17:01:21 - INFO - __main__ - Step 21230: {'lr': 0.00047946183335176307, 'samples': 4076160, 'steps': 21229, 'loss/train': 2.0773203372955322}
+08/30/2021 17:01:22 - INFO - __main__ - Step 21231: {'lr': 0.00047945972687499775, 'samples': 4076352, 'steps': 21230, 'loss/train': 1.6731206178665161}
+08/30/2021 17:01:23 - INFO - __main__ - Step 21232: {'lr': 0.0004794576202948414, 'samples': 4076544, 'steps': 21231, 'loss/train': 1.5735644102096558}
+08/30/2021 17:01:23 - INFO - __main__ - Step 21233: {'lr': 0.000479455513611295, 'samples': 4076736, 'steps': 21232, 'loss/train': 1.4337577819824219}
+08/30/2021 17:01:23 - INFO - __main__ - Step 21234: {'lr': 0.00047945340682435943, 'samples': 4076928, 'steps': 21233, 'loss/train': 1.6810390949249268}
+08/30/2021 17:01:24 - INFO - __main__ - Step 21235: {'lr': 0.00047945129993403577, 'samples': 4077120, 'steps': 21234, 'loss/train': 1.6172901391983032}
+08/30/2021 17:01:26 - INFO - __main__ - Step 21236: {'lr': 0.00047944919294032486, 'samples': 4077312, 'steps': 21235, 'loss/train': 1.9328231811523438}
+08/30/2021 17:01:27 - INFO - __main__ - Step 21237: {'lr': 0.00047944708584322763, 'samples': 4077504, 'steps': 21236, 'loss/train': 1.6461139917373657}
+08/30/2021 17:01:27 - INFO - __main__ - Step 21238: {'lr': 0.00047944497864274517, 'samples': 4077696, 'steps': 21237, 'loss/train': 1.55856192111969}
+08/30/2021 17:01:27 - INFO - __main__ - Step 21239: {'lr': 0.00047944287133887834, 'samples': 4077888, 'steps': 21238, 'loss/train': 2.0300607681274414}
+08/30/2021 17:01:28 - INFO - __main__ - Step 21240: {'lr': 0.00047944076393162806, 'samples': 4078080, 'steps': 21239, 'loss/train': 1.751529335975647}
+08/30/2021 17:01:28 - INFO - __main__ - Step 21241: {'lr': 0.00047943865642099525, 'samples': 4078272, 'steps': 21240, 'loss/train': 4.960762977600098}
+08/30/2021 17:01:30 - INFO - __main__ - Step 21242: {'lr': 0.00047943654880698106, 'samples': 4078464, 'steps': 21241, 'loss/train': 1.579373836517334}
+08/30/2021 17:01:30 - INFO - __main__ - Step 21243: {'lr': 0.00047943444108958623, 'samples': 4078656, 'steps': 21242, 'loss/train': 1.9401285648345947}
+08/30/2021 17:01:30 - INFO - __main__ - Step 21244: {'lr': 0.00047943233326881176, 'samples': 4078848, 'steps': 21243, 'loss/train': 1.4131957292556763}
+08/30/2021 17:01:31 - INFO - __main__ - Step 21245: {'lr': 0.00047943022534465866, 'samples': 4079040, 'steps': 21244, 'loss/train': 1.450485348701477}
+08/30/2021 17:01:31 - INFO - __main__ - Step 21246: {'lr': 0.00047942811731712775, 'samples': 4079232, 'steps': 21245, 'loss/train': 2.1429929733276367}
+08/30/2021 17:01:33 - INFO - __main__ - Step 21247: {'lr': 0.0004794260091862202, 'samples': 4079424, 'steps': 21246, 'loss/train': 1.7352527379989624}
+08/30/2021 17:01:34 - INFO - __main__ - Step 21248: {'lr': 0.0004794239009519368, 'samples': 4079616, 'steps': 21247, 'loss/train': 0.8411003351211548}
+08/30/2021 17:01:34 - INFO - __main__ - Step 21249: {'lr': 0.00047942179261427847, 'samples': 4079808, 'steps': 21248, 'loss/train': 1.6848970651626587}
+08/30/2021 17:01:34 - INFO - __main__ - Step 21250: {'lr': 0.0004794196841732463, 'samples': 4080000, 'steps': 21249, 'loss/train': 1.6532396078109741}
+08/30/2021 17:01:35 - INFO - __main__ - Step 21251: {'lr': 0.0004794175756288411, 'samples': 4080192, 'steps': 21250, 'loss/train': 1.8748997449874878}
+08/30/2021 17:01:35 - INFO - __main__ - Step 21252: {'lr': 0.00047941546698106386, 'samples': 4080384, 'steps': 21251, 'loss/train': 1.5357121229171753}
+08/30/2021 17:01:36 - INFO - __main__ - Step 21253: {'lr': 0.0004794133582299156, 'samples': 4080576, 'steps': 21252, 'loss/train': 1.219651699066162}
+08/30/2021 17:01:37 - INFO - __main__ - Step 21254: {'lr': 0.0004794112493753972, 'samples': 4080768, 'steps': 21253, 'loss/train': 0.07995536178350449}
+08/30/2021 17:01:37 - INFO - __main__ - Step 21255: {'lr': 0.0004794091404175097, 'samples': 4080960, 'steps': 21254, 'loss/train': 1.646977424621582}
+08/30/2021 17:01:38 - INFO - __main__ - Step 21256: {'lr': 0.00047940703135625386, 'samples': 4081152, 'steps': 21255, 'loss/train': 1.963430643081665}
+08/30/2021 17:01:38 - INFO - __main__ - Step 21257: {'lr': 0.0004794049221916308, 'samples': 4081344, 'steps': 21256, 'loss/train': 1.7822097539901733}
+08/30/2021 17:01:40 - INFO - __main__ - Step 21258: {'lr': 0.00047940281292364146, 'samples': 4081536, 'steps': 21257, 'loss/train': 1.6705876588821411}
+08/30/2021 17:01:40 - INFO - __main__ - Step 21259: {'lr': 0.0004794007035522867, 'samples': 4081728, 'steps': 21258, 'loss/train': 1.3476759195327759}
+08/30/2021 17:01:40 - INFO - __main__ - Step 21260: {'lr': 0.0004793985940775676, 'samples': 4081920, 'steps': 21259, 'loss/train': 1.230209469795227}
+08/30/2021 17:01:41 - INFO - __main__ - Step 21261: {'lr': 0.0004793964844994849, 'samples': 4082112, 'steps': 21260, 'loss/train': 1.8870868682861328}
+08/30/2021 17:01:41 - INFO - __main__ - Step 21262: {'lr': 0.00047939437481803984, 'samples': 4082304, 'steps': 21261, 'loss/train': 1.3441853523254395}
+08/30/2021 17:01:43 - INFO - __main__ - Step 21263: {'lr': 0.00047939226503323313, 'samples': 4082496, 'steps': 21262, 'loss/train': 1.5473906993865967}
+08/30/2021 17:01:43 - INFO - __main__ - Step 21264: {'lr': 0.0004793901551450658, 'samples': 4082688, 'steps': 21263, 'loss/train': 1.3980252742767334}
+08/30/2021 17:01:43 - INFO - __main__ - Step 21265: {'lr': 0.00047938804515353887, 'samples': 4082880, 'steps': 21264, 'loss/train': 1.3707047700881958}
+08/30/2021 17:01:44 - INFO - __main__ - Step 21266: {'lr': 0.00047938593505865315, 'samples': 4083072, 'steps': 21265, 'loss/train': 1.526796579360962}
+08/30/2021 17:01:44 - INFO - __main__ - Step 21267: {'lr': 0.00047938382486040963, 'samples': 4083264, 'steps': 21266, 'loss/train': 1.7023826837539673}
+08/30/2021 17:01:46 - INFO - __main__ - Step 21268: {'lr': 0.0004793817145588094, 'samples': 4083456, 'steps': 21267, 'loss/train': 1.8478944301605225}
+08/30/2021 17:01:46 - INFO - __main__ - Step 21269: {'lr': 0.0004793796041538533, 'samples': 4083648, 'steps': 21268, 'loss/train': 1.783738136291504}
+08/30/2021 17:01:46 - INFO - __main__ - Step 21270: {'lr': 0.00047937749364554226, 'samples': 4083840, 'steps': 21269, 'loss/train': 1.3065569400787354}
+08/30/2021 17:01:47 - INFO - __main__ - Step 21271: {'lr': 0.0004793753830338773, 'samples': 4084032, 'steps': 21270, 'loss/train': 1.9068880081176758}
+08/30/2021 17:01:47 - INFO - __main__ - Step 21272: {'lr': 0.00047937327231885925, 'samples': 4084224, 'steps': 21271, 'loss/train': 1.276872992515564}
+08/30/2021 17:01:49 - INFO - __main__ - Step 21273: {'lr': 0.0004793711615004892, 'samples': 4084416, 'steps': 21272, 'loss/train': 1.3377857208251953}
+08/30/2021 17:01:49 - INFO - __main__ - Step 21274: {'lr': 0.000479369050578768, 'samples': 4084608, 'steps': 21273, 'loss/train': 1.797074317932129}
+08/30/2021 17:01:50 - INFO - __main__ - Step 21275: {'lr': 0.0004793669395536967, 'samples': 4084800, 'steps': 21274, 'loss/train': 1.3432343006134033}
+08/30/2021 17:01:50 - INFO - __main__ - Step 21276: {'lr': 0.00047936482842527616, 'samples': 4084992, 'steps': 21275, 'loss/train': 0.7991041541099548}
+08/30/2021 17:01:50 - INFO - __main__ - Step 21277: {'lr': 0.00047936271719350743, 'samples': 4085184, 'steps': 21276, 'loss/train': 1.4765595197677612}
+08/30/2021 17:01:51 - INFO - __main__ - Step 21278: {'lr': 0.0004793606058583913, 'samples': 4085376, 'steps': 21277, 'loss/train': 1.7148023843765259}
+08/30/2021 17:01:52 - INFO - __main__ - Step 21279: {'lr': 0.00047935849441992887, 'samples': 4085568, 'steps': 21278, 'loss/train': 1.9708300828933716}
+08/30/2021 17:01:53 - INFO - __main__ - Step 21280: {'lr': 0.00047935638287812104, 'samples': 4085760, 'steps': 21279, 'loss/train': 1.4684146642684937}
+08/30/2021 17:01:53 - INFO - __main__ - Step 21281: {'lr': 0.00047935427123296884, 'samples': 4085952, 'steps': 21280, 'loss/train': 1.9510747194290161}
+08/30/2021 17:01:53 - INFO - __main__ - Step 21282: {'lr': 0.000479352159484473, 'samples': 4086144, 'steps': 21281, 'loss/train': 2.0200250148773193}
+08/30/2021 17:01:54 - INFO - __main__ - Step 21283: {'lr': 0.0004793500476326347, 'samples': 4086336, 'steps': 21282, 'loss/train': 1.6954630613327026}
+08/30/2021 17:01:56 - INFO - __main__ - Step 21284: {'lr': 0.0004793479356774548, 'samples': 4086528, 'steps': 21283, 'loss/train': 1.9972984790802002}
+08/30/2021 17:01:56 - INFO - __main__ - Step 21285: {'lr': 0.00047934582361893423, 'samples': 4086720, 'steps': 21284, 'loss/train': 0.32936790585517883}
+08/30/2021 17:01:56 - INFO - __main__ - Step 21286: {'lr': 0.000479343711457074, 'samples': 4086912, 'steps': 21285, 'loss/train': 1.0872018337249756}
+08/30/2021 17:01:57 - INFO - __main__ - Step 21287: {'lr': 0.00047934159919187504, 'samples': 4087104, 'steps': 21286, 'loss/train': 2.5703048706054688}
+08/30/2021 17:01:57 - INFO - __main__ - Step 21288: {'lr': 0.0004793394868233383, 'samples': 4087296, 'steps': 21287, 'loss/train': 2.1616835594177246}
+08/30/2021 17:01:59 - INFO - __main__ - Step 21289: {'lr': 0.0004793373743514647, 'samples': 4087488, 'steps': 21288, 'loss/train': 1.4142788648605347}
+08/30/2021 17:01:59 - INFO - __main__ - Step 21290: {'lr': 0.0004793352617762552, 'samples': 4087680, 'steps': 21289, 'loss/train': 1.209137201309204}
+08/30/2021 17:02:00 - INFO - __main__ - Step 21291: {'lr': 0.0004793331490977108, 'samples': 4087872, 'steps': 21290, 'loss/train': 1.85906982421875}
+08/30/2021 17:02:00 - INFO - __main__ - Step 21292: {'lr': 0.0004793310363158324, 'samples': 4088064, 'steps': 21291, 'loss/train': 1.5463615655899048}
+08/30/2021 17:02:00 - INFO - __main__ - Step 21293: {'lr': 0.00047932892343062103, 'samples': 4088256, 'steps': 21292, 'loss/train': 1.8606971502304077}
+08/30/2021 17:02:01 - INFO - __main__ - Step 21294: {'lr': 0.00047932681044207757, 'samples': 4088448, 'steps': 21293, 'loss/train': 1.606949806213379}
+08/30/2021 17:02:03 - INFO - __main__ - Step 21295: {'lr': 0.0004793246973502029, 'samples': 4088640, 'steps': 21294, 'loss/train': 1.5698412656784058}
+08/30/2021 17:02:03 - INFO - __main__ - Step 21296: {'lr': 0.0004793225841549982, 'samples': 4088832, 'steps': 21295, 'loss/train': 1.4163990020751953}
+08/30/2021 17:02:04 - INFO - __main__ - Step 21297: {'lr': 0.00047932047085646416, 'samples': 4089024, 'steps': 21296, 'loss/train': 1.8476744890213013}
+08/30/2021 17:02:04 - INFO - __main__ - Step 21298: {'lr': 0.0004793183574546019, 'samples': 4089216, 'steps': 21297, 'loss/train': 1.4494456052780151}
+08/30/2021 17:02:04 - INFO - __main__ - Step 21299: {'lr': 0.0004793162439494123, 'samples': 4089408, 'steps': 21298, 'loss/train': 2.0465006828308105}
+08/30/2021 17:02:06 - INFO - __main__ - Step 21300: {'lr': 0.00047931413034089644, 'samples': 4089600, 'steps': 21299, 'loss/train': 1.387484073638916}
+08/30/2021 17:02:06 - INFO - __main__ - Step 21301: {'lr': 0.00047931201662905503, 'samples': 4089792, 'steps': 21300, 'loss/train': 1.4023079872131348}
+08/30/2021 17:02:07 - INFO - __main__ - Step 21302: {'lr': 0.00047930990281388927, 'samples': 4089984, 'steps': 21301, 'loss/train': 0.8452826738357544}
+08/30/2021 17:02:07 - INFO - __main__ - Step 21303: {'lr': 0.00047930778889539996, 'samples': 4090176, 'steps': 21302, 'loss/train': 1.6854580640792847}
+08/30/2021 17:02:07 - INFO - __main__ - Step 21304: {'lr': 0.00047930567487358813, 'samples': 4090368, 'steps': 21303, 'loss/train': 1.1011916399002075}
+08/30/2021 17:02:09 - INFO - __main__ - Step 21305: {'lr': 0.00047930356074845466, 'samples': 4090560, 'steps': 21304, 'loss/train': 1.9323705434799194}
+08/30/2021 17:02:09 - INFO - __main__ - Step 21306: {'lr': 0.0004793014465200005, 'samples': 4090752, 'steps': 21305, 'loss/train': 2.0195205211639404}
+08/30/2021 17:02:10 - INFO - __main__ - Step 21307: {'lr': 0.0004792993321882267, 'samples': 4090944, 'steps': 21306, 'loss/train': 1.7164374589920044}
+08/30/2021 17:02:10 - INFO - __main__ - Step 21308: {'lr': 0.0004792972177531342, 'samples': 4091136, 'steps': 21307, 'loss/train': 1.4937433004379272}
+08/30/2021 17:02:10 - INFO - __main__ - Step 21309: {'lr': 0.0004792951032147239, 'samples': 4091328, 'steps': 21308, 'loss/train': 2.822166681289673}
+08/30/2021 17:02:12 - INFO - __main__ - Step 21310: {'lr': 0.00047929298857299677, 'samples': 4091520, 'steps': 21309, 'loss/train': 1.6812840700149536}
+08/30/2021 17:02:13 - INFO - __main__ - Step 21311: {'lr': 0.00047929087382795374, 'samples': 4091712, 'steps': 21310, 'loss/train': 1.897234559059143}
+08/30/2021 17:02:13 - INFO - __main__ - Step 21312: {'lr': 0.0004792887589795957, 'samples': 4091904, 'steps': 21311, 'loss/train': 1.7426352500915527}
+08/30/2021 17:02:13 - INFO - __main__ - Step 21313: {'lr': 0.00047928664402792376, 'samples': 4092096, 'steps': 21312, 'loss/train': 0.15013180673122406}
+08/30/2021 17:02:14 - INFO - __main__ - Step 21314: {'lr': 0.0004792845289729388, 'samples': 4092288, 'steps': 21313, 'loss/train': 1.1719199419021606}
+08/30/2021 17:02:14 - INFO - __main__ - Step 21315: {'lr': 0.00047928241381464177, 'samples': 4092480, 'steps': 21314, 'loss/train': 1.3982666730880737}
+08/30/2021 17:02:16 - INFO - __main__ - Step 21316: {'lr': 0.0004792802985530337, 'samples': 4092672, 'steps': 21315, 'loss/train': 1.6239895820617676}
+08/30/2021 17:02:16 - INFO - __main__ - Step 21317: {'lr': 0.0004792781831881153, 'samples': 4092864, 'steps': 21316, 'loss/train': 1.5348361730575562}
+08/30/2021 17:02:16 - INFO - __main__ - Step 21318: {'lr': 0.0004792760677198878, 'samples': 4093056, 'steps': 21317, 'loss/train': 1.8626474142074585}
+08/30/2021 17:02:17 - INFO - __main__ - Step 21319: {'lr': 0.00047927395214835203, 'samples': 4093248, 'steps': 21318, 'loss/train': 0.3177369236946106}
+08/30/2021 17:02:17 - INFO - __main__ - Step 21320: {'lr': 0.0004792718364735089, 'samples': 4093440, 'steps': 21319, 'loss/train': 1.8100190162658691}
+08/30/2021 17:02:19 - INFO - __main__ - Step 21321: {'lr': 0.00047926972069535945, 'samples': 4093632, 'steps': 21320, 'loss/train': 1.7661763429641724}
+08/30/2021 17:02:19 - INFO - __main__ - Step 21322: {'lr': 0.00047926760481390465, 'samples': 4093824, 'steps': 21321, 'loss/train': 1.6134295463562012}
+08/30/2021 17:02:19 - INFO - __main__ - Step 21323: {'lr': 0.00047926548882914533, 'samples': 4094016, 'steps': 21322, 'loss/train': 1.5928452014923096}
+08/30/2021 17:02:20 - INFO - __main__ - Step 21324: {'lr': 0.0004792633727410826, 'samples': 4094208, 'steps': 21323, 'loss/train': 2.4081175327301025}
+08/30/2021 17:02:20 - INFO - __main__ - Step 21325: {'lr': 0.0004792612565497172, 'samples': 4094400, 'steps': 21324, 'loss/train': 1.9535518884658813}
+08/30/2021 17:02:22 - INFO - __main__ - Step 21326: {'lr': 0.00047925914025505036, 'samples': 4094592, 'steps': 21325, 'loss/train': 1.9374675750732422}
+08/30/2021 17:02:22 - INFO - __main__ - Step 21327: {'lr': 0.0004792570238570828, 'samples': 4094784, 'steps': 21326, 'loss/train': 1.8380175828933716}
+08/30/2021 17:02:22 - INFO - __main__ - Step 21328: {'lr': 0.00047925490735581557, 'samples': 4094976, 'steps': 21327, 'loss/train': 1.7587676048278809}
+08/30/2021 17:02:23 - INFO - __main__ - Step 21329: {'lr': 0.00047925279075124963, 'samples': 4095168, 'steps': 21328, 'loss/train': 1.9400763511657715}
+08/30/2021 17:02:23 - INFO - __main__ - Step 21330: {'lr': 0.00047925067404338596, 'samples': 4095360, 'steps': 21329, 'loss/train': 1.9073177576065063}
+08/30/2021 17:02:25 - INFO - __main__ - Step 21331: {'lr': 0.00047924855723222536, 'samples': 4095552, 'steps': 21330, 'loss/train': 2.1923956871032715}
+08/30/2021 17:02:25 - INFO - __main__ - Step 21332: {'lr': 0.000479246440317769, 'samples': 4095744, 'steps': 21331, 'loss/train': 1.843536138534546}
+08/30/2021 17:02:26 - INFO - __main__ - Step 21333: {'lr': 0.00047924432330001776, 'samples': 4095936, 'steps': 21332, 'loss/train': 0.8867649435997009}
+08/30/2021 17:02:26 - INFO - __main__ - Step 21334: {'lr': 0.0004792422061789725, 'samples': 4096128, 'steps': 21333, 'loss/train': 1.6919630765914917}
+08/30/2021 17:02:26 - INFO - __main__ - Step 21335: {'lr': 0.0004792400889546342, 'samples': 4096320, 'steps': 21334, 'loss/train': 1.719007134437561}
+08/30/2021 17:02:27 - INFO - __main__ - Step 21336: {'lr': 0.00047923797162700393, 'samples': 4096512, 'steps': 21335, 'loss/train': 1.297482967376709}
+08/30/2021 17:02:28 - INFO - __main__ - Step 21337: {'lr': 0.0004792358541960826, 'samples': 4096704, 'steps': 21336, 'loss/train': 1.2600412368774414}
+08/30/2021 17:02:29 - INFO - __main__ - Step 21338: {'lr': 0.000479233736661871, 'samples': 4096896, 'steps': 21337, 'loss/train': 6.028919696807861}
+08/30/2021 17:02:29 - INFO - __main__ - Step 21339: {'lr': 0.0004792316190243703, 'samples': 4097088, 'steps': 21338, 'loss/train': 1.9485559463500977}
+08/30/2021 17:02:29 - INFO - __main__ - Step 21340: {'lr': 0.0004792295012835814, 'samples': 4097280, 'steps': 21339, 'loss/train': 1.1493204832077026}
+08/30/2021 17:02:30 - INFO - __main__ - Step 21341: {'lr': 0.0004792273834395052, 'samples': 4097472, 'steps': 21340, 'loss/train': 1.0050369501113892}
+08/30/2021 17:02:31 - INFO - __main__ - Step 21342: {'lr': 0.0004792252654921426, 'samples': 4097664, 'steps': 21341, 'loss/train': 0.5513942837715149}
+08/30/2021 17:02:32 - INFO - __main__ - Step 21343: {'lr': 0.00047922314744149475, 'samples': 4097856, 'steps': 21342, 'loss/train': 0.792652428150177}
+08/30/2021 17:02:32 - INFO - __main__ - Step 21344: {'lr': 0.0004792210292875624, 'samples': 4098048, 'steps': 21343, 'loss/train': 1.4035366773605347}
+08/30/2021 17:02:32 - INFO - __main__ - Step 21345: {'lr': 0.00047921891103034665, 'samples': 4098240, 'steps': 21344, 'loss/train': 1.606066346168518}
+08/30/2021 17:02:33 - INFO - __main__ - Step 21346: {'lr': 0.0004792167926698483, 'samples': 4098432, 'steps': 21345, 'loss/train': 1.0577651262283325}
+08/30/2021 17:02:33 - INFO - __main__ - Step 21347: {'lr': 0.0004792146742060685, 'samples': 4098624, 'steps': 21346, 'loss/train': 1.8724123239517212}
+08/30/2021 17:02:35 - INFO - __main__ - Step 21348: {'lr': 0.00047921255563900813, 'samples': 4098816, 'steps': 21347, 'loss/train': 0.8765449523925781}
+08/30/2021 17:02:36 - INFO - __main__ - Step 21349: {'lr': 0.000479210436968668, 'samples': 4099008, 'steps': 21348, 'loss/train': 2.4227795600891113}
+08/30/2021 17:02:36 - INFO - __main__ - Step 21350: {'lr': 0.0004792083181950493, 'samples': 4099200, 'steps': 21349, 'loss/train': 1.9457899332046509}
+08/30/2021 17:02:37 - INFO - __main__ - Step 21351: {'lr': 0.0004792061993181528, 'samples': 4099392, 'steps': 21350, 'loss/train': 1.9755337238311768}
+08/30/2021 17:02:37 - INFO - __main__ - Step 21352: {'lr': 0.00047920408033797954, 'samples': 4099584, 'steps': 21351, 'loss/train': 1.3816801309585571}
+08/30/2021 17:02:37 - INFO - __main__ - Step 21353: {'lr': 0.0004792019612545304, 'samples': 4099776, 'steps': 21352, 'loss/train': 1.5029605627059937}
+08/30/2021 17:02:39 - INFO - __main__ - Step 21354: {'lr': 0.00047919984206780647, 'samples': 4099968, 'steps': 21353, 'loss/train': 1.8080503940582275}
+08/30/2021 17:02:39 - INFO - __main__ - Step 21355: {'lr': 0.0004791977227778086, 'samples': 4100160, 'steps': 21354, 'loss/train': 1.749057650566101}
+08/30/2021 17:02:40 - INFO - __main__ - Step 21356: {'lr': 0.00047919560338453783, 'samples': 4100352, 'steps': 21355, 'loss/train': 1.466055989265442}
+08/30/2021 17:02:40 - INFO - __main__ - Step 21357: {'lr': 0.000479193483887995, 'samples': 4100544, 'steps': 21356, 'loss/train': 1.9566959142684937}
+08/30/2021 17:02:40 - INFO - __main__ - Step 21358: {'lr': 0.0004791913642881811, 'samples': 4100736, 'steps': 21357, 'loss/train': 1.5667201280593872}
+08/30/2021 17:02:42 - INFO - __main__ - Step 21359: {'lr': 0.00047918924458509717, 'samples': 4100928, 'steps': 21358, 'loss/train': 1.3140431642532349}
+08/30/2021 17:02:42 - INFO - __main__ - Step 21360: {'lr': 0.00047918712477874404, 'samples': 4101120, 'steps': 21359, 'loss/train': 1.1423887014389038}
+08/30/2021 17:02:43 - INFO - __main__ - Step 21361: {'lr': 0.00047918500486912276, 'samples': 4101312, 'steps': 21360, 'loss/train': 1.8200029134750366}
+08/30/2021 17:02:43 - INFO - __main__ - Step 21362: {'lr': 0.00047918288485623427, 'samples': 4101504, 'steps': 21361, 'loss/train': 1.862265706062317}
+08/30/2021 17:02:43 - INFO - __main__ - Step 21363: {'lr': 0.0004791807647400795, 'samples': 4101696, 'steps': 21362, 'loss/train': 1.2375341653823853}
+08/30/2021 17:02:44 - INFO - __main__ - Step 21364: {'lr': 0.0004791786445206594, 'samples': 4101888, 'steps': 21363, 'loss/train': 1.9139901399612427}
+08/30/2021 17:02:46 - INFO - __main__ - Step 21365: {'lr': 0.00047917652419797495, 'samples': 4102080, 'steps': 21364, 'loss/train': 1.5732009410858154}
+08/30/2021 17:02:46 - INFO - __main__ - Step 21366: {'lr': 0.0004791744037720271, 'samples': 4102272, 'steps': 21365, 'loss/train': 1.735299825668335}
+08/30/2021 17:02:47 - INFO - __main__ - Step 21367: {'lr': 0.00047917228324281683, 'samples': 4102464, 'steps': 21366, 'loss/train': 0.15128643810749054}
+08/30/2021 17:02:47 - INFO - __main__ - Step 21368: {'lr': 0.00047917016261034496, 'samples': 4102656, 'steps': 21367, 'loss/train': 2.277677297592163}
+08/30/2021 17:02:47 - INFO - __main__ - Step 21369: {'lr': 0.0004791680418746126, 'samples': 4102848, 'steps': 21368, 'loss/train': 1.6648612022399902}
+08/30/2021 17:02:49 - INFO - __main__ - Step 21370: {'lr': 0.00047916592103562075, 'samples': 4103040, 'steps': 21369, 'loss/train': 1.4361931085586548}
+08/30/2021 17:02:49 - INFO - __main__ - Step 21371: {'lr': 0.00047916380009337014, 'samples': 4103232, 'steps': 21370, 'loss/train': 1.1085540056228638}
+08/30/2021 17:02:50 - INFO - __main__ - Step 21372: {'lr': 0.0004791616790478619, 'samples': 4103424, 'steps': 21371, 'loss/train': 1.6016608476638794}
+08/30/2021 17:02:50 - INFO - __main__ - Step 21373: {'lr': 0.000479159557899097, 'samples': 4103616, 'steps': 21372, 'loss/train': 1.678863525390625}
+08/30/2021 17:02:50 - INFO - __main__ - Step 21374: {'lr': 0.00047915743664707626, 'samples': 4103808, 'steps': 21373, 'loss/train': 1.0617471933364868}
+08/30/2021 17:02:52 - INFO - __main__ - Step 21375: {'lr': 0.0004791553152918008, 'samples': 4104000, 'steps': 21374, 'loss/train': 1.9959217309951782}
+08/30/2021 17:02:52 - INFO - __main__ - Step 21376: {'lr': 0.0004791531938332714, 'samples': 4104192, 'steps': 21375, 'loss/train': 1.020253300666809}
+08/30/2021 17:02:53 - INFO - __main__ - Step 21377: {'lr': 0.0004791510722714891, 'samples': 4104384, 'steps': 21376, 'loss/train': 1.9851142168045044}
+08/30/2021 17:02:53 - INFO - __main__ - Step 21378: {'lr': 0.000479148950606455, 'samples': 4104576, 'steps': 21377, 'loss/train': 1.816135287284851}
+08/30/2021 17:02:53 - INFO - __main__ - Step 21379: {'lr': 0.00047914682883816977, 'samples': 4104768, 'steps': 21378, 'loss/train': 1.3393754959106445}
+08/30/2021 17:02:54 - INFO - __main__ - Step 21380: {'lr': 0.00047914470696663457, 'samples': 4104960, 'steps': 21379, 'loss/train': 1.6631602048873901}
+08/30/2021 17:02:55 - INFO - __main__ - Step 21381: {'lr': 0.00047914258499185037, 'samples': 4105152, 'steps': 21380, 'loss/train': 2.0020618438720703}
+08/30/2021 17:02:56 - INFO - __main__ - Step 21382: {'lr': 0.000479140462913818, 'samples': 4105344, 'steps': 21381, 'loss/train': 1.894571304321289}
+08/30/2021 17:02:56 - INFO - __main__ - Step 21383: {'lr': 0.0004791383407325384, 'samples': 4105536, 'steps': 21382, 'loss/train': 1.5259020328521729}
+08/30/2021 17:02:56 - INFO - __main__ - Step 21384: {'lr': 0.0004791362184480127, 'samples': 4105728, 'steps': 21383, 'loss/train': 1.774632215499878}
+08/30/2021 17:02:57 - INFO - __main__ - Step 21385: {'lr': 0.0004791340960602417, 'samples': 4105920, 'steps': 21384, 'loss/train': 1.8958078622817993}
+08/30/2021 17:02:58 - INFO - __main__ - Step 21386: {'lr': 0.0004791319735692264, 'samples': 4106112, 'steps': 21385, 'loss/train': 1.8974725008010864}
+08/30/2021 17:02:59 - INFO - __main__ - Step 21387: {'lr': 0.00047912985097496786, 'samples': 4106304, 'steps': 21386, 'loss/train': 1.1539653539657593}
+08/30/2021 17:02:59 - INFO - __main__ - Step 21388: {'lr': 0.00047912772827746685, 'samples': 4106496, 'steps': 21387, 'loss/train': 1.3914194107055664}
+08/30/2021 17:02:59 - INFO - __main__ - Step 21389: {'lr': 0.00047912560547672453, 'samples': 4106688, 'steps': 21388, 'loss/train': 0.16680869460105896}
+08/30/2021 17:03:00 - INFO - __main__ - Step 21390: {'lr': 0.0004791234825727416, 'samples': 4106880, 'steps': 21389, 'loss/train': 1.2506459951400757}
+08/30/2021 17:03:02 - INFO - __main__ - Step 21391: {'lr': 0.0004791213595655193, 'samples': 4107072, 'steps': 21390, 'loss/train': 1.9134588241577148}
+08/30/2021 17:03:02 - INFO - __main__ - Step 21392: {'lr': 0.0004791192364550584, 'samples': 4107264, 'steps': 21391, 'loss/train': 1.4890049695968628}
+08/30/2021 17:03:03 - INFO - __main__ - Step 21393: {'lr': 0.00047911711324135985, 'samples': 4107456, 'steps': 21392, 'loss/train': 1.4686373472213745}
+08/30/2021 17:03:03 - INFO - __main__ - Step 21394: {'lr': 0.00047911498992442476, 'samples': 4107648, 'steps': 21393, 'loss/train': 1.9358030557632446}
+08/30/2021 17:03:03 - INFO - __main__ - Step 21395: {'lr': 0.0004791128665042539, 'samples': 4107840, 'steps': 21394, 'loss/train': 1.6533355712890625}
+08/30/2021 17:03:04 - INFO - __main__ - Step 21396: {'lr': 0.0004791107429808484, 'samples': 4108032, 'steps': 21395, 'loss/train': 1.1145198345184326}
+08/30/2021 17:03:05 - INFO - __main__ - Step 21397: {'lr': 0.00047910861935420915, 'samples': 4108224, 'steps': 21396, 'loss/train': 3.0373291969299316}
+08/30/2021 17:03:06 - INFO - __main__ - Step 21398: {'lr': 0.00047910649562433696, 'samples': 4108416, 'steps': 21397, 'loss/train': 1.8464752435684204}
+08/30/2021 17:03:06 - INFO - __main__ - Step 21399: {'lr': 0.000479104371791233, 'samples': 4108608, 'steps': 21398, 'loss/train': 1.7620136737823486}
+08/30/2021 17:03:06 - INFO - __main__ - Step 21400: {'lr': 0.0004791022478548982, 'samples': 4108800, 'steps': 21399, 'loss/train': 1.8300144672393799}
+08/30/2021 17:03:07 - INFO - __main__ - Step 21401: {'lr': 0.0004791001238153334, 'samples': 4108992, 'steps': 21400, 'loss/train': 1.0013267993927002}
+08/30/2021 17:03:09 - INFO - __main__ - Step 21402: {'lr': 0.00047909799967253957, 'samples': 4109184, 'steps': 21401, 'loss/train': 1.5706853866577148}
+08/30/2021 17:03:09 - INFO - __main__ - Step 21403: {'lr': 0.00047909587542651776, 'samples': 4109376, 'steps': 21402, 'loss/train': 1.5404706001281738}
+08/30/2021 17:03:10 - INFO - __main__ - Step 21404: {'lr': 0.00047909375107726894, 'samples': 4109568, 'steps': 21403, 'loss/train': 1.8566616773605347}
+08/30/2021 17:03:10 - INFO - __main__ - Step 21405: {'lr': 0.000479091626624794, 'samples': 4109760, 'steps': 21404, 'loss/train': 5.978694915771484}
+08/30/2021 17:03:10 - INFO - __main__ - Step 21406: {'lr': 0.00047908950206909385, 'samples': 4109952, 'steps': 21405, 'loss/train': 1.2774567604064941}
+08/30/2021 17:03:11 - INFO - __main__ - Step 21407: {'lr': 0.0004790873774101695, 'samples': 4110144, 'steps': 21406, 'loss/train': 1.7675304412841797}
+08/30/2021 17:03:12 - INFO - __main__ - Step 21408: {'lr': 0.00047908525264802194, 'samples': 4110336, 'steps': 21407, 'loss/train': 1.8614758253097534}
+08/30/2021 17:03:13 - INFO - __main__ - Step 21409: {'lr': 0.00047908312778265213, 'samples': 4110528, 'steps': 21408, 'loss/train': 2.530635356903076}
+08/30/2021 17:03:13 - INFO - __main__ - Step 21410: {'lr': 0.00047908100281406096, 'samples': 4110720, 'steps': 21409, 'loss/train': 0.6041358113288879}
+08/30/2021 17:03:14 - INFO - __main__ - Step 21411: {'lr': 0.00047907887774224946, 'samples': 4110912, 'steps': 21410, 'loss/train': 1.3304941654205322}
+08/30/2021 17:03:14 - INFO - __main__ - Step 21412: {'lr': 0.0004790767525672185, 'samples': 4111104, 'steps': 21411, 'loss/train': 1.4318076372146606}
+08/30/2021 17:03:15 - INFO - __main__ - Step 21413: {'lr': 0.0004790746272889691, 'samples': 4111296, 'steps': 21412, 'loss/train': 1.6282638311386108}
+08/30/2021 17:03:16 - INFO - __main__ - Step 21414: {'lr': 0.00047907250190750225, 'samples': 4111488, 'steps': 21413, 'loss/train': 1.9806156158447266}
+08/30/2021 17:03:16 - INFO - __main__ - Step 21415: {'lr': 0.0004790703764228188, 'samples': 4111680, 'steps': 21414, 'loss/train': 1.3572484254837036}
+08/30/2021 17:03:17 - INFO - __main__ - Step 21416: {'lr': 0.0004790682508349198, 'samples': 4111872, 'steps': 21415, 'loss/train': 1.2222541570663452}
+08/30/2021 17:03:17 - INFO - __main__ - Step 21417: {'lr': 0.00047906612514380623, 'samples': 4112064, 'steps': 21416, 'loss/train': 1.5520838499069214}
+08/30/2021 17:03:19 - INFO - __main__ - Step 21418: {'lr': 0.000479063999349479, 'samples': 4112256, 'steps': 21417, 'loss/train': 1.7586411237716675}
+08/30/2021 17:03:20 - INFO - __main__ - Step 21419: {'lr': 0.00047906187345193895, 'samples': 4112448, 'steps': 21418, 'loss/train': 1.270230770111084}
+08/30/2021 17:03:20 - INFO - __main__ - Step 21420: {'lr': 0.0004790597474511873, 'samples': 4112640, 'steps': 21419, 'loss/train': 1.4617196321487427}
+08/30/2021 17:03:20 - INFO - __main__ - Step 21421: {'lr': 0.0004790576213472248, 'samples': 4112832, 'steps': 21420, 'loss/train': 1.1790966987609863}
+08/30/2021 17:03:21 - INFO - __main__ - Step 21422: {'lr': 0.0004790554951400524, 'samples': 4113024, 'steps': 21421, 'loss/train': 1.1328461170196533}
+08/30/2021 17:03:21 - INFO - __main__ - Step 21423: {'lr': 0.0004790533688296712, 'samples': 4113216, 'steps': 21422, 'loss/train': 1.5887815952301025}
+08/30/2021 17:03:22 - INFO - __main__ - Step 21424: {'lr': 0.0004790512424160821, 'samples': 4113408, 'steps': 21423, 'loss/train': 1.9631133079528809}
+08/30/2021 17:03:23 - INFO - __main__ - Step 21425: {'lr': 0.00047904911589928605, 'samples': 4113600, 'steps': 21424, 'loss/train': 1.9130054712295532}
+08/30/2021 17:03:23 - INFO - __main__ - Step 21426: {'lr': 0.00047904698927928404, 'samples': 4113792, 'steps': 21425, 'loss/train': 1.599796175956726}
+08/30/2021 17:03:23 - INFO - __main__ - Step 21427: {'lr': 0.0004790448625560769, 'samples': 4113984, 'steps': 21426, 'loss/train': 1.6329631805419922}
+08/30/2021 17:03:24 - INFO - __main__ - Step 21428: {'lr': 0.0004790427357296657, 'samples': 4114176, 'steps': 21427, 'loss/train': 1.3552738428115845}
+08/30/2021 17:03:26 - INFO - __main__ - Step 21429: {'lr': 0.0004790406088000514, 'samples': 4114368, 'steps': 21428, 'loss/train': 1.5520470142364502}
+08/30/2021 17:03:26 - INFO - __main__ - Step 21430: {'lr': 0.00047903848176723493, 'samples': 4114560, 'steps': 21429, 'loss/train': 1.6015326976776123}
+08/30/2021 17:03:27 - INFO - __main__ - Step 21431: {'lr': 0.0004790363546312172, 'samples': 4114752, 'steps': 21430, 'loss/train': 1.2645312547683716}
+08/30/2021 17:03:27 - INFO - __main__ - Step 21432: {'lr': 0.0004790342273919993, 'samples': 4114944, 'steps': 21431, 'loss/train': 1.4015811681747437}
+08/30/2021 17:03:27 - INFO - __main__ - Step 21433: {'lr': 0.00047903210004958207, 'samples': 4115136, 'steps': 21432, 'loss/train': 2.077160120010376}
+08/30/2021 17:03:28 - INFO - __main__ - Step 21434: {'lr': 0.0004790299726039665, 'samples': 4115328, 'steps': 21433, 'loss/train': 1.6486338376998901}
+08/30/2021 17:03:29 - INFO - __main__ - Step 21435: {'lr': 0.0004790278450551536, 'samples': 4115520, 'steps': 21434, 'loss/train': 0.08832631260156631}
+08/30/2021 17:03:30 - INFO - __main__ - Step 21436: {'lr': 0.00047902571740314427, 'samples': 4115712, 'steps': 21435, 'loss/train': 2.3777639865875244}
+08/30/2021 17:03:30 - INFO - __main__ - Step 21437: {'lr': 0.00047902358964793944, 'samples': 4115904, 'steps': 21436, 'loss/train': 1.1027485132217407}
+08/30/2021 17:03:30 - INFO - __main__ - Step 21438: {'lr': 0.0004790214617895402, 'samples': 4116096, 'steps': 21437, 'loss/train': 2.061546564102173}
+08/30/2021 17:03:31 - INFO - __main__ - Step 21439: {'lr': 0.0004790193338279474, 'samples': 4116288, 'steps': 21438, 'loss/train': 1.7133933305740356}
+08/30/2021 17:03:32 - INFO - __main__ - Step 21440: {'lr': 0.000479017205763162, 'samples': 4116480, 'steps': 21439, 'loss/train': 1.7539247274398804}
+08/30/2021 17:03:33 - INFO - __main__ - Step 21441: {'lr': 0.000479015077595185, 'samples': 4116672, 'steps': 21440, 'loss/train': 1.705939769744873}
+08/30/2021 17:03:33 - INFO - __main__ - Step 21442: {'lr': 0.0004790129493240173, 'samples': 4116864, 'steps': 21441, 'loss/train': 1.0331511497497559}
+08/30/2021 17:03:33 - INFO - __main__ - Step 21443: {'lr': 0.0004790108209496599, 'samples': 4117056, 'steps': 21442, 'loss/train': 4.733749866485596}
+08/30/2021 17:03:34 - INFO - __main__ - Step 21444: {'lr': 0.00047900869247211384, 'samples': 4117248, 'steps': 21443, 'loss/train': 1.3099116086959839}
+08/30/2021 17:03:36 - INFO - __main__ - Step 21445: {'lr': 0.0004790065638913799, 'samples': 4117440, 'steps': 21444, 'loss/train': 0.6812911033630371}
+08/30/2021 17:03:36 - INFO - __main__ - Step 21446: {'lr': 0.00047900443520745915, 'samples': 4117632, 'steps': 21445, 'loss/train': 1.9747036695480347}
+08/30/2021 17:03:36 - INFO - __main__ - Step 21447: {'lr': 0.0004790023064203526, 'samples': 4117824, 'steps': 21446, 'loss/train': 1.5440456867218018}
+08/30/2021 17:03:37 - INFO - __main__ - Step 21448: {'lr': 0.00047900017753006106, 'samples': 4118016, 'steps': 21447, 'loss/train': 1.5677807331085205}
+08/30/2021 17:03:37 - INFO - __main__ - Step 21449: {'lr': 0.0004789980485365857, 'samples': 4118208, 'steps': 21448, 'loss/train': 1.4878294467926025}
+08/30/2021 17:03:38 - INFO - __main__ - Step 21450: {'lr': 0.00047899591943992726, 'samples': 4118400, 'steps': 21449, 'loss/train': 1.6379958391189575}
+08/30/2021 17:03:39 - INFO - __main__ - Step 21451: {'lr': 0.0004789937902400868, 'samples': 4118592, 'steps': 21450, 'loss/train': 0.2603890299797058}
+08/30/2021 17:03:39 - INFO - __main__ - Step 21452: {'lr': 0.00047899166093706523, 'samples': 4118784, 'steps': 21451, 'loss/train': 1.7019600868225098}
+08/30/2021 17:03:40 - INFO - __main__ - Step 21453: {'lr': 0.0004789895315308636, 'samples': 4118976, 'steps': 21452, 'loss/train': 1.7137532234191895}
+08/30/2021 17:03:40 - INFO - __main__ - Step 21454: {'lr': 0.00047898740202148284, 'samples': 4119168, 'steps': 21453, 'loss/train': 1.0620163679122925}
+08/30/2021 17:03:41 - INFO - __main__ - Step 21455: {'lr': 0.0004789852724089239, 'samples': 4119360, 'steps': 21454, 'loss/train': 1.5766828060150146}
+08/30/2021 17:03:42 - INFO - __main__ - Step 21456: {'lr': 0.00047898314269318766, 'samples': 4119552, 'steps': 21455, 'loss/train': 1.6099308729171753}
+08/30/2021 17:03:43 - INFO - __main__ - Step 21457: {'lr': 0.00047898101287427523, 'samples': 4119744, 'steps': 21456, 'loss/train': 1.6593270301818848}
+08/30/2021 17:03:43 - INFO - __main__ - Step 21458: {'lr': 0.0004789788829521874, 'samples': 4119936, 'steps': 21457, 'loss/train': 1.2930656671524048}
+08/30/2021 17:03:44 - INFO - __main__ - Step 21459: {'lr': 0.0004789767529269253, 'samples': 4120128, 'steps': 21458, 'loss/train': 1.334293246269226}
+08/30/2021 17:03:44 - INFO - __main__ - Step 21460: {'lr': 0.0004789746227984897, 'samples': 4120320, 'steps': 21459, 'loss/train': 1.5533400774002075}
+08/30/2021 17:03:46 - INFO - __main__ - Step 21461: {'lr': 0.0004789724925668818, 'samples': 4120512, 'steps': 21460, 'loss/train': 1.022534728050232}
+08/30/2021 17:03:46 - INFO - __main__ - Step 21462: {'lr': 0.00047897036223210234, 'samples': 4120704, 'steps': 21461, 'loss/train': 1.3876748085021973}
+08/30/2021 17:03:46 - INFO - __main__ - Step 21463: {'lr': 0.00047896823179415237, 'samples': 4120896, 'steps': 21462, 'loss/train': 1.795861005783081}
+08/30/2021 17:03:47 - INFO - __main__ - Step 21464: {'lr': 0.0004789661012530329, 'samples': 4121088, 'steps': 21463, 'loss/train': 1.9045308828353882}
+08/30/2021 17:03:47 - INFO - __main__ - Step 21465: {'lr': 0.00047896397060874485, 'samples': 4121280, 'steps': 21464, 'loss/train': 1.2129464149475098}
+08/30/2021 17:03:47 - INFO - __main__ - Step 21466: {'lr': 0.0004789618398612891, 'samples': 4121472, 'steps': 21465, 'loss/train': 1.1078848838806152}
+08/30/2021 17:03:49 - INFO - __main__ - Step 21467: {'lr': 0.0004789597090106667, 'samples': 4121664, 'steps': 21466, 'loss/train': 1.749743103981018}
+08/30/2021 17:03:50 - INFO - __main__ - Step 21468: {'lr': 0.00047895757805687864, 'samples': 4121856, 'steps': 21467, 'loss/train': 2.036487102508545}
+08/30/2021 17:03:50 - INFO - __main__ - Step 21469: {'lr': 0.0004789554469999258, 'samples': 4122048, 'steps': 21468, 'loss/train': 1.7220492362976074}
+08/30/2021 17:03:50 - INFO - __main__ - Step 21470: {'lr': 0.0004789533158398091, 'samples': 4122240, 'steps': 21469, 'loss/train': 1.6133811473846436}
+08/30/2021 17:03:51 - INFO - __main__ - Step 21471: {'lr': 0.00047895118457652965, 'samples': 4122432, 'steps': 21470, 'loss/train': 1.4600428342819214}
+08/30/2021 17:03:51 - INFO - __main__ - Step 21472: {'lr': 0.0004789490532100883, 'samples': 4122624, 'steps': 21471, 'loss/train': 0.05137605592608452}
+08/30/2021 17:03:53 - INFO - __main__ - Step 21473: {'lr': 0.000478946921740486, 'samples': 4122816, 'steps': 21472, 'loss/train': 1.4794323444366455}
+08/30/2021 17:03:53 - INFO - __main__ - Step 21474: {'lr': 0.0004789447901677238, 'samples': 4123008, 'steps': 21473, 'loss/train': 1.8282737731933594}
+08/30/2021 17:03:53 - INFO - __main__ - Step 21475: {'lr': 0.00047894265849180264, 'samples': 4123200, 'steps': 21474, 'loss/train': 0.7590158581733704}
+08/30/2021 17:03:54 - INFO - __main__ - Step 21476: {'lr': 0.00047894052671272337, 'samples': 4123392, 'steps': 21475, 'loss/train': 1.4974853992462158}
+08/30/2021 17:03:54 - INFO - __main__ - Step 21477: {'lr': 0.0004789383948304871, 'samples': 4123584, 'steps': 21476, 'loss/train': 1.531650185585022}
+08/30/2021 17:03:56 - INFO - __main__ - Step 21478: {'lr': 0.00047893626284509466, 'samples': 4123776, 'steps': 21477, 'loss/train': 1.5932615995407104}
+08/30/2021 17:03:56 - INFO - __main__ - Step 21479: {'lr': 0.0004789341307565471, 'samples': 4123968, 'steps': 21478, 'loss/train': 1.7813539505004883}
+08/30/2021 17:03:56 - INFO - __main__ - Step 21480: {'lr': 0.0004789319985648454, 'samples': 4124160, 'steps': 21479, 'loss/train': 1.3085589408874512}
+08/30/2021 17:03:57 - INFO - __main__ - Step 21481: {'lr': 0.0004789298662699905, 'samples': 4124352, 'steps': 21480, 'loss/train': 1.8414041996002197}
+08/30/2021 17:03:57 - INFO - __main__ - Step 21482: {'lr': 0.0004789277338719832, 'samples': 4124544, 'steps': 21481, 'loss/train': 0.3708147406578064}
+08/30/2021 17:03:59 - INFO - __main__ - Step 21483: {'lr': 0.0004789256013708246, 'samples': 4124736, 'steps': 21482, 'loss/train': 1.0991530418395996}
+08/30/2021 17:03:59 - INFO - __main__ - Step 21484: {'lr': 0.0004789234687665158, 'samples': 4124928, 'steps': 21483, 'loss/train': 1.7097718715667725}
+08/30/2021 17:04:00 - INFO - __main__ - Step 21485: {'lr': 0.0004789213360590575, 'samples': 4125120, 'steps': 21484, 'loss/train': 1.0717169046401978}
+08/30/2021 17:04:00 - INFO - __main__ - Step 21486: {'lr': 0.00047891920324845085, 'samples': 4125312, 'steps': 21485, 'loss/train': 1.573041558265686}
+08/30/2021 17:04:00 - INFO - __main__ - Step 21487: {'lr': 0.00047891707033469665, 'samples': 4125504, 'steps': 21486, 'loss/train': 1.5038706064224243}
+08/30/2021 17:04:01 - INFO - __main__ - Step 21488: {'lr': 0.00047891493731779607, 'samples': 4125696, 'steps': 21487, 'loss/train': 2.181943893432617}
+08/30/2021 17:04:02 - INFO - __main__ - Step 21489: {'lr': 0.00047891280419774985, 'samples': 4125888, 'steps': 21488, 'loss/train': 1.6918127536773682}
+08/30/2021 17:04:03 - INFO - __main__ - Step 21490: {'lr': 0.0004789106709745591, 'samples': 4126080, 'steps': 21489, 'loss/train': 1.6460556983947754}
+08/30/2021 17:04:03 - INFO - __main__ - Step 21491: {'lr': 0.0004789085376482247, 'samples': 4126272, 'steps': 21490, 'loss/train': 1.7745941877365112}
+08/30/2021 17:04:03 - INFO - __main__ - Step 21492: {'lr': 0.00047890640421874775, 'samples': 4126464, 'steps': 21491, 'loss/train': 1.7836967706680298}
+08/30/2021 17:04:05 - INFO - __main__ - Step 21493: {'lr': 0.000478904270686129, 'samples': 4126656, 'steps': 21492, 'loss/train': 2.0360591411590576}
+08/30/2021 17:04:06 - INFO - __main__ - Step 21494: {'lr': 0.00047890213705036955, 'samples': 4126848, 'steps': 21493, 'loss/train': 1.0421425104141235}
+08/30/2021 17:04:06 - INFO - __main__ - Step 21495: {'lr': 0.00047890000331147033, 'samples': 4127040, 'steps': 21494, 'loss/train': 1.2720959186553955}
+08/30/2021 17:04:07 - INFO - __main__ - Step 21496: {'lr': 0.0004788978694694323, 'samples': 4127232, 'steps': 21495, 'loss/train': 1.3424983024597168}
+08/30/2021 17:04:07 - INFO - __main__ - Step 21497: {'lr': 0.0004788957355242564, 'samples': 4127424, 'steps': 21496, 'loss/train': 1.0823028087615967}
+08/30/2021 17:04:07 - INFO - __main__ - Step 21498: {'lr': 0.00047889360147594363, 'samples': 4127616, 'steps': 21497, 'loss/train': 2.1946630477905273}
+08/30/2021 17:04:09 - INFO - __main__ - Step 21499: {'lr': 0.00047889146732449497, 'samples': 4127808, 'steps': 21498, 'loss/train': 1.4539885520935059}
+08/30/2021 17:04:09 - INFO - __main__ - Step 21500: {'lr': 0.00047888933306991136, 'samples': 4128000, 'steps': 21499, 'loss/train': 1.671066403388977}
+08/30/2021 17:04:10 - INFO - __main__ - Step 21501: {'lr': 0.00047888719871219367, 'samples': 4128192, 'steps': 21500, 'loss/train': 2.1623952388763428}
+08/30/2021 17:04:10 - INFO - __main__ - Step 21502: {'lr': 0.00047888506425134293, 'samples': 4128384, 'steps': 21501, 'loss/train': 1.7121566534042358}
+08/30/2021 17:04:10 - INFO - __main__ - Step 21503: {'lr': 0.0004788829296873601, 'samples': 4128576, 'steps': 21502, 'loss/train': 0.30309751629829407}
+08/30/2021 17:04:12 - INFO - __main__ - Step 21504: {'lr': 0.0004788807950202463, 'samples': 4128768, 'steps': 21503, 'loss/train': 1.3717628717422485}
+08/30/2021 17:04:13 - INFO - __main__ - Step 21505: {'lr': 0.00047887866025000226, 'samples': 4128960, 'steps': 21504, 'loss/train': 1.7132471799850464}
+08/30/2021 17:04:13 - INFO - __main__ - Step 21506: {'lr': 0.000478876525376629, 'samples': 4129152, 'steps': 21505, 'loss/train': 1.2056117057800293}
+08/30/2021 17:04:13 - INFO - __main__ - Step 21507: {'lr': 0.00047887439040012755, 'samples': 4129344, 'steps': 21506, 'loss/train': 1.7914046049118042}
+08/30/2021 17:04:14 - INFO - __main__ - Step 21508: {'lr': 0.0004788722553204988, 'samples': 4129536, 'steps': 21507, 'loss/train': 1.4132291078567505}
+08/30/2021 17:04:14 - INFO - __main__ - Step 21509: {'lr': 0.0004788701201377438, 'samples': 4129728, 'steps': 21508, 'loss/train': 1.8986529111862183}
+08/30/2021 17:04:15 - INFO - __main__ - Step 21510: {'lr': 0.0004788679848518633, 'samples': 4129920, 'steps': 21509, 'loss/train': 1.638746976852417}
+08/30/2021 17:04:16 - INFO - __main__ - Step 21511: {'lr': 0.0004788658494628586, 'samples': 4130112, 'steps': 21510, 'loss/train': 1.896509051322937}
+08/30/2021 17:04:16 - INFO - __main__ - Step 21512: {'lr': 0.0004788637139707304, 'samples': 4130304, 'steps': 21511, 'loss/train': 1.7294583320617676}
+08/30/2021 17:04:16 - INFO - __main__ - Step 21513: {'lr': 0.00047886157837547975, 'samples': 4130496, 'steps': 21512, 'loss/train': 1.6490304470062256}
+08/30/2021 17:04:17 - INFO - __main__ - Step 21514: {'lr': 0.0004788594426771076, 'samples': 4130688, 'steps': 21513, 'loss/train': 1.3523578643798828}
+08/30/2021 17:04:20 - INFO - __main__ - Step 21515: {'lr': 0.0004788573068756149, 'samples': 4130880, 'steps': 21514, 'loss/train': 1.8092198371887207}
+08/30/2021 17:04:20 - INFO - __main__ - Step 21516: {'lr': 0.0004788551709710027, 'samples': 4131072, 'steps': 21515, 'loss/train': 0.7204294204711914}
+08/30/2021 17:04:21 - INFO - __main__ - Step 21517: {'lr': 0.0004788530349632718, 'samples': 4131264, 'steps': 21516, 'loss/train': 0.5451465845108032}
+08/30/2021 17:04:21 - INFO - __main__ - Step 21518: {'lr': 0.00047885089885242333, 'samples': 4131456, 'steps': 21517, 'loss/train': 1.6412653923034668}
+08/30/2021 17:04:21 - INFO - __main__ - Step 21519: {'lr': 0.0004788487626384581, 'samples': 4131648, 'steps': 21518, 'loss/train': 1.5881367921829224}
+08/30/2021 17:04:22 - INFO - __main__ - Step 21520: {'lr': 0.0004788466263213772, 'samples': 4131840, 'steps': 21519, 'loss/train': 1.8423503637313843}
+08/30/2021 17:04:23 - INFO - __main__ - Step 21521: {'lr': 0.00047884448990118155, 'samples': 4132032, 'steps': 21520, 'loss/train': 1.8779414892196655}
+08/30/2021 17:04:24 - INFO - __main__ - Step 21522: {'lr': 0.0004788423533778721, 'samples': 4132224, 'steps': 21521, 'loss/train': 1.0586224794387817}
+08/30/2021 17:04:24 - INFO - __main__ - Step 21523: {'lr': 0.00047884021675144987, 'samples': 4132416, 'steps': 21522, 'loss/train': 1.344202995300293}
+08/30/2021 17:04:24 - INFO - __main__ - Step 21524: {'lr': 0.0004788380800219156, 'samples': 4132608, 'steps': 21523, 'loss/train': 1.41176176071167}
+08/30/2021 17:04:25 - INFO - __main__ - Step 21525: {'lr': 0.0004788359431892706, 'samples': 4132800, 'steps': 21524, 'loss/train': 1.1432011127471924}
+08/30/2021 17:04:26 - INFO - __main__ - Step 21526: {'lr': 0.00047883380625351557, 'samples': 4132992, 'steps': 21525, 'loss/train': 1.7957347631454468}
+08/30/2021 17:04:27 - INFO - __main__ - Step 21527: {'lr': 0.00047883166921465156, 'samples': 4133184, 'steps': 21526, 'loss/train': 1.4472945928573608}
+08/30/2021 17:04:27 - INFO - __main__ - Step 21528: {'lr': 0.00047882953207267954, 'samples': 4133376, 'steps': 21527, 'loss/train': 1.212437391281128}
+08/30/2021 17:04:27 - INFO - __main__ - Step 21529: {'lr': 0.00047882739482760044, 'samples': 4133568, 'steps': 21528, 'loss/train': 1.0129021406173706}
+08/30/2021 17:04:28 - INFO - __main__ - Step 21530: {'lr': 0.0004788252574794153, 'samples': 4133760, 'steps': 21529, 'loss/train': 1.4399173259735107}
+08/30/2021 17:04:29 - INFO - __main__ - Step 21531: {'lr': 0.000478823120028125, 'samples': 4133952, 'steps': 21530, 'loss/train': 1.6369318962097168}
+08/30/2021 17:04:30 - INFO - __main__ - Step 21532: {'lr': 0.0004788209824737305, 'samples': 4134144, 'steps': 21531, 'loss/train': 0.7602819204330444}
+08/30/2021 17:04:30 - INFO - __main__ - Step 21533: {'lr': 0.00047881884481623286, 'samples': 4134336, 'steps': 21532, 'loss/train': 0.9776489734649658}
+08/30/2021 17:04:30 - INFO - __main__ - Step 21534: {'lr': 0.000478816707055633, 'samples': 4134528, 'steps': 21533, 'loss/train': 1.3832441568374634}
+08/30/2021 17:04:31 - INFO - __main__ - Step 21535: {'lr': 0.0004788145691919318, 'samples': 4134720, 'steps': 21534, 'loss/train': 1.7407586574554443}
+08/30/2021 17:04:31 - INFO - __main__ - Step 21536: {'lr': 0.0004788124312251303, 'samples': 4134912, 'steps': 21535, 'loss/train': 1.6053481101989746}
+08/30/2021 17:04:32 - INFO - __main__ - Step 21537: {'lr': 0.0004788102931552294, 'samples': 4135104, 'steps': 21536, 'loss/train': 1.5271402597427368}
+08/30/2021 17:04:33 - INFO - __main__ - Step 21538: {'lr': 0.0004788081549822302, 'samples': 4135296, 'steps': 21537, 'loss/train': 1.834592580795288}
+08/30/2021 17:04:33 - INFO - __main__ - Step 21539: {'lr': 0.0004788060167061335, 'samples': 4135488, 'steps': 21538, 'loss/train': 0.9684967994689941}
+08/30/2021 17:04:34 - INFO - __main__ - Step 21540: {'lr': 0.0004788038783269404, 'samples': 4135680, 'steps': 21539, 'loss/train': 1.3103408813476562}
+08/30/2021 17:04:34 - INFO - __main__ - Step 21541: {'lr': 0.00047880173984465174, 'samples': 4135872, 'steps': 21540, 'loss/train': 1.6949554681777954}
+08/30/2021 17:04:36 - INFO - __main__ - Step 21542: {'lr': 0.0004787996012592686, 'samples': 4136064, 'steps': 21541, 'loss/train': 1.6658117771148682}
+08/30/2021 17:04:36 - INFO - __main__ - Step 21543: {'lr': 0.0004787974625707919, 'samples': 4136256, 'steps': 21542, 'loss/train': 1.4745776653289795}
+08/30/2021 17:04:36 - INFO - __main__ - Step 21544: {'lr': 0.0004787953237792225, 'samples': 4136448, 'steps': 21543, 'loss/train': 1.6299556493759155}
+08/30/2021 17:04:37 - INFO - __main__ - Step 21545: {'lr': 0.0004787931848845616, 'samples': 4136640, 'steps': 21544, 'loss/train': 1.6548094749450684}
+08/30/2021 17:04:37 - INFO - __main__ - Step 21546: {'lr': 0.00047879104588680987, 'samples': 4136832, 'steps': 21545, 'loss/train': 1.4136765003204346}
+08/30/2021 17:04:38 - INFO - __main__ - Step 21547: {'lr': 0.00047878890678596854, 'samples': 4137024, 'steps': 21546, 'loss/train': 1.978952407836914}
+08/30/2021 17:04:39 - INFO - __main__ - Step 21548: {'lr': 0.00047878676758203844, 'samples': 4137216, 'steps': 21547, 'loss/train': 2.357581377029419}
+08/30/2021 17:04:39 - INFO - __main__ - Step 21549: {'lr': 0.00047878462827502055, 'samples': 4137408, 'steps': 21548, 'loss/train': 1.579661250114441}
+08/30/2021 17:04:40 - INFO - __main__ - Step 21550: {'lr': 0.0004787824888649158, 'samples': 4137600, 'steps': 21549, 'loss/train': 1.5313758850097656}
+08/30/2021 17:04:40 - INFO - __main__ - Step 21551: {'lr': 0.0004787803493517252, 'samples': 4137792, 'steps': 21550, 'loss/train': 1.173863172531128}
+08/30/2021 17:04:42 - INFO - __main__ - Step 21552: {'lr': 0.0004787782097354497, 'samples': 4137984, 'steps': 21551, 'loss/train': 1.7947689294815063}
+08/30/2021 17:04:42 - INFO - __main__ - Step 21553: {'lr': 0.00047877607001609035, 'samples': 4138176, 'steps': 21552, 'loss/train': 1.6152856349945068}
+08/30/2021 17:04:42 - INFO - __main__ - Step 21554: {'lr': 0.00047877393019364796, 'samples': 4138368, 'steps': 21553, 'loss/train': 0.08391077816486359}
+08/30/2021 17:04:43 - INFO - __main__ - Step 21555: {'lr': 0.0004787717902681236, 'samples': 4138560, 'steps': 21554, 'loss/train': 1.3522006273269653}
+08/30/2021 17:04:43 - INFO - __main__ - Step 21556: {'lr': 0.00047876965023951814, 'samples': 4138752, 'steps': 21555, 'loss/train': 1.7337920665740967}
+08/30/2021 17:04:45 - INFO - __main__ - Step 21557: {'lr': 0.00047876751010783266, 'samples': 4138944, 'steps': 21556, 'loss/train': 1.6510796546936035}
+08/30/2021 17:04:45 - INFO - __main__ - Step 21558: {'lr': 0.0004787653698730681, 'samples': 4139136, 'steps': 21557, 'loss/train': 1.9008625745773315}
+08/30/2021 17:04:46 - INFO - __main__ - Step 21559: {'lr': 0.00047876322953522535, 'samples': 4139328, 'steps': 21558, 'loss/train': 0.08120544999837875}
+08/30/2021 17:04:46 - INFO - __main__ - Step 21560: {'lr': 0.00047876108909430536, 'samples': 4139520, 'steps': 21559, 'loss/train': 1.7383759021759033}
+08/30/2021 17:04:46 - INFO - __main__ - Step 21561: {'lr': 0.00047875894855030923, 'samples': 4139712, 'steps': 21560, 'loss/train': 1.2564455270767212}
+08/30/2021 17:04:47 - INFO - __main__ - Step 21562: {'lr': 0.00047875680790323785, 'samples': 4139904, 'steps': 21561, 'loss/train': 1.6330316066741943}
+08/30/2021 17:04:48 - INFO - __main__ - Step 21563: {'lr': 0.0004787546671530921, 'samples': 4140096, 'steps': 21562, 'loss/train': 1.9583455324172974}
+08/30/2021 17:04:48 - INFO - __main__ - Step 21564: {'lr': 0.0004787525262998731, 'samples': 4140288, 'steps': 21563, 'loss/train': 2.428619146347046}
+08/30/2021 17:04:49 - INFO - __main__ - Step 21565: {'lr': 0.0004787503853435817, 'samples': 4140480, 'steps': 21564, 'loss/train': 1.3141828775405884}
+08/30/2021 17:04:49 - INFO - __main__ - Step 21566: {'lr': 0.00047874824428421897, 'samples': 4140672, 'steps': 21565, 'loss/train': 1.6801226139068604}
+08/30/2021 17:04:50 - INFO - __main__ - Step 21567: {'lr': 0.0004787461031217858, 'samples': 4140864, 'steps': 21566, 'loss/train': 1.6470086574554443}
+08/30/2021 17:04:51 - INFO - __main__ - Step 21568: {'lr': 0.0004787439618562831, 'samples': 4141056, 'steps': 21567, 'loss/train': 2.1003711223602295}
+08/30/2021 17:04:52 - INFO - __main__ - Step 21569: {'lr': 0.000478741820487712, 'samples': 4141248, 'steps': 21568, 'loss/train': 1.7431973218917847}
+08/30/2021 17:04:52 - INFO - __main__ - Step 21570: {'lr': 0.0004787396790160733, 'samples': 4141440, 'steps': 21569, 'loss/train': 1.4745862483978271}
+08/30/2021 17:04:52 - INFO - __main__ - Step 21571: {'lr': 0.00047873753744136807, 'samples': 4141632, 'steps': 21570, 'loss/train': 1.5483851432800293}
+08/30/2021 17:04:53 - INFO - __main__ - Step 21572: {'lr': 0.0004787353957635971, 'samples': 4141824, 'steps': 21571, 'loss/train': 1.7145155668258667}
+08/30/2021 17:04:55 - INFO - __main__ - Step 21573: {'lr': 0.0004787332539827617, 'samples': 4142016, 'steps': 21572, 'loss/train': 2.096367835998535}
+08/30/2021 17:04:55 - INFO - __main__ - Step 21574: {'lr': 0.00047873111209886245, 'samples': 4142208, 'steps': 21573, 'loss/train': 1.3759455680847168}
+08/30/2021 17:04:56 - INFO - __main__ - Step 21575: {'lr': 0.00047872897011190063, 'samples': 4142400, 'steps': 21574, 'loss/train': 1.3320780992507935}
+08/30/2021 17:04:56 - INFO - __main__ - Step 21576: {'lr': 0.00047872682802187693, 'samples': 4142592, 'steps': 21575, 'loss/train': 1.7277063131332397}
+08/30/2021 17:04:56 - INFO - __main__ - Step 21577: {'lr': 0.0004787246858287926, 'samples': 4142784, 'steps': 21576, 'loss/train': 1.3015682697296143}
+08/30/2021 17:04:58 - INFO - __main__ - Step 21578: {'lr': 0.0004787225435326483, 'samples': 4142976, 'steps': 21577, 'loss/train': 1.412316083908081}
+08/30/2021 17:04:58 - INFO - __main__ - Step 21579: {'lr': 0.0004787204011334453, 'samples': 4143168, 'steps': 21578, 'loss/train': 2.0656633377075195}
+08/30/2021 17:04:59 - INFO - __main__ - Step 21580: {'lr': 0.0004787182586311843, 'samples': 4143360, 'steps': 21579, 'loss/train': 1.8539068698883057}
+08/30/2021 17:04:59 - INFO - __main__ - Step 21581: {'lr': 0.0004787161160258664, 'samples': 4143552, 'steps': 21580, 'loss/train': 1.6576381921768188}
+08/30/2021 17:04:59 - INFO - __main__ - Step 21582: {'lr': 0.00047871397331749254, 'samples': 4143744, 'steps': 21581, 'loss/train': 1.424061894416809}
+08/30/2021 17:05:01 - INFO - __main__ - Step 21583: {'lr': 0.00047871183050606376, 'samples': 4143936, 'steps': 21582, 'loss/train': 1.6823989152908325}
+08/30/2021 17:05:02 - INFO - __main__ - Step 21584: {'lr': 0.00047870968759158096, 'samples': 4144128, 'steps': 21583, 'loss/train': 1.2910590171813965}
+08/30/2021 17:05:02 - INFO - __main__ - Step 21585: {'lr': 0.000478707544574045, 'samples': 4144320, 'steps': 21584, 'loss/train': 1.3867682218551636}
+08/30/2021 17:05:02 - INFO - __main__ - Step 21586: {'lr': 0.000478705401453457, 'samples': 4144512, 'steps': 21585, 'loss/train': 1.9276567697525024}
+08/30/2021 17:05:03 - INFO - __main__ - Step 21587: {'lr': 0.000478703258229818, 'samples': 4144704, 'steps': 21586, 'loss/train': 0.12375839799642563}
+08/30/2021 17:05:03 - INFO - __main__ - Step 21588: {'lr': 0.0004787011149031287, 'samples': 4144896, 'steps': 21587, 'loss/train': 1.468145728111267}
+08/30/2021 17:05:05 - INFO - __main__ - Step 21589: {'lr': 0.0004786989714733902, 'samples': 4145088, 'steps': 21588, 'loss/train': 1.724992036819458}
+08/30/2021 17:05:05 - INFO - __main__ - Step 21590: {'lr': 0.0004786968279406035, 'samples': 4145280, 'steps': 21589, 'loss/train': 1.1805689334869385}
+08/30/2021 17:05:05 - INFO - __main__ - Step 21591: {'lr': 0.0004786946843047696, 'samples': 4145472, 'steps': 21590, 'loss/train': 1.4405713081359863}
+08/30/2021 17:05:06 - INFO - __main__ - Step 21592: {'lr': 0.00047869254056588927, 'samples': 4145664, 'steps': 21591, 'loss/train': 1.5672636032104492}
+08/30/2021 17:05:06 - INFO - __main__ - Step 21593: {'lr': 0.0004786903967239637, 'samples': 4145856, 'steps': 21592, 'loss/train': 1.586122751235962}
+08/30/2021 17:05:08 - INFO - __main__ - Step 21594: {'lr': 0.0004786882527789938, 'samples': 4146048, 'steps': 21593, 'loss/train': 1.1756656169891357}
+08/30/2021 17:05:08 - INFO - __main__ - Step 21595: {'lr': 0.00047868610873098047, 'samples': 4146240, 'steps': 21594, 'loss/train': 2.0050926208496094}
+08/30/2021 17:05:09 - INFO - __main__ - Step 21596: {'lr': 0.0004786839645799247, 'samples': 4146432, 'steps': 21595, 'loss/train': 1.450789213180542}
+08/30/2021 17:05:09 - INFO - __main__ - Step 21597: {'lr': 0.00047868182032582746, 'samples': 4146624, 'steps': 21596, 'loss/train': 1.3242963552474976}
+08/30/2021 17:05:09 - INFO - __main__ - Step 21598: {'lr': 0.00047867967596868974, 'samples': 4146816, 'steps': 21597, 'loss/train': 0.3487500250339508}
+08/30/2021 17:05:11 - INFO - __main__ - Step 21599: {'lr': 0.00047867753150851244, 'samples': 4147008, 'steps': 21598, 'loss/train': 2.2175378799438477}
+08/30/2021 17:05:11 - INFO - __main__ - Step 21600: {'lr': 0.0004786753869452966, 'samples': 4147200, 'steps': 21599, 'loss/train': 1.419573426246643}
+08/30/2021 17:05:12 - INFO - __main__ - Step 21601: {'lr': 0.00047867324227904317, 'samples': 4147392, 'steps': 21600, 'loss/train': 1.3353098630905151}
+08/30/2021 17:05:12 - INFO - __main__ - Step 21602: {'lr': 0.0004786710975097531, 'samples': 4147584, 'steps': 21601, 'loss/train': 1.6635923385620117}
+08/30/2021 17:05:12 - INFO - __main__ - Step 21603: {'lr': 0.0004786689526374274, 'samples': 4147776, 'steps': 21602, 'loss/train': 1.8505805730819702}
+08/30/2021 17:05:13 - INFO - __main__ - Step 21604: {'lr': 0.00047866680766206693, 'samples': 4147968, 'steps': 21603, 'loss/train': 1.4862685203552246}
+08/30/2021 17:05:14 - INFO - __main__ - Step 21605: {'lr': 0.0004786646625836727, 'samples': 4148160, 'steps': 21604, 'loss/train': 1.943293809890747}
+08/30/2021 17:05:15 - INFO - __main__ - Step 21606: {'lr': 0.0004786625174022458, 'samples': 4148352, 'steps': 21605, 'loss/train': 1.1202270984649658}
+08/30/2021 17:05:15 - INFO - __main__ - Step 21607: {'lr': 0.00047866037211778705, 'samples': 4148544, 'steps': 21606, 'loss/train': 2.019742965698242}
+08/30/2021 17:05:16 - INFO - __main__ - Step 21608: {'lr': 0.0004786582267302975, 'samples': 4148736, 'steps': 21607, 'loss/train': 1.2123949527740479}
+08/30/2021 17:05:16 - INFO - __main__ - Step 21609: {'lr': 0.000478656081239778, 'samples': 4148928, 'steps': 21608, 'loss/train': 1.9415785074234009}
+08/30/2021 17:05:17 - INFO - __main__ - Step 21610: {'lr': 0.0004786539356462297, 'samples': 4149120, 'steps': 21609, 'loss/train': 1.5333104133605957}
+08/30/2021 17:05:18 - INFO - __main__ - Step 21611: {'lr': 0.0004786517899496534, 'samples': 4149312, 'steps': 21610, 'loss/train': 1.5422704219818115}
+08/30/2021 17:05:18 - INFO - __main__ - Step 21612: {'lr': 0.0004786496441500502, 'samples': 4149504, 'steps': 21611, 'loss/train': 1.368769645690918}
+08/30/2021 17:05:19 - INFO - __main__ - Step 21613: {'lr': 0.00047864749824742093, 'samples': 4149696, 'steps': 21612, 'loss/train': 1.8876041173934937}
+08/30/2021 17:05:19 - INFO - __main__ - Step 21614: {'lr': 0.00047864535224176666, 'samples': 4149888, 'steps': 21613, 'loss/train': 1.2801645994186401}
+08/30/2021 17:05:20 - INFO - __main__ - Step 21615: {'lr': 0.0004786432061330882, 'samples': 4150080, 'steps': 21614, 'loss/train': 1.3951793909072876}
+08/30/2021 17:05:21 - INFO - __main__ - Step 21616: {'lr': 0.0004786410599213868, 'samples': 4150272, 'steps': 21615, 'loss/train': 1.6834088563919067}
+08/30/2021 17:05:21 - INFO - __main__ - Step 21617: {'lr': 0.00047863891360666323, 'samples': 4150464, 'steps': 21616, 'loss/train': 1.1598668098449707}
+08/30/2021 17:05:22 - INFO - __main__ - Step 21618: {'lr': 0.00047863676718891846, 'samples': 4150656, 'steps': 21617, 'loss/train': 1.665282130241394}
+08/30/2021 17:05:22 - INFO - __main__ - Step 21619: {'lr': 0.0004786346206681535, 'samples': 4150848, 'steps': 21618, 'loss/train': 1.9712655544281006}
+08/30/2021 17:05:24 - INFO - __main__ - Step 21620: {'lr': 0.0004786324740443693, 'samples': 4151040, 'steps': 21619, 'loss/train': 1.265072226524353}
+08/30/2021 17:05:24 - INFO - __main__ - Step 21621: {'lr': 0.00047863032731756684, 'samples': 4151232, 'steps': 21620, 'loss/train': 0.20737281441688538}
+08/30/2021 17:05:24 - INFO - __main__ - Step 21622: {'lr': 0.0004786281804877471, 'samples': 4151424, 'steps': 21621, 'loss/train': 1.6420605182647705}
+08/30/2021 17:05:25 - INFO - __main__ - Step 21623: {'lr': 0.00047862603355491103, 'samples': 4151616, 'steps': 21622, 'loss/train': 2.252286434173584}
+08/30/2021 17:05:25 - INFO - __main__ - Step 21624: {'lr': 0.0004786238865190595, 'samples': 4151808, 'steps': 21623, 'loss/train': 1.5345619916915894}
+08/30/2021 17:05:27 - INFO - __main__ - Step 21625: {'lr': 0.0004786217393801937, 'samples': 4152000, 'steps': 21624, 'loss/train': 1.3157330751419067}
+08/30/2021 17:05:27 - INFO - __main__ - Step 21626: {'lr': 0.00047861959213831446, 'samples': 4152192, 'steps': 21625, 'loss/train': 1.9387462139129639}
+08/30/2021 17:05:28 - INFO - __main__ - Step 21627: {'lr': 0.0004786174447934227, 'samples': 4152384, 'steps': 21626, 'loss/train': 1.5936999320983887}
+08/30/2021 17:05:28 - INFO - __main__ - Step 21628: {'lr': 0.0004786152973455195, 'samples': 4152576, 'steps': 21627, 'loss/train': 1.2677874565124512}
+08/30/2021 17:05:28 - INFO - __main__ - Step 21629: {'lr': 0.0004786131497946058, 'samples': 4152768, 'steps': 21628, 'loss/train': 1.9037866592407227}
+08/30/2021 17:05:30 - INFO - __main__ - Step 21630: {'lr': 0.0004786110021406824, 'samples': 4152960, 'steps': 21629, 'loss/train': 1.6569949388504028}
+08/30/2021 17:05:30 - INFO - __main__ - Step 21631: {'lr': 0.0004786088543837506, 'samples': 4153152, 'steps': 21630, 'loss/train': 1.278141975402832}
+08/30/2021 17:05:31 - INFO - __main__ - Step 21632: {'lr': 0.00047860670652381105, 'samples': 4153344, 'steps': 21631, 'loss/train': 1.80409574508667}
+08/30/2021 17:05:31 - INFO - __main__ - Step 21633: {'lr': 0.00047860455856086487, 'samples': 4153536, 'steps': 21632, 'loss/train': 1.2285655736923218}
+08/30/2021 17:05:31 - INFO - __main__ - Step 21634: {'lr': 0.00047860241049491303, 'samples': 4153728, 'steps': 21633, 'loss/train': 1.7540972232818604}
+08/30/2021 17:05:34 - INFO - __main__ - Step 21635: {'lr': 0.00047860026232595645, 'samples': 4153920, 'steps': 21634, 'loss/train': 1.0764487981796265}
+08/30/2021 17:05:34 - INFO - __main__ - Step 21636: {'lr': 0.0004785981140539961, 'samples': 4154112, 'steps': 21635, 'loss/train': 2.0278148651123047}
+08/30/2021 17:05:34 - INFO - __main__ - Step 21637: {'lr': 0.000478595965679033, 'samples': 4154304, 'steps': 21636, 'loss/train': 1.2128251791000366}
+08/30/2021 17:05:35 - INFO - __main__ - Step 21638: {'lr': 0.0004785938172010681, 'samples': 4154496, 'steps': 21637, 'loss/train': 1.9851192235946655}
+08/30/2021 17:05:35 - INFO - __main__ - Step 21639: {'lr': 0.0004785916686201023, 'samples': 4154688, 'steps': 21638, 'loss/train': 2.2266154289245605}
+08/30/2021 17:05:35 - INFO - __main__ - Step 21640: {'lr': 0.00047858951993613665, 'samples': 4154880, 'steps': 21639, 'loss/train': 1.9012534618377686}
+08/30/2021 17:05:37 - INFO - __main__ - Step 21641: {'lr': 0.0004785873711491721, 'samples': 4155072, 'steps': 21640, 'loss/train': 1.3370827436447144}
+08/30/2021 17:05:38 - INFO - __main__ - Step 21642: {'lr': 0.00047858522225920964, 'samples': 4155264, 'steps': 21641, 'loss/train': 1.211037039756775}
+08/30/2021 17:05:38 - INFO - __main__ - Step 21643: {'lr': 0.00047858307326625014, 'samples': 4155456, 'steps': 21642, 'loss/train': 1.617024540901184}
+08/30/2021 17:05:38 - INFO - __main__ - Step 21644: {'lr': 0.00047858092417029464, 'samples': 4155648, 'steps': 21643, 'loss/train': 1.245651125907898}
+08/30/2021 17:05:39 - INFO - __main__ - Step 21645: {'lr': 0.00047857877497134416, 'samples': 4155840, 'steps': 21644, 'loss/train': 1.972427248954773}
+08/30/2021 17:05:39 - INFO - __main__ - Step 21646: {'lr': 0.0004785766256693995, 'samples': 4156032, 'steps': 21645, 'loss/train': 1.904283881187439}
+08/30/2021 17:05:41 - INFO - __main__ - Step 21647: {'lr': 0.0004785744762644619, 'samples': 4156224, 'steps': 21646, 'loss/train': 1.5063691139221191}
+08/30/2021 17:05:41 - INFO - __main__ - Step 21648: {'lr': 0.00047857232675653207, 'samples': 4156416, 'steps': 21647, 'loss/train': 0.1265147179365158}
+08/30/2021 17:05:42 - INFO - __main__ - Step 21649: {'lr': 0.00047857017714561105, 'samples': 4156608, 'steps': 21648, 'loss/train': 1.8977305889129639}
+08/30/2021 17:05:42 - INFO - __main__ - Step 21650: {'lr': 0.00047856802743169994, 'samples': 4156800, 'steps': 21649, 'loss/train': 2.013026237487793}
+08/30/2021 17:05:42 - INFO - __main__ - Step 21651: {'lr': 0.00047856587761479954, 'samples': 4156992, 'steps': 21650, 'loss/train': 2.245924711227417}
+08/30/2021 17:05:44 - INFO - __main__ - Step 21652: {'lr': 0.00047856372769491083, 'samples': 4157184, 'steps': 21651, 'loss/train': 2.003310203552246}
+08/30/2021 17:05:44 - INFO - __main__ - Step 21653: {'lr': 0.0004785615776720349, 'samples': 4157376, 'steps': 21652, 'loss/train': 1.499346375465393}
+08/30/2021 17:05:45 - INFO - __main__ - Step 21654: {'lr': 0.0004785594275461726, 'samples': 4157568, 'steps': 21653, 'loss/train': 1.6132514476776123}
+08/30/2021 17:05:45 - INFO - __main__ - Step 21655: {'lr': 0.00047855727731732503, 'samples': 4157760, 'steps': 21654, 'loss/train': 1.4317113161087036}
+08/30/2021 17:05:45 - INFO - __main__ - Step 21656: {'lr': 0.00047855512698549295, 'samples': 4157952, 'steps': 21655, 'loss/train': 1.4344325065612793}
+08/30/2021 17:05:47 - INFO - __main__ - Step 21657: {'lr': 0.00047855297655067754, 'samples': 4158144, 'steps': 21656, 'loss/train': 1.5683907270431519}
+08/30/2021 17:05:47 - INFO - __main__ - Step 21658: {'lr': 0.0004785508260128797, 'samples': 4158336, 'steps': 21657, 'loss/train': 1.5640400648117065}
+08/30/2021 17:05:48 - INFO - __main__ - Step 21659: {'lr': 0.00047854867537210034, 'samples': 4158528, 'steps': 21658, 'loss/train': 1.8587629795074463}
+08/30/2021 17:05:48 - INFO - __main__ - Step 21660: {'lr': 0.00047854652462834055, 'samples': 4158720, 'steps': 21659, 'loss/train': 1.7621623277664185}
+08/30/2021 17:05:48 - INFO - __main__ - Step 21661: {'lr': 0.0004785443737816012, 'samples': 4158912, 'steps': 21660, 'loss/train': 1.5130053758621216}
+08/30/2021 17:05:50 - INFO - __main__ - Step 21662: {'lr': 0.0004785422228318832, 'samples': 4159104, 'steps': 21661, 'loss/train': 1.2033276557922363}
+08/30/2021 17:05:50 - INFO - __main__ - Step 21663: {'lr': 0.0004785400717791877, 'samples': 4159296, 'steps': 21662, 'loss/train': 1.7768971920013428}
+08/30/2021 17:05:51 - INFO - __main__ - Step 21664: {'lr': 0.0004785379206235155, 'samples': 4159488, 'steps': 21663, 'loss/train': 1.7159216403961182}
+08/30/2021 17:05:51 - INFO - __main__ - Step 21665: {'lr': 0.00047853576936486764, 'samples': 4159680, 'steps': 21664, 'loss/train': 1.5477763414382935}
+08/30/2021 17:05:51 - INFO - __main__ - Step 21666: {'lr': 0.00047853361800324516, 'samples': 4159872, 'steps': 21665, 'loss/train': 1.7746342420578003}
+08/30/2021 17:05:53 - INFO - __main__ - Step 21667: {'lr': 0.0004785314665386489, 'samples': 4160064, 'steps': 21666, 'loss/train': 1.3123118877410889}
+08/30/2021 17:05:53 - INFO - __main__ - Step 21668: {'lr': 0.00047852931497107987, 'samples': 4160256, 'steps': 21667, 'loss/train': 1.0089551210403442}
+08/30/2021 17:05:54 - INFO - __main__ - Step 21669: {'lr': 0.0004785271633005391, 'samples': 4160448, 'steps': 21668, 'loss/train': 0.8854736089706421}
+08/30/2021 17:05:54 - INFO - __main__ - Step 21670: {'lr': 0.0004785250115270275, 'samples': 4160640, 'steps': 21669, 'loss/train': 1.405593991279602}
+08/30/2021 17:05:55 - INFO - __main__ - Step 21671: {'lr': 0.00047852285965054606, 'samples': 4160832, 'steps': 21670, 'loss/train': 1.7800955772399902}
+08/30/2021 17:05:56 - INFO - __main__ - Step 21672: {'lr': 0.00047852070767109573, 'samples': 4161024, 'steps': 21671, 'loss/train': 0.6641238927841187}
+08/30/2021 17:05:57 - INFO - __main__ - Step 21673: {'lr': 0.00047851855558867754, 'samples': 4161216, 'steps': 21672, 'loss/train': 1.8311665058135986}
+08/30/2021 17:05:57 - INFO - __main__ - Step 21674: {'lr': 0.0004785164034032924, 'samples': 4161408, 'steps': 21673, 'loss/train': 1.4423707723617554}
+08/30/2021 17:05:57 - INFO - __main__ - Step 21675: {'lr': 0.0004785142511149412, 'samples': 4161600, 'steps': 21674, 'loss/train': 1.4329500198364258}
+08/30/2021 17:05:58 - INFO - __main__ - Step 21676: {'lr': 0.0004785120987236251, 'samples': 4161792, 'steps': 21675, 'loss/train': 1.7964509725570679}
+08/30/2021 17:05:58 - INFO - __main__ - Step 21677: {'lr': 0.00047850994622934494, 'samples': 4161984, 'steps': 21676, 'loss/train': 2.149315357208252}
+08/30/2021 17:06:00 - INFO - __main__ - Step 21678: {'lr': 0.0004785077936321018, 'samples': 4162176, 'steps': 21677, 'loss/train': 1.191805362701416}
+08/30/2021 17:06:00 - INFO - __main__ - Step 21679: {'lr': 0.00047850564093189653, 'samples': 4162368, 'steps': 21678, 'loss/train': 1.8324463367462158}
+08/30/2021 17:06:01 - INFO - __main__ - Step 21680: {'lr': 0.0004785034881287301, 'samples': 4162560, 'steps': 21679, 'loss/train': 1.6059406995773315}
+08/30/2021 17:06:01 - INFO - __main__ - Step 21681: {'lr': 0.0004785013352226035, 'samples': 4162752, 'steps': 21680, 'loss/train': 1.2899469137191772}
+08/30/2021 17:06:02 - INFO - __main__ - Step 21682: {'lr': 0.00047849918221351783, 'samples': 4162944, 'steps': 21681, 'loss/train': 1.5513609647750854}
+08/30/2021 17:06:03 - INFO - __main__ - Step 21683: {'lr': 0.0004784970291014739, 'samples': 4163136, 'steps': 21682, 'loss/train': 1.4121525287628174}
+08/30/2021 17:06:04 - INFO - __main__ - Step 21684: {'lr': 0.0004784948758864727, 'samples': 4163328, 'steps': 21683, 'loss/train': 1.5040241479873657}
+08/30/2021 17:06:04 - INFO - __main__ - Step 21685: {'lr': 0.0004784927225685153, 'samples': 4163520, 'steps': 21684, 'loss/train': 1.7399235963821411}
+08/30/2021 17:06:04 - INFO - __main__ - Step 21686: {'lr': 0.00047849056914760256, 'samples': 4163712, 'steps': 21685, 'loss/train': 1.5813474655151367}
+08/30/2021 17:06:05 - INFO - __main__ - Step 21687: {'lr': 0.00047848841562373557, 'samples': 4163904, 'steps': 21686, 'loss/train': 1.3997126817703247}
+08/30/2021 17:06:06 - INFO - __main__ - Step 21688: {'lr': 0.00047848626199691513, 'samples': 4164096, 'steps': 21687, 'loss/train': 0.8966947197914124}
+08/30/2021 17:06:07 - INFO - __main__ - Step 21689: {'lr': 0.00047848410826714237, 'samples': 4164288, 'steps': 21688, 'loss/train': 2.055316209793091}
+08/30/2021 17:06:07 - INFO - __main__ - Step 21690: {'lr': 0.00047848195443441817, 'samples': 4164480, 'steps': 21689, 'loss/train': 1.6565885543823242}
+08/30/2021 17:06:07 - INFO - __main__ - Step 21691: {'lr': 0.0004784798004987435, 'samples': 4164672, 'steps': 21690, 'loss/train': 1.4507962465286255}
+08/30/2021 17:06:08 - INFO - __main__ - Step 21692: {'lr': 0.00047847764646011937, 'samples': 4164864, 'steps': 21691, 'loss/train': 1.6128380298614502}
+08/30/2021 17:06:09 - INFO - __main__ - Step 21693: {'lr': 0.0004784754923185468, 'samples': 4165056, 'steps': 21692, 'loss/train': 1.4008574485778809}
+08/30/2021 17:06:10 - INFO - __main__ - Step 21694: {'lr': 0.00047847333807402666, 'samples': 4165248, 'steps': 21693, 'loss/train': 1.9528981447219849}
+08/30/2021 17:06:10 - INFO - __main__ - Step 21695: {'lr': 0.00047847118372655996, 'samples': 4165440, 'steps': 21694, 'loss/train': 1.243920087814331}
+08/30/2021 17:06:10 - INFO - __main__ - Step 21696: {'lr': 0.00047846902927614767, 'samples': 4165632, 'steps': 21695, 'loss/train': 1.3261280059814453}
+08/30/2021 17:06:11 - INFO - __main__ - Step 21697: {'lr': 0.0004784668747227907, 'samples': 4165824, 'steps': 21696, 'loss/train': 1.3166300058364868}
+08/30/2021 17:06:12 - INFO - __main__ - Step 21698: {'lr': 0.00047846472006649016, 'samples': 4166016, 'steps': 21697, 'loss/train': 1.4801424741744995}
+08/30/2021 17:06:13 - INFO - __main__ - Step 21699: {'lr': 0.0004784625653072469, 'samples': 4166208, 'steps': 21698, 'loss/train': 1.820278286933899}
+08/30/2021 17:06:13 - INFO - __main__ - Step 21700: {'lr': 0.00047846041044506194, 'samples': 4166400, 'steps': 21699, 'loss/train': 1.6920466423034668}
+08/30/2021 17:06:13 - INFO - __main__ - Step 21701: {'lr': 0.00047845825547993627, 'samples': 4166592, 'steps': 21700, 'loss/train': 1.3065929412841797}
+08/30/2021 17:06:14 - INFO - __main__ - Step 21702: {'lr': 0.0004784561004118708, 'samples': 4166784, 'steps': 21701, 'loss/train': 0.916358470916748}
+08/30/2021 17:06:14 - INFO - __main__ - Step 21703: {'lr': 0.0004784539452408666, 'samples': 4166976, 'steps': 21702, 'loss/train': 1.397084355354309}
+08/30/2021 17:06:16 - INFO - __main__ - Step 21704: {'lr': 0.0004784517899669245, 'samples': 4167168, 'steps': 21703, 'loss/train': 1.5995969772338867}
+08/30/2021 17:06:16 - INFO - __main__ - Step 21705: {'lr': 0.00047844963459004565, 'samples': 4167360, 'steps': 21704, 'loss/train': 1.1845390796661377}
+08/30/2021 17:06:16 - INFO - __main__ - Step 21706: {'lr': 0.00047844747911023077, 'samples': 4167552, 'steps': 21705, 'loss/train': 1.4429291486740112}
+08/30/2021 17:06:17 - INFO - __main__ - Step 21707: {'lr': 0.00047844532352748115, 'samples': 4167744, 'steps': 21706, 'loss/train': 1.5198560953140259}
+08/30/2021 17:06:18 - INFO - __main__ - Step 21708: {'lr': 0.0004784431678417975, 'samples': 4167936, 'steps': 21707, 'loss/train': 1.672396183013916}
+08/30/2021 17:06:19 - INFO - __main__ - Step 21709: {'lr': 0.00047844101205318085, 'samples': 4168128, 'steps': 21708, 'loss/train': 1.552107334136963}
+08/30/2021 17:06:19 - INFO - __main__ - Step 21710: {'lr': 0.0004784388561616323, 'samples': 4168320, 'steps': 21709, 'loss/train': 1.5733312368392944}
+08/30/2021 17:06:20 - INFO - __main__ - Step 21711: {'lr': 0.0004784367001671526, 'samples': 4168512, 'steps': 21710, 'loss/train': 2.090911388397217}
+08/30/2021 17:06:20 - INFO - __main__ - Step 21712: {'lr': 0.00047843454406974295, 'samples': 4168704, 'steps': 21711, 'loss/train': 0.10917995125055313}
+08/30/2021 17:06:20 - INFO - __main__ - Step 21713: {'lr': 0.00047843238786940423, 'samples': 4168896, 'steps': 21712, 'loss/train': 1.238024115562439}
+08/30/2021 17:06:22 - INFO - __main__ - Step 21714: {'lr': 0.0004784302315661373, 'samples': 4169088, 'steps': 21713, 'loss/train': 1.3346723318099976}
+08/30/2021 17:06:22 - INFO - __main__ - Step 21715: {'lr': 0.00047842807515994335, 'samples': 4169280, 'steps': 21714, 'loss/train': 1.1240020990371704}
+08/30/2021 17:06:22 - INFO - __main__ - Step 21716: {'lr': 0.00047842591865082315, 'samples': 4169472, 'steps': 21715, 'loss/train': 1.3416444063186646}
+08/30/2021 17:06:23 - INFO - __main__ - Step 21717: {'lr': 0.0004784237620387778, 'samples': 4169664, 'steps': 21716, 'loss/train': 1.1611155271530151}
+08/30/2021 17:06:23 - INFO - __main__ - Step 21718: {'lr': 0.0004784216053238082, 'samples': 4169856, 'steps': 21717, 'loss/train': 1.9573583602905273}
+08/30/2021 17:06:25 - INFO - __main__ - Step 21719: {'lr': 0.00047841944850591535, 'samples': 4170048, 'steps': 21718, 'loss/train': 1.6516616344451904}
+08/30/2021 17:06:25 - INFO - __main__ - Step 21720: {'lr': 0.0004784172915851003, 'samples': 4170240, 'steps': 21719, 'loss/train': 1.3609671592712402}
+08/30/2021 17:06:26 - INFO - __main__ - Step 21721: {'lr': 0.00047841513456136383, 'samples': 4170432, 'steps': 21720, 'loss/train': 1.008778691291809}
+08/30/2021 17:06:26 - INFO - __main__ - Step 21722: {'lr': 0.000478412977434707, 'samples': 4170624, 'steps': 21721, 'loss/train': 1.7178418636322021}
+08/30/2021 17:06:26 - INFO - __main__ - Step 21723: {'lr': 0.00047841082020513094, 'samples': 4170816, 'steps': 21722, 'loss/train': 1.863709568977356}
+08/30/2021 17:06:28 - INFO - __main__ - Step 21724: {'lr': 0.0004784086628726364, 'samples': 4171008, 'steps': 21723, 'loss/train': 3.1482386589050293}
+08/30/2021 17:06:28 - INFO - __main__ - Step 21725: {'lr': 0.0004784065054372245, 'samples': 4171200, 'steps': 21724, 'loss/train': 1.9970582723617554}
+08/30/2021 17:06:29 - INFO - __main__ - Step 21726: {'lr': 0.0004784043478988961, 'samples': 4171392, 'steps': 21725, 'loss/train': 1.3224568367004395}
+08/30/2021 17:06:29 - INFO - __main__ - Step 21727: {'lr': 0.00047840219025765225, 'samples': 4171584, 'steps': 21726, 'loss/train': 2.3315300941467285}
+08/30/2021 17:06:29 - INFO - __main__ - Step 21728: {'lr': 0.0004784000325134939, 'samples': 4171776, 'steps': 21727, 'loss/train': 0.11365387588739395}
+08/30/2021 17:06:30 - INFO - __main__ - Step 21729: {'lr': 0.00047839787466642206, 'samples': 4171968, 'steps': 21728, 'loss/train': 1.4912441968917847}
+08/30/2021 17:06:32 - INFO - __main__ - Step 21730: {'lr': 0.00047839571671643756, 'samples': 4172160, 'steps': 21729, 'loss/train': 1.7546395063400269}
+08/30/2021 17:06:33 - INFO - __main__ - Step 21731: {'lr': 0.0004783935586635415, 'samples': 4172352, 'steps': 21730, 'loss/train': 2.2621519565582275}
+08/30/2021 17:06:33 - INFO - __main__ - Step 21732: {'lr': 0.0004783914005077349, 'samples': 4172544, 'steps': 21731, 'loss/train': 1.6448993682861328}
+08/30/2021 17:06:33 - INFO - __main__ - Step 21733: {'lr': 0.0004783892422490186, 'samples': 4172736, 'steps': 21732, 'loss/train': 1.3782418966293335}
+08/30/2021 17:06:34 - INFO - __main__ - Step 21734: {'lr': 0.00047838708388739365, 'samples': 4172928, 'steps': 21733, 'loss/train': 1.9569100141525269}
+08/30/2021 17:06:35 - INFO - __main__ - Step 21735: {'lr': 0.000478384925422861, 'samples': 4173120, 'steps': 21734, 'loss/train': 1.675588846206665}
+08/30/2021 17:06:36 - INFO - __main__ - Step 21736: {'lr': 0.00047838276685542157, 'samples': 4173312, 'steps': 21735, 'loss/train': 1.4226258993148804}
+08/30/2021 17:06:36 - INFO - __main__ - Step 21737: {'lr': 0.0004783806081850765, 'samples': 4173504, 'steps': 21736, 'loss/train': 1.2623894214630127}
+08/30/2021 17:06:37 - INFO - __main__ - Step 21738: {'lr': 0.0004783784494118266, 'samples': 4173696, 'steps': 21737, 'loss/train': 1.5730348825454712}
+08/30/2021 17:06:37 - INFO - __main__ - Step 21739: {'lr': 0.00047837629053567286, 'samples': 4173888, 'steps': 21738, 'loss/train': 1.30971360206604}
+08/30/2021 17:06:39 - INFO - __main__ - Step 21740: {'lr': 0.00047837413155661635, 'samples': 4174080, 'steps': 21739, 'loss/train': 0.17382727563381195}
+08/30/2021 17:06:39 - INFO - __main__ - Step 21741: {'lr': 0.000478371972474658, 'samples': 4174272, 'steps': 21740, 'loss/train': 1.891969084739685}
+08/30/2021 17:06:39 - INFO - __main__ - Step 21742: {'lr': 0.00047836981328979865, 'samples': 4174464, 'steps': 21741, 'loss/train': 1.3879209756851196}
+08/30/2021 17:06:40 - INFO - __main__ - Step 21743: {'lr': 0.00047836765400203953, 'samples': 4174656, 'steps': 21742, 'loss/train': 1.1069267988204956}
+08/30/2021 17:06:40 - INFO - __main__ - Step 21744: {'lr': 0.00047836549461138133, 'samples': 4174848, 'steps': 21743, 'loss/train': 1.566767930984497}
+08/30/2021 17:06:42 - INFO - __main__ - Step 21745: {'lr': 0.00047836333511782524, 'samples': 4175040, 'steps': 21744, 'loss/train': 1.494236707687378}
+08/30/2021 17:06:43 - INFO - __main__ - Step 21746: {'lr': 0.00047836117552137213, 'samples': 4175232, 'steps': 21745, 'loss/train': 1.5211020708084106}
+08/30/2021 17:06:43 - INFO - __main__ - Step 21747: {'lr': 0.00047835901582202303, 'samples': 4175424, 'steps': 21746, 'loss/train': 1.3371444940567017}
+08/30/2021 17:06:43 - INFO - __main__ - Step 21748: {'lr': 0.00047835685601977886, 'samples': 4175616, 'steps': 21747, 'loss/train': 1.6107068061828613}
+08/30/2021 17:06:44 - INFO - __main__ - Step 21749: {'lr': 0.00047835469611464055, 'samples': 4175808, 'steps': 21748, 'loss/train': 1.7145252227783203}
+08/30/2021 17:06:44 - INFO - __main__ - Step 21750: {'lr': 0.0004783525361066092, 'samples': 4176000, 'steps': 21749, 'loss/train': 1.872490644454956}
+08/30/2021 17:06:46 - INFO - __main__ - Step 21751: {'lr': 0.00047835037599568576, 'samples': 4176192, 'steps': 21750, 'loss/train': 1.7199158668518066}
+08/30/2021 17:06:46 - INFO - __main__ - Step 21752: {'lr': 0.0004783482157818711, 'samples': 4176384, 'steps': 21751, 'loss/train': 1.058449149131775}
+08/30/2021 17:06:46 - INFO - __main__ - Step 21753: {'lr': 0.0004783460554651663, 'samples': 4176576, 'steps': 21752, 'loss/train': 1.4700802564620972}
+08/30/2021 17:06:47 - INFO - __main__ - Step 21754: {'lr': 0.0004783438950455723, 'samples': 4176768, 'steps': 21753, 'loss/train': 1.7727082967758179}
+08/30/2021 17:06:47 - INFO - __main__ - Step 21755: {'lr': 0.00047834173452309005, 'samples': 4176960, 'steps': 21754, 'loss/train': 1.5789827108383179}
+08/30/2021 17:06:48 - INFO - __main__ - Step 21756: {'lr': 0.00047833957389772046, 'samples': 4177152, 'steps': 21755, 'loss/train': 1.455665946006775}
+08/30/2021 17:06:49 - INFO - __main__ - Step 21757: {'lr': 0.0004783374131694647, 'samples': 4177344, 'steps': 21756, 'loss/train': 1.679849624633789}
+08/30/2021 17:06:50 - INFO - __main__ - Step 21758: {'lr': 0.00047833525233832356, 'samples': 4177536, 'steps': 21757, 'loss/train': 0.199010968208313}
+08/30/2021 17:06:50 - INFO - __main__ - Step 21759: {'lr': 0.00047833309140429803, 'samples': 4177728, 'steps': 21758, 'loss/train': 1.6432427167892456}
+08/30/2021 17:06:50 - INFO - __main__ - Step 21760: {'lr': 0.0004783309303673892, 'samples': 4177920, 'steps': 21759, 'loss/train': 1.7864922285079956}
+08/30/2021 17:06:51 - INFO - __main__ - Step 21761: {'lr': 0.00047832876922759805, 'samples': 4178112, 'steps': 21760, 'loss/train': 1.6534661054611206}
+08/30/2021 17:06:52 - INFO - __main__ - Step 21762: {'lr': 0.0004783266079849253, 'samples': 4178304, 'steps': 21761, 'loss/train': 1.9542009830474854}
+08/30/2021 17:06:53 - INFO - __main__ - Step 21763: {'lr': 0.00047832444663937227, 'samples': 4178496, 'steps': 21762, 'loss/train': 1.3221291303634644}
+08/30/2021 17:06:53 - INFO - __main__ - Step 21764: {'lr': 0.0004783222851909397, 'samples': 4178688, 'steps': 21763, 'loss/train': 5.238156795501709}
+08/30/2021 17:06:53 - INFO - __main__ - Step 21765: {'lr': 0.0004783201236396286, 'samples': 4178880, 'steps': 21764, 'loss/train': 1.62040114402771}
+08/30/2021 17:06:54 - INFO - __main__ - Step 21766: {'lr': 0.00047831796198544, 'samples': 4179072, 'steps': 21765, 'loss/train': 1.7173926830291748}
+08/30/2021 17:06:54 - INFO - __main__ - Step 21767: {'lr': 0.0004783158002283749, 'samples': 4179264, 'steps': 21766, 'loss/train': 1.612707495689392}
+08/30/2021 17:06:56 - INFO - __main__ - Step 21768: {'lr': 0.0004783136383684342, 'samples': 4179456, 'steps': 21767, 'loss/train': 1.9059386253356934}
+08/30/2021 17:06:56 - INFO - __main__ - Step 21769: {'lr': 0.0004783114764056188, 'samples': 4179648, 'steps': 21768, 'loss/train': 1.3929764032363892}
+08/30/2021 17:06:56 - INFO - __main__ - Step 21770: {'lr': 0.00047830931433992985, 'samples': 4179840, 'steps': 21769, 'loss/train': 0.8066627979278564}
+08/30/2021 17:06:57 - INFO - __main__ - Step 21771: {'lr': 0.00047830715217136825, 'samples': 4180032, 'steps': 21770, 'loss/train': 2.010899305343628}
+08/30/2021 17:06:57 - INFO - __main__ - Step 21772: {'lr': 0.000478304989899935, 'samples': 4180224, 'steps': 21771, 'loss/train': 0.7552194595336914}
+08/30/2021 17:06:58 - INFO - __main__ - Step 21773: {'lr': 0.00047830282752563103, 'samples': 4180416, 'steps': 21772, 'loss/train': 1.7293847799301147}
+08/30/2021 17:06:59 - INFO - __main__ - Step 21774: {'lr': 0.00047830066504845725, 'samples': 4180608, 'steps': 21773, 'loss/train': 1.309455394744873}
+08/30/2021 17:06:59 - INFO - __main__ - Step 21775: {'lr': 0.0004782985024684148, 'samples': 4180800, 'steps': 21774, 'loss/train': 1.440053105354309}
+08/30/2021 17:07:00 - INFO - __main__ - Step 21776: {'lr': 0.0004782963397855046, 'samples': 4180992, 'steps': 21775, 'loss/train': 1.169439673423767}
+08/30/2021 17:07:00 - INFO - __main__ - Step 21777: {'lr': 0.00047829417699972747, 'samples': 4181184, 'steps': 21776, 'loss/train': 2.02445650100708}
+08/30/2021 17:07:02 - INFO - __main__ - Step 21778: {'lr': 0.0004782920141110846, 'samples': 4181376, 'steps': 21777, 'loss/train': 1.6135485172271729}
+08/30/2021 17:07:02 - INFO - __main__ - Step 21779: {'lr': 0.0004782898511195768, 'samples': 4181568, 'steps': 21778, 'loss/train': 0.9269253611564636}
+08/30/2021 17:07:03 - INFO - __main__ - Step 21780: {'lr': 0.00047828768802520515, 'samples': 4181760, 'steps': 21779, 'loss/train': 1.4465060234069824}
+08/30/2021 17:07:03 - INFO - __main__ - Step 21781: {'lr': 0.0004782855248279706, 'samples': 4181952, 'steps': 21780, 'loss/train': 1.769426703453064}
+08/30/2021 17:07:03 - INFO - __main__ - Step 21782: {'lr': 0.0004782833615278741, 'samples': 4182144, 'steps': 21781, 'loss/train': 1.2966687679290771}
+08/30/2021 17:07:05 - INFO - __main__ - Step 21783: {'lr': 0.00047828119812491664, 'samples': 4182336, 'steps': 21782, 'loss/train': 1.430395483970642}
+08/30/2021 17:07:05 - INFO - __main__ - Step 21784: {'lr': 0.0004782790346190993, 'samples': 4182528, 'steps': 21783, 'loss/train': 1.4945639371871948}
+08/30/2021 17:07:06 - INFO - __main__ - Step 21785: {'lr': 0.00047827687101042283, 'samples': 4182720, 'steps': 21784, 'loss/train': 2.0308988094329834}
+08/30/2021 17:07:06 - INFO - __main__ - Step 21786: {'lr': 0.00047827470729888834, 'samples': 4182912, 'steps': 21785, 'loss/train': 1.586060643196106}
+08/30/2021 17:07:06 - INFO - __main__ - Step 21787: {'lr': 0.0004782725434844968, 'samples': 4183104, 'steps': 21786, 'loss/train': 2.080684185028076}
+08/30/2021 17:07:08 - INFO - __main__ - Step 21788: {'lr': 0.00047827037956724915, 'samples': 4183296, 'steps': 21787, 'loss/train': 0.839836835861206}
+08/30/2021 17:07:09 - INFO - __main__ - Step 21789: {'lr': 0.00047826821554714644, 'samples': 4183488, 'steps': 21788, 'loss/train': 1.1939973831176758}
+08/30/2021 17:07:09 - INFO - __main__ - Step 21790: {'lr': 0.00047826605142418954, 'samples': 4183680, 'steps': 21789, 'loss/train': 1.1964384317398071}
+08/30/2021 17:07:10 - INFO - __main__ - Step 21791: {'lr': 0.0004782638871983795, 'samples': 4183872, 'steps': 21790, 'loss/train': 1.6358758211135864}
+08/30/2021 17:07:10 - INFO - __main__ - Step 21792: {'lr': 0.0004782617228697173, 'samples': 4184064, 'steps': 21791, 'loss/train': 1.5515676736831665}
+08/30/2021 17:07:11 - INFO - __main__ - Step 21793: {'lr': 0.0004782595584382039, 'samples': 4184256, 'steps': 21792, 'loss/train': 1.7221769094467163}
+08/30/2021 17:07:12 - INFO - __main__ - Step 21794: {'lr': 0.0004782573939038402, 'samples': 4184448, 'steps': 21793, 'loss/train': 1.7550474405288696}
+08/30/2021 17:07:12 - INFO - __main__ - Step 21795: {'lr': 0.0004782552292666273, 'samples': 4184640, 'steps': 21794, 'loss/train': 1.3632317781448364}
+08/30/2021 17:07:13 - INFO - __main__ - Step 21796: {'lr': 0.0004782530645265661, 'samples': 4184832, 'steps': 21795, 'loss/train': 1.9573311805725098}
+08/30/2021 17:07:13 - INFO - __main__ - Step 21797: {'lr': 0.0004782508996836576, 'samples': 4185024, 'steps': 21796, 'loss/train': 1.5223103761672974}
+08/30/2021 17:07:13 - INFO - __main__ - Step 21798: {'lr': 0.00047824873473790275, 'samples': 4185216, 'steps': 21797, 'loss/train': 1.6803069114685059}
+08/30/2021 17:07:15 - INFO - __main__ - Step 21799: {'lr': 0.0004782465696893025, 'samples': 4185408, 'steps': 21798, 'loss/train': 0.7478705644607544}
+08/30/2021 17:07:15 - INFO - __main__ - Step 21800: {'lr': 0.0004782444045378579, 'samples': 4185600, 'steps': 21799, 'loss/train': 2.2432470321655273}
+08/30/2021 17:07:16 - INFO - __main__ - Step 21801: {'lr': 0.00047824223928356993, 'samples': 4185792, 'steps': 21800, 'loss/train': 1.51249361038208}
+08/30/2021 17:07:16 - INFO - __main__ - Step 21802: {'lr': 0.0004782400739264395, 'samples': 4185984, 'steps': 21801, 'loss/train': 1.9229987859725952}
+08/30/2021 17:07:16 - INFO - __main__ - Step 21803: {'lr': 0.00047823790846646764, 'samples': 4186176, 'steps': 21802, 'loss/train': 1.9468880891799927}
+08/30/2021 17:07:18 - INFO - __main__ - Step 21804: {'lr': 0.0004782357429036553, 'samples': 4186368, 'steps': 21803, 'loss/train': 1.4829293489456177}
+08/30/2021 17:07:18 - INFO - __main__ - Step 21805: {'lr': 0.00047823357723800344, 'samples': 4186560, 'steps': 21804, 'loss/train': 1.7622202634811401}
+08/30/2021 17:07:19 - INFO - __main__ - Step 21806: {'lr': 0.000478231411469513, 'samples': 4186752, 'steps': 21805, 'loss/train': 1.6974397897720337}
+08/30/2021 17:07:19 - INFO - __main__ - Step 21807: {'lr': 0.000478229245598185, 'samples': 4186944, 'steps': 21806, 'loss/train': 0.7027131915092468}
+08/30/2021 17:07:19 - INFO - __main__ - Step 21808: {'lr': 0.00047822707962402055, 'samples': 4187136, 'steps': 21807, 'loss/train': 1.691078543663025}
+08/30/2021 17:07:21 - INFO - __main__ - Step 21809: {'lr': 0.00047822491354702044, 'samples': 4187328, 'steps': 21808, 'loss/train': 1.4254356622695923}
+08/30/2021 17:07:21 - INFO - __main__ - Step 21810: {'lr': 0.0004782227473671857, 'samples': 4187520, 'steps': 21809, 'loss/train': 0.9605146646499634}
+08/30/2021 17:07:22 - INFO - __main__ - Step 21811: {'lr': 0.00047822058108451727, 'samples': 4187712, 'steps': 21810, 'loss/train': 1.3175225257873535}
+08/30/2021 17:07:22 - INFO - __main__ - Step 21812: {'lr': 0.0004782184146990162, 'samples': 4187904, 'steps': 21811, 'loss/train': 1.8008755445480347}
+08/30/2021 17:07:22 - INFO - __main__ - Step 21813: {'lr': 0.00047821624821068346, 'samples': 4188096, 'steps': 21812, 'loss/train': 3.052218198776245}
+08/30/2021 17:07:24 - INFO - __main__ - Step 21814: {'lr': 0.00047821408161952, 'samples': 4188288, 'steps': 21813, 'loss/train': 1.5098425149917603}
+08/30/2021 17:07:24 - INFO - __main__ - Step 21815: {'lr': 0.00047821191492552676, 'samples': 4188480, 'steps': 21814, 'loss/train': 1.8102848529815674}
+08/30/2021 17:07:25 - INFO - __main__ - Step 21816: {'lr': 0.00047820974812870477, 'samples': 4188672, 'steps': 21815, 'loss/train': 1.5876659154891968}
+08/30/2021 17:07:25 - INFO - __main__ - Step 21817: {'lr': 0.00047820758122905493, 'samples': 4188864, 'steps': 21816, 'loss/train': 1.1264034509658813}
+08/30/2021 17:07:25 - INFO - __main__ - Step 21818: {'lr': 0.0004782054142265784, 'samples': 4189056, 'steps': 21817, 'loss/train': 1.609885573387146}
+08/30/2021 17:07:26 - INFO - __main__ - Step 21819: {'lr': 0.00047820324712127593, 'samples': 4189248, 'steps': 21818, 'loss/train': 1.475606083869934}
+08/30/2021 17:07:27 - INFO - __main__ - Step 21820: {'lr': 0.0004782010799131487, 'samples': 4189440, 'steps': 21819, 'loss/train': 1.5146722793579102}
+08/30/2021 17:07:28 - INFO - __main__ - Step 21821: {'lr': 0.0004781989126021975, 'samples': 4189632, 'steps': 21820, 'loss/train': 1.1020145416259766}
+08/30/2021 17:07:28 - INFO - __main__ - Step 21822: {'lr': 0.00047819674518842335, 'samples': 4189824, 'steps': 21821, 'loss/train': 1.297472596168518}
+08/30/2021 17:07:28 - INFO - __main__ - Step 21823: {'lr': 0.00047819457767182735, 'samples': 4190016, 'steps': 21822, 'loss/train': 1.6172099113464355}
+08/30/2021 17:07:29 - INFO - __main__ - Step 21824: {'lr': 0.0004781924100524104, 'samples': 4190208, 'steps': 21823, 'loss/train': 1.5605764389038086}
+08/30/2021 17:07:30 - INFO - __main__ - Step 21825: {'lr': 0.00047819024233017337, 'samples': 4190400, 'steps': 21824, 'loss/train': 1.5563044548034668}
+08/30/2021 17:07:31 - INFO - __main__ - Step 21826: {'lr': 0.00047818807450511746, 'samples': 4190592, 'steps': 21825, 'loss/train': 1.235628366470337}
+08/30/2021 17:07:31 - INFO - __main__ - Step 21827: {'lr': 0.00047818590657724345, 'samples': 4190784, 'steps': 21826, 'loss/train': 1.9041955471038818}
+08/30/2021 17:07:31 - INFO - __main__ - Step 21828: {'lr': 0.0004781837385465524, 'samples': 4190976, 'steps': 21827, 'loss/train': 1.5375030040740967}
+08/30/2021 17:07:32 - INFO - __main__ - Step 21829: {'lr': 0.00047818157041304535, 'samples': 4191168, 'steps': 21828, 'loss/train': 2.0281591415405273}
+08/30/2021 17:07:33 - INFO - __main__ - Step 21830: {'lr': 0.00047817940217672315, 'samples': 4191360, 'steps': 21829, 'loss/train': 0.9340408444404602}
+08/30/2021 17:07:34 - INFO - __main__ - Step 21831: {'lr': 0.0004781772338375868, 'samples': 4191552, 'steps': 21830, 'loss/train': 1.8971073627471924}
+08/30/2021 17:07:34 - INFO - __main__ - Step 21832: {'lr': 0.0004781750653956374, 'samples': 4191744, 'steps': 21831, 'loss/train': 2.3435568809509277}
+08/30/2021 17:07:34 - INFO - __main__ - Step 21833: {'lr': 0.00047817289685087575, 'samples': 4191936, 'steps': 21832, 'loss/train': 0.17955322563648224}
+08/30/2021 17:07:35 - INFO - __main__ - Step 21834: {'lr': 0.00047817072820330287, 'samples': 4192128, 'steps': 21833, 'loss/train': 1.461944580078125}
+08/30/2021 17:07:36 - INFO - __main__ - Step 21835: {'lr': 0.0004781685594529199, 'samples': 4192320, 'steps': 21834, 'loss/train': 1.583033800125122}
+08/30/2021 17:07:36 - INFO - __main__ - Step 21836: {'lr': 0.00047816639059972767, 'samples': 4192512, 'steps': 21835, 'loss/train': 1.778618335723877}
+08/30/2021 17:07:37 - INFO - __main__ - Step 21837: {'lr': 0.00047816422164372713, 'samples': 4192704, 'steps': 21836, 'loss/train': 0.9923926591873169}
+08/30/2021 17:07:37 - INFO - __main__ - Step 21838: {'lr': 0.00047816205258491935, 'samples': 4192896, 'steps': 21837, 'loss/train': 1.445613145828247}
+08/30/2021 17:07:38 - INFO - __main__ - Step 21839: {'lr': 0.0004781598834233053, 'samples': 4193088, 'steps': 21838, 'loss/train': 1.4672938585281372}
+08/30/2021 17:07:40 - INFO - __main__ - Step 21840: {'lr': 0.0004781577141588859, 'samples': 4193280, 'steps': 21839, 'loss/train': 1.6474761962890625}
+08/30/2021 17:07:40 - INFO - __main__ - Step 21841: {'lr': 0.0004781555447916621, 'samples': 4193472, 'steps': 21840, 'loss/train': 1.7598116397857666}
+08/30/2021 17:07:40 - INFO - __main__ - Step 21842: {'lr': 0.000478153375321635, 'samples': 4193664, 'steps': 21841, 'loss/train': 0.5458323955535889}
+08/30/2021 17:07:41 - INFO - __main__ - Step 21843: {'lr': 0.0004781512057488055, 'samples': 4193856, 'steps': 21842, 'loss/train': 1.0545837879180908}
+08/30/2021 17:07:41 - INFO - __main__ - Step 21844: {'lr': 0.00047814903607317454, 'samples': 4194048, 'steps': 21843, 'loss/train': 1.4126092195510864}
+08/30/2021 17:07:43 - INFO - __main__ - Step 21845: {'lr': 0.00047814686629474323, 'samples': 4194240, 'steps': 21844, 'loss/train': 1.4072014093399048}
+08/30/2021 17:07:43 - INFO - __main__ - Step 21846: {'lr': 0.00047814469641351237, 'samples': 4194432, 'steps': 21845, 'loss/train': 1.3051915168762207}
+08/30/2021 17:07:43 - INFO - __main__ - Step 21847: {'lr': 0.0004781425264294831, 'samples': 4194624, 'steps': 21846, 'loss/train': 1.7459301948547363}
+08/30/2021 17:07:44 - INFO - __main__ - Step 21848: {'lr': 0.0004781403563426563, 'samples': 4194816, 'steps': 21847, 'loss/train': 1.3173969984054565}
+08/30/2021 17:07:44 - INFO - __main__ - Step 21849: {'lr': 0.00047813818615303295, 'samples': 4195008, 'steps': 21848, 'loss/train': 1.407995343208313}
+08/30/2021 17:07:46 - INFO - __main__ - Step 21850: {'lr': 0.00047813601586061414, 'samples': 4195200, 'steps': 21849, 'loss/train': 1.3913586139678955}
+08/30/2021 17:07:46 - INFO - __main__ - Step 21851: {'lr': 0.0004781338454654007, 'samples': 4195392, 'steps': 21850, 'loss/train': 1.4758920669555664}
+08/30/2021 17:07:46 - INFO - __main__ - Step 21852: {'lr': 0.00047813167496739363, 'samples': 4195584, 'steps': 21851, 'loss/train': 2.059255838394165}
+08/30/2021 17:07:47 - INFO - __main__ - Step 21853: {'lr': 0.00047812950436659405, 'samples': 4195776, 'steps': 21852, 'loss/train': 1.5771533250808716}
+08/30/2021 17:07:47 - INFO - __main__ - Step 21854: {'lr': 0.0004781273336630028, 'samples': 4195968, 'steps': 21853, 'loss/train': 2.0807173252105713}
+08/30/2021 17:07:49 - INFO - __main__ - Step 21855: {'lr': 0.00047812516285662086, 'samples': 4196160, 'steps': 21854, 'loss/train': 1.947556972503662}
+08/30/2021 17:07:50 - INFO - __main__ - Step 21856: {'lr': 0.00047812299194744924, 'samples': 4196352, 'steps': 21855, 'loss/train': 1.3786648511886597}
+08/30/2021 17:07:50 - INFO - __main__ - Step 21857: {'lr': 0.0004781208209354889, 'samples': 4196544, 'steps': 21856, 'loss/train': 0.08374021202325821}
+08/30/2021 17:07:50 - INFO - __main__ - Step 21858: {'lr': 0.00047811864982074087, 'samples': 4196736, 'steps': 21857, 'loss/train': 1.6885826587677002}
+08/30/2021 17:07:51 - INFO - __main__ - Step 21859: {'lr': 0.0004781164786032061, 'samples': 4196928, 'steps': 21858, 'loss/train': 0.2487347275018692}
+08/30/2021 17:07:51 - INFO - __main__ - Step 21860: {'lr': 0.0004781143072828856, 'samples': 4197120, 'steps': 21859, 'loss/train': 0.22958756983280182}
+08/30/2021 17:07:51 - INFO - __main__ - Step 21861: {'lr': 0.00047811213585978023, 'samples': 4197312, 'steps': 21860, 'loss/train': 1.1175928115844727}
+08/30/2021 17:07:53 - INFO - __main__ - Step 21862: {'lr': 0.0004781099643338911, 'samples': 4197504, 'steps': 21861, 'loss/train': 2.00122332572937}
+08/30/2021 17:07:54 - INFO - __main__ - Step 21863: {'lr': 0.00047810779270521914, 'samples': 4197696, 'steps': 21862, 'loss/train': 1.7286481857299805}
+08/30/2021 17:07:54 - INFO - __main__ - Step 21864: {'lr': 0.0004781056209737653, 'samples': 4197888, 'steps': 21863, 'loss/train': 0.907160222530365}
+08/30/2021 17:07:54 - INFO - __main__ - Step 21865: {'lr': 0.00047810344913953065, 'samples': 4198080, 'steps': 21864, 'loss/train': 2.0779623985290527}
+08/30/2021 17:07:55 - INFO - __main__ - Step 21866: {'lr': 0.0004781012772025161, 'samples': 4198272, 'steps': 21865, 'loss/train': 1.2352877855300903}
+08/30/2021 17:07:56 - INFO - __main__ - Step 21867: {'lr': 0.0004780991051627226, 'samples': 4198464, 'steps': 21866, 'loss/train': 0.18139822781085968}
+08/30/2021 17:07:57 - INFO - __main__ - Step 21868: {'lr': 0.0004780969330201511, 'samples': 4198656, 'steps': 21867, 'loss/train': 1.1665617227554321}
+08/30/2021 17:07:57 - INFO - __main__ - Step 21869: {'lr': 0.0004780947607748027, 'samples': 4198848, 'steps': 21868, 'loss/train': 1.9979071617126465}
+08/30/2021 17:07:57 - INFO - __main__ - Step 21870: {'lr': 0.00047809258842667837, 'samples': 4199040, 'steps': 21869, 'loss/train': 1.86331307888031}
+08/30/2021 17:07:58 - INFO - __main__ - Step 21871: {'lr': 0.000478090415975779, 'samples': 4199232, 'steps': 21870, 'loss/train': 1.8044943809509277}
+08/30/2021 17:07:58 - INFO - __main__ - Step 21872: {'lr': 0.00047808824342210565, 'samples': 4199424, 'steps': 21871, 'loss/train': 1.467484951019287}
+08/30/2021 17:08:00 - INFO - __main__ - Step 21873: {'lr': 0.0004780860707656592, 'samples': 4199616, 'steps': 21872, 'loss/train': 1.7816983461380005}
+08/30/2021 17:08:00 - INFO - __main__ - Step 21874: {'lr': 0.0004780838980064407, 'samples': 4199808, 'steps': 21873, 'loss/train': 1.5336304903030396}
+08/30/2021 17:08:01 - INFO - __main__ - Step 21875: {'lr': 0.00047808172514445115, 'samples': 4200000, 'steps': 21874, 'loss/train': 0.0895189642906189}
+08/30/2021 17:08:01 - INFO - __main__ - Step 21876: {'lr': 0.0004780795521796914, 'samples': 4200192, 'steps': 21875, 'loss/train': 1.2236469984054565}
+08/30/2021 17:08:01 - INFO - __main__ - Step 21877: {'lr': 0.0004780773791121626, 'samples': 4200384, 'steps': 21876, 'loss/train': 1.1106677055358887}
+08/30/2021 17:08:03 - INFO - __main__ - Step 21878: {'lr': 0.0004780752059418656, 'samples': 4200576, 'steps': 21877, 'loss/train': 1.9841495752334595}
+08/30/2021 17:08:03 - INFO - __main__ - Step 21879: {'lr': 0.0004780730326688015, 'samples': 4200768, 'steps': 21878, 'loss/train': 1.4923685789108276}
+08/30/2021 17:08:04 - INFO - __main__ - Step 21880: {'lr': 0.0004780708592929712, 'samples': 4200960, 'steps': 21879, 'loss/train': 1.6637871265411377}
+08/30/2021 17:08:04 - INFO - __main__ - Step 21881: {'lr': 0.0004780686858143756, 'samples': 4201152, 'steps': 21880, 'loss/train': 1.4183932542800903}
+08/30/2021 17:08:04 - INFO - __main__ - Step 21882: {'lr': 0.0004780665122330159, 'samples': 4201344, 'steps': 21881, 'loss/train': 1.4498711824417114}
+08/30/2021 17:08:06 - INFO - __main__ - Step 21883: {'lr': 0.00047806433854889285, 'samples': 4201536, 'steps': 21882, 'loss/train': 1.8202253580093384}
+08/30/2021 17:08:06 - INFO - __main__ - Step 21884: {'lr': 0.0004780621647620076, 'samples': 4201728, 'steps': 21883, 'loss/train': 1.8336007595062256}
+08/30/2021 17:08:07 - INFO - __main__ - Step 21885: {'lr': 0.00047805999087236097, 'samples': 4201920, 'steps': 21884, 'loss/train': 1.5845669507980347}
+08/30/2021 17:08:07 - INFO - __main__ - Step 21886: {'lr': 0.0004780578168799541, 'samples': 4202112, 'steps': 21885, 'loss/train': 2.684797763824463}
+08/30/2021 17:08:07 - INFO - __main__ - Step 21887: {'lr': 0.00047805564278478787, 'samples': 4202304, 'steps': 21886, 'loss/train': 1.976189136505127}
+08/30/2021 17:08:09 - INFO - __main__ - Step 21888: {'lr': 0.00047805346858686325, 'samples': 4202496, 'steps': 21887, 'loss/train': 0.3722270131111145}
+08/30/2021 17:08:09 - INFO - __main__ - Step 21889: {'lr': 0.0004780512942861813, 'samples': 4202688, 'steps': 21888, 'loss/train': 1.7283111810684204}
+08/30/2021 17:08:10 - INFO - __main__ - Step 21890: {'lr': 0.00047804911988274303, 'samples': 4202880, 'steps': 21889, 'loss/train': 1.2118431329727173}
+08/30/2021 17:08:10 - INFO - __main__ - Step 21891: {'lr': 0.00047804694537654927, 'samples': 4203072, 'steps': 21890, 'loss/train': 1.284872055053711}
+08/30/2021 17:08:11 - INFO - __main__ - Step 21892: {'lr': 0.00047804477076760106, 'samples': 4203264, 'steps': 21891, 'loss/train': 1.4628698825836182}
+08/30/2021 17:08:12 - INFO - __main__ - Step 21893: {'lr': 0.0004780425960558994, 'samples': 4203456, 'steps': 21892, 'loss/train': 1.623253583908081}
+08/30/2021 17:08:13 - INFO - __main__ - Step 21894: {'lr': 0.00047804042124144526, 'samples': 4203648, 'steps': 21893, 'loss/train': 1.5874764919281006}
+08/30/2021 17:08:13 - INFO - __main__ - Step 21895: {'lr': 0.00047803824632423967, 'samples': 4203840, 'steps': 21894, 'loss/train': 2.083956480026245}
+08/30/2021 17:08:13 - INFO - __main__ - Step 21896: {'lr': 0.0004780360713042835, 'samples': 4204032, 'steps': 21895, 'loss/train': 1.4926472902297974}
+08/30/2021 17:08:14 - INFO - __main__ - Step 21897: {'lr': 0.0004780338961815779, 'samples': 4204224, 'steps': 21896, 'loss/train': 1.7445399761199951}
+08/30/2021 17:08:16 - INFO - __main__ - Step 21898: {'lr': 0.00047803172095612365, 'samples': 4204416, 'steps': 21897, 'loss/train': 1.6326509714126587}
+08/30/2021 17:08:16 - INFO - __main__ - Step 21899: {'lr': 0.00047802954562792185, 'samples': 4204608, 'steps': 21898, 'loss/train': 1.4807627201080322}
+08/30/2021 17:08:16 - INFO - __main__ - Step 21900: {'lr': 0.0004780273701969734, 'samples': 4204800, 'steps': 21899, 'loss/train': 1.3924874067306519}
+08/30/2021 17:08:17 - INFO - __main__ - Step 21901: {'lr': 0.00047802519466327945, 'samples': 4204992, 'steps': 21900, 'loss/train': 1.9246954917907715}
+08/30/2021 17:08:17 - INFO - __main__ - Step 21902: {'lr': 0.00047802301902684076, 'samples': 4205184, 'steps': 21901, 'loss/train': 1.831890344619751}
+08/30/2021 17:08:17 - INFO - __main__ - Step 21903: {'lr': 0.0004780208432876585, 'samples': 4205376, 'steps': 21902, 'loss/train': 1.668404221534729}
+08/30/2021 17:08:19 - INFO - __main__ - Step 21904: {'lr': 0.00047801866744573353, 'samples': 4205568, 'steps': 21903, 'loss/train': 1.7075095176696777}
+08/30/2021 17:08:20 - INFO - __main__ - Step 21905: {'lr': 0.00047801649150106684, 'samples': 4205760, 'steps': 21904, 'loss/train': 1.4642846584320068}
+08/30/2021 17:08:20 - INFO - __main__ - Step 21906: {'lr': 0.00047801431545365947, 'samples': 4205952, 'steps': 21905, 'loss/train': 1.674008846282959}
+08/30/2021 17:08:20 - INFO - __main__ - Step 21907: {'lr': 0.0004780121393035124, 'samples': 4206144, 'steps': 21906, 'loss/train': 1.1540557146072388}
+08/30/2021 17:08:21 - INFO - __main__ - Step 21908: {'lr': 0.0004780099630506265, 'samples': 4206336, 'steps': 21907, 'loss/train': 1.779233694076538}
+08/30/2021 17:08:22 - INFO - __main__ - Step 21909: {'lr': 0.0004780077866950029, 'samples': 4206528, 'steps': 21908, 'loss/train': 0.6303631067276001}
+08/30/2021 17:08:23 - INFO - __main__ - Step 21910: {'lr': 0.00047800561023664246, 'samples': 4206720, 'steps': 21909, 'loss/train': 1.7209911346435547}
+08/30/2021 17:08:23 - INFO - __main__ - Step 21911: {'lr': 0.0004780034336755462, 'samples': 4206912, 'steps': 21910, 'loss/train': 1.7233561277389526}
+08/30/2021 17:08:23 - INFO - __main__ - Step 21912: {'lr': 0.00047800125701171517, 'samples': 4207104, 'steps': 21911, 'loss/train': 2.067147731781006}
+08/30/2021 17:08:24 - INFO - __main__ - Step 21913: {'lr': 0.00047799908024515026, 'samples': 4207296, 'steps': 21912, 'loss/train': 1.0405805110931396}
+08/30/2021 17:08:25 - INFO - __main__ - Step 21914: {'lr': 0.0004779969033758525, 'samples': 4207488, 'steps': 21913, 'loss/train': 1.331740379333496}
+08/30/2021 17:08:26 - INFO - __main__ - Step 21915: {'lr': 0.00047799472640382287, 'samples': 4207680, 'steps': 21914, 'loss/train': 1.4365123510360718}
+08/30/2021 17:08:26 - INFO - __main__ - Step 21916: {'lr': 0.0004779925493290623, 'samples': 4207872, 'steps': 21915, 'loss/train': 1.0958466529846191}
+08/30/2021 17:08:27 - INFO - __main__ - Step 21917: {'lr': 0.00047799037215157184, 'samples': 4208064, 'steps': 21916, 'loss/train': 1.3608423471450806}
+08/30/2021 17:08:27 - INFO - __main__ - Step 21918: {'lr': 0.0004779881948713524, 'samples': 4208256, 'steps': 21917, 'loss/train': 0.11266614496707916}
+08/30/2021 17:08:28 - INFO - __main__ - Step 21919: {'lr': 0.000477986017488405, 'samples': 4208448, 'steps': 21918, 'loss/train': 1.7626110315322876}
+08/30/2021 17:08:29 - INFO - __main__ - Step 21920: {'lr': 0.00047798384000273053, 'samples': 4208640, 'steps': 21919, 'loss/train': 0.45796090364456177}
+08/30/2021 17:08:29 - INFO - __main__ - Step 21921: {'lr': 0.0004779816624143302, 'samples': 4208832, 'steps': 21920, 'loss/train': 1.6454553604125977}
+08/30/2021 17:08:29 - INFO - __main__ - Step 21922: {'lr': 0.0004779794847232048, 'samples': 4209024, 'steps': 21921, 'loss/train': 2.0480148792266846}
+08/30/2021 17:08:30 - INFO - __main__ - Step 21923: {'lr': 0.0004779773069293554, 'samples': 4209216, 'steps': 21922, 'loss/train': 1.4627642631530762}
+08/30/2021 17:08:31 - INFO - __main__ - Step 21924: {'lr': 0.00047797512903278283, 'samples': 4209408, 'steps': 21923, 'loss/train': 1.6264673471450806}
+08/30/2021 17:08:32 - INFO - __main__ - Step 21925: {'lr': 0.0004779729510334883, 'samples': 4209600, 'steps': 21924, 'loss/train': 1.714000940322876}
+08/30/2021 17:08:32 - INFO - __main__ - Step 21926: {'lr': 0.0004779707729314726, 'samples': 4209792, 'steps': 21925, 'loss/train': 1.7017693519592285}
+08/30/2021 17:08:33 - INFO - __main__ - Step 21927: {'lr': 0.0004779685947267369, 'samples': 4209984, 'steps': 21926, 'loss/train': 2.342733383178711}
+08/30/2021 17:08:33 - INFO - __main__ - Step 21928: {'lr': 0.00047796641641928195, 'samples': 4210176, 'steps': 21927, 'loss/train': 1.6500569581985474}
+08/30/2021 17:08:33 - INFO - __main__ - Step 21929: {'lr': 0.00047796423800910894, 'samples': 4210368, 'steps': 21928, 'loss/train': 1.351326823234558}
+08/30/2021 17:08:35 - INFO - __main__ - Step 21930: {'lr': 0.00047796205949621873, 'samples': 4210560, 'steps': 21929, 'loss/train': 1.819567084312439}
+08/30/2021 17:08:35 - INFO - __main__ - Step 21931: {'lr': 0.00047795988088061224, 'samples': 4210752, 'steps': 21930, 'loss/train': 2.0995278358459473}
+08/30/2021 17:08:36 - INFO - __main__ - Step 21932: {'lr': 0.00047795770216229065, 'samples': 4210944, 'steps': 21931, 'loss/train': 1.5262372493743896}
+08/30/2021 17:08:36 - INFO - __main__ - Step 21933: {'lr': 0.0004779555233412548, 'samples': 4211136, 'steps': 21932, 'loss/train': 1.0073091983795166}
+08/30/2021 17:08:36 - INFO - __main__ - Step 21934: {'lr': 0.0004779533444175058, 'samples': 4211328, 'steps': 21933, 'loss/train': 1.5977104902267456}
+08/30/2021 17:08:38 - INFO - __main__ - Step 21935: {'lr': 0.00047795116539104445, 'samples': 4211520, 'steps': 21934, 'loss/train': 1.2242472171783447}
+08/30/2021 17:08:38 - INFO - __main__ - Step 21936: {'lr': 0.0004779489862618718, 'samples': 4211712, 'steps': 21935, 'loss/train': 1.6662166118621826}
+08/30/2021 17:08:39 - INFO - __main__ - Step 21937: {'lr': 0.00047794680702998893, 'samples': 4211904, 'steps': 21936, 'loss/train': 0.9240788817405701}
+08/30/2021 17:08:39 - INFO - __main__ - Step 21938: {'lr': 0.0004779446276953967, 'samples': 4212096, 'steps': 21937, 'loss/train': 0.2507948577404022}
+08/30/2021 17:08:39 - INFO - __main__ - Step 21939: {'lr': 0.00047794244825809614, 'samples': 4212288, 'steps': 21938, 'loss/train': 1.4775242805480957}
+08/30/2021 17:08:40 - INFO - __main__ - Step 21940: {'lr': 0.0004779402687180882, 'samples': 4212480, 'steps': 21939, 'loss/train': 1.4736164808273315}
+08/30/2021 17:08:41 - INFO - __main__ - Step 21941: {'lr': 0.00047793808907537394, 'samples': 4212672, 'steps': 21940, 'loss/train': 1.6653746366500854}
+08/30/2021 17:08:42 - INFO - __main__ - Step 21942: {'lr': 0.0004779359093299543, 'samples': 4212864, 'steps': 21941, 'loss/train': 1.8226401805877686}
+08/30/2021 17:08:42 - INFO - __main__ - Step 21943: {'lr': 0.00047793372948183024, 'samples': 4213056, 'steps': 21942, 'loss/train': 1.7302875518798828}
+08/30/2021 17:08:42 - INFO - __main__ - Step 21944: {'lr': 0.0004779315495310027, 'samples': 4213248, 'steps': 21943, 'loss/train': 1.924445629119873}
+08/30/2021 17:08:43 - INFO - __main__ - Step 21945: {'lr': 0.00047792936947747285, 'samples': 4213440, 'steps': 21944, 'loss/train': 1.7569037675857544}
+08/30/2021 17:08:44 - INFO - __main__ - Step 21946: {'lr': 0.00047792718932124147, 'samples': 4213632, 'steps': 21945, 'loss/train': 2.1364247798919678}
+08/30/2021 17:08:45 - INFO - __main__ - Step 21947: {'lr': 0.00047792500906230963, 'samples': 4213824, 'steps': 21946, 'loss/train': 1.0786246061325073}
+08/30/2021 17:08:45 - INFO - __main__ - Step 21948: {'lr': 0.00047792282870067827, 'samples': 4214016, 'steps': 21947, 'loss/train': 0.824955403804779}
+08/30/2021 17:08:46 - INFO - __main__ - Step 21949: {'lr': 0.0004779206482363484, 'samples': 4214208, 'steps': 21948, 'loss/train': 2.175302267074585}
+08/30/2021 17:08:46 - INFO - __main__ - Step 21950: {'lr': 0.000477918467669321, 'samples': 4214400, 'steps': 21949, 'loss/train': 1.7836651802062988}
+08/30/2021 17:08:48 - INFO - __main__ - Step 21951: {'lr': 0.0004779162869995971, 'samples': 4214592, 'steps': 21950, 'loss/train': 1.2974724769592285}
+08/30/2021 17:08:49 - INFO - __main__ - Step 21952: {'lr': 0.00047791410622717757, 'samples': 4214784, 'steps': 21951, 'loss/train': 1.5132735967636108}
+08/30/2021 17:08:49 - INFO - __main__ - Step 21953: {'lr': 0.0004779119253520635, 'samples': 4214976, 'steps': 21952, 'loss/train': 1.8830792903900146}
+08/30/2021 17:08:49 - INFO - __main__ - Step 21954: {'lr': 0.0004779097443742558, 'samples': 4215168, 'steps': 21953, 'loss/train': 1.4688997268676758}
+08/30/2021 17:08:50 - INFO - __main__ - Step 21955: {'lr': 0.0004779075632937556, 'samples': 4215360, 'steps': 21954, 'loss/train': 1.3895879983901978}
+08/30/2021 17:08:51 - INFO - __main__ - Step 21956: {'lr': 0.00047790538211056366, 'samples': 4215552, 'steps': 21955, 'loss/train': 1.9342215061187744}
+08/30/2021 17:08:52 - INFO - __main__ - Step 21957: {'lr': 0.00047790320082468106, 'samples': 4215744, 'steps': 21956, 'loss/train': 1.418033242225647}
+08/30/2021 17:08:52 - INFO - __main__ - Step 21958: {'lr': 0.00047790101943610884, 'samples': 4215936, 'steps': 21957, 'loss/train': 1.506151795387268}
+08/30/2021 17:08:53 - INFO - __main__ - Step 21959: {'lr': 0.000477898837944848, 'samples': 4216128, 'steps': 21958, 'loss/train': 1.7700694799423218}
+08/30/2021 17:08:53 - INFO - __main__ - Step 21960: {'lr': 0.0004778966563508994, 'samples': 4216320, 'steps': 21959, 'loss/train': 0.7527241110801697}
+08/30/2021 17:08:53 - INFO - __main__ - Step 21961: {'lr': 0.00047789447465426406, 'samples': 4216512, 'steps': 21960, 'loss/train': 1.2421972751617432}
+08/30/2021 17:08:55 - INFO - __main__ - Step 21962: {'lr': 0.000477892292854943, 'samples': 4216704, 'steps': 21961, 'loss/train': 2.6127634048461914}
+08/30/2021 17:08:55 - INFO - __main__ - Step 21963: {'lr': 0.00047789011095293723, 'samples': 4216896, 'steps': 21962, 'loss/train': 1.4230536222457886}
+08/30/2021 17:08:56 - INFO - __main__ - Step 21964: {'lr': 0.0004778879289482476, 'samples': 4217088, 'steps': 21963, 'loss/train': 1.4664710760116577}
+08/30/2021 17:08:56 - INFO - __main__ - Step 21965: {'lr': 0.00047788574684087527, 'samples': 4217280, 'steps': 21964, 'loss/train': 0.14407892525196075}
+08/30/2021 17:08:56 - INFO - __main__ - Step 21966: {'lr': 0.0004778835646308211, 'samples': 4217472, 'steps': 21965, 'loss/train': 1.5930671691894531}
+08/30/2021 17:08:58 - INFO - __main__ - Step 21967: {'lr': 0.0004778813823180861, 'samples': 4217664, 'steps': 21966, 'loss/train': 1.876437783241272}
+08/30/2021 17:08:58 - INFO - __main__ - Step 21968: {'lr': 0.0004778791999026713, 'samples': 4217856, 'steps': 21967, 'loss/train': 1.6596248149871826}
+08/30/2021 17:08:59 - INFO - __main__ - Step 21969: {'lr': 0.0004778770173845777, 'samples': 4218048, 'steps': 21968, 'loss/train': 1.4142649173736572}
+08/30/2021 17:08:59 - INFO - __main__ - Step 21970: {'lr': 0.00047787483476380613, 'samples': 4218240, 'steps': 21969, 'loss/train': 1.1690462827682495}
+08/30/2021 17:08:59 - INFO - __main__ - Step 21971: {'lr': 0.0004778726520403577, 'samples': 4218432, 'steps': 21970, 'loss/train': 1.791285514831543}
+08/30/2021 17:09:01 - INFO - __main__ - Step 21972: {'lr': 0.00047787046921423336, 'samples': 4218624, 'steps': 21971, 'loss/train': 1.278337836265564}
+08/30/2021 17:09:01 - INFO - __main__ - Step 21973: {'lr': 0.00047786828628543416, 'samples': 4218816, 'steps': 21972, 'loss/train': 2.0375607013702393}
+08/30/2021 17:09:02 - INFO - __main__ - Step 21974: {'lr': 0.00047786610325396096, 'samples': 4219008, 'steps': 21973, 'loss/train': 1.6423488855361938}
+08/30/2021 17:09:02 - INFO - __main__ - Step 21975: {'lr': 0.0004778639201198149, 'samples': 4219200, 'steps': 21974, 'loss/train': 1.9463797807693481}
+08/30/2021 17:09:03 - INFO - __main__ - Step 21976: {'lr': 0.00047786173688299684, 'samples': 4219392, 'steps': 21975, 'loss/train': 2.127964496612549}
+08/30/2021 17:09:03 - INFO - __main__ - Step 21977: {'lr': 0.00047785955354350776, 'samples': 4219584, 'steps': 21976, 'loss/train': 1.3553804159164429}
+08/30/2021 17:09:04 - INFO - __main__ - Step 21978: {'lr': 0.00047785737010134865, 'samples': 4219776, 'steps': 21977, 'loss/train': 1.9687639474868774}
+08/30/2021 17:09:05 - INFO - __main__ - Step 21979: {'lr': 0.0004778551865565206, 'samples': 4219968, 'steps': 21978, 'loss/train': 0.9866222739219666}
+08/30/2021 17:09:05 - INFO - __main__ - Step 21980: {'lr': 0.00047785300290902446, 'samples': 4220160, 'steps': 21979, 'loss/train': 1.6148606538772583}
+08/30/2021 17:09:05 - INFO - __main__ - Step 21981: {'lr': 0.0004778508191588613, 'samples': 4220352, 'steps': 21980, 'loss/train': 1.819076657295227}
+08/30/2021 17:09:06 - INFO - __main__ - Step 21982: {'lr': 0.00047784863530603213, 'samples': 4220544, 'steps': 21981, 'loss/train': 1.618833065032959}
+08/30/2021 17:09:07 - INFO - __main__ - Step 21983: {'lr': 0.0004778464513505378, 'samples': 4220736, 'steps': 21982, 'loss/train': 1.7028850317001343}
+08/30/2021 17:09:08 - INFO - __main__ - Step 21984: {'lr': 0.0004778442672923794, 'samples': 4220928, 'steps': 21983, 'loss/train': 1.8046437501907349}
+08/30/2021 17:09:08 - INFO - __main__ - Step 21985: {'lr': 0.0004778420831315579, 'samples': 4221120, 'steps': 21984, 'loss/train': 1.4114447832107544}
+08/30/2021 17:09:09 - INFO - __main__ - Step 21986: {'lr': 0.0004778398988680743, 'samples': 4221312, 'steps': 21985, 'loss/train': 1.4717018604278564}
+08/30/2021 17:09:09 - INFO - __main__ - Step 21987: {'lr': 0.00047783771450192946, 'samples': 4221504, 'steps': 21986, 'loss/train': 1.534753441810608}
+08/30/2021 17:09:10 - INFO - __main__ - Step 21988: {'lr': 0.00047783553003312456, 'samples': 4221696, 'steps': 21987, 'loss/train': 1.4537556171417236}
+08/30/2021 17:09:11 - INFO - __main__ - Step 21989: {'lr': 0.00047783334546166046, 'samples': 4221888, 'steps': 21988, 'loss/train': 1.511865258216858}
+08/30/2021 17:09:11 - INFO - __main__ - Step 21990: {'lr': 0.0004778311607875382, 'samples': 4222080, 'steps': 21989, 'loss/train': 1.6200644969940186}
+08/30/2021 17:09:12 - INFO - __main__ - Step 21991: {'lr': 0.0004778289760107587, 'samples': 4222272, 'steps': 21990, 'loss/train': 1.7906439304351807}
+08/30/2021 17:09:12 - INFO - __main__ - Step 21992: {'lr': 0.00047782679113132293, 'samples': 4222464, 'steps': 21991, 'loss/train': 0.6283571720123291}
+08/30/2021 17:09:13 - INFO - __main__ - Step 21993: {'lr': 0.00047782460614923195, 'samples': 4222656, 'steps': 21992, 'loss/train': 1.5765588283538818}
+08/30/2021 17:09:14 - INFO - __main__ - Step 21994: {'lr': 0.00047782242106448675, 'samples': 4222848, 'steps': 21993, 'loss/train': 2.792832851409912}
+08/30/2021 17:09:14 - INFO - __main__ - Step 21995: {'lr': 0.00047782023587708826, 'samples': 4223040, 'steps': 21994, 'loss/train': 1.3331061601638794}
+08/30/2021 17:09:15 - INFO - __main__ - Step 21996: {'lr': 0.0004778180505870375, 'samples': 4223232, 'steps': 21995, 'loss/train': 1.5808993577957153}
+08/30/2021 17:09:15 - INFO - __main__ - Step 21997: {'lr': 0.0004778158651943355, 'samples': 4223424, 'steps': 21996, 'loss/train': 1.5907156467437744}
+08/30/2021 17:09:16 - INFO - __main__ - Step 21998: {'lr': 0.0004778136796989831, 'samples': 4223616, 'steps': 21997, 'loss/train': 1.80043363571167}
+08/30/2021 17:09:17 - INFO - __main__ - Step 21999: {'lr': 0.0004778114941009814, 'samples': 4223808, 'steps': 21998, 'loss/train': 1.2608749866485596}
+08/30/2021 17:09:17 - INFO - __main__ - Step 22000: {'lr': 0.0004778093084003313, 'samples': 4224000, 'steps': 21999, 'loss/train': 0.8539326190948486}
+08/30/2021 17:09:18 - INFO - __main__ - Step 22001: {'lr': 0.00047780712259703394, 'samples': 4224192, 'steps': 22000, 'loss/train': 1.4201937913894653}
+08/30/2021 17:09:18 - INFO - __main__ - Step 22002: {'lr': 0.00047780493669109017, 'samples': 4224384, 'steps': 22001, 'loss/train': 1.4182732105255127}
+08/30/2021 17:09:20 - INFO - __main__ - Step 22003: {'lr': 0.000477802750682501, 'samples': 4224576, 'steps': 22002, 'loss/train': 1.5219247341156006}
+08/30/2021 17:09:20 - INFO - __main__ - Step 22004: {'lr': 0.0004778005645712674, 'samples': 4224768, 'steps': 22003, 'loss/train': 1.7167892456054688}
+08/30/2021 17:09:20 - INFO - __main__ - Step 22005: {'lr': 0.00047779837835739043, 'samples': 4224960, 'steps': 22004, 'loss/train': 0.8052094578742981}
+08/30/2021 17:09:21 - INFO - __main__ - Step 22006: {'lr': 0.000477796192040871, 'samples': 4225152, 'steps': 22005, 'loss/train': 1.5867869853973389}
+08/30/2021 17:09:21 - INFO - __main__ - Step 22007: {'lr': 0.00047779400562171016, 'samples': 4225344, 'steps': 22006, 'loss/train': 1.7160247564315796}
+08/30/2021 17:09:21 - INFO - __main__ - Step 22008: {'lr': 0.00047779181909990876, 'samples': 4225536, 'steps': 22007, 'loss/train': 1.509312391281128}
+08/30/2021 17:09:23 - INFO - __main__ - Step 22009: {'lr': 0.000477789632475468, 'samples': 4225728, 'steps': 22008, 'loss/train': 1.5153206586837769}
+08/30/2021 17:09:24 - INFO - __main__ - Step 22010: {'lr': 0.00047778744574838864, 'samples': 4225920, 'steps': 22009, 'loss/train': 2.194248676300049}
+08/30/2021 17:09:24 - INFO - __main__ - Step 22011: {'lr': 0.00047778525891867187, 'samples': 4226112, 'steps': 22010, 'loss/train': 2.2969167232513428}
+08/30/2021 17:09:25 - INFO - __main__ - Step 22012: {'lr': 0.00047778307198631856, 'samples': 4226304, 'steps': 22011, 'loss/train': 1.2941278219223022}
+08/30/2021 17:09:25 - INFO - __main__ - Step 22013: {'lr': 0.00047778088495132963, 'samples': 4226496, 'steps': 22012, 'loss/train': 1.1696702241897583}
+08/30/2021 17:09:26 - INFO - __main__ - Step 22014: {'lr': 0.0004777786978137062, 'samples': 4226688, 'steps': 22013, 'loss/train': 1.2197378873825073}
+08/30/2021 17:09:27 - INFO - __main__ - Step 22015: {'lr': 0.00047777651057344915, 'samples': 4226880, 'steps': 22014, 'loss/train': 1.7497295141220093}
+08/30/2021 17:09:27 - INFO - __main__ - Step 22016: {'lr': 0.0004777743232305596, 'samples': 4227072, 'steps': 22015, 'loss/train': 1.6060482263565063}
+08/30/2021 17:09:28 - INFO - __main__ - Step 22017: {'lr': 0.00047777213578503844, 'samples': 4227264, 'steps': 22016, 'loss/train': 1.1682275533676147}
+08/30/2021 17:09:28 - INFO - __main__ - Step 22018: {'lr': 0.0004777699482368867, 'samples': 4227456, 'steps': 22017, 'loss/train': 1.8457088470458984}
+08/30/2021 17:09:29 - INFO - __main__ - Step 22019: {'lr': 0.00047776776058610525, 'samples': 4227648, 'steps': 22018, 'loss/train': 2.1102287769317627}
+08/30/2021 17:09:30 - INFO - __main__ - Step 22020: {'lr': 0.0004777655728326952, 'samples': 4227840, 'steps': 22019, 'loss/train': 1.5147463083267212}
+08/30/2021 17:09:30 - INFO - __main__ - Step 22021: {'lr': 0.0004777633849766575, 'samples': 4228032, 'steps': 22020, 'loss/train': 2.064711570739746}
+08/30/2021 17:09:31 - INFO - __main__ - Step 22022: {'lr': 0.00047776119701799317, 'samples': 4228224, 'steps': 22021, 'loss/train': 1.7333000898361206}
+08/30/2021 17:09:31 - INFO - __main__ - Step 22023: {'lr': 0.0004777590089567031, 'samples': 4228416, 'steps': 22022, 'loss/train': 1.8635295629501343}
+08/30/2021 17:09:33 - INFO - __main__ - Step 22024: {'lr': 0.00047775682079278836, 'samples': 4228608, 'steps': 22023, 'loss/train': 1.6678019762039185}
+08/30/2021 17:09:33 - INFO - __main__ - Step 22025: {'lr': 0.0004777546325262499, 'samples': 4228800, 'steps': 22024, 'loss/train': 1.0993646383285522}
+08/30/2021 17:09:34 - INFO - __main__ - Step 22026: {'lr': 0.00047775244415708873, 'samples': 4228992, 'steps': 22025, 'loss/train': 1.463771104812622}
+08/30/2021 17:09:34 - INFO - __main__ - Step 22027: {'lr': 0.0004777502556853058, 'samples': 4229184, 'steps': 22026, 'loss/train': 0.112718865275383}
+08/30/2021 17:09:34 - INFO - __main__ - Step 22028: {'lr': 0.00047774806711090213, 'samples': 4229376, 'steps': 22027, 'loss/train': 1.41226065158844}
+08/30/2021 17:09:36 - INFO - __main__ - Step 22029: {'lr': 0.0004777458784338787, 'samples': 4229568, 'steps': 22028, 'loss/train': 1.7554728984832764}
+08/30/2021 17:09:36 - INFO - __main__ - Step 22030: {'lr': 0.00047774368965423653, 'samples': 4229760, 'steps': 22029, 'loss/train': 1.7022331953048706}
+08/30/2021 17:09:36 - INFO - __main__ - Step 22031: {'lr': 0.0004777415007719765, 'samples': 4229952, 'steps': 22030, 'loss/train': 1.380596399307251}
+08/30/2021 17:09:37 - INFO - __main__ - Step 22032: {'lr': 0.00047773931178709975, 'samples': 4230144, 'steps': 22031, 'loss/train': 1.567521333694458}
+08/30/2021 17:09:37 - INFO - __main__ - Step 22033: {'lr': 0.00047773712269960714, 'samples': 4230336, 'steps': 22032, 'loss/train': 1.3691271543502808}
+08/30/2021 17:09:39 - INFO - __main__ - Step 22034: {'lr': 0.00047773493350949963, 'samples': 4230528, 'steps': 22033, 'loss/train': 1.634064793586731}
+08/30/2021 17:09:39 - INFO - __main__ - Step 22035: {'lr': 0.00047773274421677834, 'samples': 4230720, 'steps': 22034, 'loss/train': 0.20929567515850067}
+08/30/2021 17:09:39 - INFO - __main__ - Step 22036: {'lr': 0.0004777305548214442, 'samples': 4230912, 'steps': 22035, 'loss/train': 1.8736116886138916}
+08/30/2021 17:09:40 - INFO - __main__ - Step 22037: {'lr': 0.0004777283653234982, 'samples': 4231104, 'steps': 22036, 'loss/train': 1.4712235927581787}
+08/30/2021 17:09:40 - INFO - __main__ - Step 22038: {'lr': 0.00047772617572294123, 'samples': 4231296, 'steps': 22037, 'loss/train': 1.524675726890564}
+08/30/2021 17:09:41 - INFO - __main__ - Step 22039: {'lr': 0.0004777239860197744, 'samples': 4231488, 'steps': 22038, 'loss/train': 1.3708162307739258}
+08/30/2021 17:09:42 - INFO - __main__ - Step 22040: {'lr': 0.0004777217962139987, 'samples': 4231680, 'steps': 22039, 'loss/train': 1.613618016242981}
+08/30/2021 17:09:43 - INFO - __main__ - Step 22041: {'lr': 0.000477719606305615, 'samples': 4231872, 'steps': 22040, 'loss/train': 1.3604282140731812}
+08/30/2021 17:09:43 - INFO - __main__ - Step 22042: {'lr': 0.0004777174162946244, 'samples': 4232064, 'steps': 22041, 'loss/train': 1.1682003736495972}
+08/30/2021 17:09:43 - INFO - __main__ - Step 22043: {'lr': 0.0004777152261810279, 'samples': 4232256, 'steps': 22042, 'loss/train': 1.8293678760528564}
+08/30/2021 17:09:44 - INFO - __main__ - Step 22044: {'lr': 0.0004777130359648263, 'samples': 4232448, 'steps': 22043, 'loss/train': 0.9608367681503296}
+08/30/2021 17:09:45 - INFO - __main__ - Step 22045: {'lr': 0.0004777108456460208, 'samples': 4232640, 'steps': 22044, 'loss/train': 1.5555115938186646}
+08/30/2021 17:09:46 - INFO - __main__ - Step 22046: {'lr': 0.00047770865522461233, 'samples': 4232832, 'steps': 22045, 'loss/train': 1.3933627605438232}
+08/30/2021 17:09:46 - INFO - __main__ - Step 22047: {'lr': 0.0004777064647006018, 'samples': 4233024, 'steps': 22046, 'loss/train': 2.507596969604492}
+08/30/2021 17:09:46 - INFO - __main__ - Step 22048: {'lr': 0.0004777042740739903, 'samples': 4233216, 'steps': 22047, 'loss/train': 1.6716880798339844}
+08/30/2021 17:09:47 - INFO - __main__ - Step 22049: {'lr': 0.0004777020833447787, 'samples': 4233408, 'steps': 22048, 'loss/train': 0.8102055191993713}
+08/30/2021 17:09:48 - INFO - __main__ - Step 22050: {'lr': 0.0004776998925129681, 'samples': 4233600, 'steps': 22049, 'loss/train': 1.6614139080047607}
+08/30/2021 17:09:49 - INFO - __main__ - Step 22051: {'lr': 0.0004776977015785595, 'samples': 4233792, 'steps': 22050, 'loss/train': 1.5732864141464233}
+08/30/2021 17:09:49 - INFO - __main__ - Step 22052: {'lr': 0.0004776955105415537, 'samples': 4233984, 'steps': 22051, 'loss/train': 1.7298601865768433}
+08/30/2021 17:09:50 - INFO - __main__ - Step 22053: {'lr': 0.00047769331940195194, 'samples': 4234176, 'steps': 22052, 'loss/train': 1.2789348363876343}
+08/30/2021 17:09:50 - INFO - __main__ - Step 22054: {'lr': 0.00047769112815975503, 'samples': 4234368, 'steps': 22053, 'loss/train': 2.008350133895874}
+08/30/2021 17:09:50 - INFO - __main__ - Step 22055: {'lr': 0.00047768893681496397, 'samples': 4234560, 'steps': 22054, 'loss/train': 1.403056025505066}
+08/30/2021 17:09:52 - INFO - __main__ - Step 22056: {'lr': 0.00047768674536757984, 'samples': 4234752, 'steps': 22055, 'loss/train': 1.2862383127212524}
+08/30/2021 17:09:53 - INFO - __main__ - Step 22057: {'lr': 0.00047768455381760357, 'samples': 4234944, 'steps': 22056, 'loss/train': 2.275675058364868}
+08/30/2021 17:09:53 - INFO - __main__ - Step 22058: {'lr': 0.00047768236216503613, 'samples': 4235136, 'steps': 22057, 'loss/train': 1.7179292440414429}
+08/30/2021 17:09:53 - INFO - __main__ - Step 22059: {'lr': 0.00047768017040987856, 'samples': 4235328, 'steps': 22058, 'loss/train': 3.2524068355560303}
+08/30/2021 17:09:54 - INFO - __main__ - Step 22060: {'lr': 0.0004776779785521318, 'samples': 4235520, 'steps': 22059, 'loss/train': 1.4430495500564575}
+08/30/2021 17:09:56 - INFO - __main__ - Step 22061: {'lr': 0.0004776757865917969, 'samples': 4235712, 'steps': 22060, 'loss/train': 1.617902159690857}
+08/30/2021 17:09:56 - INFO - __main__ - Step 22062: {'lr': 0.0004776735945288747, 'samples': 4235904, 'steps': 22061, 'loss/train': 1.906358242034912}
+08/30/2021 17:09:56 - INFO - __main__ - Step 22063: {'lr': 0.00047767140236336635, 'samples': 4236096, 'steps': 22062, 'loss/train': 2.3241195678710938}
+08/30/2021 17:09:57 - INFO - __main__ - Step 22064: {'lr': 0.00047766921009527284, 'samples': 4236288, 'steps': 22063, 'loss/train': 1.8307621479034424}
+08/30/2021 17:09:57 - INFO - __main__ - Step 22065: {'lr': 0.00047766701772459505, 'samples': 4236480, 'steps': 22064, 'loss/train': 1.2524582147598267}
+08/30/2021 17:09:57 - INFO - __main__ - Step 22066: {'lr': 0.00047766482525133405, 'samples': 4236672, 'steps': 22065, 'loss/train': 1.5745614767074585}
+08/30/2021 17:09:59 - INFO - __main__ - Step 22067: {'lr': 0.00047766263267549073, 'samples': 4236864, 'steps': 22066, 'loss/train': 1.3962738513946533}
+08/30/2021 17:09:59 - INFO - __main__ - Step 22068: {'lr': 0.0004776604399970661, 'samples': 4237056, 'steps': 22067, 'loss/train': 1.452945590019226}
+08/30/2021 17:10:00 - INFO - __main__ - Step 22069: {'lr': 0.0004776582472160613, 'samples': 4237248, 'steps': 22068, 'loss/train': 1.9384219646453857}
+08/30/2021 17:10:00 - INFO - __main__ - Step 22070: {'lr': 0.0004776560543324772, 'samples': 4237440, 'steps': 22069, 'loss/train': 1.5681068897247314}
+08/30/2021 17:10:00 - INFO - __main__ - Step 22071: {'lr': 0.0004776538613463147, 'samples': 4237632, 'steps': 22070, 'loss/train': 2.144890069961548}
+08/30/2021 17:10:02 - INFO - __main__ - Step 22072: {'lr': 0.00047765166825757487, 'samples': 4237824, 'steps': 22071, 'loss/train': 1.6291849613189697}
+08/30/2021 17:10:03 - INFO - __main__ - Step 22073: {'lr': 0.00047764947506625887, 'samples': 4238016, 'steps': 22072, 'loss/train': 1.8141212463378906}
+08/30/2021 17:10:03 - INFO - __main__ - Step 22074: {'lr': 0.00047764728177236736, 'samples': 4238208, 'steps': 22073, 'loss/train': 2.9622011184692383}
+08/30/2021 17:10:03 - INFO - __main__ - Step 22075: {'lr': 0.0004776450883759016, 'samples': 4238400, 'steps': 22074, 'loss/train': 1.679767370223999}
+08/30/2021 17:10:04 - INFO - __main__ - Step 22076: {'lr': 0.0004776428948768625, 'samples': 4238592, 'steps': 22075, 'loss/train': 0.6758951544761658}
+08/30/2021 17:10:06 - INFO - __main__ - Step 22077: {'lr': 0.00047764070127525096, 'samples': 4238784, 'steps': 22076, 'loss/train': 1.738405704498291}
+08/30/2021 17:10:07 - INFO - __main__ - Step 22078: {'lr': 0.00047763850757106803, 'samples': 4238976, 'steps': 22077, 'loss/train': 1.8547416925430298}
+08/30/2021 17:10:07 - INFO - __main__ - Step 22079: {'lr': 0.0004776363137643147, 'samples': 4239168, 'steps': 22078, 'loss/train': 1.784899115562439}
+08/30/2021 17:10:07 - INFO - __main__ - Step 22080: {'lr': 0.000477634119854992, 'samples': 4239360, 'steps': 22079, 'loss/train': 1.3763948678970337}
+08/30/2021 17:10:08 - INFO - __main__ - Step 22081: {'lr': 0.00047763192584310087, 'samples': 4239552, 'steps': 22080, 'loss/train': 0.8035991787910461}
+08/30/2021 17:10:08 - INFO - __main__ - Step 22082: {'lr': 0.0004776297317286423, 'samples': 4239744, 'steps': 22081, 'loss/train': 0.6462414264678955}
+08/30/2021 17:10:09 - INFO - __main__ - Step 22083: {'lr': 0.00047762753751161725, 'samples': 4239936, 'steps': 22082, 'loss/train': 1.702309489250183}
+08/30/2021 17:10:10 - INFO - __main__ - Step 22084: {'lr': 0.0004776253431920268, 'samples': 4240128, 'steps': 22083, 'loss/train': 1.4913526773452759}
+08/30/2021 17:10:10 - INFO - __main__ - Step 22085: {'lr': 0.00047762314876987185, 'samples': 4240320, 'steps': 22084, 'loss/train': 0.9840775728225708}
+08/30/2021 17:10:11 - INFO - __main__ - Step 22086: {'lr': 0.0004776209542451534, 'samples': 4240512, 'steps': 22085, 'loss/train': 1.5377213954925537}
+08/30/2021 17:10:11 - INFO - __main__ - Step 22087: {'lr': 0.0004776187596178725, 'samples': 4240704, 'steps': 22086, 'loss/train': 2.0228564739227295}
+08/30/2021 17:10:12 - INFO - __main__ - Step 22088: {'lr': 0.00047761656488803006, 'samples': 4240896, 'steps': 22087, 'loss/train': 1.4768586158752441}
+08/30/2021 17:10:13 - INFO - __main__ - Step 22089: {'lr': 0.00047761437005562716, 'samples': 4241088, 'steps': 22088, 'loss/train': 1.665913462638855}
+08/30/2021 17:10:13 - INFO - __main__ - Step 22090: {'lr': 0.00047761217512066475, 'samples': 4241280, 'steps': 22089, 'loss/train': 2.0579636096954346}
+08/30/2021 17:10:14 - INFO - __main__ - Step 22091: {'lr': 0.0004776099800831437, 'samples': 4241472, 'steps': 22090, 'loss/train': 0.23284082114696503}
+08/30/2021 17:10:14 - INFO - __main__ - Step 22092: {'lr': 0.0004776077849430652, 'samples': 4241664, 'steps': 22091, 'loss/train': 1.666582465171814}
+08/30/2021 17:10:16 - INFO - __main__ - Step 22093: {'lr': 0.0004776055897004301, 'samples': 4241856, 'steps': 22092, 'loss/train': 1.771843433380127}
+08/30/2021 17:10:16 - INFO - __main__ - Step 22094: {'lr': 0.0004776033943552395, 'samples': 4242048, 'steps': 22093, 'loss/train': 2.050999402999878}
+08/30/2021 17:10:16 - INFO - __main__ - Step 22095: {'lr': 0.0004776011989074943, 'samples': 4242240, 'steps': 22094, 'loss/train': 2.2498724460601807}
+08/30/2021 17:10:17 - INFO - __main__ - Step 22096: {'lr': 0.00047759900335719543, 'samples': 4242432, 'steps': 22095, 'loss/train': 1.6556576490402222}
+08/30/2021 17:10:17 - INFO - __main__ - Step 22097: {'lr': 0.00047759680770434405, 'samples': 4242624, 'steps': 22096, 'loss/train': 1.60176420211792}
+08/30/2021 17:10:18 - INFO - __main__ - Step 22098: {'lr': 0.00047759461194894103, 'samples': 4242816, 'steps': 22097, 'loss/train': 1.6094857454299927}
+08/30/2021 17:10:19 - INFO - __main__ - Step 22099: {'lr': 0.00047759241609098734, 'samples': 4243008, 'steps': 22098, 'loss/train': 1.4421844482421875}
+08/30/2021 17:10:19 - INFO - __main__ - Step 22100: {'lr': 0.00047759022013048417, 'samples': 4243200, 'steps': 22099, 'loss/train': 1.1010295152664185}
+08/30/2021 17:10:20 - INFO - __main__ - Step 22101: {'lr': 0.00047758802406743217, 'samples': 4243392, 'steps': 22100, 'loss/train': 1.3330720663070679}
+08/30/2021 17:10:20 - INFO - __main__ - Step 22102: {'lr': 0.0004775858279018326, 'samples': 4243584, 'steps': 22101, 'loss/train': 1.3838764429092407}
+08/30/2021 17:10:21 - INFO - __main__ - Step 22103: {'lr': 0.0004775836316336864, 'samples': 4243776, 'steps': 22102, 'loss/train': 1.976652979850769}
+08/30/2021 17:10:22 - INFO - __main__ - Step 22104: {'lr': 0.00047758143526299446, 'samples': 4243968, 'steps': 22103, 'loss/train': 1.4156880378723145}
+08/30/2021 17:10:22 - INFO - __main__ - Step 22105: {'lr': 0.0004775792387897579, 'samples': 4244160, 'steps': 22104, 'loss/train': 2.0119359493255615}
+08/30/2021 17:10:23 - INFO - __main__ - Step 22106: {'lr': 0.0004775770422139776, 'samples': 4244352, 'steps': 22105, 'loss/train': 1.8513189554214478}
+08/30/2021 17:10:23 - INFO - __main__ - Step 22107: {'lr': 0.00047757484553565465, 'samples': 4244544, 'steps': 22106, 'loss/train': 1.8542102575302124}
+08/30/2021 17:10:23 - INFO - __main__ - Step 22108: {'lr': 0.00047757264875478996, 'samples': 4244736, 'steps': 22107, 'loss/train': 2.1568729877471924}
+08/30/2021 17:10:25 - INFO - __main__ - Step 22109: {'lr': 0.0004775704518713845, 'samples': 4244928, 'steps': 22108, 'loss/train': 1.6737103462219238}
+08/30/2021 17:10:25 - INFO - __main__ - Step 22110: {'lr': 0.0004775682548854394, 'samples': 4245120, 'steps': 22109, 'loss/train': 2.2088537216186523}
+08/30/2021 17:10:25 - INFO - __main__ - Step 22111: {'lr': 0.0004775660577969555, 'samples': 4245312, 'steps': 22110, 'loss/train': 1.5327880382537842}
+08/30/2021 17:10:26 - INFO - __main__ - Step 22112: {'lr': 0.0004775638606059338, 'samples': 4245504, 'steps': 22111, 'loss/train': 3.1570706367492676}
+08/30/2021 17:10:26 - INFO - __main__ - Step 22113: {'lr': 0.00047756166331237545, 'samples': 4245696, 'steps': 22112, 'loss/train': 1.7394119501113892}
+08/30/2021 17:10:28 - INFO - __main__ - Step 22114: {'lr': 0.00047755946591628126, 'samples': 4245888, 'steps': 22113, 'loss/train': 1.5016783475875854}
+08/30/2021 17:10:28 - INFO - __main__ - Step 22115: {'lr': 0.00047755726841765224, 'samples': 4246080, 'steps': 22114, 'loss/train': 1.730542540550232}
+08/30/2021 17:10:28 - INFO - __main__ - Step 22116: {'lr': 0.0004775550708164895, 'samples': 4246272, 'steps': 22115, 'loss/train': 1.4529187679290771}
+08/30/2021 17:10:29 - INFO - __main__ - Step 22117: {'lr': 0.00047755287311279394, 'samples': 4246464, 'steps': 22116, 'loss/train': 1.6635645627975464}
+08/30/2021 17:10:29 - INFO - __main__ - Step 22118: {'lr': 0.00047755067530656656, 'samples': 4246656, 'steps': 22117, 'loss/train': 1.3346130847930908}
+08/30/2021 17:10:31 - INFO - __main__ - Step 22119: {'lr': 0.00047754847739780835, 'samples': 4246848, 'steps': 22118, 'loss/train': 1.9994735717773438}
+08/30/2021 17:10:32 - INFO - __main__ - Step 22120: {'lr': 0.0004775462793865203, 'samples': 4247040, 'steps': 22119, 'loss/train': 1.7999855279922485}
+08/30/2021 17:10:32 - INFO - __main__ - Step 22121: {'lr': 0.00047754408127270346, 'samples': 4247232, 'steps': 22120, 'loss/train': 0.8281984925270081}
+08/30/2021 17:10:32 - INFO - __main__ - Step 22122: {'lr': 0.0004775418830563587, 'samples': 4247424, 'steps': 22121, 'loss/train': 1.6985368728637695}
+08/30/2021 17:10:33 - INFO - __main__ - Step 22123: {'lr': 0.0004775396847374871, 'samples': 4247616, 'steps': 22122, 'loss/train': 1.672114610671997}
+08/30/2021 17:10:34 - INFO - __main__ - Step 22124: {'lr': 0.0004775374863160896, 'samples': 4247808, 'steps': 22123, 'loss/train': 1.8892408609390259}
+08/30/2021 17:10:35 - INFO - __main__ - Step 22125: {'lr': 0.0004775352877921673, 'samples': 4248000, 'steps': 22124, 'loss/train': 1.277587652206421}
+08/30/2021 17:10:35 - INFO - __main__ - Step 22126: {'lr': 0.000477533089165721, 'samples': 4248192, 'steps': 22125, 'loss/train': 1.4643505811691284}
+08/30/2021 17:10:35 - INFO - __main__ - Step 22127: {'lr': 0.0004775308904367519, 'samples': 4248384, 'steps': 22126, 'loss/train': 4.364542007446289}
+08/30/2021 17:10:36 - INFO - __main__ - Step 22128: {'lr': 0.0004775286916052609, 'samples': 4248576, 'steps': 22127, 'loss/train': 1.5798108577728271}
+08/30/2021 17:10:38 - INFO - __main__ - Step 22129: {'lr': 0.00047752649267124894, 'samples': 4248768, 'steps': 22128, 'loss/train': 1.3072041273117065}
+08/30/2021 17:10:38 - INFO - __main__ - Step 22130: {'lr': 0.0004775242936347171, 'samples': 4248960, 'steps': 22129, 'loss/train': 1.8408241271972656}
+08/30/2021 17:10:39 - INFO - __main__ - Step 22131: {'lr': 0.0004775220944956662, 'samples': 4249152, 'steps': 22130, 'loss/train': 2.2044079303741455}
+08/30/2021 17:10:39 - INFO - __main__ - Step 22132: {'lr': 0.00047751989525409745, 'samples': 4249344, 'steps': 22131, 'loss/train': 1.4526580572128296}
+08/30/2021 17:10:39 - INFO - __main__ - Step 22133: {'lr': 0.0004775176959100117, 'samples': 4249536, 'steps': 22132, 'loss/train': 1.7001789808273315}
+08/30/2021 17:10:41 - INFO - __main__ - Step 22134: {'lr': 0.00047751549646341007, 'samples': 4249728, 'steps': 22133, 'loss/train': 1.269938588142395}
+08/30/2021 17:10:41 - INFO - __main__ - Step 22135: {'lr': 0.0004775132969142934, 'samples': 4249920, 'steps': 22134, 'loss/train': 1.303545355796814}
+08/30/2021 17:10:42 - INFO - __main__ - Step 22136: {'lr': 0.00047751109726266273, 'samples': 4250112, 'steps': 22135, 'loss/train': 0.9846208095550537}
+08/30/2021 17:10:42 - INFO - __main__ - Step 22137: {'lr': 0.00047750889750851913, 'samples': 4250304, 'steps': 22136, 'loss/train': 1.691420555114746}
+08/30/2021 17:10:42 - INFO - __main__ - Step 22138: {'lr': 0.0004775066976518635, 'samples': 4250496, 'steps': 22137, 'loss/train': 1.7628076076507568}
+08/30/2021 17:10:43 - INFO - __main__ - Step 22139: {'lr': 0.00047750449769269686, 'samples': 4250688, 'steps': 22138, 'loss/train': 1.920169711112976}
+08/30/2021 17:10:44 - INFO - __main__ - Step 22140: {'lr': 0.0004775022976310203, 'samples': 4250880, 'steps': 22139, 'loss/train': 1.5844125747680664}
+08/30/2021 17:10:45 - INFO - __main__ - Step 22141: {'lr': 0.0004775000974668345, 'samples': 4251072, 'steps': 22140, 'loss/train': 1.3784774541854858}
+08/30/2021 17:10:45 - INFO - __main__ - Step 22142: {'lr': 0.00047749789720014085, 'samples': 4251264, 'steps': 22141, 'loss/train': 2.164243698120117}
+08/30/2021 17:10:46 - INFO - __main__ - Step 22143: {'lr': 0.00047749569683094015, 'samples': 4251456, 'steps': 22142, 'loss/train': 1.156712293624878}
+08/30/2021 17:10:46 - INFO - __main__ - Step 22144: {'lr': 0.00047749349635923334, 'samples': 4251648, 'steps': 22143, 'loss/train': 2.125542640686035}
+08/30/2021 17:10:46 - INFO - __main__ - Step 22145: {'lr': 0.0004774912957850215, 'samples': 4251840, 'steps': 22144, 'loss/train': 0.0950431227684021}
+08/30/2021 17:10:49 - INFO - __main__ - Step 22146: {'lr': 0.0004774890951083055, 'samples': 4252032, 'steps': 22145, 'loss/train': 1.0042872428894043}
+08/30/2021 17:10:49 - INFO - __main__ - Step 22147: {'lr': 0.00047748689432908654, 'samples': 4252224, 'steps': 22146, 'loss/train': 1.9640812873840332}
+08/30/2021 17:10:49 - INFO - __main__ - Step 22148: {'lr': 0.00047748469344736547, 'samples': 4252416, 'steps': 22147, 'loss/train': 1.8786741495132446}
+08/30/2021 17:10:50 - INFO - __main__ - Step 22149: {'lr': 0.00047748249246314323, 'samples': 4252608, 'steps': 22148, 'loss/train': 1.8291820287704468}
+08/30/2021 17:10:50 - INFO - __main__ - Step 22150: {'lr': 0.000477480291376421, 'samples': 4252800, 'steps': 22149, 'loss/train': 1.5574336051940918}
+08/30/2021 17:10:50 - INFO - __main__ - Step 22151: {'lr': 0.0004774780901871996, 'samples': 4252992, 'steps': 22150, 'loss/train': 2.3067526817321777}
+08/30/2021 17:10:52 - INFO - __main__ - Step 22152: {'lr': 0.0004774758888954801, 'samples': 4253184, 'steps': 22151, 'loss/train': 1.6837538480758667}
+08/30/2021 17:10:52 - INFO - __main__ - Step 22153: {'lr': 0.00047747368750126345, 'samples': 4253376, 'steps': 22152, 'loss/train': 1.6451901197433472}
+08/30/2021 17:10:53 - INFO - __main__ - Step 22154: {'lr': 0.0004774714860045507, 'samples': 4253568, 'steps': 22153, 'loss/train': 0.507257342338562}
+08/30/2021 17:10:53 - INFO - __main__ - Step 22155: {'lr': 0.0004774692844053428, 'samples': 4253760, 'steps': 22154, 'loss/train': 1.1535602807998657}
+08/30/2021 17:10:53 - INFO - __main__ - Step 22156: {'lr': 0.00047746708270364073, 'samples': 4253952, 'steps': 22155, 'loss/train': 1.8781384229660034}
+08/30/2021 17:10:55 - INFO - __main__ - Step 22157: {'lr': 0.0004774648808994455, 'samples': 4254144, 'steps': 22156, 'loss/train': 1.3260270357131958}
+08/30/2021 17:10:56 - INFO - __main__ - Step 22158: {'lr': 0.0004774626789927582, 'samples': 4254336, 'steps': 22157, 'loss/train': 1.7989898920059204}
+08/30/2021 17:10:56 - INFO - __main__ - Step 22159: {'lr': 0.0004774604769835796, 'samples': 4254528, 'steps': 22158, 'loss/train': 0.3206104338169098}
+08/30/2021 17:10:56 - INFO - __main__ - Step 22160: {'lr': 0.00047745827487191087, 'samples': 4254720, 'steps': 22159, 'loss/train': 1.4987117052078247}
+08/30/2021 17:10:57 - INFO - __main__ - Step 22161: {'lr': 0.00047745607265775293, 'samples': 4254912, 'steps': 22160, 'loss/train': 2.027649164199829}
+08/30/2021 17:10:57 - INFO - __main__ - Step 22162: {'lr': 0.0004774538703411069, 'samples': 4255104, 'steps': 22161, 'loss/train': 0.652060329914093}
+08/30/2021 17:10:59 - INFO - __main__ - Step 22163: {'lr': 0.00047745166792197353, 'samples': 4255296, 'steps': 22162, 'loss/train': 1.7201666831970215}
+08/30/2021 17:10:59 - INFO - __main__ - Step 22164: {'lr': 0.000477449465400354, 'samples': 4255488, 'steps': 22163, 'loss/train': 0.7782296538352966}
+08/30/2021 17:10:59 - INFO - __main__ - Step 22165: {'lr': 0.00047744726277624926, 'samples': 4255680, 'steps': 22164, 'loss/train': 1.7708029747009277}
+08/30/2021 17:11:00 - INFO - __main__ - Step 22166: {'lr': 0.00047744506004966024, 'samples': 4255872, 'steps': 22165, 'loss/train': 2.124933958053589}
+08/30/2021 17:11:00 - INFO - __main__ - Step 22167: {'lr': 0.00047744285722058804, 'samples': 4256064, 'steps': 22166, 'loss/train': 1.7922090291976929}
+08/30/2021 17:11:02 - INFO - __main__ - Step 22168: {'lr': 0.0004774406542890336, 'samples': 4256256, 'steps': 22167, 'loss/train': 1.4843497276306152}
+08/30/2021 17:11:02 - INFO - __main__ - Step 22169: {'lr': 0.0004774384512549979, 'samples': 4256448, 'steps': 22168, 'loss/train': 1.8620972633361816}
+08/30/2021 17:11:03 - INFO - __main__ - Step 22170: {'lr': 0.00047743624811848195, 'samples': 4256640, 'steps': 22169, 'loss/train': 1.7882907390594482}
+08/30/2021 17:11:03 - INFO - __main__ - Step 22171: {'lr': 0.00047743404487948673, 'samples': 4256832, 'steps': 22170, 'loss/train': 1.7539762258529663}
+08/30/2021 17:11:03 - INFO - __main__ - Step 22172: {'lr': 0.0004774318415380132, 'samples': 4257024, 'steps': 22171, 'loss/train': 1.9795050621032715}
+08/30/2021 17:11:04 - INFO - __main__ - Step 22173: {'lr': 0.0004774296380940625, 'samples': 4257216, 'steps': 22172, 'loss/train': 1.0491347312927246}
+08/30/2021 17:11:05 - INFO - __main__ - Step 22174: {'lr': 0.0004774274345476354, 'samples': 4257408, 'steps': 22173, 'loss/train': 2.025768280029297}
+08/30/2021 17:11:06 - INFO - __main__ - Step 22175: {'lr': 0.00047742523089873304, 'samples': 4257600, 'steps': 22174, 'loss/train': 1.32821786403656}
+08/30/2021 17:11:06 - INFO - __main__ - Step 22176: {'lr': 0.0004774230271473564, 'samples': 4257792, 'steps': 22175, 'loss/train': 1.7467927932739258}
+08/30/2021 17:11:07 - INFO - __main__ - Step 22177: {'lr': 0.00047742082329350644, 'samples': 4257984, 'steps': 22176, 'loss/train': 1.1691381931304932}
+08/30/2021 17:11:07 - INFO - __main__ - Step 22178: {'lr': 0.0004774186193371841, 'samples': 4258176, 'steps': 22177, 'loss/train': 2.0946285724639893}
+08/30/2021 17:11:08 - INFO - __main__ - Step 22179: {'lr': 0.00047741641527839054, 'samples': 4258368, 'steps': 22178, 'loss/train': 1.907494306564331}
+08/30/2021 17:11:09 - INFO - __main__ - Step 22180: {'lr': 0.00047741421111712666, 'samples': 4258560, 'steps': 22179, 'loss/train': 2.1550490856170654}
+08/30/2021 17:11:09 - INFO - __main__ - Step 22181: {'lr': 0.00047741200685339337, 'samples': 4258752, 'steps': 22180, 'loss/train': 0.9798780679702759}
+08/30/2021 17:11:10 - INFO - __main__ - Step 22182: {'lr': 0.0004774098024871918, 'samples': 4258944, 'steps': 22181, 'loss/train': 1.8367745876312256}
+08/30/2021 17:11:10 - INFO - __main__ - Step 22183: {'lr': 0.00047740759801852284, 'samples': 4259136, 'steps': 22182, 'loss/train': 2.275071382522583}
+08/30/2021 17:11:10 - INFO - __main__ - Step 22184: {'lr': 0.00047740539344738754, 'samples': 4259328, 'steps': 22183, 'loss/train': 1.5963722467422485}
+08/30/2021 17:11:12 - INFO - __main__ - Step 22185: {'lr': 0.00047740318877378685, 'samples': 4259520, 'steps': 22184, 'loss/train': 5.944394111633301}
+08/30/2021 17:11:13 - INFO - __main__ - Step 22186: {'lr': 0.00047740098399772185, 'samples': 4259712, 'steps': 22185, 'loss/train': 1.6890538930892944}
+08/30/2021 17:11:13 - INFO - __main__ - Step 22187: {'lr': 0.0004773987791191935, 'samples': 4259904, 'steps': 22186, 'loss/train': 1.661117434501648}
+08/30/2021 17:11:14 - INFO - __main__ - Step 22188: {'lr': 0.0004773965741382027, 'samples': 4260096, 'steps': 22187, 'loss/train': 1.3339636325836182}
+08/30/2021 17:11:14 - INFO - __main__ - Step 22189: {'lr': 0.00047739436905475054, 'samples': 4260288, 'steps': 22188, 'loss/train': 1.8554155826568604}
+08/30/2021 17:11:15 - INFO - __main__ - Step 22190: {'lr': 0.00047739216386883797, 'samples': 4260480, 'steps': 22189, 'loss/train': 2.088022470474243}
+08/30/2021 17:11:16 - INFO - __main__ - Step 22191: {'lr': 0.000477389958580466, 'samples': 4260672, 'steps': 22190, 'loss/train': 1.8659831285476685}
+08/30/2021 17:11:16 - INFO - __main__ - Step 22192: {'lr': 0.0004773877531896356, 'samples': 4260864, 'steps': 22191, 'loss/train': 1.602364182472229}
+08/30/2021 17:11:16 - INFO - __main__ - Step 22193: {'lr': 0.00047738554769634784, 'samples': 4261056, 'steps': 22192, 'loss/train': 1.59539794921875}
+08/30/2021 17:11:17 - INFO - __main__ - Step 22194: {'lr': 0.00047738334210060366, 'samples': 4261248, 'steps': 22193, 'loss/train': 2.3934431076049805}
+08/30/2021 17:11:19 - INFO - __main__ - Step 22195: {'lr': 0.000477381136402404, 'samples': 4261440, 'steps': 22194, 'loss/train': 1.918354868888855}
+08/30/2021 17:11:19 - INFO - __main__ - Step 22196: {'lr': 0.00047737893060175, 'samples': 4261632, 'steps': 22195, 'loss/train': 1.7233904600143433}
+08/30/2021 17:11:19 - INFO - __main__ - Step 22197: {'lr': 0.00047737672469864246, 'samples': 4261824, 'steps': 22196, 'loss/train': 1.3757588863372803}
+08/30/2021 17:11:20 - INFO - __main__ - Step 22198: {'lr': 0.0004773745186930825, 'samples': 4262016, 'steps': 22197, 'loss/train': 1.9363975524902344}
+08/30/2021 17:11:20 - INFO - __main__ - Step 22199: {'lr': 0.00047737231258507116, 'samples': 4262208, 'steps': 22198, 'loss/train': 1.716389536857605}
+08/30/2021 17:11:21 - INFO - __main__ - Step 22200: {'lr': 0.00047737010637460934, 'samples': 4262400, 'steps': 22199, 'loss/train': 1.666672706604004}
+08/30/2021 17:11:21 - INFO - __main__ - Step 22201: {'lr': 0.00047736790006169794, 'samples': 4262592, 'steps': 22200, 'loss/train': 1.411740779876709}
+08/30/2021 17:11:22 - INFO - __main__ - Step 22202: {'lr': 0.00047736569364633817, 'samples': 4262784, 'steps': 22201, 'loss/train': 1.2216259241104126}
+08/30/2021 17:11:23 - INFO - __main__ - Step 22203: {'lr': 0.00047736348712853094, 'samples': 4262976, 'steps': 22202, 'loss/train': 2.133310556411743}
+08/30/2021 17:11:23 - INFO - __main__ - Step 22204: {'lr': 0.0004773612805082772, 'samples': 4263168, 'steps': 22203, 'loss/train': 2.077293634414673}
+08/30/2021 17:11:24 - INFO - __main__ - Step 22205: {'lr': 0.000477359073785578, 'samples': 4263360, 'steps': 22204, 'loss/train': 2.1532883644104004}
+08/30/2021 17:11:24 - INFO - __main__ - Step 22206: {'lr': 0.00047735686696043434, 'samples': 4263552, 'steps': 22205, 'loss/train': 2.1496901512145996}
+08/30/2021 17:11:25 - INFO - __main__ - Step 22207: {'lr': 0.0004773546600328471, 'samples': 4263744, 'steps': 22206, 'loss/train': 2.316821575164795}
+08/30/2021 17:11:26 - INFO - __main__ - Step 22208: {'lr': 0.00047735245300281745, 'samples': 4263936, 'steps': 22207, 'loss/train': 1.21135413646698}
+08/30/2021 17:11:26 - INFO - __main__ - Step 22209: {'lr': 0.00047735024587034625, 'samples': 4264128, 'steps': 22208, 'loss/train': 1.9529237747192383}
+08/30/2021 17:11:27 - INFO - __main__ - Step 22210: {'lr': 0.00047734803863543453, 'samples': 4264320, 'steps': 22209, 'loss/train': 1.8628636598587036}
+08/30/2021 17:11:27 - INFO - __main__ - Step 22211: {'lr': 0.00047734583129808327, 'samples': 4264512, 'steps': 22210, 'loss/train': 1.4725264310836792}
+08/30/2021 17:11:27 - INFO - __main__ - Step 22212: {'lr': 0.00047734362385829356, 'samples': 4264704, 'steps': 22211, 'loss/train': 2.220416784286499}
+08/30/2021 17:11:29 - INFO - __main__ - Step 22213: {'lr': 0.0004773414163160662, 'samples': 4264896, 'steps': 22212, 'loss/train': 1.9183039665222168}
+08/30/2021 17:11:29 - INFO - __main__ - Step 22214: {'lr': 0.00047733920867140244, 'samples': 4265088, 'steps': 22213, 'loss/train': 1.4160573482513428}
+08/30/2021 17:11:30 - INFO - __main__ - Step 22215: {'lr': 0.00047733700092430305, 'samples': 4265280, 'steps': 22214, 'loss/train': 1.6211538314819336}
+08/30/2021 17:11:30 - INFO - __main__ - Step 22216: {'lr': 0.0004773347930747691, 'samples': 4265472, 'steps': 22215, 'loss/train': 3.273075819015503}
+08/30/2021 17:11:30 - INFO - __main__ - Step 22217: {'lr': 0.0004773325851228017, 'samples': 4265664, 'steps': 22216, 'loss/train': 1.7557157278060913}
+08/30/2021 17:11:32 - INFO - __main__ - Step 22218: {'lr': 0.00047733037706840166, 'samples': 4265856, 'steps': 22217, 'loss/train': 1.849313735961914}
+08/30/2021 17:11:32 - INFO - __main__ - Step 22219: {'lr': 0.0004773281689115701, 'samples': 4266048, 'steps': 22218, 'loss/train': 2.089118480682373}
+08/30/2021 17:11:32 - INFO - __main__ - Step 22220: {'lr': 0.000477325960652308, 'samples': 4266240, 'steps': 22219, 'loss/train': 1.6515716314315796}
+08/30/2021 17:11:33 - INFO - __main__ - Step 22221: {'lr': 0.0004773237522906163, 'samples': 4266432, 'steps': 22220, 'loss/train': 2.2680416107177734}
+08/30/2021 17:11:33 - INFO - __main__ - Step 22222: {'lr': 0.000477321543826496, 'samples': 4266624, 'steps': 22221, 'loss/train': 1.7360239028930664}
+08/30/2021 17:11:35 - INFO - __main__ - Step 22223: {'lr': 0.00047731933525994814, 'samples': 4266816, 'steps': 22222, 'loss/train': 1.806036353111267}
+08/30/2021 17:11:35 - INFO - __main__ - Step 22224: {'lr': 0.0004773171265909737, 'samples': 4267008, 'steps': 22223, 'loss/train': 1.579102873802185}
+08/30/2021 17:11:36 - INFO - __main__ - Step 22225: {'lr': 0.00047731491781957366, 'samples': 4267200, 'steps': 22224, 'loss/train': 2.0978195667266846}
+08/30/2021 17:11:36 - INFO - __main__ - Step 22226: {'lr': 0.0004773127089457491, 'samples': 4267392, 'steps': 22225, 'loss/train': 0.35885512828826904}
+08/30/2021 17:11:36 - INFO - __main__ - Step 22227: {'lr': 0.0004773104999695008, 'samples': 4267584, 'steps': 22226, 'loss/train': 1.8843597173690796}
+08/30/2021 17:11:38 - INFO - __main__ - Step 22228: {'lr': 0.00047730829089082994, 'samples': 4267776, 'steps': 22227, 'loss/train': 1.9311151504516602}
+08/30/2021 17:11:39 - INFO - __main__ - Step 22229: {'lr': 0.00047730608170973754, 'samples': 4267968, 'steps': 22228, 'loss/train': 1.5460875034332275}
+08/30/2021 17:11:39 - INFO - __main__ - Step 22230: {'lr': 0.00047730387242622446, 'samples': 4268160, 'steps': 22229, 'loss/train': 1.5039581060409546}
+08/30/2021 17:11:39 - INFO - __main__ - Step 22231: {'lr': 0.00047730166304029185, 'samples': 4268352, 'steps': 22230, 'loss/train': 2.5621299743652344}
+08/30/2021 17:11:40 - INFO - __main__ - Step 22232: {'lr': 0.0004772994535519405, 'samples': 4268544, 'steps': 22231, 'loss/train': 0.2551862299442291}
+08/30/2021 17:11:41 - INFO - __main__ - Step 22233: {'lr': 0.0004772972439611716, 'samples': 4268736, 'steps': 22232, 'loss/train': 2.1080820560455322}
+08/30/2021 17:11:41 - INFO - __main__ - Step 22234: {'lr': 0.00047729503426798605, 'samples': 4268928, 'steps': 22233, 'loss/train': 1.5359896421432495}
+08/30/2021 17:11:42 - INFO - __main__ - Step 22235: {'lr': 0.0004772928244723849, 'samples': 4269120, 'steps': 22234, 'loss/train': 2.113858938217163}
+08/30/2021 17:11:42 - INFO - __main__ - Step 22236: {'lr': 0.00047729061457436905, 'samples': 4269312, 'steps': 22235, 'loss/train': 1.3084994554519653}
+08/30/2021 17:11:43 - INFO - __main__ - Step 22237: {'lr': 0.0004772884045739396, 'samples': 4269504, 'steps': 22236, 'loss/train': 1.6442188024520874}
+08/30/2021 17:11:45 - INFO - __main__ - Step 22238: {'lr': 0.0004772861944710974, 'samples': 4269696, 'steps': 22237, 'loss/train': 1.5789165496826172}
+08/30/2021 17:11:45 - INFO - __main__ - Step 22239: {'lr': 0.00047728398426584375, 'samples': 4269888, 'steps': 22238, 'loss/train': 1.1186904907226562}
+08/30/2021 17:11:46 - INFO - __main__ - Step 22240: {'lr': 0.0004772817739581793, 'samples': 4270080, 'steps': 22239, 'loss/train': 1.960464358329773}
+08/30/2021 17:11:46 - INFO - __main__ - Step 22241: {'lr': 0.0004772795635481052, 'samples': 4270272, 'steps': 22240, 'loss/train': 2.104534864425659}
+08/30/2021 17:11:46 - INFO - __main__ - Step 22242: {'lr': 0.00047727735303562246, 'samples': 4270464, 'steps': 22241, 'loss/train': 1.1994812488555908}
+08/30/2021 17:11:48 - INFO - __main__ - Step 22243: {'lr': 0.000477275142420732, 'samples': 4270656, 'steps': 22242, 'loss/train': 1.981293797492981}
+08/30/2021 17:11:48 - INFO - __main__ - Step 22244: {'lr': 0.000477272931703435, 'samples': 4270848, 'steps': 22243, 'loss/train': 1.873092532157898}
+08/30/2021 17:11:49 - INFO - __main__ - Step 22245: {'lr': 0.0004772707208837322, 'samples': 4271040, 'steps': 22244, 'loss/train': 2.0743179321289062}
+08/30/2021 17:11:49 - INFO - __main__ - Step 22246: {'lr': 0.0004772685099616247, 'samples': 4271232, 'steps': 22245, 'loss/train': 1.9581387042999268}
+08/30/2021 17:11:49 - INFO - __main__ - Step 22247: {'lr': 0.0004772662989371136, 'samples': 4271424, 'steps': 22246, 'loss/train': 1.8399993181228638}
+08/30/2021 17:11:51 - INFO - __main__ - Step 22248: {'lr': 0.0004772640878101998, 'samples': 4271616, 'steps': 22247, 'loss/train': 0.4765205681324005}
+08/30/2021 17:11:51 - INFO - __main__ - Step 22249: {'lr': 0.00047726187658088425, 'samples': 4271808, 'steps': 22248, 'loss/train': 0.857501208782196}
+08/30/2021 17:11:52 - INFO - __main__ - Step 22250: {'lr': 0.0004772596652491681, 'samples': 4272000, 'steps': 22249, 'loss/train': 1.1813633441925049}
+08/30/2021 17:11:52 - INFO - __main__ - Step 22251: {'lr': 0.0004772574538150522, 'samples': 4272192, 'steps': 22250, 'loss/train': 1.92146897315979}
+08/30/2021 17:11:52 - INFO - __main__ - Step 22252: {'lr': 0.0004772552422785376, 'samples': 4272384, 'steps': 22251, 'loss/train': 1.3620665073394775}
+08/30/2021 17:11:54 - INFO - __main__ - Step 22253: {'lr': 0.00047725303063962535, 'samples': 4272576, 'steps': 22252, 'loss/train': 1.442641019821167}
+08/30/2021 17:11:54 - INFO - __main__ - Step 22254: {'lr': 0.00047725081889831626, 'samples': 4272768, 'steps': 22253, 'loss/train': 1.8525470495224}
+08/30/2021 17:11:55 - INFO - __main__ - Step 22255: {'lr': 0.0004772486070546116, 'samples': 4272960, 'steps': 22254, 'loss/train': 1.4444137811660767}
+08/30/2021 17:11:55 - INFO - __main__ - Step 22256: {'lr': 0.0004772463951085121, 'samples': 4273152, 'steps': 22255, 'loss/train': 1.7241592407226562}
+08/30/2021 17:11:55 - INFO - __main__ - Step 22257: {'lr': 0.00047724418306001895, 'samples': 4273344, 'steps': 22256, 'loss/train': 1.6980116367340088}
+08/30/2021 17:11:57 - INFO - __main__ - Step 22258: {'lr': 0.0004772419709091331, 'samples': 4273536, 'steps': 22257, 'loss/train': 1.1155540943145752}
+08/30/2021 17:11:57 - INFO - __main__ - Step 22259: {'lr': 0.00047723975865585544, 'samples': 4273728, 'steps': 22258, 'loss/train': 0.32903313636779785}
+08/30/2021 17:11:58 - INFO - __main__ - Step 22260: {'lr': 0.00047723754630018715, 'samples': 4273920, 'steps': 22259, 'loss/train': 2.0642480850219727}
+08/30/2021 17:11:58 - INFO - __main__ - Step 22261: {'lr': 0.000477235333842129, 'samples': 4274112, 'steps': 22260, 'loss/train': 1.3852115869522095}
+08/30/2021 17:11:58 - INFO - __main__ - Step 22262: {'lr': 0.00047723312128168226, 'samples': 4274304, 'steps': 22261, 'loss/train': 1.337482213973999}
+08/30/2021 17:11:59 - INFO - __main__ - Step 22263: {'lr': 0.00047723090861884773, 'samples': 4274496, 'steps': 22262, 'loss/train': 2.026703357696533}
+08/30/2021 17:12:00 - INFO - __main__ - Step 22264: {'lr': 0.00047722869585362646, 'samples': 4274688, 'steps': 22263, 'loss/train': 2.6244313716888428}
+08/30/2021 17:12:01 - INFO - __main__ - Step 22265: {'lr': 0.0004772264829860194, 'samples': 4274880, 'steps': 22264, 'loss/train': 1.8513308763504028}
+08/30/2021 17:12:01 - INFO - __main__ - Step 22266: {'lr': 0.00047722427001602765, 'samples': 4275072, 'steps': 22265, 'loss/train': 5.899032115936279}
+08/30/2021 17:12:02 - INFO - __main__ - Step 22267: {'lr': 0.0004772220569436521, 'samples': 4275264, 'steps': 22266, 'loss/train': 1.5059112310409546}
+08/30/2021 17:12:02 - INFO - __main__ - Step 22268: {'lr': 0.0004772198437688938, 'samples': 4275456, 'steps': 22267, 'loss/train': 1.5607255697250366}
+08/30/2021 17:12:04 - INFO - __main__ - Step 22269: {'lr': 0.0004772176304917538, 'samples': 4275648, 'steps': 22268, 'loss/train': 1.8144924640655518}
+08/30/2021 17:12:04 - INFO - __main__ - Step 22270: {'lr': 0.00047721541711223306, 'samples': 4275840, 'steps': 22269, 'loss/train': 1.739651083946228}
+08/30/2021 17:12:04 - INFO - __main__ - Step 22271: {'lr': 0.00047721320363033247, 'samples': 4276032, 'steps': 22270, 'loss/train': 2.207659959793091}
+08/30/2021 17:12:05 - INFO - __main__ - Step 22272: {'lr': 0.00047721099004605316, 'samples': 4276224, 'steps': 22271, 'loss/train': 1.5110259056091309}
+08/30/2021 17:12:05 - INFO - __main__ - Step 22273: {'lr': 0.00047720877635939606, 'samples': 4276416, 'steps': 22272, 'loss/train': 1.3257867097854614}
+08/30/2021 17:12:05 - INFO - __main__ - Step 22274: {'lr': 0.0004772065625703622, 'samples': 4276608, 'steps': 22273, 'loss/train': 1.6748912334442139}
+08/30/2021 17:12:07 - INFO - __main__ - Step 22275: {'lr': 0.0004772043486789526, 'samples': 4276800, 'steps': 22274, 'loss/train': 1.8296105861663818}
+08/30/2021 17:12:07 - INFO - __main__ - Step 22276: {'lr': 0.0004772021346851682, 'samples': 4276992, 'steps': 22275, 'loss/train': 1.589489221572876}
+08/30/2021 17:12:08 - INFO - __main__ - Step 22277: {'lr': 0.00047719992058901006, 'samples': 4277184, 'steps': 22276, 'loss/train': 2.3670313358306885}
+08/30/2021 17:12:08 - INFO - __main__ - Step 22278: {'lr': 0.0004771977063904791, 'samples': 4277376, 'steps': 22277, 'loss/train': 1.057492971420288}
+08/30/2021 17:12:08 - INFO - __main__ - Step 22279: {'lr': 0.00047719549208957636, 'samples': 4277568, 'steps': 22278, 'loss/train': 1.414607048034668}
+08/30/2021 17:12:10 - INFO - __main__ - Step 22280: {'lr': 0.0004771932776863028, 'samples': 4277760, 'steps': 22279, 'loss/train': 1.5459754467010498}
+08/30/2021 17:12:10 - INFO - __main__ - Step 22281: {'lr': 0.0004771910631806595, 'samples': 4277952, 'steps': 22280, 'loss/train': 1.5766849517822266}
+08/30/2021 17:12:11 - INFO - __main__ - Step 22282: {'lr': 0.00047718884857264745, 'samples': 4278144, 'steps': 22281, 'loss/train': 2.308119535446167}
+08/30/2021 17:12:11 - INFO - __main__ - Step 22283: {'lr': 0.0004771866338622676, 'samples': 4278336, 'steps': 22282, 'loss/train': 1.3916943073272705}
+08/30/2021 17:12:11 - INFO - __main__ - Step 22284: {'lr': 0.0004771844190495209, 'samples': 4278528, 'steps': 22283, 'loss/train': 1.7475589513778687}
+08/30/2021 17:12:13 - INFO - __main__ - Step 22285: {'lr': 0.0004771822041344085, 'samples': 4278720, 'steps': 22284, 'loss/train': 1.9920268058776855}
+08/30/2021 17:12:13 - INFO - __main__ - Step 22286: {'lr': 0.0004771799891169312, 'samples': 4278912, 'steps': 22285, 'loss/train': 1.6034091711044312}
+08/30/2021 17:12:14 - INFO - __main__ - Step 22287: {'lr': 0.0004771777739970902, 'samples': 4279104, 'steps': 22286, 'loss/train': 1.5661957263946533}
+08/30/2021 17:12:14 - INFO - __main__ - Step 22288: {'lr': 0.0004771755587748863, 'samples': 4279296, 'steps': 22287, 'loss/train': 1.2716710567474365}
+08/30/2021 17:12:14 - INFO - __main__ - Step 22289: {'lr': 0.00047717334345032065, 'samples': 4279488, 'steps': 22288, 'loss/train': 1.3670454025268555}
+08/30/2021 17:12:16 - INFO - __main__ - Step 22290: {'lr': 0.0004771711280233942, 'samples': 4279680, 'steps': 22289, 'loss/train': 2.0890448093414307}
+08/30/2021 17:12:17 - INFO - __main__ - Step 22291: {'lr': 0.000477168912494108, 'samples': 4279872, 'steps': 22290, 'loss/train': 1.223692536354065}
+08/30/2021 17:12:17 - INFO - __main__ - Step 22292: {'lr': 0.00047716669686246287, 'samples': 4280064, 'steps': 22291, 'loss/train': 2.1673696041107178}
+08/30/2021 17:12:17 - INFO - __main__ - Step 22293: {'lr': 0.00047716448112846, 'samples': 4280256, 'steps': 22292, 'loss/train': 1.7638188600540161}
+08/30/2021 17:12:18 - INFO - __main__ - Step 22294: {'lr': 0.00047716226529210035, 'samples': 4280448, 'steps': 22293, 'loss/train': 1.263674020767212}
+08/30/2021 17:12:18 - INFO - __main__ - Step 22295: {'lr': 0.00047716004935338484, 'samples': 4280640, 'steps': 22294, 'loss/train': 2.0301637649536133}
+08/30/2021 17:12:20 - INFO - __main__ - Step 22296: {'lr': 0.0004771578333123145, 'samples': 4280832, 'steps': 22295, 'loss/train': 0.1532074362039566}
+08/30/2021 17:12:21 - INFO - __main__ - Step 22297: {'lr': 0.00047715561716889037, 'samples': 4281024, 'steps': 22296, 'loss/train': 1.6346476078033447}
+08/30/2021 17:12:21 - INFO - __main__ - Step 22298: {'lr': 0.0004771534009231134, 'samples': 4281216, 'steps': 22297, 'loss/train': 1.932807445526123}
+08/30/2021 17:12:22 - INFO - __main__ - Step 22299: {'lr': 0.00047715118457498473, 'samples': 4281408, 'steps': 22298, 'loss/train': 1.622165322303772}
+08/30/2021 17:12:22 - INFO - __main__ - Step 22300: {'lr': 0.00047714896812450514, 'samples': 4281600, 'steps': 22299, 'loss/train': 1.7235090732574463}
+08/30/2021 17:12:22 - INFO - __main__ - Step 22301: {'lr': 0.00047714675157167573, 'samples': 4281792, 'steps': 22300, 'loss/train': 1.7315394878387451}
+08/30/2021 17:12:24 - INFO - __main__ - Step 22302: {'lr': 0.00047714453491649753, 'samples': 4281984, 'steps': 22301, 'loss/train': 1.458749532699585}
+08/30/2021 17:12:24 - INFO - __main__ - Step 22303: {'lr': 0.00047714231815897145, 'samples': 4282176, 'steps': 22302, 'loss/train': 1.760093092918396}
+08/30/2021 17:12:25 - INFO - __main__ - Step 22304: {'lr': 0.0004771401012990986, 'samples': 4282368, 'steps': 22303, 'loss/train': 1.0102078914642334}
+08/30/2021 17:12:25 - INFO - __main__ - Step 22305: {'lr': 0.0004771378843368799, 'samples': 4282560, 'steps': 22304, 'loss/train': 0.8581253290176392}
+08/30/2021 17:12:25 - INFO - __main__ - Step 22306: {'lr': 0.0004771356672723164, 'samples': 4282752, 'steps': 22305, 'loss/train': 1.1559330224990845}
+08/30/2021 17:12:27 - INFO - __main__ - Step 22307: {'lr': 0.0004771334501054091, 'samples': 4282944, 'steps': 22306, 'loss/train': 1.6413648128509521}
+08/30/2021 17:12:27 - INFO - __main__ - Step 22308: {'lr': 0.0004771312328361589, 'samples': 4283136, 'steps': 22307, 'loss/train': 1.3504822254180908}
+08/30/2021 17:12:28 - INFO - __main__ - Step 22309: {'lr': 0.0004771290154645669, 'samples': 4283328, 'steps': 22308, 'loss/train': 1.6743515729904175}
+08/30/2021 17:12:28 - INFO - __main__ - Step 22310: {'lr': 0.0004771267979906341, 'samples': 4283520, 'steps': 22309, 'loss/train': 1.1398613452911377}
+08/30/2021 17:12:28 - INFO - __main__ - Step 22311: {'lr': 0.0004771245804143615, 'samples': 4283712, 'steps': 22310, 'loss/train': 1.9536066055297852}
+08/30/2021 17:12:30 - INFO - __main__ - Step 22312: {'lr': 0.00047712236273574993, 'samples': 4283904, 'steps': 22311, 'loss/train': 1.4108941555023193}
+08/30/2021 17:12:30 - INFO - __main__ - Step 22313: {'lr': 0.0004771201449548006, 'samples': 4284096, 'steps': 22312, 'loss/train': 2.030109167098999}
+08/30/2021 17:12:31 - INFO - __main__ - Step 22314: {'lr': 0.0004771179270715145, 'samples': 4284288, 'steps': 22313, 'loss/train': 1.5843579769134521}
+08/30/2021 17:12:31 - INFO - __main__ - Step 22315: {'lr': 0.0004771157090858925, 'samples': 4284480, 'steps': 22314, 'loss/train': 1.4762053489685059}
+08/30/2021 17:12:31 - INFO - __main__ - Step 22316: {'lr': 0.00047711349099793565, 'samples': 4284672, 'steps': 22315, 'loss/train': 1.261612892150879}
+08/30/2021 17:12:33 - INFO - __main__ - Step 22317: {'lr': 0.00047711127280764497, 'samples': 4284864, 'steps': 22316, 'loss/train': 1.734206199645996}
+08/30/2021 17:12:34 - INFO - __main__ - Step 22318: {'lr': 0.0004771090545150215, 'samples': 4285056, 'steps': 22317, 'loss/train': 2.0448877811431885}
+08/30/2021 17:12:34 - INFO - __main__ - Step 22319: {'lr': 0.00047710683612006623, 'samples': 4285248, 'steps': 22318, 'loss/train': 1.1970142126083374}
+08/30/2021 17:12:34 - INFO - __main__ - Step 22320: {'lr': 0.00047710461762278, 'samples': 4285440, 'steps': 22319, 'loss/train': 1.1002840995788574}
+08/30/2021 17:12:35 - INFO - __main__ - Step 22321: {'lr': 0.00047710239902316404, 'samples': 4285632, 'steps': 22320, 'loss/train': 1.3517085313796997}
+08/30/2021 17:12:35 - INFO - __main__ - Step 22322: {'lr': 0.0004771001803212192, 'samples': 4285824, 'steps': 22321, 'loss/train': 0.12081053853034973}
+08/30/2021 17:12:36 - INFO - __main__ - Step 22323: {'lr': 0.0004770979615169466, 'samples': 4286016, 'steps': 22322, 'loss/train': 1.2311862707138062}
+08/30/2021 17:12:37 - INFO - __main__ - Step 22324: {'lr': 0.00047709574261034705, 'samples': 4286208, 'steps': 22323, 'loss/train': 1.5089372396469116}
+08/30/2021 17:12:37 - INFO - __main__ - Step 22325: {'lr': 0.0004770935236014217, 'samples': 4286400, 'steps': 22324, 'loss/train': 1.385047435760498}
+08/30/2021 17:12:38 - INFO - __main__ - Step 22326: {'lr': 0.00047709130449017154, 'samples': 4286592, 'steps': 22325, 'loss/train': 1.8321505784988403}
+08/30/2021 17:12:38 - INFO - __main__ - Step 22327: {'lr': 0.0004770890852765975, 'samples': 4286784, 'steps': 22326, 'loss/train': 1.692516565322876}
+08/30/2021 17:12:39 - INFO - __main__ - Step 22328: {'lr': 0.00047708686596070065, 'samples': 4286976, 'steps': 22327, 'loss/train': 1.6043461561203003}
+08/30/2021 17:12:40 - INFO - __main__ - Step 22329: {'lr': 0.00047708464654248195, 'samples': 4287168, 'steps': 22328, 'loss/train': 3.0700507164001465}
+08/30/2021 17:12:40 - INFO - __main__ - Step 22330: {'lr': 0.0004770824270219424, 'samples': 4287360, 'steps': 22329, 'loss/train': 1.9059228897094727}
+08/30/2021 17:12:41 - INFO - __main__ - Step 22331: {'lr': 0.0004770802073990831, 'samples': 4287552, 'steps': 22330, 'loss/train': 1.1868107318878174}
+08/30/2021 17:12:41 - INFO - __main__ - Step 22332: {'lr': 0.00047707798767390486, 'samples': 4287744, 'steps': 22331, 'loss/train': 1.798985481262207}
+08/30/2021 17:12:41 - INFO - __main__ - Step 22333: {'lr': 0.00047707576784640883, 'samples': 4287936, 'steps': 22332, 'loss/train': 1.9564640522003174}
+08/30/2021 17:12:43 - INFO - __main__ - Step 22334: {'lr': 0.00047707354791659594, 'samples': 4288128, 'steps': 22333, 'loss/train': 1.6558359861373901}
+08/30/2021 17:12:44 - INFO - __main__ - Step 22335: {'lr': 0.0004770713278844672, 'samples': 4288320, 'steps': 22334, 'loss/train': 1.7436270713806152}
+08/30/2021 17:12:44 - INFO - __main__ - Step 22336: {'lr': 0.00047706910775002363, 'samples': 4288512, 'steps': 22335, 'loss/train': 1.8189456462860107}
+08/30/2021 17:12:44 - INFO - __main__ - Step 22337: {'lr': 0.0004770668875132663, 'samples': 4288704, 'steps': 22336, 'loss/train': 0.8251792192459106}
+08/30/2021 17:12:45 - INFO - __main__ - Step 22338: {'lr': 0.00047706466717419607, 'samples': 4288896, 'steps': 22337, 'loss/train': 1.2290778160095215}
+08/30/2021 17:12:46 - INFO - __main__ - Step 22339: {'lr': 0.000477062446732814, 'samples': 4289088, 'steps': 22338, 'loss/train': 1.2256410121917725}
+08/30/2021 17:12:47 - INFO - __main__ - Step 22340: {'lr': 0.0004770602261891211, 'samples': 4289280, 'steps': 22339, 'loss/train': 1.7080248594284058}
+08/30/2021 17:12:47 - INFO - __main__ - Step 22341: {'lr': 0.00047705800554311836, 'samples': 4289472, 'steps': 22340, 'loss/train': 2.1394202709198}
+08/30/2021 17:12:47 - INFO - __main__ - Step 22342: {'lr': 0.0004770557847948068, 'samples': 4289664, 'steps': 22341, 'loss/train': 0.19599613547325134}
+08/30/2021 17:12:48 - INFO - __main__ - Step 22343: {'lr': 0.0004770535639441874, 'samples': 4289856, 'steps': 22342, 'loss/train': 1.7449849843978882}
+08/30/2021 17:12:50 - INFO - __main__ - Step 22344: {'lr': 0.0004770513429912612, 'samples': 4290048, 'steps': 22343, 'loss/train': 1.2627513408660889}
+08/30/2021 17:12:50 - INFO - __main__ - Step 22345: {'lr': 0.0004770491219360291, 'samples': 4290240, 'steps': 22344, 'loss/train': 1.4885687828063965}
+08/30/2021 17:12:50 - INFO - __main__ - Step 22346: {'lr': 0.00047704690077849223, 'samples': 4290432, 'steps': 22345, 'loss/train': 1.65871000289917}
+08/30/2021 17:12:51 - INFO - __main__ - Step 22347: {'lr': 0.0004770446795186515, 'samples': 4290624, 'steps': 22346, 'loss/train': 1.5663443803787231}
+08/30/2021 17:12:51 - INFO - __main__ - Step 22348: {'lr': 0.0004770424581565079, 'samples': 4290816, 'steps': 22347, 'loss/train': 1.3566665649414062}
+08/30/2021 17:12:54 - INFO - __main__ - Step 22349: {'lr': 0.0004770402366920625, 'samples': 4291008, 'steps': 22348, 'loss/train': 0.32403233647346497}
+08/30/2021 17:12:54 - INFO - __main__ - Step 22350: {'lr': 0.00047703801512531636, 'samples': 4291200, 'steps': 22349, 'loss/train': 1.629690170288086}
+08/30/2021 17:12:55 - INFO - __main__ - Step 22351: {'lr': 0.00047703579345627036, 'samples': 4291392, 'steps': 22350, 'loss/train': 1.9505356550216675}
+08/30/2021 17:12:55 - INFO - __main__ - Step 22352: {'lr': 0.00047703357168492544, 'samples': 4291584, 'steps': 22351, 'loss/train': 1.5575278997421265}
+08/30/2021 17:12:55 - INFO - __main__ - Step 22353: {'lr': 0.0004770313498112828, 'samples': 4291776, 'steps': 22352, 'loss/train': 1.1776572465896606}
+08/30/2021 17:12:56 - INFO - __main__ - Step 22354: {'lr': 0.0004770291278353433, 'samples': 4291968, 'steps': 22353, 'loss/train': 1.4709523916244507}
+08/30/2021 17:12:56 - INFO - __main__ - Step 22355: {'lr': 0.00047702690575710796, 'samples': 4292160, 'steps': 22354, 'loss/train': 2.1087942123413086}
+08/30/2021 17:12:58 - INFO - __main__ - Step 22356: {'lr': 0.0004770246835765778, 'samples': 4292352, 'steps': 22355, 'loss/train': 1.793090581893921}
+08/30/2021 17:12:58 - INFO - __main__ - Step 22357: {'lr': 0.0004770224612937538, 'samples': 4292544, 'steps': 22356, 'loss/train': 1.7314915657043457}
+08/30/2021 17:12:58 - INFO - __main__ - Step 22358: {'lr': 0.0004770202389086371, 'samples': 4292736, 'steps': 22357, 'loss/train': 1.6197714805603027}
+08/30/2021 17:12:59 - INFO - __main__ - Step 22359: {'lr': 0.0004770180164212284, 'samples': 4292928, 'steps': 22358, 'loss/train': 2.251490831375122}
+08/30/2021 17:12:59 - INFO - __main__ - Step 22360: {'lr': 0.00047701579383152906, 'samples': 4293120, 'steps': 22359, 'loss/train': 1.3303654193878174}
+08/30/2021 17:13:01 - INFO - __main__ - Step 22361: {'lr': 0.0004770135711395398, 'samples': 4293312, 'steps': 22360, 'loss/train': 1.2282088994979858}
+08/30/2021 17:13:01 - INFO - __main__ - Step 22362: {'lr': 0.0004770113483452618, 'samples': 4293504, 'steps': 22361, 'loss/train': 2.1275947093963623}
+08/30/2021 17:13:02 - INFO - __main__ - Step 22363: {'lr': 0.00047700912544869595, 'samples': 4293696, 'steps': 22362, 'loss/train': 2.052558183670044}
+08/30/2021 17:13:02 - INFO - __main__ - Step 22364: {'lr': 0.0004770069024498433, 'samples': 4293888, 'steps': 22363, 'loss/train': 1.709843635559082}
+08/30/2021 17:13:02 - INFO - __main__ - Step 22365: {'lr': 0.00047700467934870484, 'samples': 4294080, 'steps': 22364, 'loss/train': 0.11012905836105347}
+08/30/2021 17:13:05 - INFO - __main__ - Step 22366: {'lr': 0.0004770024561452816, 'samples': 4294272, 'steps': 22365, 'loss/train': 1.4906331300735474}
+08/30/2021 17:13:05 - INFO - __main__ - Step 22367: {'lr': 0.0004770002328395745, 'samples': 4294464, 'steps': 22366, 'loss/train': 1.7107250690460205}
+08/30/2021 17:13:05 - INFO - __main__ - Step 22368: {'lr': 0.00047699800943158454, 'samples': 4294656, 'steps': 22367, 'loss/train': 0.14216406643390656}
+08/30/2021 17:13:06 - INFO - __main__ - Step 22369: {'lr': 0.0004769957859213129, 'samples': 4294848, 'steps': 22368, 'loss/train': 1.6559343338012695}
+08/30/2021 17:13:06 - INFO - __main__ - Step 22370: {'lr': 0.00047699356230876047, 'samples': 4295040, 'steps': 22369, 'loss/train': 1.896594762802124}
+08/30/2021 17:13:07 - INFO - __main__ - Step 22371: {'lr': 0.0004769913385939282, 'samples': 4295232, 'steps': 22370, 'loss/train': 1.1542118787765503}
+08/30/2021 17:13:07 - INFO - __main__ - Step 22372: {'lr': 0.0004769891147768171, 'samples': 4295424, 'steps': 22371, 'loss/train': 2.6675169467926025}
+08/30/2021 17:13:07 - INFO - __main__ - Step 22373: {'lr': 0.00047698689085742823, 'samples': 4295616, 'steps': 22372, 'loss/train': 1.9953951835632324}
+08/30/2021 17:13:09 - INFO - __main__ - Step 22374: {'lr': 0.00047698466683576256, 'samples': 4295808, 'steps': 22373, 'loss/train': 1.745845913887024}
+08/30/2021 17:13:09 - INFO - __main__ - Step 22375: {'lr': 0.0004769824427118211, 'samples': 4296000, 'steps': 22374, 'loss/train': 1.9689626693725586}
+08/30/2021 17:13:09 - INFO - __main__ - Step 22376: {'lr': 0.00047698021848560494, 'samples': 4296192, 'steps': 22375, 'loss/train': 2.4756383895874023}
+08/30/2021 17:13:10 - INFO - __main__ - Step 22377: {'lr': 0.0004769779941571149, 'samples': 4296384, 'steps': 22376, 'loss/train': 1.3743934631347656}
+08/30/2021 17:13:10 - INFO - __main__ - Step 22378: {'lr': 0.00047697576972635213, 'samples': 4296576, 'steps': 22377, 'loss/train': 1.7336702346801758}
+08/30/2021 17:13:12 - INFO - __main__ - Step 22379: {'lr': 0.0004769735451933176, 'samples': 4296768, 'steps': 22378, 'loss/train': 1.7430158853530884}
+08/30/2021 17:13:12 - INFO - __main__ - Step 22380: {'lr': 0.0004769713205580122, 'samples': 4296960, 'steps': 22379, 'loss/train': 1.7553653717041016}
+08/30/2021 17:13:12 - INFO - __main__ - Step 22381: {'lr': 0.0004769690958204371, 'samples': 4297152, 'steps': 22380, 'loss/train': 1.4760040044784546}
+08/30/2021 17:13:13 - INFO - __main__ - Step 22382: {'lr': 0.0004769668709805932, 'samples': 4297344, 'steps': 22381, 'loss/train': 2.4359185695648193}
+08/30/2021 17:13:13 - INFO - __main__ - Step 22383: {'lr': 0.0004769646460384816, 'samples': 4297536, 'steps': 22382, 'loss/train': 2.0891146659851074}
+08/30/2021 17:13:15 - INFO - __main__ - Step 22384: {'lr': 0.00047696242099410307, 'samples': 4297728, 'steps': 22383, 'loss/train': 1.869328498840332}
+08/30/2021 17:13:15 - INFO - __main__ - Step 22385: {'lr': 0.00047696019584745887, 'samples': 4297920, 'steps': 22384, 'loss/train': 1.9483591318130493}
+08/30/2021 17:13:15 - INFO - __main__ - Step 22386: {'lr': 0.00047695797059854996, 'samples': 4298112, 'steps': 22385, 'loss/train': 1.746274471282959}
+08/30/2021 17:13:16 - INFO - __main__ - Step 22387: {'lr': 0.0004769557452473772, 'samples': 4298304, 'steps': 22386, 'loss/train': 2.275529384613037}
+08/30/2021 17:13:16 - INFO - __main__ - Step 22388: {'lr': 0.00047695351979394173, 'samples': 4298496, 'steps': 22387, 'loss/train': 1.8169291019439697}
+08/30/2021 17:13:18 - INFO - __main__ - Step 22389: {'lr': 0.00047695129423824454, 'samples': 4298688, 'steps': 22388, 'loss/train': 2.1064412593841553}
+08/30/2021 17:13:18 - INFO - __main__ - Step 22390: {'lr': 0.0004769490685802865, 'samples': 4298880, 'steps': 22389, 'loss/train': 1.5430718660354614}
+08/30/2021 17:13:18 - INFO - __main__ - Step 22391: {'lr': 0.00047694684282006885, 'samples': 4299072, 'steps': 22390, 'loss/train': 1.8566498756408691}
+08/30/2021 17:13:19 - INFO - __main__ - Step 22392: {'lr': 0.00047694461695759236, 'samples': 4299264, 'steps': 22391, 'loss/train': 1.4858124256134033}
+08/30/2021 17:13:19 - INFO - __main__ - Step 22393: {'lr': 0.00047694239099285815, 'samples': 4299456, 'steps': 22392, 'loss/train': 1.1314911842346191}
+08/30/2021 17:13:21 - INFO - __main__ - Step 22394: {'lr': 0.00047694016492586715, 'samples': 4299648, 'steps': 22393, 'loss/train': 1.2198786735534668}
+08/30/2021 17:13:21 - INFO - __main__ - Step 22395: {'lr': 0.0004769379387566205, 'samples': 4299840, 'steps': 22394, 'loss/train': 2.0493226051330566}
+08/30/2021 17:13:21 - INFO - __main__ - Step 22396: {'lr': 0.000476935712485119, 'samples': 4300032, 'steps': 22395, 'loss/train': 1.9728707075119019}
+08/30/2021 17:13:22 - INFO - __main__ - Step 22397: {'lr': 0.0004769334861113639, 'samples': 4300224, 'steps': 22396, 'loss/train': 1.7758984565734863}
+08/30/2021 17:13:22 - INFO - __main__ - Step 22398: {'lr': 0.000476931259635356, 'samples': 4300416, 'steps': 22397, 'loss/train': 1.9279731512069702}
+08/30/2021 17:13:24 - INFO - __main__ - Step 22399: {'lr': 0.00047692903305709646, 'samples': 4300608, 'steps': 22398, 'loss/train': 1.7467641830444336}
+08/30/2021 17:13:25 - INFO - __main__ - Step 22400: {'lr': 0.0004769268063765861, 'samples': 4300800, 'steps': 22399, 'loss/train': 1.9367769956588745}
+08/30/2021 17:13:25 - INFO - __main__ - Step 22401: {'lr': 0.00047692457959382605, 'samples': 4300992, 'steps': 22400, 'loss/train': 2.1889874935150146}
+08/30/2021 17:13:25 - INFO - __main__ - Step 22402: {'lr': 0.0004769223527088173, 'samples': 4301184, 'steps': 22401, 'loss/train': 3.266441583633423}
+08/30/2021 17:13:26 - INFO - __main__ - Step 22403: {'lr': 0.00047692012572156086, 'samples': 4301376, 'steps': 22402, 'loss/train': 2.4790022373199463}
+08/30/2021 17:13:26 - INFO - __main__ - Step 22404: {'lr': 0.00047691789863205764, 'samples': 4301568, 'steps': 22403, 'loss/train': 1.6065174341201782}
+08/30/2021 17:13:26 - INFO - __main__ - Step 22405: {'lr': 0.0004769156714403088, 'samples': 4301760, 'steps': 22404, 'loss/train': 0.8410873413085938}
+08/30/2021 17:13:28 - INFO - __main__ - Step 22406: {'lr': 0.0004769134441463152, 'samples': 4301952, 'steps': 22405, 'loss/train': 1.2901523113250732}
+08/30/2021 17:13:29 - INFO - __main__ - Step 22407: {'lr': 0.0004769112167500779, 'samples': 4302144, 'steps': 22406, 'loss/train': 1.9885972738265991}
+08/30/2021 17:13:29 - INFO - __main__ - Step 22408: {'lr': 0.00047690898925159796, 'samples': 4302336, 'steps': 22407, 'loss/train': 2.138716697692871}
+08/30/2021 17:13:30 - INFO - __main__ - Step 22409: {'lr': 0.0004769067616508763, 'samples': 4302528, 'steps': 22408, 'loss/train': 1.79085111618042}
+08/30/2021 17:13:30 - INFO - __main__ - Step 22410: {'lr': 0.00047690453394791393, 'samples': 4302720, 'steps': 22409, 'loss/train': 2.0332047939300537}
+08/30/2021 17:13:30 - INFO - __main__ - Step 22411: {'lr': 0.0004769023061427119, 'samples': 4302912, 'steps': 22410, 'loss/train': 1.719641923904419}
+08/30/2021 17:13:32 - INFO - __main__ - Step 22412: {'lr': 0.0004769000782352713, 'samples': 4303104, 'steps': 22411, 'loss/train': 2.0749473571777344}
+08/30/2021 17:13:33 - INFO - __main__ - Step 22413: {'lr': 0.00047689785022559284, 'samples': 4303296, 'steps': 22412, 'loss/train': 2.0759830474853516}
+08/30/2021 17:13:33 - INFO - __main__ - Step 22414: {'lr': 0.0004768956221136778, 'samples': 4303488, 'steps': 22413, 'loss/train': 1.7461432218551636}
+08/30/2021 17:13:33 - INFO - __main__ - Step 22415: {'lr': 0.00047689339389952713, 'samples': 4303680, 'steps': 22414, 'loss/train': 1.7579646110534668}
+08/30/2021 17:13:34 - INFO - __main__ - Step 22416: {'lr': 0.0004768911655831417, 'samples': 4303872, 'steps': 22415, 'loss/train': 2.2065553665161133}
+08/30/2021 17:13:35 - INFO - __main__ - Step 22417: {'lr': 0.0004768889371645227, 'samples': 4304064, 'steps': 22416, 'loss/train': 1.7390761375427246}
+08/30/2021 17:13:36 - INFO - __main__ - Step 22418: {'lr': 0.000476886708643671, 'samples': 4304256, 'steps': 22417, 'loss/train': 1.4862357378005981}
+08/30/2021 17:13:36 - INFO - __main__ - Step 22419: {'lr': 0.0004768844800205877, 'samples': 4304448, 'steps': 22418, 'loss/train': 1.667893648147583}
+08/30/2021 17:13:37 - INFO - __main__ - Step 22420: {'lr': 0.0004768822512952737, 'samples': 4304640, 'steps': 22419, 'loss/train': 1.1174753904342651}
+08/30/2021 17:13:37 - INFO - __main__ - Step 22421: {'lr': 0.0004768800224677301, 'samples': 4304832, 'steps': 22420, 'loss/train': 1.2558841705322266}
+08/30/2021 17:13:39 - INFO - __main__ - Step 22422: {'lr': 0.0004768777935379578, 'samples': 4305024, 'steps': 22421, 'loss/train': 1.9752498865127563}
+08/30/2021 17:13:39 - INFO - __main__ - Step 22423: {'lr': 0.0004768755645059579, 'samples': 4305216, 'steps': 22422, 'loss/train': 1.7126777172088623}
+08/30/2021 17:13:39 - INFO - __main__ - Step 22424: {'lr': 0.00047687333537173136, 'samples': 4305408, 'steps': 22423, 'loss/train': 1.5196870565414429}
+08/30/2021 17:13:40 - INFO - __main__ - Step 22425: {'lr': 0.00047687110613527924, 'samples': 4305600, 'steps': 22424, 'loss/train': 2.162867307662964}
+08/30/2021 17:13:40 - INFO - __main__ - Step 22426: {'lr': 0.00047686887679660253, 'samples': 4305792, 'steps': 22425, 'loss/train': 1.4038060903549194}
+08/30/2021 17:13:42 - INFO - __main__ - Step 22427: {'lr': 0.0004768666473557021, 'samples': 4305984, 'steps': 22426, 'loss/train': 0.17870919406414032}
+08/30/2021 17:13:42 - INFO - __main__ - Step 22428: {'lr': 0.0004768644178125791, 'samples': 4306176, 'steps': 22427, 'loss/train': 1.2794487476348877}
+08/30/2021 17:13:43 - INFO - __main__ - Step 22429: {'lr': 0.0004768621881672345, 'samples': 4306368, 'steps': 22428, 'loss/train': 1.6502145528793335}
+08/30/2021 17:13:43 - INFO - __main__ - Step 22430: {'lr': 0.00047685995841966936, 'samples': 4306560, 'steps': 22429, 'loss/train': 1.9061843156814575}
+08/30/2021 17:13:43 - INFO - __main__ - Step 22431: {'lr': 0.0004768577285698845, 'samples': 4306752, 'steps': 22430, 'loss/train': 1.8811677694320679}
+08/30/2021 17:13:45 - INFO - __main__ - Step 22432: {'lr': 0.00047685549861788113, 'samples': 4306944, 'steps': 22431, 'loss/train': 1.7884986400604248}
+08/30/2021 17:13:45 - INFO - __main__ - Step 22433: {'lr': 0.0004768532685636602, 'samples': 4307136, 'steps': 22432, 'loss/train': 1.5401004552841187}
+08/30/2021 17:13:46 - INFO - __main__ - Step 22434: {'lr': 0.0004768510384072226, 'samples': 4307328, 'steps': 22433, 'loss/train': 1.6148316860198975}
+08/30/2021 17:13:46 - INFO - __main__ - Step 22435: {'lr': 0.0004768488081485695, 'samples': 4307520, 'steps': 22434, 'loss/train': 1.414378046989441}
+08/30/2021 17:13:46 - INFO - __main__ - Step 22436: {'lr': 0.0004768465777877018, 'samples': 4307712, 'steps': 22435, 'loss/train': 1.9817149639129639}
+08/30/2021 17:13:47 - INFO - __main__ - Step 22437: {'lr': 0.0004768443473246205, 'samples': 4307904, 'steps': 22436, 'loss/train': 1.8146398067474365}
+08/30/2021 17:13:48 - INFO - __main__ - Step 22438: {'lr': 0.00047684211675932665, 'samples': 4308096, 'steps': 22437, 'loss/train': 1.8666608333587646}
+08/30/2021 17:13:49 - INFO - __main__ - Step 22439: {'lr': 0.0004768398860918213, 'samples': 4308288, 'steps': 22438, 'loss/train': 2.1716370582580566}
+08/30/2021 17:13:49 - INFO - __main__ - Step 22440: {'lr': 0.0004768376553221053, 'samples': 4308480, 'steps': 22439, 'loss/train': 1.9423466920852661}
+08/30/2021 17:13:49 - INFO - __main__ - Step 22441: {'lr': 0.0004768354244501798, 'samples': 4308672, 'steps': 22440, 'loss/train': 1.6935824155807495}
+08/30/2021 17:13:50 - INFO - __main__ - Step 22442: {'lr': 0.0004768331934760458, 'samples': 4308864, 'steps': 22441, 'loss/train': 1.7347948551177979}
+08/30/2021 17:13:51 - INFO - __main__ - Step 22443: {'lr': 0.00047683096239970423, 'samples': 4309056, 'steps': 22442, 'loss/train': 1.7142823934555054}
+08/30/2021 17:13:52 - INFO - __main__ - Step 22444: {'lr': 0.0004768287312211561, 'samples': 4309248, 'steps': 22443, 'loss/train': 0.21094796061515808}
+08/30/2021 17:13:52 - INFO - __main__ - Step 22445: {'lr': 0.0004768264999404025, 'samples': 4309440, 'steps': 22444, 'loss/train': 1.8671423196792603}
+08/30/2021 17:13:52 - INFO - __main__ - Step 22446: {'lr': 0.00047682426855744434, 'samples': 4309632, 'steps': 22445, 'loss/train': 1.7412782907485962}
+08/30/2021 17:13:53 - INFO - __main__ - Step 22447: {'lr': 0.00047682203707228264, 'samples': 4309824, 'steps': 22446, 'loss/train': 1.6040568351745605}
+08/30/2021 17:13:55 - INFO - __main__ - Step 22448: {'lr': 0.00047681980548491853, 'samples': 4310016, 'steps': 22447, 'loss/train': 1.5771088600158691}
+08/30/2021 17:13:55 - INFO - __main__ - Step 22449: {'lr': 0.00047681757379535285, 'samples': 4310208, 'steps': 22448, 'loss/train': 1.3620716333389282}
+08/30/2021 17:13:55 - INFO - __main__ - Step 22450: {'lr': 0.00047681534200358665, 'samples': 4310400, 'steps': 22449, 'loss/train': 1.7939502000808716}
+08/30/2021 17:13:56 - INFO - __main__ - Step 22451: {'lr': 0.000476813110109621, 'samples': 4310592, 'steps': 22450, 'loss/train': 1.5142356157302856}
+08/30/2021 17:13:56 - INFO - __main__ - Step 22452: {'lr': 0.0004768108781134568, 'samples': 4310784, 'steps': 22451, 'loss/train': 3.149855375289917}
+08/30/2021 17:13:56 - INFO - __main__ - Step 22453: {'lr': 0.0004768086460150952, 'samples': 4310976, 'steps': 22452, 'loss/train': 1.7269551753997803}
+08/30/2021 17:13:58 - INFO - __main__ - Step 22454: {'lr': 0.00047680641381453703, 'samples': 4311168, 'steps': 22453, 'loss/train': 0.6760121583938599}
+08/30/2021 17:13:58 - INFO - __main__ - Step 22455: {'lr': 0.0004768041815117835, 'samples': 4311360, 'steps': 22454, 'loss/train': 1.962514042854309}
+08/30/2021 17:13:59 - INFO - __main__ - Step 22456: {'lr': 0.00047680194910683545, 'samples': 4311552, 'steps': 22455, 'loss/train': 1.614229679107666}
+08/30/2021 17:13:59 - INFO - __main__ - Step 22457: {'lr': 0.0004767997165996939, 'samples': 4311744, 'steps': 22456, 'loss/train': 1.7352981567382812}
+08/30/2021 17:13:59 - INFO - __main__ - Step 22458: {'lr': 0.00047679748399035994, 'samples': 4311936, 'steps': 22457, 'loss/train': 1.9201675653457642}
+08/30/2021 17:14:01 - INFO - __main__ - Step 22459: {'lr': 0.00047679525127883456, 'samples': 4312128, 'steps': 22458, 'loss/train': 2.225206136703491}
+08/30/2021 17:14:01 - INFO - __main__ - Step 22460: {'lr': 0.0004767930184651187, 'samples': 4312320, 'steps': 22459, 'loss/train': 1.8964154720306396}
+08/30/2021 17:14:02 - INFO - __main__ - Step 22461: {'lr': 0.0004767907855492134, 'samples': 4312512, 'steps': 22460, 'loss/train': 2.0226051807403564}
+08/30/2021 17:14:02 - INFO - __main__ - Step 22462: {'lr': 0.0004767885525311197, 'samples': 4312704, 'steps': 22461, 'loss/train': 1.9483298063278198}
+08/30/2021 17:14:02 - INFO - __main__ - Step 22463: {'lr': 0.0004767863194108386, 'samples': 4312896, 'steps': 22462, 'loss/train': 1.5516774654388428}
+08/30/2021 17:14:04 - INFO - __main__ - Step 22464: {'lr': 0.000476784086188371, 'samples': 4313088, 'steps': 22463, 'loss/train': 2.108454465866089}
+08/30/2021 17:14:05 - INFO - __main__ - Step 22465: {'lr': 0.00047678185286371803, 'samples': 4313280, 'steps': 22464, 'loss/train': 1.8621517419815063}
+08/30/2021 17:14:05 - INFO - __main__ - Step 22466: {'lr': 0.0004767796194368807, 'samples': 4313472, 'steps': 22465, 'loss/train': 2.0400550365448}
+08/30/2021 17:14:06 - INFO - __main__ - Step 22467: {'lr': 0.00047677738590786, 'samples': 4313664, 'steps': 22466, 'loss/train': 5.935624599456787}
+08/30/2021 17:14:06 - INFO - __main__ - Step 22468: {'lr': 0.0004767751522766568, 'samples': 4313856, 'steps': 22467, 'loss/train': 1.3310096263885498}
+08/30/2021 17:14:08 - INFO - __main__ - Step 22469: {'lr': 0.00047677291854327224, 'samples': 4314048, 'steps': 22468, 'loss/train': 1.2661097049713135}
+08/30/2021 17:14:08 - INFO - __main__ - Step 22470: {'lr': 0.00047677068470770737, 'samples': 4314240, 'steps': 22469, 'loss/train': 1.8714877367019653}
+08/30/2021 17:14:08 - INFO - __main__ - Step 22471: {'lr': 0.00047676845076996305, 'samples': 4314432, 'steps': 22470, 'loss/train': 1.7654696702957153}
+08/30/2021 17:14:09 - INFO - __main__ - Step 22472: {'lr': 0.0004767662167300404, 'samples': 4314624, 'steps': 22471, 'loss/train': 0.48746439814567566}
+08/30/2021 17:14:09 - INFO - __main__ - Step 22473: {'lr': 0.0004767639825879404, 'samples': 4314816, 'steps': 22472, 'loss/train': 1.8187942504882812}
+08/30/2021 17:14:09 - INFO - __main__ - Step 22474: {'lr': 0.000476761748343664, 'samples': 4315008, 'steps': 22473, 'loss/train': 0.5924195647239685}
+08/30/2021 17:14:11 - INFO - __main__ - Step 22475: {'lr': 0.00047675951399721235, 'samples': 4315200, 'steps': 22474, 'loss/train': 1.7742091417312622}
+08/30/2021 17:14:11 - INFO - __main__ - Step 22476: {'lr': 0.0004767572795485863, 'samples': 4315392, 'steps': 22475, 'loss/train': 1.7919718027114868}
+08/30/2021 17:14:12 - INFO - __main__ - Step 22477: {'lr': 0.00047675504499778695, 'samples': 4315584, 'steps': 22476, 'loss/train': 2.61266827583313}
+08/30/2021 17:14:12 - INFO - __main__ - Step 22478: {'lr': 0.0004767528103448152, 'samples': 4315776, 'steps': 22477, 'loss/train': 1.3702067136764526}
+08/30/2021 17:14:12 - INFO - __main__ - Step 22479: {'lr': 0.00047675057558967224, 'samples': 4315968, 'steps': 22478, 'loss/train': 1.984159231185913}
+08/30/2021 17:14:14 - INFO - __main__ - Step 22480: {'lr': 0.0004767483407323589, 'samples': 4316160, 'steps': 22479, 'loss/train': 2.2095019817352295}
+08/30/2021 17:14:14 - INFO - __main__ - Step 22481: {'lr': 0.00047674610577287625, 'samples': 4316352, 'steps': 22480, 'loss/train': 1.7467973232269287}
+08/30/2021 17:14:15 - INFO - __main__ - Step 22482: {'lr': 0.00047674387071122536, 'samples': 4316544, 'steps': 22481, 'loss/train': 1.6091501712799072}
+08/30/2021 17:14:15 - INFO - __main__ - Step 22483: {'lr': 0.0004767416355474071, 'samples': 4316736, 'steps': 22482, 'loss/train': 1.6895766258239746}
+08/30/2021 17:14:15 - INFO - __main__ - Step 22484: {'lr': 0.00047673940028142265, 'samples': 4316928, 'steps': 22483, 'loss/train': 1.633849024772644}
+08/30/2021 17:14:17 - INFO - __main__ - Step 22485: {'lr': 0.0004767371649132729, 'samples': 4317120, 'steps': 22484, 'loss/train': 1.660505771636963}
+08/30/2021 17:14:17 - INFO - __main__ - Step 22486: {'lr': 0.00047673492944295883, 'samples': 4317312, 'steps': 22485, 'loss/train': 1.2509496212005615}
+08/30/2021 17:14:18 - INFO - __main__ - Step 22487: {'lr': 0.0004767326938704816, 'samples': 4317504, 'steps': 22486, 'loss/train': 1.9188863039016724}
+08/30/2021 17:14:18 - INFO - __main__ - Step 22488: {'lr': 0.00047673045819584197, 'samples': 4317696, 'steps': 22487, 'loss/train': 1.0761938095092773}
+08/30/2021 17:14:18 - INFO - __main__ - Step 22489: {'lr': 0.0004767282224190412, 'samples': 4317888, 'steps': 22488, 'loss/train': 1.7531883716583252}
+08/30/2021 17:14:20 - INFO - __main__ - Step 22490: {'lr': 0.00047672598654008015, 'samples': 4318080, 'steps': 22489, 'loss/train': 1.7927989959716797}
+08/30/2021 17:14:20 - INFO - __main__ - Step 22491: {'lr': 0.0004767237505589599, 'samples': 4318272, 'steps': 22490, 'loss/train': 1.0618451833724976}
+08/30/2021 17:14:21 - INFO - __main__ - Step 22492: {'lr': 0.0004767215144756814, 'samples': 4318464, 'steps': 22491, 'loss/train': 1.719399094581604}
+08/30/2021 17:14:21 - INFO - __main__ - Step 22493: {'lr': 0.0004767192782902457, 'samples': 4318656, 'steps': 22492, 'loss/train': 1.0271601676940918}
+08/30/2021 17:14:21 - INFO - __main__ - Step 22494: {'lr': 0.0004767170420026538, 'samples': 4318848, 'steps': 22493, 'loss/train': 0.9355188012123108}
+08/30/2021 17:14:23 - INFO - __main__ - Step 22495: {'lr': 0.0004767148056129067, 'samples': 4319040, 'steps': 22494, 'loss/train': 2.2111897468566895}
+08/30/2021 17:14:23 - INFO - __main__ - Step 22496: {'lr': 0.0004767125691210054, 'samples': 4319232, 'steps': 22495, 'loss/train': 1.777457356452942}
+08/30/2021 17:14:24 - INFO - __main__ - Step 22497: {'lr': 0.00047671033252695083, 'samples': 4319424, 'steps': 22496, 'loss/train': 1.7731730937957764}
+08/30/2021 17:14:24 - INFO - __main__ - Step 22498: {'lr': 0.0004767080958307442, 'samples': 4319616, 'steps': 22497, 'loss/train': 1.4276859760284424}
+08/30/2021 17:14:24 - INFO - __main__ - Step 22499: {'lr': 0.0004767058590323864, 'samples': 4319808, 'steps': 22498, 'loss/train': 1.6239917278289795}
+08/30/2021 17:14:26 - INFO - __main__ - Step 22500: {'lr': 0.00047670362213187833, 'samples': 4320000, 'steps': 22499, 'loss/train': 1.0119229555130005}
+08/30/2021 17:14:27 - INFO - __main__ - Step 22501: {'lr': 0.0004767013851292212, 'samples': 4320192, 'steps': 22500, 'loss/train': 1.2648358345031738}
+08/30/2021 17:14:27 - INFO - __main__ - Step 22502: {'lr': 0.0004766991480244159, 'samples': 4320384, 'steps': 22501, 'loss/train': 0.3033278286457062}
+08/30/2021 17:14:28 - INFO - __main__ - Step 22503: {'lr': 0.0004766969108174635, 'samples': 4320576, 'steps': 22502, 'loss/train': 0.16322974860668182}
+08/30/2021 17:14:28 - INFO - __main__ - Step 22504: {'lr': 0.0004766946735083649, 'samples': 4320768, 'steps': 22503, 'loss/train': 1.9770796298980713}
+08/30/2021 17:14:30 - INFO - __main__ - Step 22505: {'lr': 0.0004766924360971212, 'samples': 4320960, 'steps': 22504, 'loss/train': 1.3510984182357788}
+08/30/2021 17:14:30 - INFO - __main__ - Step 22506: {'lr': 0.00047669019858373343, 'samples': 4321152, 'steps': 22505, 'loss/train': 1.9653582572937012}
+08/30/2021 17:14:30 - INFO - __main__ - Step 22507: {'lr': 0.00047668796096820247, 'samples': 4321344, 'steps': 22506, 'loss/train': 0.5082666277885437}
+08/30/2021 17:14:31 - INFO - __main__ - Step 22508: {'lr': 0.00047668572325052953, 'samples': 4321536, 'steps': 22507, 'loss/train': 1.9479482173919678}
+08/30/2021 17:14:31 - INFO - __main__ - Step 22509: {'lr': 0.00047668348543071536, 'samples': 4321728, 'steps': 22508, 'loss/train': 1.757729172706604}
+08/30/2021 17:14:31 - INFO - __main__ - Step 22510: {'lr': 0.00047668124750876117, 'samples': 4321920, 'steps': 22509, 'loss/train': 3.3465144634246826}
+08/30/2021 17:14:33 - INFO - __main__ - Step 22511: {'lr': 0.0004766790094846679, 'samples': 4322112, 'steps': 22510, 'loss/train': 2.3180856704711914}
+08/30/2021 17:14:34 - INFO - __main__ - Step 22512: {'lr': 0.0004766767713584367, 'samples': 4322304, 'steps': 22511, 'loss/train': 1.4776660203933716}
+08/30/2021 17:14:34 - INFO - __main__ - Step 22513: {'lr': 0.00047667453313006826, 'samples': 4322496, 'steps': 22512, 'loss/train': 1.8642196655273438}
+08/30/2021 17:14:34 - INFO - __main__ - Step 22514: {'lr': 0.00047667229479956386, 'samples': 4322688, 'steps': 22513, 'loss/train': 1.3936805725097656}
+08/30/2021 17:14:35 - INFO - __main__ - Step 22515: {'lr': 0.0004766700563669244, 'samples': 4322880, 'steps': 22514, 'loss/train': 1.9357175827026367}
+08/30/2021 17:14:35 - INFO - __main__ - Step 22516: {'lr': 0.0004766678178321509, 'samples': 4323072, 'steps': 22515, 'loss/train': 0.9189608097076416}
+08/30/2021 17:14:37 - INFO - __main__ - Step 22517: {'lr': 0.0004766655791952444, 'samples': 4323264, 'steps': 22516, 'loss/train': 1.9477885961532593}
+08/30/2021 17:14:38 - INFO - __main__ - Step 22518: {'lr': 0.0004766633404562059, 'samples': 4323456, 'steps': 22517, 'loss/train': 0.5487386584281921}
+08/30/2021 17:14:38 - INFO - __main__ - Step 22519: {'lr': 0.0004766611016150364, 'samples': 4323648, 'steps': 22518, 'loss/train': 1.230427861213684}
+08/30/2021 17:14:38 - INFO - __main__ - Step 22520: {'lr': 0.00047665886267173686, 'samples': 4323840, 'steps': 22519, 'loss/train': 1.2861769199371338}
+08/30/2021 17:14:39 - INFO - __main__ - Step 22521: {'lr': 0.00047665662362630836, 'samples': 4324032, 'steps': 22520, 'loss/train': 1.6450291872024536}
+08/30/2021 17:14:40 - INFO - __main__ - Step 22522: {'lr': 0.00047665438447875186, 'samples': 4324224, 'steps': 22521, 'loss/train': 1.6257888078689575}
+08/30/2021 17:14:41 - INFO - __main__ - Step 22523: {'lr': 0.0004766521452290684, 'samples': 4324416, 'steps': 22522, 'loss/train': 2.009296417236328}
+08/30/2021 17:14:41 - INFO - __main__ - Step 22524: {'lr': 0.00047664990587725905, 'samples': 4324608, 'steps': 22523, 'loss/train': 1.138895034790039}
+08/30/2021 17:14:41 - INFO - __main__ - Step 22525: {'lr': 0.0004766476664233247, 'samples': 4324800, 'steps': 22524, 'loss/train': 1.378551959991455}
+08/30/2021 17:14:42 - INFO - __main__ - Step 22526: {'lr': 0.0004766454268672664, 'samples': 4324992, 'steps': 22525, 'loss/train': 1.2025744915008545}
+08/30/2021 17:14:42 - INFO - __main__ - Step 22527: {'lr': 0.00047664318720908516, 'samples': 4325184, 'steps': 22526, 'loss/train': 2.2128894329071045}
+08/30/2021 17:14:44 - INFO - __main__ - Step 22528: {'lr': 0.000476640947448782, 'samples': 4325376, 'steps': 22527, 'loss/train': 2.173571825027466}
+08/30/2021 17:14:44 - INFO - __main__ - Step 22529: {'lr': 0.000476638707586358, 'samples': 4325568, 'steps': 22528, 'loss/train': 1.637187123298645}
+08/30/2021 17:14:44 - INFO - __main__ - Step 22530: {'lr': 0.000476636467621814, 'samples': 4325760, 'steps': 22529, 'loss/train': 1.5273845195770264}
+08/30/2021 17:14:45 - INFO - __main__ - Step 22531: {'lr': 0.00047663422755515113, 'samples': 4325952, 'steps': 22530, 'loss/train': 1.323721170425415}
+08/30/2021 17:14:45 - INFO - __main__ - Step 22532: {'lr': 0.00047663198738637035, 'samples': 4326144, 'steps': 22531, 'loss/train': 1.6435048580169678}
+08/30/2021 17:14:47 - INFO - __main__ - Step 22533: {'lr': 0.00047662974711547274, 'samples': 4326336, 'steps': 22532, 'loss/train': 1.8532849550247192}
+08/30/2021 17:14:47 - INFO - __main__ - Step 22534: {'lr': 0.0004766275067424593, 'samples': 4326528, 'steps': 22533, 'loss/train': 1.458275318145752}
+08/30/2021 17:14:47 - INFO - __main__ - Step 22535: {'lr': 0.0004766252662673309, 'samples': 4326720, 'steps': 22534, 'loss/train': 1.8849378824234009}
+08/30/2021 17:14:48 - INFO - __main__ - Step 22536: {'lr': 0.0004766230256900887, 'samples': 4326912, 'steps': 22535, 'loss/train': 1.1653574705123901}
+08/30/2021 17:14:48 - INFO - __main__ - Step 22537: {'lr': 0.0004766207850107337, 'samples': 4327104, 'steps': 22536, 'loss/train': 1.4604711532592773}
+08/30/2021 17:14:50 - INFO - __main__ - Step 22538: {'lr': 0.00047661854422926674, 'samples': 4327296, 'steps': 22537, 'loss/train': 2.063953161239624}
+08/30/2021 17:14:50 - INFO - __main__ - Step 22539: {'lr': 0.0004766163033456891, 'samples': 4327488, 'steps': 22538, 'loss/train': 1.9041965007781982}
+08/30/2021 17:14:51 - INFO - __main__ - Step 22540: {'lr': 0.0004766140623600016, 'samples': 4327680, 'steps': 22539, 'loss/train': 1.9534395933151245}
+08/30/2021 17:14:51 - INFO - __main__ - Step 22541: {'lr': 0.0004766118212722053, 'samples': 4327872, 'steps': 22540, 'loss/train': 0.12554432451725006}
+08/30/2021 17:14:51 - INFO - __main__ - Step 22542: {'lr': 0.0004766095800823013, 'samples': 4328064, 'steps': 22541, 'loss/train': 2.0189404487609863}
+08/30/2021 17:14:53 - INFO - __main__ - Step 22543: {'lr': 0.0004766073387902904, 'samples': 4328256, 'steps': 22542, 'loss/train': 0.27141886949539185}
+08/30/2021 17:14:53 - INFO - __main__ - Step 22544: {'lr': 0.00047660509739617376, 'samples': 4328448, 'steps': 22543, 'loss/train': 1.2854547500610352}
+08/30/2021 17:14:54 - INFO - __main__ - Step 22545: {'lr': 0.00047660285589995233, 'samples': 4328640, 'steps': 22544, 'loss/train': 1.238966703414917}
+08/30/2021 17:14:54 - INFO - __main__ - Step 22546: {'lr': 0.0004766006143016272, 'samples': 4328832, 'steps': 22545, 'loss/train': 2.324779510498047}
+08/30/2021 17:14:54 - INFO - __main__ - Step 22547: {'lr': 0.0004765983726011993, 'samples': 4329024, 'steps': 22546, 'loss/train': 1.4933652877807617}
+08/30/2021 17:14:56 - INFO - __main__ - Step 22548: {'lr': 0.0004765961307986697, 'samples': 4329216, 'steps': 22547, 'loss/train': 1.3241190910339355}
+08/30/2021 17:14:56 - INFO - __main__ - Step 22549: {'lr': 0.0004765938888940393, 'samples': 4329408, 'steps': 22548, 'loss/train': 1.0358211994171143}
+08/30/2021 17:14:57 - INFO - __main__ - Step 22550: {'lr': 0.00047659164688730935, 'samples': 4329600, 'steps': 22549, 'loss/train': 1.617812156677246}
+08/30/2021 17:14:57 - INFO - __main__ - Step 22551: {'lr': 0.00047658940477848056, 'samples': 4329792, 'steps': 22550, 'loss/train': 1.7339508533477783}
+08/30/2021 17:14:57 - INFO - __main__ - Step 22552: {'lr': 0.00047658716256755414, 'samples': 4329984, 'steps': 22551, 'loss/train': 1.7117106914520264}
+08/30/2021 17:14:58 - INFO - __main__ - Step 22553: {'lr': 0.00047658492025453106, 'samples': 4330176, 'steps': 22552, 'loss/train': 1.3234061002731323}
+08/30/2021 17:14:59 - INFO - __main__ - Step 22554: {'lr': 0.00047658267783941223, 'samples': 4330368, 'steps': 22553, 'loss/train': 1.2777682542800903}
+08/30/2021 17:14:59 - INFO - __main__ - Step 22555: {'lr': 0.0004765804353221988, 'samples': 4330560, 'steps': 22554, 'loss/train': 2.290679693222046}
+08/30/2021 17:15:00 - INFO - __main__ - Step 22556: {'lr': 0.0004765781927028917, 'samples': 4330752, 'steps': 22555, 'loss/train': 1.369117259979248}
+08/30/2021 17:15:00 - INFO - __main__ - Step 22557: {'lr': 0.000476575949981492, 'samples': 4330944, 'steps': 22556, 'loss/train': 1.2444427013397217}
+08/30/2021 17:15:00 - INFO - __main__ - Step 22558: {'lr': 0.00047657370715800066, 'samples': 4331136, 'steps': 22557, 'loss/train': 2.076911687850952}
+08/30/2021 17:15:02 - INFO - __main__ - Step 22559: {'lr': 0.0004765714642324187, 'samples': 4331328, 'steps': 22558, 'loss/train': 1.3288944959640503}
+08/30/2021 17:15:02 - INFO - __main__ - Step 22560: {'lr': 0.0004765692212047471, 'samples': 4331520, 'steps': 22559, 'loss/train': 1.579010248184204}
+08/30/2021 17:15:03 - INFO - __main__ - Step 22561: {'lr': 0.00047656697807498693, 'samples': 4331712, 'steps': 22560, 'loss/train': 1.5661537647247314}
+08/30/2021 17:15:03 - INFO - __main__ - Step 22562: {'lr': 0.0004765647348431392, 'samples': 4331904, 'steps': 22561, 'loss/train': 1.6125584840774536}
+08/30/2021 17:15:03 - INFO - __main__ - Step 22563: {'lr': 0.00047656249150920485, 'samples': 4332096, 'steps': 22562, 'loss/train': 2.1038525104522705}
+08/30/2021 17:15:06 - INFO - __main__ - Step 22564: {'lr': 0.000476560248073185, 'samples': 4332288, 'steps': 22563, 'loss/train': 1.730812430381775}
+08/30/2021 17:15:06 - INFO - __main__ - Step 22565: {'lr': 0.0004765580045350805, 'samples': 4332480, 'steps': 22564, 'loss/train': 1.7798317670822144}
+08/30/2021 17:15:06 - INFO - __main__ - Step 22566: {'lr': 0.00047655576089489254, 'samples': 4332672, 'steps': 22565, 'loss/train': 1.7542918920516968}
+08/30/2021 17:15:07 - INFO - __main__ - Step 22567: {'lr': 0.00047655351715262205, 'samples': 4332864, 'steps': 22566, 'loss/train': 1.4907829761505127}
+08/30/2021 17:15:07 - INFO - __main__ - Step 22568: {'lr': 0.00047655127330827, 'samples': 4333056, 'steps': 22567, 'loss/train': 3.5989739894866943}
+08/30/2021 17:15:07 - INFO - __main__ - Step 22569: {'lr': 0.00047654902936183745, 'samples': 4333248, 'steps': 22568, 'loss/train': 3.7340481281280518}
+08/30/2021 17:15:08 - INFO - __main__ - Step 22570: {'lr': 0.00047654678531332544, 'samples': 4333440, 'steps': 22569, 'loss/train': 4.774858474731445}
+08/30/2021 17:15:09 - INFO - __main__ - Step 22571: {'lr': 0.00047654454116273493, 'samples': 4333632, 'steps': 22570, 'loss/train': 1.9201209545135498}
+08/30/2021 17:15:10 - INFO - __main__ - Step 22572: {'lr': 0.0004765422969100669, 'samples': 4333824, 'steps': 22571, 'loss/train': 1.6501644849777222}
+08/30/2021 17:15:10 - INFO - __main__ - Step 22573: {'lr': 0.00047654005255532247, 'samples': 4334016, 'steps': 22572, 'loss/train': 1.9358325004577637}
+08/30/2021 17:15:10 - INFO - __main__ - Step 22574: {'lr': 0.0004765378080985026, 'samples': 4334208, 'steps': 22573, 'loss/train': 1.5381373167037964}
+08/30/2021 17:15:11 - INFO - __main__ - Step 22575: {'lr': 0.00047653556353960825, 'samples': 4334400, 'steps': 22574, 'loss/train': 1.7209357023239136}
+08/30/2021 17:15:13 - INFO - __main__ - Step 22576: {'lr': 0.0004765333188786404, 'samples': 4334592, 'steps': 22575, 'loss/train': 1.5887960195541382}
+08/30/2021 17:15:13 - INFO - __main__ - Step 22577: {'lr': 0.00047653107411560025, 'samples': 4334784, 'steps': 22576, 'loss/train': 2.440398931503296}
+08/30/2021 17:15:14 - INFO - __main__ - Step 22578: {'lr': 0.00047652882925048863, 'samples': 4334976, 'steps': 22577, 'loss/train': 1.467909336090088}
+08/30/2021 17:15:14 - INFO - __main__ - Step 22579: {'lr': 0.00047652658428330664, 'samples': 4335168, 'steps': 22578, 'loss/train': 1.7069509029388428}
+08/30/2021 17:15:14 - INFO - __main__ - Step 22580: {'lr': 0.00047652433921405526, 'samples': 4335360, 'steps': 22579, 'loss/train': 1.4549226760864258}
+08/30/2021 17:15:16 - INFO - __main__ - Step 22581: {'lr': 0.0004765220940427355, 'samples': 4335552, 'steps': 22580, 'loss/train': 1.1382648944854736}
+08/30/2021 17:15:16 - INFO - __main__ - Step 22582: {'lr': 0.0004765198487693484, 'samples': 4335744, 'steps': 22581, 'loss/train': 1.7741187810897827}
+08/30/2021 17:15:17 - INFO - __main__ - Step 22583: {'lr': 0.00047651760339389494, 'samples': 4335936, 'steps': 22582, 'loss/train': 3.3371052742004395}
+08/30/2021 17:15:17 - INFO - __main__ - Step 22584: {'lr': 0.0004765153579163761, 'samples': 4336128, 'steps': 22583, 'loss/train': 0.11780780553817749}
+08/30/2021 17:15:17 - INFO - __main__ - Step 22585: {'lr': 0.000476513112336793, 'samples': 4336320, 'steps': 22584, 'loss/train': 1.8284790515899658}
+08/30/2021 17:15:18 - INFO - __main__ - Step 22586: {'lr': 0.00047651086665514655, 'samples': 4336512, 'steps': 22585, 'loss/train': 1.7586549520492554}
+08/30/2021 17:15:19 - INFO - __main__ - Step 22587: {'lr': 0.00047650862087143787, 'samples': 4336704, 'steps': 22586, 'loss/train': 1.6524969339370728}
+08/30/2021 17:15:20 - INFO - __main__ - Step 22588: {'lr': 0.0004765063749856678, 'samples': 4336896, 'steps': 22587, 'loss/train': 1.9591922760009766}
+08/30/2021 17:15:20 - INFO - __main__ - Step 22589: {'lr': 0.00047650412899783747, 'samples': 4337088, 'steps': 22588, 'loss/train': 2.1798973083496094}
+08/30/2021 17:15:21 - INFO - __main__ - Step 22590: {'lr': 0.0004765018829079479, 'samples': 4337280, 'steps': 22589, 'loss/train': 2.203218698501587}
+08/30/2021 17:15:21 - INFO - __main__ - Step 22591: {'lr': 0.0004764996367160001, 'samples': 4337472, 'steps': 22590, 'loss/train': 1.7837680578231812}
+08/30/2021 17:15:22 - INFO - __main__ - Step 22592: {'lr': 0.000476497390421995, 'samples': 4337664, 'steps': 22591, 'loss/train': 1.498328447341919}
+08/30/2021 17:15:23 - INFO - __main__ - Step 22593: {'lr': 0.00047649514402593377, 'samples': 4337856, 'steps': 22592, 'loss/train': 1.4952605962753296}
+08/30/2021 17:15:23 - INFO - __main__ - Step 22594: {'lr': 0.0004764928975278172, 'samples': 4338048, 'steps': 22593, 'loss/train': 1.6838277578353882}
+08/30/2021 17:15:24 - INFO - __main__ - Step 22595: {'lr': 0.0004764906509276465, 'samples': 4338240, 'steps': 22594, 'loss/train': 2.1396031379699707}
+08/30/2021 17:15:24 - INFO - __main__ - Step 22596: {'lr': 0.0004764884042254226, 'samples': 4338432, 'steps': 22595, 'loss/train': 1.8890920877456665}
+08/30/2021 17:15:25 - INFO - __main__ - Step 22597: {'lr': 0.0004764861574211465, 'samples': 4338624, 'steps': 22596, 'loss/train': 1.6218863725662231}
+08/30/2021 17:15:26 - INFO - __main__ - Step 22598: {'lr': 0.0004764839105148193, 'samples': 4338816, 'steps': 22597, 'loss/train': 1.2731597423553467}
+08/30/2021 17:15:26 - INFO - __main__ - Step 22599: {'lr': 0.00047648166350644185, 'samples': 4339008, 'steps': 22598, 'loss/train': 1.2360286712646484}
+08/30/2021 17:15:26 - INFO - __main__ - Step 22600: {'lr': 0.00047647941639601535, 'samples': 4339200, 'steps': 22599, 'loss/train': 1.8576124906539917}
+08/30/2021 17:15:27 - INFO - __main__ - Step 22601: {'lr': 0.00047647716918354066, 'samples': 4339392, 'steps': 22600, 'loss/train': 2.1882736682891846}
+08/30/2021 17:15:28 - INFO - __main__ - Step 22602: {'lr': 0.00047647492186901884, 'samples': 4339584, 'steps': 22601, 'loss/train': 2.1269142627716064}
+08/30/2021 17:15:29 - INFO - __main__ - Step 22603: {'lr': 0.0004764726744524509, 'samples': 4339776, 'steps': 22602, 'loss/train': 1.6733989715576172}
+08/30/2021 17:15:29 - INFO - __main__ - Step 22604: {'lr': 0.0004764704269338379, 'samples': 4339968, 'steps': 22603, 'loss/train': 1.9329251050949097}
+08/30/2021 17:15:30 - INFO - __main__ - Step 22605: {'lr': 0.00047646817931318086, 'samples': 4340160, 'steps': 22604, 'loss/train': 1.058057427406311}
+08/30/2021 17:15:30 - INFO - __main__ - Step 22606: {'lr': 0.0004764659315904807, 'samples': 4340352, 'steps': 22605, 'loss/train': 0.18052689731121063}
+08/30/2021 17:15:32 - INFO - __main__ - Step 22607: {'lr': 0.0004764636837657385, 'samples': 4340544, 'steps': 22606, 'loss/train': 0.8237510919570923}
+08/30/2021 17:15:32 - INFO - __main__ - Step 22608: {'lr': 0.0004764614358389553, 'samples': 4340736, 'steps': 22607, 'loss/train': 1.9010093212127686}
+08/30/2021 17:15:33 - INFO - __main__ - Step 22609: {'lr': 0.00047645918781013196, 'samples': 4340928, 'steps': 22608, 'loss/train': 2.0348987579345703}
+08/30/2021 17:15:33 - INFO - __main__ - Step 22610: {'lr': 0.0004764569396792697, 'samples': 4341120, 'steps': 22609, 'loss/train': 1.808739185333252}
+08/30/2021 17:15:33 - INFO - __main__ - Step 22611: {'lr': 0.0004764546914463694, 'samples': 4341312, 'steps': 22610, 'loss/train': 0.1274918168783188}
+08/30/2021 17:15:35 - INFO - __main__ - Step 22612: {'lr': 0.0004764524431114321, 'samples': 4341504, 'steps': 22611, 'loss/train': 1.0096627473831177}
+08/30/2021 17:15:35 - INFO - __main__ - Step 22613: {'lr': 0.0004764501946744589, 'samples': 4341696, 'steps': 22612, 'loss/train': 1.1949007511138916}
+08/30/2021 17:15:36 - INFO - __main__ - Step 22614: {'lr': 0.00047644794613545065, 'samples': 4341888, 'steps': 22613, 'loss/train': 1.3782620429992676}
+08/30/2021 17:15:36 - INFO - __main__ - Step 22615: {'lr': 0.00047644569749440846, 'samples': 4342080, 'steps': 22614, 'loss/train': 1.6585488319396973}
+08/30/2021 17:15:36 - INFO - __main__ - Step 22616: {'lr': 0.0004764434487513334, 'samples': 4342272, 'steps': 22615, 'loss/train': 1.5861353874206543}
+08/30/2021 17:15:37 - INFO - __main__ - Step 22617: {'lr': 0.00047644119990622637, 'samples': 4342464, 'steps': 22616, 'loss/train': 2.112118721008301}
+08/30/2021 17:15:38 - INFO - __main__ - Step 22618: {'lr': 0.0004764389509590884, 'samples': 4342656, 'steps': 22617, 'loss/train': 1.8465508222579956}
+08/30/2021 17:15:39 - INFO - __main__ - Step 22619: {'lr': 0.0004764367019099206, 'samples': 4342848, 'steps': 22618, 'loss/train': 0.16180749237537384}
+08/30/2021 17:15:39 - INFO - __main__ - Step 22620: {'lr': 0.0004764344527587239, 'samples': 4343040, 'steps': 22619, 'loss/train': 1.7559525966644287}
+08/30/2021 17:15:39 - INFO - __main__ - Step 22621: {'lr': 0.00047643220350549934, 'samples': 4343232, 'steps': 22620, 'loss/train': 1.9561069011688232}
+08/30/2021 17:15:40 - INFO - __main__ - Step 22622: {'lr': 0.0004764299541502478, 'samples': 4343424, 'steps': 22621, 'loss/train': 1.8269357681274414}
+08/30/2021 17:15:41 - INFO - __main__ - Step 22623: {'lr': 0.0004764277046929706, 'samples': 4343616, 'steps': 22622, 'loss/train': 1.68116295337677}
+08/30/2021 17:15:42 - INFO - __main__ - Step 22624: {'lr': 0.00047642545513366843, 'samples': 4343808, 'steps': 22623, 'loss/train': 0.982194185256958}
+08/30/2021 17:15:42 - INFO - __main__ - Step 22625: {'lr': 0.0004764232054723425, 'samples': 4344000, 'steps': 22624, 'loss/train': 0.14288485050201416}
+08/30/2021 17:15:43 - INFO - __main__ - Step 22626: {'lr': 0.0004764209557089938, 'samples': 4344192, 'steps': 22625, 'loss/train': 1.557816743850708}
+08/30/2021 17:15:43 - INFO - __main__ - Step 22627: {'lr': 0.00047641870584362323, 'samples': 4344384, 'steps': 22626, 'loss/train': 1.734743595123291}
+08/30/2021 17:15:45 - INFO - __main__ - Step 22628: {'lr': 0.00047641645587623196, 'samples': 4344576, 'steps': 22627, 'loss/train': 2.719785213470459}
+08/30/2021 17:15:46 - INFO - __main__ - Step 22629: {'lr': 0.0004764142058068209, 'samples': 4344768, 'steps': 22628, 'loss/train': 1.2836214303970337}
+08/30/2021 17:15:46 - INFO - __main__ - Step 22630: {'lr': 0.00047641195563539107, 'samples': 4344960, 'steps': 22629, 'loss/train': 1.551599383354187}
+08/30/2021 17:15:47 - INFO - __main__ - Step 22631: {'lr': 0.0004764097053619435, 'samples': 4345152, 'steps': 22630, 'loss/train': 1.526296854019165}
+08/30/2021 17:15:47 - INFO - __main__ - Step 22632: {'lr': 0.00047640745498647925, 'samples': 4345344, 'steps': 22631, 'loss/train': 3.1410653591156006}
+08/30/2021 17:15:47 - INFO - __main__ - Step 22633: {'lr': 0.00047640520450899926, 'samples': 4345536, 'steps': 22632, 'loss/train': 3.2670083045959473}
+08/30/2021 17:15:49 - INFO - __main__ - Step 22634: {'lr': 0.0004764029539295046, 'samples': 4345728, 'steps': 22633, 'loss/train': 1.6931003332138062}
+08/30/2021 17:15:50 - INFO - __main__ - Step 22635: {'lr': 0.0004764007032479963, 'samples': 4345920, 'steps': 22634, 'loss/train': 1.7444283962249756}
+08/30/2021 17:15:50 - INFO - __main__ - Step 22636: {'lr': 0.00047639845246447534, 'samples': 4346112, 'steps': 22635, 'loss/train': 1.6407912969589233}
+08/30/2021 17:15:50 - INFO - __main__ - Step 22637: {'lr': 0.00047639620157894264, 'samples': 4346304, 'steps': 22636, 'loss/train': 1.3127738237380981}
+08/30/2021 17:15:51 - INFO - __main__ - Step 22638: {'lr': 0.00047639395059139936, 'samples': 4346496, 'steps': 22637, 'loss/train': 1.869842767715454}
+08/30/2021 17:15:51 - INFO - __main__ - Step 22639: {'lr': 0.0004763916995018465, 'samples': 4346688, 'steps': 22638, 'loss/train': 1.3320239782333374}
+08/30/2021 17:15:53 - INFO - __main__ - Step 22640: {'lr': 0.00047638944831028497, 'samples': 4346880, 'steps': 22639, 'loss/train': 1.6166237592697144}
+08/30/2021 17:15:53 - INFO - __main__ - Step 22641: {'lr': 0.00047638719701671587, 'samples': 4347072, 'steps': 22640, 'loss/train': 1.786665678024292}
+08/30/2021 17:15:53 - INFO - __main__ - Step 22642: {'lr': 0.00047638494562114015, 'samples': 4347264, 'steps': 22641, 'loss/train': 1.4907608032226562}
+08/30/2021 17:15:54 - INFO - __main__ - Step 22643: {'lr': 0.0004763826941235589, 'samples': 4347456, 'steps': 22642, 'loss/train': 1.1272971630096436}
+08/30/2021 17:15:54 - INFO - __main__ - Step 22644: {'lr': 0.00047638044252397313, 'samples': 4347648, 'steps': 22643, 'loss/train': 1.7200355529785156}
+08/30/2021 17:15:56 - INFO - __main__ - Step 22645: {'lr': 0.0004763781908223838, 'samples': 4347840, 'steps': 22644, 'loss/train': 1.3382102251052856}
+08/30/2021 17:15:56 - INFO - __main__ - Step 22646: {'lr': 0.00047637593901879194, 'samples': 4348032, 'steps': 22645, 'loss/train': 1.9048612117767334}
+08/30/2021 17:15:56 - INFO - __main__ - Step 22647: {'lr': 0.00047637368711319863, 'samples': 4348224, 'steps': 22646, 'loss/train': 1.7801023721694946}
+08/30/2021 17:15:57 - INFO - __main__ - Step 22648: {'lr': 0.00047637143510560477, 'samples': 4348416, 'steps': 22647, 'loss/train': 1.4967598915100098}
+08/30/2021 17:15:57 - INFO - __main__ - Step 22649: {'lr': 0.0004763691829960114, 'samples': 4348608, 'steps': 22648, 'loss/train': 1.8857465982437134}
+08/30/2021 17:15:59 - INFO - __main__ - Step 22650: {'lr': 0.00047636693078441963, 'samples': 4348800, 'steps': 22649, 'loss/train': 1.1992545127868652}
+08/30/2021 17:15:59 - INFO - __main__ - Step 22651: {'lr': 0.0004763646784708304, 'samples': 4348992, 'steps': 22650, 'loss/train': 0.19952024519443512}
+08/30/2021 17:16:00 - INFO - __main__ - Step 22652: {'lr': 0.00047636242605524477, 'samples': 4349184, 'steps': 22651, 'loss/train': 1.5169461965560913}
+08/30/2021 17:16:00 - INFO - __main__ - Step 22653: {'lr': 0.0004763601735376637, 'samples': 4349376, 'steps': 22652, 'loss/train': 1.5541881322860718}
+08/30/2021 17:16:00 - INFO - __main__ - Step 22654: {'lr': 0.0004763579209180882, 'samples': 4349568, 'steps': 22653, 'loss/train': 1.364939570426941}
+08/30/2021 17:16:02 - INFO - __main__ - Step 22655: {'lr': 0.00047635566819651936, 'samples': 4349760, 'steps': 22654, 'loss/train': 1.6734801530838013}
+08/30/2021 17:16:03 - INFO - __main__ - Step 22656: {'lr': 0.00047635341537295814, 'samples': 4349952, 'steps': 22655, 'loss/train': 2.059765338897705}
+08/30/2021 17:16:03 - INFO - __main__ - Step 22657: {'lr': 0.0004763511624474055, 'samples': 4350144, 'steps': 22656, 'loss/train': 2.098519802093506}
+08/30/2021 17:16:03 - INFO - __main__ - Step 22658: {'lr': 0.00047634890941986263, 'samples': 4350336, 'steps': 22657, 'loss/train': 1.7504721879959106}
+08/30/2021 17:16:04 - INFO - __main__ - Step 22659: {'lr': 0.00047634665629033035, 'samples': 4350528, 'steps': 22658, 'loss/train': 1.7271106243133545}
+08/30/2021 17:16:05 - INFO - __main__ - Step 22660: {'lr': 0.00047634440305880976, 'samples': 4350720, 'steps': 22659, 'loss/train': 1.0989255905151367}
+08/30/2021 17:16:05 - INFO - __main__ - Step 22661: {'lr': 0.0004763421497253019, 'samples': 4350912, 'steps': 22660, 'loss/train': 2.4688119888305664}
+08/30/2021 17:16:06 - INFO - __main__ - Step 22662: {'lr': 0.0004763398962898078, 'samples': 4351104, 'steps': 22661, 'loss/train': 1.638301134109497}
+08/30/2021 17:16:06 - INFO - __main__ - Step 22663: {'lr': 0.0004763376427523284, 'samples': 4351296, 'steps': 22662, 'loss/train': 1.5809268951416016}
+08/30/2021 17:16:06 - INFO - __main__ - Step 22664: {'lr': 0.0004763353891128648, 'samples': 4351488, 'steps': 22663, 'loss/train': 1.5273466110229492}
+08/30/2021 17:16:07 - INFO - __main__ - Step 22665: {'lr': 0.00047633313537141786, 'samples': 4351680, 'steps': 22664, 'loss/train': 1.8765552043914795}
+08/30/2021 17:16:08 - INFO - __main__ - Step 22666: {'lr': 0.00047633088152798875, 'samples': 4351872, 'steps': 22665, 'loss/train': 1.879747748374939}
+08/30/2021 17:16:09 - INFO - __main__ - Step 22667: {'lr': 0.00047632862758257845, 'samples': 4352064, 'steps': 22666, 'loss/train': 1.3156960010528564}
+08/30/2021 17:16:09 - INFO - __main__ - Step 22668: {'lr': 0.0004763263735351879, 'samples': 4352256, 'steps': 22667, 'loss/train': 1.77305269241333}
+08/30/2021 17:16:09 - INFO - __main__ - Step 22669: {'lr': 0.0004763241193858183, 'samples': 4352448, 'steps': 22668, 'loss/train': 2.2486209869384766}
+08/30/2021 17:16:10 - INFO - __main__ - Step 22670: {'lr': 0.00047632186513447045, 'samples': 4352640, 'steps': 22669, 'loss/train': 1.4093332290649414}
+08/30/2021 17:16:11 - INFO - __main__ - Step 22671: {'lr': 0.0004763196107811455, 'samples': 4352832, 'steps': 22670, 'loss/train': 1.8424217700958252}
+08/30/2021 17:16:12 - INFO - __main__ - Step 22672: {'lr': 0.0004763173563258444, 'samples': 4353024, 'steps': 22671, 'loss/train': 1.6107220649719238}
+08/30/2021 17:16:12 - INFO - __main__ - Step 22673: {'lr': 0.0004763151017685682, 'samples': 4353216, 'steps': 22672, 'loss/train': 1.0175189971923828}
+08/30/2021 17:16:12 - INFO - __main__ - Step 22674: {'lr': 0.0004763128471093179, 'samples': 4353408, 'steps': 22673, 'loss/train': 1.0710530281066895}
+08/30/2021 17:16:13 - INFO - __main__ - Step 22675: {'lr': 0.0004763105923480946, 'samples': 4353600, 'steps': 22674, 'loss/train': 1.3609719276428223}
+08/30/2021 17:16:14 - INFO - __main__ - Step 22676: {'lr': 0.0004763083374848991, 'samples': 4353792, 'steps': 22675, 'loss/train': 1.3715710639953613}
+08/30/2021 17:16:15 - INFO - __main__ - Step 22677: {'lr': 0.00047630608251973265, 'samples': 4353984, 'steps': 22676, 'loss/train': 2.1492466926574707}
+08/30/2021 17:16:15 - INFO - __main__ - Step 22678: {'lr': 0.00047630382745259616, 'samples': 4354176, 'steps': 22677, 'loss/train': 1.9249857664108276}
+08/30/2021 17:16:15 - INFO - __main__ - Step 22679: {'lr': 0.0004763015722834907, 'samples': 4354368, 'steps': 22678, 'loss/train': 1.978841781616211}
+08/30/2021 17:16:16 - INFO - __main__ - Step 22680: {'lr': 0.00047629931701241715, 'samples': 4354560, 'steps': 22679, 'loss/train': 1.268255352973938}
+08/30/2021 17:16:17 - INFO - __main__ - Step 22681: {'lr': 0.0004762970616393767, 'samples': 4354752, 'steps': 22680, 'loss/train': 1.7757965326309204}
+08/30/2021 17:16:18 - INFO - __main__ - Step 22682: {'lr': 0.0004762948061643702, 'samples': 4354944, 'steps': 22681, 'loss/train': 0.6261685490608215}
+08/30/2021 17:16:18 - INFO - __main__ - Step 22683: {'lr': 0.0004762925505873988, 'samples': 4355136, 'steps': 22682, 'loss/train': 2.0943148136138916}
+08/30/2021 17:16:18 - INFO - __main__ - Step 22684: {'lr': 0.00047629029490846346, 'samples': 4355328, 'steps': 22683, 'loss/train': 0.6795475482940674}
+08/30/2021 17:16:19 - INFO - __main__ - Step 22685: {'lr': 0.00047628803912756523, 'samples': 4355520, 'steps': 22684, 'loss/train': 1.8683626651763916}
+08/30/2021 17:16:21 - INFO - __main__ - Step 22686: {'lr': 0.00047628578324470505, 'samples': 4355712, 'steps': 22685, 'loss/train': 1.8733292818069458}
+08/30/2021 17:16:21 - INFO - __main__ - Step 22687: {'lr': 0.00047628352725988406, 'samples': 4355904, 'steps': 22686, 'loss/train': 1.759171724319458}
+08/30/2021 17:16:21 - INFO - __main__ - Step 22688: {'lr': 0.0004762812711731032, 'samples': 4356096, 'steps': 22687, 'loss/train': 1.767892837524414}
+08/30/2021 17:16:22 - INFO - __main__ - Step 22689: {'lr': 0.00047627901498436344, 'samples': 4356288, 'steps': 22688, 'loss/train': 1.8540290594100952}
+08/30/2021 17:16:22 - INFO - __main__ - Step 22690: {'lr': 0.0004762767586936658, 'samples': 4356480, 'steps': 22689, 'loss/train': 1.75572669506073}
+08/30/2021 17:16:24 - INFO - __main__ - Step 22691: {'lr': 0.00047627450230101144, 'samples': 4356672, 'steps': 22690, 'loss/train': 1.6989866495132446}
+08/30/2021 17:16:24 - INFO - __main__ - Step 22692: {'lr': 0.0004762722458064013, 'samples': 4356864, 'steps': 22691, 'loss/train': 1.6670310497283936}
+08/30/2021 17:16:24 - INFO - __main__ - Step 22693: {'lr': 0.0004762699892098363, 'samples': 4357056, 'steps': 22692, 'loss/train': 1.6908589601516724}
+08/30/2021 17:16:25 - INFO - __main__ - Step 22694: {'lr': 0.0004762677325113176, 'samples': 4357248, 'steps': 22693, 'loss/train': 1.4345744848251343}
+08/30/2021 17:16:25 - INFO - __main__ - Step 22695: {'lr': 0.0004762654757108461, 'samples': 4357440, 'steps': 22694, 'loss/train': 2.0730648040771484}
+08/30/2021 17:16:26 - INFO - __main__ - Step 22696: {'lr': 0.00047626321880842287, 'samples': 4357632, 'steps': 22695, 'loss/train': 1.5803663730621338}
+08/30/2021 17:16:27 - INFO - __main__ - Step 22697: {'lr': 0.00047626096180404895, 'samples': 4357824, 'steps': 22696, 'loss/train': 1.8902571201324463}
+08/30/2021 17:16:27 - INFO - __main__ - Step 22698: {'lr': 0.0004762587046977253, 'samples': 4358016, 'steps': 22697, 'loss/train': 1.4248958826065063}
+08/30/2021 17:16:28 - INFO - __main__ - Step 22699: {'lr': 0.000476256447489453, 'samples': 4358208, 'steps': 22698, 'loss/train': 1.7172247171401978}
+08/30/2021 17:16:28 - INFO - __main__ - Step 22700: {'lr': 0.000476254190179233, 'samples': 4358400, 'steps': 22699, 'loss/train': 1.6442368030548096}
+08/30/2021 17:16:30 - INFO - __main__ - Step 22701: {'lr': 0.0004762519327670664, 'samples': 4358592, 'steps': 22700, 'loss/train': 1.4775010347366333}
+08/30/2021 17:16:30 - INFO - __main__ - Step 22702: {'lr': 0.0004762496752529541, 'samples': 4358784, 'steps': 22701, 'loss/train': 1.758837103843689}
+08/30/2021 17:16:30 - INFO - __main__ - Step 22703: {'lr': 0.0004762474176368973, 'samples': 4358976, 'steps': 22702, 'loss/train': 1.3404951095581055}
+08/30/2021 17:16:31 - INFO - __main__ - Step 22704: {'lr': 0.00047624515991889684, 'samples': 4359168, 'steps': 22703, 'loss/train': 2.242572546005249}
+08/30/2021 17:16:31 - INFO - __main__ - Step 22705: {'lr': 0.00047624290209895384, 'samples': 4359360, 'steps': 22704, 'loss/train': 2.0615878105163574}
+08/30/2021 17:16:33 - INFO - __main__ - Step 22706: {'lr': 0.00047624064417706917, 'samples': 4359552, 'steps': 22705, 'loss/train': 1.3389997482299805}
+08/30/2021 17:16:34 - INFO - __main__ - Step 22707: {'lr': 0.00047623838615324407, 'samples': 4359744, 'steps': 22706, 'loss/train': 1.843644142150879}
+08/30/2021 17:16:34 - INFO - __main__ - Step 22708: {'lr': 0.0004762361280274794, 'samples': 4359936, 'steps': 22707, 'loss/train': 1.8705817461013794}
+08/30/2021 17:16:34 - INFO - __main__ - Step 22709: {'lr': 0.0004762338697997762, 'samples': 4360128, 'steps': 22708, 'loss/train': 1.4605693817138672}
+08/30/2021 17:16:35 - INFO - __main__ - Step 22710: {'lr': 0.00047623161147013557, 'samples': 4360320, 'steps': 22709, 'loss/train': 1.4370949268341064}
+08/30/2021 17:16:36 - INFO - __main__ - Step 22711: {'lr': 0.0004762293530385584, 'samples': 4360512, 'steps': 22710, 'loss/train': 0.1271795928478241}
+08/30/2021 17:16:36 - INFO - __main__ - Step 22712: {'lr': 0.0004762270945050458, 'samples': 4360704, 'steps': 22711, 'loss/train': 2.282175064086914}
+08/30/2021 17:16:37 - INFO - __main__ - Step 22713: {'lr': 0.00047622483586959877, 'samples': 4360896, 'steps': 22712, 'loss/train': 1.7745230197906494}
+08/30/2021 17:16:37 - INFO - __main__ - Step 22714: {'lr': 0.00047622257713221826, 'samples': 4361088, 'steps': 22713, 'loss/train': 1.5097118616104126}
+08/30/2021 17:16:38 - INFO - __main__ - Step 22715: {'lr': 0.00047622031829290545, 'samples': 4361280, 'steps': 22714, 'loss/train': 1.5611250400543213}
+08/30/2021 17:16:39 - INFO - __main__ - Step 22716: {'lr': 0.0004762180593516612, 'samples': 4361472, 'steps': 22715, 'loss/train': 1.5972368717193604}
+08/30/2021 17:16:40 - INFO - __main__ - Step 22717: {'lr': 0.0004762158003084867, 'samples': 4361664, 'steps': 22716, 'loss/train': 2.6648776531219482}
+08/30/2021 17:16:40 - INFO - __main__ - Step 22718: {'lr': 0.0004762135411633827, 'samples': 4361856, 'steps': 22717, 'loss/train': 1.5549181699752808}
+08/30/2021 17:16:40 - INFO - __main__ - Step 22719: {'lr': 0.0004762112819163504, 'samples': 4362048, 'steps': 22718, 'loss/train': 1.5840942859649658}
+08/30/2021 17:16:41 - INFO - __main__ - Step 22720: {'lr': 0.0004762090225673908, 'samples': 4362240, 'steps': 22719, 'loss/train': 1.1802986860275269}
+08/30/2021 17:16:41 - INFO - __main__ - Step 22721: {'lr': 0.0004762067631165049, 'samples': 4362432, 'steps': 22720, 'loss/train': 1.972393274307251}
+08/30/2021 17:16:43 - INFO - __main__ - Step 22722: {'lr': 0.0004762045035636937, 'samples': 4362624, 'steps': 22721, 'loss/train': 0.8380379676818848}
+08/30/2021 17:16:43 - INFO - __main__ - Step 22723: {'lr': 0.0004762022439089583, 'samples': 4362816, 'steps': 22722, 'loss/train': 1.7101861238479614}
+08/30/2021 17:16:43 - INFO - __main__ - Step 22724: {'lr': 0.0004761999841522996, 'samples': 4363008, 'steps': 22723, 'loss/train': 2.1470186710357666}
+08/30/2021 17:16:44 - INFO - __main__ - Step 22725: {'lr': 0.0004761977242937188, 'samples': 4363200, 'steps': 22724, 'loss/train': 1.7504310607910156}
+08/30/2021 17:16:44 - INFO - __main__ - Step 22726: {'lr': 0.00047619546433321663, 'samples': 4363392, 'steps': 22725, 'loss/train': 1.112618327140808}
+08/30/2021 17:16:46 - INFO - __main__ - Step 22727: {'lr': 0.00047619320427079437, 'samples': 4363584, 'steps': 22726, 'loss/train': 1.5926406383514404}
+08/30/2021 17:16:46 - INFO - __main__ - Step 22728: {'lr': 0.00047619094410645293, 'samples': 4363776, 'steps': 22727, 'loss/train': 0.8259417414665222}
+08/30/2021 17:16:47 - INFO - __main__ - Step 22729: {'lr': 0.0004761886838401933, 'samples': 4363968, 'steps': 22728, 'loss/train': 1.9355567693710327}
+08/30/2021 17:16:47 - INFO - __main__ - Step 22730: {'lr': 0.0004761864234720166, 'samples': 4364160, 'steps': 22729, 'loss/train': 1.997549057006836}
+08/30/2021 17:16:47 - INFO - __main__ - Step 22731: {'lr': 0.00047618416300192375, 'samples': 4364352, 'steps': 22730, 'loss/train': 1.2267361879348755}
+08/30/2021 17:16:48 - INFO - __main__ - Step 22732: {'lr': 0.0004761819024299158, 'samples': 4364544, 'steps': 22731, 'loss/train': 1.8489607572555542}
+08/30/2021 17:16:49 - INFO - __main__ - Step 22733: {'lr': 0.0004761796417559938, 'samples': 4364736, 'steps': 22732, 'loss/train': 1.7026993036270142}
+08/30/2021 17:16:50 - INFO - __main__ - Step 22734: {'lr': 0.0004761773809801587, 'samples': 4364928, 'steps': 22733, 'loss/train': 1.4597245454788208}
+08/30/2021 17:16:50 - INFO - __main__ - Step 22735: {'lr': 0.0004761751201024116, 'samples': 4365120, 'steps': 22734, 'loss/train': 1.5148273706436157}
+08/30/2021 17:16:50 - INFO - __main__ - Step 22736: {'lr': 0.0004761728591227535, 'samples': 4365312, 'steps': 22735, 'loss/train': 1.2636899948120117}
+08/30/2021 17:16:51 - INFO - __main__ - Step 22737: {'lr': 0.00047617059804118536, 'samples': 4365504, 'steps': 22736, 'loss/train': 1.7436262369155884}
+08/30/2021 17:16:53 - INFO - __main__ - Step 22738: {'lr': 0.0004761683368577083, 'samples': 4365696, 'steps': 22737, 'loss/train': 1.5510469675064087}
+08/30/2021 17:16:53 - INFO - __main__ - Step 22739: {'lr': 0.0004761660755723232, 'samples': 4365888, 'steps': 22738, 'loss/train': 1.2957271337509155}
+08/30/2021 17:16:54 - INFO - __main__ - Step 22740: {'lr': 0.0004761638141850312, 'samples': 4366080, 'steps': 22739, 'loss/train': 1.8613446950912476}
+08/30/2021 17:16:54 - INFO - __main__ - Step 22741: {'lr': 0.0004761615526958333, 'samples': 4366272, 'steps': 22740, 'loss/train': 1.8560149669647217}
+08/30/2021 17:16:54 - INFO - __main__ - Step 22742: {'lr': 0.0004761592911047304, 'samples': 4366464, 'steps': 22741, 'loss/train': 1.860827922821045}
+08/30/2021 17:16:56 - INFO - __main__ - Step 22743: {'lr': 0.00047615702941172366, 'samples': 4366656, 'steps': 22742, 'loss/train': 1.5457545518875122}
+08/30/2021 17:16:56 - INFO - __main__ - Step 22744: {'lr': 0.0004761547676168141, 'samples': 4366848, 'steps': 22743, 'loss/train': 1.7188726663589478}
+08/30/2021 17:16:57 - INFO - __main__ - Step 22745: {'lr': 0.0004761525057200027, 'samples': 4367040, 'steps': 22744, 'loss/train': 2.0277504920959473}
+08/30/2021 17:16:57 - INFO - __main__ - Step 22746: {'lr': 0.00047615024372129033, 'samples': 4367232, 'steps': 22745, 'loss/train': 1.4906532764434814}
+08/30/2021 17:16:57 - INFO - __main__ - Step 22747: {'lr': 0.0004761479816206783, 'samples': 4367424, 'steps': 22746, 'loss/train': 1.1546109914779663}
+08/30/2021 17:16:59 - INFO - __main__ - Step 22748: {'lr': 0.00047614571941816743, 'samples': 4367616, 'steps': 22747, 'loss/train': 0.0923515036702156}
+08/30/2021 17:16:59 - INFO - __main__ - Step 22749: {'lr': 0.00047614345711375874, 'samples': 4367808, 'steps': 22748, 'loss/train': 1.6979933977127075}
+08/30/2021 17:17:00 - INFO - __main__ - Step 22750: {'lr': 0.0004761411947074533, 'samples': 4368000, 'steps': 22749, 'loss/train': 1.2950513362884521}
+08/30/2021 17:17:00 - INFO - __main__ - Step 22751: {'lr': 0.00047613893219925217, 'samples': 4368192, 'steps': 22750, 'loss/train': 0.35021892189979553}
+08/30/2021 17:17:00 - INFO - __main__ - Step 22752: {'lr': 0.00047613666958915636, 'samples': 4368384, 'steps': 22751, 'loss/train': 0.8060241937637329}
+08/30/2021 17:17:02 - INFO - __main__ - Step 22753: {'lr': 0.0004761344068771668, 'samples': 4368576, 'steps': 22752, 'loss/train': 1.5739452838897705}
+08/30/2021 17:17:02 - INFO - __main__ - Step 22754: {'lr': 0.0004761321440632846, 'samples': 4368768, 'steps': 22753, 'loss/train': 1.9471994638442993}
+08/30/2021 17:17:03 - INFO - __main__ - Step 22755: {'lr': 0.00047612988114751074, 'samples': 4368960, 'steps': 22754, 'loss/train': 0.7910296320915222}
+08/30/2021 17:17:03 - INFO - __main__ - Step 22756: {'lr': 0.00047612761812984626, 'samples': 4369152, 'steps': 22755, 'loss/train': 1.2983958721160889}
+08/30/2021 17:17:03 - INFO - __main__ - Step 22757: {'lr': 0.00047612535501029215, 'samples': 4369344, 'steps': 22756, 'loss/train': 1.8251382112503052}
+08/30/2021 17:17:04 - INFO - __main__ - Step 22758: {'lr': 0.0004761230917888494, 'samples': 4369536, 'steps': 22757, 'loss/train': 1.9290217161178589}
+08/30/2021 17:17:05 - INFO - __main__ - Step 22759: {'lr': 0.00047612082846551913, 'samples': 4369728, 'steps': 22758, 'loss/train': 1.0281867980957031}
+08/30/2021 17:17:06 - INFO - __main__ - Step 22760: {'lr': 0.0004761185650403023, 'samples': 4369920, 'steps': 22759, 'loss/train': 1.2882440090179443}
+08/30/2021 17:17:06 - INFO - __main__ - Step 22761: {'lr': 0.0004761163015131999, 'samples': 4370112, 'steps': 22760, 'loss/train': 1.6148911714553833}
+08/30/2021 17:17:07 - INFO - __main__ - Step 22762: {'lr': 0.00047611403788421305, 'samples': 4370304, 'steps': 22761, 'loss/train': 1.910568356513977}
+08/30/2021 17:17:07 - INFO - __main__ - Step 22763: {'lr': 0.0004761117741533426, 'samples': 4370496, 'steps': 22762, 'loss/train': 1.8226226568222046}
+08/30/2021 17:17:08 - INFO - __main__ - Step 22764: {'lr': 0.0004761095103205897, 'samples': 4370688, 'steps': 22763, 'loss/train': 1.7216705083847046}
+08/30/2021 17:17:09 - INFO - __main__ - Step 22765: {'lr': 0.00047610724638595545, 'samples': 4370880, 'steps': 22764, 'loss/train': 0.06404563039541245}
+08/30/2021 17:17:09 - INFO - __main__ - Step 22766: {'lr': 0.00047610498234944065, 'samples': 4371072, 'steps': 22765, 'loss/train': 1.3860447406768799}
+08/30/2021 17:17:10 - INFO - __main__ - Step 22767: {'lr': 0.00047610271821104647, 'samples': 4371264, 'steps': 22766, 'loss/train': 1.1288124322891235}
+08/30/2021 17:17:10 - INFO - __main__ - Step 22768: {'lr': 0.0004761004539707739, 'samples': 4371456, 'steps': 22767, 'loss/train': 1.9874215126037598}
+08/30/2021 17:17:11 - INFO - __main__ - Step 22769: {'lr': 0.00047609818962862394, 'samples': 4371648, 'steps': 22768, 'loss/train': 1.9229989051818848}
+08/30/2021 17:17:12 - INFO - __main__ - Step 22770: {'lr': 0.00047609592518459766, 'samples': 4371840, 'steps': 22769, 'loss/train': 1.4309335947036743}
+08/30/2021 17:17:12 - INFO - __main__ - Step 22771: {'lr': 0.00047609366063869595, 'samples': 4372032, 'steps': 22770, 'loss/train': 1.706612467765808}
+08/30/2021 17:17:13 - INFO - __main__ - Step 22772: {'lr': 0.00047609139599092006, 'samples': 4372224, 'steps': 22771, 'loss/train': 0.9627857208251953}
+08/30/2021 17:17:13 - INFO - __main__ - Step 22773: {'lr': 0.0004760891312412708, 'samples': 4372416, 'steps': 22772, 'loss/train': 1.4608187675476074}
+08/30/2021 17:17:14 - INFO - __main__ - Step 22774: {'lr': 0.0004760868663897493, 'samples': 4372608, 'steps': 22773, 'loss/train': 1.4157202243804932}
+08/30/2021 17:17:15 - INFO - __main__ - Step 22775: {'lr': 0.0004760846014363565, 'samples': 4372800, 'steps': 22774, 'loss/train': 1.8349318504333496}
+08/30/2021 17:17:15 - INFO - __main__ - Step 22776: {'lr': 0.0004760823363810935, 'samples': 4372992, 'steps': 22775, 'loss/train': 1.6829019784927368}
+08/30/2021 17:17:16 - INFO - __main__ - Step 22777: {'lr': 0.0004760800712239612, 'samples': 4373184, 'steps': 22776, 'loss/train': 1.3641904592514038}
+08/30/2021 17:17:16 - INFO - __main__ - Step 22778: {'lr': 0.0004760778059649609, 'samples': 4373376, 'steps': 22777, 'loss/train': 1.5136724710464478}
+08/30/2021 17:17:17 - INFO - __main__ - Step 22779: {'lr': 0.0004760755406040933, 'samples': 4373568, 'steps': 22778, 'loss/train': 1.8314247131347656}
+08/30/2021 17:17:18 - INFO - __main__ - Step 22780: {'lr': 0.00047607327514135955, 'samples': 4373760, 'steps': 22779, 'loss/train': 1.7004406452178955}
+08/30/2021 17:17:18 - INFO - __main__ - Step 22781: {'lr': 0.00047607100957676067, 'samples': 4373952, 'steps': 22780, 'loss/train': 1.4628232717514038}
+08/30/2021 17:17:19 - INFO - __main__ - Step 22782: {'lr': 0.0004760687439102977, 'samples': 4374144, 'steps': 22781, 'loss/train': 1.600130558013916}
+08/30/2021 17:17:19 - INFO - __main__ - Step 22783: {'lr': 0.0004760664781419717, 'samples': 4374336, 'steps': 22782, 'loss/train': 1.2052366733551025}
+08/30/2021 17:17:21 - INFO - __main__ - Step 22784: {'lr': 0.00047606421227178354, 'samples': 4374528, 'steps': 22783, 'loss/train': 1.670741081237793}
+08/30/2021 17:17:21 - INFO - __main__ - Step 22785: {'lr': 0.0004760619462997343, 'samples': 4374720, 'steps': 22784, 'loss/train': 1.5195059776306152}
+08/30/2021 17:17:22 - INFO - __main__ - Step 22786: {'lr': 0.00047605968022582513, 'samples': 4374912, 'steps': 22785, 'loss/train': 1.409189224243164}
+08/30/2021 17:17:22 - INFO - __main__ - Step 22787: {'lr': 0.000476057414050057, 'samples': 4375104, 'steps': 22786, 'loss/train': 1.396681308746338}
+08/30/2021 17:17:22 - INFO - __main__ - Step 22788: {'lr': 0.00047605514777243076, 'samples': 4375296, 'steps': 22787, 'loss/train': 1.1407527923583984}
+08/30/2021 17:17:24 - INFO - __main__ - Step 22789: {'lr': 0.0004760528813929476, 'samples': 4375488, 'steps': 22788, 'loss/train': 0.10242465138435364}
+08/30/2021 17:17:25 - INFO - __main__ - Step 22790: {'lr': 0.0004760506149116085, 'samples': 4375680, 'steps': 22789, 'loss/train': 1.7497690916061401}
+08/30/2021 17:17:25 - INFO - __main__ - Step 22791: {'lr': 0.0004760483483284145, 'samples': 4375872, 'steps': 22790, 'loss/train': 2.0616135597229004}
+08/30/2021 17:17:25 - INFO - __main__ - Step 22792: {'lr': 0.0004760460816433666, 'samples': 4376064, 'steps': 22791, 'loss/train': 1.7703133821487427}
+08/30/2021 17:17:26 - INFO - __main__ - Step 22793: {'lr': 0.0004760438148564659, 'samples': 4376256, 'steps': 22792, 'loss/train': 1.3119556903839111}
+08/30/2021 17:17:26 - INFO - __main__ - Step 22794: {'lr': 0.00047604154796771327, 'samples': 4376448, 'steps': 22793, 'loss/train': 1.9411065578460693}
+08/30/2021 17:17:28 - INFO - __main__ - Step 22795: {'lr': 0.0004760392809771098, 'samples': 4376640, 'steps': 22794, 'loss/train': 1.8020325899124146}
+08/30/2021 17:17:28 - INFO - __main__ - Step 22796: {'lr': 0.00047603701388465646, 'samples': 4376832, 'steps': 22795, 'loss/train': 2.1383056640625}
+08/30/2021 17:17:28 - INFO - __main__ - Step 22797: {'lr': 0.0004760347466903544, 'samples': 4377024, 'steps': 22796, 'loss/train': 1.6379649639129639}
+08/30/2021 17:17:29 - INFO - __main__ - Step 22798: {'lr': 0.0004760324793942046, 'samples': 4377216, 'steps': 22797, 'loss/train': 1.4360427856445312}
+08/30/2021 17:17:29 - INFO - __main__ - Step 22799: {'lr': 0.000476030211996208, 'samples': 4377408, 'steps': 22798, 'loss/train': 0.5922221541404724}
+08/30/2021 17:17:31 - INFO - __main__ - Step 22800: {'lr': 0.0004760279444963657, 'samples': 4377600, 'steps': 22799, 'loss/train': 1.4615356922149658}
+08/30/2021 17:17:31 - INFO - __main__ - Step 22801: {'lr': 0.0004760256768946787, 'samples': 4377792, 'steps': 22800, 'loss/train': 1.6913899183273315}
+08/30/2021 17:17:31 - INFO - __main__ - Step 22802: {'lr': 0.00047602340919114793, 'samples': 4377984, 'steps': 22801, 'loss/train': 1.722115159034729}
+08/30/2021 17:17:32 - INFO - __main__ - Step 22803: {'lr': 0.00047602114138577464, 'samples': 4378176, 'steps': 22802, 'loss/train': 1.2216346263885498}
+08/30/2021 17:17:32 - INFO - __main__ - Step 22804: {'lr': 0.00047601887347855965, 'samples': 4378368, 'steps': 22803, 'loss/train': 1.5958867073059082}
+08/30/2021 17:17:34 - INFO - __main__ - Step 22805: {'lr': 0.00047601660546950396, 'samples': 4378560, 'steps': 22804, 'loss/train': 1.288720965385437}
+08/30/2021 17:17:34 - INFO - __main__ - Step 22806: {'lr': 0.0004760143373586088, 'samples': 4378752, 'steps': 22805, 'loss/train': 1.337775707244873}
+08/30/2021 17:17:35 - INFO - __main__ - Step 22807: {'lr': 0.000476012069145875, 'samples': 4378944, 'steps': 22806, 'loss/train': 1.4912784099578857}
+08/30/2021 17:17:35 - INFO - __main__ - Step 22808: {'lr': 0.00047600980083130367, 'samples': 4379136, 'steps': 22807, 'loss/train': 0.16186995804309845}
+08/30/2021 17:17:35 - INFO - __main__ - Step 22809: {'lr': 0.0004760075324148959, 'samples': 4379328, 'steps': 22808, 'loss/train': 2.0144107341766357}
+08/30/2021 17:17:36 - INFO - __main__ - Step 22810: {'lr': 0.00047600526389665246, 'samples': 4379520, 'steps': 22809, 'loss/train': 1.2294877767562866}
+08/30/2021 17:17:37 - INFO - __main__ - Step 22811: {'lr': 0.00047600299527657464, 'samples': 4379712, 'steps': 22810, 'loss/train': 1.824755072593689}
+08/30/2021 17:17:38 - INFO - __main__ - Step 22812: {'lr': 0.0004760007265546633, 'samples': 4379904, 'steps': 22811, 'loss/train': 1.269286036491394}
+08/30/2021 17:17:38 - INFO - __main__ - Step 22813: {'lr': 0.00047599845773091957, 'samples': 4380096, 'steps': 22812, 'loss/train': 1.4401121139526367}
+08/30/2021 17:17:39 - INFO - __main__ - Step 22814: {'lr': 0.0004759961888053444, 'samples': 4380288, 'steps': 22813, 'loss/train': 2.1565186977386475}
+08/30/2021 17:17:39 - INFO - __main__ - Step 22815: {'lr': 0.00047599391977793884, 'samples': 4380480, 'steps': 22814, 'loss/train': 1.5639879703521729}
+08/30/2021 17:17:40 - INFO - __main__ - Step 22816: {'lr': 0.00047599165064870385, 'samples': 4380672, 'steps': 22815, 'loss/train': 3.1073622703552246}
+08/30/2021 17:17:41 - INFO - __main__ - Step 22817: {'lr': 0.0004759893814176406, 'samples': 4380864, 'steps': 22816, 'loss/train': 0.3915186822414398}
+08/30/2021 17:17:41 - INFO - __main__ - Step 22818: {'lr': 0.00047598711208475, 'samples': 4381056, 'steps': 22817, 'loss/train': 1.7690671682357788}
+08/30/2021 17:17:41 - INFO - __main__ - Step 22819: {'lr': 0.00047598484265003307, 'samples': 4381248, 'steps': 22818, 'loss/train': 1.451126217842102}
+08/30/2021 17:17:42 - INFO - __main__ - Step 22820: {'lr': 0.00047598257311349087, 'samples': 4381440, 'steps': 22819, 'loss/train': 1.9935786724090576}
+08/30/2021 17:17:42 - INFO - __main__ - Step 22821: {'lr': 0.0004759803034751244, 'samples': 4381632, 'steps': 22820, 'loss/train': 1.9499880075454712}
+08/30/2021 17:17:44 - INFO - __main__ - Step 22822: {'lr': 0.0004759780337349347, 'samples': 4381824, 'steps': 22821, 'loss/train': 1.7148023843765259}
+08/30/2021 17:17:44 - INFO - __main__ - Step 22823: {'lr': 0.0004759757638929227, 'samples': 4382016, 'steps': 22822, 'loss/train': 5.891917705535889}
+08/30/2021 17:17:44 - INFO - __main__ - Step 22824: {'lr': 0.00047597349394908967, 'samples': 4382208, 'steps': 22823, 'loss/train': 1.981136441230774}
+08/30/2021 17:17:45 - INFO - __main__ - Step 22825: {'lr': 0.0004759712239034364, 'samples': 4382400, 'steps': 22824, 'loss/train': 1.6211497783660889}
+08/30/2021 17:17:45 - INFO - __main__ - Step 22826: {'lr': 0.0004759689537559639, 'samples': 4382592, 'steps': 22825, 'loss/train': 1.9349123239517212}
+08/30/2021 17:17:47 - INFO - __main__ - Step 22827: {'lr': 0.0004759666835066734, 'samples': 4382784, 'steps': 22826, 'loss/train': 1.3486504554748535}
+08/30/2021 17:17:47 - INFO - __main__ - Step 22828: {'lr': 0.00047596441315556575, 'samples': 4382976, 'steps': 22827, 'loss/train': 2.139190196990967}
+08/30/2021 17:17:48 - INFO - __main__ - Step 22829: {'lr': 0.00047596214270264204, 'samples': 4383168, 'steps': 22828, 'loss/train': 1.8058923482894897}
+08/30/2021 17:17:48 - INFO - __main__ - Step 22830: {'lr': 0.00047595987214790324, 'samples': 4383360, 'steps': 22829, 'loss/train': 1.976863980293274}
+08/30/2021 17:17:48 - INFO - __main__ - Step 22831: {'lr': 0.0004759576014913505, 'samples': 4383552, 'steps': 22830, 'loss/train': 0.43058809638023376}
+08/30/2021 17:17:49 - INFO - __main__ - Step 22832: {'lr': 0.0004759553307329846, 'samples': 4383744, 'steps': 22831, 'loss/train': 2.1321988105773926}
+08/30/2021 17:17:50 - INFO - __main__ - Step 22833: {'lr': 0.0004759530598728068, 'samples': 4383936, 'steps': 22832, 'loss/train': 1.539613962173462}
+08/30/2021 17:17:51 - INFO - __main__ - Step 22834: {'lr': 0.000475950788910818, 'samples': 4384128, 'steps': 22833, 'loss/train': 1.6206520795822144}
+08/30/2021 17:17:51 - INFO - __main__ - Step 22835: {'lr': 0.0004759485178470193, 'samples': 4384320, 'steps': 22834, 'loss/train': 1.404211401939392}
+08/30/2021 17:17:51 - INFO - __main__ - Step 22836: {'lr': 0.0004759462466814117, 'samples': 4384512, 'steps': 22835, 'loss/train': 1.3100310564041138}
+08/30/2021 17:17:52 - INFO - __main__ - Step 22837: {'lr': 0.0004759439754139962, 'samples': 4384704, 'steps': 22836, 'loss/train': 1.5406081676483154}
+08/30/2021 17:17:53 - INFO - __main__ - Step 22838: {'lr': 0.0004759417040447738, 'samples': 4384896, 'steps': 22837, 'loss/train': 1.3121213912963867}
+08/30/2021 17:17:54 - INFO - __main__ - Step 22839: {'lr': 0.00047593943257374563, 'samples': 4385088, 'steps': 22838, 'loss/train': 1.3830492496490479}
+08/30/2021 17:17:54 - INFO - __main__ - Step 22840: {'lr': 0.00047593716100091253, 'samples': 4385280, 'steps': 22839, 'loss/train': 1.1399668455123901}
+08/30/2021 17:17:55 - INFO - __main__ - Step 22841: {'lr': 0.00047593488932627567, 'samples': 4385472, 'steps': 22840, 'loss/train': 0.2697351276874542}
+08/30/2021 17:17:55 - INFO - __main__ - Step 22842: {'lr': 0.00047593261754983607, 'samples': 4385664, 'steps': 22841, 'loss/train': 0.36397024989128113}
+08/30/2021 17:17:55 - INFO - __main__ - Step 22843: {'lr': 0.00047593034567159465, 'samples': 4385856, 'steps': 22842, 'loss/train': 1.7801777124404907}
+08/30/2021 17:17:57 - INFO - __main__ - Step 22844: {'lr': 0.00047592807369155256, 'samples': 4386048, 'steps': 22843, 'loss/train': 1.2506732940673828}
+08/30/2021 17:17:57 - INFO - __main__ - Step 22845: {'lr': 0.0004759258016097108, 'samples': 4386240, 'steps': 22844, 'loss/train': 2.4678118228912354}
+08/30/2021 17:17:58 - INFO - __main__ - Step 22846: {'lr': 0.0004759235294260703, 'samples': 4386432, 'steps': 22845, 'loss/train': 1.5825022459030151}
+08/30/2021 17:17:58 - INFO - __main__ - Step 22847: {'lr': 0.0004759212571406321, 'samples': 4386624, 'steps': 22846, 'loss/train': 0.9864962697029114}
+08/30/2021 17:17:58 - INFO - __main__ - Step 22848: {'lr': 0.00047591898475339735, 'samples': 4386816, 'steps': 22847, 'loss/train': 1.507699966430664}
+08/30/2021 17:18:00 - INFO - __main__ - Step 22849: {'lr': 0.00047591671226436695, 'samples': 4387008, 'steps': 22848, 'loss/train': 1.8230257034301758}
+08/30/2021 17:18:01 - INFO - __main__ - Step 22850: {'lr': 0.00047591443967354196, 'samples': 4387200, 'steps': 22849, 'loss/train': 1.8146308660507202}
+08/30/2021 17:18:01 - INFO - __main__ - Step 22851: {'lr': 0.00047591216698092344, 'samples': 4387392, 'steps': 22850, 'loss/train': 1.4738590717315674}
+08/30/2021 17:18:02 - INFO - __main__ - Step 22852: {'lr': 0.00047590989418651243, 'samples': 4387584, 'steps': 22851, 'loss/train': 1.4997490644454956}
+08/30/2021 17:18:02 - INFO - __main__ - Step 22853: {'lr': 0.00047590762129030986, 'samples': 4387776, 'steps': 22852, 'loss/train': 2.373847723007202}
+08/30/2021 17:18:04 - INFO - __main__ - Step 22854: {'lr': 0.00047590534829231675, 'samples': 4387968, 'steps': 22853, 'loss/train': 1.1073637008666992}
+08/30/2021 17:18:04 - INFO - __main__ - Step 22855: {'lr': 0.00047590307519253423, 'samples': 4388160, 'steps': 22854, 'loss/train': 1.5946327447891235}
+08/30/2021 17:18:05 - INFO - __main__ - Step 22856: {'lr': 0.00047590080199096324, 'samples': 4388352, 'steps': 22855, 'loss/train': 1.5366663932800293}
+08/30/2021 17:18:05 - INFO - __main__ - Step 22857: {'lr': 0.00047589852868760486, 'samples': 4388544, 'steps': 22856, 'loss/train': 1.5052390098571777}
+08/30/2021 17:18:05 - INFO - __main__ - Step 22858: {'lr': 0.00047589625528246006, 'samples': 4388736, 'steps': 22857, 'loss/train': 1.7839717864990234}
+08/30/2021 17:18:07 - INFO - __main__ - Step 22859: {'lr': 0.0004758939817755299, 'samples': 4388928, 'steps': 22858, 'loss/train': 0.096491739153862}
+08/30/2021 17:18:07 - INFO - __main__ - Step 22860: {'lr': 0.0004758917081668155, 'samples': 4389120, 'steps': 22859, 'loss/train': 1.6763114929199219}
+08/30/2021 17:18:08 - INFO - __main__ - Step 22861: {'lr': 0.00047588943445631767, 'samples': 4389312, 'steps': 22860, 'loss/train': 1.6641391515731812}
+08/30/2021 17:18:08 - INFO - __main__ - Step 22862: {'lr': 0.0004758871606440376, 'samples': 4389504, 'steps': 22861, 'loss/train': 2.582131862640381}
+08/30/2021 17:18:08 - INFO - __main__ - Step 22863: {'lr': 0.0004758848867299762, 'samples': 4389696, 'steps': 22862, 'loss/train': 1.5989612340927124}
+08/30/2021 17:18:10 - INFO - __main__ - Step 22864: {'lr': 0.0004758826127141346, 'samples': 4389888, 'steps': 22863, 'loss/train': 1.7373689413070679}
+08/30/2021 17:18:10 - INFO - __main__ - Step 22865: {'lr': 0.00047588033859651376, 'samples': 4390080, 'steps': 22864, 'loss/train': 1.8764578104019165}
+08/30/2021 17:18:11 - INFO - __main__ - Step 22866: {'lr': 0.00047587806437711475, 'samples': 4390272, 'steps': 22865, 'loss/train': 2.0728724002838135}
+08/30/2021 17:18:11 - INFO - __main__ - Step 22867: {'lr': 0.0004758757900559385, 'samples': 4390464, 'steps': 22866, 'loss/train': 1.1344109773635864}
+08/30/2021 17:18:11 - INFO - __main__ - Step 22868: {'lr': 0.0004758735156329862, 'samples': 4390656, 'steps': 22867, 'loss/train': 1.8590474128723145}
+08/30/2021 17:18:12 - INFO - __main__ - Step 22869: {'lr': 0.00047587124110825874, 'samples': 4390848, 'steps': 22868, 'loss/train': 1.8620820045471191}
+08/30/2021 17:18:13 - INFO - __main__ - Step 22870: {'lr': 0.00047586896648175715, 'samples': 4391040, 'steps': 22869, 'loss/train': 1.315921425819397}
+08/30/2021 17:18:14 - INFO - __main__ - Step 22871: {'lr': 0.00047586669175348254, 'samples': 4391232, 'steps': 22870, 'loss/train': 1.1827940940856934}
+08/30/2021 17:18:14 - INFO - __main__ - Step 22872: {'lr': 0.0004758644169234359, 'samples': 4391424, 'steps': 22871, 'loss/train': 1.5243394374847412}
+08/30/2021 17:18:14 - INFO - __main__ - Step 22873: {'lr': 0.00047586214199161814, 'samples': 4391616, 'steps': 22872, 'loss/train': 1.2829667329788208}
+08/30/2021 17:18:15 - INFO - __main__ - Step 22874: {'lr': 0.00047585986695803046, 'samples': 4391808, 'steps': 22873, 'loss/train': 1.6022831201553345}
+08/30/2021 17:18:16 - INFO - __main__ - Step 22875: {'lr': 0.0004758575918226738, 'samples': 4392000, 'steps': 22874, 'loss/train': 2.4123387336730957}
+08/30/2021 17:18:17 - INFO - __main__ - Step 22876: {'lr': 0.0004758553165855492, 'samples': 4392192, 'steps': 22875, 'loss/train': 1.2562882900238037}
+08/30/2021 17:18:17 - INFO - __main__ - Step 22877: {'lr': 0.00047585304124665766, 'samples': 4392384, 'steps': 22876, 'loss/train': 2.1552555561065674}
+08/30/2021 17:18:17 - INFO - __main__ - Step 22878: {'lr': 0.0004758507658060003, 'samples': 4392576, 'steps': 22877, 'loss/train': 1.7031769752502441}
+08/30/2021 17:18:18 - INFO - __main__ - Step 22879: {'lr': 0.00047584849026357796, 'samples': 4392768, 'steps': 22878, 'loss/train': 1.3326934576034546}
+08/30/2021 17:18:19 - INFO - __main__ - Step 22880: {'lr': 0.0004758462146193918, 'samples': 4392960, 'steps': 22879, 'loss/train': 1.129577875137329}
+08/30/2021 17:18:20 - INFO - __main__ - Step 22881: {'lr': 0.00047584393887344285, 'samples': 4393152, 'steps': 22880, 'loss/train': 1.4693756103515625}
+08/30/2021 17:18:20 - INFO - __main__ - Step 22882: {'lr': 0.00047584166302573204, 'samples': 4393344, 'steps': 22881, 'loss/train': 1.6039628982543945}
+08/30/2021 17:18:20 - INFO - __main__ - Step 22883: {'lr': 0.0004758393870762606, 'samples': 4393536, 'steps': 22882, 'loss/train': 1.9116535186767578}
+08/30/2021 17:18:21 - INFO - __main__ - Step 22884: {'lr': 0.00047583711102502934, 'samples': 4393728, 'steps': 22883, 'loss/train': 1.4598807096481323}
+08/30/2021 17:18:22 - INFO - __main__ - Step 22885: {'lr': 0.0004758348348720393, 'samples': 4393920, 'steps': 22884, 'loss/train': 1.155315637588501}
+08/30/2021 17:18:23 - INFO - __main__ - Step 22886: {'lr': 0.00047583255861729167, 'samples': 4394112, 'steps': 22885, 'loss/train': 1.7323552370071411}
+08/30/2021 17:18:23 - INFO - __main__ - Step 22887: {'lr': 0.00047583028226078734, 'samples': 4394304, 'steps': 22886, 'loss/train': 1.7252373695373535}
+08/30/2021 17:18:23 - INFO - __main__ - Step 22888: {'lr': 0.0004758280058025274, 'samples': 4394496, 'steps': 22887, 'loss/train': 1.758551836013794}
+08/30/2021 17:18:24 - INFO - __main__ - Step 22889: {'lr': 0.00047582572924251276, 'samples': 4394688, 'steps': 22888, 'loss/train': 2.229707956314087}
+08/30/2021 17:18:25 - INFO - __main__ - Step 22890: {'lr': 0.00047582345258074453, 'samples': 4394880, 'steps': 22889, 'loss/train': 1.6733328104019165}
+08/30/2021 17:18:26 - INFO - __main__ - Step 22891: {'lr': 0.0004758211758172238, 'samples': 4395072, 'steps': 22890, 'loss/train': 1.8109558820724487}
+08/30/2021 17:18:26 - INFO - __main__ - Step 22892: {'lr': 0.00047581889895195154, 'samples': 4395264, 'steps': 22891, 'loss/train': 2.3365039825439453}
+08/30/2021 17:18:26 - INFO - __main__ - Step 22893: {'lr': 0.00047581662198492873, 'samples': 4395456, 'steps': 22892, 'loss/train': 1.775614619255066}
+08/30/2021 17:18:27 - INFO - __main__ - Step 22894: {'lr': 0.0004758143449161565, 'samples': 4395648, 'steps': 22893, 'loss/train': 1.4363470077514648}
+08/30/2021 17:18:27 - INFO - __main__ - Step 22895: {'lr': 0.00047581206774563575, 'samples': 4395840, 'steps': 22894, 'loss/train': 1.4303739070892334}
+08/30/2021 17:18:28 - INFO - __main__ - Step 22896: {'lr': 0.0004758097904733676, 'samples': 4396032, 'steps': 22895, 'loss/train': 1.9553728103637695}
+08/30/2021 17:18:29 - INFO - __main__ - Step 22897: {'lr': 0.000475807513099353, 'samples': 4396224, 'steps': 22896, 'loss/train': 1.7079744338989258}
+08/30/2021 17:18:29 - INFO - __main__ - Step 22898: {'lr': 0.000475805235623593, 'samples': 4396416, 'steps': 22897, 'loss/train': 2.0140016078948975}
+08/30/2021 17:18:30 - INFO - __main__ - Step 22899: {'lr': 0.0004758029580460887, 'samples': 4396608, 'steps': 22898, 'loss/train': 1.715692400932312}
+08/30/2021 17:18:30 - INFO - __main__ - Step 22900: {'lr': 0.0004758006803668411, 'samples': 4396800, 'steps': 22899, 'loss/train': 1.5090689659118652}
+08/30/2021 17:18:32 - INFO - __main__ - Step 22901: {'lr': 0.0004757984025858511, 'samples': 4396992, 'steps': 22900, 'loss/train': 1.0468246936798096}
+08/30/2021 17:18:33 - INFO - __main__ - Step 22902: {'lr': 0.0004757961247031199, 'samples': 4397184, 'steps': 22901, 'loss/train': 0.2992228865623474}
+08/30/2021 17:18:33 - INFO - __main__ - Step 22903: {'lr': 0.00047579384671864845, 'samples': 4397376, 'steps': 22902, 'loss/train': 1.5388532876968384}
+08/30/2021 17:18:34 - INFO - __main__ - Step 22904: {'lr': 0.0004757915686324377, 'samples': 4397568, 'steps': 22903, 'loss/train': 1.5558629035949707}
+08/30/2021 17:18:34 - INFO - __main__ - Step 22905: {'lr': 0.00047578929044448883, 'samples': 4397760, 'steps': 22904, 'loss/train': 1.2496048212051392}
+08/30/2021 17:18:36 - INFO - __main__ - Step 22906: {'lr': 0.0004757870121548028, 'samples': 4397952, 'steps': 22905, 'loss/train': 2.200721263885498}
+08/30/2021 17:18:36 - INFO - __main__ - Step 22907: {'lr': 0.0004757847337633806, 'samples': 4398144, 'steps': 22906, 'loss/train': 1.0412330627441406}
+08/30/2021 17:18:36 - INFO - __main__ - Step 22908: {'lr': 0.0004757824552702232, 'samples': 4398336, 'steps': 22907, 'loss/train': 0.11058652400970459}
+08/30/2021 17:18:37 - INFO - __main__ - Step 22909: {'lr': 0.0004757801766753318, 'samples': 4398528, 'steps': 22908, 'loss/train': 1.9616198539733887}
+08/30/2021 17:18:37 - INFO - __main__ - Step 22910: {'lr': 0.00047577789797870743, 'samples': 4398720, 'steps': 22909, 'loss/train': 1.3215875625610352}
+08/30/2021 17:18:37 - INFO - __main__ - Step 22911: {'lr': 0.0004757756191803508, 'samples': 4398912, 'steps': 22910, 'loss/train': 1.7832579612731934}
+08/30/2021 17:18:39 - INFO - __main__ - Step 22912: {'lr': 0.0004757733402802633, 'samples': 4399104, 'steps': 22911, 'loss/train': 1.880214810371399}
+08/30/2021 17:18:40 - INFO - __main__ - Step 22913: {'lr': 0.0004757710612784458, 'samples': 4399296, 'steps': 22912, 'loss/train': 0.1897026151418686}
+08/30/2021 17:18:40 - INFO - __main__ - Step 22914: {'lr': 0.0004757687821748994, 'samples': 4399488, 'steps': 22913, 'loss/train': 1.9128143787384033}
+08/30/2021 17:18:40 - INFO - __main__ - Step 22915: {'lr': 0.00047576650296962496, 'samples': 4399680, 'steps': 22914, 'loss/train': 1.9582329988479614}
+08/30/2021 17:18:41 - INFO - __main__ - Step 22916: {'lr': 0.0004757642236626237, 'samples': 4399872, 'steps': 22915, 'loss/train': 1.375234842300415}
+08/30/2021 17:18:42 - INFO - __main__ - Step 22917: {'lr': 0.00047576194425389654, 'samples': 4400064, 'steps': 22916, 'loss/train': 1.1546584367752075}
+08/30/2021 17:18:43 - INFO - __main__ - Step 22918: {'lr': 0.00047575966474344445, 'samples': 4400256, 'steps': 22917, 'loss/train': 1.2885922193527222}
+08/30/2021 17:18:43 - INFO - __main__ - Step 22919: {'lr': 0.00047575738513126867, 'samples': 4400448, 'steps': 22918, 'loss/train': 1.3296352624893188}
+08/30/2021 17:18:43 - INFO - __main__ - Step 22920: {'lr': 0.00047575510541737, 'samples': 4400640, 'steps': 22919, 'loss/train': 1.962688684463501}
+08/30/2021 17:18:44 - INFO - __main__ - Step 22921: {'lr': 0.0004757528256017496, 'samples': 4400832, 'steps': 22920, 'loss/train': 1.3125160932540894}
+08/30/2021 17:18:45 - INFO - __main__ - Step 22922: {'lr': 0.00047575054568440846, 'samples': 4401024, 'steps': 22921, 'loss/train': 3.0557782649993896}
+08/30/2021 17:18:46 - INFO - __main__ - Step 22923: {'lr': 0.00047574826566534764, 'samples': 4401216, 'steps': 22922, 'loss/train': 1.4462623596191406}
+08/30/2021 17:18:46 - INFO - __main__ - Step 22924: {'lr': 0.0004757459855445681, 'samples': 4401408, 'steps': 22923, 'loss/train': 1.3010894060134888}
+08/30/2021 17:18:46 - INFO - __main__ - Step 22925: {'lr': 0.0004757437053220709, 'samples': 4401600, 'steps': 22924, 'loss/train': 1.4071928262710571}
+08/30/2021 17:18:47 - INFO - __main__ - Step 22926: {'lr': 0.0004757414249978571, 'samples': 4401792, 'steps': 22925, 'loss/train': 1.6209383010864258}
+08/30/2021 17:18:47 - INFO - __main__ - Step 22927: {'lr': 0.0004757391445719277, 'samples': 4401984, 'steps': 22926, 'loss/train': 1.5751428604125977}
+08/30/2021 17:18:49 - INFO - __main__ - Step 22928: {'lr': 0.00047573686404428365, 'samples': 4402176, 'steps': 22927, 'loss/train': 1.1744216680526733}
+08/30/2021 17:18:49 - INFO - __main__ - Step 22929: {'lr': 0.0004757345834149261, 'samples': 4402368, 'steps': 22928, 'loss/train': 1.4119768142700195}
+08/30/2021 17:18:50 - INFO - __main__ - Step 22930: {'lr': 0.00047573230268385604, 'samples': 4402560, 'steps': 22929, 'loss/train': 1.8124980926513672}
+08/30/2021 17:18:50 - INFO - __main__ - Step 22931: {'lr': 0.0004757300218510745, 'samples': 4402752, 'steps': 22930, 'loss/train': 1.4101451635360718}
+08/30/2021 17:18:50 - INFO - __main__ - Step 22932: {'lr': 0.00047572774091658243, 'samples': 4402944, 'steps': 22931, 'loss/train': 1.6242215633392334}
+08/30/2021 17:18:52 - INFO - __main__ - Step 22933: {'lr': 0.000475725459880381, 'samples': 4403136, 'steps': 22932, 'loss/train': 1.5872819423675537}
+08/30/2021 17:18:52 - INFO - __main__ - Step 22934: {'lr': 0.00047572317874247107, 'samples': 4403328, 'steps': 22933, 'loss/train': 1.8957769870758057}
+08/30/2021 17:18:53 - INFO - __main__ - Step 22935: {'lr': 0.00047572089750285383, 'samples': 4403520, 'steps': 22934, 'loss/train': 1.7136831283569336}
+08/30/2021 17:18:53 - INFO - __main__ - Step 22936: {'lr': 0.00047571861616153025, 'samples': 4403712, 'steps': 22935, 'loss/train': 1.3539509773254395}
+08/30/2021 17:18:53 - INFO - __main__ - Step 22937: {'lr': 0.0004757163347185013, 'samples': 4403904, 'steps': 22936, 'loss/train': 1.2230592966079712}
+08/30/2021 17:18:55 - INFO - __main__ - Step 22938: {'lr': 0.00047571405317376803, 'samples': 4404096, 'steps': 22937, 'loss/train': 2.0420732498168945}
+08/30/2021 17:18:55 - INFO - __main__ - Step 22939: {'lr': 0.0004757117715273316, 'samples': 4404288, 'steps': 22938, 'loss/train': 1.3886237144470215}
+08/30/2021 17:18:56 - INFO - __main__ - Step 22940: {'lr': 0.00047570948977919284, 'samples': 4404480, 'steps': 22939, 'loss/train': 1.8188010454177856}
+08/30/2021 17:18:56 - INFO - __main__ - Step 22941: {'lr': 0.00047570720792935284, 'samples': 4404672, 'steps': 22940, 'loss/train': 1.5992809534072876}
+08/30/2021 17:18:56 - INFO - __main__ - Step 22942: {'lr': 0.00047570492597781274, 'samples': 4404864, 'steps': 22941, 'loss/train': 1.5576814413070679}
+08/30/2021 17:18:58 - INFO - __main__ - Step 22943: {'lr': 0.0004757026439245735, 'samples': 4405056, 'steps': 22942, 'loss/train': 1.3755614757537842}
+08/30/2021 17:18:59 - INFO - __main__ - Step 22944: {'lr': 0.0004757003617696361, 'samples': 4405248, 'steps': 22943, 'loss/train': 1.7030465602874756}
+08/30/2021 17:18:59 - INFO - __main__ - Step 22945: {'lr': 0.0004756980795130015, 'samples': 4405440, 'steps': 22944, 'loss/train': 1.8665271997451782}
+08/30/2021 17:18:59 - INFO - __main__ - Step 22946: {'lr': 0.00047569579715467093, 'samples': 4405632, 'steps': 22945, 'loss/train': 1.5804766416549683}
+08/30/2021 17:19:00 - INFO - __main__ - Step 22947: {'lr': 0.00047569351469464526, 'samples': 4405824, 'steps': 22946, 'loss/train': 1.5600886344909668}
+08/30/2021 17:19:00 - INFO - __main__ - Step 22948: {'lr': 0.0004756912321329256, 'samples': 4406016, 'steps': 22947, 'loss/train': 0.07514391839504242}
+08/30/2021 17:19:01 - INFO - __main__ - Step 22949: {'lr': 0.000475688949469513, 'samples': 4406208, 'steps': 22948, 'loss/train': 1.5531437397003174}
+08/30/2021 17:19:02 - INFO - __main__ - Step 22950: {'lr': 0.0004756866667044084, 'samples': 4406400, 'steps': 22949, 'loss/train': 1.7941099405288696}
+08/30/2021 17:19:02 - INFO - __main__ - Step 22951: {'lr': 0.0004756843838376128, 'samples': 4406592, 'steps': 22950, 'loss/train': 0.19485221803188324}
+08/30/2021 17:19:03 - INFO - __main__ - Step 22952: {'lr': 0.0004756821008691274, 'samples': 4406784, 'steps': 22951, 'loss/train': 1.46951162815094}
+08/30/2021 17:19:03 - INFO - __main__ - Step 22953: {'lr': 0.0004756798177989531, 'samples': 4406976, 'steps': 22952, 'loss/train': 1.5732104778289795}
+08/30/2021 17:19:05 - INFO - __main__ - Step 22954: {'lr': 0.00047567753462709095, 'samples': 4407168, 'steps': 22953, 'loss/train': 1.7873196601867676}
+08/30/2021 17:19:06 - INFO - __main__ - Step 22955: {'lr': 0.00047567525135354193, 'samples': 4407360, 'steps': 22954, 'loss/train': 1.5982166528701782}
+08/30/2021 17:19:06 - INFO - __main__ - Step 22956: {'lr': 0.00047567296797830727, 'samples': 4407552, 'steps': 22955, 'loss/train': 1.9292433261871338}
+08/30/2021 17:19:06 - INFO - __main__ - Step 22957: {'lr': 0.00047567068450138773, 'samples': 4407744, 'steps': 22956, 'loss/train': 1.453284740447998}
+08/30/2021 17:19:07 - INFO - __main__ - Step 22958: {'lr': 0.0004756684009227845, 'samples': 4407936, 'steps': 22957, 'loss/train': 1.9705432653427124}
+08/30/2021 17:19:08 - INFO - __main__ - Step 22959: {'lr': 0.0004756661172424986, 'samples': 4408128, 'steps': 22958, 'loss/train': 1.847352385520935}
+08/30/2021 17:19:08 - INFO - __main__ - Step 22960: {'lr': 0.000475663833460531, 'samples': 4408320, 'steps': 22959, 'loss/train': 1.7003968954086304}
+08/30/2021 17:19:09 - INFO - __main__ - Step 22961: {'lr': 0.00047566154957688275, 'samples': 4408512, 'steps': 22960, 'loss/train': 0.9619525671005249}
+08/30/2021 17:19:09 - INFO - __main__ - Step 22962: {'lr': 0.0004756592655915549, 'samples': 4408704, 'steps': 22961, 'loss/train': 1.66960871219635}
+08/30/2021 17:19:10 - INFO - __main__ - Step 22963: {'lr': 0.00047565698150454845, 'samples': 4408896, 'steps': 22962, 'loss/train': 1.9270974397659302}
+08/30/2021 17:19:11 - INFO - __main__ - Step 22964: {'lr': 0.0004756546973158644, 'samples': 4409088, 'steps': 22963, 'loss/train': 1.7784135341644287}
+08/30/2021 17:19:12 - INFO - __main__ - Step 22965: {'lr': 0.00047565241302550395, 'samples': 4409280, 'steps': 22964, 'loss/train': 1.859703540802002}
+08/30/2021 17:19:12 - INFO - __main__ - Step 22966: {'lr': 0.0004756501286334679, 'samples': 4409472, 'steps': 22965, 'loss/train': 1.8214054107666016}
+08/30/2021 17:19:13 - INFO - __main__ - Step 22967: {'lr': 0.0004756478441397575, 'samples': 4409664, 'steps': 22966, 'loss/train': 0.06283416599035263}
+08/30/2021 17:19:13 - INFO - __main__ - Step 22968: {'lr': 0.0004756455595443735, 'samples': 4409856, 'steps': 22967, 'loss/train': 1.3767576217651367}
+08/30/2021 17:19:13 - INFO - __main__ - Step 22969: {'lr': 0.00047564327484731725, 'samples': 4410048, 'steps': 22968, 'loss/train': 2.7831339836120605}
+08/30/2021 17:19:15 - INFO - __main__ - Step 22970: {'lr': 0.0004756409900485895, 'samples': 4410240, 'steps': 22969, 'loss/train': 2.001856803894043}
+08/30/2021 17:19:15 - INFO - __main__ - Step 22971: {'lr': 0.00047563870514819154, 'samples': 4410432, 'steps': 22970, 'loss/train': 1.5054091215133667}
+08/30/2021 17:19:16 - INFO - __main__ - Step 22972: {'lr': 0.0004756364201461241, 'samples': 4410624, 'steps': 22971, 'loss/train': 2.18689227104187}
+08/30/2021 17:19:16 - INFO - __main__ - Step 22973: {'lr': 0.00047563413504238847, 'samples': 4410816, 'steps': 22972, 'loss/train': 1.7257452011108398}
+08/30/2021 17:19:16 - INFO - __main__ - Step 22974: {'lr': 0.0004756318498369855, 'samples': 4411008, 'steps': 22973, 'loss/train': 1.1092854738235474}
+08/30/2021 17:19:18 - INFO - __main__ - Step 22975: {'lr': 0.0004756295645299164, 'samples': 4411200, 'steps': 22974, 'loss/train': 1.6956833600997925}
+08/30/2021 17:19:18 - INFO - __main__ - Step 22976: {'lr': 0.00047562727912118206, 'samples': 4411392, 'steps': 22975, 'loss/train': 2.3967127799987793}
+08/30/2021 17:19:19 - INFO - __main__ - Step 22977: {'lr': 0.00047562499361078356, 'samples': 4411584, 'steps': 22976, 'loss/train': 1.6982682943344116}
+08/30/2021 17:19:19 - INFO - __main__ - Step 22978: {'lr': 0.00047562270799872186, 'samples': 4411776, 'steps': 22977, 'loss/train': 1.9491908550262451}
+08/30/2021 17:19:19 - INFO - __main__ - Step 22979: {'lr': 0.00047562042228499815, 'samples': 4411968, 'steps': 22978, 'loss/train': 1.7589589357376099}
+08/30/2021 17:19:21 - INFO - __main__ - Step 22980: {'lr': 0.00047561813646961325, 'samples': 4412160, 'steps': 22979, 'loss/train': 1.4948928356170654}
+08/30/2021 17:19:21 - INFO - __main__ - Step 22981: {'lr': 0.0004756158505525684, 'samples': 4412352, 'steps': 22980, 'loss/train': 1.483370065689087}
+08/30/2021 17:19:22 - INFO - __main__ - Step 22982: {'lr': 0.0004756135645338644, 'samples': 4412544, 'steps': 22981, 'loss/train': 1.978050708770752}
+08/30/2021 17:19:22 - INFO - __main__ - Step 22983: {'lr': 0.00047561127841350256, 'samples': 4412736, 'steps': 22982, 'loss/train': 1.9036160707473755}
+08/30/2021 17:19:22 - INFO - __main__ - Step 22984: {'lr': 0.0004756089921914837, 'samples': 4412928, 'steps': 22983, 'loss/train': 0.5567795038223267}
+08/30/2021 17:19:23 - INFO - __main__ - Step 22985: {'lr': 0.00047560670586780886, 'samples': 4413120, 'steps': 22984, 'loss/train': 1.0332645177841187}
+08/30/2021 17:19:24 - INFO - __main__ - Step 22986: {'lr': 0.0004756044194424792, 'samples': 4413312, 'steps': 22985, 'loss/train': 1.9853816032409668}
+08/30/2021 17:19:25 - INFO - __main__ - Step 22987: {'lr': 0.0004756021329154956, 'samples': 4413504, 'steps': 22986, 'loss/train': 1.6890605688095093}
+08/30/2021 17:19:25 - INFO - __main__ - Step 22988: {'lr': 0.0004755998462868592, 'samples': 4413696, 'steps': 22987, 'loss/train': 1.4336907863616943}
+08/30/2021 17:19:25 - INFO - __main__ - Step 22989: {'lr': 0.00047559755955657097, 'samples': 4413888, 'steps': 22988, 'loss/train': 1.275169849395752}
+08/30/2021 17:19:26 - INFO - __main__ - Step 22990: {'lr': 0.000475595272724632, 'samples': 4414080, 'steps': 22989, 'loss/train': 2.0036916732788086}
+08/30/2021 17:19:27 - INFO - __main__ - Step 22991: {'lr': 0.00047559298579104325, 'samples': 4414272, 'steps': 22990, 'loss/train': 1.9356542825698853}
+08/30/2021 17:19:27 - INFO - __main__ - Step 22992: {'lr': 0.00047559069875580573, 'samples': 4414464, 'steps': 22991, 'loss/train': 2.0371615886688232}
+08/30/2021 17:19:28 - INFO - __main__ - Step 22993: {'lr': 0.00047558841161892063, 'samples': 4414656, 'steps': 22992, 'loss/train': 1.7100064754486084}
+08/30/2021 17:19:28 - INFO - __main__ - Step 22994: {'lr': 0.00047558612438038887, 'samples': 4414848, 'steps': 22993, 'loss/train': 1.5306779146194458}
+08/30/2021 17:19:29 - INFO - __main__ - Step 22995: {'lr': 0.00047558383704021136, 'samples': 4415040, 'steps': 22994, 'loss/train': 1.7773598432540894}
+08/30/2021 17:19:30 - INFO - __main__ - Step 22996: {'lr': 0.00047558154959838935, 'samples': 4415232, 'steps': 22995, 'loss/train': 2.1924450397491455}
+08/30/2021 17:19:31 - INFO - __main__ - Step 22997: {'lr': 0.0004755792620549237, 'samples': 4415424, 'steps': 22996, 'loss/train': 1.473719835281372}
+08/30/2021 17:19:31 - INFO - __main__ - Step 22998: {'lr': 0.0004755769744098156, 'samples': 4415616, 'steps': 22997, 'loss/train': 1.3908065557479858}
+08/30/2021 17:19:31 - INFO - __main__ - Step 22999: {'lr': 0.00047557468666306596, 'samples': 4415808, 'steps': 22998, 'loss/train': 1.2253528833389282}
+08/30/2021 17:19:32 - INFO - __main__ - Step 23000: {'lr': 0.00047557239881467584, 'samples': 4416000, 'steps': 22999, 'loss/train': 1.6886320114135742}
+08/30/2021 17:19:32 - INFO - __main__ - Step 23001: {'lr': 0.0004755701108646463, 'samples': 4416192, 'steps': 23000, 'loss/train': 5.877809524536133}
+08/30/2021 17:19:33 - INFO - __main__ - Step 23002: {'lr': 0.0004755678228129784, 'samples': 4416384, 'steps': 23001, 'loss/train': 1.6232523918151855}
+08/30/2021 17:19:34 - INFO - __main__ - Step 23003: {'lr': 0.000475565534659673, 'samples': 4416576, 'steps': 23002, 'loss/train': 0.8050466179847717}
+08/30/2021 17:19:34 - INFO - __main__ - Step 23004: {'lr': 0.00047556324640473134, 'samples': 4416768, 'steps': 23003, 'loss/train': 1.570481300354004}
+08/30/2021 17:19:35 - INFO - __main__ - Step 23005: {'lr': 0.0004755609580481543, 'samples': 4416960, 'steps': 23004, 'loss/train': 1.5985801219940186}
+08/30/2021 17:19:35 - INFO - __main__ - Step 23006: {'lr': 0.00047555866958994296, 'samples': 4417152, 'steps': 23005, 'loss/train': 1.6451317071914673}
+08/30/2021 17:19:36 - INFO - __main__ - Step 23007: {'lr': 0.00047555638103009845, 'samples': 4417344, 'steps': 23006, 'loss/train': 1.5482604503631592}
+08/30/2021 17:19:37 - INFO - __main__ - Step 23008: {'lr': 0.0004755540923686217, 'samples': 4417536, 'steps': 23007, 'loss/train': 2.0507125854492188}
+08/30/2021 17:19:37 - INFO - __main__ - Step 23009: {'lr': 0.0004755518036055137, 'samples': 4417728, 'steps': 23008, 'loss/train': 1.5620150566101074}
+08/30/2021 17:19:38 - INFO - __main__ - Step 23010: {'lr': 0.0004755495147407756, 'samples': 4417920, 'steps': 23009, 'loss/train': 1.3272922039031982}
+08/30/2021 17:19:38 - INFO - __main__ - Step 23011: {'lr': 0.00047554722577440833, 'samples': 4418112, 'steps': 23010, 'loss/train': 1.2647225856781006}
+08/30/2021 17:19:40 - INFO - __main__ - Step 23012: {'lr': 0.00047554493670641296, 'samples': 4418304, 'steps': 23011, 'loss/train': 1.5204968452453613}
+08/30/2021 17:19:40 - INFO - __main__ - Step 23013: {'lr': 0.0004755426475367905, 'samples': 4418496, 'steps': 23012, 'loss/train': 2.0286548137664795}
+08/30/2021 17:19:41 - INFO - __main__ - Step 23014: {'lr': 0.00047554035826554206, 'samples': 4418688, 'steps': 23013, 'loss/train': 1.5546232461929321}
+08/30/2021 17:19:41 - INFO - __main__ - Step 23015: {'lr': 0.0004755380688926686, 'samples': 4418880, 'steps': 23014, 'loss/train': 1.2495543956756592}
+08/30/2021 17:19:42 - INFO - __main__ - Step 23016: {'lr': 0.00047553577941817114, 'samples': 4419072, 'steps': 23015, 'loss/train': 1.704040765762329}
+08/30/2021 17:19:43 - INFO - __main__ - Step 23017: {'lr': 0.0004755334898420507, 'samples': 4419264, 'steps': 23016, 'loss/train': 1.5796982049942017}
+08/30/2021 17:19:43 - INFO - __main__ - Step 23018: {'lr': 0.00047553120016430837, 'samples': 4419456, 'steps': 23017, 'loss/train': 2.387077808380127}
+08/30/2021 17:19:44 - INFO - __main__ - Step 23019: {'lr': 0.0004755289103849453, 'samples': 4419648, 'steps': 23018, 'loss/train': 1.6557508707046509}
+08/30/2021 17:19:44 - INFO - __main__ - Step 23020: {'lr': 0.0004755266205039622, 'samples': 4419840, 'steps': 23019, 'loss/train': 1.4642345905303955}
+08/30/2021 17:19:44 - INFO - __main__ - Step 23021: {'lr': 0.00047552433052136034, 'samples': 4420032, 'steps': 23020, 'loss/train': 1.5368373394012451}
+08/30/2021 17:19:46 - INFO - __main__ - Step 23022: {'lr': 0.00047552204043714076, 'samples': 4420224, 'steps': 23021, 'loss/train': 1.7309247255325317}
+08/30/2021 17:19:46 - INFO - __main__ - Step 23023: {'lr': 0.0004755197502513043, 'samples': 4420416, 'steps': 23022, 'loss/train': 1.6309560537338257}
+08/30/2021 17:19:47 - INFO - __main__ - Step 23024: {'lr': 0.00047551745996385233, 'samples': 4420608, 'steps': 23023, 'loss/train': 1.8825452327728271}
+08/30/2021 17:19:47 - INFO - __main__ - Step 23025: {'lr': 0.00047551516957478545, 'samples': 4420800, 'steps': 23024, 'loss/train': 1.3205102682113647}
+08/30/2021 17:19:47 - INFO - __main__ - Step 23026: {'lr': 0.0004755128790841051, 'samples': 4420992, 'steps': 23025, 'loss/train': 1.8629093170166016}
+08/30/2021 17:19:48 - INFO - __main__ - Step 23027: {'lr': 0.000475510588491812, 'samples': 4421184, 'steps': 23026, 'loss/train': 1.561285138130188}
+08/30/2021 17:19:49 - INFO - __main__ - Step 23028: {'lr': 0.00047550829779790735, 'samples': 4421376, 'steps': 23027, 'loss/train': 1.763322114944458}
+08/30/2021 17:19:50 - INFO - __main__ - Step 23029: {'lr': 0.0004755060070023921, 'samples': 4421568, 'steps': 23028, 'loss/train': 1.6220554113388062}
+08/30/2021 17:19:50 - INFO - __main__ - Step 23030: {'lr': 0.0004755037161052674, 'samples': 4421760, 'steps': 23029, 'loss/train': 1.757729172706604}
+08/30/2021 17:19:50 - INFO - __main__ - Step 23031: {'lr': 0.00047550142510653415, 'samples': 4421952, 'steps': 23030, 'loss/train': 0.825249969959259}
+08/30/2021 17:19:51 - INFO - __main__ - Step 23032: {'lr': 0.0004754991340061935, 'samples': 4422144, 'steps': 23031, 'loss/train': 1.0758825540542603}
+08/30/2021 17:19:53 - INFO - __main__ - Step 23033: {'lr': 0.0004754968428042463, 'samples': 4422336, 'steps': 23032, 'loss/train': 1.6299127340316772}
+08/30/2021 17:19:53 - INFO - __main__ - Step 23034: {'lr': 0.0004754945515006938, 'samples': 4422528, 'steps': 23033, 'loss/train': 1.7288877964019775}
+08/30/2021 17:19:54 - INFO - __main__ - Step 23035: {'lr': 0.0004754922600955369, 'samples': 4422720, 'steps': 23034, 'loss/train': 1.4009493589401245}
+08/30/2021 17:19:54 - INFO - __main__ - Step 23036: {'lr': 0.0004754899685887767, 'samples': 4422912, 'steps': 23035, 'loss/train': 1.2913403511047363}
+08/30/2021 17:19:54 - INFO - __main__ - Step 23037: {'lr': 0.0004754876769804142, 'samples': 4423104, 'steps': 23036, 'loss/train': 1.4569898843765259}
+08/30/2021 17:19:55 - INFO - __main__ - Step 23038: {'lr': 0.00047548538527045035, 'samples': 4423296, 'steps': 23037, 'loss/train': 0.17948797345161438}
+08/30/2021 17:19:57 - INFO - __main__ - Step 23039: {'lr': 0.00047548309345888637, 'samples': 4423488, 'steps': 23038, 'loss/train': 0.34549573063850403}
+08/30/2021 17:19:57 - INFO - __main__ - Step 23040: {'lr': 0.00047548080154572315, 'samples': 4423680, 'steps': 23039, 'loss/train': 1.16763436794281}
+08/30/2021 17:19:58 - INFO - __main__ - Step 23041: {'lr': 0.00047547850953096174, 'samples': 4423872, 'steps': 23040, 'loss/train': 1.441243052482605}
+08/30/2021 17:19:58 - INFO - __main__ - Step 23042: {'lr': 0.0004754762174146032, 'samples': 4424064, 'steps': 23041, 'loss/train': 1.9190456867218018}
+08/30/2021 17:19:58 - INFO - __main__ - Step 23043: {'lr': 0.00047547392519664853, 'samples': 4424256, 'steps': 23042, 'loss/train': 2.913517713546753}
+08/30/2021 17:19:59 - INFO - __main__ - Step 23044: {'lr': 0.0004754716328770988, 'samples': 4424448, 'steps': 23043, 'loss/train': 2.9844703674316406}
+08/30/2021 17:20:00 - INFO - __main__ - Step 23045: {'lr': 0.00047546934045595516, 'samples': 4424640, 'steps': 23044, 'loss/train': 1.363848090171814}
+08/30/2021 17:20:01 - INFO - __main__ - Step 23046: {'lr': 0.00047546704793321835, 'samples': 4424832, 'steps': 23045, 'loss/train': 1.8653638362884521}
+08/30/2021 17:20:01 - INFO - __main__ - Step 23047: {'lr': 0.0004754647553088896, 'samples': 4425024, 'steps': 23046, 'loss/train': 1.5340021848678589}
+08/30/2021 17:20:02 - INFO - __main__ - Step 23048: {'lr': 0.00047546246258297, 'samples': 4425216, 'steps': 23047, 'loss/train': 1.547456979751587}
+08/30/2021 17:20:02 - INFO - __main__ - Step 23049: {'lr': 0.00047546016975546037, 'samples': 4425408, 'steps': 23048, 'loss/train': 0.10871273279190063}
+08/30/2021 17:20:03 - INFO - __main__ - Step 23050: {'lr': 0.00047545787682636194, 'samples': 4425600, 'steps': 23049, 'loss/train': 1.824331283569336}
+08/30/2021 17:20:04 - INFO - __main__ - Step 23051: {'lr': 0.00047545558379567565, 'samples': 4425792, 'steps': 23050, 'loss/train': 1.2129907608032227}
+08/30/2021 17:20:04 - INFO - __main__ - Step 23052: {'lr': 0.00047545329066340256, 'samples': 4425984, 'steps': 23051, 'loss/train': 1.473488688468933}
+08/30/2021 17:20:05 - INFO - __main__ - Step 23053: {'lr': 0.00047545099742954367, 'samples': 4426176, 'steps': 23052, 'loss/train': 1.6842970848083496}
+08/30/2021 17:20:05 - INFO - __main__ - Step 23054: {'lr': 0.0004754487040941001, 'samples': 4426368, 'steps': 23053, 'loss/train': 1.7076953649520874}
+08/30/2021 17:20:05 - INFO - __main__ - Step 23055: {'lr': 0.0004754464106570727, 'samples': 4426560, 'steps': 23054, 'loss/train': 1.6193013191223145}
+08/30/2021 17:20:07 - INFO - __main__ - Step 23056: {'lr': 0.00047544411711846277, 'samples': 4426752, 'steps': 23055, 'loss/train': 1.618159294128418}
+08/30/2021 17:20:07 - INFO - __main__ - Step 23057: {'lr': 0.00047544182347827114, 'samples': 4426944, 'steps': 23056, 'loss/train': 1.6489686965942383}
+08/30/2021 17:20:08 - INFO - __main__ - Step 23058: {'lr': 0.0004754395297364989, 'samples': 4427136, 'steps': 23057, 'loss/train': 1.1632510423660278}
+08/30/2021 17:20:08 - INFO - __main__ - Step 23059: {'lr': 0.0004754372358931471, 'samples': 4427328, 'steps': 23058, 'loss/train': 1.6978973150253296}
+08/30/2021 17:20:08 - INFO - __main__ - Step 23060: {'lr': 0.00047543494194821675, 'samples': 4427520, 'steps': 23059, 'loss/train': 2.407747983932495}
+08/30/2021 17:20:10 - INFO - __main__ - Step 23061: {'lr': 0.00047543264790170887, 'samples': 4427712, 'steps': 23060, 'loss/train': 1.26861572265625}
+08/30/2021 17:20:10 - INFO - __main__ - Step 23062: {'lr': 0.00047543035375362453, 'samples': 4427904, 'steps': 23061, 'loss/train': 1.7939304113388062}
+08/30/2021 17:20:11 - INFO - __main__ - Step 23063: {'lr': 0.00047542805950396476, 'samples': 4428096, 'steps': 23062, 'loss/train': 1.8011139631271362}
+08/30/2021 17:20:11 - INFO - __main__ - Step 23064: {'lr': 0.00047542576515273064, 'samples': 4428288, 'steps': 23063, 'loss/train': 1.9798765182495117}
+08/30/2021 17:20:11 - INFO - __main__ - Step 23065: {'lr': 0.0004754234706999231, 'samples': 4428480, 'steps': 23064, 'loss/train': 2.1380014419555664}
+08/30/2021 17:20:13 - INFO - __main__ - Step 23066: {'lr': 0.0004754211761455432, 'samples': 4428672, 'steps': 23065, 'loss/train': 1.8568460941314697}
+08/30/2021 17:20:14 - INFO - __main__ - Step 23067: {'lr': 0.000475418881489592, 'samples': 4428864, 'steps': 23066, 'loss/train': 2.2325549125671387}
+08/30/2021 17:20:14 - INFO - __main__ - Step 23068: {'lr': 0.0004754165867320706, 'samples': 4429056, 'steps': 23067, 'loss/train': 1.2719651460647583}
+08/30/2021 17:20:14 - INFO - __main__ - Step 23069: {'lr': 0.00047541429187297984, 'samples': 4429248, 'steps': 23068, 'loss/train': 0.6197928190231323}
+08/30/2021 17:20:15 - INFO - __main__ - Step 23070: {'lr': 0.00047541199691232094, 'samples': 4429440, 'steps': 23069, 'loss/train': 1.4448164701461792}
+08/30/2021 17:20:16 - INFO - __main__ - Step 23071: {'lr': 0.0004754097018500949, 'samples': 4429632, 'steps': 23070, 'loss/train': 1.665648102760315}
+08/30/2021 17:20:17 - INFO - __main__ - Step 23072: {'lr': 0.0004754074066863027, 'samples': 4429824, 'steps': 23071, 'loss/train': 1.2831231355667114}
+08/30/2021 17:20:17 - INFO - __main__ - Step 23073: {'lr': 0.0004754051114209454, 'samples': 4430016, 'steps': 23072, 'loss/train': 2.770606756210327}
+08/30/2021 17:20:18 - INFO - __main__ - Step 23074: {'lr': 0.0004754028160540241, 'samples': 4430208, 'steps': 23073, 'loss/train': 1.4709585905075073}
+08/30/2021 17:20:18 - INFO - __main__ - Step 23075: {'lr': 0.0004754005205855397, 'samples': 4430400, 'steps': 23074, 'loss/train': 1.0107523202896118}
+08/30/2021 17:20:18 - INFO - __main__ - Step 23076: {'lr': 0.0004753982250154933, 'samples': 4430592, 'steps': 23075, 'loss/train': 1.0506287813186646}
+08/30/2021 17:20:20 - INFO - __main__ - Step 23077: {'lr': 0.00047539592934388596, 'samples': 4430784, 'steps': 23076, 'loss/train': 1.9369217157363892}
+08/30/2021 17:20:20 - INFO - __main__ - Step 23078: {'lr': 0.0004753936335707187, 'samples': 4430976, 'steps': 23077, 'loss/train': 1.4263718128204346}
+08/30/2021 17:20:21 - INFO - __main__ - Step 23079: {'lr': 0.0004753913376959925, 'samples': 4431168, 'steps': 23078, 'loss/train': 1.7650058269500732}
+08/30/2021 17:20:21 - INFO - __main__ - Step 23080: {'lr': 0.00047538904171970847, 'samples': 4431360, 'steps': 23079, 'loss/train': 0.5631402730941772}
+08/30/2021 17:20:21 - INFO - __main__ - Step 23081: {'lr': 0.0004753867456418677, 'samples': 4431552, 'steps': 23080, 'loss/train': 1.8370333909988403}
+08/30/2021 17:20:23 - INFO - __main__ - Step 23082: {'lr': 0.000475384449462471, 'samples': 4431744, 'steps': 23081, 'loss/train': 1.7785964012145996}
+08/30/2021 17:20:24 - INFO - __main__ - Step 23083: {'lr': 0.00047538215318151955, 'samples': 4431936, 'steps': 23082, 'loss/train': 1.7811259031295776}
+08/30/2021 17:20:24 - INFO - __main__ - Step 23084: {'lr': 0.0004753798567990145, 'samples': 4432128, 'steps': 23083, 'loss/train': 0.8969607949256897}
+08/30/2021 17:20:24 - INFO - __main__ - Step 23085: {'lr': 0.00047537756031495673, 'samples': 4432320, 'steps': 23084, 'loss/train': 1.802507758140564}
+08/30/2021 17:20:25 - INFO - __main__ - Step 23086: {'lr': 0.0004753752637293473, 'samples': 4432512, 'steps': 23085, 'loss/train': 1.6796890497207642}
+08/30/2021 17:20:25 - INFO - __main__ - Step 23087: {'lr': 0.0004753729670421871, 'samples': 4432704, 'steps': 23086, 'loss/train': 1.564009428024292}
+08/30/2021 17:20:27 - INFO - __main__ - Step 23088: {'lr': 0.0004753706702534775, 'samples': 4432896, 'steps': 23087, 'loss/train': 2.1037065982818604}
+08/30/2021 17:20:27 - INFO - __main__ - Step 23089: {'lr': 0.0004753683733632193, 'samples': 4433088, 'steps': 23088, 'loss/train': 1.561545729637146}
+08/30/2021 17:20:28 - INFO - __main__ - Step 23090: {'lr': 0.0004753660763714136, 'samples': 4433280, 'steps': 23089, 'loss/train': 1.6166492700576782}
+08/30/2021 17:20:28 - INFO - __main__ - Step 23091: {'lr': 0.00047536377927806143, 'samples': 4433472, 'steps': 23090, 'loss/train': 1.104941487312317}
+08/30/2021 17:20:28 - INFO - __main__ - Step 23092: {'lr': 0.0004753614820831638, 'samples': 4433664, 'steps': 23091, 'loss/train': 1.2165592908859253}
+08/30/2021 17:20:29 - INFO - __main__ - Step 23093: {'lr': 0.0004753591847867218, 'samples': 4433856, 'steps': 23092, 'loss/train': 1.848177194595337}
+08/30/2021 17:20:31 - INFO - __main__ - Step 23094: {'lr': 0.0004753568873887364, 'samples': 4434048, 'steps': 23093, 'loss/train': 1.8158068656921387}
+08/30/2021 17:20:31 - INFO - __main__ - Step 23095: {'lr': 0.00047535458988920865, 'samples': 4434240, 'steps': 23094, 'loss/train': 0.7858121991157532}
+08/30/2021 17:20:31 - INFO - __main__ - Step 23096: {'lr': 0.0004753522922881396, 'samples': 4434432, 'steps': 23095, 'loss/train': 0.13198018074035645}
+08/30/2021 17:20:32 - INFO - __main__ - Step 23097: {'lr': 0.00047534999458553027, 'samples': 4434624, 'steps': 23096, 'loss/train': 1.726241111755371}
+08/30/2021 17:20:32 - INFO - __main__ - Step 23098: {'lr': 0.00047534769678138177, 'samples': 4434816, 'steps': 23097, 'loss/train': 2.280733823776245}
+08/30/2021 17:20:34 - INFO - __main__ - Step 23099: {'lr': 0.00047534539887569507, 'samples': 4435008, 'steps': 23098, 'loss/train': 1.5222843885421753}
+08/30/2021 17:20:34 - INFO - __main__ - Step 23100: {'lr': 0.00047534310086847116, 'samples': 4435200, 'steps': 23099, 'loss/train': 2.4165260791778564}
+08/30/2021 17:20:35 - INFO - __main__ - Step 23101: {'lr': 0.0004753408027597111, 'samples': 4435392, 'steps': 23100, 'loss/train': 1.8077912330627441}
+08/30/2021 17:20:35 - INFO - __main__ - Step 23102: {'lr': 0.0004753385045494161, 'samples': 4435584, 'steps': 23101, 'loss/train': 1.6808812618255615}
+08/30/2021 17:20:35 - INFO - __main__ - Step 23103: {'lr': 0.0004753362062375869, 'samples': 4435776, 'steps': 23102, 'loss/train': 1.5910356044769287}
+08/30/2021 17:20:36 - INFO - __main__ - Step 23104: {'lr': 0.0004753339078242247, 'samples': 4435968, 'steps': 23103, 'loss/train': 1.5396397113800049}
+08/30/2021 17:20:37 - INFO - __main__ - Step 23105: {'lr': 0.00047533160930933054, 'samples': 4436160, 'steps': 23104, 'loss/train': 1.3970762491226196}
+08/30/2021 17:20:38 - INFO - __main__ - Step 23106: {'lr': 0.00047532931069290546, 'samples': 4436352, 'steps': 23105, 'loss/train': 2.041872978210449}
+08/30/2021 17:20:38 - INFO - __main__ - Step 23107: {'lr': 0.00047532701197495043, 'samples': 4436544, 'steps': 23106, 'loss/train': 1.8742706775665283}
+08/30/2021 17:20:39 - INFO - __main__ - Step 23108: {'lr': 0.00047532471315546654, 'samples': 4436736, 'steps': 23107, 'loss/train': 1.6420570611953735}
+08/30/2021 17:20:39 - INFO - __main__ - Step 23109: {'lr': 0.00047532241423445487, 'samples': 4436928, 'steps': 23108, 'loss/train': 1.8693948984146118}
+08/30/2021 17:20:40 - INFO - __main__ - Step 23110: {'lr': 0.00047532011521191634, 'samples': 4437120, 'steps': 23109, 'loss/train': 2.1753315925598145}
+08/30/2021 17:20:41 - INFO - __main__ - Step 23111: {'lr': 0.00047531781608785203, 'samples': 4437312, 'steps': 23110, 'loss/train': 1.7467502355575562}
+08/30/2021 17:20:41 - INFO - __main__ - Step 23112: {'lr': 0.00047531551686226303, 'samples': 4437504, 'steps': 23111, 'loss/train': 1.3459922075271606}
+08/30/2021 17:20:42 - INFO - __main__ - Step 23113: {'lr': 0.00047531321753515026, 'samples': 4437696, 'steps': 23112, 'loss/train': 1.6046158075332642}
+08/30/2021 17:20:42 - INFO - __main__ - Step 23114: {'lr': 0.0004753109181065149, 'samples': 4437888, 'steps': 23113, 'loss/train': 1.420710563659668}
+08/30/2021 17:20:44 - INFO - __main__ - Step 23115: {'lr': 0.00047530861857635786, 'samples': 4438080, 'steps': 23114, 'loss/train': 2.168738603591919}
+08/30/2021 17:20:44 - INFO - __main__ - Step 23116: {'lr': 0.00047530631894468034, 'samples': 4438272, 'steps': 23115, 'loss/train': 0.11286278069019318}
+08/30/2021 17:20:44 - INFO - __main__ - Step 23117: {'lr': 0.0004753040192114831, 'samples': 4438464, 'steps': 23116, 'loss/train': 0.7792182564735413}
+08/30/2021 17:20:45 - INFO - __main__ - Step 23118: {'lr': 0.00047530171937676754, 'samples': 4438656, 'steps': 23117, 'loss/train': 1.52216374874115}
+08/30/2021 17:20:45 - INFO - __main__ - Step 23119: {'lr': 0.0004752994194405344, 'samples': 4438848, 'steps': 23118, 'loss/train': 1.2353326082229614}
+08/30/2021 17:20:46 - INFO - __main__ - Step 23120: {'lr': 0.0004752971194027848, 'samples': 4439040, 'steps': 23119, 'loss/train': 1.8364794254302979}
+08/30/2021 17:20:47 - INFO - __main__ - Step 23121: {'lr': 0.0004752948192635198, 'samples': 4439232, 'steps': 23120, 'loss/train': 1.6021615266799927}
+08/30/2021 17:20:47 - INFO - __main__ - Step 23122: {'lr': 0.0004752925190227405, 'samples': 4439424, 'steps': 23121, 'loss/train': 1.5915093421936035}
+08/30/2021 17:20:48 - INFO - __main__ - Step 23123: {'lr': 0.0004752902186804478, 'samples': 4439616, 'steps': 23122, 'loss/train': 1.4561430215835571}
+08/30/2021 17:20:48 - INFO - __main__ - Step 23124: {'lr': 0.0004752879182366429, 'samples': 4439808, 'steps': 23123, 'loss/train': 2.071640968322754}
+08/30/2021 17:20:50 - INFO - __main__ - Step 23125: {'lr': 0.0004752856176913266, 'samples': 4440000, 'steps': 23124, 'loss/train': 0.09368572384119034}
+08/30/2021 17:20:50 - INFO - __main__ - Step 23126: {'lr': 0.0004752833170445001, 'samples': 4440192, 'steps': 23125, 'loss/train': 1.8942292928695679}
+08/30/2021 17:20:51 - INFO - __main__ - Step 23127: {'lr': 0.0004752810162961645, 'samples': 4440384, 'steps': 23126, 'loss/train': 0.2813170254230499}
+08/30/2021 17:20:51 - INFO - __main__ - Step 23128: {'lr': 0.0004752787154463207, 'samples': 4440576, 'steps': 23127, 'loss/train': 1.6915593147277832}
+08/30/2021 17:20:51 - INFO - __main__ - Step 23129: {'lr': 0.0004752764144949698, 'samples': 4440768, 'steps': 23128, 'loss/train': 0.9356757402420044}
+08/30/2021 17:20:53 - INFO - __main__ - Step 23130: {'lr': 0.0004752741134421128, 'samples': 4440960, 'steps': 23129, 'loss/train': 1.650490164756775}
+08/30/2021 17:20:53 - INFO - __main__ - Step 23131: {'lr': 0.00047527181228775077, 'samples': 4441152, 'steps': 23130, 'loss/train': 1.3722552061080933}
+08/30/2021 17:20:54 - INFO - __main__ - Step 23132: {'lr': 0.0004752695110318848, 'samples': 4441344, 'steps': 23131, 'loss/train': 1.715676188468933}
+08/30/2021 17:20:54 - INFO - __main__ - Step 23133: {'lr': 0.00047526720967451573, 'samples': 4441536, 'steps': 23132, 'loss/train': 1.761802077293396}
+08/30/2021 17:20:54 - INFO - __main__ - Step 23134: {'lr': 0.0004752649082156448, 'samples': 4441728, 'steps': 23133, 'loss/train': 1.4513990879058838}
+08/30/2021 17:20:56 - INFO - __main__ - Step 23135: {'lr': 0.00047526260665527306, 'samples': 4441920, 'steps': 23134, 'loss/train': 1.4010471105575562}
+08/30/2021 17:20:56 - INFO - __main__ - Step 23136: {'lr': 0.0004752603049934014, 'samples': 4442112, 'steps': 23135, 'loss/train': 1.3411589860916138}
+08/30/2021 17:20:57 - INFO - __main__ - Step 23137: {'lr': 0.0004752580032300309, 'samples': 4442304, 'steps': 23136, 'loss/train': 1.944082498550415}
+08/30/2021 17:20:57 - INFO - __main__ - Step 23138: {'lr': 0.0004752557013651626, 'samples': 4442496, 'steps': 23137, 'loss/train': 1.626043677330017}
+08/30/2021 17:20:57 - INFO - __main__ - Step 23139: {'lr': 0.00047525339939879764, 'samples': 4442688, 'steps': 23138, 'loss/train': 1.9153451919555664}
+08/30/2021 17:20:58 - INFO - __main__ - Step 23140: {'lr': 0.0004752510973309369, 'samples': 4442880, 'steps': 23139, 'loss/train': 1.190613031387329}
+08/30/2021 17:20:59 - INFO - __main__ - Step 23141: {'lr': 0.00047524879516158155, 'samples': 4443072, 'steps': 23140, 'loss/train': 1.5332773923873901}
+08/30/2021 17:21:00 - INFO - __main__ - Step 23142: {'lr': 0.00047524649289073254, 'samples': 4443264, 'steps': 23141, 'loss/train': 1.2286112308502197}
+08/30/2021 17:21:00 - INFO - __main__ - Step 23143: {'lr': 0.00047524419051839093, 'samples': 4443456, 'steps': 23142, 'loss/train': 1.7234455347061157}
+08/30/2021 17:21:00 - INFO - __main__ - Step 23144: {'lr': 0.00047524188804455776, 'samples': 4443648, 'steps': 23143, 'loss/train': 0.9118403196334839}
+08/30/2021 17:21:01 - INFO - __main__ - Step 23145: {'lr': 0.0004752395854692341, 'samples': 4443840, 'steps': 23144, 'loss/train': 0.801737368106842}
+08/30/2021 17:21:02 - INFO - __main__ - Step 23146: {'lr': 0.0004752372827924209, 'samples': 4444032, 'steps': 23145, 'loss/train': 1.4815832376480103}
+08/30/2021 17:21:03 - INFO - __main__ - Step 23147: {'lr': 0.0004752349800141193, 'samples': 4444224, 'steps': 23146, 'loss/train': 0.1470886766910553}
+08/30/2021 17:21:03 - INFO - __main__ - Step 23148: {'lr': 0.0004752326771343303, 'samples': 4444416, 'steps': 23147, 'loss/train': 1.0431610345840454}
+08/30/2021 17:21:04 - INFO - __main__ - Step 23149: {'lr': 0.00047523037415305494, 'samples': 4444608, 'steps': 23148, 'loss/train': 1.5535979270935059}
+08/30/2021 17:21:04 - INFO - __main__ - Step 23150: {'lr': 0.0004752280710702942, 'samples': 4444800, 'steps': 23149, 'loss/train': 1.115715742111206}
+08/30/2021 17:21:04 - INFO - __main__ - Step 23151: {'lr': 0.0004752257678860492, 'samples': 4444992, 'steps': 23150, 'loss/train': 1.6098699569702148}
+08/30/2021 17:21:06 - INFO - __main__ - Step 23152: {'lr': 0.00047522346460032093, 'samples': 4445184, 'steps': 23151, 'loss/train': 1.8715747594833374}
+08/30/2021 17:21:07 - INFO - __main__ - Step 23153: {'lr': 0.0004752211612131104, 'samples': 4445376, 'steps': 23152, 'loss/train': 1.5347611904144287}
+08/30/2021 17:21:07 - INFO - __main__ - Step 23154: {'lr': 0.00047521885772441874, 'samples': 4445568, 'steps': 23153, 'loss/train': 0.14605779945850372}
+08/30/2021 17:21:07 - INFO - __main__ - Step 23155: {'lr': 0.00047521655413424705, 'samples': 4445760, 'steps': 23154, 'loss/train': 0.32538989186286926}
+08/30/2021 17:21:08 - INFO - __main__ - Step 23156: {'lr': 0.0004752142504425961, 'samples': 4445952, 'steps': 23155, 'loss/train': 1.354323387145996}
+08/30/2021 17:21:09 - INFO - __main__ - Step 23157: {'lr': 0.0004752119466494671, 'samples': 4446144, 'steps': 23156, 'loss/train': 1.461428165435791}
+08/30/2021 17:21:09 - INFO - __main__ - Step 23158: {'lr': 0.0004752096427548611, 'samples': 4446336, 'steps': 23157, 'loss/train': 1.5017316341400146}
+08/30/2021 17:21:10 - INFO - __main__ - Step 23159: {'lr': 0.00047520733875877906, 'samples': 4446528, 'steps': 23158, 'loss/train': 1.8959764242172241}
+08/30/2021 17:21:10 - INFO - __main__ - Step 23160: {'lr': 0.00047520503466122216, 'samples': 4446720, 'steps': 23159, 'loss/train': 1.2578843832015991}
+08/30/2021 17:21:11 - INFO - __main__ - Step 23161: {'lr': 0.0004752027304621913, 'samples': 4446912, 'steps': 23160, 'loss/train': 1.6839022636413574}
+08/30/2021 17:21:12 - INFO - __main__ - Step 23162: {'lr': 0.0004752004261616876, 'samples': 4447104, 'steps': 23161, 'loss/train': 1.5024852752685547}
+08/30/2021 17:21:12 - INFO - __main__ - Step 23163: {'lr': 0.000475198121759712, 'samples': 4447296, 'steps': 23162, 'loss/train': 1.121056079864502}
+08/30/2021 17:21:13 - INFO - __main__ - Step 23164: {'lr': 0.0004751958172562656, 'samples': 4447488, 'steps': 23163, 'loss/train': 1.6009811162948608}
+08/30/2021 17:21:13 - INFO - __main__ - Step 23165: {'lr': 0.00047519351265134954, 'samples': 4447680, 'steps': 23164, 'loss/train': 0.7221185564994812}
+08/30/2021 17:21:14 - INFO - __main__ - Step 23166: {'lr': 0.00047519120794496466, 'samples': 4447872, 'steps': 23165, 'loss/train': 1.5631213188171387}
+08/30/2021 17:21:15 - INFO - __main__ - Step 23167: {'lr': 0.00047518890313711217, 'samples': 4448064, 'steps': 23166, 'loss/train': 1.6122443675994873}
+08/30/2021 17:21:16 - INFO - __main__ - Step 23168: {'lr': 0.000475186598227793, 'samples': 4448256, 'steps': 23167, 'loss/train': 1.6459945440292358}
+08/30/2021 17:21:16 - INFO - __main__ - Step 23169: {'lr': 0.0004751842932170082, 'samples': 4448448, 'steps': 23168, 'loss/train': 2.0564258098602295}
+08/30/2021 17:21:16 - INFO - __main__ - Step 23170: {'lr': 0.00047518198810475885, 'samples': 4448640, 'steps': 23169, 'loss/train': 1.6809388399124146}
+08/30/2021 17:21:17 - INFO - __main__ - Step 23171: {'lr': 0.00047517968289104596, 'samples': 4448832, 'steps': 23170, 'loss/train': 1.9831767082214355}
+08/30/2021 17:21:17 - INFO - __main__ - Step 23172: {'lr': 0.0004751773775758706, 'samples': 4449024, 'steps': 23171, 'loss/train': 3.460151195526123}
+08/30/2021 17:21:19 - INFO - __main__ - Step 23173: {'lr': 0.00047517507215923376, 'samples': 4449216, 'steps': 23172, 'loss/train': 1.5345171689987183}
+08/30/2021 17:21:19 - INFO - __main__ - Step 23174: {'lr': 0.00047517276664113653, 'samples': 4449408, 'steps': 23173, 'loss/train': 1.496776819229126}
+08/30/2021 17:21:20 - INFO - __main__ - Step 23175: {'lr': 0.0004751704610215799, 'samples': 4449600, 'steps': 23174, 'loss/train': 2.006037950515747}
+08/30/2021 17:21:20 - INFO - __main__ - Step 23176: {'lr': 0.000475168155300565, 'samples': 4449792, 'steps': 23175, 'loss/train': 1.4301276206970215}
+08/30/2021 17:21:20 - INFO - __main__ - Step 23177: {'lr': 0.00047516584947809274, 'samples': 4449984, 'steps': 23176, 'loss/train': 1.7376550436019897}
+08/30/2021 17:21:22 - INFO - __main__ - Step 23178: {'lr': 0.00047516354355416426, 'samples': 4450176, 'steps': 23177, 'loss/train': 1.3079065084457397}
+08/30/2021 17:21:23 - INFO - __main__ - Step 23179: {'lr': 0.00047516123752878054, 'samples': 4450368, 'steps': 23178, 'loss/train': 2.0567970275878906}
+08/30/2021 17:21:23 - INFO - __main__ - Step 23180: {'lr': 0.00047515893140194265, 'samples': 4450560, 'steps': 23179, 'loss/train': 1.5286344289779663}
+08/30/2021 17:21:24 - INFO - __main__ - Step 23181: {'lr': 0.0004751566251736516, 'samples': 4450752, 'steps': 23180, 'loss/train': 1.5406385660171509}
+08/30/2021 17:21:24 - INFO - __main__ - Step 23182: {'lr': 0.00047515431884390845, 'samples': 4450944, 'steps': 23181, 'loss/train': 0.1824532300233841}
+08/30/2021 17:21:24 - INFO - __main__ - Step 23183: {'lr': 0.00047515201241271426, 'samples': 4451136, 'steps': 23182, 'loss/train': 1.3524411916732788}
+08/30/2021 17:21:26 - INFO - __main__ - Step 23184: {'lr': 0.00047514970588007007, 'samples': 4451328, 'steps': 23183, 'loss/train': 1.7183396816253662}
+08/30/2021 17:21:26 - INFO - __main__ - Step 23185: {'lr': 0.0004751473992459768, 'samples': 4451520, 'steps': 23184, 'loss/train': 1.3646972179412842}
+08/30/2021 17:21:27 - INFO - __main__ - Step 23186: {'lr': 0.0004751450925104357, 'samples': 4451712, 'steps': 23185, 'loss/train': 2.6572694778442383}
+08/30/2021 17:21:27 - INFO - __main__ - Step 23187: {'lr': 0.00047514278567344765, 'samples': 4451904, 'steps': 23186, 'loss/train': 1.613290786743164}
+08/30/2021 17:21:27 - INFO - __main__ - Step 23188: {'lr': 0.00047514047873501374, 'samples': 4452096, 'steps': 23187, 'loss/train': 1.8051426410675049}
+08/30/2021 17:21:29 - INFO - __main__ - Step 23189: {'lr': 0.000475138171695135, 'samples': 4452288, 'steps': 23188, 'loss/train': 1.572274088859558}
+08/30/2021 17:21:29 - INFO - __main__ - Step 23190: {'lr': 0.00047513586455381245, 'samples': 4452480, 'steps': 23189, 'loss/train': 1.9939802885055542}
+08/30/2021 17:21:30 - INFO - __main__ - Step 23191: {'lr': 0.00047513355731104717, 'samples': 4452672, 'steps': 23190, 'loss/train': 1.7568353414535522}
+08/30/2021 17:21:30 - INFO - __main__ - Step 23192: {'lr': 0.0004751312499668402, 'samples': 4452864, 'steps': 23191, 'loss/train': 1.5489119291305542}
+08/30/2021 17:21:30 - INFO - __main__ - Step 23193: {'lr': 0.00047512894252119256, 'samples': 4453056, 'steps': 23192, 'loss/train': 1.2617095708847046}
+08/30/2021 17:21:32 - INFO - __main__ - Step 23194: {'lr': 0.0004751266349741053, 'samples': 4453248, 'steps': 23193, 'loss/train': 1.708428144454956}
+08/30/2021 17:21:32 - INFO - __main__ - Step 23195: {'lr': 0.0004751243273255794, 'samples': 4453440, 'steps': 23194, 'loss/train': 0.8694499731063843}
+08/30/2021 17:21:33 - INFO - __main__ - Step 23196: {'lr': 0.000475122019575616, 'samples': 4453632, 'steps': 23195, 'loss/train': 2.340193510055542}
+08/30/2021 17:21:33 - INFO - __main__ - Step 23197: {'lr': 0.0004751197117242161, 'samples': 4453824, 'steps': 23196, 'loss/train': 1.6779906749725342}
+08/30/2021 17:21:33 - INFO - __main__ - Step 23198: {'lr': 0.0004751174037713807, 'samples': 4454016, 'steps': 23197, 'loss/train': 1.6135693788528442}
+08/30/2021 17:21:35 - INFO - __main__ - Step 23199: {'lr': 0.00047511509571711085, 'samples': 4454208, 'steps': 23198, 'loss/train': 1.5950708389282227}
+08/30/2021 17:21:36 - INFO - __main__ - Step 23200: {'lr': 0.00047511278756140766, 'samples': 4454400, 'steps': 23199, 'loss/train': 1.4282525777816772}
+08/30/2021 17:21:36 - INFO - __main__ - Step 23201: {'lr': 0.00047511047930427216, 'samples': 4454592, 'steps': 23200, 'loss/train': 1.557000994682312}
+08/30/2021 17:21:36 - INFO - __main__ - Step 23202: {'lr': 0.00047510817094570526, 'samples': 4454784, 'steps': 23201, 'loss/train': 1.6131747961044312}
+08/30/2021 17:21:37 - INFO - __main__ - Step 23203: {'lr': 0.00047510586248570815, 'samples': 4454976, 'steps': 23202, 'loss/train': 0.7795226573944092}
+08/30/2021 17:21:38 - INFO - __main__ - Step 23204: {'lr': 0.00047510355392428176, 'samples': 4455168, 'steps': 23203, 'loss/train': 1.7070263624191284}
+08/30/2021 17:21:39 - INFO - __main__ - Step 23205: {'lr': 0.00047510124526142723, 'samples': 4455360, 'steps': 23204, 'loss/train': 1.9022858142852783}
+08/30/2021 17:21:39 - INFO - __main__ - Step 23206: {'lr': 0.00047509893649714554, 'samples': 4455552, 'steps': 23205, 'loss/train': 1.6807376146316528}
+08/30/2021 17:21:39 - INFO - __main__ - Step 23207: {'lr': 0.00047509662763143775, 'samples': 4455744, 'steps': 23206, 'loss/train': 1.791644811630249}
+08/30/2021 17:21:40 - INFO - __main__ - Step 23208: {'lr': 0.00047509431866430487, 'samples': 4455936, 'steps': 23207, 'loss/train': 1.6276882886886597}
+08/30/2021 17:21:40 - INFO - __main__ - Step 23209: {'lr': 0.000475092009595748, 'samples': 4456128, 'steps': 23208, 'loss/train': 1.7554091215133667}
+08/30/2021 17:21:41 - INFO - __main__ - Step 23210: {'lr': 0.0004750897004257681, 'samples': 4456320, 'steps': 23209, 'loss/train': 1.5933202505111694}
+08/30/2021 17:21:42 - INFO - __main__ - Step 23211: {'lr': 0.0004750873911543663, 'samples': 4456512, 'steps': 23210, 'loss/train': 1.8493651151657104}
+08/30/2021 17:21:42 - INFO - __main__ - Step 23212: {'lr': 0.00047508508178154354, 'samples': 4456704, 'steps': 23211, 'loss/train': 1.3049308061599731}
+08/30/2021 17:21:43 - INFO - __main__ - Step 23213: {'lr': 0.00047508277230730095, 'samples': 4456896, 'steps': 23212, 'loss/train': 1.920776605606079}
+08/30/2021 17:21:43 - INFO - __main__ - Step 23214: {'lr': 0.00047508046273163953, 'samples': 4457088, 'steps': 23213, 'loss/train': 1.2272385358810425}
+08/30/2021 17:21:44 - INFO - __main__ - Step 23215: {'lr': 0.0004750781530545603, 'samples': 4457280, 'steps': 23214, 'loss/train': 1.6449463367462158}
+08/30/2021 17:21:45 - INFO - __main__ - Step 23216: {'lr': 0.0004750758432760644, 'samples': 4457472, 'steps': 23215, 'loss/train': 1.731659173965454}
+08/30/2021 17:21:45 - INFO - __main__ - Step 23217: {'lr': 0.0004750735333961527, 'samples': 4457664, 'steps': 23216, 'loss/train': 1.3513771295547485}
+08/30/2021 17:21:45 - INFO - __main__ - Step 23218: {'lr': 0.00047507122341482644, 'samples': 4457856, 'steps': 23217, 'loss/train': 1.6106244325637817}
+08/30/2021 17:21:46 - INFO - __main__ - Step 23219: {'lr': 0.00047506891333208654, 'samples': 4458048, 'steps': 23218, 'loss/train': 1.494199275970459}
+08/30/2021 17:21:47 - INFO - __main__ - Step 23220: {'lr': 0.000475066603147934, 'samples': 4458240, 'steps': 23219, 'loss/train': 1.7515572309494019}
+08/30/2021 17:21:48 - INFO - __main__ - Step 23221: {'lr': 0.00047506429286236997, 'samples': 4458432, 'steps': 23220, 'loss/train': 1.638920545578003}
+08/30/2021 17:21:48 - INFO - __main__ - Step 23222: {'lr': 0.00047506198247539546, 'samples': 4458624, 'steps': 23221, 'loss/train': 1.7657824754714966}
+08/30/2021 17:21:48 - INFO - __main__ - Step 23223: {'lr': 0.0004750596719870114, 'samples': 4458816, 'steps': 23222, 'loss/train': 1.6600230932235718}
+08/30/2021 17:21:49 - INFO - __main__ - Step 23224: {'lr': 0.000475057361397219, 'samples': 4459008, 'steps': 23223, 'loss/train': 1.6566829681396484}
+08/30/2021 17:21:50 - INFO - __main__ - Step 23225: {'lr': 0.0004750550507060192, 'samples': 4459200, 'steps': 23224, 'loss/train': 1.5358529090881348}
+08/30/2021 17:21:51 - INFO - __main__ - Step 23226: {'lr': 0.0004750527399134131, 'samples': 4459392, 'steps': 23225, 'loss/train': 1.396316647529602}
+08/30/2021 17:21:51 - INFO - __main__ - Step 23227: {'lr': 0.00047505042901940163, 'samples': 4459584, 'steps': 23226, 'loss/train': 1.651220679283142}
+08/30/2021 17:21:51 - INFO - __main__ - Step 23228: {'lr': 0.00047504811802398603, 'samples': 4459776, 'steps': 23227, 'loss/train': 1.394845962524414}
+08/30/2021 17:21:52 - INFO - __main__ - Step 23229: {'lr': 0.0004750458069271671, 'samples': 4459968, 'steps': 23228, 'loss/train': 0.3783375918865204}
+08/30/2021 17:21:54 - INFO - __main__ - Step 23230: {'lr': 0.0004750434957289461, 'samples': 4460160, 'steps': 23229, 'loss/train': 1.5883769989013672}
+08/30/2021 17:21:54 - INFO - __main__ - Step 23231: {'lr': 0.0004750411844293239, 'samples': 4460352, 'steps': 23230, 'loss/train': 1.9355220794677734}
+08/30/2021 17:21:54 - INFO - __main__ - Step 23232: {'lr': 0.0004750388730283016, 'samples': 4460544, 'steps': 23231, 'loss/train': 1.310945749282837}
+08/30/2021 17:21:55 - INFO - __main__ - Step 23233: {'lr': 0.0004750365615258804, 'samples': 4460736, 'steps': 23232, 'loss/train': 1.852506160736084}
+08/30/2021 17:21:55 - INFO - __main__ - Step 23234: {'lr': 0.00047503424992206107, 'samples': 4460928, 'steps': 23233, 'loss/train': 1.3770300149917603}
+08/30/2021 17:21:57 - INFO - __main__ - Step 23235: {'lr': 0.00047503193821684476, 'samples': 4461120, 'steps': 23234, 'loss/train': 1.3650484085083008}
+08/30/2021 17:21:57 - INFO - __main__ - Step 23236: {'lr': 0.0004750296264102326, 'samples': 4461312, 'steps': 23235, 'loss/train': 1.575400710105896}
+08/30/2021 17:21:57 - INFO - __main__ - Step 23237: {'lr': 0.0004750273145022256, 'samples': 4461504, 'steps': 23236, 'loss/train': 1.0140916109085083}
+08/30/2021 17:21:58 - INFO - __main__ - Step 23238: {'lr': 0.00047502500249282464, 'samples': 4461696, 'steps': 23237, 'loss/train': 2.0177133083343506}
+08/30/2021 17:21:58 - INFO - __main__ - Step 23239: {'lr': 0.000475022690382031, 'samples': 4461888, 'steps': 23238, 'loss/train': 1.9535596370697021}
+08/30/2021 17:22:00 - INFO - __main__ - Step 23240: {'lr': 0.0004750203781698456, 'samples': 4462080, 'steps': 23239, 'loss/train': 1.9856034517288208}
+08/30/2021 17:22:00 - INFO - __main__ - Step 23241: {'lr': 0.0004750180658562694, 'samples': 4462272, 'steps': 23240, 'loss/train': 0.20193614065647125}
+08/30/2021 17:22:00 - INFO - __main__ - Step 23242: {'lr': 0.00047501575344130356, 'samples': 4462464, 'steps': 23241, 'loss/train': 1.469152808189392}
+08/30/2021 17:22:01 - INFO - __main__ - Step 23243: {'lr': 0.00047501344092494915, 'samples': 4462656, 'steps': 23242, 'loss/train': 1.6817524433135986}
+08/30/2021 17:22:01 - INFO - __main__ - Step 23244: {'lr': 0.0004750111283072071, 'samples': 4462848, 'steps': 23243, 'loss/train': 1.05733323097229}
+08/30/2021 17:22:03 - INFO - __main__ - Step 23245: {'lr': 0.00047500881558807854, 'samples': 4463040, 'steps': 23244, 'loss/train': 1.526496410369873}
+08/30/2021 17:22:04 - INFO - __main__ - Step 23246: {'lr': 0.00047500650276756455, 'samples': 4463232, 'steps': 23245, 'loss/train': 1.9825046062469482}
+08/30/2021 17:22:04 - INFO - __main__ - Step 23247: {'lr': 0.00047500418984566594, 'samples': 4463424, 'steps': 23246, 'loss/train': 2.217878818511963}
+08/30/2021 17:22:04 - INFO - __main__ - Step 23248: {'lr': 0.000475001876822384, 'samples': 4463616, 'steps': 23247, 'loss/train': 1.6152948141098022}
+08/30/2021 17:22:05 - INFO - __main__ - Step 23249: {'lr': 0.00047499956369771967, 'samples': 4463808, 'steps': 23248, 'loss/train': 0.9902798533439636}
+08/30/2021 17:22:05 - INFO - __main__ - Step 23250: {'lr': 0.00047499725047167406, 'samples': 4464000, 'steps': 23249, 'loss/train': 1.7276273965835571}
+08/30/2021 17:22:05 - INFO - __main__ - Step 23251: {'lr': 0.0004749949371442481, 'samples': 4464192, 'steps': 23250, 'loss/train': 1.323229193687439}
+08/30/2021 17:22:07 - INFO - __main__ - Step 23252: {'lr': 0.00047499262371544294, 'samples': 4464384, 'steps': 23251, 'loss/train': 2.0143301486968994}
+08/30/2021 17:22:07 - INFO - __main__ - Step 23253: {'lr': 0.00047499031018525953, 'samples': 4464576, 'steps': 23252, 'loss/train': 1.3034156560897827}
+08/30/2021 17:22:08 - INFO - __main__ - Step 23254: {'lr': 0.00047498799655369895, 'samples': 4464768, 'steps': 23253, 'loss/train': 1.3375436067581177}
+08/30/2021 17:22:08 - INFO - __main__ - Step 23255: {'lr': 0.0004749856828207623, 'samples': 4464960, 'steps': 23254, 'loss/train': 2.0281713008880615}
+08/30/2021 17:22:08 - INFO - __main__ - Step 23256: {'lr': 0.00047498336898645055, 'samples': 4465152, 'steps': 23255, 'loss/train': 1.6792418956756592}
+08/30/2021 17:22:10 - INFO - __main__ - Step 23257: {'lr': 0.00047498105505076475, 'samples': 4465344, 'steps': 23256, 'loss/train': 0.7893033027648926}
+08/30/2021 17:22:10 - INFO - __main__ - Step 23258: {'lr': 0.000474978741013706, 'samples': 4465536, 'steps': 23257, 'loss/train': 1.6571929454803467}
+08/30/2021 17:22:11 - INFO - __main__ - Step 23259: {'lr': 0.0004749764268752753, 'samples': 4465728, 'steps': 23258, 'loss/train': 1.4134469032287598}
+08/30/2021 17:22:11 - INFO - __main__ - Step 23260: {'lr': 0.0004749741126354736, 'samples': 4465920, 'steps': 23259, 'loss/train': 1.9693456888198853}
+08/30/2021 17:22:11 - INFO - __main__ - Step 23261: {'lr': 0.00047497179829430217, 'samples': 4466112, 'steps': 23260, 'loss/train': 1.663743495941162}
+08/30/2021 17:22:13 - INFO - __main__ - Step 23262: {'lr': 0.0004749694838517619, 'samples': 4466304, 'steps': 23261, 'loss/train': 1.4114000797271729}
+08/30/2021 17:22:14 - INFO - __main__ - Step 23263: {'lr': 0.0004749671693078538, 'samples': 4466496, 'steps': 23262, 'loss/train': 1.3881969451904297}
+08/30/2021 17:22:14 - INFO - __main__ - Step 23264: {'lr': 0.00047496485466257896, 'samples': 4466688, 'steps': 23263, 'loss/train': 0.1113017275929451}
+08/30/2021 17:22:14 - INFO - __main__ - Step 23265: {'lr': 0.0004749625399159384, 'samples': 4466880, 'steps': 23264, 'loss/train': 1.3417302370071411}
+08/30/2021 17:22:15 - INFO - __main__ - Step 23266: {'lr': 0.0004749602250679332, 'samples': 4467072, 'steps': 23265, 'loss/train': 0.23997275531291962}
+08/30/2021 17:22:16 - INFO - __main__ - Step 23267: {'lr': 0.00047495791011856447, 'samples': 4467264, 'steps': 23266, 'loss/train': 0.29367148876190186}
+08/30/2021 17:22:17 - INFO - __main__ - Step 23268: {'lr': 0.00047495559506783317, 'samples': 4467456, 'steps': 23267, 'loss/train': 1.3928866386413574}
+08/30/2021 17:22:17 - INFO - __main__ - Step 23269: {'lr': 0.00047495327991574034, 'samples': 4467648, 'steps': 23268, 'loss/train': 1.7561638355255127}
+08/30/2021 17:22:17 - INFO - __main__ - Step 23270: {'lr': 0.0004749509646622869, 'samples': 4467840, 'steps': 23269, 'loss/train': 1.2333191633224487}
+08/30/2021 17:22:18 - INFO - __main__ - Step 23271: {'lr': 0.00047494864930747415, 'samples': 4468032, 'steps': 23270, 'loss/train': 1.8547008037567139}
+08/30/2021 17:22:19 - INFO - __main__ - Step 23272: {'lr': 0.000474946333851303, 'samples': 4468224, 'steps': 23271, 'loss/train': 0.4618629515171051}
+08/30/2021 17:22:20 - INFO - __main__ - Step 23273: {'lr': 0.0004749440182937745, 'samples': 4468416, 'steps': 23272, 'loss/train': 1.3728739023208618}
+08/30/2021 17:22:20 - INFO - __main__ - Step 23274: {'lr': 0.0004749417026348897, 'samples': 4468608, 'steps': 23273, 'loss/train': 2.0360350608825684}
+08/30/2021 17:22:20 - INFO - __main__ - Step 23275: {'lr': 0.0004749393868746497, 'samples': 4468800, 'steps': 23274, 'loss/train': 1.6930845975875854}
+08/30/2021 17:22:21 - INFO - __main__ - Step 23276: {'lr': 0.0004749370710130554, 'samples': 4468992, 'steps': 23275, 'loss/train': 0.9200928211212158}
+08/30/2021 17:22:22 - INFO - __main__ - Step 23277: {'lr': 0.00047493475505010793, 'samples': 4469184, 'steps': 23276, 'loss/train': 1.4903265237808228}
+08/30/2021 17:22:23 - INFO - __main__ - Step 23278: {'lr': 0.0004749324389858083, 'samples': 4469376, 'steps': 23277, 'loss/train': 1.6839574575424194}
+08/30/2021 17:22:23 - INFO - __main__ - Step 23279: {'lr': 0.00047493012282015767, 'samples': 4469568, 'steps': 23278, 'loss/train': 1.6174678802490234}
+08/30/2021 17:22:23 - INFO - __main__ - Step 23280: {'lr': 0.00047492780655315693, 'samples': 4469760, 'steps': 23279, 'loss/train': 1.8059922456741333}
+08/30/2021 17:22:24 - INFO - __main__ - Step 23281: {'lr': 0.00047492549018480725, 'samples': 4469952, 'steps': 23280, 'loss/train': 1.4149961471557617}
+08/30/2021 17:22:25 - INFO - __main__ - Step 23282: {'lr': 0.00047492317371510955, 'samples': 4470144, 'steps': 23281, 'loss/train': 0.8420997858047485}
+08/30/2021 17:22:26 - INFO - __main__ - Step 23283: {'lr': 0.00047492085714406497, 'samples': 4470336, 'steps': 23282, 'loss/train': 1.0607054233551025}
+08/30/2021 17:22:26 - INFO - __main__ - Step 23284: {'lr': 0.00047491854047167453, 'samples': 4470528, 'steps': 23283, 'loss/train': 1.798923373222351}
+08/30/2021 17:22:27 - INFO - __main__ - Step 23285: {'lr': 0.0004749162236979393, 'samples': 4470720, 'steps': 23284, 'loss/train': 1.8167866468429565}
+08/30/2021 17:22:27 - INFO - __main__ - Step 23286: {'lr': 0.0004749139068228602, 'samples': 4470912, 'steps': 23285, 'loss/train': 1.3599193096160889}
+08/30/2021 17:22:27 - INFO - __main__ - Step 23287: {'lr': 0.00047491158984643846, 'samples': 4471104, 'steps': 23286, 'loss/train': 2.153561592102051}
+08/30/2021 17:22:30 - INFO - __main__ - Step 23288: {'lr': 0.0004749092727686749, 'samples': 4471296, 'steps': 23287, 'loss/train': 1.4420368671417236}
+08/30/2021 17:22:30 - INFO - __main__ - Step 23289: {'lr': 0.00047490695558957083, 'samples': 4471488, 'steps': 23288, 'loss/train': 1.1183713674545288}
+08/30/2021 17:22:31 - INFO - __main__ - Step 23290: {'lr': 0.00047490463830912713, 'samples': 4471680, 'steps': 23289, 'loss/train': 2.230461359024048}
+08/30/2021 17:22:31 - INFO - __main__ - Step 23291: {'lr': 0.0004749023209273448, 'samples': 4471872, 'steps': 23290, 'loss/train': 2.1331839561462402}
+08/30/2021 17:22:31 - INFO - __main__ - Step 23292: {'lr': 0.000474900003444225, 'samples': 4472064, 'steps': 23291, 'loss/train': 1.9077094793319702}
+08/30/2021 17:22:33 - INFO - __main__ - Step 23293: {'lr': 0.0004748976858597687, 'samples': 4472256, 'steps': 23292, 'loss/train': 1.3912080526351929}
+08/30/2021 17:22:33 - INFO - __main__ - Step 23294: {'lr': 0.00047489536817397706, 'samples': 4472448, 'steps': 23293, 'loss/train': 1.8662384748458862}
+08/30/2021 17:22:34 - INFO - __main__ - Step 23295: {'lr': 0.00047489305038685094, 'samples': 4472640, 'steps': 23294, 'loss/train': 1.615684986114502}
+08/30/2021 17:22:34 - INFO - __main__ - Step 23296: {'lr': 0.00047489073249839153, 'samples': 4472832, 'steps': 23295, 'loss/train': 1.5429795980453491}
+08/30/2021 17:22:34 - INFO - __main__ - Step 23297: {'lr': 0.0004748884145085998, 'samples': 4473024, 'steps': 23296, 'loss/train': 1.2033603191375732}
+08/30/2021 17:22:35 - INFO - __main__ - Step 23298: {'lr': 0.0004748860964174768, 'samples': 4473216, 'steps': 23297, 'loss/train': 1.162532925605774}
+08/30/2021 17:22:36 - INFO - __main__ - Step 23299: {'lr': 0.00047488377822502365, 'samples': 4473408, 'steps': 23298, 'loss/train': 1.6472742557525635}
+08/30/2021 17:22:37 - INFO - __main__ - Step 23300: {'lr': 0.00047488145993124134, 'samples': 4473600, 'steps': 23299, 'loss/train': 1.606379747390747}
+08/30/2021 17:22:37 - INFO - __main__ - Step 23301: {'lr': 0.0004748791415361309, 'samples': 4473792, 'steps': 23300, 'loss/train': 1.5527448654174805}
+08/30/2021 17:22:37 - INFO - __main__ - Step 23302: {'lr': 0.00047487682303969336, 'samples': 4473984, 'steps': 23301, 'loss/train': 1.3916690349578857}
+08/30/2021 17:22:38 - INFO - __main__ - Step 23303: {'lr': 0.0004748745044419298, 'samples': 4474176, 'steps': 23302, 'loss/train': 0.8504519462585449}
+08/30/2021 17:22:39 - INFO - __main__ - Step 23304: {'lr': 0.0004748721857428413, 'samples': 4474368, 'steps': 23303, 'loss/train': 2.007427215576172}
+08/30/2021 17:22:40 - INFO - __main__ - Step 23305: {'lr': 0.00047486986694242887, 'samples': 4474560, 'steps': 23304, 'loss/train': 2.2359650135040283}
+08/30/2021 17:22:40 - INFO - __main__ - Step 23306: {'lr': 0.0004748675480406934, 'samples': 4474752, 'steps': 23305, 'loss/train': 1.6426920890808105}
+08/30/2021 17:22:40 - INFO - __main__ - Step 23307: {'lr': 0.0004748652290376363, 'samples': 4474944, 'steps': 23306, 'loss/train': 1.280753493309021}
+08/30/2021 17:22:41 - INFO - __main__ - Step 23308: {'lr': 0.00047486290993325824, 'samples': 4475136, 'steps': 23307, 'loss/train': 1.0288336277008057}
+08/30/2021 17:22:41 - INFO - __main__ - Step 23309: {'lr': 0.00047486059072756047, 'samples': 4475328, 'steps': 23308, 'loss/train': 1.8509293794631958}
+08/30/2021 17:22:43 - INFO - __main__ - Step 23310: {'lr': 0.00047485827142054407, 'samples': 4475520, 'steps': 23309, 'loss/train': 1.7704225778579712}
+08/30/2021 17:22:43 - INFO - __main__ - Step 23311: {'lr': 0.0004748559520122099, 'samples': 4475712, 'steps': 23310, 'loss/train': 1.6992249488830566}
+08/30/2021 17:22:44 - INFO - __main__ - Step 23312: {'lr': 0.0004748536325025591, 'samples': 4475904, 'steps': 23311, 'loss/train': 1.788007378578186}
+08/30/2021 17:22:44 - INFO - __main__ - Step 23313: {'lr': 0.0004748513128915928, 'samples': 4476096, 'steps': 23312, 'loss/train': 1.953972339630127}
+08/30/2021 17:22:44 - INFO - __main__ - Step 23314: {'lr': 0.0004748489931793119, 'samples': 4476288, 'steps': 23313, 'loss/train': 1.7730237245559692}
+08/30/2021 17:22:46 - INFO - __main__ - Step 23315: {'lr': 0.00047484667336571753, 'samples': 4476480, 'steps': 23314, 'loss/train': 1.0370426177978516}
+08/30/2021 17:22:46 - INFO - __main__ - Step 23316: {'lr': 0.0004748443534508107, 'samples': 4476672, 'steps': 23315, 'loss/train': 2.3911044597625732}
+08/30/2021 17:22:46 - INFO - __main__ - Step 23317: {'lr': 0.00047484203343459256, 'samples': 4476864, 'steps': 23316, 'loss/train': 1.7602030038833618}
+08/30/2021 17:22:47 - INFO - __main__ - Step 23318: {'lr': 0.000474839713317064, 'samples': 4477056, 'steps': 23317, 'loss/train': 1.7041176557540894}
+08/30/2021 17:22:47 - INFO - __main__ - Step 23319: {'lr': 0.00047483739309822615, 'samples': 4477248, 'steps': 23318, 'loss/train': 1.4947415590286255}
+08/30/2021 17:22:49 - INFO - __main__ - Step 23320: {'lr': 0.00047483507277808, 'samples': 4477440, 'steps': 23319, 'loss/train': 1.7281042337417603}
+08/30/2021 17:22:49 - INFO - __main__ - Step 23321: {'lr': 0.0004748327523566267, 'samples': 4477632, 'steps': 23320, 'loss/train': 1.1908296346664429}
+08/30/2021 17:22:49 - INFO - __main__ - Step 23322: {'lr': 0.0004748304318338672, 'samples': 4477824, 'steps': 23321, 'loss/train': 0.6295861005783081}
+08/30/2021 17:22:50 - INFO - __main__ - Step 23323: {'lr': 0.00047482811120980254, 'samples': 4478016, 'steps': 23322, 'loss/train': 1.4904004335403442}
+08/30/2021 17:22:50 - INFO - __main__ - Step 23324: {'lr': 0.0004748257904844339, 'samples': 4478208, 'steps': 23323, 'loss/train': 0.9871253967285156}
+08/30/2021 17:22:52 - INFO - __main__ - Step 23325: {'lr': 0.00047482346965776215, 'samples': 4478400, 'steps': 23324, 'loss/train': 1.551640510559082}
+08/30/2021 17:22:52 - INFO - __main__ - Step 23326: {'lr': 0.0004748211487297884, 'samples': 4478592, 'steps': 23325, 'loss/train': 1.6661995649337769}
+08/30/2021 17:22:52 - INFO - __main__ - Step 23327: {'lr': 0.00047481882770051377, 'samples': 4478784, 'steps': 23326, 'loss/train': 1.2789151668548584}
+08/30/2021 17:22:53 - INFO - __main__ - Step 23328: {'lr': 0.00047481650656993924, 'samples': 4478976, 'steps': 23327, 'loss/train': 1.8919947147369385}
+08/30/2021 17:22:53 - INFO - __main__ - Step 23329: {'lr': 0.00047481418533806586, 'samples': 4479168, 'steps': 23328, 'loss/train': 1.881327748298645}
+08/30/2021 17:22:55 - INFO - __main__ - Step 23330: {'lr': 0.0004748118640048946, 'samples': 4479360, 'steps': 23329, 'loss/train': 1.0059058666229248}
+08/30/2021 17:22:55 - INFO - __main__ - Step 23331: {'lr': 0.00047480954257042666, 'samples': 4479552, 'steps': 23330, 'loss/train': 1.5549612045288086}
+08/30/2021 17:22:55 - INFO - __main__ - Step 23332: {'lr': 0.000474807221034663, 'samples': 4479744, 'steps': 23331, 'loss/train': 1.6566517353057861}
+08/30/2021 17:22:56 - INFO - __main__ - Step 23333: {'lr': 0.0004748048993976046, 'samples': 4479936, 'steps': 23332, 'loss/train': 1.3243255615234375}
+08/30/2021 17:22:56 - INFO - __main__ - Step 23334: {'lr': 0.0004748025776592527, 'samples': 4480128, 'steps': 23333, 'loss/train': 1.6638424396514893}
+08/30/2021 17:22:58 - INFO - __main__ - Step 23335: {'lr': 0.00047480025581960817, 'samples': 4480320, 'steps': 23334, 'loss/train': 1.2825798988342285}
+08/30/2021 17:22:58 - INFO - __main__ - Step 23336: {'lr': 0.0004747979338786721, 'samples': 4480512, 'steps': 23335, 'loss/train': 1.877795934677124}
+08/30/2021 17:22:58 - INFO - __main__ - Step 23337: {'lr': 0.00047479561183644557, 'samples': 4480704, 'steps': 23336, 'loss/train': 1.6736769676208496}
+08/30/2021 17:22:59 - INFO - __main__ - Step 23338: {'lr': 0.00047479328969292963, 'samples': 4480896, 'steps': 23337, 'loss/train': 1.8154802322387695}
+08/30/2021 17:22:59 - INFO - __main__ - Step 23339: {'lr': 0.0004747909674481253, 'samples': 4481088, 'steps': 23338, 'loss/train': 1.9429608583450317}
+08/30/2021 17:23:01 - INFO - __main__ - Step 23340: {'lr': 0.00047478864510203355, 'samples': 4481280, 'steps': 23339, 'loss/train': 1.302916169166565}
+08/30/2021 17:23:01 - INFO - __main__ - Step 23341: {'lr': 0.0004747863226546556, 'samples': 4481472, 'steps': 23340, 'loss/train': 1.8804534673690796}
+08/30/2021 17:23:02 - INFO - __main__ - Step 23342: {'lr': 0.0004747840001059923, 'samples': 4481664, 'steps': 23341, 'loss/train': 1.4982608556747437}
+08/30/2021 17:23:02 - INFO - __main__ - Step 23343: {'lr': 0.00047478167745604495, 'samples': 4481856, 'steps': 23342, 'loss/train': 0.9054900407791138}
+08/30/2021 17:23:02 - INFO - __main__ - Step 23344: {'lr': 0.00047477935470481434, 'samples': 4482048, 'steps': 23343, 'loss/train': 1.4744951725006104}
+08/30/2021 17:23:04 - INFO - __main__ - Step 23345: {'lr': 0.00047477703185230157, 'samples': 4482240, 'steps': 23344, 'loss/train': 1.1306208372116089}
+08/30/2021 17:23:04 - INFO - __main__ - Step 23346: {'lr': 0.00047477470889850784, 'samples': 4482432, 'steps': 23345, 'loss/train': 1.7451003789901733}
+08/30/2021 17:23:05 - INFO - __main__ - Step 23347: {'lr': 0.00047477238584343407, 'samples': 4482624, 'steps': 23346, 'loss/train': 1.4920345544815063}
+08/30/2021 17:23:05 - INFO - __main__ - Step 23348: {'lr': 0.00047477006268708134, 'samples': 4482816, 'steps': 23347, 'loss/train': 1.6318023204803467}
+08/30/2021 17:23:05 - INFO - __main__ - Step 23349: {'lr': 0.00047476773942945063, 'samples': 4483008, 'steps': 23348, 'loss/train': 1.410489559173584}
+08/30/2021 17:23:06 - INFO - __main__ - Step 23350: {'lr': 0.00047476541607054313, 'samples': 4483200, 'steps': 23349, 'loss/train': 1.4952244758605957}
+08/30/2021 17:23:07 - INFO - __main__ - Step 23351: {'lr': 0.0004747630926103597, 'samples': 4483392, 'steps': 23350, 'loss/train': 1.6330492496490479}
+08/30/2021 17:23:08 - INFO - __main__ - Step 23352: {'lr': 0.0004747607690489015, 'samples': 4483584, 'steps': 23351, 'loss/train': 1.2275327444076538}
+08/30/2021 17:23:08 - INFO - __main__ - Step 23353: {'lr': 0.00047475844538616966, 'samples': 4483776, 'steps': 23352, 'loss/train': 1.9747304916381836}
+08/30/2021 17:23:08 - INFO - __main__ - Step 23354: {'lr': 0.0004747561216221651, 'samples': 4483968, 'steps': 23353, 'loss/train': 1.918383240699768}
+08/30/2021 17:23:09 - INFO - __main__ - Step 23355: {'lr': 0.0004747537977568889, 'samples': 4484160, 'steps': 23354, 'loss/train': 0.5475494265556335}
+08/30/2021 17:23:11 - INFO - __main__ - Step 23356: {'lr': 0.00047475147379034206, 'samples': 4484352, 'steps': 23355, 'loss/train': 1.4513154029846191}
+08/30/2021 17:23:11 - INFO - __main__ - Step 23357: {'lr': 0.0004747491497225257, 'samples': 4484544, 'steps': 23356, 'loss/train': 1.5879918336868286}
+08/30/2021 17:23:12 - INFO - __main__ - Step 23358: {'lr': 0.00047474682555344083, 'samples': 4484736, 'steps': 23357, 'loss/train': 1.2888751029968262}
+08/30/2021 17:23:12 - INFO - __main__ - Step 23359: {'lr': 0.00047474450128308853, 'samples': 4484928, 'steps': 23358, 'loss/train': 1.9676098823547363}
+08/30/2021 17:23:13 - INFO - __main__ - Step 23360: {'lr': 0.0004747421769114698, 'samples': 4485120, 'steps': 23359, 'loss/train': 2.159215211868286}
+08/30/2021 17:23:13 - INFO - __main__ - Step 23361: {'lr': 0.00047473985243858577, 'samples': 4485312, 'steps': 23360, 'loss/train': 1.4242740869522095}
+08/30/2021 17:23:13 - INFO - __main__ - Step 23362: {'lr': 0.00047473752786443736, 'samples': 4485504, 'steps': 23361, 'loss/train': 1.536911129951477}
+08/30/2021 17:23:15 - INFO - __main__ - Step 23363: {'lr': 0.0004747352031890257, 'samples': 4485696, 'steps': 23362, 'loss/train': 1.0240377187728882}
+08/30/2021 17:23:15 - INFO - __main__ - Step 23364: {'lr': 0.0004747328784123519, 'samples': 4485888, 'steps': 23363, 'loss/train': 1.4924437999725342}
+08/30/2021 17:23:16 - INFO - __main__ - Step 23365: {'lr': 0.00047473055353441685, 'samples': 4486080, 'steps': 23364, 'loss/train': 1.7939375638961792}
+08/30/2021 17:23:16 - INFO - __main__ - Step 23366: {'lr': 0.0004747282285552217, 'samples': 4486272, 'steps': 23365, 'loss/train': 2.470353841781616}
+08/30/2021 17:23:16 - INFO - __main__ - Step 23367: {'lr': 0.0004747259034747675, 'samples': 4486464, 'steps': 23366, 'loss/train': 2.460697889328003}
+08/30/2021 17:23:18 - INFO - __main__ - Step 23368: {'lr': 0.00047472357829305524, 'samples': 4486656, 'steps': 23367, 'loss/train': 1.9643207788467407}
+08/30/2021 17:23:18 - INFO - __main__ - Step 23369: {'lr': 0.0004747212530100861, 'samples': 4486848, 'steps': 23368, 'loss/train': 1.8857786655426025}
+08/30/2021 17:23:19 - INFO - __main__ - Step 23370: {'lr': 0.0004747189276258609, 'samples': 4487040, 'steps': 23369, 'loss/train': 1.8279653787612915}
+08/30/2021 17:23:19 - INFO - __main__ - Step 23371: {'lr': 0.0004747166021403809, 'samples': 4487232, 'steps': 23370, 'loss/train': 1.2541252374649048}
+08/30/2021 17:23:19 - INFO - __main__ - Step 23372: {'lr': 0.000474714276553647, 'samples': 4487424, 'steps': 23371, 'loss/train': 1.3642388582229614}
+08/30/2021 17:23:20 - INFO - __main__ - Step 23373: {'lr': 0.00047471195086566035, 'samples': 4487616, 'steps': 23372, 'loss/train': 1.1675230264663696}
+08/30/2021 17:23:21 - INFO - __main__ - Step 23374: {'lr': 0.000474709625076422, 'samples': 4487808, 'steps': 23373, 'loss/train': 1.4698249101638794}
+08/30/2021 17:23:22 - INFO - __main__ - Step 23375: {'lr': 0.0004747072991859329, 'samples': 4488000, 'steps': 23374, 'loss/train': 1.673593282699585}
+08/30/2021 17:23:22 - INFO - __main__ - Step 23376: {'lr': 0.0004747049731941942, 'samples': 4488192, 'steps': 23375, 'loss/train': 1.6737829446792603}
+08/30/2021 17:23:23 - INFO - __main__ - Step 23377: {'lr': 0.0004747026471012069, 'samples': 4488384, 'steps': 23376, 'loss/train': 1.8373947143554688}
+08/30/2021 17:23:23 - INFO - __main__ - Step 23378: {'lr': 0.000474700320906972, 'samples': 4488576, 'steps': 23377, 'loss/train': 0.3915119171142578}
+08/30/2021 17:23:25 - INFO - __main__ - Step 23379: {'lr': 0.0004746979946114907, 'samples': 4488768, 'steps': 23378, 'loss/train': 0.2655538320541382}
+08/30/2021 17:23:25 - INFO - __main__ - Step 23380: {'lr': 0.000474695668214764, 'samples': 4488960, 'steps': 23379, 'loss/train': 2.253612995147705}
+08/30/2021 17:23:25 - INFO - __main__ - Step 23381: {'lr': 0.00047469334171679266, 'samples': 4489152, 'steps': 23380, 'loss/train': 2.6099472045898438}
+08/30/2021 17:23:26 - INFO - __main__ - Step 23382: {'lr': 0.00047469101511757815, 'samples': 4489344, 'steps': 23381, 'loss/train': 1.9087992906570435}
+08/30/2021 17:23:26 - INFO - __main__ - Step 23383: {'lr': 0.00047468868841712134, 'samples': 4489536, 'steps': 23382, 'loss/train': 1.361952543258667}
+08/30/2021 17:23:28 - INFO - __main__ - Step 23384: {'lr': 0.00047468636161542325, 'samples': 4489728, 'steps': 23383, 'loss/train': 1.7354804277420044}
+08/30/2021 17:23:28 - INFO - __main__ - Step 23385: {'lr': 0.0004746840347124849, 'samples': 4489920, 'steps': 23384, 'loss/train': 1.5653932094573975}
+08/30/2021 17:23:28 - INFO - __main__ - Step 23386: {'lr': 0.0004746817077083074, 'samples': 4490112, 'steps': 23385, 'loss/train': 2.235689163208008}
+08/30/2021 17:23:29 - INFO - __main__ - Step 23387: {'lr': 0.00047467938060289185, 'samples': 4490304, 'steps': 23386, 'loss/train': 1.6533534526824951}
+08/30/2021 17:23:29 - INFO - __main__ - Step 23388: {'lr': 0.0004746770533962391, 'samples': 4490496, 'steps': 23387, 'loss/train': 1.812745213508606}
+08/30/2021 17:23:29 - INFO - __main__ - Step 23389: {'lr': 0.0004746747260883505, 'samples': 4490688, 'steps': 23388, 'loss/train': 1.734961748123169}
+08/30/2021 17:23:31 - INFO - __main__ - Step 23390: {'lr': 0.0004746723986792268, 'samples': 4490880, 'steps': 23389, 'loss/train': 1.3688782453536987}
+08/30/2021 17:23:31 - INFO - __main__ - Step 23391: {'lr': 0.0004746700711688693, 'samples': 4491072, 'steps': 23390, 'loss/train': 1.6471861600875854}
+08/30/2021 17:23:32 - INFO - __main__ - Step 23392: {'lr': 0.0004746677435572789, 'samples': 4491264, 'steps': 23391, 'loss/train': 1.8662527799606323}
+08/30/2021 17:23:32 - INFO - __main__ - Step 23393: {'lr': 0.00047466541584445667, 'samples': 4491456, 'steps': 23392, 'loss/train': 1.7130470275878906}
+08/30/2021 17:23:32 - INFO - __main__ - Step 23394: {'lr': 0.0004746630880304037, 'samples': 4491648, 'steps': 23393, 'loss/train': 0.8440204858779907}
+08/30/2021 17:23:34 - INFO - __main__ - Step 23395: {'lr': 0.0004746607601151209, 'samples': 4491840, 'steps': 23394, 'loss/train': 1.6433444023132324}
+08/30/2021 17:23:35 - INFO - __main__ - Step 23396: {'lr': 0.0004746584320986096, 'samples': 4492032, 'steps': 23395, 'loss/train': 1.9183671474456787}
+08/30/2021 17:23:35 - INFO - __main__ - Step 23397: {'lr': 0.0004746561039808706, 'samples': 4492224, 'steps': 23396, 'loss/train': 1.188535451889038}
+08/30/2021 17:23:35 - INFO - __main__ - Step 23398: {'lr': 0.0004746537757619049, 'samples': 4492416, 'steps': 23397, 'loss/train': 1.4544490575790405}
+08/30/2021 17:23:36 - INFO - __main__ - Step 23399: {'lr': 0.00047465144744171387, 'samples': 4492608, 'steps': 23398, 'loss/train': 1.52882719039917}
+08/30/2021 17:23:37 - INFO - __main__ - Step 23400: {'lr': 0.0004746491190202983, 'samples': 4492800, 'steps': 23399, 'loss/train': 1.3295679092407227}
+08/30/2021 17:23:38 - INFO - __main__ - Step 23401: {'lr': 0.00047464679049765926, 'samples': 4492992, 'steps': 23400, 'loss/train': 1.7973284721374512}
+08/30/2021 17:23:38 - INFO - __main__ - Step 23402: {'lr': 0.00047464446187379787, 'samples': 4493184, 'steps': 23401, 'loss/train': 1.505181074142456}
+08/30/2021 17:23:39 - INFO - __main__ - Step 23403: {'lr': 0.00047464213314871514, 'samples': 4493376, 'steps': 23402, 'loss/train': 1.8122906684875488}
+08/30/2021 17:23:39 - INFO - __main__ - Step 23404: {'lr': 0.0004746398043224122, 'samples': 4493568, 'steps': 23403, 'loss/train': 1.5950868129730225}
+08/30/2021 17:23:41 - INFO - __main__ - Step 23405: {'lr': 0.0004746374753948899, 'samples': 4493760, 'steps': 23404, 'loss/train': 1.5152009725570679}
+08/30/2021 17:23:41 - INFO - __main__ - Step 23406: {'lr': 0.00047463514636614945, 'samples': 4493952, 'steps': 23405, 'loss/train': 1.8622397184371948}
+08/30/2021 17:23:42 - INFO - __main__ - Step 23407: {'lr': 0.00047463281723619203, 'samples': 4494144, 'steps': 23406, 'loss/train': 0.7602947950363159}
+08/30/2021 17:23:42 - INFO - __main__ - Step 23408: {'lr': 0.00047463048800501837, 'samples': 4494336, 'steps': 23407, 'loss/train': 1.307937741279602}
+08/30/2021 17:23:42 - INFO - __main__ - Step 23409: {'lr': 0.00047462815867262967, 'samples': 4494528, 'steps': 23408, 'loss/train': 2.198789358139038}
+08/30/2021 17:23:44 - INFO - __main__ - Step 23410: {'lr': 0.0004746258292390271, 'samples': 4494720, 'steps': 23409, 'loss/train': 1.6767184734344482}
+08/30/2021 17:23:44 - INFO - __main__ - Step 23411: {'lr': 0.00047462349970421147, 'samples': 4494912, 'steps': 23410, 'loss/train': 1.3218573331832886}
+08/30/2021 17:23:45 - INFO - __main__ - Step 23412: {'lr': 0.0004746211700681841, 'samples': 4495104, 'steps': 23411, 'loss/train': 1.3264437913894653}
+08/30/2021 17:23:45 - INFO - __main__ - Step 23413: {'lr': 0.0004746188403309457, 'samples': 4495296, 'steps': 23412, 'loss/train': 1.8527815341949463}
+08/30/2021 17:23:45 - INFO - __main__ - Step 23414: {'lr': 0.00047461651049249764, 'samples': 4495488, 'steps': 23413, 'loss/train': 1.2875312566757202}
+08/30/2021 17:23:48 - INFO - __main__ - Step 23415: {'lr': 0.0004746141805528409, 'samples': 4495680, 'steps': 23414, 'loss/train': 1.7617915868759155}
+08/30/2021 17:23:48 - INFO - __main__ - Step 23416: {'lr': 0.00047461185051197644, 'samples': 4495872, 'steps': 23415, 'loss/train': 1.4624656438827515}
+08/30/2021 17:23:48 - INFO - __main__ - Step 23417: {'lr': 0.0004746095203699053, 'samples': 4496064, 'steps': 23416, 'loss/train': 5.8519086837768555}
+08/30/2021 17:23:49 - INFO - __main__ - Step 23418: {'lr': 0.00047460719012662857, 'samples': 4496256, 'steps': 23417, 'loss/train': 4.7854485511779785}
+08/30/2021 17:23:49 - INFO - __main__ - Step 23419: {'lr': 0.00047460485978214733, 'samples': 4496448, 'steps': 23418, 'loss/train': 5.4564738273620605}
+08/30/2021 17:23:49 - INFO - __main__ - Step 23420: {'lr': 0.00047460252933646265, 'samples': 4496640, 'steps': 23419, 'loss/train': 4.870734691619873}
+08/30/2021 17:23:50 - INFO - __main__ - Step 23421: {'lr': 0.0004746001987895755, 'samples': 4496832, 'steps': 23420, 'loss/train': 1.6050056219100952}
+08/30/2021 17:23:51 - INFO - __main__ - Step 23422: {'lr': 0.00047459786814148697, 'samples': 4497024, 'steps': 23421, 'loss/train': 1.7520097494125366}
+08/30/2021 17:23:52 - INFO - __main__ - Step 23423: {'lr': 0.0004745955373921981, 'samples': 4497216, 'steps': 23422, 'loss/train': 0.8850692510604858}
+08/30/2021 17:23:52 - INFO - __main__ - Step 23424: {'lr': 0.0004745932065417099, 'samples': 4497408, 'steps': 23423, 'loss/train': 1.8354878425598145}
+08/30/2021 17:23:52 - INFO - __main__ - Step 23425: {'lr': 0.00047459087559002355, 'samples': 4497600, 'steps': 23424, 'loss/train': 1.7539135217666626}
+08/30/2021 17:23:53 - INFO - __main__ - Step 23426: {'lr': 0.00047458854453713995, 'samples': 4497792, 'steps': 23425, 'loss/train': 1.7263280153274536}
+08/30/2021 17:23:54 - INFO - __main__ - Step 23427: {'lr': 0.0004745862133830603, 'samples': 4497984, 'steps': 23426, 'loss/train': 1.466227412223816}
+08/30/2021 17:23:55 - INFO - __main__ - Step 23428: {'lr': 0.00047458388212778547, 'samples': 4498176, 'steps': 23427, 'loss/train': 1.9011969566345215}
+08/30/2021 17:23:55 - INFO - __main__ - Step 23429: {'lr': 0.00047458155077131664, 'samples': 4498368, 'steps': 23428, 'loss/train': 0.665778636932373}
+08/30/2021 17:23:56 - INFO - __main__ - Step 23430: {'lr': 0.0004745792193136549, 'samples': 4498560, 'steps': 23429, 'loss/train': 1.4582651853561401}
+08/30/2021 17:23:56 - INFO - __main__ - Step 23431: {'lr': 0.00047457688775480114, 'samples': 4498752, 'steps': 23430, 'loss/train': 2.1060478687286377}
+08/30/2021 17:23:56 - INFO - __main__ - Step 23432: {'lr': 0.0004745745560947565, 'samples': 4498944, 'steps': 23431, 'loss/train': 0.9793155789375305}
+08/30/2021 17:23:58 - INFO - __main__ - Step 23433: {'lr': 0.0004745722243335221, 'samples': 4499136, 'steps': 23432, 'loss/train': 1.958113670349121}
+08/30/2021 17:23:59 - INFO - __main__ - Step 23434: {'lr': 0.0004745698924710988, 'samples': 4499328, 'steps': 23433, 'loss/train': 1.1268386840820312}
+08/30/2021 17:23:59 - INFO - __main__ - Step 23435: {'lr': 0.00047456756050748793, 'samples': 4499520, 'steps': 23434, 'loss/train': 2.3697609901428223}
+08/30/2021 17:23:59 - INFO - __main__ - Step 23436: {'lr': 0.0004745652284426903, 'samples': 4499712, 'steps': 23435, 'loss/train': 2.8915159702301025}
+08/30/2021 17:24:00 - INFO - __main__ - Step 23437: {'lr': 0.00047456289627670703, 'samples': 4499904, 'steps': 23436, 'loss/train': 1.2846698760986328}
+08/30/2021 17:24:01 - INFO - __main__ - Step 23438: {'lr': 0.0004745605640095392, 'samples': 4500096, 'steps': 23437, 'loss/train': 1.5122549533843994}
+08/30/2021 17:24:02 - INFO - __main__ - Step 23439: {'lr': 0.00047455823164118787, 'samples': 4500288, 'steps': 23438, 'loss/train': 2.0294601917266846}
+08/30/2021 17:24:02 - INFO - __main__ - Step 23440: {'lr': 0.00047455589917165406, 'samples': 4500480, 'steps': 23439, 'loss/train': 1.3264708518981934}
+08/30/2021 17:24:02 - INFO - __main__ - Step 23441: {'lr': 0.00047455356660093886, 'samples': 4500672, 'steps': 23440, 'loss/train': 1.8434523344039917}
+08/30/2021 17:24:03 - INFO - __main__ - Step 23442: {'lr': 0.0004745512339290432, 'samples': 4500864, 'steps': 23441, 'loss/train': 1.5019114017486572}
+08/30/2021 17:24:04 - INFO - __main__ - Step 23443: {'lr': 0.00047454890115596824, 'samples': 4501056, 'steps': 23442, 'loss/train': 1.7407407760620117}
+08/30/2021 17:24:05 - INFO - __main__ - Step 23444: {'lr': 0.00047454656828171504, 'samples': 4501248, 'steps': 23443, 'loss/train': 1.4007312059402466}
+08/30/2021 17:24:05 - INFO - __main__ - Step 23445: {'lr': 0.0004745442353062846, 'samples': 4501440, 'steps': 23444, 'loss/train': 1.9586397409439087}
+08/30/2021 17:24:05 - INFO - __main__ - Step 23446: {'lr': 0.000474541902229678, 'samples': 4501632, 'steps': 23445, 'loss/train': 0.6901741623878479}
+08/30/2021 17:24:06 - INFO - __main__ - Step 23447: {'lr': 0.0004745395690518963, 'samples': 4501824, 'steps': 23446, 'loss/train': 1.9121707677841187}
+08/30/2021 17:24:07 - INFO - __main__ - Step 23448: {'lr': 0.0004745372357729405, 'samples': 4502016, 'steps': 23447, 'loss/train': 1.4843432903289795}
+08/30/2021 17:24:08 - INFO - __main__ - Step 23449: {'lr': 0.0004745349023928117, 'samples': 4502208, 'steps': 23448, 'loss/train': 1.4363607168197632}
+08/30/2021 17:24:08 - INFO - __main__ - Step 23450: {'lr': 0.000474532568911511, 'samples': 4502400, 'steps': 23449, 'loss/train': 3.3592400550842285}
+08/30/2021 17:24:09 - INFO - __main__ - Step 23451: {'lr': 0.00047453023532903927, 'samples': 4502592, 'steps': 23450, 'loss/train': 0.9863831996917725}
+08/30/2021 17:24:09 - INFO - __main__ - Step 23452: {'lr': 0.00047452790164539775, 'samples': 4502784, 'steps': 23451, 'loss/train': 1.3867384195327759}
+08/30/2021 17:24:09 - INFO - __main__ - Step 23453: {'lr': 0.00047452556786058744, 'samples': 4502976, 'steps': 23452, 'loss/train': 2.2206199169158936}
+08/30/2021 17:24:11 - INFO - __main__ - Step 23454: {'lr': 0.0004745232339746094, 'samples': 4503168, 'steps': 23453, 'loss/train': 1.588103175163269}
+08/30/2021 17:24:12 - INFO - __main__ - Step 23455: {'lr': 0.00047452089998746463, 'samples': 4503360, 'steps': 23454, 'loss/train': 1.7924898862838745}
+08/30/2021 17:24:12 - INFO - __main__ - Step 23456: {'lr': 0.0004745185658991541, 'samples': 4503552, 'steps': 23455, 'loss/train': 1.5315626859664917}
+08/30/2021 17:24:12 - INFO - __main__ - Step 23457: {'lr': 0.0004745162317096791, 'samples': 4503744, 'steps': 23456, 'loss/train': 1.523364782333374}
+08/30/2021 17:24:13 - INFO - __main__ - Step 23458: {'lr': 0.0004745138974190405, 'samples': 4503936, 'steps': 23457, 'loss/train': 1.3494212627410889}
+08/30/2021 17:24:14 - INFO - __main__ - Step 23459: {'lr': 0.0004745115630272394, 'samples': 4504128, 'steps': 23458, 'loss/train': 1.3633402585983276}
+08/30/2021 17:24:15 - INFO - __main__ - Step 23460: {'lr': 0.00047450922853427686, 'samples': 4504320, 'steps': 23459, 'loss/train': 0.2803743779659271}
+08/30/2021 17:24:15 - INFO - __main__ - Step 23461: {'lr': 0.0004745068939401539, 'samples': 4504512, 'steps': 23460, 'loss/train': 1.6602718830108643}
+08/30/2021 17:24:16 - INFO - __main__ - Step 23462: {'lr': 0.0004745045592448717, 'samples': 4504704, 'steps': 23461, 'loss/train': 1.833642840385437}
+08/30/2021 17:24:16 - INFO - __main__ - Step 23463: {'lr': 0.00047450222444843105, 'samples': 4504896, 'steps': 23462, 'loss/train': 1.7407232522964478}
+08/30/2021 17:24:18 - INFO - __main__ - Step 23464: {'lr': 0.0004744998895508333, 'samples': 4505088, 'steps': 23463, 'loss/train': 1.4313862323760986}
+08/30/2021 17:24:18 - INFO - __main__ - Step 23465: {'lr': 0.0004744975545520793, 'samples': 4505280, 'steps': 23464, 'loss/train': 1.3955929279327393}
+08/30/2021 17:24:18 - INFO - __main__ - Step 23466: {'lr': 0.00047449521945217016, 'samples': 4505472, 'steps': 23465, 'loss/train': 0.11742239445447922}
+08/30/2021 17:24:19 - INFO - __main__ - Step 23467: {'lr': 0.00047449288425110693, 'samples': 4505664, 'steps': 23466, 'loss/train': 1.964247226715088}
+08/30/2021 17:24:19 - INFO - __main__ - Step 23468: {'lr': 0.00047449054894889073, 'samples': 4505856, 'steps': 23467, 'loss/train': 1.281093716621399}
+08/30/2021 17:24:21 - INFO - __main__ - Step 23469: {'lr': 0.00047448821354552253, 'samples': 4506048, 'steps': 23468, 'loss/train': 1.9166456460952759}
+08/30/2021 17:24:21 - INFO - __main__ - Step 23470: {'lr': 0.0004744858780410034, 'samples': 4506240, 'steps': 23469, 'loss/train': 1.4999719858169556}
+08/30/2021 17:24:22 - INFO - __main__ - Step 23471: {'lr': 0.0004744835424353344, 'samples': 4506432, 'steps': 23470, 'loss/train': 1.7396823167800903}
+08/30/2021 17:24:22 - INFO - __main__ - Step 23472: {'lr': 0.00047448120672851653, 'samples': 4506624, 'steps': 23471, 'loss/train': 2.032892942428589}
+08/30/2021 17:24:22 - INFO - __main__ - Step 23473: {'lr': 0.0004744788709205509, 'samples': 4506816, 'steps': 23472, 'loss/train': 1.2991772890090942}
+08/30/2021 17:24:23 - INFO - __main__ - Step 23474: {'lr': 0.0004744765350114386, 'samples': 4507008, 'steps': 23473, 'loss/train': 1.8414204120635986}
+08/30/2021 17:24:24 - INFO - __main__ - Step 23475: {'lr': 0.00047447419900118067, 'samples': 4507200, 'steps': 23474, 'loss/train': 2.0994033813476562}
+08/30/2021 17:24:25 - INFO - __main__ - Step 23476: {'lr': 0.00047447186288977804, 'samples': 4507392, 'steps': 23475, 'loss/train': 1.974700689315796}
+08/30/2021 17:24:25 - INFO - __main__ - Step 23477: {'lr': 0.0004744695266772319, 'samples': 4507584, 'steps': 23476, 'loss/train': 0.30462032556533813}
+08/30/2021 17:24:26 - INFO - __main__ - Step 23478: {'lr': 0.00047446719036354324, 'samples': 4507776, 'steps': 23477, 'loss/train': 1.4962259531021118}
+08/30/2021 17:24:26 - INFO - __main__ - Step 23479: {'lr': 0.0004744648539487132, 'samples': 4507968, 'steps': 23478, 'loss/train': 1.6455671787261963}
+08/30/2021 17:24:28 - INFO - __main__ - Step 23480: {'lr': 0.00047446251743274263, 'samples': 4508160, 'steps': 23479, 'loss/train': 1.8071171045303345}
+08/30/2021 17:24:28 - INFO - __main__ - Step 23481: {'lr': 0.0004744601808156328, 'samples': 4508352, 'steps': 23480, 'loss/train': 1.5873665809631348}
+08/30/2021 17:24:29 - INFO - __main__ - Step 23482: {'lr': 0.00047445784409738467, 'samples': 4508544, 'steps': 23481, 'loss/train': 1.4687551259994507}
+08/30/2021 17:24:29 - INFO - __main__ - Step 23483: {'lr': 0.0004744555072779993, 'samples': 4508736, 'steps': 23482, 'loss/train': 2.1719584465026855}
+08/30/2021 17:24:30 - INFO - __main__ - Step 23484: {'lr': 0.0004744531703574777, 'samples': 4508928, 'steps': 23483, 'loss/train': 1.622030258178711}
+08/30/2021 17:24:30 - INFO - __main__ - Step 23485: {'lr': 0.00047445083333582104, 'samples': 4509120, 'steps': 23484, 'loss/train': 0.7606672644615173}
+08/30/2021 17:24:31 - INFO - __main__ - Step 23486: {'lr': 0.00047444849621303023, 'samples': 4509312, 'steps': 23485, 'loss/train': 0.7390870451927185}
+08/30/2021 17:24:32 - INFO - __main__ - Step 23487: {'lr': 0.00047444615898910644, 'samples': 4509504, 'steps': 23486, 'loss/train': 1.55876624584198}
+08/30/2021 17:24:32 - INFO - __main__ - Step 23488: {'lr': 0.00047444382166405067, 'samples': 4509696, 'steps': 23487, 'loss/train': 2.046896457672119}
+08/30/2021 17:24:33 - INFO - __main__ - Step 23489: {'lr': 0.0004744414842378639, 'samples': 4509888, 'steps': 23488, 'loss/train': 1.255998134613037}
+08/30/2021 17:24:33 - INFO - __main__ - Step 23490: {'lr': 0.0004744391467105473, 'samples': 4510080, 'steps': 23489, 'loss/train': 1.868764042854309}
+08/30/2021 17:24:35 - INFO - __main__ - Step 23491: {'lr': 0.00047443680908210194, 'samples': 4510272, 'steps': 23490, 'loss/train': 2.182711362838745}
+08/30/2021 17:24:36 - INFO - __main__ - Step 23492: {'lr': 0.00047443447135252876, 'samples': 4510464, 'steps': 23491, 'loss/train': 1.7871869802474976}
+08/30/2021 17:24:36 - INFO - __main__ - Step 23493: {'lr': 0.0004744321335218289, 'samples': 4510656, 'steps': 23492, 'loss/train': 1.6534804105758667}
+08/30/2021 17:24:36 - INFO - __main__ - Step 23494: {'lr': 0.0004744297955900034, 'samples': 4510848, 'steps': 23493, 'loss/train': 0.16427098214626312}
+08/30/2021 17:24:37 - INFO - __main__ - Step 23495: {'lr': 0.00047442745755705326, 'samples': 4511040, 'steps': 23494, 'loss/train': 0.5807023048400879}
+08/30/2021 17:24:38 - INFO - __main__ - Step 23496: {'lr': 0.00047442511942297953, 'samples': 4511232, 'steps': 23495, 'loss/train': 1.61563241481781}
+08/30/2021 17:24:39 - INFO - __main__ - Step 23497: {'lr': 0.00047442278118778336, 'samples': 4511424, 'steps': 23496, 'loss/train': 1.7230396270751953}
+08/30/2021 17:24:39 - INFO - __main__ - Step 23498: {'lr': 0.0004744204428514658, 'samples': 4511616, 'steps': 23497, 'loss/train': 1.6623622179031372}
+08/30/2021 17:24:40 - INFO - __main__ - Step 23499: {'lr': 0.00047441810441402777, 'samples': 4511808, 'steps': 23498, 'loss/train': 0.14661931991577148}
+08/30/2021 17:24:40 - INFO - __main__ - Step 23500: {'lr': 0.0004744157658754704, 'samples': 4512000, 'steps': 23499, 'loss/train': 1.5369865894317627}
+08/30/2021 17:24:41 - INFO - __main__ - Step 23501: {'lr': 0.0004744134272357948, 'samples': 4512192, 'steps': 23500, 'loss/train': 1.2457892894744873}
+08/30/2021 17:24:42 - INFO - __main__ - Step 23502: {'lr': 0.0004744110884950019, 'samples': 4512384, 'steps': 23501, 'loss/train': 1.8913642168045044}
+08/30/2021 17:24:42 - INFO - __main__ - Step 23503: {'lr': 0.00047440874965309286, 'samples': 4512576, 'steps': 23502, 'loss/train': 1.378138542175293}
+08/30/2021 17:24:42 - INFO - __main__ - Step 23504: {'lr': 0.00047440641071006874, 'samples': 4512768, 'steps': 23503, 'loss/train': 1.9634078741073608}
+08/30/2021 17:24:43 - INFO - __main__ - Step 23505: {'lr': 0.00047440407166593056, 'samples': 4512960, 'steps': 23504, 'loss/train': 1.6665253639221191}
+08/30/2021 17:24:45 - INFO - __main__ - Step 23506: {'lr': 0.0004744017325206793, 'samples': 4513152, 'steps': 23505, 'loss/train': 1.0028982162475586}
+08/30/2021 17:24:45 - INFO - __main__ - Step 23507: {'lr': 0.00047439939327431613, 'samples': 4513344, 'steps': 23506, 'loss/train': 1.8394252061843872}
+08/30/2021 17:24:46 - INFO - __main__ - Step 23508: {'lr': 0.0004743970539268421, 'samples': 4513536, 'steps': 23507, 'loss/train': 1.3555352687835693}
+08/30/2021 17:24:46 - INFO - __main__ - Step 23509: {'lr': 0.00047439471447825813, 'samples': 4513728, 'steps': 23508, 'loss/train': 0.9830705523490906}
+08/30/2021 17:24:46 - INFO - __main__ - Step 23510: {'lr': 0.00047439237492856543, 'samples': 4513920, 'steps': 23509, 'loss/train': 1.154396891593933}
+08/30/2021 17:24:47 - INFO - __main__ - Step 23511: {'lr': 0.0004743900352777649, 'samples': 4514112, 'steps': 23510, 'loss/train': 1.7377116680145264}
+08/30/2021 17:24:48 - INFO - __main__ - Step 23512: {'lr': 0.0004743876955258578, 'samples': 4514304, 'steps': 23511, 'loss/train': 1.7903070449829102}
+08/30/2021 17:24:49 - INFO - __main__ - Step 23513: {'lr': 0.00047438535567284504, 'samples': 4514496, 'steps': 23512, 'loss/train': 2.2499351501464844}
+08/30/2021 17:24:49 - INFO - __main__ - Step 23514: {'lr': 0.00047438301571872763, 'samples': 4514688, 'steps': 23513, 'loss/train': 1.4361882209777832}
+08/30/2021 17:24:49 - INFO - __main__ - Step 23515: {'lr': 0.00047438067566350675, 'samples': 4514880, 'steps': 23514, 'loss/train': 1.3551257848739624}
+08/30/2021 17:24:50 - INFO - __main__ - Step 23516: {'lr': 0.00047437833550718336, 'samples': 4515072, 'steps': 23515, 'loss/train': 1.4749128818511963}
+08/30/2021 17:24:51 - INFO - __main__ - Step 23517: {'lr': 0.0004743759952497586, 'samples': 4515264, 'steps': 23516, 'loss/train': 1.697044849395752}
+08/30/2021 17:24:52 - INFO - __main__ - Step 23518: {'lr': 0.0004743736548912334, 'samples': 4515456, 'steps': 23517, 'loss/train': 2.0789573192596436}
+08/30/2021 17:24:52 - INFO - __main__ - Step 23519: {'lr': 0.00047437131443160897, 'samples': 4515648, 'steps': 23518, 'loss/train': 1.4848761558532715}
+08/30/2021 17:24:52 - INFO - __main__ - Step 23520: {'lr': 0.0004743689738708863, 'samples': 4515840, 'steps': 23519, 'loss/train': 1.4723833799362183}
+08/30/2021 17:24:53 - INFO - __main__ - Step 23521: {'lr': 0.0004743666332090664, 'samples': 4516032, 'steps': 23520, 'loss/train': 2.1788690090179443}
+08/30/2021 17:24:54 - INFO - __main__ - Step 23522: {'lr': 0.00047436429244615037, 'samples': 4516224, 'steps': 23521, 'loss/train': 1.716915249824524}
+08/30/2021 17:24:55 - INFO - __main__ - Step 23523: {'lr': 0.0004743619515821392, 'samples': 4516416, 'steps': 23522, 'loss/train': 1.7972381114959717}
+08/30/2021 17:24:55 - INFO - __main__ - Step 23524: {'lr': 0.00047435961061703403, 'samples': 4516608, 'steps': 23523, 'loss/train': 1.5950313806533813}
+08/30/2021 17:24:55 - INFO - __main__ - Step 23525: {'lr': 0.00047435726955083593, 'samples': 4516800, 'steps': 23524, 'loss/train': 1.8461427688598633}
+08/30/2021 17:24:56 - INFO - __main__ - Step 23526: {'lr': 0.0004743549283835459, 'samples': 4516992, 'steps': 23525, 'loss/train': 1.5676671266555786}
+08/30/2021 17:24:58 - INFO - __main__ - Step 23527: {'lr': 0.00047435258711516496, 'samples': 4517184, 'steps': 23526, 'loss/train': 1.7245956659317017}
+08/30/2021 17:24:58 - INFO - __main__ - Step 23528: {'lr': 0.0004743502457456942, 'samples': 4517376, 'steps': 23527, 'loss/train': 1.6351948976516724}
+08/30/2021 17:24:58 - INFO - __main__ - Step 23529: {'lr': 0.0004743479042751347, 'samples': 4517568, 'steps': 23528, 'loss/train': 1.687272310256958}
+08/30/2021 17:24:59 - INFO - __main__ - Step 23530: {'lr': 0.0004743455627034875, 'samples': 4517760, 'steps': 23529, 'loss/train': 1.19921875}
+08/30/2021 17:24:59 - INFO - __main__ - Step 23531: {'lr': 0.0004743432210307536, 'samples': 4517952, 'steps': 23530, 'loss/train': 0.26170551776885986}
+08/30/2021 17:25:01 - INFO - __main__ - Step 23532: {'lr': 0.00047434087925693415, 'samples': 4518144, 'steps': 23531, 'loss/train': 1.4048240184783936}
+08/30/2021 17:25:01 - INFO - __main__ - Step 23533: {'lr': 0.00047433853738203013, 'samples': 4518336, 'steps': 23532, 'loss/train': 0.34342679381370544}
+08/30/2021 17:25:02 - INFO - __main__ - Step 23534: {'lr': 0.00047433619540604264, 'samples': 4518528, 'steps': 23533, 'loss/train': 0.4432034492492676}
+08/30/2021 17:25:02 - INFO - __main__ - Step 23535: {'lr': 0.0004743338533289728, 'samples': 4518720, 'steps': 23534, 'loss/train': 1.9128985404968262}
+08/30/2021 17:25:02 - INFO - __main__ - Step 23536: {'lr': 0.0004743315111508215, 'samples': 4518912, 'steps': 23535, 'loss/train': 1.51212477684021}
+08/30/2021 17:25:03 - INFO - __main__ - Step 23537: {'lr': 0.00047432916887158995, 'samples': 4519104, 'steps': 23536, 'loss/train': 2.5439515113830566}
+08/30/2021 17:25:05 - INFO - __main__ - Step 23538: {'lr': 0.00047432682649127913, 'samples': 4519296, 'steps': 23537, 'loss/train': 1.9498885869979858}
+08/30/2021 17:25:05 - INFO - __main__ - Step 23539: {'lr': 0.00047432448400989004, 'samples': 4519488, 'steps': 23538, 'loss/train': 1.6660622358322144}
+08/30/2021 17:25:05 - INFO - __main__ - Step 23540: {'lr': 0.0004743221414274238, 'samples': 4519680, 'steps': 23539, 'loss/train': 0.14143574237823486}
+08/30/2021 17:25:06 - INFO - __main__ - Step 23541: {'lr': 0.00047431979874388154, 'samples': 4519872, 'steps': 23540, 'loss/train': 2.1670846939086914}
+08/30/2021 17:25:06 - INFO - __main__ - Step 23542: {'lr': 0.0004743174559592642, 'samples': 4520064, 'steps': 23541, 'loss/train': 0.116717129945755}
+08/30/2021 17:25:07 - INFO - __main__ - Step 23543: {'lr': 0.0004743151130735729, 'samples': 4520256, 'steps': 23542, 'loss/train': 0.14372417330741882}
+08/30/2021 17:25:08 - INFO - __main__ - Step 23544: {'lr': 0.0004743127700868086, 'samples': 4520448, 'steps': 23543, 'loss/train': 0.09387094527482986}
+08/30/2021 17:25:09 - INFO - __main__ - Step 23545: {'lr': 0.00047431042699897245, 'samples': 4520640, 'steps': 23544, 'loss/train': 1.1553503274917603}
+08/30/2021 17:25:09 - INFO - __main__ - Step 23546: {'lr': 0.0004743080838100655, 'samples': 4520832, 'steps': 23545, 'loss/train': 1.2153754234313965}
+08/30/2021 17:25:09 - INFO - __main__ - Step 23547: {'lr': 0.0004743057405200888, 'samples': 4521024, 'steps': 23546, 'loss/train': 2.096493721008301}
+08/30/2021 17:25:10 - INFO - __main__ - Step 23548: {'lr': 0.0004743033971290434, 'samples': 4521216, 'steps': 23547, 'loss/train': 1.7743288278579712}
+08/30/2021 17:25:11 - INFO - __main__ - Step 23549: {'lr': 0.00047430105363693034, 'samples': 4521408, 'steps': 23548, 'loss/train': 1.6424707174301147}
+08/30/2021 17:25:12 - INFO - __main__ - Step 23550: {'lr': 0.0004742987100437507, 'samples': 4521600, 'steps': 23549, 'loss/train': 1.471112608909607}
+08/30/2021 17:25:12 - INFO - __main__ - Step 23551: {'lr': 0.00047429636634950545, 'samples': 4521792, 'steps': 23550, 'loss/train': 1.3400425910949707}
+08/30/2021 17:25:12 - INFO - __main__ - Step 23552: {'lr': 0.0004742940225541958, 'samples': 4521984, 'steps': 23551, 'loss/train': 1.497818112373352}
+08/30/2021 17:25:13 - INFO - __main__ - Step 23553: {'lr': 0.0004742916786578227, 'samples': 4522176, 'steps': 23552, 'loss/train': 1.3833774328231812}
+08/30/2021 17:25:14 - INFO - __main__ - Step 23554: {'lr': 0.00047428933466038726, 'samples': 4522368, 'steps': 23553, 'loss/train': 1.2099409103393555}
+08/30/2021 17:25:15 - INFO - __main__ - Step 23555: {'lr': 0.00047428699056189047, 'samples': 4522560, 'steps': 23554, 'loss/train': 0.5132454633712769}
+08/30/2021 17:25:15 - INFO - __main__ - Step 23556: {'lr': 0.0004742846463623334, 'samples': 4522752, 'steps': 23555, 'loss/train': 1.5360429286956787}
+08/30/2021 17:25:15 - INFO - __main__ - Step 23557: {'lr': 0.0004742823020617172, 'samples': 4522944, 'steps': 23556, 'loss/train': 0.2798418700695038}
+08/30/2021 17:25:16 - INFO - __main__ - Step 23558: {'lr': 0.0004742799576600427, 'samples': 4523136, 'steps': 23557, 'loss/train': 1.546321153640747}
+08/30/2021 17:25:16 - INFO - __main__ - Step 23559: {'lr': 0.00047427761315731133, 'samples': 4523328, 'steps': 23558, 'loss/train': 1.2455106973648071}
+08/30/2021 17:25:17 - INFO - __main__ - Step 23560: {'lr': 0.0004742752685535238, 'samples': 4523520, 'steps': 23559, 'loss/train': 1.5118094682693481}
+08/30/2021 17:25:18 - INFO - __main__ - Step 23561: {'lr': 0.00047427292384868134, 'samples': 4523712, 'steps': 23560, 'loss/train': 1.2776174545288086}
+08/30/2021 17:25:18 - INFO - __main__ - Step 23562: {'lr': 0.0004742705790427849, 'samples': 4523904, 'steps': 23561, 'loss/train': 1.1823251247406006}
+08/30/2021 17:25:19 - INFO - __main__ - Step 23563: {'lr': 0.00047426823413583563, 'samples': 4524096, 'steps': 23562, 'loss/train': 1.9637054204940796}
+08/30/2021 17:25:19 - INFO - __main__ - Step 23564: {'lr': 0.0004742658891278346, 'samples': 4524288, 'steps': 23563, 'loss/train': 1.7814786434173584}
+08/30/2021 17:25:21 - INFO - __main__ - Step 23565: {'lr': 0.0004742635440187828, 'samples': 4524480, 'steps': 23564, 'loss/train': 1.6499422788619995}
+08/30/2021 17:25:21 - INFO - __main__ - Step 23566: {'lr': 0.00047426119880868123, 'samples': 4524672, 'steps': 23565, 'loss/train': 1.9455660581588745}
+08/30/2021 17:25:21 - INFO - __main__ - Step 23567: {'lr': 0.00047425885349753114, 'samples': 4524864, 'steps': 23566, 'loss/train': 1.504725456237793}
+08/30/2021 17:25:22 - INFO - __main__ - Step 23568: {'lr': 0.0004742565080853334, 'samples': 4525056, 'steps': 23567, 'loss/train': 1.4364367723464966}
+08/30/2021 17:25:22 - INFO - __main__ - Step 23569: {'lr': 0.00047425416257208916, 'samples': 4525248, 'steps': 23568, 'loss/train': 2.000889778137207}
+08/30/2021 17:25:24 - INFO - __main__ - Step 23570: {'lr': 0.0004742518169577994, 'samples': 4525440, 'steps': 23569, 'loss/train': 0.8818508982658386}
+08/30/2021 17:25:24 - INFO - __main__ - Step 23571: {'lr': 0.0004742494712424653, 'samples': 4525632, 'steps': 23570, 'loss/train': 1.1138865947723389}
+08/30/2021 17:25:24 - INFO - __main__ - Step 23572: {'lr': 0.0004742471254260878, 'samples': 4525824, 'steps': 23571, 'loss/train': 2.152121067047119}
+08/30/2021 17:25:25 - INFO - __main__ - Step 23573: {'lr': 0.0004742447795086681, 'samples': 4526016, 'steps': 23572, 'loss/train': 1.2545866966247559}
+08/30/2021 17:25:25 - INFO - __main__ - Step 23574: {'lr': 0.00047424243349020705, 'samples': 4526208, 'steps': 23573, 'loss/train': 1.5952011346817017}
+08/30/2021 17:25:27 - INFO - __main__ - Step 23575: {'lr': 0.0004742400873707059, 'samples': 4526400, 'steps': 23574, 'loss/train': 1.7012284994125366}
+08/30/2021 17:25:28 - INFO - __main__ - Step 23576: {'lr': 0.0004742377411501656, 'samples': 4526592, 'steps': 23575, 'loss/train': 1.9678068161010742}
+08/30/2021 17:25:28 - INFO - __main__ - Step 23577: {'lr': 0.00047423539482858724, 'samples': 4526784, 'steps': 23576, 'loss/train': 2.030181646347046}
+08/30/2021 17:25:28 - INFO - __main__ - Step 23578: {'lr': 0.0004742330484059718, 'samples': 4526976, 'steps': 23577, 'loss/train': 1.1054855585098267}
+08/30/2021 17:25:29 - INFO - __main__ - Step 23579: {'lr': 0.0004742307018823205, 'samples': 4527168, 'steps': 23578, 'loss/train': 1.9471453428268433}
+08/30/2021 17:25:29 - INFO - __main__ - Step 23580: {'lr': 0.0004742283552576343, 'samples': 4527360, 'steps': 23579, 'loss/train': 1.2475463151931763}
+08/30/2021 17:25:31 - INFO - __main__ - Step 23581: {'lr': 0.0004742260085319142, 'samples': 4527552, 'steps': 23580, 'loss/train': 1.7846564054489136}
+08/30/2021 17:25:31 - INFO - __main__ - Step 23582: {'lr': 0.0004742236617051614, 'samples': 4527744, 'steps': 23581, 'loss/train': 1.6171941757202148}
+08/30/2021 17:25:31 - INFO - __main__ - Step 23583: {'lr': 0.00047422131477737684, 'samples': 4527936, 'steps': 23582, 'loss/train': 1.8229527473449707}
+08/30/2021 17:25:32 - INFO - __main__ - Step 23584: {'lr': 0.00047421896774856156, 'samples': 4528128, 'steps': 23583, 'loss/train': 1.7556407451629639}
+08/30/2021 17:25:32 - INFO - __main__ - Step 23585: {'lr': 0.00047421662061871675, 'samples': 4528320, 'steps': 23584, 'loss/train': 1.4895778894424438}
+08/30/2021 17:25:34 - INFO - __main__ - Step 23586: {'lr': 0.0004742142733878433, 'samples': 4528512, 'steps': 23585, 'loss/train': 2.789318561553955}
+08/30/2021 17:25:34 - INFO - __main__ - Step 23587: {'lr': 0.0004742119260559424, 'samples': 4528704, 'steps': 23586, 'loss/train': 1.1185063123703003}
+08/30/2021 17:25:35 - INFO - __main__ - Step 23588: {'lr': 0.0004742095786230152, 'samples': 4528896, 'steps': 23587, 'loss/train': 1.6517226696014404}
+08/30/2021 17:25:35 - INFO - __main__ - Step 23589: {'lr': 0.00047420723108906247, 'samples': 4529088, 'steps': 23588, 'loss/train': 1.8413761854171753}
+08/30/2021 17:25:35 - INFO - __main__ - Step 23590: {'lr': 0.0004742048834540855, 'samples': 4529280, 'steps': 23589, 'loss/train': 1.9400454759597778}
+08/30/2021 17:25:36 - INFO - __main__ - Step 23591: {'lr': 0.0004742025357180852, 'samples': 4529472, 'steps': 23590, 'loss/train': 1.9612764120101929}
+08/30/2021 17:25:37 - INFO - __main__ - Step 23592: {'lr': 0.00047420018788106274, 'samples': 4529664, 'steps': 23591, 'loss/train': 1.7768454551696777}
+08/30/2021 17:25:38 - INFO - __main__ - Step 23593: {'lr': 0.00047419783994301915, 'samples': 4529856, 'steps': 23592, 'loss/train': 1.7378946542739868}
+08/30/2021 17:25:38 - INFO - __main__ - Step 23594: {'lr': 0.0004741954919039554, 'samples': 4530048, 'steps': 23593, 'loss/train': 1.406349539756775}
+08/30/2021 17:25:38 - INFO - __main__ - Step 23595: {'lr': 0.0004741931437638727, 'samples': 4530240, 'steps': 23594, 'loss/train': 1.4765241146087646}
+08/30/2021 17:25:39 - INFO - __main__ - Step 23596: {'lr': 0.000474190795522772, 'samples': 4530432, 'steps': 23595, 'loss/train': 2.1187362670898438}
+08/30/2021 17:25:40 - INFO - __main__ - Step 23597: {'lr': 0.00047418844718065433, 'samples': 4530624, 'steps': 23596, 'loss/train': 0.4812004864215851}
+08/30/2021 17:25:41 - INFO - __main__ - Step 23598: {'lr': 0.0004741860987375209, 'samples': 4530816, 'steps': 23597, 'loss/train': 1.5386368036270142}
+08/30/2021 17:25:41 - INFO - __main__ - Step 23599: {'lr': 0.00047418375019337263, 'samples': 4531008, 'steps': 23598, 'loss/train': 1.9456770420074463}
+08/30/2021 17:25:41 - INFO - __main__ - Step 23600: {'lr': 0.00047418140154821065, 'samples': 4531200, 'steps': 23599, 'loss/train': 1.0276881456375122}
+08/30/2021 17:25:42 - INFO - __main__ - Step 23601: {'lr': 0.00047417905280203594, 'samples': 4531392, 'steps': 23600, 'loss/train': 1.151970624923706}
+08/30/2021 17:25:43 - INFO - __main__ - Step 23602: {'lr': 0.00047417670395484963, 'samples': 4531584, 'steps': 23601, 'loss/train': 1.806605339050293}
+08/30/2021 17:25:44 - INFO - __main__ - Step 23603: {'lr': 0.0004741743550066527, 'samples': 4531776, 'steps': 23602, 'loss/train': 1.379116415977478}
+08/30/2021 17:25:44 - INFO - __main__ - Step 23604: {'lr': 0.00047417200595744637, 'samples': 4531968, 'steps': 23603, 'loss/train': 1.7826013565063477}
+08/30/2021 17:25:44 - INFO - __main__ - Step 23605: {'lr': 0.0004741696568072316, 'samples': 4532160, 'steps': 23604, 'loss/train': 1.6874490976333618}
+08/30/2021 17:25:45 - INFO - __main__ - Step 23606: {'lr': 0.00047416730755600936, 'samples': 4532352, 'steps': 23605, 'loss/train': 1.602535605430603}
+08/30/2021 17:25:46 - INFO - __main__ - Step 23607: {'lr': 0.0004741649582037808, 'samples': 4532544, 'steps': 23606, 'loss/train': 3.4111196994781494}
+08/30/2021 17:25:47 - INFO - __main__ - Step 23608: {'lr': 0.000474162608750547, 'samples': 4532736, 'steps': 23607, 'loss/train': 1.413873314857483}
+08/30/2021 17:25:47 - INFO - __main__ - Step 23609: {'lr': 0.000474160259196309, 'samples': 4532928, 'steps': 23608, 'loss/train': 1.287006139755249}
+08/30/2021 17:25:48 - INFO - __main__ - Step 23610: {'lr': 0.0004741579095410678, 'samples': 4533120, 'steps': 23609, 'loss/train': 2.030071496963501}
+08/30/2021 17:25:48 - INFO - __main__ - Step 23611: {'lr': 0.0004741555597848245, 'samples': 4533312, 'steps': 23610, 'loss/train': 2.079184055328369}
+08/30/2021 17:25:50 - INFO - __main__ - Step 23612: {'lr': 0.00047415320992758025, 'samples': 4533504, 'steps': 23611, 'loss/train': 2.58381724357605}
+08/30/2021 17:25:50 - INFO - __main__ - Step 23613: {'lr': 0.00047415085996933593, 'samples': 4533696, 'steps': 23612, 'loss/train': 1.6858973503112793}
+08/30/2021 17:25:50 - INFO - __main__ - Step 23614: {'lr': 0.00047414850991009275, 'samples': 4533888, 'steps': 23613, 'loss/train': 1.6573758125305176}
+08/30/2021 17:25:51 - INFO - __main__ - Step 23615: {'lr': 0.00047414615974985164, 'samples': 4534080, 'steps': 23614, 'loss/train': 1.5540821552276611}
+08/30/2021 17:25:51 - INFO - __main__ - Step 23616: {'lr': 0.0004741438094886138, 'samples': 4534272, 'steps': 23615, 'loss/train': 1.774855375289917}
+08/30/2021 17:25:51 - INFO - __main__ - Step 23617: {'lr': 0.00047414145912638017, 'samples': 4534464, 'steps': 23616, 'loss/train': 1.572225570678711}
+08/30/2021 17:25:53 - INFO - __main__ - Step 23618: {'lr': 0.00047413910866315193, 'samples': 4534656, 'steps': 23617, 'loss/train': 1.414900541305542}
+08/30/2021 17:25:53 - INFO - __main__ - Step 23619: {'lr': 0.00047413675809893, 'samples': 4534848, 'steps': 23618, 'loss/train': 1.2714629173278809}
+08/30/2021 17:25:54 - INFO - __main__ - Step 23620: {'lr': 0.0004741344074337155, 'samples': 4535040, 'steps': 23619, 'loss/train': 1.5200704336166382}
+08/30/2021 17:25:54 - INFO - __main__ - Step 23621: {'lr': 0.00047413205666750955, 'samples': 4535232, 'steps': 23620, 'loss/train': 1.6622098684310913}
+08/30/2021 17:25:55 - INFO - __main__ - Step 23622: {'lr': 0.0004741297058003131, 'samples': 4535424, 'steps': 23621, 'loss/train': 2.0289008617401123}
+08/30/2021 17:25:56 - INFO - __main__ - Step 23623: {'lr': 0.00047412735483212725, 'samples': 4535616, 'steps': 23622, 'loss/train': 1.5492668151855469}
+08/30/2021 17:25:56 - INFO - __main__ - Step 23624: {'lr': 0.0004741250037629531, 'samples': 4535808, 'steps': 23623, 'loss/train': 1.347144603729248}
+08/30/2021 17:25:57 - INFO - __main__ - Step 23625: {'lr': 0.00047412265259279176, 'samples': 4536000, 'steps': 23624, 'loss/train': 1.609100103378296}
+08/30/2021 17:25:57 - INFO - __main__ - Step 23626: {'lr': 0.0004741203013216441, 'samples': 4536192, 'steps': 23625, 'loss/train': 1.5195554494857788}
+08/30/2021 17:25:57 - INFO - __main__ - Step 23627: {'lr': 0.0004741179499495113, 'samples': 4536384, 'steps': 23626, 'loss/train': 1.8828595876693726}
+08/30/2021 17:26:00 - INFO - __main__ - Step 23628: {'lr': 0.00047411559847639447, 'samples': 4536576, 'steps': 23627, 'loss/train': 1.3689078092575073}
+08/30/2021 17:26:00 - INFO - __main__ - Step 23629: {'lr': 0.0004741132469022946, 'samples': 4536768, 'steps': 23628, 'loss/train': 6.122838973999023}
+08/30/2021 17:26:01 - INFO - __main__ - Step 23630: {'lr': 0.00047411089522721275, 'samples': 4536960, 'steps': 23629, 'loss/train': 1.442733645439148}
+08/30/2021 17:26:01 - INFO - __main__ - Step 23631: {'lr': 0.00047410854345114996, 'samples': 4537152, 'steps': 23630, 'loss/train': 1.2228111028671265}
+08/30/2021 17:26:01 - INFO - __main__ - Step 23632: {'lr': 0.0004741061915741073, 'samples': 4537344, 'steps': 23631, 'loss/train': 2.2163054943084717}
+08/30/2021 17:26:02 - INFO - __main__ - Step 23633: {'lr': 0.0004741038395960859, 'samples': 4537536, 'steps': 23632, 'loss/train': 0.09782514721155167}
+08/30/2021 17:26:03 - INFO - __main__ - Step 23634: {'lr': 0.0004741014875170867, 'samples': 4537728, 'steps': 23633, 'loss/train': 2.023845672607422}
+08/30/2021 17:26:04 - INFO - __main__ - Step 23635: {'lr': 0.0004740991353371109, 'samples': 4537920, 'steps': 23634, 'loss/train': 1.860496163368225}
+08/30/2021 17:26:04 - INFO - __main__ - Step 23636: {'lr': 0.0004740967830561595, 'samples': 4538112, 'steps': 23635, 'loss/train': 1.764891505241394}
+08/30/2021 17:26:04 - INFO - __main__ - Step 23637: {'lr': 0.0004740944306742335, 'samples': 4538304, 'steps': 23636, 'loss/train': 1.920194387435913}
+08/30/2021 17:26:05 - INFO - __main__ - Step 23638: {'lr': 0.00047409207819133406, 'samples': 4538496, 'steps': 23637, 'loss/train': 1.4395520687103271}
+08/30/2021 17:26:06 - INFO - __main__ - Step 23639: {'lr': 0.0004740897256074621, 'samples': 4538688, 'steps': 23638, 'loss/train': 1.7058806419372559}
+08/30/2021 17:26:07 - INFO - __main__ - Step 23640: {'lr': 0.00047408737292261883, 'samples': 4538880, 'steps': 23639, 'loss/train': 1.8294278383255005}
+08/30/2021 17:26:07 - INFO - __main__ - Step 23641: {'lr': 0.0004740850201368052, 'samples': 4539072, 'steps': 23640, 'loss/train': 1.08510160446167}
+08/30/2021 17:26:07 - INFO - __main__ - Step 23642: {'lr': 0.00047408266725002234, 'samples': 4539264, 'steps': 23641, 'loss/train': 1.2237006425857544}
+08/30/2021 17:26:08 - INFO - __main__ - Step 23643: {'lr': 0.00047408031426227136, 'samples': 4539456, 'steps': 23642, 'loss/train': 1.8229749202728271}
+08/30/2021 17:26:09 - INFO - __main__ - Step 23644: {'lr': 0.0004740779611735532, 'samples': 4539648, 'steps': 23643, 'loss/train': 1.9241870641708374}
+08/30/2021 17:26:10 - INFO - __main__ - Step 23645: {'lr': 0.00047407560798386894, 'samples': 4539840, 'steps': 23644, 'loss/train': 1.0174429416656494}
+08/30/2021 17:26:10 - INFO - __main__ - Step 23646: {'lr': 0.00047407325469321973, 'samples': 4540032, 'steps': 23645, 'loss/train': 1.2745970487594604}
+08/30/2021 17:26:10 - INFO - __main__ - Step 23647: {'lr': 0.0004740709013016065, 'samples': 4540224, 'steps': 23646, 'loss/train': 1.042733073234558}
+08/30/2021 17:26:11 - INFO - __main__ - Step 23648: {'lr': 0.0004740685478090304, 'samples': 4540416, 'steps': 23647, 'loss/train': 1.7291159629821777}
+08/30/2021 17:26:13 - INFO - __main__ - Step 23649: {'lr': 0.00047406619421549247, 'samples': 4540608, 'steps': 23648, 'loss/train': 1.4979697465896606}
+08/30/2021 17:26:13 - INFO - __main__ - Step 23650: {'lr': 0.0004740638405209938, 'samples': 4540800, 'steps': 23649, 'loss/train': 1.1898342370986938}
+08/30/2021 17:26:13 - INFO - __main__ - Step 23651: {'lr': 0.0004740614867255353, 'samples': 4540992, 'steps': 23650, 'loss/train': 0.5996770858764648}
+08/30/2021 17:26:14 - INFO - __main__ - Step 23652: {'lr': 0.0004740591328291183, 'samples': 4541184, 'steps': 23651, 'loss/train': 1.409492015838623}
+08/30/2021 17:26:14 - INFO - __main__ - Step 23653: {'lr': 0.0004740567788317437, 'samples': 4541376, 'steps': 23652, 'loss/train': 1.5661993026733398}
+08/30/2021 17:26:14 - INFO - __main__ - Step 23654: {'lr': 0.00047405442473341246, 'samples': 4541568, 'steps': 23653, 'loss/train': 5.594666481018066}
+08/30/2021 17:26:15 - INFO - __main__ - Step 23655: {'lr': 0.0004740520705341259, 'samples': 4541760, 'steps': 23654, 'loss/train': 6.806138515472412}
+08/30/2021 17:26:16 - INFO - __main__ - Step 23656: {'lr': 0.0004740497162338848, 'samples': 4541952, 'steps': 23655, 'loss/train': 1.7770015001296997}
+08/30/2021 17:26:17 - INFO - __main__ - Step 23657: {'lr': 0.00047404736183269045, 'samples': 4542144, 'steps': 23656, 'loss/train': 1.4531251192092896}
+08/30/2021 17:26:17 - INFO - __main__ - Step 23658: {'lr': 0.0004740450073305438, 'samples': 4542336, 'steps': 23657, 'loss/train': 1.4769870042800903}
+08/30/2021 17:26:17 - INFO - __main__ - Step 23659: {'lr': 0.00047404265272744586, 'samples': 4542528, 'steps': 23658, 'loss/train': 1.9212251901626587}
+08/30/2021 17:26:18 - INFO - __main__ - Step 23660: {'lr': 0.0004740402980233978, 'samples': 4542720, 'steps': 23659, 'loss/train': 1.7518775463104248}
+08/30/2021 17:26:19 - INFO - __main__ - Step 23661: {'lr': 0.00047403794321840064, 'samples': 4542912, 'steps': 23660, 'loss/train': 2.1008946895599365}
+08/30/2021 17:26:20 - INFO - __main__ - Step 23662: {'lr': 0.0004740355883124555, 'samples': 4543104, 'steps': 23661, 'loss/train': 1.7716931104660034}
+08/30/2021 17:26:20 - INFO - __main__ - Step 23663: {'lr': 0.0004740332333055633, 'samples': 4543296, 'steps': 23662, 'loss/train': 1.3145335912704468}
+08/30/2021 17:26:20 - INFO - __main__ - Step 23664: {'lr': 0.00047403087819772517, 'samples': 4543488, 'steps': 23663, 'loss/train': 2.1947436332702637}
+08/30/2021 17:26:21 - INFO - __main__ - Step 23665: {'lr': 0.0004740285229889423, 'samples': 4543680, 'steps': 23664, 'loss/train': 1.6230443716049194}
+08/30/2021 17:26:22 - INFO - __main__ - Step 23666: {'lr': 0.0004740261676792155, 'samples': 4543872, 'steps': 23665, 'loss/train': 1.6724753379821777}
+08/30/2021 17:26:23 - INFO - __main__ - Step 23667: {'lr': 0.00047402381226854606, 'samples': 4544064, 'steps': 23666, 'loss/train': 1.950594186782837}
+08/30/2021 17:26:23 - INFO - __main__ - Step 23668: {'lr': 0.0004740214567569349, 'samples': 4544256, 'steps': 23667, 'loss/train': 1.1832435131072998}
+08/30/2021 17:26:23 - INFO - __main__ - Step 23669: {'lr': 0.00047401910114438313, 'samples': 4544448, 'steps': 23668, 'loss/train': 0.7969381809234619}
+08/30/2021 17:26:24 - INFO - __main__ - Step 23670: {'lr': 0.0004740167454308918, 'samples': 4544640, 'steps': 23669, 'loss/train': 1.410292148590088}
+08/30/2021 17:26:25 - INFO - __main__ - Step 23671: {'lr': 0.00047401438961646206, 'samples': 4544832, 'steps': 23670, 'loss/train': 1.860082983970642}
+08/30/2021 17:26:26 - INFO - __main__ - Step 23672: {'lr': 0.0004740120337010948, 'samples': 4545024, 'steps': 23671, 'loss/train': 1.6472742557525635}
+08/30/2021 17:26:26 - INFO - __main__ - Step 23673: {'lr': 0.0004740096776847912, 'samples': 4545216, 'steps': 23672, 'loss/train': 0.9796372056007385}
+08/30/2021 17:26:26 - INFO - __main__ - Step 23674: {'lr': 0.0004740073215675523, 'samples': 4545408, 'steps': 23673, 'loss/train': 1.9655559062957764}
+08/30/2021 17:26:27 - INFO - __main__ - Step 23675: {'lr': 0.00047400496534937914, 'samples': 4545600, 'steps': 23674, 'loss/train': 1.719420075416565}
+08/30/2021 17:26:27 - INFO - __main__ - Step 23676: {'lr': 0.00047400260903027283, 'samples': 4545792, 'steps': 23675, 'loss/train': 0.5504816770553589}
+08/30/2021 17:26:29 - INFO - __main__ - Step 23677: {'lr': 0.0004740002526102344, 'samples': 4545984, 'steps': 23676, 'loss/train': 0.38618308305740356}
+08/30/2021 17:26:29 - INFO - __main__ - Step 23678: {'lr': 0.0004739978960892649, 'samples': 4546176, 'steps': 23677, 'loss/train': 1.6172184944152832}
+08/30/2021 17:26:30 - INFO - __main__ - Step 23679: {'lr': 0.0004739955394673654, 'samples': 4546368, 'steps': 23678, 'loss/train': 1.553303837776184}
+08/30/2021 17:26:30 - INFO - __main__ - Step 23680: {'lr': 0.000473993182744537, 'samples': 4546560, 'steps': 23679, 'loss/train': 1.5233919620513916}
+08/30/2021 17:26:30 - INFO - __main__ - Step 23681: {'lr': 0.0004739908259207807, 'samples': 4546752, 'steps': 23680, 'loss/train': 0.3007315993309021}
+08/30/2021 17:26:32 - INFO - __main__ - Step 23682: {'lr': 0.00047398846899609755, 'samples': 4546944, 'steps': 23681, 'loss/train': 6.533685684204102}
+08/30/2021 17:26:33 - INFO - __main__ - Step 23683: {'lr': 0.0004739861119704887, 'samples': 4547136, 'steps': 23682, 'loss/train': 1.275080919265747}
+08/30/2021 17:26:33 - INFO - __main__ - Step 23684: {'lr': 0.00047398375484395517, 'samples': 4547328, 'steps': 23683, 'loss/train': 1.5425148010253906}
+08/30/2021 17:26:33 - INFO - __main__ - Step 23685: {'lr': 0.00047398139761649794, 'samples': 4547520, 'steps': 23684, 'loss/train': 1.7344295978546143}
+08/30/2021 17:26:34 - INFO - __main__ - Step 23686: {'lr': 0.00047397904028811824, 'samples': 4547712, 'steps': 23685, 'loss/train': 1.391536831855774}
+08/30/2021 17:26:34 - INFO - __main__ - Step 23687: {'lr': 0.000473976682858817, 'samples': 4547904, 'steps': 23686, 'loss/train': 2.121718645095825}
+08/30/2021 17:26:36 - INFO - __main__ - Step 23688: {'lr': 0.00047397432532859533, 'samples': 4548096, 'steps': 23687, 'loss/train': 1.1281750202178955}
+08/30/2021 17:26:36 - INFO - __main__ - Step 23689: {'lr': 0.00047397196769745435, 'samples': 4548288, 'steps': 23688, 'loss/train': 1.6202231645584106}
+08/30/2021 17:26:36 - INFO - __main__ - Step 23690: {'lr': 0.00047396960996539495, 'samples': 4548480, 'steps': 23689, 'loss/train': 1.5830765962600708}
+08/30/2021 17:26:37 - INFO - __main__ - Step 23691: {'lr': 0.00047396725213241835, 'samples': 4548672, 'steps': 23690, 'loss/train': 1.1786617040634155}
+08/30/2021 17:26:37 - INFO - __main__ - Step 23692: {'lr': 0.0004739648941985256, 'samples': 4548864, 'steps': 23691, 'loss/train': 1.6706563234329224}
+08/30/2021 17:26:38 - INFO - __main__ - Step 23693: {'lr': 0.00047396253616371767, 'samples': 4549056, 'steps': 23692, 'loss/train': 1.6007726192474365}
+08/30/2021 17:26:39 - INFO - __main__ - Step 23694: {'lr': 0.00047396017802799566, 'samples': 4549248, 'steps': 23693, 'loss/train': 1.8842920064926147}
+08/30/2021 17:26:39 - INFO - __main__ - Step 23695: {'lr': 0.0004739578197913607, 'samples': 4549440, 'steps': 23694, 'loss/train': 1.7273802757263184}
+08/30/2021 17:26:40 - INFO - __main__ - Step 23696: {'lr': 0.00047395546145381377, 'samples': 4549632, 'steps': 23695, 'loss/train': 1.6088329553604126}
+08/30/2021 17:26:40 - INFO - __main__ - Step 23697: {'lr': 0.000473953103015356, 'samples': 4549824, 'steps': 23696, 'loss/train': 2.488471508026123}
+08/30/2021 17:26:41 - INFO - __main__ - Step 23698: {'lr': 0.0004739507444759884, 'samples': 4550016, 'steps': 23697, 'loss/train': 1.784038782119751}
+08/30/2021 17:26:42 - INFO - __main__ - Step 23699: {'lr': 0.0004739483858357121, 'samples': 4550208, 'steps': 23698, 'loss/train': 1.3716033697128296}
+08/30/2021 17:26:42 - INFO - __main__ - Step 23700: {'lr': 0.00047394602709452806, 'samples': 4550400, 'steps': 23699, 'loss/train': 1.6060470342636108}
+08/30/2021 17:26:43 - INFO - __main__ - Step 23701: {'lr': 0.0004739436682524373, 'samples': 4550592, 'steps': 23700, 'loss/train': 1.7302641868591309}
+08/30/2021 17:26:43 - INFO - __main__ - Step 23702: {'lr': 0.00047394130930944115, 'samples': 4550784, 'steps': 23701, 'loss/train': 1.2669318914413452}
+08/30/2021 17:26:45 - INFO - __main__ - Step 23703: {'lr': 0.0004739389502655404, 'samples': 4550976, 'steps': 23702, 'loss/train': 1.8177402019500732}
+08/30/2021 17:26:45 - INFO - __main__ - Step 23704: {'lr': 0.0004739365911207363, 'samples': 4551168, 'steps': 23703, 'loss/train': 1.7356849908828735}
+08/30/2021 17:26:45 - INFO - __main__ - Step 23705: {'lr': 0.0004739342318750297, 'samples': 4551360, 'steps': 23704, 'loss/train': 2.165408134460449}
+08/30/2021 17:26:46 - INFO - __main__ - Step 23706: {'lr': 0.00047393187252842183, 'samples': 4551552, 'steps': 23705, 'loss/train': 1.984107255935669}
+08/30/2021 17:26:46 - INFO - __main__ - Step 23707: {'lr': 0.0004739295130809138, 'samples': 4551744, 'steps': 23706, 'loss/train': 1.9873802661895752}
+08/30/2021 17:26:47 - INFO - __main__ - Step 23708: {'lr': 0.0004739271535325065, 'samples': 4551936, 'steps': 23707, 'loss/train': 1.2757214307785034}
+08/30/2021 17:26:48 - INFO - __main__ - Step 23709: {'lr': 0.00047392479388320106, 'samples': 4552128, 'steps': 23708, 'loss/train': 1.105953574180603}
+08/30/2021 17:26:48 - INFO - __main__ - Step 23710: {'lr': 0.0004739224341329987, 'samples': 4552320, 'steps': 23709, 'loss/train': 1.5607233047485352}
+08/30/2021 17:26:49 - INFO - __main__ - Step 23711: {'lr': 0.0004739200742819002, 'samples': 4552512, 'steps': 23710, 'loss/train': 2.1628360748291016}
+08/30/2021 17:26:49 - INFO - __main__ - Step 23712: {'lr': 0.0004739177143299068, 'samples': 4552704, 'steps': 23711, 'loss/train': 1.4729646444320679}
+08/30/2021 17:26:49 - INFO - __main__ - Step 23713: {'lr': 0.00047391535427701966, 'samples': 4552896, 'steps': 23712, 'loss/train': 1.4183703660964966}
+08/30/2021 17:26:51 - INFO - __main__ - Step 23714: {'lr': 0.0004739129941232396, 'samples': 4553088, 'steps': 23713, 'loss/train': 1.4096698760986328}
+08/30/2021 17:26:51 - INFO - __main__ - Step 23715: {'lr': 0.0004739106338685678, 'samples': 4553280, 'steps': 23714, 'loss/train': 1.3374930620193481}
+08/30/2021 17:26:52 - INFO - __main__ - Step 23716: {'lr': 0.00047390827351300537, 'samples': 4553472, 'steps': 23715, 'loss/train': 1.6537529230117798}
+08/30/2021 17:26:52 - INFO - __main__ - Step 23717: {'lr': 0.00047390591305655327, 'samples': 4553664, 'steps': 23716, 'loss/train': 1.4693373441696167}
+08/30/2021 17:26:52 - INFO - __main__ - Step 23718: {'lr': 0.0004739035524992127, 'samples': 4553856, 'steps': 23717, 'loss/train': 1.6239254474639893}
+08/30/2021 17:26:54 - INFO - __main__ - Step 23719: {'lr': 0.00047390119184098455, 'samples': 4554048, 'steps': 23718, 'loss/train': 1.8840086460113525}
+08/30/2021 17:26:55 - INFO - __main__ - Step 23720: {'lr': 0.00047389883108187004, 'samples': 4554240, 'steps': 23719, 'loss/train': 0.38106250762939453}
+08/30/2021 17:26:55 - INFO - __main__ - Step 23721: {'lr': 0.00047389647022187014, 'samples': 4554432, 'steps': 23720, 'loss/train': 1.8415324687957764}
+08/30/2021 17:26:55 - INFO - __main__ - Step 23722: {'lr': 0.000473894109260986, 'samples': 4554624, 'steps': 23721, 'loss/train': 1.9239407777786255}
+08/30/2021 17:26:56 - INFO - __main__ - Step 23723: {'lr': 0.00047389174819921856, 'samples': 4554816, 'steps': 23722, 'loss/train': 0.0727807879447937}
+08/30/2021 17:26:56 - INFO - __main__ - Step 23724: {'lr': 0.000473889387036569, 'samples': 4555008, 'steps': 23723, 'loss/train': 1.2444167137145996}
+08/30/2021 17:26:57 - INFO - __main__ - Step 23725: {'lr': 0.0004738870257730383, 'samples': 4555200, 'steps': 23724, 'loss/train': 1.8511418104171753}
+08/30/2021 17:26:58 - INFO - __main__ - Step 23726: {'lr': 0.00047388466440862755, 'samples': 4555392, 'steps': 23725, 'loss/train': 1.8768689632415771}
+08/30/2021 17:26:58 - INFO - __main__ - Step 23727: {'lr': 0.0004738823029433379, 'samples': 4555584, 'steps': 23726, 'loss/train': 1.9509973526000977}
+08/30/2021 17:26:59 - INFO - __main__ - Step 23728: {'lr': 0.0004738799413771703, 'samples': 4555776, 'steps': 23727, 'loss/train': 1.3229200839996338}
+08/30/2021 17:26:59 - INFO - __main__ - Step 23729: {'lr': 0.0004738775797101258, 'samples': 4555968, 'steps': 23728, 'loss/train': 1.505495548248291}
+08/30/2021 17:27:01 - INFO - __main__ - Step 23730: {'lr': 0.0004738752179422056, 'samples': 4556160, 'steps': 23729, 'loss/train': 1.695680022239685}
+08/30/2021 17:27:01 - INFO - __main__ - Step 23731: {'lr': 0.00047387285607341064, 'samples': 4556352, 'steps': 23730, 'loss/train': 1.7703814506530762}
+08/30/2021 17:27:01 - INFO - __main__ - Step 23732: {'lr': 0.00047387049410374207, 'samples': 4556544, 'steps': 23731, 'loss/train': 1.450698971748352}
+08/30/2021 17:27:02 - INFO - __main__ - Step 23733: {'lr': 0.00047386813203320084, 'samples': 4556736, 'steps': 23732, 'loss/train': 1.589904546737671}
+08/30/2021 17:27:02 - INFO - __main__ - Step 23734: {'lr': 0.0004738657698617881, 'samples': 4556928, 'steps': 23733, 'loss/train': 1.4130483865737915}
+08/30/2021 17:27:05 - INFO - __main__ - Step 23735: {'lr': 0.00047386340758950494, 'samples': 4557120, 'steps': 23734, 'loss/train': 1.88881254196167}
+08/30/2021 17:27:05 - INFO - __main__ - Step 23736: {'lr': 0.0004738610452163523, 'samples': 4557312, 'steps': 23735, 'loss/train': 2.1662113666534424}
+08/30/2021 17:27:05 - INFO - __main__ - Step 23737: {'lr': 0.00047385868274233144, 'samples': 4557504, 'steps': 23736, 'loss/train': 2.7109947204589844}
+08/30/2021 17:27:06 - INFO - __main__ - Step 23738: {'lr': 0.0004738563201674432, 'samples': 4557696, 'steps': 23737, 'loss/train': 1.4272804260253906}
+08/30/2021 17:27:06 - INFO - __main__ - Step 23739: {'lr': 0.00047385395749168885, 'samples': 4557888, 'steps': 23738, 'loss/train': 1.6467515230178833}
+08/30/2021 17:27:06 - INFO - __main__ - Step 23740: {'lr': 0.00047385159471506936, 'samples': 4558080, 'steps': 23739, 'loss/train': 1.569273829460144}
+08/30/2021 17:27:08 - INFO - __main__ - Step 23741: {'lr': 0.00047384923183758573, 'samples': 4558272, 'steps': 23740, 'loss/train': 0.1312096118927002}
+08/30/2021 17:27:09 - INFO - __main__ - Step 23742: {'lr': 0.0004738468688592391, 'samples': 4558464, 'steps': 23741, 'loss/train': 1.763966679573059}
+08/30/2021 17:27:09 - INFO - __main__ - Step 23743: {'lr': 0.00047384450578003055, 'samples': 4558656, 'steps': 23742, 'loss/train': 1.6272128820419312}
+08/30/2021 17:27:09 - INFO - __main__ - Step 23744: {'lr': 0.00047384214259996117, 'samples': 4558848, 'steps': 23743, 'loss/train': 1.6774150133132935}
+08/30/2021 17:27:10 - INFO - __main__ - Step 23745: {'lr': 0.0004738397793190319, 'samples': 4559040, 'steps': 23744, 'loss/train': 1.3481712341308594}
+08/30/2021 17:27:11 - INFO - __main__ - Step 23746: {'lr': 0.00047383741593724386, 'samples': 4559232, 'steps': 23745, 'loss/train': 1.5829099416732788}
+08/30/2021 17:27:12 - INFO - __main__ - Step 23747: {'lr': 0.0004738350524545982, 'samples': 4559424, 'steps': 23746, 'loss/train': 1.2665964365005493}
+08/30/2021 17:27:12 - INFO - __main__ - Step 23748: {'lr': 0.0004738326888710959, 'samples': 4559616, 'steps': 23747, 'loss/train': 1.731207013130188}
+08/30/2021 17:27:12 - INFO - __main__ - Step 23749: {'lr': 0.000473830325186738, 'samples': 4559808, 'steps': 23748, 'loss/train': 1.6543854475021362}
+08/30/2021 17:27:13 - INFO - __main__ - Step 23750: {'lr': 0.0004738279614015257, 'samples': 4560000, 'steps': 23749, 'loss/train': 1.592079758644104}
+08/30/2021 17:27:15 - INFO - __main__ - Step 23751: {'lr': 0.0004738255975154599, 'samples': 4560192, 'steps': 23750, 'loss/train': 1.4464178085327148}
+08/30/2021 17:27:15 - INFO - __main__ - Step 23752: {'lr': 0.0004738232335285417, 'samples': 4560384, 'steps': 23751, 'loss/train': 1.5318843126296997}
+08/30/2021 17:27:16 - INFO - __main__ - Step 23753: {'lr': 0.0004738208694407723, 'samples': 4560576, 'steps': 23752, 'loss/train': 1.4185625314712524}
+08/30/2021 17:27:16 - INFO - __main__ - Step 23754: {'lr': 0.00047381850525215265, 'samples': 4560768, 'steps': 23753, 'loss/train': 0.732387363910675}
+08/30/2021 17:27:16 - INFO - __main__ - Step 23755: {'lr': 0.0004738161409626838, 'samples': 4560960, 'steps': 23754, 'loss/train': 0.6555193066596985}
+08/30/2021 17:27:18 - INFO - __main__ - Step 23756: {'lr': 0.0004738137765723669, 'samples': 4561152, 'steps': 23755, 'loss/train': 1.698353886604309}
+08/30/2021 17:27:18 - INFO - __main__ - Step 23757: {'lr': 0.0004738114120812029, 'samples': 4561344, 'steps': 23756, 'loss/train': 1.4144833087921143}
+08/30/2021 17:27:19 - INFO - __main__ - Step 23758: {'lr': 0.000473809047489193, 'samples': 4561536, 'steps': 23757, 'loss/train': 1.623138189315796}
+08/30/2021 17:27:19 - INFO - __main__ - Step 23759: {'lr': 0.00047380668279633814, 'samples': 4561728, 'steps': 23758, 'loss/train': 1.5347778797149658}
+08/30/2021 17:27:19 - INFO - __main__ - Step 23760: {'lr': 0.00047380431800263945, 'samples': 4561920, 'steps': 23759, 'loss/train': 1.3153525590896606}
+08/30/2021 17:27:20 - INFO - __main__ - Step 23761: {'lr': 0.000473801953108098, 'samples': 4562112, 'steps': 23760, 'loss/train': 1.927691102027893}
+08/30/2021 17:27:21 - INFO - __main__ - Step 23762: {'lr': 0.0004737995881127149, 'samples': 4562304, 'steps': 23761, 'loss/train': 1.7205820083618164}
+08/30/2021 17:27:22 - INFO - __main__ - Step 23763: {'lr': 0.0004737972230164911, 'samples': 4562496, 'steps': 23762, 'loss/train': 1.9505927562713623}
+08/30/2021 17:27:22 - INFO - __main__ - Step 23764: {'lr': 0.0004737948578194278, 'samples': 4562688, 'steps': 23763, 'loss/train': 1.2602747678756714}
+08/30/2021 17:27:22 - INFO - __main__ - Step 23765: {'lr': 0.00047379249252152585, 'samples': 4562880, 'steps': 23764, 'loss/train': 1.6362367868423462}
+08/30/2021 17:27:23 - INFO - __main__ - Step 23766: {'lr': 0.00047379012712278656, 'samples': 4563072, 'steps': 23765, 'loss/train': 1.6800568103790283}
+08/30/2021 17:27:24 - INFO - __main__ - Step 23767: {'lr': 0.0004737877616232108, 'samples': 4563264, 'steps': 23766, 'loss/train': 0.21542313694953918}
+08/30/2021 17:27:25 - INFO - __main__ - Step 23768: {'lr': 0.0004737853960227998, 'samples': 4563456, 'steps': 23767, 'loss/train': 1.5183273553848267}
+08/30/2021 17:27:25 - INFO - __main__ - Step 23769: {'lr': 0.00047378303032155454, 'samples': 4563648, 'steps': 23768, 'loss/train': 0.9760209918022156}
+08/30/2021 17:27:25 - INFO - __main__ - Step 23770: {'lr': 0.0004737806645194761, 'samples': 4563840, 'steps': 23769, 'loss/train': 1.4840788841247559}
+08/30/2021 17:27:26 - INFO - __main__ - Step 23771: {'lr': 0.00047377829861656556, 'samples': 4564032, 'steps': 23770, 'loss/train': 1.7820886373519897}
+08/30/2021 17:27:27 - INFO - __main__ - Step 23772: {'lr': 0.000473775932612824, 'samples': 4564224, 'steps': 23771, 'loss/train': 2.6842691898345947}
+08/30/2021 17:27:28 - INFO - __main__ - Step 23773: {'lr': 0.00047377356650825245, 'samples': 4564416, 'steps': 23772, 'loss/train': 1.359667420387268}
+08/30/2021 17:27:28 - INFO - __main__ - Step 23774: {'lr': 0.00047377120030285194, 'samples': 4564608, 'steps': 23773, 'loss/train': 1.8385834693908691}
+08/30/2021 17:27:29 - INFO - __main__ - Step 23775: {'lr': 0.0004737688339966235, 'samples': 4564800, 'steps': 23774, 'loss/train': 2.1206347942352295}
+08/30/2021 17:27:29 - INFO - __main__ - Step 23776: {'lr': 0.00047376646758956844, 'samples': 4564992, 'steps': 23775, 'loss/train': 2.2828104496002197}
+08/30/2021 17:27:31 - INFO - __main__ - Step 23777: {'lr': 0.00047376410108168756, 'samples': 4565184, 'steps': 23776, 'loss/train': 1.7378520965576172}
+08/30/2021 17:27:31 - INFO - __main__ - Step 23778: {'lr': 0.0004737617344729821, 'samples': 4565376, 'steps': 23777, 'loss/train': 1.6882611513137817}
+08/30/2021 17:27:31 - INFO - __main__ - Step 23779: {'lr': 0.00047375936776345297, 'samples': 4565568, 'steps': 23778, 'loss/train': 1.908403754234314}
+08/30/2021 17:27:32 - INFO - __main__ - Step 23780: {'lr': 0.00047375700095310136, 'samples': 4565760, 'steps': 23779, 'loss/train': 1.5699435472488403}
+08/30/2021 17:27:32 - INFO - __main__ - Step 23781: {'lr': 0.0004737546340419283, 'samples': 4565952, 'steps': 23780, 'loss/train': 1.626193881034851}
+08/30/2021 17:27:34 - INFO - __main__ - Step 23782: {'lr': 0.0004737522670299349, 'samples': 4566144, 'steps': 23781, 'loss/train': 1.1423419713974}
+08/30/2021 17:27:34 - INFO - __main__ - Step 23783: {'lr': 0.00047374989991712214, 'samples': 4566336, 'steps': 23782, 'loss/train': 1.3004885911941528}
+08/30/2021 17:27:34 - INFO - __main__ - Step 23784: {'lr': 0.00047374753270349113, 'samples': 4566528, 'steps': 23783, 'loss/train': 0.8821494579315186}
+08/30/2021 17:27:35 - INFO - __main__ - Step 23785: {'lr': 0.00047374516538904287, 'samples': 4566720, 'steps': 23784, 'loss/train': 1.9171324968338013}
+08/30/2021 17:27:35 - INFO - __main__ - Step 23786: {'lr': 0.0004737427979737786, 'samples': 4566912, 'steps': 23785, 'loss/train': 0.9794736504554749}
+08/30/2021 17:27:35 - INFO - __main__ - Step 23787: {'lr': 0.0004737404304576992, 'samples': 4567104, 'steps': 23786, 'loss/train': 1.1728854179382324}
+08/30/2021 17:27:37 - INFO - __main__ - Step 23788: {'lr': 0.0004737380628408059, 'samples': 4567296, 'steps': 23787, 'loss/train': 1.5640099048614502}
+08/30/2021 17:27:37 - INFO - __main__ - Step 23789: {'lr': 0.00047373569512309963, 'samples': 4567488, 'steps': 23788, 'loss/train': 1.8454991579055786}
+08/30/2021 17:27:38 - INFO - __main__ - Step 23790: {'lr': 0.0004737333273045815, 'samples': 4567680, 'steps': 23789, 'loss/train': 1.1946204900741577}
+08/30/2021 17:27:38 - INFO - __main__ - Step 23791: {'lr': 0.00047373095938525256, 'samples': 4567872, 'steps': 23790, 'loss/train': 1.8148601055145264}
+08/30/2021 17:27:38 - INFO - __main__ - Step 23792: {'lr': 0.0004737285913651139, 'samples': 4568064, 'steps': 23791, 'loss/train': 1.5275744199752808}
+08/30/2021 17:27:40 - INFO - __main__ - Step 23793: {'lr': 0.0004737262232441667, 'samples': 4568256, 'steps': 23792, 'loss/train': 1.3972017765045166}
+08/30/2021 17:27:41 - INFO - __main__ - Step 23794: {'lr': 0.00047372385502241176, 'samples': 4568448, 'steps': 23793, 'loss/train': 2.057589054107666}
+08/30/2021 17:27:41 - INFO - __main__ - Step 23795: {'lr': 0.0004737214866998504, 'samples': 4568640, 'steps': 23794, 'loss/train': 1.5424411296844482}
+08/30/2021 17:27:42 - INFO - __main__ - Step 23796: {'lr': 0.0004737191182764836, 'samples': 4568832, 'steps': 23795, 'loss/train': 0.7936122417449951}
+08/30/2021 17:27:42 - INFO - __main__ - Step 23797: {'lr': 0.0004737167497523124, 'samples': 4569024, 'steps': 23796, 'loss/train': 1.339007019996643}
+08/30/2021 17:27:44 - INFO - __main__ - Step 23798: {'lr': 0.0004737143811273379, 'samples': 4569216, 'steps': 23797, 'loss/train': 1.971666693687439}
+08/30/2021 17:27:44 - INFO - __main__ - Step 23799: {'lr': 0.0004737120124015611, 'samples': 4569408, 'steps': 23798, 'loss/train': 1.2081353664398193}
+08/30/2021 17:27:44 - INFO - __main__ - Step 23800: {'lr': 0.00047370964357498313, 'samples': 4569600, 'steps': 23799, 'loss/train': 1.5187081098556519}
+08/30/2021 17:27:45 - INFO - __main__ - Step 23801: {'lr': 0.0004737072746476051, 'samples': 4569792, 'steps': 23800, 'loss/train': 2.2719743251800537}
+08/30/2021 17:27:45 - INFO - __main__ - Step 23802: {'lr': 0.00047370490561942795, 'samples': 4569984, 'steps': 23801, 'loss/train': 1.1148394346237183}
+08/30/2021 17:27:45 - INFO - __main__ - Step 23803: {'lr': 0.00047370253649045286, 'samples': 4570176, 'steps': 23802, 'loss/train': 0.7776064872741699}
+08/30/2021 17:27:47 - INFO - __main__ - Step 23804: {'lr': 0.00047370016726068086, 'samples': 4570368, 'steps': 23803, 'loss/train': 1.7910127639770508}
+08/30/2021 17:27:47 - INFO - __main__ - Step 23805: {'lr': 0.000473697797930113, 'samples': 4570560, 'steps': 23804, 'loss/train': 1.3740880489349365}
+08/30/2021 17:27:48 - INFO - __main__ - Step 23806: {'lr': 0.00047369542849875037, 'samples': 4570752, 'steps': 23805, 'loss/train': 0.9818909764289856}
+08/30/2021 17:27:48 - INFO - __main__ - Step 23807: {'lr': 0.0004736930589665941, 'samples': 4570944, 'steps': 23806, 'loss/train': 1.7987041473388672}
+08/30/2021 17:27:48 - INFO - __main__ - Step 23808: {'lr': 0.0004736906893336451, 'samples': 4571136, 'steps': 23807, 'loss/train': 1.6192020177841187}
+08/30/2021 17:27:50 - INFO - __main__ - Step 23809: {'lr': 0.00047368831959990453, 'samples': 4571328, 'steps': 23808, 'loss/train': 1.2590991258621216}
+08/30/2021 17:27:51 - INFO - __main__ - Step 23810: {'lr': 0.0004736859497653735, 'samples': 4571520, 'steps': 23809, 'loss/train': 1.176614761352539}
+08/30/2021 17:27:51 - INFO - __main__ - Step 23811: {'lr': 0.0004736835798300531, 'samples': 4571712, 'steps': 23810, 'loss/train': 1.0427967309951782}
+08/30/2021 17:27:52 - INFO - __main__ - Step 23812: {'lr': 0.00047368120979394415, 'samples': 4571904, 'steps': 23811, 'loss/train': 1.492321252822876}
+08/30/2021 17:27:52 - INFO - __main__ - Step 23813: {'lr': 0.000473678839657048, 'samples': 4572096, 'steps': 23812, 'loss/train': 1.3117263317108154}
+08/30/2021 17:27:52 - INFO - __main__ - Step 23814: {'lr': 0.0004736764694193656, 'samples': 4572288, 'steps': 23813, 'loss/train': 0.9067861437797546}
+08/30/2021 17:27:54 - INFO - __main__ - Step 23815: {'lr': 0.0004736740990808981, 'samples': 4572480, 'steps': 23814, 'loss/train': 2.07078218460083}
+08/30/2021 17:27:54 - INFO - __main__ - Step 23816: {'lr': 0.0004736717286416464, 'samples': 4572672, 'steps': 23815, 'loss/train': 1.5327759981155396}
+08/30/2021 17:27:54 - INFO - __main__ - Step 23817: {'lr': 0.0004736693581016117, 'samples': 4572864, 'steps': 23816, 'loss/train': 1.7998594045639038}
+08/30/2021 17:27:55 - INFO - __main__ - Step 23818: {'lr': 0.00047366698746079507, 'samples': 4573056, 'steps': 23817, 'loss/train': 1.7322137355804443}
+08/30/2021 17:27:55 - INFO - __main__ - Step 23819: {'lr': 0.0004736646167191975, 'samples': 4573248, 'steps': 23818, 'loss/train': 1.8632237911224365}
+08/30/2021 17:27:57 - INFO - __main__ - Step 23820: {'lr': 0.00047366224587682017, 'samples': 4573440, 'steps': 23819, 'loss/train': 1.5942620038986206}
+08/30/2021 17:27:57 - INFO - __main__ - Step 23821: {'lr': 0.000473659874933664, 'samples': 4573632, 'steps': 23820, 'loss/train': 1.4017938375473022}
+08/30/2021 17:27:57 - INFO - __main__ - Step 23822: {'lr': 0.0004736575038897303, 'samples': 4573824, 'steps': 23821, 'loss/train': 1.2695995569229126}
+08/30/2021 17:27:58 - INFO - __main__ - Step 23823: {'lr': 0.0004736551327450198, 'samples': 4574016, 'steps': 23822, 'loss/train': 1.5489740371704102}
+08/30/2021 17:27:58 - INFO - __main__ - Step 23824: {'lr': 0.00047365276149953387, 'samples': 4574208, 'steps': 23823, 'loss/train': 1.4475749731063843}
+08/30/2021 17:28:00 - INFO - __main__ - Step 23825: {'lr': 0.0004736503901532734, 'samples': 4574400, 'steps': 23824, 'loss/train': 1.526062250137329}
+08/30/2021 17:28:00 - INFO - __main__ - Step 23826: {'lr': 0.00047364801870623954, 'samples': 4574592, 'steps': 23825, 'loss/train': 1.7532002925872803}
+08/30/2021 17:28:00 - INFO - __main__ - Step 23827: {'lr': 0.00047364564715843326, 'samples': 4574784, 'steps': 23826, 'loss/train': 1.91557776927948}
+08/30/2021 17:28:01 - INFO - __main__ - Step 23828: {'lr': 0.00047364327550985575, 'samples': 4574976, 'steps': 23827, 'loss/train': 2.0333333015441895}
+08/30/2021 17:28:01 - INFO - __main__ - Step 23829: {'lr': 0.00047364090376050805, 'samples': 4575168, 'steps': 23828, 'loss/train': 1.6888744831085205}
+08/30/2021 17:28:03 - INFO - __main__ - Step 23830: {'lr': 0.0004736385319103912, 'samples': 4575360, 'steps': 23829, 'loss/train': 1.4075181484222412}
+08/30/2021 17:28:03 - INFO - __main__ - Step 23831: {'lr': 0.00047363615995950624, 'samples': 4575552, 'steps': 23830, 'loss/train': 1.7036877870559692}
+08/30/2021 17:28:03 - INFO - __main__ - Step 23832: {'lr': 0.0004736337879078544, 'samples': 4575744, 'steps': 23831, 'loss/train': 1.2392202615737915}
+08/30/2021 17:28:04 - INFO - __main__ - Step 23833: {'lr': 0.0004736314157554365, 'samples': 4575936, 'steps': 23832, 'loss/train': 1.7700579166412354}
+08/30/2021 17:28:04 - INFO - __main__ - Step 23834: {'lr': 0.00047362904350225376, 'samples': 4576128, 'steps': 23833, 'loss/train': 0.9120385646820068}
+08/30/2021 17:28:06 - INFO - __main__ - Step 23835: {'lr': 0.0004736266711483073, 'samples': 4576320, 'steps': 23834, 'loss/train': 0.18678513169288635}
+08/30/2021 17:28:06 - INFO - __main__ - Step 23836: {'lr': 0.00047362429869359803, 'samples': 4576512, 'steps': 23835, 'loss/train': 1.412263035774231}
+08/30/2021 17:28:07 - INFO - __main__ - Step 23837: {'lr': 0.0004736219261381271, 'samples': 4576704, 'steps': 23836, 'loss/train': 1.8080602884292603}
+08/30/2021 17:28:07 - INFO - __main__ - Step 23838: {'lr': 0.0004736195534818956, 'samples': 4576896, 'steps': 23837, 'loss/train': 0.12009059637784958}
+08/30/2021 17:28:07 - INFO - __main__ - Step 23839: {'lr': 0.00047361718072490457, 'samples': 4577088, 'steps': 23838, 'loss/train': 1.80378258228302}
+08/30/2021 17:28:09 - INFO - __main__ - Step 23840: {'lr': 0.00047361480786715514, 'samples': 4577280, 'steps': 23839, 'loss/train': 1.8580217361450195}
+08/30/2021 17:28:10 - INFO - __main__ - Step 23841: {'lr': 0.00047361243490864826, 'samples': 4577472, 'steps': 23840, 'loss/train': 1.0173853635787964}
+08/30/2021 17:28:10 - INFO - __main__ - Step 23842: {'lr': 0.00047361006184938517, 'samples': 4577664, 'steps': 23841, 'loss/train': 1.4172651767730713}
+08/30/2021 17:28:10 - INFO - __main__ - Step 23843: {'lr': 0.00047360768868936673, 'samples': 4577856, 'steps': 23842, 'loss/train': 0.18533694744110107}
+08/30/2021 17:28:11 - INFO - __main__ - Step 23844: {'lr': 0.00047360531542859415, 'samples': 4578048, 'steps': 23843, 'loss/train': 2.061516046524048}
+08/30/2021 17:28:11 - INFO - __main__ - Step 23845: {'lr': 0.00047360294206706845, 'samples': 4578240, 'steps': 23844, 'loss/train': 2.084402084350586}
+08/30/2021 17:28:13 - INFO - __main__ - Step 23846: {'lr': 0.0004736005686047907, 'samples': 4578432, 'steps': 23845, 'loss/train': 1.6754575967788696}
+08/30/2021 17:28:14 - INFO - __main__ - Step 23847: {'lr': 0.000473598195041762, 'samples': 4578624, 'steps': 23846, 'loss/train': 1.7514890432357788}
+08/30/2021 17:28:14 - INFO - __main__ - Step 23848: {'lr': 0.0004735958213779835, 'samples': 4578816, 'steps': 23847, 'loss/train': 1.93454909324646}
+08/30/2021 17:28:14 - INFO - __main__ - Step 23849: {'lr': 0.0004735934476134561, 'samples': 4579008, 'steps': 23848, 'loss/train': 1.8268200159072876}
+08/30/2021 17:28:15 - INFO - __main__ - Step 23850: {'lr': 0.0004735910737481809, 'samples': 4579200, 'steps': 23849, 'loss/train': 1.6639269590377808}
+08/30/2021 17:28:16 - INFO - __main__ - Step 23851: {'lr': 0.0004735886997821591, 'samples': 4579392, 'steps': 23850, 'loss/train': 1.5180392265319824}
+08/30/2021 17:28:17 - INFO - __main__ - Step 23852: {'lr': 0.00047358632571539163, 'samples': 4579584, 'steps': 23851, 'loss/train': 1.6867505311965942}
+08/30/2021 17:28:17 - INFO - __main__ - Step 23853: {'lr': 0.0004735839515478796, 'samples': 4579776, 'steps': 23852, 'loss/train': 1.8900582790374756}
+08/30/2021 17:28:18 - INFO - __main__ - Step 23854: {'lr': 0.0004735815772796241, 'samples': 4579968, 'steps': 23853, 'loss/train': 1.4159471988677979}
+08/30/2021 17:28:18 - INFO - __main__ - Step 23855: {'lr': 0.0004735792029106262, 'samples': 4580160, 'steps': 23854, 'loss/train': 1.7847771644592285}
+08/30/2021 17:28:19 - INFO - __main__ - Step 23856: {'lr': 0.0004735768284408869, 'samples': 4580352, 'steps': 23855, 'loss/train': 1.3962061405181885}
+08/30/2021 17:28:20 - INFO - __main__ - Step 23857: {'lr': 0.00047357445387040745, 'samples': 4580544, 'steps': 23856, 'loss/train': 1.7047101259231567}
+08/30/2021 17:28:20 - INFO - __main__ - Step 23858: {'lr': 0.0004735720791991887, 'samples': 4580736, 'steps': 23857, 'loss/train': 1.3259724378585815}
+08/30/2021 17:28:20 - INFO - __main__ - Step 23859: {'lr': 0.00047356970442723184, 'samples': 4580928, 'steps': 23858, 'loss/train': 1.4971916675567627}
+08/30/2021 17:28:21 - INFO - __main__ - Step 23860: {'lr': 0.00047356732955453794, 'samples': 4581120, 'steps': 23859, 'loss/train': 1.8438758850097656}
+08/30/2021 17:28:21 - INFO - __main__ - Step 23861: {'lr': 0.00047356495458110806, 'samples': 4581312, 'steps': 23860, 'loss/train': 1.6122157573699951}
+08/30/2021 17:28:23 - INFO - __main__ - Step 23862: {'lr': 0.00047356257950694326, 'samples': 4581504, 'steps': 23861, 'loss/train': 1.2520089149475098}
+08/30/2021 17:28:23 - INFO - __main__ - Step 23863: {'lr': 0.0004735602043320446, 'samples': 4581696, 'steps': 23862, 'loss/train': 0.912713885307312}
+08/30/2021 17:28:24 - INFO - __main__ - Step 23864: {'lr': 0.0004735578290564132, 'samples': 4581888, 'steps': 23863, 'loss/train': 2.071293830871582}
+08/30/2021 17:28:24 - INFO - __main__ - Step 23865: {'lr': 0.00047355545368005003, 'samples': 4582080, 'steps': 23864, 'loss/train': 0.1382804811000824}
+08/30/2021 17:28:24 - INFO - __main__ - Step 23866: {'lr': 0.00047355307820295625, 'samples': 4582272, 'steps': 23865, 'loss/train': 0.18995091319084167}
+08/30/2021 17:28:25 - INFO - __main__ - Step 23867: {'lr': 0.00047355070262513287, 'samples': 4582464, 'steps': 23866, 'loss/train': 0.23722438514232635}
+08/30/2021 17:28:26 - INFO - __main__ - Step 23868: {'lr': 0.00047354832694658104, 'samples': 4582656, 'steps': 23867, 'loss/train': 1.927314043045044}
+08/30/2021 17:28:27 - INFO - __main__ - Step 23869: {'lr': 0.0004735459511673018, 'samples': 4582848, 'steps': 23868, 'loss/train': 1.8384425640106201}
+08/30/2021 17:28:27 - INFO - __main__ - Step 23870: {'lr': 0.0004735435752872962, 'samples': 4583040, 'steps': 23869, 'loss/train': 1.5113917589187622}
+08/30/2021 17:28:27 - INFO - __main__ - Step 23871: {'lr': 0.00047354119930656524, 'samples': 4583232, 'steps': 23870, 'loss/train': 1.3223645687103271}
+08/30/2021 17:28:28 - INFO - __main__ - Step 23872: {'lr': 0.0004735388232251101, 'samples': 4583424, 'steps': 23871, 'loss/train': 1.503225326538086}
+08/30/2021 17:28:29 - INFO - __main__ - Step 23873: {'lr': 0.00047353644704293185, 'samples': 4583616, 'steps': 23872, 'loss/train': 1.4452446699142456}
+08/30/2021 17:28:30 - INFO - __main__ - Step 23874: {'lr': 0.0004735340707600315, 'samples': 4583808, 'steps': 23873, 'loss/train': 1.406503438949585}
+08/30/2021 17:28:30 - INFO - __main__ - Step 23875: {'lr': 0.0004735316943764102, 'samples': 4584000, 'steps': 23874, 'loss/train': 1.6812968254089355}
+08/30/2021 17:28:30 - INFO - __main__ - Step 23876: {'lr': 0.0004735293178920689, 'samples': 4584192, 'steps': 23875, 'loss/train': 2.136699914932251}
+08/30/2021 17:28:31 - INFO - __main__ - Step 23877: {'lr': 0.00047352694130700873, 'samples': 4584384, 'steps': 23876, 'loss/train': 0.8547267913818359}
+08/30/2021 17:28:32 - INFO - __main__ - Step 23878: {'lr': 0.00047352456462123086, 'samples': 4584576, 'steps': 23877, 'loss/train': 1.6009595394134521}
+08/30/2021 17:28:33 - INFO - __main__ - Step 23879: {'lr': 0.00047352218783473614, 'samples': 4584768, 'steps': 23878, 'loss/train': 0.06502050906419754}
+08/30/2021 17:28:33 - INFO - __main__ - Step 23880: {'lr': 0.0004735198109475258, 'samples': 4584960, 'steps': 23879, 'loss/train': 2.0369484424591064}
+08/30/2021 17:28:34 - INFO - __main__ - Step 23881: {'lr': 0.000473517433959601, 'samples': 4585152, 'steps': 23880, 'loss/train': 1.5942567586898804}
+08/30/2021 17:28:34 - INFO - __main__ - Step 23882: {'lr': 0.00047351505687096257, 'samples': 4585344, 'steps': 23881, 'loss/train': 2.0245325565338135}
+08/30/2021 17:28:36 - INFO - __main__ - Step 23883: {'lr': 0.00047351267968161176, 'samples': 4585536, 'steps': 23882, 'loss/train': 1.6382445096969604}
+08/30/2021 17:28:36 - INFO - __main__ - Step 23884: {'lr': 0.0004735103023915496, 'samples': 4585728, 'steps': 23883, 'loss/train': 1.2688628435134888}
+08/30/2021 17:28:37 - INFO - __main__ - Step 23885: {'lr': 0.0004735079250007771, 'samples': 4585920, 'steps': 23884, 'loss/train': 1.2023228406906128}
+08/30/2021 17:28:37 - INFO - __main__ - Step 23886: {'lr': 0.00047350554750929543, 'samples': 4586112, 'steps': 23885, 'loss/train': 1.6293264627456665}
+08/30/2021 17:28:37 - INFO - __main__ - Step 23887: {'lr': 0.0004735031699171055, 'samples': 4586304, 'steps': 23886, 'loss/train': 1.5460349321365356}
+08/30/2021 17:28:39 - INFO - __main__ - Step 23888: {'lr': 0.0004735007922242086, 'samples': 4586496, 'steps': 23887, 'loss/train': 0.10107112675905228}
+08/30/2021 17:28:39 - INFO - __main__ - Step 23889: {'lr': 0.0004734984144306057, 'samples': 4586688, 'steps': 23888, 'loss/train': 1.457375168800354}
+08/30/2021 17:28:40 - INFO - __main__ - Step 23890: {'lr': 0.0004734960365362978, 'samples': 4586880, 'steps': 23889, 'loss/train': 1.3192206621170044}
+08/30/2021 17:28:40 - INFO - __main__ - Step 23891: {'lr': 0.0004734936585412861, 'samples': 4587072, 'steps': 23890, 'loss/train': 1.0279250144958496}
+08/30/2021 17:28:40 - INFO - __main__ - Step 23892: {'lr': 0.00047349128044557153, 'samples': 4587264, 'steps': 23891, 'loss/train': 1.7531778812408447}
+08/30/2021 17:28:42 - INFO - __main__ - Step 23893: {'lr': 0.0004734889022491553, 'samples': 4587456, 'steps': 23892, 'loss/train': 1.7402050495147705}
+08/30/2021 17:28:42 - INFO - __main__ - Step 23894: {'lr': 0.0004734865239520384, 'samples': 4587648, 'steps': 23893, 'loss/train': 1.4512770175933838}
+08/30/2021 17:28:42 - INFO - __main__ - Step 23895: {'lr': 0.0004734841455542219, 'samples': 4587840, 'steps': 23894, 'loss/train': 1.7012555599212646}
+08/30/2021 17:28:43 - INFO - __main__ - Step 23896: {'lr': 0.0004734817670557069, 'samples': 4588032, 'steps': 23895, 'loss/train': 0.9944023489952087}
+08/30/2021 17:28:43 - INFO - __main__ - Step 23897: {'lr': 0.00047347938845649447, 'samples': 4588224, 'steps': 23896, 'loss/train': 1.2406022548675537}
+08/30/2021 17:28:45 - INFO - __main__ - Step 23898: {'lr': 0.0004734770097565857, 'samples': 4588416, 'steps': 23897, 'loss/train': 1.8092373609542847}
+08/30/2021 17:28:45 - INFO - __main__ - Step 23899: {'lr': 0.00047347463095598157, 'samples': 4588608, 'steps': 23898, 'loss/train': 2.0713953971862793}
+08/30/2021 17:28:45 - INFO - __main__ - Step 23900: {'lr': 0.00047347225205468323, 'samples': 4588800, 'steps': 23899, 'loss/train': 1.4054807424545288}
+08/30/2021 17:28:46 - INFO - __main__ - Step 23901: {'lr': 0.00047346987305269184, 'samples': 4588992, 'steps': 23900, 'loss/train': 1.2611148357391357}
+08/30/2021 17:28:46 - INFO - __main__ - Step 23902: {'lr': 0.0004734674939500083, 'samples': 4589184, 'steps': 23901, 'loss/train': 1.083526372909546}
+08/30/2021 17:28:46 - INFO - __main__ - Step 23903: {'lr': 0.0004734651147466338, 'samples': 4589376, 'steps': 23902, 'loss/train': 1.7088778018951416}
+08/30/2021 17:28:48 - INFO - __main__ - Step 23904: {'lr': 0.00047346273544256927, 'samples': 4589568, 'steps': 23903, 'loss/train': 0.4893910884857178}
+08/30/2021 17:28:49 - INFO - __main__ - Step 23905: {'lr': 0.00047346035603781597, 'samples': 4589760, 'steps': 23904, 'loss/train': 1.1126079559326172}
+08/30/2021 17:28:49 - INFO - __main__ - Step 23906: {'lr': 0.00047345797653237486, 'samples': 4589952, 'steps': 23905, 'loss/train': 1.494066834449768}
+08/30/2021 17:28:50 - INFO - __main__ - Step 23907: {'lr': 0.000473455596926247, 'samples': 4590144, 'steps': 23906, 'loss/train': 1.458207607269287}
+08/30/2021 17:28:50 - INFO - __main__ - Step 23908: {'lr': 0.0004734532172194335, 'samples': 4590336, 'steps': 23907, 'loss/train': 1.5953456163406372}
+08/30/2021 17:28:51 - INFO - __main__ - Step 23909: {'lr': 0.0004734508374119355, 'samples': 4590528, 'steps': 23908, 'loss/train': 1.9063292741775513}
+08/30/2021 17:28:52 - INFO - __main__ - Step 23910: {'lr': 0.0004734484575037539, 'samples': 4590720, 'steps': 23909, 'loss/train': 1.5804921388626099}
+08/30/2021 17:28:52 - INFO - __main__ - Step 23911: {'lr': 0.00047344607749489, 'samples': 4590912, 'steps': 23910, 'loss/train': 1.5822813510894775}
+08/30/2021 17:28:53 - INFO - __main__ - Step 23912: {'lr': 0.00047344369738534466, 'samples': 4591104, 'steps': 23911, 'loss/train': 1.5705474615097046}
+08/30/2021 17:28:53 - INFO - __main__ - Step 23913: {'lr': 0.000473441317175119, 'samples': 4591296, 'steps': 23912, 'loss/train': 2.1579926013946533}
+08/30/2021 17:28:54 - INFO - __main__ - Step 23914: {'lr': 0.0004734389368642142, 'samples': 4591488, 'steps': 23913, 'loss/train': 1.5677502155303955}
+08/30/2021 17:28:55 - INFO - __main__ - Step 23915: {'lr': 0.0004734365564526313, 'samples': 4591680, 'steps': 23914, 'loss/train': 1.2844774723052979}
+08/30/2021 17:28:55 - INFO - __main__ - Step 23916: {'lr': 0.00047343417594037117, 'samples': 4591872, 'steps': 23915, 'loss/train': 1.2457770109176636}
+08/30/2021 17:28:56 - INFO - __main__ - Step 23917: {'lr': 0.00047343179532743516, 'samples': 4592064, 'steps': 23916, 'loss/train': 1.7153592109680176}
+08/30/2021 17:28:56 - INFO - __main__ - Step 23918: {'lr': 0.00047342941461382427, 'samples': 4592256, 'steps': 23917, 'loss/train': 1.7542444467544556}
+08/30/2021 17:28:58 - INFO - __main__ - Step 23919: {'lr': 0.0004734270337995395, 'samples': 4592448, 'steps': 23918, 'loss/train': 1.5001026391983032}
+08/30/2021 17:28:58 - INFO - __main__ - Step 23920: {'lr': 0.0004734246528845819, 'samples': 4592640, 'steps': 23919, 'loss/train': 1.0851719379425049}
+08/30/2021 17:28:58 - INFO - __main__ - Step 23921: {'lr': 0.0004734222718689527, 'samples': 4592832, 'steps': 23920, 'loss/train': 1.639939308166504}
+08/30/2021 17:28:59 - INFO - __main__ - Step 23922: {'lr': 0.0004734198907526528, 'samples': 4593024, 'steps': 23921, 'loss/train': 1.6189429759979248}
+08/30/2021 17:28:59 - INFO - __main__ - Step 23923: {'lr': 0.00047341750953568335, 'samples': 4593216, 'steps': 23922, 'loss/train': 1.2667911052703857}
+08/30/2021 17:29:01 - INFO - __main__ - Step 23924: {'lr': 0.0004734151282180454, 'samples': 4593408, 'steps': 23923, 'loss/train': 1.7822493314743042}
+08/30/2021 17:29:01 - INFO - __main__ - Step 23925: {'lr': 0.0004734127467997401, 'samples': 4593600, 'steps': 23924, 'loss/train': 1.4168741703033447}
+08/30/2021 17:29:01 - INFO - __main__ - Step 23926: {'lr': 0.0004734103652807684, 'samples': 4593792, 'steps': 23925, 'loss/train': 1.5136585235595703}
+08/30/2021 17:29:02 - INFO - __main__ - Step 23927: {'lr': 0.0004734079836611315, 'samples': 4593984, 'steps': 23926, 'loss/train': 1.656827688217163}
+08/30/2021 17:29:02 - INFO - __main__ - Step 23928: {'lr': 0.0004734056019408304, 'samples': 4594176, 'steps': 23927, 'loss/train': 1.1633803844451904}
+08/30/2021 17:29:04 - INFO - __main__ - Step 23929: {'lr': 0.00047340322011986614, 'samples': 4594368, 'steps': 23928, 'loss/train': 1.5292781591415405}
+08/30/2021 17:29:04 - INFO - __main__ - Step 23930: {'lr': 0.0004734008381982399, 'samples': 4594560, 'steps': 23929, 'loss/train': 1.594104290008545}
+08/30/2021 17:29:05 - INFO - __main__ - Step 23931: {'lr': 0.0004733984561759527, 'samples': 4594752, 'steps': 23930, 'loss/train': 0.07521896809339523}
+08/30/2021 17:29:05 - INFO - __main__ - Step 23932: {'lr': 0.0004733960740530055, 'samples': 4594944, 'steps': 23931, 'loss/train': 0.9714577198028564}
+08/30/2021 17:29:05 - INFO - __main__ - Step 23933: {'lr': 0.0004733936918293995, 'samples': 4595136, 'steps': 23932, 'loss/train': 1.1091326475143433}
+08/30/2021 17:29:06 - INFO - __main__ - Step 23934: {'lr': 0.0004733913095051358, 'samples': 4595328, 'steps': 23933, 'loss/train': 1.7921544313430786}
+08/30/2021 17:29:07 - INFO - __main__ - Step 23935: {'lr': 0.0004733889270802154, 'samples': 4595520, 'steps': 23934, 'loss/train': 1.0680391788482666}
+08/30/2021 17:29:08 - INFO - __main__ - Step 23936: {'lr': 0.00047338654455463935, 'samples': 4595712, 'steps': 23935, 'loss/train': 1.6875224113464355}
+08/30/2021 17:29:08 - INFO - __main__ - Step 23937: {'lr': 0.00047338416192840887, 'samples': 4595904, 'steps': 23936, 'loss/train': 0.544355034828186}
+08/30/2021 17:29:08 - INFO - __main__ - Step 23938: {'lr': 0.0004733817792015249, 'samples': 4596096, 'steps': 23937, 'loss/train': 1.8118723630905151}
+08/30/2021 17:29:09 - INFO - __main__ - Step 23939: {'lr': 0.00047337939637398855, 'samples': 4596288, 'steps': 23938, 'loss/train': 0.7021389603614807}
+08/30/2021 17:29:10 - INFO - __main__ - Step 23940: {'lr': 0.0004733770134458009, 'samples': 4596480, 'steps': 23939, 'loss/train': 1.6260449886322021}
+08/30/2021 17:29:11 - INFO - __main__ - Step 23941: {'lr': 0.0004733746304169629, 'samples': 4596672, 'steps': 23940, 'loss/train': 1.067652702331543}
+08/30/2021 17:29:11 - INFO - __main__ - Step 23942: {'lr': 0.0004733722472874759, 'samples': 4596864, 'steps': 23941, 'loss/train': 0.08660119771957397}
+08/30/2021 17:29:12 - INFO - __main__ - Step 23943: {'lr': 0.0004733698640573407, 'samples': 4597056, 'steps': 23942, 'loss/train': 0.7692243456840515}
+08/30/2021 17:29:12 - INFO - __main__ - Step 23944: {'lr': 0.0004733674807265585, 'samples': 4597248, 'steps': 23943, 'loss/train': 1.3763090372085571}
+08/30/2021 17:29:14 - INFO - __main__ - Step 23945: {'lr': 0.0004733650972951304, 'samples': 4597440, 'steps': 23944, 'loss/train': 1.3232545852661133}
+08/30/2021 17:29:14 - INFO - __main__ - Step 23946: {'lr': 0.0004733627137630574, 'samples': 4597632, 'steps': 23945, 'loss/train': 1.1721309423446655}
+08/30/2021 17:29:14 - INFO - __main__ - Step 23947: {'lr': 0.00047336033013034063, 'samples': 4597824, 'steps': 23946, 'loss/train': 0.9328784346580505}
+08/30/2021 17:29:15 - INFO - __main__ - Step 23948: {'lr': 0.00047335794639698117, 'samples': 4598016, 'steps': 23947, 'loss/train': 1.1213229894638062}
+08/30/2021 17:29:15 - INFO - __main__ - Step 23949: {'lr': 0.00047335556256298, 'samples': 4598208, 'steps': 23948, 'loss/train': 1.6727445125579834}
+08/30/2021 17:29:17 - INFO - __main__ - Step 23950: {'lr': 0.0004733531786283383, 'samples': 4598400, 'steps': 23949, 'loss/train': 1.4021284580230713}
+08/30/2021 17:29:17 - INFO - __main__ - Step 23951: {'lr': 0.0004733507945930571, 'samples': 4598592, 'steps': 23950, 'loss/train': 1.8878673315048218}
+08/30/2021 17:29:18 - INFO - __main__ - Step 23952: {'lr': 0.0004733484104571375, 'samples': 4598784, 'steps': 23951, 'loss/train': 1.5105644464492798}
+08/30/2021 17:29:18 - INFO - __main__ - Step 23953: {'lr': 0.0004733460262205805, 'samples': 4598976, 'steps': 23952, 'loss/train': 2.0807597637176514}
+08/30/2021 17:29:18 - INFO - __main__ - Step 23954: {'lr': 0.00047334364188338725, 'samples': 4599168, 'steps': 23953, 'loss/train': 1.6940207481384277}
+08/30/2021 17:29:20 - INFO - __main__ - Step 23955: {'lr': 0.0004733412574455588, 'samples': 4599360, 'steps': 23954, 'loss/train': 1.5082449913024902}
+08/30/2021 17:29:21 - INFO - __main__ - Step 23956: {'lr': 0.00047333887290709623, 'samples': 4599552, 'steps': 23955, 'loss/train': 1.1699519157409668}
+08/30/2021 17:29:21 - INFO - __main__ - Step 23957: {'lr': 0.00047333648826800056, 'samples': 4599744, 'steps': 23956, 'loss/train': 1.5576560497283936}
+08/30/2021 17:29:21 - INFO - __main__ - Step 23958: {'lr': 0.000473334103528273, 'samples': 4599936, 'steps': 23957, 'loss/train': 1.5029267072677612}
+08/30/2021 17:29:22 - INFO - __main__ - Step 23959: {'lr': 0.00047333171868791453, 'samples': 4600128, 'steps': 23958, 'loss/train': 1.5009058713912964}
+08/30/2021 17:29:23 - INFO - __main__ - Step 23960: {'lr': 0.00047332933374692623, 'samples': 4600320, 'steps': 23959, 'loss/train': 1.3994954824447632}
+08/30/2021 17:29:24 - INFO - __main__ - Step 23961: {'lr': 0.0004733269487053091, 'samples': 4600512, 'steps': 23960, 'loss/train': 1.5259203910827637}
+08/30/2021 17:29:24 - INFO - __main__ - Step 23962: {'lr': 0.0004733245635630644, 'samples': 4600704, 'steps': 23961, 'loss/train': 1.4005982875823975}
+08/30/2021 17:29:24 - INFO - __main__ - Step 23963: {'lr': 0.000473322178320193, 'samples': 4600896, 'steps': 23962, 'loss/train': 1.6762452125549316}
+08/30/2021 17:29:25 - INFO - __main__ - Step 23964: {'lr': 0.0004733197929766961, 'samples': 4601088, 'steps': 23963, 'loss/train': 1.6293858289718628}
+08/30/2021 17:29:26 - INFO - __main__ - Step 23965: {'lr': 0.0004733174075325748, 'samples': 4601280, 'steps': 23964, 'loss/train': 1.3817896842956543}
+08/30/2021 17:29:27 - INFO - __main__ - Step 23966: {'lr': 0.0004733150219878301, 'samples': 4601472, 'steps': 23965, 'loss/train': 1.376197099685669}
+08/30/2021 17:29:27 - INFO - __main__ - Step 23967: {'lr': 0.00047331263634246314, 'samples': 4601664, 'steps': 23966, 'loss/train': 1.2290537357330322}
+08/30/2021 17:29:27 - INFO - __main__ - Step 23968: {'lr': 0.0004733102505964749, 'samples': 4601856, 'steps': 23967, 'loss/train': 1.452670931816101}
+08/30/2021 17:29:28 - INFO - __main__ - Step 23969: {'lr': 0.00047330786474986645, 'samples': 4602048, 'steps': 23968, 'loss/train': 1.2899892330169678}
+08/30/2021 17:29:29 - INFO - __main__ - Step 23970: {'lr': 0.00047330547880263896, 'samples': 4602240, 'steps': 23969, 'loss/train': 1.491136908531189}
+08/30/2021 17:29:30 - INFO - __main__ - Step 23971: {'lr': 0.00047330309275479354, 'samples': 4602432, 'steps': 23970, 'loss/train': 1.4215087890625}
+08/30/2021 17:29:30 - INFO - __main__ - Step 23972: {'lr': 0.00047330070660633113, 'samples': 4602624, 'steps': 23971, 'loss/train': 1.8291187286376953}
+08/30/2021 17:29:30 - INFO - __main__ - Step 23973: {'lr': 0.00047329832035725286, 'samples': 4602816, 'steps': 23972, 'loss/train': 1.5089482069015503}
+08/30/2021 17:29:31 - INFO - __main__ - Step 23974: {'lr': 0.0004732959340075598, 'samples': 4603008, 'steps': 23973, 'loss/train': 1.8125065565109253}
+08/30/2021 17:29:32 - INFO - __main__ - Step 23975: {'lr': 0.0004732935475572531, 'samples': 4603200, 'steps': 23974, 'loss/train': 1.5856719017028809}
+08/30/2021 17:29:33 - INFO - __main__ - Step 23976: {'lr': 0.00047329116100633373, 'samples': 4603392, 'steps': 23975, 'loss/train': 2.2570695877075195}
+08/30/2021 17:29:33 - INFO - __main__ - Step 23977: {'lr': 0.0004732887743548028, 'samples': 4603584, 'steps': 23976, 'loss/train': 1.0739967823028564}
+08/30/2021 17:29:33 - INFO - __main__ - Step 23978: {'lr': 0.0004732863876026614, 'samples': 4603776, 'steps': 23977, 'loss/train': 1.5266087055206299}
+08/30/2021 17:29:34 - INFO - __main__ - Step 23979: {'lr': 0.00047328400074991064, 'samples': 4603968, 'steps': 23978, 'loss/train': 0.9839372038841248}
+08/30/2021 17:29:34 - INFO - __main__ - Step 23980: {'lr': 0.00047328161379655155, 'samples': 4604160, 'steps': 23979, 'loss/train': 0.6058788895606995}
+08/30/2021 17:29:35 - INFO - __main__ - Step 23981: {'lr': 0.00047327922674258516, 'samples': 4604352, 'steps': 23980, 'loss/train': 1.6976488828659058}
+08/30/2021 17:29:36 - INFO - __main__ - Step 23982: {'lr': 0.00047327683958801257, 'samples': 4604544, 'steps': 23981, 'loss/train': 1.3941693305969238}
+08/30/2021 17:29:36 - INFO - __main__ - Step 23983: {'lr': 0.00047327445233283496, 'samples': 4604736, 'steps': 23982, 'loss/train': 1.415250539779663}
+08/30/2021 17:29:37 - INFO - __main__ - Step 23984: {'lr': 0.0004732720649770533, 'samples': 4604928, 'steps': 23983, 'loss/train': 1.7057350873947144}
+08/30/2021 17:29:37 - INFO - __main__ - Step 23985: {'lr': 0.00047326967752066876, 'samples': 4605120, 'steps': 23984, 'loss/train': 1.5120905637741089}
+08/30/2021 17:29:39 - INFO - __main__ - Step 23986: {'lr': 0.0004732672899636822, 'samples': 4605312, 'steps': 23985, 'loss/train': 1.9327870607376099}
+08/30/2021 17:29:40 - INFO - __main__ - Step 23987: {'lr': 0.00047326490230609495, 'samples': 4605504, 'steps': 23986, 'loss/train': 1.3406269550323486}
+08/30/2021 17:29:40 - INFO - __main__ - Step 23988: {'lr': 0.000473262514547908, 'samples': 4605696, 'steps': 23987, 'loss/train': 0.6682289838790894}
+08/30/2021 17:29:41 - INFO - __main__ - Step 23989: {'lr': 0.00047326012668912233, 'samples': 4605888, 'steps': 23988, 'loss/train': 0.570551335811615}
+08/30/2021 17:29:41 - INFO - __main__ - Step 23990: {'lr': 0.0004732577387297391, 'samples': 4606080, 'steps': 23989, 'loss/train': 1.1935884952545166}
+08/30/2021 17:29:41 - INFO - __main__ - Step 23991: {'lr': 0.00047325535066975946, 'samples': 4606272, 'steps': 23990, 'loss/train': 1.4759531021118164}
+08/30/2021 17:29:43 - INFO - __main__ - Step 23992: {'lr': 0.0004732529625091843, 'samples': 4606464, 'steps': 23991, 'loss/train': 1.1583490371704102}
+08/30/2021 17:29:43 - INFO - __main__ - Step 23993: {'lr': 0.0004732505742480149, 'samples': 4606656, 'steps': 23992, 'loss/train': 2.132206916809082}
+08/30/2021 17:29:44 - INFO - __main__ - Step 23994: {'lr': 0.00047324818588625214, 'samples': 4606848, 'steps': 23993, 'loss/train': 1.8066595792770386}
+08/30/2021 17:29:44 - INFO - __main__ - Step 23995: {'lr': 0.0004732457974238972, 'samples': 4607040, 'steps': 23994, 'loss/train': 2.031420946121216}
+08/30/2021 17:29:44 - INFO - __main__ - Step 23996: {'lr': 0.0004732434088609512, 'samples': 4607232, 'steps': 23995, 'loss/train': 1.9712618589401245}
+08/30/2021 17:29:46 - INFO - __main__ - Step 23997: {'lr': 0.00047324102019741514, 'samples': 4607424, 'steps': 23996, 'loss/train': 1.8564987182617188}
+08/30/2021 17:29:46 - INFO - __main__ - Step 23998: {'lr': 0.00047323863143329016, 'samples': 4607616, 'steps': 23997, 'loss/train': 1.965773582458496}
+08/30/2021 17:29:47 - INFO - __main__ - Step 23999: {'lr': 0.00047323624256857724, 'samples': 4607808, 'steps': 23998, 'loss/train': 1.5524145364761353}
+08/30/2021 17:29:47 - INFO - __main__ - Step 24000: {'lr': 0.0004732338536032775, 'samples': 4608000, 'steps': 23999, 'loss/train': 1.7805531024932861}
+08/30/2021 17:29:47 - INFO - __main__ - Step 24001: {'lr': 0.0004732314645373921, 'samples': 4608192, 'steps': 24000, 'loss/train': 1.941765308380127}
+08/30/2021 17:29:49 - INFO - __main__ - Step 24002: {'lr': 0.0004732290753709221, 'samples': 4608384, 'steps': 24001, 'loss/train': 2.1082425117492676}
+08/30/2021 17:29:49 - INFO - __main__ - Step 24003: {'lr': 0.0004732266861038684, 'samples': 4608576, 'steps': 24002, 'loss/train': 1.6280622482299805}
+08/30/2021 17:29:50 - INFO - __main__ - Step 24004: {'lr': 0.0004732242967362322, 'samples': 4608768, 'steps': 24003, 'loss/train': 1.4950611591339111}
+08/30/2021 17:29:50 - INFO - __main__ - Step 24005: {'lr': 0.00047322190726801464, 'samples': 4608960, 'steps': 24004, 'loss/train': 1.7071781158447266}
+08/30/2021 17:29:50 - INFO - __main__ - Step 24006: {'lr': 0.0004732195176992167, 'samples': 4609152, 'steps': 24005, 'loss/train': 1.6114521026611328}
+08/30/2021 17:29:52 - INFO - __main__ - Step 24007: {'lr': 0.0004732171280298395, 'samples': 4609344, 'steps': 24006, 'loss/train': 1.3769075870513916}
+08/30/2021 17:29:52 - INFO - __main__ - Step 24008: {'lr': 0.0004732147382598842, 'samples': 4609536, 'steps': 24007, 'loss/train': 1.3611992597579956}
+08/30/2021 17:29:53 - INFO - __main__ - Step 24009: {'lr': 0.00047321234838935164, 'samples': 4609728, 'steps': 24008, 'loss/train': 1.4643421173095703}
+08/30/2021 17:29:53 - INFO - __main__ - Step 24010: {'lr': 0.0004732099584182431, 'samples': 4609920, 'steps': 24009, 'loss/train': 1.8271245956420898}
+08/30/2021 17:29:53 - INFO - __main__ - Step 24011: {'lr': 0.00047320756834655955, 'samples': 4610112, 'steps': 24010, 'loss/train': 1.9192742109298706}
+08/30/2021 17:29:56 - INFO - __main__ - Step 24012: {'lr': 0.0004732051781743022, 'samples': 4610304, 'steps': 24011, 'loss/train': 1.5685092210769653}
+08/30/2021 17:29:56 - INFO - __main__ - Step 24013: {'lr': 0.00047320278790147197, 'samples': 4610496, 'steps': 24012, 'loss/train': 2.033869743347168}
+08/30/2021 17:29:56 - INFO - __main__ - Step 24014: {'lr': 0.00047320039752807, 'samples': 4610688, 'steps': 24013, 'loss/train': 1.8639260530471802}
+08/30/2021 17:29:57 - INFO - __main__ - Step 24015: {'lr': 0.0004731980070540974, 'samples': 4610880, 'steps': 24014, 'loss/train': 1.352035403251648}
+08/30/2021 17:29:57 - INFO - __main__ - Step 24016: {'lr': 0.0004731956164795552, 'samples': 4611072, 'steps': 24015, 'loss/train': 1.722882628440857}
+08/30/2021 17:29:57 - INFO - __main__ - Step 24017: {'lr': 0.0004731932258044446, 'samples': 4611264, 'steps': 24016, 'loss/train': 0.7408400177955627}
+08/30/2021 17:29:59 - INFO - __main__ - Step 24018: {'lr': 0.00047319083502876647, 'samples': 4611456, 'steps': 24017, 'loss/train': 1.7358992099761963}
+08/30/2021 17:29:59 - INFO - __main__ - Step 24019: {'lr': 0.00047318844415252204, 'samples': 4611648, 'steps': 24018, 'loss/train': 1.7989447116851807}
+08/30/2021 17:30:00 - INFO - __main__ - Step 24020: {'lr': 0.00047318605317571227, 'samples': 4611840, 'steps': 24019, 'loss/train': 1.5153939723968506}
+08/30/2021 17:30:00 - INFO - __main__ - Step 24021: {'lr': 0.0004731836620983384, 'samples': 4612032, 'steps': 24020, 'loss/train': 1.7799488306045532}
+08/30/2021 17:30:00 - INFO - __main__ - Step 24022: {'lr': 0.00047318127092040144, 'samples': 4612224, 'steps': 24021, 'loss/train': 1.7262390851974487}
+08/30/2021 17:30:02 - INFO - __main__ - Step 24023: {'lr': 0.00047317887964190233, 'samples': 4612416, 'steps': 24022, 'loss/train': 1.7322629690170288}
+08/30/2021 17:30:02 - INFO - __main__ - Step 24024: {'lr': 0.00047317648826284233, 'samples': 4612608, 'steps': 24023, 'loss/train': 1.7015255689620972}
+08/30/2021 17:30:03 - INFO - __main__ - Step 24025: {'lr': 0.0004731740967832224, 'samples': 4612800, 'steps': 24024, 'loss/train': 0.9546807408332825}
+08/30/2021 17:30:03 - INFO - __main__ - Step 24026: {'lr': 0.00047317170520304373, 'samples': 4612992, 'steps': 24025, 'loss/train': 1.139951229095459}
+08/30/2021 17:30:03 - INFO - __main__ - Step 24027: {'lr': 0.0004731693135223073, 'samples': 4613184, 'steps': 24026, 'loss/train': 1.8629801273345947}
+08/30/2021 17:30:05 - INFO - __main__ - Step 24028: {'lr': 0.0004731669217410142, 'samples': 4613376, 'steps': 24027, 'loss/train': 1.068621039390564}
+08/30/2021 17:30:05 - INFO - __main__ - Step 24029: {'lr': 0.0004731645298591656, 'samples': 4613568, 'steps': 24028, 'loss/train': 1.1456061601638794}
+08/30/2021 17:30:06 - INFO - __main__ - Step 24030: {'lr': 0.0004731621378767624, 'samples': 4613760, 'steps': 24029, 'loss/train': 1.7382146120071411}
+08/30/2021 17:30:06 - INFO - __main__ - Step 24031: {'lr': 0.0004731597457938059, 'samples': 4613952, 'steps': 24030, 'loss/train': 0.7456815242767334}
+08/30/2021 17:30:06 - INFO - __main__ - Step 24032: {'lr': 0.000473157353610297, 'samples': 4614144, 'steps': 24031, 'loss/train': 1.714818000793457}
+08/30/2021 17:30:08 - INFO - __main__ - Step 24033: {'lr': 0.0004731549613262368, 'samples': 4614336, 'steps': 24032, 'loss/train': 1.5012445449829102}
+08/30/2021 17:30:09 - INFO - __main__ - Step 24034: {'lr': 0.0004731525689416265, 'samples': 4614528, 'steps': 24033, 'loss/train': 1.5666781663894653}
+08/30/2021 17:30:09 - INFO - __main__ - Step 24035: {'lr': 0.0004731501764564671, 'samples': 4614720, 'steps': 24034, 'loss/train': 0.3431834876537323}
+08/30/2021 17:30:10 - INFO - __main__ - Step 24036: {'lr': 0.00047314778387075963, 'samples': 4614912, 'steps': 24035, 'loss/train': 1.9771511554718018}
+08/30/2021 17:30:10 - INFO - __main__ - Step 24037: {'lr': 0.00047314539118450516, 'samples': 4615104, 'steps': 24036, 'loss/train': 1.9900704622268677}
+08/30/2021 17:30:12 - INFO - __main__ - Step 24038: {'lr': 0.0004731429983977049, 'samples': 4615296, 'steps': 24037, 'loss/train': 1.5211819410324097}
+08/30/2021 17:30:12 - INFO - __main__ - Step 24039: {'lr': 0.00047314060551035983, 'samples': 4615488, 'steps': 24038, 'loss/train': 2.0710344314575195}
+08/30/2021 17:30:12 - INFO - __main__ - Step 24040: {'lr': 0.00047313821252247104, 'samples': 4615680, 'steps': 24039, 'loss/train': 1.251976490020752}
+08/30/2021 17:30:13 - INFO - __main__ - Step 24041: {'lr': 0.00047313581943403963, 'samples': 4615872, 'steps': 24040, 'loss/train': 0.08993315696716309}
+08/30/2021 17:30:13 - INFO - __main__ - Step 24042: {'lr': 0.0004731334262450666, 'samples': 4616064, 'steps': 24041, 'loss/train': 2.274127244949341}
+08/30/2021 17:30:15 - INFO - __main__ - Step 24043: {'lr': 0.00047313103295555317, 'samples': 4616256, 'steps': 24042, 'loss/train': 1.7268720865249634}
+08/30/2021 17:30:15 - INFO - __main__ - Step 24044: {'lr': 0.0004731286395655003, 'samples': 4616448, 'steps': 24043, 'loss/train': 1.7036787271499634}
+08/30/2021 17:30:15 - INFO - __main__ - Step 24045: {'lr': 0.00047312624607490913, 'samples': 4616640, 'steps': 24044, 'loss/train': 1.509076714515686}
+08/30/2021 17:30:16 - INFO - __main__ - Step 24046: {'lr': 0.0004731238524837807, 'samples': 4616832, 'steps': 24045, 'loss/train': 0.5438427329063416}
+08/30/2021 17:30:16 - INFO - __main__ - Step 24047: {'lr': 0.00047312145879211607, 'samples': 4617024, 'steps': 24046, 'loss/train': 1.9037859439849854}
+08/30/2021 17:30:18 - INFO - __main__ - Step 24048: {'lr': 0.0004731190649999164, 'samples': 4617216, 'steps': 24047, 'loss/train': 1.426287293434143}
+08/30/2021 17:30:18 - INFO - __main__ - Step 24049: {'lr': 0.0004731166711071827, 'samples': 4617408, 'steps': 24048, 'loss/train': 1.7205524444580078}
+08/30/2021 17:30:18 - INFO - __main__ - Step 24050: {'lr': 0.0004731142771139161, 'samples': 4617600, 'steps': 24049, 'loss/train': 1.7110624313354492}
+08/30/2021 17:30:19 - INFO - __main__ - Step 24051: {'lr': 0.00047311188302011766, 'samples': 4617792, 'steps': 24050, 'loss/train': 1.59541654586792}
+08/30/2021 17:30:19 - INFO - __main__ - Step 24052: {'lr': 0.00047310948882578843, 'samples': 4617984, 'steps': 24051, 'loss/train': 1.8222190141677856}
+08/30/2021 17:30:19 - INFO - __main__ - Step 24053: {'lr': 0.0004731070945309295, 'samples': 4618176, 'steps': 24052, 'loss/train': 1.5752980709075928}
+08/30/2021 17:30:21 - INFO - __main__ - Step 24054: {'lr': 0.00047310470013554195, 'samples': 4618368, 'steps': 24053, 'loss/train': 1.4789464473724365}
+08/30/2021 17:30:21 - INFO - __main__ - Step 24055: {'lr': 0.0004731023056396269, 'samples': 4618560, 'steps': 24054, 'loss/train': 1.7332782745361328}
+08/30/2021 17:30:22 - INFO - __main__ - Step 24056: {'lr': 0.00047309991104318533, 'samples': 4618752, 'steps': 24055, 'loss/train': 1.697275161743164}
+08/30/2021 17:30:22 - INFO - __main__ - Step 24057: {'lr': 0.00047309751634621845, 'samples': 4618944, 'steps': 24056, 'loss/train': 1.4491691589355469}
+08/30/2021 17:30:22 - INFO - __main__ - Step 24058: {'lr': 0.0004730951215487272, 'samples': 4619136, 'steps': 24057, 'loss/train': 1.2856816053390503}
+08/30/2021 17:30:24 - INFO - __main__ - Step 24059: {'lr': 0.0004730927266507128, 'samples': 4619328, 'steps': 24058, 'loss/train': 1.5663295984268188}
+08/30/2021 17:30:24 - INFO - __main__ - Step 24060: {'lr': 0.00047309033165217617, 'samples': 4619520, 'steps': 24059, 'loss/train': 2.148709535598755}
+08/30/2021 17:30:25 - INFO - __main__ - Step 24061: {'lr': 0.00047308793655311855, 'samples': 4619712, 'steps': 24060, 'loss/train': 1.327816128730774}
+08/30/2021 17:30:25 - INFO - __main__ - Step 24062: {'lr': 0.000473085541353541, 'samples': 4619904, 'steps': 24061, 'loss/train': 1.5505187511444092}
+08/30/2021 17:30:25 - INFO - __main__ - Step 24063: {'lr': 0.00047308314605344447, 'samples': 4620096, 'steps': 24062, 'loss/train': 1.7892699241638184}
+08/30/2021 17:30:28 - INFO - __main__ - Step 24064: {'lr': 0.00047308075065283006, 'samples': 4620288, 'steps': 24063, 'loss/train': 0.2885242700576782}
+08/30/2021 17:30:28 - INFO - __main__ - Step 24065: {'lr': 0.00047307835515169905, 'samples': 4620480, 'steps': 24064, 'loss/train': 1.5652493238449097}
+08/30/2021 17:30:29 - INFO - __main__ - Step 24066: {'lr': 0.00047307595955005226, 'samples': 4620672, 'steps': 24065, 'loss/train': 1.5013893842697144}
+08/30/2021 17:30:29 - INFO - __main__ - Step 24067: {'lr': 0.000473073563847891, 'samples': 4620864, 'steps': 24066, 'loss/train': 1.1477336883544922}
+08/30/2021 17:30:29 - INFO - __main__ - Step 24068: {'lr': 0.0004730711680452161, 'samples': 4621056, 'steps': 24067, 'loss/train': 1.3155384063720703}
+08/30/2021 17:30:30 - INFO - __main__ - Step 24069: {'lr': 0.00047306877214202885, 'samples': 4621248, 'steps': 24068, 'loss/train': 1.609187364578247}
+08/30/2021 17:30:31 - INFO - __main__ - Step 24070: {'lr': 0.00047306637613833024, 'samples': 4621440, 'steps': 24069, 'loss/train': 0.14481352269649506}
+08/30/2021 17:30:32 - INFO - __main__ - Step 24071: {'lr': 0.00047306398003412137, 'samples': 4621632, 'steps': 24070, 'loss/train': 1.548281192779541}
+08/30/2021 17:30:32 - INFO - __main__ - Step 24072: {'lr': 0.00047306158382940327, 'samples': 4621824, 'steps': 24071, 'loss/train': 1.4533778429031372}
+08/30/2021 17:30:32 - INFO - __main__ - Step 24073: {'lr': 0.0004730591875241771, 'samples': 4622016, 'steps': 24072, 'loss/train': 1.5265815258026123}
+08/30/2021 17:30:33 - INFO - __main__ - Step 24074: {'lr': 0.0004730567911184439, 'samples': 4622208, 'steps': 24073, 'loss/train': 1.9236773252487183}
+08/30/2021 17:30:34 - INFO - __main__ - Step 24075: {'lr': 0.00047305439461220477, 'samples': 4622400, 'steps': 24074, 'loss/train': 1.5820451974868774}
+08/30/2021 17:30:35 - INFO - __main__ - Step 24076: {'lr': 0.00047305199800546077, 'samples': 4622592, 'steps': 24075, 'loss/train': 1.6401923894882202}
+08/30/2021 17:30:35 - INFO - __main__ - Step 24077: {'lr': 0.00047304960129821295, 'samples': 4622784, 'steps': 24076, 'loss/train': 1.445767879486084}
+08/30/2021 17:30:35 - INFO - __main__ - Step 24078: {'lr': 0.00047304720449046247, 'samples': 4622976, 'steps': 24077, 'loss/train': 1.603904366493225}
+08/30/2021 17:30:36 - INFO - __main__ - Step 24079: {'lr': 0.0004730448075822103, 'samples': 4623168, 'steps': 24078, 'loss/train': 1.342221975326538}
+08/30/2021 17:30:37 - INFO - __main__ - Step 24080: {'lr': 0.0004730424105734576, 'samples': 4623360, 'steps': 24079, 'loss/train': 1.8074901103973389}
+08/30/2021 17:30:38 - INFO - __main__ - Step 24081: {'lr': 0.00047304001346420543, 'samples': 4623552, 'steps': 24080, 'loss/train': 1.4292932748794556}
+08/30/2021 17:30:38 - INFO - __main__ - Step 24082: {'lr': 0.0004730376162544549, 'samples': 4623744, 'steps': 24081, 'loss/train': 1.706549048423767}
+08/30/2021 17:30:38 - INFO - __main__ - Step 24083: {'lr': 0.00047303521894420707, 'samples': 4623936, 'steps': 24082, 'loss/train': 1.5007423162460327}
+08/30/2021 17:30:39 - INFO - __main__ - Step 24084: {'lr': 0.00047303282153346297, 'samples': 4624128, 'steps': 24083, 'loss/train': 1.8951566219329834}
+08/30/2021 17:30:40 - INFO - __main__ - Step 24085: {'lr': 0.00047303042402222373, 'samples': 4624320, 'steps': 24084, 'loss/train': 1.940564751625061}
+08/30/2021 17:30:41 - INFO - __main__ - Step 24086: {'lr': 0.00047302802641049045, 'samples': 4624512, 'steps': 24085, 'loss/train': 1.6670588254928589}
+08/30/2021 17:30:41 - INFO - __main__ - Step 24087: {'lr': 0.00047302562869826415, 'samples': 4624704, 'steps': 24086, 'loss/train': 1.5259641408920288}
+08/30/2021 17:30:41 - INFO - __main__ - Step 24088: {'lr': 0.000473023230885546, 'samples': 4624896, 'steps': 24087, 'loss/train': 1.1554542779922485}
+08/30/2021 17:30:42 - INFO - __main__ - Step 24089: {'lr': 0.00047302083297233693, 'samples': 4625088, 'steps': 24088, 'loss/train': 0.5441455245018005}
+08/30/2021 17:30:43 - INFO - __main__ - Step 24090: {'lr': 0.0004730184349586382, 'samples': 4625280, 'steps': 24089, 'loss/train': 1.6687731742858887}
+08/30/2021 17:30:44 - INFO - __main__ - Step 24091: {'lr': 0.0004730160368444507, 'samples': 4625472, 'steps': 24090, 'loss/train': 1.3922580480575562}
+08/30/2021 17:30:44 - INFO - __main__ - Step 24092: {'lr': 0.00047301363862977574, 'samples': 4625664, 'steps': 24091, 'loss/train': 1.4776488542556763}
+08/30/2021 17:30:44 - INFO - __main__ - Step 24093: {'lr': 0.00047301124031461425, 'samples': 4625856, 'steps': 24092, 'loss/train': 2.0109939575195312}
+08/30/2021 17:30:45 - INFO - __main__ - Step 24094: {'lr': 0.00047300884189896734, 'samples': 4626048, 'steps': 24093, 'loss/train': 1.547519564628601}
+08/30/2021 17:30:46 - INFO - __main__ - Step 24095: {'lr': 0.00047300644338283597, 'samples': 4626240, 'steps': 24094, 'loss/train': 1.7417045831680298}
+08/30/2021 17:30:47 - INFO - __main__ - Step 24096: {'lr': 0.00047300404476622145, 'samples': 4626432, 'steps': 24095, 'loss/train': 1.456769585609436}
+08/30/2021 17:30:47 - INFO - __main__ - Step 24097: {'lr': 0.0004730016460491247, 'samples': 4626624, 'steps': 24096, 'loss/train': 1.4040253162384033}
+08/30/2021 17:30:47 - INFO - __main__ - Step 24098: {'lr': 0.00047299924723154686, 'samples': 4626816, 'steps': 24097, 'loss/train': 1.5261404514312744}
+08/30/2021 17:30:48 - INFO - __main__ - Step 24099: {'lr': 0.000472996848313489, 'samples': 4627008, 'steps': 24098, 'loss/train': 1.7699613571166992}
+08/30/2021 17:30:49 - INFO - __main__ - Step 24100: {'lr': 0.0004729944492949523, 'samples': 4627200, 'steps': 24099, 'loss/train': 1.2860987186431885}
+08/30/2021 17:30:50 - INFO - __main__ - Step 24101: {'lr': 0.0004729920501759376, 'samples': 4627392, 'steps': 24100, 'loss/train': 1.514662742614746}
+08/30/2021 17:30:50 - INFO - __main__ - Step 24102: {'lr': 0.0004729896509564462, 'samples': 4627584, 'steps': 24101, 'loss/train': 0.47807011008262634}
+08/30/2021 17:30:50 - INFO - __main__ - Step 24103: {'lr': 0.00047298725163647903, 'samples': 4627776, 'steps': 24102, 'loss/train': 2.083526372909546}
+08/30/2021 17:30:51 - INFO - __main__ - Step 24104: {'lr': 0.00047298485221603735, 'samples': 4627968, 'steps': 24103, 'loss/train': 1.6912801265716553}
+08/30/2021 17:30:52 - INFO - __main__ - Step 24105: {'lr': 0.0004729824526951221, 'samples': 4628160, 'steps': 24104, 'loss/train': 1.7747036218643188}
+08/30/2021 17:30:53 - INFO - __main__ - Step 24106: {'lr': 0.0004729800530737344, 'samples': 4628352, 'steps': 24105, 'loss/train': 1.7489311695098877}
+08/30/2021 17:30:53 - INFO - __main__ - Step 24107: {'lr': 0.0004729776533518753, 'samples': 4628544, 'steps': 24106, 'loss/train': 1.7768486738204956}
+08/30/2021 17:30:53 - INFO - __main__ - Step 24108: {'lr': 0.00047297525352954587, 'samples': 4628736, 'steps': 24107, 'loss/train': 0.32257765531539917}
+08/30/2021 17:30:54 - INFO - __main__ - Step 24109: {'lr': 0.00047297285360674724, 'samples': 4628928, 'steps': 24108, 'loss/train': 1.5983144044876099}
+08/30/2021 17:30:56 - INFO - __main__ - Step 24110: {'lr': 0.0004729704535834806, 'samples': 4629120, 'steps': 24109, 'loss/train': 0.20864179730415344}
+08/30/2021 17:30:57 - INFO - __main__ - Step 24111: {'lr': 0.0004729680534597468, 'samples': 4629312, 'steps': 24110, 'loss/train': 1.459895372390747}
+08/30/2021 17:30:57 - INFO - __main__ - Step 24112: {'lr': 0.0004729656532355471, 'samples': 4629504, 'steps': 24111, 'loss/train': 1.8617894649505615}
+08/30/2021 17:30:57 - INFO - __main__ - Step 24113: {'lr': 0.00047296325291088247, 'samples': 4629696, 'steps': 24112, 'loss/train': 1.8113024234771729}
+08/30/2021 17:30:58 - INFO - __main__ - Step 24114: {'lr': 0.00047296085248575405, 'samples': 4629888, 'steps': 24113, 'loss/train': 1.8138296604156494}
+08/30/2021 17:30:58 - INFO - __main__ - Step 24115: {'lr': 0.000472958451960163, 'samples': 4630080, 'steps': 24114, 'loss/train': 1.3801623582839966}
+08/30/2021 17:30:58 - INFO - __main__ - Step 24116: {'lr': 0.0004729560513341101, 'samples': 4630272, 'steps': 24115, 'loss/train': 0.46274125576019287}
+08/30/2021 17:31:00 - INFO - __main__ - Step 24117: {'lr': 0.0004729536506075969, 'samples': 4630464, 'steps': 24116, 'loss/train': 1.6889135837554932}
+08/30/2021 17:31:01 - INFO - __main__ - Step 24118: {'lr': 0.000472951249780624, 'samples': 4630656, 'steps': 24117, 'loss/train': 0.9251886010169983}
+08/30/2021 17:31:01 - INFO - __main__ - Step 24119: {'lr': 0.0004729488488531928, 'samples': 4630848, 'steps': 24118, 'loss/train': 1.5236133337020874}
+08/30/2021 17:31:01 - INFO - __main__ - Step 24120: {'lr': 0.00047294644782530437, 'samples': 4631040, 'steps': 24119, 'loss/train': 1.7088730335235596}
+08/30/2021 17:31:02 - INFO - __main__ - Step 24121: {'lr': 0.0004729440466969596, 'samples': 4631232, 'steps': 24120, 'loss/train': 1.5327494144439697}
+08/30/2021 17:31:03 - INFO - __main__ - Step 24122: {'lr': 0.00047294164546815977, 'samples': 4631424, 'steps': 24121, 'loss/train': 1.44022798538208}
+08/30/2021 17:31:04 - INFO - __main__ - Step 24123: {'lr': 0.0004729392441389058, 'samples': 4631616, 'steps': 24122, 'loss/train': 1.5222587585449219}
+08/30/2021 17:31:04 - INFO - __main__ - Step 24124: {'lr': 0.0004729368427091989, 'samples': 4631808, 'steps': 24123, 'loss/train': 1.7540864944458008}
+08/30/2021 17:31:04 - INFO - __main__ - Step 24125: {'lr': 0.0004729344411790401, 'samples': 4632000, 'steps': 24124, 'loss/train': 1.841918706893921}
+08/30/2021 17:31:05 - INFO - __main__ - Step 24126: {'lr': 0.00047293203954843036, 'samples': 4632192, 'steps': 24125, 'loss/train': 1.6288747787475586}
+08/30/2021 17:31:05 - INFO - __main__ - Step 24127: {'lr': 0.000472929637817371, 'samples': 4632384, 'steps': 24126, 'loss/train': 2.0986011028289795}
+08/30/2021 17:31:07 - INFO - __main__ - Step 24128: {'lr': 0.00047292723598586295, 'samples': 4632576, 'steps': 24127, 'loss/train': 1.5108201503753662}
+08/30/2021 17:31:07 - INFO - __main__ - Step 24129: {'lr': 0.0004729248340539074, 'samples': 4632768, 'steps': 24128, 'loss/train': 2.7759737968444824}
+08/30/2021 17:31:08 - INFO - __main__ - Step 24130: {'lr': 0.00047292243202150524, 'samples': 4632960, 'steps': 24129, 'loss/train': 1.0917391777038574}
+08/30/2021 17:31:08 - INFO - __main__ - Step 24131: {'lr': 0.00047292002988865773, 'samples': 4633152, 'steps': 24130, 'loss/train': 1.4824484586715698}
+08/30/2021 17:31:08 - INFO - __main__ - Step 24132: {'lr': 0.0004729176276553659, 'samples': 4633344, 'steps': 24131, 'loss/train': 2.507643938064575}
+08/30/2021 17:31:10 - INFO - __main__ - Step 24133: {'lr': 0.00047291522532163084, 'samples': 4633536, 'steps': 24132, 'loss/train': 1.381656289100647}
+08/30/2021 17:31:10 - INFO - __main__ - Step 24134: {'lr': 0.0004729128228874536, 'samples': 4633728, 'steps': 24133, 'loss/train': 1.7645857334136963}
+08/30/2021 17:31:11 - INFO - __main__ - Step 24135: {'lr': 0.0004729104203528353, 'samples': 4633920, 'steps': 24134, 'loss/train': 1.740995168685913}
+08/30/2021 17:31:11 - INFO - __main__ - Step 24136: {'lr': 0.0004729080177177769, 'samples': 4634112, 'steps': 24135, 'loss/train': 1.6431689262390137}
+08/30/2021 17:31:11 - INFO - __main__ - Step 24137: {'lr': 0.0004729056149822797, 'samples': 4634304, 'steps': 24136, 'loss/train': 2.0831339359283447}
+08/30/2021 17:31:13 - INFO - __main__ - Step 24138: {'lr': 0.0004729032121463447, 'samples': 4634496, 'steps': 24137, 'loss/train': 1.8646323680877686}
+08/30/2021 17:31:13 - INFO - __main__ - Step 24139: {'lr': 0.00047290080920997285, 'samples': 4634688, 'steps': 24138, 'loss/train': 1.3936610221862793}
+08/30/2021 17:31:14 - INFO - __main__ - Step 24140: {'lr': 0.0004728984061731654, 'samples': 4634880, 'steps': 24139, 'loss/train': 1.1847268342971802}
+08/30/2021 17:31:14 - INFO - __main__ - Step 24141: {'lr': 0.00047289600303592334, 'samples': 4635072, 'steps': 24140, 'loss/train': 2.7018134593963623}
+08/30/2021 17:31:14 - INFO - __main__ - Step 24142: {'lr': 0.00047289359979824774, 'samples': 4635264, 'steps': 24141, 'loss/train': 1.3059297800064087}
+08/30/2021 17:31:15 - INFO - __main__ - Step 24143: {'lr': 0.0004728911964601398, 'samples': 4635456, 'steps': 24142, 'loss/train': 1.1995608806610107}
+08/30/2021 17:31:16 - INFO - __main__ - Step 24144: {'lr': 0.00047288879302160046, 'samples': 4635648, 'steps': 24143, 'loss/train': 1.5299186706542969}
+08/30/2021 17:31:17 - INFO - __main__ - Step 24145: {'lr': 0.000472886389482631, 'samples': 4635840, 'steps': 24144, 'loss/train': 1.3630061149597168}
+08/30/2021 17:31:17 - INFO - __main__ - Step 24146: {'lr': 0.00047288398584323225, 'samples': 4636032, 'steps': 24145, 'loss/train': 1.2673616409301758}
+08/30/2021 17:31:18 - INFO - __main__ - Step 24147: {'lr': 0.0004728815821034055, 'samples': 4636224, 'steps': 24146, 'loss/train': 1.2929073572158813}
+08/30/2021 17:31:18 - INFO - __main__ - Step 24148: {'lr': 0.00047287917826315163, 'samples': 4636416, 'steps': 24147, 'loss/train': 1.5669113397598267}
+08/30/2021 17:31:19 - INFO - __main__ - Step 24149: {'lr': 0.00047287677432247187, 'samples': 4636608, 'steps': 24148, 'loss/train': 1.558624267578125}
+08/30/2021 17:31:20 - INFO - __main__ - Step 24150: {'lr': 0.0004728743702813674, 'samples': 4636800, 'steps': 24149, 'loss/train': 1.7655826807022095}
+08/30/2021 17:31:20 - INFO - __main__ - Step 24151: {'lr': 0.00047287196613983906, 'samples': 4636992, 'steps': 24150, 'loss/train': 1.4004069566726685}
+08/30/2021 17:31:21 - INFO - __main__ - Step 24152: {'lr': 0.00047286956189788803, 'samples': 4637184, 'steps': 24151, 'loss/train': 1.6315075159072876}
+08/30/2021 17:31:21 - INFO - __main__ - Step 24153: {'lr': 0.0004728671575555155, 'samples': 4637376, 'steps': 24152, 'loss/train': 1.4012001752853394}
+08/30/2021 17:31:23 - INFO - __main__ - Step 24154: {'lr': 0.00047286475311272244, 'samples': 4637568, 'steps': 24153, 'loss/train': 1.7974354028701782}
+08/30/2021 17:31:23 - INFO - __main__ - Step 24155: {'lr': 0.00047286234856950995, 'samples': 4637760, 'steps': 24154, 'loss/train': 1.489810585975647}
+08/30/2021 17:31:23 - INFO - __main__ - Step 24156: {'lr': 0.0004728599439258791, 'samples': 4637952, 'steps': 24155, 'loss/train': 0.9652630686759949}
+08/30/2021 17:31:24 - INFO - __main__ - Step 24157: {'lr': 0.00047285753918183105, 'samples': 4638144, 'steps': 24156, 'loss/train': 1.7588778734207153}
+08/30/2021 17:31:24 - INFO - __main__ - Step 24158: {'lr': 0.0004728551343373668, 'samples': 4638336, 'steps': 24157, 'loss/train': 1.049881935119629}
+08/30/2021 17:31:26 - INFO - __main__ - Step 24159: {'lr': 0.0004728527293924875, 'samples': 4638528, 'steps': 24158, 'loss/train': 1.8188709020614624}
+08/30/2021 17:31:26 - INFO - __main__ - Step 24160: {'lr': 0.0004728503243471941, 'samples': 4638720, 'steps': 24159, 'loss/train': 1.3873933553695679}
+08/30/2021 17:31:26 - INFO - __main__ - Step 24161: {'lr': 0.00047284791920148786, 'samples': 4638912, 'steps': 24160, 'loss/train': 1.9750440120697021}
+08/30/2021 17:31:27 - INFO - __main__ - Step 24162: {'lr': 0.0004728455139553698, 'samples': 4639104, 'steps': 24161, 'loss/train': 1.8615262508392334}
+08/30/2021 17:31:27 - INFO - __main__ - Step 24163: {'lr': 0.00047284310860884097, 'samples': 4639296, 'steps': 24162, 'loss/train': 0.7791587114334106}
+08/30/2021 17:31:27 - INFO - __main__ - Step 24164: {'lr': 0.0004728407031619025, 'samples': 4639488, 'steps': 24163, 'loss/train': 1.7196199893951416}
+08/30/2021 17:31:29 - INFO - __main__ - Step 24165: {'lr': 0.00047283829761455545, 'samples': 4639680, 'steps': 24164, 'loss/train': 1.6915156841278076}
+08/30/2021 17:31:29 - INFO - __main__ - Step 24166: {'lr': 0.00047283589196680083, 'samples': 4639872, 'steps': 24165, 'loss/train': 1.31031334400177}
+08/30/2021 17:31:30 - INFO - __main__ - Step 24167: {'lr': 0.00047283348621863987, 'samples': 4640064, 'steps': 24166, 'loss/train': 2.1443991661071777}
+08/30/2021 17:31:30 - INFO - __main__ - Step 24168: {'lr': 0.0004728310803700735, 'samples': 4640256, 'steps': 24167, 'loss/train': 1.0439376831054688}
+08/30/2021 17:31:30 - INFO - __main__ - Step 24169: {'lr': 0.00047282867442110296, 'samples': 4640448, 'steps': 24168, 'loss/train': 1.2532795667648315}
+08/30/2021 17:31:32 - INFO - __main__ - Step 24170: {'lr': 0.0004728262683717292, 'samples': 4640640, 'steps': 24169, 'loss/train': 1.6778916120529175}
+08/30/2021 17:31:32 - INFO - __main__ - Step 24171: {'lr': 0.0004728238622219534, 'samples': 4640832, 'steps': 24170, 'loss/train': 0.9244217872619629}
+08/30/2021 17:31:33 - INFO - __main__ - Step 24172: {'lr': 0.0004728214559717766, 'samples': 4641024, 'steps': 24171, 'loss/train': 1.2623051404953003}
+08/30/2021 17:31:33 - INFO - __main__ - Step 24173: {'lr': 0.0004728190496211999, 'samples': 4641216, 'steps': 24172, 'loss/train': 0.8274864554405212}
+08/30/2021 17:31:33 - INFO - __main__ - Step 24174: {'lr': 0.0004728166431702243, 'samples': 4641408, 'steps': 24173, 'loss/train': 0.09556277096271515}
+08/30/2021 17:31:36 - INFO - __main__ - Step 24175: {'lr': 0.0004728142366188511, 'samples': 4641600, 'steps': 24174, 'loss/train': 1.373371958732605}
+08/30/2021 17:31:36 - INFO - __main__ - Step 24176: {'lr': 0.0004728118299670812, 'samples': 4641792, 'steps': 24175, 'loss/train': 1.5632140636444092}
+08/30/2021 17:31:36 - INFO - __main__ - Step 24177: {'lr': 0.0004728094232149156, 'samples': 4641984, 'steps': 24176, 'loss/train': 1.4556348323822021}
+08/30/2021 17:31:37 - INFO - __main__ - Step 24178: {'lr': 0.0004728070163623557, 'samples': 4642176, 'steps': 24177, 'loss/train': 1.4671134948730469}
+08/30/2021 17:31:37 - INFO - __main__ - Step 24179: {'lr': 0.00047280460940940224, 'samples': 4642368, 'steps': 24178, 'loss/train': 1.8795233964920044}
+08/30/2021 17:31:39 - INFO - __main__ - Step 24180: {'lr': 0.00047280220235605653, 'samples': 4642560, 'steps': 24179, 'loss/train': 1.7222018241882324}
+08/30/2021 17:31:39 - INFO - __main__ - Step 24181: {'lr': 0.00047279979520231956, 'samples': 4642752, 'steps': 24180, 'loss/train': 1.2071528434753418}
+08/30/2021 17:31:40 - INFO - __main__ - Step 24182: {'lr': 0.0004727973879481925, 'samples': 4642944, 'steps': 24181, 'loss/train': 1.6211045980453491}
+08/30/2021 17:31:40 - INFO - __main__ - Step 24183: {'lr': 0.0004727949805936763, 'samples': 4643136, 'steps': 24182, 'loss/train': 0.08287215232849121}
+08/30/2021 17:31:40 - INFO - __main__ - Step 24184: {'lr': 0.00047279257313877216, 'samples': 4643328, 'steps': 24183, 'loss/train': 1.7023415565490723}
+08/30/2021 17:31:42 - INFO - __main__ - Step 24185: {'lr': 0.00047279016558348107, 'samples': 4643520, 'steps': 24184, 'loss/train': 1.1026681661605835}
+08/30/2021 17:31:42 - INFO - __main__ - Step 24186: {'lr': 0.00047278775792780424, 'samples': 4643712, 'steps': 24185, 'loss/train': 1.096640706062317}
+08/30/2021 17:31:43 - INFO - __main__ - Step 24187: {'lr': 0.00047278535017174266, 'samples': 4643904, 'steps': 24186, 'loss/train': 1.5994592905044556}
+08/30/2021 17:31:43 - INFO - __main__ - Step 24188: {'lr': 0.00047278294231529745, 'samples': 4644096, 'steps': 24187, 'loss/train': 1.5921953916549683}
+08/30/2021 17:31:43 - INFO - __main__ - Step 24189: {'lr': 0.0004727805343584697, 'samples': 4644288, 'steps': 24188, 'loss/train': 2.005462646484375}
+08/30/2021 17:31:44 - INFO - __main__ - Step 24190: {'lr': 0.00047277812630126044, 'samples': 4644480, 'steps': 24189, 'loss/train': 1.9981228113174438}
+08/30/2021 17:31:45 - INFO - __main__ - Step 24191: {'lr': 0.0004727757181436708, 'samples': 4644672, 'steps': 24190, 'loss/train': 2.7588233947753906}
+08/30/2021 17:31:46 - INFO - __main__ - Step 24192: {'lr': 0.0004727733098857019, 'samples': 4644864, 'steps': 24191, 'loss/train': 1.3896721601486206}
+08/30/2021 17:31:46 - INFO - __main__ - Step 24193: {'lr': 0.0004727709015273547, 'samples': 4645056, 'steps': 24192, 'loss/train': 1.611689567565918}
+08/30/2021 17:31:46 - INFO - __main__ - Step 24194: {'lr': 0.00047276849306863045, 'samples': 4645248, 'steps': 24193, 'loss/train': 1.6118241548538208}
+08/30/2021 17:31:47 - INFO - __main__ - Step 24195: {'lr': 0.0004727660845095301, 'samples': 4645440, 'steps': 24194, 'loss/train': 1.285235047340393}
+08/30/2021 17:31:48 - INFO - __main__ - Step 24196: {'lr': 0.0004727636758500548, 'samples': 4645632, 'steps': 24195, 'loss/train': 2.496720552444458}
+08/30/2021 17:31:49 - INFO - __main__ - Step 24197: {'lr': 0.0004727612670902057, 'samples': 4645824, 'steps': 24196, 'loss/train': 1.511696457862854}
+08/30/2021 17:31:49 - INFO - __main__ - Step 24198: {'lr': 0.0004727588582299837, 'samples': 4646016, 'steps': 24197, 'loss/train': 1.4814748764038086}
+08/30/2021 17:31:50 - INFO - __main__ - Step 24199: {'lr': 0.00047275644926939004, 'samples': 4646208, 'steps': 24198, 'loss/train': 1.5196963548660278}
+08/30/2021 17:31:50 - INFO - __main__ - Step 24200: {'lr': 0.0004727540402084258, 'samples': 4646400, 'steps': 24199, 'loss/train': 0.9592801332473755}
+08/30/2021 17:31:52 - INFO - __main__ - Step 24201: {'lr': 0.00047275163104709196, 'samples': 4646592, 'steps': 24200, 'loss/train': 1.3029142618179321}
+08/30/2021 17:31:52 - INFO - __main__ - Step 24202: {'lr': 0.0004727492217853897, 'samples': 4646784, 'steps': 24201, 'loss/train': 1.6478257179260254}
+08/30/2021 17:31:53 - INFO - __main__ - Step 24203: {'lr': 0.0004727468124233201, 'samples': 4646976, 'steps': 24202, 'loss/train': 0.0755089670419693}
+08/30/2021 17:31:53 - INFO - __main__ - Step 24204: {'lr': 0.0004727444029608842, 'samples': 4647168, 'steps': 24203, 'loss/train': 1.6308687925338745}
+08/30/2021 17:31:53 - INFO - __main__ - Step 24205: {'lr': 0.0004727419933980831, 'samples': 4647360, 'steps': 24204, 'loss/train': 0.07464733719825745}
+08/30/2021 17:31:54 - INFO - __main__ - Step 24206: {'lr': 0.00047273958373491795, 'samples': 4647552, 'steps': 24205, 'loss/train': 1.1177918910980225}
+08/30/2021 17:31:55 - INFO - __main__ - Step 24207: {'lr': 0.0004727371739713897, 'samples': 4647744, 'steps': 24206, 'loss/train': 1.2107316255569458}
+08/30/2021 17:31:56 - INFO - __main__ - Step 24208: {'lr': 0.0004727347641074996, 'samples': 4647936, 'steps': 24207, 'loss/train': 0.38301005959510803}
+08/30/2021 17:31:56 - INFO - __main__ - Step 24209: {'lr': 0.0004727323541432486, 'samples': 4648128, 'steps': 24208, 'loss/train': 1.2750030755996704}
+08/30/2021 17:31:56 - INFO - __main__ - Step 24210: {'lr': 0.0004727299440786378, 'samples': 4648320, 'steps': 24209, 'loss/train': 0.07609347999095917}
+08/30/2021 17:31:57 - INFO - __main__ - Step 24211: {'lr': 0.0004727275339136684, 'samples': 4648512, 'steps': 24210, 'loss/train': 1.7404375076293945}
+08/30/2021 17:31:58 - INFO - __main__ - Step 24212: {'lr': 0.0004727251236483414, 'samples': 4648704, 'steps': 24211, 'loss/train': 1.6821720600128174}
+08/30/2021 17:31:59 - INFO - __main__ - Step 24213: {'lr': 0.0004727227132826579, 'samples': 4648896, 'steps': 24212, 'loss/train': 0.4785604774951935}
+08/30/2021 17:31:59 - INFO - __main__ - Step 24214: {'lr': 0.00047272030281661894, 'samples': 4649088, 'steps': 24213, 'loss/train': 1.7701137065887451}
+08/30/2021 17:31:59 - INFO - __main__ - Step 24215: {'lr': 0.0004727178922502257, 'samples': 4649280, 'steps': 24214, 'loss/train': 1.6530342102050781}
+08/30/2021 17:32:00 - INFO - __main__ - Step 24216: {'lr': 0.00047271548158347917, 'samples': 4649472, 'steps': 24215, 'loss/train': 1.57979154586792}
+08/30/2021 17:32:01 - INFO - __main__ - Step 24217: {'lr': 0.00047271307081638047, 'samples': 4649664, 'steps': 24216, 'loss/train': 1.8712079524993896}
+08/30/2021 17:32:02 - INFO - __main__ - Step 24218: {'lr': 0.0004727106599489307, 'samples': 4649856, 'steps': 24217, 'loss/train': 1.3714122772216797}
+08/30/2021 17:32:02 - INFO - __main__ - Step 24219: {'lr': 0.000472708248981131, 'samples': 4650048, 'steps': 24218, 'loss/train': 1.398590087890625}
+08/30/2021 17:32:03 - INFO - __main__ - Step 24220: {'lr': 0.0004727058379129824, 'samples': 4650240, 'steps': 24219, 'loss/train': 2.153866767883301}
+08/30/2021 17:32:03 - INFO - __main__ - Step 24221: {'lr': 0.00047270342674448593, 'samples': 4650432, 'steps': 24220, 'loss/train': 1.706506371498108}
+08/30/2021 17:32:03 - INFO - __main__ - Step 24222: {'lr': 0.0004727010154756427, 'samples': 4650624, 'steps': 24221, 'loss/train': 1.6973432302474976}
+08/30/2021 17:32:05 - INFO - __main__ - Step 24223: {'lr': 0.00047269860410645395, 'samples': 4650816, 'steps': 24222, 'loss/train': 0.9720464944839478}
+08/30/2021 17:32:05 - INFO - __main__ - Step 24224: {'lr': 0.00047269619263692056, 'samples': 4651008, 'steps': 24223, 'loss/train': 1.3337974548339844}
+08/30/2021 17:32:06 - INFO - __main__ - Step 24225: {'lr': 0.0004726937810670437, 'samples': 4651200, 'steps': 24224, 'loss/train': 1.5803866386413574}
+08/30/2021 17:32:06 - INFO - __main__ - Step 24226: {'lr': 0.00047269136939682445, 'samples': 4651392, 'steps': 24225, 'loss/train': 2.019972801208496}
+08/30/2021 17:32:06 - INFO - __main__ - Step 24227: {'lr': 0.00047268895762626396, 'samples': 4651584, 'steps': 24226, 'loss/train': 1.2218983173370361}
+08/30/2021 17:32:08 - INFO - __main__ - Step 24228: {'lr': 0.00047268654575536326, 'samples': 4651776, 'steps': 24227, 'loss/train': 1.298556923866272}
+08/30/2021 17:32:09 - INFO - __main__ - Step 24229: {'lr': 0.0004726841337841234, 'samples': 4651968, 'steps': 24228, 'loss/train': 1.2394062280654907}
+08/30/2021 17:32:09 - INFO - __main__ - Step 24230: {'lr': 0.00047268172171254554, 'samples': 4652160, 'steps': 24229, 'loss/train': 0.9660944938659668}
+08/30/2021 17:32:09 - INFO - __main__ - Step 24231: {'lr': 0.00047267930954063064, 'samples': 4652352, 'steps': 24230, 'loss/train': 1.059150218963623}
+08/30/2021 17:32:10 - INFO - __main__ - Step 24232: {'lr': 0.00047267689726838004, 'samples': 4652544, 'steps': 24231, 'loss/train': 1.8086531162261963}
+08/30/2021 17:32:12 - INFO - __main__ - Step 24233: {'lr': 0.00047267448489579455, 'samples': 4652736, 'steps': 24232, 'loss/train': 1.8478260040283203}
+08/30/2021 17:32:12 - INFO - __main__ - Step 24234: {'lr': 0.00047267207242287536, 'samples': 4652928, 'steps': 24233, 'loss/train': 1.5857752561569214}
+08/30/2021 17:32:12 - INFO - __main__ - Step 24235: {'lr': 0.0004726696598496236, 'samples': 4653120, 'steps': 24234, 'loss/train': 0.16051620244979858}
+08/30/2021 17:32:13 - INFO - __main__ - Step 24236: {'lr': 0.0004726672471760404, 'samples': 4653312, 'steps': 24235, 'loss/train': 1.6289249658584595}
+08/30/2021 17:32:13 - INFO - __main__ - Step 24237: {'lr': 0.0004726648344021267, 'samples': 4653504, 'steps': 24236, 'loss/train': 1.943662405014038}
+08/30/2021 17:32:14 - INFO - __main__ - Step 24238: {'lr': 0.0004726624215278836, 'samples': 4653696, 'steps': 24237, 'loss/train': 1.3714585304260254}
+08/30/2021 17:32:15 - INFO - __main__ - Step 24239: {'lr': 0.0004726600085533124, 'samples': 4653888, 'steps': 24238, 'loss/train': 0.8313621282577515}
+08/30/2021 17:32:16 - INFO - __main__ - Step 24240: {'lr': 0.0004726575954784139, 'samples': 4654080, 'steps': 24239, 'loss/train': 1.6338189840316772}
+08/30/2021 17:32:16 - INFO - __main__ - Step 24241: {'lr': 0.0004726551823031894, 'samples': 4654272, 'steps': 24240, 'loss/train': 0.32059958577156067}
+08/30/2021 17:32:16 - INFO - __main__ - Step 24242: {'lr': 0.0004726527690276399, 'samples': 4654464, 'steps': 24241, 'loss/train': 1.0379594564437866}
+08/30/2021 17:32:17 - INFO - __main__ - Step 24243: {'lr': 0.0004726503556517665, 'samples': 4654656, 'steps': 24242, 'loss/train': 0.9742986559867859}
+08/30/2021 17:32:19 - INFO - __main__ - Step 24244: {'lr': 0.0004726479421755703, 'samples': 4654848, 'steps': 24243, 'loss/train': 1.7805272340774536}
+08/30/2021 17:32:19 - INFO - __main__ - Step 24245: {'lr': 0.0004726455285990523, 'samples': 4655040, 'steps': 24244, 'loss/train': 1.415780782699585}
+08/30/2021 17:32:20 - INFO - __main__ - Step 24246: {'lr': 0.00047264311492221375, 'samples': 4655232, 'steps': 24245, 'loss/train': 1.180909514427185}
+08/30/2021 17:32:20 - INFO - __main__ - Step 24247: {'lr': 0.00047264070114505556, 'samples': 4655424, 'steps': 24246, 'loss/train': 1.2102290391921997}
+08/30/2021 17:32:20 - INFO - __main__ - Step 24248: {'lr': 0.00047263828726757897, 'samples': 4655616, 'steps': 24247, 'loss/train': 1.481451153755188}
+08/30/2021 17:32:21 - INFO - __main__ - Step 24249: {'lr': 0.00047263587328978495, 'samples': 4655808, 'steps': 24248, 'loss/train': 0.053167395293712616}
+08/30/2021 17:32:22 - INFO - __main__ - Step 24250: {'lr': 0.00047263345921167473, 'samples': 4656000, 'steps': 24249, 'loss/train': 0.05923473462462425}
+08/30/2021 17:32:23 - INFO - __main__ - Step 24251: {'lr': 0.00047263104503324926, 'samples': 4656192, 'steps': 24250, 'loss/train': 1.8162950277328491}
+08/30/2021 17:32:23 - INFO - __main__ - Step 24252: {'lr': 0.00047262863075450966, 'samples': 4656384, 'steps': 24251, 'loss/train': 1.594192624092102}
+08/30/2021 17:32:23 - INFO - __main__ - Step 24253: {'lr': 0.0004726262163754571, 'samples': 4656576, 'steps': 24252, 'loss/train': 1.113451361656189}
+08/30/2021 17:32:24 - INFO - __main__ - Step 24254: {'lr': 0.00047262380189609253, 'samples': 4656768, 'steps': 24253, 'loss/train': 1.1306809186935425}
+08/30/2021 17:32:25 - INFO - __main__ - Step 24255: {'lr': 0.0004726213873164171, 'samples': 4656960, 'steps': 24254, 'loss/train': 1.96120285987854}
+08/30/2021 17:32:25 - INFO - __main__ - Step 24256: {'lr': 0.00047261897263643196, 'samples': 4657152, 'steps': 24255, 'loss/train': 1.1570863723754883}
+08/30/2021 17:32:26 - INFO - __main__ - Step 24257: {'lr': 0.0004726165578561381, 'samples': 4657344, 'steps': 24256, 'loss/train': 1.8087940216064453}
+08/30/2021 17:32:26 - INFO - __main__ - Step 24258: {'lr': 0.0004726141429755367, 'samples': 4657536, 'steps': 24257, 'loss/train': 1.9370120763778687}
+08/30/2021 17:32:27 - INFO - __main__ - Step 24259: {'lr': 0.0004726117279946288, 'samples': 4657728, 'steps': 24258, 'loss/train': 1.0272470712661743}
+08/30/2021 17:32:27 - INFO - __main__ - Step 24260: {'lr': 0.0004726093129134155, 'samples': 4657920, 'steps': 24259, 'loss/train': 1.2489008903503418}
+08/30/2021 17:32:28 - INFO - __main__ - Step 24261: {'lr': 0.0004726068977318978, 'samples': 4658112, 'steps': 24260, 'loss/train': 1.3908486366271973}
+08/30/2021 17:32:29 - INFO - __main__ - Step 24262: {'lr': 0.0004726044824500769, 'samples': 4658304, 'steps': 24261, 'loss/train': 1.5788671970367432}
+08/30/2021 17:32:29 - INFO - __main__ - Step 24263: {'lr': 0.0004726020670679538, 'samples': 4658496, 'steps': 24262, 'loss/train': 1.5976192951202393}
+08/30/2021 17:32:29 - INFO - __main__ - Step 24264: {'lr': 0.00047259965158552976, 'samples': 4658688, 'steps': 24263, 'loss/train': 1.7133711576461792}
+08/30/2021 17:32:30 - INFO - __main__ - Step 24265: {'lr': 0.00047259723600280573, 'samples': 4658880, 'steps': 24264, 'loss/train': 1.972362756729126}
+08/30/2021 17:32:31 - INFO - __main__ - Step 24266: {'lr': 0.0004725948203197828, 'samples': 4659072, 'steps': 24265, 'loss/train': 1.0435600280761719}
+08/30/2021 17:32:32 - INFO - __main__ - Step 24267: {'lr': 0.0004725924045364621, 'samples': 4659264, 'steps': 24266, 'loss/train': 1.598348617553711}
+08/30/2021 17:32:32 - INFO - __main__ - Step 24268: {'lr': 0.00047258998865284463, 'samples': 4659456, 'steps': 24267, 'loss/train': 1.8444726467132568}
+08/30/2021 17:32:32 - INFO - __main__ - Step 24269: {'lr': 0.0004725875726689316, 'samples': 4659648, 'steps': 24268, 'loss/train': 1.5474190711975098}
+08/30/2021 17:32:33 - INFO - __main__ - Step 24270: {'lr': 0.000472585156584724, 'samples': 4659840, 'steps': 24269, 'loss/train': 0.962842583656311}
+08/30/2021 17:32:35 - INFO - __main__ - Step 24271: {'lr': 0.00047258274040022305, 'samples': 4660032, 'steps': 24270, 'loss/train': 1.7693638801574707}
+08/30/2021 17:32:35 - INFO - __main__ - Step 24272: {'lr': 0.0004725803241154297, 'samples': 4660224, 'steps': 24271, 'loss/train': 1.7162286043167114}
+08/30/2021 17:32:36 - INFO - __main__ - Step 24273: {'lr': 0.0004725779077303451, 'samples': 4660416, 'steps': 24272, 'loss/train': 1.45207679271698}
+08/30/2021 17:32:36 - INFO - __main__ - Step 24274: {'lr': 0.0004725754912449703, 'samples': 4660608, 'steps': 24273, 'loss/train': 1.6680254936218262}
+08/30/2021 17:32:36 - INFO - __main__ - Step 24275: {'lr': 0.0004725730746593064, 'samples': 4660800, 'steps': 24274, 'loss/train': 1.67513906955719}
+08/30/2021 17:32:37 - INFO - __main__ - Step 24276: {'lr': 0.0004725706579733546, 'samples': 4660992, 'steps': 24275, 'loss/train': 0.5670360326766968}
+08/30/2021 17:32:38 - INFO - __main__ - Step 24277: {'lr': 0.00047256824118711583, 'samples': 4661184, 'steps': 24276, 'loss/train': 0.58359295129776}
+08/30/2021 17:32:39 - INFO - __main__ - Step 24278: {'lr': 0.00047256582430059126, 'samples': 4661376, 'steps': 24277, 'loss/train': 1.6768839359283447}
+08/30/2021 17:32:39 - INFO - __main__ - Step 24279: {'lr': 0.00047256340731378194, 'samples': 4661568, 'steps': 24278, 'loss/train': 1.20183527469635}
+08/30/2021 17:32:39 - INFO - __main__ - Step 24280: {'lr': 0.00047256099022668896, 'samples': 4661760, 'steps': 24279, 'loss/train': 1.9832605123519897}
+08/30/2021 17:32:40 - INFO - __main__ - Step 24281: {'lr': 0.00047255857303931347, 'samples': 4661952, 'steps': 24280, 'loss/train': 1.5650697946548462}
+08/30/2021 17:32:42 - INFO - __main__ - Step 24282: {'lr': 0.00047255615575165653, 'samples': 4662144, 'steps': 24281, 'loss/train': 1.5526493787765503}
+08/30/2021 17:32:42 - INFO - __main__ - Step 24283: {'lr': 0.0004725537383637193, 'samples': 4662336, 'steps': 24282, 'loss/train': 1.8533439636230469}
+08/30/2021 17:32:42 - INFO - __main__ - Step 24284: {'lr': 0.0004725513208755027, 'samples': 4662528, 'steps': 24283, 'loss/train': 1.8512705564498901}
+08/30/2021 17:32:43 - INFO - __main__ - Step 24285: {'lr': 0.0004725489032870079, 'samples': 4662720, 'steps': 24284, 'loss/train': 1.6501190662384033}
+08/30/2021 17:32:43 - INFO - __main__ - Step 24286: {'lr': 0.000472546485598236, 'samples': 4662912, 'steps': 24285, 'loss/train': 1.2825064659118652}
+08/30/2021 17:32:45 - INFO - __main__ - Step 24287: {'lr': 0.0004725440678091881, 'samples': 4663104, 'steps': 24286, 'loss/train': 1.427514672279358}
+08/30/2021 17:32:45 - INFO - __main__ - Step 24288: {'lr': 0.00047254164991986525, 'samples': 4663296, 'steps': 24287, 'loss/train': 1.4465891122817993}
+08/30/2021 17:32:46 - INFO - __main__ - Step 24289: {'lr': 0.0004725392319302686, 'samples': 4663488, 'steps': 24288, 'loss/train': 1.5587409734725952}
+08/30/2021 17:32:46 - INFO - __main__ - Step 24290: {'lr': 0.0004725368138403992, 'samples': 4663680, 'steps': 24289, 'loss/train': 2.178434371948242}
+08/30/2021 17:32:46 - INFO - __main__ - Step 24291: {'lr': 0.00047253439565025815, 'samples': 4663872, 'steps': 24290, 'loss/train': 1.6974729299545288}
+08/30/2021 17:32:47 - INFO - __main__ - Step 24292: {'lr': 0.00047253197735984653, 'samples': 4664064, 'steps': 24291, 'loss/train': 1.7663254737854004}
+08/30/2021 17:32:48 - INFO - __main__ - Step 24293: {'lr': 0.00047252955896916546, 'samples': 4664256, 'steps': 24292, 'loss/train': 0.25294041633605957}
+08/30/2021 17:32:49 - INFO - __main__ - Step 24294: {'lr': 0.000472527140478216, 'samples': 4664448, 'steps': 24293, 'loss/train': 1.2851003408432007}
+08/30/2021 17:32:49 - INFO - __main__ - Step 24295: {'lr': 0.00047252472188699917, 'samples': 4664640, 'steps': 24294, 'loss/train': 1.701158046722412}
+08/30/2021 17:32:49 - INFO - __main__ - Step 24296: {'lr': 0.0004725223031955162, 'samples': 4664832, 'steps': 24295, 'loss/train': 1.6793968677520752}
+08/30/2021 17:32:50 - INFO - __main__ - Step 24297: {'lr': 0.0004725198844037681, 'samples': 4665024, 'steps': 24296, 'loss/train': 1.1335865259170532}
+08/30/2021 17:32:51 - INFO - __main__ - Step 24298: {'lr': 0.00047251746551175603, 'samples': 4665216, 'steps': 24297, 'loss/train': 3.253445863723755}
+08/30/2021 17:32:52 - INFO - __main__ - Step 24299: {'lr': 0.000472515046519481, 'samples': 4665408, 'steps': 24298, 'loss/train': 1.2532851696014404}
+08/30/2021 17:32:52 - INFO - __main__ - Step 24300: {'lr': 0.000472512627426944, 'samples': 4665600, 'steps': 24299, 'loss/train': 1.5509803295135498}
+08/30/2021 17:32:52 - INFO - __main__ - Step 24301: {'lr': 0.0004725102082341464, 'samples': 4665792, 'steps': 24300, 'loss/train': 1.648585319519043}
+08/30/2021 17:32:53 - INFO - __main__ - Step 24302: {'lr': 0.00047250778894108905, 'samples': 4665984, 'steps': 24301, 'loss/train': 1.331283688545227}
+08/30/2021 17:32:54 - INFO - __main__ - Step 24303: {'lr': 0.0004725053695477731, 'samples': 4666176, 'steps': 24302, 'loss/train': 1.0451349020004272}
+08/30/2021 17:32:55 - INFO - __main__ - Step 24304: {'lr': 0.0004725029500541997, 'samples': 4666368, 'steps': 24303, 'loss/train': 2.3015499114990234}
+08/30/2021 17:32:55 - INFO - __main__ - Step 24305: {'lr': 0.00047250053046036996, 'samples': 4666560, 'steps': 24304, 'loss/train': 1.9148674011230469}
+08/30/2021 17:32:55 - INFO - __main__ - Step 24306: {'lr': 0.00047249811076628483, 'samples': 4666752, 'steps': 24305, 'loss/train': 1.507433533668518}
+08/30/2021 17:32:56 - INFO - __main__ - Step 24307: {'lr': 0.00047249569097194554, 'samples': 4666944, 'steps': 24306, 'loss/train': 1.850820779800415}
+08/30/2021 17:32:58 - INFO - __main__ - Step 24308: {'lr': 0.0004724932710773531, 'samples': 4667136, 'steps': 24307, 'loss/train': 1.5423920154571533}
+08/30/2021 17:32:58 - INFO - __main__ - Step 24309: {'lr': 0.00047249085108250867, 'samples': 4667328, 'steps': 24308, 'loss/train': 1.714725375175476}
+08/30/2021 17:32:59 - INFO - __main__ - Step 24310: {'lr': 0.0004724884309874132, 'samples': 4667520, 'steps': 24309, 'loss/train': 1.6923638582229614}
+08/30/2021 17:32:59 - INFO - __main__ - Step 24311: {'lr': 0.00047248601079206797, 'samples': 4667712, 'steps': 24310, 'loss/train': 1.9769870042800903}
+08/30/2021 17:32:59 - INFO - __main__ - Step 24312: {'lr': 0.0004724835904964739, 'samples': 4667904, 'steps': 24311, 'loss/train': 1.5941286087036133}
+08/30/2021 17:33:00 - INFO - __main__ - Step 24313: {'lr': 0.0004724811701006322, 'samples': 4668096, 'steps': 24312, 'loss/train': 0.18794506788253784}
+08/30/2021 17:33:01 - INFO - __main__ - Step 24314: {'lr': 0.00047247874960454394, 'samples': 4668288, 'steps': 24313, 'loss/train': 1.3424668312072754}
+08/30/2021 17:33:02 - INFO - __main__ - Step 24315: {'lr': 0.0004724763290082102, 'samples': 4668480, 'steps': 24314, 'loss/train': 2.002727746963501}
+08/30/2021 17:33:02 - INFO - __main__ - Step 24316: {'lr': 0.000472473908311632, 'samples': 4668672, 'steps': 24315, 'loss/train': 1.3826675415039062}
+08/30/2021 17:33:02 - INFO - __main__ - Step 24317: {'lr': 0.0004724714875148105, 'samples': 4668864, 'steps': 24316, 'loss/train': 1.2146414518356323}
+08/30/2021 17:33:03 - INFO - __main__ - Step 24318: {'lr': 0.0004724690666177468, 'samples': 4669056, 'steps': 24317, 'loss/train': 1.3559935092926025}
+08/30/2021 17:33:04 - INFO - __main__ - Step 24319: {'lr': 0.00047246664562044193, 'samples': 4669248, 'steps': 24318, 'loss/train': 1.227448582649231}
+08/30/2021 17:33:05 - INFO - __main__ - Step 24320: {'lr': 0.0004724642245228971, 'samples': 4669440, 'steps': 24319, 'loss/train': 1.6217232942581177}
+08/30/2021 17:33:05 - INFO - __main__ - Step 24321: {'lr': 0.0004724618033251133, 'samples': 4669632, 'steps': 24320, 'loss/train': 2.008260726928711}
+08/30/2021 17:33:05 - INFO - __main__ - Step 24322: {'lr': 0.0004724593820270916, 'samples': 4669824, 'steps': 24321, 'loss/train': 1.8731880187988281}
+08/30/2021 17:33:06 - INFO - __main__ - Step 24323: {'lr': 0.00047245696062883316, 'samples': 4670016, 'steps': 24322, 'loss/train': 1.4362927675247192}
+08/30/2021 17:33:07 - INFO - __main__ - Step 24324: {'lr': 0.0004724545391303391, 'samples': 4670208, 'steps': 24323, 'loss/train': 1.5768028497695923}
+08/30/2021 17:33:08 - INFO - __main__ - Step 24325: {'lr': 0.0004724521175316103, 'samples': 4670400, 'steps': 24324, 'loss/train': 1.0141940116882324}
+08/30/2021 17:33:08 - INFO - __main__ - Step 24326: {'lr': 0.0004724496958326482, 'samples': 4670592, 'steps': 24325, 'loss/train': 1.013269305229187}
+08/30/2021 17:33:08 - INFO - __main__ - Step 24327: {'lr': 0.00047244727403345356, 'samples': 4670784, 'steps': 24326, 'loss/train': 1.1677967309951782}
+08/30/2021 17:33:09 - INFO - __main__ - Step 24328: {'lr': 0.00047244485213402765, 'samples': 4670976, 'steps': 24327, 'loss/train': 1.6913164854049683}
+08/30/2021 17:33:10 - INFO - __main__ - Step 24329: {'lr': 0.0004724424301343716, 'samples': 4671168, 'steps': 24328, 'loss/train': 1.6653810739517212}
+08/30/2021 17:33:11 - INFO - __main__ - Step 24330: {'lr': 0.00047244000803448635, 'samples': 4671360, 'steps': 24329, 'loss/train': 0.9741966724395752}
+08/30/2021 17:33:11 - INFO - __main__ - Step 24331: {'lr': 0.000472437585834373, 'samples': 4671552, 'steps': 24330, 'loss/train': 1.6117873191833496}
+08/30/2021 17:33:12 - INFO - __main__ - Step 24332: {'lr': 0.00047243516353403283, 'samples': 4671744, 'steps': 24331, 'loss/train': 1.9478338956832886}
+08/30/2021 17:33:12 - INFO - __main__ - Step 24333: {'lr': 0.0004724327411334668, 'samples': 4671936, 'steps': 24332, 'loss/train': 1.7630128860473633}
+08/30/2021 17:33:12 - INFO - __main__ - Step 24334: {'lr': 0.00047243031863267594, 'samples': 4672128, 'steps': 24333, 'loss/train': 1.1125938892364502}
+08/30/2021 17:33:14 - INFO - __main__ - Step 24335: {'lr': 0.0004724278960316615, 'samples': 4672320, 'steps': 24334, 'loss/train': 1.0044838190078735}
+08/30/2021 17:33:14 - INFO - __main__ - Step 24336: {'lr': 0.00047242547333042434, 'samples': 4672512, 'steps': 24335, 'loss/train': 1.2330117225646973}
+08/30/2021 17:33:15 - INFO - __main__ - Step 24337: {'lr': 0.0004724230505289658, 'samples': 4672704, 'steps': 24336, 'loss/train': 1.748183250427246}
+08/30/2021 17:33:15 - INFO - __main__ - Step 24338: {'lr': 0.0004724206276272868, 'samples': 4672896, 'steps': 24337, 'loss/train': 1.4580626487731934}
+08/30/2021 17:33:15 - INFO - __main__ - Step 24339: {'lr': 0.0004724182046253885, 'samples': 4673088, 'steps': 24338, 'loss/train': 0.9954025149345398}
+08/30/2021 17:33:17 - INFO - __main__ - Step 24340: {'lr': 0.0004724157815232721, 'samples': 4673280, 'steps': 24339, 'loss/train': 1.7079565525054932}
+08/30/2021 17:33:18 - INFO - __main__ - Step 24341: {'lr': 0.00047241335832093844, 'samples': 4673472, 'steps': 24340, 'loss/train': 1.7329707145690918}
+08/30/2021 17:33:18 - INFO - __main__ - Step 24342: {'lr': 0.00047241093501838887, 'samples': 4673664, 'steps': 24341, 'loss/train': 1.664844274520874}
+08/30/2021 17:33:19 - INFO - __main__ - Step 24343: {'lr': 0.00047240851161562433, 'samples': 4673856, 'steps': 24342, 'loss/train': 1.1673303842544556}
+08/30/2021 17:33:19 - INFO - __main__ - Step 24344: {'lr': 0.00047240608811264595, 'samples': 4674048, 'steps': 24343, 'loss/train': 1.3469853401184082}
+08/30/2021 17:33:21 - INFO - __main__ - Step 24345: {'lr': 0.0004724036645094548, 'samples': 4674240, 'steps': 24344, 'loss/train': 1.9298440217971802}
+08/30/2021 17:33:21 - INFO - __main__ - Step 24346: {'lr': 0.00047240124080605197, 'samples': 4674432, 'steps': 24345, 'loss/train': 1.7860263586044312}
+08/30/2021 17:33:21 - INFO - __main__ - Step 24347: {'lr': 0.0004723988170024386, 'samples': 4674624, 'steps': 24346, 'loss/train': 1.76042902469635}
+08/30/2021 17:33:22 - INFO - __main__ - Step 24348: {'lr': 0.0004723963930986157, 'samples': 4674816, 'steps': 24347, 'loss/train': 1.1373618841171265}
+08/30/2021 17:33:22 - INFO - __main__ - Step 24349: {'lr': 0.0004723939690945845, 'samples': 4675008, 'steps': 24348, 'loss/train': 0.9944627285003662}
+08/30/2021 17:33:22 - INFO - __main__ - Step 24350: {'lr': 0.000472391544990346, 'samples': 4675200, 'steps': 24349, 'loss/train': 1.1673153638839722}
+08/30/2021 17:33:24 - INFO - __main__ - Step 24351: {'lr': 0.0004723891207859012, 'samples': 4675392, 'steps': 24350, 'loss/train': 1.4055306911468506}
+08/30/2021 17:33:24 - INFO - __main__ - Step 24352: {'lr': 0.00047238669648125146, 'samples': 4675584, 'steps': 24351, 'loss/train': 2.0462114810943604}
+08/30/2021 17:33:25 - INFO - __main__ - Step 24353: {'lr': 0.00047238427207639755, 'samples': 4675776, 'steps': 24352, 'loss/train': 1.9095929861068726}
+08/30/2021 17:33:25 - INFO - __main__ - Step 24354: {'lr': 0.0004723818475713408, 'samples': 4675968, 'steps': 24353, 'loss/train': 1.2838232517242432}
+08/30/2021 17:33:25 - INFO - __main__ - Step 24355: {'lr': 0.00047237942296608223, 'samples': 4676160, 'steps': 24354, 'loss/train': 1.488679051399231}
+08/30/2021 17:33:27 - INFO - __main__ - Step 24356: {'lr': 0.00047237699826062286, 'samples': 4676352, 'steps': 24355, 'loss/train': 1.953740119934082}
+08/30/2021 17:33:27 - INFO - __main__ - Step 24357: {'lr': 0.0004723745734549639, 'samples': 4676544, 'steps': 24356, 'loss/train': 1.2457115650177002}
+08/30/2021 17:33:28 - INFO - __main__ - Step 24358: {'lr': 0.0004723721485491064, 'samples': 4676736, 'steps': 24357, 'loss/train': 1.6974021196365356}
+08/30/2021 17:33:28 - INFO - __main__ - Step 24359: {'lr': 0.0004723697235430514, 'samples': 4676928, 'steps': 24358, 'loss/train': 1.1630061864852905}
+08/30/2021 17:33:29 - INFO - __main__ - Step 24360: {'lr': 0.0004723672984368, 'samples': 4677120, 'steps': 24359, 'loss/train': 2.0134353637695312}
+08/30/2021 17:33:29 - INFO - __main__ - Step 24361: {'lr': 0.00047236487323035344, 'samples': 4677312, 'steps': 24360, 'loss/train': 1.538875699043274}
+08/30/2021 17:33:30 - INFO - __main__ - Step 24362: {'lr': 0.00047236244792371265, 'samples': 4677504, 'steps': 24361, 'loss/train': 1.7127004861831665}
+08/30/2021 17:33:31 - INFO - __main__ - Step 24363: {'lr': 0.0004723600225168787, 'samples': 4677696, 'steps': 24362, 'loss/train': 1.7155966758728027}
+08/30/2021 17:33:31 - INFO - __main__ - Step 24364: {'lr': 0.0004723575970098528, 'samples': 4677888, 'steps': 24363, 'loss/train': 1.8337619304656982}
+08/30/2021 17:33:31 - INFO - __main__ - Step 24365: {'lr': 0.00047235517140263605, 'samples': 4678080, 'steps': 24364, 'loss/train': 1.7331677675247192}
+08/30/2021 17:33:32 - INFO - __main__ - Step 24366: {'lr': 0.00047235274569522946, 'samples': 4678272, 'steps': 24365, 'loss/train': 1.7484673261642456}
+08/30/2021 17:33:33 - INFO - __main__ - Step 24367: {'lr': 0.0004723503198876341, 'samples': 4678464, 'steps': 24366, 'loss/train': 1.4265400171279907}
+08/30/2021 17:33:34 - INFO - __main__ - Step 24368: {'lr': 0.0004723478939798512, 'samples': 4678656, 'steps': 24367, 'loss/train': 1.637850284576416}
+08/30/2021 17:33:34 - INFO - __main__ - Step 24369: {'lr': 0.0004723454679718817, 'samples': 4678848, 'steps': 24368, 'loss/train': 1.5267797708511353}
+08/30/2021 17:33:34 - INFO - __main__ - Step 24370: {'lr': 0.00047234304186372685, 'samples': 4679040, 'steps': 24369, 'loss/train': 1.452715277671814}
+08/30/2021 17:33:35 - INFO - __main__ - Step 24371: {'lr': 0.00047234061565538753, 'samples': 4679232, 'steps': 24370, 'loss/train': 1.788153886795044}
+08/30/2021 17:33:36 - INFO - __main__ - Step 24372: {'lr': 0.0004723381893468651, 'samples': 4679424, 'steps': 24371, 'loss/train': 1.638181209564209}
+08/30/2021 17:33:37 - INFO - __main__ - Step 24373: {'lr': 0.00047233576293816045, 'samples': 4679616, 'steps': 24372, 'loss/train': 2.1719155311584473}
+08/30/2021 17:33:37 - INFO - __main__ - Step 24374: {'lr': 0.00047233333642927465, 'samples': 4679808, 'steps': 24373, 'loss/train': 1.6320966482162476}
+08/30/2021 17:33:37 - INFO - __main__ - Step 24375: {'lr': 0.000472330909820209, 'samples': 4680000, 'steps': 24374, 'loss/train': 2.1833300590515137}
+08/30/2021 17:33:38 - INFO - __main__ - Step 24376: {'lr': 0.0004723284831109644, 'samples': 4680192, 'steps': 24375, 'loss/train': 1.494808554649353}
+08/30/2021 17:33:39 - INFO - __main__ - Step 24377: {'lr': 0.0004723260563015421, 'samples': 4680384, 'steps': 24376, 'loss/train': 1.3499294519424438}
+08/30/2021 17:33:40 - INFO - __main__ - Step 24378: {'lr': 0.00047232362939194305, 'samples': 4680576, 'steps': 24377, 'loss/train': 1.245821475982666}
+08/30/2021 17:33:40 - INFO - __main__ - Step 24379: {'lr': 0.0004723212023821684, 'samples': 4680768, 'steps': 24378, 'loss/train': 1.4235199689865112}
+08/30/2021 17:33:40 - INFO - __main__ - Step 24380: {'lr': 0.0004723187752722193, 'samples': 4680960, 'steps': 24379, 'loss/train': 1.8682743310928345}
+08/30/2021 17:33:41 - INFO - __main__ - Step 24381: {'lr': 0.00047231634806209675, 'samples': 4681152, 'steps': 24380, 'loss/train': 1.592482328414917}
+08/30/2021 17:33:42 - INFO - __main__ - Step 24382: {'lr': 0.0004723139207518019, 'samples': 4681344, 'steps': 24381, 'loss/train': 1.9671236276626587}
+08/30/2021 17:33:43 - INFO - __main__ - Step 24383: {'lr': 0.00047231149334133577, 'samples': 4681536, 'steps': 24382, 'loss/train': 1.4625492095947266}
+08/30/2021 17:33:43 - INFO - __main__ - Step 24384: {'lr': 0.00047230906583069953, 'samples': 4681728, 'steps': 24383, 'loss/train': 0.7411932945251465}
+08/30/2021 17:33:44 - INFO - __main__ - Step 24385: {'lr': 0.0004723066382198943, 'samples': 4681920, 'steps': 24384, 'loss/train': 1.7482298612594604}
+08/30/2021 17:33:44 - INFO - __main__ - Step 24386: {'lr': 0.00047230421050892116, 'samples': 4682112, 'steps': 24385, 'loss/train': 1.3088852167129517}
+08/30/2021 17:33:46 - INFO - __main__ - Step 24387: {'lr': 0.00047230178269778105, 'samples': 4682304, 'steps': 24386, 'loss/train': 1.6270971298217773}
+08/30/2021 17:33:46 - INFO - __main__ - Step 24388: {'lr': 0.00047229935478647524, 'samples': 4682496, 'steps': 24387, 'loss/train': 1.438279628753662}
+08/30/2021 17:33:47 - INFO - __main__ - Step 24389: {'lr': 0.0004722969267750048, 'samples': 4682688, 'steps': 24388, 'loss/train': 0.08078933507204056}
+08/30/2021 17:33:47 - INFO - __main__ - Step 24390: {'lr': 0.0004722944986633708, 'samples': 4682880, 'steps': 24389, 'loss/train': 1.1382778882980347}
+08/30/2021 17:33:47 - INFO - __main__ - Step 24391: {'lr': 0.0004722920704515743, 'samples': 4683072, 'steps': 24390, 'loss/train': 1.44602370262146}
+08/30/2021 17:33:48 - INFO - __main__ - Step 24392: {'lr': 0.00047228964213961647, 'samples': 4683264, 'steps': 24391, 'loss/train': 1.3812720775604248}
+08/30/2021 17:33:48 - INFO - __main__ - Step 24393: {'lr': 0.00047228721372749826, 'samples': 4683456, 'steps': 24392, 'loss/train': 1.5855101346969604}
+08/30/2021 17:33:50 - INFO - __main__ - Step 24394: {'lr': 0.000472284785215221, 'samples': 4683648, 'steps': 24393, 'loss/train': 1.642717957496643}
+08/30/2021 17:33:51 - INFO - __main__ - Step 24395: {'lr': 0.0004722823566027855, 'samples': 4683840, 'steps': 24394, 'loss/train': 1.7613502740859985}
+08/30/2021 17:33:51 - INFO - __main__ - Step 24396: {'lr': 0.00047227992789019316, 'samples': 4684032, 'steps': 24395, 'loss/train': 1.6548693180084229}
+08/30/2021 17:33:51 - INFO - __main__ - Step 24397: {'lr': 0.0004722774990774448, 'samples': 4684224, 'steps': 24396, 'loss/train': 1.6467336416244507}
+08/30/2021 17:33:52 - INFO - __main__ - Step 24398: {'lr': 0.00047227507016454163, 'samples': 4684416, 'steps': 24397, 'loss/train': 1.679891586303711}
+08/30/2021 17:33:53 - INFO - __main__ - Step 24399: {'lr': 0.00047227264115148475, 'samples': 4684608, 'steps': 24398, 'loss/train': 1.6772023439407349}
+08/30/2021 17:33:54 - INFO - __main__ - Step 24400: {'lr': 0.00047227021203827523, 'samples': 4684800, 'steps': 24399, 'loss/train': 1.7842049598693848}
+08/30/2021 17:33:54 - INFO - __main__ - Step 24401: {'lr': 0.0004722677828249142, 'samples': 4684992, 'steps': 24400, 'loss/train': 1.0591225624084473}
+08/30/2021 17:33:54 - INFO - __main__ - Step 24402: {'lr': 0.0004722653535114028, 'samples': 4685184, 'steps': 24401, 'loss/train': 1.6557775735855103}
+08/30/2021 17:33:55 - INFO - __main__ - Step 24403: {'lr': 0.00047226292409774205, 'samples': 4685376, 'steps': 24402, 'loss/train': 0.9989805817604065}
+08/30/2021 17:33:56 - INFO - __main__ - Step 24404: {'lr': 0.00047226049458393306, 'samples': 4685568, 'steps': 24403, 'loss/train': 1.0077651739120483}
+08/30/2021 17:33:57 - INFO - __main__ - Step 24405: {'lr': 0.0004722580649699768, 'samples': 4685760, 'steps': 24404, 'loss/train': 1.518217921257019}
+08/30/2021 17:33:57 - INFO - __main__ - Step 24406: {'lr': 0.00047225563525587463, 'samples': 4685952, 'steps': 24405, 'loss/train': 1.2954621315002441}
+08/30/2021 17:33:57 - INFO - __main__ - Step 24407: {'lr': 0.0004722532054416274, 'samples': 4686144, 'steps': 24406, 'loss/train': 2.0343549251556396}
+08/30/2021 17:33:58 - INFO - __main__ - Step 24408: {'lr': 0.0004722507755272364, 'samples': 4686336, 'steps': 24407, 'loss/train': 1.5305819511413574}
+08/30/2021 17:33:58 - INFO - __main__ - Step 24409: {'lr': 0.0004722483455127026, 'samples': 4686528, 'steps': 24408, 'loss/train': 1.5015907287597656}
+08/30/2021 17:34:00 - INFO - __main__ - Step 24410: {'lr': 0.000472245915398027, 'samples': 4686720, 'steps': 24409, 'loss/train': 0.2329707145690918}
+08/30/2021 17:34:00 - INFO - __main__ - Step 24411: {'lr': 0.0004722434851832109, 'samples': 4686912, 'steps': 24410, 'loss/train': 0.9077503085136414}
+08/30/2021 17:34:00 - INFO - __main__ - Step 24412: {'lr': 0.00047224105486825543, 'samples': 4687104, 'steps': 24411, 'loss/train': 1.0722583532333374}
+08/30/2021 17:34:01 - INFO - __main__ - Step 24413: {'lr': 0.0004722386244531615, 'samples': 4687296, 'steps': 24412, 'loss/train': 1.7993780374526978}
+08/30/2021 17:34:01 - INFO - __main__ - Step 24414: {'lr': 0.0004722361939379302, 'samples': 4687488, 'steps': 24413, 'loss/train': 0.5120288133621216}
+08/30/2021 17:34:03 - INFO - __main__ - Step 24415: {'lr': 0.0004722337633225627, 'samples': 4687680, 'steps': 24414, 'loss/train': 1.5795621871948242}
+08/30/2021 17:34:03 - INFO - __main__ - Step 24416: {'lr': 0.0004722313326070602, 'samples': 4687872, 'steps': 24415, 'loss/train': 1.7287003993988037}
+08/30/2021 17:34:04 - INFO - __main__ - Step 24417: {'lr': 0.00047222890179142365, 'samples': 4688064, 'steps': 24416, 'loss/train': 1.6448042392730713}
+08/30/2021 17:34:04 - INFO - __main__ - Step 24418: {'lr': 0.00047222647087565413, 'samples': 4688256, 'steps': 24417, 'loss/train': 1.8849087953567505}
+08/30/2021 17:34:04 - INFO - __main__ - Step 24419: {'lr': 0.0004722240398597528, 'samples': 4688448, 'steps': 24418, 'loss/train': 1.5503348112106323}
+08/30/2021 17:34:06 - INFO - __main__ - Step 24420: {'lr': 0.0004722216087437208, 'samples': 4688640, 'steps': 24419, 'loss/train': 1.3734948635101318}
+08/30/2021 17:34:06 - INFO - __main__ - Step 24421: {'lr': 0.0004722191775275592, 'samples': 4688832, 'steps': 24420, 'loss/train': 1.6976292133331299}
+08/30/2021 17:34:07 - INFO - __main__ - Step 24422: {'lr': 0.00047221674621126896, 'samples': 4689024, 'steps': 24421, 'loss/train': 1.557907223701477}
+08/30/2021 17:34:07 - INFO - __main__ - Step 24423: {'lr': 0.0004722143147948513, 'samples': 4689216, 'steps': 24422, 'loss/train': 1.8630753755569458}
+08/30/2021 17:34:07 - INFO - __main__ - Step 24424: {'lr': 0.0004722118832783074, 'samples': 4689408, 'steps': 24423, 'loss/train': 1.3790898323059082}
+08/30/2021 17:34:09 - INFO - __main__ - Step 24425: {'lr': 0.0004722094516616382, 'samples': 4689600, 'steps': 24424, 'loss/train': 1.4910532236099243}
+08/30/2021 17:34:09 - INFO - __main__ - Step 24426: {'lr': 0.0004722070199448448, 'samples': 4689792, 'steps': 24425, 'loss/train': 1.119583010673523}
+08/30/2021 17:34:10 - INFO - __main__ - Step 24427: {'lr': 0.00047220458812792846, 'samples': 4689984, 'steps': 24426, 'loss/train': 1.6967073678970337}
+08/30/2021 17:34:10 - INFO - __main__ - Step 24428: {'lr': 0.00047220215621089005, 'samples': 4690176, 'steps': 24427, 'loss/train': 1.7348392009735107}
+08/30/2021 17:34:10 - INFO - __main__ - Step 24429: {'lr': 0.00047219972419373083, 'samples': 4690368, 'steps': 24428, 'loss/train': 2.005463123321533}
+08/30/2021 17:34:11 - INFO - __main__ - Step 24430: {'lr': 0.00047219729207645183, 'samples': 4690560, 'steps': 24429, 'loss/train': 1.2426892518997192}
+08/30/2021 17:34:12 - INFO - __main__ - Step 24431: {'lr': 0.0004721948598590542, 'samples': 4690752, 'steps': 24430, 'loss/train': 1.5733124017715454}
+08/30/2021 17:34:12 - INFO - __main__ - Step 24432: {'lr': 0.0004721924275415389, 'samples': 4690944, 'steps': 24431, 'loss/train': 1.5471230745315552}
+08/30/2021 17:34:13 - INFO - __main__ - Step 24433: {'lr': 0.0004721899951239072, 'samples': 4691136, 'steps': 24432, 'loss/train': 1.5222989320755005}
+08/30/2021 17:34:13 - INFO - __main__ - Step 24434: {'lr': 0.0004721875626061601, 'samples': 4691328, 'steps': 24433, 'loss/train': 1.4067974090576172}
+08/30/2021 17:34:14 - INFO - __main__ - Step 24435: {'lr': 0.00047218512998829874, 'samples': 4691520, 'steps': 24434, 'loss/train': 2.027573823928833}
+08/30/2021 17:34:15 - INFO - __main__ - Step 24436: {'lr': 0.00047218269727032413, 'samples': 4691712, 'steps': 24435, 'loss/train': 0.8910576701164246}
+08/30/2021 17:34:15 - INFO - __main__ - Step 24437: {'lr': 0.00047218026445223745, 'samples': 4691904, 'steps': 24436, 'loss/train': 1.7636796236038208}
+08/30/2021 17:34:16 - INFO - __main__ - Step 24438: {'lr': 0.0004721778315340398, 'samples': 4692096, 'steps': 24437, 'loss/train': 2.344608783721924}
+08/30/2021 17:34:16 - INFO - __main__ - Step 24439: {'lr': 0.0004721753985157322, 'samples': 4692288, 'steps': 24438, 'loss/train': 1.692981243133545}
+08/30/2021 17:34:17 - INFO - __main__ - Step 24440: {'lr': 0.0004721729653973158, 'samples': 4692480, 'steps': 24439, 'loss/train': 1.5303928852081299}
+08/30/2021 17:34:19 - INFO - __main__ - Step 24441: {'lr': 0.0004721705321787917, 'samples': 4692672, 'steps': 24440, 'loss/train': 1.9622113704681396}
+08/30/2021 17:34:20 - INFO - __main__ - Step 24442: {'lr': 0.00047216809886016097, 'samples': 4692864, 'steps': 24441, 'loss/train': 1.4492759704589844}
+08/30/2021 17:34:20 - INFO - __main__ - Step 24443: {'lr': 0.0004721656654414248, 'samples': 4693056, 'steps': 24442, 'loss/train': 2.025129795074463}
+08/30/2021 17:34:20 - INFO - __main__ - Step 24444: {'lr': 0.00047216323192258416, 'samples': 4693248, 'steps': 24443, 'loss/train': 1.435434103012085}
+08/30/2021 17:34:21 - INFO - __main__ - Step 24445: {'lr': 0.0004721607983036401, 'samples': 4693440, 'steps': 24444, 'loss/train': 1.6196428537368774}
+08/30/2021 17:34:21 - INFO - __main__ - Step 24446: {'lr': 0.00047215836458459393, 'samples': 4693632, 'steps': 24445, 'loss/train': 1.436138391494751}
+08/30/2021 17:34:23 - INFO - __main__ - Step 24447: {'lr': 0.00047215593076544663, 'samples': 4693824, 'steps': 24446, 'loss/train': 1.5719879865646362}
+08/30/2021 17:34:23 - INFO - __main__ - Step 24448: {'lr': 0.0004721534968461992, 'samples': 4694016, 'steps': 24447, 'loss/train': 2.2825469970703125}
+08/30/2021 17:34:24 - INFO - __main__ - Step 24449: {'lr': 0.00047215106282685296, 'samples': 4694208, 'steps': 24448, 'loss/train': 1.108061671257019}
+08/30/2021 17:34:24 - INFO - __main__ - Step 24450: {'lr': 0.0004721486287074088, 'samples': 4694400, 'steps': 24449, 'loss/train': 1.4066286087036133}
+08/30/2021 17:34:25 - INFO - __main__ - Step 24451: {'lr': 0.0004721461944878679, 'samples': 4694592, 'steps': 24450, 'loss/train': 1.2571030855178833}
+08/30/2021 17:34:26 - INFO - __main__ - Step 24452: {'lr': 0.00047214376016823143, 'samples': 4694784, 'steps': 24451, 'loss/train': 1.665950894355774}
+08/30/2021 17:34:27 - INFO - __main__ - Step 24453: {'lr': 0.0004721413257485003, 'samples': 4694976, 'steps': 24452, 'loss/train': 1.733527421951294}
+08/30/2021 17:34:27 - INFO - __main__ - Step 24454: {'lr': 0.0004721388912286758, 'samples': 4695168, 'steps': 24453, 'loss/train': 2.084660768508911}
+08/30/2021 17:34:27 - INFO - __main__ - Step 24455: {'lr': 0.0004721364566087589, 'samples': 4695360, 'steps': 24454, 'loss/train': 1.8475679159164429}
+08/30/2021 17:34:28 - INFO - __main__ - Step 24456: {'lr': 0.00047213402188875077, 'samples': 4695552, 'steps': 24455, 'loss/train': 1.7513166666030884}
+08/30/2021 17:34:29 - INFO - __main__ - Step 24457: {'lr': 0.00047213158706865246, 'samples': 4695744, 'steps': 24456, 'loss/train': 1.285531759262085}
+08/30/2021 17:34:30 - INFO - __main__ - Step 24458: {'lr': 0.000472129152148465, 'samples': 4695936, 'steps': 24457, 'loss/train': 1.658231496810913}
+08/30/2021 17:34:30 - INFO - __main__ - Step 24459: {'lr': 0.0004721267171281897, 'samples': 4696128, 'steps': 24458, 'loss/train': 0.07067694514989853}
+08/30/2021 17:34:30 - INFO - __main__ - Step 24460: {'lr': 0.00047212428200782744, 'samples': 4696320, 'steps': 24459, 'loss/train': 1.6212053298950195}
+08/30/2021 17:34:31 - INFO - __main__ - Step 24461: {'lr': 0.00047212184678737946, 'samples': 4696512, 'steps': 24460, 'loss/train': 1.081878423690796}
+08/30/2021 17:34:31 - INFO - __main__ - Step 24462: {'lr': 0.00047211941146684677, 'samples': 4696704, 'steps': 24461, 'loss/train': 0.767326295375824}
+08/30/2021 17:34:32 - INFO - __main__ - Step 24463: {'lr': 0.00047211697604623056, 'samples': 4696896, 'steps': 24462, 'loss/train': 1.8081620931625366}
+08/30/2021 17:34:33 - INFO - __main__ - Step 24464: {'lr': 0.0004721145405255318, 'samples': 4697088, 'steps': 24463, 'loss/train': 1.461976408958435}
+08/30/2021 17:34:33 - INFO - __main__ - Step 24465: {'lr': 0.00047211210490475167, 'samples': 4697280, 'steps': 24464, 'loss/train': 1.7162853479385376}
+08/30/2021 17:34:34 - INFO - __main__ - Step 24466: {'lr': 0.0004721096691838913, 'samples': 4697472, 'steps': 24465, 'loss/train': 1.5274393558502197}
+08/30/2021 17:34:34 - INFO - __main__ - Step 24467: {'lr': 0.00047210723336295167, 'samples': 4697664, 'steps': 24466, 'loss/train': 1.5892138481140137}
+08/30/2021 17:34:36 - INFO - __main__ - Step 24468: {'lr': 0.00047210479744193404, 'samples': 4697856, 'steps': 24467, 'loss/train': 1.749915361404419}
+08/30/2021 17:34:36 - INFO - __main__ - Step 24469: {'lr': 0.0004721023614208393, 'samples': 4698048, 'steps': 24468, 'loss/train': 1.882742166519165}
+08/30/2021 17:34:36 - INFO - __main__ - Step 24470: {'lr': 0.0004720999252996687, 'samples': 4698240, 'steps': 24469, 'loss/train': 1.774699330329895}
+08/30/2021 17:34:37 - INFO - __main__ - Step 24471: {'lr': 0.00047209748907842337, 'samples': 4698432, 'steps': 24470, 'loss/train': 1.6665769815444946}
+08/30/2021 17:34:37 - INFO - __main__ - Step 24472: {'lr': 0.0004720950527571043, 'samples': 4698624, 'steps': 24471, 'loss/train': 1.5818909406661987}
+08/30/2021 17:34:39 - INFO - __main__ - Step 24473: {'lr': 0.0004720926163357126, 'samples': 4698816, 'steps': 24472, 'loss/train': 1.6217882633209229}
+08/30/2021 17:34:40 - INFO - __main__ - Step 24474: {'lr': 0.0004720901798142494, 'samples': 4699008, 'steps': 24473, 'loss/train': 1.221812129020691}
+08/30/2021 17:34:40 - INFO - __main__ - Step 24475: {'lr': 0.00047208774319271586, 'samples': 4699200, 'steps': 24474, 'loss/train': 1.7934091091156006}
+08/30/2021 17:34:40 - INFO - __main__ - Step 24476: {'lr': 0.00047208530647111294, 'samples': 4699392, 'steps': 24475, 'loss/train': 1.7955983877182007}
+08/30/2021 17:34:41 - INFO - __main__ - Step 24477: {'lr': 0.0004720828696494418, 'samples': 4699584, 'steps': 24476, 'loss/train': 1.424503207206726}
+08/30/2021 17:34:41 - INFO - __main__ - Step 24478: {'lr': 0.00047208043272770354, 'samples': 4699776, 'steps': 24477, 'loss/train': 0.26392412185668945}
+08/30/2021 17:34:42 - INFO - __main__ - Step 24479: {'lr': 0.0004720779957058993, 'samples': 4699968, 'steps': 24478, 'loss/train': 1.5823725461959839}
+08/30/2021 17:34:43 - INFO - __main__ - Step 24480: {'lr': 0.0004720755585840302, 'samples': 4700160, 'steps': 24479, 'loss/train': 1.8605295419692993}
+08/30/2021 17:34:43 - INFO - __main__ - Step 24481: {'lr': 0.0004720731213620972, 'samples': 4700352, 'steps': 24480, 'loss/train': 1.994153618812561}
+08/30/2021 17:34:44 - INFO - __main__ - Step 24482: {'lr': 0.00047207068404010147, 'samples': 4700544, 'steps': 24481, 'loss/train': 2.2493860721588135}
+08/30/2021 17:34:44 - INFO - __main__ - Step 24483: {'lr': 0.00047206824661804415, 'samples': 4700736, 'steps': 24482, 'loss/train': 2.090334892272949}
+08/30/2021 17:34:44 - INFO - __main__ - Step 24484: {'lr': 0.0004720658090959263, 'samples': 4700928, 'steps': 24483, 'loss/train': 1.520559310913086}
+08/30/2021 17:34:46 - INFO - __main__ - Step 24485: {'lr': 0.000472063371473749, 'samples': 4701120, 'steps': 24484, 'loss/train': 1.8299134969711304}
+08/30/2021 17:34:46 - INFO - __main__ - Step 24486: {'lr': 0.0004720609337515134, 'samples': 4701312, 'steps': 24485, 'loss/train': 1.7684216499328613}
+08/30/2021 17:34:47 - INFO - __main__ - Step 24487: {'lr': 0.00047205849592922057, 'samples': 4701504, 'steps': 24486, 'loss/train': 1.4957983493804932}
+08/30/2021 17:34:47 - INFO - __main__ - Step 24488: {'lr': 0.00047205605800687154, 'samples': 4701696, 'steps': 24487, 'loss/train': 1.4721304178237915}
+08/30/2021 17:34:47 - INFO - __main__ - Step 24489: {'lr': 0.0004720536199844676, 'samples': 4701888, 'steps': 24488, 'loss/train': 1.8148545026779175}
+08/30/2021 17:34:49 - INFO - __main__ - Step 24490: {'lr': 0.00047205118186200963, 'samples': 4702080, 'steps': 24489, 'loss/train': 1.6523698568344116}
+08/30/2021 17:34:49 - INFO - __main__ - Step 24491: {'lr': 0.00047204874363949886, 'samples': 4702272, 'steps': 24490, 'loss/train': 1.5222666263580322}
+08/30/2021 17:34:50 - INFO - __main__ - Step 24492: {'lr': 0.00047204630531693634, 'samples': 4702464, 'steps': 24491, 'loss/train': 1.5540434122085571}
+08/30/2021 17:34:50 - INFO - __main__ - Step 24493: {'lr': 0.0004720438668943232, 'samples': 4702656, 'steps': 24492, 'loss/train': 1.5921696424484253}
+08/30/2021 17:34:50 - INFO - __main__ - Step 24494: {'lr': 0.0004720414283716605, 'samples': 4702848, 'steps': 24493, 'loss/train': 1.4510645866394043}
+08/30/2021 17:34:52 - INFO - __main__ - Step 24495: {'lr': 0.00047203898974894934, 'samples': 4703040, 'steps': 24494, 'loss/train': 1.844099998474121}
+08/30/2021 17:34:52 - INFO - __main__ - Step 24496: {'lr': 0.0004720365510261909, 'samples': 4703232, 'steps': 24495, 'loss/train': 1.3378582000732422}
+08/30/2021 17:34:53 - INFO - __main__ - Step 24497: {'lr': 0.00047203411220338615, 'samples': 4703424, 'steps': 24496, 'loss/train': 1.5024641752243042}
+08/30/2021 17:34:53 - INFO - __main__ - Step 24498: {'lr': 0.00047203167328053634, 'samples': 4703616, 'steps': 24497, 'loss/train': 1.207093358039856}
+08/30/2021 17:34:53 - INFO - __main__ - Step 24499: {'lr': 0.0004720292342576423, 'samples': 4703808, 'steps': 24498, 'loss/train': 1.2374742031097412}
+08/30/2021 17:34:55 - INFO - __main__ - Step 24500: {'lr': 0.0004720267951347055, 'samples': 4704000, 'steps': 24499, 'loss/train': 1.4379520416259766}
+08/30/2021 17:34:55 - INFO - __main__ - Step 24501: {'lr': 0.00047202435591172677, 'samples': 4704192, 'steps': 24500, 'loss/train': 1.6501487493515015}
+08/30/2021 17:34:56 - INFO - __main__ - Step 24502: {'lr': 0.00047202191658870737, 'samples': 4704384, 'steps': 24501, 'loss/train': 1.4039591550827026}
+08/30/2021 17:34:56 - INFO - __main__ - Step 24503: {'lr': 0.00047201947716564826, 'samples': 4704576, 'steps': 24502, 'loss/train': 1.4813679456710815}
+08/30/2021 17:34:56 - INFO - __main__ - Step 24504: {'lr': 0.00047201703764255057, 'samples': 4704768, 'steps': 24503, 'loss/train': 1.0740585327148438}
+08/30/2021 17:34:58 - INFO - __main__ - Step 24505: {'lr': 0.0004720145980194155, 'samples': 4704960, 'steps': 24504, 'loss/train': 1.3868985176086426}
+08/30/2021 17:34:59 - INFO - __main__ - Step 24506: {'lr': 0.000472012158296244, 'samples': 4705152, 'steps': 24505, 'loss/train': 1.3370076417922974}
+08/30/2021 17:34:59 - INFO - __main__ - Step 24507: {'lr': 0.0004720097184730373, 'samples': 4705344, 'steps': 24506, 'loss/train': 1.75924551486969}
+08/30/2021 17:34:59 - INFO - __main__ - Step 24508: {'lr': 0.00047200727854979644, 'samples': 4705536, 'steps': 24507, 'loss/train': 1.5830689668655396}
+08/30/2021 17:35:00 - INFO - __main__ - Step 24509: {'lr': 0.00047200483852652257, 'samples': 4705728, 'steps': 24508, 'loss/train': 1.1779227256774902}
+08/30/2021 17:35:01 - INFO - __main__ - Step 24510: {'lr': 0.0004720023984032167, 'samples': 4705920, 'steps': 24509, 'loss/train': 0.502585768699646}
+08/30/2021 17:35:02 - INFO - __main__ - Step 24511: {'lr': 0.00047199995817987997, 'samples': 4706112, 'steps': 24510, 'loss/train': 0.9358653426170349}
+08/30/2021 17:35:02 - INFO - __main__ - Step 24512: {'lr': 0.00047199751785651346, 'samples': 4706304, 'steps': 24511, 'loss/train': 1.063664436340332}
+08/30/2021 17:35:02 - INFO - __main__ - Step 24513: {'lr': 0.0004719950774331183, 'samples': 4706496, 'steps': 24512, 'loss/train': 2.2083916664123535}
+08/30/2021 17:35:03 - INFO - __main__ - Step 24514: {'lr': 0.00047199263690969563, 'samples': 4706688, 'steps': 24513, 'loss/train': 1.5452370643615723}
+08/30/2021 17:35:04 - INFO - __main__ - Step 24515: {'lr': 0.00047199019628624647, 'samples': 4706880, 'steps': 24514, 'loss/train': 1.8068499565124512}
+08/30/2021 17:35:05 - INFO - __main__ - Step 24516: {'lr': 0.00047198775556277195, 'samples': 4707072, 'steps': 24515, 'loss/train': 1.927861213684082}
+08/30/2021 17:35:05 - INFO - __main__ - Step 24517: {'lr': 0.0004719853147392732, 'samples': 4707264, 'steps': 24516, 'loss/train': 1.4510259628295898}
+08/30/2021 17:35:05 - INFO - __main__ - Step 24518: {'lr': 0.0004719828738157512, 'samples': 4707456, 'steps': 24517, 'loss/train': 1.6395998001098633}
+08/30/2021 17:35:06 - INFO - __main__ - Step 24519: {'lr': 0.0004719804327922073, 'samples': 4707648, 'steps': 24518, 'loss/train': 1.6449280977249146}
+08/30/2021 17:35:07 - INFO - __main__ - Step 24520: {'lr': 0.00047197799166864233, 'samples': 4707840, 'steps': 24519, 'loss/train': 1.774253249168396}
+08/30/2021 17:35:08 - INFO - __main__ - Step 24521: {'lr': 0.00047197555044505756, 'samples': 4708032, 'steps': 24520, 'loss/train': 1.4616219997406006}
+08/30/2021 17:35:08 - INFO - __main__ - Step 24522: {'lr': 0.000471973109121454, 'samples': 4708224, 'steps': 24521, 'loss/train': 1.4657056331634521}
+08/30/2021 17:35:08 - INFO - __main__ - Step 24523: {'lr': 0.00047197066769783284, 'samples': 4708416, 'steps': 24522, 'loss/train': 1.2063186168670654}
+08/30/2021 17:35:09 - INFO - __main__ - Step 24524: {'lr': 0.000471968226174195, 'samples': 4708608, 'steps': 24523, 'loss/train': 0.091896653175354}
+08/30/2021 17:35:10 - INFO - __main__ - Step 24525: {'lr': 0.00047196578455054175, 'samples': 4708800, 'steps': 24524, 'loss/train': 0.9957613348960876}
+08/30/2021 17:35:11 - INFO - __main__ - Step 24526: {'lr': 0.00047196334282687414, 'samples': 4708992, 'steps': 24525, 'loss/train': 1.7564043998718262}
+08/30/2021 17:35:11 - INFO - __main__ - Step 24527: {'lr': 0.00047196090100319333, 'samples': 4709184, 'steps': 24526, 'loss/train': 1.4603902101516724}
+08/30/2021 17:35:12 - INFO - __main__ - Step 24528: {'lr': 0.00047195845907950035, 'samples': 4709376, 'steps': 24527, 'loss/train': 1.472461223602295}
+08/30/2021 17:35:12 - INFO - __main__ - Step 24529: {'lr': 0.0004719560170557963, 'samples': 4709568, 'steps': 24528, 'loss/train': 1.436963677406311}
+08/30/2021 17:35:13 - INFO - __main__ - Step 24530: {'lr': 0.0004719535749320823, 'samples': 4709760, 'steps': 24529, 'loss/train': 0.232659712433815}
+08/30/2021 17:35:14 - INFO - __main__ - Step 24531: {'lr': 0.0004719511327083594, 'samples': 4709952, 'steps': 24530, 'loss/train': 0.26898905634880066}
+08/30/2021 17:35:14 - INFO - __main__ - Step 24532: {'lr': 0.0004719486903846288, 'samples': 4710144, 'steps': 24531, 'loss/train': 1.497463583946228}
+08/30/2021 17:35:15 - INFO - __main__ - Step 24533: {'lr': 0.0004719462479608915, 'samples': 4710336, 'steps': 24532, 'loss/train': 1.2646433115005493}
+08/30/2021 17:35:15 - INFO - __main__ - Step 24534: {'lr': 0.0004719438054371487, 'samples': 4710528, 'steps': 24533, 'loss/train': 1.1970287561416626}
+08/30/2021 17:35:15 - INFO - __main__ - Step 24535: {'lr': 0.00047194136281340137, 'samples': 4710720, 'steps': 24534, 'loss/train': 1.7726329565048218}
+08/30/2021 17:35:17 - INFO - __main__ - Step 24536: {'lr': 0.00047193892008965077, 'samples': 4710912, 'steps': 24535, 'loss/train': 1.4720901250839233}
+08/30/2021 17:35:17 - INFO - __main__ - Step 24537: {'lr': 0.0004719364772658978, 'samples': 4711104, 'steps': 24536, 'loss/train': 1.4312533140182495}
+08/30/2021 17:35:18 - INFO - __main__ - Step 24538: {'lr': 0.00047193403434214385, 'samples': 4711296, 'steps': 24537, 'loss/train': 1.2726963758468628}
+08/30/2021 17:35:18 - INFO - __main__ - Step 24539: {'lr': 0.0004719315913183897, 'samples': 4711488, 'steps': 24538, 'loss/train': 1.411854863166809}
+08/30/2021 17:35:18 - INFO - __main__ - Step 24540: {'lr': 0.0004719291481946367, 'samples': 4711680, 'steps': 24539, 'loss/train': 1.7104921340942383}
+08/30/2021 17:35:20 - INFO - __main__ - Step 24541: {'lr': 0.00047192670497088577, 'samples': 4711872, 'steps': 24540, 'loss/train': 1.3718091249465942}
+08/30/2021 17:35:20 - INFO - __main__ - Step 24542: {'lr': 0.0004719242616471381, 'samples': 4712064, 'steps': 24541, 'loss/train': 1.6246330738067627}
+08/30/2021 17:35:21 - INFO - __main__ - Step 24543: {'lr': 0.00047192181822339484, 'samples': 4712256, 'steps': 24542, 'loss/train': 1.1429835557937622}
+08/30/2021 17:35:21 - INFO - __main__ - Step 24544: {'lr': 0.000471919374699657, 'samples': 4712448, 'steps': 24543, 'loss/train': 1.4758931398391724}
+08/30/2021 17:35:21 - INFO - __main__ - Step 24545: {'lr': 0.0004719169310759257, 'samples': 4712640, 'steps': 24544, 'loss/train': 5.920523166656494}
+08/30/2021 17:35:23 - INFO - __main__ - Step 24546: {'lr': 0.0004719144873522021, 'samples': 4712832, 'steps': 24545, 'loss/train': 1.7054550647735596}
+08/30/2021 17:35:23 - INFO - __main__ - Step 24547: {'lr': 0.0004719120435284872, 'samples': 4713024, 'steps': 24546, 'loss/train': 1.2541141510009766}
+08/30/2021 17:35:24 - INFO - __main__ - Step 24548: {'lr': 0.0004719095996047822, 'samples': 4713216, 'steps': 24547, 'loss/train': 1.8921313285827637}
+08/30/2021 17:35:24 - INFO - __main__ - Step 24549: {'lr': 0.0004719071555810881, 'samples': 4713408, 'steps': 24548, 'loss/train': 1.8774735927581787}
+08/30/2021 17:35:25 - INFO - __main__ - Step 24550: {'lr': 0.00047190471145740616, 'samples': 4713600, 'steps': 24549, 'loss/train': 0.6641445159912109}
+08/30/2021 17:35:25 - INFO - __main__ - Step 24551: {'lr': 0.0004719022672337373, 'samples': 4713792, 'steps': 24550, 'loss/train': 0.7229032516479492}
+08/30/2021 17:35:26 - INFO - __main__ - Step 24552: {'lr': 0.0004718998229100827, 'samples': 4713984, 'steps': 24551, 'loss/train': 1.1109299659729004}
+08/30/2021 17:35:27 - INFO - __main__ - Step 24553: {'lr': 0.00047189737848644356, 'samples': 4714176, 'steps': 24552, 'loss/train': 1.7704217433929443}
+08/30/2021 17:35:27 - INFO - __main__ - Step 24554: {'lr': 0.0004718949339628208, 'samples': 4714368, 'steps': 24553, 'loss/train': 1.3112504482269287}
+08/30/2021 17:35:28 - INFO - __main__ - Step 24555: {'lr': 0.0004718924893392156, 'samples': 4714560, 'steps': 24554, 'loss/train': 1.695735216140747}
+08/30/2021 17:35:28 - INFO - __main__ - Step 24556: {'lr': 0.0004718900446156291, 'samples': 4714752, 'steps': 24555, 'loss/train': 1.3627787828445435}
+08/30/2021 17:35:30 - INFO - __main__ - Step 24557: {'lr': 0.00047188759979206236, 'samples': 4714944, 'steps': 24556, 'loss/train': 1.5065007209777832}
+08/30/2021 17:35:30 - INFO - __main__ - Step 24558: {'lr': 0.00047188515486851646, 'samples': 4715136, 'steps': 24557, 'loss/train': 1.5328236818313599}
+08/30/2021 17:35:31 - INFO - __main__ - Step 24559: {'lr': 0.0004718827098449926, 'samples': 4715328, 'steps': 24558, 'loss/train': 1.2341324090957642}
+08/30/2021 17:35:31 - INFO - __main__ - Step 24560: {'lr': 0.00047188026472149184, 'samples': 4715520, 'steps': 24559, 'loss/train': 2.171665906906128}
+08/30/2021 17:35:31 - INFO - __main__ - Step 24561: {'lr': 0.0004718778194980151, 'samples': 4715712, 'steps': 24560, 'loss/train': 1.7486183643341064}
+08/30/2021 17:35:33 - INFO - __main__ - Step 24562: {'lr': 0.00047187537417456375, 'samples': 4715904, 'steps': 24561, 'loss/train': 1.7060445547103882}
+08/30/2021 17:35:33 - INFO - __main__ - Step 24563: {'lr': 0.00047187292875113874, 'samples': 4716096, 'steps': 24562, 'loss/train': 2.457808017730713}
+08/30/2021 17:35:34 - INFO - __main__ - Step 24564: {'lr': 0.0004718704832277413, 'samples': 4716288, 'steps': 24563, 'loss/train': 1.622470736503601}
+08/30/2021 17:35:34 - INFO - __main__ - Step 24565: {'lr': 0.0004718680376043724, 'samples': 4716480, 'steps': 24564, 'loss/train': 1.4234267473220825}
+08/30/2021 17:35:34 - INFO - __main__ - Step 24566: {'lr': 0.00047186559188103314, 'samples': 4716672, 'steps': 24565, 'loss/train': 1.6230226755142212}
+08/30/2021 17:35:36 - INFO - __main__ - Step 24567: {'lr': 0.00047186314605772466, 'samples': 4716864, 'steps': 24566, 'loss/train': 1.4558249711990356}
+08/30/2021 17:35:36 - INFO - __main__ - Step 24568: {'lr': 0.00047186070013444814, 'samples': 4717056, 'steps': 24567, 'loss/train': 1.0605478286743164}
+08/30/2021 17:35:37 - INFO - __main__ - Step 24569: {'lr': 0.00047185825411120454, 'samples': 4717248, 'steps': 24568, 'loss/train': 1.3696558475494385}
+08/30/2021 17:35:37 - INFO - __main__ - Step 24570: {'lr': 0.0004718558079879951, 'samples': 4717440, 'steps': 24569, 'loss/train': 1.3347958326339722}
+08/30/2021 17:35:37 - INFO - __main__ - Step 24571: {'lr': 0.00047185336176482084, 'samples': 4717632, 'steps': 24570, 'loss/train': 1.8632763624191284}
+08/30/2021 17:35:39 - INFO - __main__ - Step 24572: {'lr': 0.00047185091544168286, 'samples': 4717824, 'steps': 24571, 'loss/train': 1.8458465337753296}
+08/30/2021 17:35:39 - INFO - __main__ - Step 24573: {'lr': 0.00047184846901858225, 'samples': 4718016, 'steps': 24572, 'loss/train': 0.7646589279174805}
+08/30/2021 17:35:40 - INFO - __main__ - Step 24574: {'lr': 0.0004718460224955202, 'samples': 4718208, 'steps': 24573, 'loss/train': 1.0524741411209106}
+08/30/2021 17:35:40 - INFO - __main__ - Step 24575: {'lr': 0.0004718435758724977, 'samples': 4718400, 'steps': 24574, 'loss/train': 1.3564406633377075}
+08/30/2021 17:35:40 - INFO - __main__ - Step 24576: {'lr': 0.000471841129149516, 'samples': 4718592, 'steps': 24575, 'loss/train': 1.1782338619232178}
+08/30/2021 17:35:41 - INFO - __main__ - Step 24577: {'lr': 0.000471838682326576, 'samples': 4718784, 'steps': 24576, 'loss/train': 1.1804299354553223}
+08/30/2021 17:35:42 - INFO - __main__ - Step 24578: {'lr': 0.000471836235403679, 'samples': 4718976, 'steps': 24577, 'loss/train': 1.9783321619033813}
+08/30/2021 17:35:43 - INFO - __main__ - Step 24579: {'lr': 0.000471833788380826, 'samples': 4719168, 'steps': 24578, 'loss/train': 1.8166775703430176}
+08/30/2021 17:35:43 - INFO - __main__ - Step 24580: {'lr': 0.0004718313412580181, 'samples': 4719360, 'steps': 24579, 'loss/train': 1.8016951084136963}
+08/30/2021 17:35:43 - INFO - __main__ - Step 24581: {'lr': 0.0004718288940352564, 'samples': 4719552, 'steps': 24580, 'loss/train': 1.562361717224121}
+08/30/2021 17:35:44 - INFO - __main__ - Step 24582: {'lr': 0.00047182644671254207, 'samples': 4719744, 'steps': 24581, 'loss/train': 3.886920213699341}
+08/30/2021 17:35:45 - INFO - __main__ - Step 24583: {'lr': 0.0004718239992898761, 'samples': 4719936, 'steps': 24582, 'loss/train': 1.9974838495254517}
+08/30/2021 17:35:46 - INFO - __main__ - Step 24584: {'lr': 0.00047182155176725974, 'samples': 4720128, 'steps': 24583, 'loss/train': 1.6186575889587402}
+08/30/2021 17:35:46 - INFO - __main__ - Step 24585: {'lr': 0.00047181910414469396, 'samples': 4720320, 'steps': 24584, 'loss/train': 1.5206100940704346}
+08/30/2021 17:35:46 - INFO - __main__ - Step 24586: {'lr': 0.0004718166564221799, 'samples': 4720512, 'steps': 24585, 'loss/train': 1.3282649517059326}
+08/30/2021 17:35:47 - INFO - __main__ - Step 24587: {'lr': 0.0004718142085997187, 'samples': 4720704, 'steps': 24586, 'loss/train': 1.8367680311203003}
+08/30/2021 17:35:48 - INFO - __main__ - Step 24588: {'lr': 0.0004718117606773115, 'samples': 4720896, 'steps': 24587, 'loss/train': 1.4244365692138672}
+08/30/2021 17:35:49 - INFO - __main__ - Step 24589: {'lr': 0.0004718093126549592, 'samples': 4721088, 'steps': 24588, 'loss/train': 3.3588130474090576}
+08/30/2021 17:35:49 - INFO - __main__ - Step 24590: {'lr': 0.0004718068645326632, 'samples': 4721280, 'steps': 24589, 'loss/train': 2.0005922317504883}
+08/30/2021 17:35:50 - INFO - __main__ - Step 24591: {'lr': 0.0004718044163104244, 'samples': 4721472, 'steps': 24590, 'loss/train': 1.963279366493225}
+08/30/2021 17:35:50 - INFO - __main__ - Step 24592: {'lr': 0.0004718019679882439, 'samples': 4721664, 'steps': 24591, 'loss/train': 1.429451584815979}
+08/30/2021 17:35:51 - INFO - __main__ - Step 24593: {'lr': 0.0004717995195661229, 'samples': 4721856, 'steps': 24592, 'loss/train': 1.9033617973327637}
+08/30/2021 17:35:52 - INFO - __main__ - Step 24594: {'lr': 0.00047179707104406243, 'samples': 4722048, 'steps': 24593, 'loss/train': 1.8315582275390625}
+08/30/2021 17:35:52 - INFO - __main__ - Step 24595: {'lr': 0.0004717946224220637, 'samples': 4722240, 'steps': 24594, 'loss/train': 1.625569224357605}
+08/30/2021 17:35:53 - INFO - __main__ - Step 24596: {'lr': 0.0004717921737001276, 'samples': 4722432, 'steps': 24595, 'loss/train': 1.7163532972335815}
+08/30/2021 17:35:53 - INFO - __main__ - Step 24597: {'lr': 0.0004717897248782555, 'samples': 4722624, 'steps': 24596, 'loss/train': 1.384665846824646}
+08/30/2021 17:35:55 - INFO - __main__ - Step 24598: {'lr': 0.0004717872759564483, 'samples': 4722816, 'steps': 24597, 'loss/train': 1.6244404315948486}
+08/30/2021 17:35:55 - INFO - __main__ - Step 24599: {'lr': 0.00047178482693470723, 'samples': 4723008, 'steps': 24598, 'loss/train': 1.0666124820709229}
+08/30/2021 17:35:56 - INFO - __main__ - Step 24600: {'lr': 0.0004717823778130333, 'samples': 4723200, 'steps': 24599, 'loss/train': 1.7034012079238892}
+08/30/2021 17:35:56 - INFO - __main__ - Step 24601: {'lr': 0.0004717799285914276, 'samples': 4723392, 'steps': 24600, 'loss/train': 0.16433797776699066}
+08/30/2021 17:35:56 - INFO - __main__ - Step 24602: {'lr': 0.00047177747926989134, 'samples': 4723584, 'steps': 24601, 'loss/train': 2.712157726287842}
+08/30/2021 17:35:57 - INFO - __main__ - Step 24603: {'lr': 0.00047177502984842556, 'samples': 4723776, 'steps': 24602, 'loss/train': 1.598645806312561}
+08/30/2021 17:35:58 - INFO - __main__ - Step 24604: {'lr': 0.0004717725803270314, 'samples': 4723968, 'steps': 24603, 'loss/train': 1.755679965019226}
+08/30/2021 17:35:59 - INFO - __main__ - Step 24605: {'lr': 0.00047177013070570997, 'samples': 4724160, 'steps': 24604, 'loss/train': 1.4169636964797974}
+08/30/2021 17:35:59 - INFO - __main__ - Step 24606: {'lr': 0.00047176768098446234, 'samples': 4724352, 'steps': 24605, 'loss/train': 1.1529072523117065}
+08/30/2021 17:36:00 - INFO - __main__ - Step 24607: {'lr': 0.0004717652311632895, 'samples': 4724544, 'steps': 24606, 'loss/train': 1.3863716125488281}
+08/30/2021 17:36:00 - INFO - __main__ - Step 24608: {'lr': 0.00047176278124219276, 'samples': 4724736, 'steps': 24607, 'loss/train': 1.675790786743164}
+08/30/2021 17:36:02 - INFO - __main__ - Step 24609: {'lr': 0.0004717603312211731, 'samples': 4724928, 'steps': 24608, 'loss/train': 0.26380455493927}
+08/30/2021 17:36:02 - INFO - __main__ - Step 24610: {'lr': 0.0004717578811002317, 'samples': 4725120, 'steps': 24609, 'loss/train': 1.3129373788833618}
+08/30/2021 17:36:02 - INFO - __main__ - Step 24611: {'lr': 0.00047175543087936954, 'samples': 4725312, 'steps': 24610, 'loss/train': 1.8768680095672607}
+08/30/2021 17:36:03 - INFO - __main__ - Step 24612: {'lr': 0.0004717529805585879, 'samples': 4725504, 'steps': 24611, 'loss/train': 1.6882539987564087}
+08/30/2021 17:36:03 - INFO - __main__ - Step 24613: {'lr': 0.0004717505301378877, 'samples': 4725696, 'steps': 24612, 'loss/train': 1.4596537351608276}
+08/30/2021 17:36:05 - INFO - __main__ - Step 24614: {'lr': 0.0004717480796172702, 'samples': 4725888, 'steps': 24613, 'loss/train': 1.701680064201355}
+08/30/2021 17:36:06 - INFO - __main__ - Step 24615: {'lr': 0.00047174562899673645, 'samples': 4726080, 'steps': 24614, 'loss/train': 1.0368670225143433}
+08/30/2021 17:36:06 - INFO - __main__ - Step 24616: {'lr': 0.0004717431782762875, 'samples': 4726272, 'steps': 24615, 'loss/train': 1.6600544452667236}
+08/30/2021 17:36:06 - INFO - __main__ - Step 24617: {'lr': 0.0004717407274559245, 'samples': 4726464, 'steps': 24616, 'loss/train': 1.3087135553359985}
+08/30/2021 17:36:07 - INFO - __main__ - Step 24618: {'lr': 0.0004717382765356485, 'samples': 4726656, 'steps': 24617, 'loss/train': 1.6702946424484253}
+08/30/2021 17:36:09 - INFO - __main__ - Step 24619: {'lr': 0.0004717358255154607, 'samples': 4726848, 'steps': 24618, 'loss/train': 1.688079595565796}
+08/30/2021 17:36:09 - INFO - __main__ - Step 24620: {'lr': 0.0004717333743953622, 'samples': 4727040, 'steps': 24619, 'loss/train': 1.955341100692749}
+08/30/2021 17:36:10 - INFO - __main__ - Step 24621: {'lr': 0.00047173092317535404, 'samples': 4727232, 'steps': 24620, 'loss/train': 8.874281883239746}
+08/30/2021 17:36:10 - INFO - __main__ - Step 24622: {'lr': 0.0004717284718554373, 'samples': 4727424, 'steps': 24621, 'loss/train': 2.65262508392334}
+08/30/2021 17:36:10 - INFO - __main__ - Step 24623: {'lr': 0.00047172602043561317, 'samples': 4727616, 'steps': 24622, 'loss/train': 2.1952600479125977}
+08/30/2021 17:36:11 - INFO - __main__ - Step 24624: {'lr': 0.00047172356891588273, 'samples': 4727808, 'steps': 24623, 'loss/train': 2.558573007583618}
+08/30/2021 17:36:12 - INFO - __main__ - Step 24625: {'lr': 0.0004717211172962471, 'samples': 4728000, 'steps': 24624, 'loss/train': 2.1402010917663574}
+08/30/2021 17:36:13 - INFO - __main__ - Step 24626: {'lr': 0.0004717186655767073, 'samples': 4728192, 'steps': 24625, 'loss/train': 2.7358956336975098}
+08/30/2021 17:36:13 - INFO - __main__ - Step 24627: {'lr': 0.0004717162137572645, 'samples': 4728384, 'steps': 24626, 'loss/train': 2.4930129051208496}
+08/30/2021 17:36:13 - INFO - __main__ - Step 24628: {'lr': 0.0004717137618379198, 'samples': 4728576, 'steps': 24627, 'loss/train': 1.7966632843017578}
+08/30/2021 17:36:14 - INFO - __main__ - Step 24629: {'lr': 0.0004717113098186743, 'samples': 4728768, 'steps': 24628, 'loss/train': 1.99289870262146}
+08/30/2021 17:36:15 - INFO - __main__ - Step 24630: {'lr': 0.00047170885769952907, 'samples': 4728960, 'steps': 24629, 'loss/train': 1.6715341806411743}
+08/30/2021 17:36:15 - INFO - __main__ - Step 24631: {'lr': 0.00047170640548048525, 'samples': 4729152, 'steps': 24630, 'loss/train': 1.4821505546569824}
+08/30/2021 17:36:16 - INFO - __main__ - Step 24632: {'lr': 0.000471703953161544, 'samples': 4729344, 'steps': 24631, 'loss/train': 1.797239065170288}
+08/30/2021 17:36:16 - INFO - __main__ - Step 24633: {'lr': 0.00047170150074270635, 'samples': 4729536, 'steps': 24632, 'loss/train': 1.791114091873169}
+08/30/2021 17:36:17 - INFO - __main__ - Step 24634: {'lr': 0.0004716990482239735, 'samples': 4729728, 'steps': 24633, 'loss/train': 1.8352652788162231}
+08/30/2021 17:36:18 - INFO - __main__ - Step 24635: {'lr': 0.0004716965956053463, 'samples': 4729920, 'steps': 24634, 'loss/train': 2.2326345443725586}
+08/30/2021 17:36:19 - INFO - __main__ - Step 24636: {'lr': 0.00047169414288682616, 'samples': 4730112, 'steps': 24635, 'loss/train': 2.186173677444458}
+08/30/2021 17:36:19 - INFO - __main__ - Step 24637: {'lr': 0.0004716916900684141, 'samples': 4730304, 'steps': 24636, 'loss/train': 1.9529016017913818}
+08/30/2021 17:36:19 - INFO - __main__ - Step 24638: {'lr': 0.00047168923715011103, 'samples': 4730496, 'steps': 24637, 'loss/train': 2.344886064529419}
+08/30/2021 17:36:20 - INFO - __main__ - Step 24639: {'lr': 0.00047168678413191833, 'samples': 4730688, 'steps': 24638, 'loss/train': 1.982452630996704}
+08/30/2021 17:36:21 - INFO - __main__ - Step 24640: {'lr': 0.00047168433101383694, 'samples': 4730880, 'steps': 24639, 'loss/train': 1.9556173086166382}
+08/30/2021 17:36:22 - INFO - __main__ - Step 24641: {'lr': 0.000471681877795868, 'samples': 4731072, 'steps': 24640, 'loss/train': 1.4128801822662354}
+08/30/2021 17:36:22 - INFO - __main__ - Step 24642: {'lr': 0.0004716794244780127, 'samples': 4731264, 'steps': 24641, 'loss/train': 2.0736827850341797}
+08/30/2021 17:36:22 - INFO - __main__ - Step 24643: {'lr': 0.0004716769710602721, 'samples': 4731456, 'steps': 24642, 'loss/train': 2.4431746006011963}
+08/30/2021 17:36:23 - INFO - __main__ - Step 24644: {'lr': 0.00047167451754264714, 'samples': 4731648, 'steps': 24643, 'loss/train': 1.5567020177841187}
+08/30/2021 17:36:23 - INFO - __main__ - Step 24645: {'lr': 0.0004716720639251392, 'samples': 4731840, 'steps': 24644, 'loss/train': 2.360151767730713}
+08/30/2021 17:36:24 - INFO - __main__ - Step 24646: {'lr': 0.0004716696102077491, 'samples': 4732032, 'steps': 24645, 'loss/train': 1.8170424699783325}
+08/30/2021 17:36:25 - INFO - __main__ - Step 24647: {'lr': 0.0004716671563904782, 'samples': 4732224, 'steps': 24646, 'loss/train': 2.0453975200653076}
+08/30/2021 17:36:25 - INFO - __main__ - Step 24648: {'lr': 0.0004716647024733275, 'samples': 4732416, 'steps': 24647, 'loss/train': 1.7449759244918823}
+08/30/2021 17:36:26 - INFO - __main__ - Step 24649: {'lr': 0.00047166224845629804, 'samples': 4732608, 'steps': 24648, 'loss/train': 1.9197039604187012}
+08/30/2021 17:36:26 - INFO - __main__ - Step 24650: {'lr': 0.000471659794339391, 'samples': 4732800, 'steps': 24649, 'loss/train': 1.9616122245788574}
+08/30/2021 17:36:28 - INFO - __main__ - Step 24651: {'lr': 0.00047165734012260754, 'samples': 4732992, 'steps': 24650, 'loss/train': 2.1116483211517334}
+08/30/2021 17:36:28 - INFO - __main__ - Step 24652: {'lr': 0.0004716548858059486, 'samples': 4733184, 'steps': 24651, 'loss/train': 1.3150659799575806}
+08/30/2021 17:36:28 - INFO - __main__ - Step 24653: {'lr': 0.0004716524313894155, 'samples': 4733376, 'steps': 24652, 'loss/train': 1.4902786016464233}
+08/30/2021 17:36:29 - INFO - __main__ - Step 24654: {'lr': 0.0004716499768730092, 'samples': 4733568, 'steps': 24653, 'loss/train': 1.7323554754257202}
+08/30/2021 17:36:29 - INFO - __main__ - Step 24655: {'lr': 0.0004716475222567308, 'samples': 4733760, 'steps': 24654, 'loss/train': 1.4266170263290405}
+08/30/2021 17:36:31 - INFO - __main__ - Step 24656: {'lr': 0.0004716450675405815, 'samples': 4733952, 'steps': 24655, 'loss/train': 2.019360303878784}
+08/30/2021 17:36:31 - INFO - __main__ - Step 24657: {'lr': 0.0004716426127245623, 'samples': 4734144, 'steps': 24656, 'loss/train': 1.9479265213012695}
+08/30/2021 17:36:31 - INFO - __main__ - Step 24658: {'lr': 0.00047164015780867444, 'samples': 4734336, 'steps': 24657, 'loss/train': 1.0647599697113037}
+08/30/2021 17:36:32 - INFO - __main__ - Step 24659: {'lr': 0.0004716377027929189, 'samples': 4734528, 'steps': 24658, 'loss/train': 1.8619252443313599}
+08/30/2021 17:36:32 - INFO - __main__ - Step 24660: {'lr': 0.00047163524767729684, 'samples': 4734720, 'steps': 24659, 'loss/train': 1.6403992176055908}
+08/30/2021 17:36:32 - INFO - __main__ - Step 24661: {'lr': 0.0004716327924618093, 'samples': 4734912, 'steps': 24660, 'loss/train': 0.9954274296760559}
+08/30/2021 17:36:35 - INFO - __main__ - Step 24662: {'lr': 0.0004716303371464575, 'samples': 4735104, 'steps': 24661, 'loss/train': 1.2608269453048706}
+08/30/2021 17:36:35 - INFO - __main__ - Step 24663: {'lr': 0.0004716278817312425, 'samples': 4735296, 'steps': 24662, 'loss/train': 1.1998200416564941}
+08/30/2021 17:36:35 - INFO - __main__ - Step 24664: {'lr': 0.0004716254262161653, 'samples': 4735488, 'steps': 24663, 'loss/train': 3.4208500385284424}
+08/30/2021 17:36:36 - INFO - __main__ - Step 24665: {'lr': 0.00047162297060122726, 'samples': 4735680, 'steps': 24664, 'loss/train': 1.499505639076233}
+08/30/2021 17:36:36 - INFO - __main__ - Step 24666: {'lr': 0.0004716205148864292, 'samples': 4735872, 'steps': 24665, 'loss/train': 1.7700446844100952}
+08/30/2021 17:36:38 - INFO - __main__ - Step 24667: {'lr': 0.0004716180590717724, 'samples': 4736064, 'steps': 24666, 'loss/train': 2.8480496406555176}
+08/30/2021 17:36:38 - INFO - __main__ - Step 24668: {'lr': 0.0004716156031572579, 'samples': 4736256, 'steps': 24667, 'loss/train': 1.711680293083191}
+08/30/2021 17:36:38 - INFO - __main__ - Step 24669: {'lr': 0.00047161314714288697, 'samples': 4736448, 'steps': 24668, 'loss/train': 1.791342854499817}
+08/30/2021 17:36:39 - INFO - __main__ - Step 24670: {'lr': 0.00047161069102866037, 'samples': 4736640, 'steps': 24669, 'loss/train': 2.0235402584075928}
+08/30/2021 17:36:39 - INFO - __main__ - Step 24671: {'lr': 0.00047160823481457955, 'samples': 4736832, 'steps': 24670, 'loss/train': 1.6442534923553467}
+08/30/2021 17:36:41 - INFO - __main__ - Step 24672: {'lr': 0.0004716057785006454, 'samples': 4737024, 'steps': 24671, 'loss/train': 2.016108274459839}
+08/30/2021 17:36:41 - INFO - __main__ - Step 24673: {'lr': 0.00047160332208685915, 'samples': 4737216, 'steps': 24672, 'loss/train': 1.0705252885818481}
+08/30/2021 17:36:42 - INFO - __main__ - Step 24674: {'lr': 0.00047160086557322185, 'samples': 4737408, 'steps': 24673, 'loss/train': 1.2105544805526733}
+08/30/2021 17:36:42 - INFO - __main__ - Step 24675: {'lr': 0.0004715984089597346, 'samples': 4737600, 'steps': 24674, 'loss/train': 1.826501727104187}
+08/30/2021 17:36:42 - INFO - __main__ - Step 24676: {'lr': 0.00047159595224639854, 'samples': 4737792, 'steps': 24675, 'loss/train': 0.3165826201438904}
+08/30/2021 17:36:44 - INFO - __main__ - Step 24677: {'lr': 0.00047159349543321477, 'samples': 4737984, 'steps': 24676, 'loss/train': 2.6708781719207764}
+08/30/2021 17:36:44 - INFO - __main__ - Step 24678: {'lr': 0.00047159103852018443, 'samples': 4738176, 'steps': 24677, 'loss/train': 2.4192936420440674}
+08/30/2021 17:36:45 - INFO - __main__ - Step 24679: {'lr': 0.00047158858150730856, 'samples': 4738368, 'steps': 24678, 'loss/train': 1.0226179361343384}
+08/30/2021 17:36:45 - INFO - __main__ - Step 24680: {'lr': 0.00047158612439458824, 'samples': 4738560, 'steps': 24679, 'loss/train': 1.7899672985076904}
+08/30/2021 17:36:45 - INFO - __main__ - Step 24681: {'lr': 0.00047158366718202466, 'samples': 4738752, 'steps': 24680, 'loss/train': 1.428963541984558}
+08/30/2021 17:36:47 - INFO - __main__ - Step 24682: {'lr': 0.00047158120986961897, 'samples': 4738944, 'steps': 24681, 'loss/train': 3.1310064792633057}
+08/30/2021 17:36:47 - INFO - __main__ - Step 24683: {'lr': 0.00047157875245737213, 'samples': 4739136, 'steps': 24682, 'loss/train': 1.679357886314392}
+08/30/2021 17:36:48 - INFO - __main__ - Step 24684: {'lr': 0.0004715762949452853, 'samples': 4739328, 'steps': 24683, 'loss/train': 1.8991272449493408}
+08/30/2021 17:36:48 - INFO - __main__ - Step 24685: {'lr': 0.0004715738373333597, 'samples': 4739520, 'steps': 24684, 'loss/train': 2.5505757331848145}
+08/30/2021 17:36:48 - INFO - __main__ - Step 24686: {'lr': 0.00047157137962159626, 'samples': 4739712, 'steps': 24685, 'loss/train': 1.6282877922058105}
+08/30/2021 17:36:50 - INFO - __main__ - Step 24687: {'lr': 0.00047156892180999624, 'samples': 4739904, 'steps': 24686, 'loss/train': 1.6711379289627075}
+08/30/2021 17:36:50 - INFO - __main__ - Step 24688: {'lr': 0.0004715664638985606, 'samples': 4740096, 'steps': 24687, 'loss/train': 1.3490301370620728}
+08/30/2021 17:36:51 - INFO - __main__ - Step 24689: {'lr': 0.00047156400588729066, 'samples': 4740288, 'steps': 24688, 'loss/train': 1.1491557359695435}
+08/30/2021 17:36:51 - INFO - __main__ - Step 24690: {'lr': 0.0004715615477761873, 'samples': 4740480, 'steps': 24689, 'loss/train': 1.516879677772522}
+08/30/2021 17:36:51 - INFO - __main__ - Step 24691: {'lr': 0.00047155908956525173, 'samples': 4740672, 'steps': 24690, 'loss/train': 1.952373743057251}
+08/30/2021 17:36:53 - INFO - __main__ - Step 24692: {'lr': 0.00047155663125448514, 'samples': 4740864, 'steps': 24691, 'loss/train': 1.933780550956726}
+08/30/2021 17:36:53 - INFO - __main__ - Step 24693: {'lr': 0.00047155417284388846, 'samples': 4741056, 'steps': 24692, 'loss/train': 1.5821880102157593}
+08/30/2021 17:36:54 - INFO - __main__ - Step 24694: {'lr': 0.0004715517143334629, 'samples': 4741248, 'steps': 24693, 'loss/train': 1.258436918258667}
+08/30/2021 17:36:54 - INFO - __main__ - Step 24695: {'lr': 0.00047154925572320957, 'samples': 4741440, 'steps': 24694, 'loss/train': 1.8043732643127441}
+08/30/2021 17:36:54 - INFO - __main__ - Step 24696: {'lr': 0.00047154679701312953, 'samples': 4741632, 'steps': 24695, 'loss/train': 1.8346304893493652}
+08/30/2021 17:36:56 - INFO - __main__ - Step 24697: {'lr': 0.00047154433820322395, 'samples': 4741824, 'steps': 24696, 'loss/train': 1.851894736289978}
+08/30/2021 17:36:57 - INFO - __main__ - Step 24698: {'lr': 0.0004715418792934939, 'samples': 4742016, 'steps': 24697, 'loss/train': 0.8953798413276672}
+08/30/2021 17:36:57 - INFO - __main__ - Step 24699: {'lr': 0.00047153942028394056, 'samples': 4742208, 'steps': 24698, 'loss/train': 1.6787607669830322}
+08/30/2021 17:36:57 - INFO - __main__ - Step 24700: {'lr': 0.0004715369611745649, 'samples': 4742400, 'steps': 24699, 'loss/train': 0.9864576458930969}
+08/30/2021 17:36:58 - INFO - __main__ - Step 24701: {'lr': 0.00047153450196536816, 'samples': 4742592, 'steps': 24700, 'loss/train': 1.7255611419677734}
+08/30/2021 17:36:58 - INFO - __main__ - Step 24702: {'lr': 0.00047153204265635136, 'samples': 4742784, 'steps': 24701, 'loss/train': 1.9156755208969116}
+08/30/2021 17:37:00 - INFO - __main__ - Step 24703: {'lr': 0.0004715295832475156, 'samples': 4742976, 'steps': 24702, 'loss/train': 0.8458746075630188}
+08/30/2021 17:37:00 - INFO - __main__ - Step 24704: {'lr': 0.0004715271237388621, 'samples': 4743168, 'steps': 24703, 'loss/train': 2.1463427543640137}
+08/30/2021 17:37:01 - INFO - __main__ - Step 24705: {'lr': 0.00047152466413039187, 'samples': 4743360, 'steps': 24704, 'loss/train': 1.0671817064285278}
+08/30/2021 17:37:01 - INFO - __main__ - Step 24706: {'lr': 0.000471522204422106, 'samples': 4743552, 'steps': 24705, 'loss/train': 1.732177972793579}
+08/30/2021 17:37:01 - INFO - __main__ - Step 24707: {'lr': 0.0004715197446140057, 'samples': 4743744, 'steps': 24706, 'loss/train': 1.5347830057144165}
+08/30/2021 17:37:03 - INFO - __main__ - Step 24708: {'lr': 0.000471517284706092, 'samples': 4743936, 'steps': 24707, 'loss/train': 0.5448461174964905}
+08/30/2021 17:37:04 - INFO - __main__ - Step 24709: {'lr': 0.0004715148246983661, 'samples': 4744128, 'steps': 24708, 'loss/train': 1.5225915908813477}
+08/30/2021 17:37:04 - INFO - __main__ - Step 24710: {'lr': 0.000471512364590829, 'samples': 4744320, 'steps': 24709, 'loss/train': 2.057853937149048}
+08/30/2021 17:37:05 - INFO - __main__ - Step 24711: {'lr': 0.0004715099043834818, 'samples': 4744512, 'steps': 24710, 'loss/train': 1.7252074480056763}
+08/30/2021 17:37:05 - INFO - __main__ - Step 24712: {'lr': 0.00047150744407632565, 'samples': 4744704, 'steps': 24711, 'loss/train': 1.6189361810684204}
+08/30/2021 17:37:05 - INFO - __main__ - Step 24713: {'lr': 0.00047150498366936165, 'samples': 4744896, 'steps': 24712, 'loss/train': 1.311771035194397}
+08/30/2021 17:37:07 - INFO - __main__ - Step 24714: {'lr': 0.000471502523162591, 'samples': 4745088, 'steps': 24713, 'loss/train': 0.9976238012313843}
+08/30/2021 17:37:07 - INFO - __main__ - Step 24715: {'lr': 0.00047150006255601475, 'samples': 4745280, 'steps': 24714, 'loss/train': 1.0881123542785645}
+08/30/2021 17:37:08 - INFO - __main__ - Step 24716: {'lr': 0.00047149760184963385, 'samples': 4745472, 'steps': 24715, 'loss/train': 1.610553503036499}
+08/30/2021 17:37:08 - INFO - __main__ - Step 24717: {'lr': 0.0004714951410434497, 'samples': 4745664, 'steps': 24716, 'loss/train': 1.5979219675064087}
+08/30/2021 17:37:08 - INFO - __main__ - Step 24718: {'lr': 0.00047149268013746317, 'samples': 4745856, 'steps': 24717, 'loss/train': 1.687117576599121}
+08/30/2021 17:37:09 - INFO - __main__ - Step 24719: {'lr': 0.00047149021913167545, 'samples': 4746048, 'steps': 24718, 'loss/train': 1.535128116607666}
+08/30/2021 17:37:11 - INFO - __main__ - Step 24720: {'lr': 0.0004714877580260877, 'samples': 4746240, 'steps': 24719, 'loss/train': 0.8547623157501221}
+08/30/2021 17:37:11 - INFO - __main__ - Step 24721: {'lr': 0.00047148529682070094, 'samples': 4746432, 'steps': 24720, 'loss/train': 1.5548758506774902}
+08/30/2021 17:37:12 - INFO - __main__ - Step 24722: {'lr': 0.00047148283551551643, 'samples': 4746624, 'steps': 24721, 'loss/train': 1.661041021347046}
+08/30/2021 17:37:12 - INFO - __main__ - Step 24723: {'lr': 0.000471480374110535, 'samples': 4746816, 'steps': 24722, 'loss/train': 1.4511311054229736}
+08/30/2021 17:37:12 - INFO - __main__ - Step 24724: {'lr': 0.00047147791260575804, 'samples': 4747008, 'steps': 24723, 'loss/train': 2.2207934856414795}
+08/30/2021 17:37:14 - INFO - __main__ - Step 24725: {'lr': 0.0004714754510011866, 'samples': 4747200, 'steps': 24724, 'loss/train': 1.2171140909194946}
+08/30/2021 17:37:14 - INFO - __main__ - Step 24726: {'lr': 0.0004714729892968216, 'samples': 4747392, 'steps': 24725, 'loss/train': 1.4494720697402954}
+08/30/2021 17:37:15 - INFO - __main__ - Step 24727: {'lr': 0.0004714705274926644, 'samples': 4747584, 'steps': 24726, 'loss/train': 1.689841389656067}
+08/30/2021 17:37:15 - INFO - __main__ - Step 24728: {'lr': 0.00047146806558871594, 'samples': 4747776, 'steps': 24727, 'loss/train': 2.315096139907837}
+08/30/2021 17:37:15 - INFO - __main__ - Step 24729: {'lr': 0.0004714656035849774, 'samples': 4747968, 'steps': 24728, 'loss/train': 2.113011598587036}
+08/30/2021 17:37:17 - INFO - __main__ - Step 24730: {'lr': 0.00047146314148144986, 'samples': 4748160, 'steps': 24729, 'loss/train': 1.8264377117156982}
+08/30/2021 17:37:17 - INFO - __main__ - Step 24731: {'lr': 0.00047146067927813454, 'samples': 4748352, 'steps': 24730, 'loss/train': 1.8549612760543823}
+08/30/2021 17:37:18 - INFO - __main__ - Step 24732: {'lr': 0.00047145821697503235, 'samples': 4748544, 'steps': 24731, 'loss/train': 1.5308011770248413}
+08/30/2021 17:37:18 - INFO - __main__ - Step 24733: {'lr': 0.00047145575457214453, 'samples': 4748736, 'steps': 24732, 'loss/train': 2.0067386627197266}
+08/30/2021 17:37:18 - INFO - __main__ - Step 24734: {'lr': 0.00047145329206947216, 'samples': 4748928, 'steps': 24733, 'loss/train': 2.21530818939209}
+08/30/2021 17:37:20 - INFO - __main__ - Step 24735: {'lr': 0.0004714508294670164, 'samples': 4749120, 'steps': 24734, 'loss/train': 1.8082433938980103}
+08/30/2021 17:37:21 - INFO - __main__ - Step 24736: {'lr': 0.00047144836676477823, 'samples': 4749312, 'steps': 24735, 'loss/train': 1.5817692279815674}
+08/30/2021 17:37:21 - INFO - __main__ - Step 24737: {'lr': 0.00047144590396275895, 'samples': 4749504, 'steps': 24736, 'loss/train': 1.4714477062225342}
+08/30/2021 17:37:21 - INFO - __main__ - Step 24738: {'lr': 0.0004714434410609595, 'samples': 4749696, 'steps': 24737, 'loss/train': 1.575246810913086}
+08/30/2021 17:37:22 - INFO - __main__ - Step 24739: {'lr': 0.00047144097805938104, 'samples': 4749888, 'steps': 24738, 'loss/train': 2.1753039360046387}
+08/30/2021 17:37:23 - INFO - __main__ - Step 24740: {'lr': 0.0004714385149580247, 'samples': 4750080, 'steps': 24739, 'loss/train': 1.9992939233779907}
+08/30/2021 17:37:24 - INFO - __main__ - Step 24741: {'lr': 0.0004714360517568916, 'samples': 4750272, 'steps': 24740, 'loss/train': 1.570160984992981}
+08/30/2021 17:37:24 - INFO - __main__ - Step 24742: {'lr': 0.00047143358845598283, 'samples': 4750464, 'steps': 24741, 'loss/train': 1.3570243120193481}
+08/30/2021 17:37:25 - INFO - __main__ - Step 24743: {'lr': 0.0004714311250552995, 'samples': 4750656, 'steps': 24742, 'loss/train': 1.7493219375610352}
+08/30/2021 17:37:25 - INFO - __main__ - Step 24744: {'lr': 0.0004714286615548427, 'samples': 4750848, 'steps': 24743, 'loss/train': 1.5323597192764282}
+08/30/2021 17:37:25 - INFO - __main__ - Step 24745: {'lr': 0.00047142619795461363, 'samples': 4751040, 'steps': 24744, 'loss/train': 1.1970270872116089}
+08/30/2021 17:37:27 - INFO - __main__ - Step 24746: {'lr': 0.0004714237342546133, 'samples': 4751232, 'steps': 24745, 'loss/train': 0.1257409304380417}
+08/30/2021 17:37:27 - INFO - __main__ - Step 24747: {'lr': 0.0004714212704548428, 'samples': 4751424, 'steps': 24746, 'loss/train': 1.4161252975463867}
+08/30/2021 17:37:28 - INFO - __main__ - Step 24748: {'lr': 0.0004714188065553033, 'samples': 4751616, 'steps': 24747, 'loss/train': 1.1785532236099243}
+08/30/2021 17:37:28 - INFO - __main__ - Step 24749: {'lr': 0.000471416342555996, 'samples': 4751808, 'steps': 24748, 'loss/train': 1.6573036909103394}
+08/30/2021 17:37:28 - INFO - __main__ - Step 24750: {'lr': 0.00047141387845692174, 'samples': 4752000, 'steps': 24749, 'loss/train': 1.5083427429199219}
+08/30/2021 17:37:30 - INFO - __main__ - Step 24751: {'lr': 0.0004714114142580819, 'samples': 4752192, 'steps': 24750, 'loss/train': 1.8364665508270264}
+08/30/2021 17:37:30 - INFO - __main__ - Step 24752: {'lr': 0.00047140894995947755, 'samples': 4752384, 'steps': 24751, 'loss/train': 1.4609259366989136}
+08/30/2021 17:37:31 - INFO - __main__ - Step 24753: {'lr': 0.00047140648556110966, 'samples': 4752576, 'steps': 24752, 'loss/train': 0.3895515501499176}
+08/30/2021 17:37:31 - INFO - __main__ - Step 24754: {'lr': 0.00047140402106297946, 'samples': 4752768, 'steps': 24753, 'loss/train': 0.6205389499664307}
+08/30/2021 17:37:31 - INFO - __main__ - Step 24755: {'lr': 0.000471401556465088, 'samples': 4752960, 'steps': 24754, 'loss/train': 1.293762445449829}
+08/30/2021 17:37:33 - INFO - __main__ - Step 24756: {'lr': 0.00047139909176743643, 'samples': 4753152, 'steps': 24755, 'loss/train': 2.1234817504882812}
+08/30/2021 17:37:33 - INFO - __main__ - Step 24757: {'lr': 0.0004713966269700259, 'samples': 4753344, 'steps': 24756, 'loss/train': 1.7344706058502197}
+08/30/2021 17:37:34 - INFO - __main__ - Step 24758: {'lr': 0.0004713941620728574, 'samples': 4753536, 'steps': 24757, 'loss/train': 1.5988022089004517}
+08/30/2021 17:37:34 - INFO - __main__ - Step 24759: {'lr': 0.0004713916970759321, 'samples': 4753728, 'steps': 24758, 'loss/train': 1.777037262916565}
+08/30/2021 17:37:34 - INFO - __main__ - Step 24760: {'lr': 0.0004713892319792512, 'samples': 4753920, 'steps': 24759, 'loss/train': 2.254842758178711}
+08/30/2021 17:37:35 - INFO - __main__ - Step 24761: {'lr': 0.00047138676678281564, 'samples': 4754112, 'steps': 24760, 'loss/train': 1.8314911127090454}
+08/30/2021 17:37:36 - INFO - __main__ - Step 24762: {'lr': 0.00047138430148662666, 'samples': 4754304, 'steps': 24761, 'loss/train': 1.539853572845459}
+08/30/2021 17:37:37 - INFO - __main__ - Step 24763: {'lr': 0.0004713818360906853, 'samples': 4754496, 'steps': 24762, 'loss/train': 1.1455368995666504}
+08/30/2021 17:37:37 - INFO - __main__ - Step 24764: {'lr': 0.0004713793705949927, 'samples': 4754688, 'steps': 24763, 'loss/train': 1.1345278024673462}
+08/30/2021 17:37:37 - INFO - __main__ - Step 24765: {'lr': 0.00047137690499955, 'samples': 4754880, 'steps': 24764, 'loss/train': 1.9125782251358032}
+08/30/2021 17:37:38 - INFO - __main__ - Step 24766: {'lr': 0.0004713744393043583, 'samples': 4755072, 'steps': 24765, 'loss/train': 1.405653715133667}
+08/30/2021 17:37:39 - INFO - __main__ - Step 24767: {'lr': 0.00047137197350941864, 'samples': 4755264, 'steps': 24766, 'loss/train': 2.287050485610962}
+08/30/2021 17:37:40 - INFO - __main__ - Step 24768: {'lr': 0.0004713695076147322, 'samples': 4755456, 'steps': 24767, 'loss/train': 1.530613899230957}
+08/30/2021 17:37:40 - INFO - __main__ - Step 24769: {'lr': 0.0004713670416203001, 'samples': 4755648, 'steps': 24768, 'loss/train': 1.371817708015442}
+08/30/2021 17:37:40 - INFO - __main__ - Step 24770: {'lr': 0.00047136457552612344, 'samples': 4755840, 'steps': 24769, 'loss/train': 1.6049026250839233}
+08/30/2021 17:37:41 - INFO - __main__ - Step 24771: {'lr': 0.00047136210933220325, 'samples': 4756032, 'steps': 24770, 'loss/train': 1.4269808530807495}
+08/30/2021 17:37:43 - INFO - __main__ - Step 24772: {'lr': 0.0004713596430385408, 'samples': 4756224, 'steps': 24771, 'loss/train': 1.1746535301208496}
+08/30/2021 17:37:43 - INFO - __main__ - Step 24773: {'lr': 0.00047135717664513704, 'samples': 4756416, 'steps': 24772, 'loss/train': 1.168184518814087}
+08/30/2021 17:37:43 - INFO - __main__ - Step 24774: {'lr': 0.00047135471015199315, 'samples': 4756608, 'steps': 24773, 'loss/train': 2.0779831409454346}
+08/30/2021 17:37:44 - INFO - __main__ - Step 24775: {'lr': 0.00047135224355911035, 'samples': 4756800, 'steps': 24774, 'loss/train': 1.5183665752410889}
+08/30/2021 17:37:44 - INFO - __main__ - Step 24776: {'lr': 0.0004713497768664895, 'samples': 4756992, 'steps': 24775, 'loss/train': 1.5069047212600708}
+08/30/2021 17:37:45 - INFO - __main__ - Step 24777: {'lr': 0.00047134731007413195, 'samples': 4757184, 'steps': 24776, 'loss/train': 1.4242967367172241}
+08/30/2021 17:37:46 - INFO - __main__ - Step 24778: {'lr': 0.0004713448431820387, 'samples': 4757376, 'steps': 24777, 'loss/train': 1.7829294204711914}
+08/30/2021 17:37:46 - INFO - __main__ - Step 24779: {'lr': 0.00047134237619021085, 'samples': 4757568, 'steps': 24778, 'loss/train': 1.5085433721542358}
+08/30/2021 17:37:47 - INFO - __main__ - Step 24780: {'lr': 0.00047133990909864953, 'samples': 4757760, 'steps': 24779, 'loss/train': 1.993310809135437}
+08/30/2021 17:37:47 - INFO - __main__ - Step 24781: {'lr': 0.0004713374419073559, 'samples': 4757952, 'steps': 24780, 'loss/train': 0.9177327156066895}
+08/30/2021 17:37:49 - INFO - __main__ - Step 24782: {'lr': 0.000471334974616331, 'samples': 4758144, 'steps': 24781, 'loss/train': 1.706955075263977}
+08/30/2021 17:37:49 - INFO - __main__ - Step 24783: {'lr': 0.0004713325072255761, 'samples': 4758336, 'steps': 24782, 'loss/train': 0.8460226655006409}
+08/30/2021 17:37:49 - INFO - __main__ - Step 24784: {'lr': 0.000471330039735092, 'samples': 4758528, 'steps': 24783, 'loss/train': 2.2417311668395996}
+08/30/2021 17:37:50 - INFO - __main__ - Step 24785: {'lr': 0.0004713275721448801, 'samples': 4758720, 'steps': 24784, 'loss/train': 1.4460208415985107}
+08/30/2021 17:37:50 - INFO - __main__ - Step 24786: {'lr': 0.0004713251044549414, 'samples': 4758912, 'steps': 24785, 'loss/train': 1.573750376701355}
+08/30/2021 17:37:52 - INFO - __main__ - Step 24787: {'lr': 0.000471322636665277, 'samples': 4759104, 'steps': 24786, 'loss/train': 1.1347050666809082}
+08/30/2021 17:37:52 - INFO - __main__ - Step 24788: {'lr': 0.0004713201687758881, 'samples': 4759296, 'steps': 24787, 'loss/train': 1.8069311380386353}
+08/30/2021 17:37:53 - INFO - __main__ - Step 24789: {'lr': 0.00047131770078677574, 'samples': 4759488, 'steps': 24788, 'loss/train': 1.2345600128173828}
+08/30/2021 17:37:53 - INFO - __main__ - Step 24790: {'lr': 0.000471315232697941, 'samples': 4759680, 'steps': 24789, 'loss/train': 1.3568607568740845}
+08/30/2021 17:37:53 - INFO - __main__ - Step 24791: {'lr': 0.000471312764509385, 'samples': 4759872, 'steps': 24790, 'loss/train': 1.601361870765686}
+08/30/2021 17:37:55 - INFO - __main__ - Step 24792: {'lr': 0.0004713102962211089, 'samples': 4760064, 'steps': 24791, 'loss/train': 1.5752657651901245}
+08/30/2021 17:37:55 - INFO - __main__ - Step 24793: {'lr': 0.0004713078278331138, 'samples': 4760256, 'steps': 24792, 'loss/train': 1.6407828330993652}
+08/30/2021 17:37:55 - INFO - __main__ - Step 24794: {'lr': 0.00047130535934540086, 'samples': 4760448, 'steps': 24793, 'loss/train': 1.9434902667999268}
+08/30/2021 17:37:56 - INFO - __main__ - Step 24795: {'lr': 0.00047130289075797107, 'samples': 4760640, 'steps': 24794, 'loss/train': 1.1096513271331787}
+08/30/2021 17:37:56 - INFO - __main__ - Step 24796: {'lr': 0.0004713004220708257, 'samples': 4760832, 'steps': 24795, 'loss/train': 1.5200589895248413}
+08/30/2021 17:37:56 - INFO - __main__ - Step 24797: {'lr': 0.0004712979532839656, 'samples': 4761024, 'steps': 24796, 'loss/train': 1.271109700202942}
+08/30/2021 17:37:58 - INFO - __main__ - Step 24798: {'lr': 0.00047129548439739225, 'samples': 4761216, 'steps': 24797, 'loss/train': 1.5104845762252808}
+08/30/2021 17:37:58 - INFO - __main__ - Step 24799: {'lr': 0.0004712930154111065, 'samples': 4761408, 'steps': 24798, 'loss/train': 1.9404298067092896}
+08/30/2021 17:37:59 - INFO - __main__ - Step 24800: {'lr': 0.00047129054632510947, 'samples': 4761600, 'steps': 24799, 'loss/train': 1.883735179901123}
+08/30/2021 17:37:59 - INFO - __main__ - Step 24801: {'lr': 0.00047128807713940244, 'samples': 4761792, 'steps': 24800, 'loss/train': 1.948649287223816}
+08/30/2021 17:38:00 - INFO - __main__ - Step 24802: {'lr': 0.00047128560785398633, 'samples': 4761984, 'steps': 24801, 'loss/train': 1.259140968322754}
+08/30/2021 17:38:01 - INFO - __main__ - Step 24803: {'lr': 0.0004712831384688624, 'samples': 4762176, 'steps': 24802, 'loss/train': 1.251665472984314}
+08/30/2021 17:38:01 - INFO - __main__ - Step 24804: {'lr': 0.00047128066898403166, 'samples': 4762368, 'steps': 24803, 'loss/train': 1.5575450658798218}
+08/30/2021 17:38:02 - INFO - __main__ - Step 24805: {'lr': 0.00047127819939949534, 'samples': 4762560, 'steps': 24804, 'loss/train': 1.2906776666641235}
+08/30/2021 17:38:02 - INFO - __main__ - Step 24806: {'lr': 0.00047127572971525437, 'samples': 4762752, 'steps': 24805, 'loss/train': 1.4693801403045654}
+08/30/2021 17:38:02 - INFO - __main__ - Step 24807: {'lr': 0.00047127325993131006, 'samples': 4762944, 'steps': 24806, 'loss/train': 1.3121047019958496}
+08/30/2021 17:38:04 - INFO - __main__ - Step 24808: {'lr': 0.0004712707900476634, 'samples': 4763136, 'steps': 24807, 'loss/train': 1.6688311100006104}
+08/30/2021 17:38:04 - INFO - __main__ - Step 24809: {'lr': 0.00047126832006431555, 'samples': 4763328, 'steps': 24808, 'loss/train': 1.9442788362503052}
+08/30/2021 17:38:05 - INFO - __main__ - Step 24810: {'lr': 0.00047126584998126756, 'samples': 4763520, 'steps': 24809, 'loss/train': 1.3375706672668457}
+08/30/2021 17:38:05 - INFO - __main__ - Step 24811: {'lr': 0.0004712633797985206, 'samples': 4763712, 'steps': 24810, 'loss/train': 1.653232216835022}
+08/30/2021 17:38:05 - INFO - __main__ - Step 24812: {'lr': 0.0004712609095160758, 'samples': 4763904, 'steps': 24811, 'loss/train': 1.692129373550415}
+08/30/2021 17:38:07 - INFO - __main__ - Step 24813: {'lr': 0.0004712584391339343, 'samples': 4764096, 'steps': 24812, 'loss/train': 1.700097680091858}
+08/30/2021 17:38:07 - INFO - __main__ - Step 24814: {'lr': 0.0004712559686520971, 'samples': 4764288, 'steps': 24813, 'loss/train': 1.7158104181289673}
+08/30/2021 17:38:08 - INFO - __main__ - Step 24815: {'lr': 0.0004712534980705654, 'samples': 4764480, 'steps': 24814, 'loss/train': 2.4246253967285156}
+08/30/2021 17:38:08 - INFO - __main__ - Step 24816: {'lr': 0.0004712510273893402, 'samples': 4764672, 'steps': 24815, 'loss/train': 1.4810903072357178}
+08/30/2021 17:38:08 - INFO - __main__ - Step 24817: {'lr': 0.00047124855660842283, 'samples': 4764864, 'steps': 24816, 'loss/train': 0.9266908168792725}
+08/30/2021 17:38:10 - INFO - __main__ - Step 24818: {'lr': 0.00047124608572781426, 'samples': 4765056, 'steps': 24817, 'loss/train': 1.8865001201629639}
+08/30/2021 17:38:10 - INFO - __main__ - Step 24819: {'lr': 0.0004712436147475155, 'samples': 4765248, 'steps': 24818, 'loss/train': 1.4311137199401855}
+08/30/2021 17:38:11 - INFO - __main__ - Step 24820: {'lr': 0.0004712411436675279, 'samples': 4765440, 'steps': 24819, 'loss/train': 0.7995826601982117}
+08/30/2021 17:38:11 - INFO - __main__ - Step 24821: {'lr': 0.0004712386724878524, 'samples': 4765632, 'steps': 24820, 'loss/train': 0.9235925674438477}
+08/30/2021 17:38:11 - INFO - __main__ - Step 24822: {'lr': 0.0004712362012084902, 'samples': 4765824, 'steps': 24821, 'loss/train': 1.8593734502792358}
+08/30/2021 17:38:13 - INFO - __main__ - Step 24823: {'lr': 0.00047123372982944237, 'samples': 4766016, 'steps': 24822, 'loss/train': 1.6541578769683838}
+08/30/2021 17:38:14 - INFO - __main__ - Step 24824: {'lr': 0.00047123125835071004, 'samples': 4766208, 'steps': 24823, 'loss/train': 1.3145304918289185}
+08/30/2021 17:38:14 - INFO - __main__ - Step 24825: {'lr': 0.00047122878677229426, 'samples': 4766400, 'steps': 24824, 'loss/train': 2.6243112087249756}
+08/30/2021 17:38:15 - INFO - __main__ - Step 24826: {'lr': 0.0004712263150941962, 'samples': 4766592, 'steps': 24825, 'loss/train': 1.3207083940505981}
+08/30/2021 17:38:15 - INFO - __main__ - Step 24827: {'lr': 0.0004712238433164171, 'samples': 4766784, 'steps': 24826, 'loss/train': 0.24122515320777893}
+08/30/2021 17:38:15 - INFO - __main__ - Step 24828: {'lr': 0.00047122137143895785, 'samples': 4766976, 'steps': 24827, 'loss/train': 2.5779922008514404}
+08/30/2021 17:38:18 - INFO - __main__ - Step 24829: {'lr': 0.0004712188994618197, 'samples': 4767168, 'steps': 24828, 'loss/train': 1.5170645713806152}
+08/30/2021 17:38:18 - INFO - __main__ - Step 24830: {'lr': 0.0004712164273850037, 'samples': 4767360, 'steps': 24829, 'loss/train': 1.8882523775100708}
+08/30/2021 17:38:19 - INFO - __main__ - Step 24831: {'lr': 0.00047121395520851103, 'samples': 4767552, 'steps': 24830, 'loss/train': 1.510980248451233}
+08/30/2021 17:38:19 - INFO - __main__ - Step 24832: {'lr': 0.00047121148293234274, 'samples': 4767744, 'steps': 24831, 'loss/train': 1.9384924173355103}
+08/30/2021 17:38:19 - INFO - __main__ - Step 24833: {'lr': 0.00047120901055649995, 'samples': 4767936, 'steps': 24832, 'loss/train': 1.7600089311599731}
+08/30/2021 17:38:20 - INFO - __main__ - Step 24834: {'lr': 0.0004712065380809838, 'samples': 4768128, 'steps': 24833, 'loss/train': 1.4324185848236084}
+08/30/2021 17:38:21 - INFO - __main__ - Step 24835: {'lr': 0.0004712040655057954, 'samples': 4768320, 'steps': 24834, 'loss/train': 0.06933899223804474}
+08/30/2021 17:38:22 - INFO - __main__ - Step 24836: {'lr': 0.0004712015928309359, 'samples': 4768512, 'steps': 24835, 'loss/train': 1.336204171180725}
+08/30/2021 17:38:22 - INFO - __main__ - Step 24837: {'lr': 0.0004711991200564064, 'samples': 4768704, 'steps': 24836, 'loss/train': 2.059105157852173}
+08/30/2021 17:38:22 - INFO - __main__ - Step 24838: {'lr': 0.0004711966471822079, 'samples': 4768896, 'steps': 24837, 'loss/train': 1.3179295063018799}
+08/30/2021 17:38:23 - INFO - __main__ - Step 24839: {'lr': 0.00047119417420834163, 'samples': 4769088, 'steps': 24838, 'loss/train': 1.1504651308059692}
+08/30/2021 17:38:24 - INFO - __main__ - Step 24840: {'lr': 0.00047119170113480867, 'samples': 4769280, 'steps': 24839, 'loss/train': 2.1416375637054443}
+08/30/2021 17:38:25 - INFO - __main__ - Step 24841: {'lr': 0.00047118922796161026, 'samples': 4769472, 'steps': 24840, 'loss/train': 1.8710228204727173}
+08/30/2021 17:38:25 - INFO - __main__ - Step 24842: {'lr': 0.00047118675468874727, 'samples': 4769664, 'steps': 24841, 'loss/train': 1.23186194896698}
+08/30/2021 17:38:25 - INFO - __main__ - Step 24843: {'lr': 0.00047118428131622095, 'samples': 4769856, 'steps': 24842, 'loss/train': 1.758584976196289}
+08/30/2021 17:38:26 - INFO - __main__ - Step 24844: {'lr': 0.00047118180784403243, 'samples': 4770048, 'steps': 24843, 'loss/train': 2.0206093788146973}
+08/30/2021 17:38:26 - INFO - __main__ - Step 24845: {'lr': 0.0004711793342721828, 'samples': 4770240, 'steps': 24844, 'loss/train': 1.0911056995391846}
+08/30/2021 17:38:28 - INFO - __main__ - Step 24846: {'lr': 0.00047117686060067315, 'samples': 4770432, 'steps': 24845, 'loss/train': 2.045301675796509}
+08/30/2021 17:38:28 - INFO - __main__ - Step 24847: {'lr': 0.00047117438682950467, 'samples': 4770624, 'steps': 24846, 'loss/train': 0.5238175988197327}
+08/30/2021 17:38:29 - INFO - __main__ - Step 24848: {'lr': 0.0004711719129586784, 'samples': 4770816, 'steps': 24847, 'loss/train': 1.743025302886963}
+08/30/2021 17:38:29 - INFO - __main__ - Step 24849: {'lr': 0.0004711694389881955, 'samples': 4771008, 'steps': 24848, 'loss/train': 1.199263334274292}
+08/30/2021 17:38:29 - INFO - __main__ - Step 24850: {'lr': 0.000471166964918057, 'samples': 4771200, 'steps': 24849, 'loss/train': 1.631496787071228}
+08/30/2021 17:38:31 - INFO - __main__ - Step 24851: {'lr': 0.0004711644907482641, 'samples': 4771392, 'steps': 24850, 'loss/train': 1.8362065553665161}
+08/30/2021 17:38:31 - INFO - __main__ - Step 24852: {'lr': 0.00047116201647881794, 'samples': 4771584, 'steps': 24851, 'loss/train': 1.4992926120758057}
+08/30/2021 17:38:32 - INFO - __main__ - Step 24853: {'lr': 0.00047115954210971955, 'samples': 4771776, 'steps': 24852, 'loss/train': 1.4682295322418213}
+08/30/2021 17:38:32 - INFO - __main__ - Step 24854: {'lr': 0.0004711570676409701, 'samples': 4771968, 'steps': 24853, 'loss/train': 1.775540828704834}
+08/30/2021 17:38:32 - INFO - __main__ - Step 24855: {'lr': 0.0004711545930725707, 'samples': 4772160, 'steps': 24854, 'loss/train': 1.4458611011505127}
+08/30/2021 17:38:34 - INFO - __main__ - Step 24856: {'lr': 0.0004711521184045224, 'samples': 4772352, 'steps': 24855, 'loss/train': 1.4048656225204468}
+08/30/2021 17:38:34 - INFO - __main__ - Step 24857: {'lr': 0.0004711496436368264, 'samples': 4772544, 'steps': 24856, 'loss/train': 2.022448778152466}
+08/30/2021 17:38:35 - INFO - __main__ - Step 24858: {'lr': 0.00047114716876948384, 'samples': 4772736, 'steps': 24857, 'loss/train': 1.2480905055999756}
+08/30/2021 17:38:35 - INFO - __main__ - Step 24859: {'lr': 0.0004711446938024957, 'samples': 4772928, 'steps': 24858, 'loss/train': 0.9936212301254272}
+08/30/2021 17:38:35 - INFO - __main__ - Step 24860: {'lr': 0.00047114221873586316, 'samples': 4773120, 'steps': 24859, 'loss/train': 1.71892249584198}
+08/30/2021 17:38:37 - INFO - __main__ - Step 24861: {'lr': 0.00047113974356958744, 'samples': 4773312, 'steps': 24860, 'loss/train': 1.7533053159713745}
+08/30/2021 17:38:37 - INFO - __main__ - Step 24862: {'lr': 0.0004711372683036695, 'samples': 4773504, 'steps': 24861, 'loss/train': 2.017672538757324}
+08/30/2021 17:38:38 - INFO - __main__ - Step 24863: {'lr': 0.0004711347929381105, 'samples': 4773696, 'steps': 24862, 'loss/train': 1.5883532762527466}
+08/30/2021 17:38:38 - INFO - __main__ - Step 24864: {'lr': 0.00047113231747291165, 'samples': 4773888, 'steps': 24863, 'loss/train': 1.5586352348327637}
+08/30/2021 17:38:38 - INFO - __main__ - Step 24865: {'lr': 0.0004711298419080739, 'samples': 4774080, 'steps': 24864, 'loss/train': 1.341946005821228}
+08/30/2021 17:38:40 - INFO - __main__ - Step 24866: {'lr': 0.00047112736624359855, 'samples': 4774272, 'steps': 24865, 'loss/train': 1.8073546886444092}
+08/30/2021 17:38:40 - INFO - __main__ - Step 24867: {'lr': 0.00047112489047948655, 'samples': 4774464, 'steps': 24866, 'loss/train': 1.7532434463500977}
+08/30/2021 17:38:41 - INFO - __main__ - Step 24868: {'lr': 0.00047112241461573913, 'samples': 4774656, 'steps': 24867, 'loss/train': 1.4599817991256714}
+08/30/2021 17:38:41 - INFO - __main__ - Step 24869: {'lr': 0.0004711199386523573, 'samples': 4774848, 'steps': 24868, 'loss/train': 1.343593716621399}
+08/30/2021 17:38:41 - INFO - __main__ - Step 24870: {'lr': 0.0004711174625893423, 'samples': 4775040, 'steps': 24869, 'loss/train': 1.7296785116195679}
+08/30/2021 17:38:43 - INFO - __main__ - Step 24871: {'lr': 0.00047111498642669517, 'samples': 4775232, 'steps': 24870, 'loss/train': 1.6996002197265625}
+08/30/2021 17:38:43 - INFO - __main__ - Step 24872: {'lr': 0.00047111251016441704, 'samples': 4775424, 'steps': 24871, 'loss/train': 2.030810832977295}
+08/30/2021 17:38:44 - INFO - __main__ - Step 24873: {'lr': 0.0004711100338025089, 'samples': 4775616, 'steps': 24872, 'loss/train': 0.7744000554084778}
+08/30/2021 17:38:44 - INFO - __main__ - Step 24874: {'lr': 0.00047110755734097216, 'samples': 4775808, 'steps': 24873, 'loss/train': 1.6111209392547607}
+08/30/2021 17:38:44 - INFO - __main__ - Step 24875: {'lr': 0.00047110508077980774, 'samples': 4776000, 'steps': 24874, 'loss/train': 1.3004311323165894}
+08/30/2021 17:38:46 - INFO - __main__ - Step 24876: {'lr': 0.00047110260411901674, 'samples': 4776192, 'steps': 24875, 'loss/train': 1.915921926498413}
+08/30/2021 17:38:46 - INFO - __main__ - Step 24877: {'lr': 0.0004711001273586003, 'samples': 4776384, 'steps': 24876, 'loss/train': 1.6893506050109863}
+08/30/2021 17:38:47 - INFO - __main__ - Step 24878: {'lr': 0.0004710976504985596, 'samples': 4776576, 'steps': 24877, 'loss/train': 2.1351051330566406}
+08/30/2021 17:38:47 - INFO - __main__ - Step 24879: {'lr': 0.00047109517353889575, 'samples': 4776768, 'steps': 24878, 'loss/train': 1.200385332107544}
+08/30/2021 17:38:47 - INFO - __main__ - Step 24880: {'lr': 0.0004710926964796097, 'samples': 4776960, 'steps': 24879, 'loss/train': 1.736669898033142}
+08/30/2021 17:38:50 - INFO - __main__ - Step 24881: {'lr': 0.00047109021932070284, 'samples': 4777152, 'steps': 24880, 'loss/train': 1.8226144313812256}
+08/30/2021 17:38:50 - INFO - __main__ - Step 24882: {'lr': 0.00047108774206217605, 'samples': 4777344, 'steps': 24881, 'loss/train': 1.485541582107544}
+08/30/2021 17:38:50 - INFO - __main__ - Step 24883: {'lr': 0.00047108526470403055, 'samples': 4777536, 'steps': 24882, 'loss/train': 1.3955153226852417}
+08/30/2021 17:38:51 - INFO - __main__ - Step 24884: {'lr': 0.0004710827872462674, 'samples': 4777728, 'steps': 24883, 'loss/train': 1.0091819763183594}
+08/30/2021 17:38:51 - INFO - __main__ - Step 24885: {'lr': 0.00047108030968888784, 'samples': 4777920, 'steps': 24884, 'loss/train': 1.0975103378295898}
+08/30/2021 17:38:51 - INFO - __main__ - Step 24886: {'lr': 0.00047107783203189285, 'samples': 4778112, 'steps': 24885, 'loss/train': 2.1459314823150635}
+08/30/2021 17:38:53 - INFO - __main__ - Step 24887: {'lr': 0.0004710753542752836, 'samples': 4778304, 'steps': 24886, 'loss/train': 1.6431077718734741}
+08/30/2021 17:38:53 - INFO - __main__ - Step 24888: {'lr': 0.0004710728764190612, 'samples': 4778496, 'steps': 24887, 'loss/train': 1.7486584186553955}
+08/30/2021 17:38:54 - INFO - __main__ - Step 24889: {'lr': 0.0004710703984632268, 'samples': 4778688, 'steps': 24888, 'loss/train': 1.5060125589370728}
+08/30/2021 17:38:54 - INFO - __main__ - Step 24890: {'lr': 0.0004710679204077815, 'samples': 4778880, 'steps': 24889, 'loss/train': 1.759198546409607}
+08/30/2021 17:38:55 - INFO - __main__ - Step 24891: {'lr': 0.0004710654422527264, 'samples': 4779072, 'steps': 24890, 'loss/train': 1.566688060760498}
+08/30/2021 17:38:56 - INFO - __main__ - Step 24892: {'lr': 0.0004710629639980626, 'samples': 4779264, 'steps': 24891, 'loss/train': 1.099583387374878}
+08/30/2021 17:38:57 - INFO - __main__ - Step 24893: {'lr': 0.0004710604856437912, 'samples': 4779456, 'steps': 24892, 'loss/train': 1.08847975730896}
+08/30/2021 17:38:57 - INFO - __main__ - Step 24894: {'lr': 0.00047105800718991343, 'samples': 4779648, 'steps': 24893, 'loss/train': 1.5162407159805298}
+08/30/2021 17:38:57 - INFO - __main__ - Step 24895: {'lr': 0.0004710555286364303, 'samples': 4779840, 'steps': 24894, 'loss/train': 1.71968412399292}
+08/30/2021 17:38:58 - INFO - __main__ - Step 24896: {'lr': 0.000471053049983343, 'samples': 4780032, 'steps': 24895, 'loss/train': 1.7614107131958008}
+08/30/2021 17:39:00 - INFO - __main__ - Step 24897: {'lr': 0.0004710505712306526, 'samples': 4780224, 'steps': 24896, 'loss/train': 0.6114704608917236}
+08/30/2021 17:39:00 - INFO - __main__ - Step 24898: {'lr': 0.00047104809237836023, 'samples': 4780416, 'steps': 24897, 'loss/train': 1.1677278280258179}
+08/30/2021 17:39:00 - INFO - __main__ - Step 24899: {'lr': 0.0004710456134264669, 'samples': 4780608, 'steps': 24898, 'loss/train': 2.2039995193481445}
+08/30/2021 17:39:01 - INFO - __main__ - Step 24900: {'lr': 0.0004710431343749739, 'samples': 4780800, 'steps': 24899, 'loss/train': 1.7204174995422363}
+08/30/2021 17:39:01 - INFO - __main__ - Step 24901: {'lr': 0.0004710406552238823, 'samples': 4780992, 'steps': 24900, 'loss/train': 1.0888166427612305}
+08/30/2021 17:39:02 - INFO - __main__ - Step 24902: {'lr': 0.0004710381759731932, 'samples': 4781184, 'steps': 24901, 'loss/train': 1.6266021728515625}
+08/30/2021 17:39:03 - INFO - __main__ - Step 24903: {'lr': 0.0004710356966229077, 'samples': 4781376, 'steps': 24902, 'loss/train': 1.5151076316833496}
+08/30/2021 17:39:03 - INFO - __main__ - Step 24904: {'lr': 0.00047103321717302684, 'samples': 4781568, 'steps': 24903, 'loss/train': 0.9552773833274841}
+08/30/2021 17:39:04 - INFO - __main__ - Step 24905: {'lr': 0.00047103073762355186, 'samples': 4781760, 'steps': 24904, 'loss/train': 1.417817234992981}
+08/30/2021 17:39:04 - INFO - __main__ - Step 24906: {'lr': 0.0004710282579744839, 'samples': 4781952, 'steps': 24905, 'loss/train': 1.8440959453582764}
+08/30/2021 17:39:06 - INFO - __main__ - Step 24907: {'lr': 0.000471025778225824, 'samples': 4782144, 'steps': 24906, 'loss/train': 1.4775582551956177}
+08/30/2021 17:39:06 - INFO - __main__ - Step 24908: {'lr': 0.0004710232983775733, 'samples': 4782336, 'steps': 24907, 'loss/train': 1.6019210815429688}
+08/30/2021 17:39:06 - INFO - __main__ - Step 24909: {'lr': 0.0004710208184297329, 'samples': 4782528, 'steps': 24908, 'loss/train': 0.8739994168281555}
+08/30/2021 17:39:07 - INFO - __main__ - Step 24910: {'lr': 0.0004710183383823039, 'samples': 4782720, 'steps': 24909, 'loss/train': 1.1203923225402832}
+08/30/2021 17:39:07 - INFO - __main__ - Step 24911: {'lr': 0.00047101585823528745, 'samples': 4782912, 'steps': 24910, 'loss/train': 1.5857607126235962}
+08/30/2021 17:39:08 - INFO - __main__ - Step 24912: {'lr': 0.0004710133779886847, 'samples': 4783104, 'steps': 24911, 'loss/train': 1.714115023612976}
+08/30/2021 17:39:09 - INFO - __main__ - Step 24913: {'lr': 0.00047101089764249674, 'samples': 4783296, 'steps': 24912, 'loss/train': 1.8911681175231934}
+08/30/2021 17:39:10 - INFO - __main__ - Step 24914: {'lr': 0.0004710084171967246, 'samples': 4783488, 'steps': 24913, 'loss/train': 2.1133487224578857}
+08/30/2021 17:39:10 - INFO - __main__ - Step 24915: {'lr': 0.00047100593665136946, 'samples': 4783680, 'steps': 24914, 'loss/train': 2.4652905464172363}
+08/30/2021 17:39:10 - INFO - __main__ - Step 24916: {'lr': 0.0004710034560064326, 'samples': 4783872, 'steps': 24915, 'loss/train': 1.652906060218811}
+08/30/2021 17:39:11 - INFO - __main__ - Step 24917: {'lr': 0.00047100097526191486, 'samples': 4784064, 'steps': 24916, 'loss/train': 1.570051908493042}
+08/30/2021 17:39:12 - INFO - __main__ - Step 24918: {'lr': 0.0004709984944178176, 'samples': 4784256, 'steps': 24917, 'loss/train': 0.9035937190055847}
+08/30/2021 17:39:12 - INFO - __main__ - Step 24919: {'lr': 0.0004709960134741418, 'samples': 4784448, 'steps': 24918, 'loss/train': 1.7699795961380005}
+08/30/2021 17:39:13 - INFO - __main__ - Step 24920: {'lr': 0.00047099353243088856, 'samples': 4784640, 'steps': 24919, 'loss/train': 1.5828999280929565}
+08/30/2021 17:39:13 - INFO - __main__ - Step 24921: {'lr': 0.00047099105128805906, 'samples': 4784832, 'steps': 24920, 'loss/train': 1.346340537071228}
+08/30/2021 17:39:14 - INFO - __main__ - Step 24922: {'lr': 0.00047098857004565444, 'samples': 4785024, 'steps': 24921, 'loss/train': 1.6656728982925415}
+08/30/2021 17:39:15 - INFO - __main__ - Step 24923: {'lr': 0.00047098608870367576, 'samples': 4785216, 'steps': 24922, 'loss/train': 1.6750472784042358}
+08/30/2021 17:39:15 - INFO - __main__ - Step 24924: {'lr': 0.00047098360726212406, 'samples': 4785408, 'steps': 24923, 'loss/train': 1.434363603591919}
+08/30/2021 17:39:16 - INFO - __main__ - Step 24925: {'lr': 0.0004709811257210007, 'samples': 4785600, 'steps': 24924, 'loss/train': 1.6387243270874023}
+08/30/2021 17:39:16 - INFO - __main__ - Step 24926: {'lr': 0.0004709786440803066, 'samples': 4785792, 'steps': 24925, 'loss/train': 1.2350859642028809}
+08/30/2021 17:39:16 - INFO - __main__ - Step 24927: {'lr': 0.00047097616234004295, 'samples': 4785984, 'steps': 24926, 'loss/train': 1.7146450281143188}
+08/30/2021 17:39:18 - INFO - __main__ - Step 24928: {'lr': 0.00047097368050021083, 'samples': 4786176, 'steps': 24927, 'loss/train': 1.990890383720398}
+08/30/2021 17:39:18 - INFO - __main__ - Step 24929: {'lr': 0.0004709711985608114, 'samples': 4786368, 'steps': 24928, 'loss/train': 1.1382001638412476}
+08/30/2021 17:39:19 - INFO - __main__ - Step 24930: {'lr': 0.0004709687165218457, 'samples': 4786560, 'steps': 24929, 'loss/train': 1.7983508110046387}
+08/30/2021 17:39:19 - INFO - __main__ - Step 24931: {'lr': 0.00047096623438331497, 'samples': 4786752, 'steps': 24930, 'loss/train': 1.7613146305084229}
+08/30/2021 17:39:19 - INFO - __main__ - Step 24932: {'lr': 0.00047096375214522026, 'samples': 4786944, 'steps': 24931, 'loss/train': 1.2897993326187134}
+08/30/2021 17:39:21 - INFO - __main__ - Step 24933: {'lr': 0.0004709612698075627, 'samples': 4787136, 'steps': 24932, 'loss/train': 1.6820757389068604}
+08/30/2021 17:39:21 - INFO - __main__ - Step 24934: {'lr': 0.00047095878737034335, 'samples': 4787328, 'steps': 24933, 'loss/train': 1.4690594673156738}
+08/30/2021 17:39:22 - INFO - __main__ - Step 24935: {'lr': 0.00047095630483356336, 'samples': 4787520, 'steps': 24934, 'loss/train': 1.6006884574890137}
+08/30/2021 17:39:22 - INFO - __main__ - Step 24936: {'lr': 0.00047095382219722396, 'samples': 4787712, 'steps': 24935, 'loss/train': 2.2609922885894775}
+08/30/2021 17:39:22 - INFO - __main__ - Step 24937: {'lr': 0.0004709513394613261, 'samples': 4787904, 'steps': 24936, 'loss/train': 0.47464871406555176}
+08/30/2021 17:39:25 - INFO - __main__ - Step 24938: {'lr': 0.00047094885662587104, 'samples': 4788096, 'steps': 24937, 'loss/train': 1.642889142036438}
+08/30/2021 17:39:25 - INFO - __main__ - Step 24939: {'lr': 0.0004709463736908598, 'samples': 4788288, 'steps': 24938, 'loss/train': 1.1965306997299194}
+08/30/2021 17:39:26 - INFO - __main__ - Step 24940: {'lr': 0.0004709438906562935, 'samples': 4788480, 'steps': 24939, 'loss/train': 1.2444170713424683}
+08/30/2021 17:39:26 - INFO - __main__ - Step 24941: {'lr': 0.0004709414075221734, 'samples': 4788672, 'steps': 24940, 'loss/train': 1.7122747898101807}
+08/30/2021 17:39:26 - INFO - __main__ - Step 24942: {'lr': 0.0004709389242885004, 'samples': 4788864, 'steps': 24941, 'loss/train': 1.6825224161148071}
+08/30/2021 17:39:27 - INFO - __main__ - Step 24943: {'lr': 0.00047093644095527574, 'samples': 4789056, 'steps': 24942, 'loss/train': 1.1214473247528076}
+08/30/2021 17:39:28 - INFO - __main__ - Step 24944: {'lr': 0.00047093395752250056, 'samples': 4789248, 'steps': 24943, 'loss/train': 4.759702205657959}
+08/30/2021 17:39:28 - INFO - __main__ - Step 24945: {'lr': 0.000470931473990176, 'samples': 4789440, 'steps': 24944, 'loss/train': 1.3784898519515991}
+08/30/2021 17:39:29 - INFO - __main__ - Step 24946: {'lr': 0.00047092899035830303, 'samples': 4789632, 'steps': 24945, 'loss/train': 1.405518651008606}
+08/30/2021 17:39:29 - INFO - __main__ - Step 24947: {'lr': 0.00047092650662688295, 'samples': 4789824, 'steps': 24946, 'loss/train': 2.6035568714141846}
+08/30/2021 17:39:30 - INFO - __main__ - Step 24948: {'lr': 0.00047092402279591674, 'samples': 4790016, 'steps': 24947, 'loss/train': 1.7906999588012695}
+08/30/2021 17:39:31 - INFO - __main__ - Step 24949: {'lr': 0.00047092153886540554, 'samples': 4790208, 'steps': 24948, 'loss/train': 1.128928303718567}
+08/30/2021 17:39:32 - INFO - __main__ - Step 24950: {'lr': 0.0004709190548353506, 'samples': 4790400, 'steps': 24949, 'loss/train': 1.5134373903274536}
+08/30/2021 17:39:32 - INFO - __main__ - Step 24951: {'lr': 0.0004709165707057529, 'samples': 4790592, 'steps': 24950, 'loss/train': 0.7753484845161438}
+08/30/2021 17:39:33 - INFO - __main__ - Step 24952: {'lr': 0.0004709140864766136, 'samples': 4790784, 'steps': 24951, 'loss/train': 1.4935215711593628}
+08/30/2021 17:39:33 - INFO - __main__ - Step 24953: {'lr': 0.0004709116021479338, 'samples': 4790976, 'steps': 24952, 'loss/train': 1.3633826971054077}
+08/30/2021 17:39:34 - INFO - __main__ - Step 24954: {'lr': 0.00047090911771971466, 'samples': 4791168, 'steps': 24953, 'loss/train': 1.789441466331482}
+08/30/2021 17:39:35 - INFO - __main__ - Step 24955: {'lr': 0.0004709066331919573, 'samples': 4791360, 'steps': 24954, 'loss/train': 0.17537353932857513}
+08/30/2021 17:39:36 - INFO - __main__ - Step 24956: {'lr': 0.0004709041485646628, 'samples': 4791552, 'steps': 24955, 'loss/train': 0.8306893110275269}
+08/30/2021 17:39:36 - INFO - __main__ - Step 24957: {'lr': 0.0004709016638378323, 'samples': 4791744, 'steps': 24956, 'loss/train': 1.2651863098144531}
+08/30/2021 17:39:36 - INFO - __main__ - Step 24958: {'lr': 0.00047089917901146694, 'samples': 4791936, 'steps': 24957, 'loss/train': 1.9289519786834717}
+08/30/2021 17:39:37 - INFO - __main__ - Step 24959: {'lr': 0.0004708966940855678, 'samples': 4792128, 'steps': 24958, 'loss/train': 1.972502589225769}
+08/30/2021 17:39:38 - INFO - __main__ - Step 24960: {'lr': 0.00047089420906013603, 'samples': 4792320, 'steps': 24959, 'loss/train': 1.3213255405426025}
+08/30/2021 17:39:38 - INFO - __main__ - Step 24961: {'lr': 0.0004708917239351727, 'samples': 4792512, 'steps': 24960, 'loss/train': 2.070970058441162}
+08/30/2021 17:39:39 - INFO - __main__ - Step 24962: {'lr': 0.000470889238710679, 'samples': 4792704, 'steps': 24961, 'loss/train': 1.6014602184295654}
+08/30/2021 17:39:39 - INFO - __main__ - Step 24963: {'lr': 0.00047088675338665596, 'samples': 4792896, 'steps': 24962, 'loss/train': 1.116607666015625}
+08/30/2021 17:39:40 - INFO - __main__ - Step 24964: {'lr': 0.00047088426796310486, 'samples': 4793088, 'steps': 24963, 'loss/train': 1.4058283567428589}
+08/30/2021 17:39:41 - INFO - __main__ - Step 24965: {'lr': 0.00047088178244002665, 'samples': 4793280, 'steps': 24964, 'loss/train': 1.330124855041504}
+08/30/2021 17:39:41 - INFO - __main__ - Step 24966: {'lr': 0.00047087929681742253, 'samples': 4793472, 'steps': 24965, 'loss/train': 1.7067776918411255}
+08/30/2021 17:39:42 - INFO - __main__ - Step 24967: {'lr': 0.00047087681109529364, 'samples': 4793664, 'steps': 24966, 'loss/train': 1.6116641759872437}
+08/30/2021 17:39:42 - INFO - __main__ - Step 24968: {'lr': 0.00047087432527364106, 'samples': 4793856, 'steps': 24967, 'loss/train': 1.295219898223877}
+08/30/2021 17:39:43 - INFO - __main__ - Step 24969: {'lr': 0.0004708718393524659, 'samples': 4794048, 'steps': 24968, 'loss/train': 1.5851590633392334}
+08/30/2021 17:39:44 - INFO - __main__ - Step 24970: {'lr': 0.0004708693533317693, 'samples': 4794240, 'steps': 24969, 'loss/train': 0.9088825583457947}
+08/30/2021 17:39:44 - INFO - __main__ - Step 24971: {'lr': 0.00047086686721155237, 'samples': 4794432, 'steps': 24970, 'loss/train': 1.8053698539733887}
+08/30/2021 17:39:45 - INFO - __main__ - Step 24972: {'lr': 0.00047086438099181615, 'samples': 4794624, 'steps': 24971, 'loss/train': 1.4603807926177979}
+08/30/2021 17:39:45 - INFO - __main__ - Step 24973: {'lr': 0.00047086189467256194, 'samples': 4794816, 'steps': 24972, 'loss/train': 1.676476001739502}
+08/30/2021 17:39:46 - INFO - __main__ - Step 24974: {'lr': 0.0004708594082537908, 'samples': 4795008, 'steps': 24973, 'loss/train': 1.2030974626541138}
+08/30/2021 17:39:46 - INFO - __main__ - Step 24975: {'lr': 0.00047085692173550375, 'samples': 4795200, 'steps': 24974, 'loss/train': 1.249074101448059}
+08/30/2021 17:39:47 - INFO - __main__ - Step 24976: {'lr': 0.00047085443511770206, 'samples': 4795392, 'steps': 24975, 'loss/train': 1.3432697057724}
+08/30/2021 17:39:48 - INFO - __main__ - Step 24977: {'lr': 0.0004708519484003867, 'samples': 4795584, 'steps': 24976, 'loss/train': 1.0533641576766968}
+08/30/2021 17:39:48 - INFO - __main__ - Step 24978: {'lr': 0.0004708494615835589, 'samples': 4795776, 'steps': 24977, 'loss/train': 1.8369439840316772}
+08/30/2021 17:39:49 - INFO - __main__ - Step 24979: {'lr': 0.00047084697466721973, 'samples': 4795968, 'steps': 24978, 'loss/train': 1.2232842445373535}
+08/30/2021 17:39:49 - INFO - __main__ - Step 24980: {'lr': 0.0004708444876513703, 'samples': 4796160, 'steps': 24979, 'loss/train': 1.6410752534866333}
+08/30/2021 17:39:50 - INFO - __main__ - Step 24981: {'lr': 0.0004708420005360118, 'samples': 4796352, 'steps': 24980, 'loss/train': 0.9991140365600586}
+08/30/2021 17:39:51 - INFO - __main__ - Step 24982: {'lr': 0.0004708395133211452, 'samples': 4796544, 'steps': 24981, 'loss/train': 1.582206130027771}
+08/30/2021 17:39:51 - INFO - __main__ - Step 24983: {'lr': 0.0004708370260067718, 'samples': 4796736, 'steps': 24982, 'loss/train': 1.5868440866470337}
+08/30/2021 17:39:51 - INFO - __main__ - Step 24984: {'lr': 0.00047083453859289267, 'samples': 4796928, 'steps': 24983, 'loss/train': 1.836672067642212}
+08/30/2021 17:39:52 - INFO - __main__ - Step 24985: {'lr': 0.00047083205107950886, 'samples': 4797120, 'steps': 24984, 'loss/train': 1.5847891569137573}
+08/30/2021 17:39:53 - INFO - __main__ - Step 24986: {'lr': 0.00047082956346662153, 'samples': 4797312, 'steps': 24985, 'loss/train': 0.21408843994140625}
+08/30/2021 17:39:54 - INFO - __main__ - Step 24987: {'lr': 0.00047082707575423177, 'samples': 4797504, 'steps': 24986, 'loss/train': 1.650818943977356}
+08/30/2021 17:39:54 - INFO - __main__ - Step 24988: {'lr': 0.00047082458794234087, 'samples': 4797696, 'steps': 24987, 'loss/train': 1.6033084392547607}
+08/30/2021 17:39:54 - INFO - __main__ - Step 24989: {'lr': 0.0004708221000309497, 'samples': 4797888, 'steps': 24988, 'loss/train': 1.9122878313064575}
+08/30/2021 17:39:55 - INFO - __main__ - Step 24990: {'lr': 0.0004708196120200595, 'samples': 4798080, 'steps': 24989, 'loss/train': 1.5654484033584595}
+08/30/2021 17:39:56 - INFO - __main__ - Step 24991: {'lr': 0.0004708171239096715, 'samples': 4798272, 'steps': 24990, 'loss/train': 1.3105615377426147}
+08/30/2021 17:39:57 - INFO - __main__ - Step 24992: {'lr': 0.00047081463569978655, 'samples': 4798464, 'steps': 24991, 'loss/train': 1.3675084114074707}
+08/30/2021 17:39:57 - INFO - __main__ - Step 24993: {'lr': 0.00047081214739040606, 'samples': 4798656, 'steps': 24992, 'loss/train': 1.4760974645614624}
+08/30/2021 17:39:58 - INFO - __main__ - Step 24994: {'lr': 0.000470809658981531, 'samples': 4798848, 'steps': 24993, 'loss/train': 2.2376883029937744}
+08/30/2021 17:39:58 - INFO - __main__ - Step 24995: {'lr': 0.00047080717047316245, 'samples': 4799040, 'steps': 24994, 'loss/train': 1.4054299592971802}
+08/30/2021 17:39:59 - INFO - __main__ - Step 24996: {'lr': 0.0004708046818653017, 'samples': 4799232, 'steps': 24995, 'loss/train': 1.6642056703567505}
+08/30/2021 17:40:00 - INFO - __main__ - Step 24997: {'lr': 0.0004708021931579497, 'samples': 4799424, 'steps': 24996, 'loss/train': 1.3085339069366455}
+08/30/2021 17:40:00 - INFO - __main__ - Step 24998: {'lr': 0.00047079970435110765, 'samples': 4799616, 'steps': 24997, 'loss/train': 1.699511170387268}
+08/30/2021 17:40:01 - INFO - __main__ - Step 24999: {'lr': 0.0004707972154447766, 'samples': 4799808, 'steps': 24998, 'loss/train': 4.631608963012695}
+08/30/2021 17:40:01 - INFO - __main__ - Step 25000: {'lr': 0.00047079472643895784, 'samples': 4800000, 'steps': 24999, 'loss/train': 1.5615689754486084}
+08/30/2021 17:40:01 - INFO - __main__ - Step 25001: {'lr': 0.00047079223733365234, 'samples': 4800192, 'steps': 25000, 'loss/train': 1.6584721803665161}
+08/30/2021 17:40:03 - INFO - __main__ - Step 25002: {'lr': 0.0004707897481288612, 'samples': 4800384, 'steps': 25001, 'loss/train': 1.011987328529358}
+08/30/2021 17:40:03 - INFO - __main__ - Step 25003: {'lr': 0.00047078725882458575, 'samples': 4800576, 'steps': 25002, 'loss/train': 1.2912969589233398}
+08/30/2021 17:40:04 - INFO - __main__ - Step 25004: {'lr': 0.0004707847694208269, 'samples': 4800768, 'steps': 25003, 'loss/train': 1.742913007736206}
+08/30/2021 17:40:04 - INFO - __main__ - Step 25005: {'lr': 0.0004707822799175858, 'samples': 4800960, 'steps': 25004, 'loss/train': 1.720575213432312}
+08/30/2021 17:40:04 - INFO - __main__ - Step 25006: {'lr': 0.00047077979031486363, 'samples': 4801152, 'steps': 25005, 'loss/train': 1.5674479007720947}
+08/30/2021 17:40:06 - INFO - __main__ - Step 25007: {'lr': 0.0004707773006126615, 'samples': 4801344, 'steps': 25006, 'loss/train': 1.6338114738464355}
+08/30/2021 17:40:07 - INFO - __main__ - Step 25008: {'lr': 0.0004707748108109805, 'samples': 4801536, 'steps': 25007, 'loss/train': 1.4947255849838257}
+08/30/2021 17:40:07 - INFO - __main__ - Step 25009: {'lr': 0.0004707723209098218, 'samples': 4801728, 'steps': 25008, 'loss/train': 1.4501467943191528}
+08/30/2021 17:40:08 - INFO - __main__ - Step 25010: {'lr': 0.0004707698309091865, 'samples': 4801920, 'steps': 25009, 'loss/train': 1.4030537605285645}
+08/30/2021 17:40:08 - INFO - __main__ - Step 25011: {'lr': 0.00047076734080907576, 'samples': 4802112, 'steps': 25010, 'loss/train': 1.7794524431228638}
+08/30/2021 17:40:09 - INFO - __main__ - Step 25012: {'lr': 0.0004707648506094906, 'samples': 4802304, 'steps': 25011, 'loss/train': 1.6770697832107544}
+08/30/2021 17:40:10 - INFO - __main__ - Step 25013: {'lr': 0.0004707623603104322, 'samples': 4802496, 'steps': 25012, 'loss/train': 1.873600721359253}
+08/30/2021 17:40:10 - INFO - __main__ - Step 25014: {'lr': 0.0004707598699119018, 'samples': 4802688, 'steps': 25013, 'loss/train': 1.5718786716461182}
+08/30/2021 17:40:11 - INFO - __main__ - Step 25015: {'lr': 0.0004707573794139003, 'samples': 4802880, 'steps': 25014, 'loss/train': 1.6327112913131714}
+08/30/2021 17:40:11 - INFO - __main__ - Step 25016: {'lr': 0.0004707548888164289, 'samples': 4803072, 'steps': 25015, 'loss/train': 1.7203716039657593}
+08/30/2021 17:40:12 - INFO - __main__ - Step 25017: {'lr': 0.0004707523981194889, 'samples': 4803264, 'steps': 25016, 'loss/train': 1.2609792947769165}
+08/30/2021 17:40:13 - INFO - __main__ - Step 25018: {'lr': 0.00047074990732308116, 'samples': 4803456, 'steps': 25017, 'loss/train': 1.330159068107605}
+08/30/2021 17:40:13 - INFO - __main__ - Step 25019: {'lr': 0.00047074741642720694, 'samples': 4803648, 'steps': 25018, 'loss/train': 1.607756495475769}
+08/30/2021 17:40:14 - INFO - __main__ - Step 25020: {'lr': 0.0004707449254318673, 'samples': 4803840, 'steps': 25019, 'loss/train': 1.688234567642212}
+08/30/2021 17:40:14 - INFO - __main__ - Step 25021: {'lr': 0.0004707424343370635, 'samples': 4804032, 'steps': 25020, 'loss/train': 1.5290659666061401}
+08/30/2021 17:40:16 - INFO - __main__ - Step 25022: {'lr': 0.00047073994314279647, 'samples': 4804224, 'steps': 25021, 'loss/train': 1.3709489107131958}
+08/30/2021 17:40:16 - INFO - __main__ - Step 25023: {'lr': 0.0004707374518490675, 'samples': 4804416, 'steps': 25022, 'loss/train': 1.2842025756835938}
+08/30/2021 17:40:16 - INFO - __main__ - Step 25024: {'lr': 0.0004707349604558776, 'samples': 4804608, 'steps': 25023, 'loss/train': 1.225508451461792}
+08/30/2021 17:40:17 - INFO - __main__ - Step 25025: {'lr': 0.00047073246896322797, 'samples': 4804800, 'steps': 25024, 'loss/train': 2.0839381217956543}
+08/30/2021 17:40:17 - INFO - __main__ - Step 25026: {'lr': 0.00047072997737111966, 'samples': 4804992, 'steps': 25025, 'loss/train': 1.4561882019042969}
+08/30/2021 17:40:17 - INFO - __main__ - Step 25027: {'lr': 0.0004707274856795538, 'samples': 4805184, 'steps': 25026, 'loss/train': 1.6024748086929321}
+08/30/2021 17:40:19 - INFO - __main__ - Step 25028: {'lr': 0.00047072499388853164, 'samples': 4805376, 'steps': 25027, 'loss/train': 1.900529146194458}
+08/30/2021 17:40:19 - INFO - __main__ - Step 25029: {'lr': 0.0004707225019980541, 'samples': 4805568, 'steps': 25028, 'loss/train': 1.4839271306991577}
+08/30/2021 17:40:20 - INFO - __main__ - Step 25030: {'lr': 0.00047072001000812247, 'samples': 4805760, 'steps': 25029, 'loss/train': 1.487958312034607}
+08/30/2021 17:40:20 - INFO - __main__ - Step 25031: {'lr': 0.00047071751791873774, 'samples': 4805952, 'steps': 25030, 'loss/train': 1.3906569480895996}
+08/30/2021 17:40:20 - INFO - __main__ - Step 25032: {'lr': 0.0004707150257299012, 'samples': 4806144, 'steps': 25031, 'loss/train': 1.6489684581756592}
+08/30/2021 17:40:22 - INFO - __main__ - Step 25033: {'lr': 0.0004707125334416138, 'samples': 4806336, 'steps': 25032, 'loss/train': 1.3826849460601807}
+08/30/2021 17:40:23 - INFO - __main__ - Step 25034: {'lr': 0.00047071004105387677, 'samples': 4806528, 'steps': 25033, 'loss/train': 1.9108388423919678}
+08/30/2021 17:40:23 - INFO - __main__ - Step 25035: {'lr': 0.00047070754856669115, 'samples': 4806720, 'steps': 25034, 'loss/train': 1.31353759765625}
+08/30/2021 17:40:24 - INFO - __main__ - Step 25036: {'lr': 0.0004707050559800582, 'samples': 4806912, 'steps': 25035, 'loss/train': 1.1166515350341797}
+08/30/2021 17:40:24 - INFO - __main__ - Step 25037: {'lr': 0.00047070256329397893, 'samples': 4807104, 'steps': 25036, 'loss/train': 0.8583371639251709}
+08/30/2021 17:40:24 - INFO - __main__ - Step 25038: {'lr': 0.0004707000705084545, 'samples': 4807296, 'steps': 25037, 'loss/train': 0.057708073407411575}
+08/30/2021 17:40:26 - INFO - __main__ - Step 25039: {'lr': 0.000470697577623486, 'samples': 4807488, 'steps': 25038, 'loss/train': 1.9112403392791748}
+08/30/2021 17:40:26 - INFO - __main__ - Step 25040: {'lr': 0.0004706950846390746, 'samples': 4807680, 'steps': 25039, 'loss/train': 1.9506802558898926}
+08/30/2021 17:40:27 - INFO - __main__ - Step 25041: {'lr': 0.00047069259155522135, 'samples': 4807872, 'steps': 25040, 'loss/train': 1.3299362659454346}
+08/30/2021 17:40:27 - INFO - __main__ - Step 25042: {'lr': 0.0004706900983719274, 'samples': 4808064, 'steps': 25041, 'loss/train': 2.207509756088257}
+08/30/2021 17:40:27 - INFO - __main__ - Step 25043: {'lr': 0.000470687605089194, 'samples': 4808256, 'steps': 25042, 'loss/train': 1.5854017734527588}
+08/30/2021 17:40:29 - INFO - __main__ - Step 25044: {'lr': 0.0004706851117070221, 'samples': 4808448, 'steps': 25043, 'loss/train': 1.9118982553482056}
+08/30/2021 17:40:29 - INFO - __main__ - Step 25045: {'lr': 0.0004706826182254129, 'samples': 4808640, 'steps': 25044, 'loss/train': 1.6057268381118774}
+08/30/2021 17:40:30 - INFO - __main__ - Step 25046: {'lr': 0.0004706801246443676, 'samples': 4808832, 'steps': 25045, 'loss/train': 1.7143179178237915}
+08/30/2021 17:40:30 - INFO - __main__ - Step 25047: {'lr': 0.00047067763096388717, 'samples': 4809024, 'steps': 25046, 'loss/train': 1.1472886800765991}
+08/30/2021 17:40:30 - INFO - __main__ - Step 25048: {'lr': 0.00047067513718397283, 'samples': 4809216, 'steps': 25047, 'loss/train': 1.8607536554336548}
+08/30/2021 17:40:32 - INFO - __main__ - Step 25049: {'lr': 0.0004706726433046256, 'samples': 4809408, 'steps': 25048, 'loss/train': 1.89994478225708}
+08/30/2021 17:40:32 - INFO - __main__ - Step 25050: {'lr': 0.00047067014932584674, 'samples': 4809600, 'steps': 25049, 'loss/train': 1.3649753332138062}
+08/30/2021 17:40:33 - INFO - __main__ - Step 25051: {'lr': 0.0004706676552476373, 'samples': 4809792, 'steps': 25050, 'loss/train': 1.4867832660675049}
+08/30/2021 17:40:33 - INFO - __main__ - Step 25052: {'lr': 0.0004706651610699985, 'samples': 4809984, 'steps': 25051, 'loss/train': 1.2261881828308105}
+08/30/2021 17:40:33 - INFO - __main__ - Step 25053: {'lr': 0.00047066266679293125, 'samples': 4810176, 'steps': 25052, 'loss/train': 0.8619534969329834}
+08/30/2021 17:40:34 - INFO - __main__ - Step 25054: {'lr': 0.0004706601724164369, 'samples': 4810368, 'steps': 25053, 'loss/train': 2.069847583770752}
+08/30/2021 17:40:35 - INFO - __main__ - Step 25055: {'lr': 0.0004706576779405165, 'samples': 4810560, 'steps': 25054, 'loss/train': 1.9539846181869507}
+08/30/2021 17:40:36 - INFO - __main__ - Step 25056: {'lr': 0.0004706551833651711, 'samples': 4810752, 'steps': 25055, 'loss/train': 0.2109277993440628}
+08/30/2021 17:40:36 - INFO - __main__ - Step 25057: {'lr': 0.0004706526886904019, 'samples': 4810944, 'steps': 25056, 'loss/train': 1.317997694015503}
+08/30/2021 17:40:37 - INFO - __main__ - Step 25058: {'lr': 0.00047065019391621, 'samples': 4811136, 'steps': 25057, 'loss/train': 1.2071038484573364}
+08/30/2021 17:40:37 - INFO - __main__ - Step 25059: {'lr': 0.0004706476990425965, 'samples': 4811328, 'steps': 25058, 'loss/train': 1.1856105327606201}
+08/30/2021 17:40:38 - INFO - __main__ - Step 25060: {'lr': 0.0004706452040695626, 'samples': 4811520, 'steps': 25059, 'loss/train': 1.4010510444641113}
+08/30/2021 17:40:39 - INFO - __main__ - Step 25061: {'lr': 0.0004706427089971093, 'samples': 4811712, 'steps': 25060, 'loss/train': 1.15224027633667}
+08/30/2021 17:40:39 - INFO - __main__ - Step 25062: {'lr': 0.0004706402138252379, 'samples': 4811904, 'steps': 25061, 'loss/train': 1.3296509981155396}
+08/30/2021 17:40:39 - INFO - __main__ - Step 25063: {'lr': 0.00047063771855394935, 'samples': 4812096, 'steps': 25062, 'loss/train': 2.1697821617126465}
+08/30/2021 17:40:40 - INFO - __main__ - Step 25064: {'lr': 0.00047063522318324484, 'samples': 4812288, 'steps': 25063, 'loss/train': 1.5971816778182983}
+08/30/2021 17:40:42 - INFO - __main__ - Step 25065: {'lr': 0.00047063272771312556, 'samples': 4812480, 'steps': 25064, 'loss/train': 1.9891161918640137}
+08/30/2021 17:40:43 - INFO - __main__ - Step 25066: {'lr': 0.0004706302321435926, 'samples': 4812672, 'steps': 25065, 'loss/train': 1.7171852588653564}
+08/30/2021 17:40:43 - INFO - __main__ - Step 25067: {'lr': 0.00047062773647464694, 'samples': 4812864, 'steps': 25066, 'loss/train': 1.5297914743423462}
+08/30/2021 17:40:43 - INFO - __main__ - Step 25068: {'lr': 0.00047062524070628993, 'samples': 4813056, 'steps': 25067, 'loss/train': 1.6285282373428345}
+08/30/2021 17:40:44 - INFO - __main__ - Step 25069: {'lr': 0.00047062274483852253, 'samples': 4813248, 'steps': 25068, 'loss/train': 1.307554841041565}
+08/30/2021 17:40:45 - INFO - __main__ - Step 25070: {'lr': 0.000470620248871346, 'samples': 4813440, 'steps': 25069, 'loss/train': 0.15752136707305908}
+08/30/2021 17:40:46 - INFO - __main__ - Step 25071: {'lr': 0.00047061775280476134, 'samples': 4813632, 'steps': 25070, 'loss/train': 0.3412875831127167}
+08/30/2021 17:40:46 - INFO - __main__ - Step 25072: {'lr': 0.0004706152566387697, 'samples': 4813824, 'steps': 25071, 'loss/train': 2.12052583694458}
+08/30/2021 17:40:46 - INFO - __main__ - Step 25073: {'lr': 0.0004706127603733723, 'samples': 4814016, 'steps': 25072, 'loss/train': 0.8742642402648926}
+08/30/2021 17:40:47 - INFO - __main__ - Step 25074: {'lr': 0.00047061026400857015, 'samples': 4814208, 'steps': 25073, 'loss/train': 0.27285999059677124}
+08/30/2021 17:40:49 - INFO - __main__ - Step 25075: {'lr': 0.0004706077675443644, 'samples': 4814400, 'steps': 25074, 'loss/train': 1.3892403841018677}
+08/30/2021 17:40:49 - INFO - __main__ - Step 25076: {'lr': 0.00047060527098075625, 'samples': 4814592, 'steps': 25075, 'loss/train': 1.2786834239959717}
+08/30/2021 17:40:50 - INFO - __main__ - Step 25077: {'lr': 0.0004706027743177467, 'samples': 4814784, 'steps': 25076, 'loss/train': 1.3125505447387695}
+08/30/2021 17:40:50 - INFO - __main__ - Step 25078: {'lr': 0.000470600277555337, 'samples': 4814976, 'steps': 25077, 'loss/train': 1.3752082586288452}
+08/30/2021 17:40:50 - INFO - __main__ - Step 25079: {'lr': 0.0004705977806935282, 'samples': 4815168, 'steps': 25078, 'loss/train': 1.3756707906723022}
+08/30/2021 17:40:51 - INFO - __main__ - Step 25080: {'lr': 0.00047059528373232147, 'samples': 4815360, 'steps': 25079, 'loss/train': 2.5226731300354004}
+08/30/2021 17:40:52 - INFO - __main__ - Step 25081: {'lr': 0.0004705927866717179, 'samples': 4815552, 'steps': 25080, 'loss/train': 1.7651067972183228}
+08/30/2021 17:40:53 - INFO - __main__ - Step 25082: {'lr': 0.0004705902895117186, 'samples': 4815744, 'steps': 25081, 'loss/train': 1.9038233757019043}
+08/30/2021 17:40:53 - INFO - __main__ - Step 25083: {'lr': 0.00047058779225232474, 'samples': 4815936, 'steps': 25082, 'loss/train': 1.8142799139022827}
+08/30/2021 17:40:53 - INFO - __main__ - Step 25084: {'lr': 0.0004705852948935374, 'samples': 4816128, 'steps': 25083, 'loss/train': 1.6670634746551514}
+08/30/2021 17:40:54 - INFO - __main__ - Step 25085: {'lr': 0.00047058279743535775, 'samples': 4816320, 'steps': 25084, 'loss/train': 1.678105115890503}
+08/30/2021 17:40:55 - INFO - __main__ - Step 25086: {'lr': 0.0004705802998777869, 'samples': 4816512, 'steps': 25085, 'loss/train': 1.5790992975234985}
+08/30/2021 17:40:56 - INFO - __main__ - Step 25087: {'lr': 0.0004705778022208259, 'samples': 4816704, 'steps': 25086, 'loss/train': 1.2291311025619507}
+08/30/2021 17:40:56 - INFO - __main__ - Step 25088: {'lr': 0.000470575304464476, 'samples': 4816896, 'steps': 25087, 'loss/train': 1.6294530630111694}
+08/30/2021 17:40:57 - INFO - __main__ - Step 25089: {'lr': 0.00047057280660873835, 'samples': 4817088, 'steps': 25088, 'loss/train': 1.641780972480774}
+08/30/2021 17:40:57 - INFO - __main__ - Step 25090: {'lr': 0.00047057030865361397, 'samples': 4817280, 'steps': 25089, 'loss/train': 1.677525520324707}
+08/30/2021 17:40:59 - INFO - __main__ - Step 25091: {'lr': 0.0004705678105991039, 'samples': 4817472, 'steps': 25090, 'loss/train': 0.21901018917560577}
+08/30/2021 17:40:59 - INFO - __main__ - Step 25092: {'lr': 0.00047056531244520945, 'samples': 4817664, 'steps': 25091, 'loss/train': 0.9002791047096252}
+08/30/2021 17:41:00 - INFO - __main__ - Step 25093: {'lr': 0.0004705628141919317, 'samples': 4817856, 'steps': 25092, 'loss/train': 0.9649285674095154}
+08/30/2021 17:41:00 - INFO - __main__ - Step 25094: {'lr': 0.00047056031583927175, 'samples': 4818048, 'steps': 25093, 'loss/train': 1.1545499563217163}
+08/30/2021 17:41:00 - INFO - __main__ - Step 25095: {'lr': 0.00047055781738723063, 'samples': 4818240, 'steps': 25094, 'loss/train': 1.1860684156417847}
+08/30/2021 17:41:02 - INFO - __main__ - Step 25096: {'lr': 0.0004705553188358096, 'samples': 4818432, 'steps': 25095, 'loss/train': 1.0877487659454346}
+08/30/2021 17:41:02 - INFO - __main__ - Step 25097: {'lr': 0.00047055282018500976, 'samples': 4818624, 'steps': 25096, 'loss/train': 1.5303350687026978}
+08/30/2021 17:41:03 - INFO - __main__ - Step 25098: {'lr': 0.0004705503214348323, 'samples': 4818816, 'steps': 25097, 'loss/train': 1.5555001497268677}
+08/30/2021 17:41:03 - INFO - __main__ - Step 25099: {'lr': 0.0004705478225852782, 'samples': 4819008, 'steps': 25098, 'loss/train': 1.4041889905929565}
+08/30/2021 17:41:03 - INFO - __main__ - Step 25100: {'lr': 0.0004705453236363486, 'samples': 4819200, 'steps': 25099, 'loss/train': 2.064286947250366}
+08/30/2021 17:41:04 - INFO - __main__ - Step 25101: {'lr': 0.00047054282458804477, 'samples': 4819392, 'steps': 25100, 'loss/train': 1.1360825300216675}
+08/30/2021 17:41:05 - INFO - __main__ - Step 25102: {'lr': 0.0004705403254403677, 'samples': 4819584, 'steps': 25101, 'loss/train': 1.521355152130127}
+08/30/2021 17:41:06 - INFO - __main__ - Step 25103: {'lr': 0.0004705378261933186, 'samples': 4819776, 'steps': 25102, 'loss/train': 0.9425626993179321}
+08/30/2021 17:41:06 - INFO - __main__ - Step 25104: {'lr': 0.0004705353268468985, 'samples': 4819968, 'steps': 25103, 'loss/train': 1.4939793348312378}
+08/30/2021 17:41:06 - INFO - __main__ - Step 25105: {'lr': 0.00047053282740110863, 'samples': 4820160, 'steps': 25104, 'loss/train': 1.3788909912109375}
+08/30/2021 17:41:07 - INFO - __main__ - Step 25106: {'lr': 0.00047053032785595005, 'samples': 4820352, 'steps': 25105, 'loss/train': 1.9078004360198975}
+08/30/2021 17:41:09 - INFO - __main__ - Step 25107: {'lr': 0.0004705278282114239, 'samples': 4820544, 'steps': 25106, 'loss/train': 1.6420369148254395}
+08/30/2021 17:41:09 - INFO - __main__ - Step 25108: {'lr': 0.0004705253284675314, 'samples': 4820736, 'steps': 25107, 'loss/train': 1.7942553758621216}
+08/30/2021 17:41:09 - INFO - __main__ - Step 25109: {'lr': 0.00047052282862427355, 'samples': 4820928, 'steps': 25108, 'loss/train': 1.8953509330749512}
+08/30/2021 17:41:10 - INFO - __main__ - Step 25110: {'lr': 0.0004705203286816514, 'samples': 4821120, 'steps': 25109, 'loss/train': 1.2782175540924072}
+08/30/2021 17:41:10 - INFO - __main__ - Step 25111: {'lr': 0.0004705178286396663, 'samples': 4821312, 'steps': 25110, 'loss/train': 1.3305717706680298}
+08/30/2021 17:41:10 - INFO - __main__ - Step 25112: {'lr': 0.0004705153284983192, 'samples': 4821504, 'steps': 25111, 'loss/train': 0.05513116344809532}
+08/30/2021 17:41:12 - INFO - __main__ - Step 25113: {'lr': 0.00047051282825761145, 'samples': 4821696, 'steps': 25112, 'loss/train': 1.161117672920227}
+08/30/2021 17:41:12 - INFO - __main__ - Step 25114: {'lr': 0.0004705103279175439, 'samples': 4821888, 'steps': 25113, 'loss/train': 1.6258196830749512}
+08/30/2021 17:41:13 - INFO - __main__ - Step 25115: {'lr': 0.0004705078274781178, 'samples': 4822080, 'steps': 25114, 'loss/train': 1.7940661907196045}
+08/30/2021 17:41:13 - INFO - __main__ - Step 25116: {'lr': 0.0004705053269393343, 'samples': 4822272, 'steps': 25115, 'loss/train': 0.8398537635803223}
+08/30/2021 17:41:13 - INFO - __main__ - Step 25117: {'lr': 0.00047050282630119444, 'samples': 4822464, 'steps': 25116, 'loss/train': 1.5013272762298584}
+08/30/2021 17:41:15 - INFO - __main__ - Step 25118: {'lr': 0.0004705003255636995, 'samples': 4822656, 'steps': 25117, 'loss/train': 1.9050203561782837}
+08/30/2021 17:41:16 - INFO - __main__ - Step 25119: {'lr': 0.0004704978247268505, 'samples': 4822848, 'steps': 25118, 'loss/train': 0.638746440410614}
+08/30/2021 17:41:16 - INFO - __main__ - Step 25120: {'lr': 0.0004704953237906485, 'samples': 4823040, 'steps': 25119, 'loss/train': 1.5404378175735474}
+08/30/2021 17:41:17 - INFO - __main__ - Step 25121: {'lr': 0.0004704928227550949, 'samples': 4823232, 'steps': 25120, 'loss/train': 1.76178777217865}
+08/30/2021 17:41:17 - INFO - __main__ - Step 25122: {'lr': 0.00047049032162019044, 'samples': 4823424, 'steps': 25121, 'loss/train': 1.4631903171539307}
+08/30/2021 17:41:19 - INFO - __main__ - Step 25123: {'lr': 0.0004704878203859365, 'samples': 4823616, 'steps': 25122, 'loss/train': 0.8127224445343018}
+08/30/2021 17:41:19 - INFO - __main__ - Step 25124: {'lr': 0.0004704853190523342, 'samples': 4823808, 'steps': 25123, 'loss/train': 1.4740229845046997}
+08/30/2021 17:41:19 - INFO - __main__ - Step 25125: {'lr': 0.00047048281761938456, 'samples': 4824000, 'steps': 25124, 'loss/train': 1.1336865425109863}
+08/30/2021 17:41:20 - INFO - __main__ - Step 25126: {'lr': 0.00047048031608708875, 'samples': 4824192, 'steps': 25125, 'loss/train': 1.0112028121948242}
+08/30/2021 17:41:20 - INFO - __main__ - Step 25127: {'lr': 0.000470477814455448, 'samples': 4824384, 'steps': 25126, 'loss/train': 1.4916080236434937}
+08/30/2021 17:41:22 - INFO - __main__ - Step 25128: {'lr': 0.0004704753127244633, 'samples': 4824576, 'steps': 25127, 'loss/train': 0.8901615142822266}
+08/30/2021 17:41:22 - INFO - __main__ - Step 25129: {'lr': 0.0004704728108941358, 'samples': 4824768, 'steps': 25128, 'loss/train': 1.0653492212295532}
+08/30/2021 17:41:22 - INFO - __main__ - Step 25130: {'lr': 0.00047047030896446665, 'samples': 4824960, 'steps': 25129, 'loss/train': 1.1029903888702393}
+08/30/2021 17:41:23 - INFO - __main__ - Step 25131: {'lr': 0.000470467806935457, 'samples': 4825152, 'steps': 25130, 'loss/train': 1.9126156568527222}
+08/30/2021 17:41:23 - INFO - __main__ - Step 25132: {'lr': 0.000470465304807108, 'samples': 4825344, 'steps': 25131, 'loss/train': 1.6000009775161743}
+08/30/2021 17:41:25 - INFO - __main__ - Step 25133: {'lr': 0.00047046280257942067, 'samples': 4825536, 'steps': 25132, 'loss/train': 1.7084357738494873}
+08/30/2021 17:41:25 - INFO - __main__ - Step 25134: {'lr': 0.0004704603002523962, 'samples': 4825728, 'steps': 25133, 'loss/train': 1.66991126537323}
+08/30/2021 17:41:25 - INFO - __main__ - Step 25135: {'lr': 0.00047045779782603584, 'samples': 4825920, 'steps': 25134, 'loss/train': 1.288764476776123}
+08/30/2021 17:41:26 - INFO - __main__ - Step 25136: {'lr': 0.0004704552953003405, 'samples': 4826112, 'steps': 25135, 'loss/train': 1.651648759841919}
+08/30/2021 17:41:26 - INFO - __main__ - Step 25137: {'lr': 0.0004704527926753114, 'samples': 4826304, 'steps': 25136, 'loss/train': 2.0784590244293213}
+08/30/2021 17:41:28 - INFO - __main__ - Step 25138: {'lr': 0.00047045028995094967, 'samples': 4826496, 'steps': 25137, 'loss/train': 1.7070115804672241}
+08/30/2021 17:41:28 - INFO - __main__ - Step 25139: {'lr': 0.0004704477871272564, 'samples': 4826688, 'steps': 25138, 'loss/train': 1.3351141214370728}
+08/30/2021 17:41:28 - INFO - __main__ - Step 25140: {'lr': 0.0004704452842042329, 'samples': 4826880, 'steps': 25139, 'loss/train': 1.4742670059204102}
+08/30/2021 17:41:29 - INFO - __main__ - Step 25141: {'lr': 0.00047044278118188004, 'samples': 4827072, 'steps': 25140, 'loss/train': 1.3778868913650513}
+08/30/2021 17:41:29 - INFO - __main__ - Step 25142: {'lr': 0.00047044027806019914, 'samples': 4827264, 'steps': 25141, 'loss/train': 1.4661959409713745}
+08/30/2021 17:41:31 - INFO - __main__ - Step 25143: {'lr': 0.0004704377748391912, 'samples': 4827456, 'steps': 25142, 'loss/train': 2.056394577026367}
+08/30/2021 17:41:31 - INFO - __main__ - Step 25144: {'lr': 0.0004704352715188574, 'samples': 4827648, 'steps': 25143, 'loss/train': 1.6076358556747437}
+08/30/2021 17:41:31 - INFO - __main__ - Step 25145: {'lr': 0.0004704327680991989, 'samples': 4827840, 'steps': 25144, 'loss/train': 1.732292890548706}
+08/30/2021 17:41:32 - INFO - __main__ - Step 25146: {'lr': 0.00047043026458021677, 'samples': 4828032, 'steps': 25145, 'loss/train': 1.7129887342453003}
+08/30/2021 17:41:32 - INFO - __main__ - Step 25147: {'lr': 0.0004704277609619122, 'samples': 4828224, 'steps': 25146, 'loss/train': 1.8288956880569458}
+08/30/2021 17:41:34 - INFO - __main__ - Step 25148: {'lr': 0.0004704252572442862, 'samples': 4828416, 'steps': 25147, 'loss/train': 0.5143375992774963}
+08/30/2021 17:41:34 - INFO - __main__ - Step 25149: {'lr': 0.00047042275342734006, 'samples': 4828608, 'steps': 25148, 'loss/train': 1.0501458644866943}
+08/30/2021 17:41:35 - INFO - __main__ - Step 25150: {'lr': 0.0004704202495110748, 'samples': 4828800, 'steps': 25149, 'loss/train': 0.18096794188022614}
+08/30/2021 17:41:35 - INFO - __main__ - Step 25151: {'lr': 0.00047041774549549156, 'samples': 4828992, 'steps': 25150, 'loss/train': 0.6156520843505859}
+08/30/2021 17:41:35 - INFO - __main__ - Step 25152: {'lr': 0.00047041524138059153, 'samples': 4829184, 'steps': 25151, 'loss/train': 1.241715908050537}
+08/30/2021 17:41:36 - INFO - __main__ - Step 25153: {'lr': 0.00047041273716637576, 'samples': 4829376, 'steps': 25152, 'loss/train': 1.6219685077667236}
+08/30/2021 17:41:37 - INFO - __main__ - Step 25154: {'lr': 0.00047041023285284545, 'samples': 4829568, 'steps': 25153, 'loss/train': 1.4883368015289307}
+08/30/2021 17:41:37 - INFO - __main__ - Step 25155: {'lr': 0.0004704077284400017, 'samples': 4829760, 'steps': 25154, 'loss/train': 1.6693414449691772}
+08/30/2021 17:41:38 - INFO - __main__ - Step 25156: {'lr': 0.0004704052239278456, 'samples': 4829952, 'steps': 25155, 'loss/train': 1.5799920558929443}
+08/30/2021 17:41:38 - INFO - __main__ - Step 25157: {'lr': 0.00047040271931637824, 'samples': 4830144, 'steps': 25156, 'loss/train': 1.7024641036987305}
+08/30/2021 17:41:38 - INFO - __main__ - Step 25158: {'lr': 0.0004704002146056009, 'samples': 4830336, 'steps': 25157, 'loss/train': 1.5750199556350708}
+08/30/2021 17:41:40 - INFO - __main__ - Step 25159: {'lr': 0.0004703977097955146, 'samples': 4830528, 'steps': 25158, 'loss/train': 1.4540636539459229}
+08/30/2021 17:41:41 - INFO - __main__ - Step 25160: {'lr': 0.0004703952048861204, 'samples': 4830720, 'steps': 25159, 'loss/train': 1.2269320487976074}
+08/30/2021 17:41:41 - INFO - __main__ - Step 25161: {'lr': 0.00047039269987741967, 'samples': 4830912, 'steps': 25160, 'loss/train': 1.3916511535644531}
+08/30/2021 17:41:41 - INFO - __main__ - Step 25162: {'lr': 0.0004703901947694134, 'samples': 4831104, 'steps': 25161, 'loss/train': 1.8600291013717651}
+08/30/2021 17:41:42 - INFO - __main__ - Step 25163: {'lr': 0.0004703876895621025, 'samples': 4831296, 'steps': 25162, 'loss/train': 1.2141042947769165}
+08/30/2021 17:41:43 - INFO - __main__ - Step 25164: {'lr': 0.0004703851842554885, 'samples': 4831488, 'steps': 25163, 'loss/train': 1.958831787109375}
+08/30/2021 17:41:44 - INFO - __main__ - Step 25165: {'lr': 0.0004703826788495723, 'samples': 4831680, 'steps': 25164, 'loss/train': 1.3399730920791626}
+08/30/2021 17:41:44 - INFO - __main__ - Step 25166: {'lr': 0.00047038017334435504, 'samples': 4831872, 'steps': 25165, 'loss/train': 0.9132199883460999}
+08/30/2021 17:41:44 - INFO - __main__ - Step 25167: {'lr': 0.00047037766773983794, 'samples': 4832064, 'steps': 25166, 'loss/train': 1.8331776857376099}
+08/30/2021 17:41:45 - INFO - __main__ - Step 25168: {'lr': 0.00047037516203602195, 'samples': 4832256, 'steps': 25167, 'loss/train': 1.5712714195251465}
+08/30/2021 17:41:46 - INFO - __main__ - Step 25169: {'lr': 0.0004703726562329084, 'samples': 4832448, 'steps': 25168, 'loss/train': 1.8494906425476074}
+08/30/2021 17:41:47 - INFO - __main__ - Step 25170: {'lr': 0.0004703701503304983, 'samples': 4832640, 'steps': 25169, 'loss/train': 0.22215215861797333}
+08/30/2021 17:41:47 - INFO - __main__ - Step 25171: {'lr': 0.0004703676443287928, 'samples': 4832832, 'steps': 25170, 'loss/train': 1.6323357820510864}
+08/30/2021 17:41:47 - INFO - __main__ - Step 25172: {'lr': 0.000470365138227793, 'samples': 4833024, 'steps': 25171, 'loss/train': 0.9610714912414551}
+08/30/2021 17:41:48 - INFO - __main__ - Step 25173: {'lr': 0.0004703626320275002, 'samples': 4833216, 'steps': 25172, 'loss/train': 1.2970154285430908}
+08/30/2021 17:41:48 - INFO - __main__ - Step 25174: {'lr': 0.0004703601257279153, 'samples': 4833408, 'steps': 25173, 'loss/train': 2.189345598220825}
+08/30/2021 17:41:50 - INFO - __main__ - Step 25175: {'lr': 0.0004703576193290395, 'samples': 4833600, 'steps': 25174, 'loss/train': 1.9523824453353882}
+08/30/2021 17:41:51 - INFO - __main__ - Step 25176: {'lr': 0.0004703551128308741, 'samples': 4833792, 'steps': 25175, 'loss/train': 1.7613623142242432}
+08/30/2021 17:41:51 - INFO - __main__ - Step 25177: {'lr': 0.00047035260623341996, 'samples': 4833984, 'steps': 25176, 'loss/train': 1.345569133758545}
+08/30/2021 17:41:51 - INFO - __main__ - Step 25178: {'lr': 0.0004703500995366784, 'samples': 4834176, 'steps': 25177, 'loss/train': 1.8932678699493408}
+08/30/2021 17:41:52 - INFO - __main__ - Step 25179: {'lr': 0.00047034759274065043, 'samples': 4834368, 'steps': 25178, 'loss/train': 1.2226879596710205}
+08/30/2021 17:41:53 - INFO - __main__ - Step 25180: {'lr': 0.00047034508584533724, 'samples': 4834560, 'steps': 25179, 'loss/train': 1.2147520780563354}
+08/30/2021 17:41:53 - INFO - __main__ - Step 25181: {'lr': 0.00047034257885074, 'samples': 4834752, 'steps': 25180, 'loss/train': 1.4377487897872925}
+08/30/2021 17:41:54 - INFO - __main__ - Step 25182: {'lr': 0.00047034007175685976, 'samples': 4834944, 'steps': 25181, 'loss/train': 1.7231919765472412}
+08/30/2021 17:41:54 - INFO - __main__ - Step 25183: {'lr': 0.0004703375645636977, 'samples': 4835136, 'steps': 25182, 'loss/train': 1.3159558773040771}
+08/30/2021 17:41:54 - INFO - __main__ - Step 25184: {'lr': 0.0004703350572712549, 'samples': 4835328, 'steps': 25183, 'loss/train': 1.1757681369781494}
+08/30/2021 17:41:56 - INFO - __main__ - Step 25185: {'lr': 0.00047033254987953254, 'samples': 4835520, 'steps': 25184, 'loss/train': 1.2443501949310303}
+08/30/2021 17:41:57 - INFO - __main__ - Step 25186: {'lr': 0.0004703300423885318, 'samples': 4835712, 'steps': 25185, 'loss/train': 1.4792664051055908}
+08/30/2021 17:41:57 - INFO - __main__ - Step 25187: {'lr': 0.0004703275347982536, 'samples': 4835904, 'steps': 25186, 'loss/train': 1.8373013734817505}
+08/30/2021 17:41:57 - INFO - __main__ - Step 25188: {'lr': 0.00047032502710869935, 'samples': 4836096, 'steps': 25187, 'loss/train': 1.3806008100509644}
+08/30/2021 17:41:58 - INFO - __main__ - Step 25189: {'lr': 0.00047032251931987, 'samples': 4836288, 'steps': 25188, 'loss/train': 1.3953410387039185}
+08/30/2021 17:42:00 - INFO - __main__ - Step 25190: {'lr': 0.0004703200114317667, 'samples': 4836480, 'steps': 25189, 'loss/train': 1.228415608406067}
+08/30/2021 17:42:00 - INFO - __main__ - Step 25191: {'lr': 0.0004703175034443906, 'samples': 4836672, 'steps': 25190, 'loss/train': 1.8546063899993896}
+08/30/2021 17:42:00 - INFO - __main__ - Step 25192: {'lr': 0.00047031499535774284, 'samples': 4836864, 'steps': 25191, 'loss/train': 1.718413233757019}
+08/30/2021 17:42:01 - INFO - __main__ - Step 25193: {'lr': 0.00047031248717182455, 'samples': 4837056, 'steps': 25192, 'loss/train': 1.4340121746063232}
+08/30/2021 17:42:01 - INFO - __main__ - Step 25194: {'lr': 0.00047030997888663687, 'samples': 4837248, 'steps': 25193, 'loss/train': 0.7193629145622253}
+08/30/2021 17:42:01 - INFO - __main__ - Step 25195: {'lr': 0.00047030747050218094, 'samples': 4837440, 'steps': 25194, 'loss/train': 1.7720571756362915}
+08/30/2021 17:42:02 - INFO - __main__ - Step 25196: {'lr': 0.0004703049620184578, 'samples': 4837632, 'steps': 25195, 'loss/train': 1.7892900705337524}
+08/30/2021 17:42:03 - INFO - __main__ - Step 25197: {'lr': 0.0004703024534354686, 'samples': 4837824, 'steps': 25196, 'loss/train': 2.4770662784576416}
+08/30/2021 17:42:04 - INFO - __main__ - Step 25198: {'lr': 0.0004702999447532146, 'samples': 4838016, 'steps': 25197, 'loss/train': 1.5416127443313599}
+08/30/2021 17:42:04 - INFO - __main__ - Step 25199: {'lr': 0.00047029743597169684, 'samples': 4838208, 'steps': 25198, 'loss/train': 1.4073939323425293}
+08/30/2021 17:42:04 - INFO - __main__ - Step 25200: {'lr': 0.0004702949270909164, 'samples': 4838400, 'steps': 25199, 'loss/train': 1.692219614982605}
+08/30/2021 17:42:05 - INFO - __main__ - Step 25201: {'lr': 0.0004702924181108745, 'samples': 4838592, 'steps': 25200, 'loss/train': 1.675784945487976}
+08/30/2021 17:42:06 - INFO - __main__ - Step 25202: {'lr': 0.00047028990903157233, 'samples': 4838784, 'steps': 25201, 'loss/train': 1.6392043828964233}
+08/30/2021 17:42:07 - INFO - __main__ - Step 25203: {'lr': 0.0004702873998530108, 'samples': 4838976, 'steps': 25202, 'loss/train': 1.324642300605774}
+08/30/2021 17:42:07 - INFO - __main__ - Step 25204: {'lr': 0.0004702848905751912, 'samples': 4839168, 'steps': 25203, 'loss/train': 1.2755097150802612}
+08/30/2021 17:42:08 - INFO - __main__ - Step 25205: {'lr': 0.0004702823811981146, 'samples': 4839360, 'steps': 25204, 'loss/train': 0.1903872936964035}
+08/30/2021 17:42:08 - INFO - __main__ - Step 25206: {'lr': 0.0004702798717217822, 'samples': 4839552, 'steps': 25205, 'loss/train': 1.8723169565200806}
+08/30/2021 17:42:09 - INFO - __main__ - Step 25207: {'lr': 0.0004702773621461951, 'samples': 4839744, 'steps': 25206, 'loss/train': 1.4872665405273438}
+08/30/2021 17:42:10 - INFO - __main__ - Step 25208: {'lr': 0.0004702748524713544, 'samples': 4839936, 'steps': 25207, 'loss/train': 1.4404301643371582}
+08/30/2021 17:42:10 - INFO - __main__ - Step 25209: {'lr': 0.00047027234269726123, 'samples': 4840128, 'steps': 25208, 'loss/train': 1.5485769510269165}
+08/30/2021 17:42:11 - INFO - __main__ - Step 25210: {'lr': 0.0004702698328239167, 'samples': 4840320, 'steps': 25209, 'loss/train': 1.690459132194519}
+08/30/2021 17:42:11 - INFO - __main__ - Step 25211: {'lr': 0.0004702673228513221, 'samples': 4840512, 'steps': 25210, 'loss/train': 1.505952000617981}
+08/30/2021 17:42:12 - INFO - __main__ - Step 25212: {'lr': 0.00047026481277947835, 'samples': 4840704, 'steps': 25211, 'loss/train': 1.7400099039077759}
+08/30/2021 17:42:13 - INFO - __main__ - Step 25213: {'lr': 0.0004702623026083867, 'samples': 4840896, 'steps': 25212, 'loss/train': 1.3989006280899048}
+08/30/2021 17:42:13 - INFO - __main__ - Step 25214: {'lr': 0.00047025979233804825, 'samples': 4841088, 'steps': 25213, 'loss/train': 1.509686827659607}
+08/30/2021 17:42:14 - INFO - __main__ - Step 25215: {'lr': 0.00047025728196846417, 'samples': 4841280, 'steps': 25214, 'loss/train': 1.5531995296478271}
+08/30/2021 17:42:14 - INFO - __main__ - Step 25216: {'lr': 0.0004702547714996355, 'samples': 4841472, 'steps': 25215, 'loss/train': 1.4401838779449463}
+08/30/2021 17:42:15 - INFO - __main__ - Step 25217: {'lr': 0.00047025226093156346, 'samples': 4841664, 'steps': 25216, 'loss/train': 1.3402336835861206}
+08/30/2021 17:42:16 - INFO - __main__ - Step 25218: {'lr': 0.0004702497502642492, 'samples': 4841856, 'steps': 25217, 'loss/train': 1.020683765411377}
+08/30/2021 17:42:16 - INFO - __main__ - Step 25219: {'lr': 0.0004702472394976938, 'samples': 4842048, 'steps': 25218, 'loss/train': 1.6742174625396729}
+08/30/2021 17:42:17 - INFO - __main__ - Step 25220: {'lr': 0.0004702447286318983, 'samples': 4842240, 'steps': 25219, 'loss/train': 1.570212721824646}
+08/30/2021 17:42:17 - INFO - __main__ - Step 25221: {'lr': 0.0004702422176668639, 'samples': 4842432, 'steps': 25220, 'loss/train': 1.4703494310379028}
+08/30/2021 17:42:18 - INFO - __main__ - Step 25222: {'lr': 0.00047023970660259193, 'samples': 4842624, 'steps': 25221, 'loss/train': 1.8031941652297974}
+08/30/2021 17:42:19 - INFO - __main__ - Step 25223: {'lr': 0.0004702371954390832, 'samples': 4842816, 'steps': 25222, 'loss/train': 1.4215047359466553}
+08/30/2021 17:42:19 - INFO - __main__ - Step 25224: {'lr': 0.00047023468417633905, 'samples': 4843008, 'steps': 25223, 'loss/train': 0.1384240835905075}
+08/30/2021 17:42:20 - INFO - __main__ - Step 25225: {'lr': 0.0004702321728143605, 'samples': 4843200, 'steps': 25224, 'loss/train': 1.4457356929779053}
+08/30/2021 17:42:20 - INFO - __main__ - Step 25226: {'lr': 0.0004702296613531488, 'samples': 4843392, 'steps': 25225, 'loss/train': 1.6307753324508667}
+08/30/2021 17:42:20 - INFO - __main__ - Step 25227: {'lr': 0.00047022714979270497, 'samples': 4843584, 'steps': 25226, 'loss/train': 1.2742396593093872}
+08/30/2021 17:42:22 - INFO - __main__ - Step 25228: {'lr': 0.0004702246381330302, 'samples': 4843776, 'steps': 25227, 'loss/train': 1.5508121252059937}
+08/30/2021 17:42:23 - INFO - __main__ - Step 25229: {'lr': 0.00047022212637412553, 'samples': 4843968, 'steps': 25228, 'loss/train': 1.4460803270339966}
+08/30/2021 17:42:23 - INFO - __main__ - Step 25230: {'lr': 0.00047021961451599226, 'samples': 4844160, 'steps': 25229, 'loss/train': 1.8290355205535889}
+08/30/2021 17:42:24 - INFO - __main__ - Step 25231: {'lr': 0.00047021710255863144, 'samples': 4844352, 'steps': 25230, 'loss/train': 1.8114560842514038}
+08/30/2021 17:42:24 - INFO - __main__ - Step 25232: {'lr': 0.0004702145905020442, 'samples': 4844544, 'steps': 25231, 'loss/train': 1.5833290815353394}
+08/30/2021 17:42:26 - INFO - __main__ - Step 25233: {'lr': 0.0004702120783462316, 'samples': 4844736, 'steps': 25232, 'loss/train': 1.5759029388427734}
+08/30/2021 17:42:26 - INFO - __main__ - Step 25234: {'lr': 0.00047020956609119483, 'samples': 4844928, 'steps': 25233, 'loss/train': 1.5939463376998901}
+08/30/2021 17:42:27 - INFO - __main__ - Step 25235: {'lr': 0.0004702070537369351, 'samples': 4845120, 'steps': 25234, 'loss/train': 1.4793111085891724}
+08/30/2021 17:42:27 - INFO - __main__ - Step 25236: {'lr': 0.00047020454128345333, 'samples': 4845312, 'steps': 25235, 'loss/train': 1.8605574369430542}
+08/30/2021 17:42:27 - INFO - __main__ - Step 25237: {'lr': 0.00047020202873075093, 'samples': 4845504, 'steps': 25236, 'loss/train': 1.7368876934051514}
+08/30/2021 17:42:29 - INFO - __main__ - Step 25238: {'lr': 0.00047019951607882884, 'samples': 4845696, 'steps': 25237, 'loss/train': 1.234832525253296}
+08/30/2021 17:42:29 - INFO - __main__ - Step 25239: {'lr': 0.0004701970033276882, 'samples': 4845888, 'steps': 25238, 'loss/train': 1.7299489974975586}
+08/30/2021 17:42:30 - INFO - __main__ - Step 25240: {'lr': 0.0004701944904773303, 'samples': 4846080, 'steps': 25239, 'loss/train': 1.5737006664276123}
+08/30/2021 17:42:30 - INFO - __main__ - Step 25241: {'lr': 0.0004701919775277561, 'samples': 4846272, 'steps': 25240, 'loss/train': 1.537653923034668}
+08/30/2021 17:42:30 - INFO - __main__ - Step 25242: {'lr': 0.0004701894644789668, 'samples': 4846464, 'steps': 25241, 'loss/train': 1.1209821701049805}
+08/30/2021 17:42:31 - INFO - __main__ - Step 25243: {'lr': 0.0004701869513309635, 'samples': 4846656, 'steps': 25242, 'loss/train': 2.0428268909454346}
+08/30/2021 17:42:32 - INFO - __main__ - Step 25244: {'lr': 0.0004701844380837474, 'samples': 4846848, 'steps': 25243, 'loss/train': 1.5601223707199097}
+08/30/2021 17:42:33 - INFO - __main__ - Step 25245: {'lr': 0.00047018192473731956, 'samples': 4847040, 'steps': 25244, 'loss/train': 1.5865105390548706}
+08/30/2021 17:42:33 - INFO - __main__ - Step 25246: {'lr': 0.0004701794112916812, 'samples': 4847232, 'steps': 25245, 'loss/train': 1.503543496131897}
+08/30/2021 17:42:34 - INFO - __main__ - Step 25247: {'lr': 0.00047017689774683325, 'samples': 4847424, 'steps': 25246, 'loss/train': 0.28209388256073}
+08/30/2021 17:42:34 - INFO - __main__ - Step 25248: {'lr': 0.0004701743841027771, 'samples': 4847616, 'steps': 25247, 'loss/train': 0.06271487474441528}
+08/30/2021 17:42:34 - INFO - __main__ - Step 25249: {'lr': 0.0004701718703595138, 'samples': 4847808, 'steps': 25248, 'loss/train': 2.7639365196228027}
+08/30/2021 17:42:36 - INFO - __main__ - Step 25250: {'lr': 0.0004701693565170444, 'samples': 4848000, 'steps': 25249, 'loss/train': 1.5656744241714478}
+08/30/2021 17:42:36 - INFO - __main__ - Step 25251: {'lr': 0.0004701668425753701, 'samples': 4848192, 'steps': 25250, 'loss/train': 1.3499870300292969}
+08/30/2021 17:42:37 - INFO - __main__ - Step 25252: {'lr': 0.000470164328534492, 'samples': 4848384, 'steps': 25251, 'loss/train': 1.202694296836853}
+08/30/2021 17:42:37 - INFO - __main__ - Step 25253: {'lr': 0.00047016181439441126, 'samples': 4848576, 'steps': 25252, 'loss/train': 1.1313468217849731}
+08/30/2021 17:42:37 - INFO - __main__ - Step 25254: {'lr': 0.000470159300155129, 'samples': 4848768, 'steps': 25253, 'loss/train': 1.4647761583328247}
+08/30/2021 17:42:39 - INFO - __main__ - Step 25255: {'lr': 0.00047015678581664635, 'samples': 4848960, 'steps': 25254, 'loss/train': 1.358678936958313}
+08/30/2021 17:42:39 - INFO - __main__ - Step 25256: {'lr': 0.00047015427137896446, 'samples': 4849152, 'steps': 25255, 'loss/train': 1.532971978187561}
+08/30/2021 17:42:40 - INFO - __main__ - Step 25257: {'lr': 0.0004701517568420844, 'samples': 4849344, 'steps': 25256, 'loss/train': 1.8707044124603271}
+08/30/2021 17:42:40 - INFO - __main__ - Step 25258: {'lr': 0.0004701492422060074, 'samples': 4849536, 'steps': 25257, 'loss/train': 1.8581136465072632}
+08/30/2021 17:42:40 - INFO - __main__ - Step 25259: {'lr': 0.0004701467274707346, 'samples': 4849728, 'steps': 25258, 'loss/train': 1.7593551874160767}
+08/30/2021 17:42:42 - INFO - __main__ - Step 25260: {'lr': 0.0004701442126362671, 'samples': 4849920, 'steps': 25259, 'loss/train': 1.5137451887130737}
+08/30/2021 17:42:42 - INFO - __main__ - Step 25261: {'lr': 0.0004701416977026059, 'samples': 4850112, 'steps': 25260, 'loss/train': 1.8200294971466064}
+08/30/2021 17:42:43 - INFO - __main__ - Step 25262: {'lr': 0.0004701391826697523, 'samples': 4850304, 'steps': 25261, 'loss/train': 1.3076450824737549}
+08/30/2021 17:42:43 - INFO - __main__ - Step 25263: {'lr': 0.00047013666753770736, 'samples': 4850496, 'steps': 25262, 'loss/train': 1.9197431802749634}
+08/30/2021 17:42:43 - INFO - __main__ - Step 25264: {'lr': 0.00047013415230647227, 'samples': 4850688, 'steps': 25263, 'loss/train': 1.3357831239700317}
+08/30/2021 17:42:44 - INFO - __main__ - Step 25265: {'lr': 0.0004701316369760481, 'samples': 4850880, 'steps': 25264, 'loss/train': 1.7137293815612793}
+08/30/2021 17:42:45 - INFO - __main__ - Step 25266: {'lr': 0.00047012912154643607, 'samples': 4851072, 'steps': 25265, 'loss/train': 1.2234370708465576}
+08/30/2021 17:42:46 - INFO - __main__ - Step 25267: {'lr': 0.0004701266060176372, 'samples': 4851264, 'steps': 25266, 'loss/train': 1.6347157955169678}
+08/30/2021 17:42:46 - INFO - __main__ - Step 25268: {'lr': 0.00047012409038965267, 'samples': 4851456, 'steps': 25267, 'loss/train': 0.9743822813034058}
+08/30/2021 17:42:47 - INFO - __main__ - Step 25269: {'lr': 0.0004701215746624836, 'samples': 4851648, 'steps': 25268, 'loss/train': 1.2258555889129639}
+08/30/2021 17:42:47 - INFO - __main__ - Step 25270: {'lr': 0.0004701190588361312, 'samples': 4851840, 'steps': 25269, 'loss/train': 1.1441996097564697}
+08/30/2021 17:42:48 - INFO - __main__ - Step 25271: {'lr': 0.0004701165429105966, 'samples': 4852032, 'steps': 25270, 'loss/train': 1.479071021080017}
+08/30/2021 17:42:49 - INFO - __main__ - Step 25272: {'lr': 0.0004701140268858808, 'samples': 4852224, 'steps': 25271, 'loss/train': 1.2729097604751587}
+08/30/2021 17:42:49 - INFO - __main__ - Step 25273: {'lr': 0.000470111510761985, 'samples': 4852416, 'steps': 25272, 'loss/train': 1.414404273033142}
+08/30/2021 17:42:49 - INFO - __main__ - Step 25274: {'lr': 0.0004701089945389104, 'samples': 4852608, 'steps': 25273, 'loss/train': 1.2719674110412598}
+08/30/2021 17:42:50 - INFO - __main__ - Step 25275: {'lr': 0.00047010647821665803, 'samples': 4852800, 'steps': 25274, 'loss/train': 1.6211355924606323}
+08/30/2021 17:42:52 - INFO - __main__ - Step 25276: {'lr': 0.0004701039617952291, 'samples': 4852992, 'steps': 25275, 'loss/train': 1.2120165824890137}
+08/30/2021 17:42:52 - INFO - __main__ - Step 25277: {'lr': 0.00047010144527462474, 'samples': 4853184, 'steps': 25276, 'loss/train': 1.619185209274292}
+08/30/2021 17:42:53 - INFO - __main__ - Step 25278: {'lr': 0.00047009892865484607, 'samples': 4853376, 'steps': 25277, 'loss/train': 1.2005964517593384}
+08/30/2021 17:42:53 - INFO - __main__ - Step 25279: {'lr': 0.00047009641193589423, 'samples': 4853568, 'steps': 25278, 'loss/train': 1.9050300121307373}
+08/30/2021 17:42:53 - INFO - __main__ - Step 25280: {'lr': 0.00047009389511777036, 'samples': 4853760, 'steps': 25279, 'loss/train': 1.250523328781128}
+08/30/2021 17:42:54 - INFO - __main__ - Step 25281: {'lr': 0.0004700913782004755, 'samples': 4853952, 'steps': 25280, 'loss/train': 0.06701329350471497}
+08/30/2021 17:42:56 - INFO - __main__ - Step 25282: {'lr': 0.00047008886118401084, 'samples': 4854144, 'steps': 25281, 'loss/train': 0.11463990062475204}
+08/30/2021 17:42:57 - INFO - __main__ - Step 25283: {'lr': 0.0004700863440683776, 'samples': 4854336, 'steps': 25282, 'loss/train': 1.488193392753601}
+08/30/2021 17:42:57 - INFO - __main__ - Step 25284: {'lr': 0.00047008382685357686, 'samples': 4854528, 'steps': 25283, 'loss/train': 1.741093635559082}
+08/30/2021 17:42:58 - INFO - __main__ - Step 25285: {'lr': 0.0004700813095396098, 'samples': 4854720, 'steps': 25284, 'loss/train': 0.9684827327728271}
+08/30/2021 17:42:58 - INFO - __main__ - Step 25286: {'lr': 0.00047007879212647744, 'samples': 4854912, 'steps': 25285, 'loss/train': 2.1591384410858154}
+08/30/2021 17:42:58 - INFO - __main__ - Step 25287: {'lr': 0.0004700762746141809, 'samples': 4855104, 'steps': 25286, 'loss/train': 0.5560943484306335}
+08/30/2021 17:42:59 - INFO - __main__ - Step 25288: {'lr': 0.0004700737570027214, 'samples': 4855296, 'steps': 25287, 'loss/train': 0.5318044424057007}
+08/30/2021 17:43:00 - INFO - __main__ - Step 25289: {'lr': 0.00047007123929210015, 'samples': 4855488, 'steps': 25288, 'loss/train': 1.8834632635116577}
+08/30/2021 17:43:01 - INFO - __main__ - Step 25290: {'lr': 0.00047006872148231814, 'samples': 4855680, 'steps': 25289, 'loss/train': 1.5034270286560059}
+08/30/2021 17:43:01 - INFO - __main__ - Step 25291: {'lr': 0.0004700662035733766, 'samples': 4855872, 'steps': 25290, 'loss/train': 1.0896543264389038}
+08/30/2021 17:43:01 - INFO - __main__ - Step 25292: {'lr': 0.0004700636855652766, 'samples': 4856064, 'steps': 25291, 'loss/train': 1.7092068195343018}
+08/30/2021 17:43:02 - INFO - __main__ - Step 25293: {'lr': 0.0004700611674580193, 'samples': 4856256, 'steps': 25292, 'loss/train': 1.38180410861969}
+08/30/2021 17:43:03 - INFO - __main__ - Step 25294: {'lr': 0.0004700586492516058, 'samples': 4856448, 'steps': 25293, 'loss/train': 1.4817906618118286}
+08/30/2021 17:43:04 - INFO - __main__ - Step 25295: {'lr': 0.00047005613094603727, 'samples': 4856640, 'steps': 25294, 'loss/train': 1.761993169784546}
+08/30/2021 17:43:04 - INFO - __main__ - Step 25296: {'lr': 0.0004700536125413149, 'samples': 4856832, 'steps': 25295, 'loss/train': 1.5468003749847412}
+08/30/2021 17:43:04 - INFO - __main__ - Step 25297: {'lr': 0.00047005109403743976, 'samples': 4857024, 'steps': 25296, 'loss/train': 1.3205429315567017}
+08/30/2021 17:43:05 - INFO - __main__ - Step 25298: {'lr': 0.00047004857543441294, 'samples': 4857216, 'steps': 25297, 'loss/train': 1.649469256401062}
+08/30/2021 17:43:06 - INFO - __main__ - Step 25299: {'lr': 0.00047004605673223567, 'samples': 4857408, 'steps': 25298, 'loss/train': 1.7398124933242798}
+08/30/2021 17:43:07 - INFO - __main__ - Step 25300: {'lr': 0.00047004353793090903, 'samples': 4857600, 'steps': 25299, 'loss/train': 1.5071388483047485}
+08/30/2021 17:43:07 - INFO - __main__ - Step 25301: {'lr': 0.00047004101903043416, 'samples': 4857792, 'steps': 25300, 'loss/train': 2.0160562992095947}
+08/30/2021 17:43:07 - INFO - __main__ - Step 25302: {'lr': 0.00047003850003081215, 'samples': 4857984, 'steps': 25301, 'loss/train': 1.5995603799819946}
+08/30/2021 17:43:08 - INFO - __main__ - Step 25303: {'lr': 0.0004700359809320443, 'samples': 4858176, 'steps': 25302, 'loss/train': 1.3620502948760986}
+08/30/2021 17:43:09 - INFO - __main__ - Step 25304: {'lr': 0.0004700334617341316, 'samples': 4858368, 'steps': 25303, 'loss/train': 1.541378378868103}
+08/30/2021 17:43:10 - INFO - __main__ - Step 25305: {'lr': 0.0004700309424370752, 'samples': 4858560, 'steps': 25304, 'loss/train': 1.3634676933288574}
+08/30/2021 17:43:10 - INFO - __main__ - Step 25306: {'lr': 0.00047002842304087625, 'samples': 4858752, 'steps': 25305, 'loss/train': 1.8207916021347046}
+08/30/2021 17:43:10 - INFO - __main__ - Step 25307: {'lr': 0.00047002590354553586, 'samples': 4858944, 'steps': 25306, 'loss/train': 1.3307744264602661}
+08/30/2021 17:43:11 - INFO - __main__ - Step 25308: {'lr': 0.00047002338395105527, 'samples': 4859136, 'steps': 25307, 'loss/train': 1.7076677083969116}
+08/30/2021 17:43:12 - INFO - __main__ - Step 25309: {'lr': 0.00047002086425743545, 'samples': 4859328, 'steps': 25308, 'loss/train': 1.6849370002746582}
+08/30/2021 17:43:13 - INFO - __main__ - Step 25310: {'lr': 0.0004700183444646776, 'samples': 4859520, 'steps': 25309, 'loss/train': 1.9664829969406128}
+08/30/2021 17:43:13 - INFO - __main__ - Step 25311: {'lr': 0.000470015824572783, 'samples': 4859712, 'steps': 25310, 'loss/train': 1.1894611120224}
+08/30/2021 17:43:13 - INFO - __main__ - Step 25312: {'lr': 0.00047001330458175264, 'samples': 4859904, 'steps': 25311, 'loss/train': 1.2179572582244873}
+08/30/2021 17:43:14 - INFO - __main__ - Step 25313: {'lr': 0.0004700107844915876, 'samples': 4860096, 'steps': 25312, 'loss/train': 1.4157882928848267}
+08/30/2021 17:43:15 - INFO - __main__ - Step 25314: {'lr': 0.00047000826430228915, 'samples': 4860288, 'steps': 25313, 'loss/train': 1.395578145980835}
+08/30/2021 17:43:16 - INFO - __main__ - Step 25315: {'lr': 0.00047000574401385835, 'samples': 4860480, 'steps': 25314, 'loss/train': 1.1564863920211792}
+08/30/2021 17:43:16 - INFO - __main__ - Step 25316: {'lr': 0.0004700032236262964, 'samples': 4860672, 'steps': 25315, 'loss/train': 1.2295942306518555}
+08/30/2021 17:43:16 - INFO - __main__ - Step 25317: {'lr': 0.00047000070313960436, 'samples': 4860864, 'steps': 25316, 'loss/train': 1.541870355606079}
+08/30/2021 17:43:17 - INFO - __main__ - Step 25318: {'lr': 0.00046999818255378335, 'samples': 4861056, 'steps': 25317, 'loss/train': 1.2594361305236816}
+08/30/2021 17:43:17 - INFO - __main__ - Step 25319: {'lr': 0.00046999566186883466, 'samples': 4861248, 'steps': 25318, 'loss/train': 1.2627118825912476}
+08/30/2021 17:43:19 - INFO - __main__ - Step 25320: {'lr': 0.0004699931410847592, 'samples': 4861440, 'steps': 25319, 'loss/train': 2.373678684234619}
+08/30/2021 17:43:19 - INFO - __main__ - Step 25321: {'lr': 0.00046999062020155834, 'samples': 4861632, 'steps': 25320, 'loss/train': 1.7835915088653564}
+08/30/2021 17:43:19 - INFO - __main__ - Step 25322: {'lr': 0.00046998809921923305, 'samples': 4861824, 'steps': 25321, 'loss/train': 1.5494893789291382}
+08/30/2021 17:43:20 - INFO - __main__ - Step 25323: {'lr': 0.0004699855781377845, 'samples': 4862016, 'steps': 25322, 'loss/train': 1.909134030342102}
+08/30/2021 17:43:20 - INFO - __main__ - Step 25324: {'lr': 0.0004699830569572139, 'samples': 4862208, 'steps': 25323, 'loss/train': 1.4210063219070435}
+08/30/2021 17:43:22 - INFO - __main__ - Step 25325: {'lr': 0.00046998053567752225, 'samples': 4862400, 'steps': 25324, 'loss/train': 1.3654412031173706}
+08/30/2021 17:43:22 - INFO - __main__ - Step 25326: {'lr': 0.0004699780142987108, 'samples': 4862592, 'steps': 25325, 'loss/train': 1.767876386642456}
+08/30/2021 17:43:23 - INFO - __main__ - Step 25327: {'lr': 0.0004699754928207807, 'samples': 4862784, 'steps': 25326, 'loss/train': 1.529049038887024}
+08/30/2021 17:43:23 - INFO - __main__ - Step 25328: {'lr': 0.00046997297124373293, 'samples': 4862976, 'steps': 25327, 'loss/train': 1.7410838603973389}
+08/30/2021 17:43:23 - INFO - __main__ - Step 25329: {'lr': 0.00046997044956756883, 'samples': 4863168, 'steps': 25328, 'loss/train': 2.0541467666625977}
+08/30/2021 17:43:25 - INFO - __main__ - Step 25330: {'lr': 0.00046996792779228935, 'samples': 4863360, 'steps': 25329, 'loss/train': 1.0298115015029907}
+08/30/2021 17:43:25 - INFO - __main__ - Step 25331: {'lr': 0.00046996540591789584, 'samples': 4863552, 'steps': 25330, 'loss/train': 1.5683554410934448}
+08/30/2021 17:43:26 - INFO - __main__ - Step 25332: {'lr': 0.00046996288394438924, 'samples': 4863744, 'steps': 25331, 'loss/train': 1.9218753576278687}
+08/30/2021 17:43:26 - INFO - __main__ - Step 25333: {'lr': 0.00046996036187177073, 'samples': 4863936, 'steps': 25332, 'loss/train': 1.5016952753067017}
+08/30/2021 17:43:26 - INFO - __main__ - Step 25334: {'lr': 0.0004699578397000415, 'samples': 4864128, 'steps': 25333, 'loss/train': 1.7984638214111328}
+08/30/2021 17:43:27 - INFO - __main__ - Step 25335: {'lr': 0.00046995531742920264, 'samples': 4864320, 'steps': 25334, 'loss/train': 1.4689041376113892}
+08/30/2021 17:43:28 - INFO - __main__ - Step 25336: {'lr': 0.00046995279505925535, 'samples': 4864512, 'steps': 25335, 'loss/train': 2.0290894508361816}
+08/30/2021 17:43:29 - INFO - __main__ - Step 25337: {'lr': 0.00046995027259020075, 'samples': 4864704, 'steps': 25336, 'loss/train': 0.7744262218475342}
+08/30/2021 17:43:29 - INFO - __main__ - Step 25338: {'lr': 0.00046994775002203994, 'samples': 4864896, 'steps': 25337, 'loss/train': 1.737314224243164}
+08/30/2021 17:43:29 - INFO - __main__ - Step 25339: {'lr': 0.000469945227354774, 'samples': 4865088, 'steps': 25338, 'loss/train': 1.1786948442459106}
+08/30/2021 17:43:30 - INFO - __main__ - Step 25340: {'lr': 0.00046994270458840416, 'samples': 4865280, 'steps': 25339, 'loss/train': 1.2766237258911133}
+08/30/2021 17:43:32 - INFO - __main__ - Step 25341: {'lr': 0.0004699401817229316, 'samples': 4865472, 'steps': 25340, 'loss/train': 5.965412139892578}
+08/30/2021 17:43:32 - INFO - __main__ - Step 25342: {'lr': 0.0004699376587583573, 'samples': 4865664, 'steps': 25341, 'loss/train': 1.4611304998397827}
+08/30/2021 17:43:33 - INFO - __main__ - Step 25343: {'lr': 0.0004699351356946825, 'samples': 4865856, 'steps': 25342, 'loss/train': 1.7490977048873901}
+08/30/2021 17:43:33 - INFO - __main__ - Step 25344: {'lr': 0.00046993261253190833, 'samples': 4866048, 'steps': 25343, 'loss/train': 0.5217673182487488}
+08/30/2021 17:43:33 - INFO - __main__ - Step 25345: {'lr': 0.000469930089270036, 'samples': 4866240, 'steps': 25344, 'loss/train': 1.523060917854309}
+08/30/2021 17:43:35 - INFO - __main__ - Step 25346: {'lr': 0.0004699275659090665, 'samples': 4866432, 'steps': 25345, 'loss/train': 1.999556064605713}
+08/30/2021 17:43:35 - INFO - __main__ - Step 25347: {'lr': 0.000469925042449001, 'samples': 4866624, 'steps': 25346, 'loss/train': 1.2873411178588867}
+08/30/2021 17:43:35 - INFO - __main__ - Step 25348: {'lr': 0.0004699225188898407, 'samples': 4866816, 'steps': 25347, 'loss/train': 1.5357632637023926}
+08/30/2021 17:43:36 - INFO - __main__ - Step 25349: {'lr': 0.00046991999523158666, 'samples': 4867008, 'steps': 25348, 'loss/train': 2.1388795375823975}
+08/30/2021 17:43:36 - INFO - __main__ - Step 25350: {'lr': 0.0004699174714742401, 'samples': 4867200, 'steps': 25349, 'loss/train': 1.9474326372146606}
+08/30/2021 17:43:38 - INFO - __main__ - Step 25351: {'lr': 0.0004699149476178022, 'samples': 4867392, 'steps': 25350, 'loss/train': 1.4059033393859863}
+08/30/2021 17:43:38 - INFO - __main__ - Step 25352: {'lr': 0.00046991242366227395, 'samples': 4867584, 'steps': 25351, 'loss/train': 1.1270959377288818}
+08/30/2021 17:43:39 - INFO - __main__ - Step 25353: {'lr': 0.0004699098996076565, 'samples': 4867776, 'steps': 25352, 'loss/train': 1.432145595550537}
+08/30/2021 17:43:39 - INFO - __main__ - Step 25354: {'lr': 0.0004699073754539511, 'samples': 4867968, 'steps': 25353, 'loss/train': 3.1782290935516357}
+08/30/2021 17:43:39 - INFO - __main__ - Step 25355: {'lr': 0.0004699048512011588, 'samples': 4868160, 'steps': 25354, 'loss/train': 1.304602026939392}
+08/30/2021 17:43:40 - INFO - __main__ - Step 25356: {'lr': 0.0004699023268492808, 'samples': 4868352, 'steps': 25355, 'loss/train': 1.4980871677398682}
+08/30/2021 17:43:41 - INFO - __main__ - Step 25357: {'lr': 0.0004698998023983182, 'samples': 4868544, 'steps': 25356, 'loss/train': 1.8318673372268677}
+08/30/2021 17:43:42 - INFO - __main__ - Step 25358: {'lr': 0.0004698972778482722, 'samples': 4868736, 'steps': 25357, 'loss/train': 0.9058358073234558}
+08/30/2021 17:43:42 - INFO - __main__ - Step 25359: {'lr': 0.0004698947531991438, 'samples': 4868928, 'steps': 25358, 'loss/train': 2.269063711166382}
+08/30/2021 17:43:42 - INFO - __main__ - Step 25360: {'lr': 0.0004698922284509342, 'samples': 4869120, 'steps': 25359, 'loss/train': 1.332290768623352}
+08/30/2021 17:43:43 - INFO - __main__ - Step 25361: {'lr': 0.00046988970360364456, 'samples': 4869312, 'steps': 25360, 'loss/train': 0.07109788060188293}
+08/30/2021 17:43:44 - INFO - __main__ - Step 25362: {'lr': 0.0004698871786572761, 'samples': 4869504, 'steps': 25361, 'loss/train': 1.6190969944000244}
+08/30/2021 17:43:45 - INFO - __main__ - Step 25363: {'lr': 0.0004698846536118298, 'samples': 4869696, 'steps': 25362, 'loss/train': 1.6887255907058716}
+08/30/2021 17:43:45 - INFO - __main__ - Step 25364: {'lr': 0.00046988212846730686, 'samples': 4869888, 'steps': 25363, 'loss/train': 0.9800006747245789}
+08/30/2021 17:43:46 - INFO - __main__ - Step 25365: {'lr': 0.0004698796032237085, 'samples': 4870080, 'steps': 25364, 'loss/train': 1.5346888303756714}
+08/30/2021 17:43:46 - INFO - __main__ - Step 25366: {'lr': 0.0004698770778810357, 'samples': 4870272, 'steps': 25365, 'loss/train': 1.5946332216262817}
+08/30/2021 17:43:47 - INFO - __main__ - Step 25367: {'lr': 0.00046987455243928974, 'samples': 4870464, 'steps': 25366, 'loss/train': 0.903740644454956}
+08/30/2021 17:43:48 - INFO - __main__ - Step 25368: {'lr': 0.00046987202689847165, 'samples': 4870656, 'steps': 25367, 'loss/train': 1.2486778497695923}
+08/30/2021 17:43:48 - INFO - __main__ - Step 25369: {'lr': 0.00046986950125858264, 'samples': 4870848, 'steps': 25368, 'loss/train': 0.8976453542709351}
+08/30/2021 17:43:48 - INFO - __main__ - Step 25370: {'lr': 0.0004698669755196239, 'samples': 4871040, 'steps': 25369, 'loss/train': 0.5826310515403748}
+08/30/2021 17:43:49 - INFO - __main__ - Step 25371: {'lr': 0.0004698644496815964, 'samples': 4871232, 'steps': 25370, 'loss/train': 1.3482331037521362}
+08/30/2021 17:43:49 - INFO - __main__ - Step 25372: {'lr': 0.0004698619237445013, 'samples': 4871424, 'steps': 25371, 'loss/train': 1.227567195892334}
+08/30/2021 17:43:51 - INFO - __main__ - Step 25373: {'lr': 0.00046985939770834, 'samples': 4871616, 'steps': 25372, 'loss/train': 1.7992637157440186}
+08/30/2021 17:43:51 - INFO - __main__ - Step 25374: {'lr': 0.0004698568715731133, 'samples': 4871808, 'steps': 25373, 'loss/train': 1.4941823482513428}
+08/30/2021 17:43:51 - INFO - __main__ - Step 25375: {'lr': 0.00046985434533882255, 'samples': 4872000, 'steps': 25374, 'loss/train': 1.5480879545211792}
+08/30/2021 17:43:52 - INFO - __main__ - Step 25376: {'lr': 0.00046985181900546883, 'samples': 4872192, 'steps': 25375, 'loss/train': 1.8641072511672974}
+08/30/2021 17:43:52 - INFO - __main__ - Step 25377: {'lr': 0.0004698492925730532, 'samples': 4872384, 'steps': 25376, 'loss/train': 0.9216536283493042}
+08/30/2021 17:43:54 - INFO - __main__ - Step 25378: {'lr': 0.00046984676604157696, 'samples': 4872576, 'steps': 25377, 'loss/train': 1.636277198791504}
+08/30/2021 17:43:54 - INFO - __main__ - Step 25379: {'lr': 0.0004698442394110411, 'samples': 4872768, 'steps': 25378, 'loss/train': 1.1136679649353027}
+08/30/2021 17:43:54 - INFO - __main__ - Step 25380: {'lr': 0.0004698417126814468, 'samples': 4872960, 'steps': 25379, 'loss/train': 1.6927865743637085}
+08/30/2021 17:43:55 - INFO - __main__ - Step 25381: {'lr': 0.0004698391858527953, 'samples': 4873152, 'steps': 25380, 'loss/train': 1.4523926973342896}
+08/30/2021 17:43:55 - INFO - __main__ - Step 25382: {'lr': 0.0004698366589250876, 'samples': 4873344, 'steps': 25381, 'loss/train': 0.926530122756958}
+08/30/2021 17:43:57 - INFO - __main__ - Step 25383: {'lr': 0.0004698341318983249, 'samples': 4873536, 'steps': 25382, 'loss/train': 1.1641733646392822}
+08/30/2021 17:43:57 - INFO - __main__ - Step 25384: {'lr': 0.00046983160477250837, 'samples': 4873728, 'steps': 25383, 'loss/train': 1.6348788738250732}
+08/30/2021 17:43:57 - INFO - __main__ - Step 25385: {'lr': 0.00046982907754763905, 'samples': 4873920, 'steps': 25384, 'loss/train': 1.8218257427215576}
+08/30/2021 17:43:58 - INFO - __main__ - Step 25386: {'lr': 0.0004698265502237182, 'samples': 4874112, 'steps': 25385, 'loss/train': 1.2216225862503052}
+08/30/2021 17:43:58 - INFO - __main__ - Step 25387: {'lr': 0.0004698240228007469, 'samples': 4874304, 'steps': 25386, 'loss/train': 1.2502230405807495}
+08/30/2021 17:44:00 - INFO - __main__ - Step 25388: {'lr': 0.0004698214952787262, 'samples': 4874496, 'steps': 25387, 'loss/train': 1.3003475666046143}
+08/30/2021 17:44:00 - INFO - __main__ - Step 25389: {'lr': 0.0004698189676576574, 'samples': 4874688, 'steps': 25388, 'loss/train': 1.8169384002685547}
+08/30/2021 17:44:00 - INFO - __main__ - Step 25390: {'lr': 0.00046981643993754155, 'samples': 4874880, 'steps': 25389, 'loss/train': 1.12261962890625}
+08/30/2021 17:44:01 - INFO - __main__ - Step 25391: {'lr': 0.0004698139121183798, 'samples': 4875072, 'steps': 25390, 'loss/train': 0.12249408662319183}
+08/30/2021 17:44:01 - INFO - __main__ - Step 25392: {'lr': 0.00046981138420017335, 'samples': 4875264, 'steps': 25391, 'loss/train': 1.4036651849746704}
+08/30/2021 17:44:03 - INFO - __main__ - Step 25393: {'lr': 0.00046980885618292317, 'samples': 4875456, 'steps': 25392, 'loss/train': 1.4431445598602295}
+08/30/2021 17:44:04 - INFO - __main__ - Step 25394: {'lr': 0.0004698063280666306, 'samples': 4875648, 'steps': 25393, 'loss/train': 1.2885441780090332}
+08/30/2021 17:44:04 - INFO - __main__ - Step 25395: {'lr': 0.0004698037998512966, 'samples': 4875840, 'steps': 25394, 'loss/train': 1.0415525436401367}
+08/30/2021 17:44:04 - INFO - __main__ - Step 25396: {'lr': 0.00046980127153692256, 'samples': 4876032, 'steps': 25395, 'loss/train': 0.9374186992645264}
+08/30/2021 17:44:05 - INFO - __main__ - Step 25397: {'lr': 0.00046979874312350935, 'samples': 4876224, 'steps': 25396, 'loss/train': 1.3083512783050537}
+08/30/2021 17:44:06 - INFO - __main__ - Step 25398: {'lr': 0.00046979621461105817, 'samples': 4876416, 'steps': 25397, 'loss/train': 2.505147933959961}
+08/30/2021 17:44:07 - INFO - __main__ - Step 25399: {'lr': 0.0004697936859995703, 'samples': 4876608, 'steps': 25398, 'loss/train': 1.09427809715271}
+08/30/2021 17:44:07 - INFO - __main__ - Step 25400: {'lr': 0.00046979115728904675, 'samples': 4876800, 'steps': 25399, 'loss/train': 1.5842044353485107}
+08/30/2021 17:44:07 - INFO - __main__ - Step 25401: {'lr': 0.0004697886284794887, 'samples': 4876992, 'steps': 25400, 'loss/train': 1.6713145971298218}
+08/30/2021 17:44:08 - INFO - __main__ - Step 25402: {'lr': 0.00046978609957089724, 'samples': 4877184, 'steps': 25401, 'loss/train': 1.7712210416793823}
+08/30/2021 17:44:09 - INFO - __main__ - Step 25403: {'lr': 0.0004697835705632736, 'samples': 4877376, 'steps': 25402, 'loss/train': 1.5067243576049805}
+08/30/2021 17:44:10 - INFO - __main__ - Step 25404: {'lr': 0.00046978104145661885, 'samples': 4877568, 'steps': 25403, 'loss/train': 1.6991065740585327}
+08/30/2021 17:44:10 - INFO - __main__ - Step 25405: {'lr': 0.00046977851225093423, 'samples': 4877760, 'steps': 25404, 'loss/train': 1.6329655647277832}
+08/30/2021 17:44:10 - INFO - __main__ - Step 25406: {'lr': 0.0004697759829462207, 'samples': 4877952, 'steps': 25405, 'loss/train': 0.882095217704773}
+08/30/2021 17:44:11 - INFO - __main__ - Step 25407: {'lr': 0.0004697734535424796, 'samples': 4878144, 'steps': 25406, 'loss/train': 1.3212653398513794}
+08/30/2021 17:44:12 - INFO - __main__ - Step 25408: {'lr': 0.0004697709240397119, 'samples': 4878336, 'steps': 25407, 'loss/train': 1.644166111946106}
+08/30/2021 17:44:13 - INFO - __main__ - Step 25409: {'lr': 0.00046976839443791887, 'samples': 4878528, 'steps': 25408, 'loss/train': 1.7067017555236816}
+08/30/2021 17:44:13 - INFO - __main__ - Step 25410: {'lr': 0.00046976586473710156, 'samples': 4878720, 'steps': 25409, 'loss/train': 1.8410892486572266}
+08/30/2021 17:44:13 - INFO - __main__ - Step 25411: {'lr': 0.0004697633349372611, 'samples': 4878912, 'steps': 25410, 'loss/train': 1.5275639295578003}
+08/30/2021 17:44:14 - INFO - __main__ - Step 25412: {'lr': 0.00046976080503839874, 'samples': 4879104, 'steps': 25411, 'loss/train': 1.1855192184448242}
+08/30/2021 17:44:14 - INFO - __main__ - Step 25413: {'lr': 0.0004697582750405155, 'samples': 4879296, 'steps': 25412, 'loss/train': 1.9466181993484497}
+08/30/2021 17:44:15 - INFO - __main__ - Step 25414: {'lr': 0.00046975574494361263, 'samples': 4879488, 'steps': 25413, 'loss/train': 1.5716698169708252}
+08/30/2021 17:44:16 - INFO - __main__ - Step 25415: {'lr': 0.00046975321474769115, 'samples': 4879680, 'steps': 25414, 'loss/train': 1.5435230731964111}
+08/30/2021 17:44:16 - INFO - __main__ - Step 25416: {'lr': 0.0004697506844527523, 'samples': 4879872, 'steps': 25415, 'loss/train': 1.956175446510315}
+08/30/2021 17:44:17 - INFO - __main__ - Step 25417: {'lr': 0.0004697481540587972, 'samples': 4880064, 'steps': 25416, 'loss/train': 1.6351418495178223}
+08/30/2021 17:44:18 - INFO - __main__ - Step 25418: {'lr': 0.00046974562356582694, 'samples': 4880256, 'steps': 25417, 'loss/train': 1.8114688396453857}
+08/30/2021 17:44:19 - INFO - __main__ - Step 25419: {'lr': 0.0004697430929738427, 'samples': 4880448, 'steps': 25418, 'loss/train': 1.5406980514526367}
+08/30/2021 17:44:19 - INFO - __main__ - Step 25420: {'lr': 0.0004697405622828456, 'samples': 4880640, 'steps': 25419, 'loss/train': 1.1471892595291138}
+08/30/2021 17:44:19 - INFO - __main__ - Step 25421: {'lr': 0.00046973803149283686, 'samples': 4880832, 'steps': 25420, 'loss/train': 1.5557366609573364}
+08/30/2021 17:44:20 - INFO - __main__ - Step 25422: {'lr': 0.0004697355006038175, 'samples': 4881024, 'steps': 25421, 'loss/train': 1.213868498802185}
+08/30/2021 17:44:20 - INFO - __main__ - Step 25423: {'lr': 0.0004697329696157887, 'samples': 4881216, 'steps': 25422, 'loss/train': 1.227020502090454}
+08/30/2021 17:44:22 - INFO - __main__ - Step 25424: {'lr': 0.00046973043852875163, 'samples': 4881408, 'steps': 25423, 'loss/train': 1.4905178546905518}
+08/30/2021 17:44:22 - INFO - __main__ - Step 25425: {'lr': 0.00046972790734270745, 'samples': 4881600, 'steps': 25424, 'loss/train': 1.2755528688430786}
+08/30/2021 17:44:23 - INFO - __main__ - Step 25426: {'lr': 0.0004697253760576572, 'samples': 4881792, 'steps': 25425, 'loss/train': 0.5819177627563477}
+08/30/2021 17:44:23 - INFO - __main__ - Step 25427: {'lr': 0.00046972284467360217, 'samples': 4881984, 'steps': 25426, 'loss/train': 2.251990795135498}
+08/30/2021 17:44:23 - INFO - __main__ - Step 25428: {'lr': 0.0004697203131905433, 'samples': 4882176, 'steps': 25427, 'loss/train': 1.4739199876785278}
+08/30/2021 17:44:25 - INFO - __main__ - Step 25429: {'lr': 0.00046971778160848196, 'samples': 4882368, 'steps': 25428, 'loss/train': 1.7662568092346191}
+08/30/2021 17:44:25 - INFO - __main__ - Step 25430: {'lr': 0.0004697152499274191, 'samples': 4882560, 'steps': 25429, 'loss/train': 1.4754798412322998}
+08/30/2021 17:44:26 - INFO - __main__ - Step 25431: {'lr': 0.00046971271814735593, 'samples': 4882752, 'steps': 25430, 'loss/train': 1.8401789665222168}
+08/30/2021 17:44:26 - INFO - __main__ - Step 25432: {'lr': 0.0004697101862682936, 'samples': 4882944, 'steps': 25431, 'loss/train': 1.6103200912475586}
+08/30/2021 17:44:26 - INFO - __main__ - Step 25433: {'lr': 0.00046970765429023336, 'samples': 4883136, 'steps': 25432, 'loss/train': 1.4708747863769531}
+08/30/2021 17:44:27 - INFO - __main__ - Step 25434: {'lr': 0.00046970512221317616, 'samples': 4883328, 'steps': 25433, 'loss/train': 2.0800564289093018}
+08/30/2021 17:44:28 - INFO - __main__ - Step 25435: {'lr': 0.00046970259003712323, 'samples': 4883520, 'steps': 25434, 'loss/train': 1.524448275566101}
+08/30/2021 17:44:29 - INFO - __main__ - Step 25436: {'lr': 0.00046970005776207575, 'samples': 4883712, 'steps': 25435, 'loss/train': 1.4247024059295654}
+08/30/2021 17:44:29 - INFO - __main__ - Step 25437: {'lr': 0.00046969752538803477, 'samples': 4883904, 'steps': 25436, 'loss/train': 1.6538536548614502}
+08/30/2021 17:44:29 - INFO - __main__ - Step 25438: {'lr': 0.0004696949929150015, 'samples': 4884096, 'steps': 25437, 'loss/train': 1.7013219594955444}
+08/30/2021 17:44:30 - INFO - __main__ - Step 25439: {'lr': 0.00046969246034297697, 'samples': 4884288, 'steps': 25438, 'loss/train': 1.6243163347244263}
+08/30/2021 17:44:32 - INFO - __main__ - Step 25440: {'lr': 0.0004696899276719625, 'samples': 4884480, 'steps': 25439, 'loss/train': 1.6684882640838623}
+08/30/2021 17:44:32 - INFO - __main__ - Step 25441: {'lr': 0.0004696873949019591, 'samples': 4884672, 'steps': 25440, 'loss/train': 1.020603895187378}
+08/30/2021 17:44:32 - INFO - __main__ - Step 25442: {'lr': 0.000469684862032968, 'samples': 4884864, 'steps': 25441, 'loss/train': 1.7380231618881226}
+08/30/2021 17:44:33 - INFO - __main__ - Step 25443: {'lr': 0.0004696823290649902, 'samples': 4885056, 'steps': 25442, 'loss/train': 1.3856931924819946}
+08/30/2021 17:44:33 - INFO - __main__ - Step 25444: {'lr': 0.000469679795998027, 'samples': 4885248, 'steps': 25443, 'loss/train': 1.4510107040405273}
+08/30/2021 17:44:35 - INFO - __main__ - Step 25445: {'lr': 0.00046967726283207945, 'samples': 4885440, 'steps': 25444, 'loss/train': 0.13812634348869324}
+08/30/2021 17:44:36 - INFO - __main__ - Step 25446: {'lr': 0.0004696747295671487, 'samples': 4885632, 'steps': 25445, 'loss/train': 2.291543960571289}
+08/30/2021 17:44:36 - INFO - __main__ - Step 25447: {'lr': 0.000469672196203236, 'samples': 4885824, 'steps': 25446, 'loss/train': 1.3286209106445312}
+08/30/2021 17:44:36 - INFO - __main__ - Step 25448: {'lr': 0.0004696696627403423, 'samples': 4886016, 'steps': 25447, 'loss/train': 1.4469770193099976}
+08/30/2021 17:44:37 - INFO - __main__ - Step 25449: {'lr': 0.00046966712917846887, 'samples': 4886208, 'steps': 25448, 'loss/train': 1.811905860900879}
+08/30/2021 17:44:38 - INFO - __main__ - Step 25450: {'lr': 0.00046966459551761684, 'samples': 4886400, 'steps': 25449, 'loss/train': 1.3242791891098022}
+08/30/2021 17:44:39 - INFO - __main__ - Step 25451: {'lr': 0.00046966206175778723, 'samples': 4886592, 'steps': 25450, 'loss/train': 1.4418113231658936}
+08/30/2021 17:44:39 - INFO - __main__ - Step 25452: {'lr': 0.0004696595278989814, 'samples': 4886784, 'steps': 25451, 'loss/train': 0.7630012035369873}
+08/30/2021 17:44:39 - INFO - __main__ - Step 25453: {'lr': 0.00046965699394120033, 'samples': 4886976, 'steps': 25452, 'loss/train': 1.5333282947540283}
+08/30/2021 17:44:40 - INFO - __main__ - Step 25454: {'lr': 0.0004696544598844452, 'samples': 4887168, 'steps': 25453, 'loss/train': 1.9732431173324585}
+08/30/2021 17:44:40 - INFO - __main__ - Step 25455: {'lr': 0.00046965192572871723, 'samples': 4887360, 'steps': 25454, 'loss/train': 2.340667486190796}
+08/30/2021 17:44:42 - INFO - __main__ - Step 25456: {'lr': 0.0004696493914740174, 'samples': 4887552, 'steps': 25455, 'loss/train': 1.558553695678711}
+08/30/2021 17:44:42 - INFO - __main__ - Step 25457: {'lr': 0.00046964685712034697, 'samples': 4887744, 'steps': 25456, 'loss/train': 1.2132066488265991}
+08/30/2021 17:44:42 - INFO - __main__ - Step 25458: {'lr': 0.00046964432266770713, 'samples': 4887936, 'steps': 25457, 'loss/train': 1.4271546602249146}
+08/30/2021 17:44:43 - INFO - __main__ - Step 25459: {'lr': 0.0004696417881160989, 'samples': 4888128, 'steps': 25458, 'loss/train': 1.5363397598266602}
+08/30/2021 17:44:43 - INFO - __main__ - Step 25460: {'lr': 0.0004696392534655234, 'samples': 4888320, 'steps': 25459, 'loss/train': 1.0493687391281128}
+08/30/2021 17:44:45 - INFO - __main__ - Step 25461: {'lr': 0.0004696367187159819, 'samples': 4888512, 'steps': 25460, 'loss/train': 1.2178057432174683}
+08/30/2021 17:44:45 - INFO - __main__ - Step 25462: {'lr': 0.00046963418386747547, 'samples': 4888704, 'steps': 25461, 'loss/train': 1.4813568592071533}
+08/30/2021 17:44:46 - INFO - __main__ - Step 25463: {'lr': 0.0004696316489200053, 'samples': 4888896, 'steps': 25462, 'loss/train': 1.36184823513031}
+08/30/2021 17:44:46 - INFO - __main__ - Step 25464: {'lr': 0.00046962911387357246, 'samples': 4889088, 'steps': 25463, 'loss/train': 1.0938376188278198}
+08/30/2021 17:44:46 - INFO - __main__ - Step 25465: {'lr': 0.0004696265787281782, 'samples': 4889280, 'steps': 25464, 'loss/train': 1.818878412246704}
+08/30/2021 17:44:48 - INFO - __main__ - Step 25466: {'lr': 0.0004696240434838235, 'samples': 4889472, 'steps': 25465, 'loss/train': 1.3407108783721924}
+08/30/2021 17:44:48 - INFO - __main__ - Step 25467: {'lr': 0.00046962150814050963, 'samples': 4889664, 'steps': 25466, 'loss/train': 0.990451455116272}
+08/30/2021 17:44:49 - INFO - __main__ - Step 25468: {'lr': 0.0004696189726982377, 'samples': 4889856, 'steps': 25467, 'loss/train': 1.6361366510391235}
+08/30/2021 17:44:49 - INFO - __main__ - Step 25469: {'lr': 0.00046961643715700885, 'samples': 4890048, 'steps': 25468, 'loss/train': 1.463179111480713}
+08/30/2021 17:44:49 - INFO - __main__ - Step 25470: {'lr': 0.00046961390151682426, 'samples': 4890240, 'steps': 25469, 'loss/train': 2.0250563621520996}
+08/30/2021 17:44:51 - INFO - __main__ - Step 25471: {'lr': 0.000469611365777685, 'samples': 4890432, 'steps': 25470, 'loss/train': 1.1111315488815308}
+08/30/2021 17:44:51 - INFO - __main__ - Step 25472: {'lr': 0.0004696088299395922, 'samples': 4890624, 'steps': 25471, 'loss/train': 1.9752123355865479}
+08/30/2021 17:44:52 - INFO - __main__ - Step 25473: {'lr': 0.0004696062940025471, 'samples': 4890816, 'steps': 25472, 'loss/train': 1.439778447151184}
+08/30/2021 17:44:52 - INFO - __main__ - Step 25474: {'lr': 0.0004696037579665509, 'samples': 4891008, 'steps': 25473, 'loss/train': 1.630651593208313}
+08/30/2021 17:44:52 - INFO - __main__ - Step 25475: {'lr': 0.00046960122183160446, 'samples': 4891200, 'steps': 25474, 'loss/train': 1.4994152784347534}
+08/30/2021 17:44:54 - INFO - __main__ - Step 25476: {'lr': 0.00046959868559770914, 'samples': 4891392, 'steps': 25475, 'loss/train': 0.9759613871574402}
+08/30/2021 17:44:54 - INFO - __main__ - Step 25477: {'lr': 0.00046959614926486606, 'samples': 4891584, 'steps': 25476, 'loss/train': 0.8181150555610657}
+08/30/2021 17:44:55 - INFO - __main__ - Step 25478: {'lr': 0.00046959361283307636, 'samples': 4891776, 'steps': 25477, 'loss/train': 2.7366108894348145}
+08/30/2021 17:44:55 - INFO - __main__ - Step 25479: {'lr': 0.0004695910763023412, 'samples': 4891968, 'steps': 25478, 'loss/train': 1.9911137819290161}
+08/30/2021 17:44:55 - INFO - __main__ - Step 25480: {'lr': 0.0004695885396726616, 'samples': 4892160, 'steps': 25479, 'loss/train': 1.0219414234161377}
+08/30/2021 17:44:56 - INFO - __main__ - Step 25481: {'lr': 0.00046958600294403887, 'samples': 4892352, 'steps': 25480, 'loss/train': 1.419118046760559}
+08/30/2021 17:44:57 - INFO - __main__ - Step 25482: {'lr': 0.000469583466116474, 'samples': 4892544, 'steps': 25481, 'loss/train': 1.3893498182296753}
+08/30/2021 17:44:58 - INFO - __main__ - Step 25483: {'lr': 0.00046958092918996823, 'samples': 4892736, 'steps': 25482, 'loss/train': 0.8322604298591614}
+08/30/2021 17:44:58 - INFO - __main__ - Step 25484: {'lr': 0.0004695783921645227, 'samples': 4892928, 'steps': 25483, 'loss/train': 2.1924386024475098}
+08/30/2021 17:44:59 - INFO - __main__ - Step 25485: {'lr': 0.00046957585504013853, 'samples': 4893120, 'steps': 25484, 'loss/train': 1.9128268957138062}
+08/30/2021 17:44:59 - INFO - __main__ - Step 25486: {'lr': 0.0004695733178168169, 'samples': 4893312, 'steps': 25485, 'loss/train': 1.4193248748779297}
+08/30/2021 17:45:00 - INFO - __main__ - Step 25487: {'lr': 0.00046957078049455895, 'samples': 4893504, 'steps': 25486, 'loss/train': 0.7644988894462585}
+08/30/2021 17:45:01 - INFO - __main__ - Step 25488: {'lr': 0.00046956824307336565, 'samples': 4893696, 'steps': 25487, 'loss/train': 1.4632740020751953}
+08/30/2021 17:45:01 - INFO - __main__ - Step 25489: {'lr': 0.0004695657055532384, 'samples': 4893888, 'steps': 25488, 'loss/train': 1.8015514612197876}
+08/30/2021 17:45:02 - INFO - __main__ - Step 25490: {'lr': 0.0004695631679341782, 'samples': 4894080, 'steps': 25489, 'loss/train': 1.416368842124939}
+08/30/2021 17:45:02 - INFO - __main__ - Step 25491: {'lr': 0.0004695606302161862, 'samples': 4894272, 'steps': 25490, 'loss/train': 1.3531547784805298}
+08/30/2021 17:45:04 - INFO - __main__ - Step 25492: {'lr': 0.0004695580923992636, 'samples': 4894464, 'steps': 25491, 'loss/train': 1.4158116579055786}
+08/30/2021 17:45:04 - INFO - __main__ - Step 25493: {'lr': 0.0004695555544834116, 'samples': 4894656, 'steps': 25492, 'loss/train': 1.2660306692123413}
+08/30/2021 17:45:04 - INFO - __main__ - Step 25494: {'lr': 0.00046955301646863114, 'samples': 4894848, 'steps': 25493, 'loss/train': 1.0336216688156128}
+08/30/2021 17:45:05 - INFO - __main__ - Step 25495: {'lr': 0.0004695504783549235, 'samples': 4895040, 'steps': 25494, 'loss/train': 1.3519583940505981}
+08/30/2021 17:45:05 - INFO - __main__ - Step 25496: {'lr': 0.0004695479401422898, 'samples': 4895232, 'steps': 25495, 'loss/train': 1.8910647630691528}
+08/30/2021 17:45:07 - INFO - __main__ - Step 25497: {'lr': 0.0004695454018307312, 'samples': 4895424, 'steps': 25496, 'loss/train': 1.2742998600006104}
+08/30/2021 17:45:08 - INFO - __main__ - Step 25498: {'lr': 0.0004695428634202488, 'samples': 4895616, 'steps': 25497, 'loss/train': 1.496669888496399}
+08/30/2021 17:45:08 - INFO - __main__ - Step 25499: {'lr': 0.0004695403249108438, 'samples': 4895808, 'steps': 25498, 'loss/train': 1.51729416847229}
+08/30/2021 17:45:08 - INFO - __main__ - Step 25500: {'lr': 0.0004695377863025173, 'samples': 4896000, 'steps': 25499, 'loss/train': 0.8094951510429382}
+08/30/2021 17:45:09 - INFO - __main__ - Step 25501: {'lr': 0.00046953524759527055, 'samples': 4896192, 'steps': 25500, 'loss/train': 1.338602900505066}
+08/30/2021 17:45:10 - INFO - __main__ - Step 25502: {'lr': 0.0004695327087891045, 'samples': 4896384, 'steps': 25501, 'loss/train': 0.6852303147315979}
+08/30/2021 17:45:11 - INFO - __main__ - Step 25503: {'lr': 0.00046953016988402044, 'samples': 4896576, 'steps': 25502, 'loss/train': 1.0759178400039673}
+08/30/2021 17:45:11 - INFO - __main__ - Step 25504: {'lr': 0.0004695276308800194, 'samples': 4896768, 'steps': 25503, 'loss/train': 1.9079062938690186}
+08/30/2021 17:45:11 - INFO - __main__ - Step 25505: {'lr': 0.00046952509177710267, 'samples': 4896960, 'steps': 25504, 'loss/train': 1.7435216903686523}
+08/30/2021 17:45:12 - INFO - __main__ - Step 25506: {'lr': 0.00046952255257527134, 'samples': 4897152, 'steps': 25505, 'loss/train': 1.421472430229187}
+08/30/2021 17:45:12 - INFO - __main__ - Step 25507: {'lr': 0.0004695200132745265, 'samples': 4897344, 'steps': 25506, 'loss/train': 0.0785176008939743}
+08/30/2021 17:45:14 - INFO - __main__ - Step 25508: {'lr': 0.00046951747387486933, 'samples': 4897536, 'steps': 25507, 'loss/train': 1.4423470497131348}
+08/30/2021 17:45:14 - INFO - __main__ - Step 25509: {'lr': 0.00046951493437630097, 'samples': 4897728, 'steps': 25508, 'loss/train': 1.6386562585830688}
+08/30/2021 17:45:15 - INFO - __main__ - Step 25510: {'lr': 0.0004695123947788226, 'samples': 4897920, 'steps': 25509, 'loss/train': 1.7119576930999756}
+08/30/2021 17:45:15 - INFO - __main__ - Step 25511: {'lr': 0.0004695098550824353, 'samples': 4898112, 'steps': 25510, 'loss/train': 1.0653730630874634}
+08/30/2021 17:45:15 - INFO - __main__ - Step 25512: {'lr': 0.0004695073152871403, 'samples': 4898304, 'steps': 25511, 'loss/train': 1.4548927545547485}
+08/30/2021 17:45:17 - INFO - __main__ - Step 25513: {'lr': 0.00046950477539293864, 'samples': 4898496, 'steps': 25512, 'loss/train': 1.291247844696045}
+08/30/2021 17:45:17 - INFO - __main__ - Step 25514: {'lr': 0.0004695022353998315, 'samples': 4898688, 'steps': 25513, 'loss/train': 0.42855507135391235}
+08/30/2021 17:45:18 - INFO - __main__ - Step 25515: {'lr': 0.0004694996953078201, 'samples': 4898880, 'steps': 25514, 'loss/train': 1.4016495943069458}
+08/30/2021 17:45:18 - INFO - __main__ - Step 25516: {'lr': 0.0004694971551169055, 'samples': 4899072, 'steps': 25515, 'loss/train': 2.0857272148132324}
+08/30/2021 17:45:18 - INFO - __main__ - Step 25517: {'lr': 0.00046949461482708875, 'samples': 4899264, 'steps': 25516, 'loss/train': 1.2822951078414917}
+08/30/2021 17:45:20 - INFO - __main__ - Step 25518: {'lr': 0.0004694920744383713, 'samples': 4899456, 'steps': 25517, 'loss/train': 2.0646729469299316}
+08/30/2021 17:45:20 - INFO - __main__ - Step 25519: {'lr': 0.000469489533950754, 'samples': 4899648, 'steps': 25518, 'loss/train': 1.6781165599822998}
+08/30/2021 17:45:21 - INFO - __main__ - Step 25520: {'lr': 0.00046948699336423817, 'samples': 4899840, 'steps': 25519, 'loss/train': 2.136193037033081}
+08/30/2021 17:45:21 - INFO - __main__ - Step 25521: {'lr': 0.0004694844526788248, 'samples': 4900032, 'steps': 25520, 'loss/train': 1.3668781518936157}
+08/30/2021 17:45:21 - INFO - __main__ - Step 25522: {'lr': 0.0004694819118945152, 'samples': 4900224, 'steps': 25521, 'loss/train': 1.7951041460037231}
+08/30/2021 17:45:22 - INFO - __main__ - Step 25523: {'lr': 0.00046947937101131046, 'samples': 4900416, 'steps': 25522, 'loss/train': 1.076138973236084}
+08/30/2021 17:45:23 - INFO - __main__ - Step 25524: {'lr': 0.0004694768300292116, 'samples': 4900608, 'steps': 25523, 'loss/train': 0.799167811870575}
+08/30/2021 17:45:24 - INFO - __main__ - Step 25525: {'lr': 0.0004694742889482199, 'samples': 4900800, 'steps': 25524, 'loss/train': 1.3842781782150269}
+08/30/2021 17:45:24 - INFO - __main__ - Step 25526: {'lr': 0.0004694717477683365, 'samples': 4900992, 'steps': 25525, 'loss/train': 1.9871892929077148}
+08/30/2021 17:45:25 - INFO - __main__ - Step 25527: {'lr': 0.0004694692064895625, 'samples': 4901184, 'steps': 25526, 'loss/train': 1.5205962657928467}
+08/30/2021 17:45:25 - INFO - __main__ - Step 25528: {'lr': 0.0004694666651118991, 'samples': 4901376, 'steps': 25527, 'loss/train': 0.9289355278015137}
+08/30/2021 17:45:27 - INFO - __main__ - Step 25529: {'lr': 0.00046946412363534735, 'samples': 4901568, 'steps': 25528, 'loss/train': 1.7455404996871948}
+08/30/2021 17:45:28 - INFO - __main__ - Step 25530: {'lr': 0.0004694615820599085, 'samples': 4901760, 'steps': 25529, 'loss/train': 0.96571284532547}
+08/30/2021 17:45:28 - INFO - __main__ - Step 25531: {'lr': 0.00046945904038558364, 'samples': 4901952, 'steps': 25530, 'loss/train': 1.6810768842697144}
+08/30/2021 17:45:28 - INFO - __main__ - Step 25532: {'lr': 0.00046945649861237387, 'samples': 4902144, 'steps': 25531, 'loss/train': 2.0984668731689453}
+08/30/2021 17:45:29 - INFO - __main__ - Step 25533: {'lr': 0.00046945395674028047, 'samples': 4902336, 'steps': 25532, 'loss/train': 1.5089911222457886}
+08/30/2021 17:45:29 - INFO - __main__ - Step 25534: {'lr': 0.0004694514147693044, 'samples': 4902528, 'steps': 25533, 'loss/train': 1.3756768703460693}
+08/30/2021 17:45:31 - INFO - __main__ - Step 25535: {'lr': 0.000469448872699447, 'samples': 4902720, 'steps': 25534, 'loss/train': 0.13290277123451233}
+08/30/2021 17:45:31 - INFO - __main__ - Step 25536: {'lr': 0.0004694463305307093, 'samples': 4902912, 'steps': 25535, 'loss/train': 1.2443565130233765}
+08/30/2021 17:45:31 - INFO - __main__ - Step 25537: {'lr': 0.00046944378826309244, 'samples': 4903104, 'steps': 25536, 'loss/train': 1.7121107578277588}
+08/30/2021 17:45:32 - INFO - __main__ - Step 25538: {'lr': 0.00046944124589659765, 'samples': 4903296, 'steps': 25537, 'loss/train': 1.3854635953903198}
+08/30/2021 17:45:32 - INFO - __main__ - Step 25539: {'lr': 0.00046943870343122595, 'samples': 4903488, 'steps': 25538, 'loss/train': 1.3788626194000244}
+08/30/2021 17:45:34 - INFO - __main__ - Step 25540: {'lr': 0.0004694361608669786, 'samples': 4903680, 'steps': 25539, 'loss/train': 1.0962517261505127}
+08/30/2021 17:45:34 - INFO - __main__ - Step 25541: {'lr': 0.0004694336182038567, 'samples': 4903872, 'steps': 25540, 'loss/train': 1.5978034734725952}
+08/30/2021 17:45:34 - INFO - __main__ - Step 25542: {'lr': 0.00046943107544186144, 'samples': 4904064, 'steps': 25541, 'loss/train': 1.7243266105651855}
+08/30/2021 17:45:35 - INFO - __main__ - Step 25543: {'lr': 0.0004694285325809938, 'samples': 4904256, 'steps': 25542, 'loss/train': 1.7463313341140747}
+08/30/2021 17:45:35 - INFO - __main__ - Step 25544: {'lr': 0.00046942598962125515, 'samples': 4904448, 'steps': 25543, 'loss/train': 1.8773432970046997}
+08/30/2021 17:45:37 - INFO - __main__ - Step 25545: {'lr': 0.00046942344656264657, 'samples': 4904640, 'steps': 25544, 'loss/train': 1.6174808740615845}
+08/30/2021 17:45:38 - INFO - __main__ - Step 25546: {'lr': 0.0004694209034051691, 'samples': 4904832, 'steps': 25545, 'loss/train': 1.2789280414581299}
+08/30/2021 17:45:38 - INFO - __main__ - Step 25547: {'lr': 0.00046941836014882394, 'samples': 4905024, 'steps': 25546, 'loss/train': 0.8335281610488892}
+08/30/2021 17:45:38 - INFO - __main__ - Step 25548: {'lr': 0.00046941581679361234, 'samples': 4905216, 'steps': 25547, 'loss/train': 0.897831380367279}
+08/30/2021 17:45:39 - INFO - __main__ - Step 25549: {'lr': 0.00046941327333953526, 'samples': 4905408, 'steps': 25548, 'loss/train': 1.5635565519332886}
+08/30/2021 17:45:39 - INFO - __main__ - Step 25550: {'lr': 0.00046941072978659397, 'samples': 4905600, 'steps': 25549, 'loss/train': 1.523878574371338}
+08/30/2021 17:45:40 - INFO - __main__ - Step 25551: {'lr': 0.00046940818613478964, 'samples': 4905792, 'steps': 25550, 'loss/train': 0.07167031615972519}
+08/30/2021 17:45:41 - INFO - __main__ - Step 25552: {'lr': 0.0004694056423841233, 'samples': 4905984, 'steps': 25551, 'loss/train': 1.5276508331298828}
+08/30/2021 17:45:41 - INFO - __main__ - Step 25553: {'lr': 0.00046940309853459625, 'samples': 4906176, 'steps': 25552, 'loss/train': 1.7026442289352417}
+08/30/2021 17:45:42 - INFO - __main__ - Step 25554: {'lr': 0.00046940055458620945, 'samples': 4906368, 'steps': 25553, 'loss/train': 1.2607771158218384}
+08/30/2021 17:45:42 - INFO - __main__ - Step 25555: {'lr': 0.0004693980105389642, 'samples': 4906560, 'steps': 25554, 'loss/train': 1.650815725326538}
+08/30/2021 17:45:44 - INFO - __main__ - Step 25556: {'lr': 0.00046939546639286156, 'samples': 4906752, 'steps': 25555, 'loss/train': 1.2766176462173462}
+08/30/2021 17:45:44 - INFO - __main__ - Step 25557: {'lr': 0.00046939292214790275, 'samples': 4906944, 'steps': 25556, 'loss/train': 1.824107050895691}
+08/30/2021 17:45:45 - INFO - __main__ - Step 25558: {'lr': 0.0004693903778040889, 'samples': 4907136, 'steps': 25557, 'loss/train': 1.6804702281951904}
+08/30/2021 17:45:45 - INFO - __main__ - Step 25559: {'lr': 0.0004693878333614211, 'samples': 4907328, 'steps': 25558, 'loss/train': 0.14626309275627136}
+08/30/2021 17:45:45 - INFO - __main__ - Step 25560: {'lr': 0.0004693852888199005, 'samples': 4907520, 'steps': 25559, 'loss/train': 1.5664700269699097}
+08/30/2021 17:45:47 - INFO - __main__ - Step 25561: {'lr': 0.0004693827441795283, 'samples': 4907712, 'steps': 25560, 'loss/train': 1.2916374206542969}
+08/30/2021 17:45:47 - INFO - __main__ - Step 25562: {'lr': 0.00046938019944030556, 'samples': 4907904, 'steps': 25561, 'loss/train': 1.253320574760437}
+08/30/2021 17:45:48 - INFO - __main__ - Step 25563: {'lr': 0.00046937765460223357, 'samples': 4908096, 'steps': 25562, 'loss/train': 1.8996003866195679}
+08/30/2021 17:45:48 - INFO - __main__ - Step 25564: {'lr': 0.0004693751096653134, 'samples': 4908288, 'steps': 25563, 'loss/train': 1.5907924175262451}
+08/30/2021 17:45:48 - INFO - __main__ - Step 25565: {'lr': 0.00046937256462954615, 'samples': 4908480, 'steps': 25564, 'loss/train': 1.7696524858474731}
+08/30/2021 17:45:50 - INFO - __main__ - Step 25566: {'lr': 0.00046937001949493294, 'samples': 4908672, 'steps': 25565, 'loss/train': 1.5918571949005127}
+08/30/2021 17:45:50 - INFO - __main__ - Step 25567: {'lr': 0.0004693674742614751, 'samples': 4908864, 'steps': 25566, 'loss/train': 1.2720521688461304}
+08/30/2021 17:45:51 - INFO - __main__ - Step 25568: {'lr': 0.0004693649289291736, 'samples': 4909056, 'steps': 25567, 'loss/train': 1.2477308511734009}
+08/30/2021 17:45:51 - INFO - __main__ - Step 25569: {'lr': 0.0004693623834980297, 'samples': 4909248, 'steps': 25568, 'loss/train': 0.08667182177305222}
+08/30/2021 17:45:52 - INFO - __main__ - Step 25570: {'lr': 0.00046935983796804443, 'samples': 4909440, 'steps': 25569, 'loss/train': 1.7546091079711914}
+08/30/2021 17:45:52 - INFO - __main__ - Step 25571: {'lr': 0.000469357292339219, 'samples': 4909632, 'steps': 25570, 'loss/train': 2.3846867084503174}
+08/30/2021 17:45:54 - INFO - __main__ - Step 25572: {'lr': 0.00046935474661155465, 'samples': 4909824, 'steps': 25571, 'loss/train': 1.219957947731018}
+08/30/2021 17:45:54 - INFO - __main__ - Step 25573: {'lr': 0.00046935220078505235, 'samples': 4910016, 'steps': 25572, 'loss/train': 2.4779434204101562}
+08/30/2021 17:45:54 - INFO - __main__ - Step 25574: {'lr': 0.00046934965485971337, 'samples': 4910208, 'steps': 25573, 'loss/train': 1.1145262718200684}
+08/30/2021 17:45:55 - INFO - __main__ - Step 25575: {'lr': 0.00046934710883553884, 'samples': 4910400, 'steps': 25574, 'loss/train': 0.08766800910234451}
+08/30/2021 17:45:55 - INFO - __main__ - Step 25576: {'lr': 0.00046934456271252985, 'samples': 4910592, 'steps': 25575, 'loss/train': 1.6031591892242432}
+08/30/2021 17:45:57 - INFO - __main__ - Step 25577: {'lr': 0.0004693420164906876, 'samples': 4910784, 'steps': 25576, 'loss/train': 1.3525570631027222}
+08/30/2021 17:45:57 - INFO - __main__ - Step 25578: {'lr': 0.0004693394701700132, 'samples': 4910976, 'steps': 25577, 'loss/train': 1.410264015197754}
+08/30/2021 17:45:58 - INFO - __main__ - Step 25579: {'lr': 0.00046933692375050783, 'samples': 4911168, 'steps': 25578, 'loss/train': 1.3000317811965942}
+08/30/2021 17:45:58 - INFO - __main__ - Step 25580: {'lr': 0.00046933437723217265, 'samples': 4911360, 'steps': 25579, 'loss/train': 1.3320658206939697}
+08/30/2021 17:45:58 - INFO - __main__ - Step 25581: {'lr': 0.0004693318306150087, 'samples': 4911552, 'steps': 25580, 'loss/train': 0.5477054119110107}
+08/30/2021 17:46:00 - INFO - __main__ - Step 25582: {'lr': 0.0004693292838990173, 'samples': 4911744, 'steps': 25581, 'loss/train': 1.3790009021759033}
+08/30/2021 17:46:01 - INFO - __main__ - Step 25583: {'lr': 0.0004693267370841995, 'samples': 4911936, 'steps': 25582, 'loss/train': 1.1315293312072754}
+08/30/2021 17:46:01 - INFO - __main__ - Step 25584: {'lr': 0.00046932419017055646, 'samples': 4912128, 'steps': 25583, 'loss/train': 1.6476805210113525}
+08/30/2021 17:46:01 - INFO - __main__ - Step 25585: {'lr': 0.0004693216431580893, 'samples': 4912320, 'steps': 25584, 'loss/train': 1.3029710054397583}
+08/30/2021 17:46:02 - INFO - __main__ - Step 25586: {'lr': 0.00046931909604679925, 'samples': 4912512, 'steps': 25585, 'loss/train': 1.1572575569152832}
+08/30/2021 17:46:03 - INFO - __main__ - Step 25587: {'lr': 0.0004693165488366873, 'samples': 4912704, 'steps': 25586, 'loss/train': 1.7142897844314575}
+08/30/2021 17:46:04 - INFO - __main__ - Step 25588: {'lr': 0.00046931400152775473, 'samples': 4912896, 'steps': 25587, 'loss/train': 1.4758199453353882}
+08/30/2021 17:46:04 - INFO - __main__ - Step 25589: {'lr': 0.00046931145412000265, 'samples': 4913088, 'steps': 25588, 'loss/train': 1.551531434059143}
+08/30/2021 17:46:04 - INFO - __main__ - Step 25590: {'lr': 0.00046930890661343226, 'samples': 4913280, 'steps': 25589, 'loss/train': 1.546036720275879}
+08/30/2021 17:46:05 - INFO - __main__ - Step 25591: {'lr': 0.00046930635900804466, 'samples': 4913472, 'steps': 25590, 'loss/train': 1.1229722499847412}
+08/30/2021 17:46:06 - INFO - __main__ - Step 25592: {'lr': 0.0004693038113038409, 'samples': 4913664, 'steps': 25591, 'loss/train': 1.2015138864517212}
+08/30/2021 17:46:07 - INFO - __main__ - Step 25593: {'lr': 0.0004693012635008224, 'samples': 4913856, 'steps': 25592, 'loss/train': 1.4687280654907227}
+08/30/2021 17:46:07 - INFO - __main__ - Step 25594: {'lr': 0.00046929871559898994, 'samples': 4914048, 'steps': 25593, 'loss/train': 1.2752095460891724}
+08/30/2021 17:46:07 - INFO - __main__ - Step 25595: {'lr': 0.00046929616759834505, 'samples': 4914240, 'steps': 25594, 'loss/train': 1.6353528499603271}
+08/30/2021 17:46:08 - INFO - __main__ - Step 25596: {'lr': 0.00046929361949888857, 'samples': 4914432, 'steps': 25595, 'loss/train': 1.7392250299453735}
+08/30/2021 17:46:09 - INFO - __main__ - Step 25597: {'lr': 0.00046929107130062176, 'samples': 4914624, 'steps': 25596, 'loss/train': 1.8298649787902832}
+08/30/2021 17:46:10 - INFO - __main__ - Step 25598: {'lr': 0.00046928852300354585, 'samples': 4914816, 'steps': 25597, 'loss/train': 1.7110896110534668}
+08/30/2021 17:46:10 - INFO - __main__ - Step 25599: {'lr': 0.0004692859746076619, 'samples': 4915008, 'steps': 25598, 'loss/train': 1.1671812534332275}
+08/30/2021 17:46:11 - INFO - __main__ - Step 25600: {'lr': 0.00046928342611297105, 'samples': 4915200, 'steps': 25599, 'loss/train': 1.6852355003356934}
+08/30/2021 17:46:11 - INFO - __main__ - Step 25601: {'lr': 0.00046928087751947444, 'samples': 4915392, 'steps': 25600, 'loss/train': 0.975641131401062}
+08/30/2021 17:46:12 - INFO - __main__ - Step 25602: {'lr': 0.00046927832882717323, 'samples': 4915584, 'steps': 25601, 'loss/train': 1.9378066062927246}
+08/30/2021 17:46:13 - INFO - __main__ - Step 25603: {'lr': 0.0004692757800360687, 'samples': 4915776, 'steps': 25602, 'loss/train': 1.595958948135376}
+08/30/2021 17:46:13 - INFO - __main__ - Step 25604: {'lr': 0.0004692732311461618, 'samples': 4915968, 'steps': 25603, 'loss/train': 1.5733797550201416}
+08/30/2021 17:46:13 - INFO - __main__ - Step 25605: {'lr': 0.0004692706821574538, 'samples': 4916160, 'steps': 25604, 'loss/train': 1.6840075254440308}
+08/30/2021 17:46:14 - INFO - __main__ - Step 25606: {'lr': 0.00046926813306994586, 'samples': 4916352, 'steps': 25605, 'loss/train': 1.3816670179367065}
+08/30/2021 17:46:15 - INFO - __main__ - Step 25607: {'lr': 0.00046926558388363904, 'samples': 4916544, 'steps': 25606, 'loss/train': 1.2792718410491943}
+08/30/2021 17:46:16 - INFO - __main__ - Step 25608: {'lr': 0.00046926303459853447, 'samples': 4916736, 'steps': 25607, 'loss/train': 1.5633635520935059}
+08/30/2021 17:46:16 - INFO - __main__ - Step 25609: {'lr': 0.00046926048521463344, 'samples': 4916928, 'steps': 25608, 'loss/train': 1.4930192232131958}
+08/30/2021 17:46:16 - INFO - __main__ - Step 25610: {'lr': 0.000469257935731937, 'samples': 4917120, 'steps': 25609, 'loss/train': 1.3920789957046509}
+08/30/2021 17:46:17 - INFO - __main__ - Step 25611: {'lr': 0.0004692553861504463, 'samples': 4917312, 'steps': 25610, 'loss/train': 1.2099542617797852}
+08/30/2021 17:46:17 - INFO - __main__ - Step 25612: {'lr': 0.00046925283647016253, 'samples': 4917504, 'steps': 25611, 'loss/train': 0.5829740762710571}
+08/30/2021 17:46:19 - INFO - __main__ - Step 25613: {'lr': 0.0004692502866910868, 'samples': 4917696, 'steps': 25612, 'loss/train': 1.332496166229248}
+08/30/2021 17:46:20 - INFO - __main__ - Step 25614: {'lr': 0.0004692477368132203, 'samples': 4917888, 'steps': 25613, 'loss/train': 2.0153746604919434}
+08/30/2021 17:46:20 - INFO - __main__ - Step 25615: {'lr': 0.0004692451868365641, 'samples': 4918080, 'steps': 25614, 'loss/train': 1.5743674039840698}
+08/30/2021 17:46:21 - INFO - __main__ - Step 25616: {'lr': 0.00046924263676111945, 'samples': 4918272, 'steps': 25615, 'loss/train': 1.4915242195129395}
+08/30/2021 17:46:21 - INFO - __main__ - Step 25617: {'lr': 0.00046924008658688745, 'samples': 4918464, 'steps': 25616, 'loss/train': 1.3996468782424927}
+08/30/2021 17:46:22 - INFO - __main__ - Step 25618: {'lr': 0.00046923753631386924, 'samples': 4918656, 'steps': 25617, 'loss/train': 2.0151290893554688}
+08/30/2021 17:46:23 - INFO - __main__ - Step 25619: {'lr': 0.0004692349859420659, 'samples': 4918848, 'steps': 25618, 'loss/train': 1.116296648979187}
+08/30/2021 17:46:23 - INFO - __main__ - Step 25620: {'lr': 0.00046923243547147874, 'samples': 4919040, 'steps': 25619, 'loss/train': 1.6149743795394897}
+08/30/2021 17:46:24 - INFO - __main__ - Step 25621: {'lr': 0.0004692298849021088, 'samples': 4919232, 'steps': 25620, 'loss/train': 1.7254117727279663}
+08/30/2021 17:46:24 - INFO - __main__ - Step 25622: {'lr': 0.00046922733423395736, 'samples': 4919424, 'steps': 25621, 'loss/train': 0.910541296005249}
+08/30/2021 17:46:25 - INFO - __main__ - Step 25623: {'lr': 0.0004692247834670253, 'samples': 4919616, 'steps': 25622, 'loss/train': 1.3471633195877075}
+08/30/2021 17:46:26 - INFO - __main__ - Step 25624: {'lr': 0.000469222232601314, 'samples': 4919808, 'steps': 25623, 'loss/train': 1.6275146007537842}
+08/30/2021 17:46:26 - INFO - __main__ - Step 25625: {'lr': 0.0004692196816368246, 'samples': 4920000, 'steps': 25624, 'loss/train': 0.9021770358085632}
+08/30/2021 17:46:27 - INFO - __main__ - Step 25626: {'lr': 0.00046921713057355817, 'samples': 4920192, 'steps': 25625, 'loss/train': 1.6000720262527466}
+08/30/2021 17:46:27 - INFO - __main__ - Step 25627: {'lr': 0.0004692145794115159, 'samples': 4920384, 'steps': 25626, 'loss/train': 2.384751081466675}
+08/30/2021 17:46:29 - INFO - __main__ - Step 25628: {'lr': 0.00046921202815069883, 'samples': 4920576, 'steps': 25627, 'loss/train': 0.963126003742218}
+08/30/2021 17:46:29 - INFO - __main__ - Step 25629: {'lr': 0.00046920947679110833, 'samples': 4920768, 'steps': 25628, 'loss/train': 1.5333893299102783}
+08/30/2021 17:46:30 - INFO - __main__ - Step 25630: {'lr': 0.00046920692533274533, 'samples': 4920960, 'steps': 25629, 'loss/train': 5.969575881958008}
+08/30/2021 17:46:30 - INFO - __main__ - Step 25631: {'lr': 0.0004692043737756111, 'samples': 4921152, 'steps': 25630, 'loss/train': 5.858996391296387}
+08/30/2021 17:46:30 - INFO - __main__ - Step 25632: {'lr': 0.00046920182211970677, 'samples': 4921344, 'steps': 25631, 'loss/train': 1.7322770357131958}
+08/30/2021 17:46:31 - INFO - __main__ - Step 25633: {'lr': 0.00046919927036503353, 'samples': 4921536, 'steps': 25632, 'loss/train': 1.5119572877883911}
+08/30/2021 17:46:31 - INFO - __main__ - Step 25634: {'lr': 0.0004691967185115924, 'samples': 4921728, 'steps': 25633, 'loss/train': 1.7821234464645386}
+08/30/2021 17:46:33 - INFO - __main__ - Step 25635: {'lr': 0.00046919416655938465, 'samples': 4921920, 'steps': 25634, 'loss/train': 1.7719392776489258}
+08/30/2021 17:46:33 - INFO - __main__ - Step 25636: {'lr': 0.0004691916145084113, 'samples': 4922112, 'steps': 25635, 'loss/train': 1.672731876373291}
+08/30/2021 17:46:34 - INFO - __main__ - Step 25637: {'lr': 0.0004691890623586737, 'samples': 4922304, 'steps': 25636, 'loss/train': 1.2098770141601562}
+08/30/2021 17:46:34 - INFO - __main__ - Step 25638: {'lr': 0.00046918651011017287, 'samples': 4922496, 'steps': 25637, 'loss/train': 1.5956040620803833}
+08/30/2021 17:46:34 - INFO - __main__ - Step 25639: {'lr': 0.00046918395776290997, 'samples': 4922688, 'steps': 25638, 'loss/train': 1.457015037536621}
+08/30/2021 17:46:36 - INFO - __main__ - Step 25640: {'lr': 0.0004691814053168861, 'samples': 4922880, 'steps': 25639, 'loss/train': 1.3072255849838257}
+08/30/2021 17:46:36 - INFO - __main__ - Step 25641: {'lr': 0.0004691788527721026, 'samples': 4923072, 'steps': 25640, 'loss/train': 1.556615948677063}
+08/30/2021 17:46:37 - INFO - __main__ - Step 25642: {'lr': 0.0004691763001285604, 'samples': 4923264, 'steps': 25641, 'loss/train': 1.2920417785644531}
+08/30/2021 17:46:37 - INFO - __main__ - Step 25643: {'lr': 0.0004691737473862607, 'samples': 4923456, 'steps': 25642, 'loss/train': 1.911281704902649}
+08/30/2021 17:46:37 - INFO - __main__ - Step 25644: {'lr': 0.00046917119454520487, 'samples': 4923648, 'steps': 25643, 'loss/train': 1.6087640523910522}
+08/30/2021 17:46:39 - INFO - __main__ - Step 25645: {'lr': 0.00046916864160539376, 'samples': 4923840, 'steps': 25644, 'loss/train': 1.8666285276412964}
+08/30/2021 17:46:39 - INFO - __main__ - Step 25646: {'lr': 0.00046916608856682865, 'samples': 4924032, 'steps': 25645, 'loss/train': 1.5911983251571655}
+08/30/2021 17:46:40 - INFO - __main__ - Step 25647: {'lr': 0.0004691635354295106, 'samples': 4924224, 'steps': 25646, 'loss/train': 1.169861912727356}
+08/30/2021 17:46:40 - INFO - __main__ - Step 25648: {'lr': 0.00046916098219344093, 'samples': 4924416, 'steps': 25647, 'loss/train': 1.3354626893997192}
+08/30/2021 17:46:40 - INFO - __main__ - Step 25649: {'lr': 0.0004691584288586207, 'samples': 4924608, 'steps': 25648, 'loss/train': 1.26406729221344}
+08/30/2021 17:46:42 - INFO - __main__ - Step 25650: {'lr': 0.0004691558754250511, 'samples': 4924800, 'steps': 25649, 'loss/train': 1.3049681186676025}
+08/30/2021 17:46:42 - INFO - __main__ - Step 25651: {'lr': 0.0004691533218927332, 'samples': 4924992, 'steps': 25650, 'loss/train': 1.289215326309204}
+08/30/2021 17:46:43 - INFO - __main__ - Step 25652: {'lr': 0.00046915076826166814, 'samples': 4925184, 'steps': 25651, 'loss/train': 1.2583330869674683}
+08/30/2021 17:46:43 - INFO - __main__ - Step 25653: {'lr': 0.0004691482145318572, 'samples': 4925376, 'steps': 25652, 'loss/train': 1.0070675611495972}
+08/30/2021 17:46:43 - INFO - __main__ - Step 25654: {'lr': 0.00046914566070330144, 'samples': 4925568, 'steps': 25653, 'loss/train': 1.2272132635116577}
+08/30/2021 17:46:44 - INFO - __main__ - Step 25655: {'lr': 0.00046914310677600204, 'samples': 4925760, 'steps': 25654, 'loss/train': 1.4363913536071777}
+08/30/2021 17:46:45 - INFO - __main__ - Step 25656: {'lr': 0.00046914055274996017, 'samples': 4925952, 'steps': 25655, 'loss/train': 1.8204822540283203}
+08/30/2021 17:46:46 - INFO - __main__ - Step 25657: {'lr': 0.00046913799862517686, 'samples': 4926144, 'steps': 25656, 'loss/train': 1.3860546350479126}
+08/30/2021 17:46:46 - INFO - __main__ - Step 25658: {'lr': 0.0004691354444016534, 'samples': 4926336, 'steps': 25657, 'loss/train': 1.6931554079055786}
+08/30/2021 17:46:46 - INFO - __main__ - Step 25659: {'lr': 0.00046913289007939087, 'samples': 4926528, 'steps': 25658, 'loss/train': 1.4370806217193604}
+08/30/2021 17:46:47 - INFO - __main__ - Step 25660: {'lr': 0.00046913033565839046, 'samples': 4926720, 'steps': 25659, 'loss/train': 1.4942413568496704}
+08/30/2021 17:46:49 - INFO - __main__ - Step 25661: {'lr': 0.0004691277811386533, 'samples': 4926912, 'steps': 25660, 'loss/train': 1.5427632331848145}
+08/30/2021 17:46:49 - INFO - __main__ - Step 25662: {'lr': 0.0004691252265201805, 'samples': 4927104, 'steps': 25661, 'loss/train': 1.3137925863265991}
+08/30/2021 17:46:50 - INFO - __main__ - Step 25663: {'lr': 0.00046912267180297337, 'samples': 4927296, 'steps': 25662, 'loss/train': 0.063136987388134}
+08/30/2021 17:46:50 - INFO - __main__ - Step 25664: {'lr': 0.0004691201169870328, 'samples': 4927488, 'steps': 25663, 'loss/train': 2.225656509399414}
+08/30/2021 17:46:50 - INFO - __main__ - Step 25665: {'lr': 0.00046911756207236024, 'samples': 4927680, 'steps': 25664, 'loss/train': 1.6347001791000366}
+08/30/2021 17:46:51 - INFO - __main__ - Step 25666: {'lr': 0.0004691150070589566, 'samples': 4927872, 'steps': 25665, 'loss/train': 1.7294188737869263}
+08/30/2021 17:46:53 - INFO - __main__ - Step 25667: {'lr': 0.00046911245194682306, 'samples': 4928064, 'steps': 25666, 'loss/train': 1.6906583309173584}
+08/30/2021 17:46:53 - INFO - __main__ - Step 25668: {'lr': 0.00046910989673596093, 'samples': 4928256, 'steps': 25667, 'loss/train': 1.4899779558181763}
+08/30/2021 17:46:53 - INFO - __main__ - Step 25669: {'lr': 0.00046910734142637124, 'samples': 4928448, 'steps': 25668, 'loss/train': 1.5659645795822144}
+08/30/2021 17:46:54 - INFO - __main__ - Step 25670: {'lr': 0.00046910478601805514, 'samples': 4928640, 'steps': 25669, 'loss/train': 1.0884144306182861}
+08/30/2021 17:46:54 - INFO - __main__ - Step 25671: {'lr': 0.0004691022305110138, 'samples': 4928832, 'steps': 25670, 'loss/train': 1.4707077741622925}
+08/30/2021 17:46:56 - INFO - __main__ - Step 25672: {'lr': 0.0004690996749052484, 'samples': 4929024, 'steps': 25671, 'loss/train': 1.7564407587051392}
+08/30/2021 17:46:56 - INFO - __main__ - Step 25673: {'lr': 0.00046909711920076, 'samples': 4929216, 'steps': 25672, 'loss/train': 2.032792091369629}
+08/30/2021 17:46:56 - INFO - __main__ - Step 25674: {'lr': 0.0004690945633975499, 'samples': 4929408, 'steps': 25673, 'loss/train': 1.2514983415603638}
+08/30/2021 17:46:57 - INFO - __main__ - Step 25675: {'lr': 0.00046909200749561914, 'samples': 4929600, 'steps': 25674, 'loss/train': 1.769295334815979}
+08/30/2021 17:46:57 - INFO - __main__ - Step 25676: {'lr': 0.00046908945149496897, 'samples': 4929792, 'steps': 25675, 'loss/train': 1.2579846382141113}
+08/30/2021 17:46:59 - INFO - __main__ - Step 25677: {'lr': 0.00046908689539560034, 'samples': 4929984, 'steps': 25676, 'loss/train': 1.221014380455017}
+08/30/2021 17:46:59 - INFO - __main__ - Step 25678: {'lr': 0.0004690843391975146, 'samples': 4930176, 'steps': 25677, 'loss/train': 1.0823017358779907}
+08/30/2021 17:47:00 - INFO - __main__ - Step 25679: {'lr': 0.0004690817829007129, 'samples': 4930368, 'steps': 25678, 'loss/train': 1.5751724243164062}
+08/30/2021 17:47:00 - INFO - __main__ - Step 25680: {'lr': 0.00046907922650519623, 'samples': 4930560, 'steps': 25679, 'loss/train': 0.8998758792877197}
+08/30/2021 17:47:00 - INFO - __main__ - Step 25681: {'lr': 0.0004690766700109659, 'samples': 4930752, 'steps': 25680, 'loss/train': 1.2231260538101196}
+08/30/2021 17:47:02 - INFO - __main__ - Step 25682: {'lr': 0.00046907411341802295, 'samples': 4930944, 'steps': 25681, 'loss/train': 1.7166142463684082}
+08/30/2021 17:47:02 - INFO - __main__ - Step 25683: {'lr': 0.0004690715567263687, 'samples': 4931136, 'steps': 25682, 'loss/train': 1.4265334606170654}
+08/30/2021 17:47:03 - INFO - __main__ - Step 25684: {'lr': 0.00046906899993600406, 'samples': 4931328, 'steps': 25683, 'loss/train': 0.09770724177360535}
+08/30/2021 17:47:03 - INFO - __main__ - Step 25685: {'lr': 0.00046906644304693033, 'samples': 4931520, 'steps': 25684, 'loss/train': 1.1788661479949951}
+08/30/2021 17:47:03 - INFO - __main__ - Step 25686: {'lr': 0.0004690638860591487, 'samples': 4931712, 'steps': 25685, 'loss/train': 1.6538797616958618}
+08/30/2021 17:47:04 - INFO - __main__ - Step 25687: {'lr': 0.00046906132897266026, 'samples': 4931904, 'steps': 25686, 'loss/train': 1.9894604682922363}
+08/30/2021 17:47:05 - INFO - __main__ - Step 25688: {'lr': 0.00046905877178746614, 'samples': 4932096, 'steps': 25687, 'loss/train': 1.5378966331481934}
+08/30/2021 17:47:06 - INFO - __main__ - Step 25689: {'lr': 0.0004690562145035675, 'samples': 4932288, 'steps': 25688, 'loss/train': 1.540313720703125}
+08/30/2021 17:47:06 - INFO - __main__ - Step 25690: {'lr': 0.00046905365712096553, 'samples': 4932480, 'steps': 25689, 'loss/train': 1.1325825452804565}
+08/30/2021 17:47:06 - INFO - __main__ - Step 25691: {'lr': 0.0004690510996396614, 'samples': 4932672, 'steps': 25690, 'loss/train': 1.6712768077850342}
+08/30/2021 17:47:07 - INFO - __main__ - Step 25692: {'lr': 0.0004690485420596561, 'samples': 4932864, 'steps': 25691, 'loss/train': 1.5641427040100098}
+08/30/2021 17:47:08 - INFO - __main__ - Step 25693: {'lr': 0.000469045984380951, 'samples': 4933056, 'steps': 25692, 'loss/train': 1.4656329154968262}
+08/30/2021 17:47:09 - INFO - __main__ - Step 25694: {'lr': 0.0004690434266035471, 'samples': 4933248, 'steps': 25693, 'loss/train': 1.7872800827026367}
+08/30/2021 17:47:09 - INFO - __main__ - Step 25695: {'lr': 0.00046904086872744577, 'samples': 4933440, 'steps': 25694, 'loss/train': 1.1971526145935059}
+08/30/2021 17:47:10 - INFO - __main__ - Step 25696: {'lr': 0.0004690383107526479, 'samples': 4933632, 'steps': 25695, 'loss/train': 1.3781235218048096}
+08/30/2021 17:47:10 - INFO - __main__ - Step 25697: {'lr': 0.0004690357526791547, 'samples': 4933824, 'steps': 25696, 'loss/train': 0.2671090066432953}
+08/30/2021 17:47:11 - INFO - __main__ - Step 25698: {'lr': 0.00046903319450696744, 'samples': 4934016, 'steps': 25697, 'loss/train': 1.2729966640472412}
+08/30/2021 17:47:12 - INFO - __main__ - Step 25699: {'lr': 0.00046903063623608714, 'samples': 4934208, 'steps': 25698, 'loss/train': 1.397875189781189}
+08/30/2021 17:47:12 - INFO - __main__ - Step 25700: {'lr': 0.00046902807786651507, 'samples': 4934400, 'steps': 25699, 'loss/train': 1.6402528285980225}
+08/30/2021 17:47:13 - INFO - __main__ - Step 25701: {'lr': 0.00046902551939825236, 'samples': 4934592, 'steps': 25700, 'loss/train': 1.5903586149215698}
+08/30/2021 17:47:13 - INFO - __main__ - Step 25702: {'lr': 0.00046902296083130003, 'samples': 4934784, 'steps': 25701, 'loss/train': 1.797283411026001}
+08/30/2021 17:47:14 - INFO - __main__ - Step 25703: {'lr': 0.00046902040216565945, 'samples': 4934976, 'steps': 25702, 'loss/train': 1.37621009349823}
+08/30/2021 17:47:15 - INFO - __main__ - Step 25704: {'lr': 0.0004690178434013316, 'samples': 4935168, 'steps': 25703, 'loss/train': 1.568002700805664}
+08/30/2021 17:47:15 - INFO - __main__ - Step 25705: {'lr': 0.00046901528453831764, 'samples': 4935360, 'steps': 25704, 'loss/train': 2.126760482788086}
+08/30/2021 17:47:16 - INFO - __main__ - Step 25706: {'lr': 0.0004690127255766188, 'samples': 4935552, 'steps': 25705, 'loss/train': 1.5658352375030518}
+08/30/2021 17:47:16 - INFO - __main__ - Step 25707: {'lr': 0.0004690101665162362, 'samples': 4935744, 'steps': 25706, 'loss/train': 1.1048375368118286}
+08/30/2021 17:47:17 - INFO - __main__ - Step 25708: {'lr': 0.00046900760735717103, 'samples': 4935936, 'steps': 25707, 'loss/train': 1.774127721786499}
+08/30/2021 17:47:18 - INFO - __main__ - Step 25709: {'lr': 0.00046900504809942433, 'samples': 4936128, 'steps': 25708, 'loss/train': 1.4984357357025146}
+08/30/2021 17:47:18 - INFO - __main__ - Step 25710: {'lr': 0.00046900248874299746, 'samples': 4936320, 'steps': 25709, 'loss/train': 1.3653550148010254}
+08/30/2021 17:47:18 - INFO - __main__ - Step 25711: {'lr': 0.0004689999292878914, 'samples': 4936512, 'steps': 25710, 'loss/train': 1.5078903436660767}
+08/30/2021 17:47:19 - INFO - __main__ - Step 25712: {'lr': 0.00046899736973410734, 'samples': 4936704, 'steps': 25711, 'loss/train': 3.89837384223938}
+08/30/2021 17:47:19 - INFO - __main__ - Step 25713: {'lr': 0.0004689948100816465, 'samples': 4936896, 'steps': 25712, 'loss/train': 1.0883709192276}
+08/30/2021 17:47:21 - INFO - __main__ - Step 25714: {'lr': 0.00046899225033050985, 'samples': 4937088, 'steps': 25713, 'loss/train': 1.235689401626587}
+08/30/2021 17:47:21 - INFO - __main__ - Step 25715: {'lr': 0.0004689896904806987, 'samples': 4937280, 'steps': 25714, 'loss/train': 0.9609364867210388}
+08/30/2021 17:47:22 - INFO - __main__ - Step 25716: {'lr': 0.0004689871305322143, 'samples': 4937472, 'steps': 25715, 'loss/train': 0.1189139187335968}
+08/30/2021 17:47:22 - INFO - __main__ - Step 25717: {'lr': 0.0004689845704850576, 'samples': 4937664, 'steps': 25716, 'loss/train': 1.5079913139343262}
+08/30/2021 17:47:22 - INFO - __main__ - Step 25718: {'lr': 0.0004689820103392298, 'samples': 4937856, 'steps': 25717, 'loss/train': 0.09478290379047394}
+08/30/2021 17:47:24 - INFO - __main__ - Step 25719: {'lr': 0.0004689794500947321, 'samples': 4938048, 'steps': 25718, 'loss/train': 1.803954839706421}
+08/30/2021 17:47:25 - INFO - __main__ - Step 25720: {'lr': 0.0004689768897515657, 'samples': 4938240, 'steps': 25719, 'loss/train': 1.8638983964920044}
+08/30/2021 17:47:25 - INFO - __main__ - Step 25721: {'lr': 0.0004689743293097316, 'samples': 4938432, 'steps': 25720, 'loss/train': 0.07366359978914261}
+08/30/2021 17:47:26 - INFO - __main__ - Step 25722: {'lr': 0.0004689717687692311, 'samples': 4938624, 'steps': 25721, 'loss/train': 0.05595998093485832}
+08/30/2021 17:47:26 - INFO - __main__ - Step 25723: {'lr': 0.0004689692081300653, 'samples': 4938816, 'steps': 25722, 'loss/train': 1.9962135553359985}
+08/30/2021 17:47:28 - INFO - __main__ - Step 25724: {'lr': 0.0004689666473922354, 'samples': 4939008, 'steps': 25723, 'loss/train': 1.1417449712753296}
+08/30/2021 17:47:28 - INFO - __main__ - Step 25725: {'lr': 0.0004689640865557424, 'samples': 4939200, 'steps': 25724, 'loss/train': 2.1349759101867676}
+08/30/2021 17:47:28 - INFO - __main__ - Step 25726: {'lr': 0.0004689615256205876, 'samples': 4939392, 'steps': 25725, 'loss/train': 1.6161985397338867}
+08/30/2021 17:47:29 - INFO - __main__ - Step 25727: {'lr': 0.0004689589645867721, 'samples': 4939584, 'steps': 25726, 'loss/train': 1.3147382736206055}
+08/30/2021 17:47:29 - INFO - __main__ - Step 25728: {'lr': 0.0004689564034542971, 'samples': 4939776, 'steps': 25727, 'loss/train': 1.0522000789642334}
+08/30/2021 17:47:31 - INFO - __main__ - Step 25729: {'lr': 0.00046895384222316375, 'samples': 4939968, 'steps': 25728, 'loss/train': 0.741268515586853}
+08/30/2021 17:47:31 - INFO - __main__ - Step 25730: {'lr': 0.0004689512808933731, 'samples': 4940160, 'steps': 25729, 'loss/train': 1.3964345455169678}
+08/30/2021 17:47:31 - INFO - __main__ - Step 25731: {'lr': 0.0004689487194649265, 'samples': 4940352, 'steps': 25730, 'loss/train': 1.5941787958145142}
+08/30/2021 17:47:32 - INFO - __main__ - Step 25732: {'lr': 0.0004689461579378249, 'samples': 4940544, 'steps': 25731, 'loss/train': 0.07148110121488571}
+08/30/2021 17:47:32 - INFO - __main__ - Step 25733: {'lr': 0.0004689435963120696, 'samples': 4940736, 'steps': 25732, 'loss/train': 1.2390637397766113}
+08/30/2021 17:47:34 - INFO - __main__ - Step 25734: {'lr': 0.00046894103458766163, 'samples': 4940928, 'steps': 25733, 'loss/train': 1.6882007122039795}
+08/30/2021 17:47:34 - INFO - __main__ - Step 25735: {'lr': 0.0004689384727646022, 'samples': 4941120, 'steps': 25734, 'loss/train': 1.6453152894973755}
+08/30/2021 17:47:34 - INFO - __main__ - Step 25736: {'lr': 0.00046893591084289256, 'samples': 4941312, 'steps': 25735, 'loss/train': 1.415347933769226}
+08/30/2021 17:47:35 - INFO - __main__ - Step 25737: {'lr': 0.0004689333488225337, 'samples': 4941504, 'steps': 25736, 'loss/train': 2.184805393218994}
+08/30/2021 17:47:35 - INFO - __main__ - Step 25738: {'lr': 0.00046893078670352686, 'samples': 4941696, 'steps': 25737, 'loss/train': 1.5168434381484985}
+08/30/2021 17:47:37 - INFO - __main__ - Step 25739: {'lr': 0.0004689282244858732, 'samples': 4941888, 'steps': 25738, 'loss/train': 1.8757611513137817}
+08/30/2021 17:47:37 - INFO - __main__ - Step 25740: {'lr': 0.00046892566216957387, 'samples': 4942080, 'steps': 25739, 'loss/train': 0.890189528465271}
+08/30/2021 17:47:37 - INFO - __main__ - Step 25741: {'lr': 0.00046892309975463, 'samples': 4942272, 'steps': 25740, 'loss/train': 0.6732057332992554}
+08/30/2021 17:47:38 - INFO - __main__ - Step 25742: {'lr': 0.0004689205372410427, 'samples': 4942464, 'steps': 25741, 'loss/train': 1.7113462686538696}
+08/30/2021 17:47:38 - INFO - __main__ - Step 25743: {'lr': 0.00046891797462881327, 'samples': 4942656, 'steps': 25742, 'loss/train': 1.5250897407531738}
+08/30/2021 17:47:40 - INFO - __main__ - Step 25744: {'lr': 0.0004689154119179427, 'samples': 4942848, 'steps': 25743, 'loss/train': 0.9668641090393066}
+08/30/2021 17:47:40 - INFO - __main__ - Step 25745: {'lr': 0.00046891284910843237, 'samples': 4943040, 'steps': 25744, 'loss/train': 1.6589901447296143}
+08/30/2021 17:47:40 - INFO - __main__ - Step 25746: {'lr': 0.0004689102862002832, 'samples': 4943232, 'steps': 25745, 'loss/train': 1.1028515100479126}
+08/30/2021 17:47:41 - INFO - __main__ - Step 25747: {'lr': 0.00046890772319349637, 'samples': 4943424, 'steps': 25746, 'loss/train': 0.047654375433921814}
+08/30/2021 17:47:41 - INFO - __main__ - Step 25748: {'lr': 0.00046890516008807315, 'samples': 4943616, 'steps': 25747, 'loss/train': 1.8506273031234741}
+08/30/2021 17:47:43 - INFO - __main__ - Step 25749: {'lr': 0.0004689025968840147, 'samples': 4943808, 'steps': 25748, 'loss/train': 1.621748447418213}
+08/30/2021 17:47:43 - INFO - __main__ - Step 25750: {'lr': 0.00046890003358132204, 'samples': 4944000, 'steps': 25749, 'loss/train': 0.8986481428146362}
+08/30/2021 17:47:43 - INFO - __main__ - Step 25751: {'lr': 0.0004688974701799964, 'samples': 4944192, 'steps': 25750, 'loss/train': 1.985831379890442}
+08/30/2021 17:47:44 - INFO - __main__ - Step 25752: {'lr': 0.00046889490668003896, 'samples': 4944384, 'steps': 25751, 'loss/train': 1.158137321472168}
+08/30/2021 17:47:44 - INFO - __main__ - Step 25753: {'lr': 0.0004688923430814509, 'samples': 4944576, 'steps': 25752, 'loss/train': 2.002857208251953}
+08/30/2021 17:47:44 - INFO - __main__ - Step 25754: {'lr': 0.00046888977938423326, 'samples': 4944768, 'steps': 25753, 'loss/train': 1.1062910556793213}
+08/30/2021 17:47:46 - INFO - __main__ - Step 25755: {'lr': 0.00046888721558838734, 'samples': 4944960, 'steps': 25754, 'loss/train': 1.763000249862671}
+08/30/2021 17:47:46 - INFO - __main__ - Step 25756: {'lr': 0.00046888465169391414, 'samples': 4945152, 'steps': 25755, 'loss/train': 1.028965711593628}
+08/30/2021 17:47:47 - INFO - __main__ - Step 25757: {'lr': 0.00046888208770081493, 'samples': 4945344, 'steps': 25756, 'loss/train': 1.6193593740463257}
+08/30/2021 17:47:47 - INFO - __main__ - Step 25758: {'lr': 0.0004688795236090908, 'samples': 4945536, 'steps': 25757, 'loss/train': 1.2246124744415283}
+08/30/2021 17:47:47 - INFO - __main__ - Step 25759: {'lr': 0.000468876959418743, 'samples': 4945728, 'steps': 25758, 'loss/train': 1.90020751953125}
+08/30/2021 17:47:49 - INFO - __main__ - Step 25760: {'lr': 0.0004688743951297726, 'samples': 4945920, 'steps': 25759, 'loss/train': 1.3285982608795166}
+08/30/2021 17:47:49 - INFO - __main__ - Step 25761: {'lr': 0.0004688718307421807, 'samples': 4946112, 'steps': 25760, 'loss/train': 0.6641785502433777}
+08/30/2021 17:47:50 - INFO - __main__ - Step 25762: {'lr': 0.0004688692662559686, 'samples': 4946304, 'steps': 25761, 'loss/train': 1.5299488306045532}
+08/30/2021 17:47:50 - INFO - __main__ - Step 25763: {'lr': 0.00046886670167113734, 'samples': 4946496, 'steps': 25762, 'loss/train': 1.4613096714019775}
+08/30/2021 17:47:50 - INFO - __main__ - Step 25764: {'lr': 0.00046886413698768816, 'samples': 4946688, 'steps': 25763, 'loss/train': 1.715574860572815}
+08/30/2021 17:47:52 - INFO - __main__ - Step 25765: {'lr': 0.0004688615722056222, 'samples': 4946880, 'steps': 25764, 'loss/train': 1.7326476573944092}
+08/30/2021 17:47:52 - INFO - __main__ - Step 25766: {'lr': 0.00046885900732494053, 'samples': 4947072, 'steps': 25765, 'loss/train': 1.8465771675109863}
+08/30/2021 17:47:53 - INFO - __main__ - Step 25767: {'lr': 0.0004688564423456444, 'samples': 4947264, 'steps': 25766, 'loss/train': 2.3126943111419678}
+08/30/2021 17:47:53 - INFO - __main__ - Step 25768: {'lr': 0.00046885387726773494, 'samples': 4947456, 'steps': 25767, 'loss/train': 1.471281886100769}
+08/30/2021 17:47:53 - INFO - __main__ - Step 25769: {'lr': 0.0004688513120912133, 'samples': 4947648, 'steps': 25768, 'loss/train': 1.0972404479980469}
+08/30/2021 17:47:55 - INFO - __main__ - Step 25770: {'lr': 0.0004688487468160806, 'samples': 4947840, 'steps': 25769, 'loss/train': 1.7421773672103882}
+08/30/2021 17:47:55 - INFO - __main__ - Step 25771: {'lr': 0.000468846181442338, 'samples': 4948032, 'steps': 25770, 'loss/train': 1.0144166946411133}
+08/30/2021 17:47:56 - INFO - __main__ - Step 25772: {'lr': 0.0004688436159699868, 'samples': 4948224, 'steps': 25771, 'loss/train': 1.7927099466323853}
+08/30/2021 17:47:56 - INFO - __main__ - Step 25773: {'lr': 0.000468841050399028, 'samples': 4948416, 'steps': 25772, 'loss/train': 1.3223836421966553}
+08/30/2021 17:47:56 - INFO - __main__ - Step 25774: {'lr': 0.0004688384847294628, 'samples': 4948608, 'steps': 25773, 'loss/train': 1.6288995742797852}
+08/30/2021 17:47:58 - INFO - __main__ - Step 25775: {'lr': 0.0004688359189612923, 'samples': 4948800, 'steps': 25774, 'loss/train': 0.46493470668792725}
+08/30/2021 17:47:59 - INFO - __main__ - Step 25776: {'lr': 0.0004688333530945178, 'samples': 4948992, 'steps': 25775, 'loss/train': 1.0550819635391235}
+08/30/2021 17:47:59 - INFO - __main__ - Step 25777: {'lr': 0.0004688307871291403, 'samples': 4949184, 'steps': 25776, 'loss/train': 1.7852526903152466}
+08/30/2021 17:47:59 - INFO - __main__ - Step 25778: {'lr': 0.0004688282210651611, 'samples': 4949376, 'steps': 25777, 'loss/train': 1.324590802192688}
+08/30/2021 17:48:00 - INFO - __main__ - Step 25779: {'lr': 0.00046882565490258125, 'samples': 4949568, 'steps': 25778, 'loss/train': 1.9621769189834595}
+08/30/2021 17:48:00 - INFO - __main__ - Step 25780: {'lr': 0.0004688230886414019, 'samples': 4949760, 'steps': 25779, 'loss/train': 1.7752286195755005}
+08/30/2021 17:48:02 - INFO - __main__ - Step 25781: {'lr': 0.0004688205222816242, 'samples': 4949952, 'steps': 25780, 'loss/train': 1.5793185234069824}
+08/30/2021 17:48:02 - INFO - __main__ - Step 25782: {'lr': 0.00046881795582324944, 'samples': 4950144, 'steps': 25781, 'loss/train': 1.5692440271377563}
+08/30/2021 17:48:03 - INFO - __main__ - Step 25783: {'lr': 0.00046881538926627864, 'samples': 4950336, 'steps': 25782, 'loss/train': 1.4250872135162354}
+08/30/2021 17:48:03 - INFO - __main__ - Step 25784: {'lr': 0.000468812822610713, 'samples': 4950528, 'steps': 25783, 'loss/train': 1.7000045776367188}
+08/30/2021 17:48:03 - INFO - __main__ - Step 25785: {'lr': 0.00046881025585655367, 'samples': 4950720, 'steps': 25784, 'loss/train': 1.6478009223937988}
+08/30/2021 17:48:05 - INFO - __main__ - Step 25786: {'lr': 0.0004688076890038019, 'samples': 4950912, 'steps': 25785, 'loss/train': 3.8902199268341064}
+08/30/2021 17:48:05 - INFO - __main__ - Step 25787: {'lr': 0.00046880512205245867, 'samples': 4951104, 'steps': 25786, 'loss/train': 1.7694299221038818}
+08/30/2021 17:48:06 - INFO - __main__ - Step 25788: {'lr': 0.00046880255500252526, 'samples': 4951296, 'steps': 25787, 'loss/train': 1.4008413553237915}
+08/30/2021 17:48:06 - INFO - __main__ - Step 25789: {'lr': 0.0004687999878540028, 'samples': 4951488, 'steps': 25788, 'loss/train': 1.402262568473816}
+08/30/2021 17:48:06 - INFO - __main__ - Step 25790: {'lr': 0.00046879742060689243, 'samples': 4951680, 'steps': 25789, 'loss/train': 1.4390090703964233}
+08/30/2021 17:48:08 - INFO - __main__ - Step 25791: {'lr': 0.0004687948532611953, 'samples': 4951872, 'steps': 25790, 'loss/train': 1.5752841234207153}
+08/30/2021 17:48:08 - INFO - __main__ - Step 25792: {'lr': 0.0004687922858169126, 'samples': 4952064, 'steps': 25791, 'loss/train': 1.81866455078125}
+08/30/2021 17:48:09 - INFO - __main__ - Step 25793: {'lr': 0.0004687897182740455, 'samples': 4952256, 'steps': 25792, 'loss/train': 1.4577043056488037}
+08/30/2021 17:48:09 - INFO - __main__ - Step 25794: {'lr': 0.0004687871506325951, 'samples': 4952448, 'steps': 25793, 'loss/train': 1.6696598529815674}
+08/30/2021 17:48:09 - INFO - __main__ - Step 25795: {'lr': 0.00046878458289256264, 'samples': 4952640, 'steps': 25794, 'loss/train': 1.4243284463882446}
+08/30/2021 17:48:11 - INFO - __main__ - Step 25796: {'lr': 0.00046878201505394913, 'samples': 4952832, 'steps': 25795, 'loss/train': 1.4257913827896118}
+08/30/2021 17:48:12 - INFO - __main__ - Step 25797: {'lr': 0.0004687794471167559, 'samples': 4953024, 'steps': 25796, 'loss/train': 1.295582890510559}
+08/30/2021 17:48:12 - INFO - __main__ - Step 25798: {'lr': 0.00046877687908098396, 'samples': 4953216, 'steps': 25797, 'loss/train': 1.5752441883087158}
+08/30/2021 17:48:12 - INFO - __main__ - Step 25799: {'lr': 0.0004687743109466346, 'samples': 4953408, 'steps': 25798, 'loss/train': 0.2516460716724396}
+08/30/2021 17:48:13 - INFO - __main__ - Step 25800: {'lr': 0.00046877174271370894, 'samples': 4953600, 'steps': 25799, 'loss/train': 1.274735927581787}
+08/30/2021 17:48:14 - INFO - __main__ - Step 25801: {'lr': 0.000468769174382208, 'samples': 4953792, 'steps': 25800, 'loss/train': 0.0804050862789154}
+08/30/2021 17:48:14 - INFO - __main__ - Step 25802: {'lr': 0.0004687666059521331, 'samples': 4953984, 'steps': 25801, 'loss/train': 1.858128547668457}
+08/30/2021 17:48:15 - INFO - __main__ - Step 25803: {'lr': 0.0004687640374234854, 'samples': 4954176, 'steps': 25802, 'loss/train': 1.530103087425232}
+08/30/2021 17:48:15 - INFO - __main__ - Step 25804: {'lr': 0.0004687614687962659, 'samples': 4954368, 'steps': 25803, 'loss/train': 0.8512210845947266}
+08/30/2021 17:48:16 - INFO - __main__ - Step 25805: {'lr': 0.0004687589000704759, 'samples': 4954560, 'steps': 25804, 'loss/train': 1.9007976055145264}
+08/30/2021 17:48:18 - INFO - __main__ - Step 25806: {'lr': 0.0004687563312461165, 'samples': 4954752, 'steps': 25805, 'loss/train': 1.5209821462631226}
+08/30/2021 17:48:18 - INFO - __main__ - Step 25807: {'lr': 0.00046875376232318887, 'samples': 4954944, 'steps': 25806, 'loss/train': 1.3787906169891357}
+08/30/2021 17:48:19 - INFO - __main__ - Step 25808: {'lr': 0.00046875119330169426, 'samples': 4955136, 'steps': 25807, 'loss/train': 0.5449550747871399}
+08/30/2021 17:48:19 - INFO - __main__ - Step 25809: {'lr': 0.00046874862418163363, 'samples': 4955328, 'steps': 25808, 'loss/train': 0.5622909069061279}
+08/30/2021 17:48:19 - INFO - __main__ - Step 25810: {'lr': 0.00046874605496300824, 'samples': 4955520, 'steps': 25809, 'loss/train': 1.6267250776290894}
+08/30/2021 17:48:20 - INFO - __main__ - Step 25811: {'lr': 0.00046874348564581933, 'samples': 4955712, 'steps': 25810, 'loss/train': 1.5047783851623535}
+08/30/2021 17:48:20 - INFO - __main__ - Step 25812: {'lr': 0.00046874091623006793, 'samples': 4955904, 'steps': 25811, 'loss/train': 1.4574873447418213}
+08/30/2021 17:48:22 - INFO - __main__ - Step 25813: {'lr': 0.0004687383467157553, 'samples': 4956096, 'steps': 25812, 'loss/train': 1.5586751699447632}
+08/30/2021 17:48:22 - INFO - __main__ - Step 25814: {'lr': 0.0004687357771028825, 'samples': 4956288, 'steps': 25813, 'loss/train': 1.671359658241272}
+08/30/2021 17:48:22 - INFO - __main__ - Step 25815: {'lr': 0.00046873320739145073, 'samples': 4956480, 'steps': 25814, 'loss/train': 1.4551055431365967}
+08/30/2021 17:48:23 - INFO - __main__ - Step 25816: {'lr': 0.0004687306375814612, 'samples': 4956672, 'steps': 25815, 'loss/train': 1.6281694173812866}
+08/30/2021 17:48:23 - INFO - __main__ - Step 25817: {'lr': 0.000468728067672915, 'samples': 4956864, 'steps': 25816, 'loss/train': 1.8594871759414673}
+08/30/2021 17:48:25 - INFO - __main__ - Step 25818: {'lr': 0.00046872549766581326, 'samples': 4957056, 'steps': 25817, 'loss/train': 1.5035878419876099}
+08/30/2021 17:48:25 - INFO - __main__ - Step 25819: {'lr': 0.00046872292756015724, 'samples': 4957248, 'steps': 25818, 'loss/train': 1.4658355712890625}
+08/30/2021 17:48:25 - INFO - __main__ - Step 25820: {'lr': 0.000468720357355948, 'samples': 4957440, 'steps': 25819, 'loss/train': 1.4506713151931763}
+08/30/2021 17:48:26 - INFO - __main__ - Step 25821: {'lr': 0.00046871778705318673, 'samples': 4957632, 'steps': 25820, 'loss/train': 1.3372007608413696}
+08/30/2021 17:48:26 - INFO - __main__ - Step 25822: {'lr': 0.0004687152166518747, 'samples': 4957824, 'steps': 25821, 'loss/train': 2.044471502304077}
+08/30/2021 17:48:28 - INFO - __main__ - Step 25823: {'lr': 0.0004687126461520128, 'samples': 4958016, 'steps': 25822, 'loss/train': 1.5280523300170898}
+08/30/2021 17:48:28 - INFO - __main__ - Step 25824: {'lr': 0.0004687100755536025, 'samples': 4958208, 'steps': 25823, 'loss/train': 1.6051236391067505}
+08/30/2021 17:48:29 - INFO - __main__ - Step 25825: {'lr': 0.00046870750485664484, 'samples': 4958400, 'steps': 25824, 'loss/train': 0.11616300791501999}
+08/30/2021 17:48:29 - INFO - __main__ - Step 25826: {'lr': 0.00046870493406114084, 'samples': 4958592, 'steps': 25825, 'loss/train': 1.6234893798828125}
+08/30/2021 17:48:29 - INFO - __main__ - Step 25827: {'lr': 0.0004687023631670918, 'samples': 4958784, 'steps': 25826, 'loss/train': 1.6770555973052979}
+08/30/2021 17:48:31 - INFO - __main__ - Step 25828: {'lr': 0.0004686997921744989, 'samples': 4958976, 'steps': 25827, 'loss/train': 0.9241091012954712}
+08/30/2021 17:48:32 - INFO - __main__ - Step 25829: {'lr': 0.0004686972210833632, 'samples': 4959168, 'steps': 25828, 'loss/train': 0.8609564900398254}
+08/30/2021 17:48:32 - INFO - __main__ - Step 25830: {'lr': 0.0004686946498936859, 'samples': 4959360, 'steps': 25829, 'loss/train': 0.9588181972503662}
+08/30/2021 17:48:33 - INFO - __main__ - Step 25831: {'lr': 0.00046869207860546826, 'samples': 4959552, 'steps': 25830, 'loss/train': 1.30747652053833}
+08/30/2021 17:48:33 - INFO - __main__ - Step 25832: {'lr': 0.00046868950721871126, 'samples': 4959744, 'steps': 25831, 'loss/train': 0.08194424957036972}
+08/30/2021 17:48:35 - INFO - __main__ - Step 25833: {'lr': 0.00046868693573341616, 'samples': 4959936, 'steps': 25832, 'loss/train': 1.5127626657485962}
+08/30/2021 17:48:35 - INFO - __main__ - Step 25834: {'lr': 0.00046868436414958405, 'samples': 4960128, 'steps': 25833, 'loss/train': 1.5270503759384155}
+08/30/2021 17:48:35 - INFO - __main__ - Step 25835: {'lr': 0.00046868179246721623, 'samples': 4960320, 'steps': 25834, 'loss/train': 1.227791428565979}
+08/30/2021 17:48:36 - INFO - __main__ - Step 25836: {'lr': 0.00046867922068631374, 'samples': 4960512, 'steps': 25835, 'loss/train': 1.333652377128601}
+08/30/2021 17:48:36 - INFO - __main__ - Step 25837: {'lr': 0.00046867664880687775, 'samples': 4960704, 'steps': 25836, 'loss/train': 1.6279029846191406}
+08/30/2021 17:48:37 - INFO - __main__ - Step 25838: {'lr': 0.00046867407682890937, 'samples': 4960896, 'steps': 25837, 'loss/train': 2.670116662979126}
+08/30/2021 17:48:38 - INFO - __main__ - Step 25839: {'lr': 0.00046867150475240994, 'samples': 4961088, 'steps': 25838, 'loss/train': 1.530759334564209}
+08/30/2021 17:48:39 - INFO - __main__ - Step 25840: {'lr': 0.0004686689325773805, 'samples': 4961280, 'steps': 25839, 'loss/train': 0.8202062845230103}
+08/30/2021 17:48:39 - INFO - __main__ - Step 25841: {'lr': 0.00046866636030382217, 'samples': 4961472, 'steps': 25840, 'loss/train': 0.588380753993988}
+08/30/2021 17:48:40 - INFO - __main__ - Step 25842: {'lr': 0.00046866378793173616, 'samples': 4961664, 'steps': 25841, 'loss/train': 0.047773007303476334}
+08/30/2021 17:48:40 - INFO - __main__ - Step 25843: {'lr': 0.0004686612154611236, 'samples': 4961856, 'steps': 25842, 'loss/train': 0.8975650668144226}
+08/30/2021 17:48:40 - INFO - __main__ - Step 25844: {'lr': 0.0004686586428919857, 'samples': 4962048, 'steps': 25843, 'loss/train': 1.4415950775146484}
+08/30/2021 17:48:42 - INFO - __main__ - Step 25845: {'lr': 0.00046865607022432356, 'samples': 4962240, 'steps': 25844, 'loss/train': 1.4818027019500732}
+08/30/2021 17:48:43 - INFO - __main__ - Step 25846: {'lr': 0.00046865349745813835, 'samples': 4962432, 'steps': 25845, 'loss/train': 0.41203126311302185}
+08/30/2021 17:48:43 - INFO - __main__ - Step 25847: {'lr': 0.00046865092459343126, 'samples': 4962624, 'steps': 25846, 'loss/train': 0.39638659358024597}
+08/30/2021 17:48:43 - INFO - __main__ - Step 25848: {'lr': 0.00046864835163020353, 'samples': 4962816, 'steps': 25847, 'loss/train': 3.1060988903045654}
+08/30/2021 17:48:44 - INFO - __main__ - Step 25849: {'lr': 0.00046864577856845613, 'samples': 4963008, 'steps': 25848, 'loss/train': 1.3016031980514526}
+08/30/2021 17:48:45 - INFO - __main__ - Step 25850: {'lr': 0.0004686432054081904, 'samples': 4963200, 'steps': 25849, 'loss/train': 1.7076200246810913}
+08/30/2021 17:48:46 - INFO - __main__ - Step 25851: {'lr': 0.00046864063214940735, 'samples': 4963392, 'steps': 25850, 'loss/train': 1.5625218152999878}
+08/30/2021 17:48:46 - INFO - __main__ - Step 25852: {'lr': 0.0004686380587921082, 'samples': 4963584, 'steps': 25851, 'loss/train': 1.1658756732940674}
+08/30/2021 17:48:46 - INFO - __main__ - Step 25853: {'lr': 0.00046863548533629406, 'samples': 4963776, 'steps': 25852, 'loss/train': 1.4682843685150146}
+08/30/2021 17:48:47 - INFO - __main__ - Step 25854: {'lr': 0.00046863291178196625, 'samples': 4963968, 'steps': 25853, 'loss/train': 1.3993884325027466}
+08/30/2021 17:48:48 - INFO - __main__ - Step 25855: {'lr': 0.0004686303381291258, 'samples': 4964160, 'steps': 25854, 'loss/train': 1.115661382675171}
+08/30/2021 17:48:49 - INFO - __main__ - Step 25856: {'lr': 0.00046862776437777386, 'samples': 4964352, 'steps': 25855, 'loss/train': 1.8204008340835571}
+08/30/2021 17:48:49 - INFO - __main__ - Step 25857: {'lr': 0.00046862519052791166, 'samples': 4964544, 'steps': 25856, 'loss/train': 1.7891380786895752}
+08/30/2021 17:48:49 - INFO - __main__ - Step 25858: {'lr': 0.00046862261657954033, 'samples': 4964736, 'steps': 25857, 'loss/train': 1.8477543592453003}
+08/30/2021 17:48:50 - INFO - __main__ - Step 25859: {'lr': 0.000468620042532661, 'samples': 4964928, 'steps': 25858, 'loss/train': 1.9821393489837646}
+08/30/2021 17:48:50 - INFO - __main__ - Step 25860: {'lr': 0.0004686174683872748, 'samples': 4965120, 'steps': 25859, 'loss/train': 1.1302052736282349}
+08/30/2021 17:48:52 - INFO - __main__ - Step 25861: {'lr': 0.00046861489414338304, 'samples': 4965312, 'steps': 25860, 'loss/train': 1.3140689134597778}
+08/30/2021 17:48:52 - INFO - __main__ - Step 25862: {'lr': 0.0004686123198009867, 'samples': 4965504, 'steps': 25861, 'loss/train': 1.688848853111267}
+08/30/2021 17:48:52 - INFO - __main__ - Step 25863: {'lr': 0.00046860974536008706, 'samples': 4965696, 'steps': 25862, 'loss/train': 2.353419065475464}
+08/30/2021 17:48:53 - INFO - __main__ - Step 25864: {'lr': 0.0004686071708206853, 'samples': 4965888, 'steps': 25863, 'loss/train': 1.376936912536621}
+08/30/2021 17:48:53 - INFO - __main__ - Step 25865: {'lr': 0.0004686045961827824, 'samples': 4966080, 'steps': 25864, 'loss/train': 1.745242714881897}
+08/30/2021 17:48:55 - INFO - __main__ - Step 25866: {'lr': 0.00046860202144637976, 'samples': 4966272, 'steps': 25865, 'loss/train': 1.4062267541885376}
+08/30/2021 17:48:55 - INFO - __main__ - Step 25867: {'lr': 0.00046859944661147837, 'samples': 4966464, 'steps': 25866, 'loss/train': 1.6638727188110352}
+08/30/2021 17:48:55 - INFO - __main__ - Step 25868: {'lr': 0.00046859687167807943, 'samples': 4966656, 'steps': 25867, 'loss/train': 1.9906589984893799}
+08/30/2021 17:48:56 - INFO - __main__ - Step 25869: {'lr': 0.0004685942966461841, 'samples': 4966848, 'steps': 25868, 'loss/train': 0.9553824663162231}
+08/30/2021 17:48:56 - INFO - __main__ - Step 25870: {'lr': 0.00046859172151579354, 'samples': 4967040, 'steps': 25869, 'loss/train': 1.0746548175811768}
+08/30/2021 17:48:58 - INFO - __main__ - Step 25871: {'lr': 0.00046858914628690896, 'samples': 4967232, 'steps': 25870, 'loss/train': 1.5431541204452515}
+08/30/2021 17:48:58 - INFO - __main__ - Step 25872: {'lr': 0.0004685865709595315, 'samples': 4967424, 'steps': 25871, 'loss/train': 0.1604749858379364}
+08/30/2021 17:48:59 - INFO - __main__ - Step 25873: {'lr': 0.00046858399553366224, 'samples': 4967616, 'steps': 25872, 'loss/train': 0.8738030791282654}
+08/30/2021 17:48:59 - INFO - __main__ - Step 25874: {'lr': 0.0004685814200093025, 'samples': 4967808, 'steps': 25873, 'loss/train': 1.4320909976959229}
+08/30/2021 17:48:59 - INFO - __main__ - Step 25875: {'lr': 0.00046857884438645327, 'samples': 4968000, 'steps': 25874, 'loss/train': 1.1554865837097168}
+08/30/2021 17:49:01 - INFO - __main__ - Step 25876: {'lr': 0.0004685762686651158, 'samples': 4968192, 'steps': 25875, 'loss/train': 1.8846144676208496}
+08/30/2021 17:49:02 - INFO - __main__ - Step 25877: {'lr': 0.0004685736928452913, 'samples': 4968384, 'steps': 25876, 'loss/train': 0.9436670541763306}
+08/30/2021 17:49:02 - INFO - __main__ - Step 25878: {'lr': 0.00046857111692698083, 'samples': 4968576, 'steps': 25877, 'loss/train': 1.8042160272598267}
+08/30/2021 17:49:02 - INFO - __main__ - Step 25879: {'lr': 0.0004685685409101855, 'samples': 4968768, 'steps': 25878, 'loss/train': 1.3830060958862305}
+08/30/2021 17:49:03 - INFO - __main__ - Step 25880: {'lr': 0.00046856596479490667, 'samples': 4968960, 'steps': 25879, 'loss/train': 0.16645364463329315}
+08/30/2021 17:49:05 - INFO - __main__ - Step 25881: {'lr': 0.0004685633885811453, 'samples': 4969152, 'steps': 25880, 'loss/train': 1.3824928998947144}
+08/30/2021 17:49:05 - INFO - __main__ - Step 25882: {'lr': 0.0004685608122689027, 'samples': 4969344, 'steps': 25881, 'loss/train': 0.9586479663848877}
+08/30/2021 17:49:06 - INFO - __main__ - Step 25883: {'lr': 0.00046855823585818004, 'samples': 4969536, 'steps': 25882, 'loss/train': 1.8196073770523071}
+08/30/2021 17:49:06 - INFO - __main__ - Step 25884: {'lr': 0.0004685556593489783, 'samples': 4969728, 'steps': 25883, 'loss/train': 1.5329629182815552}
+08/30/2021 17:49:06 - INFO - __main__ - Step 25885: {'lr': 0.0004685530827412988, 'samples': 4969920, 'steps': 25884, 'loss/train': 1.9199702739715576}
+08/30/2021 17:49:08 - INFO - __main__ - Step 25886: {'lr': 0.0004685505060351426, 'samples': 4970112, 'steps': 25885, 'loss/train': 0.08527534455060959}
+08/30/2021 17:49:08 - INFO - __main__ - Step 25887: {'lr': 0.00046854792923051094, 'samples': 4970304, 'steps': 25886, 'loss/train': 1.6177213191986084}
+08/30/2021 17:49:09 - INFO - __main__ - Step 25888: {'lr': 0.00046854535232740505, 'samples': 4970496, 'steps': 25887, 'loss/train': 1.8536111116409302}
+08/30/2021 17:49:09 - INFO - __main__ - Step 25889: {'lr': 0.00046854277532582585, 'samples': 4970688, 'steps': 25888, 'loss/train': 1.2673453092575073}
+08/30/2021 17:49:10 - INFO - __main__ - Step 25890: {'lr': 0.0004685401982257747, 'samples': 4970880, 'steps': 25889, 'loss/train': 1.2118864059448242}
+08/30/2021 17:49:11 - INFO - __main__ - Step 25891: {'lr': 0.0004685376210272527, 'samples': 4971072, 'steps': 25890, 'loss/train': 1.2783883810043335}
+08/30/2021 17:49:11 - INFO - __main__ - Step 25892: {'lr': 0.00046853504373026107, 'samples': 4971264, 'steps': 25891, 'loss/train': 1.3913556337356567}
+08/30/2021 17:49:12 - INFO - __main__ - Step 25893: {'lr': 0.00046853246633480087, 'samples': 4971456, 'steps': 25892, 'loss/train': 0.5311654806137085}
+08/30/2021 17:49:12 - INFO - __main__ - Step 25894: {'lr': 0.0004685298888408733, 'samples': 4971648, 'steps': 25893, 'loss/train': 1.2150635719299316}
+08/30/2021 17:49:13 - INFO - __main__ - Step 25895: {'lr': 0.0004685273112484796, 'samples': 4971840, 'steps': 25894, 'loss/train': 1.3217010498046875}
+08/30/2021 17:49:14 - INFO - __main__ - Step 25896: {'lr': 0.0004685247335576209, 'samples': 4972032, 'steps': 25895, 'loss/train': 1.5537326335906982}
+08/30/2021 17:49:15 - INFO - __main__ - Step 25897: {'lr': 0.00046852215576829824, 'samples': 4972224, 'steps': 25896, 'loss/train': 2.15730881690979}
+08/30/2021 17:49:15 - INFO - __main__ - Step 25898: {'lr': 0.0004685195778805129, 'samples': 4972416, 'steps': 25897, 'loss/train': 1.7009484767913818}
+08/30/2021 17:49:15 - INFO - __main__ - Step 25899: {'lr': 0.000468516999894266, 'samples': 4972608, 'steps': 25898, 'loss/train': 1.350884199142456}
+08/30/2021 17:49:16 - INFO - __main__ - Step 25900: {'lr': 0.0004685144218095587, 'samples': 4972800, 'steps': 25899, 'loss/train': 1.6464431285858154}
+08/30/2021 17:49:16 - INFO - __main__ - Step 25901: {'lr': 0.00046851184362639223, 'samples': 4972992, 'steps': 25900, 'loss/train': 1.436650037765503}
+08/30/2021 17:49:18 - INFO - __main__ - Step 25902: {'lr': 0.0004685092653447676, 'samples': 4973184, 'steps': 25901, 'loss/train': 1.5484634637832642}
+08/30/2021 17:49:18 - INFO - __main__ - Step 25903: {'lr': 0.00046850668696468614, 'samples': 4973376, 'steps': 25902, 'loss/train': 1.5408024787902832}
+08/30/2021 17:49:19 - INFO - __main__ - Step 25904: {'lr': 0.0004685041084861489, 'samples': 4973568, 'steps': 25903, 'loss/train': 1.5481486320495605}
+08/30/2021 17:49:19 - INFO - __main__ - Step 25905: {'lr': 0.00046850152990915705, 'samples': 4973760, 'steps': 25904, 'loss/train': 2.10436749458313}
+08/30/2021 17:49:19 - INFO - __main__ - Step 25906: {'lr': 0.0004684989512337119, 'samples': 4973952, 'steps': 25905, 'loss/train': 1.1209992170333862}
+08/30/2021 17:49:21 - INFO - __main__ - Step 25907: {'lr': 0.00046849637245981434, 'samples': 4974144, 'steps': 25906, 'loss/train': 1.4587196111679077}
+08/30/2021 17:49:21 - INFO - __main__ - Step 25908: {'lr': 0.0004684937935874658, 'samples': 4974336, 'steps': 25907, 'loss/train': 1.7507963180541992}
+08/30/2021 17:49:22 - INFO - __main__ - Step 25909: {'lr': 0.00046849121461666734, 'samples': 4974528, 'steps': 25908, 'loss/train': 1.6651357412338257}
+08/30/2021 17:49:22 - INFO - __main__ - Step 25910: {'lr': 0.00046848863554742006, 'samples': 4974720, 'steps': 25909, 'loss/train': 0.44157132506370544}
+08/30/2021 17:49:22 - INFO - __main__ - Step 25911: {'lr': 0.0004684860563797252, 'samples': 4974912, 'steps': 25910, 'loss/train': 1.385323166847229}
+08/30/2021 17:49:24 - INFO - __main__ - Step 25912: {'lr': 0.00046848347711358384, 'samples': 4975104, 'steps': 25911, 'loss/train': 1.5163391828536987}
+08/30/2021 17:49:24 - INFO - __main__ - Step 25913: {'lr': 0.0004684808977489973, 'samples': 4975296, 'steps': 25912, 'loss/train': 1.2386027574539185}
+08/30/2021 17:49:25 - INFO - __main__ - Step 25914: {'lr': 0.00046847831828596647, 'samples': 4975488, 'steps': 25913, 'loss/train': 1.4422698020935059}
+08/30/2021 17:49:25 - INFO - __main__ - Step 25915: {'lr': 0.0004684757387244928, 'samples': 4975680, 'steps': 25914, 'loss/train': 1.869231104850769}
+08/30/2021 17:49:25 - INFO - __main__ - Step 25916: {'lr': 0.00046847315906457733, 'samples': 4975872, 'steps': 25915, 'loss/train': 1.5322262048721313}
+08/30/2021 17:49:27 - INFO - __main__ - Step 25917: {'lr': 0.0004684705793062212, 'samples': 4976064, 'steps': 25916, 'loss/train': 1.3759723901748657}
+08/30/2021 17:49:27 - INFO - __main__ - Step 25918: {'lr': 0.00046846799944942564, 'samples': 4976256, 'steps': 25917, 'loss/train': 1.4368705749511719}
+08/30/2021 17:49:28 - INFO - __main__ - Step 25919: {'lr': 0.00046846541949419177, 'samples': 4976448, 'steps': 25918, 'loss/train': 0.6463767886161804}
+08/30/2021 17:49:28 - INFO - __main__ - Step 25920: {'lr': 0.00046846283944052073, 'samples': 4976640, 'steps': 25919, 'loss/train': 1.723982334136963}
+08/30/2021 17:49:28 - INFO - __main__ - Step 25921: {'lr': 0.0004684602592884136, 'samples': 4976832, 'steps': 25920, 'loss/train': 0.3706967830657959}
+08/30/2021 17:49:30 - INFO - __main__ - Step 25922: {'lr': 0.0004684576790378718, 'samples': 4977024, 'steps': 25921, 'loss/train': 1.5728548765182495}
+08/30/2021 17:49:31 - INFO - __main__ - Step 25923: {'lr': 0.00046845509868889625, 'samples': 4977216, 'steps': 25922, 'loss/train': 1.5348352193832397}
+08/30/2021 17:49:31 - INFO - __main__ - Step 25924: {'lr': 0.00046845251824148825, 'samples': 4977408, 'steps': 25923, 'loss/train': 1.6719447374343872}
+08/30/2021 17:49:31 - INFO - __main__ - Step 25925: {'lr': 0.0004684499376956489, 'samples': 4977600, 'steps': 25924, 'loss/train': 0.8076337575912476}
+08/30/2021 17:49:32 - INFO - __main__ - Step 25926: {'lr': 0.00046844735705137944, 'samples': 4977792, 'steps': 25925, 'loss/train': 1.2432372570037842}
+08/30/2021 17:49:32 - INFO - __main__ - Step 25927: {'lr': 0.0004684447763086809, 'samples': 4977984, 'steps': 25926, 'loss/train': 1.2376854419708252}
+08/30/2021 17:49:34 - INFO - __main__ - Step 25928: {'lr': 0.00046844219546755454, 'samples': 4978176, 'steps': 25927, 'loss/train': 2.077136754989624}
+08/30/2021 17:49:34 - INFO - __main__ - Step 25929: {'lr': 0.0004684396145280014, 'samples': 4978368, 'steps': 25928, 'loss/train': 1.3480955362319946}
+08/30/2021 17:49:34 - INFO - __main__ - Step 25930: {'lr': 0.00046843703349002286, 'samples': 4978560, 'steps': 25929, 'loss/train': 1.5316728353500366}
+08/30/2021 17:49:35 - INFO - __main__ - Step 25931: {'lr': 0.00046843445235361994, 'samples': 4978752, 'steps': 25930, 'loss/train': 0.6487564444541931}
+08/30/2021 17:49:35 - INFO - __main__ - Step 25932: {'lr': 0.0004684318711187938, 'samples': 4978944, 'steps': 25931, 'loss/train': 0.9000486135482788}
+08/30/2021 17:49:37 - INFO - __main__ - Step 25933: {'lr': 0.0004684292897855457, 'samples': 4979136, 'steps': 25932, 'loss/train': 1.7701318264007568}
+08/30/2021 17:49:37 - INFO - __main__ - Step 25934: {'lr': 0.00046842670835387667, 'samples': 4979328, 'steps': 25933, 'loss/train': 1.7426519393920898}
+08/30/2021 17:49:38 - INFO - __main__ - Step 25935: {'lr': 0.00046842412682378796, 'samples': 4979520, 'steps': 25934, 'loss/train': 2.0687735080718994}
+08/30/2021 17:49:38 - INFO - __main__ - Step 25936: {'lr': 0.0004684215451952807, 'samples': 4979712, 'steps': 25935, 'loss/train': 0.18766005337238312}
+08/30/2021 17:49:38 - INFO - __main__ - Step 25937: {'lr': 0.000468418963468356, 'samples': 4979904, 'steps': 25936, 'loss/train': 0.8473954200744629}
+08/30/2021 17:49:40 - INFO - __main__ - Step 25938: {'lr': 0.0004684163816430152, 'samples': 4980096, 'steps': 25937, 'loss/train': 1.2398358583450317}
+08/30/2021 17:49:41 - INFO - __main__ - Step 25939: {'lr': 0.00046841379971925923, 'samples': 4980288, 'steps': 25938, 'loss/train': 2.2545342445373535}
+08/30/2021 17:49:41 - INFO - __main__ - Step 25940: {'lr': 0.0004684112176970895, 'samples': 4980480, 'steps': 25939, 'loss/train': 0.9708952307701111}
+08/30/2021 17:49:42 - INFO - __main__ - Step 25941: {'lr': 0.0004684086355765069, 'samples': 4980672, 'steps': 25940, 'loss/train': 1.5442172288894653}
+08/30/2021 17:49:42 - INFO - __main__ - Step 25942: {'lr': 0.00046840605335751284, 'samples': 4980864, 'steps': 25941, 'loss/train': 0.12289529293775558}
+08/30/2021 17:49:42 - INFO - __main__ - Step 25943: {'lr': 0.0004684034710401084, 'samples': 4981056, 'steps': 25942, 'loss/train': 1.1677873134613037}
+08/30/2021 17:49:44 - INFO - __main__ - Step 25944: {'lr': 0.00046840088862429465, 'samples': 4981248, 'steps': 25943, 'loss/train': 0.9567702412605286}
+08/30/2021 17:49:44 - INFO - __main__ - Step 25945: {'lr': 0.00046839830611007297, 'samples': 4981440, 'steps': 25944, 'loss/train': 1.7980859279632568}
+08/30/2021 17:49:44 - INFO - __main__ - Step 25946: {'lr': 0.00046839572349744417, 'samples': 4981632, 'steps': 25945, 'loss/train': 1.9469941854476929}
+08/30/2021 17:49:45 - INFO - __main__ - Step 25947: {'lr': 0.0004683931407864098, 'samples': 4981824, 'steps': 25946, 'loss/train': 1.7215113639831543}
+08/30/2021 17:49:45 - INFO - __main__ - Step 25948: {'lr': 0.0004683905579769708, 'samples': 4982016, 'steps': 25947, 'loss/train': 1.8378640413284302}
+08/30/2021 17:49:47 - INFO - __main__ - Step 25949: {'lr': 0.0004683879750691283, 'samples': 4982208, 'steps': 25948, 'loss/train': 1.6385730504989624}
+08/30/2021 17:49:47 - INFO - __main__ - Step 25950: {'lr': 0.00046838539206288366, 'samples': 4982400, 'steps': 25949, 'loss/train': 0.9481050968170166}
+08/30/2021 17:49:48 - INFO - __main__ - Step 25951: {'lr': 0.00046838280895823795, 'samples': 4982592, 'steps': 25950, 'loss/train': 1.8381636142730713}
+08/30/2021 17:49:48 - INFO - __main__ - Step 25952: {'lr': 0.0004683802257551922, 'samples': 4982784, 'steps': 25951, 'loss/train': 0.21413718163967133}
+08/30/2021 17:49:48 - INFO - __main__ - Step 25953: {'lr': 0.00046837764245374777, 'samples': 4982976, 'steps': 25952, 'loss/train': 1.6276837587356567}
+08/30/2021 17:49:50 - INFO - __main__ - Step 25954: {'lr': 0.0004683750590539057, 'samples': 4983168, 'steps': 25953, 'loss/train': 1.499752163887024}
+08/30/2021 17:49:51 - INFO - __main__ - Step 25955: {'lr': 0.00046837247555566727, 'samples': 4983360, 'steps': 25954, 'loss/train': 1.5714073181152344}
+08/30/2021 17:49:51 - INFO - __main__ - Step 25956: {'lr': 0.00046836989195903344, 'samples': 4983552, 'steps': 25955, 'loss/train': 1.6329160928726196}
+08/30/2021 17:49:51 - INFO - __main__ - Step 25957: {'lr': 0.00046836730826400565, 'samples': 4983744, 'steps': 25956, 'loss/train': 0.05928225815296173}
+08/30/2021 17:49:52 - INFO - __main__ - Step 25958: {'lr': 0.00046836472447058485, 'samples': 4983936, 'steps': 25957, 'loss/train': 1.316361427307129}
+08/30/2021 17:49:52 - INFO - __main__ - Step 25959: {'lr': 0.0004683621405787723, 'samples': 4984128, 'steps': 25958, 'loss/train': 1.761487364768982}
+08/30/2021 17:49:54 - INFO - __main__ - Step 25960: {'lr': 0.0004683595565885691, 'samples': 4984320, 'steps': 25959, 'loss/train': 1.3059948682785034}
+08/30/2021 17:49:54 - INFO - __main__ - Step 25961: {'lr': 0.0004683569724999765, 'samples': 4984512, 'steps': 25960, 'loss/train': 1.4094239473342896}
+08/30/2021 17:49:54 - INFO - __main__ - Step 25962: {'lr': 0.0004683543883129956, 'samples': 4984704, 'steps': 25961, 'loss/train': 1.1170181035995483}
+08/30/2021 17:49:55 - INFO - __main__ - Step 25963: {'lr': 0.00046835180402762756, 'samples': 4984896, 'steps': 25962, 'loss/train': 1.4737088680267334}
+08/30/2021 17:49:55 - INFO - __main__ - Step 25964: {'lr': 0.00046834921964387363, 'samples': 4985088, 'steps': 25963, 'loss/train': 1.6293675899505615}
+08/30/2021 17:49:57 - INFO - __main__ - Step 25965: {'lr': 0.0004683466351617348, 'samples': 4985280, 'steps': 25964, 'loss/train': 1.4512293338775635}
+08/30/2021 17:49:57 - INFO - __main__ - Step 25966: {'lr': 0.00046834405058121244, 'samples': 4985472, 'steps': 25965, 'loss/train': 1.2718610763549805}
+08/30/2021 17:49:58 - INFO - __main__ - Step 25967: {'lr': 0.0004683414659023076, 'samples': 4985664, 'steps': 25966, 'loss/train': 1.3894829750061035}
+08/30/2021 17:49:58 - INFO - __main__ - Step 25968: {'lr': 0.0004683388811250214, 'samples': 4985856, 'steps': 25967, 'loss/train': 0.07728894799947739}
+08/30/2021 17:49:58 - INFO - __main__ - Step 25969: {'lr': 0.0004683362962493552, 'samples': 4986048, 'steps': 25968, 'loss/train': 1.0849885940551758}
+08/30/2021 17:50:00 - INFO - __main__ - Step 25970: {'lr': 0.00046833371127530995, 'samples': 4986240, 'steps': 25969, 'loss/train': 1.3206024169921875}
+08/30/2021 17:50:00 - INFO - __main__ - Step 25971: {'lr': 0.00046833112620288684, 'samples': 4986432, 'steps': 25970, 'loss/train': 1.8398730754852295}
+08/30/2021 17:50:01 - INFO - __main__ - Step 25972: {'lr': 0.0004683285410320872, 'samples': 4986624, 'steps': 25971, 'loss/train': 1.4553896188735962}
+08/30/2021 17:50:01 - INFO - __main__ - Step 25973: {'lr': 0.000468325955762912, 'samples': 4986816, 'steps': 25972, 'loss/train': 2.4145243167877197}
+08/30/2021 17:50:01 - INFO - __main__ - Step 25974: {'lr': 0.0004683233703953626, 'samples': 4987008, 'steps': 25973, 'loss/train': 0.05586782097816467}
+08/30/2021 17:50:03 - INFO - __main__ - Step 25975: {'lr': 0.00046832078492944, 'samples': 4987200, 'steps': 25974, 'loss/train': 1.1521482467651367}
+08/30/2021 17:50:04 - INFO - __main__ - Step 25976: {'lr': 0.0004683181993651454, 'samples': 4987392, 'steps': 25975, 'loss/train': 1.6343966722488403}
+08/30/2021 17:50:04 - INFO - __main__ - Step 25977: {'lr': 0.0004683156137024801, 'samples': 4987584, 'steps': 25976, 'loss/train': 1.1978342533111572}
+08/30/2021 17:50:05 - INFO - __main__ - Step 25978: {'lr': 0.00046831302794144504, 'samples': 4987776, 'steps': 25977, 'loss/train': 1.5771232843399048}
+08/30/2021 17:50:05 - INFO - __main__ - Step 25979: {'lr': 0.00046831044208204154, 'samples': 4987968, 'steps': 25978, 'loss/train': 0.8119454383850098}
+08/30/2021 17:50:05 - INFO - __main__ - Step 25980: {'lr': 0.0004683078561242707, 'samples': 4988160, 'steps': 25979, 'loss/train': 1.2827008962631226}
+08/30/2021 17:50:06 - INFO - __main__ - Step 25981: {'lr': 0.00046830527006813373, 'samples': 4988352, 'steps': 25980, 'loss/train': 1.6679977178573608}
+08/30/2021 17:50:07 - INFO - __main__ - Step 25982: {'lr': 0.00046830268391363176, 'samples': 4988544, 'steps': 25981, 'loss/train': 1.65229332447052}
+08/30/2021 17:50:08 - INFO - __main__ - Step 25983: {'lr': 0.0004683000976607659, 'samples': 4988736, 'steps': 25982, 'loss/train': 1.8264904022216797}
+08/30/2021 17:50:08 - INFO - __main__ - Step 25984: {'lr': 0.00046829751130953747, 'samples': 4988928, 'steps': 25983, 'loss/train': 1.3469122648239136}
+08/30/2021 17:50:08 - INFO - __main__ - Step 25985: {'lr': 0.0004682949248599476, 'samples': 4989120, 'steps': 25984, 'loss/train': 1.5895007848739624}
+08/30/2021 17:50:09 - INFO - __main__ - Step 25986: {'lr': 0.0004682923383119973, 'samples': 4989312, 'steps': 25985, 'loss/train': 1.8001866340637207}
+08/30/2021 17:50:10 - INFO - __main__ - Step 25987: {'lr': 0.0004682897516656879, 'samples': 4989504, 'steps': 25986, 'loss/train': 1.8371360301971436}
+08/30/2021 17:50:11 - INFO - __main__ - Step 25988: {'lr': 0.00046828716492102043, 'samples': 4989696, 'steps': 25987, 'loss/train': 1.1633650064468384}
+08/30/2021 17:50:11 - INFO - __main__ - Step 25989: {'lr': 0.0004682845780779962, 'samples': 4989888, 'steps': 25988, 'loss/train': 1.2397024631500244}
+08/30/2021 17:50:11 - INFO - __main__ - Step 25990: {'lr': 0.00046828199113661627, 'samples': 4990080, 'steps': 25989, 'loss/train': 1.7234729528427124}
+08/30/2021 17:50:12 - INFO - __main__ - Step 25991: {'lr': 0.0004682794040968819, 'samples': 4990272, 'steps': 25990, 'loss/train': 1.2466639280319214}
+08/30/2021 17:50:14 - INFO - __main__ - Step 25992: {'lr': 0.0004682768169587942, 'samples': 4990464, 'steps': 25991, 'loss/train': 1.100614070892334}
+08/30/2021 17:50:15 - INFO - __main__ - Step 25993: {'lr': 0.0004682742297223543, 'samples': 4990656, 'steps': 25992, 'loss/train': 1.6922521591186523}
+08/30/2021 17:50:15 - INFO - __main__ - Step 25994: {'lr': 0.00046827164238756337, 'samples': 4990848, 'steps': 25993, 'loss/train': 0.9433560371398926}
+08/30/2021 17:50:15 - INFO - __main__ - Step 25995: {'lr': 0.00046826905495442263, 'samples': 4991040, 'steps': 25994, 'loss/train': 0.9941039681434631}
+08/30/2021 17:50:16 - INFO - __main__ - Step 25996: {'lr': 0.00046826646742293326, 'samples': 4991232, 'steps': 25995, 'loss/train': 1.782634973526001}
+08/30/2021 17:50:16 - INFO - __main__ - Step 25997: {'lr': 0.00046826387979309635, 'samples': 4991424, 'steps': 25996, 'loss/train': 3.086235761642456}
+08/30/2021 17:50:18 - INFO - __main__ - Step 25998: {'lr': 0.0004682612920649131, 'samples': 4991616, 'steps': 25997, 'loss/train': 0.8794245719909668}
+08/30/2021 17:50:18 - INFO - __main__ - Step 25999: {'lr': 0.00046825870423838466, 'samples': 4991808, 'steps': 25998, 'loss/train': 0.8561205863952637}
+08/30/2021 17:50:18 - INFO - __main__ - Step 26000: {'lr': 0.00046825611631351227, 'samples': 4992000, 'steps': 25999, 'loss/train': 0.7992864847183228}
+08/30/2021 17:50:19 - INFO - __main__ - Step 26001: {'lr': 0.00046825352829029705, 'samples': 4992192, 'steps': 26000, 'loss/train': 1.2635619640350342}
+08/30/2021 17:50:19 - INFO - __main__ - Step 26002: {'lr': 0.00046825094016874014, 'samples': 4992384, 'steps': 26001, 'loss/train': 0.7718640565872192}
+08/30/2021 17:50:21 - INFO - __main__ - Step 26003: {'lr': 0.00046824835194884273, 'samples': 4992576, 'steps': 26002, 'loss/train': 2.029985189437866}
+08/30/2021 17:50:21 - INFO - __main__ - Step 26004: {'lr': 0.0004682457636306059, 'samples': 4992768, 'steps': 26003, 'loss/train': 0.8590334057807922}
+08/30/2021 17:50:22 - INFO - __main__ - Step 26005: {'lr': 0.000468243175214031, 'samples': 4992960, 'steps': 26004, 'loss/train': 1.890396237373352}
+08/30/2021 17:50:22 - INFO - __main__ - Step 26006: {'lr': 0.00046824058669911906, 'samples': 4993152, 'steps': 26005, 'loss/train': 1.6611837148666382}
+08/30/2021 17:50:22 - INFO - __main__ - Step 26007: {'lr': 0.00046823799808587126, 'samples': 4993344, 'steps': 26006, 'loss/train': 1.3633774518966675}
+08/30/2021 17:50:23 - INFO - __main__ - Step 26008: {'lr': 0.00046823540937428876, 'samples': 4993536, 'steps': 26007, 'loss/train': 1.5682960748672485}
+08/30/2021 17:50:24 - INFO - __main__ - Step 26009: {'lr': 0.0004682328205643728, 'samples': 4993728, 'steps': 26008, 'loss/train': 1.2900131940841675}
+08/30/2021 17:50:25 - INFO - __main__ - Step 26010: {'lr': 0.00046823023165612455, 'samples': 4993920, 'steps': 26009, 'loss/train': 1.6659449338912964}
+08/30/2021 17:50:25 - INFO - __main__ - Step 26011: {'lr': 0.000468227642649545, 'samples': 4994112, 'steps': 26010, 'loss/train': 1.5601441860198975}
+08/30/2021 17:50:25 - INFO - __main__ - Step 26012: {'lr': 0.00046822505354463553, 'samples': 4994304, 'steps': 26011, 'loss/train': 1.3833215236663818}
+08/30/2021 17:50:26 - INFO - __main__ - Step 26013: {'lr': 0.0004682224643413972, 'samples': 4994496, 'steps': 26012, 'loss/train': 1.6717795133590698}
+08/30/2021 17:50:27 - INFO - __main__ - Step 26014: {'lr': 0.0004682198750398312, 'samples': 4994688, 'steps': 26013, 'loss/train': 1.347379446029663}
+08/30/2021 17:50:28 - INFO - __main__ - Step 26015: {'lr': 0.00046821728563993867, 'samples': 4994880, 'steps': 26014, 'loss/train': 0.42934542894363403}
+08/30/2021 17:50:28 - INFO - __main__ - Step 26016: {'lr': 0.0004682146961417208, 'samples': 4995072, 'steps': 26015, 'loss/train': 1.59308922290802}
+08/30/2021 17:50:28 - INFO - __main__ - Step 26017: {'lr': 0.00046821210654517874, 'samples': 4995264, 'steps': 26016, 'loss/train': 1.338724970817566}
+08/30/2021 17:50:29 - INFO - __main__ - Step 26018: {'lr': 0.0004682095168503137, 'samples': 4995456, 'steps': 26017, 'loss/train': 1.399625539779663}
+08/30/2021 17:50:30 - INFO - __main__ - Step 26019: {'lr': 0.00046820692705712685, 'samples': 4995648, 'steps': 26018, 'loss/train': 1.3258057832717896}
+08/30/2021 17:50:31 - INFO - __main__ - Step 26020: {'lr': 0.00046820433716561927, 'samples': 4995840, 'steps': 26019, 'loss/train': 0.8071329593658447}
+08/30/2021 17:50:31 - INFO - __main__ - Step 26021: {'lr': 0.0004682017471757922, 'samples': 4996032, 'steps': 26020, 'loss/train': 1.1271674633026123}
+08/30/2021 17:50:32 - INFO - __main__ - Step 26022: {'lr': 0.0004681991570876468, 'samples': 4996224, 'steps': 26021, 'loss/train': 1.7399072647094727}
+08/30/2021 17:50:32 - INFO - __main__ - Step 26023: {'lr': 0.00046819656690118424, 'samples': 4996416, 'steps': 26022, 'loss/train': 0.3772258162498474}
+08/30/2021 17:50:32 - INFO - __main__ - Step 26024: {'lr': 0.00046819397661640563, 'samples': 4996608, 'steps': 26023, 'loss/train': 1.1453603506088257}
+08/30/2021 17:50:34 - INFO - __main__ - Step 26025: {'lr': 0.0004681913862333122, 'samples': 4996800, 'steps': 26024, 'loss/train': 1.5894954204559326}
+08/30/2021 17:50:34 - INFO - __main__ - Step 26026: {'lr': 0.0004681887957519051, 'samples': 4996992, 'steps': 26025, 'loss/train': 1.5680606365203857}
+08/30/2021 17:50:35 - INFO - __main__ - Step 26027: {'lr': 0.00046818620517218544, 'samples': 4997184, 'steps': 26026, 'loss/train': 1.8114136457443237}
+08/30/2021 17:50:35 - INFO - __main__ - Step 26028: {'lr': 0.00046818361449415456, 'samples': 4997376, 'steps': 26027, 'loss/train': 1.4232066869735718}
+08/30/2021 17:50:35 - INFO - __main__ - Step 26029: {'lr': 0.00046818102371781343, 'samples': 4997568, 'steps': 26028, 'loss/train': 1.4627221822738647}
+08/30/2021 17:50:37 - INFO - __main__ - Step 26030: {'lr': 0.0004681784328431633, 'samples': 4997760, 'steps': 26029, 'loss/train': 1.7061995267868042}
+08/30/2021 17:50:37 - INFO - __main__ - Step 26031: {'lr': 0.0004681758418702054, 'samples': 4997952, 'steps': 26030, 'loss/train': 1.5513299703598022}
+08/30/2021 17:50:37 - INFO - __main__ - Step 26032: {'lr': 0.0004681732507989408, 'samples': 4998144, 'steps': 26031, 'loss/train': 1.32917320728302}
+08/30/2021 17:50:38 - INFO - __main__ - Step 26033: {'lr': 0.00046817065962937067, 'samples': 4998336, 'steps': 26032, 'loss/train': 1.118119478225708}
+08/30/2021 17:50:38 - INFO - __main__ - Step 26034: {'lr': 0.00046816806836149624, 'samples': 4998528, 'steps': 26033, 'loss/train': 1.4400163888931274}
+08/30/2021 17:50:40 - INFO - __main__ - Step 26035: {'lr': 0.00046816547699531866, 'samples': 4998720, 'steps': 26034, 'loss/train': 1.7957981824874878}
+08/30/2021 17:50:40 - INFO - __main__ - Step 26036: {'lr': 0.000468162885530839, 'samples': 4998912, 'steps': 26035, 'loss/train': 1.4501303434371948}
+08/30/2021 17:50:40 - INFO - __main__ - Step 26037: {'lr': 0.00046816029396805857, 'samples': 4999104, 'steps': 26036, 'loss/train': 1.2901222705841064}
+08/30/2021 17:50:41 - INFO - __main__ - Step 26038: {'lr': 0.00046815770230697844, 'samples': 4999296, 'steps': 26037, 'loss/train': 1.858233094215393}
+08/30/2021 17:50:41 - INFO - __main__ - Step 26039: {'lr': 0.0004681551105475999, 'samples': 4999488, 'steps': 26038, 'loss/train': 1.8129796981811523}
+08/30/2021 17:50:41 - INFO - __main__ - Step 26040: {'lr': 0.0004681525186899239, 'samples': 4999680, 'steps': 26039, 'loss/train': 1.7217713594436646}
+08/30/2021 17:50:43 - INFO - __main__ - Step 26041: {'lr': 0.00046814992673395185, 'samples': 4999872, 'steps': 26040, 'loss/train': 1.1990773677825928}
+08/30/2021 17:50:44 - INFO - __main__ - Step 26042: {'lr': 0.0004681473346796848, 'samples': 5000064, 'steps': 26041, 'loss/train': 1.7544848918914795}
+08/30/2021 17:50:44 - INFO - __main__ - Step 26043: {'lr': 0.0004681447425271239, 'samples': 5000256, 'steps': 26042, 'loss/train': 1.2271026372909546}
+08/30/2021 17:50:44 - INFO - __main__ - Step 26044: {'lr': 0.0004681421502762704, 'samples': 5000448, 'steps': 26043, 'loss/train': 1.074222207069397}
+08/30/2021 17:50:45 - INFO - __main__ - Step 26045: {'lr': 0.0004681395579271253, 'samples': 5000640, 'steps': 26044, 'loss/train': 2.0768239498138428}
+08/30/2021 17:50:47 - INFO - __main__ - Step 26046: {'lr': 0.00046813696547969, 'samples': 5000832, 'steps': 26045, 'loss/train': 1.8352888822555542}
+08/30/2021 17:50:48 - INFO - __main__ - Step 26047: {'lr': 0.00046813437293396543, 'samples': 5001024, 'steps': 26046, 'loss/train': 1.2411599159240723}
+08/30/2021 17:50:48 - INFO - __main__ - Step 26048: {'lr': 0.000468131780289953, 'samples': 5001216, 'steps': 26047, 'loss/train': 4.784865379333496}
+08/30/2021 17:50:48 - INFO - __main__ - Step 26049: {'lr': 0.00046812918754765364, 'samples': 5001408, 'steps': 26048, 'loss/train': 2.1499345302581787}
+08/30/2021 17:50:49 - INFO - __main__ - Step 26050: {'lr': 0.00046812659470706877, 'samples': 5001600, 'steps': 26049, 'loss/train': 1.6595525741577148}
+08/30/2021 17:50:49 - INFO - __main__ - Step 26051: {'lr': 0.0004681240017681993, 'samples': 5001792, 'steps': 26050, 'loss/train': 0.07554569095373154}
+08/30/2021 17:50:51 - INFO - __main__ - Step 26052: {'lr': 0.00046812140873104657, 'samples': 5001984, 'steps': 26051, 'loss/train': 0.09549978375434875}
+08/30/2021 17:50:51 - INFO - __main__ - Step 26053: {'lr': 0.00046811881559561167, 'samples': 5002176, 'steps': 26052, 'loss/train': 1.808426856994629}
+08/30/2021 17:50:51 - INFO - __main__ - Step 26054: {'lr': 0.00046811622236189585, 'samples': 5002368, 'steps': 26053, 'loss/train': 2.0313563346862793}
+08/30/2021 17:50:52 - INFO - __main__ - Step 26055: {'lr': 0.0004681136290299002, 'samples': 5002560, 'steps': 26054, 'loss/train': 1.5682562589645386}
+08/30/2021 17:50:52 - INFO - __main__ - Step 26056: {'lr': 0.00046811103559962585, 'samples': 5002752, 'steps': 26055, 'loss/train': 1.0956287384033203}
+08/30/2021 17:50:54 - INFO - __main__ - Step 26057: {'lr': 0.00046810844207107415, 'samples': 5002944, 'steps': 26056, 'loss/train': 1.8528767824172974}
+08/30/2021 17:50:54 - INFO - __main__ - Step 26058: {'lr': 0.0004681058484442461, 'samples': 5003136, 'steps': 26057, 'loss/train': 1.6794477701187134}
+08/30/2021 17:50:54 - INFO - __main__ - Step 26059: {'lr': 0.00046810325471914295, 'samples': 5003328, 'steps': 26058, 'loss/train': 1.7115200757980347}
+08/30/2021 17:50:55 - INFO - __main__ - Step 26060: {'lr': 0.00046810066089576573, 'samples': 5003520, 'steps': 26059, 'loss/train': 1.1765812635421753}
+08/30/2021 17:50:55 - INFO - __main__ - Step 26061: {'lr': 0.00046809806697411583, 'samples': 5003712, 'steps': 26060, 'loss/train': 2.1888034343719482}
+08/30/2021 17:50:55 - INFO - __main__ - Step 26062: {'lr': 0.0004680954729541942, 'samples': 5003904, 'steps': 26061, 'loss/train': 1.1539087295532227}
+08/30/2021 17:50:57 - INFO - __main__ - Step 26063: {'lr': 0.00046809287883600227, 'samples': 5004096, 'steps': 26062, 'loss/train': 2.0836567878723145}
+08/30/2021 17:50:57 - INFO - __main__ - Step 26064: {'lr': 0.00046809028461954093, 'samples': 5004288, 'steps': 26063, 'loss/train': 1.8824714422225952}
+08/30/2021 17:50:58 - INFO - __main__ - Step 26065: {'lr': 0.00046808769030481153, 'samples': 5004480, 'steps': 26064, 'loss/train': 1.9013277292251587}
+08/30/2021 17:50:58 - INFO - __main__ - Step 26066: {'lr': 0.00046808509589181513, 'samples': 5004672, 'steps': 26065, 'loss/train': 1.2778221368789673}
+08/30/2021 17:50:58 - INFO - __main__ - Step 26067: {'lr': 0.00046808250138055305, 'samples': 5004864, 'steps': 26066, 'loss/train': 1.5713587999343872}
+08/30/2021 17:51:00 - INFO - __main__ - Step 26068: {'lr': 0.0004680799067710263, 'samples': 5005056, 'steps': 26067, 'loss/train': 1.123359203338623}
+08/30/2021 17:51:00 - INFO - __main__ - Step 26069: {'lr': 0.00046807731206323605, 'samples': 5005248, 'steps': 26068, 'loss/train': 1.8972338438034058}
+08/30/2021 17:51:01 - INFO - __main__ - Step 26070: {'lr': 0.00046807471725718357, 'samples': 5005440, 'steps': 26069, 'loss/train': 1.82386314868927}
+08/30/2021 17:51:01 - INFO - __main__ - Step 26071: {'lr': 0.00046807212235287, 'samples': 5005632, 'steps': 26070, 'loss/train': 2.1682937145233154}
+08/30/2021 17:51:01 - INFO - __main__ - Step 26072: {'lr': 0.0004680695273502965, 'samples': 5005824, 'steps': 26071, 'loss/train': 1.6509768962860107}
+08/30/2021 17:51:03 - INFO - __main__ - Step 26073: {'lr': 0.00046806693224946426, 'samples': 5006016, 'steps': 26072, 'loss/train': 1.665516972541809}
+08/30/2021 17:51:03 - INFO - __main__ - Step 26074: {'lr': 0.00046806433705037445, 'samples': 5006208, 'steps': 26073, 'loss/train': 1.6082911491394043}
+08/30/2021 17:51:04 - INFO - __main__ - Step 26075: {'lr': 0.00046806174175302806, 'samples': 5006400, 'steps': 26074, 'loss/train': 1.735235571861267}
+08/30/2021 17:51:04 - INFO - __main__ - Step 26076: {'lr': 0.00046805914635742656, 'samples': 5006592, 'steps': 26075, 'loss/train': 1.4829130172729492}
+08/30/2021 17:51:04 - INFO - __main__ - Step 26077: {'lr': 0.0004680565508635709, 'samples': 5006784, 'steps': 26076, 'loss/train': 1.7443983554840088}
+08/30/2021 17:51:06 - INFO - __main__ - Step 26078: {'lr': 0.00046805395527146237, 'samples': 5006976, 'steps': 26077, 'loss/train': 1.7859952449798584}
+08/30/2021 17:51:06 - INFO - __main__ - Step 26079: {'lr': 0.0004680513595811021, 'samples': 5007168, 'steps': 26078, 'loss/train': 2.150747060775757}
+08/30/2021 17:51:07 - INFO - __main__ - Step 26080: {'lr': 0.0004680487637924912, 'samples': 5007360, 'steps': 26079, 'loss/train': 1.501441478729248}
+08/30/2021 17:51:07 - INFO - __main__ - Step 26081: {'lr': 0.0004680461679056309, 'samples': 5007552, 'steps': 26080, 'loss/train': 1.599752426147461}
+08/30/2021 17:51:07 - INFO - __main__ - Step 26082: {'lr': 0.00046804357192052246, 'samples': 5007744, 'steps': 26081, 'loss/train': 1.835063099861145}
+08/30/2021 17:51:08 - INFO - __main__ - Step 26083: {'lr': 0.00046804097583716685, 'samples': 5007936, 'steps': 26082, 'loss/train': 1.6404485702514648}
+08/30/2021 17:51:09 - INFO - __main__ - Step 26084: {'lr': 0.0004680383796555654, 'samples': 5008128, 'steps': 26083, 'loss/train': 1.8288980722427368}
+08/30/2021 17:51:10 - INFO - __main__ - Step 26085: {'lr': 0.00046803578337571917, 'samples': 5008320, 'steps': 26084, 'loss/train': 1.72828209400177}
+08/30/2021 17:51:10 - INFO - __main__ - Step 26086: {'lr': 0.00046803318699762937, 'samples': 5008512, 'steps': 26085, 'loss/train': 1.5738255977630615}
+08/30/2021 17:51:10 - INFO - __main__ - Step 26087: {'lr': 0.0004680305905212972, 'samples': 5008704, 'steps': 26086, 'loss/train': 1.195892095565796}
+08/30/2021 17:51:11 - INFO - __main__ - Step 26088: {'lr': 0.0004680279939467238, 'samples': 5008896, 'steps': 26087, 'loss/train': 1.6134518384933472}
+08/30/2021 17:51:12 - INFO - __main__ - Step 26089: {'lr': 0.00046802539727391033, 'samples': 5009088, 'steps': 26088, 'loss/train': 1.4556657075881958}
+08/30/2021 17:51:13 - INFO - __main__ - Step 26090: {'lr': 0.0004680228005028581, 'samples': 5009280, 'steps': 26089, 'loss/train': 1.530471682548523}
+08/30/2021 17:51:13 - INFO - __main__ - Step 26091: {'lr': 0.000468020203633568, 'samples': 5009472, 'steps': 26090, 'loss/train': 1.8344494104385376}
+08/30/2021 17:51:13 - INFO - __main__ - Step 26092: {'lr': 0.0004680176066660415, 'samples': 5009664, 'steps': 26091, 'loss/train': 1.8249365091323853}
+08/30/2021 17:51:14 - INFO - __main__ - Step 26093: {'lr': 0.00046801500960027957, 'samples': 5009856, 'steps': 26092, 'loss/train': 1.8713473081588745}
+08/30/2021 17:51:15 - INFO - __main__ - Step 26094: {'lr': 0.00046801241243628344, 'samples': 5010048, 'steps': 26093, 'loss/train': 1.3450409173965454}
+08/30/2021 17:51:16 - INFO - __main__ - Step 26095: {'lr': 0.00046800981517405426, 'samples': 5010240, 'steps': 26094, 'loss/train': 1.082474708557129}
+08/30/2021 17:51:16 - INFO - __main__ - Step 26096: {'lr': 0.0004680072178135932, 'samples': 5010432, 'steps': 26095, 'loss/train': 2.279996871948242}
+08/30/2021 17:51:17 - INFO - __main__ - Step 26097: {'lr': 0.00046800462035490156, 'samples': 5010624, 'steps': 26096, 'loss/train': 0.10333873331546783}
+08/30/2021 17:51:17 - INFO - __main__ - Step 26098: {'lr': 0.0004680020227979803, 'samples': 5010816, 'steps': 26097, 'loss/train': 1.4143881797790527}
+08/30/2021 17:51:18 - INFO - __main__ - Step 26099: {'lr': 0.0004679994251428308, 'samples': 5011008, 'steps': 26098, 'loss/train': 0.8577102422714233}
+08/30/2021 17:51:19 - INFO - __main__ - Step 26100: {'lr': 0.00046799682738945397, 'samples': 5011200, 'steps': 26099, 'loss/train': 1.9826905727386475}
+08/30/2021 17:51:19 - INFO - __main__ - Step 26101: {'lr': 0.00046799422953785124, 'samples': 5011392, 'steps': 26100, 'loss/train': 0.7031465768814087}
+08/30/2021 17:51:20 - INFO - __main__ - Step 26102: {'lr': 0.00046799163158802365, 'samples': 5011584, 'steps': 26101, 'loss/train': 0.7783217430114746}
+08/30/2021 17:51:20 - INFO - __main__ - Step 26103: {'lr': 0.00046798903353997243, 'samples': 5011776, 'steps': 26102, 'loss/train': 1.5363852977752686}
+08/30/2021 17:51:22 - INFO - __main__ - Step 26104: {'lr': 0.0004679864353936987, 'samples': 5011968, 'steps': 26103, 'loss/train': 1.148025393486023}
+08/30/2021 17:51:23 - INFO - __main__ - Step 26105: {'lr': 0.0004679838371492036, 'samples': 5012160, 'steps': 26104, 'loss/train': 1.8366453647613525}
+08/30/2021 17:51:23 - INFO - __main__ - Step 26106: {'lr': 0.00046798123880648833, 'samples': 5012352, 'steps': 26105, 'loss/train': 0.735233724117279}
+08/30/2021 17:51:23 - INFO - __main__ - Step 26107: {'lr': 0.0004679786403655542, 'samples': 5012544, 'steps': 26106, 'loss/train': 0.5969606637954712}
+08/30/2021 17:51:24 - INFO - __main__ - Step 26108: {'lr': 0.0004679760418264021, 'samples': 5012736, 'steps': 26107, 'loss/train': 1.3180538415908813}
+08/30/2021 17:51:25 - INFO - __main__ - Step 26109: {'lr': 0.00046797344318903343, 'samples': 5012928, 'steps': 26108, 'loss/train': 1.8988051414489746}
+08/30/2021 17:51:26 - INFO - __main__ - Step 26110: {'lr': 0.0004679708444534493, 'samples': 5013120, 'steps': 26109, 'loss/train': 1.5253174304962158}
+08/30/2021 17:51:26 - INFO - __main__ - Step 26111: {'lr': 0.0004679682456196509, 'samples': 5013312, 'steps': 26110, 'loss/train': 0.9396080374717712}
+08/30/2021 17:51:26 - INFO - __main__ - Step 26112: {'lr': 0.0004679656466876393, 'samples': 5013504, 'steps': 26111, 'loss/train': 1.5866893529891968}
+08/30/2021 17:51:27 - INFO - __main__ - Step 26113: {'lr': 0.00046796304765741583, 'samples': 5013696, 'steps': 26112, 'loss/train': 1.6055492162704468}
+08/30/2021 17:51:27 - INFO - __main__ - Step 26114: {'lr': 0.00046796044852898144, 'samples': 5013888, 'steps': 26113, 'loss/train': 1.7148551940917969}
+08/30/2021 17:51:28 - INFO - __main__ - Step 26115: {'lr': 0.0004679578493023375, 'samples': 5014080, 'steps': 26114, 'loss/train': 1.5810562372207642}
+08/30/2021 17:51:29 - INFO - __main__ - Step 26116: {'lr': 0.00046795524997748515, 'samples': 5014272, 'steps': 26115, 'loss/train': 1.0068461894989014}
+08/30/2021 17:51:29 - INFO - __main__ - Step 26117: {'lr': 0.0004679526505544256, 'samples': 5014464, 'steps': 26116, 'loss/train': 1.168715000152588}
+08/30/2021 17:51:30 - INFO - __main__ - Step 26118: {'lr': 0.0004679500510331598, 'samples': 5014656, 'steps': 26117, 'loss/train': 2.080726385116577}
+08/30/2021 17:51:30 - INFO - __main__ - Step 26119: {'lr': 0.00046794745141368917, 'samples': 5014848, 'steps': 26118, 'loss/train': 1.7851732969284058}
+08/30/2021 17:51:32 - INFO - __main__ - Step 26120: {'lr': 0.00046794485169601474, 'samples': 5015040, 'steps': 26119, 'loss/train': 1.5185885429382324}
+08/30/2021 17:51:32 - INFO - __main__ - Step 26121: {'lr': 0.00046794225188013773, 'samples': 5015232, 'steps': 26120, 'loss/train': 1.8581764698028564}
+08/30/2021 17:51:32 - INFO - __main__ - Step 26122: {'lr': 0.00046793965196605927, 'samples': 5015424, 'steps': 26121, 'loss/train': 1.7707773447036743}
+08/30/2021 17:51:33 - INFO - __main__ - Step 26123: {'lr': 0.00046793705195378066, 'samples': 5015616, 'steps': 26122, 'loss/train': 1.5318524837493896}
+08/30/2021 17:51:33 - INFO - __main__ - Step 26124: {'lr': 0.0004679344518433029, 'samples': 5015808, 'steps': 26123, 'loss/train': 1.4481995105743408}
+08/30/2021 17:51:35 - INFO - __main__ - Step 26125: {'lr': 0.0004679318516346273, 'samples': 5016000, 'steps': 26124, 'loss/train': 1.2897790670394897}
+08/30/2021 17:51:35 - INFO - __main__ - Step 26126: {'lr': 0.0004679292513277549, 'samples': 5016192, 'steps': 26125, 'loss/train': 1.6501446962356567}
+08/30/2021 17:51:35 - INFO - __main__ - Step 26127: {'lr': 0.0004679266509226869, 'samples': 5016384, 'steps': 26126, 'loss/train': 1.3101930618286133}
+08/30/2021 17:51:36 - INFO - __main__ - Step 26128: {'lr': 0.0004679240504194246, 'samples': 5016576, 'steps': 26127, 'loss/train': 1.645825982093811}
+08/30/2021 17:51:36 - INFO - __main__ - Step 26129: {'lr': 0.00046792144981796905, 'samples': 5016768, 'steps': 26128, 'loss/train': 0.7791157364845276}
+08/30/2021 17:51:38 - INFO - __main__ - Step 26130: {'lr': 0.0004679188491183215, 'samples': 5016960, 'steps': 26129, 'loss/train': 1.2416889667510986}
+08/30/2021 17:51:38 - INFO - __main__ - Step 26131: {'lr': 0.00046791624832048307, 'samples': 5017152, 'steps': 26130, 'loss/train': 1.7181764841079712}
+08/30/2021 17:51:39 - INFO - __main__ - Step 26132: {'lr': 0.0004679136474244549, 'samples': 5017344, 'steps': 26131, 'loss/train': 1.6692501306533813}
+08/30/2021 17:51:39 - INFO - __main__ - Step 26133: {'lr': 0.00046791104643023823, 'samples': 5017536, 'steps': 26132, 'loss/train': 1.8287296295166016}
+08/30/2021 17:51:39 - INFO - __main__ - Step 26134: {'lr': 0.0004679084453378342, 'samples': 5017728, 'steps': 26133, 'loss/train': 0.9401084780693054}
+08/30/2021 17:51:41 - INFO - __main__ - Step 26135: {'lr': 0.00046790584414724404, 'samples': 5017920, 'steps': 26134, 'loss/train': 1.7611048221588135}
+08/30/2021 17:51:41 - INFO - __main__ - Step 26136: {'lr': 0.0004679032428584687, 'samples': 5018112, 'steps': 26135, 'loss/train': 1.5844484567642212}
+08/30/2021 17:51:42 - INFO - __main__ - Step 26137: {'lr': 0.0004679006414715097, 'samples': 5018304, 'steps': 26136, 'loss/train': 0.9440152645111084}
+08/30/2021 17:51:42 - INFO - __main__ - Step 26138: {'lr': 0.00046789803998636796, 'samples': 5018496, 'steps': 26137, 'loss/train': 2.4105002880096436}
+08/30/2021 17:51:42 - INFO - __main__ - Step 26139: {'lr': 0.0004678954384030448, 'samples': 5018688, 'steps': 26138, 'loss/train': 1.4241313934326172}
+08/30/2021 17:51:44 - INFO - __main__ - Step 26140: {'lr': 0.00046789283672154125, 'samples': 5018880, 'steps': 26139, 'loss/train': 0.9175655841827393}
+08/30/2021 17:51:44 - INFO - __main__ - Step 26141: {'lr': 0.00046789023494185855, 'samples': 5019072, 'steps': 26140, 'loss/train': 1.0826953649520874}
+08/30/2021 17:51:45 - INFO - __main__ - Step 26142: {'lr': 0.0004678876330639978, 'samples': 5019264, 'steps': 26141, 'loss/train': 1.167996883392334}
+08/30/2021 17:51:45 - INFO - __main__ - Step 26143: {'lr': 0.0004678850310879604, 'samples': 5019456, 'steps': 26142, 'loss/train': 1.8836358785629272}
+08/30/2021 17:51:45 - INFO - __main__ - Step 26144: {'lr': 0.0004678824290137473, 'samples': 5019648, 'steps': 26143, 'loss/train': 1.3544318675994873}
+08/30/2021 17:51:47 - INFO - __main__ - Step 26145: {'lr': 0.0004678798268413597, 'samples': 5019840, 'steps': 26144, 'loss/train': 1.3764623403549194}
+08/30/2021 17:51:47 - INFO - __main__ - Step 26146: {'lr': 0.00046787722457079887, 'samples': 5020032, 'steps': 26145, 'loss/train': 1.5148603916168213}
+08/30/2021 17:51:48 - INFO - __main__ - Step 26147: {'lr': 0.00046787462220206587, 'samples': 5020224, 'steps': 26146, 'loss/train': 1.8436599969863892}
+08/30/2021 17:51:48 - INFO - __main__ - Step 26148: {'lr': 0.00046787201973516195, 'samples': 5020416, 'steps': 26147, 'loss/train': 0.5548301339149475}
+08/30/2021 17:51:48 - INFO - __main__ - Step 26149: {'lr': 0.00046786941717008823, 'samples': 5020608, 'steps': 26148, 'loss/train': 0.637928307056427}
+08/30/2021 17:51:49 - INFO - __main__ - Step 26150: {'lr': 0.00046786681450684597, 'samples': 5020800, 'steps': 26149, 'loss/train': 2.0019750595092773}
+08/30/2021 17:51:50 - INFO - __main__ - Step 26151: {'lr': 0.00046786421174543625, 'samples': 5020992, 'steps': 26150, 'loss/train': 1.213064193725586}
+08/30/2021 17:51:51 - INFO - __main__ - Step 26152: {'lr': 0.0004678616088858603, 'samples': 5021184, 'steps': 26151, 'loss/train': 1.6105926036834717}
+08/30/2021 17:51:51 - INFO - __main__ - Step 26153: {'lr': 0.0004678590059281193, 'samples': 5021376, 'steps': 26152, 'loss/train': 1.7457095384597778}
+08/30/2021 17:51:51 - INFO - __main__ - Step 26154: {'lr': 0.0004678564028722143, 'samples': 5021568, 'steps': 26153, 'loss/train': 2.446765184402466}
+08/30/2021 17:51:52 - INFO - __main__ - Step 26155: {'lr': 0.0004678537997181467, 'samples': 5021760, 'steps': 26154, 'loss/train': 1.2729811668395996}
+08/30/2021 17:51:54 - INFO - __main__ - Step 26156: {'lr': 0.00046785119646591746, 'samples': 5021952, 'steps': 26155, 'loss/train': 1.7035256624221802}
+08/30/2021 17:51:54 - INFO - __main__ - Step 26157: {'lr': 0.0004678485931155278, 'samples': 5022144, 'steps': 26156, 'loss/train': 1.5122156143188477}
+08/30/2021 17:51:55 - INFO - __main__ - Step 26158: {'lr': 0.000467845989666979, 'samples': 5022336, 'steps': 26157, 'loss/train': 1.3289146423339844}
+08/30/2021 17:51:55 - INFO - __main__ - Step 26159: {'lr': 0.0004678433861202721, 'samples': 5022528, 'steps': 26158, 'loss/train': 1.6197569370269775}
+08/30/2021 17:51:55 - INFO - __main__ - Step 26160: {'lr': 0.0004678407824754083, 'samples': 5022720, 'steps': 26159, 'loss/train': 1.7705466747283936}
+08/30/2021 17:51:56 - INFO - __main__ - Step 26161: {'lr': 0.00046783817873238885, 'samples': 5022912, 'steps': 26160, 'loss/train': 0.09180153906345367}
+08/30/2021 17:51:57 - INFO - __main__ - Step 26162: {'lr': 0.0004678355748912149, 'samples': 5023104, 'steps': 26161, 'loss/train': 0.6512777209281921}
+08/30/2021 17:51:58 - INFO - __main__ - Step 26163: {'lr': 0.0004678329709518876, 'samples': 5023296, 'steps': 26162, 'loss/train': 1.0051910877227783}
+08/30/2021 17:51:58 - INFO - __main__ - Step 26164: {'lr': 0.0004678303669144081, 'samples': 5023488, 'steps': 26163, 'loss/train': 1.294397234916687}
+08/30/2021 17:51:58 - INFO - __main__ - Step 26165: {'lr': 0.0004678277627787776, 'samples': 5023680, 'steps': 26164, 'loss/train': 0.5985181927680969}
+08/30/2021 17:51:59 - INFO - __main__ - Step 26166: {'lr': 0.0004678251585449973, 'samples': 5023872, 'steps': 26165, 'loss/train': 1.6224207878112793}
+08/30/2021 17:52:00 - INFO - __main__ - Step 26167: {'lr': 0.0004678225542130683, 'samples': 5024064, 'steps': 26166, 'loss/train': 1.5821278095245361}
+08/30/2021 17:52:01 - INFO - __main__ - Step 26168: {'lr': 0.0004678199497829919, 'samples': 5024256, 'steps': 26167, 'loss/train': 1.2952234745025635}
+08/30/2021 17:52:01 - INFO - __main__ - Step 26169: {'lr': 0.0004678173452547691, 'samples': 5024448, 'steps': 26168, 'loss/train': 1.4567570686340332}
+08/30/2021 17:52:01 - INFO - __main__ - Step 26170: {'lr': 0.00046781474062840126, 'samples': 5024640, 'steps': 26169, 'loss/train': 1.1379626989364624}
+08/30/2021 17:52:02 - INFO - __main__ - Step 26171: {'lr': 0.0004678121359038894, 'samples': 5024832, 'steps': 26170, 'loss/train': 1.627280831336975}
+08/30/2021 17:52:04 - INFO - __main__ - Step 26172: {'lr': 0.0004678095310812347, 'samples': 5025024, 'steps': 26171, 'loss/train': 0.38083937764167786}
+08/30/2021 17:52:04 - INFO - __main__ - Step 26173: {'lr': 0.0004678069261604384, 'samples': 5025216, 'steps': 26172, 'loss/train': 1.146022081375122}
+08/30/2021 17:52:05 - INFO - __main__ - Step 26174: {'lr': 0.00046780432114150173, 'samples': 5025408, 'steps': 26173, 'loss/train': 1.4485677480697632}
+08/30/2021 17:52:05 - INFO - __main__ - Step 26175: {'lr': 0.0004678017160244258, 'samples': 5025600, 'steps': 26174, 'loss/train': 1.5082147121429443}
+08/30/2021 17:52:05 - INFO - __main__ - Step 26176: {'lr': 0.00046779911080921166, 'samples': 5025792, 'steps': 26175, 'loss/train': 2.016350269317627}
+08/30/2021 17:52:06 - INFO - __main__ - Step 26177: {'lr': 0.00046779650549586075, 'samples': 5025984, 'steps': 26176, 'loss/train': 1.5053982734680176}
+08/30/2021 17:52:07 - INFO - __main__ - Step 26178: {'lr': 0.000467793900084374, 'samples': 5026176, 'steps': 26177, 'loss/train': 0.363174706697464}
+08/30/2021 17:52:08 - INFO - __main__ - Step 26179: {'lr': 0.0004677912945747527, 'samples': 5026368, 'steps': 26178, 'loss/train': 2.0944387912750244}
+08/30/2021 17:52:08 - INFO - __main__ - Step 26180: {'lr': 0.000467788688966998, 'samples': 5026560, 'steps': 26179, 'loss/train': 1.557246446609497}
+08/30/2021 17:52:08 - INFO - __main__ - Step 26181: {'lr': 0.00046778608326111104, 'samples': 5026752, 'steps': 26180, 'loss/train': 2.4179751873016357}
+08/30/2021 17:52:09 - INFO - __main__ - Step 26182: {'lr': 0.00046778347745709317, 'samples': 5026944, 'steps': 26181, 'loss/train': 1.5029606819152832}
+08/30/2021 17:52:10 - INFO - __main__ - Step 26183: {'lr': 0.0004677808715549453, 'samples': 5027136, 'steps': 26182, 'loss/train': 0.08202935755252838}
+08/30/2021 17:52:11 - INFO - __main__ - Step 26184: {'lr': 0.0004677782655546687, 'samples': 5027328, 'steps': 26183, 'loss/train': 2.0947749614715576}
+08/30/2021 17:52:11 - INFO - __main__ - Step 26185: {'lr': 0.00046777565945626463, 'samples': 5027520, 'steps': 26184, 'loss/train': 0.14571039378643036}
+08/30/2021 17:52:12 - INFO - __main__ - Step 26186: {'lr': 0.0004677730532597343, 'samples': 5027712, 'steps': 26185, 'loss/train': 0.664777398109436}
+08/30/2021 17:52:12 - INFO - __main__ - Step 26187: {'lr': 0.00046777044696507867, 'samples': 5027904, 'steps': 26186, 'loss/train': 1.4623806476593018}
+08/30/2021 17:52:14 - INFO - __main__ - Step 26188: {'lr': 0.00046776784057229906, 'samples': 5028096, 'steps': 26187, 'loss/train': 1.3610191345214844}
+08/30/2021 17:52:14 - INFO - __main__ - Step 26189: {'lr': 0.00046776523408139666, 'samples': 5028288, 'steps': 26188, 'loss/train': 1.5496939420700073}
+08/30/2021 17:52:14 - INFO - __main__ - Step 26190: {'lr': 0.0004677626274923726, 'samples': 5028480, 'steps': 26189, 'loss/train': 1.611902117729187}
+08/30/2021 17:52:15 - INFO - __main__ - Step 26191: {'lr': 0.000467760020805228, 'samples': 5028672, 'steps': 26190, 'loss/train': 1.2484333515167236}
+08/30/2021 17:52:15 - INFO - __main__ - Step 26192: {'lr': 0.0004677574140199642, 'samples': 5028864, 'steps': 26191, 'loss/train': 1.459053635597229}
+08/30/2021 17:52:16 - INFO - __main__ - Step 26193: {'lr': 0.00046775480713658215, 'samples': 5029056, 'steps': 26192, 'loss/train': 1.6826428174972534}
+08/30/2021 17:52:17 - INFO - __main__ - Step 26194: {'lr': 0.00046775220015508325, 'samples': 5029248, 'steps': 26193, 'loss/train': 1.5191541910171509}
+08/30/2021 17:52:17 - INFO - __main__ - Step 26195: {'lr': 0.0004677495930754685, 'samples': 5029440, 'steps': 26194, 'loss/train': 1.6067183017730713}
+08/30/2021 17:52:18 - INFO - __main__ - Step 26196: {'lr': 0.0004677469858977391, 'samples': 5029632, 'steps': 26195, 'loss/train': 1.3620458841323853}
+08/30/2021 17:52:18 - INFO - __main__ - Step 26197: {'lr': 0.00046774437862189634, 'samples': 5029824, 'steps': 26196, 'loss/train': 1.465554118156433}
+08/30/2021 17:52:19 - INFO - __main__ - Step 26198: {'lr': 0.00046774177124794136, 'samples': 5030016, 'steps': 26197, 'loss/train': 0.8533470034599304}
+08/30/2021 17:52:20 - INFO - __main__ - Step 26199: {'lr': 0.00046773916377587524, 'samples': 5030208, 'steps': 26198, 'loss/train': 1.480251431465149}
+08/30/2021 17:52:20 - INFO - __main__ - Step 26200: {'lr': 0.00046773655620569924, 'samples': 5030400, 'steps': 26199, 'loss/train': 1.3872203826904297}
+08/30/2021 17:52:20 - INFO - __main__ - Step 26201: {'lr': 0.0004677339485374145, 'samples': 5030592, 'steps': 26200, 'loss/train': 1.836183786392212}
+08/30/2021 17:52:21 - INFO - __main__ - Step 26202: {'lr': 0.00046773134077102217, 'samples': 5030784, 'steps': 26201, 'loss/train': 1.560879111289978}
+08/30/2021 17:52:22 - INFO - __main__ - Step 26203: {'lr': 0.00046772873290652344, 'samples': 5030976, 'steps': 26202, 'loss/train': 1.932642936706543}
+08/30/2021 17:52:23 - INFO - __main__ - Step 26204: {'lr': 0.0004677261249439196, 'samples': 5031168, 'steps': 26203, 'loss/train': 1.487125039100647}
+08/30/2021 17:52:23 - INFO - __main__ - Step 26205: {'lr': 0.0004677235168832117, 'samples': 5031360, 'steps': 26204, 'loss/train': 0.585166871547699}
+08/30/2021 17:52:24 - INFO - __main__ - Step 26206: {'lr': 0.0004677209087244009, 'samples': 5031552, 'steps': 26205, 'loss/train': 1.2288188934326172}
+08/30/2021 17:52:24 - INFO - __main__ - Step 26207: {'lr': 0.0004677183004674884, 'samples': 5031744, 'steps': 26206, 'loss/train': 1.764260172843933}
+08/30/2021 17:52:24 - INFO - __main__ - Step 26208: {'lr': 0.00046771569211247546, 'samples': 5031936, 'steps': 26207, 'loss/train': 1.874774694442749}
+08/30/2021 17:52:27 - INFO - __main__ - Step 26209: {'lr': 0.00046771308365936315, 'samples': 5032128, 'steps': 26208, 'loss/train': 1.7931764125823975}
+08/30/2021 17:52:27 - INFO - __main__ - Step 26210: {'lr': 0.00046771047510815267, 'samples': 5032320, 'steps': 26209, 'loss/train': 1.2996633052825928}
+08/30/2021 17:52:27 - INFO - __main__ - Step 26211: {'lr': 0.0004677078664588452, 'samples': 5032512, 'steps': 26210, 'loss/train': 1.447281002998352}
+08/30/2021 17:52:28 - INFO - __main__ - Step 26212: {'lr': 0.000467705257711442, 'samples': 5032704, 'steps': 26211, 'loss/train': 1.5091127157211304}
+08/30/2021 17:52:28 - INFO - __main__ - Step 26213: {'lr': 0.0004677026488659441, 'samples': 5032896, 'steps': 26212, 'loss/train': 1.8863173723220825}
+08/30/2021 17:52:29 - INFO - __main__ - Step 26214: {'lr': 0.0004677000399223528, 'samples': 5033088, 'steps': 26213, 'loss/train': 2.09542179107666}
+08/30/2021 17:52:30 - INFO - __main__ - Step 26215: {'lr': 0.0004676974308806692, 'samples': 5033280, 'steps': 26214, 'loss/train': 1.9482330083847046}
+08/30/2021 17:52:30 - INFO - __main__ - Step 26216: {'lr': 0.00046769482174089446, 'samples': 5033472, 'steps': 26215, 'loss/train': 1.2161154747009277}
+08/30/2021 17:52:31 - INFO - __main__ - Step 26217: {'lr': 0.00046769221250302984, 'samples': 5033664, 'steps': 26216, 'loss/train': 0.5359983444213867}
+08/30/2021 17:52:31 - INFO - __main__ - Step 26218: {'lr': 0.0004676896031670764, 'samples': 5033856, 'steps': 26217, 'loss/train': 1.6811681985855103}
+08/30/2021 17:52:32 - INFO - __main__ - Step 26219: {'lr': 0.00046768699373303546, 'samples': 5034048, 'steps': 26218, 'loss/train': 1.6467416286468506}
+08/30/2021 17:52:33 - INFO - __main__ - Step 26220: {'lr': 0.00046768438420090807, 'samples': 5034240, 'steps': 26219, 'loss/train': 1.2183287143707275}
+08/30/2021 17:52:33 - INFO - __main__ - Step 26221: {'lr': 0.0004676817745706955, 'samples': 5034432, 'steps': 26220, 'loss/train': 1.2806841135025024}
+08/30/2021 17:52:34 - INFO - __main__ - Step 26222: {'lr': 0.0004676791648423989, 'samples': 5034624, 'steps': 26221, 'loss/train': 1.8384215831756592}
+08/30/2021 17:52:34 - INFO - __main__ - Step 26223: {'lr': 0.00046767655501601935, 'samples': 5034816, 'steps': 26222, 'loss/train': 1.3472853899002075}
+08/30/2021 17:52:36 - INFO - __main__ - Step 26224: {'lr': 0.0004676739450915581, 'samples': 5035008, 'steps': 26223, 'loss/train': 1.0090837478637695}
+08/30/2021 17:52:36 - INFO - __main__ - Step 26225: {'lr': 0.0004676713350690164, 'samples': 5035200, 'steps': 26224, 'loss/train': 1.7016509771347046}
+08/30/2021 17:52:36 - INFO - __main__ - Step 26226: {'lr': 0.0004676687249483953, 'samples': 5035392, 'steps': 26225, 'loss/train': 2.773500919342041}
+08/30/2021 17:52:37 - INFO - __main__ - Step 26227: {'lr': 0.0004676661147296961, 'samples': 5035584, 'steps': 26226, 'loss/train': 1.444489598274231}
+08/30/2021 17:52:37 - INFO - __main__ - Step 26228: {'lr': 0.00046766350441291985, 'samples': 5035776, 'steps': 26227, 'loss/train': 1.0572092533111572}
+08/30/2021 17:52:39 - INFO - __main__ - Step 26229: {'lr': 0.00046766089399806775, 'samples': 5035968, 'steps': 26228, 'loss/train': 0.6948620080947876}
+08/30/2021 17:52:39 - INFO - __main__ - Step 26230: {'lr': 0.0004676582834851411, 'samples': 5036160, 'steps': 26229, 'loss/train': 1.6123915910720825}
+08/30/2021 17:52:39 - INFO - __main__ - Step 26231: {'lr': 0.0004676556728741409, 'samples': 5036352, 'steps': 26230, 'loss/train': 0.19862884283065796}
+08/30/2021 17:52:40 - INFO - __main__ - Step 26232: {'lr': 0.0004676530621650685, 'samples': 5036544, 'steps': 26231, 'loss/train': 1.3207002878189087}
+08/30/2021 17:52:40 - INFO - __main__ - Step 26233: {'lr': 0.00046765045135792495, 'samples': 5036736, 'steps': 26232, 'loss/train': 2.133751153945923}
+08/30/2021 17:52:42 - INFO - __main__ - Step 26234: {'lr': 0.00046764784045271146, 'samples': 5036928, 'steps': 26233, 'loss/train': 1.8287540674209595}
+08/30/2021 17:52:42 - INFO - __main__ - Step 26235: {'lr': 0.0004676452294494292, 'samples': 5037120, 'steps': 26234, 'loss/train': 1.5834941864013672}
+08/30/2021 17:52:42 - INFO - __main__ - Step 26236: {'lr': 0.00046764261834807944, 'samples': 5037312, 'steps': 26235, 'loss/train': 2.87629771232605}
+08/30/2021 17:52:43 - INFO - __main__ - Step 26237: {'lr': 0.0004676400071486632, 'samples': 5037504, 'steps': 26236, 'loss/train': 2.2349281311035156}
+08/30/2021 17:52:43 - INFO - __main__ - Step 26238: {'lr': 0.0004676373958511817, 'samples': 5037696, 'steps': 26237, 'loss/train': 1.0710747241973877}
+08/30/2021 17:52:45 - INFO - __main__ - Step 26239: {'lr': 0.00046763478445563617, 'samples': 5037888, 'steps': 26238, 'loss/train': 2.6107187271118164}
+08/30/2021 17:52:45 - INFO - __main__ - Step 26240: {'lr': 0.0004676321729620278, 'samples': 5038080, 'steps': 26239, 'loss/train': 1.5706325769424438}
+08/30/2021 17:52:46 - INFO - __main__ - Step 26241: {'lr': 0.0004676295613703577, 'samples': 5038272, 'steps': 26240, 'loss/train': 1.8564623594284058}
+08/30/2021 17:52:46 - INFO - __main__ - Step 26242: {'lr': 0.00046762694968062706, 'samples': 5038464, 'steps': 26241, 'loss/train': 1.5979385375976562}
+08/30/2021 17:52:46 - INFO - __main__ - Step 26243: {'lr': 0.0004676243378928371, 'samples': 5038656, 'steps': 26242, 'loss/train': 2.0918338298797607}
+08/30/2021 17:52:47 - INFO - __main__ - Step 26244: {'lr': 0.000467621726006989, 'samples': 5038848, 'steps': 26243, 'loss/train': 0.6312897205352783}
+08/30/2021 17:52:48 - INFO - __main__ - Step 26245: {'lr': 0.0004676191140230839, 'samples': 5039040, 'steps': 26244, 'loss/train': 1.396957516670227}
+08/30/2021 17:52:49 - INFO - __main__ - Step 26246: {'lr': 0.0004676165019411229, 'samples': 5039232, 'steps': 26245, 'loss/train': 1.4047967195510864}
+08/30/2021 17:52:49 - INFO - __main__ - Step 26247: {'lr': 0.00046761388976110737, 'samples': 5039424, 'steps': 26246, 'loss/train': 1.378141164779663}
+08/30/2021 17:52:49 - INFO - __main__ - Step 26248: {'lr': 0.00046761127748303833, 'samples': 5039616, 'steps': 26247, 'loss/train': 1.552869439125061}
+08/30/2021 17:52:50 - INFO - __main__ - Step 26249: {'lr': 0.000467608665106917, 'samples': 5039808, 'steps': 26248, 'loss/train': 1.6121121644973755}
+08/30/2021 17:52:51 - INFO - __main__ - Step 26250: {'lr': 0.0004676060526327446, 'samples': 5040000, 'steps': 26249, 'loss/train': 1.5323083400726318}
+08/30/2021 17:52:52 - INFO - __main__ - Step 26251: {'lr': 0.00046760344006052223, 'samples': 5040192, 'steps': 26250, 'loss/train': 1.0000609159469604}
+08/30/2021 17:52:52 - INFO - __main__ - Step 26252: {'lr': 0.00046760082739025113, 'samples': 5040384, 'steps': 26251, 'loss/train': 1.5879063606262207}
+08/30/2021 17:52:52 - INFO - __main__ - Step 26253: {'lr': 0.0004675982146219324, 'samples': 5040576, 'steps': 26252, 'loss/train': 0.24589650332927704}
+08/30/2021 17:52:53 - INFO - __main__ - Step 26254: {'lr': 0.00046759560175556737, 'samples': 5040768, 'steps': 26253, 'loss/train': 1.4122611284255981}
+08/30/2021 17:52:54 - INFO - __main__ - Step 26255: {'lr': 0.0004675929887911571, 'samples': 5040960, 'steps': 26254, 'loss/train': 1.3601524829864502}
+08/30/2021 17:52:55 - INFO - __main__ - Step 26256: {'lr': 0.0004675903757287027, 'samples': 5041152, 'steps': 26255, 'loss/train': 1.5401798486709595}
+08/30/2021 17:52:55 - INFO - __main__ - Step 26257: {'lr': 0.0004675877625682055, 'samples': 5041344, 'steps': 26256, 'loss/train': 1.829728126525879}
+08/30/2021 17:52:55 - INFO - __main__ - Step 26258: {'lr': 0.00046758514930966664, 'samples': 5041536, 'steps': 26257, 'loss/train': 1.5436458587646484}
+08/30/2021 17:52:56 - INFO - __main__ - Step 26259: {'lr': 0.0004675825359530872, 'samples': 5041728, 'steps': 26258, 'loss/train': 1.1547647714614868}
+08/30/2021 17:52:58 - INFO - __main__ - Step 26260: {'lr': 0.0004675799224984685, 'samples': 5041920, 'steps': 26259, 'loss/train': 1.8499315977096558}
+08/30/2021 17:52:58 - INFO - __main__ - Step 26261: {'lr': 0.00046757730894581164, 'samples': 5042112, 'steps': 26260, 'loss/train': 1.8405916690826416}
+08/30/2021 17:52:58 - INFO - __main__ - Step 26262: {'lr': 0.00046757469529511777, 'samples': 5042304, 'steps': 26261, 'loss/train': 1.6968600749969482}
+08/30/2021 17:52:59 - INFO - __main__ - Step 26263: {'lr': 0.0004675720815463881, 'samples': 5042496, 'steps': 26262, 'loss/train': 1.6263556480407715}
+08/30/2021 17:52:59 - INFO - __main__ - Step 26264: {'lr': 0.00046756946769962375, 'samples': 5042688, 'steps': 26263, 'loss/train': 1.757317066192627}
+08/30/2021 17:53:01 - INFO - __main__ - Step 26265: {'lr': 0.000467566853754826, 'samples': 5042880, 'steps': 26264, 'loss/train': 1.6671481132507324}
+08/30/2021 17:53:01 - INFO - __main__ - Step 26266: {'lr': 0.00046756423971199603, 'samples': 5043072, 'steps': 26265, 'loss/train': 1.3835176229476929}
+08/30/2021 17:53:02 - INFO - __main__ - Step 26267: {'lr': 0.0004675616255711349, 'samples': 5043264, 'steps': 26266, 'loss/train': 5.911319732666016}
+08/30/2021 17:53:02 - INFO - __main__ - Step 26268: {'lr': 0.0004675590113322439, 'samples': 5043456, 'steps': 26267, 'loss/train': 1.204235315322876}
+08/30/2021 17:53:02 - INFO - __main__ - Step 26269: {'lr': 0.00046755639699532414, 'samples': 5043648, 'steps': 26268, 'loss/train': 1.2118866443634033}
+08/30/2021 17:53:03 - INFO - __main__ - Step 26270: {'lr': 0.00046755378256037685, 'samples': 5043840, 'steps': 26269, 'loss/train': 1.761609435081482}
+08/30/2021 17:53:04 - INFO - __main__ - Step 26271: {'lr': 0.00046755116802740316, 'samples': 5044032, 'steps': 26270, 'loss/train': 1.9451550245285034}
+08/30/2021 17:53:05 - INFO - __main__ - Step 26272: {'lr': 0.00046754855339640436, 'samples': 5044224, 'steps': 26271, 'loss/train': 0.941116213798523}
+08/30/2021 17:53:05 - INFO - __main__ - Step 26273: {'lr': 0.00046754593866738144, 'samples': 5044416, 'steps': 26272, 'loss/train': 1.11298668384552}
+08/30/2021 17:53:06 - INFO - __main__ - Step 26274: {'lr': 0.0004675433238403357, 'samples': 5044608, 'steps': 26273, 'loss/train': 1.162381887435913}
+08/30/2021 17:53:06 - INFO - __main__ - Step 26275: {'lr': 0.0004675407089152683, 'samples': 5044800, 'steps': 26274, 'loss/train': 1.1345688104629517}
+08/30/2021 17:53:06 - INFO - __main__ - Step 26276: {'lr': 0.00046753809389218036, 'samples': 5044992, 'steps': 26275, 'loss/train': 1.559865117073059}
+08/30/2021 17:53:08 - INFO - __main__ - Step 26277: {'lr': 0.0004675354787710732, 'samples': 5045184, 'steps': 26276, 'loss/train': 1.0282788276672363}
+08/30/2021 17:53:08 - INFO - __main__ - Step 26278: {'lr': 0.0004675328635519479, 'samples': 5045376, 'steps': 26277, 'loss/train': 0.7387611269950867}
+08/30/2021 17:53:08 - INFO - __main__ - Step 26279: {'lr': 0.0004675302482348056, 'samples': 5045568, 'steps': 26278, 'loss/train': 1.364940881729126}
+08/30/2021 17:53:09 - INFO - __main__ - Step 26280: {'lr': 0.00046752763281964757, 'samples': 5045760, 'steps': 26279, 'loss/train': 1.4897438287734985}
+08/30/2021 17:53:09 - INFO - __main__ - Step 26281: {'lr': 0.0004675250173064749, 'samples': 5045952, 'steps': 26280, 'loss/train': 1.7558190822601318}
+08/30/2021 17:53:11 - INFO - __main__ - Step 26282: {'lr': 0.0004675224016952888, 'samples': 5046144, 'steps': 26281, 'loss/train': 1.4290552139282227}
+08/30/2021 17:53:11 - INFO - __main__ - Step 26283: {'lr': 0.00046751978598609056, 'samples': 5046336, 'steps': 26282, 'loss/train': 1.4846059083938599}
+08/30/2021 17:53:11 - INFO - __main__ - Step 26284: {'lr': 0.00046751717017888116, 'samples': 5046528, 'steps': 26283, 'loss/train': 1.951148509979248}
+08/30/2021 17:53:12 - INFO - __main__ - Step 26285: {'lr': 0.00046751455427366194, 'samples': 5046720, 'steps': 26284, 'loss/train': 1.6930569410324097}
+08/30/2021 17:53:12 - INFO - __main__ - Step 26286: {'lr': 0.00046751193827043405, 'samples': 5046912, 'steps': 26285, 'loss/train': 1.0926343202590942}
+08/30/2021 17:53:14 - INFO - __main__ - Step 26287: {'lr': 0.0004675093221691985, 'samples': 5047104, 'steps': 26286, 'loss/train': 1.2144969701766968}
+08/30/2021 17:53:14 - INFO - __main__ - Step 26288: {'lr': 0.0004675067059699567, 'samples': 5047296, 'steps': 26287, 'loss/train': 1.193758249282837}
+08/30/2021 17:53:15 - INFO - __main__ - Step 26289: {'lr': 0.00046750408967270973, 'samples': 5047488, 'steps': 26288, 'loss/train': 1.3849986791610718}
+08/30/2021 17:53:15 - INFO - __main__ - Step 26290: {'lr': 0.0004675014732774588, 'samples': 5047680, 'steps': 26289, 'loss/train': 1.406269907951355}
+08/30/2021 17:53:15 - INFO - __main__ - Step 26291: {'lr': 0.000467498856784205, 'samples': 5047872, 'steps': 26290, 'loss/train': 1.1837278604507446}
+08/30/2021 17:53:17 - INFO - __main__ - Step 26292: {'lr': 0.0004674962401929496, 'samples': 5048064, 'steps': 26291, 'loss/train': 1.9569282531738281}
+08/30/2021 17:53:17 - INFO - __main__ - Step 26293: {'lr': 0.0004674936235036938, 'samples': 5048256, 'steps': 26292, 'loss/train': 1.192387580871582}
+08/30/2021 17:53:18 - INFO - __main__ - Step 26294: {'lr': 0.00046749100671643866, 'samples': 5048448, 'steps': 26293, 'loss/train': 0.874843418598175}
+08/30/2021 17:53:18 - INFO - __main__ - Step 26295: {'lr': 0.00046748838983118546, 'samples': 5048640, 'steps': 26294, 'loss/train': 0.8066315650939941}
+08/30/2021 17:53:18 - INFO - __main__ - Step 26296: {'lr': 0.00046748577284793535, 'samples': 5048832, 'steps': 26295, 'loss/train': 1.4623510837554932}
+08/30/2021 17:53:20 - INFO - __main__ - Step 26297: {'lr': 0.00046748315576668946, 'samples': 5049024, 'steps': 26296, 'loss/train': 1.4491009712219238}
+08/30/2021 17:53:20 - INFO - __main__ - Step 26298: {'lr': 0.0004674805385874491, 'samples': 5049216, 'steps': 26297, 'loss/train': 2.0263445377349854}
+08/30/2021 17:53:21 - INFO - __main__ - Step 26299: {'lr': 0.0004674779213102153, 'samples': 5049408, 'steps': 26298, 'loss/train': 0.7796643972396851}
+08/30/2021 17:53:21 - INFO - __main__ - Step 26300: {'lr': 0.00046747530393498934, 'samples': 5049600, 'steps': 26299, 'loss/train': 5.412769317626953}
+08/30/2021 17:53:21 - INFO - __main__ - Step 26301: {'lr': 0.0004674726864617723, 'samples': 5049792, 'steps': 26300, 'loss/train': 1.9228533506393433}
+08/30/2021 17:53:22 - INFO - __main__ - Step 26302: {'lr': 0.00046747006889056556, 'samples': 5049984, 'steps': 26301, 'loss/train': 2.1370584964752197}
+08/30/2021 17:53:23 - INFO - __main__ - Step 26303: {'lr': 0.00046746745122137, 'samples': 5050176, 'steps': 26302, 'loss/train': 1.3682295083999634}
+08/30/2021 17:53:24 - INFO - __main__ - Step 26304: {'lr': 0.000467464833454187, 'samples': 5050368, 'steps': 26303, 'loss/train': 1.6545788049697876}
+08/30/2021 17:53:24 - INFO - __main__ - Step 26305: {'lr': 0.0004674622155890178, 'samples': 5050560, 'steps': 26304, 'loss/train': 1.717965006828308}
+08/30/2021 17:53:25 - INFO - __main__ - Step 26306: {'lr': 0.00046745959762586344, 'samples': 5050752, 'steps': 26305, 'loss/train': 0.475311279296875}
+08/30/2021 17:53:25 - INFO - __main__ - Step 26307: {'lr': 0.0004674569795647251, 'samples': 5050944, 'steps': 26306, 'loss/train': 1.924486756324768}
+08/30/2021 17:53:27 - INFO - __main__ - Step 26308: {'lr': 0.00046745436140560397, 'samples': 5051136, 'steps': 26307, 'loss/train': 1.3409497737884521}
+08/30/2021 17:53:27 - INFO - __main__ - Step 26309: {'lr': 0.00046745174314850136, 'samples': 5051328, 'steps': 26308, 'loss/train': 1.4483742713928223}
+08/30/2021 17:53:27 - INFO - __main__ - Step 26310: {'lr': 0.00046744912479341826, 'samples': 5051520, 'steps': 26309, 'loss/train': 0.8104193806648254}
+08/30/2021 17:53:28 - INFO - __main__ - Step 26311: {'lr': 0.00046744650634035603, 'samples': 5051712, 'steps': 26310, 'loss/train': 1.873723030090332}
+08/30/2021 17:53:28 - INFO - __main__ - Step 26312: {'lr': 0.0004674438877893157, 'samples': 5051904, 'steps': 26311, 'loss/train': 2.0275466442108154}
+08/30/2021 17:53:29 - INFO - __main__ - Step 26313: {'lr': 0.0004674412691402985, 'samples': 5052096, 'steps': 26312, 'loss/train': 1.306639552116394}
+08/30/2021 17:53:30 - INFO - __main__ - Step 26314: {'lr': 0.00046743865039330565, 'samples': 5052288, 'steps': 26313, 'loss/train': 1.2984265089035034}
+08/30/2021 17:53:30 - INFO - __main__ - Step 26315: {'lr': 0.00046743603154833827, 'samples': 5052480, 'steps': 26314, 'loss/train': 0.90952467918396}
+08/30/2021 17:53:31 - INFO - __main__ - Step 26316: {'lr': 0.00046743341260539756, 'samples': 5052672, 'steps': 26315, 'loss/train': 1.4084138870239258}
+08/30/2021 17:53:31 - INFO - __main__ - Step 26317: {'lr': 0.00046743079356448476, 'samples': 5052864, 'steps': 26316, 'loss/train': 1.8966929912567139}
+08/30/2021 17:53:33 - INFO - __main__ - Step 26318: {'lr': 0.000467428174425601, 'samples': 5053056, 'steps': 26317, 'loss/train': 1.3839093446731567}
+08/30/2021 17:53:33 - INFO - __main__ - Step 26319: {'lr': 0.0004674255551887474, 'samples': 5053248, 'steps': 26318, 'loss/train': 1.144919753074646}
+08/30/2021 17:53:34 - INFO - __main__ - Step 26320: {'lr': 0.0004674229358539253, 'samples': 5053440, 'steps': 26319, 'loss/train': 1.1010702848434448}
+08/30/2021 17:53:34 - INFO - __main__ - Step 26321: {'lr': 0.0004674203164211357, 'samples': 5053632, 'steps': 26320, 'loss/train': 1.3001075983047485}
+08/30/2021 17:53:34 - INFO - __main__ - Step 26322: {'lr': 0.00046741769689037985, 'samples': 5053824, 'steps': 26321, 'loss/train': 1.4087958335876465}
+08/30/2021 17:53:36 - INFO - __main__ - Step 26323: {'lr': 0.0004674150772616589, 'samples': 5054016, 'steps': 26322, 'loss/train': 1.2034153938293457}
+08/30/2021 17:53:36 - INFO - __main__ - Step 26324: {'lr': 0.0004674124575349742, 'samples': 5054208, 'steps': 26323, 'loss/train': 1.8088667392730713}
+08/30/2021 17:53:37 - INFO - __main__ - Step 26325: {'lr': 0.00046740983771032674, 'samples': 5054400, 'steps': 26324, 'loss/train': 5.845498085021973}
+08/30/2021 17:53:37 - INFO - __main__ - Step 26326: {'lr': 0.0004674072177877178, 'samples': 5054592, 'steps': 26325, 'loss/train': 1.6823536157608032}
+08/30/2021 17:53:37 - INFO - __main__ - Step 26327: {'lr': 0.0004674045977671484, 'samples': 5054784, 'steps': 26326, 'loss/train': 1.9012107849121094}
+08/30/2021 17:53:38 - INFO - __main__ - Step 26328: {'lr': 0.00046740197764862, 'samples': 5054976, 'steps': 26327, 'loss/train': 2.1735944747924805}
+08/30/2021 17:53:39 - INFO - __main__ - Step 26329: {'lr': 0.00046739935743213344, 'samples': 5055168, 'steps': 26328, 'loss/train': 1.2146939039230347}
+08/30/2021 17:53:40 - INFO - __main__ - Step 26330: {'lr': 0.00046739673711769026, 'samples': 5055360, 'steps': 26329, 'loss/train': 1.8299793004989624}
+08/30/2021 17:53:40 - INFO - __main__ - Step 26331: {'lr': 0.0004673941167052914, 'samples': 5055552, 'steps': 26330, 'loss/train': 1.4739185571670532}
+08/30/2021 17:53:41 - INFO - __main__ - Step 26332: {'lr': 0.0004673914961949381, 'samples': 5055744, 'steps': 26331, 'loss/train': 2.0954718589782715}
+08/30/2021 17:53:41 - INFO - __main__ - Step 26333: {'lr': 0.0004673888755866316, 'samples': 5055936, 'steps': 26332, 'loss/train': 0.09940269589424133}
+08/30/2021 17:53:42 - INFO - __main__ - Step 26334: {'lr': 0.0004673862548803729, 'samples': 5056128, 'steps': 26333, 'loss/train': 2.0142016410827637}
+08/30/2021 17:53:43 - INFO - __main__ - Step 26335: {'lr': 0.0004673836340761634, 'samples': 5056320, 'steps': 26334, 'loss/train': 1.219390630722046}
+08/30/2021 17:53:43 - INFO - __main__ - Step 26336: {'lr': 0.00046738101317400415, 'samples': 5056512, 'steps': 26335, 'loss/train': 1.3998562097549438}
+08/30/2021 17:53:44 - INFO - __main__ - Step 26337: {'lr': 0.00046737839217389645, 'samples': 5056704, 'steps': 26336, 'loss/train': 0.6932715773582458}
+08/30/2021 17:53:44 - INFO - __main__ - Step 26338: {'lr': 0.0004673757710758413, 'samples': 5056896, 'steps': 26337, 'loss/train': 1.809666395187378}
+08/30/2021 17:53:46 - INFO - __main__ - Step 26339: {'lr': 0.00046737314987984, 'samples': 5057088, 'steps': 26338, 'loss/train': 1.7099965810775757}
+08/30/2021 17:53:46 - INFO - __main__ - Step 26340: {'lr': 0.0004673705285858938, 'samples': 5057280, 'steps': 26339, 'loss/train': 1.4753388166427612}
+08/30/2021 17:53:47 - INFO - __main__ - Step 26341: {'lr': 0.00046736790719400373, 'samples': 5057472, 'steps': 26340, 'loss/train': 1.5072438716888428}
+08/30/2021 17:53:47 - INFO - __main__ - Step 26342: {'lr': 0.000467365285704171, 'samples': 5057664, 'steps': 26341, 'loss/train': 1.5418766736984253}
+08/30/2021 17:53:48 - INFO - __main__ - Step 26343: {'lr': 0.00046736266411639694, 'samples': 5057856, 'steps': 26342, 'loss/train': 1.4100966453552246}
+08/30/2021 17:53:49 - INFO - __main__ - Step 26344: {'lr': 0.00046736004243068255, 'samples': 5058048, 'steps': 26343, 'loss/train': 0.12519323825836182}
+08/30/2021 17:53:50 - INFO - __main__ - Step 26345: {'lr': 0.00046735742064702904, 'samples': 5058240, 'steps': 26344, 'loss/train': 1.8921748399734497}
+08/30/2021 17:53:50 - INFO - __main__ - Step 26346: {'lr': 0.00046735479876543765, 'samples': 5058432, 'steps': 26345, 'loss/train': 1.4676744937896729}
+08/30/2021 17:53:51 - INFO - __main__ - Step 26347: {'lr': 0.00046735217678590957, 'samples': 5058624, 'steps': 26346, 'loss/train': 0.17673909664154053}
+08/30/2021 17:53:51 - INFO - __main__ - Step 26348: {'lr': 0.00046734955470844594, 'samples': 5058816, 'steps': 26347, 'loss/train': 1.8397572040557861}
+08/30/2021 17:53:51 - INFO - __main__ - Step 26349: {'lr': 0.00046734693253304795, 'samples': 5059008, 'steps': 26348, 'loss/train': 1.236518144607544}
+08/30/2021 17:53:53 - INFO - __main__ - Step 26350: {'lr': 0.0004673443102597168, 'samples': 5059200, 'steps': 26349, 'loss/train': 1.5384405851364136}
+08/30/2021 17:53:53 - INFO - __main__ - Step 26351: {'lr': 0.00046734168788845363, 'samples': 5059392, 'steps': 26350, 'loss/train': 1.015964150428772}
+08/30/2021 17:53:54 - INFO - __main__ - Step 26352: {'lr': 0.00046733906541925963, 'samples': 5059584, 'steps': 26351, 'loss/train': 0.9438610076904297}
+08/30/2021 17:53:54 - INFO - __main__ - Step 26353: {'lr': 0.00046733644285213604, 'samples': 5059776, 'steps': 26352, 'loss/train': 1.6680570840835571}
+08/30/2021 17:53:54 - INFO - __main__ - Step 26354: {'lr': 0.00046733382018708405, 'samples': 5059968, 'steps': 26353, 'loss/train': 1.1922476291656494}
+08/30/2021 17:53:56 - INFO - __main__ - Step 26355: {'lr': 0.00046733119742410476, 'samples': 5060160, 'steps': 26354, 'loss/train': 1.4690243005752563}
+08/30/2021 17:53:56 - INFO - __main__ - Step 26356: {'lr': 0.0004673285745631993, 'samples': 5060352, 'steps': 26355, 'loss/train': 1.4539414644241333}
+08/30/2021 17:53:57 - INFO - __main__ - Step 26357: {'lr': 0.000467325951604369, 'samples': 5060544, 'steps': 26356, 'loss/train': 2.1293528079986572}
+08/30/2021 17:53:57 - INFO - __main__ - Step 26358: {'lr': 0.00046732332854761507, 'samples': 5060736, 'steps': 26357, 'loss/train': 1.4316747188568115}
+08/30/2021 17:53:57 - INFO - __main__ - Step 26359: {'lr': 0.00046732070539293847, 'samples': 5060928, 'steps': 26358, 'loss/train': 1.9339829683303833}
+08/30/2021 17:53:59 - INFO - __main__ - Step 26360: {'lr': 0.0004673180821403405, 'samples': 5061120, 'steps': 26359, 'loss/train': 3.5390784740448}
+08/30/2021 17:53:59 - INFO - __main__ - Step 26361: {'lr': 0.00046731545878982253, 'samples': 5061312, 'steps': 26360, 'loss/train': 1.214211344718933}
+08/30/2021 17:54:00 - INFO - __main__ - Step 26362: {'lr': 0.0004673128353413854, 'samples': 5061504, 'steps': 26361, 'loss/train': 1.7859796285629272}
+08/30/2021 17:54:00 - INFO - __main__ - Step 26363: {'lr': 0.00046731021179503054, 'samples': 5061696, 'steps': 26362, 'loss/train': 5.96531343460083}
+08/30/2021 17:54:00 - INFO - __main__ - Step 26364: {'lr': 0.00046730758815075903, 'samples': 5061888, 'steps': 26363, 'loss/train': 1.6871147155761719}
+08/30/2021 17:54:01 - INFO - __main__ - Step 26365: {'lr': 0.0004673049644085721, 'samples': 5062080, 'steps': 26364, 'loss/train': 1.836182951927185}
+08/30/2021 17:54:02 - INFO - __main__ - Step 26366: {'lr': 0.00046730234056847084, 'samples': 5062272, 'steps': 26365, 'loss/train': 1.4646716117858887}
+08/30/2021 17:54:03 - INFO - __main__ - Step 26367: {'lr': 0.00046729971663045654, 'samples': 5062464, 'steps': 26366, 'loss/train': 0.11875174939632416}
+08/30/2021 17:54:03 - INFO - __main__ - Step 26368: {'lr': 0.00046729709259453033, 'samples': 5062656, 'steps': 26367, 'loss/train': 0.17010241746902466}
+08/30/2021 17:54:04 - INFO - __main__ - Step 26369: {'lr': 0.0004672944684606934, 'samples': 5062848, 'steps': 26368, 'loss/train': 2.159951686859131}
+08/30/2021 17:54:04 - INFO - __main__ - Step 26370: {'lr': 0.000467291844228947, 'samples': 5063040, 'steps': 26369, 'loss/train': 1.3013253211975098}
+08/30/2021 17:54:05 - INFO - __main__ - Step 26371: {'lr': 0.00046728921989929215, 'samples': 5063232, 'steps': 26370, 'loss/train': 1.547684669494629}
+08/30/2021 17:54:06 - INFO - __main__ - Step 26372: {'lr': 0.0004672865954717301, 'samples': 5063424, 'steps': 26371, 'loss/train': 1.6107161045074463}
+08/30/2021 17:54:06 - INFO - __main__ - Step 26373: {'lr': 0.00046728397094626217, 'samples': 5063616, 'steps': 26372, 'loss/train': 1.6851725578308105}
+08/30/2021 17:54:06 - INFO - __main__ - Step 26374: {'lr': 0.0004672813463228894, 'samples': 5063808, 'steps': 26373, 'loss/train': 1.5158199071884155}
+08/30/2021 17:54:07 - INFO - __main__ - Step 26375: {'lr': 0.00046727872160161305, 'samples': 5064000, 'steps': 26374, 'loss/train': 1.4802353382110596}
+08/30/2021 17:54:09 - INFO - __main__ - Step 26376: {'lr': 0.0004672760967824342, 'samples': 5064192, 'steps': 26375, 'loss/train': 1.8279871940612793}
+08/30/2021 17:54:09 - INFO - __main__ - Step 26377: {'lr': 0.0004672734718653541, 'samples': 5064384, 'steps': 26376, 'loss/train': 0.11590936779975891}
+08/30/2021 17:54:10 - INFO - __main__ - Step 26378: {'lr': 0.00046727084685037394, 'samples': 5064576, 'steps': 26377, 'loss/train': 3.5200276374816895}
+08/30/2021 17:54:10 - INFO - __main__ - Step 26379: {'lr': 0.00046726822173749497, 'samples': 5064768, 'steps': 26378, 'loss/train': 1.3514212369918823}
+08/30/2021 17:54:11 - INFO - __main__ - Step 26380: {'lr': 0.0004672655965267182, 'samples': 5064960, 'steps': 26379, 'loss/train': 1.2324953079223633}
+08/30/2021 17:54:12 - INFO - __main__ - Step 26381: {'lr': 0.0004672629712180448, 'samples': 5065152, 'steps': 26380, 'loss/train': 1.6526532173156738}
+08/30/2021 17:54:13 - INFO - __main__ - Step 26382: {'lr': 0.00046726034581147624, 'samples': 5065344, 'steps': 26381, 'loss/train': 0.951452910900116}
+08/30/2021 17:54:13 - INFO - __main__ - Step 26383: {'lr': 0.0004672577203070135, 'samples': 5065536, 'steps': 26382, 'loss/train': 1.8518738746643066}
+08/30/2021 17:54:13 - INFO - __main__ - Step 26384: {'lr': 0.0004672550947046577, 'samples': 5065728, 'steps': 26383, 'loss/train': 0.9917610883712769}
+08/30/2021 17:54:14 - INFO - __main__ - Step 26385: {'lr': 0.0004672524690044102, 'samples': 5065920, 'steps': 26384, 'loss/train': 2.4184682369232178}
+08/30/2021 17:54:14 - INFO - __main__ - Step 26386: {'lr': 0.000467249843206272, 'samples': 5066112, 'steps': 26385, 'loss/train': 1.4285353422164917}
+08/30/2021 17:54:15 - INFO - __main__ - Step 26387: {'lr': 0.00046724721731024446, 'samples': 5066304, 'steps': 26386, 'loss/train': 1.8097509145736694}
+08/30/2021 17:54:16 - INFO - __main__ - Step 26388: {'lr': 0.00046724459131632854, 'samples': 5066496, 'steps': 26387, 'loss/train': 1.3934749364852905}
+08/30/2021 17:54:16 - INFO - __main__ - Step 26389: {'lr': 0.00046724196522452565, 'samples': 5066688, 'steps': 26388, 'loss/train': 1.9031007289886475}
+08/30/2021 17:54:17 - INFO - __main__ - Step 26390: {'lr': 0.00046723933903483687, 'samples': 5066880, 'steps': 26389, 'loss/train': 1.7344425916671753}
+08/30/2021 17:54:17 - INFO - __main__ - Step 26391: {'lr': 0.00046723671274726344, 'samples': 5067072, 'steps': 26390, 'loss/train': 1.6269930601119995}
+08/30/2021 17:54:18 - INFO - __main__ - Step 26392: {'lr': 0.00046723408636180645, 'samples': 5067264, 'steps': 26391, 'loss/train': 1.904179334640503}
+08/30/2021 17:54:19 - INFO - __main__ - Step 26393: {'lr': 0.00046723145987846715, 'samples': 5067456, 'steps': 26392, 'loss/train': 1.6348963975906372}
+08/30/2021 17:54:19 - INFO - __main__ - Step 26394: {'lr': 0.00046722883329724667, 'samples': 5067648, 'steps': 26393, 'loss/train': 1.3784867525100708}
+08/30/2021 17:54:19 - INFO - __main__ - Step 26395: {'lr': 0.0004672262066181463, 'samples': 5067840, 'steps': 26394, 'loss/train': 1.7997623682022095}
+08/30/2021 17:54:20 - INFO - __main__ - Step 26396: {'lr': 0.00046722357984116717, 'samples': 5068032, 'steps': 26395, 'loss/train': 1.4385432004928589}
+08/30/2021 17:54:21 - INFO - __main__ - Step 26397: {'lr': 0.0004672209529663103, 'samples': 5068224, 'steps': 26396, 'loss/train': 1.9246010780334473}
+08/30/2021 17:54:22 - INFO - __main__ - Step 26398: {'lr': 0.00046721832599357717, 'samples': 5068416, 'steps': 26397, 'loss/train': 1.470102071762085}
+08/30/2021 17:54:22 - INFO - __main__ - Step 26399: {'lr': 0.00046721569892296875, 'samples': 5068608, 'steps': 26398, 'loss/train': 1.6469706296920776}
+08/30/2021 17:54:22 - INFO - __main__ - Step 26400: {'lr': 0.00046721307175448626, 'samples': 5068800, 'steps': 26399, 'loss/train': 1.223879337310791}
+08/30/2021 17:54:23 - INFO - __main__ - Step 26401: {'lr': 0.000467210444488131, 'samples': 5068992, 'steps': 26400, 'loss/train': 0.6934109330177307}
+08/30/2021 17:54:25 - INFO - __main__ - Step 26402: {'lr': 0.000467207817123904, 'samples': 5069184, 'steps': 26401, 'loss/train': 1.8567276000976562}
+08/30/2021 17:54:25 - INFO - __main__ - Step 26403: {'lr': 0.0004672051896618065, 'samples': 5069376, 'steps': 26402, 'loss/train': 0.9742704033851624}
+08/30/2021 17:54:25 - INFO - __main__ - Step 26404: {'lr': 0.0004672025621018397, 'samples': 5069568, 'steps': 26403, 'loss/train': 0.0499262660741806}
+08/30/2021 17:54:26 - INFO - __main__ - Step 26405: {'lr': 0.00046719993444400477, 'samples': 5069760, 'steps': 26404, 'loss/train': 1.4353646039962769}
+08/30/2021 17:54:26 - INFO - __main__ - Step 26406: {'lr': 0.00046719730668830293, 'samples': 5069952, 'steps': 26405, 'loss/train': 1.8499877452850342}
+08/30/2021 17:54:27 - INFO - __main__ - Step 26407: {'lr': 0.0004671946788347353, 'samples': 5070144, 'steps': 26406, 'loss/train': 1.4248777627944946}
+08/30/2021 17:54:27 - INFO - __main__ - Step 26408: {'lr': 0.00046719205088330317, 'samples': 5070336, 'steps': 26407, 'loss/train': 1.6838206052780151}
+08/30/2021 17:54:28 - INFO - __main__ - Step 26409: {'lr': 0.0004671894228340076, 'samples': 5070528, 'steps': 26408, 'loss/train': 1.920997977256775}
+08/30/2021 17:54:29 - INFO - __main__ - Step 26410: {'lr': 0.0004671867946868499, 'samples': 5070720, 'steps': 26409, 'loss/train': 1.8226802349090576}
+08/30/2021 17:54:29 - INFO - __main__ - Step 26411: {'lr': 0.000467184166441831, 'samples': 5070912, 'steps': 26410, 'loss/train': 1.7642099857330322}
+08/30/2021 17:54:29 - INFO - __main__ - Step 26412: {'lr': 0.0004671815380989525, 'samples': 5071104, 'steps': 26411, 'loss/train': 0.9808248281478882}
+08/30/2021 17:54:30 - INFO - __main__ - Step 26413: {'lr': 0.0004671789096582152, 'samples': 5071296, 'steps': 26412, 'loss/train': 1.769890546798706}
+08/30/2021 17:54:32 - INFO - __main__ - Step 26414: {'lr': 0.00046717628111962045, 'samples': 5071488, 'steps': 26413, 'loss/train': 1.6621394157409668}
+08/30/2021 17:54:32 - INFO - __main__ - Step 26415: {'lr': 0.00046717365248316947, 'samples': 5071680, 'steps': 26414, 'loss/train': 1.7568658590316772}
+08/30/2021 17:54:33 - INFO - __main__ - Step 26416: {'lr': 0.00046717102374886334, 'samples': 5071872, 'steps': 26415, 'loss/train': 0.8884730935096741}
+08/30/2021 17:54:33 - INFO - __main__ - Step 26417: {'lr': 0.0004671683949167033, 'samples': 5072064, 'steps': 26416, 'loss/train': 1.5018233060836792}
+08/30/2021 17:54:33 - INFO - __main__ - Step 26418: {'lr': 0.0004671657659866906, 'samples': 5072256, 'steps': 26417, 'loss/train': 2.1330373287200928}
+08/30/2021 17:54:34 - INFO - __main__ - Step 26419: {'lr': 0.00046716313695882626, 'samples': 5072448, 'steps': 26418, 'loss/train': 0.3153764307498932}
+08/30/2021 17:54:36 - INFO - __main__ - Step 26420: {'lr': 0.00046716050783311166, 'samples': 5072640, 'steps': 26419, 'loss/train': 0.04831329733133316}
+08/30/2021 17:54:36 - INFO - __main__ - Step 26421: {'lr': 0.00046715787860954785, 'samples': 5072832, 'steps': 26420, 'loss/train': 1.573830008506775}
+08/30/2021 17:54:36 - INFO - __main__ - Step 26422: {'lr': 0.000467155249288136, 'samples': 5073024, 'steps': 26421, 'loss/train': 1.1698150634765625}
+08/30/2021 17:54:37 - INFO - __main__ - Step 26423: {'lr': 0.00046715261986887734, 'samples': 5073216, 'steps': 26422, 'loss/train': 1.5478065013885498}
+08/30/2021 17:54:37 - INFO - __main__ - Step 26424: {'lr': 0.0004671499903517732, 'samples': 5073408, 'steps': 26423, 'loss/train': 1.3033256530761719}
+08/30/2021 17:54:39 - INFO - __main__ - Step 26425: {'lr': 0.00046714736073682453, 'samples': 5073600, 'steps': 26424, 'loss/train': 0.21836160123348236}
+08/30/2021 17:54:39 - INFO - __main__ - Step 26426: {'lr': 0.00046714473102403255, 'samples': 5073792, 'steps': 26425, 'loss/train': 1.481293797492981}
+08/30/2021 17:54:39 - INFO - __main__ - Step 26427: {'lr': 0.0004671421012133986, 'samples': 5073984, 'steps': 26426, 'loss/train': 1.5887008905410767}
+08/30/2021 17:54:40 - INFO - __main__ - Step 26428: {'lr': 0.00046713947130492373, 'samples': 5074176, 'steps': 26427, 'loss/train': 1.770939826965332}
+08/30/2021 17:54:40 - INFO - __main__ - Step 26429: {'lr': 0.0004671368412986091, 'samples': 5074368, 'steps': 26428, 'loss/train': 1.5196409225463867}
+08/30/2021 17:54:43 - INFO - __main__ - Step 26430: {'lr': 0.0004671342111944561, 'samples': 5074560, 'steps': 26429, 'loss/train': 1.2715877294540405}
+08/30/2021 17:54:44 - INFO - __main__ - Step 26431: {'lr': 0.00046713158099246564, 'samples': 5074752, 'steps': 26430, 'loss/train': 1.879807710647583}
+08/30/2021 17:54:44 - INFO - __main__ - Step 26432: {'lr': 0.00046712895069263917, 'samples': 5074944, 'steps': 26431, 'loss/train': 1.8316450119018555}
+08/30/2021 17:54:44 - INFO - __main__ - Step 26433: {'lr': 0.00046712632029497766, 'samples': 5075136, 'steps': 26432, 'loss/train': 1.1785908937454224}
+08/30/2021 17:54:45 - INFO - __main__ - Step 26434: {'lr': 0.0004671236897994824, 'samples': 5075328, 'steps': 26433, 'loss/train': 1.2271547317504883}
+08/30/2021 17:54:45 - INFO - __main__ - Step 26435: {'lr': 0.00046712105920615455, 'samples': 5075520, 'steps': 26434, 'loss/train': 2.026353120803833}
+08/30/2021 17:54:45 - INFO - __main__ - Step 26436: {'lr': 0.00046711842851499533, 'samples': 5075712, 'steps': 26435, 'loss/train': 3.067622661590576}
+08/30/2021 17:54:46 - INFO - __main__ - Step 26437: {'lr': 0.0004671157977260059, 'samples': 5075904, 'steps': 26436, 'loss/train': 1.6393345594406128}
+08/30/2021 17:54:47 - INFO - __main__ - Step 26438: {'lr': 0.0004671131668391874, 'samples': 5076096, 'steps': 26437, 'loss/train': 0.8563994765281677}
+08/30/2021 17:54:48 - INFO - __main__ - Step 26439: {'lr': 0.00046711053585454104, 'samples': 5076288, 'steps': 26438, 'loss/train': 1.2317432165145874}
+08/30/2021 17:54:48 - INFO - __main__ - Step 26440: {'lr': 0.0004671079047720681, 'samples': 5076480, 'steps': 26439, 'loss/train': 1.503592610359192}
+08/30/2021 17:54:49 - INFO - __main__ - Step 26441: {'lr': 0.00046710527359176957, 'samples': 5076672, 'steps': 26440, 'loss/train': 1.7058897018432617}
+08/30/2021 17:54:49 - INFO - __main__ - Step 26442: {'lr': 0.0004671026423136469, 'samples': 5076864, 'steps': 26441, 'loss/train': 1.1538952589035034}
+08/30/2021 17:54:50 - INFO - __main__ - Step 26443: {'lr': 0.00046710001093770107, 'samples': 5077056, 'steps': 26442, 'loss/train': 1.1952552795410156}
+08/30/2021 17:54:51 - INFO - __main__ - Step 26444: {'lr': 0.0004670973794639333, 'samples': 5077248, 'steps': 26443, 'loss/train': 1.5073482990264893}
+08/30/2021 17:54:51 - INFO - __main__ - Step 26445: {'lr': 0.0004670947478923447, 'samples': 5077440, 'steps': 26444, 'loss/train': 1.3746172189712524}
+08/30/2021 17:54:52 - INFO - __main__ - Step 26446: {'lr': 0.00046709211622293677, 'samples': 5077632, 'steps': 26445, 'loss/train': 1.3588981628417969}
+08/30/2021 17:54:52 - INFO - __main__ - Step 26447: {'lr': 0.00046708948445571037, 'samples': 5077824, 'steps': 26446, 'loss/train': 1.8258367776870728}
+08/30/2021 17:54:54 - INFO - __main__ - Step 26448: {'lr': 0.0004670868525906668, 'samples': 5078016, 'steps': 26447, 'loss/train': 1.0081768035888672}
+08/30/2021 17:54:55 - INFO - __main__ - Step 26449: {'lr': 0.00046708422062780725, 'samples': 5078208, 'steps': 26448, 'loss/train': 1.5623821020126343}
+08/30/2021 17:54:55 - INFO - __main__ - Step 26450: {'lr': 0.0004670815885671329, 'samples': 5078400, 'steps': 26449, 'loss/train': 1.381220817565918}
+08/30/2021 17:54:56 - INFO - __main__ - Step 26451: {'lr': 0.00046707895640864494, 'samples': 5078592, 'steps': 26450, 'loss/train': 0.7613924145698547}
+08/30/2021 17:54:56 - INFO - __main__ - Step 26452: {'lr': 0.0004670763241523446, 'samples': 5078784, 'steps': 26451, 'loss/train': 0.6841173768043518}
+08/30/2021 17:54:56 - INFO - __main__ - Step 26453: {'lr': 0.00046707369179823294, 'samples': 5078976, 'steps': 26452, 'loss/train': 0.5758198499679565}
+08/30/2021 17:54:57 - INFO - __main__ - Step 26454: {'lr': 0.00046707105934631123, 'samples': 5079168, 'steps': 26453, 'loss/train': 0.5321375727653503}
+08/30/2021 17:54:58 - INFO - __main__ - Step 26455: {'lr': 0.00046706842679658067, 'samples': 5079360, 'steps': 26454, 'loss/train': 1.0598952770233154}
+08/30/2021 17:54:59 - INFO - __main__ - Step 26456: {'lr': 0.0004670657941490425, 'samples': 5079552, 'steps': 26455, 'loss/train': 0.2264997810125351}
+08/30/2021 17:54:59 - INFO - __main__ - Step 26457: {'lr': 0.00046706316140369774, 'samples': 5079744, 'steps': 26456, 'loss/train': 1.4735705852508545}
+08/30/2021 17:54:59 - INFO - __main__ - Step 26458: {'lr': 0.0004670605285605477, 'samples': 5079936, 'steps': 26457, 'loss/train': 1.39555025100708}
+08/30/2021 17:55:00 - INFO - __main__ - Step 26459: {'lr': 0.0004670578956195935, 'samples': 5080128, 'steps': 26458, 'loss/train': 1.5469558238983154}
+08/30/2021 17:55:01 - INFO - __main__ - Step 26460: {'lr': 0.00046705526258083643, 'samples': 5080320, 'steps': 26459, 'loss/train': 1.3662614822387695}
+08/30/2021 17:55:02 - INFO - __main__ - Step 26461: {'lr': 0.0004670526294442775, 'samples': 5080512, 'steps': 26460, 'loss/train': 1.7535197734832764}
+08/30/2021 17:55:02 - INFO - __main__ - Step 26462: {'lr': 0.0004670499962099181, 'samples': 5080704, 'steps': 26461, 'loss/train': 2.2103404998779297}
+08/30/2021 17:55:02 - INFO - __main__ - Step 26463: {'lr': 0.0004670473628777593, 'samples': 5080896, 'steps': 26462, 'loss/train': 1.1556077003479004}
+08/30/2021 17:55:03 - INFO - __main__ - Step 26464: {'lr': 0.0004670447294478023, 'samples': 5081088, 'steps': 26463, 'loss/train': 1.4666619300842285}
+08/30/2021 17:55:04 - INFO - __main__ - Step 26465: {'lr': 0.0004670420959200483, 'samples': 5081280, 'steps': 26464, 'loss/train': 1.7490825653076172}
+08/30/2021 17:55:05 - INFO - __main__ - Step 26466: {'lr': 0.00046703946229449846, 'samples': 5081472, 'steps': 26465, 'loss/train': 1.3428783416748047}
+08/30/2021 17:55:05 - INFO - __main__ - Step 26467: {'lr': 0.00046703682857115406, 'samples': 5081664, 'steps': 26466, 'loss/train': 1.2313660383224487}
+08/30/2021 17:55:06 - INFO - __main__ - Step 26468: {'lr': 0.0004670341947500161, 'samples': 5081856, 'steps': 26467, 'loss/train': 1.5175172090530396}
+08/30/2021 17:55:06 - INFO - __main__ - Step 26469: {'lr': 0.00046703156083108597, 'samples': 5082048, 'steps': 26468, 'loss/train': 1.4003242254257202}
+08/30/2021 17:55:07 - INFO - __main__ - Step 26470: {'lr': 0.0004670289268143647, 'samples': 5082240, 'steps': 26469, 'loss/train': 0.4863508343696594}
+08/30/2021 17:55:08 - INFO - __main__ - Step 26471: {'lr': 0.0004670262926998536, 'samples': 5082432, 'steps': 26470, 'loss/train': 1.4212708473205566}
+08/30/2021 17:55:08 - INFO - __main__ - Step 26472: {'lr': 0.00046702365848755377, 'samples': 5082624, 'steps': 26471, 'loss/train': 1.6410430669784546}
+08/30/2021 17:55:08 - INFO - __main__ - Step 26473: {'lr': 0.0004670210241774664, 'samples': 5082816, 'steps': 26472, 'loss/train': 1.008784294128418}
+08/30/2021 17:55:09 - INFO - __main__ - Step 26474: {'lr': 0.0004670183897695928, 'samples': 5083008, 'steps': 26473, 'loss/train': 1.7928823232650757}
+08/30/2021 17:55:10 - INFO - __main__ - Step 26475: {'lr': 0.00046701575526393395, 'samples': 5083200, 'steps': 26474, 'loss/train': 1.339598536491394}
+08/30/2021 17:55:11 - INFO - __main__ - Step 26476: {'lr': 0.00046701312066049126, 'samples': 5083392, 'steps': 26475, 'loss/train': 1.4918270111083984}
+08/30/2021 17:55:11 - INFO - __main__ - Step 26477: {'lr': 0.00046701048595926574, 'samples': 5083584, 'steps': 26476, 'loss/train': 2.120662212371826}
+08/30/2021 17:55:12 - INFO - __main__ - Step 26478: {'lr': 0.00046700785116025867, 'samples': 5083776, 'steps': 26477, 'loss/train': 1.672579050064087}
+08/30/2021 17:55:12 - INFO - __main__ - Step 26479: {'lr': 0.0004670052162634712, 'samples': 5083968, 'steps': 26478, 'loss/train': 1.7572641372680664}
+08/30/2021 17:55:12 - INFO - __main__ - Step 26480: {'lr': 0.0004670025812689045, 'samples': 5084160, 'steps': 26479, 'loss/train': 1.507641315460205}
+08/30/2021 17:55:14 - INFO - __main__ - Step 26481: {'lr': 0.00046699994617655985, 'samples': 5084352, 'steps': 26480, 'loss/train': 1.281359314918518}
+08/30/2021 17:55:14 - INFO - __main__ - Step 26482: {'lr': 0.0004669973109864383, 'samples': 5084544, 'steps': 26481, 'loss/train': 1.397874116897583}
+08/30/2021 17:55:14 - INFO - __main__ - Step 26483: {'lr': 0.00046699467569854115, 'samples': 5084736, 'steps': 26482, 'loss/train': 1.1106603145599365}
+08/30/2021 17:55:15 - INFO - __main__ - Step 26484: {'lr': 0.0004669920403128696, 'samples': 5084928, 'steps': 26483, 'loss/train': 1.7543003559112549}
+08/30/2021 17:55:15 - INFO - __main__ - Step 26485: {'lr': 0.00046698940482942466, 'samples': 5085120, 'steps': 26484, 'loss/train': 1.2458912134170532}
+08/30/2021 17:55:17 - INFO - __main__ - Step 26486: {'lr': 0.0004669867692482077, 'samples': 5085312, 'steps': 26485, 'loss/train': 1.9360105991363525}
+08/30/2021 17:55:18 - INFO - __main__ - Step 26487: {'lr': 0.00046698413356921985, 'samples': 5085504, 'steps': 26486, 'loss/train': 0.9060123562812805}
+08/30/2021 17:55:18 - INFO - __main__ - Step 26488: {'lr': 0.00046698149779246235, 'samples': 5085696, 'steps': 26487, 'loss/train': 1.7709970474243164}
+08/30/2021 17:55:18 - INFO - __main__ - Step 26489: {'lr': 0.0004669788619179363, 'samples': 5085888, 'steps': 26488, 'loss/train': 1.8481642007827759}
+08/30/2021 17:55:19 - INFO - __main__ - Step 26490: {'lr': 0.0004669762259456429, 'samples': 5086080, 'steps': 26489, 'loss/train': 1.6907516717910767}
+08/30/2021 17:55:20 - INFO - __main__ - Step 26491: {'lr': 0.00046697358987558336, 'samples': 5086272, 'steps': 26490, 'loss/train': 1.2334203720092773}
+08/30/2021 17:55:21 - INFO - __main__ - Step 26492: {'lr': 0.0004669709537077589, 'samples': 5086464, 'steps': 26491, 'loss/train': 1.840136170387268}
+08/30/2021 17:55:21 - INFO - __main__ - Step 26493: {'lr': 0.00046696831744217065, 'samples': 5086656, 'steps': 26492, 'loss/train': 0.9647053480148315}
+08/30/2021 17:55:21 - INFO - __main__ - Step 26494: {'lr': 0.0004669656810788199, 'samples': 5086848, 'steps': 26493, 'loss/train': 1.555384635925293}
+08/30/2021 17:55:22 - INFO - __main__ - Step 26495: {'lr': 0.0004669630446177077, 'samples': 5087040, 'steps': 26494, 'loss/train': 0.9002858400344849}
+08/30/2021 17:55:24 - INFO - __main__ - Step 26496: {'lr': 0.0004669604080588352, 'samples': 5087232, 'steps': 26495, 'loss/train': 2.0909271240234375}
+08/30/2021 17:55:24 - INFO - __main__ - Step 26497: {'lr': 0.0004669577714022039, 'samples': 5087424, 'steps': 26496, 'loss/train': 1.7274521589279175}
+08/30/2021 17:55:24 - INFO - __main__ - Step 26498: {'lr': 0.00046695513464781456, 'samples': 5087616, 'steps': 26497, 'loss/train': 1.4134820699691772}
+08/30/2021 17:55:25 - INFO - __main__ - Step 26499: {'lr': 0.00046695249779566875, 'samples': 5087808, 'steps': 26498, 'loss/train': 1.7090868949890137}
+08/30/2021 17:55:25 - INFO - __main__ - Step 26500: {'lr': 0.0004669498608457674, 'samples': 5088000, 'steps': 26499, 'loss/train': 2.725168466567993}
+08/30/2021 17:55:25 - INFO - __main__ - Step 26501: {'lr': 0.0004669472237981118, 'samples': 5088192, 'steps': 26500, 'loss/train': 1.5974403619766235}
+08/30/2021 17:55:27 - INFO - __main__ - Step 26502: {'lr': 0.00046694458665270315, 'samples': 5088384, 'steps': 26501, 'loss/train': 1.7336952686309814}
+08/30/2021 17:55:28 - INFO - __main__ - Step 26503: {'lr': 0.0004669419494095426, 'samples': 5088576, 'steps': 26502, 'loss/train': 1.2236595153808594}
+08/30/2021 17:55:28 - INFO - __main__ - Step 26504: {'lr': 0.0004669393120686314, 'samples': 5088768, 'steps': 26503, 'loss/train': 1.8604410886764526}
+08/30/2021 17:55:28 - INFO - __main__ - Step 26505: {'lr': 0.0004669366746299707, 'samples': 5088960, 'steps': 26504, 'loss/train': 4.852655410766602}
+08/30/2021 17:55:29 - INFO - __main__ - Step 26506: {'lr': 0.00046693403709356163, 'samples': 5089152, 'steps': 26505, 'loss/train': 1.74601149559021}
+08/30/2021 17:55:29 - INFO - __main__ - Step 26507: {'lr': 0.00046693139945940546, 'samples': 5089344, 'steps': 26506, 'loss/train': 1.7411202192306519}
+08/30/2021 17:55:31 - INFO - __main__ - Step 26508: {'lr': 0.0004669287617275033, 'samples': 5089536, 'steps': 26507, 'loss/train': 2.4722275733947754}
+08/30/2021 17:55:31 - INFO - __main__ - Step 26509: {'lr': 0.0004669261238978564, 'samples': 5089728, 'steps': 26508, 'loss/train': 1.3681408166885376}
+08/30/2021 17:55:31 - INFO - __main__ - Step 26510: {'lr': 0.00046692348597046596, 'samples': 5089920, 'steps': 26509, 'loss/train': 1.345752239227295}
+08/30/2021 17:55:32 - INFO - __main__ - Step 26511: {'lr': 0.0004669208479453332, 'samples': 5090112, 'steps': 26510, 'loss/train': 1.8200063705444336}
+08/30/2021 17:55:32 - INFO - __main__ - Step 26512: {'lr': 0.00046691820982245913, 'samples': 5090304, 'steps': 26511, 'loss/train': 1.7139945030212402}
+08/30/2021 17:55:34 - INFO - __main__ - Step 26513: {'lr': 0.00046691557160184516, 'samples': 5090496, 'steps': 26512, 'loss/train': 1.4040721654891968}
+08/30/2021 17:55:34 - INFO - __main__ - Step 26514: {'lr': 0.0004669129332834923, 'samples': 5090688, 'steps': 26513, 'loss/train': 1.6137622594833374}
+08/30/2021 17:55:34 - INFO - __main__ - Step 26515: {'lr': 0.0004669102948674019, 'samples': 5090880, 'steps': 26514, 'loss/train': 1.3544131517410278}
+08/30/2021 17:55:35 - INFO - __main__ - Step 26516: {'lr': 0.000466907656353575, 'samples': 5091072, 'steps': 26515, 'loss/train': 1.6316208839416504}
+08/30/2021 17:55:35 - INFO - __main__ - Step 26517: {'lr': 0.0004669050177420129, 'samples': 5091264, 'steps': 26516, 'loss/train': 1.7549480199813843}
+08/30/2021 17:55:35 - INFO - __main__ - Step 26518: {'lr': 0.0004669023790327168, 'samples': 5091456, 'steps': 26517, 'loss/train': 1.9351155757904053}
+08/30/2021 17:55:37 - INFO - __main__ - Step 26519: {'lr': 0.0004668997402256877, 'samples': 5091648, 'steps': 26518, 'loss/train': 1.75971519947052}
+08/30/2021 17:55:37 - INFO - __main__ - Step 26520: {'lr': 0.00046689710132092704, 'samples': 5091840, 'steps': 26519, 'loss/train': 1.475289225578308}
+08/30/2021 17:55:38 - INFO - __main__ - Step 26521: {'lr': 0.00046689446231843585, 'samples': 5092032, 'steps': 26520, 'loss/train': 0.4546389579772949}
+08/30/2021 17:55:38 - INFO - __main__ - Step 26522: {'lr': 0.0004668918232182153, 'samples': 5092224, 'steps': 26521, 'loss/train': 1.20957612991333}
+08/30/2021 17:55:38 - INFO - __main__ - Step 26523: {'lr': 0.0004668891840202668, 'samples': 5092416, 'steps': 26522, 'loss/train': 1.6378568410873413}
+08/30/2021 17:55:40 - INFO - __main__ - Step 26524: {'lr': 0.00046688654472459124, 'samples': 5092608, 'steps': 26523, 'loss/train': 1.5544283390045166}
+08/30/2021 17:55:41 - INFO - __main__ - Step 26525: {'lr': 0.00046688390533119003, 'samples': 5092800, 'steps': 26524, 'loss/train': 1.7190724611282349}
+08/30/2021 17:55:41 - INFO - __main__ - Step 26526: {'lr': 0.00046688126584006425, 'samples': 5092992, 'steps': 26525, 'loss/train': 2.415898323059082}
+08/30/2021 17:55:41 - INFO - __main__ - Step 26527: {'lr': 0.00046687862625121505, 'samples': 5093184, 'steps': 26526, 'loss/train': 1.759015679359436}
+08/30/2021 17:55:42 - INFO - __main__ - Step 26528: {'lr': 0.0004668759865646438, 'samples': 5093376, 'steps': 26527, 'loss/train': 0.3155175745487213}
+08/30/2021 17:55:43 - INFO - __main__ - Step 26529: {'lr': 0.00046687334678035153, 'samples': 5093568, 'steps': 26528, 'loss/train': 1.1815344095230103}
+08/30/2021 17:55:44 - INFO - __main__ - Step 26530: {'lr': 0.00046687070689833943, 'samples': 5093760, 'steps': 26529, 'loss/train': 1.4764231443405151}
+08/30/2021 17:55:44 - INFO - __main__ - Step 26531: {'lr': 0.00046686806691860884, 'samples': 5093952, 'steps': 26530, 'loss/train': 1.9032479524612427}
+08/30/2021 17:55:44 - INFO - __main__ - Step 26532: {'lr': 0.00046686542684116073, 'samples': 5094144, 'steps': 26531, 'loss/train': 1.7096304893493652}
+08/30/2021 17:55:45 - INFO - __main__ - Step 26533: {'lr': 0.00046686278666599647, 'samples': 5094336, 'steps': 26532, 'loss/train': 1.3388385772705078}
+08/30/2021 17:55:46 - INFO - __main__ - Step 26534: {'lr': 0.0004668601463931172, 'samples': 5094528, 'steps': 26533, 'loss/train': 1.315308928489685}
+08/30/2021 17:55:47 - INFO - __main__ - Step 26535: {'lr': 0.00046685750602252406, 'samples': 5094720, 'steps': 26534, 'loss/train': 1.5765104293823242}
+08/30/2021 17:55:47 - INFO - __main__ - Step 26536: {'lr': 0.0004668548655542183, 'samples': 5094912, 'steps': 26535, 'loss/train': 1.4822983741760254}
+08/30/2021 17:55:47 - INFO - __main__ - Step 26537: {'lr': 0.000466852224988201, 'samples': 5095104, 'steps': 26536, 'loss/train': 0.7185746431350708}
+08/30/2021 17:55:48 - INFO - __main__ - Step 26538: {'lr': 0.00046684958432447355, 'samples': 5095296, 'steps': 26537, 'loss/train': 1.265125036239624}
+08/30/2021 17:55:50 - INFO - __main__ - Step 26539: {'lr': 0.00046684694356303693, 'samples': 5095488, 'steps': 26538, 'loss/train': 1.5037517547607422}
+08/30/2021 17:55:50 - INFO - __main__ - Step 26540: {'lr': 0.0004668443027038925, 'samples': 5095680, 'steps': 26539, 'loss/train': 2.094182252883911}
+08/30/2021 17:55:50 - INFO - __main__ - Step 26541: {'lr': 0.00046684166174704134, 'samples': 5095872, 'steps': 26540, 'loss/train': 1.6000418663024902}
+08/30/2021 17:55:51 - INFO - __main__ - Step 26542: {'lr': 0.00046683902069248465, 'samples': 5096064, 'steps': 26541, 'loss/train': 1.3042372465133667}
+08/30/2021 17:55:51 - INFO - __main__ - Step 26543: {'lr': 0.0004668363795402237, 'samples': 5096256, 'steps': 26542, 'loss/train': 1.4274382591247559}
+08/30/2021 17:55:53 - INFO - __main__ - Step 26544: {'lr': 0.00046683373829025954, 'samples': 5096448, 'steps': 26543, 'loss/train': 1.6654459238052368}
+08/30/2021 17:55:53 - INFO - __main__ - Step 26545: {'lr': 0.0004668310969425935, 'samples': 5096640, 'steps': 26544, 'loss/train': 1.9225696325302124}
+08/30/2021 17:55:53 - INFO - __main__ - Step 26546: {'lr': 0.00046682845549722677, 'samples': 5096832, 'steps': 26545, 'loss/train': 1.6828829050064087}
+08/30/2021 17:55:54 - INFO - __main__ - Step 26547: {'lr': 0.0004668258139541604, 'samples': 5097024, 'steps': 26546, 'loss/train': 2.350262403488159}
+08/30/2021 17:55:54 - INFO - __main__ - Step 26548: {'lr': 0.00046682317231339565, 'samples': 5097216, 'steps': 26547, 'loss/train': 1.8005173206329346}
+08/30/2021 17:55:56 - INFO - __main__ - Step 26549: {'lr': 0.00046682053057493377, 'samples': 5097408, 'steps': 26548, 'loss/train': 1.7175638675689697}
+08/30/2021 17:55:56 - INFO - __main__ - Step 26550: {'lr': 0.00046681788873877595, 'samples': 5097600, 'steps': 26549, 'loss/train': 1.4173011779785156}
+08/30/2021 17:55:57 - INFO - __main__ - Step 26551: {'lr': 0.00046681524680492327, 'samples': 5097792, 'steps': 26550, 'loss/train': 2.0777764320373535}
+08/30/2021 17:55:57 - INFO - __main__ - Step 26552: {'lr': 0.00046681260477337693, 'samples': 5097984, 'steps': 26551, 'loss/train': 0.9717393517494202}
+08/30/2021 17:55:57 - INFO - __main__ - Step 26553: {'lr': 0.0004668099626441383, 'samples': 5098176, 'steps': 26552, 'loss/train': 4.609521389007568}
+08/30/2021 17:55:58 - INFO - __main__ - Step 26554: {'lr': 0.00046680732041720836, 'samples': 5098368, 'steps': 26553, 'loss/train': 1.4219341278076172}
+08/30/2021 17:55:59 - INFO - __main__ - Step 26555: {'lr': 0.0004668046780925884, 'samples': 5098560, 'steps': 26554, 'loss/train': 1.711804747581482}
+08/30/2021 17:56:00 - INFO - __main__ - Step 26556: {'lr': 0.0004668020356702796, 'samples': 5098752, 'steps': 26555, 'loss/train': 1.7388359308242798}
+08/30/2021 17:56:00 - INFO - __main__ - Step 26557: {'lr': 0.0004667993931502832, 'samples': 5098944, 'steps': 26556, 'loss/train': 1.4576250314712524}
+08/30/2021 17:56:00 - INFO - __main__ - Step 26558: {'lr': 0.00046679675053260027, 'samples': 5099136, 'steps': 26557, 'loss/train': 2.0638508796691895}
+08/30/2021 17:56:01 - INFO - __main__ - Step 26559: {'lr': 0.00046679410781723206, 'samples': 5099328, 'steps': 26558, 'loss/train': 1.4840946197509766}
+08/30/2021 17:56:02 - INFO - __main__ - Step 26560: {'lr': 0.0004667914650041799, 'samples': 5099520, 'steps': 26559, 'loss/train': 2.2055389881134033}
+08/30/2021 17:56:03 - INFO - __main__ - Step 26561: {'lr': 0.00046678882209344474, 'samples': 5099712, 'steps': 26560, 'loss/train': 1.8977118730545044}
+08/30/2021 17:56:03 - INFO - __main__ - Step 26562: {'lr': 0.00046678617908502785, 'samples': 5099904, 'steps': 26561, 'loss/train': 0.975948691368103}
+08/30/2021 17:56:04 - INFO - __main__ - Step 26563: {'lr': 0.00046678353597893053, 'samples': 5100096, 'steps': 26562, 'loss/train': 0.4861288368701935}
+08/30/2021 17:56:04 - INFO - __main__ - Step 26564: {'lr': 0.0004667808927751539, 'samples': 5100288, 'steps': 26563, 'loss/train': 0.9822503924369812}
+08/30/2021 17:56:06 - INFO - __main__ - Step 26565: {'lr': 0.00046677824947369907, 'samples': 5100480, 'steps': 26564, 'loss/train': 1.2419246435165405}
+08/30/2021 17:56:06 - INFO - __main__ - Step 26566: {'lr': 0.0004667756060745674, 'samples': 5100672, 'steps': 26565, 'loss/train': 1.6193146705627441}
+08/30/2021 17:56:06 - INFO - __main__ - Step 26567: {'lr': 0.0004667729625777599, 'samples': 5100864, 'steps': 26566, 'loss/train': 1.7757670879364014}
+08/30/2021 17:56:07 - INFO - __main__ - Step 26568: {'lr': 0.0004667703189832779, 'samples': 5101056, 'steps': 26567, 'loss/train': 1.699609637260437}
+08/30/2021 17:56:07 - INFO - __main__ - Step 26569: {'lr': 0.00046676767529112254, 'samples': 5101248, 'steps': 26568, 'loss/train': 1.9243919849395752}
+08/30/2021 17:56:07 - INFO - __main__ - Step 26570: {'lr': 0.000466765031501295, 'samples': 5101440, 'steps': 26569, 'loss/train': 1.4580461978912354}
+08/30/2021 17:56:09 - INFO - __main__ - Step 26571: {'lr': 0.0004667623876137965, 'samples': 5101632, 'steps': 26570, 'loss/train': 1.9228307008743286}
+08/30/2021 17:56:09 - INFO - __main__ - Step 26572: {'lr': 0.00046675974362862815, 'samples': 5101824, 'steps': 26571, 'loss/train': 1.4032305479049683}
+08/30/2021 17:56:10 - INFO - __main__ - Step 26573: {'lr': 0.00046675709954579125, 'samples': 5102016, 'steps': 26572, 'loss/train': 1.2667769193649292}
+08/30/2021 17:56:10 - INFO - __main__ - Step 26574: {'lr': 0.0004667544553652869, 'samples': 5102208, 'steps': 26573, 'loss/train': 1.661678671836853}
+08/30/2021 17:56:10 - INFO - __main__ - Step 26575: {'lr': 0.0004667518110871164, 'samples': 5102400, 'steps': 26574, 'loss/train': 0.1847216784954071}
+08/30/2021 17:56:12 - INFO - __main__ - Step 26576: {'lr': 0.0004667491667112809, 'samples': 5102592, 'steps': 26575, 'loss/train': 0.9313610196113586}
+08/30/2021 17:56:12 - INFO - __main__ - Step 26577: {'lr': 0.0004667465222377815, 'samples': 5102784, 'steps': 26576, 'loss/train': 1.1827235221862793}
+08/30/2021 17:56:13 - INFO - __main__ - Step 26578: {'lr': 0.0004667438776666195, 'samples': 5102976, 'steps': 26577, 'loss/train': 1.0463329553604126}
+08/30/2021 17:56:13 - INFO - __main__ - Step 26579: {'lr': 0.00046674123299779603, 'samples': 5103168, 'steps': 26578, 'loss/train': 1.9854336977005005}
+08/30/2021 17:56:13 - INFO - __main__ - Step 26580: {'lr': 0.0004667385882313123, 'samples': 5103360, 'steps': 26579, 'loss/train': 0.7418782711029053}
+08/30/2021 17:56:15 - INFO - __main__ - Step 26581: {'lr': 0.0004667359433671695, 'samples': 5103552, 'steps': 26580, 'loss/train': 1.5804579257965088}
+08/30/2021 17:56:15 - INFO - __main__ - Step 26582: {'lr': 0.0004667332984053689, 'samples': 5103744, 'steps': 26581, 'loss/train': 1.3505744934082031}
+08/30/2021 17:56:16 - INFO - __main__ - Step 26583: {'lr': 0.00046673065334591155, 'samples': 5103936, 'steps': 26582, 'loss/train': 1.6267030239105225}
+08/30/2021 17:56:16 - INFO - __main__ - Step 26584: {'lr': 0.00046672800818879873, 'samples': 5104128, 'steps': 26583, 'loss/train': 1.9608153104782104}
+08/30/2021 17:56:16 - INFO - __main__ - Step 26585: {'lr': 0.0004667253629340316, 'samples': 5104320, 'steps': 26584, 'loss/train': 1.3606011867523193}
+08/30/2021 17:56:17 - INFO - __main__ - Step 26586: {'lr': 0.0004667227175816114, 'samples': 5104512, 'steps': 26585, 'loss/train': 1.891992449760437}
+08/30/2021 17:56:18 - INFO - __main__ - Step 26587: {'lr': 0.0004667200721315393, 'samples': 5104704, 'steps': 26586, 'loss/train': 1.6568644046783447}
+08/30/2021 17:56:19 - INFO - __main__ - Step 26588: {'lr': 0.00046671742658381646, 'samples': 5104896, 'steps': 26587, 'loss/train': 1.5922542810440063}
+08/30/2021 17:56:19 - INFO - __main__ - Step 26589: {'lr': 0.000466714780938444, 'samples': 5105088, 'steps': 26588, 'loss/train': 0.1373966485261917}
+08/30/2021 17:56:20 - INFO - __main__ - Step 26590: {'lr': 0.0004667121351954233, 'samples': 5105280, 'steps': 26589, 'loss/train': 1.6285159587860107}
+08/30/2021 17:56:20 - INFO - __main__ - Step 26591: {'lr': 0.00046670948935475544, 'samples': 5105472, 'steps': 26590, 'loss/train': 1.7560625076293945}
+08/30/2021 17:56:21 - INFO - __main__ - Step 26592: {'lr': 0.00046670684341644167, 'samples': 5105664, 'steps': 26591, 'loss/train': 1.802418828010559}
+08/30/2021 17:56:22 - INFO - __main__ - Step 26593: {'lr': 0.0004667041973804831, 'samples': 5105856, 'steps': 26592, 'loss/train': 1.8346643447875977}
+08/30/2021 17:56:22 - INFO - __main__ - Step 26594: {'lr': 0.00046670155124688096, 'samples': 5106048, 'steps': 26593, 'loss/train': 2.776232957839966}
+08/30/2021 17:56:23 - INFO - __main__ - Step 26595: {'lr': 0.00046669890501563636, 'samples': 5106240, 'steps': 26594, 'loss/train': 0.9451594948768616}
+08/30/2021 17:56:23 - INFO - __main__ - Step 26596: {'lr': 0.0004666962586867507, 'samples': 5106432, 'steps': 26595, 'loss/train': 1.706702709197998}
+08/30/2021 17:56:25 - INFO - __main__ - Step 26597: {'lr': 0.000466693612260225, 'samples': 5106624, 'steps': 26596, 'loss/train': 2.128802537918091}
+08/30/2021 17:56:26 - INFO - __main__ - Step 26598: {'lr': 0.00046669096573606053, 'samples': 5106816, 'steps': 26597, 'loss/train': 1.3077977895736694}
+08/30/2021 17:56:26 - INFO - __main__ - Step 26599: {'lr': 0.00046668831911425844, 'samples': 5107008, 'steps': 26598, 'loss/train': 0.24058596789836884}
+08/30/2021 17:56:26 - INFO - __main__ - Step 26600: {'lr': 0.00046668567239481994, 'samples': 5107200, 'steps': 26599, 'loss/train': 1.5694202184677124}
+08/30/2021 17:56:27 - INFO - __main__ - Step 26601: {'lr': 0.0004666830255777462, 'samples': 5107392, 'steps': 26600, 'loss/train': 1.5089735984802246}
+08/30/2021 17:56:28 - INFO - __main__ - Step 26602: {'lr': 0.00046668037866303845, 'samples': 5107584, 'steps': 26601, 'loss/train': 1.3394880294799805}
+08/30/2021 17:56:29 - INFO - __main__ - Step 26603: {'lr': 0.0004666777316506979, 'samples': 5107776, 'steps': 26602, 'loss/train': 1.7052606344223022}
+08/30/2021 17:56:29 - INFO - __main__ - Step 26604: {'lr': 0.00046667508454072566, 'samples': 5107968, 'steps': 26603, 'loss/train': 1.8480103015899658}
+08/30/2021 17:56:29 - INFO - __main__ - Step 26605: {'lr': 0.00046667243733312296, 'samples': 5108160, 'steps': 26604, 'loss/train': 1.675742745399475}
+08/30/2021 17:56:30 - INFO - __main__ - Step 26606: {'lr': 0.000466669790027891, 'samples': 5108352, 'steps': 26605, 'loss/train': 1.3788155317306519}
+08/30/2021 17:56:31 - INFO - __main__ - Step 26607: {'lr': 0.00046666714262503107, 'samples': 5108544, 'steps': 26606, 'loss/train': 1.5237983465194702}
+08/30/2021 17:56:32 - INFO - __main__ - Step 26608: {'lr': 0.00046666449512454416, 'samples': 5108736, 'steps': 26607, 'loss/train': 1.323991060256958}
+08/30/2021 17:56:32 - INFO - __main__ - Step 26609: {'lr': 0.0004666618475264316, 'samples': 5108928, 'steps': 26608, 'loss/train': 1.3702112436294556}
+08/30/2021 17:56:32 - INFO - __main__ - Step 26610: {'lr': 0.0004666591998306946, 'samples': 5109120, 'steps': 26609, 'loss/train': 1.3449513912200928}
+08/30/2021 17:56:33 - INFO - __main__ - Step 26611: {'lr': 0.0004666565520373343, 'samples': 5109312, 'steps': 26610, 'loss/train': 1.2981202602386475}
+08/30/2021 17:56:33 - INFO - __main__ - Step 26612: {'lr': 0.00046665390414635184, 'samples': 5109504, 'steps': 26611, 'loss/train': 1.5928764343261719}
+08/30/2021 17:56:34 - INFO - __main__ - Step 26613: {'lr': 0.0004666512561577485, 'samples': 5109696, 'steps': 26612, 'loss/train': 1.3780946731567383}
+08/30/2021 17:56:35 - INFO - __main__ - Step 26614: {'lr': 0.0004666486080715255, 'samples': 5109888, 'steps': 26613, 'loss/train': 1.5655570030212402}
+08/30/2021 17:56:35 - INFO - __main__ - Step 26615: {'lr': 0.0004666459598876839, 'samples': 5110080, 'steps': 26614, 'loss/train': 1.0367977619171143}
+08/30/2021 17:56:36 - INFO - __main__ - Step 26616: {'lr': 0.000466643311606225, 'samples': 5110272, 'steps': 26615, 'loss/train': 1.6685724258422852}
+08/30/2021 17:56:36 - INFO - __main__ - Step 26617: {'lr': 0.00046664066322715006, 'samples': 5110464, 'steps': 26616, 'loss/train': 1.5906468629837036}
+08/30/2021 17:56:38 - INFO - __main__ - Step 26618: {'lr': 0.00046663801475046004, 'samples': 5110656, 'steps': 26617, 'loss/train': 1.2674009799957275}
+08/30/2021 17:56:38 - INFO - __main__ - Step 26619: {'lr': 0.0004666353661761563, 'samples': 5110848, 'steps': 26618, 'loss/train': 1.5779671669006348}
+08/30/2021 17:56:39 - INFO - __main__ - Step 26620: {'lr': 0.0004666327175042401, 'samples': 5111040, 'steps': 26619, 'loss/train': 0.14954562485218048}
+08/30/2021 17:56:39 - INFO - __main__ - Step 26621: {'lr': 0.00046663006873471247, 'samples': 5111232, 'steps': 26620, 'loss/train': 1.7937462329864502}
+08/30/2021 17:56:39 - INFO - __main__ - Step 26622: {'lr': 0.00046662741986757463, 'samples': 5111424, 'steps': 26621, 'loss/train': 1.360806941986084}
+08/30/2021 17:56:41 - INFO - __main__ - Step 26623: {'lr': 0.0004666247709028279, 'samples': 5111616, 'steps': 26622, 'loss/train': 1.251752257347107}
+08/30/2021 17:56:41 - INFO - __main__ - Step 26624: {'lr': 0.00046662212184047334, 'samples': 5111808, 'steps': 26623, 'loss/train': 1.4638067483901978}
+08/30/2021 17:56:42 - INFO - __main__ - Step 26625: {'lr': 0.0004666194726805122, 'samples': 5112000, 'steps': 26624, 'loss/train': 0.9021357297897339}
+08/30/2021 17:56:42 - INFO - __main__ - Step 26626: {'lr': 0.0004666168234229457, 'samples': 5112192, 'steps': 26625, 'loss/train': 2.011953592300415}
+08/30/2021 17:56:42 - INFO - __main__ - Step 26627: {'lr': 0.000466614174067775, 'samples': 5112384, 'steps': 26626, 'loss/train': 0.7863146066665649}
+08/30/2021 17:56:44 - INFO - __main__ - Step 26628: {'lr': 0.00046661152461500126, 'samples': 5112576, 'steps': 26627, 'loss/train': 2.0708909034729004}
+08/30/2021 17:56:45 - INFO - __main__ - Step 26629: {'lr': 0.0004666088750646257, 'samples': 5112768, 'steps': 26628, 'loss/train': 1.9464064836502075}
+08/30/2021 17:56:45 - INFO - __main__ - Step 26630: {'lr': 0.0004666062254166496, 'samples': 5112960, 'steps': 26629, 'loss/train': 0.6118735671043396}
+08/30/2021 17:56:45 - INFO - __main__ - Step 26631: {'lr': 0.000466603575671074, 'samples': 5113152, 'steps': 26630, 'loss/train': 1.2635018825531006}
+08/30/2021 17:56:46 - INFO - __main__ - Step 26632: {'lr': 0.00046660092582790025, 'samples': 5113344, 'steps': 26631, 'loss/train': 1.6213116645812988}
+08/30/2021 17:56:46 - INFO - __main__ - Step 26633: {'lr': 0.0004665982758871294, 'samples': 5113536, 'steps': 26632, 'loss/train': 1.2657393217086792}
+08/30/2021 17:56:48 - INFO - __main__ - Step 26634: {'lr': 0.0004665956258487627, 'samples': 5113728, 'steps': 26633, 'loss/train': 1.2259384393692017}
+08/30/2021 17:56:48 - INFO - __main__ - Step 26635: {'lr': 0.0004665929757128014, 'samples': 5113920, 'steps': 26634, 'loss/train': 1.1367225646972656}
+08/30/2021 17:56:48 - INFO - __main__ - Step 26636: {'lr': 0.0004665903254792466, 'samples': 5114112, 'steps': 26635, 'loss/train': 1.2556160688400269}
+08/30/2021 17:56:49 - INFO - __main__ - Step 26637: {'lr': 0.0004665876751480996, 'samples': 5114304, 'steps': 26636, 'loss/train': 1.492944359779358}
+08/30/2021 17:56:49 - INFO - __main__ - Step 26638: {'lr': 0.0004665850247193615, 'samples': 5114496, 'steps': 26637, 'loss/train': 1.5703942775726318}
+08/30/2021 17:56:51 - INFO - __main__ - Step 26639: {'lr': 0.0004665823741930335, 'samples': 5114688, 'steps': 26638, 'loss/train': 1.1665278673171997}
+08/30/2021 17:56:51 - INFO - __main__ - Step 26640: {'lr': 0.00046657972356911696, 'samples': 5114880, 'steps': 26639, 'loss/train': 0.4462893307209015}
+08/30/2021 17:56:51 - INFO - __main__ - Step 26641: {'lr': 0.00046657707284761274, 'samples': 5115072, 'steps': 26640, 'loss/train': 1.648575782775879}
+08/30/2021 17:56:52 - INFO - __main__ - Step 26642: {'lr': 0.0004665744220285224, 'samples': 5115264, 'steps': 26641, 'loss/train': 1.681076169013977}
+08/30/2021 17:56:52 - INFO - __main__ - Step 26643: {'lr': 0.0004665717711118469, 'samples': 5115456, 'steps': 26642, 'loss/train': 2.1270596981048584}
+08/30/2021 17:56:54 - INFO - __main__ - Step 26644: {'lr': 0.00046656912009758743, 'samples': 5115648, 'steps': 26643, 'loss/train': 1.60477614402771}
+08/30/2021 17:56:54 - INFO - __main__ - Step 26645: {'lr': 0.0004665664689857454, 'samples': 5115840, 'steps': 26644, 'loss/train': 1.2852739095687866}
+08/30/2021 17:56:55 - INFO - __main__ - Step 26646: {'lr': 0.00046656381777632173, 'samples': 5116032, 'steps': 26645, 'loss/train': 1.433002233505249}
+08/30/2021 17:56:55 - INFO - __main__ - Step 26647: {'lr': 0.0004665611664693178, 'samples': 5116224, 'steps': 26646, 'loss/train': 0.8877944350242615}
+08/30/2021 17:56:55 - INFO - __main__ - Step 26648: {'lr': 0.0004665585150647348, 'samples': 5116416, 'steps': 26647, 'loss/train': 0.9069812893867493}
+08/30/2021 17:56:57 - INFO - __main__ - Step 26649: {'lr': 0.0004665558635625738, 'samples': 5116608, 'steps': 26648, 'loss/train': 1.624466896057129}
+08/30/2021 17:56:57 - INFO - __main__ - Step 26650: {'lr': 0.00046655321196283604, 'samples': 5116800, 'steps': 26649, 'loss/train': 1.2025951147079468}
+08/30/2021 17:56:58 - INFO - __main__ - Step 26651: {'lr': 0.00046655056026552287, 'samples': 5116992, 'steps': 26650, 'loss/train': 1.448067307472229}
+08/30/2021 17:56:58 - INFO - __main__ - Step 26652: {'lr': 0.0004665479084706353, 'samples': 5117184, 'steps': 26651, 'loss/train': 1.4956330060958862}
+08/30/2021 17:56:58 - INFO - __main__ - Step 26653: {'lr': 0.00046654525657817457, 'samples': 5117376, 'steps': 26652, 'loss/train': 1.2684885263442993}
+08/30/2021 17:57:00 - INFO - __main__ - Step 26654: {'lr': 0.0004665426045881419, 'samples': 5117568, 'steps': 26653, 'loss/train': 1.571487307548523}
+08/30/2021 17:57:01 - INFO - __main__ - Step 26655: {'lr': 0.00046653995250053843, 'samples': 5117760, 'steps': 26654, 'loss/train': 1.648902416229248}
+08/30/2021 17:57:01 - INFO - __main__ - Step 26656: {'lr': 0.00046653730031536545, 'samples': 5117952, 'steps': 26655, 'loss/train': 0.6627792119979858}
+08/30/2021 17:57:02 - INFO - __main__ - Step 26657: {'lr': 0.0004665346480326241, 'samples': 5118144, 'steps': 26656, 'loss/train': 1.4905503988265991}
+08/30/2021 17:57:02 - INFO - __main__ - Step 26658: {'lr': 0.00046653199565231554, 'samples': 5118336, 'steps': 26657, 'loss/train': 1.935055136680603}
+08/30/2021 17:57:03 - INFO - __main__ - Step 26659: {'lr': 0.00046652934317444104, 'samples': 5118528, 'steps': 26658, 'loss/train': 1.2012574672698975}
+08/30/2021 17:57:04 - INFO - __main__ - Step 26660: {'lr': 0.00046652669059900174, 'samples': 5118720, 'steps': 26659, 'loss/train': 1.693825364112854}
+08/30/2021 17:57:04 - INFO - __main__ - Step 26661: {'lr': 0.0004665240379259989, 'samples': 5118912, 'steps': 26660, 'loss/train': 2.019569158554077}
+08/30/2021 17:57:05 - INFO - __main__ - Step 26662: {'lr': 0.00046652138515543366, 'samples': 5119104, 'steps': 26661, 'loss/train': 1.3235939741134644}
+08/30/2021 17:57:05 - INFO - __main__ - Step 26663: {'lr': 0.00046651873228730715, 'samples': 5119296, 'steps': 26662, 'loss/train': 0.3999435007572174}
+08/30/2021 17:57:05 - INFO - __main__ - Step 26664: {'lr': 0.0004665160793216207, 'samples': 5119488, 'steps': 26663, 'loss/train': 1.3439934253692627}
+08/30/2021 17:57:07 - INFO - __main__ - Step 26665: {'lr': 0.00046651342625837544, 'samples': 5119680, 'steps': 26664, 'loss/train': 1.6201248168945312}
+08/30/2021 17:57:07 - INFO - __main__ - Step 26666: {'lr': 0.00046651077309757256, 'samples': 5119872, 'steps': 26665, 'loss/train': 1.9719942808151245}
+08/30/2021 17:57:08 - INFO - __main__ - Step 26667: {'lr': 0.0004665081198392133, 'samples': 5120064, 'steps': 26666, 'loss/train': 1.5221664905548096}
+08/30/2021 17:57:08 - INFO - __main__ - Step 26668: {'lr': 0.0004665054664832988, 'samples': 5120256, 'steps': 26667, 'loss/train': 1.5162558555603027}
+08/30/2021 17:57:08 - INFO - __main__ - Step 26669: {'lr': 0.00046650281302983024, 'samples': 5120448, 'steps': 26668, 'loss/train': 1.4170496463775635}
+08/30/2021 17:57:10 - INFO - __main__ - Step 26670: {'lr': 0.00046650015947880886, 'samples': 5120640, 'steps': 26669, 'loss/train': 1.8704843521118164}
+08/30/2021 17:57:10 - INFO - __main__ - Step 26671: {'lr': 0.00046649750583023595, 'samples': 5120832, 'steps': 26670, 'loss/train': 1.5668845176696777}
+08/30/2021 17:57:11 - INFO - __main__ - Step 26672: {'lr': 0.00046649485208411244, 'samples': 5121024, 'steps': 26671, 'loss/train': 1.3336966037750244}
+08/30/2021 17:57:11 - INFO - __main__ - Step 26673: {'lr': 0.00046649219824043984, 'samples': 5121216, 'steps': 26672, 'loss/train': 1.2383750677108765}
+08/30/2021 17:57:11 - INFO - __main__ - Step 26674: {'lr': 0.00046648954429921914, 'samples': 5121408, 'steps': 26673, 'loss/train': 1.6487102508544922}
+08/30/2021 17:57:13 - INFO - __main__ - Step 26675: {'lr': 0.00046648689026045157, 'samples': 5121600, 'steps': 26674, 'loss/train': 1.3962541818618774}
+08/30/2021 17:57:13 - INFO - __main__ - Step 26676: {'lr': 0.0004664842361241384, 'samples': 5121792, 'steps': 26675, 'loss/train': 1.617918848991394}
+08/30/2021 17:57:14 - INFO - __main__ - Step 26677: {'lr': 0.00046648158189028073, 'samples': 5121984, 'steps': 26676, 'loss/train': 1.6024278402328491}
+08/30/2021 17:57:14 - INFO - __main__ - Step 26678: {'lr': 0.0004664789275588798, 'samples': 5122176, 'steps': 26677, 'loss/train': 1.7752492427825928}
+08/30/2021 17:57:14 - INFO - __main__ - Step 26679: {'lr': 0.0004664762731299368, 'samples': 5122368, 'steps': 26678, 'loss/train': 0.10728741437196732}
+08/30/2021 17:57:16 - INFO - __main__ - Step 26680: {'lr': 0.00046647361860345293, 'samples': 5122560, 'steps': 26679, 'loss/train': 1.3969312906265259}
+08/30/2021 17:57:16 - INFO - __main__ - Step 26681: {'lr': 0.00046647096397942945, 'samples': 5122752, 'steps': 26680, 'loss/train': 1.6737064123153687}
+08/30/2021 17:57:17 - INFO - __main__ - Step 26682: {'lr': 0.0004664683092578674, 'samples': 5122944, 'steps': 26681, 'loss/train': 1.1327248811721802}
+08/30/2021 17:57:17 - INFO - __main__ - Step 26683: {'lr': 0.00046646565443876815, 'samples': 5123136, 'steps': 26682, 'loss/train': 1.356799602508545}
+08/30/2021 17:57:17 - INFO - __main__ - Step 26684: {'lr': 0.00046646299952213277, 'samples': 5123328, 'steps': 26683, 'loss/train': 0.6211066842079163}
+08/30/2021 17:57:19 - INFO - __main__ - Step 26685: {'lr': 0.00046646034450796255, 'samples': 5123520, 'steps': 26684, 'loss/train': 2.2446956634521484}
+08/30/2021 17:57:19 - INFO - __main__ - Step 26686: {'lr': 0.0004664576893962586, 'samples': 5123712, 'steps': 26685, 'loss/train': 1.8335237503051758}
+08/30/2021 17:57:20 - INFO - __main__ - Step 26687: {'lr': 0.0004664550341870222, 'samples': 5123904, 'steps': 26686, 'loss/train': 1.1680623292922974}
+08/30/2021 17:57:20 - INFO - __main__ - Step 26688: {'lr': 0.00046645237888025444, 'samples': 5124096, 'steps': 26687, 'loss/train': 2.169955253601074}
+08/30/2021 17:57:20 - INFO - __main__ - Step 26689: {'lr': 0.0004664497234759566, 'samples': 5124288, 'steps': 26688, 'loss/train': 0.5427646040916443}
+08/30/2021 17:57:21 - INFO - __main__ - Step 26690: {'lr': 0.00046644706797412984, 'samples': 5124480, 'steps': 26689, 'loss/train': 1.4893057346343994}
+08/30/2021 17:57:22 - INFO - __main__ - Step 26691: {'lr': 0.00046644441237477544, 'samples': 5124672, 'steps': 26690, 'loss/train': 1.658414602279663}
+08/30/2021 17:57:23 - INFO - __main__ - Step 26692: {'lr': 0.00046644175667789444, 'samples': 5124864, 'steps': 26691, 'loss/train': 1.52473783493042}
+08/30/2021 17:57:23 - INFO - __main__ - Step 26693: {'lr': 0.00046643910088348817, 'samples': 5125056, 'steps': 26692, 'loss/train': 0.9235119819641113}
+08/30/2021 17:57:23 - INFO - __main__ - Step 26694: {'lr': 0.0004664364449915578, 'samples': 5125248, 'steps': 26693, 'loss/train': 1.717477560043335}
+08/30/2021 17:57:24 - INFO - __main__ - Step 26695: {'lr': 0.0004664337890021044, 'samples': 5125440, 'steps': 26694, 'loss/train': 1.2940359115600586}
+08/30/2021 17:57:25 - INFO - __main__ - Step 26696: {'lr': 0.0004664311329151294, 'samples': 5125632, 'steps': 26695, 'loss/train': 1.9891644716262817}
+08/30/2021 17:57:26 - INFO - __main__ - Step 26697: {'lr': 0.0004664284767306338, 'samples': 5125824, 'steps': 26696, 'loss/train': 1.8456469774246216}
+08/30/2021 17:57:26 - INFO - __main__ - Step 26698: {'lr': 0.0004664258204486189, 'samples': 5126016, 'steps': 26697, 'loss/train': 1.663969874382019}
+08/30/2021 17:57:27 - INFO - __main__ - Step 26699: {'lr': 0.0004664231640690859, 'samples': 5126208, 'steps': 26698, 'loss/train': 1.5915356874465942}
+08/30/2021 17:57:27 - INFO - __main__ - Step 26700: {'lr': 0.0004664205075920359, 'samples': 5126400, 'steps': 26699, 'loss/train': 1.0144003629684448}
+08/30/2021 17:57:29 - INFO - __main__ - Step 26701: {'lr': 0.0004664178510174702, 'samples': 5126592, 'steps': 26700, 'loss/train': 1.863483190536499}
+08/30/2021 17:57:30 - INFO - __main__ - Step 26702: {'lr': 0.0004664151943453899, 'samples': 5126784, 'steps': 26701, 'loss/train': 1.5355284214019775}
+08/30/2021 17:57:30 - INFO - __main__ - Step 26703: {'lr': 0.0004664125375757963, 'samples': 5126976, 'steps': 26702, 'loss/train': 1.4345295429229736}
+08/30/2021 17:57:30 - INFO - __main__ - Step 26704: {'lr': 0.00046640988070869053, 'samples': 5127168, 'steps': 26703, 'loss/train': 1.6513216495513916}
+08/30/2021 17:57:31 - INFO - __main__ - Step 26705: {'lr': 0.00046640722374407384, 'samples': 5127360, 'steps': 26704, 'loss/train': 1.3768072128295898}
+08/30/2021 17:57:31 - INFO - __main__ - Step 26706: {'lr': 0.00046640456668194737, 'samples': 5127552, 'steps': 26705, 'loss/train': 1.8468369245529175}
+08/30/2021 17:57:32 - INFO - __main__ - Step 26707: {'lr': 0.0004664019095223123, 'samples': 5127744, 'steps': 26706, 'loss/train': 2.6544859409332275}
+08/30/2021 17:57:33 - INFO - __main__ - Step 26708: {'lr': 0.00046639925226517, 'samples': 5127936, 'steps': 26707, 'loss/train': 1.6677361726760864}
+08/30/2021 17:57:33 - INFO - __main__ - Step 26709: {'lr': 0.0004663965949105214, 'samples': 5128128, 'steps': 26708, 'loss/train': 1.158858060836792}
+08/30/2021 17:57:34 - INFO - __main__ - Step 26710: {'lr': 0.0004663939374583679, 'samples': 5128320, 'steps': 26709, 'loss/train': 1.6500035524368286}
+08/30/2021 17:57:34 - INFO - __main__ - Step 26711: {'lr': 0.00046639127990871055, 'samples': 5128512, 'steps': 26710, 'loss/train': 1.7814421653747559}
+08/30/2021 17:57:36 - INFO - __main__ - Step 26712: {'lr': 0.00046638862226155075, 'samples': 5128704, 'steps': 26711, 'loss/train': 1.1269235610961914}
+08/30/2021 17:57:36 - INFO - __main__ - Step 26713: {'lr': 0.0004663859645168895, 'samples': 5128896, 'steps': 26712, 'loss/train': 1.0910543203353882}
+08/30/2021 17:57:36 - INFO - __main__ - Step 26714: {'lr': 0.00046638330667472805, 'samples': 5129088, 'steps': 26713, 'loss/train': 1.7232025861740112}
+08/30/2021 17:57:37 - INFO - __main__ - Step 26715: {'lr': 0.0004663806487350677, 'samples': 5129280, 'steps': 26714, 'loss/train': 1.5871376991271973}
+08/30/2021 17:57:37 - INFO - __main__ - Step 26716: {'lr': 0.00046637799069790953, 'samples': 5129472, 'steps': 26715, 'loss/train': 0.08858071267604828}
+08/30/2021 17:57:39 - INFO - __main__ - Step 26717: {'lr': 0.00046637533256325476, 'samples': 5129664, 'steps': 26716, 'loss/train': 1.5392704010009766}
+08/30/2021 17:57:39 - INFO - __main__ - Step 26718: {'lr': 0.0004663726743311046, 'samples': 5129856, 'steps': 26717, 'loss/train': 1.4603545665740967}
+08/30/2021 17:57:40 - INFO - __main__ - Step 26719: {'lr': 0.00046637001600146027, 'samples': 5130048, 'steps': 26718, 'loss/train': 0.09331375360488892}
+08/30/2021 17:57:40 - INFO - __main__ - Step 26720: {'lr': 0.000466367357574323, 'samples': 5130240, 'steps': 26719, 'loss/train': 1.9333102703094482}
+08/30/2021 17:57:41 - INFO - __main__ - Step 26721: {'lr': 0.00046636469904969387, 'samples': 5130432, 'steps': 26720, 'loss/train': 1.365154504776001}
+08/30/2021 17:57:41 - INFO - __main__ - Step 26722: {'lr': 0.0004663620404275741, 'samples': 5130624, 'steps': 26721, 'loss/train': 1.0078293085098267}
+08/30/2021 17:57:42 - INFO - __main__ - Step 26723: {'lr': 0.00046635938170796505, 'samples': 5130816, 'steps': 26722, 'loss/train': 1.0311357975006104}
+08/30/2021 17:57:43 - INFO - __main__ - Step 26724: {'lr': 0.00046635672289086774, 'samples': 5131008, 'steps': 26723, 'loss/train': 1.319662094116211}
+08/30/2021 17:57:43 - INFO - __main__ - Step 26725: {'lr': 0.00046635406397628346, 'samples': 5131200, 'steps': 26724, 'loss/train': 1.5365781784057617}
+08/30/2021 17:57:44 - INFO - __main__ - Step 26726: {'lr': 0.00046635140496421336, 'samples': 5131392, 'steps': 26725, 'loss/train': 1.5976406335830688}
+08/30/2021 17:57:44 - INFO - __main__ - Step 26727: {'lr': 0.0004663487458546586, 'samples': 5131584, 'steps': 26726, 'loss/train': 1.6156132221221924}
+08/30/2021 17:57:45 - INFO - __main__ - Step 26728: {'lr': 0.0004663460866476205, 'samples': 5131776, 'steps': 26727, 'loss/train': 1.5820831060409546}
+08/30/2021 17:57:46 - INFO - __main__ - Step 26729: {'lr': 0.00046634342734310023, 'samples': 5131968, 'steps': 26728, 'loss/train': 1.461832880973816}
+08/30/2021 17:57:46 - INFO - __main__ - Step 26730: {'lr': 0.0004663407679410988, 'samples': 5132160, 'steps': 26729, 'loss/train': 0.21380048990249634}
+08/30/2021 17:57:47 - INFO - __main__ - Step 26731: {'lr': 0.0004663381084416177, 'samples': 5132352, 'steps': 26730, 'loss/train': 1.8571300506591797}
+08/30/2021 17:57:47 - INFO - __main__ - Step 26732: {'lr': 0.00046633544884465796, 'samples': 5132544, 'steps': 26731, 'loss/train': 1.300208330154419}
+08/30/2021 17:57:48 - INFO - __main__ - Step 26733: {'lr': 0.0004663327891502208, 'samples': 5132736, 'steps': 26732, 'loss/train': 0.3474135100841522}
+08/30/2021 17:57:49 - INFO - __main__ - Step 26734: {'lr': 0.0004663301293583073, 'samples': 5132928, 'steps': 26733, 'loss/train': 1.2446075677871704}
+08/30/2021 17:57:49 - INFO - __main__ - Step 26735: {'lr': 0.000466327469468919, 'samples': 5133120, 'steps': 26734, 'loss/train': 1.6891194581985474}
+08/30/2021 17:57:50 - INFO - __main__ - Step 26736: {'lr': 0.0004663248094820567, 'samples': 5133312, 'steps': 26735, 'loss/train': 1.2903902530670166}
+08/30/2021 17:57:50 - INFO - __main__ - Step 26737: {'lr': 0.00046632214939772187, 'samples': 5133504, 'steps': 26736, 'loss/train': 1.6359522342681885}
+08/30/2021 17:57:52 - INFO - __main__ - Step 26738: {'lr': 0.0004663194892159156, 'samples': 5133696, 'steps': 26737, 'loss/train': 1.2313135862350464}
+08/30/2021 17:57:52 - INFO - __main__ - Step 26739: {'lr': 0.0004663168289366391, 'samples': 5133888, 'steps': 26738, 'loss/train': 1.1805410385131836}
+08/30/2021 17:57:52 - INFO - __main__ - Step 26740: {'lr': 0.0004663141685598936, 'samples': 5134080, 'steps': 26739, 'loss/train': 4.346454620361328}
+08/30/2021 17:57:53 - INFO - __main__ - Step 26741: {'lr': 0.00046631150808568026, 'samples': 5134272, 'steps': 26740, 'loss/train': 1.359296441078186}
+08/30/2021 17:57:53 - INFO - __main__ - Step 26742: {'lr': 0.00046630884751400024, 'samples': 5134464, 'steps': 26741, 'loss/train': 1.4907121658325195}
+08/30/2021 17:57:53 - INFO - __main__ - Step 26743: {'lr': 0.0004663061868448548, 'samples': 5134656, 'steps': 26742, 'loss/train': 1.8572890758514404}
+08/30/2021 17:57:55 - INFO - __main__ - Step 26744: {'lr': 0.0004663035260782452, 'samples': 5134848, 'steps': 26743, 'loss/train': 1.7632564306259155}
+08/30/2021 17:57:55 - INFO - __main__ - Step 26745: {'lr': 0.0004663008652141726, 'samples': 5135040, 'steps': 26744, 'loss/train': 1.5466748476028442}
+08/30/2021 17:57:56 - INFO - __main__ - Step 26746: {'lr': 0.00046629820425263805, 'samples': 5135232, 'steps': 26745, 'loss/train': 1.1536327600479126}
+08/30/2021 17:57:56 - INFO - __main__ - Step 26747: {'lr': 0.00046629554319364293, 'samples': 5135424, 'steps': 26746, 'loss/train': 1.0963774919509888}
+08/30/2021 17:57:56 - INFO - __main__ - Step 26748: {'lr': 0.00046629288203718834, 'samples': 5135616, 'steps': 26747, 'loss/train': 1.7901570796966553}
+08/30/2021 17:57:58 - INFO - __main__ - Step 26749: {'lr': 0.00046629022078327557, 'samples': 5135808, 'steps': 26748, 'loss/train': 1.4945642948150635}
+08/30/2021 17:57:58 - INFO - __main__ - Step 26750: {'lr': 0.0004662875594319057, 'samples': 5136000, 'steps': 26749, 'loss/train': 1.3612560033798218}
+08/30/2021 17:57:59 - INFO - __main__ - Step 26751: {'lr': 0.00046628489798308006, 'samples': 5136192, 'steps': 26750, 'loss/train': 1.6134798526763916}
+08/30/2021 17:57:59 - INFO - __main__ - Step 26752: {'lr': 0.0004662822364367997, 'samples': 5136384, 'steps': 26751, 'loss/train': 1.331142783164978}
+08/30/2021 17:57:59 - INFO - __main__ - Step 26753: {'lr': 0.000466279574793066, 'samples': 5136576, 'steps': 26752, 'loss/train': 1.8044636249542236}
+08/30/2021 17:58:01 - INFO - __main__ - Step 26754: {'lr': 0.00046627691305188004, 'samples': 5136768, 'steps': 26753, 'loss/train': 0.5285789966583252}
+08/30/2021 17:58:02 - INFO - __main__ - Step 26755: {'lr': 0.00046627425121324294, 'samples': 5136960, 'steps': 26754, 'loss/train': 2.230715751647949}
+08/30/2021 17:58:02 - INFO - __main__ - Step 26756: {'lr': 0.0004662715892771561, 'samples': 5137152, 'steps': 26755, 'loss/train': 1.5442594289779663}
+08/30/2021 17:58:03 - INFO - __main__ - Step 26757: {'lr': 0.0004662689272436206, 'samples': 5137344, 'steps': 26756, 'loss/train': 1.7846076488494873}
+08/30/2021 17:58:03 - INFO - __main__ - Step 26758: {'lr': 0.00046626626511263764, 'samples': 5137536, 'steps': 26757, 'loss/train': 0.08230098336935043}
+08/30/2021 17:58:03 - INFO - __main__ - Step 26759: {'lr': 0.00046626360288420845, 'samples': 5137728, 'steps': 26758, 'loss/train': 1.536605715751648}
+08/30/2021 17:58:05 - INFO - __main__ - Step 26760: {'lr': 0.00046626094055833426, 'samples': 5137920, 'steps': 26759, 'loss/train': 1.6113698482513428}
+08/30/2021 17:58:06 - INFO - __main__ - Step 26761: {'lr': 0.0004662582781350161, 'samples': 5138112, 'steps': 26760, 'loss/train': 1.4732036590576172}
+08/30/2021 17:58:06 - INFO - __main__ - Step 26762: {'lr': 0.00046625561561425543, 'samples': 5138304, 'steps': 26761, 'loss/train': 1.2604283094406128}
+08/30/2021 17:58:06 - INFO - __main__ - Step 26763: {'lr': 0.00046625295299605323, 'samples': 5138496, 'steps': 26762, 'loss/train': 1.4922982454299927}
+08/30/2021 17:58:07 - INFO - __main__ - Step 26764: {'lr': 0.0004662502902804109, 'samples': 5138688, 'steps': 26763, 'loss/train': 1.4694780111312866}
+08/30/2021 17:58:07 - INFO - __main__ - Step 26765: {'lr': 0.0004662476274673294, 'samples': 5138880, 'steps': 26764, 'loss/train': 1.683996319770813}
+08/30/2021 17:58:09 - INFO - __main__ - Step 26766: {'lr': 0.00046624496455681006, 'samples': 5139072, 'steps': 26765, 'loss/train': 1.5728793144226074}
+08/30/2021 17:58:09 - INFO - __main__ - Step 26767: {'lr': 0.00046624230154885415, 'samples': 5139264, 'steps': 26766, 'loss/train': 1.5897480249404907}
+08/30/2021 17:58:10 - INFO - __main__ - Step 26768: {'lr': 0.0004662396384434627, 'samples': 5139456, 'steps': 26767, 'loss/train': 1.5656379461288452}
+08/30/2021 17:58:10 - INFO - __main__ - Step 26769: {'lr': 0.00046623697524063713, 'samples': 5139648, 'steps': 26768, 'loss/train': 1.7227659225463867}
+08/30/2021 17:58:10 - INFO - __main__ - Step 26770: {'lr': 0.00046623431194037847, 'samples': 5139840, 'steps': 26769, 'loss/train': 1.4630969762802124}
+08/30/2021 17:58:12 - INFO - __main__ - Step 26771: {'lr': 0.000466231648542688, 'samples': 5140032, 'steps': 26770, 'loss/train': 1.9150218963623047}
+08/30/2021 17:58:12 - INFO - __main__ - Step 26772: {'lr': 0.0004662289850475668, 'samples': 5140224, 'steps': 26771, 'loss/train': 1.0994112491607666}
+08/30/2021 17:58:13 - INFO - __main__ - Step 26773: {'lr': 0.0004662263214550162, 'samples': 5140416, 'steps': 26772, 'loss/train': 1.8346391916275024}
+08/30/2021 17:58:13 - INFO - __main__ - Step 26774: {'lr': 0.00046622365776503735, 'samples': 5140608, 'steps': 26773, 'loss/train': 1.2081940174102783}
+08/30/2021 17:58:14 - INFO - __main__ - Step 26775: {'lr': 0.0004662209939776315, 'samples': 5140800, 'steps': 26774, 'loss/train': 1.7097142934799194}
+08/30/2021 17:58:15 - INFO - __main__ - Step 26776: {'lr': 0.0004662183300927997, 'samples': 5140992, 'steps': 26775, 'loss/train': 1.4779356718063354}
+08/30/2021 17:58:16 - INFO - __main__ - Step 26777: {'lr': 0.0004662156661105433, 'samples': 5141184, 'steps': 26776, 'loss/train': 1.3889614343643188}
+08/30/2021 17:58:16 - INFO - __main__ - Step 26778: {'lr': 0.0004662130020308635, 'samples': 5141376, 'steps': 26777, 'loss/train': 1.6845752000808716}
+08/30/2021 17:58:16 - INFO - __main__ - Step 26779: {'lr': 0.00046621033785376146, 'samples': 5141568, 'steps': 26778, 'loss/train': 1.0824769735336304}
+08/30/2021 17:58:17 - INFO - __main__ - Step 26780: {'lr': 0.00046620767357923834, 'samples': 5141760, 'steps': 26779, 'loss/train': 1.6082614660263062}
+08/30/2021 17:58:18 - INFO - __main__ - Step 26781: {'lr': 0.0004662050092072954, 'samples': 5141952, 'steps': 26780, 'loss/train': 1.775464653968811}
+08/30/2021 17:58:19 - INFO - __main__ - Step 26782: {'lr': 0.0004662023447379338, 'samples': 5142144, 'steps': 26781, 'loss/train': 1.8717602491378784}
+08/30/2021 17:58:19 - INFO - __main__ - Step 26783: {'lr': 0.0004661996801711548, 'samples': 5142336, 'steps': 26782, 'loss/train': 1.1960712671279907}
+08/30/2021 17:58:19 - INFO - __main__ - Step 26784: {'lr': 0.0004661970155069595, 'samples': 5142528, 'steps': 26783, 'loss/train': 1.3057440519332886}
+08/30/2021 17:58:20 - INFO - __main__ - Step 26785: {'lr': 0.00046619435074534923, 'samples': 5142720, 'steps': 26784, 'loss/train': 1.7113823890686035}
+08/30/2021 17:58:22 - INFO - __main__ - Step 26786: {'lr': 0.0004661916858863251, 'samples': 5142912, 'steps': 26785, 'loss/train': 1.7824463844299316}
+08/30/2021 17:58:22 - INFO - __main__ - Step 26787: {'lr': 0.00046618902092988824, 'samples': 5143104, 'steps': 26786, 'loss/train': 1.6778502464294434}
+08/30/2021 17:58:22 - INFO - __main__ - Step 26788: {'lr': 0.00046618635587604006, 'samples': 5143296, 'steps': 26787, 'loss/train': 0.2964571714401245}
+08/30/2021 17:58:23 - INFO - __main__ - Step 26789: {'lr': 0.00046618369072478163, 'samples': 5143488, 'steps': 26788, 'loss/train': 1.3270459175109863}
+08/30/2021 17:58:23 - INFO - __main__ - Step 26790: {'lr': 0.0004661810254761141, 'samples': 5143680, 'steps': 26789, 'loss/train': 0.05226729065179825}
+08/30/2021 17:58:23 - INFO - __main__ - Step 26791: {'lr': 0.0004661783601300388, 'samples': 5143872, 'steps': 26790, 'loss/train': 1.418766975402832}
+08/30/2021 17:58:25 - INFO - __main__ - Step 26792: {'lr': 0.00046617569468655686, 'samples': 5144064, 'steps': 26791, 'loss/train': 1.2048664093017578}
+08/30/2021 17:58:25 - INFO - __main__ - Step 26793: {'lr': 0.00046617302914566945, 'samples': 5144256, 'steps': 26792, 'loss/train': 0.2802641987800598}
+08/30/2021 17:58:26 - INFO - __main__ - Step 26794: {'lr': 0.00046617036350737786, 'samples': 5144448, 'steps': 26793, 'loss/train': 2.003206729888916}
+08/30/2021 17:58:26 - INFO - __main__ - Step 26795: {'lr': 0.0004661676977716832, 'samples': 5144640, 'steps': 26794, 'loss/train': 1.377181887626648}
+08/30/2021 17:58:26 - INFO - __main__ - Step 26796: {'lr': 0.0004661650319385867, 'samples': 5144832, 'steps': 26795, 'loss/train': 1.4903490543365479}
+08/30/2021 17:58:28 - INFO - __main__ - Step 26797: {'lr': 0.0004661623660080896, 'samples': 5145024, 'steps': 26796, 'loss/train': 1.5612714290618896}
+08/30/2021 17:58:28 - INFO - __main__ - Step 26798: {'lr': 0.000466159699980193, 'samples': 5145216, 'steps': 26797, 'loss/train': 2.395564556121826}
+08/30/2021 17:58:29 - INFO - __main__ - Step 26799: {'lr': 0.0004661570338548983, 'samples': 5145408, 'steps': 26798, 'loss/train': 1.3965349197387695}
+08/30/2021 17:58:29 - INFO - __main__ - Step 26800: {'lr': 0.00046615436763220645, 'samples': 5145600, 'steps': 26799, 'loss/train': 1.2196152210235596}
+08/30/2021 17:58:29 - INFO - __main__ - Step 26801: {'lr': 0.0004661517013121189, 'samples': 5145792, 'steps': 26800, 'loss/train': 1.6071802377700806}
+08/30/2021 17:58:31 - INFO - __main__ - Step 26802: {'lr': 0.00046614903489463667, 'samples': 5145984, 'steps': 26801, 'loss/train': 1.6098366975784302}
+08/30/2021 17:58:31 - INFO - __main__ - Step 26803: {'lr': 0.000466146368379761, 'samples': 5146176, 'steps': 26802, 'loss/train': 1.8973139524459839}
+08/30/2021 17:58:32 - INFO - __main__ - Step 26804: {'lr': 0.0004661437017674931, 'samples': 5146368, 'steps': 26803, 'loss/train': 1.0908960103988647}
+08/30/2021 17:58:32 - INFO - __main__ - Step 26805: {'lr': 0.00046614103505783423, 'samples': 5146560, 'steps': 26804, 'loss/train': 1.4314018487930298}
+08/30/2021 17:58:32 - INFO - __main__ - Step 26806: {'lr': 0.0004661383682507856, 'samples': 5146752, 'steps': 26805, 'loss/train': 1.9222533702850342}
+08/30/2021 17:58:34 - INFO - __main__ - Step 26807: {'lr': 0.00046613570134634825, 'samples': 5146944, 'steps': 26806, 'loss/train': 1.7310898303985596}
+08/30/2021 17:58:34 - INFO - __main__ - Step 26808: {'lr': 0.00046613303434452346, 'samples': 5147136, 'steps': 26807, 'loss/train': 1.17205810546875}
+08/30/2021 17:58:35 - INFO - __main__ - Step 26809: {'lr': 0.00046613036724531254, 'samples': 5147328, 'steps': 26808, 'loss/train': 0.9658483862876892}
+08/30/2021 17:58:35 - INFO - __main__ - Step 26810: {'lr': 0.00046612770004871663, 'samples': 5147520, 'steps': 26809, 'loss/train': 1.5939700603485107}
+08/30/2021 17:58:35 - INFO - __main__ - Step 26811: {'lr': 0.00046612503275473687, 'samples': 5147712, 'steps': 26810, 'loss/train': 1.7550020217895508}
+08/30/2021 17:58:37 - INFO - __main__ - Step 26812: {'lr': 0.00046612236536337456, 'samples': 5147904, 'steps': 26811, 'loss/train': 1.9856510162353516}
+08/30/2021 17:58:38 - INFO - __main__ - Step 26813: {'lr': 0.00046611969787463083, 'samples': 5148096, 'steps': 26812, 'loss/train': 4.578228950500488}
+08/30/2021 17:58:38 - INFO - __main__ - Step 26814: {'lr': 0.00046611703028850683, 'samples': 5148288, 'steps': 26813, 'loss/train': 1.394594430923462}
+08/30/2021 17:58:38 - INFO - __main__ - Step 26815: {'lr': 0.00046611436260500386, 'samples': 5148480, 'steps': 26814, 'loss/train': 1.1023682355880737}
+08/30/2021 17:58:39 - INFO - __main__ - Step 26816: {'lr': 0.00046611169482412305, 'samples': 5148672, 'steps': 26815, 'loss/train': 1.971582055091858}
+08/30/2021 17:58:39 - INFO - __main__ - Step 26817: {'lr': 0.00046610902694586576, 'samples': 5148864, 'steps': 26816, 'loss/train': 0.7202461957931519}
+08/30/2021 17:58:41 - INFO - __main__ - Step 26818: {'lr': 0.00046610635897023303, 'samples': 5149056, 'steps': 26817, 'loss/train': 1.480725646018982}
+08/30/2021 17:58:41 - INFO - __main__ - Step 26819: {'lr': 0.0004661036908972261, 'samples': 5149248, 'steps': 26818, 'loss/train': 2.1650359630584717}
+08/30/2021 17:58:41 - INFO - __main__ - Step 26820: {'lr': 0.0004661010227268462, 'samples': 5149440, 'steps': 26819, 'loss/train': 1.171453595161438}
+08/30/2021 17:58:42 - INFO - __main__ - Step 26821: {'lr': 0.0004660983544590944, 'samples': 5149632, 'steps': 26820, 'loss/train': 1.4449701309204102}
+08/30/2021 17:58:42 - INFO - __main__ - Step 26822: {'lr': 0.0004660956860939722, 'samples': 5149824, 'steps': 26821, 'loss/train': 1.9287570714950562}
+08/30/2021 17:58:44 - INFO - __main__ - Step 26823: {'lr': 0.0004660930176314805, 'samples': 5150016, 'steps': 26822, 'loss/train': 1.3852072954177856}
+08/30/2021 17:58:44 - INFO - __main__ - Step 26824: {'lr': 0.0004660903490716206, 'samples': 5150208, 'steps': 26823, 'loss/train': 1.145975112915039}
+08/30/2021 17:58:44 - INFO - __main__ - Step 26825: {'lr': 0.0004660876804143938, 'samples': 5150400, 'steps': 26824, 'loss/train': 1.3981616497039795}
+08/30/2021 17:58:45 - INFO - __main__ - Step 26826: {'lr': 0.0004660850116598012, 'samples': 5150592, 'steps': 26825, 'loss/train': 1.5617139339447021}
+08/30/2021 17:58:45 - INFO - __main__ - Step 26827: {'lr': 0.00046608234280784406, 'samples': 5150784, 'steps': 26826, 'loss/train': 1.561122179031372}
+08/30/2021 17:58:47 - INFO - __main__ - Step 26828: {'lr': 0.0004660796738585235, 'samples': 5150976, 'steps': 26827, 'loss/train': 1.611430287361145}
+08/30/2021 17:58:47 - INFO - __main__ - Step 26829: {'lr': 0.0004660770048118408, 'samples': 5151168, 'steps': 26828, 'loss/train': 1.7318994998931885}
+08/30/2021 17:58:47 - INFO - __main__ - Step 26830: {'lr': 0.00046607433566779713, 'samples': 5151360, 'steps': 26829, 'loss/train': 1.8213824033737183}
+08/30/2021 17:58:48 - INFO - __main__ - Step 26831: {'lr': 0.00046607166642639365, 'samples': 5151552, 'steps': 26830, 'loss/train': 1.9512497186660767}
+08/30/2021 17:58:48 - INFO - __main__ - Step 26832: {'lr': 0.00046606899708763174, 'samples': 5151744, 'steps': 26831, 'loss/train': 1.0352290868759155}
+08/30/2021 17:58:50 - INFO - __main__ - Step 26833: {'lr': 0.0004660663276515124, 'samples': 5151936, 'steps': 26832, 'loss/train': 1.424996256828308}
+08/30/2021 17:58:50 - INFO - __main__ - Step 26834: {'lr': 0.00046606365811803686, 'samples': 5152128, 'steps': 26833, 'loss/train': 1.511102557182312}
+08/30/2021 17:58:50 - INFO - __main__ - Step 26835: {'lr': 0.0004660609884872064, 'samples': 5152320, 'steps': 26834, 'loss/train': 1.5556164979934692}
+08/30/2021 17:58:51 - INFO - __main__ - Step 26836: {'lr': 0.00046605831875902215, 'samples': 5152512, 'steps': 26835, 'loss/train': 1.4919860363006592}
+08/30/2021 17:58:51 - INFO - __main__ - Step 26837: {'lr': 0.00046605564893348545, 'samples': 5152704, 'steps': 26836, 'loss/train': 1.5208078622817993}
+08/30/2021 17:58:52 - INFO - __main__ - Step 26838: {'lr': 0.0004660529790105974, 'samples': 5152896, 'steps': 26837, 'loss/train': 1.2910549640655518}
+08/30/2021 17:58:53 - INFO - __main__ - Step 26839: {'lr': 0.00046605030899035915, 'samples': 5153088, 'steps': 26838, 'loss/train': 1.374462366104126}
+08/30/2021 17:58:53 - INFO - __main__ - Step 26840: {'lr': 0.000466047638872772, 'samples': 5153280, 'steps': 26839, 'loss/train': 2.2235822677612305}
+08/30/2021 17:58:54 - INFO - __main__ - Step 26841: {'lr': 0.0004660449686578371, 'samples': 5153472, 'steps': 26840, 'loss/train': 1.8461415767669678}
+08/30/2021 17:58:54 - INFO - __main__ - Step 26842: {'lr': 0.0004660422983455557, 'samples': 5153664, 'steps': 26841, 'loss/train': 1.227088451385498}
+08/30/2021 17:58:56 - INFO - __main__ - Step 26843: {'lr': 0.0004660396279359289, 'samples': 5153856, 'steps': 26842, 'loss/train': 1.391221284866333}
+08/30/2021 17:58:56 - INFO - __main__ - Step 26844: {'lr': 0.000466036957428958, 'samples': 5154048, 'steps': 26843, 'loss/train': 1.4195990562438965}
+08/30/2021 17:58:57 - INFO - __main__ - Step 26845: {'lr': 0.0004660342868246442, 'samples': 5154240, 'steps': 26844, 'loss/train': 1.849786400794983}
+08/30/2021 17:58:57 - INFO - __main__ - Step 26846: {'lr': 0.0004660316161229887, 'samples': 5154432, 'steps': 26845, 'loss/train': 0.9779144525527954}
+08/30/2021 17:58:57 - INFO - __main__ - Step 26847: {'lr': 0.00046602894532399275, 'samples': 5154624, 'steps': 26846, 'loss/train': 1.4024840593338013}
+08/30/2021 17:58:59 - INFO - __main__ - Step 26848: {'lr': 0.00046602627442765744, 'samples': 5154816, 'steps': 26847, 'loss/train': 1.672475814819336}
+08/30/2021 17:58:59 - INFO - __main__ - Step 26849: {'lr': 0.00046602360343398397, 'samples': 5155008, 'steps': 26848, 'loss/train': 2.846569061279297}
+08/30/2021 17:58:59 - INFO - __main__ - Step 26850: {'lr': 0.0004660209323429736, 'samples': 5155200, 'steps': 26849, 'loss/train': 1.5409947633743286}
+08/30/2021 17:59:00 - INFO - __main__ - Step 26851: {'lr': 0.0004660182611546276, 'samples': 5155392, 'steps': 26850, 'loss/train': 1.9352277517318726}
+08/30/2021 17:59:00 - INFO - __main__ - Step 26852: {'lr': 0.0004660155898689471, 'samples': 5155584, 'steps': 26851, 'loss/train': 1.462173581123352}
+08/30/2021 17:59:01 - INFO - __main__ - Step 26853: {'lr': 0.0004660129184859332, 'samples': 5155776, 'steps': 26852, 'loss/train': 1.3452694416046143}
+08/30/2021 17:59:02 - INFO - __main__ - Step 26854: {'lr': 0.00046601024700558736, 'samples': 5155968, 'steps': 26853, 'loss/train': 1.82614004611969}
+08/30/2021 17:59:02 - INFO - __main__ - Step 26855: {'lr': 0.0004660075754279105, 'samples': 5156160, 'steps': 26854, 'loss/train': 0.9493875503540039}
+08/30/2021 17:59:03 - INFO - __main__ - Step 26856: {'lr': 0.00046600490375290406, 'samples': 5156352, 'steps': 26855, 'loss/train': 1.6828885078430176}
+08/30/2021 17:59:03 - INFO - __main__ - Step 26857: {'lr': 0.0004660022319805691, 'samples': 5156544, 'steps': 26856, 'loss/train': 1.6080266237258911}
+08/30/2021 17:59:03 - INFO - __main__ - Step 26858: {'lr': 0.0004659995601109069, 'samples': 5156736, 'steps': 26857, 'loss/train': 1.231449007987976}
+08/30/2021 17:59:05 - INFO - __main__ - Step 26859: {'lr': 0.0004659968881439186, 'samples': 5156928, 'steps': 26858, 'loss/train': 0.4787122309207916}
+08/30/2021 17:59:06 - INFO - __main__ - Step 26860: {'lr': 0.00046599421607960545, 'samples': 5157120, 'steps': 26859, 'loss/train': 1.3173683881759644}
+08/30/2021 17:59:06 - INFO - __main__ - Step 26861: {'lr': 0.0004659915439179686, 'samples': 5157312, 'steps': 26860, 'loss/train': 0.1036704033613205}
+08/30/2021 17:59:06 - INFO - __main__ - Step 26862: {'lr': 0.0004659888716590094, 'samples': 5157504, 'steps': 26861, 'loss/train': 1.4828739166259766}
+08/30/2021 17:59:07 - INFO - __main__ - Step 26863: {'lr': 0.00046598619930272883, 'samples': 5157696, 'steps': 26862, 'loss/train': 1.2362053394317627}
+08/30/2021 17:59:08 - INFO - __main__ - Step 26864: {'lr': 0.00046598352684912824, 'samples': 5157888, 'steps': 26863, 'loss/train': 1.6815341711044312}
+08/30/2021 17:59:09 - INFO - __main__ - Step 26865: {'lr': 0.0004659808542982088, 'samples': 5158080, 'steps': 26864, 'loss/train': 1.1082732677459717}
+08/30/2021 17:59:09 - INFO - __main__ - Step 26866: {'lr': 0.0004659781816499718, 'samples': 5158272, 'steps': 26865, 'loss/train': 1.7296682596206665}
+08/30/2021 17:59:09 - INFO - __main__ - Step 26867: {'lr': 0.0004659755089044183, 'samples': 5158464, 'steps': 26866, 'loss/train': 1.1451698541641235}
+08/30/2021 17:59:10 - INFO - __main__ - Step 26868: {'lr': 0.00046597283606154957, 'samples': 5158656, 'steps': 26867, 'loss/train': 1.3216966390609741}
+08/30/2021 17:59:12 - INFO - __main__ - Step 26869: {'lr': 0.0004659701631213668, 'samples': 5158848, 'steps': 26868, 'loss/train': 0.9072578549385071}
+08/30/2021 17:59:12 - INFO - __main__ - Step 26870: {'lr': 0.00046596749008387124, 'samples': 5159040, 'steps': 26869, 'loss/train': 1.7794842720031738}
+08/30/2021 17:59:13 - INFO - __main__ - Step 26871: {'lr': 0.00046596481694906403, 'samples': 5159232, 'steps': 26870, 'loss/train': 1.610386610031128}
+08/30/2021 17:59:13 - INFO - __main__ - Step 26872: {'lr': 0.00046596214371694643, 'samples': 5159424, 'steps': 26871, 'loss/train': 1.3272669315338135}
+08/30/2021 17:59:13 - INFO - __main__ - Step 26873: {'lr': 0.00046595947038751963, 'samples': 5159616, 'steps': 26872, 'loss/train': 1.3920873403549194}
+08/30/2021 17:59:15 - INFO - __main__ - Step 26874: {'lr': 0.00046595679696078476, 'samples': 5159808, 'steps': 26873, 'loss/train': 2.0769612789154053}
+08/30/2021 17:59:15 - INFO - __main__ - Step 26875: {'lr': 0.00046595412343674317, 'samples': 5160000, 'steps': 26874, 'loss/train': 1.1637133359909058}
+08/30/2021 17:59:15 - INFO - __main__ - Step 26876: {'lr': 0.00046595144981539596, 'samples': 5160192, 'steps': 26875, 'loss/train': 1.4622235298156738}
+08/30/2021 17:59:16 - INFO - __main__ - Step 26877: {'lr': 0.00046594877609674437, 'samples': 5160384, 'steps': 26876, 'loss/train': 1.3788200616836548}
+08/30/2021 17:59:16 - INFO - __main__ - Step 26878: {'lr': 0.00046594610228078954, 'samples': 5160576, 'steps': 26877, 'loss/train': 1.8409117460250854}
+08/30/2021 17:59:18 - INFO - __main__ - Step 26879: {'lr': 0.00046594342836753276, 'samples': 5160768, 'steps': 26878, 'loss/train': 1.4835433959960938}
+08/30/2021 17:59:18 - INFO - __main__ - Step 26880: {'lr': 0.0004659407543569752, 'samples': 5160960, 'steps': 26879, 'loss/train': 0.2934632897377014}
+08/30/2021 17:59:19 - INFO - __main__ - Step 26881: {'lr': 0.0004659380802491181, 'samples': 5161152, 'steps': 26880, 'loss/train': 0.262529581785202}
+08/30/2021 17:59:19 - INFO - __main__ - Step 26882: {'lr': 0.00046593540604396256, 'samples': 5161344, 'steps': 26881, 'loss/train': 1.2058743238449097}
+08/30/2021 17:59:19 - INFO - __main__ - Step 26883: {'lr': 0.00046593273174150995, 'samples': 5161536, 'steps': 26882, 'loss/train': 1.7408865690231323}
+08/30/2021 17:59:20 - INFO - __main__ - Step 26884: {'lr': 0.0004659300573417613, 'samples': 5161728, 'steps': 26883, 'loss/train': 0.8488700985908508}
+08/30/2021 17:59:22 - INFO - __main__ - Step 26885: {'lr': 0.00046592738284471794, 'samples': 5161920, 'steps': 26884, 'loss/train': 1.6995694637298584}
+08/30/2021 17:59:22 - INFO - __main__ - Step 26886: {'lr': 0.000465924708250381, 'samples': 5162112, 'steps': 26885, 'loss/train': 1.3161303997039795}
+08/30/2021 17:59:22 - INFO - __main__ - Step 26887: {'lr': 0.00046592203355875177, 'samples': 5162304, 'steps': 26886, 'loss/train': 1.1734241247177124}
+08/30/2021 17:59:23 - INFO - __main__ - Step 26888: {'lr': 0.00046591935876983136, 'samples': 5162496, 'steps': 26887, 'loss/train': 0.04021792858839035}
+08/30/2021 17:59:23 - INFO - __main__ - Step 26889: {'lr': 0.0004659166838836211, 'samples': 5162688, 'steps': 26888, 'loss/train': 1.476667046546936}
+08/30/2021 17:59:24 - INFO - __main__ - Step 26890: {'lr': 0.000465914008900122, 'samples': 5162880, 'steps': 26889, 'loss/train': 2.0075557231903076}
+08/30/2021 17:59:25 - INFO - __main__ - Step 26891: {'lr': 0.00046591133381933546, 'samples': 5163072, 'steps': 26890, 'loss/train': 1.437656044960022}
+08/30/2021 17:59:26 - INFO - __main__ - Step 26892: {'lr': 0.0004659086586412626, 'samples': 5163264, 'steps': 26891, 'loss/train': 0.061180729418992996}
+08/30/2021 17:59:26 - INFO - __main__ - Step 26893: {'lr': 0.0004659059833659046, 'samples': 5163456, 'steps': 26892, 'loss/train': 0.9740949869155884}
+08/30/2021 17:59:26 - INFO - __main__ - Step 26894: {'lr': 0.0004659033079932627, 'samples': 5163648, 'steps': 26893, 'loss/train': 2.013864278793335}
+08/30/2021 17:59:27 - INFO - __main__ - Step 26895: {'lr': 0.00046590063252333806, 'samples': 5163840, 'steps': 26894, 'loss/train': 1.2683641910552979}
+08/30/2021 17:59:28 - INFO - __main__ - Step 26896: {'lr': 0.000465897956956132, 'samples': 5164032, 'steps': 26895, 'loss/train': 0.9575828313827515}
+08/30/2021 17:59:29 - INFO - __main__ - Step 26897: {'lr': 0.0004658952812916456, 'samples': 5164224, 'steps': 26896, 'loss/train': 1.3946799039840698}
+08/30/2021 17:59:29 - INFO - __main__ - Step 26898: {'lr': 0.0004658926055298802, 'samples': 5164416, 'steps': 26897, 'loss/train': 1.4117990732192993}
+08/30/2021 17:59:29 - INFO - __main__ - Step 26899: {'lr': 0.0004658899296708369, 'samples': 5164608, 'steps': 26898, 'loss/train': 1.3764944076538086}
+08/30/2021 17:59:30 - INFO - __main__ - Step 26900: {'lr': 0.00046588725371451685, 'samples': 5164800, 'steps': 26899, 'loss/train': 1.512864589691162}
+08/30/2021 17:59:31 - INFO - __main__ - Step 26901: {'lr': 0.00046588457766092134, 'samples': 5164992, 'steps': 26900, 'loss/train': 1.5008000135421753}
+08/30/2021 17:59:31 - INFO - __main__ - Step 26902: {'lr': 0.00046588190151005163, 'samples': 5165184, 'steps': 26901, 'loss/train': 1.5895146131515503}
+08/30/2021 17:59:32 - INFO - __main__ - Step 26903: {'lr': 0.00046587922526190883, 'samples': 5165376, 'steps': 26902, 'loss/train': 1.352649211883545}
+08/30/2021 17:59:32 - INFO - __main__ - Step 26904: {'lr': 0.00046587654891649423, 'samples': 5165568, 'steps': 26903, 'loss/train': 2.2640106678009033}
+08/30/2021 17:59:32 - INFO - __main__ - Step 26905: {'lr': 0.00046587387247380897, 'samples': 5165760, 'steps': 26904, 'loss/train': 1.7070716619491577}
+08/30/2021 17:59:34 - INFO - __main__ - Step 26906: {'lr': 0.00046587119593385424, 'samples': 5165952, 'steps': 26905, 'loss/train': 1.495260238647461}
+08/30/2021 17:59:34 - INFO - __main__ - Step 26907: {'lr': 0.00046586851929663134, 'samples': 5166144, 'steps': 26906, 'loss/train': 1.2227405309677124}
+08/30/2021 17:59:35 - INFO - __main__ - Step 26908: {'lr': 0.00046586584256214135, 'samples': 5166336, 'steps': 26907, 'loss/train': 1.274914026260376}
+08/30/2021 17:59:35 - INFO - __main__ - Step 26909: {'lr': 0.0004658631657303856, 'samples': 5166528, 'steps': 26908, 'loss/train': 0.8560934662818909}
+08/30/2021 17:59:36 - INFO - __main__ - Step 26910: {'lr': 0.0004658604888013652, 'samples': 5166720, 'steps': 26909, 'loss/train': 1.6615206003189087}
+08/30/2021 17:59:36 - INFO - __main__ - Step 26911: {'lr': 0.00046585781177508137, 'samples': 5166912, 'steps': 26910, 'loss/train': 2.079286813735962}
+08/30/2021 17:59:38 - INFO - __main__ - Step 26912: {'lr': 0.0004658551346515354, 'samples': 5167104, 'steps': 26911, 'loss/train': 0.07465283572673798}
+08/30/2021 17:59:38 - INFO - __main__ - Step 26913: {'lr': 0.00046585245743072833, 'samples': 5167296, 'steps': 26912, 'loss/train': 1.620635986328125}
+08/30/2021 17:59:39 - INFO - __main__ - Step 26914: {'lr': 0.0004658497801126616, 'samples': 5167488, 'steps': 26913, 'loss/train': 1.3414040803909302}
+08/30/2021 17:59:39 - INFO - __main__ - Step 26915: {'lr': 0.00046584710269733623, 'samples': 5167680, 'steps': 26914, 'loss/train': 1.435752272605896}
+08/30/2021 17:59:39 - INFO - __main__ - Step 26916: {'lr': 0.00046584442518475354, 'samples': 5167872, 'steps': 26915, 'loss/train': 1.3708261251449585}
+08/30/2021 17:59:41 - INFO - __main__ - Step 26917: {'lr': 0.0004658417475749146, 'samples': 5168064, 'steps': 26916, 'loss/train': 0.06692387163639069}
+08/30/2021 17:59:41 - INFO - __main__ - Step 26918: {'lr': 0.00046583906986782074, 'samples': 5168256, 'steps': 26917, 'loss/train': 1.6083214282989502}
+08/30/2021 17:59:42 - INFO - __main__ - Step 26919: {'lr': 0.0004658363920634732, 'samples': 5168448, 'steps': 26918, 'loss/train': 1.3549399375915527}
+08/30/2021 17:59:42 - INFO - __main__ - Step 26920: {'lr': 0.000465833714161873, 'samples': 5168640, 'steps': 26919, 'loss/train': 1.7720448970794678}
+08/30/2021 17:59:42 - INFO - __main__ - Step 26921: {'lr': 0.00046583103616302146, 'samples': 5168832, 'steps': 26920, 'loss/train': 0.20303179323673248}
+08/30/2021 17:59:43 - INFO - __main__ - Step 26922: {'lr': 0.0004658283580669198, 'samples': 5169024, 'steps': 26921, 'loss/train': 1.0080013275146484}
+08/30/2021 17:59:45 - INFO - __main__ - Step 26923: {'lr': 0.0004658256798735693, 'samples': 5169216, 'steps': 26922, 'loss/train': 1.368169903755188}
+08/30/2021 17:59:45 - INFO - __main__ - Step 26924: {'lr': 0.000465823001582971, 'samples': 5169408, 'steps': 26923, 'loss/train': 1.1282775402069092}
+08/30/2021 17:59:46 - INFO - __main__ - Step 26925: {'lr': 0.00046582032319512624, 'samples': 5169600, 'steps': 26924, 'loss/train': 2.120058536529541}
+08/30/2021 17:59:46 - INFO - __main__ - Step 26926: {'lr': 0.00046581764471003605, 'samples': 5169792, 'steps': 26925, 'loss/train': 1.5686094760894775}
+08/30/2021 17:59:46 - INFO - __main__ - Step 26927: {'lr': 0.0004658149661277019, 'samples': 5169984, 'steps': 26926, 'loss/train': 1.1897062063217163}
+08/30/2021 17:59:48 - INFO - __main__ - Step 26928: {'lr': 0.0004658122874481248, 'samples': 5170176, 'steps': 26927, 'loss/train': 1.6875969171524048}
+08/30/2021 17:59:48 - INFO - __main__ - Step 26929: {'lr': 0.000465809608671306, 'samples': 5170368, 'steps': 26928, 'loss/train': 1.5299280881881714}
+08/30/2021 17:59:49 - INFO - __main__ - Step 26930: {'lr': 0.0004658069297972467, 'samples': 5170560, 'steps': 26929, 'loss/train': 1.452596664428711}
+08/30/2021 17:59:49 - INFO - __main__ - Step 26931: {'lr': 0.00046580425082594823, 'samples': 5170752, 'steps': 26930, 'loss/train': 1.6443637609481812}
+08/30/2021 17:59:49 - INFO - __main__ - Step 26932: {'lr': 0.00046580157175741155, 'samples': 5170944, 'steps': 26931, 'loss/train': 1.6452678442001343}
+08/30/2021 17:59:51 - INFO - __main__ - Step 26933: {'lr': 0.0004657988925916381, 'samples': 5171136, 'steps': 26932, 'loss/train': 1.4347848892211914}
+08/30/2021 17:59:51 - INFO - __main__ - Step 26934: {'lr': 0.000465796213328629, 'samples': 5171328, 'steps': 26933, 'loss/train': 1.8302736282348633}
+08/30/2021 17:59:52 - INFO - __main__ - Step 26935: {'lr': 0.00046579353396838545, 'samples': 5171520, 'steps': 26934, 'loss/train': 1.3067013025283813}
+08/30/2021 17:59:52 - INFO - __main__ - Step 26936: {'lr': 0.00046579085451090864, 'samples': 5171712, 'steps': 26935, 'loss/train': 2.155531406402588}
+08/30/2021 17:59:52 - INFO - __main__ - Step 26937: {'lr': 0.00046578817495619983, 'samples': 5171904, 'steps': 26936, 'loss/train': 1.717665672302246}
+08/30/2021 17:59:54 - INFO - __main__ - Step 26938: {'lr': 0.0004657854953042602, 'samples': 5172096, 'steps': 26937, 'loss/train': 1.2332600355148315}
+08/30/2021 17:59:55 - INFO - __main__ - Step 26939: {'lr': 0.00046578281555509094, 'samples': 5172288, 'steps': 26938, 'loss/train': 1.4292773008346558}
+08/30/2021 17:59:55 - INFO - __main__ - Step 26940: {'lr': 0.00046578013570869325, 'samples': 5172480, 'steps': 26939, 'loss/train': 0.8554905652999878}
+08/30/2021 17:59:55 - INFO - __main__ - Step 26941: {'lr': 0.00046577745576506844, 'samples': 5172672, 'steps': 26940, 'loss/train': 1.1735535860061646}
+08/30/2021 17:59:56 - INFO - __main__ - Step 26942: {'lr': 0.00046577477572421757, 'samples': 5172864, 'steps': 26941, 'loss/train': 1.6115187406539917}
+08/30/2021 17:59:57 - INFO - __main__ - Step 26943: {'lr': 0.0004657720955861419, 'samples': 5173056, 'steps': 26942, 'loss/train': 1.2197036743164062}
+08/30/2021 17:59:58 - INFO - __main__ - Step 26944: {'lr': 0.00046576941535084274, 'samples': 5173248, 'steps': 26943, 'loss/train': 1.4582329988479614}
+08/30/2021 17:59:58 - INFO - __main__ - Step 26945: {'lr': 0.0004657667350183211, 'samples': 5173440, 'steps': 26944, 'loss/train': 1.435172200202942}
+08/30/2021 17:59:58 - INFO - __main__ - Step 26946: {'lr': 0.00046576405458857836, 'samples': 5173632, 'steps': 26945, 'loss/train': 1.965851068496704}
+08/30/2021 17:59:59 - INFO - __main__ - Step 26947: {'lr': 0.0004657613740616157, 'samples': 5173824, 'steps': 26946, 'loss/train': 1.4533733129501343}
+08/30/2021 18:00:00 - INFO - __main__ - Step 26948: {'lr': 0.0004657586934374342, 'samples': 5174016, 'steps': 26947, 'loss/train': 2.0454695224761963}
+08/30/2021 18:00:01 - INFO - __main__ - Step 26949: {'lr': 0.0004657560127160352, 'samples': 5174208, 'steps': 26948, 'loss/train': 0.8816270232200623}
+08/30/2021 18:00:01 - INFO - __main__ - Step 26950: {'lr': 0.00046575333189741993, 'samples': 5174400, 'steps': 26949, 'loss/train': 1.6166325807571411}
+08/30/2021 18:00:01 - INFO - __main__ - Step 26951: {'lr': 0.00046575065098158945, 'samples': 5174592, 'steps': 26950, 'loss/train': 1.4760130643844604}
+08/30/2021 18:00:02 - INFO - __main__ - Step 26952: {'lr': 0.0004657479699685451, 'samples': 5174784, 'steps': 26951, 'loss/train': 1.284529447555542}
+08/30/2021 18:00:03 - INFO - __main__ - Step 26953: {'lr': 0.00046574528885828803, 'samples': 5174976, 'steps': 26952, 'loss/train': 1.1363043785095215}
+08/30/2021 18:00:04 - INFO - __main__ - Step 26954: {'lr': 0.0004657426076508195, 'samples': 5175168, 'steps': 26953, 'loss/train': 0.8876258134841919}
+08/30/2021 18:00:04 - INFO - __main__ - Step 26955: {'lr': 0.00046573992634614064, 'samples': 5175360, 'steps': 26954, 'loss/train': 1.6934928894042969}
+08/30/2021 18:00:04 - INFO - __main__ - Step 26956: {'lr': 0.00046573724494425274, 'samples': 5175552, 'steps': 26955, 'loss/train': 1.5810352563858032}
+08/30/2021 18:00:05 - INFO - __main__ - Step 26957: {'lr': 0.00046573456344515694, 'samples': 5175744, 'steps': 26956, 'loss/train': 1.250922679901123}
+08/30/2021 18:00:06 - INFO - __main__ - Step 26958: {'lr': 0.00046573188184885445, 'samples': 5175936, 'steps': 26957, 'loss/train': 1.3188906908035278}
+08/30/2021 18:00:07 - INFO - __main__ - Step 26959: {'lr': 0.0004657292001553465, 'samples': 5176128, 'steps': 26958, 'loss/train': 0.06328149139881134}
+08/30/2021 18:00:07 - INFO - __main__ - Step 26960: {'lr': 0.0004657265183646344, 'samples': 5176320, 'steps': 26959, 'loss/train': 1.6511822938919067}
+08/30/2021 18:00:07 - INFO - __main__ - Step 26961: {'lr': 0.00046572383647671913, 'samples': 5176512, 'steps': 26960, 'loss/train': 1.7765454053878784}
+08/30/2021 18:00:08 - INFO - __main__ - Step 26962: {'lr': 0.0004657211544916021, 'samples': 5176704, 'steps': 26961, 'loss/train': 0.3017668128013611}
+08/30/2021 18:00:08 - INFO - __main__ - Step 26963: {'lr': 0.00046571847240928444, 'samples': 5176896, 'steps': 26962, 'loss/train': 1.1066577434539795}
+08/30/2021 18:00:10 - INFO - __main__ - Step 26964: {'lr': 0.0004657157902297674, 'samples': 5177088, 'steps': 26963, 'loss/train': 1.6019381284713745}
+08/30/2021 18:00:10 - INFO - __main__ - Step 26965: {'lr': 0.00046571310795305213, 'samples': 5177280, 'steps': 26964, 'loss/train': 1.538810133934021}
+08/30/2021 18:00:10 - INFO - __main__ - Step 26966: {'lr': 0.0004657104255791398, 'samples': 5177472, 'steps': 26965, 'loss/train': 1.459782600402832}
+08/30/2021 18:00:11 - INFO - __main__ - Step 26967: {'lr': 0.0004657077431080317, 'samples': 5177664, 'steps': 26966, 'loss/train': 0.059555113315582275}
+08/30/2021 18:00:11 - INFO - __main__ - Step 26968: {'lr': 0.00046570506053972906, 'samples': 5177856, 'steps': 26967, 'loss/train': 0.24769888818264008}
+08/30/2021 18:00:13 - INFO - __main__ - Step 26969: {'lr': 0.000465702377874233, 'samples': 5178048, 'steps': 26968, 'loss/train': 1.255476474761963}
+08/30/2021 18:00:13 - INFO - __main__ - Step 26970: {'lr': 0.00046569969511154485, 'samples': 5178240, 'steps': 26969, 'loss/train': 1.66780424118042}
+08/30/2021 18:00:13 - INFO - __main__ - Step 26971: {'lr': 0.0004656970122516657, 'samples': 5178432, 'steps': 26970, 'loss/train': 1.5754352807998657}
+08/30/2021 18:00:14 - INFO - __main__ - Step 26972: {'lr': 0.0004656943292945968, 'samples': 5178624, 'steps': 26971, 'loss/train': 1.924007773399353}
+08/30/2021 18:00:14 - INFO - __main__ - Step 26973: {'lr': 0.0004656916462403394, 'samples': 5178816, 'steps': 26972, 'loss/train': 1.4658902883529663}
+08/30/2021 18:00:17 - INFO - __main__ - Step 26974: {'lr': 0.0004656889630888946, 'samples': 5179008, 'steps': 26973, 'loss/train': 2.0741961002349854}
+08/30/2021 18:00:18 - INFO - __main__ - Step 26975: {'lr': 0.0004656862798402638, 'samples': 5179200, 'steps': 26974, 'loss/train': 1.6244912147521973}
+08/30/2021 18:00:18 - INFO - __main__ - Step 26976: {'lr': 0.00046568359649444796, 'samples': 5179392, 'steps': 26975, 'loss/train': 1.8216925859451294}
+08/30/2021 18:00:18 - INFO - __main__ - Step 26977: {'lr': 0.0004656809130514485, 'samples': 5179584, 'steps': 26976, 'loss/train': 1.8022947311401367}
+08/30/2021 18:00:19 - INFO - __main__ - Step 26978: {'lr': 0.00046567822951126646, 'samples': 5179776, 'steps': 26977, 'loss/train': 1.8025085926055908}
+08/30/2021 18:00:19 - INFO - __main__ - Step 26979: {'lr': 0.00046567554587390324, 'samples': 5179968, 'steps': 26978, 'loss/train': 1.7827305793762207}
+08/30/2021 18:00:19 - INFO - __main__ - Step 26980: {'lr': 0.00046567286213935994, 'samples': 5180160, 'steps': 26979, 'loss/train': 1.6404439210891724}
+08/30/2021 18:00:20 - INFO - __main__ - Step 26981: {'lr': 0.00046567017830763776, 'samples': 5180352, 'steps': 26980, 'loss/train': 1.7375833988189697}
+08/30/2021 18:00:22 - INFO - __main__ - Step 26982: {'lr': 0.0004656674943787379, 'samples': 5180544, 'steps': 26981, 'loss/train': 1.5636651515960693}
+08/30/2021 18:00:22 - INFO - __main__ - Step 26983: {'lr': 0.0004656648103526616, 'samples': 5180736, 'steps': 26982, 'loss/train': 1.382455825805664}
+08/30/2021 18:00:23 - INFO - __main__ - Step 26984: {'lr': 0.00046566212622941005, 'samples': 5180928, 'steps': 26983, 'loss/train': 1.688787579536438}
+08/30/2021 18:00:23 - INFO - __main__ - Step 26985: {'lr': 0.00046565944200898453, 'samples': 5181120, 'steps': 26984, 'loss/train': 1.9001823663711548}
+08/30/2021 18:00:23 - INFO - __main__ - Step 26986: {'lr': 0.00046565675769138614, 'samples': 5181312, 'steps': 26985, 'loss/train': 0.9823494553565979}
+08/30/2021 18:00:25 - INFO - __main__ - Step 26987: {'lr': 0.00046565407327661614, 'samples': 5181504, 'steps': 26986, 'loss/train': 1.2785985469818115}
+08/30/2021 18:00:25 - INFO - __main__ - Step 26988: {'lr': 0.0004656513887646758, 'samples': 5181696, 'steps': 26987, 'loss/train': 0.9510458707809448}
+08/30/2021 18:00:26 - INFO - __main__ - Step 26989: {'lr': 0.00046564870415556625, 'samples': 5181888, 'steps': 26988, 'loss/train': 1.7741374969482422}
+08/30/2021 18:00:26 - INFO - __main__ - Step 26990: {'lr': 0.0004656460194492887, 'samples': 5182080, 'steps': 26989, 'loss/train': 1.8898942470550537}
+08/30/2021 18:00:26 - INFO - __main__ - Step 26991: {'lr': 0.0004656433346458444, 'samples': 5182272, 'steps': 26990, 'loss/train': 1.4533418416976929}
+08/30/2021 18:00:28 - INFO - __main__ - Step 26992: {'lr': 0.0004656406497452345, 'samples': 5182464, 'steps': 26991, 'loss/train': 0.4570915102958679}
+08/30/2021 18:00:29 - INFO - __main__ - Step 26993: {'lr': 0.0004656379647474603, 'samples': 5182656, 'steps': 26992, 'loss/train': 1.7154120206832886}
+08/30/2021 18:00:29 - INFO - __main__ - Step 26994: {'lr': 0.0004656352796525229, 'samples': 5182848, 'steps': 26993, 'loss/train': 1.6002998352050781}
+08/30/2021 18:00:29 - INFO - __main__ - Step 26995: {'lr': 0.0004656325944604236, 'samples': 5183040, 'steps': 26994, 'loss/train': 2.3379414081573486}
+08/30/2021 18:00:30 - INFO - __main__ - Step 26996: {'lr': 0.00046562990917116366, 'samples': 5183232, 'steps': 26995, 'loss/train': 2.3268332481384277}
+08/30/2021 18:00:30 - INFO - __main__ - Step 26997: {'lr': 0.0004656272237847441, 'samples': 5183424, 'steps': 26996, 'loss/train': 1.5761443376541138}
+08/30/2021 18:00:31 - INFO - __main__ - Step 26998: {'lr': 0.0004656245383011663, 'samples': 5183616, 'steps': 26997, 'loss/train': 1.7556006908416748}
+08/30/2021 18:00:32 - INFO - __main__ - Step 26999: {'lr': 0.00046562185272043137, 'samples': 5183808, 'steps': 26998, 'loss/train': 1.1383898258209229}
+08/30/2021 18:00:32 - INFO - __main__ - Step 27000: {'lr': 0.00046561916704254057, 'samples': 5184000, 'steps': 26999, 'loss/train': 1.391679048538208}
+08/30/2021 18:00:33 - INFO - __main__ - Step 27001: {'lr': 0.0004656164812674951, 'samples': 5184192, 'steps': 27000, 'loss/train': 1.0219672918319702}
+08/30/2021 18:00:33 - INFO - __main__ - Step 27002: {'lr': 0.00046561379539529626, 'samples': 5184384, 'steps': 27001, 'loss/train': 1.7161716222763062}
+08/30/2021 18:00:34 - INFO - __main__ - Step 27003: {'lr': 0.0004656111094259451, 'samples': 5184576, 'steps': 27002, 'loss/train': 1.537265658378601}
+08/30/2021 18:00:35 - INFO - __main__ - Step 27004: {'lr': 0.0004656084233594429, 'samples': 5184768, 'steps': 27003, 'loss/train': 1.6356860399246216}
+08/30/2021 18:00:35 - INFO - __main__ - Step 27005: {'lr': 0.0004656057371957908, 'samples': 5184960, 'steps': 27004, 'loss/train': 1.807446837425232}
+08/30/2021 18:00:36 - INFO - __main__ - Step 27006: {'lr': 0.00046560305093499015, 'samples': 5185152, 'steps': 27005, 'loss/train': 1.366638422012329}
+08/30/2021 18:00:36 - INFO - __main__ - Step 27007: {'lr': 0.00046560036457704215, 'samples': 5185344, 'steps': 27006, 'loss/train': 1.4681525230407715}
+08/30/2021 18:00:37 - INFO - __main__ - Step 27008: {'lr': 0.00046559767812194786, 'samples': 5185536, 'steps': 27007, 'loss/train': 1.4224255084991455}
+08/30/2021 18:00:38 - INFO - __main__ - Step 27009: {'lr': 0.0004655949915697086, 'samples': 5185728, 'steps': 27008, 'loss/train': 1.3201313018798828}
+08/30/2021 18:00:38 - INFO - __main__ - Step 27010: {'lr': 0.0004655923049203256, 'samples': 5185920, 'steps': 27009, 'loss/train': 1.4706474542617798}
+08/30/2021 18:00:39 - INFO - __main__ - Step 27011: {'lr': 0.00046558961817380005, 'samples': 5186112, 'steps': 27010, 'loss/train': 2.05584454536438}
+08/30/2021 18:00:39 - INFO - __main__ - Step 27012: {'lr': 0.00046558693133013306, 'samples': 5186304, 'steps': 27011, 'loss/train': 1.6807987689971924}
+08/30/2021 18:00:39 - INFO - __main__ - Step 27013: {'lr': 0.000465584244389326, 'samples': 5186496, 'steps': 27012, 'loss/train': 1.2257968187332153}
+08/30/2021 18:00:41 - INFO - __main__ - Step 27014: {'lr': 0.00046558155735137996, 'samples': 5186688, 'steps': 27013, 'loss/train': 1.448624610900879}
+08/30/2021 18:00:41 - INFO - __main__ - Step 27015: {'lr': 0.00046557887021629623, 'samples': 5186880, 'steps': 27014, 'loss/train': 1.1582815647125244}
+08/30/2021 18:00:41 - INFO - __main__ - Step 27016: {'lr': 0.000465576182984076, 'samples': 5187072, 'steps': 27015, 'loss/train': 2.0148961544036865}
+08/30/2021 18:00:42 - INFO - __main__ - Step 27017: {'lr': 0.0004655734956547204, 'samples': 5187264, 'steps': 27016, 'loss/train': 1.5241016149520874}
+08/30/2021 18:00:42 - INFO - __main__ - Step 27018: {'lr': 0.00046557080822823076, 'samples': 5187456, 'steps': 27017, 'loss/train': 1.4491941928863525}
+08/30/2021 18:00:44 - INFO - __main__ - Step 27019: {'lr': 0.0004655681207046083, 'samples': 5187648, 'steps': 27018, 'loss/train': 0.8379098176956177}
+08/30/2021 18:00:44 - INFO - __main__ - Step 27020: {'lr': 0.0004655654330838541, 'samples': 5187840, 'steps': 27019, 'loss/train': 1.3857444524765015}
+08/30/2021 18:00:44 - INFO - __main__ - Step 27021: {'lr': 0.00046556274536596945, 'samples': 5188032, 'steps': 27020, 'loss/train': 1.6075927019119263}
+08/30/2021 18:00:45 - INFO - __main__ - Step 27022: {'lr': 0.00046556005755095555, 'samples': 5188224, 'steps': 27021, 'loss/train': 1.4196367263793945}
+08/30/2021 18:00:45 - INFO - __main__ - Step 27023: {'lr': 0.00046555736963881355, 'samples': 5188416, 'steps': 27022, 'loss/train': 1.0890384912490845}
+08/30/2021 18:00:47 - INFO - __main__ - Step 27024: {'lr': 0.0004655546816295448, 'samples': 5188608, 'steps': 27023, 'loss/train': 1.5265403985977173}
+08/30/2021 18:00:47 - INFO - __main__ - Step 27025: {'lr': 0.0004655519935231505, 'samples': 5188800, 'steps': 27024, 'loss/train': 1.6783900260925293}
+08/30/2021 18:00:47 - INFO - __main__ - Step 27026: {'lr': 0.00046554930531963166, 'samples': 5188992, 'steps': 27025, 'loss/train': 1.0980746746063232}
+08/30/2021 18:00:48 - INFO - __main__ - Step 27027: {'lr': 0.0004655466170189897, 'samples': 5189184, 'steps': 27026, 'loss/train': 1.1677947044372559}
+08/30/2021 18:00:48 - INFO - __main__ - Step 27028: {'lr': 0.0004655439286212257, 'samples': 5189376, 'steps': 27027, 'loss/train': 1.392407774925232}
+08/30/2021 18:00:50 - INFO - __main__ - Step 27029: {'lr': 0.00046554124012634105, 'samples': 5189568, 'steps': 27028, 'loss/train': 1.6881626844406128}
+08/30/2021 18:00:50 - INFO - __main__ - Step 27030: {'lr': 0.0004655385515343368, 'samples': 5189760, 'steps': 27029, 'loss/train': 1.3778564929962158}
+08/30/2021 18:00:51 - INFO - __main__ - Step 27031: {'lr': 0.0004655358628452142, 'samples': 5189952, 'steps': 27030, 'loss/train': 1.9335951805114746}
+08/30/2021 18:00:51 - INFO - __main__ - Step 27032: {'lr': 0.00046553317405897444, 'samples': 5190144, 'steps': 27031, 'loss/train': 1.3064842224121094}
+08/30/2021 18:00:51 - INFO - __main__ - Step 27033: {'lr': 0.0004655304851756188, 'samples': 5190336, 'steps': 27032, 'loss/train': 1.3732681274414062}
+08/30/2021 18:00:53 - INFO - __main__ - Step 27034: {'lr': 0.0004655277961951484, 'samples': 5190528, 'steps': 27033, 'loss/train': 1.7316031455993652}
+08/30/2021 18:00:54 - INFO - __main__ - Step 27035: {'lr': 0.00046552510711756444, 'samples': 5190720, 'steps': 27034, 'loss/train': 1.9706547260284424}
+08/30/2021 18:00:54 - INFO - __main__ - Step 27036: {'lr': 0.0004655224179428683, 'samples': 5190912, 'steps': 27035, 'loss/train': 1.7437993288040161}
+08/30/2021 18:00:54 - INFO - __main__ - Step 27037: {'lr': 0.00046551972867106106, 'samples': 5191104, 'steps': 27036, 'loss/train': 1.3878881931304932}
+08/30/2021 18:00:55 - INFO - __main__ - Step 27038: {'lr': 0.00046551703930214393, 'samples': 5191296, 'steps': 27037, 'loss/train': 1.2605842351913452}
+08/30/2021 18:00:56 - INFO - __main__ - Step 27039: {'lr': 0.00046551434983611823, 'samples': 5191488, 'steps': 27038, 'loss/train': 1.619400143623352}
+08/30/2021 18:00:57 - INFO - __main__ - Step 27040: {'lr': 0.00046551166027298505, 'samples': 5191680, 'steps': 27039, 'loss/train': 1.4501162767410278}
+08/30/2021 18:00:57 - INFO - __main__ - Step 27041: {'lr': 0.0004655089706127456, 'samples': 5191872, 'steps': 27040, 'loss/train': 1.5991936922073364}
+08/30/2021 18:00:57 - INFO - __main__ - Step 27042: {'lr': 0.00046550628085540114, 'samples': 5192064, 'steps': 27041, 'loss/train': 1.3747488260269165}
+08/30/2021 18:00:58 - INFO - __main__ - Step 27043: {'lr': 0.0004655035910009529, 'samples': 5192256, 'steps': 27042, 'loss/train': 1.0718268156051636}
+08/30/2021 18:00:58 - INFO - __main__ - Step 27044: {'lr': 0.00046550090104940207, 'samples': 5192448, 'steps': 27043, 'loss/train': 1.4601668119430542}
+08/30/2021 18:00:59 - INFO - __main__ - Step 27045: {'lr': 0.00046549821100074987, 'samples': 5192640, 'steps': 27044, 'loss/train': 1.5553958415985107}
+08/30/2021 18:01:00 - INFO - __main__ - Step 27046: {'lr': 0.0004654955208549975, 'samples': 5192832, 'steps': 27045, 'loss/train': 0.8060368895530701}
+08/30/2021 18:01:00 - INFO - __main__ - Step 27047: {'lr': 0.0004654928306121461, 'samples': 5193024, 'steps': 27046, 'loss/train': 1.4210699796676636}
+08/30/2021 18:01:00 - INFO - __main__ - Step 27048: {'lr': 0.000465490140272197, 'samples': 5193216, 'steps': 27047, 'loss/train': 1.130094289779663}
+08/30/2021 18:01:01 - INFO - __main__ - Step 27049: {'lr': 0.00046548744983515133, 'samples': 5193408, 'steps': 27048, 'loss/train': 1.4835467338562012}
+08/30/2021 18:01:02 - INFO - __main__ - Step 27050: {'lr': 0.0004654847593010104, 'samples': 5193600, 'steps': 27049, 'loss/train': 1.7109342813491821}
+08/30/2021 18:01:03 - INFO - __main__ - Step 27051: {'lr': 0.0004654820686697754, 'samples': 5193792, 'steps': 27050, 'loss/train': 1.5904674530029297}
+08/30/2021 18:01:03 - INFO - __main__ - Step 27052: {'lr': 0.00046547937794144743, 'samples': 5193984, 'steps': 27051, 'loss/train': 0.756737470626831}
+08/30/2021 18:01:03 - INFO - __main__ - Step 27053: {'lr': 0.00046547668711602774, 'samples': 5194176, 'steps': 27052, 'loss/train': 2.063991069793701}
+08/30/2021 18:01:04 - INFO - __main__ - Step 27054: {'lr': 0.0004654739961935177, 'samples': 5194368, 'steps': 27053, 'loss/train': 1.1815845966339111}
+08/30/2021 18:01:06 - INFO - __main__ - Step 27055: {'lr': 0.0004654713051739183, 'samples': 5194560, 'steps': 27054, 'loss/train': 1.8301626443862915}
+08/30/2021 18:01:06 - INFO - __main__ - Step 27056: {'lr': 0.000465468614057231, 'samples': 5194752, 'steps': 27055, 'loss/train': 1.7003332376480103}
+08/30/2021 18:01:06 - INFO - __main__ - Step 27057: {'lr': 0.0004654659228434567, 'samples': 5194944, 'steps': 27056, 'loss/train': 1.5856363773345947}
+08/30/2021 18:01:07 - INFO - __main__ - Step 27058: {'lr': 0.00046546323153259686, 'samples': 5195136, 'steps': 27057, 'loss/train': 0.06997363269329071}
+08/30/2021 18:01:07 - INFO - __main__ - Step 27059: {'lr': 0.00046546054012465253, 'samples': 5195328, 'steps': 27058, 'loss/train': 1.8706170320510864}
+08/30/2021 18:01:09 - INFO - __main__ - Step 27060: {'lr': 0.00046545784861962516, 'samples': 5195520, 'steps': 27059, 'loss/train': 1.5879230499267578}
+08/30/2021 18:01:09 - INFO - __main__ - Step 27061: {'lr': 0.00046545515701751567, 'samples': 5195712, 'steps': 27060, 'loss/train': 1.664392113685608}
+08/30/2021 18:01:10 - INFO - __main__ - Step 27062: {'lr': 0.00046545246531832547, 'samples': 5195904, 'steps': 27061, 'loss/train': 1.0261359214782715}
+08/30/2021 18:01:10 - INFO - __main__ - Step 27063: {'lr': 0.0004654497735220557, 'samples': 5196096, 'steps': 27062, 'loss/train': 1.1374526023864746}
+08/30/2021 18:01:10 - INFO - __main__ - Step 27064: {'lr': 0.0004654470816287076, 'samples': 5196288, 'steps': 27063, 'loss/train': 1.4947664737701416}
+08/30/2021 18:01:12 - INFO - __main__ - Step 27065: {'lr': 0.0004654443896382824, 'samples': 5196480, 'steps': 27064, 'loss/train': 1.6301007270812988}
+08/30/2021 18:01:13 - INFO - __main__ - Step 27066: {'lr': 0.0004654416975507812, 'samples': 5196672, 'steps': 27065, 'loss/train': 1.6354727745056152}
+08/30/2021 18:01:13 - INFO - __main__ - Step 27067: {'lr': 0.0004654390053662053, 'samples': 5196864, 'steps': 27066, 'loss/train': 1.7120006084442139}
+08/30/2021 18:01:13 - INFO - __main__ - Step 27068: {'lr': 0.000465436313084556, 'samples': 5197056, 'steps': 27067, 'loss/train': 0.16369417309761047}
+08/30/2021 18:01:14 - INFO - __main__ - Step 27069: {'lr': 0.0004654336207058344, 'samples': 5197248, 'steps': 27068, 'loss/train': 0.050382111221551895}
+08/30/2021 18:01:14 - INFO - __main__ - Step 27070: {'lr': 0.0004654309282300416, 'samples': 5197440, 'steps': 27069, 'loss/train': 1.7151918411254883}
+08/30/2021 18:01:16 - INFO - __main__ - Step 27071: {'lr': 0.00046542823565717914, 'samples': 5197632, 'steps': 27070, 'loss/train': 1.1886026859283447}
+08/30/2021 18:01:16 - INFO - __main__ - Step 27072: {'lr': 0.00046542554298724793, 'samples': 5197824, 'steps': 27071, 'loss/train': 2.072775363922119}
+08/30/2021 18:01:17 - INFO - __main__ - Step 27073: {'lr': 0.00046542285022024935, 'samples': 5198016, 'steps': 27072, 'loss/train': 1.4394422769546509}
+08/30/2021 18:01:17 - INFO - __main__ - Step 27074: {'lr': 0.0004654201573561845, 'samples': 5198208, 'steps': 27073, 'loss/train': 1.8477309942245483}
+08/30/2021 18:01:17 - INFO - __main__ - Step 27075: {'lr': 0.00046541746439505467, 'samples': 5198400, 'steps': 27074, 'loss/train': 1.052707314491272}
+08/30/2021 18:01:19 - INFO - __main__ - Step 27076: {'lr': 0.00046541477133686107, 'samples': 5198592, 'steps': 27075, 'loss/train': 1.182202696800232}
+08/30/2021 18:01:19 - INFO - __main__ - Step 27077: {'lr': 0.0004654120781816049, 'samples': 5198784, 'steps': 27076, 'loss/train': 1.7987797260284424}
+08/30/2021 18:01:20 - INFO - __main__ - Step 27078: {'lr': 0.00046540938492928735, 'samples': 5198976, 'steps': 27077, 'loss/train': 0.34112757444381714}
+08/30/2021 18:01:20 - INFO - __main__ - Step 27079: {'lr': 0.0004654066915799097, 'samples': 5199168, 'steps': 27078, 'loss/train': 1.1117234230041504}
+08/30/2021 18:01:20 - INFO - __main__ - Step 27080: {'lr': 0.000465403998133473, 'samples': 5199360, 'steps': 27079, 'loss/train': 1.4834051132202148}
+08/30/2021 18:01:22 - INFO - __main__ - Step 27081: {'lr': 0.0004654013045899788, 'samples': 5199552, 'steps': 27080, 'loss/train': 1.434158444404602}
+08/30/2021 18:01:22 - INFO - __main__ - Step 27082: {'lr': 0.00046539861094942794, 'samples': 5199744, 'steps': 27081, 'loss/train': 1.2534668445587158}
+08/30/2021 18:01:23 - INFO - __main__ - Step 27083: {'lr': 0.00046539591721182175, 'samples': 5199936, 'steps': 27082, 'loss/train': 1.9246628284454346}
+08/30/2021 18:01:23 - INFO - __main__ - Step 27084: {'lr': 0.00046539322337716153, 'samples': 5200128, 'steps': 27083, 'loss/train': 3.3916218280792236}
+08/30/2021 18:01:23 - INFO - __main__ - Step 27085: {'lr': 0.00046539052944544846, 'samples': 5200320, 'steps': 27084, 'loss/train': 1.1483354568481445}
+08/30/2021 18:01:26 - INFO - __main__ - Step 27086: {'lr': 0.0004653878354166838, 'samples': 5200512, 'steps': 27085, 'loss/train': 0.10694511234760284}
+08/30/2021 18:01:26 - INFO - __main__ - Step 27087: {'lr': 0.0004653851412908686, 'samples': 5200704, 'steps': 27086, 'loss/train': 1.6052772998809814}
+08/30/2021 18:01:27 - INFO - __main__ - Step 27088: {'lr': 0.0004653824470680043, 'samples': 5200896, 'steps': 27087, 'loss/train': 1.2588305473327637}
+08/30/2021 18:01:27 - INFO - __main__ - Step 27089: {'lr': 0.00046537975274809186, 'samples': 5201088, 'steps': 27088, 'loss/train': 0.16034357249736786}
+08/30/2021 18:01:27 - INFO - __main__ - Step 27090: {'lr': 0.0004653770583311327, 'samples': 5201280, 'steps': 27089, 'loss/train': 1.302323579788208}
+08/30/2021 18:01:29 - INFO - __main__ - Step 27091: {'lr': 0.00046537436381712796, 'samples': 5201472, 'steps': 27090, 'loss/train': 1.091360330581665}
+08/30/2021 18:01:29 - INFO - __main__ - Step 27092: {'lr': 0.00046537166920607886, 'samples': 5201664, 'steps': 27091, 'loss/train': 1.9743883609771729}
+08/30/2021 18:01:30 - INFO - __main__ - Step 27093: {'lr': 0.00046536897449798656, 'samples': 5201856, 'steps': 27092, 'loss/train': 1.6381726264953613}
+08/30/2021 18:01:30 - INFO - __main__ - Step 27094: {'lr': 0.00046536627969285236, 'samples': 5202048, 'steps': 27093, 'loss/train': 1.96189546585083}
+08/30/2021 18:01:30 - INFO - __main__ - Step 27095: {'lr': 0.0004653635847906774, 'samples': 5202240, 'steps': 27094, 'loss/train': 1.8539103269577026}
+08/30/2021 18:01:31 - INFO - __main__ - Step 27096: {'lr': 0.000465360889791463, 'samples': 5202432, 'steps': 27095, 'loss/train': 1.4487504959106445}
+08/30/2021 18:01:32 - INFO - __main__ - Step 27097: {'lr': 0.0004653581946952103, 'samples': 5202624, 'steps': 27096, 'loss/train': 2.0275697708129883}
+08/30/2021 18:01:33 - INFO - __main__ - Step 27098: {'lr': 0.0004653554995019205, 'samples': 5202816, 'steps': 27097, 'loss/train': 1.635689377784729}
+08/30/2021 18:01:33 - INFO - __main__ - Step 27099: {'lr': 0.0004653528042115948, 'samples': 5203008, 'steps': 27098, 'loss/train': 1.2576196193695068}
+08/30/2021 18:01:33 - INFO - __main__ - Step 27100: {'lr': 0.0004653501088242345, 'samples': 5203200, 'steps': 27099, 'loss/train': 1.8818833827972412}
+08/30/2021 18:01:34 - INFO - __main__ - Step 27101: {'lr': 0.0004653474133398408, 'samples': 5203392, 'steps': 27100, 'loss/train': 1.4839212894439697}
+08/30/2021 18:01:35 - INFO - __main__ - Step 27102: {'lr': 0.00046534471775841474, 'samples': 5203584, 'steps': 27101, 'loss/train': 0.7570738196372986}
+08/30/2021 18:01:36 - INFO - __main__ - Step 27103: {'lr': 0.0004653420220799578, 'samples': 5203776, 'steps': 27102, 'loss/train': 0.6034243702888489}
+08/30/2021 18:01:36 - INFO - __main__ - Step 27104: {'lr': 0.000465339326304471, 'samples': 5203968, 'steps': 27103, 'loss/train': 0.27861687541007996}
+08/30/2021 18:01:37 - INFO - __main__ - Step 27105: {'lr': 0.0004653366304319556, 'samples': 5204160, 'steps': 27104, 'loss/train': 1.9334520101547241}
+08/30/2021 18:01:37 - INFO - __main__ - Step 27106: {'lr': 0.0004653339344624129, 'samples': 5204352, 'steps': 27105, 'loss/train': 1.6144770383834839}
+08/30/2021 18:01:38 - INFO - __main__ - Step 27107: {'lr': 0.00046533123839584406, 'samples': 5204544, 'steps': 27106, 'loss/train': 0.9711307883262634}
+08/30/2021 18:01:39 - INFO - __main__ - Step 27108: {'lr': 0.0004653285422322503, 'samples': 5204736, 'steps': 27107, 'loss/train': 2.1607308387756348}
+08/30/2021 18:01:39 - INFO - __main__ - Step 27109: {'lr': 0.00046532584597163275, 'samples': 5204928, 'steps': 27108, 'loss/train': 1.4216431379318237}
+08/30/2021 18:01:40 - INFO - __main__ - Step 27110: {'lr': 0.0004653231496139927, 'samples': 5205120, 'steps': 27109, 'loss/train': 1.1179980039596558}
+08/30/2021 18:01:40 - INFO - __main__ - Step 27111: {'lr': 0.0004653204531593315, 'samples': 5205312, 'steps': 27110, 'loss/train': 1.4066784381866455}
+08/30/2021 18:01:42 - INFO - __main__ - Step 27112: {'lr': 0.0004653177566076501, 'samples': 5205504, 'steps': 27111, 'loss/train': 1.4669851064682007}
+08/30/2021 18:01:42 - INFO - __main__ - Step 27113: {'lr': 0.0004653150599589498, 'samples': 5205696, 'steps': 27112, 'loss/train': 2.0896048545837402}
+08/30/2021 18:01:42 - INFO - __main__ - Step 27114: {'lr': 0.0004653123632132319, 'samples': 5205888, 'steps': 27113, 'loss/train': 2.693441867828369}
+08/30/2021 18:01:43 - INFO - __main__ - Step 27115: {'lr': 0.0004653096663704976, 'samples': 5206080, 'steps': 27114, 'loss/train': 1.4360371828079224}
+08/30/2021 18:01:43 - INFO - __main__ - Step 27116: {'lr': 0.0004653069694307481, 'samples': 5206272, 'steps': 27115, 'loss/train': 1.2330105304718018}
+08/30/2021 18:01:44 - INFO - __main__ - Step 27117: {'lr': 0.00046530427239398453, 'samples': 5206464, 'steps': 27116, 'loss/train': 1.0283563137054443}
+08/30/2021 18:01:45 - INFO - __main__ - Step 27118: {'lr': 0.0004653015752602082, 'samples': 5206656, 'steps': 27117, 'loss/train': 1.6964225769042969}
+08/30/2021 18:01:45 - INFO - __main__ - Step 27119: {'lr': 0.0004652988780294204, 'samples': 5206848, 'steps': 27118, 'loss/train': 1.095198392868042}
+08/30/2021 18:01:46 - INFO - __main__ - Step 27120: {'lr': 0.00046529618070162215, 'samples': 5207040, 'steps': 27119, 'loss/train': 1.318901777267456}
+08/30/2021 18:01:46 - INFO - __main__ - Step 27121: {'lr': 0.00046529348327681476, 'samples': 5207232, 'steps': 27120, 'loss/train': 1.682550311088562}
+08/30/2021 18:01:46 - INFO - __main__ - Step 27122: {'lr': 0.0004652907857549995, 'samples': 5207424, 'steps': 27121, 'loss/train': 1.5472487211227417}
+08/30/2021 18:01:48 - INFO - __main__ - Step 27123: {'lr': 0.0004652880881361775, 'samples': 5207616, 'steps': 27122, 'loss/train': 0.8448706865310669}
+08/30/2021 18:01:48 - INFO - __main__ - Step 27124: {'lr': 0.00046528539042035, 'samples': 5207808, 'steps': 27123, 'loss/train': 1.7188612222671509}
+08/30/2021 18:01:49 - INFO - __main__ - Step 27125: {'lr': 0.0004652826926075183, 'samples': 5208000, 'steps': 27124, 'loss/train': 1.3044096231460571}
+08/30/2021 18:01:49 - INFO - __main__ - Step 27126: {'lr': 0.00046527999469768346, 'samples': 5208192, 'steps': 27125, 'loss/train': 1.2946099042892456}
+08/30/2021 18:01:49 - INFO - __main__ - Step 27127: {'lr': 0.0004652772966908468, 'samples': 5208384, 'steps': 27126, 'loss/train': 1.1339104175567627}
+08/30/2021 18:01:51 - INFO - __main__ - Step 27128: {'lr': 0.0004652745985870095, 'samples': 5208576, 'steps': 27127, 'loss/train': 1.3347536325454712}
+08/30/2021 18:01:51 - INFO - __main__ - Step 27129: {'lr': 0.0004652719003861728, 'samples': 5208768, 'steps': 27128, 'loss/train': 1.338863730430603}
+08/30/2021 18:01:52 - INFO - __main__ - Step 27130: {'lr': 0.0004652692020883379, 'samples': 5208960, 'steps': 27129, 'loss/train': 0.1407596915960312}
+08/30/2021 18:01:52 - INFO - __main__ - Step 27131: {'lr': 0.00046526650369350605, 'samples': 5209152, 'steps': 27130, 'loss/train': 1.8553941249847412}
+08/30/2021 18:01:53 - INFO - __main__ - Step 27132: {'lr': 0.0004652638052016784, 'samples': 5209344, 'steps': 27131, 'loss/train': 1.689576268196106}
+08/30/2021 18:01:54 - INFO - __main__ - Step 27133: {'lr': 0.00046526110661285615, 'samples': 5209536, 'steps': 27132, 'loss/train': 1.757028341293335}
+08/30/2021 18:01:55 - INFO - __main__ - Step 27134: {'lr': 0.00046525840792704064, 'samples': 5209728, 'steps': 27133, 'loss/train': 2.376382350921631}
+08/30/2021 18:01:55 - INFO - __main__ - Step 27135: {'lr': 0.000465255709144233, 'samples': 5209920, 'steps': 27134, 'loss/train': 1.4509390592575073}
+08/30/2021 18:01:55 - INFO - __main__ - Step 27136: {'lr': 0.00046525301026443443, 'samples': 5210112, 'steps': 27135, 'loss/train': 1.6816036701202393}
+08/30/2021 18:01:56 - INFO - __main__ - Step 27137: {'lr': 0.0004652503112876463, 'samples': 5210304, 'steps': 27136, 'loss/train': 1.2493385076522827}
+08/30/2021 18:01:57 - INFO - __main__ - Step 27138: {'lr': 0.00046524761221386956, 'samples': 5210496, 'steps': 27137, 'loss/train': 1.4471927881240845}
+08/30/2021 18:01:58 - INFO - __main__ - Step 27139: {'lr': 0.0004652449130431056, 'samples': 5210688, 'steps': 27138, 'loss/train': 1.7560170888900757}
+08/30/2021 18:01:58 - INFO - __main__ - Step 27140: {'lr': 0.00046524221377535564, 'samples': 5210880, 'steps': 27139, 'loss/train': 1.0139490365982056}
+08/30/2021 18:01:58 - INFO - __main__ - Step 27141: {'lr': 0.00046523951441062087, 'samples': 5211072, 'steps': 27140, 'loss/train': 1.6119662523269653}
+08/30/2021 18:01:59 - INFO - __main__ - Step 27142: {'lr': 0.0004652368149489024, 'samples': 5211264, 'steps': 27141, 'loss/train': 1.7705886363983154}
+08/30/2021 18:02:01 - INFO - __main__ - Step 27143: {'lr': 0.0004652341153902016, 'samples': 5211456, 'steps': 27142, 'loss/train': 1.0436846017837524}
+08/30/2021 18:02:01 - INFO - __main__ - Step 27144: {'lr': 0.00046523141573451965, 'samples': 5211648, 'steps': 27143, 'loss/train': 0.8901267051696777}
+08/30/2021 18:02:02 - INFO - __main__ - Step 27145: {'lr': 0.0004652287159818577, 'samples': 5211840, 'steps': 27144, 'loss/train': 1.3173696994781494}
+08/30/2021 18:02:02 - INFO - __main__ - Step 27146: {'lr': 0.00046522601613221704, 'samples': 5212032, 'steps': 27145, 'loss/train': 1.683090329170227}
+08/30/2021 18:02:02 - INFO - __main__ - Step 27147: {'lr': 0.0004652233161855989, 'samples': 5212224, 'steps': 27146, 'loss/train': 1.6737595796585083}
+08/30/2021 18:02:04 - INFO - __main__ - Step 27148: {'lr': 0.0004652206161420044, 'samples': 5212416, 'steps': 27147, 'loss/train': 1.9634326696395874}
+08/30/2021 18:02:04 - INFO - __main__ - Step 27149: {'lr': 0.00046521791600143483, 'samples': 5212608, 'steps': 27148, 'loss/train': 1.0778173208236694}
+08/30/2021 18:02:05 - INFO - __main__ - Step 27150: {'lr': 0.00046521521576389134, 'samples': 5212800, 'steps': 27149, 'loss/train': 1.6184779405593872}
+08/30/2021 18:02:05 - INFO - __main__ - Step 27151: {'lr': 0.00046521251542937524, 'samples': 5212992, 'steps': 27150, 'loss/train': 1.2396254539489746}
+08/30/2021 18:02:05 - INFO - __main__ - Step 27152: {'lr': 0.0004652098149978877, 'samples': 5213184, 'steps': 27151, 'loss/train': 1.4671834707260132}
+08/30/2021 18:02:06 - INFO - __main__ - Step 27153: {'lr': 0.00046520711446943, 'samples': 5213376, 'steps': 27152, 'loss/train': 1.4779397249221802}
+08/30/2021 18:02:07 - INFO - __main__ - Step 27154: {'lr': 0.0004652044138440032, 'samples': 5213568, 'steps': 27153, 'loss/train': 1.2149711847305298}
+08/30/2021 18:02:08 - INFO - __main__ - Step 27155: {'lr': 0.00046520171312160863, 'samples': 5213760, 'steps': 27154, 'loss/train': 1.5334635972976685}
+08/30/2021 18:02:08 - INFO - __main__ - Step 27156: {'lr': 0.00046519901230224756, 'samples': 5213952, 'steps': 27155, 'loss/train': 1.6847068071365356}
+08/30/2021 18:02:08 - INFO - __main__ - Step 27157: {'lr': 0.000465196311385921, 'samples': 5214144, 'steps': 27156, 'loss/train': 1.1634342670440674}
+08/30/2021 18:02:09 - INFO - __main__ - Step 27158: {'lr': 0.0004651936103726304, 'samples': 5214336, 'steps': 27157, 'loss/train': 1.6953181028366089}
+08/30/2021 18:02:10 - INFO - __main__ - Step 27159: {'lr': 0.0004651909092623769, 'samples': 5214528, 'steps': 27158, 'loss/train': 1.682037115097046}
+08/30/2021 18:02:11 - INFO - __main__ - Step 27160: {'lr': 0.00046518820805516165, 'samples': 5214720, 'steps': 27159, 'loss/train': 2.1666359901428223}
+08/30/2021 18:02:11 - INFO - __main__ - Step 27161: {'lr': 0.0004651855067509859, 'samples': 5214912, 'steps': 27160, 'loss/train': 0.923642635345459}
+08/30/2021 18:02:11 - INFO - __main__ - Step 27162: {'lr': 0.0004651828053498509, 'samples': 5215104, 'steps': 27161, 'loss/train': 0.15039899945259094}
+08/30/2021 18:02:12 - INFO - __main__ - Step 27163: {'lr': 0.0004651801038517579, 'samples': 5215296, 'steps': 27162, 'loss/train': 1.6620742082595825}
+08/30/2021 18:02:13 - INFO - __main__ - Step 27164: {'lr': 0.000465177402256708, 'samples': 5215488, 'steps': 27163, 'loss/train': 1.2420668601989746}
+08/30/2021 18:02:14 - INFO - __main__ - Step 27165: {'lr': 0.00046517470056470244, 'samples': 5215680, 'steps': 27164, 'loss/train': 1.8143824338912964}
+08/30/2021 18:02:14 - INFO - __main__ - Step 27166: {'lr': 0.00046517199877574257, 'samples': 5215872, 'steps': 27165, 'loss/train': 1.2720283269882202}
+08/30/2021 18:02:14 - INFO - __main__ - Step 27167: {'lr': 0.0004651692968898295, 'samples': 5216064, 'steps': 27166, 'loss/train': 1.4383347034454346}
+08/30/2021 18:02:15 - INFO - __main__ - Step 27168: {'lr': 0.00046516659490696444, 'samples': 5216256, 'steps': 27167, 'loss/train': 1.142825722694397}
+08/30/2021 18:02:16 - INFO - __main__ - Step 27169: {'lr': 0.0004651638928271487, 'samples': 5216448, 'steps': 27168, 'loss/train': 1.1730382442474365}
+08/30/2021 18:02:17 - INFO - __main__ - Step 27170: {'lr': 0.00046516119065038335, 'samples': 5216640, 'steps': 27169, 'loss/train': 1.4490641355514526}
+08/30/2021 18:02:17 - INFO - __main__ - Step 27171: {'lr': 0.00046515848837666975, 'samples': 5216832, 'steps': 27170, 'loss/train': 1.3089524507522583}
+08/30/2021 18:02:17 - INFO - __main__ - Step 27172: {'lr': 0.00046515578600600895, 'samples': 5217024, 'steps': 27171, 'loss/train': 1.6375516653060913}
+08/30/2021 18:02:18 - INFO - __main__ - Step 27173: {'lr': 0.0004651530835384024, 'samples': 5217216, 'steps': 27172, 'loss/train': 0.993874192237854}
+08/30/2021 18:02:20 - INFO - __main__ - Step 27174: {'lr': 0.0004651503809738511, 'samples': 5217408, 'steps': 27173, 'loss/train': 1.8553403615951538}
+08/30/2021 18:02:20 - INFO - __main__ - Step 27175: {'lr': 0.0004651476783123564, 'samples': 5217600, 'steps': 27174, 'loss/train': 0.7931986451148987}
+08/30/2021 18:02:20 - INFO - __main__ - Step 27176: {'lr': 0.00046514497555391946, 'samples': 5217792, 'steps': 27175, 'loss/train': 1.2725205421447754}
+08/30/2021 18:02:21 - INFO - __main__ - Step 27177: {'lr': 0.0004651422726985415, 'samples': 5217984, 'steps': 27176, 'loss/train': 1.2557040452957153}
+08/30/2021 18:02:21 - INFO - __main__ - Step 27178: {'lr': 0.00046513956974622377, 'samples': 5218176, 'steps': 27177, 'loss/train': 1.3666027784347534}
+08/30/2021 18:02:21 - INFO - __main__ - Step 27179: {'lr': 0.00046513686669696756, 'samples': 5218368, 'steps': 27178, 'loss/train': 1.3838618993759155}
+08/30/2021 18:02:23 - INFO - __main__ - Step 27180: {'lr': 0.00046513416355077386, 'samples': 5218560, 'steps': 27179, 'loss/train': 0.4842136800289154}
+08/30/2021 18:02:23 - INFO - __main__ - Step 27181: {'lr': 0.0004651314603076441, 'samples': 5218752, 'steps': 27180, 'loss/train': 0.9858081936836243}
+08/30/2021 18:02:24 - INFO - __main__ - Step 27182: {'lr': 0.00046512875696757937, 'samples': 5218944, 'steps': 27181, 'loss/train': 1.5500998497009277}
+08/30/2021 18:02:24 - INFO - __main__ - Step 27183: {'lr': 0.00046512605353058096, 'samples': 5219136, 'steps': 27182, 'loss/train': 1.9521722793579102}
+08/30/2021 18:02:24 - INFO - __main__ - Step 27184: {'lr': 0.00046512334999665006, 'samples': 5219328, 'steps': 27183, 'loss/train': 1.0258973836898804}
+08/30/2021 18:02:26 - INFO - __main__ - Step 27185: {'lr': 0.000465120646365788, 'samples': 5219520, 'steps': 27184, 'loss/train': 1.4164693355560303}
+08/30/2021 18:02:26 - INFO - __main__ - Step 27186: {'lr': 0.0004651179426379958, 'samples': 5219712, 'steps': 27185, 'loss/train': 1.3320482969284058}
+08/30/2021 18:02:27 - INFO - __main__ - Step 27187: {'lr': 0.00046511523881327476, 'samples': 5219904, 'steps': 27186, 'loss/train': 1.5076208114624023}
+08/30/2021 18:02:27 - INFO - __main__ - Step 27188: {'lr': 0.00046511253489162616, 'samples': 5220096, 'steps': 27187, 'loss/train': 1.540059208869934}
+08/30/2021 18:02:27 - INFO - __main__ - Step 27189: {'lr': 0.00046510983087305114, 'samples': 5220288, 'steps': 27188, 'loss/train': 1.2916322946548462}
+08/30/2021 18:02:29 - INFO - __main__ - Step 27190: {'lr': 0.00046510712675755094, 'samples': 5220480, 'steps': 27189, 'loss/train': 1.959316611289978}
+08/30/2021 18:02:29 - INFO - __main__ - Step 27191: {'lr': 0.00046510442254512686, 'samples': 5220672, 'steps': 27190, 'loss/train': 1.4867103099822998}
+08/30/2021 18:02:30 - INFO - __main__ - Step 27192: {'lr': 0.00046510171823578, 'samples': 5220864, 'steps': 27191, 'loss/train': 1.876558542251587}
+08/30/2021 18:02:30 - INFO - __main__ - Step 27193: {'lr': 0.0004650990138295116, 'samples': 5221056, 'steps': 27192, 'loss/train': 1.6605374813079834}
+08/30/2021 18:02:30 - INFO - __main__ - Step 27194: {'lr': 0.00046509630932632293, 'samples': 5221248, 'steps': 27193, 'loss/train': 1.2944283485412598}
+08/30/2021 18:02:31 - INFO - __main__ - Step 27195: {'lr': 0.0004650936047262152, 'samples': 5221440, 'steps': 27194, 'loss/train': 1.754934310913086}
+08/30/2021 18:02:33 - INFO - __main__ - Step 27196: {'lr': 0.0004650909000291895, 'samples': 5221632, 'steps': 27195, 'loss/train': 0.21176883578300476}
+08/30/2021 18:02:33 - INFO - __main__ - Step 27197: {'lr': 0.00046508819523524724, 'samples': 5221824, 'steps': 27196, 'loss/train': 1.88222336769104}
+08/30/2021 18:02:33 - INFO - __main__ - Step 27198: {'lr': 0.0004650854903443896, 'samples': 5222016, 'steps': 27197, 'loss/train': 1.7587685585021973}
+08/30/2021 18:02:34 - INFO - __main__ - Step 27199: {'lr': 0.00046508278535661775, 'samples': 5222208, 'steps': 27198, 'loss/train': 1.02782142162323}
+08/30/2021 18:02:34 - INFO - __main__ - Step 27200: {'lr': 0.00046508008027193286, 'samples': 5222400, 'steps': 27199, 'loss/train': 1.965057373046875}
+08/30/2021 18:02:36 - INFO - __main__ - Step 27201: {'lr': 0.0004650773750903363, 'samples': 5222592, 'steps': 27200, 'loss/train': 1.212222695350647}
+08/30/2021 18:02:36 - INFO - __main__ - Step 27202: {'lr': 0.0004650746698118291, 'samples': 5222784, 'steps': 27201, 'loss/train': 1.7200069427490234}
+08/30/2021 18:02:36 - INFO - __main__ - Step 27203: {'lr': 0.0004650719644364126, 'samples': 5222976, 'steps': 27202, 'loss/train': 1.4639238119125366}
+08/30/2021 18:02:37 - INFO - __main__ - Step 27204: {'lr': 0.000465069258964088, 'samples': 5223168, 'steps': 27203, 'loss/train': 1.1928578615188599}
+08/30/2021 18:02:37 - INFO - __main__ - Step 27205: {'lr': 0.0004650665533948565, 'samples': 5223360, 'steps': 27204, 'loss/train': 1.671126127243042}
+08/30/2021 18:02:39 - INFO - __main__ - Step 27206: {'lr': 0.00046506384772871935, 'samples': 5223552, 'steps': 27205, 'loss/train': 1.2450087070465088}
+08/30/2021 18:02:39 - INFO - __main__ - Step 27207: {'lr': 0.0004650611419656777, 'samples': 5223744, 'steps': 27206, 'loss/train': 1.1245115995407104}
+08/30/2021 18:02:39 - INFO - __main__ - Step 27208: {'lr': 0.0004650584361057328, 'samples': 5223936, 'steps': 27207, 'loss/train': 0.17484788596630096}
+08/30/2021 18:02:40 - INFO - __main__ - Step 27209: {'lr': 0.00046505573014888604, 'samples': 5224128, 'steps': 27208, 'loss/train': 1.763199806213379}
+08/30/2021 18:02:40 - INFO - __main__ - Step 27210: {'lr': 0.0004650530240951383, 'samples': 5224320, 'steps': 27209, 'loss/train': 1.5048365592956543}
+08/30/2021 18:02:42 - INFO - __main__ - Step 27211: {'lr': 0.0004650503179444911, 'samples': 5224512, 'steps': 27210, 'loss/train': 1.3131428956985474}
+08/30/2021 18:02:42 - INFO - __main__ - Step 27212: {'lr': 0.00046504761169694555, 'samples': 5224704, 'steps': 27211, 'loss/train': 1.455526351928711}
+08/30/2021 18:02:42 - INFO - __main__ - Step 27213: {'lr': 0.0004650449053525028, 'samples': 5224896, 'steps': 27212, 'loss/train': 1.5415327548980713}
+08/30/2021 18:02:43 - INFO - __main__ - Step 27214: {'lr': 0.00046504219891116416, 'samples': 5225088, 'steps': 27213, 'loss/train': 1.2887331247329712}
+08/30/2021 18:02:43 - INFO - __main__ - Step 27215: {'lr': 0.0004650394923729309, 'samples': 5225280, 'steps': 27214, 'loss/train': 1.2204267978668213}
+08/30/2021 18:02:45 - INFO - __main__ - Step 27216: {'lr': 0.00046503678573780403, 'samples': 5225472, 'steps': 27215, 'loss/train': 1.389278531074524}
+08/30/2021 18:02:45 - INFO - __main__ - Step 27217: {'lr': 0.000465034079005785, 'samples': 5225664, 'steps': 27216, 'loss/train': 2.055776596069336}
+08/30/2021 18:02:46 - INFO - __main__ - Step 27218: {'lr': 0.00046503137217687485, 'samples': 5225856, 'steps': 27217, 'loss/train': 0.0949811041355133}
+08/30/2021 18:02:46 - INFO - __main__ - Step 27219: {'lr': 0.0004650286652510749, 'samples': 5226048, 'steps': 27218, 'loss/train': 1.3490337133407593}
+08/30/2021 18:02:46 - INFO - __main__ - Step 27220: {'lr': 0.0004650259582283864, 'samples': 5226240, 'steps': 27219, 'loss/train': 1.026698112487793}
+08/30/2021 18:02:48 - INFO - __main__ - Step 27221: {'lr': 0.0004650232511088105, 'samples': 5226432, 'steps': 27220, 'loss/train': 1.5688090324401855}
+08/30/2021 18:02:48 - INFO - __main__ - Step 27222: {'lr': 0.00046502054389234844, 'samples': 5226624, 'steps': 27221, 'loss/train': 1.7997719049453735}
+08/30/2021 18:02:49 - INFO - __main__ - Step 27223: {'lr': 0.0004650178365790014, 'samples': 5226816, 'steps': 27222, 'loss/train': 0.0738530382514}
+08/30/2021 18:02:49 - INFO - __main__ - Step 27224: {'lr': 0.0004650151291687707, 'samples': 5227008, 'steps': 27223, 'loss/train': 1.3296082019805908}
+08/30/2021 18:02:49 - INFO - __main__ - Step 27225: {'lr': 0.00046501242166165747, 'samples': 5227200, 'steps': 27224, 'loss/train': 1.095910906791687}
+08/30/2021 18:02:51 - INFO - __main__ - Step 27226: {'lr': 0.000465009714057663, 'samples': 5227392, 'steps': 27225, 'loss/train': 1.1816964149475098}
+08/30/2021 18:02:51 - INFO - __main__ - Step 27227: {'lr': 0.00046500700635678844, 'samples': 5227584, 'steps': 27226, 'loss/train': 1.519883155822754}
+08/30/2021 18:02:52 - INFO - __main__ - Step 27228: {'lr': 0.000465004298559035, 'samples': 5227776, 'steps': 27227, 'loss/train': 1.5541470050811768}
+08/30/2021 18:02:52 - INFO - __main__ - Step 27229: {'lr': 0.00046500159066440404, 'samples': 5227968, 'steps': 27228, 'loss/train': 1.4665356874465942}
+08/30/2021 18:02:52 - INFO - __main__ - Step 27230: {'lr': 0.0004649988826728966, 'samples': 5228160, 'steps': 27229, 'loss/train': 0.8733643889427185}
+08/30/2021 18:02:53 - INFO - __main__ - Step 27231: {'lr': 0.000464996174584514, 'samples': 5228352, 'steps': 27230, 'loss/train': 1.6681219339370728}
+08/30/2021 18:02:54 - INFO - __main__ - Step 27232: {'lr': 0.00046499346639925746, 'samples': 5228544, 'steps': 27231, 'loss/train': 1.3323636054992676}
+08/30/2021 18:02:55 - INFO - __main__ - Step 27233: {'lr': 0.0004649907581171282, 'samples': 5228736, 'steps': 27232, 'loss/train': 1.2746250629425049}
+08/30/2021 18:02:55 - INFO - __main__ - Step 27234: {'lr': 0.00046498804973812735, 'samples': 5228928, 'steps': 27233, 'loss/train': 1.0236037969589233}
+08/30/2021 18:02:56 - INFO - __main__ - Step 27235: {'lr': 0.00046498534126225625, 'samples': 5229120, 'steps': 27234, 'loss/train': 1.393905520439148}
+08/30/2021 18:02:56 - INFO - __main__ - Step 27236: {'lr': 0.0004649826326895161, 'samples': 5229312, 'steps': 27235, 'loss/train': 1.0438834428787231}
+08/30/2021 18:02:57 - INFO - __main__ - Step 27237: {'lr': 0.0004649799240199081, 'samples': 5229504, 'steps': 27236, 'loss/train': 0.7269102931022644}
+08/30/2021 18:02:58 - INFO - __main__ - Step 27238: {'lr': 0.0004649772152534334, 'samples': 5229696, 'steps': 27237, 'loss/train': 1.5188666582107544}
+08/30/2021 18:02:58 - INFO - __main__ - Step 27239: {'lr': 0.0004649745063900933, 'samples': 5229888, 'steps': 27238, 'loss/train': 1.9725725650787354}
+08/30/2021 18:02:58 - INFO - __main__ - Step 27240: {'lr': 0.000464971797429889, 'samples': 5230080, 'steps': 27239, 'loss/train': 1.210260033607483}
+08/30/2021 18:02:59 - INFO - __main__ - Step 27241: {'lr': 0.00046496908837282173, 'samples': 5230272, 'steps': 27240, 'loss/train': 1.168676495552063}
+08/30/2021 18:03:00 - INFO - __main__ - Step 27242: {'lr': 0.00046496637921889276, 'samples': 5230464, 'steps': 27241, 'loss/train': 1.859948992729187}
+08/30/2021 18:03:01 - INFO - __main__ - Step 27243: {'lr': 0.0004649636699681031, 'samples': 5230656, 'steps': 27242, 'loss/train': 1.5435638427734375}
+08/30/2021 18:03:01 - INFO - __main__ - Step 27244: {'lr': 0.00046496096062045427, 'samples': 5230848, 'steps': 27243, 'loss/train': 1.488871693611145}
+08/30/2021 18:03:02 - INFO - __main__ - Step 27245: {'lr': 0.00046495825117594735, 'samples': 5231040, 'steps': 27244, 'loss/train': 1.4715319871902466}
+08/30/2021 18:03:02 - INFO - __main__ - Step 27246: {'lr': 0.0004649555416345835, 'samples': 5231232, 'steps': 27245, 'loss/train': 1.8495218753814697}
+08/30/2021 18:03:04 - INFO - __main__ - Step 27247: {'lr': 0.0004649528319963641, 'samples': 5231424, 'steps': 27246, 'loss/train': 1.6618481874465942}
+08/30/2021 18:03:04 - INFO - __main__ - Step 27248: {'lr': 0.0004649501222612901, 'samples': 5231616, 'steps': 27247, 'loss/train': 1.2079572677612305}
+08/30/2021 18:03:05 - INFO - __main__ - Step 27249: {'lr': 0.000464947412429363, 'samples': 5231808, 'steps': 27248, 'loss/train': 1.9796838760375977}
+08/30/2021 18:03:05 - INFO - __main__ - Step 27250: {'lr': 0.000464944702500584, 'samples': 5232000, 'steps': 27249, 'loss/train': 1.690522313117981}
+08/30/2021 18:03:05 - INFO - __main__ - Step 27251: {'lr': 0.0004649419924749541, 'samples': 5232192, 'steps': 27250, 'loss/train': 1.7213099002838135}
+08/30/2021 18:03:06 - INFO - __main__ - Step 27252: {'lr': 0.0004649392823524746, 'samples': 5232384, 'steps': 27251, 'loss/train': 0.9100295901298523}
+08/30/2021 18:03:07 - INFO - __main__ - Step 27253: {'lr': 0.0004649365721331469, 'samples': 5232576, 'steps': 27252, 'loss/train': 1.5809015035629272}
+08/30/2021 18:03:08 - INFO - __main__ - Step 27254: {'lr': 0.00046493386181697206, 'samples': 5232768, 'steps': 27253, 'loss/train': 1.7417445182800293}
+08/30/2021 18:03:08 - INFO - __main__ - Step 27255: {'lr': 0.00046493115140395136, 'samples': 5232960, 'steps': 27254, 'loss/train': 1.5555888414382935}
+08/30/2021 18:03:08 - INFO - __main__ - Step 27256: {'lr': 0.000464928440894086, 'samples': 5233152, 'steps': 27255, 'loss/train': 1.2720096111297607}
+08/30/2021 18:03:09 - INFO - __main__ - Step 27257: {'lr': 0.00046492573028737716, 'samples': 5233344, 'steps': 27256, 'loss/train': 1.5129177570343018}
+08/30/2021 18:03:10 - INFO - __main__ - Step 27258: {'lr': 0.0004649230195838261, 'samples': 5233536, 'steps': 27257, 'loss/train': 1.2692806720733643}
+08/30/2021 18:03:11 - INFO - __main__ - Step 27259: {'lr': 0.00046492030878343406, 'samples': 5233728, 'steps': 27258, 'loss/train': 1.562685251235962}
+08/30/2021 18:03:11 - INFO - __main__ - Step 27260: {'lr': 0.00046491759788620227, 'samples': 5233920, 'steps': 27259, 'loss/train': 1.3309409618377686}
+08/30/2021 18:03:12 - INFO - __main__ - Step 27261: {'lr': 0.0004649148868921319, 'samples': 5234112, 'steps': 27260, 'loss/train': 1.4846631288528442}
+08/30/2021 18:03:12 - INFO - __main__ - Step 27262: {'lr': 0.00046491217580122427, 'samples': 5234304, 'steps': 27261, 'loss/train': 1.4535695314407349}
+08/30/2021 18:03:14 - INFO - __main__ - Step 27263: {'lr': 0.00046490946461348045, 'samples': 5234496, 'steps': 27262, 'loss/train': 0.7473717927932739}
+08/30/2021 18:03:14 - INFO - __main__ - Step 27264: {'lr': 0.00046490675332890177, 'samples': 5234688, 'steps': 27263, 'loss/train': 0.19532035291194916}
+08/30/2021 18:03:14 - INFO - __main__ - Step 27265: {'lr': 0.00046490404194748935, 'samples': 5234880, 'steps': 27264, 'loss/train': 1.9025545120239258}
+08/30/2021 18:03:15 - INFO - __main__ - Step 27266: {'lr': 0.00046490133046924457, 'samples': 5235072, 'steps': 27265, 'loss/train': 0.9349351525306702}
+08/30/2021 18:03:15 - INFO - __main__ - Step 27267: {'lr': 0.0004648986188941685, 'samples': 5235264, 'steps': 27266, 'loss/train': 0.78515625}
+08/30/2021 18:03:16 - INFO - __main__ - Step 27268: {'lr': 0.0004648959072222625, 'samples': 5235456, 'steps': 27267, 'loss/train': 1.3551311492919922}
+08/30/2021 18:03:17 - INFO - __main__ - Step 27269: {'lr': 0.0004648931954535277, 'samples': 5235648, 'steps': 27268, 'loss/train': 1.1315070390701294}
+08/30/2021 18:03:17 - INFO - __main__ - Step 27270: {'lr': 0.0004648904835879654, 'samples': 5235840, 'steps': 27269, 'loss/train': 1.0739414691925049}
+08/30/2021 18:03:18 - INFO - __main__ - Step 27271: {'lr': 0.0004648877716255766, 'samples': 5236032, 'steps': 27270, 'loss/train': 1.052010178565979}
+08/30/2021 18:03:18 - INFO - __main__ - Step 27272: {'lr': 0.00046488505956636286, 'samples': 5236224, 'steps': 27271, 'loss/train': 0.9770748019218445}
+08/30/2021 18:03:20 - INFO - __main__ - Step 27273: {'lr': 0.0004648823474103251, 'samples': 5236416, 'steps': 27272, 'loss/train': 1.6778689622879028}
+08/30/2021 18:03:20 - INFO - __main__ - Step 27274: {'lr': 0.0004648796351574648, 'samples': 5236608, 'steps': 27273, 'loss/train': 1.8462250232696533}
+08/30/2021 18:03:20 - INFO - __main__ - Step 27275: {'lr': 0.0004648769228077829, 'samples': 5236800, 'steps': 27274, 'loss/train': 1.6655688285827637}
+08/30/2021 18:03:21 - INFO - __main__ - Step 27276: {'lr': 0.00046487421036128085, 'samples': 5236992, 'steps': 27275, 'loss/train': 1.4138898849487305}
+08/30/2021 18:03:21 - INFO - __main__ - Step 27277: {'lr': 0.00046487149781795976, 'samples': 5237184, 'steps': 27276, 'loss/train': 0.10334265977144241}
+08/30/2021 18:03:21 - INFO - __main__ - Step 27278: {'lr': 0.00046486878517782094, 'samples': 5237376, 'steps': 27277, 'loss/train': 1.682212471961975}
+08/30/2021 18:03:23 - INFO - __main__ - Step 27279: {'lr': 0.0004648660724408656, 'samples': 5237568, 'steps': 27278, 'loss/train': 1.694521427154541}
+08/30/2021 18:03:23 - INFO - __main__ - Step 27280: {'lr': 0.00046486335960709485, 'samples': 5237760, 'steps': 27279, 'loss/train': 1.7350554466247559}
+08/30/2021 18:03:24 - INFO - __main__ - Step 27281: {'lr': 0.00046486064667651, 'samples': 5237952, 'steps': 27280, 'loss/train': 1.4675053358078003}
+08/30/2021 18:03:24 - INFO - __main__ - Step 27282: {'lr': 0.0004648579336491123, 'samples': 5238144, 'steps': 27281, 'loss/train': 1.6293554306030273}
+08/30/2021 18:03:24 - INFO - __main__ - Step 27283: {'lr': 0.0004648552205249029, 'samples': 5238336, 'steps': 27282, 'loss/train': 1.2510106563568115}
+08/30/2021 18:03:26 - INFO - __main__ - Step 27284: {'lr': 0.000464852507303883, 'samples': 5238528, 'steps': 27283, 'loss/train': 2.3260385990142822}
+08/30/2021 18:03:26 - INFO - __main__ - Step 27285: {'lr': 0.0004648497939860539, 'samples': 5238720, 'steps': 27284, 'loss/train': 1.5813488960266113}
+08/30/2021 18:03:27 - INFO - __main__ - Step 27286: {'lr': 0.0004648470805714169, 'samples': 5238912, 'steps': 27285, 'loss/train': 1.4133464097976685}
+08/30/2021 18:03:27 - INFO - __main__ - Step 27287: {'lr': 0.00046484436705997303, 'samples': 5239104, 'steps': 27286, 'loss/train': 1.6518265008926392}
+08/30/2021 18:03:27 - INFO - __main__ - Step 27288: {'lr': 0.0004648416534517236, 'samples': 5239296, 'steps': 27287, 'loss/train': 1.3845692873001099}
+08/30/2021 18:03:29 - INFO - __main__ - Step 27289: {'lr': 0.00046483893974666983, 'samples': 5239488, 'steps': 27288, 'loss/train': 3.8499529361724854}
+08/30/2021 18:03:30 - INFO - __main__ - Step 27290: {'lr': 0.000464836225944813, 'samples': 5239680, 'steps': 27289, 'loss/train': 2.0362470149993896}
+08/30/2021 18:03:30 - INFO - __main__ - Step 27291: {'lr': 0.00046483351204615423, 'samples': 5239872, 'steps': 27290, 'loss/train': 1.3258978128433228}
+08/30/2021 18:03:30 - INFO - __main__ - Step 27292: {'lr': 0.0004648307980506948, 'samples': 5240064, 'steps': 27291, 'loss/train': 1.7532356977462769}
+08/30/2021 18:03:31 - INFO - __main__ - Step 27293: {'lr': 0.00046482808395843594, 'samples': 5240256, 'steps': 27292, 'loss/train': 0.10539980977773666}
+08/30/2021 18:03:31 - INFO - __main__ - Step 27294: {'lr': 0.0004648253697693789, 'samples': 5240448, 'steps': 27293, 'loss/train': 0.046046182513237}
+08/30/2021 18:03:32 - INFO - __main__ - Step 27295: {'lr': 0.0004648226554835248, 'samples': 5240640, 'steps': 27294, 'loss/train': 1.7988481521606445}
+08/30/2021 18:03:33 - INFO - __main__ - Step 27296: {'lr': 0.000464819941100875, 'samples': 5240832, 'steps': 27295, 'loss/train': 1.3836617469787598}
+08/30/2021 18:03:33 - INFO - __main__ - Step 27297: {'lr': 0.00046481722662143057, 'samples': 5241024, 'steps': 27296, 'loss/train': 1.6231448650360107}
+08/30/2021 18:03:34 - INFO - __main__ - Step 27298: {'lr': 0.0004648145120451929, 'samples': 5241216, 'steps': 27297, 'loss/train': 1.3917350769042969}
+08/30/2021 18:03:34 - INFO - __main__ - Step 27299: {'lr': 0.000464811797372163, 'samples': 5241408, 'steps': 27298, 'loss/train': 1.4628976583480835}
+08/30/2021 18:03:36 - INFO - __main__ - Step 27300: {'lr': 0.00046480908260234234, 'samples': 5241600, 'steps': 27299, 'loss/train': 1.3640955686569214}
+08/30/2021 18:03:36 - INFO - __main__ - Step 27301: {'lr': 0.0004648063677357319, 'samples': 5241792, 'steps': 27300, 'loss/train': 0.8540429472923279}
+08/30/2021 18:03:36 - INFO - __main__ - Step 27302: {'lr': 0.00046480365277233316, 'samples': 5241984, 'steps': 27301, 'loss/train': 1.4378702640533447}
+08/30/2021 18:03:37 - INFO - __main__ - Step 27303: {'lr': 0.00046480093771214716, 'samples': 5242176, 'steps': 27302, 'loss/train': 1.3795442581176758}
+08/30/2021 18:03:37 - INFO - __main__ - Step 27304: {'lr': 0.0004647982225551751, 'samples': 5242368, 'steps': 27303, 'loss/train': 1.8644474744796753}
+08/30/2021 18:03:39 - INFO - __main__ - Step 27305: {'lr': 0.0004647955073014184, 'samples': 5242560, 'steps': 27304, 'loss/train': 1.4457502365112305}
+08/30/2021 18:03:39 - INFO - __main__ - Step 27306: {'lr': 0.00046479279195087804, 'samples': 5242752, 'steps': 27305, 'loss/train': 0.8158540725708008}
+08/30/2021 18:03:40 - INFO - __main__ - Step 27307: {'lr': 0.0004647900765035554, 'samples': 5242944, 'steps': 27306, 'loss/train': 1.3061364889144897}
+08/30/2021 18:03:40 - INFO - __main__ - Step 27308: {'lr': 0.0004647873609594517, 'samples': 5243136, 'steps': 27307, 'loss/train': 1.8341137170791626}
+08/30/2021 18:03:40 - INFO - __main__ - Step 27309: {'lr': 0.0004647846453185681, 'samples': 5243328, 'steps': 27308, 'loss/train': 1.4347705841064453}
+08/30/2021 18:03:42 - INFO - __main__ - Step 27310: {'lr': 0.0004647819295809059, 'samples': 5243520, 'steps': 27309, 'loss/train': 1.2835569381713867}
+08/30/2021 18:03:43 - INFO - __main__ - Step 27311: {'lr': 0.00046477921374646624, 'samples': 5243712, 'steps': 27310, 'loss/train': 1.5727505683898926}
+08/30/2021 18:03:43 - INFO - __main__ - Step 27312: {'lr': 0.0004647764978152503, 'samples': 5243904, 'steps': 27311, 'loss/train': 1.3658605813980103}
+08/30/2021 18:03:43 - INFO - __main__ - Step 27313: {'lr': 0.0004647737817872595, 'samples': 5244096, 'steps': 27312, 'loss/train': 0.8591522574424744}
+08/30/2021 18:03:44 - INFO - __main__ - Step 27314: {'lr': 0.0004647710656624949, 'samples': 5244288, 'steps': 27313, 'loss/train': 1.8187135457992554}
+08/30/2021 18:03:45 - INFO - __main__ - Step 27315: {'lr': 0.0004647683494409578, 'samples': 5244480, 'steps': 27314, 'loss/train': 1.6067172288894653}
+08/30/2021 18:03:45 - INFO - __main__ - Step 27316: {'lr': 0.0004647656331226494, 'samples': 5244672, 'steps': 27315, 'loss/train': 1.51498281955719}
+08/30/2021 18:03:46 - INFO - __main__ - Step 27317: {'lr': 0.0004647629167075709, 'samples': 5244864, 'steps': 27316, 'loss/train': 1.5694047212600708}
+08/30/2021 18:03:46 - INFO - __main__ - Step 27318: {'lr': 0.00046476020019572354, 'samples': 5245056, 'steps': 27317, 'loss/train': 1.5925524234771729}
+08/30/2021 18:03:46 - INFO - __main__ - Step 27319: {'lr': 0.00046475748358710856, 'samples': 5245248, 'steps': 27318, 'loss/train': 1.0620713233947754}
+08/30/2021 18:03:47 - INFO - __main__ - Step 27320: {'lr': 0.0004647547668817271, 'samples': 5245440, 'steps': 27319, 'loss/train': 1.2808213233947754}
+08/30/2021 18:03:49 - INFO - __main__ - Step 27321: {'lr': 0.00046475205007958054, 'samples': 5245632, 'steps': 27320, 'loss/train': 1.625947117805481}
+08/30/2021 18:03:49 - INFO - __main__ - Step 27322: {'lr': 0.00046474933318067004, 'samples': 5245824, 'steps': 27321, 'loss/train': 1.7700499296188354}
+08/30/2021 18:03:49 - INFO - __main__ - Step 27323: {'lr': 0.0004647466161849968, 'samples': 5246016, 'steps': 27322, 'loss/train': 1.7060738801956177}
+08/30/2021 18:03:50 - INFO - __main__ - Step 27324: {'lr': 0.000464743899092562, 'samples': 5246208, 'steps': 27323, 'loss/train': 1.4622997045516968}
+08/30/2021 18:03:50 - INFO - __main__ - Step 27325: {'lr': 0.0004647411819033669, 'samples': 5246400, 'steps': 27324, 'loss/train': 0.04158177599310875}
+08/30/2021 18:03:50 - INFO - __main__ - Step 27326: {'lr': 0.00046473846461741276, 'samples': 5246592, 'steps': 27325, 'loss/train': 1.4114559888839722}
+08/30/2021 18:03:52 - INFO - __main__ - Step 27327: {'lr': 0.0004647357472347008, 'samples': 5246784, 'steps': 27326, 'loss/train': 1.964754343032837}
+08/30/2021 18:03:52 - INFO - __main__ - Step 27328: {'lr': 0.00046473302975523224, 'samples': 5246976, 'steps': 27327, 'loss/train': 1.4276273250579834}
+08/30/2021 18:03:53 - INFO - __main__ - Step 27329: {'lr': 0.0004647303121790082, 'samples': 5247168, 'steps': 27328, 'loss/train': 1.6231714487075806}
+08/30/2021 18:03:53 - INFO - __main__ - Step 27330: {'lr': 0.0004647275945060301, 'samples': 5247360, 'steps': 27329, 'loss/train': 1.151721715927124}
+08/30/2021 18:03:53 - INFO - __main__ - Step 27331: {'lr': 0.000464724876736299, 'samples': 5247552, 'steps': 27330, 'loss/train': 2.5251708030700684}
+08/30/2021 18:03:55 - INFO - __main__ - Step 27332: {'lr': 0.00046472215886981616, 'samples': 5247744, 'steps': 27331, 'loss/train': 0.6353248953819275}
+08/30/2021 18:03:55 - INFO - __main__ - Step 27333: {'lr': 0.00046471944090658294, 'samples': 5247936, 'steps': 27332, 'loss/train': 1.8478977680206299}
+08/30/2021 18:03:56 - INFO - __main__ - Step 27334: {'lr': 0.0004647167228466004, 'samples': 5248128, 'steps': 27333, 'loss/train': 0.6284403800964355}
+08/30/2021 18:03:56 - INFO - __main__ - Step 27335: {'lr': 0.0004647140046898697, 'samples': 5248320, 'steps': 27334, 'loss/train': 1.6182653903961182}
+08/30/2021 18:03:56 - INFO - __main__ - Step 27336: {'lr': 0.0004647112864363923, 'samples': 5248512, 'steps': 27335, 'loss/train': 1.2258281707763672}
+08/30/2021 18:03:58 - INFO - __main__ - Step 27337: {'lr': 0.00046470856808616934, 'samples': 5248704, 'steps': 27336, 'loss/train': 1.7995223999023438}
+08/30/2021 18:03:58 - INFO - __main__ - Step 27338: {'lr': 0.0004647058496392019, 'samples': 5248896, 'steps': 27337, 'loss/train': 0.9250343441963196}
+08/30/2021 18:03:59 - INFO - __main__ - Step 27339: {'lr': 0.0004647031310954914, 'samples': 5249088, 'steps': 27338, 'loss/train': 1.7553257942199707}
+08/30/2021 18:03:59 - INFO - __main__ - Step 27340: {'lr': 0.00046470041245503895, 'samples': 5249280, 'steps': 27339, 'loss/train': 1.399047613143921}
+08/30/2021 18:03:59 - INFO - __main__ - Step 27341: {'lr': 0.0004646976937178459, 'samples': 5249472, 'steps': 27340, 'loss/train': 2.1510541439056396}
+08/30/2021 18:04:01 - INFO - __main__ - Step 27342: {'lr': 0.0004646949748839132, 'samples': 5249664, 'steps': 27341, 'loss/train': 0.9165777564048767}
+08/30/2021 18:04:01 - INFO - __main__ - Step 27343: {'lr': 0.0004646922559532424, 'samples': 5249856, 'steps': 27342, 'loss/train': 1.3690391778945923}
+08/30/2021 18:04:02 - INFO - __main__ - Step 27344: {'lr': 0.0004646895369258345, 'samples': 5250048, 'steps': 27343, 'loss/train': 0.8818331360816956}
+08/30/2021 18:04:02 - INFO - __main__ - Step 27345: {'lr': 0.00046468681780169086, 'samples': 5250240, 'steps': 27344, 'loss/train': 1.3514323234558105}
+08/30/2021 18:04:02 - INFO - __main__ - Step 27346: {'lr': 0.0004646840985808126, 'samples': 5250432, 'steps': 27345, 'loss/train': 1.0465266704559326}
+08/30/2021 18:04:04 - INFO - __main__ - Step 27347: {'lr': 0.0004646813792632011, 'samples': 5250624, 'steps': 27346, 'loss/train': 1.541799545288086}
+08/30/2021 18:04:04 - INFO - __main__ - Step 27348: {'lr': 0.00046467865984885736, 'samples': 5250816, 'steps': 27347, 'loss/train': 1.7342004776000977}
+08/30/2021 18:04:05 - INFO - __main__ - Step 27349: {'lr': 0.0004646759403377828, 'samples': 5251008, 'steps': 27348, 'loss/train': 1.3066784143447876}
+08/30/2021 18:04:05 - INFO - __main__ - Step 27350: {'lr': 0.00046467322072997865, 'samples': 5251200, 'steps': 27349, 'loss/train': 1.6642979383468628}
+08/30/2021 18:04:05 - INFO - __main__ - Step 27351: {'lr': 0.00046467050102544594, 'samples': 5251392, 'steps': 27350, 'loss/train': 1.3448563814163208}
+08/30/2021 18:04:06 - INFO - __main__ - Step 27352: {'lr': 0.0004646677812241861, 'samples': 5251584, 'steps': 27351, 'loss/train': 1.191585659980774}
+08/30/2021 18:04:07 - INFO - __main__ - Step 27353: {'lr': 0.0004646650613262001, 'samples': 5251776, 'steps': 27352, 'loss/train': 0.6744791865348816}
+08/30/2021 18:04:08 - INFO - __main__ - Step 27354: {'lr': 0.00046466234133148957, 'samples': 5251968, 'steps': 27353, 'loss/train': 1.1724281311035156}
+08/30/2021 18:04:08 - INFO - __main__ - Step 27355: {'lr': 0.00046465962124005535, 'samples': 5252160, 'steps': 27354, 'loss/train': 1.4432481527328491}
+08/30/2021 18:04:08 - INFO - __main__ - Step 27356: {'lr': 0.0004646569010518988, 'samples': 5252352, 'steps': 27355, 'loss/train': 1.5820986032485962}
+08/30/2021 18:04:09 - INFO - __main__ - Step 27357: {'lr': 0.00046465418076702125, 'samples': 5252544, 'steps': 27356, 'loss/train': 1.2430405616760254}
+08/30/2021 18:04:11 - INFO - __main__ - Step 27358: {'lr': 0.00046465146038542375, 'samples': 5252736, 'steps': 27357, 'loss/train': 1.4338152408599854}
+08/30/2021 18:04:11 - INFO - __main__ - Step 27359: {'lr': 0.0004646487399071077, 'samples': 5252928, 'steps': 27358, 'loss/train': 1.0728802680969238}
+08/30/2021 18:04:12 - INFO - __main__ - Step 27360: {'lr': 0.00046464601933207417, 'samples': 5253120, 'steps': 27359, 'loss/train': 1.418859839439392}
+08/30/2021 18:04:12 - INFO - __main__ - Step 27361: {'lr': 0.0004646432986603245, 'samples': 5253312, 'steps': 27360, 'loss/train': 1.0611650943756104}
+08/30/2021 18:04:12 - INFO - __main__ - Step 27362: {'lr': 0.00046464057789185985, 'samples': 5253504, 'steps': 27361, 'loss/train': 0.5609676241874695}
+08/30/2021 18:04:15 - INFO - __main__ - Step 27363: {'lr': 0.00046463785702668156, 'samples': 5253696, 'steps': 27362, 'loss/train': 2.100377082824707}
+08/30/2021 18:04:15 - INFO - __main__ - Step 27364: {'lr': 0.0004646351360647907, 'samples': 5253888, 'steps': 27363, 'loss/train': 1.3934309482574463}
+08/30/2021 18:04:16 - INFO - __main__ - Step 27365: {'lr': 0.00046463241500618846, 'samples': 5254080, 'steps': 27364, 'loss/train': 1.6407395601272583}
+08/30/2021 18:04:16 - INFO - __main__ - Step 27366: {'lr': 0.00046462969385087626, 'samples': 5254272, 'steps': 27365, 'loss/train': 1.9130204916000366}
+08/30/2021 18:04:16 - INFO - __main__ - Step 27367: {'lr': 0.00046462697259885523, 'samples': 5254464, 'steps': 27366, 'loss/train': 3.333629846572876}
+08/30/2021 18:04:17 - INFO - __main__ - Step 27368: {'lr': 0.0004646242512501266, 'samples': 5254656, 'steps': 27367, 'loss/train': 2.2948241233825684}
+08/30/2021 18:04:18 - INFO - __main__ - Step 27369: {'lr': 0.0004646215298046916, 'samples': 5254848, 'steps': 27368, 'loss/train': 2.367582082748413}
+08/30/2021 18:04:19 - INFO - __main__ - Step 27370: {'lr': 0.00046461880826255143, 'samples': 5255040, 'steps': 27369, 'loss/train': 1.4502631425857544}
+08/30/2021 18:04:19 - INFO - __main__ - Step 27371: {'lr': 0.00046461608662370734, 'samples': 5255232, 'steps': 27370, 'loss/train': 1.9257307052612305}
+08/30/2021 18:04:19 - INFO - __main__ - Step 27372: {'lr': 0.0004646133648881606, 'samples': 5255424, 'steps': 27371, 'loss/train': 1.5148178339004517}
+08/30/2021 18:04:20 - INFO - __main__ - Step 27373: {'lr': 0.00046461064305591235, 'samples': 5255616, 'steps': 27372, 'loss/train': 1.9873127937316895}
+08/30/2021 18:04:20 - INFO - __main__ - Step 27374: {'lr': 0.00046460792112696384, 'samples': 5255808, 'steps': 27373, 'loss/train': 0.8149328231811523}
+08/30/2021 18:04:21 - INFO - __main__ - Step 27375: {'lr': 0.0004646051991013163, 'samples': 5256000, 'steps': 27374, 'loss/train': 1.8680310249328613}
+08/30/2021 18:04:22 - INFO - __main__ - Step 27376: {'lr': 0.000464602476978971, 'samples': 5256192, 'steps': 27375, 'loss/train': 0.9939104318618774}
+08/30/2021 18:04:22 - INFO - __main__ - Step 27377: {'lr': 0.00046459975475992914, 'samples': 5256384, 'steps': 27376, 'loss/train': 1.577289342880249}
+08/30/2021 18:04:23 - INFO - __main__ - Step 27378: {'lr': 0.00046459703244419194, 'samples': 5256576, 'steps': 27377, 'loss/train': 1.6684318780899048}
+08/30/2021 18:04:23 - INFO - __main__ - Step 27379: {'lr': 0.0004645943100317606, 'samples': 5256768, 'steps': 27378, 'loss/train': 1.620996356010437}
+08/30/2021 18:04:25 - INFO - __main__ - Step 27380: {'lr': 0.00046459158752263643, 'samples': 5256960, 'steps': 27379, 'loss/train': 1.4244303703308105}
+08/30/2021 18:04:25 - INFO - __main__ - Step 27381: {'lr': 0.0004645888649168205, 'samples': 5257152, 'steps': 27380, 'loss/train': 1.8420264720916748}
+08/30/2021 18:04:25 - INFO - __main__ - Step 27382: {'lr': 0.0004645861422143143, 'samples': 5257344, 'steps': 27381, 'loss/train': 1.68105149269104}
+08/30/2021 18:04:26 - INFO - __main__ - Step 27383: {'lr': 0.0004645834194151187, 'samples': 5257536, 'steps': 27382, 'loss/train': 1.6556614637374878}
+08/30/2021 18:04:26 - INFO - __main__ - Step 27384: {'lr': 0.0004645806965192353, 'samples': 5257728, 'steps': 27383, 'loss/train': 1.6255290508270264}
+08/30/2021 18:04:28 - INFO - __main__ - Step 27385: {'lr': 0.000464577973526665, 'samples': 5257920, 'steps': 27384, 'loss/train': 1.6095224618911743}
+08/30/2021 18:04:28 - INFO - __main__ - Step 27386: {'lr': 0.00046457525043740926, 'samples': 5258112, 'steps': 27385, 'loss/train': 1.5118950605392456}
+08/30/2021 18:04:29 - INFO - __main__ - Step 27387: {'lr': 0.0004645725272514693, 'samples': 5258304, 'steps': 27386, 'loss/train': 1.5710792541503906}
+08/30/2021 18:04:29 - INFO - __main__ - Step 27388: {'lr': 0.0004645698039688461, 'samples': 5258496, 'steps': 27387, 'loss/train': 1.990828514099121}
+08/30/2021 18:04:29 - INFO - __main__ - Step 27389: {'lr': 0.00046456708058954116, 'samples': 5258688, 'steps': 27388, 'loss/train': 1.6931428909301758}
+08/30/2021 18:04:31 - INFO - __main__ - Step 27390: {'lr': 0.0004645643571135556, 'samples': 5258880, 'steps': 27389, 'loss/train': 1.568619966506958}
+08/30/2021 18:04:31 - INFO - __main__ - Step 27391: {'lr': 0.00046456163354089065, 'samples': 5259072, 'steps': 27390, 'loss/train': 1.7756857872009277}
+08/30/2021 18:04:31 - INFO - __main__ - Step 27392: {'lr': 0.00046455890987154747, 'samples': 5259264, 'steps': 27391, 'loss/train': 2.837989330291748}
+08/30/2021 18:04:32 - INFO - __main__ - Step 27393: {'lr': 0.0004645561861055274, 'samples': 5259456, 'steps': 27392, 'loss/train': 1.8848211765289307}
+08/30/2021 18:04:32 - INFO - __main__ - Step 27394: {'lr': 0.00046455346224283167, 'samples': 5259648, 'steps': 27393, 'loss/train': 0.8997451663017273}
+08/30/2021 18:04:34 - INFO - __main__ - Step 27395: {'lr': 0.00046455073828346137, 'samples': 5259840, 'steps': 27394, 'loss/train': 1.7699164152145386}
+08/30/2021 18:04:34 - INFO - __main__ - Step 27396: {'lr': 0.0004645480142274179, 'samples': 5260032, 'steps': 27395, 'loss/train': 1.2306593656539917}
+08/30/2021 18:04:34 - INFO - __main__ - Step 27397: {'lr': 0.0004645452900747024, 'samples': 5260224, 'steps': 27396, 'loss/train': 1.6315412521362305}
+08/30/2021 18:04:35 - INFO - __main__ - Step 27398: {'lr': 0.00046454256582531604, 'samples': 5260416, 'steps': 27397, 'loss/train': 2.2044410705566406}
+08/30/2021 18:04:35 - INFO - __main__ - Step 27399: {'lr': 0.0004645398414792602, 'samples': 5260608, 'steps': 27398, 'loss/train': 0.7364284992218018}
+08/30/2021 18:04:37 - INFO - __main__ - Step 27400: {'lr': 0.000464537117036536, 'samples': 5260800, 'steps': 27399, 'loss/train': 1.4160264730453491}
+08/30/2021 18:04:37 - INFO - __main__ - Step 27401: {'lr': 0.00046453439249714466, 'samples': 5260992, 'steps': 27400, 'loss/train': 2.031721830368042}
+08/30/2021 18:04:37 - INFO - __main__ - Step 27402: {'lr': 0.00046453166786108736, 'samples': 5261184, 'steps': 27401, 'loss/train': 1.9949887990951538}
+08/30/2021 18:04:38 - INFO - __main__ - Step 27403: {'lr': 0.00046452894312836547, 'samples': 5261376, 'steps': 27402, 'loss/train': 1.9851300716400146}
+08/30/2021 18:04:38 - INFO - __main__ - Step 27404: {'lr': 0.0004645262182989802, 'samples': 5261568, 'steps': 27403, 'loss/train': 1.0105459690093994}
+08/30/2021 18:04:40 - INFO - __main__ - Step 27405: {'lr': 0.0004645234933729327, 'samples': 5261760, 'steps': 27404, 'loss/train': 0.06788698583841324}
+08/30/2021 18:04:40 - INFO - __main__ - Step 27406: {'lr': 0.00046452076835022416, 'samples': 5261952, 'steps': 27405, 'loss/train': 1.4818108081817627}
+08/30/2021 18:04:41 - INFO - __main__ - Step 27407: {'lr': 0.0004645180432308559, 'samples': 5262144, 'steps': 27406, 'loss/train': 1.0781244039535522}
+08/30/2021 18:04:41 - INFO - __main__ - Step 27408: {'lr': 0.00046451531801482913, 'samples': 5262336, 'steps': 27407, 'loss/train': 1.3619756698608398}
+08/30/2021 18:04:41 - INFO - __main__ - Step 27409: {'lr': 0.00046451259270214505, 'samples': 5262528, 'steps': 27408, 'loss/train': 1.224409580230713}
+08/30/2021 18:04:42 - INFO - __main__ - Step 27410: {'lr': 0.00046450986729280495, 'samples': 5262720, 'steps': 27409, 'loss/train': 1.8427653312683105}
+08/30/2021 18:04:43 - INFO - __main__ - Step 27411: {'lr': 0.00046450714178680996, 'samples': 5262912, 'steps': 27410, 'loss/train': 1.615390658378601}
+08/30/2021 18:04:44 - INFO - __main__ - Step 27412: {'lr': 0.0004645044161841614, 'samples': 5263104, 'steps': 27411, 'loss/train': 1.1181161403656006}
+08/30/2021 18:04:44 - INFO - __main__ - Step 27413: {'lr': 0.00046450169048486045, 'samples': 5263296, 'steps': 27412, 'loss/train': 1.1217595338821411}
+08/30/2021 18:04:44 - INFO - __main__ - Step 27414: {'lr': 0.0004644989646889084, 'samples': 5263488, 'steps': 27413, 'loss/train': 1.69459068775177}
+08/30/2021 18:04:45 - INFO - __main__ - Step 27415: {'lr': 0.0004644962387963063, 'samples': 5263680, 'steps': 27414, 'loss/train': 1.5929012298583984}
+08/30/2021 18:04:47 - INFO - __main__ - Step 27416: {'lr': 0.0004644935128070556, 'samples': 5263872, 'steps': 27415, 'loss/train': 1.9933714866638184}
+08/30/2021 18:04:47 - INFO - __main__ - Step 27417: {'lr': 0.0004644907867211574, 'samples': 5264064, 'steps': 27416, 'loss/train': 1.4617135524749756}
+08/30/2021 18:04:47 - INFO - __main__ - Step 27418: {'lr': 0.000464488060538613, 'samples': 5264256, 'steps': 27417, 'loss/train': 1.5432010889053345}
+08/30/2021 18:04:48 - INFO - __main__ - Step 27419: {'lr': 0.0004644853342594235, 'samples': 5264448, 'steps': 27418, 'loss/train': 1.5122867822647095}
+08/30/2021 18:04:48 - INFO - __main__ - Step 27420: {'lr': 0.0004644826078835903, 'samples': 5264640, 'steps': 27419, 'loss/train': 1.713381290435791}
+08/30/2021 18:04:50 - INFO - __main__ - Step 27421: {'lr': 0.00046447988141111457, 'samples': 5264832, 'steps': 27420, 'loss/train': 1.7288973331451416}
+08/30/2021 18:04:50 - INFO - __main__ - Step 27422: {'lr': 0.0004644771548419975, 'samples': 5265024, 'steps': 27421, 'loss/train': 1.3567960262298584}
+08/30/2021 18:04:51 - INFO - __main__ - Step 27423: {'lr': 0.0004644744281762403, 'samples': 5265216, 'steps': 27422, 'loss/train': 2.2251620292663574}
+08/30/2021 18:04:51 - INFO - __main__ - Step 27424: {'lr': 0.0004644717014138442, 'samples': 5265408, 'steps': 27423, 'loss/train': 1.5661921501159668}
+08/30/2021 18:04:51 - INFO - __main__ - Step 27425: {'lr': 0.0004644689745548105, 'samples': 5265600, 'steps': 27424, 'loss/train': 0.5250753164291382}
+08/30/2021 18:04:53 - INFO - __main__ - Step 27426: {'lr': 0.00046446624759914043, 'samples': 5265792, 'steps': 27425, 'loss/train': 1.2815206050872803}
+08/30/2021 18:04:53 - INFO - __main__ - Step 27427: {'lr': 0.0004644635205468351, 'samples': 5265984, 'steps': 27426, 'loss/train': 1.7290304899215698}
+08/30/2021 18:04:54 - INFO - __main__ - Step 27428: {'lr': 0.00046446079339789587, 'samples': 5266176, 'steps': 27427, 'loss/train': 1.6286661624908447}
+08/30/2021 18:04:54 - INFO - __main__ - Step 27429: {'lr': 0.0004644580661523239, 'samples': 5266368, 'steps': 27428, 'loss/train': 1.294432520866394}
+08/30/2021 18:04:54 - INFO - __main__ - Step 27430: {'lr': 0.00046445533881012043, 'samples': 5266560, 'steps': 27429, 'loss/train': 1.2775497436523438}
+08/30/2021 18:04:56 - INFO - __main__ - Step 27431: {'lr': 0.0004644526113712867, 'samples': 5266752, 'steps': 27430, 'loss/train': 1.9153541326522827}
+08/30/2021 18:04:57 - INFO - __main__ - Step 27432: {'lr': 0.00046444988383582394, 'samples': 5266944, 'steps': 27431, 'loss/train': 1.5451918840408325}
+08/30/2021 18:04:57 - INFO - __main__ - Step 27433: {'lr': 0.0004644471562037333, 'samples': 5267136, 'steps': 27432, 'loss/train': 0.24773718416690826}
+08/30/2021 18:04:57 - INFO - __main__ - Step 27434: {'lr': 0.0004644444284750162, 'samples': 5267328, 'steps': 27433, 'loss/train': 1.4150580167770386}
+08/30/2021 18:04:58 - INFO - __main__ - Step 27435: {'lr': 0.0004644417006496737, 'samples': 5267520, 'steps': 27434, 'loss/train': 1.601648211479187}
+08/30/2021 18:04:59 - INFO - __main__ - Step 27436: {'lr': 0.0004644389727277071, 'samples': 5267712, 'steps': 27435, 'loss/train': 1.2211816310882568}
+08/30/2021 18:05:00 - INFO - __main__ - Step 27437: {'lr': 0.00046443624470911754, 'samples': 5267904, 'steps': 27436, 'loss/train': 1.636705994606018}
+08/30/2021 18:05:00 - INFO - __main__ - Step 27438: {'lr': 0.00046443351659390637, 'samples': 5268096, 'steps': 27437, 'loss/train': 1.3936412334442139}
+08/30/2021 18:05:01 - INFO - __main__ - Step 27439: {'lr': 0.00046443078838207474, 'samples': 5268288, 'steps': 27438, 'loss/train': 1.8843578100204468}
+08/30/2021 18:05:01 - INFO - __main__ - Step 27440: {'lr': 0.00046442806007362394, 'samples': 5268480, 'steps': 27439, 'loss/train': 1.2439494132995605}
+08/30/2021 18:05:01 - INFO - __main__ - Step 27441: {'lr': 0.00046442533166855517, 'samples': 5268672, 'steps': 27440, 'loss/train': 0.8290183544158936}
+08/30/2021 18:05:03 - INFO - __main__ - Step 27442: {'lr': 0.00046442260316686957, 'samples': 5268864, 'steps': 27441, 'loss/train': 1.4382227659225464}
+08/30/2021 18:05:03 - INFO - __main__ - Step 27443: {'lr': 0.0004644198745685685, 'samples': 5269056, 'steps': 27442, 'loss/train': 1.6046395301818848}
+08/30/2021 18:05:04 - INFO - __main__ - Step 27444: {'lr': 0.00046441714587365317, 'samples': 5269248, 'steps': 27443, 'loss/train': 2.005960464477539}
+08/30/2021 18:05:04 - INFO - __main__ - Step 27445: {'lr': 0.00046441441708212477, 'samples': 5269440, 'steps': 27444, 'loss/train': 2.0347695350646973}
+08/30/2021 18:05:04 - INFO - __main__ - Step 27446: {'lr': 0.00046441168819398457, 'samples': 5269632, 'steps': 27445, 'loss/train': 1.2989490032196045}
+08/30/2021 18:05:06 - INFO - __main__ - Step 27447: {'lr': 0.0004644089592092338, 'samples': 5269824, 'steps': 27446, 'loss/train': 1.4103548526763916}
+08/30/2021 18:05:07 - INFO - __main__ - Step 27448: {'lr': 0.0004644062301278735, 'samples': 5270016, 'steps': 27447, 'loss/train': 1.3690731525421143}
+08/30/2021 18:05:07 - INFO - __main__ - Step 27449: {'lr': 0.0004644035009499052, 'samples': 5270208, 'steps': 27448, 'loss/train': 1.497934103012085}
+08/30/2021 18:05:07 - INFO - __main__ - Step 27450: {'lr': 0.0004644007716753299, 'samples': 5270400, 'steps': 27449, 'loss/train': 1.3804068565368652}
+08/30/2021 18:05:08 - INFO - __main__ - Step 27451: {'lr': 0.00046439804230414904, 'samples': 5270592, 'steps': 27450, 'loss/train': 1.993382215499878}
+08/30/2021 18:05:09 - INFO - __main__ - Step 27452: {'lr': 0.0004643953128363637, 'samples': 5270784, 'steps': 27451, 'loss/train': 0.4664199650287628}
+08/30/2021 18:05:10 - INFO - __main__ - Step 27453: {'lr': 0.0004643925832719751, 'samples': 5270976, 'steps': 27452, 'loss/train': 1.0037028789520264}
+08/30/2021 18:05:10 - INFO - __main__ - Step 27454: {'lr': 0.0004643898536109845, 'samples': 5271168, 'steps': 27453, 'loss/train': 1.2655574083328247}
+08/30/2021 18:05:10 - INFO - __main__ - Step 27455: {'lr': 0.0004643871238533931, 'samples': 5271360, 'steps': 27454, 'loss/train': 1.277710199356079}
+08/30/2021 18:05:11 - INFO - __main__ - Step 27456: {'lr': 0.0004643843939992022, 'samples': 5271552, 'steps': 27455, 'loss/train': 1.315433144569397}
+08/30/2021 18:05:11 - INFO - __main__ - Step 27457: {'lr': 0.0004643816640484131, 'samples': 5271744, 'steps': 27456, 'loss/train': 1.73223876953125}
+08/30/2021 18:05:13 - INFO - __main__ - Step 27458: {'lr': 0.0004643789340010268, 'samples': 5271936, 'steps': 27457, 'loss/train': 1.7017115354537964}
+08/30/2021 18:05:13 - INFO - __main__ - Step 27459: {'lr': 0.00046437620385704476, 'samples': 5272128, 'steps': 27458, 'loss/train': 1.2132965326309204}
+08/30/2021 18:05:13 - INFO - __main__ - Step 27460: {'lr': 0.0004643734736164681, 'samples': 5272320, 'steps': 27459, 'loss/train': 1.5949082374572754}
+08/30/2021 18:05:14 - INFO - __main__ - Step 27461: {'lr': 0.00046437074327929795, 'samples': 5272512, 'steps': 27460, 'loss/train': 1.6055718660354614}
+08/30/2021 18:05:14 - INFO - __main__ - Step 27462: {'lr': 0.0004643680128455358, 'samples': 5272704, 'steps': 27461, 'loss/train': 1.2206093072891235}
+08/30/2021 18:05:15 - INFO - __main__ - Step 27463: {'lr': 0.00046436528231518263, 'samples': 5272896, 'steps': 27462, 'loss/train': 1.6541802883148193}
+08/30/2021 18:05:16 - INFO - __main__ - Step 27464: {'lr': 0.0004643625516882398, 'samples': 5273088, 'steps': 27463, 'loss/train': 0.5171638131141663}
+08/30/2021 18:05:16 - INFO - __main__ - Step 27465: {'lr': 0.0004643598209647085, 'samples': 5273280, 'steps': 27464, 'loss/train': 1.495107650756836}
+08/30/2021 18:05:17 - INFO - __main__ - Step 27466: {'lr': 0.00046435709014459, 'samples': 5273472, 'steps': 27465, 'loss/train': 0.47101113200187683}
+08/30/2021 18:05:17 - INFO - __main__ - Step 27467: {'lr': 0.0004643543592278855, 'samples': 5273664, 'steps': 27466, 'loss/train': 1.4665911197662354}
+08/30/2021 18:05:19 - INFO - __main__ - Step 27468: {'lr': 0.0004643516282145962, 'samples': 5273856, 'steps': 27467, 'loss/train': 1.4858365058898926}
+08/30/2021 18:05:20 - INFO - __main__ - Step 27469: {'lr': 0.0004643488971047234, 'samples': 5274048, 'steps': 27468, 'loss/train': 1.8858387470245361}
+08/30/2021 18:05:20 - INFO - __main__ - Step 27470: {'lr': 0.0004643461658982683, 'samples': 5274240, 'steps': 27469, 'loss/train': 1.5373194217681885}
+08/30/2021 18:05:20 - INFO - __main__ - Step 27471: {'lr': 0.00046434343459523207, 'samples': 5274432, 'steps': 27470, 'loss/train': 1.1708983182907104}
+08/30/2021 18:05:21 - INFO - __main__ - Step 27472: {'lr': 0.00046434070319561604, 'samples': 5274624, 'steps': 27471, 'loss/train': 2.240302324295044}
+08/30/2021 18:05:21 - INFO - __main__ - Step 27473: {'lr': 0.0004643379716994214, 'samples': 5274816, 'steps': 27472, 'loss/train': 1.2890220880508423}
+08/30/2021 18:05:23 - INFO - __main__ - Step 27474: {'lr': 0.0004643352401066494, 'samples': 5275008, 'steps': 27473, 'loss/train': 1.1141462326049805}
+08/30/2021 18:05:23 - INFO - __main__ - Step 27475: {'lr': 0.00046433250841730123, 'samples': 5275200, 'steps': 27474, 'loss/train': 1.5007108449935913}
+08/30/2021 18:05:23 - INFO - __main__ - Step 27476: {'lr': 0.0004643297766313781, 'samples': 5275392, 'steps': 27475, 'loss/train': 0.09506670385599136}
+08/30/2021 18:05:24 - INFO - __main__ - Step 27477: {'lr': 0.0004643270447488813, 'samples': 5275584, 'steps': 27476, 'loss/train': 1.9615954160690308}
+08/30/2021 18:05:24 - INFO - __main__ - Step 27478: {'lr': 0.000464324312769812, 'samples': 5275776, 'steps': 27477, 'loss/train': 0.7599114179611206}
+08/30/2021 18:05:25 - INFO - __main__ - Step 27479: {'lr': 0.0004643215806941716, 'samples': 5275968, 'steps': 27478, 'loss/train': 1.615844488143921}
+08/30/2021 18:05:26 - INFO - __main__ - Step 27480: {'lr': 0.00046431884852196105, 'samples': 5276160, 'steps': 27479, 'loss/train': 1.6542208194732666}
+08/30/2021 18:05:26 - INFO - __main__ - Step 27481: {'lr': 0.0004643161162531818, 'samples': 5276352, 'steps': 27480, 'loss/train': 0.086514413356781}
+08/30/2021 18:05:27 - INFO - __main__ - Step 27482: {'lr': 0.00046431338388783504, 'samples': 5276544, 'steps': 27481, 'loss/train': 1.6083823442459106}
+08/30/2021 18:05:27 - INFO - __main__ - Step 27483: {'lr': 0.000464310651425922, 'samples': 5276736, 'steps': 27482, 'loss/train': 1.7101365327835083}
+08/30/2021 18:05:28 - INFO - __main__ - Step 27484: {'lr': 0.00046430791886744384, 'samples': 5276928, 'steps': 27483, 'loss/train': 1.96410071849823}
+08/30/2021 18:05:29 - INFO - __main__ - Step 27485: {'lr': 0.0004643051862124018, 'samples': 5277120, 'steps': 27484, 'loss/train': 1.3670763969421387}
+08/30/2021 18:05:29 - INFO - __main__ - Step 27486: {'lr': 0.0004643024534607973, 'samples': 5277312, 'steps': 27485, 'loss/train': 1.7785871028900146}
+08/30/2021 18:05:30 - INFO - __main__ - Step 27487: {'lr': 0.00046429972061263125, 'samples': 5277504, 'steps': 27486, 'loss/train': 1.5298993587493896}
+08/30/2021 18:05:30 - INFO - __main__ - Step 27488: {'lr': 0.0004642969876679051, 'samples': 5277696, 'steps': 27487, 'loss/train': 1.6133230924606323}
+08/30/2021 18:05:32 - INFO - __main__ - Step 27489: {'lr': 0.00046429425462662, 'samples': 5277888, 'steps': 27488, 'loss/train': 1.0676636695861816}
+08/30/2021 18:05:32 - INFO - __main__ - Step 27490: {'lr': 0.00046429152148877727, 'samples': 5278080, 'steps': 27489, 'loss/train': 0.8648391962051392}
+08/30/2021 18:05:32 - INFO - __main__ - Step 27491: {'lr': 0.00046428878825437815, 'samples': 5278272, 'steps': 27490, 'loss/train': 1.1295976638793945}
+08/30/2021 18:05:33 - INFO - __main__ - Step 27492: {'lr': 0.00046428605492342367, 'samples': 5278464, 'steps': 27491, 'loss/train': 1.5803020000457764}
+08/30/2021 18:05:33 - INFO - __main__ - Step 27493: {'lr': 0.00046428332149591535, 'samples': 5278656, 'steps': 27492, 'loss/train': 1.3380845785140991}
+08/30/2021 18:05:35 - INFO - __main__ - Step 27494: {'lr': 0.0004642805879718541, 'samples': 5278848, 'steps': 27493, 'loss/train': 0.903255820274353}
+08/30/2021 18:05:35 - INFO - __main__ - Step 27495: {'lr': 0.00046427785435124147, 'samples': 5279040, 'steps': 27494, 'loss/train': 1.5985044240951538}
+08/30/2021 18:05:35 - INFO - __main__ - Step 27496: {'lr': 0.0004642751206340785, 'samples': 5279232, 'steps': 27495, 'loss/train': 1.9975924491882324}
+08/30/2021 18:05:36 - INFO - __main__ - Step 27497: {'lr': 0.00046427238682036643, 'samples': 5279424, 'steps': 27496, 'loss/train': 1.249411940574646}
+08/30/2021 18:05:36 - INFO - __main__ - Step 27498: {'lr': 0.0004642696529101066, 'samples': 5279616, 'steps': 27497, 'loss/train': 2.1159005165100098}
+08/30/2021 18:05:38 - INFO - __main__ - Step 27499: {'lr': 0.0004642669189033001, 'samples': 5279808, 'steps': 27498, 'loss/train': 1.5861256122589111}
+08/30/2021 18:05:38 - INFO - __main__ - Step 27500: {'lr': 0.0004642641847999483, 'samples': 5280000, 'steps': 27499, 'loss/train': 1.195245623588562}
+08/30/2021 18:05:39 - INFO - __main__ - Step 27501: {'lr': 0.0004642614506000523, 'samples': 5280192, 'steps': 27500, 'loss/train': 1.4239248037338257}
+08/30/2021 18:05:39 - INFO - __main__ - Step 27502: {'lr': 0.00046425871630361343, 'samples': 5280384, 'steps': 27501, 'loss/train': 0.8084686398506165}
+08/30/2021 18:05:39 - INFO - __main__ - Step 27503: {'lr': 0.0004642559819106329, 'samples': 5280576, 'steps': 27502, 'loss/train': 0.9394906759262085}
+08/30/2021 18:05:41 - INFO - __main__ - Step 27504: {'lr': 0.0004642532474211119, 'samples': 5280768, 'steps': 27503, 'loss/train': 0.7073948979377747}
+08/30/2021 18:05:41 - INFO - __main__ - Step 27505: {'lr': 0.0004642505128350517, 'samples': 5280960, 'steps': 27504, 'loss/train': 1.5602253675460815}
+08/30/2021 18:05:42 - INFO - __main__ - Step 27506: {'lr': 0.00046424777815245354, 'samples': 5281152, 'steps': 27505, 'loss/train': 1.404266595840454}
+08/30/2021 18:05:42 - INFO - __main__ - Step 27507: {'lr': 0.0004642450433733186, 'samples': 5281344, 'steps': 27506, 'loss/train': 1.1671524047851562}
+08/30/2021 18:05:42 - INFO - __main__ - Step 27508: {'lr': 0.0004642423084976482, 'samples': 5281536, 'steps': 27507, 'loss/train': 1.3224974870681763}
+08/30/2021 18:05:43 - INFO - __main__ - Step 27509: {'lr': 0.0004642395735254435, 'samples': 5281728, 'steps': 27508, 'loss/train': 1.2267792224884033}
+08/30/2021 18:05:44 - INFO - __main__ - Step 27510: {'lr': 0.0004642368384567058, 'samples': 5281920, 'steps': 27509, 'loss/train': 1.0123409032821655}
+08/30/2021 18:05:45 - INFO - __main__ - Step 27511: {'lr': 0.0004642341032914362, 'samples': 5282112, 'steps': 27510, 'loss/train': 1.685687780380249}
+08/30/2021 18:05:45 - INFO - __main__ - Step 27512: {'lr': 0.00046423136802963607, 'samples': 5282304, 'steps': 27511, 'loss/train': 1.1748380661010742}
+08/30/2021 18:05:45 - INFO - __main__ - Step 27513: {'lr': 0.0004642286326713065, 'samples': 5282496, 'steps': 27512, 'loss/train': 0.4168582260608673}
+08/30/2021 18:05:46 - INFO - __main__ - Step 27514: {'lr': 0.000464225897216449, 'samples': 5282688, 'steps': 27513, 'loss/train': 1.7291203737258911}
+08/30/2021 18:05:47 - INFO - __main__ - Step 27515: {'lr': 0.0004642231616650645, 'samples': 5282880, 'steps': 27514, 'loss/train': 1.0879120826721191}
+08/30/2021 18:05:48 - INFO - __main__ - Step 27516: {'lr': 0.00046422042601715433, 'samples': 5283072, 'steps': 27515, 'loss/train': 1.5452195405960083}
+08/30/2021 18:05:48 - INFO - __main__ - Step 27517: {'lr': 0.00046421769027271974, 'samples': 5283264, 'steps': 27516, 'loss/train': 1.001875638961792}
+08/30/2021 18:05:48 - INFO - __main__ - Step 27518: {'lr': 0.00046421495443176204, 'samples': 5283456, 'steps': 27517, 'loss/train': 1.0665472745895386}
+08/30/2021 18:05:49 - INFO - __main__ - Step 27519: {'lr': 0.0004642122184942824, 'samples': 5283648, 'steps': 27518, 'loss/train': 1.7137739658355713}
+08/30/2021 18:05:49 - INFO - __main__ - Step 27520: {'lr': 0.00046420948246028194, 'samples': 5283840, 'steps': 27519, 'loss/train': 1.6226041316986084}
+08/30/2021 18:05:51 - INFO - __main__ - Step 27521: {'lr': 0.000464206746329762, 'samples': 5284032, 'steps': 27520, 'loss/train': 0.6680510640144348}
+08/30/2021 18:05:52 - INFO - __main__ - Step 27522: {'lr': 0.00046420401010272385, 'samples': 5284224, 'steps': 27521, 'loss/train': 0.7357050776481628}
+08/30/2021 18:05:52 - INFO - __main__ - Step 27523: {'lr': 0.00046420127377916863, 'samples': 5284416, 'steps': 27522, 'loss/train': 1.5431907176971436}
+08/30/2021 18:05:53 - INFO - __main__ - Step 27524: {'lr': 0.0004641985373590977, 'samples': 5284608, 'steps': 27523, 'loss/train': 1.854203224182129}
+08/30/2021 18:05:53 - INFO - __main__ - Step 27525: {'lr': 0.00046419580084251224, 'samples': 5284800, 'steps': 27524, 'loss/train': 1.321053147315979}
+08/30/2021 18:05:55 - INFO - __main__ - Step 27526: {'lr': 0.0004641930642294133, 'samples': 5284992, 'steps': 27525, 'loss/train': 1.2070436477661133}
+08/30/2021 18:05:55 - INFO - __main__ - Step 27527: {'lr': 0.0004641903275198024, 'samples': 5285184, 'steps': 27526, 'loss/train': 1.359650731086731}
+08/30/2021 18:05:56 - INFO - __main__ - Step 27528: {'lr': 0.0004641875907136806, 'samples': 5285376, 'steps': 27527, 'loss/train': 2.0673930644989014}
+08/30/2021 18:05:56 - INFO - __main__ - Step 27529: {'lr': 0.0004641848538110492, 'samples': 5285568, 'steps': 27528, 'loss/train': 1.2977995872497559}
+08/30/2021 18:05:56 - INFO - __main__ - Step 27530: {'lr': 0.00046418211681190937, 'samples': 5285760, 'steps': 27529, 'loss/train': 0.6407142877578735}
+08/30/2021 18:05:57 - INFO - __main__ - Step 27531: {'lr': 0.00046417937971626245, 'samples': 5285952, 'steps': 27530, 'loss/train': 1.3707348108291626}
+08/30/2021 18:05:59 - INFO - __main__ - Step 27532: {'lr': 0.0004641766425241095, 'samples': 5286144, 'steps': 27531, 'loss/train': 1.8964557647705078}
+08/30/2021 18:05:59 - INFO - __main__ - Step 27533: {'lr': 0.000464173905235452, 'samples': 5286336, 'steps': 27532, 'loss/train': 1.7082087993621826}
+08/30/2021 18:06:00 - INFO - __main__ - Step 27534: {'lr': 0.0004641711678502909, 'samples': 5286528, 'steps': 27533, 'loss/train': 0.717869758605957}
+08/30/2021 18:06:00 - INFO - __main__ - Step 27535: {'lr': 0.00046416843036862766, 'samples': 5286720, 'steps': 27534, 'loss/train': 1.10735023021698}
+08/30/2021 18:06:00 - INFO - __main__ - Step 27536: {'lr': 0.0004641656927904634, 'samples': 5286912, 'steps': 27535, 'loss/train': 1.5429867506027222}
+08/30/2021 18:06:01 - INFO - __main__ - Step 27537: {'lr': 0.00046416295511579944, 'samples': 5287104, 'steps': 27536, 'loss/train': 1.511547565460205}
+08/30/2021 18:06:02 - INFO - __main__ - Step 27538: {'lr': 0.0004641602173446369, 'samples': 5287296, 'steps': 27537, 'loss/train': 1.8700331449508667}
+08/30/2021 18:06:03 - INFO - __main__ - Step 27539: {'lr': 0.00046415747947697704, 'samples': 5287488, 'steps': 27538, 'loss/train': 1.083155870437622}
+08/30/2021 18:06:03 - INFO - __main__ - Step 27540: {'lr': 0.00046415474151282124, 'samples': 5287680, 'steps': 27539, 'loss/train': 1.6107252836227417}
+08/30/2021 18:06:04 - INFO - __main__ - Step 27541: {'lr': 0.0004641520034521705, 'samples': 5287872, 'steps': 27540, 'loss/train': 1.9646943807601929}
+08/30/2021 18:06:04 - INFO - __main__ - Step 27542: {'lr': 0.0004641492652950262, 'samples': 5288064, 'steps': 27541, 'loss/train': 1.8504058122634888}
+08/30/2021 18:06:06 - INFO - __main__ - Step 27543: {'lr': 0.0004641465270413896, 'samples': 5288256, 'steps': 27542, 'loss/train': 1.7035349607467651}
+08/30/2021 18:06:06 - INFO - __main__ - Step 27544: {'lr': 0.00046414378869126185, 'samples': 5288448, 'steps': 27543, 'loss/train': 1.5890493392944336}
+08/30/2021 18:06:06 - INFO - __main__ - Step 27545: {'lr': 0.0004641410502446442, 'samples': 5288640, 'steps': 27544, 'loss/train': 1.467052698135376}
+08/30/2021 18:06:07 - INFO - __main__ - Step 27546: {'lr': 0.00046413831170153785, 'samples': 5288832, 'steps': 27545, 'loss/train': 1.6460683345794678}
+08/30/2021 18:06:07 - INFO - __main__ - Step 27547: {'lr': 0.0004641355730619442, 'samples': 5289024, 'steps': 27546, 'loss/train': 1.3892771005630493}
+08/30/2021 18:06:08 - INFO - __main__ - Step 27548: {'lr': 0.0004641328343258643, 'samples': 5289216, 'steps': 27547, 'loss/train': 1.299553632736206}
+08/30/2021 18:06:09 - INFO - __main__ - Step 27549: {'lr': 0.00046413009549329946, 'samples': 5289408, 'steps': 27548, 'loss/train': 1.835012435913086}
+08/30/2021 18:06:09 - INFO - __main__ - Step 27550: {'lr': 0.0004641273565642509, 'samples': 5289600, 'steps': 27549, 'loss/train': 1.6101205348968506}
+08/30/2021 18:06:10 - INFO - __main__ - Step 27551: {'lr': 0.0004641246175387198, 'samples': 5289792, 'steps': 27550, 'loss/train': 1.294134497642517}
+08/30/2021 18:06:10 - INFO - __main__ - Step 27552: {'lr': 0.0004641218784167075, 'samples': 5289984, 'steps': 27551, 'loss/train': 1.0548399686813354}
+08/30/2021 18:06:11 - INFO - __main__ - Step 27553: {'lr': 0.0004641191391982152, 'samples': 5290176, 'steps': 27552, 'loss/train': 0.045883212238550186}
+08/30/2021 18:06:12 - INFO - __main__ - Step 27554: {'lr': 0.00046411639988324407, 'samples': 5290368, 'steps': 27553, 'loss/train': 1.2484043836593628}
+08/30/2021 18:06:12 - INFO - __main__ - Step 27555: {'lr': 0.00046411366047179547, 'samples': 5290560, 'steps': 27554, 'loss/train': 1.6914410591125488}
+08/30/2021 18:06:13 - INFO - __main__ - Step 27556: {'lr': 0.00046411092096387054, 'samples': 5290752, 'steps': 27555, 'loss/train': 1.036177396774292}
+08/30/2021 18:06:13 - INFO - __main__ - Step 27557: {'lr': 0.0004641081813594705, 'samples': 5290944, 'steps': 27556, 'loss/train': 1.6183223724365234}
+08/30/2021 18:06:14 - INFO - __main__ - Step 27558: {'lr': 0.0004641054416585966, 'samples': 5291136, 'steps': 27557, 'loss/train': 1.4377225637435913}
+08/30/2021 18:06:15 - INFO - __main__ - Step 27559: {'lr': 0.00046410270186125014, 'samples': 5291328, 'steps': 27558, 'loss/train': 1.66042959690094}
+08/30/2021 18:06:15 - INFO - __main__ - Step 27560: {'lr': 0.0004640999619674323, 'samples': 5291520, 'steps': 27559, 'loss/train': 1.374444603919983}
+08/30/2021 18:06:16 - INFO - __main__ - Step 27561: {'lr': 0.0004640972219771443, 'samples': 5291712, 'steps': 27560, 'loss/train': 1.6468956470489502}
+08/30/2021 18:06:16 - INFO - __main__ - Step 27562: {'lr': 0.00046409448189038737, 'samples': 5291904, 'steps': 27561, 'loss/train': 0.9795956611633301}
+08/30/2021 18:06:16 - INFO - __main__ - Step 27563: {'lr': 0.00046409174170716284, 'samples': 5292096, 'steps': 27562, 'loss/train': 1.2625643014907837}
+08/30/2021 18:06:18 - INFO - __main__ - Step 27564: {'lr': 0.0004640890014274718, 'samples': 5292288, 'steps': 27563, 'loss/train': 1.4325306415557861}
+08/30/2021 18:06:18 - INFO - __main__ - Step 27565: {'lr': 0.0004640862610513156, 'samples': 5292480, 'steps': 27564, 'loss/train': 1.565487265586853}
+08/30/2021 18:06:19 - INFO - __main__ - Step 27566: {'lr': 0.00046408352057869545, 'samples': 5292672, 'steps': 27565, 'loss/train': 1.7046473026275635}
+08/30/2021 18:06:19 - INFO - __main__ - Step 27567: {'lr': 0.0004640807800096126, 'samples': 5292864, 'steps': 27566, 'loss/train': 1.3343174457550049}
+08/30/2021 18:06:19 - INFO - __main__ - Step 27568: {'lr': 0.0004640780393440682, 'samples': 5293056, 'steps': 27567, 'loss/train': 1.3126369714736938}
+08/30/2021 18:06:21 - INFO - __main__ - Step 27569: {'lr': 0.0004640752985820635, 'samples': 5293248, 'steps': 27568, 'loss/train': 1.5438686609268188}
+08/30/2021 18:06:21 - INFO - __main__ - Step 27570: {'lr': 0.0004640725577235998, 'samples': 5293440, 'steps': 27569, 'loss/train': 1.6290587186813354}
+08/30/2021 18:06:22 - INFO - __main__ - Step 27571: {'lr': 0.00046406981676867836, 'samples': 5293632, 'steps': 27570, 'loss/train': 1.1571675539016724}
+08/30/2021 18:06:22 - INFO - __main__ - Step 27572: {'lr': 0.00046406707571730035, 'samples': 5293824, 'steps': 27571, 'loss/train': 1.7105413675308228}
+08/30/2021 18:06:22 - INFO - __main__ - Step 27573: {'lr': 0.000464064334569467, 'samples': 5294016, 'steps': 27572, 'loss/train': 1.4792060852050781}
+08/30/2021 18:06:23 - INFO - __main__ - Step 27574: {'lr': 0.00046406159332517956, 'samples': 5294208, 'steps': 27573, 'loss/train': 1.5216033458709717}
+08/30/2021 18:06:24 - INFO - __main__ - Step 27575: {'lr': 0.00046405885198443926, 'samples': 5294400, 'steps': 27574, 'loss/train': 1.0698562860488892}
+08/30/2021 18:06:25 - INFO - __main__ - Step 27576: {'lr': 0.00046405611054724737, 'samples': 5294592, 'steps': 27575, 'loss/train': 0.6250839829444885}
+08/30/2021 18:06:25 - INFO - __main__ - Step 27577: {'lr': 0.00046405336901360507, 'samples': 5294784, 'steps': 27576, 'loss/train': 1.4426932334899902}
+08/30/2021 18:06:26 - INFO - __main__ - Step 27578: {'lr': 0.00046405062738351366, 'samples': 5294976, 'steps': 27577, 'loss/train': 1.29835844039917}
+08/30/2021 18:06:26 - INFO - __main__ - Step 27579: {'lr': 0.00046404788565697434, 'samples': 5295168, 'steps': 27578, 'loss/train': 1.392787218093872}
+08/30/2021 18:06:29 - INFO - __main__ - Step 27580: {'lr': 0.00046404514383398835, 'samples': 5295360, 'steps': 27579, 'loss/train': 1.0488930940628052}
+08/30/2021 18:06:29 - INFO - __main__ - Step 27581: {'lr': 0.0004640424019145568, 'samples': 5295552, 'steps': 27580, 'loss/train': 1.4656857252120972}
+08/30/2021 18:06:29 - INFO - __main__ - Step 27582: {'lr': 0.00046403965989868124, 'samples': 5295744, 'steps': 27581, 'loss/train': 1.8126304149627686}
+08/30/2021 18:06:30 - INFO - __main__ - Step 27583: {'lr': 0.0004640369177863626, 'samples': 5295936, 'steps': 27582, 'loss/train': 7.011992454528809}
+08/30/2021 18:06:30 - INFO - __main__ - Step 27584: {'lr': 0.00046403417557760226, 'samples': 5296128, 'steps': 27583, 'loss/train': 6.432428359985352}
+08/30/2021 18:06:30 - INFO - __main__ - Step 27585: {'lr': 0.00046403143327240136, 'samples': 5296320, 'steps': 27584, 'loss/train': 1.8334565162658691}
+08/30/2021 18:06:32 - INFO - __main__ - Step 27586: {'lr': 0.00046402869087076127, 'samples': 5296512, 'steps': 27585, 'loss/train': 1.7581672668457031}
+08/30/2021 18:06:32 - INFO - __main__ - Step 27587: {'lr': 0.00046402594837268314, 'samples': 5296704, 'steps': 27586, 'loss/train': 1.6860690116882324}
+08/30/2021 18:06:33 - INFO - __main__ - Step 27588: {'lr': 0.0004640232057781682, 'samples': 5296896, 'steps': 27587, 'loss/train': 1.6744991540908813}
+08/30/2021 18:06:33 - INFO - __main__ - Step 27589: {'lr': 0.00046402046308721776, 'samples': 5297088, 'steps': 27588, 'loss/train': 1.4241410493850708}
+08/30/2021 18:06:33 - INFO - __main__ - Step 27590: {'lr': 0.0004640177202998329, 'samples': 5297280, 'steps': 27589, 'loss/train': 1.7457475662231445}
+08/30/2021 18:06:35 - INFO - __main__ - Step 27591: {'lr': 0.00046401497741601505, 'samples': 5297472, 'steps': 27590, 'loss/train': 1.491798996925354}
+08/30/2021 18:06:35 - INFO - __main__ - Step 27592: {'lr': 0.00046401223443576537, 'samples': 5297664, 'steps': 27591, 'loss/train': 1.9089938402175903}
+08/30/2021 18:06:36 - INFO - __main__ - Step 27593: {'lr': 0.00046400949135908497, 'samples': 5297856, 'steps': 27592, 'loss/train': 1.1968921422958374}
+08/30/2021 18:06:36 - INFO - __main__ - Step 27594: {'lr': 0.0004640067481859753, 'samples': 5298048, 'steps': 27593, 'loss/train': 1.713312029838562}
+08/30/2021 18:06:36 - INFO - __main__ - Step 27595: {'lr': 0.00046400400491643744, 'samples': 5298240, 'steps': 27594, 'loss/train': 1.557417392730713}
+08/30/2021 18:06:38 - INFO - __main__ - Step 27596: {'lr': 0.00046400126155047265, 'samples': 5298432, 'steps': 27595, 'loss/train': 1.3746501207351685}
+08/30/2021 18:06:38 - INFO - __main__ - Step 27597: {'lr': 0.0004639985180880822, 'samples': 5298624, 'steps': 27596, 'loss/train': 1.3247319459915161}
+08/30/2021 18:06:39 - INFO - __main__ - Step 27598: {'lr': 0.0004639957745292674, 'samples': 5298816, 'steps': 27597, 'loss/train': 2.03164005279541}
+08/30/2021 18:06:39 - INFO - __main__ - Step 27599: {'lr': 0.00046399303087402935, 'samples': 5299008, 'steps': 27598, 'loss/train': 2.0356204509735107}
+08/30/2021 18:06:39 - INFO - __main__ - Step 27600: {'lr': 0.00046399028712236935, 'samples': 5299200, 'steps': 27599, 'loss/train': 1.4001091718673706}
+08/30/2021 18:06:40 - INFO - __main__ - Step 27601: {'lr': 0.0004639875432742886, 'samples': 5299392, 'steps': 27600, 'loss/train': 1.5931395292282104}
+08/30/2021 18:06:41 - INFO - __main__ - Step 27602: {'lr': 0.0004639847993297884, 'samples': 5299584, 'steps': 27601, 'loss/train': 1.3520549535751343}
+08/30/2021 18:06:42 - INFO - __main__ - Step 27603: {'lr': 0.00046398205528886994, 'samples': 5299776, 'steps': 27602, 'loss/train': 1.39707350730896}
+08/30/2021 18:06:42 - INFO - __main__ - Step 27604: {'lr': 0.00046397931115153444, 'samples': 5299968, 'steps': 27603, 'loss/train': 1.2671536207199097}
+08/30/2021 18:06:42 - INFO - __main__ - Step 27605: {'lr': 0.0004639765669177833, 'samples': 5300160, 'steps': 27604, 'loss/train': 1.5328627824783325}
+08/30/2021 18:06:43 - INFO - __main__ - Step 27606: {'lr': 0.00046397382258761744, 'samples': 5300352, 'steps': 27605, 'loss/train': 1.51702082157135}
+08/30/2021 18:06:44 - INFO - __main__ - Step 27607: {'lr': 0.0004639710781610384, 'samples': 5300544, 'steps': 27606, 'loss/train': 1.5836141109466553}
+08/30/2021 18:06:45 - INFO - __main__ - Step 27608: {'lr': 0.00046396833363804724, 'samples': 5300736, 'steps': 27607, 'loss/train': 1.9068845510482788}
+08/30/2021 18:06:45 - INFO - __main__ - Step 27609: {'lr': 0.00046396558901864527, 'samples': 5300928, 'steps': 27608, 'loss/train': 1.3824971914291382}
+08/30/2021 18:06:45 - INFO - __main__ - Step 27610: {'lr': 0.0004639628443028337, 'samples': 5301120, 'steps': 27609, 'loss/train': 1.9928569793701172}
+08/30/2021 18:06:46 - INFO - __main__ - Step 27611: {'lr': 0.0004639600994906138, 'samples': 5301312, 'steps': 27610, 'loss/train': 1.3614623546600342}
+08/30/2021 18:06:47 - INFO - __main__ - Step 27612: {'lr': 0.00046395735458198674, 'samples': 5301504, 'steps': 27611, 'loss/train': 1.3806707859039307}
+08/30/2021 18:06:48 - INFO - __main__ - Step 27613: {'lr': 0.0004639546095769538, 'samples': 5301696, 'steps': 27612, 'loss/train': 1.3501548767089844}
+08/30/2021 18:06:48 - INFO - __main__ - Step 27614: {'lr': 0.00046395186447551617, 'samples': 5301888, 'steps': 27613, 'loss/train': 1.0119539499282837}
+08/30/2021 18:06:48 - INFO - __main__ - Step 27615: {'lr': 0.00046394911927767526, 'samples': 5302080, 'steps': 27614, 'loss/train': 1.538619875907898}
+08/30/2021 18:06:49 - INFO - __main__ - Step 27616: {'lr': 0.0004639463739834321, 'samples': 5302272, 'steps': 27615, 'loss/train': 1.4405438899993896}
+08/30/2021 18:06:50 - INFO - __main__ - Step 27617: {'lr': 0.00046394362859278793, 'samples': 5302464, 'steps': 27616, 'loss/train': 1.3817137479782104}
+08/30/2021 18:06:51 - INFO - __main__ - Step 27618: {'lr': 0.00046394088310574416, 'samples': 5302656, 'steps': 27617, 'loss/train': 1.5324381589889526}
+08/30/2021 18:06:51 - INFO - __main__ - Step 27619: {'lr': 0.000463938137522302, 'samples': 5302848, 'steps': 27618, 'loss/train': 0.08424973487854004}
+08/30/2021 18:06:52 - INFO - __main__ - Step 27620: {'lr': 0.00046393539184246246, 'samples': 5303040, 'steps': 27619, 'loss/train': 2.311727523803711}
+08/30/2021 18:06:52 - INFO - __main__ - Step 27621: {'lr': 0.000463932646066227, 'samples': 5303232, 'steps': 27620, 'loss/train': 1.9144822359085083}
+08/30/2021 18:06:54 - INFO - __main__ - Step 27622: {'lr': 0.0004639299001935968, 'samples': 5303424, 'steps': 27621, 'loss/train': 2.442072629928589}
+08/30/2021 18:06:54 - INFO - __main__ - Step 27623: {'lr': 0.0004639271542245731, 'samples': 5303616, 'steps': 27622, 'loss/train': 1.1727242469787598}
+08/30/2021 18:06:55 - INFO - __main__ - Step 27624: {'lr': 0.000463924408159157, 'samples': 5303808, 'steps': 27623, 'loss/train': 1.5860928297042847}
+08/30/2021 18:06:55 - INFO - __main__ - Step 27625: {'lr': 0.00046392166199735, 'samples': 5304000, 'steps': 27624, 'loss/train': 4.4631733894348145}
+08/30/2021 18:06:55 - INFO - __main__ - Step 27626: {'lr': 0.00046391891573915325, 'samples': 5304192, 'steps': 27625, 'loss/train': 1.963142991065979}
+08/30/2021 18:06:56 - INFO - __main__ - Step 27627: {'lr': 0.0004639161693845678, 'samples': 5304384, 'steps': 27626, 'loss/train': 1.4789601564407349}
+08/30/2021 18:06:58 - INFO - __main__ - Step 27628: {'lr': 0.0004639134229335951, 'samples': 5304576, 'steps': 27627, 'loss/train': 1.5334399938583374}
+08/30/2021 18:06:58 - INFO - __main__ - Step 27629: {'lr': 0.0004639106763862363, 'samples': 5304768, 'steps': 27628, 'loss/train': 2.497802495956421}
+08/30/2021 18:06:59 - INFO - __main__ - Step 27630: {'lr': 0.00046390792974249263, 'samples': 5304960, 'steps': 27629, 'loss/train': 1.5521652698516846}
+08/30/2021 18:06:59 - INFO - __main__ - Step 27631: {'lr': 0.00046390518300236535, 'samples': 5305152, 'steps': 27630, 'loss/train': 0.13609883189201355}
+08/30/2021 18:07:00 - INFO - __main__ - Step 27632: {'lr': 0.0004639024361658557, 'samples': 5305344, 'steps': 27631, 'loss/train': 1.7635130882263184}
+08/30/2021 18:07:00 - INFO - __main__ - Step 27633: {'lr': 0.00046389968923296496, 'samples': 5305536, 'steps': 27632, 'loss/train': 0.6495070457458496}
+08/30/2021 18:07:00 - INFO - __main__ - Step 27634: {'lr': 0.0004638969422036943, 'samples': 5305728, 'steps': 27633, 'loss/train': 0.4948667287826538}
+08/30/2021 18:07:02 - INFO - __main__ - Step 27635: {'lr': 0.00046389419507804493, 'samples': 5305920, 'steps': 27634, 'loss/train': 0.7599722146987915}
+08/30/2021 18:07:03 - INFO - __main__ - Step 27636: {'lr': 0.00046389144785601813, 'samples': 5306112, 'steps': 27635, 'loss/train': 1.4174884557724}
+08/30/2021 18:07:03 - INFO - __main__ - Step 27637: {'lr': 0.0004638887005376152, 'samples': 5306304, 'steps': 27636, 'loss/train': 1.350616693496704}
+08/30/2021 18:07:03 - INFO - __main__ - Step 27638: {'lr': 0.0004638859531228373, 'samples': 5306496, 'steps': 27637, 'loss/train': 1.6200162172317505}
+08/30/2021 18:07:04 - INFO - __main__ - Step 27639: {'lr': 0.00046388320561168567, 'samples': 5306688, 'steps': 27638, 'loss/train': 1.3006216287612915}
+08/30/2021 18:07:05 - INFO - __main__ - Step 27640: {'lr': 0.00046388045800416157, 'samples': 5306880, 'steps': 27639, 'loss/train': 1.7380802631378174}
+08/30/2021 18:07:06 - INFO - __main__ - Step 27641: {'lr': 0.00046387771030026627, 'samples': 5307072, 'steps': 27640, 'loss/train': 1.850737452507019}
+08/30/2021 18:07:06 - INFO - __main__ - Step 27642: {'lr': 0.00046387496250000095, 'samples': 5307264, 'steps': 27641, 'loss/train': 1.9918535947799683}
+08/30/2021 18:07:06 - INFO - __main__ - Step 27643: {'lr': 0.0004638722146033669, 'samples': 5307456, 'steps': 27642, 'loss/train': 1.4941896200180054}
+08/30/2021 18:07:07 - INFO - __main__ - Step 27644: {'lr': 0.0004638694666103653, 'samples': 5307648, 'steps': 27643, 'loss/train': 2.074228525161743}
+08/30/2021 18:07:08 - INFO - __main__ - Step 27645: {'lr': 0.00046386671852099743, 'samples': 5307840, 'steps': 27644, 'loss/train': 1.5714284181594849}
+08/30/2021 18:07:09 - INFO - __main__ - Step 27646: {'lr': 0.0004638639703352645, 'samples': 5308032, 'steps': 27645, 'loss/train': 1.7330057621002197}
+08/30/2021 18:07:09 - INFO - __main__ - Step 27647: {'lr': 0.00046386122205316783, 'samples': 5308224, 'steps': 27646, 'loss/train': 1.4205405712127686}
+08/30/2021 18:07:09 - INFO - __main__ - Step 27648: {'lr': 0.0004638584736747085, 'samples': 5308416, 'steps': 27647, 'loss/train': 1.7681492567062378}
+08/30/2021 18:07:10 - INFO - __main__ - Step 27649: {'lr': 0.00046385572519988793, 'samples': 5308608, 'steps': 27648, 'loss/train': 1.0372158288955688}
+08/30/2021 18:07:11 - INFO - __main__ - Step 27650: {'lr': 0.00046385297662870716, 'samples': 5308800, 'steps': 27649, 'loss/train': 1.9399640560150146}
+08/30/2021 18:07:12 - INFO - __main__ - Step 27651: {'lr': 0.00046385022796116766, 'samples': 5308992, 'steps': 27650, 'loss/train': 1.3714888095855713}
+08/30/2021 18:07:12 - INFO - __main__ - Step 27652: {'lr': 0.0004638474791972705, 'samples': 5309184, 'steps': 27651, 'loss/train': 1.6928040981292725}
+08/30/2021 18:07:12 - INFO - __main__ - Step 27653: {'lr': 0.000463844730337017, 'samples': 5309376, 'steps': 27652, 'loss/train': 0.8629988431930542}
+08/30/2021 18:07:13 - INFO - __main__ - Step 27654: {'lr': 0.00046384198138040825, 'samples': 5309568, 'steps': 27653, 'loss/train': 1.1709786653518677}
+08/30/2021 18:07:14 - INFO - __main__ - Step 27655: {'lr': 0.00046383923232744565, 'samples': 5309760, 'steps': 27654, 'loss/train': 1.6784054040908813}
+08/30/2021 18:07:15 - INFO - __main__ - Step 27656: {'lr': 0.00046383648317813045, 'samples': 5309952, 'steps': 27655, 'loss/train': 1.5674488544464111}
+08/30/2021 18:07:15 - INFO - __main__ - Step 27657: {'lr': 0.0004638337339324638, 'samples': 5310144, 'steps': 27656, 'loss/train': 0.7143456935882568}
+08/30/2021 18:07:16 - INFO - __main__ - Step 27658: {'lr': 0.00046383098459044697, 'samples': 5310336, 'steps': 27657, 'loss/train': 1.4924540519714355}
+08/30/2021 18:07:16 - INFO - __main__ - Step 27659: {'lr': 0.0004638282351520812, 'samples': 5310528, 'steps': 27658, 'loss/train': 1.1130164861679077}
+08/30/2021 18:07:18 - INFO - __main__ - Step 27660: {'lr': 0.00046382548561736773, 'samples': 5310720, 'steps': 27659, 'loss/train': 1.682997226715088}
+08/30/2021 18:07:18 - INFO - __main__ - Step 27661: {'lr': 0.0004638227359863078, 'samples': 5310912, 'steps': 27660, 'loss/train': 1.1483876705169678}
+08/30/2021 18:07:18 - INFO - __main__ - Step 27662: {'lr': 0.0004638199862589026, 'samples': 5311104, 'steps': 27661, 'loss/train': 1.8646984100341797}
+08/30/2021 18:07:19 - INFO - __main__ - Step 27663: {'lr': 0.0004638172364351535, 'samples': 5311296, 'steps': 27662, 'loss/train': 1.0410184860229492}
+08/30/2021 18:07:19 - INFO - __main__ - Step 27664: {'lr': 0.00046381448651506153, 'samples': 5311488, 'steps': 27663, 'loss/train': 1.3917937278747559}
+08/30/2021 18:07:21 - INFO - __main__ - Step 27665: {'lr': 0.00046381173649862815, 'samples': 5311680, 'steps': 27664, 'loss/train': 1.5901403427124023}
+08/30/2021 18:07:21 - INFO - __main__ - Step 27666: {'lr': 0.00046380898638585447, 'samples': 5311872, 'steps': 27665, 'loss/train': 1.7387356758117676}
+08/30/2021 18:07:22 - INFO - __main__ - Step 27667: {'lr': 0.0004638062361767418, 'samples': 5312064, 'steps': 27666, 'loss/train': 0.9809238314628601}
+08/30/2021 18:07:22 - INFO - __main__ - Step 27668: {'lr': 0.00046380348587129127, 'samples': 5312256, 'steps': 27667, 'loss/train': 1.879568099975586}
+08/30/2021 18:07:22 - INFO - __main__ - Step 27669: {'lr': 0.0004638007354695042, 'samples': 5312448, 'steps': 27668, 'loss/train': 2.2002036571502686}
+08/30/2021 18:07:23 - INFO - __main__ - Step 27670: {'lr': 0.0004637979849713818, 'samples': 5312640, 'steps': 27669, 'loss/train': 1.5881483554840088}
+08/30/2021 18:07:25 - INFO - __main__ - Step 27671: {'lr': 0.0004637952343769254, 'samples': 5312832, 'steps': 27670, 'loss/train': 1.7404872179031372}
+08/30/2021 18:07:25 - INFO - __main__ - Step 27672: {'lr': 0.00046379248368613615, 'samples': 5313024, 'steps': 27671, 'loss/train': 1.6770353317260742}
+08/30/2021 18:07:25 - INFO - __main__ - Step 27673: {'lr': 0.0004637897328990153, 'samples': 5313216, 'steps': 27672, 'loss/train': 1.2560689449310303}
+08/30/2021 18:07:26 - INFO - __main__ - Step 27674: {'lr': 0.000463786982015564, 'samples': 5313408, 'steps': 27673, 'loss/train': 1.4442033767700195}
+08/30/2021 18:07:26 - INFO - __main__ - Step 27675: {'lr': 0.00046378423103578373, 'samples': 5313600, 'steps': 27674, 'loss/train': 1.6111303567886353}
+08/30/2021 18:07:28 - INFO - __main__ - Step 27676: {'lr': 0.0004637814799596755, 'samples': 5313792, 'steps': 27675, 'loss/train': 0.23090513050556183}
+08/30/2021 18:07:28 - INFO - __main__ - Step 27677: {'lr': 0.00046377872878724066, 'samples': 5313984, 'steps': 27676, 'loss/train': 1.3465864658355713}
+08/30/2021 18:07:29 - INFO - __main__ - Step 27678: {'lr': 0.0004637759775184804, 'samples': 5314176, 'steps': 27677, 'loss/train': 0.9396185278892517}
+08/30/2021 18:07:29 - INFO - __main__ - Step 27679: {'lr': 0.000463773226153396, 'samples': 5314368, 'steps': 27678, 'loss/train': 1.0420961380004883}
+08/30/2021 18:07:29 - INFO - __main__ - Step 27680: {'lr': 0.00046377047469198875, 'samples': 5314560, 'steps': 27679, 'loss/train': 0.2202690839767456}
+08/30/2021 18:07:30 - INFO - __main__ - Step 27681: {'lr': 0.00046376772313425974, 'samples': 5314752, 'steps': 27680, 'loss/train': 1.2297792434692383}
+08/30/2021 18:07:31 - INFO - __main__ - Step 27682: {'lr': 0.0004637649714802102, 'samples': 5314944, 'steps': 27681, 'loss/train': 1.2670255899429321}
+08/30/2021 18:07:32 - INFO - __main__ - Step 27683: {'lr': 0.0004637622197298417, 'samples': 5315136, 'steps': 27682, 'loss/train': 1.1371203660964966}
+08/30/2021 18:07:32 - INFO - __main__ - Step 27684: {'lr': 0.000463759467883155, 'samples': 5315328, 'steps': 27683, 'loss/train': 1.7195202112197876}
+08/30/2021 18:07:32 - INFO - __main__ - Step 27685: {'lr': 0.0004637567159401518, 'samples': 5315520, 'steps': 27684, 'loss/train': 2.2589163780212402}
+08/30/2021 18:07:33 - INFO - __main__ - Step 27686: {'lr': 0.00046375396390083303, 'samples': 5315712, 'steps': 27685, 'loss/train': 1.4878872632980347}
+08/30/2021 18:07:35 - INFO - __main__ - Step 27687: {'lr': 0.0004637512117652, 'samples': 5315904, 'steps': 27686, 'loss/train': 0.6817157864570618}
+08/30/2021 18:07:35 - INFO - __main__ - Step 27688: {'lr': 0.00046374845953325394, 'samples': 5316096, 'steps': 27687, 'loss/train': 1.3332120180130005}
+08/30/2021 18:07:36 - INFO - __main__ - Step 27689: {'lr': 0.0004637457072049962, 'samples': 5316288, 'steps': 27688, 'loss/train': 1.6221702098846436}
+08/30/2021 18:07:36 - INFO - __main__ - Step 27690: {'lr': 0.0004637429547804279, 'samples': 5316480, 'steps': 27689, 'loss/train': 0.9120870232582092}
+08/30/2021 18:07:36 - INFO - __main__ - Step 27691: {'lr': 0.0004637402022595503, 'samples': 5316672, 'steps': 27690, 'loss/train': 3.143947124481201}
+08/30/2021 18:07:38 - INFO - __main__ - Step 27692: {'lr': 0.0004637374496423647, 'samples': 5316864, 'steps': 27691, 'loss/train': 1.8292323350906372}
+08/30/2021 18:07:39 - INFO - __main__ - Step 27693: {'lr': 0.0004637346969288723, 'samples': 5317056, 'steps': 27692, 'loss/train': 1.2111611366271973}
+08/30/2021 18:07:39 - INFO - __main__ - Step 27694: {'lr': 0.0004637319441190743, 'samples': 5317248, 'steps': 27693, 'loss/train': 1.5030843019485474}
+08/30/2021 18:07:39 - INFO - __main__ - Step 27695: {'lr': 0.00046372919121297207, 'samples': 5317440, 'steps': 27694, 'loss/train': 1.5317778587341309}
+08/30/2021 18:07:40 - INFO - __main__ - Step 27696: {'lr': 0.0004637264382105667, 'samples': 5317632, 'steps': 27695, 'loss/train': 6.138783931732178}
+08/30/2021 18:07:40 - INFO - __main__ - Step 27697: {'lr': 0.00046372368511185953, 'samples': 5317824, 'steps': 27696, 'loss/train': 1.5839647054672241}
+08/30/2021 18:07:41 - INFO - __main__ - Step 27698: {'lr': 0.0004637209319168517, 'samples': 5318016, 'steps': 27697, 'loss/train': 1.3210899829864502}
+08/30/2021 18:07:42 - INFO - __main__ - Step 27699: {'lr': 0.0004637181786255446, 'samples': 5318208, 'steps': 27698, 'loss/train': 1.011793613433838}
+08/30/2021 18:07:42 - INFO - __main__ - Step 27700: {'lr': 0.0004637154252379394, 'samples': 5318400, 'steps': 27699, 'loss/train': 1.6124320030212402}
+08/30/2021 18:07:42 - INFO - __main__ - Step 27701: {'lr': 0.00046371267175403724, 'samples': 5318592, 'steps': 27700, 'loss/train': 1.9815433025360107}
+08/30/2021 18:07:43 - INFO - __main__ - Step 27702: {'lr': 0.0004637099181738395, 'samples': 5318784, 'steps': 27701, 'loss/train': 1.3882966041564941}
+08/30/2021 18:07:44 - INFO - __main__ - Step 27703: {'lr': 0.00046370716449734733, 'samples': 5318976, 'steps': 27702, 'loss/train': 1.6488699913024902}
+08/30/2021 18:07:45 - INFO - __main__ - Step 27704: {'lr': 0.00046370441072456206, 'samples': 5319168, 'steps': 27703, 'loss/train': 1.132298231124878}
+08/30/2021 18:07:45 - INFO - __main__ - Step 27705: {'lr': 0.00046370165685548484, 'samples': 5319360, 'steps': 27704, 'loss/train': 1.264633297920227}
+08/30/2021 18:07:45 - INFO - __main__ - Step 27706: {'lr': 0.00046369890289011696, 'samples': 5319552, 'steps': 27705, 'loss/train': 1.7231214046478271}
+08/30/2021 18:07:46 - INFO - __main__ - Step 27707: {'lr': 0.0004636961488284597, 'samples': 5319744, 'steps': 27706, 'loss/train': 1.0639294385910034}
+08/30/2021 18:07:47 - INFO - __main__ - Step 27708: {'lr': 0.0004636933946705142, 'samples': 5319936, 'steps': 27707, 'loss/train': 1.6238598823547363}
+08/30/2021 18:07:48 - INFO - __main__ - Step 27709: {'lr': 0.00046369064041628175, 'samples': 5320128, 'steps': 27708, 'loss/train': 1.059350609779358}
+08/30/2021 18:07:48 - INFO - __main__ - Step 27710: {'lr': 0.00046368788606576363, 'samples': 5320320, 'steps': 27709, 'loss/train': 0.749843418598175}
+08/30/2021 18:07:48 - INFO - __main__ - Step 27711: {'lr': 0.00046368513161896104, 'samples': 5320512, 'steps': 27710, 'loss/train': 0.402189701795578}
+08/30/2021 18:07:49 - INFO - __main__ - Step 27712: {'lr': 0.0004636823770758752, 'samples': 5320704, 'steps': 27711, 'loss/train': 2.0030534267425537}
+08/30/2021 18:07:49 - INFO - __main__ - Step 27713: {'lr': 0.0004636796224365074, 'samples': 5320896, 'steps': 27712, 'loss/train': 0.44293150305747986}
+08/30/2021 18:07:51 - INFO - __main__ - Step 27714: {'lr': 0.0004636768677008588, 'samples': 5321088, 'steps': 27713, 'loss/train': 1.1427805423736572}
+08/30/2021 18:07:51 - INFO - __main__ - Step 27715: {'lr': 0.0004636741128689308, 'samples': 5321280, 'steps': 27714, 'loss/train': 1.3262362480163574}
+08/30/2021 18:07:52 - INFO - __main__ - Step 27716: {'lr': 0.00046367135794072445, 'samples': 5321472, 'steps': 27715, 'loss/train': 1.7071841955184937}
+08/30/2021 18:07:52 - INFO - __main__ - Step 27717: {'lr': 0.0004636686029162411, 'samples': 5321664, 'steps': 27716, 'loss/train': 1.0002169609069824}
+08/30/2021 18:07:52 - INFO - __main__ - Step 27718: {'lr': 0.000463665847795482, 'samples': 5321856, 'steps': 27717, 'loss/train': 1.683854341506958}
+08/30/2021 18:07:54 - INFO - __main__ - Step 27719: {'lr': 0.0004636630925784484, 'samples': 5322048, 'steps': 27718, 'loss/train': 1.710624098777771}
+08/30/2021 18:07:54 - INFO - __main__ - Step 27720: {'lr': 0.0004636603372651415, 'samples': 5322240, 'steps': 27719, 'loss/train': 1.7615082263946533}
+08/30/2021 18:07:54 - INFO - __main__ - Step 27721: {'lr': 0.0004636575818555625, 'samples': 5322432, 'steps': 27720, 'loss/train': 1.3039824962615967}
+08/30/2021 18:07:55 - INFO - __main__ - Step 27722: {'lr': 0.00046365482634971275, 'samples': 5322624, 'steps': 27721, 'loss/train': 1.5380810499191284}
+08/30/2021 18:07:55 - INFO - __main__ - Step 27723: {'lr': 0.00046365207074759344, 'samples': 5322816, 'steps': 27722, 'loss/train': 1.315588355064392}
+08/30/2021 18:07:57 - INFO - __main__ - Step 27724: {'lr': 0.0004636493150492057, 'samples': 5323008, 'steps': 27723, 'loss/train': 1.7833211421966553}
+08/30/2021 18:07:57 - INFO - __main__ - Step 27725: {'lr': 0.00046364655925455094, 'samples': 5323200, 'steps': 27724, 'loss/train': 1.352582335472107}
+08/30/2021 18:07:57 - INFO - __main__ - Step 27726: {'lr': 0.0004636438033636303, 'samples': 5323392, 'steps': 27725, 'loss/train': 1.3288015127182007}
+08/30/2021 18:07:58 - INFO - __main__ - Step 27727: {'lr': 0.00046364104737644515, 'samples': 5323584, 'steps': 27726, 'loss/train': 1.1080595254898071}
+08/30/2021 18:07:58 - INFO - __main__ - Step 27728: {'lr': 0.00046363829129299655, 'samples': 5323776, 'steps': 27727, 'loss/train': 1.3275203704833984}
+08/30/2021 18:08:00 - INFO - __main__ - Step 27729: {'lr': 0.0004636355351132859, 'samples': 5323968, 'steps': 27728, 'loss/train': 1.7928476333618164}
+08/30/2021 18:08:00 - INFO - __main__ - Step 27730: {'lr': 0.00046363277883731437, 'samples': 5324160, 'steps': 27729, 'loss/train': 1.2326266765594482}
+08/30/2021 18:08:01 - INFO - __main__ - Step 27731: {'lr': 0.0004636300224650831, 'samples': 5324352, 'steps': 27730, 'loss/train': 1.0478222370147705}
+08/30/2021 18:08:01 - INFO - __main__ - Step 27732: {'lr': 0.00046362726599659355, 'samples': 5324544, 'steps': 27731, 'loss/train': 1.4498744010925293}
+08/30/2021 18:08:01 - INFO - __main__ - Step 27733: {'lr': 0.0004636245094318468, 'samples': 5324736, 'steps': 27732, 'loss/train': 1.5391539335250854}
+08/30/2021 18:08:03 - INFO - __main__ - Step 27734: {'lr': 0.0004636217527708442, 'samples': 5324928, 'steps': 27733, 'loss/train': 1.9058687686920166}
+08/30/2021 18:08:03 - INFO - __main__ - Step 27735: {'lr': 0.0004636189960135869, 'samples': 5325120, 'steps': 27734, 'loss/train': 1.4752416610717773}
+08/30/2021 18:08:04 - INFO - __main__ - Step 27736: {'lr': 0.0004636162391600761, 'samples': 5325312, 'steps': 27735, 'loss/train': 1.8577532768249512}
+08/30/2021 18:08:04 - INFO - __main__ - Step 27737: {'lr': 0.00046361348221031316, 'samples': 5325504, 'steps': 27736, 'loss/train': 1.8980063199996948}
+08/30/2021 18:08:04 - INFO - __main__ - Step 27738: {'lr': 0.00046361072516429936, 'samples': 5325696, 'steps': 27737, 'loss/train': 1.3145451545715332}
+08/30/2021 18:08:06 - INFO - __main__ - Step 27739: {'lr': 0.0004636079680220358, 'samples': 5325888, 'steps': 27738, 'loss/train': 4.672932147979736}
+08/30/2021 18:08:06 - INFO - __main__ - Step 27740: {'lr': 0.0004636052107835238, 'samples': 5326080, 'steps': 27739, 'loss/train': 1.2719616889953613}
+08/30/2021 18:08:07 - INFO - __main__ - Step 27741: {'lr': 0.0004636024534487646, 'samples': 5326272, 'steps': 27740, 'loss/train': 1.4490892887115479}
+08/30/2021 18:08:07 - INFO - __main__ - Step 27742: {'lr': 0.0004635996960177594, 'samples': 5326464, 'steps': 27741, 'loss/train': 0.4310019612312317}
+08/30/2021 18:08:07 - INFO - __main__ - Step 27743: {'lr': 0.0004635969384905095, 'samples': 5326656, 'steps': 27742, 'loss/train': 1.8816343545913696}
+08/30/2021 18:08:10 - INFO - __main__ - Step 27744: {'lr': 0.0004635941808670161, 'samples': 5326848, 'steps': 27743, 'loss/train': 1.5247331857681274}
+08/30/2021 18:08:10 - INFO - __main__ - Step 27745: {'lr': 0.00046359142314728047, 'samples': 5327040, 'steps': 27744, 'loss/train': 1.325038194656372}
+08/30/2021 18:08:10 - INFO - __main__ - Step 27746: {'lr': 0.00046358866533130385, 'samples': 5327232, 'steps': 27745, 'loss/train': 1.7034525871276855}
+08/30/2021 18:08:11 - INFO - __main__ - Step 27747: {'lr': 0.00046358590741908744, 'samples': 5327424, 'steps': 27746, 'loss/train': 0.06704515218734741}
+08/30/2021 18:08:11 - INFO - __main__ - Step 27748: {'lr': 0.0004635831494106325, 'samples': 5327616, 'steps': 27747, 'loss/train': 1.8906948566436768}
+08/30/2021 18:08:11 - INFO - __main__ - Step 27749: {'lr': 0.0004635803913059404, 'samples': 5327808, 'steps': 27748, 'loss/train': 1.3078497648239136}
+08/30/2021 18:08:13 - INFO - __main__ - Step 27750: {'lr': 0.00046357763310501216, 'samples': 5328000, 'steps': 27749, 'loss/train': 0.392612099647522}
+08/30/2021 18:08:13 - INFO - __main__ - Step 27751: {'lr': 0.0004635748748078492, 'samples': 5328192, 'steps': 27750, 'loss/train': 1.9263042211532593}
+08/30/2021 18:08:14 - INFO - __main__ - Step 27752: {'lr': 0.0004635721164144526, 'samples': 5328384, 'steps': 27751, 'loss/train': 1.4707145690917969}
+08/30/2021 18:08:14 - INFO - __main__ - Step 27753: {'lr': 0.0004635693579248238, 'samples': 5328576, 'steps': 27752, 'loss/train': 1.5500909090042114}
+08/30/2021 18:08:14 - INFO - __main__ - Step 27754: {'lr': 0.00046356659933896393, 'samples': 5328768, 'steps': 27753, 'loss/train': 1.6524235010147095}
+08/30/2021 18:08:16 - INFO - __main__ - Step 27755: {'lr': 0.0004635638406568742, 'samples': 5328960, 'steps': 27754, 'loss/train': 1.7313227653503418}
+08/30/2021 18:08:16 - INFO - __main__ - Step 27756: {'lr': 0.00046356108187855594, 'samples': 5329152, 'steps': 27755, 'loss/train': 1.8637701272964478}
+08/30/2021 18:08:17 - INFO - __main__ - Step 27757: {'lr': 0.00046355832300401035, 'samples': 5329344, 'steps': 27756, 'loss/train': 2.080235481262207}
+08/30/2021 18:08:17 - INFO - __main__ - Step 27758: {'lr': 0.0004635555640332386, 'samples': 5329536, 'steps': 27757, 'loss/train': 0.8100613951683044}
+08/30/2021 18:08:17 - INFO - __main__ - Step 27759: {'lr': 0.0004635528049662421, 'samples': 5329728, 'steps': 27758, 'loss/train': 1.736909031867981}
+08/30/2021 18:08:19 - INFO - __main__ - Step 27760: {'lr': 0.000463550045803022, 'samples': 5329920, 'steps': 27759, 'loss/train': 1.4985519647598267}
+08/30/2021 18:08:19 - INFO - __main__ - Step 27761: {'lr': 0.00046354728654357947, 'samples': 5330112, 'steps': 27760, 'loss/train': 1.5650149583816528}
+08/30/2021 18:08:20 - INFO - __main__ - Step 27762: {'lr': 0.00046354452718791586, 'samples': 5330304, 'steps': 27761, 'loss/train': 1.3432813882827759}
+08/30/2021 18:08:20 - INFO - __main__ - Step 27763: {'lr': 0.0004635417677360324, 'samples': 5330496, 'steps': 27762, 'loss/train': 1.792452096939087}
+08/30/2021 18:08:21 - INFO - __main__ - Step 27764: {'lr': 0.0004635390081879303, 'samples': 5330688, 'steps': 27763, 'loss/train': 1.4342265129089355}
+08/30/2021 18:08:22 - INFO - __main__ - Step 27765: {'lr': 0.0004635362485436109, 'samples': 5330880, 'steps': 27764, 'loss/train': 1.653233289718628}
+08/30/2021 18:08:22 - INFO - __main__ - Step 27766: {'lr': 0.00046353348880307524, 'samples': 5331072, 'steps': 27765, 'loss/train': 0.8268206715583801}
+08/30/2021 18:08:23 - INFO - __main__ - Step 27767: {'lr': 0.0004635307289663248, 'samples': 5331264, 'steps': 27766, 'loss/train': 1.4286202192306519}
+08/30/2021 18:08:23 - INFO - __main__ - Step 27768: {'lr': 0.0004635279690333606, 'samples': 5331456, 'steps': 27767, 'loss/train': 1.7019968032836914}
+08/30/2021 18:08:23 - INFO - __main__ - Step 27769: {'lr': 0.00046352520900418403, 'samples': 5331648, 'steps': 27768, 'loss/train': 1.6425319910049438}
+08/30/2021 18:08:24 - INFO - __main__ - Step 27770: {'lr': 0.00046352244887879623, 'samples': 5331840, 'steps': 27769, 'loss/train': 1.5490469932556152}
+08/30/2021 18:08:25 - INFO - __main__ - Step 27771: {'lr': 0.0004635196886571986, 'samples': 5332032, 'steps': 27770, 'loss/train': 1.528705358505249}
+08/30/2021 18:08:26 - INFO - __main__ - Step 27772: {'lr': 0.0004635169283393923, 'samples': 5332224, 'steps': 27771, 'loss/train': 1.4694417715072632}
+08/30/2021 18:08:26 - INFO - __main__ - Step 27773: {'lr': 0.0004635141679253785, 'samples': 5332416, 'steps': 27772, 'loss/train': 1.395058512687683}
+08/30/2021 18:08:27 - INFO - __main__ - Step 27774: {'lr': 0.0004635114074151586, 'samples': 5332608, 'steps': 27773, 'loss/train': 1.6506497859954834}
+08/30/2021 18:08:27 - INFO - __main__ - Step 27775: {'lr': 0.00046350864680873375, 'samples': 5332800, 'steps': 27774, 'loss/train': 1.5567878484725952}
+08/30/2021 18:08:29 - INFO - __main__ - Step 27776: {'lr': 0.0004635058861061051, 'samples': 5332992, 'steps': 27775, 'loss/train': 0.40147650241851807}
+08/30/2021 18:08:30 - INFO - __main__ - Step 27777: {'lr': 0.00046350312530727403, 'samples': 5333184, 'steps': 27776, 'loss/train': 1.261691689491272}
+08/30/2021 18:08:30 - INFO - __main__ - Step 27778: {'lr': 0.00046350036441224175, 'samples': 5333376, 'steps': 27777, 'loss/train': 0.7986395955085754}
+08/30/2021 18:08:30 - INFO - __main__ - Step 27779: {'lr': 0.00046349760342100955, 'samples': 5333568, 'steps': 27778, 'loss/train': 0.9109395146369934}
+08/30/2021 18:08:31 - INFO - __main__ - Step 27780: {'lr': 0.00046349484233357854, 'samples': 5333760, 'steps': 27779, 'loss/train': 0.8990795016288757}
+08/30/2021 18:08:31 - INFO - __main__ - Step 27781: {'lr': 0.0004634920811499501, 'samples': 5333952, 'steps': 27780, 'loss/train': 1.3686414957046509}
+08/30/2021 18:08:32 - INFO - __main__ - Step 27782: {'lr': 0.00046348931987012543, 'samples': 5334144, 'steps': 27781, 'loss/train': 1.518345594406128}
+08/30/2021 18:08:33 - INFO - __main__ - Step 27783: {'lr': 0.00046348655849410577, 'samples': 5334336, 'steps': 27782, 'loss/train': 1.1290329694747925}
+08/30/2021 18:08:33 - INFO - __main__ - Step 27784: {'lr': 0.0004634837970218924, 'samples': 5334528, 'steps': 27783, 'loss/train': 1.4776440858840942}
+08/30/2021 18:08:34 - INFO - __main__ - Step 27785: {'lr': 0.0004634810354534864, 'samples': 5334720, 'steps': 27784, 'loss/train': 1.881790280342102}
+08/30/2021 18:08:34 - INFO - __main__ - Step 27786: {'lr': 0.0004634782737888892, 'samples': 5334912, 'steps': 27785, 'loss/train': 1.4031047821044922}
+08/30/2021 18:08:35 - INFO - __main__ - Step 27787: {'lr': 0.000463475512028102, 'samples': 5335104, 'steps': 27786, 'loss/train': 1.4787510633468628}
+08/30/2021 18:08:36 - INFO - __main__ - Step 27788: {'lr': 0.000463472750171126, 'samples': 5335296, 'steps': 27787, 'loss/train': 0.08194834738969803}
+08/30/2021 18:08:36 - INFO - __main__ - Step 27789: {'lr': 0.0004634699882179625, 'samples': 5335488, 'steps': 27788, 'loss/train': 1.0469577312469482}
+08/30/2021 18:08:37 - INFO - __main__ - Step 27790: {'lr': 0.0004634672261686127, 'samples': 5335680, 'steps': 27789, 'loss/train': 1.6386882066726685}
+08/30/2021 18:08:37 - INFO - __main__ - Step 27791: {'lr': 0.0004634644640230779, 'samples': 5335872, 'steps': 27790, 'loss/train': 0.704902708530426}
+08/30/2021 18:08:39 - INFO - __main__ - Step 27792: {'lr': 0.0004634617017813593, 'samples': 5336064, 'steps': 27791, 'loss/train': 1.4183684587478638}
+08/30/2021 18:08:39 - INFO - __main__ - Step 27793: {'lr': 0.00046345893944345806, 'samples': 5336256, 'steps': 27792, 'loss/train': 2.2018020153045654}
+08/30/2021 18:08:39 - INFO - __main__ - Step 27794: {'lr': 0.00046345617700937564, 'samples': 5336448, 'steps': 27793, 'loss/train': 1.7258145809173584}
+08/30/2021 18:08:40 - INFO - __main__ - Step 27795: {'lr': 0.0004634534144791131, 'samples': 5336640, 'steps': 27794, 'loss/train': 0.2126784771680832}
+08/30/2021 18:08:40 - INFO - __main__ - Step 27796: {'lr': 0.0004634506518526718, 'samples': 5336832, 'steps': 27795, 'loss/train': 1.3140028715133667}
+08/30/2021 18:08:40 - INFO - __main__ - Step 27797: {'lr': 0.00046344788913005286, 'samples': 5337024, 'steps': 27796, 'loss/train': 1.5470367670059204}
+08/30/2021 18:08:42 - INFO - __main__ - Step 27798: {'lr': 0.00046344512631125756, 'samples': 5337216, 'steps': 27797, 'loss/train': 1.9504424333572388}
+08/30/2021 18:08:43 - INFO - __main__ - Step 27799: {'lr': 0.00046344236339628724, 'samples': 5337408, 'steps': 27798, 'loss/train': 0.5643483400344849}
+08/30/2021 18:08:43 - INFO - __main__ - Step 27800: {'lr': 0.0004634396003851431, 'samples': 5337600, 'steps': 27799, 'loss/train': 1.915980577468872}
+08/30/2021 18:08:43 - INFO - __main__ - Step 27801: {'lr': 0.00046343683727782635, 'samples': 5337792, 'steps': 27800, 'loss/train': 1.5329633951187134}
+08/30/2021 18:08:44 - INFO - __main__ - Step 27802: {'lr': 0.0004634340740743382, 'samples': 5337984, 'steps': 27801, 'loss/train': 1.385451078414917}
+08/30/2021 18:08:46 - INFO - __main__ - Step 27803: {'lr': 0.00046343131077468, 'samples': 5338176, 'steps': 27802, 'loss/train': 0.9860138893127441}
+08/30/2021 18:08:46 - INFO - __main__ - Step 27804: {'lr': 0.00046342854737885296, 'samples': 5338368, 'steps': 27803, 'loss/train': 1.3522201776504517}
+08/30/2021 18:08:46 - INFO - __main__ - Step 27805: {'lr': 0.00046342578388685837, 'samples': 5338560, 'steps': 27804, 'loss/train': 1.868133544921875}
+08/30/2021 18:08:47 - INFO - __main__ - Step 27806: {'lr': 0.0004634230202986973, 'samples': 5338752, 'steps': 27805, 'loss/train': 1.3344823122024536}
+08/30/2021 18:08:47 - INFO - __main__ - Step 27807: {'lr': 0.0004634202566143712, 'samples': 5338944, 'steps': 27806, 'loss/train': 1.7863492965698242}
+08/30/2021 18:08:49 - INFO - __main__ - Step 27808: {'lr': 0.00046341749283388117, 'samples': 5339136, 'steps': 27807, 'loss/train': 1.4219354391098022}
+08/30/2021 18:08:49 - INFO - __main__ - Step 27809: {'lr': 0.0004634147289572285, 'samples': 5339328, 'steps': 27808, 'loss/train': 1.2044622898101807}
+08/30/2021 18:08:49 - INFO - __main__ - Step 27810: {'lr': 0.00046341196498441453, 'samples': 5339520, 'steps': 27809, 'loss/train': 1.3901963233947754}
+08/30/2021 18:08:50 - INFO - __main__ - Step 27811: {'lr': 0.0004634092009154403, 'samples': 5339712, 'steps': 27810, 'loss/train': 1.82839834690094}
+08/30/2021 18:08:50 - INFO - __main__ - Step 27812: {'lr': 0.0004634064367503072, 'samples': 5339904, 'steps': 27811, 'loss/train': 0.2811654508113861}
+08/30/2021 18:08:52 - INFO - __main__ - Step 27813: {'lr': 0.00046340367248901655, 'samples': 5340096, 'steps': 27812, 'loss/train': 1.6390193700790405}
+08/30/2021 18:08:52 - INFO - __main__ - Step 27814: {'lr': 0.00046340090813156944, 'samples': 5340288, 'steps': 27813, 'loss/train': 1.7161142826080322}
+08/30/2021 18:08:53 - INFO - __main__ - Step 27815: {'lr': 0.00046339814367796716, 'samples': 5340480, 'steps': 27814, 'loss/train': 1.2551450729370117}
+08/30/2021 18:08:53 - INFO - __main__ - Step 27816: {'lr': 0.00046339537912821094, 'samples': 5340672, 'steps': 27815, 'loss/train': 2.1397149562835693}
+08/30/2021 18:08:53 - INFO - __main__ - Step 27817: {'lr': 0.0004633926144823022, 'samples': 5340864, 'steps': 27816, 'loss/train': 1.7750980854034424}
+08/30/2021 18:08:54 - INFO - __main__ - Step 27818: {'lr': 0.0004633898497402419, 'samples': 5341056, 'steps': 27817, 'loss/train': 1.7932462692260742}
+08/30/2021 18:08:55 - INFO - __main__ - Step 27819: {'lr': 0.0004633870849020314, 'samples': 5341248, 'steps': 27818, 'loss/train': 0.15541088581085205}
+08/30/2021 18:08:56 - INFO - __main__ - Step 27820: {'lr': 0.00046338431996767205, 'samples': 5341440, 'steps': 27819, 'loss/train': 5.489909648895264}
+08/30/2021 18:08:56 - INFO - __main__ - Step 27821: {'lr': 0.00046338155493716503, 'samples': 5341632, 'steps': 27820, 'loss/train': 1.8474998474121094}
+08/30/2021 18:08:56 - INFO - __main__ - Step 27822: {'lr': 0.0004633787898105115, 'samples': 5341824, 'steps': 27821, 'loss/train': 1.2274061441421509}
+08/30/2021 18:08:57 - INFO - __main__ - Step 27823: {'lr': 0.0004633760245877129, 'samples': 5342016, 'steps': 27822, 'loss/train': 1.5886231660842896}
+08/30/2021 18:08:58 - INFO - __main__ - Step 27824: {'lr': 0.0004633732592687703, 'samples': 5342208, 'steps': 27823, 'loss/train': 0.9894622564315796}
+08/30/2021 18:08:59 - INFO - __main__ - Step 27825: {'lr': 0.00046337049385368495, 'samples': 5342400, 'steps': 27824, 'loss/train': 1.9861916303634644}
+08/30/2021 18:08:59 - INFO - __main__ - Step 27826: {'lr': 0.00046336772834245824, 'samples': 5342592, 'steps': 27825, 'loss/train': 1.5195856094360352}
+08/30/2021 18:08:59 - INFO - __main__ - Step 27827: {'lr': 0.0004633649627350912, 'samples': 5342784, 'steps': 27826, 'loss/train': 1.1240161657333374}
+08/30/2021 18:09:00 - INFO - __main__ - Step 27828: {'lr': 0.00046336219703158526, 'samples': 5342976, 'steps': 27827, 'loss/train': 1.9857053756713867}
+08/30/2021 18:09:02 - INFO - __main__ - Step 27829: {'lr': 0.00046335943123194164, 'samples': 5343168, 'steps': 27828, 'loss/train': 1.4039204120635986}
+08/30/2021 18:09:02 - INFO - __main__ - Step 27830: {'lr': 0.0004633566653361615, 'samples': 5343360, 'steps': 27829, 'loss/train': 1.4734183549880981}
+08/30/2021 18:09:03 - INFO - __main__ - Step 27831: {'lr': 0.0004633538993442462, 'samples': 5343552, 'steps': 27830, 'loss/train': 1.527032732963562}
+08/30/2021 18:09:03 - INFO - __main__ - Step 27832: {'lr': 0.00046335113325619685, 'samples': 5343744, 'steps': 27831, 'loss/train': 1.4288867712020874}
+08/30/2021 18:09:03 - INFO - __main__ - Step 27833: {'lr': 0.00046334836707201486, 'samples': 5343936, 'steps': 27832, 'loss/train': 1.7638781070709229}
+08/30/2021 18:09:04 - INFO - __main__ - Step 27834: {'lr': 0.0004633456007917013, 'samples': 5344128, 'steps': 27833, 'loss/train': 1.0613548755645752}
+08/30/2021 18:09:04 - INFO - __main__ - Step 27835: {'lr': 0.0004633428344152576, 'samples': 5344320, 'steps': 27834, 'loss/train': 1.0412993431091309}
+08/30/2021 18:09:06 - INFO - __main__ - Step 27836: {'lr': 0.0004633400679426848, 'samples': 5344512, 'steps': 27835, 'loss/train': 1.024503231048584}
+08/30/2021 18:09:06 - INFO - __main__ - Step 27837: {'lr': 0.00046333730137398433, 'samples': 5344704, 'steps': 27836, 'loss/train': 0.8051562309265137}
+08/30/2021 18:09:07 - INFO - __main__ - Step 27838: {'lr': 0.00046333453470915736, 'samples': 5344896, 'steps': 27837, 'loss/train': 0.09756675362586975}
+08/30/2021 18:09:07 - INFO - __main__ - Step 27839: {'lr': 0.0004633317679482051, 'samples': 5345088, 'steps': 27838, 'loss/train': 1.6739451885223389}
+08/30/2021 18:09:07 - INFO - __main__ - Step 27840: {'lr': 0.00046332900109112893, 'samples': 5345280, 'steps': 27839, 'loss/train': 1.2744837999343872}
+08/30/2021 18:09:09 - INFO - __main__ - Step 27841: {'lr': 0.0004633262341379299, 'samples': 5345472, 'steps': 27840, 'loss/train': 1.4695515632629395}
+08/30/2021 18:09:09 - INFO - __main__ - Step 27842: {'lr': 0.0004633234670886094, 'samples': 5345664, 'steps': 27841, 'loss/train': 1.4233691692352295}
+08/30/2021 18:09:10 - INFO - __main__ - Step 27843: {'lr': 0.0004633206999431686, 'samples': 5345856, 'steps': 27842, 'loss/train': 1.7822850942611694}
+08/30/2021 18:09:10 - INFO - __main__ - Step 27844: {'lr': 0.00046331793270160885, 'samples': 5346048, 'steps': 27843, 'loss/train': 1.6514739990234375}
+08/30/2021 18:09:10 - INFO - __main__ - Step 27845: {'lr': 0.0004633151653639314, 'samples': 5346240, 'steps': 27844, 'loss/train': 2.3348324298858643}
+08/30/2021 18:09:12 - INFO - __main__ - Step 27846: {'lr': 0.00046331239793013726, 'samples': 5346432, 'steps': 27845, 'loss/train': 1.9039591550827026}
+08/30/2021 18:09:12 - INFO - __main__ - Step 27847: {'lr': 0.0004633096304002279, 'samples': 5346624, 'steps': 27846, 'loss/train': 1.19235360622406}
+08/30/2021 18:09:13 - INFO - __main__ - Step 27848: {'lr': 0.00046330686277420454, 'samples': 5346816, 'steps': 27847, 'loss/train': 1.4089248180389404}
+08/30/2021 18:09:13 - INFO - __main__ - Step 27849: {'lr': 0.00046330409505206837, 'samples': 5347008, 'steps': 27848, 'loss/train': 1.5183302164077759}
+08/30/2021 18:09:13 - INFO - __main__ - Step 27850: {'lr': 0.00046330132723382066, 'samples': 5347200, 'steps': 27849, 'loss/train': 1.5850435495376587}
+08/30/2021 18:09:15 - INFO - __main__ - Step 27851: {'lr': 0.0004632985593194627, 'samples': 5347392, 'steps': 27850, 'loss/train': 1.0716716051101685}
+08/30/2021 18:09:15 - INFO - __main__ - Step 27852: {'lr': 0.00046329579130899567, 'samples': 5347584, 'steps': 27851, 'loss/train': 1.5987440347671509}
+08/30/2021 18:09:16 - INFO - __main__ - Step 27853: {'lr': 0.0004632930232024209, 'samples': 5347776, 'steps': 27852, 'loss/train': 1.7953028678894043}
+08/30/2021 18:09:16 - INFO - __main__ - Step 27854: {'lr': 0.0004632902549997395, 'samples': 5347968, 'steps': 27853, 'loss/train': 1.2598515748977661}
+08/30/2021 18:09:16 - INFO - __main__ - Step 27855: {'lr': 0.00046328748670095287, 'samples': 5348160, 'steps': 27854, 'loss/train': 1.3424211740493774}
+08/30/2021 18:09:18 - INFO - __main__ - Step 27856: {'lr': 0.0004632847183060622, 'samples': 5348352, 'steps': 27855, 'loss/train': 1.6653623580932617}
+08/30/2021 18:09:19 - INFO - __main__ - Step 27857: {'lr': 0.0004632819498150688, 'samples': 5348544, 'steps': 27856, 'loss/train': 1.4488108158111572}
+08/30/2021 18:09:19 - INFO - __main__ - Step 27858: {'lr': 0.00046327918122797363, 'samples': 5348736, 'steps': 27857, 'loss/train': 1.2262461185455322}
+08/30/2021 18:09:20 - INFO - __main__ - Step 27859: {'lr': 0.00046327641254477833, 'samples': 5348928, 'steps': 27858, 'loss/train': 1.7536661624908447}
+08/30/2021 18:09:20 - INFO - __main__ - Step 27860: {'lr': 0.00046327364376548384, 'samples': 5349120, 'steps': 27859, 'loss/train': 0.9308289885520935}
+08/30/2021 18:09:21 - INFO - __main__ - Step 27861: {'lr': 0.0004632708748900917, 'samples': 5349312, 'steps': 27860, 'loss/train': 1.4292386770248413}
+08/30/2021 18:09:22 - INFO - __main__ - Step 27862: {'lr': 0.00046326810591860285, 'samples': 5349504, 'steps': 27861, 'loss/train': 1.91312575340271}
+08/30/2021 18:09:22 - INFO - __main__ - Step 27863: {'lr': 0.0004632653368510187, 'samples': 5349696, 'steps': 27862, 'loss/train': 1.5734388828277588}
+08/30/2021 18:09:23 - INFO - __main__ - Step 27864: {'lr': 0.00046326256768734053, 'samples': 5349888, 'steps': 27863, 'loss/train': 1.2745591402053833}
+08/30/2021 18:09:23 - INFO - __main__ - Step 27865: {'lr': 0.0004632597984275695, 'samples': 5350080, 'steps': 27864, 'loss/train': 0.9460969567298889}
+08/30/2021 18:09:23 - INFO - __main__ - Step 27866: {'lr': 0.00046325702907170697, 'samples': 5350272, 'steps': 27865, 'loss/train': 1.5940924882888794}
+08/30/2021 18:09:25 - INFO - __main__ - Step 27867: {'lr': 0.000463254259619754, 'samples': 5350464, 'steps': 27866, 'loss/train': 1.37678861618042}
+08/30/2021 18:09:25 - INFO - __main__ - Step 27868: {'lr': 0.000463251490071712, 'samples': 5350656, 'steps': 27867, 'loss/train': 1.644361138343811}
+08/30/2021 18:09:26 - INFO - __main__ - Step 27869: {'lr': 0.0004632487204275822, 'samples': 5350848, 'steps': 27868, 'loss/train': 1.1219329833984375}
+08/30/2021 18:09:26 - INFO - __main__ - Step 27870: {'lr': 0.0004632459506873658, 'samples': 5351040, 'steps': 27869, 'loss/train': 1.184278964996338}
+08/30/2021 18:09:26 - INFO - __main__ - Step 27871: {'lr': 0.0004632431808510641, 'samples': 5351232, 'steps': 27870, 'loss/train': 1.9152334928512573}
+08/30/2021 18:09:28 - INFO - __main__ - Step 27872: {'lr': 0.0004632404109186782, 'samples': 5351424, 'steps': 27871, 'loss/train': 1.5471254587173462}
+08/30/2021 18:09:28 - INFO - __main__ - Step 27873: {'lr': 0.0004632376408902096, 'samples': 5351616, 'steps': 27872, 'loss/train': 1.623543620109558}
+08/30/2021 18:09:29 - INFO - __main__ - Step 27874: {'lr': 0.0004632348707656593, 'samples': 5351808, 'steps': 27873, 'loss/train': 1.6411412954330444}
+08/30/2021 18:09:29 - INFO - __main__ - Step 27875: {'lr': 0.00046323210054502874, 'samples': 5352000, 'steps': 27874, 'loss/train': 1.30329167842865}
+08/30/2021 18:09:29 - INFO - __main__ - Step 27876: {'lr': 0.00046322933022831903, 'samples': 5352192, 'steps': 27875, 'loss/train': 1.4236921072006226}
+08/30/2021 18:09:31 - INFO - __main__ - Step 27877: {'lr': 0.0004632265598155315, 'samples': 5352384, 'steps': 27876, 'loss/train': 1.4609565734863281}
+08/30/2021 18:09:31 - INFO - __main__ - Step 27878: {'lr': 0.00046322378930666736, 'samples': 5352576, 'steps': 27877, 'loss/train': 1.5716593265533447}
+08/30/2021 18:09:32 - INFO - __main__ - Step 27879: {'lr': 0.0004632210187017278, 'samples': 5352768, 'steps': 27878, 'loss/train': 0.8533258438110352}
+08/30/2021 18:09:32 - INFO - __main__ - Step 27880: {'lr': 0.00046321824800071425, 'samples': 5352960, 'steps': 27879, 'loss/train': 1.2530912160873413}
+08/30/2021 18:09:32 - INFO - __main__ - Step 27881: {'lr': 0.0004632154772036279, 'samples': 5353152, 'steps': 27880, 'loss/train': 1.4827314615249634}
+08/30/2021 18:09:34 - INFO - __main__ - Step 27882: {'lr': 0.0004632127063104698, 'samples': 5353344, 'steps': 27881, 'loss/train': 1.599303126335144}
+08/30/2021 18:09:34 - INFO - __main__ - Step 27883: {'lr': 0.00046320993532124137, 'samples': 5353536, 'steps': 27882, 'loss/train': 1.5524917840957642}
+08/30/2021 18:09:35 - INFO - __main__ - Step 27884: {'lr': 0.0004632071642359439, 'samples': 5353728, 'steps': 27883, 'loss/train': 1.8457468748092651}
+08/30/2021 18:09:35 - INFO - __main__ - Step 27885: {'lr': 0.0004632043930545785, 'samples': 5353920, 'steps': 27884, 'loss/train': 0.07377669960260391}
+08/30/2021 18:09:35 - INFO - __main__ - Step 27886: {'lr': 0.00046320162177714653, 'samples': 5354112, 'steps': 27885, 'loss/train': 1.8720864057540894}
+08/30/2021 18:09:37 - INFO - __main__ - Step 27887: {'lr': 0.00046319885040364925, 'samples': 5354304, 'steps': 27886, 'loss/train': 1.5645158290863037}
+08/30/2021 18:09:38 - INFO - __main__ - Step 27888: {'lr': 0.00046319607893408776, 'samples': 5354496, 'steps': 27887, 'loss/train': 1.0230780839920044}
+08/30/2021 18:09:38 - INFO - __main__ - Step 27889: {'lr': 0.0004631933073684635, 'samples': 5354688, 'steps': 27888, 'loss/train': 0.8020130395889282}
+08/30/2021 18:09:38 - INFO - __main__ - Step 27890: {'lr': 0.00046319053570677754, 'samples': 5354880, 'steps': 27889, 'loss/train': 1.6323224306106567}
+08/30/2021 18:09:39 - INFO - __main__ - Step 27891: {'lr': 0.0004631877639490313, 'samples': 5355072, 'steps': 27890, 'loss/train': 1.1596242189407349}
+08/30/2021 18:09:40 - INFO - __main__ - Step 27892: {'lr': 0.0004631849920952259, 'samples': 5355264, 'steps': 27891, 'loss/train': 1.720773458480835}
+08/30/2021 18:09:40 - INFO - __main__ - Step 27893: {'lr': 0.0004631822201453626, 'samples': 5355456, 'steps': 27892, 'loss/train': 1.4729856252670288}
+08/30/2021 18:09:41 - INFO - __main__ - Step 27894: {'lr': 0.0004631794480994427, 'samples': 5355648, 'steps': 27893, 'loss/train': 1.6313401460647583}
+08/30/2021 18:09:41 - INFO - __main__ - Step 27895: {'lr': 0.0004631766759574675, 'samples': 5355840, 'steps': 27894, 'loss/train': 0.4398038983345032}
+08/30/2021 18:09:42 - INFO - __main__ - Step 27896: {'lr': 0.0004631739037194381, 'samples': 5356032, 'steps': 27895, 'loss/train': 1.3815815448760986}
+08/30/2021 18:09:43 - INFO - __main__ - Step 27897: {'lr': 0.00046317113138535584, 'samples': 5356224, 'steps': 27896, 'loss/train': 1.543875813484192}
+08/30/2021 18:09:44 - INFO - __main__ - Step 27898: {'lr': 0.0004631683589552219, 'samples': 5356416, 'steps': 27897, 'loss/train': 1.45516836643219}
+08/30/2021 18:09:44 - INFO - __main__ - Step 27899: {'lr': 0.00046316558642903774, 'samples': 5356608, 'steps': 27898, 'loss/train': 1.6084994077682495}
+08/30/2021 18:09:44 - INFO - __main__ - Step 27900: {'lr': 0.0004631628138068043, 'samples': 5356800, 'steps': 27899, 'loss/train': 1.3844728469848633}
+08/30/2021 18:09:45 - INFO - __main__ - Step 27901: {'lr': 0.00046316004108852305, 'samples': 5356992, 'steps': 27900, 'loss/train': 1.730255365371704}
+08/30/2021 18:09:45 - INFO - __main__ - Step 27902: {'lr': 0.0004631572682741952, 'samples': 5357184, 'steps': 27901, 'loss/train': 1.5052891969680786}
+08/30/2021 18:09:47 - INFO - __main__ - Step 27903: {'lr': 0.0004631544953638219, 'samples': 5357376, 'steps': 27902, 'loss/train': 0.9532438516616821}
+08/30/2021 18:09:47 - INFO - __main__ - Step 27904: {'lr': 0.00046315172235740455, 'samples': 5357568, 'steps': 27903, 'loss/train': 0.07877084612846375}
+08/30/2021 18:09:47 - INFO - __main__ - Step 27905: {'lr': 0.0004631489492549443, 'samples': 5357760, 'steps': 27904, 'loss/train': 1.857937216758728}
+08/30/2021 18:09:48 - INFO - __main__ - Step 27906: {'lr': 0.00046314617605644243, 'samples': 5357952, 'steps': 27905, 'loss/train': 1.09197199344635}
+08/30/2021 18:09:48 - INFO - __main__ - Step 27907: {'lr': 0.0004631434027619001, 'samples': 5358144, 'steps': 27906, 'loss/train': 0.6468884944915771}
+08/30/2021 18:09:50 - INFO - __main__ - Step 27908: {'lr': 0.0004631406293713188, 'samples': 5358336, 'steps': 27907, 'loss/train': 0.38434073328971863}
+08/30/2021 18:09:51 - INFO - __main__ - Step 27909: {'lr': 0.0004631378558846995, 'samples': 5358528, 'steps': 27908, 'loss/train': 1.4693931341171265}
+08/30/2021 18:09:51 - INFO - __main__ - Step 27910: {'lr': 0.00046313508230204364, 'samples': 5358720, 'steps': 27909, 'loss/train': 1.861594319343567}
+08/30/2021 18:09:51 - INFO - __main__ - Step 27911: {'lr': 0.00046313230862335235, 'samples': 5358912, 'steps': 27910, 'loss/train': 1.4517710208892822}
+08/30/2021 18:09:52 - INFO - __main__ - Step 27912: {'lr': 0.000463129534848627, 'samples': 5359104, 'steps': 27911, 'loss/train': 1.1970484256744385}
+08/30/2021 18:09:53 - INFO - __main__ - Step 27913: {'lr': 0.0004631267609778687, 'samples': 5359296, 'steps': 27912, 'loss/train': 1.354780912399292}
+08/30/2021 18:09:54 - INFO - __main__ - Step 27914: {'lr': 0.0004631239870110788, 'samples': 5359488, 'steps': 27913, 'loss/train': 0.8847267031669617}
+08/30/2021 18:09:54 - INFO - __main__ - Step 27915: {'lr': 0.00046312121294825846, 'samples': 5359680, 'steps': 27914, 'loss/train': 2.010751485824585}
+08/30/2021 18:09:54 - INFO - __main__ - Step 27916: {'lr': 0.00046311843878940904, 'samples': 5359872, 'steps': 27915, 'loss/train': 1.421433925628662}
+08/30/2021 18:09:55 - INFO - __main__ - Step 27917: {'lr': 0.0004631156645345318, 'samples': 5360064, 'steps': 27916, 'loss/train': 1.6389130353927612}
+08/30/2021 18:09:56 - INFO - __main__ - Step 27918: {'lr': 0.0004631128901836278, 'samples': 5360256, 'steps': 27917, 'loss/train': 2.283113479614258}
+08/30/2021 18:09:57 - INFO - __main__ - Step 27919: {'lr': 0.0004631101157366985, 'samples': 5360448, 'steps': 27918, 'loss/train': 0.6903948187828064}
+08/30/2021 18:09:57 - INFO - __main__ - Step 27920: {'lr': 0.0004631073411937451, 'samples': 5360640, 'steps': 27919, 'loss/train': 1.649309515953064}
+08/30/2021 18:09:57 - INFO - __main__ - Step 27921: {'lr': 0.00046310456655476875, 'samples': 5360832, 'steps': 27920, 'loss/train': 1.745056390762329}
+08/30/2021 18:09:58 - INFO - __main__ - Step 27922: {'lr': 0.0004631017918197709, 'samples': 5361024, 'steps': 27921, 'loss/train': 1.7016445398330688}
+08/30/2021 18:09:59 - INFO - __main__ - Step 27923: {'lr': 0.00046309901698875244, 'samples': 5361216, 'steps': 27922, 'loss/train': 1.6440163850784302}
+08/30/2021 18:10:00 - INFO - __main__ - Step 27924: {'lr': 0.00046309624206171505, 'samples': 5361408, 'steps': 27923, 'loss/train': 2.148451328277588}
+08/30/2021 18:10:00 - INFO - __main__ - Step 27925: {'lr': 0.00046309346703865973, 'samples': 5361600, 'steps': 27924, 'loss/train': 1.5376533269882202}
+08/30/2021 18:10:00 - INFO - __main__ - Step 27926: {'lr': 0.00046309069191958775, 'samples': 5361792, 'steps': 27925, 'loss/train': 1.7108235359191895}
+08/30/2021 18:10:01 - INFO - __main__ - Step 27927: {'lr': 0.00046308791670450033, 'samples': 5361984, 'steps': 27926, 'loss/train': 1.6991583108901978}
+08/30/2021 18:10:02 - INFO - __main__ - Step 27928: {'lr': 0.00046308514139339896, 'samples': 5362176, 'steps': 27927, 'loss/train': 1.648048758506775}
+08/30/2021 18:10:03 - INFO - __main__ - Step 27929: {'lr': 0.0004630823659862846, 'samples': 5362368, 'steps': 27928, 'loss/train': 1.1558430194854736}
+08/30/2021 18:10:03 - INFO - __main__ - Step 27930: {'lr': 0.0004630795904831586, 'samples': 5362560, 'steps': 27929, 'loss/train': 1.4804942607879639}
+08/30/2021 18:10:03 - INFO - __main__ - Step 27931: {'lr': 0.0004630768148840223, 'samples': 5362752, 'steps': 27930, 'loss/train': 0.8264032006263733}
+08/30/2021 18:10:04 - INFO - __main__ - Step 27932: {'lr': 0.0004630740391888768, 'samples': 5362944, 'steps': 27931, 'loss/train': 1.671456217765808}
+08/30/2021 18:10:04 - INFO - __main__ - Step 27933: {'lr': 0.0004630712633977234, 'samples': 5363136, 'steps': 27932, 'loss/train': 1.25258469581604}
+08/30/2021 18:10:05 - INFO - __main__ - Step 27934: {'lr': 0.00046306848751056346, 'samples': 5363328, 'steps': 27933, 'loss/train': 0.786181628704071}
+08/30/2021 18:10:06 - INFO - __main__ - Step 27935: {'lr': 0.0004630657115273981, 'samples': 5363520, 'steps': 27934, 'loss/train': 1.7340360879898071}
+08/30/2021 18:10:06 - INFO - __main__ - Step 27936: {'lr': 0.0004630629354482286, 'samples': 5363712, 'steps': 27935, 'loss/train': 1.613985538482666}
+08/30/2021 18:10:07 - INFO - __main__ - Step 27937: {'lr': 0.00046306015927305633, 'samples': 5363904, 'steps': 27936, 'loss/train': 1.5055582523345947}
+08/30/2021 18:10:07 - INFO - __main__ - Step 27938: {'lr': 0.0004630573830018824, 'samples': 5364096, 'steps': 27937, 'loss/train': 0.9066299200057983}
+08/30/2021 18:10:08 - INFO - __main__ - Step 27939: {'lr': 0.00046305460663470803, 'samples': 5364288, 'steps': 27938, 'loss/train': 1.687584638595581}
+08/30/2021 18:10:09 - INFO - __main__ - Step 27940: {'lr': 0.0004630518301715346, 'samples': 5364480, 'steps': 27939, 'loss/train': 1.1913965940475464}
+08/30/2021 18:10:09 - INFO - __main__ - Step 27941: {'lr': 0.00046304905361236335, 'samples': 5364672, 'steps': 27940, 'loss/train': 1.8258600234985352}
+08/30/2021 18:10:09 - INFO - __main__ - Step 27942: {'lr': 0.00046304627695719535, 'samples': 5364864, 'steps': 27941, 'loss/train': 1.5701454877853394}
+08/30/2021 18:10:10 - INFO - __main__ - Step 27943: {'lr': 0.0004630435002060321, 'samples': 5365056, 'steps': 27942, 'loss/train': 1.3512667417526245}
+08/30/2021 18:10:12 - INFO - __main__ - Step 27944: {'lr': 0.0004630407233588747, 'samples': 5365248, 'steps': 27943, 'loss/train': 1.5550307035446167}
+08/30/2021 18:10:12 - INFO - __main__ - Step 27945: {'lr': 0.00046303794641572445, 'samples': 5365440, 'steps': 27944, 'loss/train': 1.9324413537979126}
+08/30/2021 18:10:12 - INFO - __main__ - Step 27946: {'lr': 0.0004630351693765825, 'samples': 5365632, 'steps': 27945, 'loss/train': 1.4949580430984497}
+08/30/2021 18:10:13 - INFO - __main__ - Step 27947: {'lr': 0.0004630323922414503, 'samples': 5365824, 'steps': 27946, 'loss/train': 1.6540135145187378}
+08/30/2021 18:10:13 - INFO - __main__ - Step 27948: {'lr': 0.00046302961501032896, 'samples': 5366016, 'steps': 27947, 'loss/train': 1.3547570705413818}
+08/30/2021 18:10:15 - INFO - __main__ - Step 27949: {'lr': 0.00046302683768321973, 'samples': 5366208, 'steps': 27948, 'loss/train': 0.8375091552734375}
+08/30/2021 18:10:15 - INFO - __main__ - Step 27950: {'lr': 0.00046302406026012396, 'samples': 5366400, 'steps': 27949, 'loss/train': 1.5853266716003418}
+08/30/2021 18:10:16 - INFO - __main__ - Step 27951: {'lr': 0.0004630212827410428, 'samples': 5366592, 'steps': 27950, 'loss/train': 2.0909345149993896}
+08/30/2021 18:10:16 - INFO - __main__ - Step 27952: {'lr': 0.00046301850512597755, 'samples': 5366784, 'steps': 27951, 'loss/train': 1.000041127204895}
+08/30/2021 18:10:16 - INFO - __main__ - Step 27953: {'lr': 0.0004630157274149294, 'samples': 5366976, 'steps': 27952, 'loss/train': 1.8751729726791382}
+08/30/2021 18:10:18 - INFO - __main__ - Step 27954: {'lr': 0.0004630129496078997, 'samples': 5367168, 'steps': 27953, 'loss/train': 1.3810734748840332}
+08/30/2021 18:10:18 - INFO - __main__ - Step 27955: {'lr': 0.00046301017170488965, 'samples': 5367360, 'steps': 27954, 'loss/train': 1.148566484451294}
+08/30/2021 18:10:19 - INFO - __main__ - Step 27956: {'lr': 0.0004630073937059005, 'samples': 5367552, 'steps': 27955, 'loss/train': 0.05812060460448265}
+08/30/2021 18:10:19 - INFO - __main__ - Step 27957: {'lr': 0.0004630046156109334, 'samples': 5367744, 'steps': 27956, 'loss/train': 0.6879861354827881}
+08/30/2021 18:10:19 - INFO - __main__ - Step 27958: {'lr': 0.0004630018374199899, 'samples': 5367936, 'steps': 27957, 'loss/train': 1.4244699478149414}
+08/30/2021 18:10:21 - INFO - __main__ - Step 27959: {'lr': 0.00046299905913307096, 'samples': 5368128, 'steps': 27958, 'loss/train': 1.2281049489974976}
+08/30/2021 18:10:22 - INFO - __main__ - Step 27960: {'lr': 0.00046299628075017785, 'samples': 5368320, 'steps': 27959, 'loss/train': 1.7666549682617188}
+08/30/2021 18:10:22 - INFO - __main__ - Step 27961: {'lr': 0.000462993502271312, 'samples': 5368512, 'steps': 27960, 'loss/train': 1.5040251016616821}
+08/30/2021 18:10:22 - INFO - __main__ - Step 27962: {'lr': 0.00046299072369647453, 'samples': 5368704, 'steps': 27961, 'loss/train': 1.8474175930023193}
+08/30/2021 18:10:23 - INFO - __main__ - Step 27963: {'lr': 0.00046298794502566676, 'samples': 5368896, 'steps': 27962, 'loss/train': 1.0150020122528076}
+08/30/2021 18:10:24 - INFO - __main__ - Step 27964: {'lr': 0.0004629851662588899, 'samples': 5369088, 'steps': 27963, 'loss/train': 1.4271022081375122}
+08/30/2021 18:10:25 - INFO - __main__ - Step 27965: {'lr': 0.00046298238739614524, 'samples': 5369280, 'steps': 27964, 'loss/train': 1.410161018371582}
+08/30/2021 18:10:25 - INFO - __main__ - Step 27966: {'lr': 0.0004629796084374339, 'samples': 5369472, 'steps': 27965, 'loss/train': 1.77895987033844}
+08/30/2021 18:10:25 - INFO - __main__ - Step 27967: {'lr': 0.00046297682938275733, 'samples': 5369664, 'steps': 27966, 'loss/train': 1.7697396278381348}
+08/30/2021 18:10:26 - INFO - __main__ - Step 27968: {'lr': 0.0004629740502321167, 'samples': 5369856, 'steps': 27967, 'loss/train': 1.216433048248291}
+08/30/2021 18:10:27 - INFO - __main__ - Step 27969: {'lr': 0.00046297127098551317, 'samples': 5370048, 'steps': 27968, 'loss/train': 1.5631228685379028}
+08/30/2021 18:10:28 - INFO - __main__ - Step 27970: {'lr': 0.00046296849164294816, 'samples': 5370240, 'steps': 27969, 'loss/train': 1.7805249691009521}
+08/30/2021 18:10:28 - INFO - __main__ - Step 27971: {'lr': 0.00046296571220442274, 'samples': 5370432, 'steps': 27970, 'loss/train': 1.0356769561767578}
+08/30/2021 18:10:28 - INFO - __main__ - Step 27972: {'lr': 0.00046296293266993833, 'samples': 5370624, 'steps': 27971, 'loss/train': 1.3386609554290771}
+08/30/2021 18:10:29 - INFO - __main__ - Step 27973: {'lr': 0.00046296015303949606, 'samples': 5370816, 'steps': 27972, 'loss/train': 1.3475388288497925}
+08/30/2021 18:10:29 - INFO - __main__ - Step 27974: {'lr': 0.0004629573733130973, 'samples': 5371008, 'steps': 27973, 'loss/train': 1.4497339725494385}
+08/30/2021 18:10:31 - INFO - __main__ - Step 27975: {'lr': 0.00046295459349074316, 'samples': 5371200, 'steps': 27974, 'loss/train': 1.2262866497039795}
+08/30/2021 18:10:31 - INFO - __main__ - Step 27976: {'lr': 0.000462951813572435, 'samples': 5371392, 'steps': 27975, 'loss/train': 0.8015449643135071}
+08/30/2021 18:10:31 - INFO - __main__ - Step 27977: {'lr': 0.00046294903355817397, 'samples': 5371584, 'steps': 27976, 'loss/train': 1.5901968479156494}
+08/30/2021 18:10:32 - INFO - __main__ - Step 27978: {'lr': 0.0004629462534479615, 'samples': 5371776, 'steps': 27977, 'loss/train': 1.8777004480361938}
+08/30/2021 18:10:32 - INFO - __main__ - Step 27979: {'lr': 0.0004629434732417986, 'samples': 5371968, 'steps': 27978, 'loss/train': 1.5026010274887085}
+08/30/2021 18:10:34 - INFO - __main__ - Step 27980: {'lr': 0.0004629406929396868, 'samples': 5372160, 'steps': 27979, 'loss/train': 1.3599811792373657}
+08/30/2021 18:10:34 - INFO - __main__ - Step 27981: {'lr': 0.00046293791254162713, 'samples': 5372352, 'steps': 27980, 'loss/train': 1.7414216995239258}
+08/30/2021 18:10:35 - INFO - __main__ - Step 27982: {'lr': 0.0004629351320476209, 'samples': 5372544, 'steps': 27981, 'loss/train': 1.5243333578109741}
+08/30/2021 18:10:35 - INFO - __main__ - Step 27983: {'lr': 0.00046293235145766955, 'samples': 5372736, 'steps': 27982, 'loss/train': 1.3205631971359253}
+08/30/2021 18:10:35 - INFO - __main__ - Step 27984: {'lr': 0.000462929570771774, 'samples': 5372928, 'steps': 27983, 'loss/train': 1.3177266120910645}
+08/30/2021 18:10:36 - INFO - __main__ - Step 27985: {'lr': 0.0004629267899899358, 'samples': 5373120, 'steps': 27984, 'loss/train': 0.0660424679517746}
+08/30/2021 18:10:37 - INFO - __main__ - Step 27986: {'lr': 0.00046292400911215594, 'samples': 5373312, 'steps': 27985, 'loss/train': 0.288720041513443}
+08/30/2021 18:10:38 - INFO - __main__ - Step 27987: {'lr': 0.00046292122813843586, 'samples': 5373504, 'steps': 27986, 'loss/train': 1.9169349670410156}
+08/30/2021 18:10:38 - INFO - __main__ - Step 27988: {'lr': 0.00046291844706877674, 'samples': 5373696, 'steps': 27987, 'loss/train': 0.8314317464828491}
+08/30/2021 18:10:38 - INFO - __main__ - Step 27989: {'lr': 0.0004629156659031799, 'samples': 5373888, 'steps': 27988, 'loss/train': 1.9417732954025269}
+08/30/2021 18:10:39 - INFO - __main__ - Step 27990: {'lr': 0.0004629128846416465, 'samples': 5374080, 'steps': 27989, 'loss/train': 1.337670087814331}
+08/30/2021 18:10:40 - INFO - __main__ - Step 27991: {'lr': 0.00046291010328417784, 'samples': 5374272, 'steps': 27990, 'loss/train': 1.6752270460128784}
+08/30/2021 18:10:41 - INFO - __main__ - Step 27992: {'lr': 0.0004629073218307752, 'samples': 5374464, 'steps': 27991, 'loss/train': 1.6669642925262451}
+08/30/2021 18:10:41 - INFO - __main__ - Step 27993: {'lr': 0.0004629045402814398, 'samples': 5374656, 'steps': 27992, 'loss/train': 1.9049948453903198}
+08/30/2021 18:10:41 - INFO - __main__ - Step 27994: {'lr': 0.0004629017586361729, 'samples': 5374848, 'steps': 27993, 'loss/train': 0.12876975536346436}
+08/30/2021 18:10:42 - INFO - __main__ - Step 27995: {'lr': 0.0004628989768949757, 'samples': 5375040, 'steps': 27994, 'loss/train': 1.8217722177505493}
+08/30/2021 18:10:44 - INFO - __main__ - Step 27996: {'lr': 0.0004628961950578496, 'samples': 5375232, 'steps': 27995, 'loss/train': 1.3383779525756836}
+08/30/2021 18:10:44 - INFO - __main__ - Step 27997: {'lr': 0.00046289341312479574, 'samples': 5375424, 'steps': 27996, 'loss/train': 1.4796178340911865}
+08/30/2021 18:10:44 - INFO - __main__ - Step 27998: {'lr': 0.0004628906310958153, 'samples': 5375616, 'steps': 27997, 'loss/train': 1.280945062637329}
+08/30/2021 18:10:45 - INFO - __main__ - Step 27999: {'lr': 0.00046288784897090973, 'samples': 5375808, 'steps': 27998, 'loss/train': 1.3560783863067627}
+08/30/2021 18:10:45 - INFO - __main__ - Step 28000: {'lr': 0.00046288506675008014, 'samples': 5376000, 'steps': 27999, 'loss/train': 1.3295682668685913}
+08/30/2021 18:10:45 - INFO - __main__ - Step 28001: {'lr': 0.0004628822844333278, 'samples': 5376192, 'steps': 28000, 'loss/train': 0.049830805510282516}
+08/30/2021 18:10:47 - INFO - __main__ - Step 28002: {'lr': 0.0004628795020206541, 'samples': 5376384, 'steps': 28001, 'loss/train': 1.1427934169769287}
+08/30/2021 18:10:47 - INFO - __main__ - Step 28003: {'lr': 0.00046287671951206004, 'samples': 5376576, 'steps': 28002, 'loss/train': 1.6543828248977661}
+08/30/2021 18:10:48 - INFO - __main__ - Step 28004: {'lr': 0.0004628739369075471, 'samples': 5376768, 'steps': 28003, 'loss/train': 1.4621587991714478}
+08/30/2021 18:10:48 - INFO - __main__ - Step 28005: {'lr': 0.00046287115420711643, 'samples': 5376960, 'steps': 28004, 'loss/train': 1.7530735731124878}
+08/30/2021 18:10:48 - INFO - __main__ - Step 28006: {'lr': 0.00046286837141076934, 'samples': 5377152, 'steps': 28005, 'loss/train': 1.7326995134353638}
+08/30/2021 18:10:50 - INFO - __main__ - Step 28007: {'lr': 0.0004628655885185069, 'samples': 5377344, 'steps': 28006, 'loss/train': 1.432509422302246}
+08/30/2021 18:10:50 - INFO - __main__ - Step 28008: {'lr': 0.00046286280553033067, 'samples': 5377536, 'steps': 28007, 'loss/train': 1.2272719144821167}
+08/30/2021 18:10:51 - INFO - __main__ - Step 28009: {'lr': 0.0004628600224462417, 'samples': 5377728, 'steps': 28008, 'loss/train': 1.5074902772903442}
+08/30/2021 18:10:51 - INFO - __main__ - Step 28010: {'lr': 0.00046285723926624126, 'samples': 5377920, 'steps': 28009, 'loss/train': 1.5878270864486694}
+08/30/2021 18:10:51 - INFO - __main__ - Step 28011: {'lr': 0.00046285445599033063, 'samples': 5378112, 'steps': 28010, 'loss/train': 1.471692681312561}
+08/30/2021 18:10:54 - INFO - __main__ - Step 28012: {'lr': 0.00046285167261851114, 'samples': 5378304, 'steps': 28011, 'loss/train': 1.634076714515686}
+08/30/2021 18:10:54 - INFO - __main__ - Step 28013: {'lr': 0.00046284888915078384, 'samples': 5378496, 'steps': 28012, 'loss/train': 1.475229024887085}
+08/30/2021 18:10:54 - INFO - __main__ - Step 28014: {'lr': 0.00046284610558715024, 'samples': 5378688, 'steps': 28013, 'loss/train': 0.9592087268829346}
+08/30/2021 18:10:55 - INFO - __main__ - Step 28015: {'lr': 0.00046284332192761136, 'samples': 5378880, 'steps': 28014, 'loss/train': 1.7823725938796997}
+08/30/2021 18:10:55 - INFO - __main__ - Step 28016: {'lr': 0.0004628405381721686, 'samples': 5379072, 'steps': 28015, 'loss/train': 0.370857298374176}
+08/30/2021 18:10:57 - INFO - __main__ - Step 28017: {'lr': 0.00046283775432082327, 'samples': 5379264, 'steps': 28016, 'loss/train': 0.9909529685974121}
+08/30/2021 18:10:57 - INFO - __main__ - Step 28018: {'lr': 0.0004628349703735765, 'samples': 5379456, 'steps': 28017, 'loss/train': 1.7473207712173462}
+08/30/2021 18:10:57 - INFO - __main__ - Step 28019: {'lr': 0.0004628321863304295, 'samples': 5379648, 'steps': 28018, 'loss/train': 1.4742985963821411}
+08/30/2021 18:10:58 - INFO - __main__ - Step 28020: {'lr': 0.00046282940219138366, 'samples': 5379840, 'steps': 28019, 'loss/train': 0.8732110857963562}
+08/30/2021 18:10:58 - INFO - __main__ - Step 28021: {'lr': 0.0004628266179564401, 'samples': 5380032, 'steps': 28020, 'loss/train': 0.06682850420475006}
+08/30/2021 18:11:00 - INFO - __main__ - Step 28022: {'lr': 0.0004628238336256002, 'samples': 5380224, 'steps': 28021, 'loss/train': 1.029103398323059}
+08/30/2021 18:11:00 - INFO - __main__ - Step 28023: {'lr': 0.0004628210491988652, 'samples': 5380416, 'steps': 28022, 'loss/train': 0.6956168413162231}
+08/30/2021 18:11:00 - INFO - __main__ - Step 28024: {'lr': 0.0004628182646762363, 'samples': 5380608, 'steps': 28023, 'loss/train': 1.4460898637771606}
+08/30/2021 18:11:01 - INFO - __main__ - Step 28025: {'lr': 0.00046281548005771476, 'samples': 5380800, 'steps': 28024, 'loss/train': 1.5885947942733765}
+08/30/2021 18:11:01 - INFO - __main__ - Step 28026: {'lr': 0.0004628126953433018, 'samples': 5380992, 'steps': 28025, 'loss/train': 0.1988345831632614}
+08/30/2021 18:11:03 - INFO - __main__ - Step 28027: {'lr': 0.00046280991053299883, 'samples': 5381184, 'steps': 28026, 'loss/train': 1.525325059890747}
+08/30/2021 18:11:03 - INFO - __main__ - Step 28028: {'lr': 0.00046280712562680695, 'samples': 5381376, 'steps': 28027, 'loss/train': 1.526443600654602}
+08/30/2021 18:11:03 - INFO - __main__ - Step 28029: {'lr': 0.0004628043406247274, 'samples': 5381568, 'steps': 28028, 'loss/train': 1.3917332887649536}
+08/30/2021 18:11:04 - INFO - __main__ - Step 28030: {'lr': 0.0004628015555267616, 'samples': 5381760, 'steps': 28029, 'loss/train': 1.0822982788085938}
+08/30/2021 18:11:04 - INFO - __main__ - Step 28031: {'lr': 0.00046279877033291063, 'samples': 5381952, 'steps': 28030, 'loss/train': 1.3407223224639893}
+08/30/2021 18:11:04 - INFO - __main__ - Step 28032: {'lr': 0.0004627959850431759, 'samples': 5382144, 'steps': 28031, 'loss/train': 1.6693180799484253}
+08/30/2021 18:11:06 - INFO - __main__ - Step 28033: {'lr': 0.0004627931996575585, 'samples': 5382336, 'steps': 28032, 'loss/train': 1.3858481645584106}
+08/30/2021 18:11:06 - INFO - __main__ - Step 28034: {'lr': 0.0004627904141760598, 'samples': 5382528, 'steps': 28033, 'loss/train': 1.325707197189331}
+08/30/2021 18:11:07 - INFO - __main__ - Step 28035: {'lr': 0.000462787628598681, 'samples': 5382720, 'steps': 28034, 'loss/train': 1.443479299545288}
+08/30/2021 18:11:07 - INFO - __main__ - Step 28036: {'lr': 0.00046278484292542346, 'samples': 5382912, 'steps': 28035, 'loss/train': 1.2646863460540771}
+08/30/2021 18:11:07 - INFO - __main__ - Step 28037: {'lr': 0.0004627820571562883, 'samples': 5383104, 'steps': 28036, 'loss/train': 0.8303531408309937}
+08/30/2021 18:11:09 - INFO - __main__ - Step 28038: {'lr': 0.0004627792712912768, 'samples': 5383296, 'steps': 28037, 'loss/train': 1.3916767835617065}
+08/30/2021 18:11:10 - INFO - __main__ - Step 28039: {'lr': 0.0004627764853303902, 'samples': 5383488, 'steps': 28038, 'loss/train': 1.7772756814956665}
+08/30/2021 18:11:10 - INFO - __main__ - Step 28040: {'lr': 0.00046277369927362987, 'samples': 5383680, 'steps': 28039, 'loss/train': 0.15569743514060974}
+08/30/2021 18:11:10 - INFO - __main__ - Step 28041: {'lr': 0.00046277091312099704, 'samples': 5383872, 'steps': 28040, 'loss/train': 0.9434666633605957}
+08/30/2021 18:11:11 - INFO - __main__ - Step 28042: {'lr': 0.00046276812687249283, 'samples': 5384064, 'steps': 28041, 'loss/train': 2.144589900970459}
+08/30/2021 18:11:12 - INFO - __main__ - Step 28043: {'lr': 0.00046276534052811863, 'samples': 5384256, 'steps': 28042, 'loss/train': 1.721571683883667}
+08/30/2021 18:11:13 - INFO - __main__ - Step 28044: {'lr': 0.00046276255408787565, 'samples': 5384448, 'steps': 28043, 'loss/train': 2.0207138061523438}
+08/30/2021 18:11:13 - INFO - __main__ - Step 28045: {'lr': 0.0004627597675517652, 'samples': 5384640, 'steps': 28044, 'loss/train': 1.3871874809265137}
+08/30/2021 18:11:13 - INFO - __main__ - Step 28046: {'lr': 0.00046275698091978836, 'samples': 5384832, 'steps': 28045, 'loss/train': 1.3740190267562866}
+08/30/2021 18:11:14 - INFO - __main__ - Step 28047: {'lr': 0.0004627541941919466, 'samples': 5385024, 'steps': 28046, 'loss/train': 1.1003849506378174}
+08/30/2021 18:11:15 - INFO - __main__ - Step 28048: {'lr': 0.00046275140736824104, 'samples': 5385216, 'steps': 28047, 'loss/train': 1.3855782747268677}
+08/30/2021 18:11:16 - INFO - __main__ - Step 28049: {'lr': 0.000462748620448673, 'samples': 5385408, 'steps': 28048, 'loss/train': 1.782700538635254}
+08/30/2021 18:11:16 - INFO - __main__ - Step 28050: {'lr': 0.0004627458334332437, 'samples': 5385600, 'steps': 28049, 'loss/train': 1.8163042068481445}
+08/30/2021 18:11:16 - INFO - __main__ - Step 28051: {'lr': 0.0004627430463219544, 'samples': 5385792, 'steps': 28050, 'loss/train': 1.3694815635681152}
+08/30/2021 18:11:17 - INFO - __main__ - Step 28052: {'lr': 0.0004627402591148064, 'samples': 5385984, 'steps': 28051, 'loss/train': 1.3943809270858765}
+08/30/2021 18:11:19 - INFO - __main__ - Step 28053: {'lr': 0.0004627374718118009, 'samples': 5386176, 'steps': 28052, 'loss/train': 1.8527545928955078}
+08/30/2021 18:11:19 - INFO - __main__ - Step 28054: {'lr': 0.0004627346844129392, 'samples': 5386368, 'steps': 28053, 'loss/train': 1.161802887916565}
+08/30/2021 18:11:19 - INFO - __main__ - Step 28055: {'lr': 0.0004627318969182225, 'samples': 5386560, 'steps': 28054, 'loss/train': 0.08127857744693756}
+08/30/2021 18:11:20 - INFO - __main__ - Step 28056: {'lr': 0.0004627291093276521, 'samples': 5386752, 'steps': 28055, 'loss/train': 1.6853795051574707}
+08/30/2021 18:11:20 - INFO - __main__ - Step 28057: {'lr': 0.0004627263216412292, 'samples': 5386944, 'steps': 28056, 'loss/train': 0.6058462858200073}
+08/30/2021 18:11:20 - INFO - __main__ - Step 28058: {'lr': 0.00046272353385895515, 'samples': 5387136, 'steps': 28057, 'loss/train': 1.2188124656677246}
+08/30/2021 18:11:22 - INFO - __main__ - Step 28059: {'lr': 0.0004627207459808312, 'samples': 5387328, 'steps': 28058, 'loss/train': 1.4666595458984375}
+08/30/2021 18:11:22 - INFO - __main__ - Step 28060: {'lr': 0.00046271795800685854, 'samples': 5387520, 'steps': 28059, 'loss/train': 1.025999903678894}
+08/30/2021 18:11:23 - INFO - __main__ - Step 28061: {'lr': 0.00046271516993703844, 'samples': 5387712, 'steps': 28060, 'loss/train': 1.3338897228240967}
+08/30/2021 18:11:23 - INFO - __main__ - Step 28062: {'lr': 0.00046271238177137216, 'samples': 5387904, 'steps': 28061, 'loss/train': 1.6672204732894897}
+08/30/2021 18:11:23 - INFO - __main__ - Step 28063: {'lr': 0.00046270959350986095, 'samples': 5388096, 'steps': 28062, 'loss/train': 1.9613392353057861}
+08/30/2021 18:11:25 - INFO - __main__ - Step 28064: {'lr': 0.0004627068051525061, 'samples': 5388288, 'steps': 28063, 'loss/train': 1.6687133312225342}
+08/30/2021 18:11:25 - INFO - __main__ - Step 28065: {'lr': 0.00046270401669930885, 'samples': 5388480, 'steps': 28064, 'loss/train': 2.189272165298462}
+08/30/2021 18:11:26 - INFO - __main__ - Step 28066: {'lr': 0.0004627012281502704, 'samples': 5388672, 'steps': 28065, 'loss/train': 1.5187551975250244}
+08/30/2021 18:11:26 - INFO - __main__ - Step 28067: {'lr': 0.00046269843950539214, 'samples': 5388864, 'steps': 28066, 'loss/train': 0.9895861148834229}
+08/30/2021 18:11:26 - INFO - __main__ - Step 28068: {'lr': 0.00046269565076467517, 'samples': 5389056, 'steps': 28067, 'loss/train': 1.294631004333496}
+08/30/2021 18:11:28 - INFO - __main__ - Step 28069: {'lr': 0.0004626928619281209, 'samples': 5389248, 'steps': 28068, 'loss/train': 1.447240948677063}
+08/30/2021 18:11:29 - INFO - __main__ - Step 28070: {'lr': 0.0004626900729957305, 'samples': 5389440, 'steps': 28069, 'loss/train': 0.9354313015937805}
+08/30/2021 18:11:29 - INFO - __main__ - Step 28071: {'lr': 0.00046268728396750515, 'samples': 5389632, 'steps': 28070, 'loss/train': 1.1724275350570679}
+08/30/2021 18:11:29 - INFO - __main__ - Step 28072: {'lr': 0.0004626844948434462, 'samples': 5389824, 'steps': 28071, 'loss/train': 1.544147253036499}
+08/30/2021 18:11:30 - INFO - __main__ - Step 28073: {'lr': 0.00046268170562355497, 'samples': 5390016, 'steps': 28072, 'loss/train': 0.8086039423942566}
+08/30/2021 18:11:30 - INFO - __main__ - Step 28074: {'lr': 0.0004626789163078327, 'samples': 5390208, 'steps': 28073, 'loss/train': 2.0508766174316406}
+08/30/2021 18:11:32 - INFO - __main__ - Step 28075: {'lr': 0.00046267612689628046, 'samples': 5390400, 'steps': 28074, 'loss/train': 1.5743684768676758}
+08/30/2021 18:11:32 - INFO - __main__ - Step 28076: {'lr': 0.00046267333738889973, 'samples': 5390592, 'steps': 28075, 'loss/train': 1.4540815353393555}
+08/30/2021 18:11:33 - INFO - __main__ - Step 28077: {'lr': 0.00046267054778569163, 'samples': 5390784, 'steps': 28076, 'loss/train': 1.152719497680664}
+08/30/2021 18:11:33 - INFO - __main__ - Step 28078: {'lr': 0.0004626677580866574, 'samples': 5390976, 'steps': 28077, 'loss/train': 1.2343814373016357}
+08/30/2021 18:11:33 - INFO - __main__ - Step 28079: {'lr': 0.00046266496829179847, 'samples': 5391168, 'steps': 28078, 'loss/train': 1.8133282661437988}
+08/30/2021 18:11:35 - INFO - __main__ - Step 28080: {'lr': 0.0004626621784011159, 'samples': 5391360, 'steps': 28079, 'loss/train': 1.8737905025482178}
+08/30/2021 18:11:35 - INFO - __main__ - Step 28081: {'lr': 0.0004626593884146111, 'samples': 5391552, 'steps': 28080, 'loss/train': 1.972983956336975}
+08/30/2021 18:11:36 - INFO - __main__ - Step 28082: {'lr': 0.00046265659833228523, 'samples': 5391744, 'steps': 28081, 'loss/train': 1.348278522491455}
+08/30/2021 18:11:36 - INFO - __main__ - Step 28083: {'lr': 0.0004626538081541396, 'samples': 5391936, 'steps': 28082, 'loss/train': 1.663896918296814}
+08/30/2021 18:11:36 - INFO - __main__ - Step 28084: {'lr': 0.00046265101788017543, 'samples': 5392128, 'steps': 28083, 'loss/train': 1.6296148300170898}
+08/30/2021 18:11:38 - INFO - __main__ - Step 28085: {'lr': 0.00046264822751039406, 'samples': 5392320, 'steps': 28084, 'loss/train': 1.5372482538223267}
+08/30/2021 18:11:38 - INFO - __main__ - Step 28086: {'lr': 0.00046264543704479654, 'samples': 5392512, 'steps': 28085, 'loss/train': 1.3979026079177856}
+08/30/2021 18:11:38 - INFO - __main__ - Step 28087: {'lr': 0.0004626426464833844, 'samples': 5392704, 'steps': 28086, 'loss/train': 1.364237666130066}
+08/30/2021 18:11:39 - INFO - __main__ - Step 28088: {'lr': 0.0004626398558261586, 'samples': 5392896, 'steps': 28087, 'loss/train': 1.6765680313110352}
+08/30/2021 18:11:39 - INFO - __main__ - Step 28089: {'lr': 0.00046263706507312073, 'samples': 5393088, 'steps': 28088, 'loss/train': 1.1328810453414917}
+08/30/2021 18:11:41 - INFO - __main__ - Step 28090: {'lr': 0.00046263427422427183, 'samples': 5393280, 'steps': 28089, 'loss/train': 1.327867865562439}
+08/30/2021 18:11:41 - INFO - __main__ - Step 28091: {'lr': 0.00046263148327961324, 'samples': 5393472, 'steps': 28090, 'loss/train': 1.3953214883804321}
+08/30/2021 18:11:42 - INFO - __main__ - Step 28092: {'lr': 0.00046262869223914613, 'samples': 5393664, 'steps': 28091, 'loss/train': 1.0453213453292847}
+08/30/2021 18:11:42 - INFO - __main__ - Step 28093: {'lr': 0.00046262590110287183, 'samples': 5393856, 'steps': 28092, 'loss/train': 1.854308843612671}
+08/30/2021 18:11:42 - INFO - __main__ - Step 28094: {'lr': 0.00046262310987079156, 'samples': 5394048, 'steps': 28093, 'loss/train': 1.4553587436676025}
+08/30/2021 18:11:44 - INFO - __main__ - Step 28095: {'lr': 0.0004626203185429066, 'samples': 5394240, 'steps': 28094, 'loss/train': 1.2204734086990356}
+08/30/2021 18:11:45 - INFO - __main__ - Step 28096: {'lr': 0.00046261752711921825, 'samples': 5394432, 'steps': 28095, 'loss/train': 1.5668973922729492}
+08/30/2021 18:11:45 - INFO - __main__ - Step 28097: {'lr': 0.00046261473559972764, 'samples': 5394624, 'steps': 28096, 'loss/train': 1.6996465921401978}
+08/30/2021 18:11:45 - INFO - __main__ - Step 28098: {'lr': 0.00046261194398443617, 'samples': 5394816, 'steps': 28097, 'loss/train': 1.5285561084747314}
+08/30/2021 18:11:46 - INFO - __main__ - Step 28099: {'lr': 0.00046260915227334503, 'samples': 5395008, 'steps': 28098, 'loss/train': 1.1275972127914429}
+08/30/2021 18:11:47 - INFO - __main__ - Step 28100: {'lr': 0.0004626063604664555, 'samples': 5395200, 'steps': 28099, 'loss/train': 0.4824984073638916}
+08/30/2021 18:11:48 - INFO - __main__ - Step 28101: {'lr': 0.00046260356856376884, 'samples': 5395392, 'steps': 28100, 'loss/train': 1.8263745307922363}
+08/30/2021 18:11:48 - INFO - __main__ - Step 28102: {'lr': 0.0004626007765652862, 'samples': 5395584, 'steps': 28101, 'loss/train': 1.334649920463562}
+08/30/2021 18:11:48 - INFO - __main__ - Step 28103: {'lr': 0.00046259798447100903, 'samples': 5395776, 'steps': 28102, 'loss/train': 0.9247645735740662}
+08/30/2021 18:11:49 - INFO - __main__ - Step 28104: {'lr': 0.0004625951922809385, 'samples': 5395968, 'steps': 28103, 'loss/train': 1.1381335258483887}
+08/30/2021 18:11:50 - INFO - __main__ - Step 28105: {'lr': 0.0004625923999950758, 'samples': 5396160, 'steps': 28104, 'loss/train': 1.7762413024902344}
+08/30/2021 18:11:51 - INFO - __main__ - Step 28106: {'lr': 0.0004625896076134222, 'samples': 5396352, 'steps': 28105, 'loss/train': 1.751448154449463}
+08/30/2021 18:11:51 - INFO - __main__ - Step 28107: {'lr': 0.00046258681513597913, 'samples': 5396544, 'steps': 28106, 'loss/train': 1.4575424194335938}
+08/30/2021 18:11:51 - INFO - __main__ - Step 28108: {'lr': 0.0004625840225627476, 'samples': 5396736, 'steps': 28107, 'loss/train': 1.5888158082962036}
+08/30/2021 18:11:52 - INFO - __main__ - Step 28109: {'lr': 0.0004625812298937291, 'samples': 5396928, 'steps': 28108, 'loss/train': 1.4933538436889648}
+08/30/2021 18:11:53 - INFO - __main__ - Step 28110: {'lr': 0.0004625784371289247, 'samples': 5397120, 'steps': 28109, 'loss/train': 1.0874392986297607}
+08/30/2021 18:11:54 - INFO - __main__ - Step 28111: {'lr': 0.00046257564426833574, 'samples': 5397312, 'steps': 28110, 'loss/train': 2.6032867431640625}
+08/30/2021 18:11:54 - INFO - __main__ - Step 28112: {'lr': 0.0004625728513119635, 'samples': 5397504, 'steps': 28111, 'loss/train': 0.4529555141925812}
+08/30/2021 18:11:54 - INFO - __main__ - Step 28113: {'lr': 0.0004625700582598092, 'samples': 5397696, 'steps': 28112, 'loss/train': 1.5608940124511719}
+08/30/2021 18:11:55 - INFO - __main__ - Step 28114: {'lr': 0.00046256726511187407, 'samples': 5397888, 'steps': 28113, 'loss/train': 1.8138625621795654}
+08/30/2021 18:11:56 - INFO - __main__ - Step 28115: {'lr': 0.0004625644718681595, 'samples': 5398080, 'steps': 28114, 'loss/train': 1.496962070465088}
+08/30/2021 18:11:57 - INFO - __main__ - Step 28116: {'lr': 0.0004625616785286666, 'samples': 5398272, 'steps': 28115, 'loss/train': 1.181666612625122}
+08/30/2021 18:11:57 - INFO - __main__ - Step 28117: {'lr': 0.0004625588850933967, 'samples': 5398464, 'steps': 28116, 'loss/train': 1.881162166595459}
+08/30/2021 18:11:58 - INFO - __main__ - Step 28118: {'lr': 0.00046255609156235105, 'samples': 5398656, 'steps': 28117, 'loss/train': 1.7869846820831299}
+08/30/2021 18:11:58 - INFO - __main__ - Step 28119: {'lr': 0.0004625532979355309, 'samples': 5398848, 'steps': 28118, 'loss/train': 1.6022080183029175}
+08/30/2021 18:11:58 - INFO - __main__ - Step 28120: {'lr': 0.00046255050421293756, 'samples': 5399040, 'steps': 28119, 'loss/train': 1.5461374521255493}
+08/30/2021 18:12:00 - INFO - __main__ - Step 28121: {'lr': 0.0004625477103945722, 'samples': 5399232, 'steps': 28120, 'loss/train': 1.3789361715316772}
+08/30/2021 18:12:01 - INFO - __main__ - Step 28122: {'lr': 0.00046254491648043604, 'samples': 5399424, 'steps': 28121, 'loss/train': 0.5235848426818848}
+08/30/2021 18:12:01 - INFO - __main__ - Step 28123: {'lr': 0.00046254212247053055, 'samples': 5399616, 'steps': 28122, 'loss/train': 1.7202489376068115}
+08/30/2021 18:12:01 - INFO - __main__ - Step 28124: {'lr': 0.0004625393283648568, 'samples': 5399808, 'steps': 28123, 'loss/train': 1.5611282587051392}
+08/30/2021 18:12:02 - INFO - __main__ - Step 28125: {'lr': 0.0004625365341634161, 'samples': 5400000, 'steps': 28124, 'loss/train': 1.266133427619934}
+08/30/2021 18:12:03 - INFO - __main__ - Step 28126: {'lr': 0.00046253373986620985, 'samples': 5400192, 'steps': 28125, 'loss/train': 1.058297872543335}
+08/30/2021 18:12:04 - INFO - __main__ - Step 28127: {'lr': 0.00046253094547323904, 'samples': 5400384, 'steps': 28126, 'loss/train': 1.3797509670257568}
+08/30/2021 18:12:04 - INFO - __main__ - Step 28128: {'lr': 0.0004625281509845051, 'samples': 5400576, 'steps': 28127, 'loss/train': 1.6242307424545288}
+08/30/2021 18:12:04 - INFO - __main__ - Step 28129: {'lr': 0.0004625253564000092, 'samples': 5400768, 'steps': 28128, 'loss/train': 0.6565216183662415}
+08/30/2021 18:12:05 - INFO - __main__ - Step 28130: {'lr': 0.00046252256171975273, 'samples': 5400960, 'steps': 28129, 'loss/train': 1.4239695072174072}
+08/30/2021 18:12:06 - INFO - __main__ - Step 28131: {'lr': 0.0004625197669437368, 'samples': 5401152, 'steps': 28130, 'loss/train': 2.020134449005127}
+08/30/2021 18:12:07 - INFO - __main__ - Step 28132: {'lr': 0.0004625169720719628, 'samples': 5401344, 'steps': 28131, 'loss/train': 1.8320237398147583}
+08/30/2021 18:12:07 - INFO - __main__ - Step 28133: {'lr': 0.0004625141771044319, 'samples': 5401536, 'steps': 28132, 'loss/train': 1.5916252136230469}
+08/30/2021 18:12:08 - INFO - __main__ - Step 28134: {'lr': 0.0004625113820411454, 'samples': 5401728, 'steps': 28133, 'loss/train': 1.3905489444732666}
+08/30/2021 18:12:08 - INFO - __main__ - Step 28135: {'lr': 0.0004625085868821046, 'samples': 5401920, 'steps': 28134, 'loss/train': 1.620387077331543}
+08/30/2021 18:12:09 - INFO - __main__ - Step 28136: {'lr': 0.0004625057916273107, 'samples': 5402112, 'steps': 28135, 'loss/train': 1.5118495225906372}
+08/30/2021 18:12:10 - INFO - __main__ - Step 28137: {'lr': 0.00046250299627676486, 'samples': 5402304, 'steps': 28136, 'loss/train': 1.7144805192947388}
+08/30/2021 18:12:10 - INFO - __main__ - Step 28138: {'lr': 0.0004625002008304685, 'samples': 5402496, 'steps': 28137, 'loss/train': 0.9722861051559448}
+08/30/2021 18:12:11 - INFO - __main__ - Step 28139: {'lr': 0.00046249740528842286, 'samples': 5402688, 'steps': 28138, 'loss/train': 1.4861527681350708}
+08/30/2021 18:12:11 - INFO - __main__ - Step 28140: {'lr': 0.00046249460965062917, 'samples': 5402880, 'steps': 28139, 'loss/train': 0.9521327018737793}
+08/30/2021 18:12:11 - INFO - __main__ - Step 28141: {'lr': 0.0004624918139170887, 'samples': 5403072, 'steps': 28140, 'loss/train': 1.579189658164978}
+08/30/2021 18:12:13 - INFO - __main__ - Step 28142: {'lr': 0.0004624890180878027, 'samples': 5403264, 'steps': 28141, 'loss/train': 2.330486297607422}
+08/30/2021 18:12:13 - INFO - __main__ - Step 28143: {'lr': 0.00046248622216277235, 'samples': 5403456, 'steps': 28142, 'loss/train': 1.2355427742004395}
+08/30/2021 18:12:13 - INFO - __main__ - Step 28144: {'lr': 0.0004624834261419991, 'samples': 5403648, 'steps': 28143, 'loss/train': 1.6283841133117676}
+08/30/2021 18:12:14 - INFO - __main__ - Step 28145: {'lr': 0.000462480630025484, 'samples': 5403840, 'steps': 28144, 'loss/train': 0.5533981323242188}
+08/30/2021 18:12:14 - INFO - __main__ - Step 28146: {'lr': 0.0004624778338132285, 'samples': 5404032, 'steps': 28145, 'loss/train': 1.2688381671905518}
+08/30/2021 18:12:16 - INFO - __main__ - Step 28147: {'lr': 0.0004624750375052337, 'samples': 5404224, 'steps': 28146, 'loss/train': 1.3087410926818848}
+08/30/2021 18:12:17 - INFO - __main__ - Step 28148: {'lr': 0.0004624722411015009, 'samples': 5404416, 'steps': 28147, 'loss/train': 1.15404212474823}
+08/30/2021 18:12:17 - INFO - __main__ - Step 28149: {'lr': 0.0004624694446020314, 'samples': 5404608, 'steps': 28148, 'loss/train': 1.3155434131622314}
+08/30/2021 18:12:17 - INFO - __main__ - Step 28150: {'lr': 0.0004624666480068265, 'samples': 5404800, 'steps': 28149, 'loss/train': 0.2286374717950821}
+08/30/2021 18:12:18 - INFO - __main__ - Step 28151: {'lr': 0.0004624638513158874, 'samples': 5404992, 'steps': 28150, 'loss/train': 1.9606057405471802}
+08/30/2021 18:12:19 - INFO - __main__ - Step 28152: {'lr': 0.0004624610545292154, 'samples': 5405184, 'steps': 28151, 'loss/train': 1.2808737754821777}
+08/30/2021 18:12:20 - INFO - __main__ - Step 28153: {'lr': 0.00046245825764681166, 'samples': 5405376, 'steps': 28152, 'loss/train': 2.141594409942627}
+08/30/2021 18:12:20 - INFO - __main__ - Step 28154: {'lr': 0.0004624554606686775, 'samples': 5405568, 'steps': 28153, 'loss/train': 1.5030946731567383}
+08/30/2021 18:12:21 - INFO - __main__ - Step 28155: {'lr': 0.0004624526635948142, 'samples': 5405760, 'steps': 28154, 'loss/train': 0.11189009994268417}
+08/30/2021 18:12:21 - INFO - __main__ - Step 28156: {'lr': 0.000462449866425223, 'samples': 5405952, 'steps': 28155, 'loss/train': 0.05983877554535866}
+08/30/2021 18:12:21 - INFO - __main__ - Step 28157: {'lr': 0.0004624470691599052, 'samples': 5406144, 'steps': 28156, 'loss/train': 1.673291802406311}
+08/30/2021 18:12:23 - INFO - __main__ - Step 28158: {'lr': 0.00046244427179886207, 'samples': 5406336, 'steps': 28157, 'loss/train': 1.4050617218017578}
+08/30/2021 18:12:23 - INFO - __main__ - Step 28159: {'lr': 0.0004624414743420947, 'samples': 5406528, 'steps': 28158, 'loss/train': 2.366166353225708}
+08/30/2021 18:12:24 - INFO - __main__ - Step 28160: {'lr': 0.00046243867678960463, 'samples': 5406720, 'steps': 28159, 'loss/train': 1.3358148336410522}
+08/30/2021 18:12:24 - INFO - __main__ - Step 28161: {'lr': 0.00046243587914139285, 'samples': 5406912, 'steps': 28160, 'loss/train': 1.6666492223739624}
+08/30/2021 18:12:24 - INFO - __main__ - Step 28162: {'lr': 0.00046243308139746076, 'samples': 5407104, 'steps': 28161, 'loss/train': 1.4736043214797974}
+08/30/2021 18:12:26 - INFO - __main__ - Step 28163: {'lr': 0.00046243028355780967, 'samples': 5407296, 'steps': 28162, 'loss/train': 1.0821442604064941}
+08/30/2021 18:12:26 - INFO - __main__ - Step 28164: {'lr': 0.00046242748562244076, 'samples': 5407488, 'steps': 28163, 'loss/train': 0.5729638934135437}
+08/30/2021 18:12:27 - INFO - __main__ - Step 28165: {'lr': 0.00046242468759135523, 'samples': 5407680, 'steps': 28164, 'loss/train': 1.7088289260864258}
+08/30/2021 18:12:27 - INFO - __main__ - Step 28166: {'lr': 0.00046242188946455444, 'samples': 5407872, 'steps': 28165, 'loss/train': 1.187338948249817}
+08/30/2021 18:12:28 - INFO - __main__ - Step 28167: {'lr': 0.0004624190912420397, 'samples': 5408064, 'steps': 28166, 'loss/train': 1.3360848426818848}
+08/30/2021 18:12:29 - INFO - __main__ - Step 28168: {'lr': 0.0004624162929238121, 'samples': 5408256, 'steps': 28167, 'loss/train': 1.753943920135498}
+08/30/2021 18:12:30 - INFO - __main__ - Step 28169: {'lr': 0.000462413494509873, 'samples': 5408448, 'steps': 28168, 'loss/train': 1.607373833656311}
+08/30/2021 18:12:30 - INFO - __main__ - Step 28170: {'lr': 0.0004624106960002237, 'samples': 5408640, 'steps': 28169, 'loss/train': 1.3224910497665405}
+08/30/2021 18:12:30 - INFO - __main__ - Step 28171: {'lr': 0.0004624078973948654, 'samples': 5408832, 'steps': 28170, 'loss/train': 0.07940766960382462}
+08/30/2021 18:12:31 - INFO - __main__ - Step 28172: {'lr': 0.00046240509869379943, 'samples': 5409024, 'steps': 28171, 'loss/train': 1.4734846353530884}
+08/30/2021 18:12:31 - INFO - __main__ - Step 28173: {'lr': 0.00046240229989702697, 'samples': 5409216, 'steps': 28172, 'loss/train': 1.5718226432800293}
+08/30/2021 18:12:33 - INFO - __main__ - Step 28174: {'lr': 0.0004623995010045493, 'samples': 5409408, 'steps': 28173, 'loss/train': 1.8593250513076782}
+08/30/2021 18:12:34 - INFO - __main__ - Step 28175: {'lr': 0.0004623967020163677, 'samples': 5409600, 'steps': 28174, 'loss/train': 1.6550480127334595}
+08/30/2021 18:12:34 - INFO - __main__ - Step 28176: {'lr': 0.0004623939029324834, 'samples': 5409792, 'steps': 28175, 'loss/train': 1.3389935493469238}
+08/30/2021 18:12:34 - INFO - __main__ - Step 28177: {'lr': 0.0004623911037528977, 'samples': 5409984, 'steps': 28176, 'loss/train': 1.6478055715560913}
+08/30/2021 18:12:35 - INFO - __main__ - Step 28178: {'lr': 0.00046238830447761184, 'samples': 5410176, 'steps': 28177, 'loss/train': 1.7442591190338135}
+08/30/2021 18:12:35 - INFO - __main__ - Step 28179: {'lr': 0.0004623855051066271, 'samples': 5410368, 'steps': 28178, 'loss/train': 1.2677836418151855}
+08/30/2021 18:12:37 - INFO - __main__ - Step 28180: {'lr': 0.00046238270563994465, 'samples': 5410560, 'steps': 28179, 'loss/train': 1.6171486377716064}
+08/30/2021 18:12:38 - INFO - __main__ - Step 28181: {'lr': 0.00046237990607756596, 'samples': 5410752, 'steps': 28180, 'loss/train': 1.4700666666030884}
+08/30/2021 18:12:38 - INFO - __main__ - Step 28182: {'lr': 0.0004623771064194921, 'samples': 5410944, 'steps': 28181, 'loss/train': 0.5983209609985352}
+08/30/2021 18:12:38 - INFO - __main__ - Step 28183: {'lr': 0.0004623743066657244, 'samples': 5411136, 'steps': 28182, 'loss/train': 0.4780607223510742}
+08/30/2021 18:12:39 - INFO - __main__ - Step 28184: {'lr': 0.00046237150681626414, 'samples': 5411328, 'steps': 28183, 'loss/train': 0.4769774377346039}
+08/30/2021 18:12:39 - INFO - __main__ - Step 28185: {'lr': 0.00046236870687111254, 'samples': 5411520, 'steps': 28184, 'loss/train': 1.4490569829940796}
+08/30/2021 18:12:41 - INFO - __main__ - Step 28186: {'lr': 0.0004623659068302708, 'samples': 5411712, 'steps': 28185, 'loss/train': 0.22667363286018372}
+08/30/2021 18:12:41 - INFO - __main__ - Step 28187: {'lr': 0.00046236310669374035, 'samples': 5411904, 'steps': 28186, 'loss/train': 2.009615898132324}
+08/30/2021 18:12:41 - INFO - __main__ - Step 28188: {'lr': 0.0004623603064615223, 'samples': 5412096, 'steps': 28187, 'loss/train': 0.99207603931427}
+08/30/2021 18:12:42 - INFO - __main__ - Step 28189: {'lr': 0.000462357506133618, 'samples': 5412288, 'steps': 28188, 'loss/train': 1.8395366668701172}
+08/30/2021 18:12:42 - INFO - __main__ - Step 28190: {'lr': 0.00046235470571002877, 'samples': 5412480, 'steps': 28189, 'loss/train': 1.4065794944763184}
+08/30/2021 18:12:42 - INFO - __main__ - Step 28191: {'lr': 0.00046235190519075564, 'samples': 5412672, 'steps': 28190, 'loss/train': 1.8146851062774658}
+08/30/2021 18:12:44 - INFO - __main__ - Step 28192: {'lr': 0.00046234910457580014, 'samples': 5412864, 'steps': 28191, 'loss/train': 1.6898690462112427}
+08/30/2021 18:12:45 - INFO - __main__ - Step 28193: {'lr': 0.0004623463038651633, 'samples': 5413056, 'steps': 28192, 'loss/train': 0.153415709733963}
+08/30/2021 18:12:45 - INFO - __main__ - Step 28194: {'lr': 0.0004623435030588466, 'samples': 5413248, 'steps': 28193, 'loss/train': 1.0885311365127563}
+08/30/2021 18:12:45 - INFO - __main__ - Step 28195: {'lr': 0.00046234070215685116, 'samples': 5413440, 'steps': 28194, 'loss/train': 1.56862473487854}
+08/30/2021 18:12:46 - INFO - __main__ - Step 28196: {'lr': 0.0004623379011591782, 'samples': 5413632, 'steps': 28195, 'loss/train': 0.537412703037262}
+08/30/2021 18:12:47 - INFO - __main__ - Step 28197: {'lr': 0.00046233510006582913, 'samples': 5413824, 'steps': 28196, 'loss/train': 1.6278892755508423}
+08/30/2021 18:12:48 - INFO - __main__ - Step 28198: {'lr': 0.00046233229887680517, 'samples': 5414016, 'steps': 28197, 'loss/train': 2.501605749130249}
+08/30/2021 18:12:48 - INFO - __main__ - Step 28199: {'lr': 0.00046232949759210753, 'samples': 5414208, 'steps': 28198, 'loss/train': 1.147364854812622}
+08/30/2021 18:12:48 - INFO - __main__ - Step 28200: {'lr': 0.00046232669621173745, 'samples': 5414400, 'steps': 28199, 'loss/train': 1.6096371412277222}
+08/30/2021 18:12:49 - INFO - __main__ - Step 28201: {'lr': 0.00046232389473569623, 'samples': 5414592, 'steps': 28200, 'loss/train': 1.3819606304168701}
+08/30/2021 18:12:50 - INFO - __main__ - Step 28202: {'lr': 0.0004623210931639852, 'samples': 5414784, 'steps': 28201, 'loss/train': 2.25793719291687}
+08/30/2021 18:12:51 - INFO - __main__ - Step 28203: {'lr': 0.00046231829149660553, 'samples': 5414976, 'steps': 28202, 'loss/train': 1.1932913064956665}
+08/30/2021 18:12:51 - INFO - __main__ - Step 28204: {'lr': 0.00046231548973355854, 'samples': 5415168, 'steps': 28203, 'loss/train': 1.3090009689331055}
+08/30/2021 18:12:51 - INFO - __main__ - Step 28205: {'lr': 0.00046231268787484545, 'samples': 5415360, 'steps': 28204, 'loss/train': 2.3537867069244385}
+08/30/2021 18:12:52 - INFO - __main__ - Step 28206: {'lr': 0.0004623098859204675, 'samples': 5415552, 'steps': 28205, 'loss/train': 1.8150583505630493}
+08/30/2021 18:12:53 - INFO - __main__ - Step 28207: {'lr': 0.00046230708387042603, 'samples': 5415744, 'steps': 28206, 'loss/train': 1.7018022537231445}
+08/30/2021 18:12:54 - INFO - __main__ - Step 28208: {'lr': 0.0004623042817247223, 'samples': 5415936, 'steps': 28207, 'loss/train': 1.6013038158416748}
+08/30/2021 18:12:54 - INFO - __main__ - Step 28209: {'lr': 0.00046230147948335746, 'samples': 5416128, 'steps': 28208, 'loss/train': 1.664321780204773}
+08/30/2021 18:12:54 - INFO - __main__ - Step 28210: {'lr': 0.0004622986771463329, 'samples': 5416320, 'steps': 28209, 'loss/train': 1.4428523778915405}
+08/30/2021 18:12:55 - INFO - __main__ - Step 28211: {'lr': 0.0004622958747136498, 'samples': 5416512, 'steps': 28210, 'loss/train': 1.4926539659500122}
+08/30/2021 18:12:56 - INFO - __main__ - Step 28212: {'lr': 0.00046229307218530945, 'samples': 5416704, 'steps': 28211, 'loss/train': 1.5020993947982788}
+08/30/2021 18:12:57 - INFO - __main__ - Step 28213: {'lr': 0.0004622902695613131, 'samples': 5416896, 'steps': 28212, 'loss/train': 1.1484891176223755}
+08/30/2021 18:12:57 - INFO - __main__ - Step 28214: {'lr': 0.00046228746684166214, 'samples': 5417088, 'steps': 28213, 'loss/train': 1.8509457111358643}
+08/30/2021 18:12:57 - INFO - __main__ - Step 28215: {'lr': 0.00046228466402635764, 'samples': 5417280, 'steps': 28214, 'loss/train': 1.9831180572509766}
+08/30/2021 18:12:58 - INFO - __main__ - Step 28216: {'lr': 0.0004622818611154009, 'samples': 5417472, 'steps': 28215, 'loss/train': 1.021217942237854}
+08/30/2021 18:12:58 - INFO - __main__ - Step 28217: {'lr': 0.00046227905810879334, 'samples': 5417664, 'steps': 28216, 'loss/train': 0.9175899028778076}
+08/30/2021 18:13:00 - INFO - __main__ - Step 28218: {'lr': 0.0004622762550065361, 'samples': 5417856, 'steps': 28217, 'loss/train': 1.1760281324386597}
+08/30/2021 18:13:00 - INFO - __main__ - Step 28219: {'lr': 0.0004622734518086304, 'samples': 5418048, 'steps': 28218, 'loss/train': 1.3560354709625244}
+08/30/2021 18:13:01 - INFO - __main__ - Step 28220: {'lr': 0.0004622706485150776, 'samples': 5418240, 'steps': 28219, 'loss/train': 1.9772204160690308}
+08/30/2021 18:13:01 - INFO - __main__ - Step 28221: {'lr': 0.0004622678451258788, 'samples': 5418432, 'steps': 28220, 'loss/train': 2.1146113872528076}
+08/30/2021 18:13:01 - INFO - __main__ - Step 28222: {'lr': 0.00046226504164103557, 'samples': 5418624, 'steps': 28221, 'loss/train': 1.2535582780838013}
+08/30/2021 18:13:03 - INFO - __main__ - Step 28223: {'lr': 0.0004622622380605489, 'samples': 5418816, 'steps': 28222, 'loss/train': 0.22345010936260223}
+08/30/2021 18:13:03 - INFO - __main__ - Step 28224: {'lr': 0.0004622594343844201, 'samples': 5419008, 'steps': 28223, 'loss/train': 1.1060556173324585}
+08/30/2021 18:13:04 - INFO - __main__ - Step 28225: {'lr': 0.00046225663061265056, 'samples': 5419200, 'steps': 28224, 'loss/train': 1.5601060390472412}
+08/30/2021 18:13:04 - INFO - __main__ - Step 28226: {'lr': 0.0004622538267452414, 'samples': 5419392, 'steps': 28225, 'loss/train': 1.9933298826217651}
+08/30/2021 18:13:04 - INFO - __main__ - Step 28227: {'lr': 0.00046225102278219394, 'samples': 5419584, 'steps': 28226, 'loss/train': 1.4421290159225464}
+08/30/2021 18:13:07 - INFO - __main__ - Step 28228: {'lr': 0.0004622482187235094, 'samples': 5419776, 'steps': 28227, 'loss/train': 1.6272094249725342}
+08/30/2021 18:13:07 - INFO - __main__ - Step 28229: {'lr': 0.00046224541456918916, 'samples': 5419968, 'steps': 28228, 'loss/train': 1.554030418395996}
+08/30/2021 18:13:07 - INFO - __main__ - Step 28230: {'lr': 0.0004622426103192344, 'samples': 5420160, 'steps': 28229, 'loss/train': 1.3759022951126099}
+08/30/2021 18:13:08 - INFO - __main__ - Step 28231: {'lr': 0.00046223980597364647, 'samples': 5420352, 'steps': 28230, 'loss/train': 1.3608697652816772}
+08/30/2021 18:13:08 - INFO - __main__ - Step 28232: {'lr': 0.0004622370015324264, 'samples': 5420544, 'steps': 28231, 'loss/train': 2.0276691913604736}
+08/30/2021 18:13:08 - INFO - __main__ - Step 28233: {'lr': 0.0004622341969955757, 'samples': 5420736, 'steps': 28232, 'loss/train': 1.8577359914779663}
+08/30/2021 18:13:10 - INFO - __main__ - Step 28234: {'lr': 0.00046223139236309553, 'samples': 5420928, 'steps': 28233, 'loss/train': 0.9461192488670349}
+08/30/2021 18:13:11 - INFO - __main__ - Step 28235: {'lr': 0.0004622285876349872, 'samples': 5421120, 'steps': 28234, 'loss/train': 0.7482120990753174}
+08/30/2021 18:13:11 - INFO - __main__ - Step 28236: {'lr': 0.00046222578281125194, 'samples': 5421312, 'steps': 28235, 'loss/train': 1.4742566347122192}
+08/30/2021 18:13:11 - INFO - __main__ - Step 28237: {'lr': 0.0004622229778918909, 'samples': 5421504, 'steps': 28236, 'loss/train': 0.9649300575256348}
+08/30/2021 18:13:12 - INFO - __main__ - Step 28238: {'lr': 0.00046222017287690566, 'samples': 5421696, 'steps': 28237, 'loss/train': 1.6385213136672974}
+08/30/2021 18:13:14 - INFO - __main__ - Step 28239: {'lr': 0.00046221736776629713, 'samples': 5421888, 'steps': 28238, 'loss/train': 1.564038872718811}
+08/30/2021 18:13:14 - INFO - __main__ - Step 28240: {'lr': 0.0004622145625600668, 'samples': 5422080, 'steps': 28239, 'loss/train': 1.3118025064468384}
+08/30/2021 18:13:15 - INFO - __main__ - Step 28241: {'lr': 0.00046221175725821585, 'samples': 5422272, 'steps': 28240, 'loss/train': 1.225050687789917}
+08/30/2021 18:13:15 - INFO - __main__ - Step 28242: {'lr': 0.00046220895186074553, 'samples': 5422464, 'steps': 28241, 'loss/train': 1.1002739667892456}
+08/30/2021 18:13:15 - INFO - __main__ - Step 28243: {'lr': 0.0004622061463676572, 'samples': 5422656, 'steps': 28242, 'loss/train': 1.6412336826324463}
+08/30/2021 18:13:16 - INFO - __main__ - Step 28244: {'lr': 0.000462203340778952, 'samples': 5422848, 'steps': 28243, 'loss/train': 1.8457484245300293}
+08/30/2021 18:13:16 - INFO - __main__ - Step 28245: {'lr': 0.0004622005350946312, 'samples': 5423040, 'steps': 28244, 'loss/train': 0.09960411489009857}
+08/30/2021 18:13:17 - INFO - __main__ - Step 28246: {'lr': 0.00046219772931469617, 'samples': 5423232, 'steps': 28245, 'loss/train': 1.8270965814590454}
+08/30/2021 18:13:18 - INFO - __main__ - Step 28247: {'lr': 0.00046219492343914815, 'samples': 5423424, 'steps': 28246, 'loss/train': 1.3844245672225952}
+08/30/2021 18:13:18 - INFO - __main__ - Step 28248: {'lr': 0.00046219211746798835, 'samples': 5423616, 'steps': 28247, 'loss/train': 1.5090340375900269}
+08/30/2021 18:13:19 - INFO - __main__ - Step 28249: {'lr': 0.000462189311401218, 'samples': 5423808, 'steps': 28248, 'loss/train': 1.3838329315185547}
+08/30/2021 18:13:20 - INFO - __main__ - Step 28250: {'lr': 0.0004621865052388385, 'samples': 5424000, 'steps': 28249, 'loss/train': 1.3188226222991943}
+08/30/2021 18:13:20 - INFO - __main__ - Step 28251: {'lr': 0.00046218369898085097, 'samples': 5424192, 'steps': 28250, 'loss/train': 0.8289266228675842}
+08/30/2021 18:13:21 - INFO - __main__ - Step 28252: {'lr': 0.0004621808926272568, 'samples': 5424384, 'steps': 28251, 'loss/train': 1.43550705909729}
+08/30/2021 18:13:21 - INFO - __main__ - Step 28253: {'lr': 0.0004621780861780572, 'samples': 5424576, 'steps': 28252, 'loss/train': 1.619834303855896}
+08/30/2021 18:13:21 - INFO - __main__ - Step 28254: {'lr': 0.00046217527963325335, 'samples': 5424768, 'steps': 28253, 'loss/train': 1.370830774307251}
+08/30/2021 18:13:22 - INFO - __main__ - Step 28255: {'lr': 0.00046217247299284666, 'samples': 5424960, 'steps': 28254, 'loss/train': 1.5683119297027588}
+08/30/2021 18:13:23 - INFO - __main__ - Step 28256: {'lr': 0.00046216966625683834, 'samples': 5425152, 'steps': 28255, 'loss/train': 1.78057861328125}
+08/30/2021 18:13:24 - INFO - __main__ - Step 28257: {'lr': 0.00046216685942522957, 'samples': 5425344, 'steps': 28256, 'loss/train': 1.5489559173583984}
+08/30/2021 18:13:24 - INFO - __main__ - Step 28258: {'lr': 0.00046216405249802176, 'samples': 5425536, 'steps': 28257, 'loss/train': 0.8627528548240662}
+08/30/2021 18:13:25 - INFO - __main__ - Step 28259: {'lr': 0.000462161245475216, 'samples': 5425728, 'steps': 28258, 'loss/train': 1.8499099016189575}
+08/30/2021 18:13:25 - INFO - __main__ - Step 28260: {'lr': 0.0004621584383568137, 'samples': 5425920, 'steps': 28259, 'loss/train': 1.62791907787323}
+08/30/2021 18:13:27 - INFO - __main__ - Step 28261: {'lr': 0.00046215563114281613, 'samples': 5426112, 'steps': 28260, 'loss/train': 1.87300443649292}
+08/30/2021 18:13:27 - INFO - __main__ - Step 28262: {'lr': 0.0004621528238332245, 'samples': 5426304, 'steps': 28261, 'loss/train': 1.4125200510025024}
+08/30/2021 18:13:28 - INFO - __main__ - Step 28263: {'lr': 0.00046215001642804, 'samples': 5426496, 'steps': 28262, 'loss/train': 1.8862314224243164}
+08/30/2021 18:13:28 - INFO - __main__ - Step 28264: {'lr': 0.0004621472089272641, 'samples': 5426688, 'steps': 28263, 'loss/train': 1.7736948728561401}
+08/30/2021 18:13:28 - INFO - __main__ - Step 28265: {'lr': 0.0004621444013308979, 'samples': 5426880, 'steps': 28264, 'loss/train': 0.8786599636077881}
+08/30/2021 18:13:30 - INFO - __main__ - Step 28266: {'lr': 0.00046214159363894264, 'samples': 5427072, 'steps': 28265, 'loss/train': 1.8863425254821777}
+08/30/2021 18:13:30 - INFO - __main__ - Step 28267: {'lr': 0.0004621387858513997, 'samples': 5427264, 'steps': 28266, 'loss/train': 1.5940356254577637}
+08/30/2021 18:13:31 - INFO - __main__ - Step 28268: {'lr': 0.0004621359779682703, 'samples': 5427456, 'steps': 28267, 'loss/train': 1.152202844619751}
+08/30/2021 18:13:31 - INFO - __main__ - Step 28269: {'lr': 0.0004621331699895557, 'samples': 5427648, 'steps': 28268, 'loss/train': 1.841621994972229}
+08/30/2021 18:13:31 - INFO - __main__ - Step 28270: {'lr': 0.00046213036191525714, 'samples': 5427840, 'steps': 28269, 'loss/train': 1.209489107131958}
+08/30/2021 18:13:33 - INFO - __main__ - Step 28271: {'lr': 0.00046212755374537594, 'samples': 5428032, 'steps': 28270, 'loss/train': 2.1603636741638184}
+08/30/2021 18:13:34 - INFO - __main__ - Step 28272: {'lr': 0.0004621247454799133, 'samples': 5428224, 'steps': 28271, 'loss/train': 2.1762497425079346}
+08/30/2021 18:13:34 - INFO - __main__ - Step 28273: {'lr': 0.0004621219371188706, 'samples': 5428416, 'steps': 28272, 'loss/train': 1.7961615324020386}
+08/30/2021 18:13:34 - INFO - __main__ - Step 28274: {'lr': 0.0004621191286622489, 'samples': 5428608, 'steps': 28273, 'loss/train': 1.6145116090774536}
+08/30/2021 18:13:35 - INFO - __main__ - Step 28275: {'lr': 0.00046211632011004973, 'samples': 5428800, 'steps': 28274, 'loss/train': 1.9258496761322021}
+08/30/2021 18:13:35 - INFO - __main__ - Step 28276: {'lr': 0.0004621135114622742, 'samples': 5428992, 'steps': 28275, 'loss/train': 1.7441402673721313}
+08/30/2021 18:13:37 - INFO - __main__ - Step 28277: {'lr': 0.00046211070271892353, 'samples': 5429184, 'steps': 28276, 'loss/train': 1.7774789333343506}
+08/30/2021 18:13:37 - INFO - __main__ - Step 28278: {'lr': 0.00046210789387999906, 'samples': 5429376, 'steps': 28277, 'loss/train': 1.2015700340270996}
+08/30/2021 18:13:37 - INFO - __main__ - Step 28279: {'lr': 0.00046210508494550206, 'samples': 5429568, 'steps': 28278, 'loss/train': 1.683435082435608}
+08/30/2021 18:13:38 - INFO - __main__ - Step 28280: {'lr': 0.0004621022759154338, 'samples': 5429760, 'steps': 28279, 'loss/train': 1.4273407459259033}
+08/30/2021 18:13:38 - INFO - __main__ - Step 28281: {'lr': 0.0004620994667897955, 'samples': 5429952, 'steps': 28280, 'loss/train': 1.6851435899734497}
+08/30/2021 18:13:40 - INFO - __main__ - Step 28282: {'lr': 0.0004620966575685885, 'samples': 5430144, 'steps': 28281, 'loss/train': 1.733172059059143}
+08/30/2021 18:13:40 - INFO - __main__ - Step 28283: {'lr': 0.000462093848251814, 'samples': 5430336, 'steps': 28282, 'loss/train': 2.0656027793884277}
+08/30/2021 18:13:40 - INFO - __main__ - Step 28284: {'lr': 0.00046209103883947323, 'samples': 5430528, 'steps': 28283, 'loss/train': 2.0980305671691895}
+08/30/2021 18:13:41 - INFO - __main__ - Step 28285: {'lr': 0.00046208822933156756, 'samples': 5430720, 'steps': 28284, 'loss/train': 0.9545504450798035}
+08/30/2021 18:13:41 - INFO - __main__ - Step 28286: {'lr': 0.00046208541972809824, 'samples': 5430912, 'steps': 28285, 'loss/train': 1.118975281715393}
+08/30/2021 18:13:43 - INFO - __main__ - Step 28287: {'lr': 0.00046208261002906643, 'samples': 5431104, 'steps': 28286, 'loss/train': 1.6077806949615479}
+08/30/2021 18:13:44 - INFO - __main__ - Step 28288: {'lr': 0.00046207980023447347, 'samples': 5431296, 'steps': 28287, 'loss/train': 1.4952181577682495}
+08/30/2021 18:13:44 - INFO - __main__ - Step 28289: {'lr': 0.0004620769903443207, 'samples': 5431488, 'steps': 28288, 'loss/train': 1.4617315530776978}
+08/30/2021 18:13:44 - INFO - __main__ - Step 28290: {'lr': 0.00046207418035860927, 'samples': 5431680, 'steps': 28289, 'loss/train': 1.4859063625335693}
+08/30/2021 18:13:45 - INFO - __main__ - Step 28291: {'lr': 0.00046207137027734046, 'samples': 5431872, 'steps': 28290, 'loss/train': 1.8514564037322998}
+08/30/2021 18:13:47 - INFO - __main__ - Step 28292: {'lr': 0.00046206856010051555, 'samples': 5432064, 'steps': 28291, 'loss/train': 2.224961757659912}
+08/30/2021 18:13:47 - INFO - __main__ - Step 28293: {'lr': 0.0004620657498281359, 'samples': 5432256, 'steps': 28292, 'loss/train': 0.8435643911361694}
+08/30/2021 18:13:47 - INFO - __main__ - Step 28294: {'lr': 0.0004620629394602027, 'samples': 5432448, 'steps': 28293, 'loss/train': 1.0814980268478394}
+08/30/2021 18:13:48 - INFO - __main__ - Step 28295: {'lr': 0.00046206012899671715, 'samples': 5432640, 'steps': 28294, 'loss/train': 1.6488440036773682}
+08/30/2021 18:13:48 - INFO - __main__ - Step 28296: {'lr': 0.00046205731843768056, 'samples': 5432832, 'steps': 28295, 'loss/train': 0.16759580373764038}
+08/30/2021 18:13:48 - INFO - __main__ - Step 28297: {'lr': 0.0004620545077830942, 'samples': 5433024, 'steps': 28296, 'loss/train': 1.2041758298873901}
+08/30/2021 18:13:50 - INFO - __main__ - Step 28298: {'lr': 0.00046205169703295945, 'samples': 5433216, 'steps': 28297, 'loss/train': 0.05389319732785225}
+08/30/2021 18:13:50 - INFO - __main__ - Step 28299: {'lr': 0.00046204888618727743, 'samples': 5433408, 'steps': 28298, 'loss/train': 1.9713691473007202}
+08/30/2021 18:13:51 - INFO - __main__ - Step 28300: {'lr': 0.00046204607524604944, 'samples': 5433600, 'steps': 28299, 'loss/train': 1.9003307819366455}
+08/30/2021 18:13:51 - INFO - __main__ - Step 28301: {'lr': 0.0004620432642092768, 'samples': 5433792, 'steps': 28300, 'loss/train': 1.5967423915863037}
+08/30/2021 18:13:51 - INFO - __main__ - Step 28302: {'lr': 0.00046204045307696065, 'samples': 5433984, 'steps': 28301, 'loss/train': 1.4647635221481323}
+08/30/2021 18:13:53 - INFO - __main__ - Step 28303: {'lr': 0.0004620376418491024, 'samples': 5434176, 'steps': 28302, 'loss/train': 1.2555168867111206}
+08/30/2021 18:13:53 - INFO - __main__ - Step 28304: {'lr': 0.0004620348305257033, 'samples': 5434368, 'steps': 28303, 'loss/train': 1.426172137260437}
+08/30/2021 18:13:54 - INFO - __main__ - Step 28305: {'lr': 0.00046203201910676453, 'samples': 5434560, 'steps': 28304, 'loss/train': 2.701510429382324}
+08/30/2021 18:13:54 - INFO - __main__ - Step 28306: {'lr': 0.0004620292075922874, 'samples': 5434752, 'steps': 28305, 'loss/train': 0.5252964496612549}
+08/30/2021 18:13:55 - INFO - __main__ - Step 28307: {'lr': 0.0004620263959822732, 'samples': 5434944, 'steps': 28306, 'loss/train': 1.3321943283081055}
+08/30/2021 18:13:56 - INFO - __main__ - Step 28308: {'lr': 0.00046202358427672313, 'samples': 5435136, 'steps': 28307, 'loss/train': 1.5458296537399292}
+08/30/2021 18:13:56 - INFO - __main__ - Step 28309: {'lr': 0.0004620207724756386, 'samples': 5435328, 'steps': 28308, 'loss/train': 2.0445430278778076}
+08/30/2021 18:13:57 - INFO - __main__ - Step 28310: {'lr': 0.0004620179605790207, 'samples': 5435520, 'steps': 28309, 'loss/train': 1.6305828094482422}
+08/30/2021 18:13:57 - INFO - __main__ - Step 28311: {'lr': 0.00046201514858687075, 'samples': 5435712, 'steps': 28310, 'loss/train': 1.4723097085952759}
+08/30/2021 18:13:57 - INFO - __main__ - Step 28312: {'lr': 0.00046201233649919015, 'samples': 5435904, 'steps': 28311, 'loss/train': 1.7970898151397705}
+08/30/2021 18:13:58 - INFO - __main__ - Step 28313: {'lr': 0.00046200952431598, 'samples': 5436096, 'steps': 28312, 'loss/train': 1.403132438659668}
+08/30/2021 18:13:59 - INFO - __main__ - Step 28314: {'lr': 0.00046200671203724166, 'samples': 5436288, 'steps': 28313, 'loss/train': 1.559372067451477}
+08/30/2021 18:14:00 - INFO - __main__ - Step 28315: {'lr': 0.00046200389966297633, 'samples': 5436480, 'steps': 28314, 'loss/train': 1.3774646520614624}
+08/30/2021 18:14:00 - INFO - __main__ - Step 28316: {'lr': 0.00046200108719318537, 'samples': 5436672, 'steps': 28315, 'loss/train': 1.62782883644104}
+08/30/2021 18:14:01 - INFO - __main__ - Step 28317: {'lr': 0.0004619982746278699, 'samples': 5436864, 'steps': 28316, 'loss/train': 1.450161099433899}
+08/30/2021 18:14:01 - INFO - __main__ - Step 28318: {'lr': 0.00046199546196703134, 'samples': 5437056, 'steps': 28317, 'loss/train': 1.4043141603469849}
+08/30/2021 18:14:02 - INFO - __main__ - Step 28319: {'lr': 0.0004619926492106709, 'samples': 5437248, 'steps': 28318, 'loss/train': 1.6663156747817993}
+08/30/2021 18:14:03 - INFO - __main__ - Step 28320: {'lr': 0.0004619898363587899, 'samples': 5437440, 'steps': 28319, 'loss/train': 1.7252740859985352}
+08/30/2021 18:14:03 - INFO - __main__ - Step 28321: {'lr': 0.00046198702341138944, 'samples': 5437632, 'steps': 28320, 'loss/train': 1.3548163175582886}
+08/30/2021 18:14:04 - INFO - __main__ - Step 28322: {'lr': 0.00046198421036847093, 'samples': 5437824, 'steps': 28321, 'loss/train': 1.4695861339569092}
+08/30/2021 18:14:04 - INFO - __main__ - Step 28323: {'lr': 0.00046198139723003563, 'samples': 5438016, 'steps': 28322, 'loss/train': 1.5358189344406128}
+08/30/2021 18:14:05 - INFO - __main__ - Step 28324: {'lr': 0.00046197858399608477, 'samples': 5438208, 'steps': 28323, 'loss/train': 1.2871755361557007}
+08/30/2021 18:14:06 - INFO - __main__ - Step 28325: {'lr': 0.00046197577066661965, 'samples': 5438400, 'steps': 28324, 'loss/train': 1.3666163682937622}
+08/30/2021 18:14:06 - INFO - __main__ - Step 28326: {'lr': 0.0004619729572416415, 'samples': 5438592, 'steps': 28325, 'loss/train': 2.72617244720459}
+08/30/2021 18:14:07 - INFO - __main__ - Step 28327: {'lr': 0.0004619701437211516, 'samples': 5438784, 'steps': 28326, 'loss/train': 1.4934099912643433}
+08/30/2021 18:14:07 - INFO - __main__ - Step 28328: {'lr': 0.00046196733010515125, 'samples': 5438976, 'steps': 28327, 'loss/train': 1.6686969995498657}
+08/30/2021 18:14:08 - INFO - __main__ - Step 28329: {'lr': 0.0004619645163936417, 'samples': 5439168, 'steps': 28328, 'loss/train': 1.957667350769043}
+08/30/2021 18:14:09 - INFO - __main__ - Step 28330: {'lr': 0.0004619617025866242, 'samples': 5439360, 'steps': 28329, 'loss/train': 1.5146355628967285}
+08/30/2021 18:14:09 - INFO - __main__ - Step 28331: {'lr': 0.00046195888868409994, 'samples': 5439552, 'steps': 28330, 'loss/train': 1.9308141469955444}
+08/30/2021 18:14:10 - INFO - __main__ - Step 28332: {'lr': 0.0004619560746860704, 'samples': 5439744, 'steps': 28331, 'loss/train': 1.9257309436798096}
+08/30/2021 18:14:10 - INFO - __main__ - Step 28333: {'lr': 0.0004619532605925366, 'samples': 5439936, 'steps': 28332, 'loss/train': 1.0161665678024292}
+08/30/2021 18:14:10 - INFO - __main__ - Step 28334: {'lr': 0.00046195044640350003, 'samples': 5440128, 'steps': 28333, 'loss/train': 1.4778785705566406}
+08/30/2021 18:14:12 - INFO - __main__ - Step 28335: {'lr': 0.00046194763211896187, 'samples': 5440320, 'steps': 28334, 'loss/train': 1.8597382307052612}
+08/30/2021 18:14:12 - INFO - __main__ - Step 28336: {'lr': 0.0004619448177389233, 'samples': 5440512, 'steps': 28335, 'loss/train': 1.4075936079025269}
+08/30/2021 18:14:13 - INFO - __main__ - Step 28337: {'lr': 0.0004619420032633857, 'samples': 5440704, 'steps': 28336, 'loss/train': 2.8559982776641846}
+08/30/2021 18:14:13 - INFO - __main__ - Step 28338: {'lr': 0.0004619391886923503, 'samples': 5440896, 'steps': 28337, 'loss/train': 1.4946178197860718}
+08/30/2021 18:14:13 - INFO - __main__ - Step 28339: {'lr': 0.0004619363740258184, 'samples': 5441088, 'steps': 28338, 'loss/train': 0.7726243138313293}
+08/30/2021 18:14:15 - INFO - __main__ - Step 28340: {'lr': 0.00046193355926379124, 'samples': 5441280, 'steps': 28339, 'loss/train': 1.4866501092910767}
+08/30/2021 18:14:16 - INFO - __main__ - Step 28341: {'lr': 0.00046193074440627, 'samples': 5441472, 'steps': 28340, 'loss/train': 1.4543671607971191}
+08/30/2021 18:14:16 - INFO - __main__ - Step 28342: {'lr': 0.0004619279294532561, 'samples': 5441664, 'steps': 28341, 'loss/train': 1.950999140739441}
+08/30/2021 18:14:16 - INFO - __main__ - Step 28343: {'lr': 0.00046192511440475083, 'samples': 5441856, 'steps': 28342, 'loss/train': 1.2707509994506836}
+08/30/2021 18:14:17 - INFO - __main__ - Step 28344: {'lr': 0.00046192229926075526, 'samples': 5442048, 'steps': 28343, 'loss/train': 1.6523293256759644}
+08/30/2021 18:14:18 - INFO - __main__ - Step 28345: {'lr': 0.0004619194840212708, 'samples': 5442240, 'steps': 28344, 'loss/train': 1.6364619731903076}
+08/30/2021 18:14:19 - INFO - __main__ - Step 28346: {'lr': 0.0004619166686862987, 'samples': 5442432, 'steps': 28345, 'loss/train': 1.5701013803482056}
+08/30/2021 18:14:19 - INFO - __main__ - Step 28347: {'lr': 0.0004619138532558402, 'samples': 5442624, 'steps': 28346, 'loss/train': 1.5248124599456787}
+08/30/2021 18:14:19 - INFO - __main__ - Step 28348: {'lr': 0.00046191103772989664, 'samples': 5442816, 'steps': 28347, 'loss/train': 1.0147887468338013}
+08/30/2021 18:14:20 - INFO - __main__ - Step 28349: {'lr': 0.00046190822210846917, 'samples': 5443008, 'steps': 28348, 'loss/train': 1.3319716453552246}
+08/30/2021 18:14:21 - INFO - __main__ - Step 28350: {'lr': 0.0004619054063915592, 'samples': 5443200, 'steps': 28349, 'loss/train': 1.3324525356292725}
+08/30/2021 18:14:22 - INFO - __main__ - Step 28351: {'lr': 0.00046190259057916786, 'samples': 5443392, 'steps': 28350, 'loss/train': 0.8180599212646484}
+08/30/2021 18:14:22 - INFO - __main__ - Step 28352: {'lr': 0.0004618997746712965, 'samples': 5443584, 'steps': 28351, 'loss/train': 1.5923995971679688}
+08/30/2021 18:14:22 - INFO - __main__ - Step 28353: {'lr': 0.00046189695866794635, 'samples': 5443776, 'steps': 28352, 'loss/train': 1.2761247158050537}
+08/30/2021 18:14:23 - INFO - __main__ - Step 28354: {'lr': 0.00046189414256911875, 'samples': 5443968, 'steps': 28353, 'loss/train': 2.637528419494629}
+08/30/2021 18:14:25 - INFO - __main__ - Step 28355: {'lr': 0.0004618913263748149, 'samples': 5444160, 'steps': 28354, 'loss/train': 1.7462899684906006}
+08/30/2021 18:14:25 - INFO - __main__ - Step 28356: {'lr': 0.0004618885100850361, 'samples': 5444352, 'steps': 28355, 'loss/train': 1.6216866970062256}
+08/30/2021 18:14:26 - INFO - __main__ - Step 28357: {'lr': 0.0004618856936997836, 'samples': 5444544, 'steps': 28356, 'loss/train': 1.2861307859420776}
+08/30/2021 18:14:26 - INFO - __main__ - Step 28358: {'lr': 0.0004618828772190586, 'samples': 5444736, 'steps': 28357, 'loss/train': 1.8551957607269287}
+08/30/2021 18:14:26 - INFO - __main__ - Step 28359: {'lr': 0.0004618800606428626, 'samples': 5444928, 'steps': 28358, 'loss/train': 1.779967188835144}
+08/30/2021 18:14:27 - INFO - __main__ - Step 28360: {'lr': 0.00046187724397119657, 'samples': 5445120, 'steps': 28359, 'loss/train': 1.662474513053894}
+08/30/2021 18:14:29 - INFO - __main__ - Step 28361: {'lr': 0.000461874427204062, 'samples': 5445312, 'steps': 28360, 'loss/train': 1.8396095037460327}
+08/30/2021 18:14:29 - INFO - __main__ - Step 28362: {'lr': 0.00046187161034146, 'samples': 5445504, 'steps': 28361, 'loss/train': 1.1978753805160522}
+08/30/2021 18:14:29 - INFO - __main__ - Step 28363: {'lr': 0.00046186879338339207, 'samples': 5445696, 'steps': 28362, 'loss/train': 1.5329073667526245}
+08/30/2021 18:14:30 - INFO - __main__ - Step 28364: {'lr': 0.0004618659763298592, 'samples': 5445888, 'steps': 28363, 'loss/train': 1.1845771074295044}
+08/30/2021 18:14:30 - INFO - __main__ - Step 28365: {'lr': 0.00046186315918086285, 'samples': 5446080, 'steps': 28364, 'loss/train': 1.5781322717666626}
+08/30/2021 18:14:30 - INFO - __main__ - Step 28366: {'lr': 0.0004618603419364042, 'samples': 5446272, 'steps': 28365, 'loss/train': 1.47245192527771}
+08/30/2021 18:14:32 - INFO - __main__ - Step 28367: {'lr': 0.00046185752459648456, 'samples': 5446464, 'steps': 28366, 'loss/train': 0.07523348927497864}
+08/30/2021 18:14:33 - INFO - __main__ - Step 28368: {'lr': 0.00046185470716110516, 'samples': 5446656, 'steps': 28367, 'loss/train': 1.4055206775665283}
+08/30/2021 18:14:33 - INFO - __main__ - Step 28369: {'lr': 0.00046185188963026734, 'samples': 5446848, 'steps': 28368, 'loss/train': 3.3890609741210938}
+08/30/2021 18:14:33 - INFO - __main__ - Step 28370: {'lr': 0.0004618490720039723, 'samples': 5447040, 'steps': 28369, 'loss/train': 1.3116455078125}
+08/30/2021 18:14:34 - INFO - __main__ - Step 28371: {'lr': 0.0004618462542822214, 'samples': 5447232, 'steps': 28370, 'loss/train': 1.5488499402999878}
+08/30/2021 18:14:34 - INFO - __main__ - Step 28372: {'lr': 0.0004618434364650158, 'samples': 5447424, 'steps': 28371, 'loss/train': 1.957581639289856}
+08/30/2021 18:14:36 - INFO - __main__ - Step 28373: {'lr': 0.00046184061855235683, 'samples': 5447616, 'steps': 28372, 'loss/train': 1.416306495666504}
+08/30/2021 18:14:36 - INFO - __main__ - Step 28374: {'lr': 0.00046183780054424574, 'samples': 5447808, 'steps': 28373, 'loss/train': 1.3398233652114868}
+08/30/2021 18:14:36 - INFO - __main__ - Step 28375: {'lr': 0.00046183498244068376, 'samples': 5448000, 'steps': 28374, 'loss/train': 1.2787036895751953}
+08/30/2021 18:14:37 - INFO - __main__ - Step 28376: {'lr': 0.00046183216424167226, 'samples': 5448192, 'steps': 28375, 'loss/train': 1.8297516107559204}
+08/30/2021 18:14:37 - INFO - __main__ - Step 28377: {'lr': 0.0004618293459472124, 'samples': 5448384, 'steps': 28376, 'loss/train': 1.5445353984832764}
+08/30/2021 18:14:39 - INFO - __main__ - Step 28378: {'lr': 0.0004618265275573056, 'samples': 5448576, 'steps': 28377, 'loss/train': 2.1174182891845703}
+08/30/2021 18:14:39 - INFO - __main__ - Step 28379: {'lr': 0.00046182370907195294, 'samples': 5448768, 'steps': 28378, 'loss/train': 1.0556801557540894}
+08/30/2021 18:14:40 - INFO - __main__ - Step 28380: {'lr': 0.00046182089049115585, 'samples': 5448960, 'steps': 28379, 'loss/train': 4.267399787902832}
+08/30/2021 18:14:40 - INFO - __main__ - Step 28381: {'lr': 0.0004618180718149155, 'samples': 5449152, 'steps': 28380, 'loss/train': 1.6334525346755981}
+08/30/2021 18:14:40 - INFO - __main__ - Step 28382: {'lr': 0.00046181525304323325, 'samples': 5449344, 'steps': 28381, 'loss/train': 1.448195219039917}
+08/30/2021 18:14:42 - INFO - __main__ - Step 28383: {'lr': 0.0004618124341761102, 'samples': 5449536, 'steps': 28382, 'loss/train': 1.6182572841644287}
+08/30/2021 18:14:42 - INFO - __main__ - Step 28384: {'lr': 0.0004618096152135478, 'samples': 5449728, 'steps': 28383, 'loss/train': 2.207749366760254}
+08/30/2021 18:14:42 - INFO - __main__ - Step 28385: {'lr': 0.00046180679615554735, 'samples': 5449920, 'steps': 28384, 'loss/train': 2.3146650791168213}
+08/30/2021 18:14:43 - INFO - __main__ - Step 28386: {'lr': 0.00046180397700210985, 'samples': 5450112, 'steps': 28385, 'loss/train': 1.8278053998947144}
+08/30/2021 18:14:43 - INFO - __main__ - Step 28387: {'lr': 0.0004618011577532368, 'samples': 5450304, 'steps': 28386, 'loss/train': 1.7210609912872314}
+08/30/2021 18:14:45 - INFO - __main__ - Step 28388: {'lr': 0.0004617983384089295, 'samples': 5450496, 'steps': 28387, 'loss/train': 1.3940378427505493}
+08/30/2021 18:14:45 - INFO - __main__ - Step 28389: {'lr': 0.00046179551896918916, 'samples': 5450688, 'steps': 28388, 'loss/train': 0.582719624042511}
+08/30/2021 18:14:46 - INFO - __main__ - Step 28390: {'lr': 0.00046179269943401693, 'samples': 5450880, 'steps': 28389, 'loss/train': 2.3339428901672363}
+08/30/2021 18:14:46 - INFO - __main__ - Step 28391: {'lr': 0.00046178987980341414, 'samples': 5451072, 'steps': 28390, 'loss/train': 1.3789128065109253}
+08/30/2021 18:14:47 - INFO - __main__ - Step 28392: {'lr': 0.00046178706007738227, 'samples': 5451264, 'steps': 28391, 'loss/train': 0.16868636012077332}
+08/30/2021 18:14:47 - INFO - __main__ - Step 28393: {'lr': 0.0004617842402559223, 'samples': 5451456, 'steps': 28392, 'loss/train': 0.0908598005771637}
+08/30/2021 18:14:48 - INFO - __main__ - Step 28394: {'lr': 0.0004617814203390356, 'samples': 5451648, 'steps': 28393, 'loss/train': 2.0442283153533936}
+08/30/2021 18:14:49 - INFO - __main__ - Step 28395: {'lr': 0.0004617786003267235, 'samples': 5451840, 'steps': 28394, 'loss/train': 1.7698763608932495}
+08/30/2021 18:14:49 - INFO - __main__ - Step 28396: {'lr': 0.00046177578021898717, 'samples': 5452032, 'steps': 28395, 'loss/train': 0.9512029886245728}
+08/30/2021 18:14:50 - INFO - __main__ - Step 28397: {'lr': 0.000461772960015828, 'samples': 5452224, 'steps': 28396, 'loss/train': 1.8937252759933472}
+08/30/2021 18:14:50 - INFO - __main__ - Step 28398: {'lr': 0.00046177013971724723, 'samples': 5452416, 'steps': 28397, 'loss/train': 2.0061144828796387}
+08/30/2021 18:14:50 - INFO - __main__ - Step 28399: {'lr': 0.00046176731932324604, 'samples': 5452608, 'steps': 28398, 'loss/train': 1.6485087871551514}
+08/30/2021 18:14:52 - INFO - __main__ - Step 28400: {'lr': 0.0004617644988338258, 'samples': 5452800, 'steps': 28399, 'loss/train': 1.1261181831359863}
+08/30/2021 18:14:53 - INFO - __main__ - Step 28401: {'lr': 0.0004617616782489877, 'samples': 5452992, 'steps': 28400, 'loss/train': 0.9156551957130432}
+08/30/2021 18:14:53 - INFO - __main__ - Step 28402: {'lr': 0.00046175885756873314, 'samples': 5453184, 'steps': 28401, 'loss/train': 0.07958393543958664}
+08/30/2021 18:14:54 - INFO - __main__ - Step 28403: {'lr': 0.00046175603679306324, 'samples': 5453376, 'steps': 28402, 'loss/train': 1.9514942169189453}
+08/30/2021 18:14:54 - INFO - __main__ - Step 28404: {'lr': 0.0004617532159219794, 'samples': 5453568, 'steps': 28403, 'loss/train': 1.5115739107131958}
+08/30/2021 18:14:55 - INFO - __main__ - Step 28405: {'lr': 0.0004617503949554828, 'samples': 5453760, 'steps': 28404, 'loss/train': 2.2763118743896484}
+08/30/2021 18:14:56 - INFO - __main__ - Step 28406: {'lr': 0.0004617475738935747, 'samples': 5453952, 'steps': 28405, 'loss/train': 1.9992116689682007}
+08/30/2021 18:14:56 - INFO - __main__ - Step 28407: {'lr': 0.0004617447527362564, 'samples': 5454144, 'steps': 28406, 'loss/train': 1.4851759672164917}
+08/30/2021 18:14:57 - INFO - __main__ - Step 28408: {'lr': 0.00046174193148352914, 'samples': 5454336, 'steps': 28407, 'loss/train': 1.3432347774505615}
+08/30/2021 18:14:57 - INFO - __main__ - Step 28409: {'lr': 0.00046173911013539437, 'samples': 5454528, 'steps': 28408, 'loss/train': 2.709536075592041}
+08/30/2021 18:14:58 - INFO - __main__ - Step 28410: {'lr': 0.0004617362886918531, 'samples': 5454720, 'steps': 28409, 'loss/train': 1.2044527530670166}
+08/30/2021 18:14:59 - INFO - __main__ - Step 28411: {'lr': 0.0004617334671529069, 'samples': 5454912, 'steps': 28410, 'loss/train': 2.171020030975342}
+08/30/2021 18:14:59 - INFO - __main__ - Step 28412: {'lr': 0.0004617306455185567, 'samples': 5455104, 'steps': 28411, 'loss/train': 1.7233283519744873}
+08/30/2021 18:15:00 - INFO - __main__ - Step 28413: {'lr': 0.00046172782378880404, 'samples': 5455296, 'steps': 28412, 'loss/train': 1.5373201370239258}
+08/30/2021 18:15:00 - INFO - __main__ - Step 28414: {'lr': 0.00046172500196364996, 'samples': 5455488, 'steps': 28413, 'loss/train': 1.5885015726089478}
+08/30/2021 18:15:02 - INFO - __main__ - Step 28415: {'lr': 0.000461722180043096, 'samples': 5455680, 'steps': 28414, 'loss/train': 1.087518572807312}
+08/30/2021 18:15:02 - INFO - __main__ - Step 28416: {'lr': 0.0004617193580271433, 'samples': 5455872, 'steps': 28415, 'loss/train': 1.7424510717391968}
+08/30/2021 18:15:03 - INFO - __main__ - Step 28417: {'lr': 0.000461716535915793, 'samples': 5456064, 'steps': 28416, 'loss/train': 1.5177549123764038}
+08/30/2021 18:15:03 - INFO - __main__ - Step 28418: {'lr': 0.0004617137137090466, 'samples': 5456256, 'steps': 28417, 'loss/train': 1.6655724048614502}
+08/30/2021 18:15:03 - INFO - __main__ - Step 28419: {'lr': 0.0004617108914069052, 'samples': 5456448, 'steps': 28418, 'loss/train': 1.6813396215438843}
+08/30/2021 18:15:04 - INFO - __main__ - Step 28420: {'lr': 0.0004617080690093701, 'samples': 5456640, 'steps': 28419, 'loss/train': 0.90381920337677}
+08/30/2021 18:15:05 - INFO - __main__ - Step 28421: {'lr': 0.00046170524651644276, 'samples': 5456832, 'steps': 28420, 'loss/train': 1.3693146705627441}
+08/30/2021 18:15:06 - INFO - __main__ - Step 28422: {'lr': 0.00046170242392812425, 'samples': 5457024, 'steps': 28421, 'loss/train': 1.5474826097488403}
+08/30/2021 18:15:06 - INFO - __main__ - Step 28423: {'lr': 0.0004616996012444158, 'samples': 5457216, 'steps': 28422, 'loss/train': 2.1661765575408936}
+08/30/2021 18:15:06 - INFO - __main__ - Step 28424: {'lr': 0.00046169677846531884, 'samples': 5457408, 'steps': 28423, 'loss/train': 1.5340081453323364}
+08/30/2021 18:15:07 - INFO - __main__ - Step 28425: {'lr': 0.0004616939555908346, 'samples': 5457600, 'steps': 28424, 'loss/train': 1.557504415512085}
+08/30/2021 18:15:08 - INFO - __main__ - Step 28426: {'lr': 0.0004616911326209643, 'samples': 5457792, 'steps': 28425, 'loss/train': 2.089592456817627}
+08/30/2021 18:15:09 - INFO - __main__ - Step 28427: {'lr': 0.0004616883095557092, 'samples': 5457984, 'steps': 28426, 'loss/train': 1.8241089582443237}
+08/30/2021 18:15:09 - INFO - __main__ - Step 28428: {'lr': 0.0004616854863950707, 'samples': 5458176, 'steps': 28427, 'loss/train': 0.5400580167770386}
+08/30/2021 18:15:09 - INFO - __main__ - Step 28429: {'lr': 0.00046168266313904995, 'samples': 5458368, 'steps': 28428, 'loss/train': 2.1024491786956787}
+08/30/2021 18:15:10 - INFO - __main__ - Step 28430: {'lr': 0.00046167983978764827, 'samples': 5458560, 'steps': 28429, 'loss/train': 1.6214874982833862}
+08/30/2021 18:15:11 - INFO - __main__ - Step 28431: {'lr': 0.0004616770163408669, 'samples': 5458752, 'steps': 28430, 'loss/train': 1.847511649131775}
+08/30/2021 18:15:12 - INFO - __main__ - Step 28432: {'lr': 0.00046167419279870715, 'samples': 5458944, 'steps': 28431, 'loss/train': 1.8810951709747314}
+08/30/2021 18:15:12 - INFO - __main__ - Step 28433: {'lr': 0.00046167136916117025, 'samples': 5459136, 'steps': 28432, 'loss/train': 1.4094552993774414}
+08/30/2021 18:15:12 - INFO - __main__ - Step 28434: {'lr': 0.00046166854542825756, 'samples': 5459328, 'steps': 28433, 'loss/train': 1.757566213607788}
+08/30/2021 18:15:13 - INFO - __main__ - Step 28435: {'lr': 0.0004616657215999702, 'samples': 5459520, 'steps': 28434, 'loss/train': 1.060879111289978}
+08/30/2021 18:15:14 - INFO - __main__ - Step 28436: {'lr': 0.0004616628976763096, 'samples': 5459712, 'steps': 28435, 'loss/train': 1.269731044769287}
+08/30/2021 18:15:14 - INFO - __main__ - Step 28437: {'lr': 0.0004616600736572769, 'samples': 5459904, 'steps': 28436, 'loss/train': 1.401597261428833}
+08/30/2021 18:15:15 - INFO - __main__ - Step 28438: {'lr': 0.0004616572495428735, 'samples': 5460096, 'steps': 28437, 'loss/train': 1.4698482751846313}
+08/30/2021 18:15:15 - INFO - __main__ - Step 28439: {'lr': 0.0004616544253331006, 'samples': 5460288, 'steps': 28438, 'loss/train': 0.9774594902992249}
+08/30/2021 18:15:15 - INFO - __main__ - Step 28440: {'lr': 0.00046165160102795943, 'samples': 5460480, 'steps': 28439, 'loss/train': 1.3149068355560303}
+08/30/2021 18:15:17 - INFO - __main__ - Step 28441: {'lr': 0.0004616487766274514, 'samples': 5460672, 'steps': 28440, 'loss/train': 1.6768009662628174}
+08/30/2021 18:15:18 - INFO - __main__ - Step 28442: {'lr': 0.0004616459521315777, 'samples': 5460864, 'steps': 28441, 'loss/train': 1.2131375074386597}
+08/30/2021 18:15:18 - INFO - __main__ - Step 28443: {'lr': 0.0004616431275403395, 'samples': 5461056, 'steps': 28442, 'loss/train': 1.0739957094192505}
+08/30/2021 18:15:18 - INFO - __main__ - Step 28444: {'lr': 0.0004616403028537382, 'samples': 5461248, 'steps': 28443, 'loss/train': 3.931757926940918}
+08/30/2021 18:15:19 - INFO - __main__ - Step 28445: {'lr': 0.0004616374780717751, 'samples': 5461440, 'steps': 28444, 'loss/train': 1.139050841331482}
+08/30/2021 18:15:19 - INFO - __main__ - Step 28446: {'lr': 0.0004616346531944514, 'samples': 5461632, 'steps': 28445, 'loss/train': 1.621245265007019}
+08/30/2021 18:15:21 - INFO - __main__ - Step 28447: {'lr': 0.00046163182822176835, 'samples': 5461824, 'steps': 28446, 'loss/train': 1.4106972217559814}
+08/30/2021 18:15:21 - INFO - __main__ - Step 28448: {'lr': 0.0004616290031537273, 'samples': 5462016, 'steps': 28447, 'loss/train': 0.29630017280578613}
+08/30/2021 18:15:21 - INFO - __main__ - Step 28449: {'lr': 0.0004616261779903295, 'samples': 5462208, 'steps': 28448, 'loss/train': 1.1605528593063354}
+08/30/2021 18:15:22 - INFO - __main__ - Step 28450: {'lr': 0.0004616233527315762, 'samples': 5462400, 'steps': 28449, 'loss/train': 1.7201234102249146}
+08/30/2021 18:15:22 - INFO - __main__ - Step 28451: {'lr': 0.0004616205273774686, 'samples': 5462592, 'steps': 28450, 'loss/train': 1.6046078205108643}
+08/30/2021 18:15:22 - INFO - __main__ - Step 28452: {'lr': 0.00046161770192800817, 'samples': 5462784, 'steps': 28451, 'loss/train': 1.3255046606063843}
+08/30/2021 18:15:24 - INFO - __main__ - Step 28453: {'lr': 0.000461614876383196, 'samples': 5462976, 'steps': 28452, 'loss/train': 1.2627551555633545}
+08/30/2021 18:15:25 - INFO - __main__ - Step 28454: {'lr': 0.0004616120507430335, 'samples': 5463168, 'steps': 28453, 'loss/train': 1.7005821466445923}
+08/30/2021 18:15:25 - INFO - __main__ - Step 28455: {'lr': 0.00046160922500752176, 'samples': 5463360, 'steps': 28454, 'loss/train': 0.6630153656005859}
+08/30/2021 18:15:25 - INFO - __main__ - Step 28456: {'lr': 0.0004616063991766623, 'samples': 5463552, 'steps': 28455, 'loss/train': 1.7326027154922485}
+08/30/2021 18:15:26 - INFO - __main__ - Step 28457: {'lr': 0.0004616035732504562, 'samples': 5463744, 'steps': 28456, 'loss/train': 1.629073143005371}
+08/30/2021 18:15:27 - INFO - __main__ - Step 28458: {'lr': 0.0004616007472289048, 'samples': 5463936, 'steps': 28457, 'loss/train': 1.4131532907485962}
+08/30/2021 18:15:28 - INFO - __main__ - Step 28459: {'lr': 0.00046159792111200937, 'samples': 5464128, 'steps': 28458, 'loss/train': 1.3037713766098022}
+08/30/2021 18:15:28 - INFO - __main__ - Step 28460: {'lr': 0.0004615950948997711, 'samples': 5464320, 'steps': 28459, 'loss/train': 1.4961373805999756}
+08/30/2021 18:15:29 - INFO - __main__ - Step 28461: {'lr': 0.0004615922685921915, 'samples': 5464512, 'steps': 28460, 'loss/train': 1.4120932817459106}
+08/30/2021 18:15:29 - INFO - __main__ - Step 28462: {'lr': 0.0004615894421892716, 'samples': 5464704, 'steps': 28461, 'loss/train': 1.5001535415649414}
+08/30/2021 18:15:31 - INFO - __main__ - Step 28463: {'lr': 0.0004615866156910128, 'samples': 5464896, 'steps': 28462, 'loss/train': 1.1565515995025635}
+08/30/2021 18:15:31 - INFO - __main__ - Step 28464: {'lr': 0.00046158378909741626, 'samples': 5465088, 'steps': 28463, 'loss/train': 2.036403179168701}
+08/30/2021 18:15:31 - INFO - __main__ - Step 28465: {'lr': 0.00046158096240848343, 'samples': 5465280, 'steps': 28464, 'loss/train': 1.703019618988037}
+08/30/2021 18:15:32 - INFO - __main__ - Step 28466: {'lr': 0.00046157813562421545, 'samples': 5465472, 'steps': 28465, 'loss/train': 1.6842516660690308}
+08/30/2021 18:15:32 - INFO - __main__ - Step 28467: {'lr': 0.0004615753087446136, 'samples': 5465664, 'steps': 28466, 'loss/train': 1.8737887144088745}
+08/30/2021 18:15:34 - INFO - __main__ - Step 28468: {'lr': 0.00046157248176967915, 'samples': 5465856, 'steps': 28467, 'loss/train': 1.8135250806808472}
+08/30/2021 18:15:34 - INFO - __main__ - Step 28469: {'lr': 0.0004615696546994135, 'samples': 5466048, 'steps': 28468, 'loss/train': 1.4749095439910889}
+08/30/2021 18:15:35 - INFO - __main__ - Step 28470: {'lr': 0.00046156682753381774, 'samples': 5466240, 'steps': 28469, 'loss/train': 1.223831295967102}
+08/30/2021 18:15:35 - INFO - __main__ - Step 28471: {'lr': 0.0004615640002728932, 'samples': 5466432, 'steps': 28470, 'loss/train': 1.4210262298583984}
+08/30/2021 18:15:35 - INFO - __main__ - Step 28472: {'lr': 0.00046156117291664133, 'samples': 5466624, 'steps': 28471, 'loss/train': 1.3265413045883179}
+08/30/2021 18:15:36 - INFO - __main__ - Step 28473: {'lr': 0.0004615583454650632, 'samples': 5466816, 'steps': 28472, 'loss/train': 1.6798558235168457}
+08/30/2021 18:15:37 - INFO - __main__ - Step 28474: {'lr': 0.00046155551791816007, 'samples': 5467008, 'steps': 28473, 'loss/train': 0.0545647032558918}
+08/30/2021 18:15:38 - INFO - __main__ - Step 28475: {'lr': 0.00046155269027593337, 'samples': 5467200, 'steps': 28474, 'loss/train': 1.4392448663711548}
+08/30/2021 18:15:38 - INFO - __main__ - Step 28476: {'lr': 0.00046154986253838426, 'samples': 5467392, 'steps': 28475, 'loss/train': 1.3955795764923096}
+08/30/2021 18:15:38 - INFO - __main__ - Step 28477: {'lr': 0.00046154703470551405, 'samples': 5467584, 'steps': 28476, 'loss/train': 1.797864556312561}
+08/30/2021 18:15:39 - INFO - __main__ - Step 28478: {'lr': 0.000461544206777324, 'samples': 5467776, 'steps': 28477, 'loss/train': 0.6715664267539978}
+08/30/2021 18:15:40 - INFO - __main__ - Step 28479: {'lr': 0.00046154137875381547, 'samples': 5467968, 'steps': 28478, 'loss/train': 1.7450462579727173}
+08/30/2021 18:15:41 - INFO - __main__ - Step 28480: {'lr': 0.00046153855063498964, 'samples': 5468160, 'steps': 28479, 'loss/train': 1.654579758644104}
+08/30/2021 18:15:41 - INFO - __main__ - Step 28481: {'lr': 0.00046153572242084776, 'samples': 5468352, 'steps': 28480, 'loss/train': 1.3318246603012085}
+08/30/2021 18:15:41 - INFO - __main__ - Step 28482: {'lr': 0.0004615328941113911, 'samples': 5468544, 'steps': 28481, 'loss/train': 1.3417713642120361}
+08/30/2021 18:15:42 - INFO - __main__ - Step 28483: {'lr': 0.00046153006570662106, 'samples': 5468736, 'steps': 28482, 'loss/train': 1.5684040784835815}
+08/30/2021 18:15:43 - INFO - __main__ - Step 28484: {'lr': 0.0004615272372065388, 'samples': 5468928, 'steps': 28483, 'loss/train': 1.7049928903579712}
+08/30/2021 18:15:44 - INFO - __main__ - Step 28485: {'lr': 0.0004615244086111456, 'samples': 5469120, 'steps': 28484, 'loss/train': 1.32969331741333}
+08/30/2021 18:15:44 - INFO - __main__ - Step 28486: {'lr': 0.00046152157992044283, 'samples': 5469312, 'steps': 28485, 'loss/train': 1.4608381986618042}
+08/30/2021 18:15:44 - INFO - __main__ - Step 28487: {'lr': 0.0004615187511344316, 'samples': 5469504, 'steps': 28486, 'loss/train': 1.3725831508636475}
+08/30/2021 18:15:45 - INFO - __main__ - Step 28488: {'lr': 0.00046151592225311347, 'samples': 5469696, 'steps': 28487, 'loss/train': 1.6761726140975952}
+08/30/2021 18:15:46 - INFO - __main__ - Step 28489: {'lr': 0.0004615130932764894, 'samples': 5469888, 'steps': 28488, 'loss/train': 1.3599092960357666}
+08/30/2021 18:15:46 - INFO - __main__ - Step 28490: {'lr': 0.0004615102642045608, 'samples': 5470080, 'steps': 28489, 'loss/train': 1.5636268854141235}
+08/30/2021 18:15:47 - INFO - __main__ - Step 28491: {'lr': 0.00046150743503732897, 'samples': 5470272, 'steps': 28490, 'loss/train': 1.3444204330444336}
+08/30/2021 18:15:47 - INFO - __main__ - Step 28492: {'lr': 0.0004615046057747951, 'samples': 5470464, 'steps': 28491, 'loss/train': 1.6677089929580688}
+08/30/2021 18:15:48 - INFO - __main__ - Step 28493: {'lr': 0.0004615017764169606, 'samples': 5470656, 'steps': 28492, 'loss/train': 1.0866971015930176}
+08/30/2021 18:15:49 - INFO - __main__ - Step 28494: {'lr': 0.00046149894696382655, 'samples': 5470848, 'steps': 28493, 'loss/train': 1.7957838773727417}
+08/30/2021 18:15:50 - INFO - __main__ - Step 28495: {'lr': 0.00046149611741539445, 'samples': 5471040, 'steps': 28494, 'loss/train': 1.851419448852539}
+08/30/2021 18:15:50 - INFO - __main__ - Step 28496: {'lr': 0.00046149328777166543, 'samples': 5471232, 'steps': 28495, 'loss/train': 1.5098599195480347}
+08/30/2021 18:15:50 - INFO - __main__ - Step 28497: {'lr': 0.0004614904580326408, 'samples': 5471424, 'steps': 28496, 'loss/train': 1.1656744480133057}
+08/30/2021 18:15:51 - INFO - __main__ - Step 28498: {'lr': 0.0004614876281983218, 'samples': 5471616, 'steps': 28497, 'loss/train': 2.112806797027588}
+08/30/2021 18:15:51 - INFO - __main__ - Step 28499: {'lr': 0.0004614847982687097, 'samples': 5471808, 'steps': 28498, 'loss/train': 0.9596072435379028}
+08/30/2021 18:15:53 - INFO - __main__ - Step 28500: {'lr': 0.0004614819682438059, 'samples': 5472000, 'steps': 28499, 'loss/train': 1.330038070678711}
+08/30/2021 18:15:53 - INFO - __main__ - Step 28501: {'lr': 0.00046147913812361155, 'samples': 5472192, 'steps': 28500, 'loss/train': 0.7673311233520508}
+08/30/2021 18:15:53 - INFO - __main__ - Step 28502: {'lr': 0.000461476307908128, 'samples': 5472384, 'steps': 28501, 'loss/train': 0.8263532519340515}
+08/30/2021 18:15:54 - INFO - __main__ - Step 28503: {'lr': 0.00046147347759735647, 'samples': 5472576, 'steps': 28502, 'loss/train': 1.9476468563079834}
+08/30/2021 18:15:54 - INFO - __main__ - Step 28504: {'lr': 0.00046147064719129823, 'samples': 5472768, 'steps': 28503, 'loss/train': 1.6908648014068604}
+08/30/2021 18:15:56 - INFO - __main__ - Step 28505: {'lr': 0.00046146781668995456, 'samples': 5472960, 'steps': 28504, 'loss/train': 1.075881004333496}
+08/30/2021 18:15:57 - INFO - __main__ - Step 28506: {'lr': 0.0004614649860933268, 'samples': 5473152, 'steps': 28505, 'loss/train': 1.9262429475784302}
+08/30/2021 18:15:57 - INFO - __main__ - Step 28507: {'lr': 0.0004614621554014162, 'samples': 5473344, 'steps': 28506, 'loss/train': 1.8057692050933838}
+08/30/2021 18:15:58 - INFO - __main__ - Step 28508: {'lr': 0.00046145932461422396, 'samples': 5473536, 'steps': 28507, 'loss/train': 1.4998582601547241}
+08/30/2021 18:15:58 - INFO - __main__ - Step 28509: {'lr': 0.00046145649373175145, 'samples': 5473728, 'steps': 28508, 'loss/train': 1.477571725845337}
+08/30/2021 18:15:58 - INFO - __main__ - Step 28510: {'lr': 0.0004614536627539999, 'samples': 5473920, 'steps': 28509, 'loss/train': 1.7403695583343506}
+08/30/2021 18:16:00 - INFO - __main__ - Step 28511: {'lr': 0.0004614508316809706, 'samples': 5474112, 'steps': 28510, 'loss/train': 2.421569347381592}
+08/30/2021 18:16:00 - INFO - __main__ - Step 28512: {'lr': 0.00046144800051266477, 'samples': 5474304, 'steps': 28511, 'loss/train': 1.2638709545135498}
+08/30/2021 18:16:01 - INFO - __main__ - Step 28513: {'lr': 0.00046144516924908377, 'samples': 5474496, 'steps': 28512, 'loss/train': 1.592155933380127}
+08/30/2021 18:16:01 - INFO - __main__ - Step 28514: {'lr': 0.0004614423378902289, 'samples': 5474688, 'steps': 28513, 'loss/train': 1.9909541606903076}
+08/30/2021 18:16:01 - INFO - __main__ - Step 28515: {'lr': 0.0004614395064361013, 'samples': 5474880, 'steps': 28514, 'loss/train': 0.7892037630081177}
+08/30/2021 18:16:03 - INFO - __main__ - Step 28516: {'lr': 0.00046143667488670226, 'samples': 5475072, 'steps': 28515, 'loss/train': 1.0137324333190918}
+08/30/2021 18:16:04 - INFO - __main__ - Step 28517: {'lr': 0.00046143384324203325, 'samples': 5475264, 'steps': 28516, 'loss/train': 1.8772464990615845}
+08/30/2021 18:16:04 - INFO - __main__ - Step 28518: {'lr': 0.00046143101150209533, 'samples': 5475456, 'steps': 28517, 'loss/train': 0.062400247901678085}
+08/30/2021 18:16:04 - INFO - __main__ - Step 28519: {'lr': 0.0004614281796668899, 'samples': 5475648, 'steps': 28518, 'loss/train': 1.7559754848480225}
+08/30/2021 18:16:05 - INFO - __main__ - Step 28520: {'lr': 0.0004614253477364182, 'samples': 5475840, 'steps': 28519, 'loss/train': 1.6631942987442017}
+08/30/2021 18:16:05 - INFO - __main__ - Step 28521: {'lr': 0.0004614225157106815, 'samples': 5476032, 'steps': 28520, 'loss/train': 1.5449906587600708}
+08/30/2021 18:16:06 - INFO - __main__ - Step 28522: {'lr': 0.00046141968358968103, 'samples': 5476224, 'steps': 28521, 'loss/train': 2.165684223175049}
+08/30/2021 18:16:07 - INFO - __main__ - Step 28523: {'lr': 0.00046141685137341814, 'samples': 5476416, 'steps': 28522, 'loss/train': 1.218667984008789}
+08/30/2021 18:16:07 - INFO - __main__ - Step 28524: {'lr': 0.00046141401906189404, 'samples': 5476608, 'steps': 28523, 'loss/train': 1.5562207698822021}
+08/30/2021 18:16:07 - INFO - __main__ - Step 28525: {'lr': 0.0004614111866551101, 'samples': 5476800, 'steps': 28524, 'loss/train': 1.8598761558532715}
+08/30/2021 18:16:08 - INFO - __main__ - Step 28526: {'lr': 0.0004614083541530675, 'samples': 5476992, 'steps': 28525, 'loss/train': 1.8451690673828125}
+08/30/2021 18:16:09 - INFO - __main__ - Step 28527: {'lr': 0.00046140552155576767, 'samples': 5477184, 'steps': 28526, 'loss/train': 1.7072362899780273}
+08/30/2021 18:16:10 - INFO - __main__ - Step 28528: {'lr': 0.0004614026888632116, 'samples': 5477376, 'steps': 28527, 'loss/train': 1.3507329225540161}
+08/30/2021 18:16:10 - INFO - __main__ - Step 28529: {'lr': 0.00046139985607540087, 'samples': 5477568, 'steps': 28528, 'loss/train': 1.6900264024734497}
+08/30/2021 18:16:10 - INFO - __main__ - Step 28530: {'lr': 0.00046139702319233656, 'samples': 5477760, 'steps': 28529, 'loss/train': 1.7837227582931519}
+08/30/2021 18:16:11 - INFO - __main__ - Step 28531: {'lr': 0.00046139419021402005, 'samples': 5477952, 'steps': 28530, 'loss/train': 1.7546217441558838}
+08/30/2021 18:16:11 - INFO - __main__ - Step 28532: {'lr': 0.00046139135714045253, 'samples': 5478144, 'steps': 28531, 'loss/train': 1.699596881866455}
+08/30/2021 18:16:13 - INFO - __main__ - Step 28533: {'lr': 0.00046138852397163547, 'samples': 5478336, 'steps': 28532, 'loss/train': 1.8266007900238037}
+08/30/2021 18:16:13 - INFO - __main__ - Step 28534: {'lr': 0.00046138569070756984, 'samples': 5478528, 'steps': 28533, 'loss/train': 0.06760618835687637}
+08/30/2021 18:16:14 - INFO - __main__ - Step 28535: {'lr': 0.00046138285734825715, 'samples': 5478720, 'steps': 28534, 'loss/train': 1.34406578540802}
+08/30/2021 18:16:14 - INFO - __main__ - Step 28536: {'lr': 0.0004613800238936986, 'samples': 5478912, 'steps': 28535, 'loss/train': 1.4671729803085327}
+08/30/2021 18:16:14 - INFO - __main__ - Step 28537: {'lr': 0.0004613771903438955, 'samples': 5479104, 'steps': 28536, 'loss/train': 1.3227908611297607}
+08/30/2021 18:16:16 - INFO - __main__ - Step 28538: {'lr': 0.00046137435669884897, 'samples': 5479296, 'steps': 28537, 'loss/train': 1.5423678159713745}
+08/30/2021 18:16:17 - INFO - __main__ - Step 28539: {'lr': 0.00046137152295856054, 'samples': 5479488, 'steps': 28538, 'loss/train': 0.17428183555603027}
+08/30/2021 18:16:17 - INFO - __main__ - Step 28540: {'lr': 0.0004613686891230313, 'samples': 5479680, 'steps': 28539, 'loss/train': 1.2126985788345337}
+08/30/2021 18:16:17 - INFO - __main__ - Step 28541: {'lr': 0.0004613658551922627, 'samples': 5479872, 'steps': 28540, 'loss/train': 2.0219058990478516}
+08/30/2021 18:16:18 - INFO - __main__ - Step 28542: {'lr': 0.0004613630211662558, 'samples': 5480064, 'steps': 28541, 'loss/train': 1.5777045488357544}
+08/30/2021 18:16:19 - INFO - __main__ - Step 28543: {'lr': 0.00046136018704501203, 'samples': 5480256, 'steps': 28542, 'loss/train': 1.443447232246399}
+08/30/2021 18:16:19 - INFO - __main__ - Step 28544: {'lr': 0.00046135735282853263, 'samples': 5480448, 'steps': 28543, 'loss/train': 1.5230565071105957}
+08/30/2021 18:16:20 - INFO - __main__ - Step 28545: {'lr': 0.0004613545185168188, 'samples': 5480640, 'steps': 28544, 'loss/train': 1.427353024482727}
+08/30/2021 18:16:20 - INFO - __main__ - Step 28546: {'lr': 0.0004613516841098719, 'samples': 5480832, 'steps': 28545, 'loss/train': 2.22821307182312}
+08/30/2021 18:16:21 - INFO - __main__ - Step 28547: {'lr': 0.0004613488496076933, 'samples': 5481024, 'steps': 28546, 'loss/train': 1.7149930000305176}
+08/30/2021 18:16:22 - INFO - __main__ - Step 28548: {'lr': 0.00046134601501028404, 'samples': 5481216, 'steps': 28547, 'loss/train': 1.4018101692199707}
+08/30/2021 18:16:23 - INFO - __main__ - Step 28549: {'lr': 0.0004613431803176456, 'samples': 5481408, 'steps': 28548, 'loss/train': 0.6721023321151733}
+08/30/2021 18:16:23 - INFO - __main__ - Step 28550: {'lr': 0.00046134034552977924, 'samples': 5481600, 'steps': 28549, 'loss/train': 1.870675802230835}
+08/30/2021 18:16:23 - INFO - __main__ - Step 28551: {'lr': 0.00046133751064668605, 'samples': 5481792, 'steps': 28550, 'loss/train': 1.046642780303955}
+08/30/2021 18:16:24 - INFO - __main__ - Step 28552: {'lr': 0.0004613346756683675, 'samples': 5481984, 'steps': 28551, 'loss/train': 1.702518343925476}
+08/30/2021 18:16:25 - INFO - __main__ - Step 28553: {'lr': 0.0004613318405948248, 'samples': 5482176, 'steps': 28552, 'loss/train': 1.886941909790039}
+08/30/2021 18:16:26 - INFO - __main__ - Step 28554: {'lr': 0.00046132900542605925, 'samples': 5482368, 'steps': 28553, 'loss/train': 1.116611123085022}
+08/30/2021 18:16:26 - INFO - __main__ - Step 28555: {'lr': 0.0004613261701620721, 'samples': 5482560, 'steps': 28554, 'loss/train': 1.2434521913528442}
+08/30/2021 18:16:26 - INFO - __main__ - Step 28556: {'lr': 0.0004613233348028646, 'samples': 5482752, 'steps': 28555, 'loss/train': 0.9997589588165283}
+08/30/2021 18:16:27 - INFO - __main__ - Step 28557: {'lr': 0.0004613204993484381, 'samples': 5482944, 'steps': 28556, 'loss/train': 1.574049472808838}
+08/30/2021 18:16:29 - INFO - __main__ - Step 28558: {'lr': 0.00046131766379879386, 'samples': 5483136, 'steps': 28557, 'loss/train': 1.684670329093933}
+08/30/2021 18:16:29 - INFO - __main__ - Step 28559: {'lr': 0.0004613148281539331, 'samples': 5483328, 'steps': 28558, 'loss/train': 1.2109357118606567}
+08/30/2021 18:16:30 - INFO - __main__ - Step 28560: {'lr': 0.00046131199241385726, 'samples': 5483520, 'steps': 28559, 'loss/train': 1.1717592477798462}
+08/30/2021 18:16:30 - INFO - __main__ - Step 28561: {'lr': 0.0004613091565785673, 'samples': 5483712, 'steps': 28560, 'loss/train': 1.4759520292282104}
+08/30/2021 18:16:30 - INFO - __main__ - Step 28562: {'lr': 0.0004613063206480649, 'samples': 5483904, 'steps': 28561, 'loss/train': 1.250970482826233}
+08/30/2021 18:16:31 - INFO - __main__ - Step 28563: {'lr': 0.000461303484622351, 'samples': 5484096, 'steps': 28562, 'loss/train': 1.0326673984527588}
+08/30/2021 18:16:32 - INFO - __main__ - Step 28564: {'lr': 0.00046130064850142703, 'samples': 5484288, 'steps': 28563, 'loss/train': 1.2959872484207153}
+08/30/2021 18:16:33 - INFO - __main__ - Step 28565: {'lr': 0.0004612978122852942, 'samples': 5484480, 'steps': 28564, 'loss/train': 2.220444440841675}
+08/30/2021 18:16:33 - INFO - __main__ - Step 28566: {'lr': 0.000461294975973954, 'samples': 5484672, 'steps': 28565, 'loss/train': 1.4092081785202026}
+08/30/2021 18:16:34 - INFO - __main__ - Step 28567: {'lr': 0.0004612921395674074, 'samples': 5484864, 'steps': 28566, 'loss/train': 1.0749324560165405}
+08/30/2021 18:16:34 - INFO - __main__ - Step 28568: {'lr': 0.0004612893030656559, 'samples': 5485056, 'steps': 28567, 'loss/train': 0.9329726099967957}
+08/30/2021 18:16:36 - INFO - __main__ - Step 28569: {'lr': 0.0004612864664687007, 'samples': 5485248, 'steps': 28568, 'loss/train': 1.4765939712524414}
+08/30/2021 18:16:36 - INFO - __main__ - Step 28570: {'lr': 0.0004612836297765429, 'samples': 5485440, 'steps': 28569, 'loss/train': 1.9534573554992676}
+08/30/2021 18:16:37 - INFO - __main__ - Step 28571: {'lr': 0.00046128079298918414, 'samples': 5485632, 'steps': 28570, 'loss/train': 0.09738225489854813}
+08/30/2021 18:16:37 - INFO - __main__ - Step 28572: {'lr': 0.00046127795610662547, 'samples': 5485824, 'steps': 28571, 'loss/train': 0.056263361126184464}
+08/30/2021 18:16:37 - INFO - __main__ - Step 28573: {'lr': 0.0004612751191288682, 'samples': 5486016, 'steps': 28572, 'loss/train': 2.102567434310913}
+08/30/2021 18:16:38 - INFO - __main__ - Step 28574: {'lr': 0.00046127228205591366, 'samples': 5486208, 'steps': 28573, 'loss/train': 0.9623347520828247}
+08/30/2021 18:16:39 - INFO - __main__ - Step 28575: {'lr': 0.0004612694448877631, 'samples': 5486400, 'steps': 28574, 'loss/train': 0.7900848984718323}
+08/30/2021 18:16:40 - INFO - __main__ - Step 28576: {'lr': 0.00046126660762441774, 'samples': 5486592, 'steps': 28575, 'loss/train': 1.0455816984176636}
+08/30/2021 18:16:40 - INFO - __main__ - Step 28577: {'lr': 0.00046126377026587897, 'samples': 5486784, 'steps': 28576, 'loss/train': 1.4658417701721191}
+08/30/2021 18:16:40 - INFO - __main__ - Step 28578: {'lr': 0.0004612609328121479, 'samples': 5486976, 'steps': 28577, 'loss/train': 0.8452721834182739}
+08/30/2021 18:16:41 - INFO - __main__ - Step 28579: {'lr': 0.000461258095263226, 'samples': 5487168, 'steps': 28578, 'loss/train': 1.8922438621520996}
+08/30/2021 18:16:43 - INFO - __main__ - Step 28580: {'lr': 0.00046125525761911445, 'samples': 5487360, 'steps': 28579, 'loss/train': 2.147704839706421}
+08/30/2021 18:16:43 - INFO - __main__ - Step 28581: {'lr': 0.00046125241987981445, 'samples': 5487552, 'steps': 28580, 'loss/train': 1.194510817527771}
+08/30/2021 18:16:44 - INFO - __main__ - Step 28582: {'lr': 0.0004612495820453275, 'samples': 5487744, 'steps': 28581, 'loss/train': 1.61212956905365}
+08/30/2021 18:16:44 - INFO - __main__ - Step 28583: {'lr': 0.0004612467441156547, 'samples': 5487936, 'steps': 28582, 'loss/train': 1.9254000186920166}
+08/30/2021 18:16:44 - INFO - __main__ - Step 28584: {'lr': 0.00046124390609079735, 'samples': 5488128, 'steps': 28583, 'loss/train': 1.859422206878662}
+08/30/2021 18:16:45 - INFO - __main__ - Step 28585: {'lr': 0.00046124106797075683, 'samples': 5488320, 'steps': 28584, 'loss/train': 1.4304039478302002}
+08/30/2021 18:16:46 - INFO - __main__ - Step 28586: {'lr': 0.00046123822975553425, 'samples': 5488512, 'steps': 28585, 'loss/train': 0.14914561808109283}
+08/30/2021 18:16:47 - INFO - __main__ - Step 28587: {'lr': 0.00046123539144513103, 'samples': 5488704, 'steps': 28586, 'loss/train': 1.3258082866668701}
+08/30/2021 18:16:47 - INFO - __main__ - Step 28588: {'lr': 0.00046123255303954835, 'samples': 5488896, 'steps': 28587, 'loss/train': 1.047844409942627}
+08/30/2021 18:16:47 - INFO - __main__ - Step 28589: {'lr': 0.0004612297145387876, 'samples': 5489088, 'steps': 28588, 'loss/train': 1.5251235961914062}
+08/30/2021 18:16:48 - INFO - __main__ - Step 28590: {'lr': 0.00046122687594285, 'samples': 5489280, 'steps': 28589, 'loss/train': 1.2259701490402222}
+08/30/2021 18:16:49 - INFO - __main__ - Step 28591: {'lr': 0.0004612240372517368, 'samples': 5489472, 'steps': 28590, 'loss/train': 1.267090916633606}
+08/30/2021 18:16:50 - INFO - __main__ - Step 28592: {'lr': 0.00046122119846544936, 'samples': 5489664, 'steps': 28591, 'loss/train': 1.0689455270767212}
+08/30/2021 18:16:50 - INFO - __main__ - Step 28593: {'lr': 0.00046121835958398883, 'samples': 5489856, 'steps': 28592, 'loss/train': 1.6659600734710693}
+08/30/2021 18:16:50 - INFO - __main__ - Step 28594: {'lr': 0.0004612155206073566, 'samples': 5490048, 'steps': 28593, 'loss/train': 1.393333911895752}
+08/30/2021 18:16:51 - INFO - __main__ - Step 28595: {'lr': 0.000461212681535554, 'samples': 5490240, 'steps': 28594, 'loss/train': 1.847856879234314}
+08/30/2021 18:16:51 - INFO - __main__ - Step 28596: {'lr': 0.0004612098423685821, 'samples': 5490432, 'steps': 28595, 'loss/train': 1.8090723752975464}
+08/30/2021 18:16:53 - INFO - __main__ - Step 28597: {'lr': 0.0004612070031064424, 'samples': 5490624, 'steps': 28596, 'loss/train': 1.2842819690704346}
+08/30/2021 18:16:54 - INFO - __main__ - Step 28598: {'lr': 0.000461204163749136, 'samples': 5490816, 'steps': 28597, 'loss/train': 1.440927505493164}
+08/30/2021 18:16:54 - INFO - __main__ - Step 28599: {'lr': 0.0004612013242966643, 'samples': 5491008, 'steps': 28598, 'loss/train': 1.4508466720581055}
+08/30/2021 18:16:54 - INFO - __main__ - Step 28600: {'lr': 0.0004611984847490285, 'samples': 5491200, 'steps': 28599, 'loss/train': 2.039684534072876}
+08/30/2021 18:16:55 - INFO - __main__ - Step 28601: {'lr': 0.00046119564510623, 'samples': 5491392, 'steps': 28600, 'loss/train': 1.1459662914276123}
+08/30/2021 18:16:57 - INFO - __main__ - Step 28602: {'lr': 0.00046119280536827, 'samples': 5491584, 'steps': 28601, 'loss/train': 9.737241744995117}
+08/30/2021 18:16:57 - INFO - __main__ - Step 28603: {'lr': 0.0004611899655351497, 'samples': 5491776, 'steps': 28602, 'loss/train': 1.809079647064209}
+08/30/2021 18:16:57 - INFO - __main__ - Step 28604: {'lr': 0.0004611871256068705, 'samples': 5491968, 'steps': 28603, 'loss/train': 1.655714988708496}
+08/30/2021 18:16:58 - INFO - __main__ - Step 28605: {'lr': 0.0004611842855834336, 'samples': 5492160, 'steps': 28604, 'loss/train': 1.823891520500183}
+08/30/2021 18:16:58 - INFO - __main__ - Step 28606: {'lr': 0.00046118144546484043, 'samples': 5492352, 'steps': 28605, 'loss/train': 0.7643401026725769}
+08/30/2021 18:16:58 - INFO - __main__ - Step 28607: {'lr': 0.0004611786052510921, 'samples': 5492544, 'steps': 28606, 'loss/train': 1.5874062776565552}
+08/30/2021 18:17:00 - INFO - __main__ - Step 28608: {'lr': 0.0004611757649421899, 'samples': 5492736, 'steps': 28607, 'loss/train': 1.956817626953125}
+08/30/2021 18:17:01 - INFO - __main__ - Step 28609: {'lr': 0.0004611729245381352, 'samples': 5492928, 'steps': 28608, 'loss/train': 1.2808642387390137}
+08/30/2021 18:17:01 - INFO - __main__ - Step 28610: {'lr': 0.00046117008403892925, 'samples': 5493120, 'steps': 28609, 'loss/train': 1.8965907096862793}
+08/30/2021 18:17:01 - INFO - __main__ - Step 28611: {'lr': 0.0004611672434445733, 'samples': 5493312, 'steps': 28610, 'loss/train': 1.635274052619934}
+08/30/2021 18:17:02 - INFO - __main__ - Step 28612: {'lr': 0.0004611644027550687, 'samples': 5493504, 'steps': 28611, 'loss/train': 1.6674134731292725}
+08/30/2021 18:17:03 - INFO - __main__ - Step 28613: {'lr': 0.00046116156197041657, 'samples': 5493696, 'steps': 28612, 'loss/train': 1.4661076068878174}
+08/30/2021 18:17:04 - INFO - __main__ - Step 28614: {'lr': 0.0004611587210906184, 'samples': 5493888, 'steps': 28613, 'loss/train': 1.6048845052719116}
+08/30/2021 18:17:04 - INFO - __main__ - Step 28615: {'lr': 0.0004611558801156753, 'samples': 5494080, 'steps': 28614, 'loss/train': 0.12729088962078094}
+08/30/2021 18:17:04 - INFO - __main__ - Step 28616: {'lr': 0.0004611530390455887, 'samples': 5494272, 'steps': 28615, 'loss/train': 1.6169594526290894}
+08/30/2021 18:17:05 - INFO - __main__ - Step 28617: {'lr': 0.00046115019788035974, 'samples': 5494464, 'steps': 28616, 'loss/train': 1.4557987451553345}
+08/30/2021 18:17:07 - INFO - __main__ - Step 28618: {'lr': 0.00046114735661998975, 'samples': 5494656, 'steps': 28617, 'loss/train': 2.5542166233062744}
+08/30/2021 18:17:07 - INFO - __main__ - Step 28619: {'lr': 0.0004611445152644801, 'samples': 5494848, 'steps': 28618, 'loss/train': 0.11091788113117218}
+08/30/2021 18:17:08 - INFO - __main__ - Step 28620: {'lr': 0.00046114167381383186, 'samples': 5495040, 'steps': 28619, 'loss/train': 1.2085102796554565}
+08/30/2021 18:17:08 - INFO - __main__ - Step 28621: {'lr': 0.0004611388322680465, 'samples': 5495232, 'steps': 28620, 'loss/train': 1.140795111656189}
+08/30/2021 18:17:08 - INFO - __main__ - Step 28622: {'lr': 0.0004611359906271253, 'samples': 5495424, 'steps': 28621, 'loss/train': 1.7540414333343506}
+08/30/2021 18:17:10 - INFO - __main__ - Step 28623: {'lr': 0.0004611331488910694, 'samples': 5495616, 'steps': 28622, 'loss/train': 1.9007771015167236}
+08/30/2021 18:17:10 - INFO - __main__ - Step 28624: {'lr': 0.00046113030705988026, 'samples': 5495808, 'steps': 28623, 'loss/train': 1.7109884023666382}
+08/30/2021 18:17:11 - INFO - __main__ - Step 28625: {'lr': 0.000461127465133559, 'samples': 5496000, 'steps': 28624, 'loss/train': 1.7091494798660278}
+08/30/2021 18:17:11 - INFO - __main__ - Step 28626: {'lr': 0.0004611246231121069, 'samples': 5496192, 'steps': 28625, 'loss/train': 1.8191943168640137}
+08/30/2021 18:17:12 - INFO - __main__ - Step 28627: {'lr': 0.00046112178099552535, 'samples': 5496384, 'steps': 28626, 'loss/train': 1.2781901359558105}
+08/30/2021 18:17:13 - INFO - __main__ - Step 28628: {'lr': 0.0004611189387838156, 'samples': 5496576, 'steps': 28627, 'loss/train': 0.9486587047576904}
+08/30/2021 18:17:13 - INFO - __main__ - Step 28629: {'lr': 0.00046111609647697893, 'samples': 5496768, 'steps': 28628, 'loss/train': 0.8507620692253113}
+08/30/2021 18:17:14 - INFO - __main__ - Step 28630: {'lr': 0.0004611132540750166, 'samples': 5496960, 'steps': 28629, 'loss/train': 2.0000696182250977}
+08/30/2021 18:17:14 - INFO - __main__ - Step 28631: {'lr': 0.00046111041157792987, 'samples': 5497152, 'steps': 28630, 'loss/train': 1.7961006164550781}
+08/30/2021 18:17:14 - INFO - __main__ - Step 28632: {'lr': 0.00046110756898572, 'samples': 5497344, 'steps': 28631, 'loss/train': 1.5291951894760132}
+08/30/2021 18:17:15 - INFO - __main__ - Step 28633: {'lr': 0.0004611047262983884, 'samples': 5497536, 'steps': 28632, 'loss/train': 1.3961063623428345}
+08/30/2021 18:17:16 - INFO - __main__ - Step 28634: {'lr': 0.00046110188351593625, 'samples': 5497728, 'steps': 28633, 'loss/train': 1.6091190576553345}
+08/30/2021 18:17:17 - INFO - __main__ - Step 28635: {'lr': 0.0004610990406383648, 'samples': 5497920, 'steps': 28634, 'loss/train': 0.5210306644439697}
+08/30/2021 18:17:17 - INFO - __main__ - Step 28636: {'lr': 0.00046109619766567547, 'samples': 5498112, 'steps': 28635, 'loss/train': 1.5592787265777588}
+08/30/2021 18:17:18 - INFO - __main__ - Step 28637: {'lr': 0.0004610933545978694, 'samples': 5498304, 'steps': 28636, 'loss/train': 0.9747006297111511}
+08/30/2021 18:17:18 - INFO - __main__ - Step 28638: {'lr': 0.0004610905114349478, 'samples': 5498496, 'steps': 28637, 'loss/train': 1.6787627935409546}
+08/30/2021 18:17:19 - INFO - __main__ - Step 28639: {'lr': 0.0004610876681769123, 'samples': 5498688, 'steps': 28638, 'loss/train': 1.808143973350525}
+08/30/2021 18:17:20 - INFO - __main__ - Step 28640: {'lr': 0.0004610848248237638, 'samples': 5498880, 'steps': 28639, 'loss/train': 1.4617542028427124}
+08/30/2021 18:17:20 - INFO - __main__ - Step 28641: {'lr': 0.00046108198137550377, 'samples': 5499072, 'steps': 28640, 'loss/train': 1.4664337635040283}
+08/30/2021 18:17:21 - INFO - __main__ - Step 28642: {'lr': 0.0004610791378321335, 'samples': 5499264, 'steps': 28641, 'loss/train': 1.9164260625839233}
+08/30/2021 18:17:21 - INFO - __main__ - Step 28643: {'lr': 0.0004610762941936542, 'samples': 5499456, 'steps': 28642, 'loss/train': 1.7378405332565308}
+08/30/2021 18:17:23 - INFO - __main__ - Step 28644: {'lr': 0.0004610734504600671, 'samples': 5499648, 'steps': 28643, 'loss/train': 1.5796711444854736}
+08/30/2021 18:17:23 - INFO - __main__ - Step 28645: {'lr': 0.00046107060663137366, 'samples': 5499840, 'steps': 28644, 'loss/train': 1.4716848134994507}
+08/30/2021 18:17:23 - INFO - __main__ - Step 28646: {'lr': 0.00046106776270757506, 'samples': 5500032, 'steps': 28645, 'loss/train': 1.6572840213775635}
+08/30/2021 18:17:24 - INFO - __main__ - Step 28647: {'lr': 0.0004610649186886725, 'samples': 5500224, 'steps': 28646, 'loss/train': 1.657213568687439}
+08/30/2021 18:17:24 - INFO - __main__ - Step 28648: {'lr': 0.00046106207457466744, 'samples': 5500416, 'steps': 28647, 'loss/train': 1.7196182012557983}
+08/30/2021 18:17:26 - INFO - __main__ - Step 28649: {'lr': 0.0004610592303655611, 'samples': 5500608, 'steps': 28648, 'loss/train': 1.4266602993011475}
+08/30/2021 18:17:26 - INFO - __main__ - Step 28650: {'lr': 0.0004610563860613546, 'samples': 5500800, 'steps': 28649, 'loss/train': 2.1116340160369873}
+08/30/2021 18:17:27 - INFO - __main__ - Step 28651: {'lr': 0.00046105354166204937, 'samples': 5500992, 'steps': 28650, 'loss/train': 1.671355962753296}
+08/30/2021 18:17:27 - INFO - __main__ - Step 28652: {'lr': 0.00046105069716764676, 'samples': 5501184, 'steps': 28651, 'loss/train': 0.30662935972213745}
+08/30/2021 18:17:27 - INFO - __main__ - Step 28653: {'lr': 0.00046104785257814786, 'samples': 5501376, 'steps': 28652, 'loss/train': 1.6948570013046265}
+08/30/2021 18:17:28 - INFO - __main__ - Step 28654: {'lr': 0.0004610450078935541, 'samples': 5501568, 'steps': 28653, 'loss/train': 1.4901260137557983}
+08/30/2021 18:17:29 - INFO - __main__ - Step 28655: {'lr': 0.00046104216311386676, 'samples': 5501760, 'steps': 28654, 'loss/train': 1.6524717807769775}
+08/30/2021 18:17:30 - INFO - __main__ - Step 28656: {'lr': 0.000461039318239087, 'samples': 5501952, 'steps': 28655, 'loss/train': 1.4687788486480713}
+08/30/2021 18:17:30 - INFO - __main__ - Step 28657: {'lr': 0.00046103647326921625, 'samples': 5502144, 'steps': 28656, 'loss/train': 1.4570131301879883}
+08/30/2021 18:17:30 - INFO - __main__ - Step 28658: {'lr': 0.00046103362820425567, 'samples': 5502336, 'steps': 28657, 'loss/train': 0.17846554517745972}
+08/30/2021 18:17:31 - INFO - __main__ - Step 28659: {'lr': 0.00046103078304420665, 'samples': 5502528, 'steps': 28658, 'loss/train': 1.890275239944458}
+08/30/2021 18:17:32 - INFO - __main__ - Step 28660: {'lr': 0.0004610279377890704, 'samples': 5502720, 'steps': 28659, 'loss/train': 1.4584637880325317}
+08/30/2021 18:17:33 - INFO - __main__ - Step 28661: {'lr': 0.00046102509243884813, 'samples': 5502912, 'steps': 28660, 'loss/train': 1.3846909999847412}
+08/30/2021 18:17:33 - INFO - __main__ - Step 28662: {'lr': 0.0004610222469935413, 'samples': 5503104, 'steps': 28661, 'loss/train': 1.1878535747528076}
+08/30/2021 18:17:33 - INFO - __main__ - Step 28663: {'lr': 0.000461019401453151, 'samples': 5503296, 'steps': 28662, 'loss/train': 1.9918683767318726}
+08/30/2021 18:17:34 - INFO - __main__ - Step 28664: {'lr': 0.00046101655581767874, 'samples': 5503488, 'steps': 28663, 'loss/train': 1.6148306131362915}
+08/30/2021 18:17:35 - INFO - __main__ - Step 28665: {'lr': 0.0004610137100871257, 'samples': 5503680, 'steps': 28664, 'loss/train': 2.0255563259124756}
+08/30/2021 18:17:36 - INFO - __main__ - Step 28666: {'lr': 0.00046101086426149297, 'samples': 5503872, 'steps': 28665, 'loss/train': 1.5599926710128784}
+08/30/2021 18:17:36 - INFO - __main__ - Step 28667: {'lr': 0.0004610080183407821, 'samples': 5504064, 'steps': 28666, 'loss/train': 1.6037590503692627}
+08/30/2021 18:17:36 - INFO - __main__ - Step 28668: {'lr': 0.0004610051723249943, 'samples': 5504256, 'steps': 28667, 'loss/train': 1.7684967517852783}
+08/30/2021 18:17:37 - INFO - __main__ - Step 28669: {'lr': 0.0004610023262141308, 'samples': 5504448, 'steps': 28668, 'loss/train': 1.2390328645706177}
+08/30/2021 18:17:39 - INFO - __main__ - Step 28670: {'lr': 0.00046099948000819294, 'samples': 5504640, 'steps': 28669, 'loss/train': 0.09077593684196472}
+08/30/2021 18:17:40 - INFO - __main__ - Step 28671: {'lr': 0.0004609966337071819, 'samples': 5504832, 'steps': 28670, 'loss/train': 1.1359988451004028}
+08/30/2021 18:17:40 - INFO - __main__ - Step 28672: {'lr': 0.00046099378731109906, 'samples': 5505024, 'steps': 28671, 'loss/train': 0.1055753082036972}
+08/30/2021 18:17:40 - INFO - __main__ - Step 28673: {'lr': 0.00046099094081994565, 'samples': 5505216, 'steps': 28672, 'loss/train': 1.326877474784851}
+08/30/2021 18:17:41 - INFO - __main__ - Step 28674: {'lr': 0.000460988094233723, 'samples': 5505408, 'steps': 28673, 'loss/train': 1.7359426021575928}
+08/30/2021 18:17:42 - INFO - __main__ - Step 28675: {'lr': 0.00046098524755243246, 'samples': 5505600, 'steps': 28674, 'loss/train': 2.0015597343444824}
+08/30/2021 18:17:43 - INFO - __main__ - Step 28676: {'lr': 0.0004609824007760751, 'samples': 5505792, 'steps': 28675, 'loss/train': 1.6945456266403198}
+08/30/2021 18:17:43 - INFO - __main__ - Step 28677: {'lr': 0.0004609795539046524, 'samples': 5505984, 'steps': 28676, 'loss/train': 1.8516099452972412}
+08/30/2021 18:17:43 - INFO - __main__ - Step 28678: {'lr': 0.0004609767069381655, 'samples': 5506176, 'steps': 28677, 'loss/train': 0.09904380142688751}
+08/30/2021 18:17:44 - INFO - __main__ - Step 28679: {'lr': 0.00046097385987661576, 'samples': 5506368, 'steps': 28678, 'loss/train': 1.4202141761779785}
+08/30/2021 18:17:46 - INFO - __main__ - Step 28680: {'lr': 0.00046097101272000454, 'samples': 5506560, 'steps': 28679, 'loss/train': 1.6175774335861206}
+08/30/2021 18:17:46 - INFO - __main__ - Step 28681: {'lr': 0.0004609681654683329, 'samples': 5506752, 'steps': 28680, 'loss/train': 0.10689815133810043}
+08/30/2021 18:17:46 - INFO - __main__ - Step 28682: {'lr': 0.0004609653181216024, 'samples': 5506944, 'steps': 28681, 'loss/train': 1.893286108970642}
+08/30/2021 18:17:47 - INFO - __main__ - Step 28683: {'lr': 0.0004609624706798141, 'samples': 5507136, 'steps': 28682, 'loss/train': 1.6242172718048096}
+08/30/2021 18:17:47 - INFO - __main__ - Step 28684: {'lr': 0.00046095962314296934, 'samples': 5507328, 'steps': 28683, 'loss/train': 1.661780834197998}
+08/30/2021 18:17:49 - INFO - __main__ - Step 28685: {'lr': 0.00046095677551106953, 'samples': 5507520, 'steps': 28684, 'loss/train': 1.8052581548690796}
+08/30/2021 18:17:49 - INFO - __main__ - Step 28686: {'lr': 0.00046095392778411576, 'samples': 5507712, 'steps': 28685, 'loss/train': 1.7522753477096558}
+08/30/2021 18:17:49 - INFO - __main__ - Step 28687: {'lr': 0.0004609510799621095, 'samples': 5507904, 'steps': 28686, 'loss/train': 0.726565420627594}
+08/30/2021 18:17:50 - INFO - __main__ - Step 28688: {'lr': 0.0004609482320450519, 'samples': 5508096, 'steps': 28687, 'loss/train': 1.686182975769043}
+08/30/2021 18:17:50 - INFO - __main__ - Step 28689: {'lr': 0.00046094538403294416, 'samples': 5508288, 'steps': 28688, 'loss/train': 2.193859100341797}
+08/30/2021 18:17:51 - INFO - __main__ - Step 28690: {'lr': 0.00046094253592578784, 'samples': 5508480, 'steps': 28689, 'loss/train': 2.0816071033477783}
+08/30/2021 18:17:52 - INFO - __main__ - Step 28691: {'lr': 0.000460939687723584, 'samples': 5508672, 'steps': 28690, 'loss/train': 1.7358242273330688}
+08/30/2021 18:17:52 - INFO - __main__ - Step 28692: {'lr': 0.000460936839426334, 'samples': 5508864, 'steps': 28691, 'loss/train': 1.5767308473587036}
+08/30/2021 18:17:53 - INFO - __main__ - Step 28693: {'lr': 0.00046093399103403913, 'samples': 5509056, 'steps': 28692, 'loss/train': 1.9537839889526367}
+08/30/2021 18:17:53 - INFO - __main__ - Step 28694: {'lr': 0.00046093114254670066, 'samples': 5509248, 'steps': 28693, 'loss/train': 0.5270798206329346}
+08/30/2021 18:17:55 - INFO - __main__ - Step 28695: {'lr': 0.0004609282939643199, 'samples': 5509440, 'steps': 28694, 'loss/train': 1.5301392078399658}
+08/30/2021 18:17:55 - INFO - __main__ - Step 28696: {'lr': 0.00046092544528689806, 'samples': 5509632, 'steps': 28695, 'loss/train': 1.502647876739502}
+08/30/2021 18:17:55 - INFO - __main__ - Step 28697: {'lr': 0.0004609225965144365, 'samples': 5509824, 'steps': 28696, 'loss/train': 1.330797791481018}
+08/30/2021 18:17:56 - INFO - __main__ - Step 28698: {'lr': 0.00046091974764693645, 'samples': 5510016, 'steps': 28697, 'loss/train': 1.330105185508728}
+08/30/2021 18:17:56 - INFO - __main__ - Step 28699: {'lr': 0.0004609168986843992, 'samples': 5510208, 'steps': 28698, 'loss/train': 1.7887258529663086}
+08/30/2021 18:17:56 - INFO - __main__ - Step 28700: {'lr': 0.000460914049626826, 'samples': 5510400, 'steps': 28699, 'loss/train': 2.4512386322021484}
+08/30/2021 18:17:58 - INFO - __main__ - Step 28701: {'lr': 0.0004609112004742183, 'samples': 5510592, 'steps': 28700, 'loss/train': 1.8095072507858276}
+08/30/2021 18:17:59 - INFO - __main__ - Step 28702: {'lr': 0.0004609083512265773, 'samples': 5510784, 'steps': 28701, 'loss/train': 1.917091727256775}
+08/30/2021 18:17:59 - INFO - __main__ - Step 28703: {'lr': 0.0004609055018839041, 'samples': 5510976, 'steps': 28702, 'loss/train': 1.2911368608474731}
+08/30/2021 18:17:59 - INFO - __main__ - Step 28704: {'lr': 0.0004609026524462002, 'samples': 5511168, 'steps': 28703, 'loss/train': 0.9765636324882507}
+08/30/2021 18:18:00 - INFO - __main__ - Step 28705: {'lr': 0.00046089980291346685, 'samples': 5511360, 'steps': 28704, 'loss/train': 1.4764583110809326}
+08/30/2021 18:18:00 - INFO - __main__ - Step 28706: {'lr': 0.00046089695328570523, 'samples': 5511552, 'steps': 28705, 'loss/train': 1.5844409465789795}
+08/30/2021 18:18:02 - INFO - __main__ - Step 28707: {'lr': 0.0004608941035629168, 'samples': 5511744, 'steps': 28706, 'loss/train': 1.1635280847549438}
+08/30/2021 18:18:02 - INFO - __main__ - Step 28708: {'lr': 0.0004608912537451027, 'samples': 5511936, 'steps': 28707, 'loss/train': 1.0059483051300049}
+08/30/2021 18:18:02 - INFO - __main__ - Step 28709: {'lr': 0.0004608884038322642, 'samples': 5512128, 'steps': 28708, 'loss/train': 2.412945032119751}
+08/30/2021 18:18:03 - INFO - __main__ - Step 28710: {'lr': 0.00046088555382440275, 'samples': 5512320, 'steps': 28709, 'loss/train': 1.2494611740112305}
+08/30/2021 18:18:03 - INFO - __main__ - Step 28711: {'lr': 0.0004608827037215194, 'samples': 5512512, 'steps': 28710, 'loss/train': 1.1306918859481812}
+08/30/2021 18:18:04 - INFO - __main__ - Step 28712: {'lr': 0.0004608798535236156, 'samples': 5512704, 'steps': 28711, 'loss/train': 1.6654123067855835}
+08/30/2021 18:18:05 - INFO - __main__ - Step 28713: {'lr': 0.0004608770032306926, 'samples': 5512896, 'steps': 28712, 'loss/train': 1.8448811769485474}
+08/30/2021 18:18:05 - INFO - __main__ - Step 28714: {'lr': 0.0004608741528427517, 'samples': 5513088, 'steps': 28713, 'loss/train': 1.4382745027542114}
+08/30/2021 18:18:06 - INFO - __main__ - Step 28715: {'lr': 0.0004608713023597941, 'samples': 5513280, 'steps': 28714, 'loss/train': 1.543492317199707}
+08/30/2021 18:18:06 - INFO - __main__ - Step 28716: {'lr': 0.00046086845178182123, 'samples': 5513472, 'steps': 28715, 'loss/train': 1.132645845413208}
+08/30/2021 18:18:08 - INFO - __main__ - Step 28717: {'lr': 0.00046086560110883423, 'samples': 5513664, 'steps': 28716, 'loss/train': 1.647782325744629}
+08/30/2021 18:18:08 - INFO - __main__ - Step 28718: {'lr': 0.00046086275034083453, 'samples': 5513856, 'steps': 28717, 'loss/train': 1.545560359954834}
+08/30/2021 18:18:09 - INFO - __main__ - Step 28719: {'lr': 0.00046085989947782327, 'samples': 5514048, 'steps': 28718, 'loss/train': 1.9469356536865234}
+08/30/2021 18:18:09 - INFO - __main__ - Step 28720: {'lr': 0.00046085704851980174, 'samples': 5514240, 'steps': 28719, 'loss/train': 0.14269833266735077}
+08/30/2021 18:18:09 - INFO - __main__ - Step 28721: {'lr': 0.00046085419746677136, 'samples': 5514432, 'steps': 28720, 'loss/train': 1.31236732006073}
+08/30/2021 18:18:11 - INFO - __main__ - Step 28722: {'lr': 0.00046085134631873326, 'samples': 5514624, 'steps': 28721, 'loss/train': 1.4599498510360718}
+08/30/2021 18:18:11 - INFO - __main__ - Step 28723: {'lr': 0.0004608484950756888, 'samples': 5514816, 'steps': 28722, 'loss/train': 1.5662461519241333}
+08/30/2021 18:18:11 - INFO - __main__ - Step 28724: {'lr': 0.0004608456437376393, 'samples': 5515008, 'steps': 28723, 'loss/train': 1.6499756574630737}
+08/30/2021 18:18:12 - INFO - __main__ - Step 28725: {'lr': 0.000460842792304586, 'samples': 5515200, 'steps': 28724, 'loss/train': 1.1057729721069336}
+08/30/2021 18:18:12 - INFO - __main__ - Step 28726: {'lr': 0.00046083994077653024, 'samples': 5515392, 'steps': 28725, 'loss/train': 1.292879581451416}
+08/30/2021 18:18:14 - INFO - __main__ - Step 28727: {'lr': 0.0004608370891534732, 'samples': 5515584, 'steps': 28726, 'loss/train': 1.3703200817108154}
+08/30/2021 18:18:15 - INFO - __main__ - Step 28728: {'lr': 0.0004608342374354162, 'samples': 5515776, 'steps': 28727, 'loss/train': 1.7802619934082031}
+08/30/2021 18:18:15 - INFO - __main__ - Step 28729: {'lr': 0.0004608313856223606, 'samples': 5515968, 'steps': 28728, 'loss/train': 2.003765106201172}
+08/30/2021 18:18:16 - INFO - __main__ - Step 28730: {'lr': 0.00046082853371430754, 'samples': 5516160, 'steps': 28729, 'loss/train': 1.603506088256836}
+08/30/2021 18:18:16 - INFO - __main__ - Step 28731: {'lr': 0.0004608256817112585, 'samples': 5516352, 'steps': 28730, 'loss/train': 1.374673843383789}
+08/30/2021 18:18:17 - INFO - __main__ - Step 28732: {'lr': 0.00046082282961321466, 'samples': 5516544, 'steps': 28731, 'loss/train': 1.6801224946975708}
+08/30/2021 18:18:18 - INFO - __main__ - Step 28733: {'lr': 0.00046081997742017725, 'samples': 5516736, 'steps': 28732, 'loss/train': 1.1425230503082275}
+08/30/2021 18:18:18 - INFO - __main__ - Step 28734: {'lr': 0.00046081712513214757, 'samples': 5516928, 'steps': 28733, 'loss/train': 1.9179368019104004}
+08/30/2021 18:18:19 - INFO - __main__ - Step 28735: {'lr': 0.0004608142727491271, 'samples': 5517120, 'steps': 28734, 'loss/train': 1.8448516130447388}
+08/30/2021 18:18:19 - INFO - __main__ - Step 28736: {'lr': 0.00046081142027111683, 'samples': 5517312, 'steps': 28735, 'loss/train': 1.168526530265808}
+08/30/2021 18:18:21 - INFO - __main__ - Step 28737: {'lr': 0.0004608085676981182, 'samples': 5517504, 'steps': 28736, 'loss/train': 1.8542293310165405}
+08/30/2021 18:18:21 - INFO - __main__ - Step 28738: {'lr': 0.0004608057150301326, 'samples': 5517696, 'steps': 28737, 'loss/train': 0.9919119477272034}
+08/30/2021 18:18:21 - INFO - __main__ - Step 28739: {'lr': 0.00046080286226716106, 'samples': 5517888, 'steps': 28738, 'loss/train': 0.2748536765575409}
+08/30/2021 18:18:22 - INFO - __main__ - Step 28740: {'lr': 0.00046080000940920506, 'samples': 5518080, 'steps': 28739, 'loss/train': 1.6069672107696533}
+08/30/2021 18:18:22 - INFO - __main__ - Step 28741: {'lr': 0.00046079715645626584, 'samples': 5518272, 'steps': 28740, 'loss/train': 0.7914718389511108}
+08/30/2021 18:18:23 - INFO - __main__ - Step 28742: {'lr': 0.00046079430340834467, 'samples': 5518464, 'steps': 28741, 'loss/train': 1.358385443687439}
+08/30/2021 18:18:24 - INFO - __main__ - Step 28743: {'lr': 0.00046079145026544277, 'samples': 5518656, 'steps': 28742, 'loss/train': 1.2105307579040527}
+08/30/2021 18:18:24 - INFO - __main__ - Step 28744: {'lr': 0.0004607885970275616, 'samples': 5518848, 'steps': 28743, 'loss/train': 1.393981695175171}
+08/30/2021 18:18:25 - INFO - __main__ - Step 28745: {'lr': 0.0004607857436947023, 'samples': 5519040, 'steps': 28744, 'loss/train': 1.690173864364624}
+08/30/2021 18:18:25 - INFO - __main__ - Step 28746: {'lr': 0.00046078289026686616, 'samples': 5519232, 'steps': 28745, 'loss/train': 1.5842844247817993}
+08/30/2021 18:18:25 - INFO - __main__ - Step 28747: {'lr': 0.00046078003674405457, 'samples': 5519424, 'steps': 28746, 'loss/train': 1.2636808156967163}
+08/30/2021 18:18:27 - INFO - __main__ - Step 28748: {'lr': 0.0004607771831262687, 'samples': 5519616, 'steps': 28747, 'loss/train': 0.9195443391799927}
+08/30/2021 18:18:27 - INFO - __main__ - Step 28749: {'lr': 0.00046077432941350993, 'samples': 5519808, 'steps': 28748, 'loss/train': 1.424353837966919}
+08/30/2021 18:18:28 - INFO - __main__ - Step 28750: {'lr': 0.00046077147560577943, 'samples': 5520000, 'steps': 28749, 'loss/train': 1.416340947151184}
+08/30/2021 18:18:28 - INFO - __main__ - Step 28751: {'lr': 0.0004607686217030786, 'samples': 5520192, 'steps': 28750, 'loss/train': 1.5812209844589233}
+08/30/2021 18:18:28 - INFO - __main__ - Step 28752: {'lr': 0.00046076576770540865, 'samples': 5520384, 'steps': 28751, 'loss/train': 1.2292712926864624}
+08/30/2021 18:18:30 - INFO - __main__ - Step 28753: {'lr': 0.00046076291361277097, 'samples': 5520576, 'steps': 28752, 'loss/train': 1.74449622631073}
+08/30/2021 18:18:31 - INFO - __main__ - Step 28754: {'lr': 0.00046076005942516666, 'samples': 5520768, 'steps': 28753, 'loss/train': 1.7540959119796753}
+08/30/2021 18:18:31 - INFO - __main__ - Step 28755: {'lr': 0.0004607572051425972, 'samples': 5520960, 'steps': 28754, 'loss/train': 1.4322564601898193}
+08/30/2021 18:18:32 - INFO - __main__ - Step 28756: {'lr': 0.00046075435076506376, 'samples': 5521152, 'steps': 28755, 'loss/train': 0.1628573089838028}
+08/30/2021 18:18:32 - INFO - __main__ - Step 28757: {'lr': 0.0004607514962925677, 'samples': 5521344, 'steps': 28756, 'loss/train': 1.1711376905441284}
+08/30/2021 18:18:33 - INFO - __main__ - Step 28758: {'lr': 0.00046074864172511025, 'samples': 5521536, 'steps': 28757, 'loss/train': 0.9528539776802063}
+08/30/2021 18:18:34 - INFO - __main__ - Step 28759: {'lr': 0.0004607457870626928, 'samples': 5521728, 'steps': 28758, 'loss/train': 1.6156426668167114}
+08/30/2021 18:18:34 - INFO - __main__ - Step 28760: {'lr': 0.0004607429323053164, 'samples': 5521920, 'steps': 28759, 'loss/train': 1.670474648475647}
+08/30/2021 18:18:34 - INFO - __main__ - Step 28761: {'lr': 0.0004607400774529825, 'samples': 5522112, 'steps': 28760, 'loss/train': 1.3794561624526978}
+08/30/2021 18:18:35 - INFO - __main__ - Step 28762: {'lr': 0.0004607372225056925, 'samples': 5522304, 'steps': 28761, 'loss/train': 1.0120388269424438}
+08/30/2021 18:18:36 - INFO - __main__ - Step 28763: {'lr': 0.00046073436746344744, 'samples': 5522496, 'steps': 28762, 'loss/train': 1.1292396783828735}
+08/30/2021 18:18:37 - INFO - __main__ - Step 28764: {'lr': 0.0004607315123262488, 'samples': 5522688, 'steps': 28763, 'loss/train': 1.728515625}
+08/30/2021 18:18:37 - INFO - __main__ - Step 28765: {'lr': 0.0004607286570940977, 'samples': 5522880, 'steps': 28764, 'loss/train': 1.4552578926086426}
+08/30/2021 18:18:37 - INFO - __main__ - Step 28766: {'lr': 0.0004607258017669956, 'samples': 5523072, 'steps': 28765, 'loss/train': 1.4807502031326294}
+08/30/2021 18:18:38 - INFO - __main__ - Step 28767: {'lr': 0.0004607229463449437, 'samples': 5523264, 'steps': 28766, 'loss/train': 1.7356168031692505}
+08/30/2021 18:18:38 - INFO - __main__ - Step 28768: {'lr': 0.00046072009082794333, 'samples': 5523456, 'steps': 28767, 'loss/train': 1.394574522972107}
+08/30/2021 18:18:40 - INFO - __main__ - Step 28769: {'lr': 0.00046071723521599563, 'samples': 5523648, 'steps': 28768, 'loss/train': 1.4062213897705078}
+08/30/2021 18:18:40 - INFO - __main__ - Step 28770: {'lr': 0.000460714379509102, 'samples': 5523840, 'steps': 28769, 'loss/train': 1.4895013570785522}
+08/30/2021 18:18:40 - INFO - __main__ - Step 28771: {'lr': 0.0004607115237072638, 'samples': 5524032, 'steps': 28770, 'loss/train': 1.6866536140441895}
+08/30/2021 18:18:41 - INFO - __main__ - Step 28772: {'lr': 0.00046070866781048225, 'samples': 5524224, 'steps': 28771, 'loss/train': 0.6956020593643188}
+08/30/2021 18:18:41 - INFO - __main__ - Step 28773: {'lr': 0.0004607058118187586, 'samples': 5524416, 'steps': 28772, 'loss/train': 1.3922953605651855}
+08/30/2021 18:18:43 - INFO - __main__ - Step 28774: {'lr': 0.00046070295573209406, 'samples': 5524608, 'steps': 28773, 'loss/train': 1.3464394807815552}
+08/30/2021 18:18:43 - INFO - __main__ - Step 28775: {'lr': 0.00046070009955049017, 'samples': 5524800, 'steps': 28774, 'loss/train': 1.44407057762146}
+08/30/2021 18:18:43 - INFO - __main__ - Step 28776: {'lr': 0.000460697243273948, 'samples': 5524992, 'steps': 28775, 'loss/train': 1.6780152320861816}
+08/30/2021 18:18:44 - INFO - __main__ - Step 28777: {'lr': 0.0004606943869024689, 'samples': 5525184, 'steps': 28776, 'loss/train': 1.5969003438949585}
+08/30/2021 18:18:44 - INFO - __main__ - Step 28778: {'lr': 0.0004606915304360542, 'samples': 5525376, 'steps': 28777, 'loss/train': 2.0217835903167725}
+08/30/2021 18:18:46 - INFO - __main__ - Step 28779: {'lr': 0.00046068867387470507, 'samples': 5525568, 'steps': 28778, 'loss/train': 1.3903378248214722}
+08/30/2021 18:18:47 - INFO - __main__ - Step 28780: {'lr': 0.00046068581721842294, 'samples': 5525760, 'steps': 28779, 'loss/train': 1.7632614374160767}
+08/30/2021 18:18:47 - INFO - __main__ - Step 28781: {'lr': 0.00046068296046720904, 'samples': 5525952, 'steps': 28780, 'loss/train': 1.5530871152877808}
+08/30/2021 18:18:48 - INFO - __main__ - Step 28782: {'lr': 0.0004606801036210646, 'samples': 5526144, 'steps': 28781, 'loss/train': 1.5877370834350586}
+08/30/2021 18:18:48 - INFO - __main__ - Step 28783: {'lr': 0.000460677246679991, 'samples': 5526336, 'steps': 28782, 'loss/train': 0.5917261242866516}
+08/30/2021 18:18:49 - INFO - __main__ - Step 28784: {'lr': 0.00046067438964398944, 'samples': 5526528, 'steps': 28783, 'loss/train': 1.719201683998108}
+08/30/2021 18:18:50 - INFO - __main__ - Step 28785: {'lr': 0.00046067153251306127, 'samples': 5526720, 'steps': 28784, 'loss/train': 0.9624534249305725}
+08/30/2021 18:18:50 - INFO - __main__ - Step 28786: {'lr': 0.0004606686752872078, 'samples': 5526912, 'steps': 28785, 'loss/train': 1.9532489776611328}
+08/30/2021 18:18:50 - INFO - __main__ - Step 28787: {'lr': 0.0004606658179664302, 'samples': 5527104, 'steps': 28786, 'loss/train': 1.748219609260559}
+08/30/2021 18:18:51 - INFO - __main__ - Step 28788: {'lr': 0.00046066296055072986, 'samples': 5527296, 'steps': 28787, 'loss/train': 1.2918643951416016}
+08/30/2021 18:18:52 - INFO - __main__ - Step 28789: {'lr': 0.0004606601030401081, 'samples': 5527488, 'steps': 28788, 'loss/train': 1.6055225133895874}
+08/30/2021 18:18:53 - INFO - __main__ - Step 28790: {'lr': 0.0004606572454345661, 'samples': 5527680, 'steps': 28789, 'loss/train': 2.2760958671569824}
+08/30/2021 18:18:53 - INFO - __main__ - Step 28791: {'lr': 0.0004606543877341052, 'samples': 5527872, 'steps': 28790, 'loss/train': 1.3080912828445435}
+08/30/2021 18:18:54 - INFO - __main__ - Step 28792: {'lr': 0.00046065152993872665, 'samples': 5528064, 'steps': 28791, 'loss/train': 0.6149696111679077}
+08/30/2021 18:18:54 - INFO - __main__ - Step 28793: {'lr': 0.0004606486720484318, 'samples': 5528256, 'steps': 28792, 'loss/train': 1.9276411533355713}
+08/30/2021 18:18:55 - INFO - __main__ - Step 28794: {'lr': 0.0004606458140632219, 'samples': 5528448, 'steps': 28793, 'loss/train': 1.213881015777588}
+08/30/2021 18:18:56 - INFO - __main__ - Step 28795: {'lr': 0.0004606429559830982, 'samples': 5528640, 'steps': 28794, 'loss/train': 1.8192152976989746}
+08/30/2021 18:18:56 - INFO - __main__ - Step 28796: {'lr': 0.00046064009780806217, 'samples': 5528832, 'steps': 28795, 'loss/train': 1.3204809427261353}
+08/30/2021 18:18:57 - INFO - __main__ - Step 28797: {'lr': 0.0004606372395381149, 'samples': 5529024, 'steps': 28796, 'loss/train': 1.1457908153533936}
+08/30/2021 18:18:57 - INFO - __main__ - Step 28798: {'lr': 0.0004606343811732577, 'samples': 5529216, 'steps': 28797, 'loss/train': 1.4433735609054565}
+08/30/2021 18:18:58 - INFO - __main__ - Step 28799: {'lr': 0.0004606315227134919, 'samples': 5529408, 'steps': 28798, 'loss/train': 1.2644931077957153}
+08/30/2021 18:18:59 - INFO - __main__ - Step 28800: {'lr': 0.0004606286641588188, 'samples': 5529600, 'steps': 28799, 'loss/train': 1.5006144046783447}
+08/30/2021 18:18:59 - INFO - __main__ - Step 28801: {'lr': 0.0004606258055092397, 'samples': 5529792, 'steps': 28800, 'loss/train': 1.426822304725647}
+08/30/2021 18:19:00 - INFO - __main__ - Step 28802: {'lr': 0.00046062294676475584, 'samples': 5529984, 'steps': 28801, 'loss/train': 1.4379661083221436}
+08/30/2021 18:19:00 - INFO - __main__ - Step 28803: {'lr': 0.0004606200879253685, 'samples': 5530176, 'steps': 28802, 'loss/train': 1.4996684789657593}
+08/30/2021 18:19:02 - INFO - __main__ - Step 28804: {'lr': 0.00046061722899107905, 'samples': 5530368, 'steps': 28803, 'loss/train': 1.2916420698165894}
+08/30/2021 18:19:02 - INFO - __main__ - Step 28805: {'lr': 0.0004606143699618888, 'samples': 5530560, 'steps': 28804, 'loss/train': 1.4700864553451538}
+08/30/2021 18:19:02 - INFO - __main__ - Step 28806: {'lr': 0.00046061151083779886, 'samples': 5530752, 'steps': 28805, 'loss/train': 1.9744372367858887}
+08/30/2021 18:19:03 - INFO - __main__ - Step 28807: {'lr': 0.0004606086516188106, 'samples': 5530944, 'steps': 28806, 'loss/train': 1.173879861831665}
+08/30/2021 18:19:03 - INFO - __main__ - Step 28808: {'lr': 0.00046060579230492533, 'samples': 5531136, 'steps': 28807, 'loss/train': 1.6978788375854492}
+08/30/2021 18:19:04 - INFO - __main__ - Step 28809: {'lr': 0.0004606029328961444, 'samples': 5531328, 'steps': 28808, 'loss/train': 1.7924799919128418}
+08/30/2021 18:19:05 - INFO - __main__ - Step 28810: {'lr': 0.000460600073392469, 'samples': 5531520, 'steps': 28809, 'loss/train': 1.2540429830551147}
+08/30/2021 18:19:05 - INFO - __main__ - Step 28811: {'lr': 0.00046059721379390053, 'samples': 5531712, 'steps': 28810, 'loss/train': 0.6633529663085938}
+08/30/2021 18:19:06 - INFO - __main__ - Step 28812: {'lr': 0.0004605943541004401, 'samples': 5531904, 'steps': 28811, 'loss/train': 1.1641274690628052}
+08/30/2021 18:19:06 - INFO - __main__ - Step 28813: {'lr': 0.00046059149431208914, 'samples': 5532096, 'steps': 28812, 'loss/train': 1.72393000125885}
+08/30/2021 18:19:06 - INFO - __main__ - Step 28814: {'lr': 0.0004605886344288489, 'samples': 5532288, 'steps': 28813, 'loss/train': 1.344095230102539}
+08/30/2021 18:19:08 - INFO - __main__ - Step 28815: {'lr': 0.0004605857744507207, 'samples': 5532480, 'steps': 28814, 'loss/train': 1.4743280410766602}
+08/30/2021 18:19:08 - INFO - __main__ - Step 28816: {'lr': 0.00046058291437770584, 'samples': 5532672, 'steps': 28815, 'loss/train': 1.1923967599868774}
+08/30/2021 18:19:09 - INFO - __main__ - Step 28817: {'lr': 0.0004605800542098054, 'samples': 5532864, 'steps': 28816, 'loss/train': 1.0488197803497314}
+08/30/2021 18:19:09 - INFO - __main__ - Step 28818: {'lr': 0.00046057719394702103, 'samples': 5533056, 'steps': 28817, 'loss/train': 1.435438632965088}
+08/30/2021 18:19:09 - INFO - __main__ - Step 28819: {'lr': 0.00046057433358935373, 'samples': 5533248, 'steps': 28818, 'loss/train': 0.1840985119342804}
+08/30/2021 18:19:11 - INFO - __main__ - Step 28820: {'lr': 0.0004605714731368049, 'samples': 5533440, 'steps': 28819, 'loss/train': 1.9750401973724365}
+08/30/2021 18:19:12 - INFO - __main__ - Step 28821: {'lr': 0.0004605686125893758, 'samples': 5533632, 'steps': 28820, 'loss/train': 1.3374357223510742}
+08/30/2021 18:19:12 - INFO - __main__ - Step 28822: {'lr': 0.00046056575194706773, 'samples': 5533824, 'steps': 28821, 'loss/train': 0.9989317655563354}
+08/30/2021 18:19:12 - INFO - __main__ - Step 28823: {'lr': 0.000460562891209882, 'samples': 5534016, 'steps': 28822, 'loss/train': 1.727424144744873}
+08/30/2021 18:19:13 - INFO - __main__ - Step 28824: {'lr': 0.0004605600303778199, 'samples': 5534208, 'steps': 28823, 'loss/train': 1.3220311403274536}
+08/30/2021 18:19:13 - INFO - __main__ - Step 28825: {'lr': 0.0004605571694508827, 'samples': 5534400, 'steps': 28824, 'loss/train': 1.4859980344772339}
+08/30/2021 18:19:14 - INFO - __main__ - Step 28826: {'lr': 0.0004605543084290716, 'samples': 5534592, 'steps': 28825, 'loss/train': 1.5253325700759888}
+08/30/2021 18:19:15 - INFO - __main__ - Step 28827: {'lr': 0.00046055144731238805, 'samples': 5534784, 'steps': 28826, 'loss/train': 1.4258514642715454}
+08/30/2021 18:19:15 - INFO - __main__ - Step 28828: {'lr': 0.00046054858610083325, 'samples': 5534976, 'steps': 28827, 'loss/train': 1.5617334842681885}
+08/30/2021 18:19:16 - INFO - __main__ - Step 28829: {'lr': 0.0004605457247944086, 'samples': 5535168, 'steps': 28828, 'loss/train': 1.6477042436599731}
+08/30/2021 18:19:16 - INFO - __main__ - Step 28830: {'lr': 0.0004605428633931152, 'samples': 5535360, 'steps': 28829, 'loss/train': 1.5681991577148438}
+08/30/2021 18:19:18 - INFO - __main__ - Step 28831: {'lr': 0.00046054000189695444, 'samples': 5535552, 'steps': 28830, 'loss/train': 1.8616143465042114}
+08/30/2021 18:19:18 - INFO - __main__ - Step 28832: {'lr': 0.00046053714030592764, 'samples': 5535744, 'steps': 28831, 'loss/train': 5.211965084075928}
+08/30/2021 18:19:19 - INFO - __main__ - Step 28833: {'lr': 0.0004605342786200359, 'samples': 5535936, 'steps': 28832, 'loss/train': 5.299749374389648}
+08/30/2021 18:19:19 - INFO - __main__ - Step 28834: {'lr': 0.0004605314168392809, 'samples': 5536128, 'steps': 28833, 'loss/train': 1.5922120809555054}
+08/30/2021 18:19:19 - INFO - __main__ - Step 28835: {'lr': 0.00046052855496366354, 'samples': 5536320, 'steps': 28834, 'loss/train': 2.2216432094573975}
+08/30/2021 18:19:20 - INFO - __main__ - Step 28836: {'lr': 0.0004605256929931853, 'samples': 5536512, 'steps': 28835, 'loss/train': 1.0870556831359863}
+08/30/2021 18:19:22 - INFO - __main__ - Step 28837: {'lr': 0.0004605228309278474, 'samples': 5536704, 'steps': 28836, 'loss/train': 1.584465503692627}
+08/30/2021 18:19:22 - INFO - __main__ - Step 28838: {'lr': 0.0004605199687676512, 'samples': 5536896, 'steps': 28837, 'loss/train': 1.690821886062622}
+08/30/2021 18:19:23 - INFO - __main__ - Step 28839: {'lr': 0.00046051710651259797, 'samples': 5537088, 'steps': 28838, 'loss/train': 1.9488508701324463}
+08/30/2021 18:19:23 - INFO - __main__ - Step 28840: {'lr': 0.00046051424416268896, 'samples': 5537280, 'steps': 28839, 'loss/train': 1.453596591949463}
+08/30/2021 18:19:23 - INFO - __main__ - Step 28841: {'lr': 0.0004605113817179255, 'samples': 5537472, 'steps': 28840, 'loss/train': 1.7849009037017822}
+08/30/2021 18:19:25 - INFO - __main__ - Step 28842: {'lr': 0.00046050851917830884, 'samples': 5537664, 'steps': 28841, 'loss/train': 1.0420764684677124}
+08/30/2021 18:19:25 - INFO - __main__ - Step 28843: {'lr': 0.00046050565654384023, 'samples': 5537856, 'steps': 28842, 'loss/train': 1.6934154033660889}
+08/30/2021 18:19:26 - INFO - __main__ - Step 28844: {'lr': 0.0004605027938145211, 'samples': 5538048, 'steps': 28843, 'loss/train': 1.946616768836975}
+08/30/2021 18:19:26 - INFO - __main__ - Step 28845: {'lr': 0.0004604999309903526, 'samples': 5538240, 'steps': 28844, 'loss/train': 1.6108081340789795}
+08/30/2021 18:19:26 - INFO - __main__ - Step 28846: {'lr': 0.0004604970680713362, 'samples': 5538432, 'steps': 28845, 'loss/train': 2.1126925945281982}
+08/30/2021 18:19:27 - INFO - __main__ - Step 28847: {'lr': 0.00046049420505747294, 'samples': 5538624, 'steps': 28846, 'loss/train': 1.4479706287384033}
+08/30/2021 18:19:28 - INFO - __main__ - Step 28848: {'lr': 0.0004604913419487643, 'samples': 5538816, 'steps': 28847, 'loss/train': 1.1913269758224487}
+08/30/2021 18:19:29 - INFO - __main__ - Step 28849: {'lr': 0.00046048847874521144, 'samples': 5539008, 'steps': 28848, 'loss/train': 1.337689995765686}
+08/30/2021 18:19:29 - INFO - __main__ - Step 28850: {'lr': 0.00046048561544681575, 'samples': 5539200, 'steps': 28849, 'loss/train': 1.0054725408554077}
+08/30/2021 18:19:29 - INFO - __main__ - Step 28851: {'lr': 0.00046048275205357855, 'samples': 5539392, 'steps': 28850, 'loss/train': 1.068784475326538}
+08/30/2021 18:19:30 - INFO - __main__ - Step 28852: {'lr': 0.00046047988856550104, 'samples': 5539584, 'steps': 28851, 'loss/train': 1.2208802700042725}
+08/30/2021 18:19:31 - INFO - __main__ - Step 28853: {'lr': 0.00046047702498258446, 'samples': 5539776, 'steps': 28852, 'loss/train': 1.698395848274231}
+08/30/2021 18:19:32 - INFO - __main__ - Step 28854: {'lr': 0.00046047416130483033, 'samples': 5539968, 'steps': 28853, 'loss/train': 1.7481921911239624}
+08/30/2021 18:19:32 - INFO - __main__ - Step 28855: {'lr': 0.00046047129753223973, 'samples': 5540160, 'steps': 28854, 'loss/train': 1.0832093954086304}
+08/30/2021 18:19:32 - INFO - __main__ - Step 28856: {'lr': 0.0004604684336648139, 'samples': 5540352, 'steps': 28855, 'loss/train': 1.8524690866470337}
+08/30/2021 18:19:33 - INFO - __main__ - Step 28857: {'lr': 0.00046046556970255435, 'samples': 5540544, 'steps': 28856, 'loss/train': 1.2693358659744263}
+08/30/2021 18:19:34 - INFO - __main__ - Step 28858: {'lr': 0.0004604627056454622, 'samples': 5540736, 'steps': 28857, 'loss/train': 1.1964995861053467}
+08/30/2021 18:19:34 - INFO - __main__ - Step 28859: {'lr': 0.00046045984149353894, 'samples': 5540928, 'steps': 28858, 'loss/train': 1.4220203161239624}
+08/30/2021 18:19:35 - INFO - __main__ - Step 28860: {'lr': 0.0004604569772467856, 'samples': 5541120, 'steps': 28859, 'loss/train': 1.0095555782318115}
+08/30/2021 18:19:35 - INFO - __main__ - Step 28861: {'lr': 0.00046045411290520364, 'samples': 5541312, 'steps': 28860, 'loss/train': 1.8971298933029175}
+08/30/2021 18:19:36 - INFO - __main__ - Step 28862: {'lr': 0.00046045124846879427, 'samples': 5541504, 'steps': 28861, 'loss/train': 1.142421007156372}
+08/30/2021 18:19:37 - INFO - __main__ - Step 28863: {'lr': 0.00046044838393755885, 'samples': 5541696, 'steps': 28862, 'loss/train': 1.459968090057373}
+08/30/2021 18:19:38 - INFO - __main__ - Step 28864: {'lr': 0.00046044551931149856, 'samples': 5541888, 'steps': 28863, 'loss/train': 0.4833144247531891}
+08/30/2021 18:19:38 - INFO - __main__ - Step 28865: {'lr': 0.0004604426545906149, 'samples': 5542080, 'steps': 28864, 'loss/train': 1.4947117567062378}
+08/30/2021 18:19:38 - INFO - __main__ - Step 28866: {'lr': 0.0004604397897749089, 'samples': 5542272, 'steps': 28865, 'loss/train': 1.7568550109863281}
+08/30/2021 18:19:39 - INFO - __main__ - Step 28867: {'lr': 0.00046043692486438207, 'samples': 5542464, 'steps': 28866, 'loss/train': 1.0612441301345825}
+08/30/2021 18:19:40 - INFO - __main__ - Step 28868: {'lr': 0.00046043405985903555, 'samples': 5542656, 'steps': 28867, 'loss/train': 1.6154786348342896}
+08/30/2021 18:19:41 - INFO - __main__ - Step 28869: {'lr': 0.00046043119475887073, 'samples': 5542848, 'steps': 28868, 'loss/train': 1.5218857526779175}
+08/30/2021 18:19:41 - INFO - __main__ - Step 28870: {'lr': 0.0004604283295638888, 'samples': 5543040, 'steps': 28869, 'loss/train': 1.3188573122024536}
+08/30/2021 18:19:42 - INFO - __main__ - Step 28871: {'lr': 0.00046042546427409116, 'samples': 5543232, 'steps': 28870, 'loss/train': 0.7918139696121216}
+08/30/2021 18:19:42 - INFO - __main__ - Step 28872: {'lr': 0.000460422598889479, 'samples': 5543424, 'steps': 28871, 'loss/train': 1.4799987077713013}
+08/30/2021 18:19:43 - INFO - __main__ - Step 28873: {'lr': 0.0004604197334100537, 'samples': 5543616, 'steps': 28872, 'loss/train': 1.4581646919250488}
+08/30/2021 18:19:44 - INFO - __main__ - Step 28874: {'lr': 0.0004604168678358166, 'samples': 5543808, 'steps': 28873, 'loss/train': 1.1605101823806763}
+08/30/2021 18:19:44 - INFO - __main__ - Step 28875: {'lr': 0.00046041400216676874, 'samples': 5544000, 'steps': 28874, 'loss/train': 1.4286561012268066}
+08/30/2021 18:19:45 - INFO - __main__ - Step 28876: {'lr': 0.0004604111364029118, 'samples': 5544192, 'steps': 28875, 'loss/train': 1.7455028295516968}
+08/30/2021 18:19:45 - INFO - __main__ - Step 28877: {'lr': 0.0004604082705442466, 'samples': 5544384, 'steps': 28876, 'loss/train': 1.7974566221237183}
+08/30/2021 18:19:46 - INFO - __main__ - Step 28878: {'lr': 0.00046040540459077483, 'samples': 5544576, 'steps': 28877, 'loss/train': 0.9158125519752502}
+08/30/2021 18:19:47 - INFO - __main__ - Step 28879: {'lr': 0.0004604025385424976, 'samples': 5544768, 'steps': 28878, 'loss/train': 1.5195859670639038}
+08/30/2021 18:19:47 - INFO - __main__ - Step 28880: {'lr': 0.00046039967239941626, 'samples': 5544960, 'steps': 28879, 'loss/train': 1.4470536708831787}
+08/30/2021 18:19:48 - INFO - __main__ - Step 28881: {'lr': 0.000460396806161532, 'samples': 5545152, 'steps': 28880, 'loss/train': 1.6458234786987305}
+08/30/2021 18:19:48 - INFO - __main__ - Step 28882: {'lr': 0.0004603939398288463, 'samples': 5545344, 'steps': 28881, 'loss/train': 1.1609463691711426}
+08/30/2021 18:19:49 - INFO - __main__ - Step 28883: {'lr': 0.00046039107340136023, 'samples': 5545536, 'steps': 28882, 'loss/train': 1.6444604396820068}
+08/30/2021 18:19:50 - INFO - __main__ - Step 28884: {'lr': 0.00046038820687907523, 'samples': 5545728, 'steps': 28883, 'loss/train': 1.0269838571548462}
+08/30/2021 18:19:50 - INFO - __main__ - Step 28885: {'lr': 0.0004603853402619925, 'samples': 5545920, 'steps': 28884, 'loss/train': 1.2960134744644165}
+08/30/2021 18:19:51 - INFO - __main__ - Step 28886: {'lr': 0.00046038247355011347, 'samples': 5546112, 'steps': 28885, 'loss/train': 1.117455005645752}
+08/30/2021 18:19:51 - INFO - __main__ - Step 28887: {'lr': 0.00046037960674343925, 'samples': 5546304, 'steps': 28886, 'loss/train': 0.9311093688011169}
+08/30/2021 18:19:51 - INFO - __main__ - Step 28888: {'lr': 0.0004603767398419713, 'samples': 5546496, 'steps': 28887, 'loss/train': 1.880321741104126}
+08/30/2021 18:19:54 - INFO - __main__ - Step 28889: {'lr': 0.0004603738728457109, 'samples': 5546688, 'steps': 28888, 'loss/train': 1.6211706399917603}
+08/30/2021 18:19:54 - INFO - __main__ - Step 28890: {'lr': 0.0004603710057546592, 'samples': 5546880, 'steps': 28889, 'loss/train': 0.2054881751537323}
+08/30/2021 18:19:55 - INFO - __main__ - Step 28891: {'lr': 0.0004603681385688175, 'samples': 5547072, 'steps': 28890, 'loss/train': 0.07243458181619644}
+08/30/2021 18:19:55 - INFO - __main__ - Step 28892: {'lr': 0.00046036527128818724, 'samples': 5547264, 'steps': 28891, 'loss/train': 1.0678194761276245}
+08/30/2021 18:19:55 - INFO - __main__ - Step 28893: {'lr': 0.0004603624039127696, 'samples': 5547456, 'steps': 28892, 'loss/train': 1.3182927370071411}
+08/30/2021 18:19:56 - INFO - __main__ - Step 28894: {'lr': 0.00046035953644256596, 'samples': 5547648, 'steps': 28893, 'loss/train': 1.3891026973724365}
+08/30/2021 18:19:57 - INFO - __main__ - Step 28895: {'lr': 0.00046035666887757755, 'samples': 5547840, 'steps': 28894, 'loss/train': 0.2706478536128998}
+08/30/2021 18:19:58 - INFO - __main__ - Step 28896: {'lr': 0.00046035380121780563, 'samples': 5548032, 'steps': 28895, 'loss/train': 0.8166786432266235}
+08/30/2021 18:19:58 - INFO - __main__ - Step 28897: {'lr': 0.0004603509334632515, 'samples': 5548224, 'steps': 28896, 'loss/train': 1.5154094696044922}
+08/30/2021 18:19:58 - INFO - __main__ - Step 28898: {'lr': 0.00046034806561391655, 'samples': 5548416, 'steps': 28897, 'loss/train': 1.4594331979751587}
+08/30/2021 18:19:59 - INFO - __main__ - Step 28899: {'lr': 0.000460345197669802, 'samples': 5548608, 'steps': 28898, 'loss/train': 1.543952465057373}
+08/30/2021 18:19:59 - INFO - __main__ - Step 28900: {'lr': 0.0004603423296309092, 'samples': 5548800, 'steps': 28899, 'loss/train': 1.7093851566314697}
+08/30/2021 18:20:01 - INFO - __main__ - Step 28901: {'lr': 0.0004603394614972393, 'samples': 5548992, 'steps': 28900, 'loss/train': 1.3952860832214355}
+08/30/2021 18:20:01 - INFO - __main__ - Step 28902: {'lr': 0.00046033659326879373, 'samples': 5549184, 'steps': 28901, 'loss/train': 2.4770402908325195}
+08/30/2021 18:20:02 - INFO - __main__ - Step 28903: {'lr': 0.00046033372494557373, 'samples': 5549376, 'steps': 28902, 'loss/train': 0.9451573491096497}
+08/30/2021 18:20:02 - INFO - __main__ - Step 28904: {'lr': 0.00046033085652758053, 'samples': 5549568, 'steps': 28903, 'loss/train': 0.03911512717604637}
+08/30/2021 18:20:02 - INFO - __main__ - Step 28905: {'lr': 0.00046032798801481564, 'samples': 5549760, 'steps': 28904, 'loss/train': 1.26829993724823}
+08/30/2021 18:20:03 - INFO - __main__ - Step 28906: {'lr': 0.0004603251194072801, 'samples': 5549952, 'steps': 28905, 'loss/train': 1.5318100452423096}
+08/30/2021 18:20:04 - INFO - __main__ - Step 28907: {'lr': 0.0004603222507049754, 'samples': 5550144, 'steps': 28906, 'loss/train': 1.6907885074615479}
+08/30/2021 18:20:05 - INFO - __main__ - Step 28908: {'lr': 0.00046031938190790254, 'samples': 5550336, 'steps': 28907, 'loss/train': 1.842464804649353}
+08/30/2021 18:20:05 - INFO - __main__ - Step 28909: {'lr': 0.0004603165130160633, 'samples': 5550528, 'steps': 28908, 'loss/train': 1.7786346673965454}
+08/30/2021 18:20:05 - INFO - __main__ - Step 28910: {'lr': 0.0004603136440294584, 'samples': 5550720, 'steps': 28909, 'loss/train': 1.5675617456436157}
+08/30/2021 18:20:06 - INFO - __main__ - Step 28911: {'lr': 0.0004603107749480896, 'samples': 5550912, 'steps': 28910, 'loss/train': 1.4550175666809082}
+08/30/2021 18:20:07 - INFO - __main__ - Step 28912: {'lr': 0.0004603079057719579, 'samples': 5551104, 'steps': 28911, 'loss/train': 1.8844538927078247}
+08/30/2021 18:20:08 - INFO - __main__ - Step 28913: {'lr': 0.0004603050365010648, 'samples': 5551296, 'steps': 28912, 'loss/train': 1.815502405166626}
+08/30/2021 18:20:08 - INFO - __main__ - Step 28914: {'lr': 0.00046030216713541147, 'samples': 5551488, 'steps': 28913, 'loss/train': 1.5247673988342285}
+08/30/2021 18:20:08 - INFO - __main__ - Step 28915: {'lr': 0.00046029929767499924, 'samples': 5551680, 'steps': 28914, 'loss/train': 1.4302256107330322}
+08/30/2021 18:20:09 - INFO - __main__ - Step 28916: {'lr': 0.0004602964281198293, 'samples': 5551872, 'steps': 28915, 'loss/train': 1.7288661003112793}
+08/30/2021 18:20:10 - INFO - __main__ - Step 28917: {'lr': 0.0004602935584699031, 'samples': 5552064, 'steps': 28916, 'loss/train': 1.8400119543075562}
+08/30/2021 18:20:11 - INFO - __main__ - Step 28918: {'lr': 0.00046029068872522185, 'samples': 5552256, 'steps': 28917, 'loss/train': 1.44405198097229}
+08/30/2021 18:20:11 - INFO - __main__ - Step 28919: {'lr': 0.0004602878188857869, 'samples': 5552448, 'steps': 28918, 'loss/train': 1.474245548248291}
+08/30/2021 18:20:11 - INFO - __main__ - Step 28920: {'lr': 0.0004602849489515995, 'samples': 5552640, 'steps': 28919, 'loss/train': 1.9890936613082886}
+08/30/2021 18:20:12 - INFO - __main__ - Step 28921: {'lr': 0.00046028207892266095, 'samples': 5552832, 'steps': 28920, 'loss/train': 1.5841706991195679}
+08/30/2021 18:20:13 - INFO - __main__ - Step 28922: {'lr': 0.00046027920879897243, 'samples': 5553024, 'steps': 28921, 'loss/train': 0.14850802719593048}
+08/30/2021 18:20:14 - INFO - __main__ - Step 28923: {'lr': 0.00046027633858053554, 'samples': 5553216, 'steps': 28922, 'loss/train': 1.1777100563049316}
+08/30/2021 18:20:14 - INFO - __main__ - Step 28924: {'lr': 0.0004602734682673512, 'samples': 5553408, 'steps': 28923, 'loss/train': 1.2692878246307373}
+08/30/2021 18:20:14 - INFO - __main__ - Step 28925: {'lr': 0.0004602705978594209, 'samples': 5553600, 'steps': 28924, 'loss/train': 1.4671497344970703}
+08/30/2021 18:20:15 - INFO - __main__ - Step 28926: {'lr': 0.00046026772735674606, 'samples': 5553792, 'steps': 28925, 'loss/train': 1.2502681016921997}
+08/30/2021 18:20:16 - INFO - __main__ - Step 28927: {'lr': 0.00046026485675932765, 'samples': 5553984, 'steps': 28926, 'loss/train': 1.571979284286499}
+08/30/2021 18:20:17 - INFO - __main__ - Step 28928: {'lr': 0.0004602619860671672, 'samples': 5554176, 'steps': 28927, 'loss/train': 0.8823884129524231}
+08/30/2021 18:20:17 - INFO - __main__ - Step 28929: {'lr': 0.000460259115280266, 'samples': 5554368, 'steps': 28928, 'loss/train': 2.0176033973693848}
+08/30/2021 18:20:17 - INFO - __main__ - Step 28930: {'lr': 0.00046025624439862523, 'samples': 5554560, 'steps': 28929, 'loss/train': 1.8027647733688354}
+08/30/2021 18:20:18 - INFO - __main__ - Step 28931: {'lr': 0.0004602533734222463, 'samples': 5554752, 'steps': 28930, 'loss/train': 1.4804277420043945}
+08/30/2021 18:20:18 - INFO - __main__ - Step 28932: {'lr': 0.00046025050235113036, 'samples': 5554944, 'steps': 28931, 'loss/train': 1.4038063287734985}
+08/30/2021 18:20:20 - INFO - __main__ - Step 28933: {'lr': 0.00046024763118527885, 'samples': 5555136, 'steps': 28932, 'loss/train': 1.8037775754928589}
+08/30/2021 18:20:20 - INFO - __main__ - Step 28934: {'lr': 0.00046024475992469295, 'samples': 5555328, 'steps': 28933, 'loss/train': 1.4444252252578735}
+08/30/2021 18:20:20 - INFO - __main__ - Step 28935: {'lr': 0.0004602418885693741, 'samples': 5555520, 'steps': 28934, 'loss/train': 1.142490029335022}
+08/30/2021 18:20:21 - INFO - __main__ - Step 28936: {'lr': 0.0004602390171193234, 'samples': 5555712, 'steps': 28935, 'loss/train': 1.1529531478881836}
+08/30/2021 18:20:21 - INFO - __main__ - Step 28937: {'lr': 0.0004602361455745423, 'samples': 5555904, 'steps': 28936, 'loss/train': 1.541255235671997}
+08/30/2021 18:20:23 - INFO - __main__ - Step 28938: {'lr': 0.000460233273935032, 'samples': 5556096, 'steps': 28937, 'loss/train': 1.4332858324050903}
+08/30/2021 18:20:23 - INFO - __main__ - Step 28939: {'lr': 0.00046023040220079383, 'samples': 5556288, 'steps': 28938, 'loss/train': 1.8582457304000854}
+08/30/2021 18:20:23 - INFO - __main__ - Step 28940: {'lr': 0.00046022753037182915, 'samples': 5556480, 'steps': 28939, 'loss/train': 1.4308955669403076}
+08/30/2021 18:20:24 - INFO - __main__ - Step 28941: {'lr': 0.0004602246584481391, 'samples': 5556672, 'steps': 28940, 'loss/train': 2.558939218521118}
+08/30/2021 18:20:24 - INFO - __main__ - Step 28942: {'lr': 0.00046022178642972513, 'samples': 5556864, 'steps': 28941, 'loss/train': 0.9509792327880859}
+08/30/2021 18:20:26 - INFO - __main__ - Step 28943: {'lr': 0.00046021891431658845, 'samples': 5557056, 'steps': 28942, 'loss/train': 1.919646143913269}
+08/30/2021 18:20:27 - INFO - __main__ - Step 28944: {'lr': 0.00046021604210873035, 'samples': 5557248, 'steps': 28943, 'loss/train': 0.7934926748275757}
+08/30/2021 18:20:27 - INFO - __main__ - Step 28945: {'lr': 0.0004602131698061521, 'samples': 5557440, 'steps': 28944, 'loss/train': 1.622161626815796}
+08/30/2021 18:20:27 - INFO - __main__ - Step 28946: {'lr': 0.0004602102974088551, 'samples': 5557632, 'steps': 28945, 'loss/train': 0.7455008029937744}
+08/30/2021 18:20:28 - INFO - __main__ - Step 28947: {'lr': 0.00046020742491684067, 'samples': 5557824, 'steps': 28946, 'loss/train': 1.1160584688186646}
+08/30/2021 18:20:29 - INFO - __main__ - Step 28948: {'lr': 0.0004602045523301099, 'samples': 5558016, 'steps': 28947, 'loss/train': 2.048121213912964}
+08/30/2021 18:20:30 - INFO - __main__ - Step 28949: {'lr': 0.0004602016796486642, 'samples': 5558208, 'steps': 28948, 'loss/train': 1.2027957439422607}
+08/30/2021 18:20:30 - INFO - __main__ - Step 28950: {'lr': 0.00046019880687250494, 'samples': 5558400, 'steps': 28949, 'loss/train': 1.0947144031524658}
+08/30/2021 18:20:30 - INFO - __main__ - Step 28951: {'lr': 0.0004601959340016333, 'samples': 5558592, 'steps': 28950, 'loss/train': 0.3539426922798157}
+08/30/2021 18:20:31 - INFO - __main__ - Step 28952: {'lr': 0.0004601930610360506, 'samples': 5558784, 'steps': 28951, 'loss/train': 1.6546393632888794}
+08/30/2021 18:20:32 - INFO - __main__ - Step 28953: {'lr': 0.0004601901879757582, 'samples': 5558976, 'steps': 28952, 'loss/train': 1.4125444889068604}
+08/30/2021 18:20:33 - INFO - __main__ - Step 28954: {'lr': 0.0004601873148207573, 'samples': 5559168, 'steps': 28953, 'loss/train': 1.53622305393219}
+08/30/2021 18:20:33 - INFO - __main__ - Step 28955: {'lr': 0.00046018444157104924, 'samples': 5559360, 'steps': 28954, 'loss/train': 1.8789094686508179}
+08/30/2021 18:20:33 - INFO - __main__ - Step 28956: {'lr': 0.0004601815682266353, 'samples': 5559552, 'steps': 28955, 'loss/train': 0.9152023196220398}
+08/30/2021 18:20:34 - INFO - __main__ - Step 28957: {'lr': 0.00046017869478751685, 'samples': 5559744, 'steps': 28956, 'loss/train': 1.435634970664978}
+08/30/2021 18:20:36 - INFO - __main__ - Step 28958: {'lr': 0.00046017582125369505, 'samples': 5559936, 'steps': 28957, 'loss/train': 2.5206053256988525}
+08/30/2021 18:20:36 - INFO - __main__ - Step 28959: {'lr': 0.00046017294762517127, 'samples': 5560128, 'steps': 28958, 'loss/train': 1.719394564628601}
+08/30/2021 18:20:36 - INFO - __main__ - Step 28960: {'lr': 0.0004601700739019469, 'samples': 5560320, 'steps': 28959, 'loss/train': 1.458498477935791}
+08/30/2021 18:20:37 - INFO - __main__ - Step 28961: {'lr': 0.000460167200084023, 'samples': 5560512, 'steps': 28960, 'loss/train': 0.8339565992355347}
+08/30/2021 18:20:37 - INFO - __main__ - Step 28962: {'lr': 0.00046016432617140113, 'samples': 5560704, 'steps': 28961, 'loss/train': 1.3075861930847168}
+08/30/2021 18:20:38 - INFO - __main__ - Step 28963: {'lr': 0.0004601614521640824, 'samples': 5560896, 'steps': 28962, 'loss/train': 1.3877896070480347}
+08/30/2021 18:20:38 - INFO - __main__ - Step 28964: {'lr': 0.00046015857806206816, 'samples': 5561088, 'steps': 28963, 'loss/train': 0.10883594304323196}
+08/30/2021 18:20:40 - INFO - __main__ - Step 28965: {'lr': 0.0004601557038653597, 'samples': 5561280, 'steps': 28964, 'loss/train': 0.3230167329311371}
+08/30/2021 18:20:40 - INFO - __main__ - Step 28966: {'lr': 0.0004601528295739583, 'samples': 5561472, 'steps': 28965, 'loss/train': 0.9901770353317261}
+08/30/2021 18:20:40 - INFO - __main__ - Step 28967: {'lr': 0.00046014995518786536, 'samples': 5561664, 'steps': 28966, 'loss/train': 2.1910712718963623}
+08/30/2021 18:20:41 - INFO - __main__ - Step 28968: {'lr': 0.000460147080707082, 'samples': 5561856, 'steps': 28967, 'loss/train': 1.1445995569229126}
+08/30/2021 18:20:41 - INFO - __main__ - Step 28969: {'lr': 0.00046014420613160967, 'samples': 5562048, 'steps': 28968, 'loss/train': 1.4583795070648193}
+08/30/2021 18:20:42 - INFO - __main__ - Step 28970: {'lr': 0.00046014133146144966, 'samples': 5562240, 'steps': 28969, 'loss/train': 1.804777979850769}
+08/30/2021 18:20:43 - INFO - __main__ - Step 28971: {'lr': 0.0004601384566966031, 'samples': 5562432, 'steps': 28970, 'loss/train': 1.1418389081954956}
+08/30/2021 18:20:43 - INFO - __main__ - Step 28972: {'lr': 0.0004601355818370714, 'samples': 5562624, 'steps': 28971, 'loss/train': 1.0044198036193848}
+08/30/2021 18:20:44 - INFO - __main__ - Step 28973: {'lr': 0.0004601327068828559, 'samples': 5562816, 'steps': 28972, 'loss/train': 1.4819682836532593}
+08/30/2021 18:20:44 - INFO - __main__ - Step 28974: {'lr': 0.0004601298318339578, 'samples': 5563008, 'steps': 28973, 'loss/train': 1.3393051624298096}
+08/30/2021 18:20:46 - INFO - __main__ - Step 28975: {'lr': 0.0004601269566903785, 'samples': 5563200, 'steps': 28974, 'loss/train': 0.6184431910514832}
+08/30/2021 18:20:46 - INFO - __main__ - Step 28976: {'lr': 0.0004601240814521192, 'samples': 5563392, 'steps': 28975, 'loss/train': 1.1198714971542358}
+08/30/2021 18:20:47 - INFO - __main__ - Step 28977: {'lr': 0.00046012120611918126, 'samples': 5563584, 'steps': 28976, 'loss/train': 2.6182427406311035}
+08/30/2021 18:20:47 - INFO - __main__ - Step 28978: {'lr': 0.0004601183306915659, 'samples': 5563776, 'steps': 28977, 'loss/train': 0.9519802927970886}
+08/30/2021 18:20:47 - INFO - __main__ - Step 28979: {'lr': 0.0004601154551692745, 'samples': 5563968, 'steps': 28978, 'loss/train': 1.9191051721572876}
+08/30/2021 18:20:48 - INFO - __main__ - Step 28980: {'lr': 0.00046011257955230826, 'samples': 5564160, 'steps': 28979, 'loss/train': 1.1937226057052612}
+08/30/2021 18:20:49 - INFO - __main__ - Step 28981: {'lr': 0.00046010970384066863, 'samples': 5564352, 'steps': 28980, 'loss/train': 0.980539083480835}
+08/30/2021 18:20:50 - INFO - __main__ - Step 28982: {'lr': 0.00046010682803435674, 'samples': 5564544, 'steps': 28981, 'loss/train': 1.0843158960342407}
+08/30/2021 18:20:50 - INFO - __main__ - Step 28983: {'lr': 0.000460103952133374, 'samples': 5564736, 'steps': 28982, 'loss/train': 1.4898028373718262}
+08/30/2021 18:20:50 - INFO - __main__ - Step 28984: {'lr': 0.00046010107613772154, 'samples': 5564928, 'steps': 28983, 'loss/train': 1.7888057231903076}
+08/30/2021 18:20:51 - INFO - __main__ - Step 28985: {'lr': 0.0004600982000474009, 'samples': 5565120, 'steps': 28984, 'loss/train': 1.3882951736450195}
+08/30/2021 18:20:53 - INFO - __main__ - Step 28986: {'lr': 0.0004600953238624133, 'samples': 5565312, 'steps': 28985, 'loss/train': 1.7313249111175537}
+08/30/2021 18:20:53 - INFO - __main__ - Step 28987: {'lr': 0.00046009244758275986, 'samples': 5565504, 'steps': 28986, 'loss/train': 1.7693266868591309}
+08/30/2021 18:20:54 - INFO - __main__ - Step 28988: {'lr': 0.0004600895712084421, 'samples': 5565696, 'steps': 28987, 'loss/train': 0.8204891085624695}
+08/30/2021 18:20:54 - INFO - __main__ - Step 28989: {'lr': 0.0004600866947394611, 'samples': 5565888, 'steps': 28988, 'loss/train': 1.4293334484100342}
+08/30/2021 18:20:54 - INFO - __main__ - Step 28990: {'lr': 0.0004600838181758184, 'samples': 5566080, 'steps': 28989, 'loss/train': 0.9987662434577942}
+08/30/2021 18:20:55 - INFO - __main__ - Step 28991: {'lr': 0.00046008094151751513, 'samples': 5566272, 'steps': 28990, 'loss/train': 1.6933869123458862}
+08/30/2021 18:20:56 - INFO - __main__ - Step 28992: {'lr': 0.0004600780647645526, 'samples': 5566464, 'steps': 28991, 'loss/train': 0.10519556701183319}
+08/30/2021 18:20:57 - INFO - __main__ - Step 28993: {'lr': 0.0004600751879169321, 'samples': 5566656, 'steps': 28992, 'loss/train': 1.2371454238891602}
+08/30/2021 18:20:57 - INFO - __main__ - Step 28994: {'lr': 0.00046007231097465505, 'samples': 5566848, 'steps': 28993, 'loss/train': 1.0152714252471924}
+08/30/2021 18:20:57 - INFO - __main__ - Step 28995: {'lr': 0.00046006943393772274, 'samples': 5567040, 'steps': 28994, 'loss/train': 1.2526971101760864}
+08/30/2021 18:20:58 - INFO - __main__ - Step 28996: {'lr': 0.00046006655680613616, 'samples': 5567232, 'steps': 28995, 'loss/train': 1.8520199060440063}
+08/30/2021 18:20:59 - INFO - __main__ - Step 28997: {'lr': 0.00046006367957989705, 'samples': 5567424, 'steps': 28996, 'loss/train': 1.6551318168640137}
+08/30/2021 18:21:00 - INFO - __main__ - Step 28998: {'lr': 0.0004600608022590064, 'samples': 5567616, 'steps': 28997, 'loss/train': 1.4023603200912476}
+08/30/2021 18:21:00 - INFO - __main__ - Step 28999: {'lr': 0.0004600579248434655, 'samples': 5567808, 'steps': 28998, 'loss/train': 1.3744001388549805}
+08/30/2021 18:21:01 - INFO - __main__ - Step 29000: {'lr': 0.0004600550473332759, 'samples': 5568000, 'steps': 28999, 'loss/train': 5.890665531158447}
+08/30/2021 18:21:01 - INFO - __main__ - Step 29001: {'lr': 0.0004600521697284386, 'samples': 5568192, 'steps': 29000, 'loss/train': 1.5829437971115112}
+08/30/2021 18:21:01 - INFO - __main__ - Step 29002: {'lr': 0.0004600492920289551, 'samples': 5568384, 'steps': 29001, 'loss/train': 1.630038857460022}
+08/30/2021 18:21:03 - INFO - __main__ - Step 29003: {'lr': 0.00046004641423482665, 'samples': 5568576, 'steps': 29002, 'loss/train': 1.9166052341461182}
+08/30/2021 18:21:04 - INFO - __main__ - Step 29004: {'lr': 0.00046004353634605447, 'samples': 5568768, 'steps': 29003, 'loss/train': 1.3703222274780273}
+08/30/2021 18:21:04 - INFO - __main__ - Step 29005: {'lr': 0.00046004065836263995, 'samples': 5568960, 'steps': 29004, 'loss/train': 1.461896300315857}
+08/30/2021 18:21:04 - INFO - __main__ - Step 29006: {'lr': 0.00046003778028458434, 'samples': 5569152, 'steps': 29005, 'loss/train': 1.6786259412765503}
+08/30/2021 18:21:05 - INFO - __main__ - Step 29007: {'lr': 0.00046003490211188894, 'samples': 5569344, 'steps': 29006, 'loss/train': 1.2999341487884521}
+08/30/2021 18:21:06 - INFO - __main__ - Step 29008: {'lr': 0.00046003202384455505, 'samples': 5569536, 'steps': 29007, 'loss/train': 0.8424675464630127}
+08/30/2021 18:21:07 - INFO - __main__ - Step 29009: {'lr': 0.000460029145482584, 'samples': 5569728, 'steps': 29008, 'loss/train': 1.7033573389053345}
+08/30/2021 18:21:07 - INFO - __main__ - Step 29010: {'lr': 0.00046002626702597706, 'samples': 5569920, 'steps': 29009, 'loss/train': 1.7456250190734863}
+08/30/2021 18:21:07 - INFO - __main__ - Step 29011: {'lr': 0.00046002338847473545, 'samples': 5570112, 'steps': 29010, 'loss/train': 1.8192698955535889}
+08/30/2021 18:21:08 - INFO - __main__ - Step 29012: {'lr': 0.0004600205098288606, 'samples': 5570304, 'steps': 29011, 'loss/train': 1.402625560760498}
+08/30/2021 18:21:09 - INFO - __main__ - Step 29013: {'lr': 0.00046001763108835384, 'samples': 5570496, 'steps': 29012, 'loss/train': 0.7089826464653015}
+08/30/2021 18:21:10 - INFO - __main__ - Step 29014: {'lr': 0.0004600147522532162, 'samples': 5570688, 'steps': 29013, 'loss/train': 2.035728931427002}
+08/30/2021 18:21:10 - INFO - __main__ - Step 29015: {'lr': 0.0004600118733234493, 'samples': 5570880, 'steps': 29014, 'loss/train': 1.5968133211135864}
+08/30/2021 18:21:10 - INFO - __main__ - Step 29016: {'lr': 0.0004600089942990542, 'samples': 5571072, 'steps': 29015, 'loss/train': 1.2618802785873413}
+08/30/2021 18:21:11 - INFO - __main__ - Step 29017: {'lr': 0.00046000611518003234, 'samples': 5571264, 'steps': 29016, 'loss/train': 1.3774456977844238}
+08/30/2021 18:21:11 - INFO - __main__ - Step 29018: {'lr': 0.00046000323596638495, 'samples': 5571456, 'steps': 29017, 'loss/train': 1.3386033773422241}
+08/30/2021 18:21:13 - INFO - __main__ - Step 29019: {'lr': 0.0004600003566581133, 'samples': 5571648, 'steps': 29018, 'loss/train': 1.303830623626709}
+08/30/2021 18:21:13 - INFO - __main__ - Step 29020: {'lr': 0.00045999747725521876, 'samples': 5571840, 'steps': 29019, 'loss/train': 1.6431649923324585}
+08/30/2021 18:21:14 - INFO - __main__ - Step 29021: {'lr': 0.0004599945977577026, 'samples': 5572032, 'steps': 29020, 'loss/train': 0.18844221532344818}
+08/30/2021 18:21:14 - INFO - __main__ - Step 29022: {'lr': 0.0004599917181655661, 'samples': 5572224, 'steps': 29021, 'loss/train': 2.0019733905792236}
+08/30/2021 18:21:14 - INFO - __main__ - Step 29023: {'lr': 0.00045998883847881057, 'samples': 5572416, 'steps': 29022, 'loss/train': 1.8991312980651855}
+08/30/2021 18:21:16 - INFO - __main__ - Step 29024: {'lr': 0.00045998595869743735, 'samples': 5572608, 'steps': 29023, 'loss/train': 1.6134456396102905}
+08/30/2021 18:21:16 - INFO - __main__ - Step 29025: {'lr': 0.0004599830788214477, 'samples': 5572800, 'steps': 29024, 'loss/train': 0.056618429720401764}
+08/30/2021 18:21:17 - INFO - __main__ - Step 29026: {'lr': 0.0004599801988508429, 'samples': 5572992, 'steps': 29025, 'loss/train': 1.6746482849121094}
+08/30/2021 18:21:17 - INFO - __main__ - Step 29027: {'lr': 0.00045997731878562423, 'samples': 5573184, 'steps': 29026, 'loss/train': 1.0732512474060059}
+08/30/2021 18:21:18 - INFO - __main__ - Step 29028: {'lr': 0.000459974438625793, 'samples': 5573376, 'steps': 29027, 'loss/train': 1.6636924743652344}
+08/30/2021 18:21:19 - INFO - __main__ - Step 29029: {'lr': 0.0004599715583713506, 'samples': 5573568, 'steps': 29028, 'loss/train': 2.3188862800598145}
+08/30/2021 18:21:20 - INFO - __main__ - Step 29030: {'lr': 0.00045996867802229824, 'samples': 5573760, 'steps': 29029, 'loss/train': 1.6132086515426636}
+08/30/2021 18:21:20 - INFO - __main__ - Step 29031: {'lr': 0.0004599657975786372, 'samples': 5573952, 'steps': 29030, 'loss/train': 0.8914322257041931}
+08/30/2021 18:21:20 - INFO - __main__ - Step 29032: {'lr': 0.00045996291704036884, 'samples': 5574144, 'steps': 29031, 'loss/train': 1.1770182847976685}
+08/30/2021 18:21:21 - INFO - __main__ - Step 29033: {'lr': 0.00045996003640749446, 'samples': 5574336, 'steps': 29032, 'loss/train': 1.8061771392822266}
+08/30/2021 18:21:21 - INFO - __main__ - Step 29034: {'lr': 0.0004599571556800153, 'samples': 5574528, 'steps': 29033, 'loss/train': 1.0761033296585083}
+08/30/2021 18:21:23 - INFO - __main__ - Step 29035: {'lr': 0.00045995427485793263, 'samples': 5574720, 'steps': 29034, 'loss/train': 4.809989929199219}
+08/30/2021 18:21:23 - INFO - __main__ - Step 29036: {'lr': 0.00045995139394124784, 'samples': 5574912, 'steps': 29035, 'loss/train': 1.8105863332748413}
+08/30/2021 18:21:24 - INFO - __main__ - Step 29037: {'lr': 0.0004599485129299622, 'samples': 5575104, 'steps': 29036, 'loss/train': 1.9833271503448486}
+08/30/2021 18:21:24 - INFO - __main__ - Step 29038: {'lr': 0.000459945631824077, 'samples': 5575296, 'steps': 29037, 'loss/train': 2.1372933387756348}
+08/30/2021 18:21:24 - INFO - __main__ - Step 29039: {'lr': 0.0004599427506235936, 'samples': 5575488, 'steps': 29038, 'loss/train': 1.6469768285751343}
+08/30/2021 18:21:26 - INFO - __main__ - Step 29040: {'lr': 0.0004599398693285132, 'samples': 5575680, 'steps': 29039, 'loss/train': 1.6811004877090454}
+08/30/2021 18:21:26 - INFO - __main__ - Step 29041: {'lr': 0.0004599369879388371, 'samples': 5575872, 'steps': 29040, 'loss/train': 2.101963996887207}
+08/30/2021 18:21:27 - INFO - __main__ - Step 29042: {'lr': 0.0004599341064545666, 'samples': 5576064, 'steps': 29041, 'loss/train': 1.8116940259933472}
+08/30/2021 18:21:27 - INFO - __main__ - Step 29043: {'lr': 0.00045993122487570303, 'samples': 5576256, 'steps': 29042, 'loss/train': 1.2629058361053467}
+08/30/2021 18:21:27 - INFO - __main__ - Step 29044: {'lr': 0.00045992834320224773, 'samples': 5576448, 'steps': 29043, 'loss/train': 1.6439467668533325}
+08/30/2021 18:21:29 - INFO - __main__ - Step 29045: {'lr': 0.000459925461434202, 'samples': 5576640, 'steps': 29044, 'loss/train': 1.284886121749878}
+08/30/2021 18:21:29 - INFO - __main__ - Step 29046: {'lr': 0.00045992257957156704, 'samples': 5576832, 'steps': 29045, 'loss/train': 1.5194182395935059}
+08/30/2021 18:21:29 - INFO - __main__ - Step 29047: {'lr': 0.00045991969761434426, 'samples': 5577024, 'steps': 29046, 'loss/train': 0.9067851305007935}
+08/30/2021 18:21:30 - INFO - __main__ - Step 29048: {'lr': 0.0004599168155625348, 'samples': 5577216, 'steps': 29047, 'loss/train': 1.4850435256958008}
+08/30/2021 18:21:30 - INFO - __main__ - Step 29049: {'lr': 0.00045991393341614017, 'samples': 5577408, 'steps': 29048, 'loss/train': 1.5920634269714355}
+08/30/2021 18:21:32 - INFO - __main__ - Step 29050: {'lr': 0.0004599110511751615, 'samples': 5577600, 'steps': 29049, 'loss/train': 2.0021350383758545}
+08/30/2021 18:21:32 - INFO - __main__ - Step 29051: {'lr': 0.0004599081688396002, 'samples': 5577792, 'steps': 29050, 'loss/train': 1.9680159091949463}
+08/30/2021 18:21:32 - INFO - __main__ - Step 29052: {'lr': 0.0004599052864094575, 'samples': 5577984, 'steps': 29051, 'loss/train': 1.4609522819519043}
+08/30/2021 18:21:33 - INFO - __main__ - Step 29053: {'lr': 0.0004599024038847347, 'samples': 5578176, 'steps': 29052, 'loss/train': 1.6223266124725342}
+08/30/2021 18:21:33 - INFO - __main__ - Step 29054: {'lr': 0.0004598995212654331, 'samples': 5578368, 'steps': 29053, 'loss/train': 1.5891494750976562}
+08/30/2021 18:21:35 - INFO - __main__ - Step 29055: {'lr': 0.0004598966385515541, 'samples': 5578560, 'steps': 29054, 'loss/train': 1.203086018562317}
+08/30/2021 18:21:36 - INFO - __main__ - Step 29056: {'lr': 0.00045989375574309875, 'samples': 5578752, 'steps': 29055, 'loss/train': 1.7755188941955566}
+08/30/2021 18:21:36 - INFO - __main__ - Step 29057: {'lr': 0.00045989087284006863, 'samples': 5578944, 'steps': 29056, 'loss/train': 1.4583615064620972}
+08/30/2021 18:21:36 - INFO - __main__ - Step 29058: {'lr': 0.00045988798984246496, 'samples': 5579136, 'steps': 29057, 'loss/train': 1.4929167032241821}
+08/30/2021 18:21:37 - INFO - __main__ - Step 29059: {'lr': 0.0004598851067502889, 'samples': 5579328, 'steps': 29058, 'loss/train': 0.9355854392051697}
+08/30/2021 18:21:37 - INFO - __main__ - Step 29060: {'lr': 0.00045988222356354186, 'samples': 5579520, 'steps': 29059, 'loss/train': 1.2193325757980347}
+08/30/2021 18:21:39 - INFO - __main__ - Step 29061: {'lr': 0.00045987934028222515, 'samples': 5579712, 'steps': 29060, 'loss/train': 1.1979621648788452}
+08/30/2021 18:21:39 - INFO - __main__ - Step 29062: {'lr': 0.00045987645690634003, 'samples': 5579904, 'steps': 29061, 'loss/train': 0.2693827152252197}
+08/30/2021 18:21:39 - INFO - __main__ - Step 29063: {'lr': 0.0004598735734358879, 'samples': 5580096, 'steps': 29062, 'loss/train': 1.5783582925796509}
+08/30/2021 18:21:40 - INFO - __main__ - Step 29064: {'lr': 0.0004598706898708699, 'samples': 5580288, 'steps': 29063, 'loss/train': 0.9061970710754395}
+08/30/2021 18:21:40 - INFO - __main__ - Step 29065: {'lr': 0.00045986780621128743, 'samples': 5580480, 'steps': 29064, 'loss/train': 1.7659823894500732}
+08/30/2021 18:21:42 - INFO - __main__ - Step 29066: {'lr': 0.00045986492245714175, 'samples': 5580672, 'steps': 29065, 'loss/train': 1.4529715776443481}
+08/30/2021 18:21:42 - INFO - __main__ - Step 29067: {'lr': 0.0004598620386084342, 'samples': 5580864, 'steps': 29066, 'loss/train': 1.672145962715149}
+08/30/2021 18:21:42 - INFO - __main__ - Step 29068: {'lr': 0.00045985915466516605, 'samples': 5581056, 'steps': 29067, 'loss/train': 1.891939640045166}
+08/30/2021 18:21:43 - INFO - __main__ - Step 29069: {'lr': 0.0004598562706273386, 'samples': 5581248, 'steps': 29068, 'loss/train': 1.370741367340088}
+08/30/2021 18:21:43 - INFO - __main__ - Step 29070: {'lr': 0.0004598533864949531, 'samples': 5581440, 'steps': 29069, 'loss/train': 1.5381206274032593}
+08/30/2021 18:21:45 - INFO - __main__ - Step 29071: {'lr': 0.00045985050226801097, 'samples': 5581632, 'steps': 29070, 'loss/train': 1.79341459274292}
+08/30/2021 18:21:45 - INFO - __main__ - Step 29072: {'lr': 0.0004598476179465134, 'samples': 5581824, 'steps': 29071, 'loss/train': 1.566278338432312}
+08/30/2021 18:21:46 - INFO - __main__ - Step 29073: {'lr': 0.00045984473353046174, 'samples': 5582016, 'steps': 29072, 'loss/train': 2.284355401992798}
+08/30/2021 18:21:46 - INFO - __main__ - Step 29074: {'lr': 0.00045984184901985735, 'samples': 5582208, 'steps': 29073, 'loss/train': 0.9142330288887024}
+08/30/2021 18:21:46 - INFO - __main__ - Step 29075: {'lr': 0.00045983896441470143, 'samples': 5582400, 'steps': 29074, 'loss/train': 0.06127826124429703}
+08/30/2021 18:21:48 - INFO - __main__ - Step 29076: {'lr': 0.00045983607971499527, 'samples': 5582592, 'steps': 29075, 'loss/train': 1.9395575523376465}
+08/30/2021 18:21:48 - INFO - __main__ - Step 29077: {'lr': 0.0004598331949207402, 'samples': 5582784, 'steps': 29076, 'loss/train': 0.9161554574966431}
+08/30/2021 18:21:49 - INFO - __main__ - Step 29078: {'lr': 0.00045983031003193756, 'samples': 5582976, 'steps': 29077, 'loss/train': 1.269913911819458}
+08/30/2021 18:21:49 - INFO - __main__ - Step 29079: {'lr': 0.0004598274250485886, 'samples': 5583168, 'steps': 29078, 'loss/train': 1.933900237083435}
+08/30/2021 18:21:49 - INFO - __main__ - Step 29080: {'lr': 0.00045982453997069463, 'samples': 5583360, 'steps': 29079, 'loss/train': 1.6913996934890747}
+08/30/2021 18:21:50 - INFO - __main__ - Step 29081: {'lr': 0.00045982165479825697, 'samples': 5583552, 'steps': 29080, 'loss/train': 0.9966526627540588}
+08/30/2021 18:21:51 - INFO - __main__ - Step 29082: {'lr': 0.000459818769531277, 'samples': 5583744, 'steps': 29081, 'loss/train': 1.1565251350402832}
+08/30/2021 18:21:52 - INFO - __main__ - Step 29083: {'lr': 0.00045981588416975583, 'samples': 5583936, 'steps': 29082, 'loss/train': 1.4232019186019897}
+08/30/2021 18:21:52 - INFO - __main__ - Step 29084: {'lr': 0.00045981299871369484, 'samples': 5584128, 'steps': 29083, 'loss/train': 1.2171101570129395}
+08/30/2021 18:21:53 - INFO - __main__ - Step 29085: {'lr': 0.0004598101131630954, 'samples': 5584320, 'steps': 29084, 'loss/train': 0.9350250363349915}
+08/30/2021 18:21:53 - INFO - __main__ - Step 29086: {'lr': 0.0004598072275179588, 'samples': 5584512, 'steps': 29085, 'loss/train': 1.704522728919983}
+08/30/2021 18:21:54 - INFO - __main__ - Step 29087: {'lr': 0.00045980434177828625, 'samples': 5584704, 'steps': 29086, 'loss/train': 0.9867247343063354}
+08/30/2021 18:21:55 - INFO - __main__ - Step 29088: {'lr': 0.00045980145594407907, 'samples': 5584896, 'steps': 29087, 'loss/train': 1.415088176727295}
+08/30/2021 18:21:55 - INFO - __main__ - Step 29089: {'lr': 0.00045979857001533867, 'samples': 5585088, 'steps': 29088, 'loss/train': 0.9071172475814819}
+08/30/2021 18:21:56 - INFO - __main__ - Step 29090: {'lr': 0.0004597956839920662, 'samples': 5585280, 'steps': 29089, 'loss/train': 2.0894312858581543}
+08/30/2021 18:21:56 - INFO - __main__ - Step 29091: {'lr': 0.00045979279787426307, 'samples': 5585472, 'steps': 29090, 'loss/train': 1.352568507194519}
+08/30/2021 18:21:57 - INFO - __main__ - Step 29092: {'lr': 0.00045978991166193057, 'samples': 5585664, 'steps': 29091, 'loss/train': 0.5328934192657471}
+08/30/2021 18:21:58 - INFO - __main__ - Step 29093: {'lr': 0.0004597870253550699, 'samples': 5585856, 'steps': 29092, 'loss/train': 1.7023544311523438}
+08/30/2021 18:21:58 - INFO - __main__ - Step 29094: {'lr': 0.0004597841389536825, 'samples': 5586048, 'steps': 29093, 'loss/train': 1.6095505952835083}
+08/30/2021 18:21:58 - INFO - __main__ - Step 29095: {'lr': 0.00045978125245776957, 'samples': 5586240, 'steps': 29094, 'loss/train': 1.1898564100265503}
+08/30/2021 18:21:59 - INFO - __main__ - Step 29096: {'lr': 0.00045977836586733246, 'samples': 5586432, 'steps': 29095, 'loss/train': 1.627050518989563}
+08/30/2021 18:22:00 - INFO - __main__ - Step 29097: {'lr': 0.00045977547918237243, 'samples': 5586624, 'steps': 29096, 'loss/train': 1.6160439252853394}
+08/30/2021 18:22:01 - INFO - __main__ - Step 29098: {'lr': 0.0004597725924028908, 'samples': 5586816, 'steps': 29097, 'loss/train': 2.4444825649261475}
+08/30/2021 18:22:01 - INFO - __main__ - Step 29099: {'lr': 0.00045976970552888896, 'samples': 5587008, 'steps': 29098, 'loss/train': 1.269550085067749}
+08/30/2021 18:22:01 - INFO - __main__ - Step 29100: {'lr': 0.00045976681856036805, 'samples': 5587200, 'steps': 29099, 'loss/train': 1.4420042037963867}
+08/30/2021 18:22:02 - INFO - __main__ - Step 29101: {'lr': 0.00045976393149732943, 'samples': 5587392, 'steps': 29100, 'loss/train': 1.3307113647460938}
+08/30/2021 18:22:04 - INFO - __main__ - Step 29102: {'lr': 0.0004597610443397745, 'samples': 5587584, 'steps': 29101, 'loss/train': 1.515670657157898}
+08/30/2021 18:22:04 - INFO - __main__ - Step 29103: {'lr': 0.0004597581570877044, 'samples': 5587776, 'steps': 29102, 'loss/train': 1.5040066242218018}
+08/30/2021 18:22:05 - INFO - __main__ - Step 29104: {'lr': 0.00045975526974112056, 'samples': 5587968, 'steps': 29103, 'loss/train': 1.9000853300094604}
+08/30/2021 18:22:05 - INFO - __main__ - Step 29105: {'lr': 0.0004597523823000243, 'samples': 5588160, 'steps': 29104, 'loss/train': 1.9205955266952515}
+08/30/2021 18:22:05 - INFO - __main__ - Step 29106: {'lr': 0.0004597494947644167, 'samples': 5588352, 'steps': 29105, 'loss/train': 0.8787484169006348}
+08/30/2021 18:22:06 - INFO - __main__ - Step 29107: {'lr': 0.0004597466071342993, 'samples': 5588544, 'steps': 29106, 'loss/train': 0.05248590558767319}
+08/30/2021 18:22:08 - INFO - __main__ - Step 29108: {'lr': 0.0004597437194096733, 'samples': 5588736, 'steps': 29107, 'loss/train': 1.3961764574050903}
+08/30/2021 18:22:08 - INFO - __main__ - Step 29109: {'lr': 0.00045974083159054, 'samples': 5588928, 'steps': 29108, 'loss/train': 1.5835131406784058}
+08/30/2021 18:22:09 - INFO - __main__ - Step 29110: {'lr': 0.0004597379436769008, 'samples': 5589120, 'steps': 29109, 'loss/train': 1.570286750793457}
+08/30/2021 18:22:09 - INFO - __main__ - Step 29111: {'lr': 0.00045973505566875684, 'samples': 5589312, 'steps': 29110, 'loss/train': 1.2224258184432983}
+08/30/2021 18:22:09 - INFO - __main__ - Step 29112: {'lr': 0.00045973216756610945, 'samples': 5589504, 'steps': 29111, 'loss/train': 2.063640832901001}
+08/30/2021 18:22:11 - INFO - __main__ - Step 29113: {'lr': 0.00045972927936896007, 'samples': 5589696, 'steps': 29112, 'loss/train': 1.0846408605575562}
+08/30/2021 18:22:11 - INFO - __main__ - Step 29114: {'lr': 0.0004597263910773099, 'samples': 5589888, 'steps': 29113, 'loss/train': 1.6578137874603271}
+08/30/2021 18:22:12 - INFO - __main__ - Step 29115: {'lr': 0.0004597235026911603, 'samples': 5590080, 'steps': 29114, 'loss/train': 1.6081702709197998}
+08/30/2021 18:22:12 - INFO - __main__ - Step 29116: {'lr': 0.0004597206142105124, 'samples': 5590272, 'steps': 29115, 'loss/train': 1.46647310256958}
+08/30/2021 18:22:12 - INFO - __main__ - Step 29117: {'lr': 0.0004597177256353677, 'samples': 5590464, 'steps': 29116, 'loss/train': 1.7984187602996826}
+08/30/2021 18:22:14 - INFO - __main__ - Step 29118: {'lr': 0.0004597148369657275, 'samples': 5590656, 'steps': 29117, 'loss/train': 2.0254669189453125}
+08/30/2021 18:22:14 - INFO - __main__ - Step 29119: {'lr': 0.0004597119482015929, 'samples': 5590848, 'steps': 29118, 'loss/train': 1.6421504020690918}
+08/30/2021 18:22:15 - INFO - __main__ - Step 29120: {'lr': 0.00045970905934296537, 'samples': 5591040, 'steps': 29119, 'loss/train': 1.6421531438827515}
+08/30/2021 18:22:15 - INFO - __main__ - Step 29121: {'lr': 0.0004597061703898462, 'samples': 5591232, 'steps': 29120, 'loss/train': 1.3585336208343506}
+08/30/2021 18:22:15 - INFO - __main__ - Step 29122: {'lr': 0.0004597032813422367, 'samples': 5591424, 'steps': 29121, 'loss/train': 1.2464593648910522}
+08/30/2021 18:22:17 - INFO - __main__ - Step 29123: {'lr': 0.00045970039220013804, 'samples': 5591616, 'steps': 29122, 'loss/train': 1.6743971109390259}
+08/30/2021 18:22:17 - INFO - __main__ - Step 29124: {'lr': 0.00045969750296355173, 'samples': 5591808, 'steps': 29123, 'loss/train': 1.6649267673492432}
+08/30/2021 18:22:18 - INFO - __main__ - Step 29125: {'lr': 0.0004596946136324789, 'samples': 5592000, 'steps': 29124, 'loss/train': 1.6004528999328613}
+08/30/2021 18:22:18 - INFO - __main__ - Step 29126: {'lr': 0.0004596917242069209, 'samples': 5592192, 'steps': 29125, 'loss/train': 2.043062686920166}
+08/30/2021 18:22:18 - INFO - __main__ - Step 29127: {'lr': 0.00045968883468687906, 'samples': 5592384, 'steps': 29126, 'loss/train': 1.749453067779541}
+08/30/2021 18:22:19 - INFO - __main__ - Step 29128: {'lr': 0.00045968594507235467, 'samples': 5592576, 'steps': 29127, 'loss/train': 1.4296698570251465}
+08/30/2021 18:22:20 - INFO - __main__ - Step 29129: {'lr': 0.00045968305536334906, 'samples': 5592768, 'steps': 29128, 'loss/train': 1.8172740936279297}
+08/30/2021 18:22:21 - INFO - __main__ - Step 29130: {'lr': 0.00045968016555986347, 'samples': 5592960, 'steps': 29129, 'loss/train': 1.2048875093460083}
+08/30/2021 18:22:21 - INFO - __main__ - Step 29131: {'lr': 0.0004596772756618992, 'samples': 5593152, 'steps': 29130, 'loss/train': 0.16799619793891907}
+08/30/2021 18:22:21 - INFO - __main__ - Step 29132: {'lr': 0.0004596743856694576, 'samples': 5593344, 'steps': 29131, 'loss/train': 1.5724396705627441}
+08/30/2021 18:22:22 - INFO - __main__ - Step 29133: {'lr': 0.00045967149558254, 'samples': 5593536, 'steps': 29132, 'loss/train': 1.320733666419983}
+08/30/2021 18:22:23 - INFO - __main__ - Step 29134: {'lr': 0.0004596686054011476, 'samples': 5593728, 'steps': 29133, 'loss/train': 1.5041048526763916}
+08/30/2021 18:22:24 - INFO - __main__ - Step 29135: {'lr': 0.0004596657151252819, 'samples': 5593920, 'steps': 29134, 'loss/train': 1.3871675729751587}
+08/30/2021 18:22:24 - INFO - __main__ - Step 29136: {'lr': 0.0004596628247549439, 'samples': 5594112, 'steps': 29135, 'loss/train': 1.1521623134613037}
+08/30/2021 18:22:24 - INFO - __main__ - Step 29137: {'lr': 0.00045965993429013507, 'samples': 5594304, 'steps': 29136, 'loss/train': 1.2652631998062134}
+08/30/2021 18:22:25 - INFO - __main__ - Step 29138: {'lr': 0.0004596570437308568, 'samples': 5594496, 'steps': 29137, 'loss/train': 1.6733323335647583}
+08/30/2021 18:22:26 - INFO - __main__ - Step 29139: {'lr': 0.0004596541530771103, 'samples': 5594688, 'steps': 29138, 'loss/train': 1.4596182107925415}
+08/30/2021 18:22:27 - INFO - __main__ - Step 29140: {'lr': 0.0004596512623288969, 'samples': 5594880, 'steps': 29139, 'loss/train': 1.0607844591140747}
+08/30/2021 18:22:27 - INFO - __main__ - Step 29141: {'lr': 0.00045964837148621776, 'samples': 5595072, 'steps': 29140, 'loss/train': 1.5667705535888672}
+08/30/2021 18:22:27 - INFO - __main__ - Step 29142: {'lr': 0.00045964548054907434, 'samples': 5595264, 'steps': 29141, 'loss/train': 1.7079411745071411}
+08/30/2021 18:22:28 - INFO - __main__ - Step 29143: {'lr': 0.00045964258951746795, 'samples': 5595456, 'steps': 29142, 'loss/train': 1.4324219226837158}
+08/30/2021 18:22:29 - INFO - __main__ - Step 29144: {'lr': 0.0004596396983913998, 'samples': 5595648, 'steps': 29143, 'loss/train': 1.4762330055236816}
+08/30/2021 18:22:30 - INFO - __main__ - Step 29145: {'lr': 0.00045963680717087124, 'samples': 5595840, 'steps': 29144, 'loss/train': 0.9415585994720459}
+08/30/2021 18:22:30 - INFO - __main__ - Step 29146: {'lr': 0.0004596339158558835, 'samples': 5596032, 'steps': 29145, 'loss/train': 1.843888759613037}
+08/30/2021 18:22:30 - INFO - __main__ - Step 29147: {'lr': 0.0004596310244464381, 'samples': 5596224, 'steps': 29146, 'loss/train': 1.2072358131408691}
+08/30/2021 18:22:31 - INFO - __main__ - Step 29148: {'lr': 0.0004596281329425361, 'samples': 5596416, 'steps': 29147, 'loss/train': 1.0851892232894897}
+08/30/2021 18:22:32 - INFO - __main__ - Step 29149: {'lr': 0.0004596252413441789, 'samples': 5596608, 'steps': 29148, 'loss/train': 1.4955570697784424}
+08/30/2021 18:22:33 - INFO - __main__ - Step 29150: {'lr': 0.00045962234965136783, 'samples': 5596800, 'steps': 29149, 'loss/train': 2.4021732807159424}
+08/30/2021 18:22:33 - INFO - __main__ - Step 29151: {'lr': 0.0004596194578641042, 'samples': 5596992, 'steps': 29150, 'loss/train': 1.2575191259384155}
+08/30/2021 18:22:33 - INFO - __main__ - Step 29152: {'lr': 0.00045961656598238925, 'samples': 5597184, 'steps': 29151, 'loss/train': 1.2860348224639893}
+08/30/2021 18:22:34 - INFO - __main__ - Step 29153: {'lr': 0.00045961367400622436, 'samples': 5597376, 'steps': 29152, 'loss/train': 1.8073841333389282}
+08/30/2021 18:22:35 - INFO - __main__ - Step 29154: {'lr': 0.00045961078193561066, 'samples': 5597568, 'steps': 29153, 'loss/train': 1.476631760597229}
+08/30/2021 18:22:36 - INFO - __main__ - Step 29155: {'lr': 0.00045960788977054967, 'samples': 5597760, 'steps': 29154, 'loss/train': 1.0465525388717651}
+08/30/2021 18:22:36 - INFO - __main__ - Step 29156: {'lr': 0.0004596049975110426, 'samples': 5597952, 'steps': 29155, 'loss/train': 1.152707576751709}
+08/30/2021 18:22:36 - INFO - __main__ - Step 29157: {'lr': 0.00045960210515709064, 'samples': 5598144, 'steps': 29156, 'loss/train': 0.7667427062988281}
+08/30/2021 18:22:37 - INFO - __main__ - Step 29158: {'lr': 0.0004595992127086953, 'samples': 5598336, 'steps': 29157, 'loss/train': 1.2475523948669434}
+08/30/2021 18:22:37 - INFO - __main__ - Step 29159: {'lr': 0.00045959632016585774, 'samples': 5598528, 'steps': 29158, 'loss/train': 1.6949416399002075}
+08/30/2021 18:22:39 - INFO - __main__ - Step 29160: {'lr': 0.0004595934275285794, 'samples': 5598720, 'steps': 29159, 'loss/train': 1.3139251470565796}
+08/30/2021 18:22:39 - INFO - __main__ - Step 29161: {'lr': 0.00045959053479686143, 'samples': 5598912, 'steps': 29160, 'loss/train': 1.4462741613388062}
+08/30/2021 18:22:40 - INFO - __main__ - Step 29162: {'lr': 0.0004595876419707052, 'samples': 5599104, 'steps': 29161, 'loss/train': 1.3975965976715088}
+08/30/2021 18:22:40 - INFO - __main__ - Step 29163: {'lr': 0.00045958474905011205, 'samples': 5599296, 'steps': 29162, 'loss/train': 1.3741061687469482}
+08/30/2021 18:22:40 - INFO - __main__ - Step 29164: {'lr': 0.0004595818560350832, 'samples': 5599488, 'steps': 29163, 'loss/train': 1.5134464502334595}
+08/30/2021 18:22:42 - INFO - __main__ - Step 29165: {'lr': 0.00045957896292562003, 'samples': 5599680, 'steps': 29164, 'loss/train': 0.25229430198669434}
+08/30/2021 18:22:43 - INFO - __main__ - Step 29166: {'lr': 0.0004595760697217238, 'samples': 5599872, 'steps': 29165, 'loss/train': 0.8913015723228455}
+08/30/2021 18:22:43 - INFO - __main__ - Step 29167: {'lr': 0.0004595731764233958, 'samples': 5600064, 'steps': 29166, 'loss/train': 1.661893367767334}
+08/30/2021 18:22:43 - INFO - __main__ - Step 29168: {'lr': 0.0004595702830306374, 'samples': 5600256, 'steps': 29167, 'loss/train': 1.9168347120285034}
+08/30/2021 18:22:44 - INFO - __main__ - Step 29169: {'lr': 0.0004595673895434498, 'samples': 5600448, 'steps': 29168, 'loss/train': 0.8361132144927979}
+08/30/2021 18:22:45 - INFO - __main__ - Step 29170: {'lr': 0.00045956449596183446, 'samples': 5600640, 'steps': 29169, 'loss/train': 1.3470408916473389}
+08/30/2021 18:22:46 - INFO - __main__ - Step 29171: {'lr': 0.00045956160228579257, 'samples': 5600832, 'steps': 29170, 'loss/train': 1.165398120880127}
+08/30/2021 18:22:46 - INFO - __main__ - Step 29172: {'lr': 0.00045955870851532545, 'samples': 5601024, 'steps': 29171, 'loss/train': 1.80191171169281}
+08/30/2021 18:22:46 - INFO - __main__ - Step 29173: {'lr': 0.0004595558146504344, 'samples': 5601216, 'steps': 29172, 'loss/train': 2.0715763568878174}
+08/30/2021 18:22:47 - INFO - __main__ - Step 29174: {'lr': 0.0004595529206911207, 'samples': 5601408, 'steps': 29173, 'loss/train': 1.1101596355438232}
+08/30/2021 18:22:48 - INFO - __main__ - Step 29175: {'lr': 0.00045955002663738574, 'samples': 5601600, 'steps': 29174, 'loss/train': 0.09882716089487076}
+08/30/2021 18:22:49 - INFO - __main__ - Step 29176: {'lr': 0.0004595471324892307, 'samples': 5601792, 'steps': 29175, 'loss/train': 1.6886543035507202}
+08/30/2021 18:22:49 - INFO - __main__ - Step 29177: {'lr': 0.00045954423824665704, 'samples': 5601984, 'steps': 29176, 'loss/train': 1.2996711730957031}
+08/30/2021 18:22:49 - INFO - __main__ - Step 29178: {'lr': 0.00045954134390966593, 'samples': 5602176, 'steps': 29177, 'loss/train': 1.4013592004776}
+08/30/2021 18:22:50 - INFO - __main__ - Step 29179: {'lr': 0.00045953844947825876, 'samples': 5602368, 'steps': 29178, 'loss/train': 1.9827604293823242}
+08/30/2021 18:22:52 - INFO - __main__ - Step 29180: {'lr': 0.0004595355549524368, 'samples': 5602560, 'steps': 29179, 'loss/train': 1.980088233947754}
+08/30/2021 18:22:52 - INFO - __main__ - Step 29181: {'lr': 0.0004595326603322013, 'samples': 5602752, 'steps': 29180, 'loss/train': 1.4789692163467407}
+08/30/2021 18:22:52 - INFO - __main__ - Step 29182: {'lr': 0.00045952976561755365, 'samples': 5602944, 'steps': 29181, 'loss/train': 1.647566556930542}
+08/30/2021 18:22:53 - INFO - __main__ - Step 29183: {'lr': 0.00045952687080849517, 'samples': 5603136, 'steps': 29182, 'loss/train': 0.47545647621154785}
+08/30/2021 18:22:53 - INFO - __main__ - Step 29184: {'lr': 0.000459523975905027, 'samples': 5603328, 'steps': 29183, 'loss/train': 1.475440502166748}
+08/30/2021 18:22:53 - INFO - __main__ - Step 29185: {'lr': 0.0004595210809071506, 'samples': 5603520, 'steps': 29184, 'loss/train': 0.9235596656799316}
+08/30/2021 18:22:55 - INFO - __main__ - Step 29186: {'lr': 0.0004595181858148673, 'samples': 5603712, 'steps': 29185, 'loss/train': 1.172926664352417}
+08/30/2021 18:22:55 - INFO - __main__ - Step 29187: {'lr': 0.00045951529062817834, 'samples': 5603904, 'steps': 29186, 'loss/train': 2.1116085052490234}
+08/30/2021 18:22:56 - INFO - __main__ - Step 29188: {'lr': 0.00045951239534708496, 'samples': 5604096, 'steps': 29187, 'loss/train': 0.9593750238418579}
+08/30/2021 18:22:56 - INFO - __main__ - Step 29189: {'lr': 0.0004595094999715885, 'samples': 5604288, 'steps': 29188, 'loss/train': 1.3687018156051636}
+08/30/2021 18:22:56 - INFO - __main__ - Step 29190: {'lr': 0.00045950660450169034, 'samples': 5604480, 'steps': 29189, 'loss/train': 1.3395719528198242}
+08/30/2021 18:22:58 - INFO - __main__ - Step 29191: {'lr': 0.0004595037089373918, 'samples': 5604672, 'steps': 29190, 'loss/train': 1.7803689241409302}
+08/30/2021 18:22:59 - INFO - __main__ - Step 29192: {'lr': 0.000459500813278694, 'samples': 5604864, 'steps': 29191, 'loss/train': 1.9081834554672241}
+08/30/2021 18:22:59 - INFO - __main__ - Step 29193: {'lr': 0.0004594979175255984, 'samples': 5605056, 'steps': 29192, 'loss/train': 1.6339938640594482}
+08/30/2021 18:22:59 - INFO - __main__ - Step 29194: {'lr': 0.0004594950216781063, 'samples': 5605248, 'steps': 29193, 'loss/train': 1.5923702716827393}
+08/30/2021 18:23:00 - INFO - __main__ - Step 29195: {'lr': 0.000459492125736219, 'samples': 5605440, 'steps': 29194, 'loss/train': 1.3523986339569092}
+08/30/2021 18:23:00 - INFO - __main__ - Step 29196: {'lr': 0.00045948922969993777, 'samples': 5605632, 'steps': 29195, 'loss/train': 1.2019221782684326}
+08/30/2021 18:23:02 - INFO - __main__ - Step 29197: {'lr': 0.0004594863335692639, 'samples': 5605824, 'steps': 29196, 'loss/train': 1.6492379903793335}
+08/30/2021 18:23:02 - INFO - __main__ - Step 29198: {'lr': 0.00045948343734419873, 'samples': 5606016, 'steps': 29197, 'loss/train': 1.7129063606262207}
+08/30/2021 18:23:03 - INFO - __main__ - Step 29199: {'lr': 0.00045948054102474357, 'samples': 5606208, 'steps': 29198, 'loss/train': 1.426788091659546}
+08/30/2021 18:23:03 - INFO - __main__ - Step 29200: {'lr': 0.00045947764461089967, 'samples': 5606400, 'steps': 29199, 'loss/train': 0.5952116847038269}
+08/30/2021 18:23:03 - INFO - __main__ - Step 29201: {'lr': 0.00045947474810266844, 'samples': 5606592, 'steps': 29200, 'loss/train': 1.5822315216064453}
+08/30/2021 18:23:05 - INFO - __main__ - Step 29202: {'lr': 0.00045947185150005106, 'samples': 5606784, 'steps': 29201, 'loss/train': 2.031177520751953}
+08/30/2021 18:23:05 - INFO - __main__ - Step 29203: {'lr': 0.0004594689548030489, 'samples': 5606976, 'steps': 29202, 'loss/train': 1.9758672714233398}
+08/30/2021 18:23:06 - INFO - __main__ - Step 29204: {'lr': 0.0004594660580116633, 'samples': 5607168, 'steps': 29203, 'loss/train': 1.39204740524292}
+08/30/2021 18:23:06 - INFO - __main__ - Step 29205: {'lr': 0.00045946316112589546, 'samples': 5607360, 'steps': 29204, 'loss/train': 1.5581611394882202}
+08/30/2021 18:23:06 - INFO - __main__ - Step 29206: {'lr': 0.0004594602641457468, 'samples': 5607552, 'steps': 29205, 'loss/train': 1.5157995223999023}
+08/30/2021 18:23:08 - INFO - __main__ - Step 29207: {'lr': 0.0004594573670712186, 'samples': 5607744, 'steps': 29206, 'loss/train': 1.6905176639556885}
+08/30/2021 18:23:08 - INFO - __main__ - Step 29208: {'lr': 0.0004594544699023121, 'samples': 5607936, 'steps': 29207, 'loss/train': 1.2826634645462036}
+08/30/2021 18:23:09 - INFO - __main__ - Step 29209: {'lr': 0.0004594515726390287, 'samples': 5608128, 'steps': 29208, 'loss/train': 0.9444410800933838}
+08/30/2021 18:23:09 - INFO - __main__ - Step 29210: {'lr': 0.00045944867528136956, 'samples': 5608320, 'steps': 29209, 'loss/train': 1.087119460105896}
+08/30/2021 18:23:09 - INFO - __main__ - Step 29211: {'lr': 0.00045944577782933615, 'samples': 5608512, 'steps': 29210, 'loss/train': 1.0510333776474}
+08/30/2021 18:23:10 - INFO - __main__ - Step 29212: {'lr': 0.0004594428802829297, 'samples': 5608704, 'steps': 29211, 'loss/train': 1.255640983581543}
+08/30/2021 18:23:11 - INFO - __main__ - Step 29213: {'lr': 0.00045943998264215153, 'samples': 5608896, 'steps': 29212, 'loss/train': 1.7238624095916748}
+08/30/2021 18:23:12 - INFO - __main__ - Step 29214: {'lr': 0.0004594370849070029, 'samples': 5609088, 'steps': 29213, 'loss/train': 1.659794569015503}
+08/30/2021 18:23:12 - INFO - __main__ - Step 29215: {'lr': 0.00045943418707748517, 'samples': 5609280, 'steps': 29214, 'loss/train': 1.7247980833053589}
+08/30/2021 18:23:12 - INFO - __main__ - Step 29216: {'lr': 0.00045943128915359966, 'samples': 5609472, 'steps': 29215, 'loss/train': 1.1598666906356812}
+08/30/2021 18:23:13 - INFO - __main__ - Step 29217: {'lr': 0.0004594283911353476, 'samples': 5609664, 'steps': 29216, 'loss/train': 1.5883209705352783}
+08/30/2021 18:23:15 - INFO - __main__ - Step 29218: {'lr': 0.0004594254930227303, 'samples': 5609856, 'steps': 29217, 'loss/train': 1.5780142545700073}
+08/30/2021 18:23:15 - INFO - __main__ - Step 29219: {'lr': 0.0004594225948157492, 'samples': 5610048, 'steps': 29218, 'loss/train': 1.6981172561645508}
+08/30/2021 18:23:16 - INFO - __main__ - Step 29220: {'lr': 0.0004594196965144054, 'samples': 5610240, 'steps': 29219, 'loss/train': 1.4002854824066162}
+08/30/2021 18:23:16 - INFO - __main__ - Step 29221: {'lr': 0.0004594167981187004, 'samples': 5610432, 'steps': 29220, 'loss/train': 1.4901771545410156}
+08/30/2021 18:23:16 - INFO - __main__ - Step 29222: {'lr': 0.00045941389962863546, 'samples': 5610624, 'steps': 29221, 'loss/train': 1.5295490026474}
+08/30/2021 18:23:18 - INFO - __main__ - Step 29223: {'lr': 0.00045941100104421176, 'samples': 5610816, 'steps': 29222, 'loss/train': 1.678505539894104}
+08/30/2021 18:23:18 - INFO - __main__ - Step 29224: {'lr': 0.0004594081023654307, 'samples': 5611008, 'steps': 29223, 'loss/train': 1.438895344734192}
+08/30/2021 18:23:19 - INFO - __main__ - Step 29225: {'lr': 0.00045940520359229366, 'samples': 5611200, 'steps': 29224, 'loss/train': 1.273938536643982}
+08/30/2021 18:23:19 - INFO - __main__ - Step 29226: {'lr': 0.0004594023047248018, 'samples': 5611392, 'steps': 29225, 'loss/train': 1.7192295789718628}
+08/30/2021 18:23:19 - INFO - __main__ - Step 29227: {'lr': 0.0004593994057629565, 'samples': 5611584, 'steps': 29226, 'loss/train': 1.2510654926300049}
+08/30/2021 18:23:21 - INFO - __main__ - Step 29228: {'lr': 0.000459396506706759, 'samples': 5611776, 'steps': 29227, 'loss/train': 0.9602096676826477}
+08/30/2021 18:23:21 - INFO - __main__ - Step 29229: {'lr': 0.00045939360755621074, 'samples': 5611968, 'steps': 29228, 'loss/train': 1.667063593864441}
+08/30/2021 18:23:22 - INFO - __main__ - Step 29230: {'lr': 0.00045939070831131293, 'samples': 5612160, 'steps': 29229, 'loss/train': 1.843064546585083}
+08/30/2021 18:23:22 - INFO - __main__ - Step 29231: {'lr': 0.00045938780897206686, 'samples': 5612352, 'steps': 29230, 'loss/train': 1.830507755279541}
+08/30/2021 18:23:22 - INFO - __main__ - Step 29232: {'lr': 0.000459384909538474, 'samples': 5612544, 'steps': 29231, 'loss/train': 1.4795317649841309}
+08/30/2021 18:23:24 - INFO - __main__ - Step 29233: {'lr': 0.00045938201001053546, 'samples': 5612736, 'steps': 29232, 'loss/train': 1.0575584173202515}
+08/30/2021 18:23:24 - INFO - __main__ - Step 29234: {'lr': 0.00045937911038825257, 'samples': 5612928, 'steps': 29233, 'loss/train': 1.151182770729065}
+08/30/2021 18:23:24 - INFO - __main__ - Step 29235: {'lr': 0.00045937621067162674, 'samples': 5613120, 'steps': 29234, 'loss/train': 1.608346700668335}
+08/30/2021 18:23:25 - INFO - __main__ - Step 29236: {'lr': 0.0004593733108606592, 'samples': 5613312, 'steps': 29235, 'loss/train': 1.6283247470855713}
+08/30/2021 18:23:25 - INFO - __main__ - Step 29237: {'lr': 0.00045937041095535125, 'samples': 5613504, 'steps': 29236, 'loss/train': 0.992626965045929}
+08/30/2021 18:23:27 - INFO - __main__ - Step 29238: {'lr': 0.00045936751095570426, 'samples': 5613696, 'steps': 29237, 'loss/train': 1.8615106344223022}
+08/30/2021 18:23:27 - INFO - __main__ - Step 29239: {'lr': 0.0004593646108617195, 'samples': 5613888, 'steps': 29238, 'loss/train': 1.2490863800048828}
+08/30/2021 18:23:28 - INFO - __main__ - Step 29240: {'lr': 0.00045936171067339826, 'samples': 5614080, 'steps': 29239, 'loss/train': 0.8721458911895752}
+08/30/2021 18:23:28 - INFO - __main__ - Step 29241: {'lr': 0.0004593588103907419, 'samples': 5614272, 'steps': 29240, 'loss/train': 1.4577882289886475}
+08/30/2021 18:23:28 - INFO - __main__ - Step 29242: {'lr': 0.00045935591001375163, 'samples': 5614464, 'steps': 29241, 'loss/train': 1.1836299896240234}
+08/30/2021 18:23:30 - INFO - __main__ - Step 29243: {'lr': 0.0004593530095424289, 'samples': 5614656, 'steps': 29242, 'loss/train': 1.4437614679336548}
+08/30/2021 18:23:30 - INFO - __main__ - Step 29244: {'lr': 0.0004593501089767749, 'samples': 5614848, 'steps': 29243, 'loss/train': 1.8363823890686035}
+08/30/2021 18:23:31 - INFO - __main__ - Step 29245: {'lr': 0.00045934720831679093, 'samples': 5615040, 'steps': 29244, 'loss/train': 1.7396713495254517}
+08/30/2021 18:23:31 - INFO - __main__ - Step 29246: {'lr': 0.00045934430756247835, 'samples': 5615232, 'steps': 29245, 'loss/train': 1.134104609489441}
+08/30/2021 18:23:31 - INFO - __main__ - Step 29247: {'lr': 0.0004593414067138385, 'samples': 5615424, 'steps': 29246, 'loss/train': 1.3727607727050781}
+08/30/2021 18:23:33 - INFO - __main__ - Step 29248: {'lr': 0.0004593385057708726, 'samples': 5615616, 'steps': 29247, 'loss/train': 2.2144601345062256}
+08/30/2021 18:23:33 - INFO - __main__ - Step 29249: {'lr': 0.00045933560473358206, 'samples': 5615808, 'steps': 29248, 'loss/train': 0.8779964447021484}
+08/30/2021 18:23:34 - INFO - __main__ - Step 29250: {'lr': 0.00045933270360196804, 'samples': 5616000, 'steps': 29249, 'loss/train': 0.9211687445640564}
+08/30/2021 18:23:34 - INFO - __main__ - Step 29251: {'lr': 0.00045932980237603196, 'samples': 5616192, 'steps': 29250, 'loss/train': 1.9939184188842773}
+08/30/2021 18:23:34 - INFO - __main__ - Step 29252: {'lr': 0.0004593269010557751, 'samples': 5616384, 'steps': 29251, 'loss/train': 1.875595211982727}
+08/30/2021 18:23:36 - INFO - __main__ - Step 29253: {'lr': 0.00045932399964119884, 'samples': 5616576, 'steps': 29252, 'loss/train': 0.7005326151847839}
+08/30/2021 18:23:36 - INFO - __main__ - Step 29254: {'lr': 0.00045932109813230437, 'samples': 5616768, 'steps': 29253, 'loss/train': 0.7504449486732483}
+08/30/2021 18:23:37 - INFO - __main__ - Step 29255: {'lr': 0.00045931819652909303, 'samples': 5616960, 'steps': 29254, 'loss/train': 1.004144310951233}
+08/30/2021 18:23:37 - INFO - __main__ - Step 29256: {'lr': 0.0004593152948315661, 'samples': 5617152, 'steps': 29255, 'loss/train': 2.0227677822113037}
+08/30/2021 18:23:37 - INFO - __main__ - Step 29257: {'lr': 0.000459312393039725, 'samples': 5617344, 'steps': 29256, 'loss/train': 1.3434467315673828}
+08/30/2021 18:23:39 - INFO - __main__ - Step 29258: {'lr': 0.0004593094911535709, 'samples': 5617536, 'steps': 29257, 'loss/train': 1.2487927675247192}
+08/30/2021 18:23:39 - INFO - __main__ - Step 29259: {'lr': 0.00045930658917310525, 'samples': 5617728, 'steps': 29258, 'loss/train': 1.1003031730651855}
+08/30/2021 18:23:40 - INFO - __main__ - Step 29260: {'lr': 0.0004593036870983293, 'samples': 5617920, 'steps': 29259, 'loss/train': 0.5249273777008057}
+08/30/2021 18:23:40 - INFO - __main__ - Step 29261: {'lr': 0.0004593007849292442, 'samples': 5618112, 'steps': 29260, 'loss/train': 1.3971539735794067}
+08/30/2021 18:23:40 - INFO - __main__ - Step 29262: {'lr': 0.0004592978826658515, 'samples': 5618304, 'steps': 29261, 'loss/train': 1.1266720294952393}
+08/30/2021 18:23:41 - INFO - __main__ - Step 29263: {'lr': 0.0004592949803081524, 'samples': 5618496, 'steps': 29262, 'loss/train': 1.3973729610443115}
+08/30/2021 18:23:42 - INFO - __main__ - Step 29264: {'lr': 0.0004592920778561481, 'samples': 5618688, 'steps': 29263, 'loss/train': 1.573115587234497}
+08/30/2021 18:23:43 - INFO - __main__ - Step 29265: {'lr': 0.00045928917530984014, 'samples': 5618880, 'steps': 29264, 'loss/train': 1.5579097270965576}
+08/30/2021 18:23:43 - INFO - __main__ - Step 29266: {'lr': 0.00045928627266922974, 'samples': 5619072, 'steps': 29265, 'loss/train': 1.3227323293685913}
+08/30/2021 18:23:43 - INFO - __main__ - Step 29267: {'lr': 0.0004592833699343181, 'samples': 5619264, 'steps': 29266, 'loss/train': 1.3814913034439087}
+08/30/2021 18:23:44 - INFO - __main__ - Step 29268: {'lr': 0.0004592804671051066, 'samples': 5619456, 'steps': 29267, 'loss/train': 1.4172732830047607}
+08/30/2021 18:23:46 - INFO - __main__ - Step 29269: {'lr': 0.0004592775641815966, 'samples': 5619648, 'steps': 29268, 'loss/train': 1.255063772201538}
+08/30/2021 18:23:46 - INFO - __main__ - Step 29270: {'lr': 0.0004592746611637893, 'samples': 5619840, 'steps': 29269, 'loss/train': 1.000472068786621}
+08/30/2021 18:23:46 - INFO - __main__ - Step 29271: {'lr': 0.00045927175805168607, 'samples': 5620032, 'steps': 29270, 'loss/train': 1.4347294569015503}
+08/30/2021 18:23:47 - INFO - __main__ - Step 29272: {'lr': 0.00045926885484528823, 'samples': 5620224, 'steps': 29271, 'loss/train': 1.3716964721679688}
+08/30/2021 18:23:47 - INFO - __main__ - Step 29273: {'lr': 0.0004592659515445971, 'samples': 5620416, 'steps': 29272, 'loss/train': 1.3793617486953735}
+08/30/2021 18:23:49 - INFO - __main__ - Step 29274: {'lr': 0.00045926304814961397, 'samples': 5620608, 'steps': 29273, 'loss/train': 2.1355173587799072}
+08/30/2021 18:23:49 - INFO - __main__ - Step 29275: {'lr': 0.00045926014466034004, 'samples': 5620800, 'steps': 29274, 'loss/train': 1.9838016033172607}
+08/30/2021 18:23:49 - INFO - __main__ - Step 29276: {'lr': 0.0004592572410767768, 'samples': 5620992, 'steps': 29275, 'loss/train': 1.316576600074768}
+08/30/2021 18:23:50 - INFO - __main__ - Step 29277: {'lr': 0.0004592543373989255, 'samples': 5621184, 'steps': 29276, 'loss/train': 1.364548921585083}
+08/30/2021 18:23:50 - INFO - __main__ - Step 29278: {'lr': 0.0004592514336267874, 'samples': 5621376, 'steps': 29277, 'loss/train': 0.8687638640403748}
+08/30/2021 18:23:52 - INFO - __main__ - Step 29279: {'lr': 0.0004592485297603638, 'samples': 5621568, 'steps': 29278, 'loss/train': 1.6683703660964966}
+08/30/2021 18:23:52 - INFO - __main__ - Step 29280: {'lr': 0.0004592456257996561, 'samples': 5621760, 'steps': 29279, 'loss/train': 1.223831295967102}
+08/30/2021 18:23:53 - INFO - __main__ - Step 29281: {'lr': 0.0004592427217446655, 'samples': 5621952, 'steps': 29280, 'loss/train': 1.568655014038086}
+08/30/2021 18:23:53 - INFO - __main__ - Step 29282: {'lr': 0.00045923981759539336, 'samples': 5622144, 'steps': 29281, 'loss/train': 0.8661690950393677}
+08/30/2021 18:23:53 - INFO - __main__ - Step 29283: {'lr': 0.000459236913351841, 'samples': 5622336, 'steps': 29282, 'loss/train': 2.0108747482299805}
+08/30/2021 18:23:54 - INFO - __main__ - Step 29284: {'lr': 0.0004592340090140097, 'samples': 5622528, 'steps': 29283, 'loss/train': 0.9387965202331543}
+08/30/2021 18:23:55 - INFO - __main__ - Step 29285: {'lr': 0.0004592311045819008, 'samples': 5622720, 'steps': 29284, 'loss/train': 1.8075882196426392}
+08/30/2021 18:23:56 - INFO - __main__ - Step 29286: {'lr': 0.00045922820005551556, 'samples': 5622912, 'steps': 29285, 'loss/train': 0.9452568292617798}
+08/30/2021 18:23:56 - INFO - __main__ - Step 29287: {'lr': 0.0004592252954348554, 'samples': 5623104, 'steps': 29286, 'loss/train': 1.3390796184539795}
+08/30/2021 18:23:56 - INFO - __main__ - Step 29288: {'lr': 0.0004592223907199215, 'samples': 5623296, 'steps': 29287, 'loss/train': 1.1554780006408691}
+08/30/2021 18:23:57 - INFO - __main__ - Step 29289: {'lr': 0.0004592194859107153, 'samples': 5623488, 'steps': 29288, 'loss/train': 1.4837032556533813}
+08/30/2021 18:23:58 - INFO - __main__ - Step 29290: {'lr': 0.0004592165810072379, 'samples': 5623680, 'steps': 29289, 'loss/train': 1.022546648979187}
+08/30/2021 18:23:58 - INFO - __main__ - Step 29291: {'lr': 0.00045921367600949077, 'samples': 5623872, 'steps': 29290, 'loss/train': 2.0431230068206787}
+08/30/2021 18:23:59 - INFO - __main__ - Step 29292: {'lr': 0.0004592107709174752, 'samples': 5624064, 'steps': 29291, 'loss/train': 1.0799243450164795}
+08/30/2021 18:23:59 - INFO - __main__ - Step 29293: {'lr': 0.0004592078657311925, 'samples': 5624256, 'steps': 29292, 'loss/train': 1.9466733932495117}
+08/30/2021 18:24:00 - INFO - __main__ - Step 29294: {'lr': 0.000459204960450644, 'samples': 5624448, 'steps': 29293, 'loss/train': 1.696338415145874}
+08/30/2021 18:24:01 - INFO - __main__ - Step 29295: {'lr': 0.0004592020550758309, 'samples': 5624640, 'steps': 29294, 'loss/train': 1.9128203392028809}
+08/30/2021 18:24:02 - INFO - __main__ - Step 29296: {'lr': 0.0004591991496067546, 'samples': 5624832, 'steps': 29295, 'loss/train': 0.7891136407852173}
+08/30/2021 18:24:02 - INFO - __main__ - Step 29297: {'lr': 0.00045919624404341643, 'samples': 5625024, 'steps': 29296, 'loss/train': 0.862982988357544}
+08/30/2021 18:24:02 - INFO - __main__ - Step 29298: {'lr': 0.00045919333838581757, 'samples': 5625216, 'steps': 29297, 'loss/train': 1.9168561697006226}
+08/30/2021 18:24:03 - INFO - __main__ - Step 29299: {'lr': 0.00045919043263395953, 'samples': 5625408, 'steps': 29298, 'loss/train': 2.242788076400757}
+08/30/2021 18:24:05 - INFO - __main__ - Step 29300: {'lr': 0.00045918752678784344, 'samples': 5625600, 'steps': 29299, 'loss/train': 0.987244725227356}
+08/30/2021 18:24:05 - INFO - __main__ - Step 29301: {'lr': 0.0004591846208474707, 'samples': 5625792, 'steps': 29300, 'loss/train': 1.4617302417755127}
+08/30/2021 18:24:05 - INFO - __main__ - Step 29302: {'lr': 0.00045918171481284256, 'samples': 5625984, 'steps': 29301, 'loss/train': 1.0888047218322754}
+08/30/2021 18:24:06 - INFO - __main__ - Step 29303: {'lr': 0.0004591788086839604, 'samples': 5626176, 'steps': 29302, 'loss/train': 1.3656442165374756}
+08/30/2021 18:24:06 - INFO - __main__ - Step 29304: {'lr': 0.0004591759024608255, 'samples': 5626368, 'steps': 29303, 'loss/train': 0.27926814556121826}
+08/30/2021 18:24:08 - INFO - __main__ - Step 29305: {'lr': 0.0004591729961434392, 'samples': 5626560, 'steps': 29304, 'loss/train': 0.8646825551986694}
+08/30/2021 18:24:08 - INFO - __main__ - Step 29306: {'lr': 0.00045917008973180273, 'samples': 5626752, 'steps': 29305, 'loss/train': 1.7475866079330444}
+08/30/2021 18:24:09 - INFO - __main__ - Step 29307: {'lr': 0.0004591671832259174, 'samples': 5626944, 'steps': 29306, 'loss/train': 1.5658386945724487}
+08/30/2021 18:24:09 - INFO - __main__ - Step 29308: {'lr': 0.00045916427662578464, 'samples': 5627136, 'steps': 29307, 'loss/train': 1.567349910736084}
+08/30/2021 18:24:09 - INFO - __main__ - Step 29309: {'lr': 0.00045916136993140574, 'samples': 5627328, 'steps': 29308, 'loss/train': 1.929797649383545}
+08/30/2021 18:24:11 - INFO - __main__ - Step 29310: {'lr': 0.00045915846314278187, 'samples': 5627520, 'steps': 29309, 'loss/train': 1.587865948677063}
+08/30/2021 18:24:11 - INFO - __main__ - Step 29311: {'lr': 0.0004591555562599144, 'samples': 5627712, 'steps': 29310, 'loss/train': 1.904259443283081}
+08/30/2021 18:24:11 - INFO - __main__ - Step 29312: {'lr': 0.00045915264928280476, 'samples': 5627904, 'steps': 29311, 'loss/train': 0.4572484493255615}
+08/30/2021 18:24:12 - INFO - __main__ - Step 29313: {'lr': 0.00045914974221145403, 'samples': 5628096, 'steps': 29312, 'loss/train': 1.4013017416000366}
+08/30/2021 18:24:12 - INFO - __main__ - Step 29314: {'lr': 0.00045914683504586374, 'samples': 5628288, 'steps': 29313, 'loss/train': 1.0001164674758911}
+08/30/2021 18:24:13 - INFO - __main__ - Step 29315: {'lr': 0.0004591439277860351, 'samples': 5628480, 'steps': 29314, 'loss/train': 1.1321221590042114}
+08/30/2021 18:24:14 - INFO - __main__ - Step 29316: {'lr': 0.00045914102043196947, 'samples': 5628672, 'steps': 29315, 'loss/train': 1.1323622465133667}
+08/30/2021 18:24:14 - INFO - __main__ - Step 29317: {'lr': 0.00045913811298366804, 'samples': 5628864, 'steps': 29316, 'loss/train': 0.9505067467689514}
+08/30/2021 18:24:15 - INFO - __main__ - Step 29318: {'lr': 0.0004591352054411323, 'samples': 5629056, 'steps': 29317, 'loss/train': 1.6290580034255981}
+08/30/2021 18:24:15 - INFO - __main__ - Step 29319: {'lr': 0.00045913229780436337, 'samples': 5629248, 'steps': 29318, 'loss/train': 1.8942209482192993}
+08/30/2021 18:24:16 - INFO - __main__ - Step 29320: {'lr': 0.00045912939007336273, 'samples': 5629440, 'steps': 29319, 'loss/train': 1.6758254766464233}
+08/30/2021 18:24:17 - INFO - __main__ - Step 29321: {'lr': 0.0004591264822481316, 'samples': 5629632, 'steps': 29320, 'loss/train': 1.3814494609832764}
+08/30/2021 18:24:17 - INFO - __main__ - Step 29322: {'lr': 0.00045912357432867124, 'samples': 5629824, 'steps': 29321, 'loss/train': 1.2043546438217163}
+08/30/2021 18:24:18 - INFO - __main__ - Step 29323: {'lr': 0.00045912066631498304, 'samples': 5630016, 'steps': 29322, 'loss/train': 2.0598459243774414}
+08/30/2021 18:24:18 - INFO - __main__ - Step 29324: {'lr': 0.00045911775820706835, 'samples': 5630208, 'steps': 29323, 'loss/train': 0.9047432541847229}
+08/30/2021 18:24:18 - INFO - __main__ - Step 29325: {'lr': 0.0004591148500049284, 'samples': 5630400, 'steps': 29324, 'loss/train': 0.9984139800071716}
+08/30/2021 18:24:21 - INFO - __main__ - Step 29326: {'lr': 0.00045911194170856454, 'samples': 5630592, 'steps': 29325, 'loss/train': 1.636504888534546}
+08/30/2021 18:24:21 - INFO - __main__ - Step 29327: {'lr': 0.00045910903331797807, 'samples': 5630784, 'steps': 29326, 'loss/train': 2.1306819915771484}
+08/30/2021 18:24:22 - INFO - __main__ - Step 29328: {'lr': 0.00045910612483317025, 'samples': 5630976, 'steps': 29327, 'loss/train': 1.4284075498580933}
+08/30/2021 18:24:22 - INFO - __main__ - Step 29329: {'lr': 0.00045910321625414245, 'samples': 5631168, 'steps': 29328, 'loss/train': 1.2354590892791748}
+08/30/2021 18:24:22 - INFO - __main__ - Step 29330: {'lr': 0.00045910030758089597, 'samples': 5631360, 'steps': 29329, 'loss/train': 1.5467263460159302}
+08/30/2021 18:24:24 - INFO - __main__ - Step 29331: {'lr': 0.00045909739881343215, 'samples': 5631552, 'steps': 29330, 'loss/train': 1.8582510948181152}
+08/30/2021 18:24:24 - INFO - __main__ - Step 29332: {'lr': 0.00045909448995175224, 'samples': 5631744, 'steps': 29331, 'loss/train': 1.2985451221466064}
+08/30/2021 18:24:25 - INFO - __main__ - Step 29333: {'lr': 0.00045909158099585756, 'samples': 5631936, 'steps': 29332, 'loss/train': 1.6099449396133423}
+08/30/2021 18:24:25 - INFO - __main__ - Step 29334: {'lr': 0.00045908867194574955, 'samples': 5632128, 'steps': 29333, 'loss/train': 2.1385371685028076}
+08/30/2021 18:24:25 - INFO - __main__ - Step 29335: {'lr': 0.00045908576280142925, 'samples': 5632320, 'steps': 29334, 'loss/train': 1.5409995317459106}
+08/30/2021 18:24:26 - INFO - __main__ - Step 29336: {'lr': 0.00045908285356289824, 'samples': 5632512, 'steps': 29335, 'loss/train': 1.1011066436767578}
+08/30/2021 18:24:27 - INFO - __main__ - Step 29337: {'lr': 0.0004590799442301577, 'samples': 5632704, 'steps': 29336, 'loss/train': 1.2381199598312378}
+08/30/2021 18:24:28 - INFO - __main__ - Step 29338: {'lr': 0.00045907703480320894, 'samples': 5632896, 'steps': 29337, 'loss/train': 1.1147611141204834}
+08/30/2021 18:24:28 - INFO - __main__ - Step 29339: {'lr': 0.0004590741252820533, 'samples': 5633088, 'steps': 29338, 'loss/train': 1.4083908796310425}
+08/30/2021 18:24:29 - INFO - __main__ - Step 29340: {'lr': 0.00045907121566669216, 'samples': 5633280, 'steps': 29339, 'loss/train': 1.5535962581634521}
+08/30/2021 18:24:29 - INFO - __main__ - Step 29341: {'lr': 0.0004590683059571267, 'samples': 5633472, 'steps': 29340, 'loss/train': 1.7197771072387695}
+08/30/2021 18:24:30 - INFO - __main__ - Step 29342: {'lr': 0.0004590653961533582, 'samples': 5633664, 'steps': 29341, 'loss/train': 1.7851433753967285}
+08/30/2021 18:24:31 - INFO - __main__ - Step 29343: {'lr': 0.00045906248625538816, 'samples': 5633856, 'steps': 29342, 'loss/train': 1.4537101984024048}
+08/30/2021 18:24:31 - INFO - __main__ - Step 29344: {'lr': 0.00045905957626321775, 'samples': 5634048, 'steps': 29343, 'loss/train': 1.348261833190918}
+08/30/2021 18:24:32 - INFO - __main__ - Step 29345: {'lr': 0.0004590566661768484, 'samples': 5634240, 'steps': 29344, 'loss/train': 1.3653773069381714}
+08/30/2021 18:24:32 - INFO - __main__ - Step 29346: {'lr': 0.00045905375599628127, 'samples': 5634432, 'steps': 29345, 'loss/train': 0.8258079290390015}
+08/30/2021 18:24:33 - INFO - __main__ - Step 29347: {'lr': 0.00045905084572151774, 'samples': 5634624, 'steps': 29346, 'loss/train': 1.3003286123275757}
+08/30/2021 18:24:34 - INFO - __main__ - Step 29348: {'lr': 0.0004590479353525591, 'samples': 5634816, 'steps': 29347, 'loss/train': 1.6447889804840088}
+08/30/2021 18:24:34 - INFO - __main__ - Step 29349: {'lr': 0.00045904502488940677, 'samples': 5635008, 'steps': 29348, 'loss/train': 1.581138253211975}
+08/30/2021 18:24:35 - INFO - __main__ - Step 29350: {'lr': 0.0004590421143320619, 'samples': 5635200, 'steps': 29349, 'loss/train': 1.915869116783142}
+08/30/2021 18:24:35 - INFO - __main__ - Step 29351: {'lr': 0.0004590392036805259, 'samples': 5635392, 'steps': 29350, 'loss/train': 1.9172983169555664}
+08/30/2021 18:24:35 - INFO - __main__ - Step 29352: {'lr': 0.0004590362929348001, 'samples': 5635584, 'steps': 29351, 'loss/train': 2.118647336959839}
+08/30/2021 18:24:37 - INFO - __main__ - Step 29353: {'lr': 0.00045903338209488575, 'samples': 5635776, 'steps': 29352, 'loss/train': 1.2624213695526123}
+08/30/2021 18:24:37 - INFO - __main__ - Step 29354: {'lr': 0.0004590304711607842, 'samples': 5635968, 'steps': 29353, 'loss/train': 0.9841771721839905}
+08/30/2021 18:24:38 - INFO - __main__ - Step 29355: {'lr': 0.0004590275601324967, 'samples': 5636160, 'steps': 29354, 'loss/train': 1.7141315937042236}
+08/30/2021 18:24:38 - INFO - __main__ - Step 29356: {'lr': 0.0004590246490100246, 'samples': 5636352, 'steps': 29355, 'loss/train': 1.6033127307891846}
+08/30/2021 18:24:38 - INFO - __main__ - Step 29357: {'lr': 0.00045902173779336925, 'samples': 5636544, 'steps': 29356, 'loss/train': 1.4778285026550293}
+08/30/2021 18:24:40 - INFO - __main__ - Step 29358: {'lr': 0.0004590188264825319, 'samples': 5636736, 'steps': 29357, 'loss/train': 1.6052192449569702}
+08/30/2021 18:24:41 - INFO - __main__ - Step 29359: {'lr': 0.00045901591507751393, 'samples': 5636928, 'steps': 29358, 'loss/train': 3.5689525604248047}
+08/30/2021 18:24:41 - INFO - __main__ - Step 29360: {'lr': 0.00045901300357831666, 'samples': 5637120, 'steps': 29359, 'loss/train': 9.343769073486328}
+08/30/2021 18:24:41 - INFO - __main__ - Step 29361: {'lr': 0.00045901009198494124, 'samples': 5637312, 'steps': 29360, 'loss/train': 1.572585940361023}
+08/30/2021 18:24:42 - INFO - __main__ - Step 29362: {'lr': 0.0004590071802973892, 'samples': 5637504, 'steps': 29361, 'loss/train': 1.0418428182601929}
+08/30/2021 18:24:42 - INFO - __main__ - Step 29363: {'lr': 0.0004590042685156617, 'samples': 5637696, 'steps': 29362, 'loss/train': 1.0124503374099731}
+08/30/2021 18:24:43 - INFO - __main__ - Step 29364: {'lr': 0.0004590013566397601, 'samples': 5637888, 'steps': 29363, 'loss/train': 1.5964131355285645}
+08/30/2021 18:24:44 - INFO - __main__ - Step 29365: {'lr': 0.00045899844466968574, 'samples': 5638080, 'steps': 29364, 'loss/train': 1.4689416885375977}
+08/30/2021 18:24:44 - INFO - __main__ - Step 29366: {'lr': 0.00045899553260543986, 'samples': 5638272, 'steps': 29365, 'loss/train': 1.0361446142196655}
+08/30/2021 18:24:45 - INFO - __main__ - Step 29367: {'lr': 0.0004589926204470238, 'samples': 5638464, 'steps': 29366, 'loss/train': 1.4815704822540283}
+08/30/2021 18:24:45 - INFO - __main__ - Step 29368: {'lr': 0.000458989708194439, 'samples': 5638656, 'steps': 29367, 'loss/train': 1.4048242568969727}
+08/30/2021 18:24:45 - INFO - __main__ - Step 29369: {'lr': 0.0004589867958476866, 'samples': 5638848, 'steps': 29368, 'loss/train': 1.5980817079544067}
+08/30/2021 18:24:47 - INFO - __main__ - Step 29370: {'lr': 0.000458983883406768, 'samples': 5639040, 'steps': 29369, 'loss/train': 1.6755766868591309}
+08/30/2021 18:24:48 - INFO - __main__ - Step 29371: {'lr': 0.0004589809708716844, 'samples': 5639232, 'steps': 29370, 'loss/train': 1.5317788124084473}
+08/30/2021 18:24:48 - INFO - __main__ - Step 29372: {'lr': 0.0004589780582424373, 'samples': 5639424, 'steps': 29371, 'loss/train': 1.7573219537734985}
+08/30/2021 18:24:48 - INFO - __main__ - Step 29373: {'lr': 0.00045897514551902785, 'samples': 5639616, 'steps': 29372, 'loss/train': 1.8937082290649414}
+08/30/2021 18:24:49 - INFO - __main__ - Step 29374: {'lr': 0.0004589722327014575, 'samples': 5639808, 'steps': 29373, 'loss/train': 0.046694349497556686}
+08/30/2021 18:24:50 - INFO - __main__ - Step 29375: {'lr': 0.0004589693197897274, 'samples': 5640000, 'steps': 29374, 'loss/train': 1.5517034530639648}
+08/30/2021 18:24:51 - INFO - __main__ - Step 29376: {'lr': 0.0004589664067838389, 'samples': 5640192, 'steps': 29375, 'loss/train': 1.9797797203063965}
+08/30/2021 18:24:51 - INFO - __main__ - Step 29377: {'lr': 0.00045896349368379356, 'samples': 5640384, 'steps': 29376, 'loss/train': 1.8868993520736694}
+08/30/2021 18:24:51 - INFO - __main__ - Step 29378: {'lr': 0.00045896058048959233, 'samples': 5640576, 'steps': 29377, 'loss/train': 1.7486587762832642}
+08/30/2021 18:24:52 - INFO - __main__ - Step 29379: {'lr': 0.00045895766720123677, 'samples': 5640768, 'steps': 29378, 'loss/train': 1.639821171760559}
+08/30/2021 18:24:52 - INFO - __main__ - Step 29380: {'lr': 0.0004589547538187281, 'samples': 5640960, 'steps': 29379, 'loss/train': 1.2783039808273315}
+08/30/2021 18:24:54 - INFO - __main__ - Step 29381: {'lr': 0.0004589518403420676, 'samples': 5641152, 'steps': 29380, 'loss/train': 1.9844601154327393}
+08/30/2021 18:24:54 - INFO - __main__ - Step 29382: {'lr': 0.00045894892677125667, 'samples': 5641344, 'steps': 29381, 'loss/train': 0.6697326302528381}
+08/30/2021 18:24:54 - INFO - __main__ - Step 29383: {'lr': 0.0004589460131062965, 'samples': 5641536, 'steps': 29382, 'loss/train': 1.7014347314834595}
+08/30/2021 18:24:55 - INFO - __main__ - Step 29384: {'lr': 0.00045894309934718853, 'samples': 5641728, 'steps': 29383, 'loss/train': 1.9141618013381958}
+08/30/2021 18:24:55 - INFO - __main__ - Step 29385: {'lr': 0.00045894018549393404, 'samples': 5641920, 'steps': 29384, 'loss/train': 1.6436084508895874}
+08/30/2021 18:24:57 - INFO - __main__ - Step 29386: {'lr': 0.0004589372715465343, 'samples': 5642112, 'steps': 29385, 'loss/train': 1.6123789548873901}
+08/30/2021 18:24:57 - INFO - __main__ - Step 29387: {'lr': 0.0004589343575049907, 'samples': 5642304, 'steps': 29386, 'loss/train': 0.6841147541999817}
+08/30/2021 18:24:58 - INFO - __main__ - Step 29388: {'lr': 0.0004589314433693044, 'samples': 5642496, 'steps': 29387, 'loss/train': 1.6462756395339966}
+08/30/2021 18:24:58 - INFO - __main__ - Step 29389: {'lr': 0.0004589285291394769, 'samples': 5642688, 'steps': 29388, 'loss/train': 3.1464827060699463}
+08/30/2021 18:24:58 - INFO - __main__ - Step 29390: {'lr': 0.00045892561481550943, 'samples': 5642880, 'steps': 29389, 'loss/train': 1.0138169527053833}
+08/30/2021 18:25:00 - INFO - __main__ - Step 29391: {'lr': 0.0004589227003974032, 'samples': 5643072, 'steps': 29390, 'loss/train': 1.6912964582443237}
+08/30/2021 18:25:00 - INFO - __main__ - Step 29392: {'lr': 0.00045891978588515975, 'samples': 5643264, 'steps': 29391, 'loss/train': 2.052468776702881}
+08/30/2021 18:25:01 - INFO - __main__ - Step 29393: {'lr': 0.0004589168712787802, 'samples': 5643456, 'steps': 29392, 'loss/train': 1.9062495231628418}
+08/30/2021 18:25:01 - INFO - __main__ - Step 29394: {'lr': 0.00045891395657826595, 'samples': 5643648, 'steps': 29393, 'loss/train': 1.2196245193481445}
+08/30/2021 18:25:01 - INFO - __main__ - Step 29395: {'lr': 0.0004589110417836183, 'samples': 5643840, 'steps': 29394, 'loss/train': 1.4842808246612549}
+08/30/2021 18:25:03 - INFO - __main__ - Step 29396: {'lr': 0.0004589081268948386, 'samples': 5644032, 'steps': 29395, 'loss/train': 1.4386818408966064}
+08/30/2021 18:25:04 - INFO - __main__ - Step 29397: {'lr': 0.00045890521191192807, 'samples': 5644224, 'steps': 29396, 'loss/train': 0.10482214391231537}
+08/30/2021 18:25:04 - INFO - __main__ - Step 29398: {'lr': 0.0004589022968348881, 'samples': 5644416, 'steps': 29397, 'loss/train': 1.5119930505752563}
+08/30/2021 18:25:04 - INFO - __main__ - Step 29399: {'lr': 0.0004588993816637199, 'samples': 5644608, 'steps': 29398, 'loss/train': 1.028935194015503}
+08/30/2021 18:25:05 - INFO - __main__ - Step 29400: {'lr': 0.00045889646639842496, 'samples': 5644800, 'steps': 29399, 'loss/train': 1.5866012573242188}
+08/30/2021 18:25:06 - INFO - __main__ - Step 29401: {'lr': 0.0004588935510390045, 'samples': 5644992, 'steps': 29400, 'loss/train': 1.3974342346191406}
+08/30/2021 18:25:07 - INFO - __main__ - Step 29402: {'lr': 0.00045889063558545974, 'samples': 5645184, 'steps': 29401, 'loss/train': 1.3678932189941406}
+08/30/2021 18:25:07 - INFO - __main__ - Step 29403: {'lr': 0.0004588877200377921, 'samples': 5645376, 'steps': 29402, 'loss/train': 2.091094970703125}
+08/30/2021 18:25:07 - INFO - __main__ - Step 29404: {'lr': 0.000458884804396003, 'samples': 5645568, 'steps': 29403, 'loss/train': 0.39705920219421387}
+08/30/2021 18:25:08 - INFO - __main__ - Step 29405: {'lr': 0.0004588818886600935, 'samples': 5645760, 'steps': 29404, 'loss/train': 1.5316617488861084}
+08/30/2021 18:25:09 - INFO - __main__ - Step 29406: {'lr': 0.00045887897283006506, 'samples': 5645952, 'steps': 29405, 'loss/train': 1.222008228302002}
+08/30/2021 18:25:10 - INFO - __main__ - Step 29407: {'lr': 0.00045887605690591904, 'samples': 5646144, 'steps': 29406, 'loss/train': 1.6904852390289307}
+08/30/2021 18:25:10 - INFO - __main__ - Step 29408: {'lr': 0.0004588731408876566, 'samples': 5646336, 'steps': 29407, 'loss/train': 1.104187250137329}
+08/30/2021 18:25:11 - INFO - __main__ - Step 29409: {'lr': 0.00045887022477527923, 'samples': 5646528, 'steps': 29408, 'loss/train': 0.0872500017285347}
+08/30/2021 18:25:11 - INFO - __main__ - Step 29410: {'lr': 0.0004588673085687881, 'samples': 5646720, 'steps': 29409, 'loss/train': 3.6997017860412598}
+08/30/2021 18:25:11 - INFO - __main__ - Step 29411: {'lr': 0.00045886439226818464, 'samples': 5646912, 'steps': 29410, 'loss/train': 1.5496467351913452}
+08/30/2021 18:25:13 - INFO - __main__ - Step 29412: {'lr': 0.0004588614758734701, 'samples': 5647104, 'steps': 29411, 'loss/train': 1.7699309587478638}
+08/30/2021 18:25:14 - INFO - __main__ - Step 29413: {'lr': 0.0004588585593846458, 'samples': 5647296, 'steps': 29412, 'loss/train': 0.24823713302612305}
+08/30/2021 18:25:14 - INFO - __main__ - Step 29414: {'lr': 0.000458855642801713, 'samples': 5647488, 'steps': 29413, 'loss/train': 1.5737879276275635}
+08/30/2021 18:25:14 - INFO - __main__ - Step 29415: {'lr': 0.00045885272612467313, 'samples': 5647680, 'steps': 29414, 'loss/train': 0.5294879078865051}
+08/30/2021 18:25:15 - INFO - __main__ - Step 29416: {'lr': 0.0004588498093535274, 'samples': 5647872, 'steps': 29415, 'loss/train': 1.0835024118423462}
+08/30/2021 18:25:15 - INFO - __main__ - Step 29417: {'lr': 0.0004588468924882772, 'samples': 5648064, 'steps': 29416, 'loss/train': 1.8900400400161743}
+08/30/2021 18:25:17 - INFO - __main__ - Step 29418: {'lr': 0.0004588439755289238, 'samples': 5648256, 'steps': 29417, 'loss/train': 1.8867288827896118}
+08/30/2021 18:25:18 - INFO - __main__ - Step 29419: {'lr': 0.00045884105847546853, 'samples': 5648448, 'steps': 29418, 'loss/train': 1.3944100141525269}
+08/30/2021 18:25:18 - INFO - __main__ - Step 29420: {'lr': 0.00045883814132791274, 'samples': 5648640, 'steps': 29419, 'loss/train': 1.8383020162582397}
+08/30/2021 18:25:18 - INFO - __main__ - Step 29421: {'lr': 0.0004588352240862577, 'samples': 5648832, 'steps': 29420, 'loss/train': 1.4362998008728027}
+08/30/2021 18:25:19 - INFO - __main__ - Step 29422: {'lr': 0.0004588323067505047, 'samples': 5649024, 'steps': 29421, 'loss/train': 1.4182742834091187}
+08/30/2021 18:25:20 - INFO - __main__ - Step 29423: {'lr': 0.00045882938932065504, 'samples': 5649216, 'steps': 29422, 'loss/train': 1.8948737382888794}
+08/30/2021 18:25:21 - INFO - __main__ - Step 29424: {'lr': 0.0004588264717967101, 'samples': 5649408, 'steps': 29423, 'loss/train': 1.822411060333252}
+08/30/2021 18:25:21 - INFO - __main__ - Step 29425: {'lr': 0.00045882355417867124, 'samples': 5649600, 'steps': 29424, 'loss/train': 0.877035915851593}
+08/30/2021 18:25:21 - INFO - __main__ - Step 29426: {'lr': 0.00045882063646653966, 'samples': 5649792, 'steps': 29425, 'loss/train': 0.966000497341156}
+08/30/2021 18:25:22 - INFO - __main__ - Step 29427: {'lr': 0.00045881771866031673, 'samples': 5649984, 'steps': 29426, 'loss/train': 1.2050514221191406}
+08/30/2021 18:25:23 - INFO - __main__ - Step 29428: {'lr': 0.00045881480076000376, 'samples': 5650176, 'steps': 29427, 'loss/train': 1.1730661392211914}
+08/30/2021 18:25:24 - INFO - __main__ - Step 29429: {'lr': 0.00045881188276560204, 'samples': 5650368, 'steps': 29428, 'loss/train': 1.0626200437545776}
+08/30/2021 18:25:24 - INFO - __main__ - Step 29430: {'lr': 0.000458808964677113, 'samples': 5650560, 'steps': 29429, 'loss/train': 1.5473029613494873}
+08/30/2021 18:25:24 - INFO - __main__ - Step 29431: {'lr': 0.00045880604649453774, 'samples': 5650752, 'steps': 29430, 'loss/train': 1.8532428741455078}
+08/30/2021 18:25:25 - INFO - __main__ - Step 29432: {'lr': 0.00045880312821787775, 'samples': 5650944, 'steps': 29431, 'loss/train': 1.6421610116958618}
+08/30/2021 18:25:26 - INFO - __main__ - Step 29433: {'lr': 0.00045880020984713434, 'samples': 5651136, 'steps': 29432, 'loss/train': 1.980318546295166}
+08/30/2021 18:25:27 - INFO - __main__ - Step 29434: {'lr': 0.0004587972913823087, 'samples': 5651328, 'steps': 29433, 'loss/train': 1.8178534507751465}
+08/30/2021 18:25:27 - INFO - __main__ - Step 29435: {'lr': 0.00045879437282340225, 'samples': 5651520, 'steps': 29434, 'loss/train': 1.2301417589187622}
+08/30/2021 18:25:27 - INFO - __main__ - Step 29436: {'lr': 0.00045879145417041623, 'samples': 5651712, 'steps': 29435, 'loss/train': 1.4887574911117554}
+08/30/2021 18:25:28 - INFO - __main__ - Step 29437: {'lr': 0.0004587885354233521, 'samples': 5651904, 'steps': 29436, 'loss/train': 1.3315002918243408}
+08/30/2021 18:25:29 - INFO - __main__ - Step 29438: {'lr': 0.0004587856165822111, 'samples': 5652096, 'steps': 29437, 'loss/train': 1.6939550638198853}
+08/30/2021 18:25:30 - INFO - __main__ - Step 29439: {'lr': 0.0004587826976469944, 'samples': 5652288, 'steps': 29438, 'loss/train': 1.3654032945632935}
+08/30/2021 18:25:30 - INFO - __main__ - Step 29440: {'lr': 0.0004587797786177035, 'samples': 5652480, 'steps': 29439, 'loss/train': 1.600990891456604}
+08/30/2021 18:25:30 - INFO - __main__ - Step 29441: {'lr': 0.0004587768594943396, 'samples': 5652672, 'steps': 29440, 'loss/train': 1.4263916015625}
+08/30/2021 18:25:31 - INFO - __main__ - Step 29442: {'lr': 0.00045877394027690413, 'samples': 5652864, 'steps': 29441, 'loss/train': 1.4905107021331787}
+08/30/2021 18:25:31 - INFO - __main__ - Step 29443: {'lr': 0.0004587710209653984, 'samples': 5653056, 'steps': 29442, 'loss/train': 1.9826242923736572}
+08/30/2021 18:25:32 - INFO - __main__ - Step 29444: {'lr': 0.0004587681015598235, 'samples': 5653248, 'steps': 29443, 'loss/train': 1.6064846515655518}
+08/30/2021 18:25:33 - INFO - __main__ - Step 29445: {'lr': 0.00045876518206018103, 'samples': 5653440, 'steps': 29444, 'loss/train': 1.5464205741882324}
+08/30/2021 18:25:33 - INFO - __main__ - Step 29446: {'lr': 0.00045876226246647226, 'samples': 5653632, 'steps': 29445, 'loss/train': 1.4796415567398071}
+08/30/2021 18:25:34 - INFO - __main__ - Step 29447: {'lr': 0.0004587593427786983, 'samples': 5653824, 'steps': 29446, 'loss/train': 0.5536571741104126}
+08/30/2021 18:25:34 - INFO - __main__ - Step 29448: {'lr': 0.0004587564229968606, 'samples': 5654016, 'steps': 29447, 'loss/train': 1.7594894170761108}
+08/30/2021 18:25:35 - INFO - __main__ - Step 29449: {'lr': 0.00045875350312096053, 'samples': 5654208, 'steps': 29448, 'loss/train': 1.3968859910964966}
+08/30/2021 18:25:36 - INFO - __main__ - Step 29450: {'lr': 0.0004587505831509994, 'samples': 5654400, 'steps': 29449, 'loss/train': 1.7576875686645508}
+08/30/2021 18:25:36 - INFO - __main__ - Step 29451: {'lr': 0.0004587476630869784, 'samples': 5654592, 'steps': 29450, 'loss/train': 1.3094887733459473}
+08/30/2021 18:25:37 - INFO - __main__ - Step 29452: {'lr': 0.000458744742928899, 'samples': 5654784, 'steps': 29451, 'loss/train': 1.0282065868377686}
+08/30/2021 18:25:37 - INFO - __main__ - Step 29453: {'lr': 0.00045874182267676236, 'samples': 5654976, 'steps': 29452, 'loss/train': 1.4678053855895996}
+08/30/2021 18:25:39 - INFO - __main__ - Step 29454: {'lr': 0.0004587389023305699, 'samples': 5655168, 'steps': 29453, 'loss/train': 1.8546245098114014}
+08/30/2021 18:25:39 - INFO - __main__ - Step 29455: {'lr': 0.00045873598189032295, 'samples': 5655360, 'steps': 29454, 'loss/train': 0.6133260130882263}
+08/30/2021 18:25:39 - INFO - __main__ - Step 29456: {'lr': 0.00045873306135602276, 'samples': 5655552, 'steps': 29455, 'loss/train': 1.0019116401672363}
+08/30/2021 18:25:40 - INFO - __main__ - Step 29457: {'lr': 0.00045873014072767064, 'samples': 5655744, 'steps': 29456, 'loss/train': 0.6915490627288818}
+08/30/2021 18:25:40 - INFO - __main__ - Step 29458: {'lr': 0.000458727220005268, 'samples': 5655936, 'steps': 29457, 'loss/train': 1.015907645225525}
+08/30/2021 18:25:40 - INFO - __main__ - Step 29459: {'lr': 0.00045872429918881606, 'samples': 5656128, 'steps': 29458, 'loss/train': 0.957791268825531}
+08/30/2021 18:25:42 - INFO - __main__ - Step 29460: {'lr': 0.00045872137827831616, 'samples': 5656320, 'steps': 29459, 'loss/train': 1.2022985219955444}
+08/30/2021 18:25:42 - INFO - __main__ - Step 29461: {'lr': 0.00045871845727376973, 'samples': 5656512, 'steps': 29460, 'loss/train': 1.2923895120620728}
+08/30/2021 18:25:43 - INFO - __main__ - Step 29462: {'lr': 0.0004587155361751778, 'samples': 5656704, 'steps': 29461, 'loss/train': 0.9164935350418091}
+08/30/2021 18:25:43 - INFO - __main__ - Step 29463: {'lr': 0.000458712614982542, 'samples': 5656896, 'steps': 29462, 'loss/train': 1.6710330247879028}
+08/30/2021 18:25:43 - INFO - __main__ - Step 29464: {'lr': 0.00045870969369586346, 'samples': 5657088, 'steps': 29463, 'loss/train': 2.187263011932373}
+08/30/2021 18:25:45 - INFO - __main__ - Step 29465: {'lr': 0.00045870677231514356, 'samples': 5657280, 'steps': 29464, 'loss/train': 1.160699486732483}
+08/30/2021 18:25:45 - INFO - __main__ - Step 29466: {'lr': 0.0004587038508403837, 'samples': 5657472, 'steps': 29465, 'loss/train': 1.2791696786880493}
+08/30/2021 18:25:46 - INFO - __main__ - Step 29467: {'lr': 0.000458700929271585, 'samples': 5657664, 'steps': 29466, 'loss/train': 1.6932755708694458}
+08/30/2021 18:25:46 - INFO - __main__ - Step 29468: {'lr': 0.0004586980076087489, 'samples': 5657856, 'steps': 29467, 'loss/train': 1.0619211196899414}
+08/30/2021 18:25:46 - INFO - __main__ - Step 29469: {'lr': 0.0004586950858518767, 'samples': 5658048, 'steps': 29468, 'loss/train': 0.9249522686004639}
+08/30/2021 18:25:48 - INFO - __main__ - Step 29470: {'lr': 0.0004586921640009697, 'samples': 5658240, 'steps': 29469, 'loss/train': 1.277970790863037}
+08/30/2021 18:25:49 - INFO - __main__ - Step 29471: {'lr': 0.0004586892420560294, 'samples': 5658432, 'steps': 29470, 'loss/train': 1.4958105087280273}
+08/30/2021 18:25:49 - INFO - __main__ - Step 29472: {'lr': 0.0004586863200170567, 'samples': 5658624, 'steps': 29471, 'loss/train': 1.5742889642715454}
+08/30/2021 18:25:50 - INFO - __main__ - Step 29473: {'lr': 0.00045868339788405333, 'samples': 5658816, 'steps': 29472, 'loss/train': 1.2178361415863037}
+08/30/2021 18:25:50 - INFO - __main__ - Step 29474: {'lr': 0.0004586804756570204, 'samples': 5659008, 'steps': 29473, 'loss/train': 0.9887757301330566}
+08/30/2021 18:25:52 - INFO - __main__ - Step 29475: {'lr': 0.0004586775533359592, 'samples': 5659200, 'steps': 29474, 'loss/train': 1.120389461517334}
+08/30/2021 18:25:52 - INFO - __main__ - Step 29476: {'lr': 0.00045867463092087116, 'samples': 5659392, 'steps': 29475, 'loss/train': 1.218640923500061}
+08/30/2021 18:25:52 - INFO - __main__ - Step 29477: {'lr': 0.00045867170841175755, 'samples': 5659584, 'steps': 29476, 'loss/train': 1.182020902633667}
+08/30/2021 18:25:53 - INFO - __main__ - Step 29478: {'lr': 0.0004586687858086197, 'samples': 5659776, 'steps': 29477, 'loss/train': 0.715477466583252}
+08/30/2021 18:25:53 - INFO - __main__ - Step 29479: {'lr': 0.0004586658631114589, 'samples': 5659968, 'steps': 29478, 'loss/train': 1.6136478185653687}
+08/30/2021 18:25:55 - INFO - __main__ - Step 29480: {'lr': 0.0004586629403202765, 'samples': 5660160, 'steps': 29479, 'loss/train': 1.5179307460784912}
+08/30/2021 18:25:55 - INFO - __main__ - Step 29481: {'lr': 0.0004586600174350738, 'samples': 5660352, 'steps': 29480, 'loss/train': 0.09195207059383392}
+08/30/2021 18:25:56 - INFO - __main__ - Step 29482: {'lr': 0.0004586570944558521, 'samples': 5660544, 'steps': 29481, 'loss/train': 1.2771415710449219}
+08/30/2021 18:25:56 - INFO - __main__ - Step 29483: {'lr': 0.00045865417138261276, 'samples': 5660736, 'steps': 29482, 'loss/train': 0.06736479699611664}
+08/30/2021 18:25:56 - INFO - __main__ - Step 29484: {'lr': 0.00045865124821535704, 'samples': 5660928, 'steps': 29483, 'loss/train': 0.6730112433433533}
+08/30/2021 18:25:58 - INFO - __main__ - Step 29485: {'lr': 0.00045864832495408624, 'samples': 5661120, 'steps': 29484, 'loss/train': 2.730788230895996}
+08/30/2021 18:25:59 - INFO - __main__ - Step 29486: {'lr': 0.0004586454015988019, 'samples': 5661312, 'steps': 29485, 'loss/train': 0.9634883403778076}
+08/30/2021 18:25:59 - INFO - __main__ - Step 29487: {'lr': 0.000458642478149505, 'samples': 5661504, 'steps': 29486, 'loss/train': 1.6337947845458984}
+08/30/2021 18:25:59 - INFO - __main__ - Step 29488: {'lr': 0.00045863955460619707, 'samples': 5661696, 'steps': 29487, 'loss/train': 1.7172850370407104}
+08/30/2021 18:26:00 - INFO - __main__ - Step 29489: {'lr': 0.0004586366309688793, 'samples': 5661888, 'steps': 29488, 'loss/train': 0.0479944609105587}
+08/30/2021 18:26:00 - INFO - __main__ - Step 29490: {'lr': 0.00045863370723755315, 'samples': 5662080, 'steps': 29489, 'loss/train': 0.6843440532684326}
+08/30/2021 18:26:01 - INFO - __main__ - Step 29491: {'lr': 0.00045863078341221993, 'samples': 5662272, 'steps': 29490, 'loss/train': 1.3027055263519287}
+08/30/2021 18:26:02 - INFO - __main__ - Step 29492: {'lr': 0.0004586278594928808, 'samples': 5662464, 'steps': 29491, 'loss/train': 0.09501402080059052}
+08/30/2021 18:26:02 - INFO - __main__ - Step 29493: {'lr': 0.0004586249354795372, 'samples': 5662656, 'steps': 29492, 'loss/train': 1.4198743104934692}
+08/30/2021 18:26:03 - INFO - __main__ - Step 29494: {'lr': 0.0004586220113721905, 'samples': 5662848, 'steps': 29493, 'loss/train': 1.2894880771636963}
+08/30/2021 18:26:03 - INFO - __main__ - Step 29495: {'lr': 0.0004586190871708419, 'samples': 5663040, 'steps': 29494, 'loss/train': 1.7419530153274536}
+08/30/2021 18:26:03 - INFO - __main__ - Step 29496: {'lr': 0.0004586161628754927, 'samples': 5663232, 'steps': 29495, 'loss/train': 1.8950157165527344}
+08/30/2021 18:26:06 - INFO - __main__ - Step 29497: {'lr': 0.0004586132384861443, 'samples': 5663424, 'steps': 29496, 'loss/train': 0.32504117488861084}
+08/30/2021 18:26:06 - INFO - __main__ - Step 29498: {'lr': 0.000458610314002798, 'samples': 5663616, 'steps': 29497, 'loss/train': 1.5534977912902832}
+08/30/2021 18:26:07 - INFO - __main__ - Step 29499: {'lr': 0.0004586073894254551, 'samples': 5663808, 'steps': 29498, 'loss/train': 1.144694447517395}
+08/30/2021 18:26:07 - INFO - __main__ - Step 29500: {'lr': 0.000458604464754117, 'samples': 5664000, 'steps': 29499, 'loss/train': 1.829520583152771}
+08/30/2021 18:26:07 - INFO - __main__ - Step 29501: {'lr': 0.0004586015399887849, 'samples': 5664192, 'steps': 29500, 'loss/train': 0.6112343668937683}
+08/30/2021 18:26:08 - INFO - __main__ - Step 29502: {'lr': 0.0004585986151294602, 'samples': 5664384, 'steps': 29501, 'loss/train': 0.5225926637649536}
+08/30/2021 18:26:09 - INFO - __main__ - Step 29503: {'lr': 0.0004585956901761441, 'samples': 5664576, 'steps': 29502, 'loss/train': 0.5445204377174377}
+08/30/2021 18:26:10 - INFO - __main__ - Step 29504: {'lr': 0.00045859276512883807, 'samples': 5664768, 'steps': 29503, 'loss/train': 1.7337385416030884}
+08/30/2021 18:26:10 - INFO - __main__ - Step 29505: {'lr': 0.00045858983998754336, 'samples': 5664960, 'steps': 29504, 'loss/train': 1.2972288131713867}
+08/30/2021 18:26:10 - INFO - __main__ - Step 29506: {'lr': 0.0004585869147522612, 'samples': 5665152, 'steps': 29505, 'loss/train': 1.3692007064819336}
+08/30/2021 18:26:11 - INFO - __main__ - Step 29507: {'lr': 0.00045858398942299306, 'samples': 5665344, 'steps': 29506, 'loss/train': 2.033146858215332}
+08/30/2021 18:26:12 - INFO - __main__ - Step 29508: {'lr': 0.0004585810639997402, 'samples': 5665536, 'steps': 29507, 'loss/train': 1.3620285987854004}
+08/30/2021 18:26:13 - INFO - __main__ - Step 29509: {'lr': 0.0004585781384825039, 'samples': 5665728, 'steps': 29508, 'loss/train': 1.6803773641586304}
+08/30/2021 18:26:13 - INFO - __main__ - Step 29510: {'lr': 0.00045857521287128556, 'samples': 5665920, 'steps': 29509, 'loss/train': 0.9989269971847534}
+08/30/2021 18:26:13 - INFO - __main__ - Step 29511: {'lr': 0.0004585722871660864, 'samples': 5666112, 'steps': 29510, 'loss/train': 1.6287176609039307}
+08/30/2021 18:26:14 - INFO - __main__ - Step 29512: {'lr': 0.0004585693613669078, 'samples': 5666304, 'steps': 29511, 'loss/train': 1.455241322517395}
+08/30/2021 18:26:15 - INFO - __main__ - Step 29513: {'lr': 0.0004585664354737511, 'samples': 5666496, 'steps': 29512, 'loss/train': 1.7103053331375122}
+08/30/2021 18:26:16 - INFO - __main__ - Step 29514: {'lr': 0.0004585635094866175, 'samples': 5666688, 'steps': 29513, 'loss/train': 1.5950748920440674}
+08/30/2021 18:26:16 - INFO - __main__ - Step 29515: {'lr': 0.0004585605834055084, 'samples': 5666880, 'steps': 29514, 'loss/train': 0.6312817335128784}
+08/30/2021 18:26:16 - INFO - __main__ - Step 29516: {'lr': 0.00045855765723042526, 'samples': 5667072, 'steps': 29515, 'loss/train': 1.4721404314041138}
+08/30/2021 18:26:17 - INFO - __main__ - Step 29517: {'lr': 0.00045855473096136914, 'samples': 5667264, 'steps': 29516, 'loss/train': 1.3437658548355103}
+08/30/2021 18:26:18 - INFO - __main__ - Step 29518: {'lr': 0.00045855180459834153, 'samples': 5667456, 'steps': 29517, 'loss/train': 1.1570112705230713}
+08/30/2021 18:26:19 - INFO - __main__ - Step 29519: {'lr': 0.0004585488781413437, 'samples': 5667648, 'steps': 29518, 'loss/train': 1.4586642980575562}
+08/30/2021 18:26:19 - INFO - __main__ - Step 29520: {'lr': 0.00045854595159037695, 'samples': 5667840, 'steps': 29519, 'loss/train': 1.6733678579330444}
+08/30/2021 18:26:19 - INFO - __main__ - Step 29521: {'lr': 0.0004585430249454425, 'samples': 5668032, 'steps': 29520, 'loss/train': 1.654155969619751}
+08/30/2021 18:26:20 - INFO - __main__ - Step 29522: {'lr': 0.000458540098206542, 'samples': 5668224, 'steps': 29521, 'loss/train': 1.9122824668884277}
+08/30/2021 18:26:21 - INFO - __main__ - Step 29523: {'lr': 0.00045853717137367634, 'samples': 5668416, 'steps': 29522, 'loss/train': 1.2130546569824219}
+08/30/2021 18:26:22 - INFO - __main__ - Step 29524: {'lr': 0.0004585342444468471, 'samples': 5668608, 'steps': 29523, 'loss/train': 1.0073513984680176}
+08/30/2021 18:26:22 - INFO - __main__ - Step 29525: {'lr': 0.00045853131742605563, 'samples': 5668800, 'steps': 29524, 'loss/train': 1.2143741846084595}
+08/30/2021 18:26:22 - INFO - __main__ - Step 29526: {'lr': 0.0004585283903113031, 'samples': 5668992, 'steps': 29525, 'loss/train': 1.5078721046447754}
+08/30/2021 18:26:23 - INFO - __main__ - Step 29527: {'lr': 0.00045852546310259093, 'samples': 5669184, 'steps': 29526, 'loss/train': 1.5619242191314697}
+08/30/2021 18:26:23 - INFO - __main__ - Step 29528: {'lr': 0.00045852253579992043, 'samples': 5669376, 'steps': 29527, 'loss/train': 1.0531502962112427}
+08/30/2021 18:26:25 - INFO - __main__ - Step 29529: {'lr': 0.0004585196084032928, 'samples': 5669568, 'steps': 29528, 'loss/train': 1.3731187582015991}
+08/30/2021 18:26:26 - INFO - __main__ - Step 29530: {'lr': 0.0004585166809127095, 'samples': 5669760, 'steps': 29529, 'loss/train': 1.3357107639312744}
+08/30/2021 18:26:26 - INFO - __main__ - Step 29531: {'lr': 0.0004585137533281718, 'samples': 5669952, 'steps': 29530, 'loss/train': 0.8998951315879822}
+08/30/2021 18:26:27 - INFO - __main__ - Step 29532: {'lr': 0.00045851082564968103, 'samples': 5670144, 'steps': 29531, 'loss/train': 1.4392424821853638}
+08/30/2021 18:26:27 - INFO - __main__ - Step 29533: {'lr': 0.0004585078978772385, 'samples': 5670336, 'steps': 29532, 'loss/train': 1.5617882013320923}
+08/30/2021 18:26:29 - INFO - __main__ - Step 29534: {'lr': 0.0004585049700108455, 'samples': 5670528, 'steps': 29533, 'loss/train': 1.0490193367004395}
+08/30/2021 18:26:29 - INFO - __main__ - Step 29535: {'lr': 0.00045850204205050344, 'samples': 5670720, 'steps': 29534, 'loss/train': 1.2691662311553955}
+08/30/2021 18:26:30 - INFO - __main__ - Step 29536: {'lr': 0.0004584991139962135, 'samples': 5670912, 'steps': 29535, 'loss/train': 1.3712712526321411}
+08/30/2021 18:26:30 - INFO - __main__ - Step 29537: {'lr': 0.00045849618584797717, 'samples': 5671104, 'steps': 29536, 'loss/train': 1.5839011669158936}
+08/30/2021 18:26:30 - INFO - __main__ - Step 29538: {'lr': 0.0004584932576057956, 'samples': 5671296, 'steps': 29537, 'loss/train': 0.07783497124910355}
+08/30/2021 18:26:31 - INFO - __main__ - Step 29539: {'lr': 0.00045849032926967016, 'samples': 5671488, 'steps': 29538, 'loss/train': 0.04371124133467674}
+08/30/2021 18:26:32 - INFO - __main__ - Step 29540: {'lr': 0.0004584874008396023, 'samples': 5671680, 'steps': 29539, 'loss/train': 1.6364810466766357}
+08/30/2021 18:26:33 - INFO - __main__ - Step 29541: {'lr': 0.00045848447231559315, 'samples': 5671872, 'steps': 29540, 'loss/train': 1.350569248199463}
+08/30/2021 18:26:33 - INFO - __main__ - Step 29542: {'lr': 0.00045848154369764415, 'samples': 5672064, 'steps': 29541, 'loss/train': 1.412458896636963}
+08/30/2021 18:26:33 - INFO - __main__ - Step 29543: {'lr': 0.0004584786149857566, 'samples': 5672256, 'steps': 29542, 'loss/train': 1.7077301740646362}
+08/30/2021 18:26:34 - INFO - __main__ - Step 29544: {'lr': 0.00045847568617993174, 'samples': 5672448, 'steps': 29543, 'loss/train': 1.4265661239624023}
+08/30/2021 18:26:35 - INFO - __main__ - Step 29545: {'lr': 0.000458472757280171, 'samples': 5672640, 'steps': 29544, 'loss/train': 1.2461732625961304}
+08/30/2021 18:26:36 - INFO - __main__ - Step 29546: {'lr': 0.0004584698282864757, 'samples': 5672832, 'steps': 29545, 'loss/train': 0.269072026014328}
+08/30/2021 18:26:36 - INFO - __main__ - Step 29547: {'lr': 0.000458466899198847, 'samples': 5673024, 'steps': 29546, 'loss/train': 0.7153891324996948}
+08/30/2021 18:26:36 - INFO - __main__ - Step 29548: {'lr': 0.0004584639700172863, 'samples': 5673216, 'steps': 29547, 'loss/train': 1.3654835224151611}
+08/30/2021 18:26:37 - INFO - __main__ - Step 29549: {'lr': 0.00045846104074179504, 'samples': 5673408, 'steps': 29548, 'loss/train': 2.0023417472839355}
+08/30/2021 18:26:37 - INFO - __main__ - Step 29550: {'lr': 0.00045845811137237445, 'samples': 5673600, 'steps': 29549, 'loss/train': 1.5485824346542358}
+08/30/2021 18:26:39 - INFO - __main__ - Step 29551: {'lr': 0.0004584551819090259, 'samples': 5673792, 'steps': 29550, 'loss/train': 0.6402052640914917}
+08/30/2021 18:26:39 - INFO - __main__ - Step 29552: {'lr': 0.0004584522523517506, 'samples': 5673984, 'steps': 29551, 'loss/train': 1.4533443450927734}
+08/30/2021 18:26:40 - INFO - __main__ - Step 29553: {'lr': 0.00045844932270054997, 'samples': 5674176, 'steps': 29552, 'loss/train': 1.2149449586868286}
+08/30/2021 18:26:40 - INFO - __main__ - Step 29554: {'lr': 0.00045844639295542525, 'samples': 5674368, 'steps': 29553, 'loss/train': 0.05344089865684509}
+08/30/2021 18:26:40 - INFO - __main__ - Step 29555: {'lr': 0.0004584434631163779, 'samples': 5674560, 'steps': 29554, 'loss/train': 3.456982135772705}
+08/30/2021 18:26:41 - INFO - __main__ - Step 29556: {'lr': 0.000458440533183409, 'samples': 5674752, 'steps': 29555, 'loss/train': 2.0972509384155273}
+08/30/2021 18:26:42 - INFO - __main__ - Step 29557: {'lr': 0.0004584376031565201, 'samples': 5674944, 'steps': 29556, 'loss/train': 1.2078018188476562}
+08/30/2021 18:26:43 - INFO - __main__ - Step 29558: {'lr': 0.0004584346730357124, 'samples': 5675136, 'steps': 29557, 'loss/train': 1.2920725345611572}
+08/30/2021 18:26:43 - INFO - __main__ - Step 29559: {'lr': 0.0004584317428209872, 'samples': 5675328, 'steps': 29558, 'loss/train': 0.9063498377799988}
+08/30/2021 18:26:43 - INFO - __main__ - Step 29560: {'lr': 0.0004584288125123459, 'samples': 5675520, 'steps': 29559, 'loss/train': 0.9930772185325623}
+08/30/2021 18:26:44 - INFO - __main__ - Step 29561: {'lr': 0.0004584258821097899, 'samples': 5675712, 'steps': 29560, 'loss/train': 1.6734131574630737}
+08/30/2021 18:26:45 - INFO - __main__ - Step 29562: {'lr': 0.0004584229516133203, 'samples': 5675904, 'steps': 29561, 'loss/train': 1.4462260007858276}
+08/30/2021 18:26:46 - INFO - __main__ - Step 29563: {'lr': 0.00045842002102293856, 'samples': 5676096, 'steps': 29562, 'loss/train': 1.4785751104354858}
+08/30/2021 18:26:46 - INFO - __main__ - Step 29564: {'lr': 0.000458417090338646, 'samples': 5676288, 'steps': 29563, 'loss/train': 2.1335296630859375}
+08/30/2021 18:26:46 - INFO - __main__ - Step 29565: {'lr': 0.00045841415956044394, 'samples': 5676480, 'steps': 29564, 'loss/train': 1.2591972351074219}
+08/30/2021 18:26:47 - INFO - __main__ - Step 29566: {'lr': 0.0004584112286883336, 'samples': 5676672, 'steps': 29565, 'loss/train': 0.08477567136287689}
+08/30/2021 18:26:48 - INFO - __main__ - Step 29567: {'lr': 0.0004584082977223164, 'samples': 5676864, 'steps': 29566, 'loss/train': 1.3854612112045288}
+08/30/2021 18:26:48 - INFO - __main__ - Step 29568: {'lr': 0.0004584053666623937, 'samples': 5677056, 'steps': 29567, 'loss/train': 1.5562198162078857}
+08/30/2021 18:26:49 - INFO - __main__ - Step 29569: {'lr': 0.00045840243550856666, 'samples': 5677248, 'steps': 29568, 'loss/train': 1.6854863166809082}
+08/30/2021 18:26:49 - INFO - __main__ - Step 29570: {'lr': 0.00045839950426083677, 'samples': 5677440, 'steps': 29569, 'loss/train': 1.2686117887496948}
+08/30/2021 18:26:50 - INFO - __main__ - Step 29571: {'lr': 0.0004583965729192052, 'samples': 5677632, 'steps': 29570, 'loss/train': 1.0729773044586182}
+08/30/2021 18:26:51 - INFO - __main__ - Step 29572: {'lr': 0.00045839364148367345, 'samples': 5677824, 'steps': 29571, 'loss/train': 1.7262150049209595}
+08/30/2021 18:26:52 - INFO - __main__ - Step 29573: {'lr': 0.00045839070995424273, 'samples': 5678016, 'steps': 29572, 'loss/train': 1.5303738117218018}
+08/30/2021 18:26:52 - INFO - __main__ - Step 29574: {'lr': 0.00045838777833091425, 'samples': 5678208, 'steps': 29573, 'loss/train': 1.3324564695358276}
+08/30/2021 18:26:53 - INFO - __main__ - Step 29575: {'lr': 0.00045838484661368963, 'samples': 5678400, 'steps': 29574, 'loss/train': 1.9263807535171509}
+08/30/2021 18:26:53 - INFO - __main__ - Step 29576: {'lr': 0.00045838191480256985, 'samples': 5678592, 'steps': 29575, 'loss/train': 0.2690824866294861}
+08/30/2021 18:26:53 - INFO - __main__ - Step 29577: {'lr': 0.00045837898289755654, 'samples': 5678784, 'steps': 29576, 'loss/train': 0.047330599278211594}
+08/30/2021 18:26:55 - INFO - __main__ - Step 29578: {'lr': 0.0004583760508986508, 'samples': 5678976, 'steps': 29577, 'loss/train': 1.3086485862731934}
+08/30/2021 18:26:55 - INFO - __main__ - Step 29579: {'lr': 0.000458373118805854, 'samples': 5679168, 'steps': 29578, 'loss/train': 1.364263653755188}
+08/30/2021 18:26:56 - INFO - __main__ - Step 29580: {'lr': 0.00045837018661916754, 'samples': 5679360, 'steps': 29579, 'loss/train': 1.464563250541687}
+08/30/2021 18:26:56 - INFO - __main__ - Step 29581: {'lr': 0.00045836725433859266, 'samples': 5679552, 'steps': 29580, 'loss/train': 1.7931222915649414}
+08/30/2021 18:26:56 - INFO - __main__ - Step 29582: {'lr': 0.0004583643219641307, 'samples': 5679744, 'steps': 29581, 'loss/train': 1.1459400653839111}
+08/30/2021 18:26:59 - INFO - __main__ - Step 29583: {'lr': 0.00045836138949578297, 'samples': 5679936, 'steps': 29582, 'loss/train': 1.4620206356048584}
+08/30/2021 18:26:59 - INFO - __main__ - Step 29584: {'lr': 0.00045835845693355096, 'samples': 5680128, 'steps': 29583, 'loss/train': 1.4040746688842773}
+08/30/2021 18:26:59 - INFO - __main__ - Step 29585: {'lr': 0.00045835552427743567, 'samples': 5680320, 'steps': 29584, 'loss/train': 1.2760283946990967}
+08/30/2021 18:27:00 - INFO - __main__ - Step 29586: {'lr': 0.00045835259152743866, 'samples': 5680512, 'steps': 29585, 'loss/train': 1.6704434156417847}
+08/30/2021 18:27:00 - INFO - __main__ - Step 29587: {'lr': 0.0004583496586835612, 'samples': 5680704, 'steps': 29586, 'loss/train': 0.11828450858592987}
+08/30/2021 18:27:01 - INFO - __main__ - Step 29588: {'lr': 0.0004583467257458046, 'samples': 5680896, 'steps': 29587, 'loss/train': 1.6639827489852905}
+08/30/2021 18:27:02 - INFO - __main__ - Step 29589: {'lr': 0.00045834379271417013, 'samples': 5681088, 'steps': 29588, 'loss/train': 1.6343023777008057}
+08/30/2021 18:27:02 - INFO - __main__ - Step 29590: {'lr': 0.0004583408595886592, 'samples': 5681280, 'steps': 29589, 'loss/train': 1.898882508277893}
+08/30/2021 18:27:03 - INFO - __main__ - Step 29591: {'lr': 0.0004583379263692732, 'samples': 5681472, 'steps': 29590, 'loss/train': 2.0787954330444336}
+08/30/2021 18:27:03 - INFO - __main__ - Step 29592: {'lr': 0.0004583349930560132, 'samples': 5681664, 'steps': 29591, 'loss/train': 2.2682175636291504}
+08/30/2021 18:27:06 - INFO - __main__ - Step 29593: {'lr': 0.0004583320596488807, 'samples': 5681856, 'steps': 29592, 'loss/train': 1.465067982673645}
+08/30/2021 18:27:06 - INFO - __main__ - Step 29594: {'lr': 0.000458329126147877, 'samples': 5682048, 'steps': 29593, 'loss/train': 1.508357048034668}
+08/30/2021 18:27:06 - INFO - __main__ - Step 29595: {'lr': 0.00045832619255300344, 'samples': 5682240, 'steps': 29594, 'loss/train': 1.2611652612686157}
+08/30/2021 18:27:07 - INFO - __main__ - Step 29596: {'lr': 0.00045832325886426125, 'samples': 5682432, 'steps': 29595, 'loss/train': 1.4101680517196655}
+08/30/2021 18:27:07 - INFO - __main__ - Step 29597: {'lr': 0.0004583203250816518, 'samples': 5682624, 'steps': 29596, 'loss/train': 0.9930189847946167}
+08/30/2021 18:27:07 - INFO - __main__ - Step 29598: {'lr': 0.0004583173912051765, 'samples': 5682816, 'steps': 29597, 'loss/train': 0.9272570610046387}
+08/30/2021 18:27:08 - INFO - __main__ - Step 29599: {'lr': 0.00045831445723483656, 'samples': 5683008, 'steps': 29598, 'loss/train': 0.8228551745414734}
+08/30/2021 18:27:08 - INFO - __main__ - Step 29600: {'lr': 0.0004583115231706334, 'samples': 5683200, 'steps': 29599, 'loss/train': 0.8430296182632446}
+08/30/2021 18:27:10 - INFO - __main__ - Step 29601: {'lr': 0.0004583085890125682, 'samples': 5683392, 'steps': 29600, 'loss/train': 0.9320297241210938}
+08/30/2021 18:27:10 - INFO - __main__ - Step 29602: {'lr': 0.0004583056547606424, 'samples': 5683584, 'steps': 29601, 'loss/train': 1.4654074907302856}
+08/30/2021 18:27:10 - INFO - __main__ - Step 29603: {'lr': 0.0004583027204148573, 'samples': 5683776, 'steps': 29602, 'loss/train': 1.8659985065460205}
+08/30/2021 18:27:11 - INFO - __main__ - Step 29604: {'lr': 0.0004582997859752142, 'samples': 5683968, 'steps': 29603, 'loss/train': 1.5351128578186035}
+08/30/2021 18:27:11 - INFO - __main__ - Step 29605: {'lr': 0.0004582968514417144, 'samples': 5684160, 'steps': 29604, 'loss/train': 1.4761664867401123}
+08/30/2021 18:27:14 - INFO - __main__ - Step 29606: {'lr': 0.00045829391681435926, 'samples': 5684352, 'steps': 29605, 'loss/train': 1.10630464553833}
+08/30/2021 18:27:14 - INFO - __main__ - Step 29607: {'lr': 0.0004582909820931501, 'samples': 5684544, 'steps': 29606, 'loss/train': 1.7708563804626465}
+08/30/2021 18:27:15 - INFO - __main__ - Step 29608: {'lr': 0.00045828804727808824, 'samples': 5684736, 'steps': 29607, 'loss/train': 1.4790401458740234}
+08/30/2021 18:27:15 - INFO - __main__ - Step 29609: {'lr': 0.000458285112369175, 'samples': 5684928, 'steps': 29608, 'loss/train': 1.481463074684143}
+08/30/2021 18:27:15 - INFO - __main__ - Step 29610: {'lr': 0.0004582821773664118, 'samples': 5685120, 'steps': 29609, 'loss/train': 1.332221269607544}
+08/30/2021 18:27:16 - INFO - __main__ - Step 29611: {'lr': 0.0004582792422697997, 'samples': 5685312, 'steps': 29610, 'loss/train': 1.6628471612930298}
+08/30/2021 18:27:16 - INFO - __main__ - Step 29612: {'lr': 0.0004582763070793403, 'samples': 5685504, 'steps': 29611, 'loss/train': 2.3646347522735596}
+08/30/2021 18:27:18 - INFO - __main__ - Step 29613: {'lr': 0.0004582733717950347, 'samples': 5685696, 'steps': 29612, 'loss/train': 5.348879337310791}
+08/30/2021 18:27:18 - INFO - __main__ - Step 29614: {'lr': 0.00045827043641688444, 'samples': 5685888, 'steps': 29613, 'loss/train': 2.010775327682495}
+08/30/2021 18:27:18 - INFO - __main__ - Step 29615: {'lr': 0.00045826750094489065, 'samples': 5686080, 'steps': 29614, 'loss/train': 1.7838435173034668}
+08/30/2021 18:27:19 - INFO - __main__ - Step 29616: {'lr': 0.00045826456537905483, 'samples': 5686272, 'steps': 29615, 'loss/train': 1.4085440635681152}
+08/30/2021 18:27:19 - INFO - __main__ - Step 29617: {'lr': 0.0004582616297193781, 'samples': 5686464, 'steps': 29616, 'loss/train': 1.5924851894378662}
+08/30/2021 18:27:19 - INFO - __main__ - Step 29618: {'lr': 0.000458258693965862, 'samples': 5686656, 'steps': 29617, 'loss/train': 1.6739227771759033}
+08/30/2021 18:27:21 - INFO - __main__ - Step 29619: {'lr': 0.0004582557581185077, 'samples': 5686848, 'steps': 29618, 'loss/train': 1.4708425998687744}
+08/30/2021 18:27:21 - INFO - __main__ - Step 29620: {'lr': 0.00045825282217731655, 'samples': 5687040, 'steps': 29619, 'loss/train': 1.946986436843872}
+08/30/2021 18:27:22 - INFO - __main__ - Step 29621: {'lr': 0.00045824988614228995, 'samples': 5687232, 'steps': 29620, 'loss/train': 2.37992262840271}
+08/30/2021 18:27:22 - INFO - __main__ - Step 29622: {'lr': 0.0004582469500134292, 'samples': 5687424, 'steps': 29621, 'loss/train': 1.5118401050567627}
+08/30/2021 18:27:22 - INFO - __main__ - Step 29623: {'lr': 0.00045824401379073544, 'samples': 5687616, 'steps': 29622, 'loss/train': 1.385564923286438}
+08/30/2021 18:27:24 - INFO - __main__ - Step 29624: {'lr': 0.0004582410774742103, 'samples': 5687808, 'steps': 29623, 'loss/train': 1.0063823461532593}
+08/30/2021 18:27:25 - INFO - __main__ - Step 29625: {'lr': 0.00045823814106385485, 'samples': 5688000, 'steps': 29624, 'loss/train': 1.956981897354126}
+08/30/2021 18:27:25 - INFO - __main__ - Step 29626: {'lr': 0.0004582352045596705, 'samples': 5688192, 'steps': 29625, 'loss/train': 1.6747437715530396}
+08/30/2021 18:27:26 - INFO - __main__ - Step 29627: {'lr': 0.0004582322679616586, 'samples': 5688384, 'steps': 29626, 'loss/train': 1.8953553438186646}
+08/30/2021 18:27:26 - INFO - __main__ - Step 29628: {'lr': 0.0004582293312698205, 'samples': 5688576, 'steps': 29627, 'loss/train': 1.556592583656311}
+08/30/2021 18:27:26 - INFO - __main__ - Step 29629: {'lr': 0.00045822639448415736, 'samples': 5688768, 'steps': 29628, 'loss/train': 2.9476187229156494}
+08/30/2021 18:27:28 - INFO - __main__ - Step 29630: {'lr': 0.0004582234576046707, 'samples': 5688960, 'steps': 29629, 'loss/train': 0.1175139769911766}
+08/30/2021 18:27:28 - INFO - __main__ - Step 29631: {'lr': 0.00045822052063136177, 'samples': 5689152, 'steps': 29630, 'loss/train': 1.4863507747650146}
+08/30/2021 18:27:29 - INFO - __main__ - Step 29632: {'lr': 0.0004582175835642319, 'samples': 5689344, 'steps': 29631, 'loss/train': 1.4567972421646118}
+08/30/2021 18:27:29 - INFO - __main__ - Step 29633: {'lr': 0.0004582146464032824, 'samples': 5689536, 'steps': 29632, 'loss/train': 2.4604380130767822}
+08/30/2021 18:27:29 - INFO - __main__ - Step 29634: {'lr': 0.0004582117091485145, 'samples': 5689728, 'steps': 29633, 'loss/train': 1.3318003416061401}
+08/30/2021 18:27:31 - INFO - __main__ - Step 29635: {'lr': 0.0004582087717999297, 'samples': 5689920, 'steps': 29634, 'loss/train': 1.550450325012207}
+08/30/2021 18:27:31 - INFO - __main__ - Step 29636: {'lr': 0.0004582058343575292, 'samples': 5690112, 'steps': 29635, 'loss/train': 1.9619405269622803}
+08/30/2021 18:27:32 - INFO - __main__ - Step 29637: {'lr': 0.00045820289682131437, 'samples': 5690304, 'steps': 29636, 'loss/train': 1.9311447143554688}
+08/30/2021 18:27:32 - INFO - __main__ - Step 29638: {'lr': 0.0004581999591912865, 'samples': 5690496, 'steps': 29637, 'loss/train': 1.916884183883667}
+08/30/2021 18:27:32 - INFO - __main__ - Step 29639: {'lr': 0.000458197021467447, 'samples': 5690688, 'steps': 29638, 'loss/train': 1.9588192701339722}
+08/30/2021 18:27:34 - INFO - __main__ - Step 29640: {'lr': 0.00045819408364979714, 'samples': 5690880, 'steps': 29639, 'loss/train': 1.8672581911087036}
+08/30/2021 18:27:34 - INFO - __main__ - Step 29641: {'lr': 0.0004581911457383382, 'samples': 5691072, 'steps': 29640, 'loss/train': 1.2657244205474854}
+08/30/2021 18:27:35 - INFO - __main__ - Step 29642: {'lr': 0.0004581882077330716, 'samples': 5691264, 'steps': 29641, 'loss/train': 2.0068185329437256}
+08/30/2021 18:27:35 - INFO - __main__ - Step 29643: {'lr': 0.0004581852696339985, 'samples': 5691456, 'steps': 29642, 'loss/train': 1.3693592548370361}
+08/30/2021 18:27:35 - INFO - __main__ - Step 29644: {'lr': 0.00045818233144112044, 'samples': 5691648, 'steps': 29643, 'loss/train': 1.9072682857513428}
+08/30/2021 18:27:37 - INFO - __main__ - Step 29645: {'lr': 0.00045817939315443855, 'samples': 5691840, 'steps': 29644, 'loss/train': 1.1360223293304443}
+08/30/2021 18:27:38 - INFO - __main__ - Step 29646: {'lr': 0.0004581764547739543, 'samples': 5692032, 'steps': 29645, 'loss/train': 1.7882003784179688}
+08/30/2021 18:27:38 - INFO - __main__ - Step 29647: {'lr': 0.00045817351629966896, 'samples': 5692224, 'steps': 29646, 'loss/train': 2.02164626121521}
+08/30/2021 18:27:38 - INFO - __main__ - Step 29648: {'lr': 0.00045817057773158375, 'samples': 5692416, 'steps': 29647, 'loss/train': 1.7786821126937866}
+08/30/2021 18:27:39 - INFO - __main__ - Step 29649: {'lr': 0.0004581676390697002, 'samples': 5692608, 'steps': 29648, 'loss/train': 1.0712475776672363}
+08/30/2021 18:27:40 - INFO - __main__ - Step 29650: {'lr': 0.00045816470031401945, 'samples': 5692800, 'steps': 29649, 'loss/train': 0.9194968938827515}
+08/30/2021 18:27:41 - INFO - __main__ - Step 29651: {'lr': 0.00045816176146454296, 'samples': 5692992, 'steps': 29650, 'loss/train': 1.670853614807129}
+08/30/2021 18:27:41 - INFO - __main__ - Step 29652: {'lr': 0.00045815882252127197, 'samples': 5693184, 'steps': 29651, 'loss/train': 0.986540675163269}
+08/30/2021 18:27:41 - INFO - __main__ - Step 29653: {'lr': 0.0004581558834842078, 'samples': 5693376, 'steps': 29652, 'loss/train': 1.2599154710769653}
+08/30/2021 18:27:42 - INFO - __main__ - Step 29654: {'lr': 0.00045815294435335184, 'samples': 5693568, 'steps': 29653, 'loss/train': 1.7173832654953003}
+08/30/2021 18:27:43 - INFO - __main__ - Step 29655: {'lr': 0.0004581500051287053, 'samples': 5693760, 'steps': 29654, 'loss/train': 1.1453946828842163}
+08/30/2021 18:27:44 - INFO - __main__ - Step 29656: {'lr': 0.00045814706581026967, 'samples': 5693952, 'steps': 29655, 'loss/train': 1.1144442558288574}
+08/30/2021 18:27:44 - INFO - __main__ - Step 29657: {'lr': 0.0004581441263980461, 'samples': 5694144, 'steps': 29656, 'loss/train': 0.86360764503479}
+08/30/2021 18:27:44 - INFO - __main__ - Step 29658: {'lr': 0.0004581411868920361, 'samples': 5694336, 'steps': 29657, 'loss/train': 1.7170466184616089}
+08/30/2021 18:27:45 - INFO - __main__ - Step 29659: {'lr': 0.00045813824729224085, 'samples': 5694528, 'steps': 29658, 'loss/train': 1.596787452697754}
+08/30/2021 18:27:45 - INFO - __main__ - Step 29660: {'lr': 0.0004581353075986617, 'samples': 5694720, 'steps': 29659, 'loss/train': 1.4135023355484009}
+08/30/2021 18:27:47 - INFO - __main__ - Step 29661: {'lr': 0.00045813236781129996, 'samples': 5694912, 'steps': 29660, 'loss/train': 1.6739174127578735}
+08/30/2021 18:27:47 - INFO - __main__ - Step 29662: {'lr': 0.00045812942793015707, 'samples': 5695104, 'steps': 29661, 'loss/train': 1.202912449836731}
+08/30/2021 18:27:47 - INFO - __main__ - Step 29663: {'lr': 0.0004581264879552342, 'samples': 5695296, 'steps': 29662, 'loss/train': 0.19049958884716034}
+08/30/2021 18:27:48 - INFO - __main__ - Step 29664: {'lr': 0.00045812354788653275, 'samples': 5695488, 'steps': 29663, 'loss/train': 1.0727471113204956}
+08/30/2021 18:27:48 - INFO - __main__ - Step 29665: {'lr': 0.00045812060772405403, 'samples': 5695680, 'steps': 29664, 'loss/train': 1.5303667783737183}
+08/30/2021 18:27:50 - INFO - __main__ - Step 29666: {'lr': 0.0004581176674677995, 'samples': 5695872, 'steps': 29665, 'loss/train': 1.313496708869934}
+08/30/2021 18:27:50 - INFO - __main__ - Step 29667: {'lr': 0.00045811472711777026, 'samples': 5696064, 'steps': 29666, 'loss/train': 1.6279692649841309}
+08/30/2021 18:27:50 - INFO - __main__ - Step 29668: {'lr': 0.0004581117866739677, 'samples': 5696256, 'steps': 29667, 'loss/train': 1.3790535926818848}
+08/30/2021 18:27:51 - INFO - __main__ - Step 29669: {'lr': 0.00045810884613639325, 'samples': 5696448, 'steps': 29668, 'loss/train': 1.1239794492721558}
+08/30/2021 18:27:51 - INFO - __main__ - Step 29670: {'lr': 0.00045810590550504816, 'samples': 5696640, 'steps': 29669, 'loss/train': 1.9284592866897583}
+08/30/2021 18:27:53 - INFO - __main__ - Step 29671: {'lr': 0.0004581029647799337, 'samples': 5696832, 'steps': 29670, 'loss/train': 1.4202970266342163}
+08/30/2021 18:27:53 - INFO - __main__ - Step 29672: {'lr': 0.0004581000239610513, 'samples': 5697024, 'steps': 29671, 'loss/train': 1.2471117973327637}
+08/30/2021 18:27:53 - INFO - __main__ - Step 29673: {'lr': 0.0004580970830484023, 'samples': 5697216, 'steps': 29672, 'loss/train': 1.6633930206298828}
+08/30/2021 18:27:54 - INFO - __main__ - Step 29674: {'lr': 0.00045809414204198785, 'samples': 5697408, 'steps': 29673, 'loss/train': 1.426016926765442}
+08/30/2021 18:27:54 - INFO - __main__ - Step 29675: {'lr': 0.00045809120094180946, 'samples': 5697600, 'steps': 29674, 'loss/train': 1.453947901725769}
+08/30/2021 18:27:56 - INFO - __main__ - Step 29676: {'lr': 0.00045808825974786834, 'samples': 5697792, 'steps': 29675, 'loss/train': 1.6104342937469482}
+08/30/2021 18:27:56 - INFO - __main__ - Step 29677: {'lr': 0.0004580853184601659, 'samples': 5697984, 'steps': 29676, 'loss/train': 1.46486234664917}
+08/30/2021 18:27:57 - INFO - __main__ - Step 29678: {'lr': 0.0004580823770787034, 'samples': 5698176, 'steps': 29677, 'loss/train': 1.7360520362854004}
+08/30/2021 18:27:57 - INFO - __main__ - Step 29679: {'lr': 0.0004580794356034822, 'samples': 5698368, 'steps': 29678, 'loss/train': 1.6491705179214478}
+08/30/2021 18:27:57 - INFO - __main__ - Step 29680: {'lr': 0.0004580764940345036, 'samples': 5698560, 'steps': 29679, 'loss/train': 1.6530210971832275}
+08/30/2021 18:27:59 - INFO - __main__ - Step 29681: {'lr': 0.00045807355237176896, 'samples': 5698752, 'steps': 29680, 'loss/train': 1.5946695804595947}
+08/30/2021 18:27:59 - INFO - __main__ - Step 29682: {'lr': 0.0004580706106152796, 'samples': 5698944, 'steps': 29681, 'loss/train': 1.322835922241211}
+08/30/2021 18:28:00 - INFO - __main__ - Step 29683: {'lr': 0.00045806766876503683, 'samples': 5699136, 'steps': 29682, 'loss/train': 2.5335166454315186}
+08/30/2021 18:28:00 - INFO - __main__ - Step 29684: {'lr': 0.000458064726821042, 'samples': 5699328, 'steps': 29683, 'loss/train': 1.5357316732406616}
+08/30/2021 18:28:00 - INFO - __main__ - Step 29685: {'lr': 0.0004580617847832964, 'samples': 5699520, 'steps': 29684, 'loss/train': 1.5088759660720825}
+08/30/2021 18:28:02 - INFO - __main__ - Step 29686: {'lr': 0.0004580588426518013, 'samples': 5699712, 'steps': 29685, 'loss/train': 1.354177474975586}
+08/30/2021 18:28:02 - INFO - __main__ - Step 29687: {'lr': 0.0004580559004265582, 'samples': 5699904, 'steps': 29686, 'loss/train': 1.7243818044662476}
+08/30/2021 18:28:03 - INFO - __main__ - Step 29688: {'lr': 0.0004580529581075683, 'samples': 5700096, 'steps': 29687, 'loss/train': 1.3967630863189697}
+08/30/2021 18:28:03 - INFO - __main__ - Step 29689: {'lr': 0.0004580500156948329, 'samples': 5700288, 'steps': 29688, 'loss/train': 1.497321367263794}
+08/30/2021 18:28:03 - INFO - __main__ - Step 29690: {'lr': 0.0004580470731883534, 'samples': 5700480, 'steps': 29689, 'loss/train': 1.810050129890442}
+08/30/2021 18:28:04 - INFO - __main__ - Step 29691: {'lr': 0.0004580441305881311, 'samples': 5700672, 'steps': 29690, 'loss/train': 0.927593469619751}
+08/30/2021 18:28:05 - INFO - __main__ - Step 29692: {'lr': 0.0004580411878941673, 'samples': 5700864, 'steps': 29691, 'loss/train': 2.807532548904419}
+08/30/2021 18:28:06 - INFO - __main__ - Step 29693: {'lr': 0.0004580382451064634, 'samples': 5701056, 'steps': 29692, 'loss/train': 1.5563640594482422}
+08/30/2021 18:28:06 - INFO - __main__ - Step 29694: {'lr': 0.00045803530222502065, 'samples': 5701248, 'steps': 29693, 'loss/train': 1.595654010772705}
+08/30/2021 18:28:07 - INFO - __main__ - Step 29695: {'lr': 0.0004580323592498404, 'samples': 5701440, 'steps': 29694, 'loss/train': 1.2515085935592651}
+08/30/2021 18:28:07 - INFO - __main__ - Step 29696: {'lr': 0.00045802941618092397, 'samples': 5701632, 'steps': 29695, 'loss/train': 0.2638806700706482}
+08/30/2021 18:28:09 - INFO - __main__ - Step 29697: {'lr': 0.0004580264730182727, 'samples': 5701824, 'steps': 29696, 'loss/train': 1.4753319025039673}
+08/30/2021 18:28:10 - INFO - __main__ - Step 29698: {'lr': 0.000458023529761888, 'samples': 5702016, 'steps': 29697, 'loss/train': 1.6588515043258667}
+08/30/2021 18:28:10 - INFO - __main__ - Step 29699: {'lr': 0.00045802058641177104, 'samples': 5702208, 'steps': 29698, 'loss/train': 1.7861418724060059}
+08/30/2021 18:28:10 - INFO - __main__ - Step 29700: {'lr': 0.00045801764296792317, 'samples': 5702400, 'steps': 29699, 'loss/train': 1.6370424032211304}
+08/30/2021 18:28:11 - INFO - __main__ - Step 29701: {'lr': 0.0004580146994303458, 'samples': 5702592, 'steps': 29700, 'loss/train': 1.1859413385391235}
+08/30/2021 18:28:12 - INFO - __main__ - Step 29702: {'lr': 0.0004580117557990402, 'samples': 5702784, 'steps': 29701, 'loss/train': 1.4897328615188599}
+08/30/2021 18:28:13 - INFO - __main__ - Step 29703: {'lr': 0.0004580088120740077, 'samples': 5702976, 'steps': 29702, 'loss/train': 1.4795736074447632}
+08/30/2021 18:28:13 - INFO - __main__ - Step 29704: {'lr': 0.0004580058682552497, 'samples': 5703168, 'steps': 29703, 'loss/train': 2.0447490215301514}
+08/30/2021 18:28:13 - INFO - __main__ - Step 29705: {'lr': 0.00045800292434276736, 'samples': 5703360, 'steps': 29704, 'loss/train': 1.5913904905319214}
+08/30/2021 18:28:14 - INFO - __main__ - Step 29706: {'lr': 0.0004579999803365622, 'samples': 5703552, 'steps': 29705, 'loss/train': 1.6796106100082397}
+08/30/2021 18:28:15 - INFO - __main__ - Step 29707: {'lr': 0.00045799703623663546, 'samples': 5703744, 'steps': 29706, 'loss/train': 1.5506706237792969}
+08/30/2021 18:28:16 - INFO - __main__ - Step 29708: {'lr': 0.00045799409204298844, 'samples': 5703936, 'steps': 29707, 'loss/train': 1.0952070951461792}
+08/30/2021 18:28:16 - INFO - __main__ - Step 29709: {'lr': 0.00045799114775562245, 'samples': 5704128, 'steps': 29708, 'loss/train': 1.8405007123947144}
+08/30/2021 18:28:16 - INFO - __main__ - Step 29710: {'lr': 0.00045798820337453894, 'samples': 5704320, 'steps': 29709, 'loss/train': 1.6173516511917114}
+08/30/2021 18:28:17 - INFO - __main__ - Step 29711: {'lr': 0.00045798525889973905, 'samples': 5704512, 'steps': 29710, 'loss/train': 1.2189722061157227}
+08/30/2021 18:28:18 - INFO - __main__ - Step 29712: {'lr': 0.00045798231433122436, 'samples': 5704704, 'steps': 29711, 'loss/train': 1.2220425605773926}
+08/30/2021 18:28:19 - INFO - __main__ - Step 29713: {'lr': 0.00045797936966899595, 'samples': 5704896, 'steps': 29712, 'loss/train': 1.3528696298599243}
+08/30/2021 18:28:19 - INFO - __main__ - Step 29714: {'lr': 0.00045797642491305523, 'samples': 5705088, 'steps': 29713, 'loss/train': 1.8279149532318115}
+08/30/2021 18:28:19 - INFO - __main__ - Step 29715: {'lr': 0.0004579734800634036, 'samples': 5705280, 'steps': 29714, 'loss/train': 1.3975285291671753}
+08/30/2021 18:28:20 - INFO - __main__ - Step 29716: {'lr': 0.0004579705351200423, 'samples': 5705472, 'steps': 29715, 'loss/train': 1.6372387409210205}
+08/30/2021 18:28:21 - INFO - __main__ - Step 29717: {'lr': 0.0004579675900829727, 'samples': 5705664, 'steps': 29716, 'loss/train': 1.507022738456726}
+08/30/2021 18:28:22 - INFO - __main__ - Step 29718: {'lr': 0.00045796464495219614, 'samples': 5705856, 'steps': 29717, 'loss/train': 1.4987457990646362}
+08/30/2021 18:28:22 - INFO - __main__ - Step 29719: {'lr': 0.00045796169972771387, 'samples': 5706048, 'steps': 29718, 'loss/train': 1.08888840675354}
+08/30/2021 18:28:23 - INFO - __main__ - Step 29720: {'lr': 0.00045795875440952726, 'samples': 5706240, 'steps': 29719, 'loss/train': 1.1902862787246704}
+08/30/2021 18:28:23 - INFO - __main__ - Step 29721: {'lr': 0.00045795580899763767, 'samples': 5706432, 'steps': 29720, 'loss/train': 1.6228948831558228}
+08/30/2021 18:28:23 - INFO - __main__ - Step 29722: {'lr': 0.00045795286349204633, 'samples': 5706624, 'steps': 29721, 'loss/train': 1.4023505449295044}
+08/30/2021 18:28:25 - INFO - __main__ - Step 29723: {'lr': 0.0004579499178927547, 'samples': 5706816, 'steps': 29722, 'loss/train': 1.3119184970855713}
+08/30/2021 18:28:25 - INFO - __main__ - Step 29724: {'lr': 0.0004579469721997641, 'samples': 5707008, 'steps': 29723, 'loss/train': 1.5725725889205933}
+08/30/2021 18:28:26 - INFO - __main__ - Step 29725: {'lr': 0.0004579440264130758, 'samples': 5707200, 'steps': 29724, 'loss/train': 1.6831140518188477}
+08/30/2021 18:28:26 - INFO - __main__ - Step 29726: {'lr': 0.000457941080532691, 'samples': 5707392, 'steps': 29725, 'loss/train': 1.8906539678573608}
+08/30/2021 18:28:26 - INFO - __main__ - Step 29727: {'lr': 0.0004579381345586113, 'samples': 5707584, 'steps': 29726, 'loss/train': 1.6148093938827515}
+08/30/2021 18:28:28 - INFO - __main__ - Step 29728: {'lr': 0.0004579351884908378, 'samples': 5707776, 'steps': 29727, 'loss/train': 1.54594886302948}
+08/30/2021 18:28:28 - INFO - __main__ - Step 29729: {'lr': 0.00045793224232937193, 'samples': 5707968, 'steps': 29728, 'loss/train': 1.3913178443908691}
+08/30/2021 18:28:29 - INFO - __main__ - Step 29730: {'lr': 0.0004579292960742151, 'samples': 5708160, 'steps': 29729, 'loss/train': 1.354109764099121}
+08/30/2021 18:28:29 - INFO - __main__ - Step 29731: {'lr': 0.0004579263497253684, 'samples': 5708352, 'steps': 29730, 'loss/train': 2.0978946685791016}
+08/30/2021 18:28:29 - INFO - __main__ - Step 29732: {'lr': 0.00045792340328283334, 'samples': 5708544, 'steps': 29731, 'loss/train': 1.5430909395217896}
+08/30/2021 18:28:31 - INFO - __main__ - Step 29733: {'lr': 0.0004579204567466112, 'samples': 5708736, 'steps': 29732, 'loss/train': 1.5453301668167114}
+08/30/2021 18:28:31 - INFO - __main__ - Step 29734: {'lr': 0.0004579175101167033, 'samples': 5708928, 'steps': 29733, 'loss/train': 1.5608700513839722}
+08/30/2021 18:28:32 - INFO - __main__ - Step 29735: {'lr': 0.000457914563393111, 'samples': 5709120, 'steps': 29734, 'loss/train': 0.512084424495697}
+08/30/2021 18:28:32 - INFO - __main__ - Step 29736: {'lr': 0.00045791161657583555, 'samples': 5709312, 'steps': 29735, 'loss/train': 1.3737982511520386}
+08/30/2021 18:28:32 - INFO - __main__ - Step 29737: {'lr': 0.00045790866966487843, 'samples': 5709504, 'steps': 29736, 'loss/train': 0.9926096796989441}
+08/30/2021 18:28:34 - INFO - __main__ - Step 29738: {'lr': 0.0004579057226602408, 'samples': 5709696, 'steps': 29737, 'loss/train': 0.20578551292419434}
+08/30/2021 18:28:34 - INFO - __main__ - Step 29739: {'lr': 0.00045790277556192414, 'samples': 5709888, 'steps': 29738, 'loss/train': 1.2388333082199097}
+08/30/2021 18:28:35 - INFO - __main__ - Step 29740: {'lr': 0.0004578998283699296, 'samples': 5710080, 'steps': 29739, 'loss/train': 1.7845193147659302}
+08/30/2021 18:28:35 - INFO - __main__ - Step 29741: {'lr': 0.0004578968810842586, 'samples': 5710272, 'steps': 29740, 'loss/train': 1.3406702280044556}
+08/30/2021 18:28:35 - INFO - __main__ - Step 29742: {'lr': 0.0004578939337049126, 'samples': 5710464, 'steps': 29741, 'loss/train': 1.8162589073181152}
+08/30/2021 18:28:37 - INFO - __main__ - Step 29743: {'lr': 0.0004578909862318927, 'samples': 5710656, 'steps': 29742, 'loss/train': 0.7952150702476501}
+08/30/2021 18:28:37 - INFO - __main__ - Step 29744: {'lr': 0.00045788803866520037, 'samples': 5710848, 'steps': 29743, 'loss/train': 2.365987539291382}
+08/30/2021 18:28:38 - INFO - __main__ - Step 29745: {'lr': 0.0004578850910048369, 'samples': 5711040, 'steps': 29744, 'loss/train': 1.553279161453247}
+08/30/2021 18:28:38 - INFO - __main__ - Step 29746: {'lr': 0.0004578821432508036, 'samples': 5711232, 'steps': 29745, 'loss/train': 1.640616774559021}
+08/30/2021 18:28:38 - INFO - __main__ - Step 29747: {'lr': 0.00045787919540310175, 'samples': 5711424, 'steps': 29746, 'loss/train': 1.5358890295028687}
+08/30/2021 18:28:39 - INFO - __main__ - Step 29748: {'lr': 0.0004578762474617328, 'samples': 5711616, 'steps': 29747, 'loss/train': 1.5220602750778198}
+08/30/2021 18:28:40 - INFO - __main__ - Step 29749: {'lr': 0.00045787329942669803, 'samples': 5711808, 'steps': 29748, 'loss/train': 1.587807059288025}
+08/30/2021 18:28:41 - INFO - __main__ - Step 29750: {'lr': 0.0004578703512979988, 'samples': 5712000, 'steps': 29749, 'loss/train': 1.354875087738037}
+08/30/2021 18:28:41 - INFO - __main__ - Step 29751: {'lr': 0.00045786740307563633, 'samples': 5712192, 'steps': 29750, 'loss/train': 1.7917624711990356}
+08/30/2021 18:28:41 - INFO - __main__ - Step 29752: {'lr': 0.000457864454759612, 'samples': 5712384, 'steps': 29751, 'loss/train': 2.8033447265625}
+08/30/2021 18:28:42 - INFO - __main__ - Step 29753: {'lr': 0.00045786150634992716, 'samples': 5712576, 'steps': 29752, 'loss/train': 1.4662129878997803}
+08/30/2021 18:28:44 - INFO - __main__ - Step 29754: {'lr': 0.0004578585578465833, 'samples': 5712768, 'steps': 29753, 'loss/train': 1.7054139375686646}
+08/30/2021 18:28:44 - INFO - __main__ - Step 29755: {'lr': 0.00045785560924958135, 'samples': 5712960, 'steps': 29754, 'loss/train': 1.5506590604782104}
+08/30/2021 18:28:45 - INFO - __main__ - Step 29756: {'lr': 0.00045785266055892296, 'samples': 5713152, 'steps': 29755, 'loss/train': 0.8969353437423706}
+08/30/2021 18:28:45 - INFO - __main__ - Step 29757: {'lr': 0.0004578497117746094, 'samples': 5713344, 'steps': 29756, 'loss/train': 1.6206135749816895}
+08/30/2021 18:28:45 - INFO - __main__ - Step 29758: {'lr': 0.00045784676289664194, 'samples': 5713536, 'steps': 29757, 'loss/train': 2.000650405883789}
+08/30/2021 18:28:47 - INFO - __main__ - Step 29759: {'lr': 0.00045784381392502193, 'samples': 5713728, 'steps': 29758, 'loss/train': 1.9538886547088623}
+08/30/2021 18:28:47 - INFO - __main__ - Step 29760: {'lr': 0.00045784086485975076, 'samples': 5713920, 'steps': 29759, 'loss/train': 1.460592269897461}
+08/30/2021 18:28:48 - INFO - __main__ - Step 29761: {'lr': 0.00045783791570082956, 'samples': 5714112, 'steps': 29760, 'loss/train': 1.3283790349960327}
+08/30/2021 18:28:48 - INFO - __main__ - Step 29762: {'lr': 0.00045783496644825997, 'samples': 5714304, 'steps': 29761, 'loss/train': 1.9077951908111572}
+08/30/2021 18:28:48 - INFO - __main__ - Step 29763: {'lr': 0.000457832017102043, 'samples': 5714496, 'steps': 29762, 'loss/train': 1.3710795640945435}
+08/30/2021 18:28:50 - INFO - __main__ - Step 29764: {'lr': 0.00045782906766218026, 'samples': 5714688, 'steps': 29763, 'loss/train': 1.4096707105636597}
+08/30/2021 18:28:50 - INFO - __main__ - Step 29765: {'lr': 0.00045782611812867285, 'samples': 5714880, 'steps': 29764, 'loss/train': 1.261650562286377}
+08/30/2021 18:28:51 - INFO - __main__ - Step 29766: {'lr': 0.0004578231685015223, 'samples': 5715072, 'steps': 29765, 'loss/train': 1.4897416830062866}
+08/30/2021 18:28:51 - INFO - __main__ - Step 29767: {'lr': 0.00045782021878072976, 'samples': 5715264, 'steps': 29766, 'loss/train': 1.155381202697754}
+08/30/2021 18:28:51 - INFO - __main__ - Step 29768: {'lr': 0.0004578172689662967, 'samples': 5715456, 'steps': 29767, 'loss/train': 1.8191925287246704}
+08/30/2021 18:28:53 - INFO - __main__ - Step 29769: {'lr': 0.0004578143190582243, 'samples': 5715648, 'steps': 29768, 'loss/train': 1.3403890132904053}
+08/30/2021 18:28:53 - INFO - __main__ - Step 29770: {'lr': 0.000457811369056514, 'samples': 5715840, 'steps': 29769, 'loss/train': 1.5078458786010742}
+08/30/2021 18:28:53 - INFO - __main__ - Step 29771: {'lr': 0.0004578084189611671, 'samples': 5716032, 'steps': 29770, 'loss/train': 1.5487326383590698}
+08/30/2021 18:28:54 - INFO - __main__ - Step 29772: {'lr': 0.000457805468772185, 'samples': 5716224, 'steps': 29771, 'loss/train': 1.6098134517669678}
+08/30/2021 18:28:54 - INFO - __main__ - Step 29773: {'lr': 0.00045780251848956887, 'samples': 5716416, 'steps': 29772, 'loss/train': 0.9175944924354553}
+08/30/2021 18:28:56 - INFO - __main__ - Step 29774: {'lr': 0.0004577995681133202, 'samples': 5716608, 'steps': 29773, 'loss/train': 1.8215703964233398}
+08/30/2021 18:28:56 - INFO - __main__ - Step 29775: {'lr': 0.00045779661764344025, 'samples': 5716800, 'steps': 29774, 'loss/train': 1.6772704124450684}
+08/30/2021 18:28:56 - INFO - __main__ - Step 29776: {'lr': 0.0004577936670799303, 'samples': 5716992, 'steps': 29775, 'loss/train': 1.6390513181686401}
+08/30/2021 18:28:57 - INFO - __main__ - Step 29777: {'lr': 0.00045779071642279177, 'samples': 5717184, 'steps': 29776, 'loss/train': 1.5799801349639893}
+08/30/2021 18:28:57 - INFO - __main__ - Step 29778: {'lr': 0.00045778776567202597, 'samples': 5717376, 'steps': 29777, 'loss/train': 1.326113224029541}
+08/30/2021 18:28:57 - INFO - __main__ - Step 29779: {'lr': 0.0004577848148276341, 'samples': 5717568, 'steps': 29778, 'loss/train': 1.3282570838928223}
+08/30/2021 18:28:59 - INFO - __main__ - Step 29780: {'lr': 0.00045778186388961776, 'samples': 5717760, 'steps': 29779, 'loss/train': 1.3016703128814697}
+08/30/2021 18:28:59 - INFO - __main__ - Step 29781: {'lr': 0.000457778912857978, 'samples': 5717952, 'steps': 29780, 'loss/train': 1.7542059421539307}
+08/30/2021 18:29:00 - INFO - __main__ - Step 29782: {'lr': 0.0004577759617327163, 'samples': 5718144, 'steps': 29781, 'loss/train': 1.3037378787994385}
+08/30/2021 18:29:00 - INFO - __main__ - Step 29783: {'lr': 0.000457773010513834, 'samples': 5718336, 'steps': 29782, 'loss/train': 1.2276067733764648}
+08/30/2021 18:29:00 - INFO - __main__ - Step 29784: {'lr': 0.0004577700592013323, 'samples': 5718528, 'steps': 29783, 'loss/train': 1.6257506608963013}
+08/30/2021 18:29:02 - INFO - __main__ - Step 29785: {'lr': 0.0004577671077952127, 'samples': 5718720, 'steps': 29784, 'loss/train': 1.7140051126480103}
+08/30/2021 18:29:03 - INFO - __main__ - Step 29786: {'lr': 0.0004577641562954764, 'samples': 5718912, 'steps': 29785, 'loss/train': 0.15526026487350464}
+08/30/2021 18:29:03 - INFO - __main__ - Step 29787: {'lr': 0.00045776120470212477, 'samples': 5719104, 'steps': 29786, 'loss/train': 1.3239808082580566}
+08/30/2021 18:29:03 - INFO - __main__ - Step 29788: {'lr': 0.00045775825301515923, 'samples': 5719296, 'steps': 29787, 'loss/train': 1.4864088296890259}
+08/30/2021 18:29:04 - INFO - __main__ - Step 29789: {'lr': 0.00045775530123458096, 'samples': 5719488, 'steps': 29788, 'loss/train': 2.255086898803711}
+08/30/2021 18:29:05 - INFO - __main__ - Step 29790: {'lr': 0.00045775234936039133, 'samples': 5719680, 'steps': 29789, 'loss/train': 1.44126558303833}
+08/30/2021 18:29:05 - INFO - __main__ - Step 29791: {'lr': 0.00045774939739259173, 'samples': 5719872, 'steps': 29790, 'loss/train': 1.770522117614746}
+08/30/2021 18:29:06 - INFO - __main__ - Step 29792: {'lr': 0.0004577464453311835, 'samples': 5720064, 'steps': 29791, 'loss/train': 0.2801794409751892}
+08/30/2021 18:29:06 - INFO - __main__ - Step 29793: {'lr': 0.00045774349317616786, 'samples': 5720256, 'steps': 29792, 'loss/train': 1.2711302042007446}
+08/30/2021 18:29:07 - INFO - __main__ - Step 29794: {'lr': 0.00045774054092754624, 'samples': 5720448, 'steps': 29793, 'loss/train': 1.5915980339050293}
+08/30/2021 18:29:08 - INFO - __main__ - Step 29795: {'lr': 0.00045773758858531997, 'samples': 5720640, 'steps': 29794, 'loss/train': 1.4245502948760986}
+08/30/2021 18:29:09 - INFO - __main__ - Step 29796: {'lr': 0.0004577346361494903, 'samples': 5720832, 'steps': 29795, 'loss/train': 0.8146663904190063}
+08/30/2021 18:29:09 - INFO - __main__ - Step 29797: {'lr': 0.0004577316836200586, 'samples': 5721024, 'steps': 29796, 'loss/train': 0.95196133852005}
+08/30/2021 18:29:09 - INFO - __main__ - Step 29798: {'lr': 0.0004577287309970262, 'samples': 5721216, 'steps': 29797, 'loss/train': 0.8967983722686768}
+08/30/2021 18:29:10 - INFO - __main__ - Step 29799: {'lr': 0.0004577257782803945, 'samples': 5721408, 'steps': 29798, 'loss/train': 1.5457720756530762}
+08/30/2021 18:29:11 - INFO - __main__ - Step 29800: {'lr': 0.00045772282547016475, 'samples': 5721600, 'steps': 29799, 'loss/train': 1.2335726022720337}
+08/30/2021 18:29:12 - INFO - __main__ - Step 29801: {'lr': 0.0004577198725663383, 'samples': 5721792, 'steps': 29800, 'loss/train': 1.3536510467529297}
+08/30/2021 18:29:12 - INFO - __main__ - Step 29802: {'lr': 0.00045771691956891645, 'samples': 5721984, 'steps': 29801, 'loss/train': 1.571109652519226}
+08/30/2021 18:29:12 - INFO - __main__ - Step 29803: {'lr': 0.00045771396647790053, 'samples': 5722176, 'steps': 29802, 'loss/train': 0.9780459403991699}
+08/30/2021 18:29:13 - INFO - __main__ - Step 29804: {'lr': 0.00045771101329329195, 'samples': 5722368, 'steps': 29803, 'loss/train': 1.5371843576431274}
+08/30/2021 18:29:13 - INFO - __main__ - Step 29805: {'lr': 0.00045770806001509205, 'samples': 5722560, 'steps': 29804, 'loss/train': 1.6407279968261719}
+08/30/2021 18:29:15 - INFO - __main__ - Step 29806: {'lr': 0.00045770510664330203, 'samples': 5722752, 'steps': 29805, 'loss/train': 3.0229039192199707}
+08/30/2021 18:29:16 - INFO - __main__ - Step 29807: {'lr': 0.0004577021531779233, 'samples': 5722944, 'steps': 29806, 'loss/train': 1.6292167901992798}
+08/30/2021 18:29:16 - INFO - __main__ - Step 29808: {'lr': 0.00045769919961895716, 'samples': 5723136, 'steps': 29807, 'loss/train': 1.7189383506774902}
+08/30/2021 18:29:17 - INFO - __main__ - Step 29809: {'lr': 0.000457696245966405, 'samples': 5723328, 'steps': 29808, 'loss/train': 1.4111695289611816}
+08/30/2021 18:29:17 - INFO - __main__ - Step 29810: {'lr': 0.0004576932922202681, 'samples': 5723520, 'steps': 29809, 'loss/train': 1.9019224643707275}
+08/30/2021 18:29:19 - INFO - __main__ - Step 29811: {'lr': 0.00045769033838054783, 'samples': 5723712, 'steps': 29810, 'loss/train': 1.5190767049789429}
+08/30/2021 18:29:19 - INFO - __main__ - Step 29812: {'lr': 0.0004576873844472455, 'samples': 5723904, 'steps': 29811, 'loss/train': 1.2523224353790283}
+08/30/2021 18:29:19 - INFO - __main__ - Step 29813: {'lr': 0.00045768443042036247, 'samples': 5724096, 'steps': 29812, 'loss/train': 1.69696843624115}
+08/30/2021 18:29:20 - INFO - __main__ - Step 29814: {'lr': 0.0004576814762999, 'samples': 5724288, 'steps': 29813, 'loss/train': 0.5058253407478333}
+08/30/2021 18:29:20 - INFO - __main__ - Step 29815: {'lr': 0.00045767852208585945, 'samples': 5724480, 'steps': 29814, 'loss/train': 1.6717995405197144}
+08/30/2021 18:29:21 - INFO - __main__ - Step 29816: {'lr': 0.00045767556777824217, 'samples': 5724672, 'steps': 29815, 'loss/train': 1.5186625719070435}
+08/30/2021 18:29:22 - INFO - __main__ - Step 29817: {'lr': 0.00045767261337704946, 'samples': 5724864, 'steps': 29816, 'loss/train': 1.3946292400360107}
+08/30/2021 18:29:22 - INFO - __main__ - Step 29818: {'lr': 0.00045766965888228273, 'samples': 5725056, 'steps': 29817, 'loss/train': 1.4422296285629272}
+08/30/2021 18:29:23 - INFO - __main__ - Step 29819: {'lr': 0.00045766670429394317, 'samples': 5725248, 'steps': 29818, 'loss/train': 1.076311469078064}
+08/30/2021 18:29:23 - INFO - __main__ - Step 29820: {'lr': 0.00045766374961203236, 'samples': 5725440, 'steps': 29819, 'loss/train': 1.0208680629730225}
+08/30/2021 18:29:25 - INFO - __main__ - Step 29821: {'lr': 0.0004576607948365513, 'samples': 5725632, 'steps': 29820, 'loss/train': 1.6473058462142944}
+08/30/2021 18:29:25 - INFO - __main__ - Step 29822: {'lr': 0.0004576578399675015, 'samples': 5725824, 'steps': 29821, 'loss/train': 1.4750052690505981}
+08/30/2021 18:29:25 - INFO - __main__ - Step 29823: {'lr': 0.00045765488500488437, 'samples': 5726016, 'steps': 29822, 'loss/train': 1.0241910219192505}
+08/30/2021 18:29:26 - INFO - __main__ - Step 29824: {'lr': 0.0004576519299487012, 'samples': 5726208, 'steps': 29823, 'loss/train': 1.5517184734344482}
+08/30/2021 18:29:26 - INFO - __main__ - Step 29825: {'lr': 0.00045764897479895315, 'samples': 5726400, 'steps': 29824, 'loss/train': 1.3328709602355957}
+08/30/2021 18:29:28 - INFO - __main__ - Step 29826: {'lr': 0.0004576460195556418, 'samples': 5726592, 'steps': 29825, 'loss/train': 1.3228015899658203}
+08/30/2021 18:29:28 - INFO - __main__ - Step 29827: {'lr': 0.0004576430642187682, 'samples': 5726784, 'steps': 29826, 'loss/train': 1.466692328453064}
+08/30/2021 18:29:28 - INFO - __main__ - Step 29828: {'lr': 0.00045764010878833396, 'samples': 5726976, 'steps': 29827, 'loss/train': 1.0952364206314087}
+08/30/2021 18:29:29 - INFO - __main__ - Step 29829: {'lr': 0.00045763715326434023, 'samples': 5727168, 'steps': 29828, 'loss/train': 1.3330249786376953}
+08/30/2021 18:29:29 - INFO - __main__ - Step 29830: {'lr': 0.0004576341976467884, 'samples': 5727360, 'steps': 29829, 'loss/train': 1.300980567932129}
+08/30/2021 18:29:29 - INFO - __main__ - Step 29831: {'lr': 0.00045763124193567983, 'samples': 5727552, 'steps': 29830, 'loss/train': 1.2432913780212402}
+08/30/2021 18:29:31 - INFO - __main__ - Step 29832: {'lr': 0.0004576282861310158, 'samples': 5727744, 'steps': 29831, 'loss/train': 1.5756326913833618}
+08/30/2021 18:29:31 - INFO - __main__ - Step 29833: {'lr': 0.00045762533023279773, 'samples': 5727936, 'steps': 29832, 'loss/train': 1.3727688789367676}
+08/30/2021 18:29:32 - INFO - __main__ - Step 29834: {'lr': 0.00045762237424102687, 'samples': 5728128, 'steps': 29833, 'loss/train': 1.3507001399993896}
+08/30/2021 18:29:32 - INFO - __main__ - Step 29835: {'lr': 0.0004576194181557045, 'samples': 5728320, 'steps': 29834, 'loss/train': 1.5258768796920776}
+08/30/2021 18:29:32 - INFO - __main__ - Step 29836: {'lr': 0.00045761646197683216, 'samples': 5728512, 'steps': 29835, 'loss/train': 1.6856153011322021}
+08/30/2021 18:29:34 - INFO - __main__ - Step 29837: {'lr': 0.00045761350570441096, 'samples': 5728704, 'steps': 29836, 'loss/train': 1.1569122076034546}
+08/30/2021 18:29:34 - INFO - __main__ - Step 29838: {'lr': 0.0004576105493384423, 'samples': 5728896, 'steps': 29837, 'loss/train': 1.3239467144012451}
+08/30/2021 18:29:35 - INFO - __main__ - Step 29839: {'lr': 0.00045760759287892755, 'samples': 5729088, 'steps': 29838, 'loss/train': 0.49414050579071045}
+08/30/2021 18:29:35 - INFO - __main__ - Step 29840: {'lr': 0.000457604636325868, 'samples': 5729280, 'steps': 29839, 'loss/train': 1.2491590976715088}
+08/30/2021 18:29:35 - INFO - __main__ - Step 29841: {'lr': 0.00045760167967926504, 'samples': 5729472, 'steps': 29840, 'loss/train': 1.202050805091858}
+08/30/2021 18:29:37 - INFO - __main__ - Step 29842: {'lr': 0.00045759872293911995, 'samples': 5729664, 'steps': 29841, 'loss/train': 1.5716712474822998}
+08/30/2021 18:29:37 - INFO - __main__ - Step 29843: {'lr': 0.00045759576610543407, 'samples': 5729856, 'steps': 29842, 'loss/train': 1.3601289987564087}
+08/30/2021 18:29:38 - INFO - __main__ - Step 29844: {'lr': 0.0004575928091782088, 'samples': 5730048, 'steps': 29843, 'loss/train': 1.9324127435684204}
+08/30/2021 18:29:38 - INFO - __main__ - Step 29845: {'lr': 0.00045758985215744536, 'samples': 5730240, 'steps': 29844, 'loss/train': 1.5306636095046997}
+08/30/2021 18:29:38 - INFO - __main__ - Step 29846: {'lr': 0.0004575868950431452, 'samples': 5730432, 'steps': 29845, 'loss/train': 1.7896960973739624}
+08/30/2021 18:29:40 - INFO - __main__ - Step 29847: {'lr': 0.0004575839378353095, 'samples': 5730624, 'steps': 29846, 'loss/train': 1.4041900634765625}
+08/30/2021 18:29:40 - INFO - __main__ - Step 29848: {'lr': 0.0004575809805339397, 'samples': 5730816, 'steps': 29847, 'loss/train': 0.7040590047836304}
+08/30/2021 18:29:41 - INFO - __main__ - Step 29849: {'lr': 0.0004575780231390371, 'samples': 5731008, 'steps': 29848, 'loss/train': 0.7328097820281982}
+08/30/2021 18:29:41 - INFO - __main__ - Step 29850: {'lr': 0.0004575750656506031, 'samples': 5731200, 'steps': 29849, 'loss/train': 1.475000262260437}
+08/30/2021 18:29:41 - INFO - __main__ - Step 29851: {'lr': 0.00045757210806863895, 'samples': 5731392, 'steps': 29850, 'loss/train': 0.813751757144928}
+08/30/2021 18:29:43 - INFO - __main__ - Step 29852: {'lr': 0.0004575691503931461, 'samples': 5731584, 'steps': 29851, 'loss/train': 1.2440426349639893}
+08/30/2021 18:29:43 - INFO - __main__ - Step 29853: {'lr': 0.00045756619262412565, 'samples': 5731776, 'steps': 29852, 'loss/train': 1.576850175857544}
+08/30/2021 18:29:44 - INFO - __main__ - Step 29854: {'lr': 0.0004575632347615791, 'samples': 5731968, 'steps': 29853, 'loss/train': 1.7223079204559326}
+08/30/2021 18:29:44 - INFO - __main__ - Step 29855: {'lr': 0.0004575602768055078, 'samples': 5732160, 'steps': 29854, 'loss/train': 1.3341399431228638}
+08/30/2021 18:29:44 - INFO - __main__ - Step 29856: {'lr': 0.00045755731875591303, 'samples': 5732352, 'steps': 29855, 'loss/train': 0.9654378294944763}
+08/30/2021 18:29:47 - INFO - __main__ - Step 29857: {'lr': 0.0004575543606127961, 'samples': 5732544, 'steps': 29856, 'loss/train': 1.348114252090454}
+08/30/2021 18:29:47 - INFO - __main__ - Step 29858: {'lr': 0.0004575514023761585, 'samples': 5732736, 'steps': 29857, 'loss/train': 1.888065218925476}
+08/30/2021 18:29:48 - INFO - __main__ - Step 29859: {'lr': 0.00045754844404600136, 'samples': 5732928, 'steps': 29858, 'loss/train': 2.2803468704223633}
+08/30/2021 18:29:48 - INFO - __main__ - Step 29860: {'lr': 0.00045754548562232605, 'samples': 5733120, 'steps': 29859, 'loss/train': 1.4766547679901123}
+08/30/2021 18:29:48 - INFO - __main__ - Step 29861: {'lr': 0.00045754252710513397, 'samples': 5733312, 'steps': 29860, 'loss/train': 1.2961032390594482}
+08/30/2021 18:29:49 - INFO - __main__ - Step 29862: {'lr': 0.00045753956849442647, 'samples': 5733504, 'steps': 29861, 'loss/train': 1.358559250831604}
+08/30/2021 18:29:50 - INFO - __main__ - Step 29863: {'lr': 0.00045753660979020485, 'samples': 5733696, 'steps': 29862, 'loss/train': 1.7077391147613525}
+08/30/2021 18:29:51 - INFO - __main__ - Step 29864: {'lr': 0.0004575336509924704, 'samples': 5733888, 'steps': 29863, 'loss/train': 1.4787989854812622}
+08/30/2021 18:29:51 - INFO - __main__ - Step 29865: {'lr': 0.0004575306921012245, 'samples': 5734080, 'steps': 29864, 'loss/train': 2.005549907684326}
+08/30/2021 18:29:51 - INFO - __main__ - Step 29866: {'lr': 0.00045752773311646846, 'samples': 5734272, 'steps': 29865, 'loss/train': 1.8861044645309448}
+08/30/2021 18:29:52 - INFO - __main__ - Step 29867: {'lr': 0.0004575247740382037, 'samples': 5734464, 'steps': 29866, 'loss/train': 1.520192265510559}
+08/30/2021 18:29:52 - INFO - __main__ - Step 29868: {'lr': 0.0004575218148664314, 'samples': 5734656, 'steps': 29867, 'loss/train': 0.6959830522537231}
+08/30/2021 18:29:54 - INFO - __main__ - Step 29869: {'lr': 0.00045751885560115294, 'samples': 5734848, 'steps': 29868, 'loss/train': 1.4108071327209473}
+08/30/2021 18:29:54 - INFO - __main__ - Step 29870: {'lr': 0.0004575158962423698, 'samples': 5735040, 'steps': 29869, 'loss/train': 2.066143751144409}
+08/30/2021 18:29:55 - INFO - __main__ - Step 29871: {'lr': 0.0004575129367900831, 'samples': 5735232, 'steps': 29870, 'loss/train': 1.474915623664856}
+08/30/2021 18:29:55 - INFO - __main__ - Step 29872: {'lr': 0.0004575099772442943, 'samples': 5735424, 'steps': 29871, 'loss/train': 1.578248143196106}
+08/30/2021 18:29:55 - INFO - __main__ - Step 29873: {'lr': 0.0004575070176050047, 'samples': 5735616, 'steps': 29872, 'loss/train': 0.0819786787033081}
+08/30/2021 18:29:57 - INFO - __main__ - Step 29874: {'lr': 0.00045750405787221566, 'samples': 5735808, 'steps': 29873, 'loss/train': 2.4636528491973877}
+08/30/2021 18:29:57 - INFO - __main__ - Step 29875: {'lr': 0.0004575010980459285, 'samples': 5736000, 'steps': 29874, 'loss/train': 1.9061830043792725}
+08/30/2021 18:29:58 - INFO - __main__ - Step 29876: {'lr': 0.0004574981381261445, 'samples': 5736192, 'steps': 29875, 'loss/train': 1.2713805437088013}
+08/30/2021 18:29:58 - INFO - __main__ - Step 29877: {'lr': 0.0004574951781128651, 'samples': 5736384, 'steps': 29876, 'loss/train': 1.6363621950149536}
+08/30/2021 18:29:59 - INFO - __main__ - Step 29878: {'lr': 0.0004574922180060915, 'samples': 5736576, 'steps': 29877, 'loss/train': 1.4786618947982788}
+08/30/2021 18:30:00 - INFO - __main__ - Step 29879: {'lr': 0.0004574892578058252, 'samples': 5736768, 'steps': 29878, 'loss/train': 1.4830291271209717}
+08/30/2021 18:30:01 - INFO - __main__ - Step 29880: {'lr': 0.0004574862975120674, 'samples': 5736960, 'steps': 29879, 'loss/train': 1.4662595987319946}
+08/30/2021 18:30:01 - INFO - __main__ - Step 29881: {'lr': 0.0004574833371248195, 'samples': 5737152, 'steps': 29880, 'loss/train': 2.465188503265381}
+08/30/2021 18:30:01 - INFO - __main__ - Step 29882: {'lr': 0.00045748037664408275, 'samples': 5737344, 'steps': 29881, 'loss/train': 1.308503270149231}
+08/30/2021 18:30:02 - INFO - __main__ - Step 29883: {'lr': 0.0004574774160698586, 'samples': 5737536, 'steps': 29882, 'loss/train': 0.6008021831512451}
+08/30/2021 18:30:03 - INFO - __main__ - Step 29884: {'lr': 0.00045747445540214826, 'samples': 5737728, 'steps': 29883, 'loss/train': 1.2538586854934692}
+08/30/2021 18:30:04 - INFO - __main__ - Step 29885: {'lr': 0.00045747149464095324, 'samples': 5737920, 'steps': 29884, 'loss/train': 1.5160785913467407}
+08/30/2021 18:30:04 - INFO - __main__ - Step 29886: {'lr': 0.00045746853378627467, 'samples': 5738112, 'steps': 29885, 'loss/train': 1.453216791152954}
+08/30/2021 18:30:04 - INFO - __main__ - Step 29887: {'lr': 0.000457465572838114, 'samples': 5738304, 'steps': 29886, 'loss/train': 1.4027401208877563}
+08/30/2021 18:30:05 - INFO - __main__ - Step 29888: {'lr': 0.0004574626117964726, 'samples': 5738496, 'steps': 29887, 'loss/train': 1.1967679262161255}
+08/30/2021 18:30:05 - INFO - __main__ - Step 29889: {'lr': 0.00045745965066135163, 'samples': 5738688, 'steps': 29888, 'loss/train': 1.338134527206421}
+08/30/2021 18:30:07 - INFO - __main__ - Step 29890: {'lr': 0.00045745668943275266, 'samples': 5738880, 'steps': 29889, 'loss/train': 1.9230146408081055}
+08/30/2021 18:30:07 - INFO - __main__ - Step 29891: {'lr': 0.00045745372811067687, 'samples': 5739072, 'steps': 29890, 'loss/train': 0.5520074963569641}
+08/30/2021 18:30:07 - INFO - __main__ - Step 29892: {'lr': 0.00045745076669512566, 'samples': 5739264, 'steps': 29891, 'loss/train': 1.6947280168533325}
+08/30/2021 18:30:08 - INFO - __main__ - Step 29893: {'lr': 0.0004574478051861003, 'samples': 5739456, 'steps': 29892, 'loss/train': 1.720933198928833}
+08/30/2021 18:30:08 - INFO - __main__ - Step 29894: {'lr': 0.00045744484358360216, 'samples': 5739648, 'steps': 29893, 'loss/train': 1.9582308530807495}
+08/30/2021 18:30:09 - INFO - __main__ - Step 29895: {'lr': 0.0004574418818876326, 'samples': 5739840, 'steps': 29894, 'loss/train': 0.9471269845962524}
+08/30/2021 18:30:10 - INFO - __main__ - Step 29896: {'lr': 0.0004574389200981929, 'samples': 5740032, 'steps': 29895, 'loss/train': 1.3663339614868164}
+08/30/2021 18:30:10 - INFO - __main__ - Step 29897: {'lr': 0.00045743595821528437, 'samples': 5740224, 'steps': 29896, 'loss/train': 1.9239739179611206}
+08/30/2021 18:30:11 - INFO - __main__ - Step 29898: {'lr': 0.0004574329962389085, 'samples': 5740416, 'steps': 29897, 'loss/train': 1.5327961444854736}
+08/30/2021 18:30:11 - INFO - __main__ - Step 29899: {'lr': 0.0004574300341690665, 'samples': 5740608, 'steps': 29898, 'loss/train': 1.6033366918563843}
+08/30/2021 18:30:12 - INFO - __main__ - Step 29900: {'lr': 0.00045742707200575975, 'samples': 5740800, 'steps': 29899, 'loss/train': 1.089516282081604}
+08/30/2021 18:30:13 - INFO - __main__ - Step 29901: {'lr': 0.00045742410974898947, 'samples': 5740992, 'steps': 29900, 'loss/train': 1.4063479900360107}
+08/30/2021 18:30:13 - INFO - __main__ - Step 29902: {'lr': 0.0004574211473987571, 'samples': 5741184, 'steps': 29901, 'loss/train': 1.282423496246338}
+08/30/2021 18:30:13 - INFO - __main__ - Step 29903: {'lr': 0.00045741818495506403, 'samples': 5741376, 'steps': 29902, 'loss/train': 1.4164947271347046}
+08/30/2021 18:30:14 - INFO - __main__ - Step 29904: {'lr': 0.0004574152224179115, 'samples': 5741568, 'steps': 29903, 'loss/train': 1.2825496196746826}
+08/30/2021 18:30:15 - INFO - __main__ - Step 29905: {'lr': 0.0004574122597873008, 'samples': 5741760, 'steps': 29904, 'loss/train': 1.7941032648086548}
+08/30/2021 18:30:16 - INFO - __main__ - Step 29906: {'lr': 0.0004574092970632335, 'samples': 5741952, 'steps': 29905, 'loss/train': 1.6563183069229126}
+08/30/2021 18:30:16 - INFO - __main__ - Step 29907: {'lr': 0.00045740633424571064, 'samples': 5742144, 'steps': 29906, 'loss/train': 0.6336389183998108}
+08/30/2021 18:30:17 - INFO - __main__ - Step 29908: {'lr': 0.00045740337133473374, 'samples': 5742336, 'steps': 29907, 'loss/train': 1.3014731407165527}
+08/30/2021 18:30:17 - INFO - __main__ - Step 29909: {'lr': 0.00045740040833030404, 'samples': 5742528, 'steps': 29908, 'loss/train': 1.1213966608047485}
+08/30/2021 18:30:20 - INFO - __main__ - Step 29910: {'lr': 0.00045739744523242294, 'samples': 5742720, 'steps': 29909, 'loss/train': 1.2861236333847046}
+08/30/2021 18:30:21 - INFO - __main__ - Step 29911: {'lr': 0.0004573944820410918, 'samples': 5742912, 'steps': 29910, 'loss/train': 1.6103925704956055}
+08/30/2021 18:30:21 - INFO - __main__ - Step 29912: {'lr': 0.0004573915187563118, 'samples': 5743104, 'steps': 29911, 'loss/train': 1.726737141609192}
+08/30/2021 18:30:21 - INFO - __main__ - Step 29913: {'lr': 0.00045738855537808443, 'samples': 5743296, 'steps': 29912, 'loss/train': 1.719698190689087}
+08/30/2021 18:30:22 - INFO - __main__ - Step 29914: {'lr': 0.000457385591906411, 'samples': 5743488, 'steps': 29913, 'loss/train': 1.1147890090942383}
+08/30/2021 18:30:22 - INFO - __main__ - Step 29915: {'lr': 0.00045738262834129283, 'samples': 5743680, 'steps': 29914, 'loss/train': 1.87599515914917}
+08/30/2021 18:30:22 - INFO - __main__ - Step 29916: {'lr': 0.0004573796646827312, 'samples': 5743872, 'steps': 29915, 'loss/train': 1.8886315822601318}
+08/30/2021 18:30:23 - INFO - __main__ - Step 29917: {'lr': 0.0004573767009307276, 'samples': 5744064, 'steps': 29916, 'loss/train': 1.277214527130127}
+08/30/2021 18:30:24 - INFO - __main__ - Step 29918: {'lr': 0.0004573737370852831, 'samples': 5744256, 'steps': 29917, 'loss/train': 2.1520116329193115}
+08/30/2021 18:30:25 - INFO - __main__ - Step 29919: {'lr': 0.0004573707731463993, 'samples': 5744448, 'steps': 29918, 'loss/train': 1.8385660648345947}
+08/30/2021 18:30:25 - INFO - __main__ - Step 29920: {'lr': 0.00045736780911407736, 'samples': 5744640, 'steps': 29919, 'loss/train': 1.6175665855407715}
+08/30/2021 18:30:25 - INFO - __main__ - Step 29921: {'lr': 0.00045736484498831877, 'samples': 5744832, 'steps': 29920, 'loss/train': 1.7936135530471802}
+08/30/2021 18:30:26 - INFO - __main__ - Step 29922: {'lr': 0.0004573618807691248, 'samples': 5745024, 'steps': 29921, 'loss/train': 1.5341824293136597}
+08/30/2021 18:30:27 - INFO - __main__ - Step 29923: {'lr': 0.0004573589164564966, 'samples': 5745216, 'steps': 29922, 'loss/train': 1.5022945404052734}
+08/30/2021 18:30:28 - INFO - __main__ - Step 29924: {'lr': 0.00045735595205043583, 'samples': 5745408, 'steps': 29923, 'loss/train': 1.0516347885131836}
+08/30/2021 18:30:28 - INFO - __main__ - Step 29925: {'lr': 0.00045735298755094364, 'samples': 5745600, 'steps': 29924, 'loss/train': 1.4194567203521729}
+08/30/2021 18:30:29 - INFO - __main__ - Step 29926: {'lr': 0.00045735002295802137, 'samples': 5745792, 'steps': 29925, 'loss/train': 1.909565806388855}
+08/30/2021 18:30:29 - INFO - __main__ - Step 29927: {'lr': 0.00045734705827167035, 'samples': 5745984, 'steps': 29926, 'loss/train': 1.2392679452896118}
+08/30/2021 18:30:31 - INFO - __main__ - Step 29928: {'lr': 0.000457344093491892, 'samples': 5746176, 'steps': 29927, 'loss/train': 0.4013739824295044}
+08/30/2021 18:30:31 - INFO - __main__ - Step 29929: {'lr': 0.00045734112861868753, 'samples': 5746368, 'steps': 29928, 'loss/train': 1.5148979425430298}
+08/30/2021 18:30:32 - INFO - __main__ - Step 29930: {'lr': 0.0004573381636520584, 'samples': 5746560, 'steps': 29929, 'loss/train': 0.2414027750492096}
+08/30/2021 18:30:32 - INFO - __main__ - Step 29931: {'lr': 0.0004573351985920059, 'samples': 5746752, 'steps': 29930, 'loss/train': 0.13806553184986115}
+08/30/2021 18:30:32 - INFO - __main__ - Step 29932: {'lr': 0.0004573322334385314, 'samples': 5746944, 'steps': 29931, 'loss/train': 0.06139226257801056}
+08/30/2021 18:30:33 - INFO - __main__ - Step 29933: {'lr': 0.0004573292681916361, 'samples': 5747136, 'steps': 29932, 'loss/train': 2.4596898555755615}
+08/30/2021 18:30:34 - INFO - __main__ - Step 29934: {'lr': 0.0004573263028513214, 'samples': 5747328, 'steps': 29933, 'loss/train': 1.724640130996704}
+08/30/2021 18:30:35 - INFO - __main__ - Step 29935: {'lr': 0.0004573233374175888, 'samples': 5747520, 'steps': 29934, 'loss/train': 1.6728287935256958}
+08/30/2021 18:30:35 - INFO - __main__ - Step 29936: {'lr': 0.0004573203718904394, 'samples': 5747712, 'steps': 29935, 'loss/train': 1.489703893661499}
+08/30/2021 18:30:36 - INFO - __main__ - Step 29937: {'lr': 0.00045731740626987473, 'samples': 5747904, 'steps': 29936, 'loss/train': 1.1529443264007568}
+08/30/2021 18:30:36 - INFO - __main__ - Step 29938: {'lr': 0.00045731444055589597, 'samples': 5748096, 'steps': 29937, 'loss/train': 1.6943330764770508}
+08/30/2021 18:30:36 - INFO - __main__ - Step 29939: {'lr': 0.0004573114747485045, 'samples': 5748288, 'steps': 29938, 'loss/train': 1.0642552375793457}
+08/30/2021 18:30:38 - INFO - __main__ - Step 29940: {'lr': 0.0004573085088477017, 'samples': 5748480, 'steps': 29939, 'loss/train': 1.3704547882080078}
+08/30/2021 18:30:38 - INFO - __main__ - Step 29941: {'lr': 0.0004573055428534889, 'samples': 5748672, 'steps': 29940, 'loss/train': 1.265084981918335}
+08/30/2021 18:30:39 - INFO - __main__ - Step 29942: {'lr': 0.00045730257676586747, 'samples': 5748864, 'steps': 29941, 'loss/train': 1.354390025138855}
+08/30/2021 18:30:39 - INFO - __main__ - Step 29943: {'lr': 0.0004572996105848386, 'samples': 5749056, 'steps': 29942, 'loss/train': 1.4503631591796875}
+08/30/2021 18:30:39 - INFO - __main__ - Step 29944: {'lr': 0.0004572966443104038, 'samples': 5749248, 'steps': 29943, 'loss/train': 1.7153041362762451}
+08/30/2021 18:30:41 - INFO - __main__ - Step 29945: {'lr': 0.00045729367794256434, 'samples': 5749440, 'steps': 29944, 'loss/train': 0.713683009147644}
+08/30/2021 18:30:41 - INFO - __main__ - Step 29946: {'lr': 0.0004572907114813215, 'samples': 5749632, 'steps': 29945, 'loss/train': 1.6766033172607422}
+08/30/2021 18:30:42 - INFO - __main__ - Step 29947: {'lr': 0.0004572877449266767, 'samples': 5749824, 'steps': 29946, 'loss/train': 1.700985074043274}
+08/30/2021 18:30:42 - INFO - __main__ - Step 29948: {'lr': 0.0004572847782786312, 'samples': 5750016, 'steps': 29947, 'loss/train': 1.3387649059295654}
+08/30/2021 18:30:42 - INFO - __main__ - Step 29949: {'lr': 0.0004572818115371864, 'samples': 5750208, 'steps': 29948, 'loss/train': 1.493436574935913}
+08/30/2021 18:30:44 - INFO - __main__ - Step 29950: {'lr': 0.0004572788447023436, 'samples': 5750400, 'steps': 29949, 'loss/train': 1.8604241609573364}
+08/30/2021 18:30:44 - INFO - __main__ - Step 29951: {'lr': 0.00045727587777410415, 'samples': 5750592, 'steps': 29950, 'loss/train': 1.41011381149292}
+08/30/2021 18:30:45 - INFO - __main__ - Step 29952: {'lr': 0.00045727291075246937, 'samples': 5750784, 'steps': 29951, 'loss/train': 1.568453073501587}
+08/30/2021 18:30:45 - INFO - __main__ - Step 29953: {'lr': 0.0004572699436374407, 'samples': 5750976, 'steps': 29952, 'loss/train': 2.2069711685180664}
+08/30/2021 18:30:45 - INFO - __main__ - Step 29954: {'lr': 0.00045726697642901925, 'samples': 5751168, 'steps': 29953, 'loss/train': 0.19367405772209167}
+08/30/2021 18:30:47 - INFO - __main__ - Step 29955: {'lr': 0.0004572640091272066, 'samples': 5751360, 'steps': 29954, 'loss/train': 1.5525058507919312}
+08/30/2021 18:30:48 - INFO - __main__ - Step 29956: {'lr': 0.000457261041732004, 'samples': 5751552, 'steps': 29955, 'loss/train': 1.349680781364441}
+08/30/2021 18:30:48 - INFO - __main__ - Step 29957: {'lr': 0.0004572580742434127, 'samples': 5751744, 'steps': 29956, 'loss/train': 1.949102759361267}
+08/30/2021 18:30:48 - INFO - __main__ - Step 29958: {'lr': 0.00045725510666143424, 'samples': 5751936, 'steps': 29957, 'loss/train': 1.4559065103530884}
+08/30/2021 18:30:49 - INFO - __main__ - Step 29959: {'lr': 0.0004572521389860697, 'samples': 5752128, 'steps': 29958, 'loss/train': 1.6270986795425415}
+08/30/2021 18:30:50 - INFO - __main__ - Step 29960: {'lr': 0.00045724917121732055, 'samples': 5752320, 'steps': 29959, 'loss/train': 1.2723875045776367}
+08/30/2021 18:30:51 - INFO - __main__ - Step 29961: {'lr': 0.0004572462033551882, 'samples': 5752512, 'steps': 29960, 'loss/train': 2.9785878658294678}
+08/30/2021 18:30:51 - INFO - __main__ - Step 29962: {'lr': 0.00045724323539967385, 'samples': 5752704, 'steps': 29961, 'loss/train': 1.342309832572937}
+08/30/2021 18:30:51 - INFO - __main__ - Step 29963: {'lr': 0.00045724026735077886, 'samples': 5752896, 'steps': 29962, 'loss/train': 1.3100159168243408}
+08/30/2021 18:30:52 - INFO - __main__ - Step 29964: {'lr': 0.00045723729920850464, 'samples': 5753088, 'steps': 29963, 'loss/train': 1.652289628982544}
+08/30/2021 18:30:54 - INFO - __main__ - Step 29965: {'lr': 0.00045723433097285247, 'samples': 5753280, 'steps': 29964, 'loss/train': 1.4638392925262451}
+08/30/2021 18:30:55 - INFO - __main__ - Step 29966: {'lr': 0.0004572313626438238, 'samples': 5753472, 'steps': 29965, 'loss/train': 1.4360930919647217}
+08/30/2021 18:30:55 - INFO - __main__ - Step 29967: {'lr': 0.00045722839422141984, 'samples': 5753664, 'steps': 29966, 'loss/train': 1.658735990524292}
+08/30/2021 18:30:55 - INFO - __main__ - Step 29968: {'lr': 0.000457225425705642, 'samples': 5753856, 'steps': 29967, 'loss/train': 1.8419651985168457}
+08/30/2021 18:30:56 - INFO - __main__ - Step 29969: {'lr': 0.0004572224570964915, 'samples': 5754048, 'steps': 29968, 'loss/train': 1.4746346473693848}
+08/30/2021 18:30:56 - INFO - __main__ - Step 29970: {'lr': 0.0004572194883939697, 'samples': 5754240, 'steps': 29969, 'loss/train': 0.20525215566158295}
+08/30/2021 18:30:58 - INFO - __main__ - Step 29971: {'lr': 0.0004572165195980781, 'samples': 5754432, 'steps': 29970, 'loss/train': 1.2932289838790894}
+08/30/2021 18:30:59 - INFO - __main__ - Step 29972: {'lr': 0.0004572135507088179, 'samples': 5754624, 'steps': 29971, 'loss/train': 1.5811430215835571}
+08/30/2021 18:30:59 - INFO - __main__ - Step 29973: {'lr': 0.00045721058172619043, 'samples': 5754816, 'steps': 29972, 'loss/train': 0.12158104032278061}
+08/30/2021 18:30:59 - INFO - __main__ - Step 29974: {'lr': 0.0004572076126501972, 'samples': 5755008, 'steps': 29973, 'loss/train': 1.4291597604751587}
+08/30/2021 18:31:00 - INFO - __main__ - Step 29975: {'lr': 0.00045720464348083937, 'samples': 5755200, 'steps': 29974, 'loss/train': 1.1311383247375488}
+08/30/2021 18:31:00 - INFO - __main__ - Step 29976: {'lr': 0.0004572016742181182, 'samples': 5755392, 'steps': 29975, 'loss/train': 2.0455069541931152}
+08/30/2021 18:31:02 - INFO - __main__ - Step 29977: {'lr': 0.0004571987048620353, 'samples': 5755584, 'steps': 29976, 'loss/train': 1.865699052810669}
+08/30/2021 18:31:02 - INFO - __main__ - Step 29978: {'lr': 0.0004571957354125918, 'samples': 5755776, 'steps': 29977, 'loss/train': 1.4434974193572998}
+08/30/2021 18:31:03 - INFO - __main__ - Step 29979: {'lr': 0.00045719276586978907, 'samples': 5755968, 'steps': 29978, 'loss/train': 1.4251376390457153}
+08/30/2021 18:31:03 - INFO - __main__ - Step 29980: {'lr': 0.00045718979623362855, 'samples': 5756160, 'steps': 29979, 'loss/train': 2.0122334957122803}
+08/30/2021 18:31:04 - INFO - __main__ - Step 29981: {'lr': 0.00045718682650411146, 'samples': 5756352, 'steps': 29980, 'loss/train': 1.199205994606018}
+08/30/2021 18:31:05 - INFO - __main__ - Step 29982: {'lr': 0.0004571838566812392, 'samples': 5756544, 'steps': 29981, 'loss/train': 0.8048202991485596}
+08/30/2021 18:31:05 - INFO - __main__ - Step 29983: {'lr': 0.00045718088676501305, 'samples': 5756736, 'steps': 29982, 'loss/train': 1.4998470544815063}
+08/30/2021 18:31:06 - INFO - __main__ - Step 29984: {'lr': 0.0004571779167554344, 'samples': 5756928, 'steps': 29983, 'loss/train': 1.5507581233978271}
+08/30/2021 18:31:06 - INFO - __main__ - Step 29985: {'lr': 0.0004571749466525046, 'samples': 5757120, 'steps': 29984, 'loss/train': 0.9107785224914551}
+08/30/2021 18:31:06 - INFO - __main__ - Step 29986: {'lr': 0.000457171976456225, 'samples': 5757312, 'steps': 29985, 'loss/train': 1.2444286346435547}
+08/30/2021 18:31:08 - INFO - __main__ - Step 29987: {'lr': 0.00045716900616659686, 'samples': 5757504, 'steps': 29986, 'loss/train': 1.2106409072875977}
+08/30/2021 18:31:08 - INFO - __main__ - Step 29988: {'lr': 0.00045716603578362157, 'samples': 5757696, 'steps': 29987, 'loss/train': 1.3851398229599}
+08/30/2021 18:31:09 - INFO - __main__ - Step 29989: {'lr': 0.00045716306530730043, 'samples': 5757888, 'steps': 29988, 'loss/train': 1.0019110441207886}
+08/30/2021 18:31:09 - INFO - __main__ - Step 29990: {'lr': 0.00045716009473763486, 'samples': 5758080, 'steps': 29989, 'loss/train': 1.4916727542877197}
+08/30/2021 18:31:09 - INFO - __main__ - Step 29991: {'lr': 0.0004571571240746262, 'samples': 5758272, 'steps': 29990, 'loss/train': 1.093345046043396}
+08/30/2021 18:31:10 - INFO - __main__ - Step 29992: {'lr': 0.00045715415331827564, 'samples': 5758464, 'steps': 29991, 'loss/train': 1.9349569082260132}
+08/30/2021 18:31:11 - INFO - __main__ - Step 29993: {'lr': 0.00045715118246858466, 'samples': 5758656, 'steps': 29992, 'loss/train': 1.2344725131988525}
+08/30/2021 18:31:12 - INFO - __main__ - Step 29994: {'lr': 0.0004571482115255545, 'samples': 5758848, 'steps': 29993, 'loss/train': 2.0704667568206787}
+08/30/2021 18:31:12 - INFO - __main__ - Step 29995: {'lr': 0.0004571452404891866, 'samples': 5759040, 'steps': 29994, 'loss/train': 1.8195703029632568}
+08/30/2021 18:31:12 - INFO - __main__ - Step 29996: {'lr': 0.0004571422693594822, 'samples': 5759232, 'steps': 29995, 'loss/train': 1.6077555418014526}
+08/30/2021 18:31:14 - INFO - __main__ - Step 29997: {'lr': 0.00045713929813644274, 'samples': 5759424, 'steps': 29996, 'loss/train': 2.4970226287841797}
+08/30/2021 18:31:14 - INFO - __main__ - Step 29998: {'lr': 0.0004571363268200695, 'samples': 5759616, 'steps': 29997, 'loss/train': 1.3227806091308594}
+08/30/2021 18:31:15 - INFO - __main__ - Step 29999: {'lr': 0.0004571333554103638, 'samples': 5759808, 'steps': 29998, 'loss/train': 1.6352428197860718}
+08/30/2021 18:31:15 - INFO - __main__ - Step 30000: {'lr': 0.0004571303839073271, 'samples': 5760000, 'steps': 29999, 'loss/train': 1.503125548362732}
+08/30/2021 18:31:15 - INFO - __main__ - Evaluating model checkpoint
+08/30/2021 18:40:00 - INFO - __main__ - Step 30000: {'loss/eval': 1.3865768909454346, 'perplexity': 4.0011305809021}
+08/30/2021 18:40:00 - INFO - __main__ - Saving model checkpoint
+08/30/2021 18:40:12 - WARNING - huggingface_hub.repository - Adding files tracked by Git LFS: ['wandb/run-20210830_131354-2654p8r7/logs/debug-internal.log', 'wandb/run-20210830_131354-2654p8r7/run-2654p8r7.wandb']. This may take a bit of time if the files are large.