diff --git "a/log/debug_0.log" "b/log/debug_0.log"
--- "a/log/debug_0.log"
+++ "b/log/debug_0.log"
@@ -17548,3 +17548,2506 @@ Use FP16 precision: False
 12/24/2021 22:52:30 - INFO - codeparrot_training - Step 14999: {'lr': 0.00039851679344352385, 'samples': 7680000, 'steps': 14999, 'batch_loss/train': 0.8290996924042702}
 12/24/2021 22:52:30 - INFO - codeparrot_training - Evaluating and saving model checkpoint
 12/24/2021 22:55:51 - INFO - codeparrot_training - Step 15000: {'loss/eval': 0.8110089898109436, 'perplexity': 2.2501771450042725}
+12/24/2021 22:56:09 - WARNING - huggingface_hub.repository - Several commits (4) will be pushed upstream.
+12/24/2021 22:56:25 - INFO - codeparrot_training - Step 15000: {'lr': 0.0003985041130398145, 'samples': 7680512, 'steps': 15000, 'batch_loss/train': 0.7323928384575993}
+12/24/2021 22:56:36 - INFO - codeparrot_training - Step 15001: {'lr': 0.00039849143204570884, 'samples': 7681024, 'steps': 15001, 'batch_loss/train': 0.7468573972582817}
+12/24/2021 22:56:46 - INFO - codeparrot_training - Step 15002: {'lr': 0.0003984787504612574, 'samples': 7681536, 'steps': 15002, 'batch_loss/train': 0.8788123605772853}
+12/24/2021 22:56:59 - INFO - codeparrot_training - Step 15003: {'lr': 0.00039846606828651033, 'samples': 7682048, 'steps': 15003, 'batch_loss/train': 0.7611135505139828}
+12/24/2021 22:57:10 - INFO - codeparrot_training - Step 15004: {'lr': 0.0003984533855215184, 'samples': 7682560, 'steps': 15004, 'batch_loss/train': 0.7579456567764282}
+12/24/2021 22:57:20 - INFO - codeparrot_training - Step 15005: {'lr': 0.00039844070216633177, 'samples': 7683072, 'steps': 15005, 'batch_loss/train': 1.1400523371994495}
+12/24/2021 22:57:31 - INFO - codeparrot_training - Step 15006: {'lr': 0.0003984280182210009, 'samples': 7683584, 'steps': 15006, 'batch_loss/train': 0.9818686752114445}
+12/24/2021 22:57:43 - INFO - codeparrot_training - Step 15007: {'lr': 0.0003984153336855764, 'samples': 7684096, 'steps': 15007, 'batch_loss/train': 0.8182533206418157}
+12/24/2021 22:57:53 - INFO - codeparrot_training - Step 15008: {'lr': 0.00039840264856010857, 'samples': 7684608, 'steps': 15008, 'batch_loss/train': 0.8189091105014086}
+12/24/2021 22:58:04 - INFO - codeparrot_training - Step 15009: {'lr': 0.0003983899628446478, 'samples': 7685120, 'steps': 15009, 'batch_loss/train': 0.856389774940908}
+12/24/2021 22:58:16 - INFO - codeparrot_training - Step 15010: {'lr': 0.0003983772765392446, 'samples': 7685632, 'steps': 15010, 'batch_loss/train': 0.8704529319657013}
+12/24/2021 22:58:27 - INFO - codeparrot_training - Step 15011: {'lr': 0.0003983645896439493, 'samples': 7686144, 'steps': 15011, 'batch_loss/train': 0.7813219825038686}
+12/24/2021 22:58:37 - INFO - codeparrot_training - Step 15012: {'lr': 0.0003983519021588125, 'samples': 7686656, 'steps': 15012, 'batch_loss/train': 0.7942292508669198}
+12/24/2021 22:58:51 - INFO - codeparrot_training - Step 15013: {'lr': 0.0003983392140838845, 'samples': 7687168, 'steps': 15013, 'batch_loss/train': 0.8168053589761257}
+12/24/2021 22:59:02 - INFO - codeparrot_training - Step 15014: {'lr': 0.0003983265254192158, 'samples': 7687680, 'steps': 15014, 'batch_loss/train': 0.8579426174983382}
+12/24/2021 22:59:12 - INFO - codeparrot_training - Step 15015: {'lr': 0.00039831383616485683, 'samples': 7688192, 'steps': 15015, 'batch_loss/train': 0.8076726503204554}
+12/24/2021 22:59:23 - INFO - codeparrot_training - Step 15016: {'lr': 0.000398301146320858, 'samples': 7688704, 'steps': 15016, 'batch_loss/train': 0.7976699406281114}
+12/24/2021 22:59:35 - INFO - codeparrot_training - Step 15017: {'lr': 0.00039828845588726994, 'samples': 7689216, 'steps': 15017, 'batch_loss/train': 0.9528036992996931}
+12/24/2021 22:59:46 - INFO - codeparrot_training - Step 15018: {'lr': 0.00039827576486414285, 'samples': 7689728, 'steps': 15018, 'batch_loss/train': 0.7632062267512083}
+12/24/2021 22:59:56 - INFO - codeparrot_training - Step 15019: {'lr': 0.00039826307325152745, 'samples': 7690240, 'steps': 15019, 'batch_loss/train': 0.7892520194873214}
+12/24/2021 23:00:08 - INFO - codeparrot_training - Step 15020: {'lr': 0.00039825038104947393, 'samples': 7690752, 'steps': 15020, 'batch_loss/train': 0.869445831514895}
+12/24/2021 23:00:19 - INFO - codeparrot_training - Step 15021: {'lr': 0.00039823768825803294, 'samples': 7691264, 'steps': 15021, 'batch_loss/train': 0.8454812597483397}
+12/24/2021 23:00:29 - INFO - codeparrot_training - Step 15022: {'lr': 0.0003982249948772548, 'samples': 7691776, 'steps': 15022, 'batch_loss/train': 0.8623221954330802}
+12/24/2021 23:00:43 - INFO - codeparrot_training - Step 15023: {'lr': 0.00039821230090719006, 'samples': 7692288, 'steps': 15023, 'batch_loss/train': 0.87711819447577}
+12/24/2021 23:00:54 - INFO - codeparrot_training - Step 15024: {'lr': 0.00039819960634788923, 'samples': 7692800, 'steps': 15024, 'batch_loss/train': 0.7335321521386504}
+12/24/2021 23:01:05 - INFO - codeparrot_training - Step 15025: {'lr': 0.0003981869111994027, 'samples': 7693312, 'steps': 15025, 'batch_loss/train': 0.810753146186471}
+12/24/2021 23:01:15 - INFO - codeparrot_training - Step 15026: {'lr': 0.00039817421546178096, 'samples': 7693824, 'steps': 15026, 'batch_loss/train': 0.7496292444411665}
+12/24/2021 23:01:27 - INFO - codeparrot_training - Step 15027: {'lr': 0.00039816151913507446, 'samples': 7694336, 'steps': 15027, 'batch_loss/train': 0.7806814622599632}
+12/24/2021 23:01:38 - INFO - codeparrot_training - Step 15028: {'lr': 0.00039814882221933377, 'samples': 7694848, 'steps': 15028, 'batch_loss/train': 0.8405343350023031}
+12/24/2021 23:01:49 - INFO - codeparrot_training - Step 15029: {'lr': 0.00039813612471460924, 'samples': 7695360, 'steps': 15029, 'batch_loss/train': 0.816377985291183}
+12/24/2021 23:02:02 - INFO - codeparrot_training - Step 15030: {'lr': 0.00039812342662095147, 'samples': 7695872, 'steps': 15030, 'batch_loss/train': 0.8074464499950409}
+12/24/2021 23:02:13 - INFO - codeparrot_training - Step 15031: {'lr': 0.0003981107279384108, 'samples': 7696384, 'steps': 15031, 'batch_loss/train': 0.9141397182829678}
+12/24/2021 23:02:24 - INFO - codeparrot_training - Step 15032: {'lr': 0.0003980980286670378, 'samples': 7696896, 'steps': 15032, 'batch_loss/train': 0.8522725664079189}
+12/24/2021 23:02:36 - INFO - codeparrot_training - Step 15033: {'lr': 0.0003980853288068831, 'samples': 7697408, 'steps': 15033, 'batch_loss/train': 0.806667416356504}
+12/24/2021 23:02:46 - INFO - codeparrot_training - Step 15034: {'lr': 0.00039807262835799695, 'samples': 7697920, 'steps': 15034, 'batch_loss/train': 0.8526432104408741}
+12/24/2021 23:02:57 - INFO - codeparrot_training - Step 15035: {'lr': 0.00039805992732042995, 'samples': 7698432, 'steps': 15035, 'batch_loss/train': 0.7657937714830041}
+12/24/2021 23:03:07 - INFO - codeparrot_training - Step 15036: {'lr': 0.00039804722569423257, 'samples': 7698944, 'steps': 15036, 'batch_loss/train': 0.6937014763243496}
+12/24/2021 23:03:20 - INFO - codeparrot_training - Step 15037: {'lr': 0.0003980345234794553, 'samples': 7699456, 'steps': 15037, 'batch_loss/train': 0.7814481174573302}
+12/24/2021 23:03:31 - INFO - codeparrot_training - Step 15038: {'lr': 0.00039802182067614865, 'samples': 7699968, 'steps': 15038, 'batch_loss/train': 0.8368531824089587}
+12/24/2021 23:03:41 - INFO - codeparrot_training - Step 15039: {'lr': 0.00039800911728436316, 'samples': 7700480, 'steps': 15039, 'batch_loss/train': 0.7595681836828589}
+12/24/2021 23:03:55 - INFO - codeparrot_training - Step 15040: {'lr': 0.0003979964133041494, 'samples': 7700992, 'steps': 15040, 'batch_loss/train': 0.9541434911079705}
+12/24/2021 23:04:06 - INFO - codeparrot_training - Step 15041: {'lr': 0.0003979837087355577, 'samples': 7701504, 'steps': 15041, 'batch_loss/train': 0.7991894581355155}
+12/24/2021 23:04:16 - INFO - codeparrot_training - Step 15042: {'lr': 0.0003979710035786386, 'samples': 7702016, 'steps': 15042, 'batch_loss/train': 0.8787587517872453}
+12/24/2021 23:04:28 - INFO - codeparrot_training - Step 15043: {'lr': 0.0003979582978334427, 'samples': 7702528, 'steps': 15043, 'batch_loss/train': 0.7576564309420064}
+12/24/2021 23:04:39 - INFO - codeparrot_training - Step 15044: {'lr': 0.00039794559150002054, 'samples': 7703040, 'steps': 15044, 'batch_loss/train': 0.7905866168439388}
+12/24/2021 23:04:50 - INFO - codeparrot_training - Step 15045: {'lr': 0.0003979328845784225, 'samples': 7703552, 'steps': 15045, 'batch_loss/train': 0.822965175844729}
+12/24/2021 23:05:00 - INFO - codeparrot_training - Step 15046: {'lr': 0.0003979201770686991, 'samples': 7704064, 'steps': 15046, 'batch_loss/train': 0.7433033818379045}
+12/24/2021 23:05:12 - INFO - codeparrot_training - Step 15047: {'lr': 0.0003979074689709011, 'samples': 7704576, 'steps': 15047, 'batch_loss/train': 0.7430890733376145}
+12/24/2021 23:05:23 - INFO - codeparrot_training - Step 15048: {'lr': 0.00039789476028507875, 'samples': 7705088, 'steps': 15048, 'batch_loss/train': 0.9044713494367898}
+12/24/2021 23:05:34 - INFO - codeparrot_training - Step 15049: {'lr': 0.0003978820510112827, 'samples': 7705600, 'steps': 15049, 'batch_loss/train': 1.03290344029665}
+12/24/2021 23:05:46 - INFO - codeparrot_training - Step 15050: {'lr': 0.00039786934114956343, 'samples': 7706112, 'steps': 15050, 'batch_loss/train': 0.8341285428032279}
+12/24/2021 23:05:56 - INFO - codeparrot_training - Step 15051: {'lr': 0.00039785663069997145, 'samples': 7706624, 'steps': 15051, 'batch_loss/train': 0.8590572364628315}
+12/24/2021 23:06:07 - INFO - codeparrot_training - Step 15052: {'lr': 0.0003978439196625574, 'samples': 7707136, 'steps': 15052, 'batch_loss/train': 0.7257058883551508}
+12/24/2021 23:06:21 - INFO - codeparrot_training - Step 15053: {'lr': 0.00039783120803737175, 'samples': 7707648, 'steps': 15053, 'batch_loss/train': 0.7481983585748821}
+12/24/2021 23:06:31 - INFO - codeparrot_training - Step 15054: {'lr': 0.00039781849582446507, 'samples': 7708160, 'steps': 15054, 'batch_loss/train': 0.8697206219658256}
+12/24/2021 23:06:42 - INFO - codeparrot_training - Step 15055: {'lr': 0.0003978057830238878, 'samples': 7708672, 'steps': 15055, 'batch_loss/train': 0.7952612451044843}
+12/24/2021 23:06:53 - INFO - codeparrot_training - Step 15056: {'lr': 0.00039779306963569057, 'samples': 7709184, 'steps': 15056, 'batch_loss/train': 0.8505194690078497}
+12/24/2021 23:07:05 - INFO - codeparrot_training - Step 15057: {'lr': 0.00039778035565992385, 'samples': 7709696, 'steps': 15057, 'batch_loss/train': 0.7527310631703585}
+12/24/2021 23:07:15 - INFO - codeparrot_training - Step 15058: {'lr': 0.00039776764109663833, 'samples': 7710208, 'steps': 15058, 'batch_loss/train': 0.7145704725990072}
+12/24/2021 23:07:26 - INFO - codeparrot_training - Step 15059: {'lr': 0.0003977549259458844, 'samples': 7710720, 'steps': 15059, 'batch_loss/train': 0.717323882272467}
+12/24/2021 23:07:38 - INFO - codeparrot_training - Step 15060: {'lr': 0.00039774221020771276, 'samples': 7711232, 'steps': 15060, 'batch_loss/train': 0.6659583924338222}
+12/24/2021 23:07:48 - INFO - codeparrot_training - Step 15061: {'lr': 0.0003977294938821737, 'samples': 7711744, 'steps': 15061, 'batch_loss/train': 0.7779099374311045}
+12/24/2021 23:07:59 - INFO - codeparrot_training - Step 15062: {'lr': 0.00039771677696931815, 'samples': 7712256, 'steps': 15062, 'batch_loss/train': 0.7578109826426953}
+12/24/2021 23:08:13 - INFO - codeparrot_training - Step 15063: {'lr': 0.0003977040594691963, 'samples': 7712768, 'steps': 15063, 'batch_loss/train': 0.7201820353511721}
+12/24/2021 23:08:23 - INFO - codeparrot_training - Step 15064: {'lr': 0.00039769134138185896, 'samples': 7713280, 'steps': 15064, 'batch_loss/train': 0.7406089096330106}
+12/24/2021 23:08:34 - INFO - codeparrot_training - Step 15065: {'lr': 0.00039767862270735665, 'samples': 7713792, 'steps': 15065, 'batch_loss/train': 0.8531364137306809}
+12/24/2021 23:08:45 - INFO - codeparrot_training - Step 15066: {'lr': 0.00039766590344573983, 'samples': 7714304, 'steps': 15066, 'batch_loss/train': 0.7384786889888346}
+12/24/2021 23:08:57 - INFO - codeparrot_training - Step 15067: {'lr': 0.0003976531835970592, 'samples': 7714816, 'steps': 15067, 'batch_loss/train': 0.8131009351927787}
+12/24/2021 23:09:07 - INFO - codeparrot_training - Step 15068: {'lr': 0.0003976404631613652, 'samples': 7715328, 'steps': 15068, 'batch_loss/train': 0.6923494255170226}
+12/24/2021 23:09:18 - INFO - codeparrot_training - Step 15069: {'lr': 0.0003976277421387085, 'samples': 7715840, 'steps': 15069, 'batch_loss/train': 0.7069573672488332}
+12/24/2021 23:09:32 - INFO - codeparrot_training - Step 15070: {'lr': 0.0003976150205291397, 'samples': 7716352, 'steps': 15070, 'batch_loss/train': 0.8969735838472843}
+12/24/2021 23:09:42 - INFO - codeparrot_training - Step 15071: {'lr': 0.0003976022983327092, 'samples': 7716864, 'steps': 15071, 'batch_loss/train': 0.8563282443210483}
+12/24/2021 23:09:53 - INFO - codeparrot_training - Step 15072: {'lr': 0.00039758957554946774, 'samples': 7717376, 'steps': 15072, 'batch_loss/train': 0.8789429324679077}
+12/24/2021 23:10:05 - INFO - codeparrot_training - Step 15073: {'lr': 0.0003975768521794659, 'samples': 7717888, 'steps': 15073, 'batch_loss/train': 0.8038508519530296}
+12/24/2021 23:10:16 - INFO - codeparrot_training - Step 15074: {'lr': 0.00039756412822275413, 'samples': 7718400, 'steps': 15074, 'batch_loss/train': 0.8309927452355623}
+12/24/2021 23:10:26 - INFO - codeparrot_training - Step 15075: {'lr': 0.00039755140367938316, 'samples': 7718912, 'steps': 15075, 'batch_loss/train': 0.7763067381456494}
+12/24/2021 23:10:38 - INFO - codeparrot_training - Step 15076: {'lr': 0.00039753867854940353, 'samples': 7719424, 'steps': 15076, 'batch_loss/train': 0.7739174454472959}
+12/24/2021 23:10:49 - INFO - codeparrot_training - Step 15077: {'lr': 0.00039752595283286575, 'samples': 7719936, 'steps': 15077, 'batch_loss/train': 0.8755602966994047}
+12/24/2021 23:10:59 - INFO - codeparrot_training - Step 15078: {'lr': 0.00039751322652982056, 'samples': 7720448, 'steps': 15078, 'batch_loss/train': 0.8920748624950647}
+12/24/2021 23:11:10 - INFO - codeparrot_training - Step 15079: {'lr': 0.00039750049964031844, 'samples': 7720960, 'steps': 15079, 'batch_loss/train': 0.8616991052404046}
+12/24/2021 23:11:24 - INFO - codeparrot_training - Step 15080: {'lr': 0.00039748777216441013, 'samples': 7721472, 'steps': 15080, 'batch_loss/train': 0.7732932986691594}
+12/24/2021 23:11:35 - INFO - codeparrot_training - Step 15081: {'lr': 0.000397475044102146, 'samples': 7721984, 'steps': 15081, 'batch_loss/train': 0.6883193701505661}
+12/24/2021 23:11:45 - INFO - codeparrot_training - Step 15082: {'lr': 0.0003974623154535768, 'samples': 7722496, 'steps': 15082, 'batch_loss/train': 0.829625194426626}
+12/24/2021 23:11:57 - INFO - codeparrot_training - Step 15083: {'lr': 0.00039744958621875314, 'samples': 7723008, 'steps': 15083, 'batch_loss/train': 0.8233994143083692}
+12/24/2021 23:12:08 - INFO - codeparrot_training - Step 15084: {'lr': 0.00039743685639772566, 'samples': 7723520, 'steps': 15084, 'batch_loss/train': 0.8417293066158891}
+12/24/2021 23:12:19 - INFO - codeparrot_training - Step 15085: {'lr': 0.0003974241259905448, 'samples': 7724032, 'steps': 15085, 'batch_loss/train': 0.8430235777050257}
+12/24/2021 23:12:31 - INFO - codeparrot_training - Step 15086: {'lr': 0.0003974113949972614, 'samples': 7724544, 'steps': 15086, 'batch_loss/train': 0.7918209033086896}
+12/24/2021 23:12:41 - INFO - codeparrot_training - Step 15087: {'lr': 0.0003973986634179259, 'samples': 7725056, 'steps': 15087, 'batch_loss/train': 0.8122613496379927}
+12/24/2021 23:12:52 - INFO - codeparrot_training - Step 15088: {'lr': 0.00039738593125258887, 'samples': 7725568, 'steps': 15088, 'batch_loss/train': 0.798822452314198}
+12/24/2021 23:13:02 - INFO - codeparrot_training - Step 15089: {'lr': 0.0003973731985013011, 'samples': 7726080, 'steps': 15089, 'batch_loss/train': 0.8528025895357132}
+12/24/2021 23:13:14 - INFO - codeparrot_training - Step 15090: {'lr': 0.00039736046516411315, 'samples': 7726592, 'steps': 15090, 'batch_loss/train': 0.7823106086580083}
+12/24/2021 23:13:25 - INFO - codeparrot_training - Step 15091: {'lr': 0.00039734773124107566, 'samples': 7727104, 'steps': 15091, 'batch_loss/train': 0.7150093035306782}
+12/24/2021 23:13:36 - INFO - codeparrot_training - Step 15092: {'lr': 0.00039733499673223917, 'samples': 7727616, 'steps': 15092, 'batch_loss/train': 0.8804581421427429}
+12/24/2021 23:13:50 - INFO - codeparrot_training - Step 15093: {'lr': 0.0003973222616376544, 'samples': 7728128, 'steps': 15093, 'batch_loss/train': 0.8199139162898064}
+12/24/2021 23:14:00 - INFO - codeparrot_training - Step 15094: {'lr': 0.00039730952595737193, 'samples': 7728640, 'steps': 15094, 'batch_loss/train': 0.7786889607086778}
+12/24/2021 23:14:11 - INFO - codeparrot_training - Step 15095: {'lr': 0.00039729678969144244, 'samples': 7729152, 'steps': 15095, 'batch_loss/train': 0.6638925014995039}
+12/24/2021 23:14:23 - INFO - codeparrot_training - Step 15096: {'lr': 0.0003972840528399165, 'samples': 7729664, 'steps': 15096, 'batch_loss/train': 0.7942576501518488}
+12/24/2021 23:14:34 - INFO - codeparrot_training - Step 15097: {'lr': 0.0003972713154028448, 'samples': 7730176, 'steps': 15097, 'batch_loss/train': 0.8614864069968462}
+12/24/2021 23:14:44 - INFO - codeparrot_training - Step 15098: {'lr': 0.0003972585773802779, 'samples': 7730688, 'steps': 15098, 'batch_loss/train': 0.8010946726426482}
+12/24/2021 23:14:58 - INFO - codeparrot_training - Step 15099: {'lr': 0.00039724583877226655, 'samples': 7731200, 'steps': 15099, 'batch_loss/train': 0.8070316882804036}
+12/24/2021 23:15:09 - INFO - codeparrot_training - Step 15100: {'lr': 0.00039723309957886136, 'samples': 7731712, 'steps': 15100, 'batch_loss/train': 0.8169192844070494}
+12/24/2021 23:15:19 - INFO - codeparrot_training - Step 15101: {'lr': 0.0003972203598001129, 'samples': 7732224, 'steps': 15101, 'batch_loss/train': 0.6924112597480416}
+12/24/2021 23:15:30 - INFO - codeparrot_training - Step 15102: {'lr': 0.00039720761943607194, 'samples': 7732736, 'steps': 15102, 'batch_loss/train': 0.8531133430078626}
+12/24/2021 23:15:42 - INFO - codeparrot_training - Step 15103: {'lr': 0.00039719487848678903, 'samples': 7733248, 'steps': 15103, 'batch_loss/train': 0.7288213148713112}
+12/24/2021 23:15:53 - INFO - codeparrot_training - Step 15104: {'lr': 0.0003971821369523149, 'samples': 7733760, 'steps': 15104, 'batch_loss/train': 0.8520951448008418}
+12/24/2021 23:16:03 - INFO - codeparrot_training - Step 15105: {'lr': 0.00039716939483270007, 'samples': 7734272, 'steps': 15105, 'batch_loss/train': 0.7818022151477635}
+12/24/2021 23:16:15 - INFO - codeparrot_training - Step 15106: {'lr': 0.00039715665212799534, 'samples': 7734784, 'steps': 15106, 'batch_loss/train': 0.8393593486398458}
+12/24/2021 23:16:26 - INFO - codeparrot_training - Step 15107: {'lr': 0.0003971439088382514, 'samples': 7735296, 'steps': 15107, 'batch_loss/train': 0.8650860283523798}
+12/24/2021 23:16:36 - INFO - codeparrot_training - Step 15108: {'lr': 0.00039713116496351876, 'samples': 7735808, 'steps': 15108, 'batch_loss/train': 0.8163296999409795}
+12/24/2021 23:16:50 - INFO - codeparrot_training - Step 15109: {'lr': 0.0003971184205038482, 'samples': 7736320, 'steps': 15109, 'batch_loss/train': 0.7946484116837382}
+12/24/2021 23:17:01 - INFO - codeparrot_training - Step 15110: {'lr': 0.0003971056754592903, 'samples': 7736832, 'steps': 15110, 'batch_loss/train': 0.7268859702162445}
+12/24/2021 23:17:12 - INFO - codeparrot_training - Step 15111: {'lr': 0.00039709292982989584, 'samples': 7737344, 'steps': 15111, 'batch_loss/train': 0.8360483264550567}
+12/24/2021 23:17:22 - INFO - codeparrot_training - Step 15112: {'lr': 0.0003970801836157154, 'samples': 7737856, 'steps': 15112, 'batch_loss/train': 0.8480463186278939}
+12/24/2021 23:17:34 - INFO - codeparrot_training - Step 15113: {'lr': 0.00039706743681679966, 'samples': 7738368, 'steps': 15113, 'batch_loss/train': 0.8101447802037001}
+12/24/2021 23:17:45 - INFO - codeparrot_training - Step 15114: {'lr': 0.00039705468943319937, 'samples': 7738880, 'steps': 15114, 'batch_loss/train': 0.7534350296482444}
+12/24/2021 23:17:55 - INFO - codeparrot_training - Step 15115: {'lr': 0.0003970419414649652, 'samples': 7739392, 'steps': 15115, 'batch_loss/train': 0.8573392233811319}
+12/24/2021 23:18:09 - INFO - codeparrot_training - Step 15116: {'lr': 0.00039702919291214765, 'samples': 7739904, 'steps': 15116, 'batch_loss/train': 0.8077794564887881}
+12/24/2021 23:18:20 - INFO - codeparrot_training - Step 15117: {'lr': 0.0003970164437747977, 'samples': 7740416, 'steps': 15117, 'batch_loss/train': 0.8712782580405474}
+12/24/2021 23:18:31 - INFO - codeparrot_training - Step 15118: {'lr': 0.00039700369405296575, 'samples': 7740928, 'steps': 15118, 'batch_loss/train': 0.6550051795784384}
+12/24/2021 23:18:43 - INFO - codeparrot_training - Step 15119: {'lr': 0.00039699094374670275, 'samples': 7741440, 'steps': 15119, 'batch_loss/train': 0.8504453618079424}
+12/24/2021 23:18:53 - INFO - codeparrot_training - Step 15120: {'lr': 0.00039697819285605917, 'samples': 7741952, 'steps': 15120, 'batch_loss/train': 0.7935726381838322}
+12/24/2021 23:19:04 - INFO - codeparrot_training - Step 15121: {'lr': 0.0003969654413810858, 'samples': 7742464, 'steps': 15121, 'batch_loss/train': 0.7337455414235592}
+12/24/2021 23:19:15 - INFO - codeparrot_training - Step 15122: {'lr': 0.0003969526893218334, 'samples': 7742976, 'steps': 15122, 'batch_loss/train': 0.8123761937022209}
+12/24/2021 23:19:27 - INFO - codeparrot_training - Step 15123: {'lr': 0.00039693993667835246, 'samples': 7743488, 'steps': 15123, 'batch_loss/train': 0.800334285479039}
+12/24/2021 23:19:37 - INFO - codeparrot_training - Step 15124: {'lr': 0.0003969271834506939, 'samples': 7744000, 'steps': 15124, 'batch_loss/train': 0.6258733808062971}
+12/24/2021 23:19:48 - INFO - codeparrot_training - Step 15125: {'lr': 0.00039691442963890833, 'samples': 7744512, 'steps': 15125, 'batch_loss/train': 0.7738456185907125}
+12/24/2021 23:20:00 - INFO - codeparrot_training - Step 15126: {'lr': 0.00039690167524304644, 'samples': 7745024, 'steps': 15126, 'batch_loss/train': 0.7364361896179616}
+12/24/2021 23:20:11 - INFO - codeparrot_training - Step 15127: {'lr': 0.000396888920263159, 'samples': 7745536, 'steps': 15127, 'batch_loss/train': 0.7780486447736621}
+12/24/2021 23:20:22 - INFO - codeparrot_training - Step 15128: {'lr': 0.0003968761646992967, 'samples': 7746048, 'steps': 15128, 'batch_loss/train': 0.7675537450704724}
+12/24/2021 23:20:35 - INFO - codeparrot_training - Step 15129: {'lr': 0.00039686340855151007, 'samples': 7746560, 'steps': 15129, 'batch_loss/train': 0.8317308062687516}
+12/24/2021 23:20:46 - INFO - codeparrot_training - Step 15130: {'lr': 0.0003968506518198501, 'samples': 7747072, 'steps': 15130, 'batch_loss/train': 0.8268822989193723}
+12/24/2021 23:20:57 - INFO - codeparrot_training - Step 15131: {'lr': 0.00039683789450436737, 'samples': 7747584, 'steps': 15131, 'batch_loss/train': 0.9185410728678107}
+12/24/2021 23:21:07 - INFO - codeparrot_training - Step 15132: {'lr': 0.00039682513660511265, 'samples': 7748096, 'steps': 15132, 'batch_loss/train': 0.7483747224323452}
+12/24/2021 23:21:20 - INFO - codeparrot_training - Step 15133: {'lr': 0.0003968123781221366, 'samples': 7748608, 'steps': 15133, 'batch_loss/train': 0.7404730105772614}
+12/24/2021 23:21:30 - INFO - codeparrot_training - Step 15134: {'lr': 0.00039679961905549, 'samples': 7749120, 'steps': 15134, 'batch_loss/train': 0.8691325206309557}
+12/24/2021 23:21:41 - INFO - codeparrot_training - Step 15135: {'lr': 0.00039678685940522346, 'samples': 7749632, 'steps': 15135, 'batch_loss/train': 0.8440402615815401}
+12/24/2021 23:21:53 - INFO - codeparrot_training - Step 15136: {'lr': 0.00039677409917138786, 'samples': 7750144, 'steps': 15136, 'batch_loss/train': 0.6636732942424715}
+12/24/2021 23:22:03 - INFO - codeparrot_training - Step 15137: {'lr': 0.00039676133835403384, 'samples': 7750656, 'steps': 15137, 'batch_loss/train': 0.8741588294506073}
+12/24/2021 23:22:14 - INFO - codeparrot_training - Step 15138: {'lr': 0.0003967485769532121, 'samples': 7751168, 'steps': 15138, 'batch_loss/train': 0.8052665712311864}
+12/24/2021 23:22:28 - INFO - codeparrot_training - Step 15139: {'lr': 0.0003967358149689735, 'samples': 7751680, 'steps': 15139, 'batch_loss/train': 0.7525038653984666}
+12/24/2021 23:22:38 - INFO - codeparrot_training - Step 15140: {'lr': 0.00039672305240136876, 'samples': 7752192, 'steps': 15140, 'batch_loss/train': 0.7669370144139975}
+12/24/2021 23:22:49 - INFO - codeparrot_training - Step 15141: {'lr': 0.00039671028925044845, 'samples': 7752704, 'steps': 15141, 'batch_loss/train': 0.7143866987898946}
+12/24/2021 23:23:00 - INFO - codeparrot_training - Step 15142: {'lr': 0.0003966975255162635, 'samples': 7753216, 'steps': 15142, 'batch_loss/train': 0.8555583218112588}
+12/24/2021 23:23:12 - INFO - codeparrot_training - Step 15143: {'lr': 0.00039668476119886453, 'samples': 7753728, 'steps': 15143, 'batch_loss/train': 0.8193344594910741}
+12/24/2021 23:23:22 - INFO - codeparrot_training - Step 15144: {'lr': 0.0003966719962983023, 'samples': 7754240, 'steps': 15144, 'batch_loss/train': 0.7991278534755111}
+12/24/2021 23:23:33 - INFO - codeparrot_training - Step 15145: {'lr': 0.00039665923081462766, 'samples': 7754752, 'steps': 15145, 'batch_loss/train': 0.8186865486204624}
+12/24/2021 23:23:45 - INFO - codeparrot_training - Step 15146: {'lr': 0.0003966464647478913, 'samples': 7755264, 'steps': 15146, 'batch_loss/train': 0.8277139340061694}
+12/24/2021 23:23:56 - INFO - codeparrot_training - Step 15147: {'lr': 0.000396633698098144, 'samples': 7755776, 'steps': 15147, 'batch_loss/train': 0.810782527551055}
+12/24/2021 23:24:06 - INFO - codeparrot_training - Step 15148: {'lr': 0.00039662093086543636, 'samples': 7756288, 'steps': 15148, 'batch_loss/train': 0.7826961502432823}
+12/24/2021 23:24:20 - INFO - codeparrot_training - Step 15149: {'lr': 0.0003966081630498193, 'samples': 7756800, 'steps': 15149, 'batch_loss/train': 0.7071765039581805}
+12/24/2021 23:24:30 - INFO - codeparrot_training - Step 15150: {'lr': 0.00039659539465134363, 'samples': 7757312, 'steps': 15150, 'batch_loss/train': 0.7552444115281105}
+12/24/2021 23:24:41 - INFO - codeparrot_training - Step 15151: {'lr': 0.00039658262567005996, 'samples': 7757824, 'steps': 15151, 'batch_loss/train': 0.814811140531674}
+12/24/2021 23:24:53 - INFO - codeparrot_training - Step 15152: {'lr': 0.00039656985610601913, 'samples': 7758336, 'steps': 15152, 'batch_loss/train': 0.7091871043667197}
+12/24/2021 23:25:04 - INFO - codeparrot_training - Step 15153: {'lr': 0.0003965570859592719, 'samples': 7758848, 'steps': 15153, 'batch_loss/train': 0.7672374583780766}
+12/24/2021 23:25:14 - INFO - codeparrot_training - Step 15154: {'lr': 0.000396544315229869, 'samples': 7759360, 'steps': 15154, 'batch_loss/train': 0.7738391431048512}
+12/24/2021 23:25:25 - INFO - codeparrot_training - Step 15155: {'lr': 0.00039653154391786126, 'samples': 7759872, 'steps': 15155, 'batch_loss/train': 0.8447645823471248}
+12/24/2021 23:25:39 - INFO - codeparrot_training - Step 15156: {'lr': 0.00039651877202329946, 'samples': 7760384, 'steps': 15156, 'batch_loss/train': 0.8995185848325491}
+12/24/2021 23:25:50 - INFO - codeparrot_training - Step 15157: {'lr': 0.0003965059995462342, 'samples': 7760896, 'steps': 15157, 'batch_loss/train': 0.8583915270864964}
+12/24/2021 23:26:00 - INFO - codeparrot_training - Step 15158: {'lr': 0.0003964932264867166, 'samples': 7761408, 'steps': 15158, 'batch_loss/train': 0.8328680917620659}
+12/24/2021 23:26:12 - INFO - codeparrot_training - Step 15159: {'lr': 0.00039648045284479714, 'samples': 7761920, 'steps': 15159, 'batch_loss/train': 0.7826241133734584}
+12/24/2021 23:26:23 - INFO - codeparrot_training - Step 15160: {'lr': 0.0003964676786205268, 'samples': 7762432, 'steps': 15160, 'batch_loss/train': 0.8668542206287384}
+12/24/2021 23:26:33 - INFO - codeparrot_training - Step 15161: {'lr': 0.00039645490381395615, 'samples': 7762944, 'steps': 15161, 'batch_loss/train': 0.9402839401736856}
+12/24/2021 23:26:45 - INFO - codeparrot_training - Step 15162: {'lr': 0.00039644212842513614, 'samples': 7763456, 'steps': 15162, 'batch_loss/train': 0.7987944409251213}
+12/24/2021 23:26:56 - INFO - codeparrot_training - Step 15163: {'lr': 0.0003964293524541176, 'samples': 7763968, 'steps': 15163, 'batch_loss/train': 0.8435867577791214}
+12/24/2021 23:27:07 - INFO - codeparrot_training - Step 15164: {'lr': 0.00039641657590095113, 'samples': 7764480, 'steps': 15164, 'batch_loss/train': 0.7539418437518179}
+12/24/2021 23:27:17 - INFO - codeparrot_training - Step 15165: {'lr': 0.00039640379876568774, 'samples': 7764992, 'steps': 15165, 'batch_loss/train': 0.6861504239495844}
+12/24/2021 23:27:29 - INFO - codeparrot_training - Step 15166: {'lr': 0.00039639102104837805, 'samples': 7765504, 'steps': 15166, 'batch_loss/train': 0.7977317944169044}
+12/24/2021 23:27:40 - INFO - codeparrot_training - Step 15167: {'lr': 0.000396378242749073, 'samples': 7766016, 'steps': 15167, 'batch_loss/train': 0.7883560061454773}
+12/24/2021 23:27:51 - INFO - codeparrot_training - Step 15168: {'lr': 0.00039636546386782325, 'samples': 7766528, 'steps': 15168, 'batch_loss/train': 0.8972636186517775}
+12/24/2021 23:28:04 - INFO - codeparrot_training - Step 15169: {'lr': 0.00039635268440467973, 'samples': 7767040, 'steps': 15169, 'batch_loss/train': 0.8340826760977507}
+12/24/2021 23:28:15 - INFO - codeparrot_training - Step 15170: {'lr': 0.00039633990435969314, 'samples': 7767552, 'steps': 15170, 'batch_loss/train': 0.8260392621159554}
+12/24/2021 23:28:26 - INFO - codeparrot_training - Step 15171: {'lr': 0.00039632712373291446, 'samples': 7768064, 'steps': 15171, 'batch_loss/train': 0.669057690538466}
+12/24/2021 23:28:38 - INFO - codeparrot_training - Step 15172: {'lr': 0.0003963143425243943, 'samples': 7768576, 'steps': 15172, 'batch_loss/train': 0.8530959747731686}
+12/24/2021 23:28:48 - INFO - codeparrot_training - Step 15173: {'lr': 0.0003963015607341836, 'samples': 7769088, 'steps': 15173, 'batch_loss/train': 0.7718411954119802}
+12/24/2021 23:28:59 - INFO - codeparrot_training - Step 15174: {'lr': 0.00039628877836233315, 'samples': 7769600, 'steps': 15174, 'batch_loss/train': 0.8343448443338275}
+12/24/2021 23:29:09 - INFO - codeparrot_training - Step 15175: {'lr': 0.0003962759954088936, 'samples': 7770112, 'steps': 15175, 'batch_loss/train': 0.876037257257849}
+12/24/2021 23:29:23 - INFO - codeparrot_training - Step 15176: {'lr': 0.00039626321187391614, 'samples': 7770624, 'steps': 15176, 'batch_loss/train': 0.8979691732674837}
+12/24/2021 23:29:34 - INFO - codeparrot_training - Step 15177: {'lr': 0.0003962504277574512, 'samples': 7771136, 'steps': 15177, 'batch_loss/train': 1.0067491391673684}
+12/24/2021 23:29:45 - INFO - codeparrot_training - Step 15178: {'lr': 0.0003962376430595499, 'samples': 7771648, 'steps': 15178, 'batch_loss/train': 0.6952723423019052}
+12/24/2021 23:29:57 - INFO - codeparrot_training - Step 15179: {'lr': 0.000396224857780263, 'samples': 7772160, 'steps': 15179, 'batch_loss/train': 0.8290817383676767}
+12/24/2021 23:30:07 - INFO - codeparrot_training - Step 15180: {'lr': 0.00039621207191964115, 'samples': 7772672, 'steps': 15180, 'batch_loss/train': 0.8133543627336621}
+12/24/2021 23:30:18 - INFO - codeparrot_training - Step 15181: {'lr': 0.00039619928547773533, 'samples': 7773184, 'steps': 15181, 'batch_loss/train': 0.8846636367961764}
+12/24/2021 23:30:30 - INFO - codeparrot_training - Step 15182: {'lr': 0.00039618649845459637, 'samples': 7773696, 'steps': 15182, 'batch_loss/train': 0.7706340712029487}
+12/24/2021 23:30:41 - INFO - codeparrot_training - Step 15183: {'lr': 0.0003961737108502751, 'samples': 7774208, 'steps': 15183, 'batch_loss/train': 0.733369723893702}
+12/24/2021 23:30:51 - INFO - codeparrot_training - Step 15184: {'lr': 0.00039616092266482237, 'samples': 7774720, 'steps': 15184, 'batch_loss/train': 0.7700279669370502}
+12/24/2021 23:31:02 - INFO - codeparrot_training - Step 15185: {'lr': 0.00039614813389828897, 'samples': 7775232, 'steps': 15185, 'batch_loss/train': 0.7666797069832683}
+12/24/2021 23:31:16 - INFO - codeparrot_training - Step 15186: {'lr': 0.0003961353445507258, 'samples': 7775744, 'steps': 15186, 'batch_loss/train': 0.830552932806313}
+12/24/2021 23:31:27 - INFO - codeparrot_training - Step 15187: {'lr': 0.00039612255462218363, 'samples': 7776256, 'steps': 15187, 'batch_loss/train': 0.5156158680329099}
+12/24/2021 23:31:37 - INFO - codeparrot_training - Step 15188: {'lr': 0.00039610976411271333, 'samples': 7776768, 'steps': 15188, 'batch_loss/train': 0.791062846314162}
+12/24/2021 23:31:49 - INFO - codeparrot_training - Step 15189: {'lr': 0.00039609697302236583, 'samples': 7777280, 'steps': 15189, 'batch_loss/train': 0.7706606574356556}
+12/24/2021 23:32:00 - INFO - codeparrot_training - Step 15190: {'lr': 0.00039608418135119193, 'samples': 7777792, 'steps': 15190, 'batch_loss/train': 0.7988136233761907}
+12/24/2021 23:32:11 - INFO - codeparrot_training - Step 15191: {'lr': 0.0003960713890992425, 'samples': 7778304, 'steps': 15191, 'batch_loss/train': 0.8365946924313903}
+12/24/2021 23:32:23 - INFO - codeparrot_training - Step 15192: {'lr': 0.0003960585962665683, 'samples': 7778816, 'steps': 15192, 'batch_loss/train': 1.058469807729125}
+12/24/2021 23:32:33 - INFO - codeparrot_training - Step 15193: {'lr': 0.0003960458028532204, 'samples': 7779328, 'steps': 15193, 'batch_loss/train': 0.7676019659265876}
+12/24/2021 23:32:44 - INFO - codeparrot_training - Step 15194: {'lr': 0.00039603300885924944, 'samples': 7779840, 'steps': 15194, 'batch_loss/train': 0.8938004188239574}
+12/24/2021 23:32:55 - INFO - codeparrot_training - Step 15195: {'lr': 0.0003960202142847064, 'samples': 7780352, 'steps': 15195, 'batch_loss/train': 0.7109097065404058}
+12/24/2021 23:33:08 - INFO - codeparrot_training - Step 15196: {'lr': 0.0003960074191296421, 'samples': 7780864, 'steps': 15196, 'batch_loss/train': 0.8934599608182907}
+12/24/2021 23:33:19 - INFO - codeparrot_training - Step 15197: {'lr': 0.00039599462339410754, 'samples': 7781376, 'steps': 15197, 'batch_loss/train': 0.7967575890943408}
+12/24/2021 23:33:30 - INFO - codeparrot_training - Step 15198: {'lr': 0.0003959818270781533, 'samples': 7781888, 'steps': 15198, 'batch_loss/train': 0.8008099119178951}
+12/24/2021 23:33:42 - INFO - codeparrot_training - Step 15199: {'lr': 0.00039596903018183054, 'samples': 7782400, 'steps': 15199, 'batch_loss/train': 0.8431852860376239}
+12/24/2021 23:33:53 - INFO - codeparrot_training - Step 15200: {'lr': 0.00039595623270519007, 'samples': 7782912, 'steps': 15200, 'batch_loss/train': 0.8032833319157362}
+12/24/2021 23:34:03 - INFO - codeparrot_training - Step 15201: {'lr': 0.00039594343464828264, 'samples': 7783424, 'steps': 15201, 'batch_loss/train': 0.7308995230123401}
+12/24/2021 23:34:15 - INFO - codeparrot_training - Step 15202: {'lr': 0.00039593063601115933, 'samples': 7783936, 'steps': 15202, 'batch_loss/train': 0.8329409470316023}
+12/24/2021 23:34:26 - INFO - codeparrot_training - Step 15203: {'lr': 0.0003959178367938708, 'samples': 7784448, 'steps': 15203, 'batch_loss/train': 0.8268965412862599}
+12/24/2021 23:34:37 - INFO - codeparrot_training - Step 15204: {'lr': 0.0003959050369964681, 'samples': 7784960, 'steps': 15204, 'batch_loss/train': 0.8728166855871677}
+12/24/2021 23:34:49 - INFO - codeparrot_training - Step 15205: {'lr': 0.00039589223661900207, 'samples': 7785472, 'steps': 15205, 'batch_loss/train': 0.8298898874782026}
+12/24/2021 23:34:59 - INFO - codeparrot_training - Step 15206: {'lr': 0.00039587943566152364, 'samples': 7785984, 'steps': 15206, 'batch_loss/train': 0.7540445271879435}
+12/24/2021 23:35:10 - INFO - codeparrot_training - Step 15207: {'lr': 0.0003958666341240835, 'samples': 7786496, 'steps': 15207, 'batch_loss/train': 0.8549695904366672}
+12/24/2021 23:35:20 - INFO - codeparrot_training - Step 15208: {'lr': 0.00039585383200673287, 'samples': 7787008, 'steps': 15208, 'batch_loss/train': 0.8277378026396036}
+12/24/2021 23:35:34 - INFO - codeparrot_training - Step 15209: {'lr': 0.0003958410293095224, 'samples': 7787520, 'steps': 15209, 'batch_loss/train': 0.8565903278067708}
+12/24/2021 23:35:45 - INFO - codeparrot_training - Step 15210: {'lr': 0.000395828226032503, 'samples': 7788032, 'steps': 15210, 'batch_loss/train': 0.9148605838418007}
+12/24/2021 23:35:55 - INFO - codeparrot_training - Step 15211: {'lr': 0.00039581542217572574, 'samples': 7788544, 'steps': 15211, 'batch_loss/train': 0.6562419291585684}
+12/24/2021 23:36:07 - INFO - codeparrot_training - Step 15212: {'lr': 0.00039580261773924144, 'samples': 7789056, 'steps': 15212, 'batch_loss/train': 0.8248153859749436}
+12/24/2021 23:36:18 - INFO - codeparrot_training - Step 15213: {'lr': 0.0003957898127231009, 'samples': 7789568, 'steps': 15213, 'batch_loss/train': 0.6860710091423243}
+12/24/2021 23:36:29 - INFO - codeparrot_training - Step 15214: {'lr': 0.00039577700712735517, 'samples': 7790080, 'steps': 15214, 'batch_loss/train': 0.8259097570553422}
+12/24/2021 23:36:42 - INFO - codeparrot_training - Step 15215: {'lr': 0.00039576420095205507, 'samples': 7790592, 'steps': 15215, 'batch_loss/train': 0.7875052792951465}
+12/24/2021 23:36:53 - INFO - codeparrot_training - Step 15216: {'lr': 0.0003957513941972515, 'samples': 7791104, 'steps': 15216, 'batch_loss/train': 0.7290696385316551}
+12/24/2021 23:37:04 - INFO - codeparrot_training - Step 15217: {'lr': 0.00039573858686299556, 'samples': 7791616, 'steps': 15217, 'batch_loss/train': 0.8668636307120323}
+12/24/2021 23:37:14 - INFO - codeparrot_training - Step 15218: {'lr': 0.0003957257789493379, 'samples': 7792128, 'steps': 15218, 'batch_loss/train': 0.7975559551268816}
+12/24/2021 23:37:26 - INFO - codeparrot_training - Step 15219: {'lr': 0.0003957129704563296, 'samples': 7792640, 'steps': 15219, 'batch_loss/train': 0.7456521112471819}
+12/24/2021 23:37:37 - INFO - codeparrot_training - Step 15220: {'lr': 0.00039570016138402157, 'samples': 7793152, 'steps': 15220, 'batch_loss/train': 0.7849466083571315}
+12/24/2021 23:37:48 - INFO - codeparrot_training - Step 15221: {'lr': 0.00039568735173246475, 'samples': 7793664, 'steps': 15221, 'batch_loss/train': 0.8994745616801083}
+12/24/2021 23:38:02 - INFO - codeparrot_training - Step 15222: {'lr': 0.0003956745415017099, 'samples': 7794176, 'steps': 15222, 'batch_loss/train': 0.8183975322172046}
+12/24/2021 23:38:12 - INFO - codeparrot_training - Step 15223: {'lr': 0.0003956617306918081, 'samples': 7794688, 'steps': 15223, 'batch_loss/train': 0.7495822970522568}
+12/24/2021 23:38:23 - INFO - codeparrot_training - Step 15224: {'lr': 0.00039564891930281043, 'samples': 7795200, 'steps': 15224, 'batch_loss/train': 0.6374032786698081}
+12/24/2021 23:38:35 - INFO - codeparrot_training - Step 15225: {'lr': 0.00039563610733476753, 'samples': 7795712, 'steps': 15225, 'batch_loss/train': 0.7640522895380855}
+12/24/2021 23:38:46 - INFO - codeparrot_training - Step 15226: {'lr': 0.0003956232947877304, 'samples': 7796224, 'steps': 15226, 'batch_loss/train': 0.9347076122649014}
+12/24/2021 23:38:56 - INFO - codeparrot_training - Step 15227: {'lr': 0.0003956104816617501, 'samples': 7796736, 'steps': 15227, 'batch_loss/train': 0.5211698145139962}
+12/24/2021 23:39:07 - INFO - codeparrot_training - Step 15228: {'lr': 0.00039559766795687755, 'samples': 7797248, 'steps': 15228, 'batch_loss/train': 0.7111411956138909}
+12/24/2021 23:39:20 - INFO - codeparrot_training - Step 15229: {'lr': 0.00039558485367316356, 'samples': 7797760, 'steps': 15229, 'batch_loss/train': 0.8849537717178464}
+12/24/2021 23:39:30 - INFO - codeparrot_training - Step 15230: {'lr': 0.00039557203881065924, 'samples': 7798272, 'steps': 15230, 'batch_loss/train': 0.635241795796901}
+12/24/2021 23:39:41 - INFO - codeparrot_training - Step 15231: {'lr': 0.00039555922336941544, 'samples': 7798784, 'steps': 15231, 'batch_loss/train': 0.8372219274751842}
+12/24/2021 23:39:55 - INFO - codeparrot_training - Step 15232: {'lr': 0.0003955464073494831, 'samples': 7799296, 'steps': 15232, 'batch_loss/train': 1.033272203989327}
+12/24/2021 23:40:05 - INFO - codeparrot_training - Step 15233: {'lr': 0.00039553359075091324, 'samples': 7799808, 'steps': 15233, 'batch_loss/train': 0.9007005114108324}
+12/24/2021 23:40:16 - INFO - codeparrot_training - Step 15234: {'lr': 0.0003955207735737567, 'samples': 7800320, 'steps': 15234, 'batch_loss/train': 0.8266675611957908}
+12/24/2021 23:40:26 - INFO - codeparrot_training - Step 15235: {'lr': 0.00039550795581806453, 'samples': 7800832, 'steps': 15235, 'batch_loss/train': 0.824978893622756}
+12/24/2021 23:40:38 - INFO - codeparrot_training - Step 15236: {'lr': 0.00039549513748388766, 'samples': 7801344, 'steps': 15236, 'batch_loss/train': 0.9377342509105802}
+12/24/2021 23:40:49 - INFO - codeparrot_training - Step 15237: {'lr': 0.00039548231857127717, 'samples': 7801856, 'steps': 15237, 'batch_loss/train': 0.8612476494163275}
+12/24/2021 23:41:00 - INFO - codeparrot_training - Step 15238: {'lr': 0.00039546949908028385, 'samples': 7802368, 'steps': 15238, 'batch_loss/train': 0.8517179070040584}
+12/24/2021 23:41:12 - INFO - codeparrot_training - Step 15239: {'lr': 0.0003954566790109587, 'samples': 7802880, 'steps': 15239, 'batch_loss/train': 0.8091731970198452}
+12/24/2021 23:41:23 - INFO - codeparrot_training - Step 15240: {'lr': 0.0003954438583633527, 'samples': 7803392, 'steps': 15240, 'batch_loss/train': 1.7024442432448268}
+12/24/2021 23:41:33 - INFO - codeparrot_training - Step 15241: {'lr': 0.00039543103713751693, 'samples': 7803904, 'steps': 15241, 'batch_loss/train': 0.7636218355037272}
+12/24/2021 23:41:45 - INFO - codeparrot_training - Step 15242: {'lr': 0.0003954182153335022, 'samples': 7804416, 'steps': 15242, 'batch_loss/train': 0.7916224421933293}
+12/24/2021 23:41:56 - INFO - codeparrot_training - Step 15243: {'lr': 0.0003954053929513596, 'samples': 7804928, 'steps': 15243, 'batch_loss/train': 0.5504813748411834}
+12/24/2021 23:42:07 - INFO - codeparrot_training - Step 15244: {'lr': 0.00039539256999113995, 'samples': 7805440, 'steps': 15244, 'batch_loss/train': 0.7843561815097928}
+12/24/2021 23:42:17 - INFO - codeparrot_training - Step 15245: {'lr': 0.0003953797464528944, 'samples': 7805952, 'steps': 15245, 'batch_loss/train': 0.8095387681387365}
+12/24/2021 23:42:31 - INFO - codeparrot_training - Step 15246: {'lr': 0.0003953669223366739, 'samples': 7806464, 'steps': 15246, 'batch_loss/train': 0.7328188996762037}
+12/24/2021 23:42:42 - INFO - codeparrot_training - Step 15247: {'lr': 0.00039535409764252937, 'samples': 7806976, 'steps': 15247, 'batch_loss/train': 0.822218150831759}
+12/24/2021 23:42:52 - INFO - codeparrot_training - Step 15248: {'lr': 0.0003953412723705119, 'samples': 7807488, 'steps': 15248, 'batch_loss/train': 0.8289752132259309}
+12/24/2021 23:43:05 - INFO - codeparrot_training - Step 15249: {'lr': 0.00039532844652067235, 'samples': 7808000, 'steps': 15249, 'batch_loss/train': 0.845595276914537}
+12/24/2021 23:43:15 - INFO - codeparrot_training - Step 15250: {'lr': 0.0003953156200930618, 'samples': 7808512, 'steps': 15250, 'batch_loss/train': 0.6388786202296615}
+12/24/2021 23:43:26 - INFO - codeparrot_training - Step 15251: {'lr': 0.0003953027930877312, 'samples': 7809024, 'steps': 15251, 'batch_loss/train': 0.8394711501896381}
+12/24/2021 23:43:38 - INFO - codeparrot_training - Step 15252: {'lr': 0.0003952899655047315, 'samples': 7809536, 'steps': 15252, 'batch_loss/train': 0.8296585688367486}
+12/24/2021 23:43:49 - INFO - codeparrot_training - Step 15253: {'lr': 0.00039527713734411387, 'samples': 7810048, 'steps': 15253, 'batch_loss/train': 0.7796742038335651}
+12/24/2021 23:43:59 - INFO - codeparrot_training - Step 15254: {'lr': 0.0003952643086059291, 'samples': 7810560, 'steps': 15254, 'batch_loss/train': 0.8325061895884573}
+12/24/2021 23:44:10 - INFO - codeparrot_training - Step 15255: {'lr': 0.00039525147929022833, 'samples': 7811072, 'steps': 15255, 'batch_loss/train': 0.7886962532065809}
+12/24/2021 23:44:24 - INFO - codeparrot_training - Step 15256: {'lr': 0.00039523864939706256, 'samples': 7811584, 'steps': 15256, 'batch_loss/train': 0.8393502626568079}
+12/24/2021 23:44:34 - INFO - codeparrot_training - Step 15257: {'lr': 0.0003952258189264827, 'samples': 7812096, 'steps': 15257, 'batch_loss/train': 0.9068024298176169}
+12/24/2021 23:44:45 - INFO - codeparrot_training - Step 15258: {'lr': 0.00039521298787853986, 'samples': 7812608, 'steps': 15258, 'batch_loss/train': 0.8234501127153635}
+12/24/2021 23:44:57 - INFO - codeparrot_training - Step 15259: {'lr': 0.000395200156253285, 'samples': 7813120, 'steps': 15259, 'batch_loss/train': 0.8700215429998934}
+12/24/2021 23:45:08 - INFO - codeparrot_training - Step 15260: {'lr': 0.0003951873240507691, 'samples': 7813632, 'steps': 15260, 'batch_loss/train': 0.853349793702364}
+12/24/2021 23:45:18 - INFO - codeparrot_training - Step 15261: {'lr': 0.00039517449127104325, 'samples': 7814144, 'steps': 15261, 'batch_loss/train': 0.8446015669032931}
+12/24/2021 23:45:32 - INFO - codeparrot_training - Step 15262: {'lr': 0.0003951616579141585, 'samples': 7814656, 'steps': 15262, 'batch_loss/train': 0.7721384083852172}
+12/24/2021 23:45:43 - INFO - codeparrot_training - Step 15263: {'lr': 0.00039514882398016573, 'samples': 7815168, 'steps': 15263, 'batch_loss/train': 0.7718077804893255}
+12/24/2021 23:45:53 - INFO - codeparrot_training - Step 15264: {'lr': 0.000395135989469116, 'samples': 7815680, 'steps': 15264, 'batch_loss/train': 0.902513300999999}
+12/24/2021 23:46:04 - INFO - codeparrot_training - Step 15265: {'lr': 0.0003951231543810605, 'samples': 7816192, 'steps': 15265, 'batch_loss/train': 0.7315835314802825}
+12/24/2021 23:46:16 - INFO - codeparrot_training - Step 15266: {'lr': 0.0003951103187160501, 'samples': 7816704, 'steps': 15266, 'batch_loss/train': 0.8205102658830583}
+12/24/2021 23:46:27 - INFO - codeparrot_training - Step 15267: {'lr': 0.0003950974824741358, 'samples': 7817216, 'steps': 15267, 'batch_loss/train': 0.8576538264751434}
+12/24/2021 23:46:37 - INFO - codeparrot_training - Step 15268: {'lr': 0.0003950846456553687, 'samples': 7817728, 'steps': 15268, 'batch_loss/train': 0.8596719820052385}
+12/24/2021 23:46:50 - INFO - codeparrot_training - Step 15269: {'lr': 0.00039507180825979995, 'samples': 7818240, 'steps': 15269, 'batch_loss/train': 0.7999380528926849}
+12/24/2021 23:47:00 - INFO - codeparrot_training - Step 15270: {'lr': 0.00039505897028748035, 'samples': 7818752, 'steps': 15270, 'batch_loss/train': 0.6651856862008572}
+12/24/2021 23:47:11 - INFO - codeparrot_training - Step 15271: {'lr': 0.0003950461317384611, 'samples': 7819264, 'steps': 15271, 'batch_loss/train': 0.8458511978387833}
+12/24/2021 23:47:23 - INFO - codeparrot_training - Step 15272: {'lr': 0.0003950332926127932, 'samples': 7819776, 'steps': 15272, 'batch_loss/train': 0.6369884633459151}
+12/24/2021 23:47:34 - INFO - codeparrot_training - Step 15273: {'lr': 0.00039502045291052765, 'samples': 7820288, 'steps': 15273, 'batch_loss/train': 0.807364541105926}
+12/24/2021 23:47:44 - INFO - codeparrot_training - Step 15274: {'lr': 0.0003950076126317156, 'samples': 7820800, 'steps': 15274, 'batch_loss/train': 0.8725978098809719}
+12/24/2021 23:47:55 - INFO - codeparrot_training - Step 15275: {'lr': 0.000394994771776408, 'samples': 7821312, 'steps': 15275, 'batch_loss/train': 0.8805484967306256}
+12/24/2021 23:48:09 - INFO - codeparrot_training - Step 15276: {'lr': 0.0003949819303446559, 'samples': 7821824, 'steps': 15276, 'batch_loss/train': 0.8575741044478491}
+12/24/2021 23:48:20 - INFO - codeparrot_training - Step 15277: {'lr': 0.0003949690883365104, 'samples': 7822336, 'steps': 15277, 'batch_loss/train': 0.7590005556121469}
+12/24/2021 23:48:30 - INFO - codeparrot_training - Step 15278: {'lr': 0.0003949562457520226, 'samples': 7822848, 'steps': 15278, 'batch_loss/train': 0.7179674888029695}
+12/24/2021 23:48:42 - INFO - codeparrot_training - Step 15279: {'lr': 0.00039494340259124347, 'samples': 7823360, 'steps': 15279, 'batch_loss/train': 0.7208007965236902}
+12/24/2021 23:48:53 - INFO - codeparrot_training - Step 15280: {'lr': 0.0003949305588542241, 'samples': 7823872, 'steps': 15280, 'batch_loss/train': 0.7616277313791215}
+12/24/2021 23:49:03 - INFO - codeparrot_training - Step 15281: {'lr': 0.00039491771454101555, 'samples': 7824384, 'steps': 15281, 'batch_loss/train': 0.8682294376194477}
+12/24/2021 23:49:16 - INFO - codeparrot_training - Step 15282: {'lr': 0.0003949048696516689, 'samples': 7824896, 'steps': 15282, 'batch_loss/train': 0.8339403097052127}
+12/24/2021 23:49:27 - INFO - codeparrot_training - Step 15283: {'lr': 0.00039489202418623514, 'samples': 7825408, 'steps': 15283, 'batch_loss/train': 1.1996589116752148}
+12/24/2021 23:49:38 - INFO - codeparrot_training - Step 15284: {'lr': 0.0003948791781447655, 'samples': 7825920, 'steps': 15284, 'batch_loss/train': 0.9651167918927968}
+12/24/2021 23:49:48 - INFO - codeparrot_training - Step 15285: {'lr': 0.0003948663315273109, 'samples': 7826432, 'steps': 15285, 'batch_loss/train': 1.0895264390856028}
+12/24/2021 23:50:02 - INFO - codeparrot_training - Step 15286: {'lr': 0.00039485348433392244, 'samples': 7826944, 'steps': 15286, 'batch_loss/train': 0.8015530379489064}
+12/24/2021 23:50:12 - INFO - codeparrot_training - Step 15287: {'lr': 0.00039484063656465123, 'samples': 7827456, 'steps': 15287, 'batch_loss/train': 0.8312156777828932}
+12/24/2021 23:50:23 - INFO - codeparrot_training - Step 15288: {'lr': 0.0003948277882195483, 'samples': 7827968, 'steps': 15288, 'batch_loss/train': 0.6776157435961068}
+12/24/2021 23:50:35 - INFO - codeparrot_training - Step 15289: {'lr': 0.00039481493929866484, 'samples': 7828480, 'steps': 15289, 'batch_loss/train': 0.7711026258766651}
+12/24/2021 23:50:46 - INFO - codeparrot_training - Step 15290: {'lr': 0.0003948020898020519, 'samples': 7828992, 'steps': 15290, 'batch_loss/train': 0.8091305615380406}
+12/24/2021 23:50:56 - INFO - codeparrot_training - Step 15291: {'lr': 0.00039478923972976045, 'samples': 7829504, 'steps': 15291, 'batch_loss/train': 0.8416535463184118}
+12/24/2021 23:51:07 - INFO - codeparrot_training - Step 15292: {'lr': 0.00039477638908184167, 'samples': 7830016, 'steps': 15292, 'batch_loss/train': 0.7902555484324694}
+12/24/2021 23:51:21 - INFO - codeparrot_training - Step 15293: {'lr': 0.0003947635378583467, 'samples': 7830528, 'steps': 15293, 'batch_loss/train': 0.7495507840067148}
+12/24/2021 23:51:32 - INFO - codeparrot_training - Step 15294: {'lr': 0.0003947506860593264, 'samples': 7831040, 'steps': 15294, 'batch_loss/train': 0.814183505717665}
+12/24/2021 23:51:42 - INFO - codeparrot_training - Step 15295: {'lr': 0.0003947378336848322, 'samples': 7831552, 'steps': 15295, 'batch_loss/train': 1.0456463396549225}
+12/24/2021 23:51:55 - INFO - codeparrot_training - Step 15296: {'lr': 0.00039472498073491493, 'samples': 7832064, 'steps': 15296, 'batch_loss/train': 1.7354341787286103}
+12/24/2021 23:52:05 - INFO - codeparrot_training - Step 15297: {'lr': 0.0003947121272096258, 'samples': 7832576, 'steps': 15297, 'batch_loss/train': 0.7719140336848795}
+12/24/2021 23:52:16 - INFO - codeparrot_training - Step 15298: {'lr': 0.00039469927310901585, 'samples': 7833088, 'steps': 15298, 'batch_loss/train': 0.7897148537449539}
+12/24/2021 23:52:28 - INFO - codeparrot_training - Step 15299: {'lr': 0.0003946864184331363, 'samples': 7833600, 'steps': 15299, 'batch_loss/train': 0.8273596549406648}
+12/24/2021 23:52:38 - INFO - codeparrot_training - Step 15300: {'lr': 0.0003946735631820382, 'samples': 7834112, 'steps': 15300, 'batch_loss/train': 0.9460896928794682}
+12/24/2021 23:52:49 - INFO - codeparrot_training - Step 15301: {'lr': 0.00039466070735577255, 'samples': 7834624, 'steps': 15301, 'batch_loss/train': 0.8251147661358118}
+12/24/2021 23:53:00 - INFO - codeparrot_training - Step 15302: {'lr': 0.0003946478509543906, 'samples': 7835136, 'steps': 15302, 'batch_loss/train': 0.7804057290777564}
+12/24/2021 23:53:14 - INFO - codeparrot_training - Step 15303: {'lr': 0.00039463499397794345, 'samples': 7835648, 'steps': 15303, 'batch_loss/train': 0.8204263602383435}
+12/24/2021 23:53:24 - INFO - codeparrot_training - Step 15304: {'lr': 0.00039462213642648216, 'samples': 7836160, 'steps': 15304, 'batch_loss/train': 0.6956490692682564}
+12/24/2021 23:53:35 - INFO - codeparrot_training - Step 15305: {'lr': 0.0003946092783000578, 'samples': 7836672, 'steps': 15305, 'batch_loss/train': 0.827483655884862}
+12/24/2021 23:53:47 - INFO - codeparrot_training - Step 15306: {'lr': 0.0003945964195987216, 'samples': 7837184, 'steps': 15306, 'batch_loss/train': 0.8577577485702932}
+12/24/2021 23:53:57 - INFO - codeparrot_training - Step 15307: {'lr': 0.00039458356032252465, 'samples': 7837696, 'steps': 15307, 'batch_loss/train': 0.877626858651638}
+12/24/2021 23:54:08 - INFO - codeparrot_training - Step 15308: {'lr': 0.000394570700471518, 'samples': 7838208, 'steps': 15308, 'batch_loss/train': 0.7947085397318006}
+12/24/2021 23:54:20 - INFO - codeparrot_training - Step 15309: {'lr': 0.00039455784004575287, 'samples': 7838720, 'steps': 15309, 'batch_loss/train': 0.7105868139769882}
+12/24/2021 23:54:31 - INFO - codeparrot_training - Step 15310: {'lr': 0.0003945449790452803, 'samples': 7839232, 'steps': 15310, 'batch_loss/train': 0.7947533294791356}
+12/24/2021 23:54:42 - INFO - codeparrot_training - Step 15311: {'lr': 0.0003945321174701515, 'samples': 7839744, 'steps': 15311, 'batch_loss/train': 0.9295290433801711}
+12/24/2021 23:54:52 - INFO - codeparrot_training - Step 15312: {'lr': 0.0003945192553204176, 'samples': 7840256, 'steps': 15312, 'batch_loss/train': 1.2544735125266016}
+12/24/2021 23:55:06 - INFO - codeparrot_training - Step 15313: {'lr': 0.0003945063925961297, 'samples': 7840768, 'steps': 15313, 'batch_loss/train': 0.7409102916717529}
+12/24/2021 23:55:17 - INFO - codeparrot_training - Step 15314: {'lr': 0.00039449352929733897, 'samples': 7841280, 'steps': 15314, 'batch_loss/train': 0.934954047203064}
+12/24/2021 23:55:27 - INFO - codeparrot_training - Step 15315: {'lr': 0.00039448066542409647, 'samples': 7841792, 'steps': 15315, 'batch_loss/train': 0.7833278919570148}
+12/24/2021 23:55:39 - INFO - codeparrot_training - Step 15316: {'lr': 0.0003944678009764534, 'samples': 7842304, 'steps': 15316, 'batch_loss/train': 0.6941078037489206}
+12/24/2021 23:55:50 - INFO - codeparrot_training - Step 15317: {'lr': 0.000394454935954461, 'samples': 7842816, 'steps': 15317, 'batch_loss/train': 0.8945236026775092}
+12/24/2021 23:56:01 - INFO - codeparrot_training - Step 15318: {'lr': 0.0003944420703581702, 'samples': 7843328, 'steps': 15318, 'batch_loss/train': 0.8717637844383717}
+12/24/2021 23:56:13 - INFO - codeparrot_training - Step 15319: {'lr': 0.0003944292041876324, 'samples': 7843840, 'steps': 15319, 'batch_loss/train': 0.7810328742489219}
+12/24/2021 23:56:23 - INFO - codeparrot_training - Step 15320: {'lr': 0.00039441633744289847, 'samples': 7844352, 'steps': 15320, 'batch_loss/train': 0.8049283623695374}
+12/24/2021 23:56:34 - INFO - codeparrot_training - Step 15321: {'lr': 0.0003944034701240198, 'samples': 7844864, 'steps': 15321, 'batch_loss/train': 0.8648116923868656}
+12/24/2021 23:56:44 - INFO - codeparrot_training - Step 15322: {'lr': 0.0003943906022310474, 'samples': 7845376, 'steps': 15322, 'batch_loss/train': 0.6674295370467007}
+12/24/2021 23:56:58 - INFO - codeparrot_training - Step 15323: {'lr': 0.0003943777337640325, 'samples': 7845888, 'steps': 15323, 'batch_loss/train': 0.6943317730911076}
+12/24/2021 23:57:09 - INFO - codeparrot_training - Step 15324: {'lr': 0.0003943648647230263, 'samples': 7846400, 'steps': 15324, 'batch_loss/train': 0.84399195574224}
+12/24/2021 23:57:19 - INFO - codeparrot_training - Step 15325: {'lr': 0.00039435199510807985, 'samples': 7846912, 'steps': 15325, 'batch_loss/train': 0.8206710597733036}
+12/24/2021 23:57:32 - INFO - codeparrot_training - Step 15326: {'lr': 0.0003943391249192444, 'samples': 7847424, 'steps': 15326, 'batch_loss/train': 0.7402524277567863}
+12/24/2021 23:57:42 - INFO - codeparrot_training - Step 15327: {'lr': 0.0003943262541565711, 'samples': 7847936, 'steps': 15327, 'batch_loss/train': 0.8995179804041982}
+12/24/2021 23:57:53 - INFO - codeparrot_training - Step 15328: {'lr': 0.0003943133828201111, 'samples': 7848448, 'steps': 15328, 'batch_loss/train': 0.7442954215221107}
+12/24/2021 23:58:05 - INFO - codeparrot_training - Step 15329: {'lr': 0.0003943005109099156, 'samples': 7848960, 'steps': 15329, 'batch_loss/train': 0.7635772693902254}
+12/24/2021 23:58:15 - INFO - codeparrot_training - Step 15330: {'lr': 0.00039428763842603567, 'samples': 7849472, 'steps': 15330, 'batch_loss/train': 0.9991921787150204}
+12/24/2021 23:58:26 - INFO - codeparrot_training - Step 15331: {'lr': 0.00039427476536852264, 'samples': 7849984, 'steps': 15331, 'batch_loss/train': 0.8093024604022503}
+12/24/2021 23:58:37 - INFO - codeparrot_training - Step 15332: {'lr': 0.00039426189173742763, 'samples': 7850496, 'steps': 15332, 'batch_loss/train': 0.8615695964545012}
+12/24/2021 23:58:51 - INFO - codeparrot_training - Step 15333: {'lr': 0.00039424901753280176, 'samples': 7851008, 'steps': 15333, 'batch_loss/train': 0.7762933578342199}
+12/24/2021 23:59:02 - INFO - codeparrot_training - Step 15334: {'lr': 0.00039423614275469626, 'samples': 7851520, 'steps': 15334, 'batch_loss/train': 1.2032432123087347}
+12/24/2021 23:59:12 - INFO - codeparrot_training - Step 15335: {'lr': 0.0003942232674031624, 'samples': 7852032, 'steps': 15335, 'batch_loss/train': 0.7871411154046655}
+12/24/2021 23:59:24 - INFO - codeparrot_training - Step 15336: {'lr': 0.0003942103914782512, 'samples': 7852544, 'steps': 15336, 'batch_loss/train': 0.8919547973200679}
+12/24/2021 23:59:35 - INFO - codeparrot_training - Step 15337: {'lr': 0.000394197514980014, 'samples': 7853056, 'steps': 15337, 'batch_loss/train': 0.978473620954901}
+12/24/2021 23:59:46 - INFO - codeparrot_training - Step 15338: {'lr': 0.0003941846379085019, 'samples': 7853568, 'steps': 15338, 'batch_loss/train': 0.8288198690861464}
+12/24/2021 23:59:58 - INFO - codeparrot_training - Step 15339: {'lr': 0.00039417176026376613, 'samples': 7854080, 'steps': 15339, 'batch_loss/train': 0.8032253300771117}
+12/25/2021 00:00:08 - INFO - codeparrot_training - Step 15340: {'lr': 0.0003941588820458578, 'samples': 7854592, 'steps': 15340, 'batch_loss/train': 0.7834733896888793}
+12/25/2021 00:00:19 - INFO - codeparrot_training - Step 15341: {'lr': 0.0003941460032548283, 'samples': 7855104, 'steps': 15341, 'batch_loss/train': 0.9138165982440114}
+12/25/2021 00:00:29 - INFO - codeparrot_training - Step 15342: {'lr': 0.00039413312389072864, 'samples': 7855616, 'steps': 15342, 'batch_loss/train': 0.9806715538725257}
+12/25/2021 00:00:43 - INFO - codeparrot_training - Step 15343: {'lr': 0.0003941202439536101, 'samples': 7856128, 'steps': 15343, 'batch_loss/train': 0.7262321896851063}
+12/25/2021 00:00:54 - INFO - codeparrot_training - Step 15344: {'lr': 0.00039410736344352396, 'samples': 7856640, 'steps': 15344, 'batch_loss/train': 0.8052313097286969}
+12/25/2021 00:01:04 - INFO - codeparrot_training - Step 15345: {'lr': 0.00039409448236052137, 'samples': 7857152, 'steps': 15345, 'batch_loss/train': 0.7908361717127264}
+12/25/2021 00:01:17 - INFO - codeparrot_training - Step 15346: {'lr': 0.00039408160070465346, 'samples': 7857664, 'steps': 15346, 'batch_loss/train': 0.8719135774299502}
+12/25/2021 00:01:27 - INFO - codeparrot_training - Step 15347: {'lr': 0.0003940687184759715, 'samples': 7858176, 'steps': 15347, 'batch_loss/train': 0.7877610977739096}
+12/25/2021 00:01:38 - INFO - codeparrot_training - Step 15348: {'lr': 0.00039405583567452674, 'samples': 7858688, 'steps': 15348, 'batch_loss/train': 0.8835359560325742}
+12/25/2021 00:01:52 - INFO - codeparrot_training - Step 15349: {'lr': 0.00039404295230037033, 'samples': 7859200, 'steps': 15349, 'batch_loss/train': 0.7950740053784102}
+12/25/2021 00:02:02 - INFO - codeparrot_training - Step 15350: {'lr': 0.0003940300683535536, 'samples': 7859712, 'steps': 15350, 'batch_loss/train': 0.7297645083162934}
+12/25/2021 00:02:13 - INFO - codeparrot_training - Step 15351: {'lr': 0.00039401718383412764, 'samples': 7860224, 'steps': 15351, 'batch_loss/train': 0.7984880302101374}
+12/25/2021 00:02:24 - INFO - codeparrot_training - Step 15352: {'lr': 0.00039400429874214375, 'samples': 7860736, 'steps': 15352, 'batch_loss/train': 0.7347029009833932}
+12/25/2021 00:02:36 - INFO - codeparrot_training - Step 15353: {'lr': 0.0003939914130776532, 'samples': 7861248, 'steps': 15353, 'batch_loss/train': 0.7624992993660271}
+12/25/2021 00:02:46 - INFO - codeparrot_training - Step 15354: {'lr': 0.00039397852684070714, 'samples': 7861760, 'steps': 15354, 'batch_loss/train': 0.8180785411968827}
+12/25/2021 00:02:57 - INFO - codeparrot_training - Step 15355: {'lr': 0.00039396564003135677, 'samples': 7862272, 'steps': 15355, 'batch_loss/train': 0.8469901252537966}
+12/25/2021 00:03:09 - INFO - codeparrot_training - Step 15356: {'lr': 0.0003939527526496534, 'samples': 7862784, 'steps': 15356, 'batch_loss/train': 0.8815382746979594}
+12/25/2021 00:03:20 - INFO - codeparrot_training - Step 15357: {'lr': 0.00039393986469564825, 'samples': 7863296, 'steps': 15357, 'batch_loss/train': 0.9258132046088576}
+12/25/2021 00:03:30 - INFO - codeparrot_training - Step 15358: {'lr': 0.0003939269761693925, 'samples': 7863808, 'steps': 15358, 'batch_loss/train': 1.0674787480384111}
+12/25/2021 00:03:42 - INFO - codeparrot_training - Step 15359: {'lr': 0.00039391408707093747, 'samples': 7864320, 'steps': 15359, 'batch_loss/train': 0.8111414082814008}
+12/25/2021 00:03:53 - INFO - codeparrot_training - Step 15360: {'lr': 0.00039390119740033435, 'samples': 7864832, 'steps': 15360, 'batch_loss/train': 0.7386034093797207}
+12/25/2021 00:04:04 - INFO - codeparrot_training - Step 15361: {'lr': 0.00039388830715763446, 'samples': 7865344, 'steps': 15361, 'batch_loss/train': 0.8536323141306639}
+12/25/2021 00:04:14 - INFO - codeparrot_training - Step 15362: {'lr': 0.00039387541634288895, 'samples': 7865856, 'steps': 15362, 'batch_loss/train': 0.7349637674633414}
+12/25/2021 00:04:28 - INFO - codeparrot_training - Step 15363: {'lr': 0.00039386252495614917, 'samples': 7866368, 'steps': 15363, 'batch_loss/train': 0.7472774405032396}
+12/25/2021 00:04:39 - INFO - codeparrot_training - Step 15364: {'lr': 0.00039384963299746623, 'samples': 7866880, 'steps': 15364, 'batch_loss/train': 0.7057433561421931}
+12/25/2021 00:04:49 - INFO - codeparrot_training - Step 15365: {'lr': 0.0003938367404668915, 'samples': 7867392, 'steps': 15365, 'batch_loss/train': 0.8308334683533758}
+12/25/2021 00:05:01 - INFO - codeparrot_training - Step 15366: {'lr': 0.0003938238473644762, 'samples': 7867904, 'steps': 15366, 'batch_loss/train': 0.7694023521617055}
+12/25/2021 00:05:12 - INFO - codeparrot_training - Step 15367: {'lr': 0.00039381095369027164, 'samples': 7868416, 'steps': 15367, 'batch_loss/train': 0.8482060246169567}
+12/25/2021 00:05:22 - INFO - codeparrot_training - Step 15368: {'lr': 0.0003937980594443289, 'samples': 7868928, 'steps': 15368, 'batch_loss/train': 0.7649976285174489}
+12/25/2021 00:05:34 - INFO - codeparrot_training - Step 15369: {'lr': 0.0003937851646266995, 'samples': 7869440, 'steps': 15369, 'batch_loss/train': 0.8743349593132734}
+12/25/2021 00:05:45 - INFO - codeparrot_training - Step 15370: {'lr': 0.00039377226923743445, 'samples': 7869952, 'steps': 15370, 'batch_loss/train': 1.009115882217884}
+12/25/2021 00:05:56 - INFO - codeparrot_training - Step 15371: {'lr': 0.0003937593732765853, 'samples': 7870464, 'steps': 15371, 'batch_loss/train': 0.7386303464882076}
+12/25/2021 00:06:06 - INFO - codeparrot_training - Step 15372: {'lr': 0.00039374647674420303, 'samples': 7870976, 'steps': 15372, 'batch_loss/train': 0.7017532768659294}
+12/25/2021 00:06:19 - INFO - codeparrot_training - Step 15373: {'lr': 0.0003937335796403391, 'samples': 7871488, 'steps': 15373, 'batch_loss/train': 0.8037280533462763}
+12/25/2021 00:06:30 - INFO - codeparrot_training - Step 15374: {'lr': 0.00039372068196504473, 'samples': 7872000, 'steps': 15374, 'batch_loss/train': 0.8005885374732316}
+12/25/2021 00:06:40 - INFO - codeparrot_training - Step 15375: {'lr': 0.00039370778371837116, 'samples': 7872512, 'steps': 15375, 'batch_loss/train': 0.7594993752427399}
+12/25/2021 00:06:55 - INFO - codeparrot_training - Step 15376: {'lr': 0.00039369488490036977, 'samples': 7873024, 'steps': 15376, 'batch_loss/train': 0.923601589165628}
+12/25/2021 00:07:05 - INFO - codeparrot_training - Step 15377: {'lr': 0.00039368198551109173, 'samples': 7873536, 'steps': 15377, 'batch_loss/train': 0.8154107974842191}
+12/25/2021 00:07:16 - INFO - codeparrot_training - Step 15378: {'lr': 0.00039366908555058845, 'samples': 7874048, 'steps': 15378, 'batch_loss/train': 0.6304224440827966}
+12/25/2021 00:07:28 - INFO - codeparrot_training - Step 15379: {'lr': 0.000393656185018911, 'samples': 7874560, 'steps': 15379, 'batch_loss/train': 0.8558851694688201}
+12/25/2021 00:07:38 - INFO - codeparrot_training - Step 15380: {'lr': 0.00039364328391611094, 'samples': 7875072, 'steps': 15380, 'batch_loss/train': 0.8929771557450294}
+12/25/2021 00:07:49 - INFO - codeparrot_training - Step 15381: {'lr': 0.00039363038224223923, 'samples': 7875584, 'steps': 15381, 'batch_loss/train': 0.7742041076999158}
+12/25/2021 00:08:03 - INFO - codeparrot_training - Step 15382: {'lr': 0.00039361747999734756, 'samples': 7876096, 'steps': 15382, 'batch_loss/train': 0.7681278521195054}
+12/25/2021 00:08:14 - INFO - codeparrot_training - Step 15383: {'lr': 0.0003936045771814869, 'samples': 7876608, 'steps': 15383, 'batch_loss/train': 0.79065868165344}
+12/25/2021 00:08:24 - INFO - codeparrot_training - Step 15384: {'lr': 0.0003935916737947086, 'samples': 7877120, 'steps': 15384, 'batch_loss/train': 0.802138869650662}
+12/25/2021 00:08:35 - INFO - codeparrot_training - Step 15385: {'lr': 0.0003935787698370642, 'samples': 7877632, 'steps': 15385, 'batch_loss/train': 0.8399899676442146}
+12/25/2021 00:08:47 - INFO - codeparrot_training - Step 15386: {'lr': 0.0003935658653086047, 'samples': 7878144, 'steps': 15386, 'batch_loss/train': 0.8955361098051071}
+12/25/2021 00:08:58 - INFO - codeparrot_training - Step 15387: {'lr': 0.0003935529602093816, 'samples': 7878656, 'steps': 15387, 'batch_loss/train': 0.8994762925431132}
+12/25/2021 00:09:08 - INFO - codeparrot_training - Step 15388: {'lr': 0.0003935400545394461, 'samples': 7879168, 'steps': 15388, 'batch_loss/train': 0.8322640594560653}
+12/25/2021 00:09:20 - INFO - codeparrot_training - Step 15389: {'lr': 0.0003935271482988495, 'samples': 7879680, 'steps': 15389, 'batch_loss/train': 0.691342709120363}
+12/25/2021 00:09:31 - INFO - codeparrot_training - Step 15390: {'lr': 0.00039351424148764317, 'samples': 7880192, 'steps': 15390, 'batch_loss/train': 0.7536364635452628}
+12/25/2021 00:09:42 - INFO - codeparrot_training - Step 15391: {'lr': 0.0003935013341058785, 'samples': 7880704, 'steps': 15391, 'batch_loss/train': 0.8349892925471067}
+12/25/2021 00:09:55 - INFO - codeparrot_training - Step 15392: {'lr': 0.0003934884261536066, 'samples': 7881216, 'steps': 15392, 'batch_loss/train': 0.831968973390758}
+12/25/2021 00:10:06 - INFO - codeparrot_training - Step 15393: {'lr': 0.0003934755176308789, 'samples': 7881728, 'steps': 15393, 'batch_loss/train': 0.9420473920181394}
+12/25/2021 00:10:17 - INFO - codeparrot_training - Step 15394: {'lr': 0.00039346260853774675, 'samples': 7882240, 'steps': 15394, 'batch_loss/train': 0.7862703111022711}
+12/25/2021 00:10:27 - INFO - codeparrot_training - Step 15395: {'lr': 0.0003934496988742614, 'samples': 7882752, 'steps': 15395, 'batch_loss/train': 0.8618777603842318}
+12/25/2021 00:10:39 - INFO - codeparrot_training - Step 15396: {'lr': 0.00039343678864047426, 'samples': 7883264, 'steps': 15396, 'batch_loss/train': 0.8074067840352654}
+12/25/2021 00:10:50 - INFO - codeparrot_training - Step 15397: {'lr': 0.00039342387783643663, 'samples': 7883776, 'steps': 15397, 'batch_loss/train': 0.8848116304725409}
+12/25/2021 00:11:01 - INFO - codeparrot_training - Step 15398: {'lr': 0.0003934109664621998, 'samples': 7884288, 'steps': 15398, 'batch_loss/train': 0.8217656603083014}
+12/25/2021 00:11:15 - INFO - codeparrot_training - Step 15399: {'lr': 0.00039339805451781506, 'samples': 7884800, 'steps': 15399, 'batch_loss/train': 0.7408628053963184}
+12/25/2021 00:11:25 - INFO - codeparrot_training - Step 15400: {'lr': 0.00039338514200333384, 'samples': 7885312, 'steps': 15400, 'batch_loss/train': 0.7160932403057814}
+12/25/2021 00:11:36 - INFO - codeparrot_training - Step 15401: {'lr': 0.0003933722289188074, 'samples': 7885824, 'steps': 15401, 'batch_loss/train': 0.8668087217956781}
+12/25/2021 00:11:48 - INFO - codeparrot_training - Step 15402: {'lr': 0.00039335931526428714, 'samples': 7886336, 'steps': 15402, 'batch_loss/train': 0.8535954095423222}
+12/25/2021 00:11:59 - INFO - codeparrot_training - Step 15403: {'lr': 0.00039334640103982443, 'samples': 7886848, 'steps': 15403, 'batch_loss/train': 0.7793702550698072}
+12/25/2021 00:12:09 - INFO - codeparrot_training - Step 15404: {'lr': 0.0003933334862454705, 'samples': 7887360, 'steps': 15404, 'batch_loss/train': 0.7852452073711902}
+12/25/2021 00:12:20 - INFO - codeparrot_training - Step 15405: {'lr': 0.0003933205708812768, 'samples': 7887872, 'steps': 15405, 'batch_loss/train': 0.7534645590931177}
+12/25/2021 00:12:33 - INFO - codeparrot_training - Step 15406: {'lr': 0.0003933076549472946, 'samples': 7888384, 'steps': 15406, 'batch_loss/train': 0.8160502659156919}
+12/25/2021 00:12:43 - INFO - codeparrot_training - Step 15407: {'lr': 0.00039329473844357515, 'samples': 7888896, 'steps': 15407, 'batch_loss/train': 0.7635744772851467}
+12/25/2021 00:12:54 - INFO - codeparrot_training - Step 15408: {'lr': 0.00039328182137017006, 'samples': 7889408, 'steps': 15408, 'batch_loss/train': 0.7269302839413285}
+12/25/2021 00:13:06 - INFO - codeparrot_training - Step 15409: {'lr': 0.0003932689037271305, 'samples': 7889920, 'steps': 15409, 'batch_loss/train': 0.696372346021235}
+12/25/2021 00:13:16 - INFO - codeparrot_training - Step 15410: {'lr': 0.0003932559855145079, 'samples': 7890432, 'steps': 15410, 'batch_loss/train': 0.8139834208413959}
+12/25/2021 00:13:27 - INFO - codeparrot_training - Step 15411: {'lr': 0.0003932430667323536, 'samples': 7890944, 'steps': 15411, 'batch_loss/train': 0.8406892237253487}
+12/25/2021 00:13:41 - INFO - codeparrot_training - Step 15412: {'lr': 0.00039323014738071896, 'samples': 7891456, 'steps': 15412, 'batch_loss/train': 0.9310083440504968}
+12/25/2021 00:13:51 - INFO - codeparrot_training - Step 15413: {'lr': 0.0003932172274596553, 'samples': 7891968, 'steps': 15413, 'batch_loss/train': 0.87450149981305}
+12/25/2021 00:14:02 - INFO - codeparrot_training - Step 15414: {'lr': 0.00039320430696921407, 'samples': 7892480, 'steps': 15414, 'batch_loss/train': 0.7474045334383845}
+12/25/2021 00:14:14 - INFO - codeparrot_training - Step 15415: {'lr': 0.0003931913859094465, 'samples': 7892992, 'steps': 15415, 'batch_loss/train': 0.8597736386582255}
+12/25/2021 00:14:25 - INFO - codeparrot_training - Step 15416: {'lr': 0.00039317846428040416, 'samples': 7893504, 'steps': 15416, 'batch_loss/train': 0.809345924295485}
+12/25/2021 00:14:36 - INFO - codeparrot_training - Step 15417: {'lr': 0.00039316554208213825, 'samples': 7894016, 'steps': 15417, 'batch_loss/train': 0.7909046276472509}
+12/25/2021 00:14:46 - INFO - codeparrot_training - Step 15418: {'lr': 0.00039315261931470013, 'samples': 7894528, 'steps': 15418, 'batch_loss/train': 0.8312062285840511}
+12/25/2021 00:14:58 - INFO - codeparrot_training - Step 15419: {'lr': 0.00039313969597814136, 'samples': 7895040, 'steps': 15419, 'batch_loss/train': 0.8647487591952085}
+12/25/2021 00:15:09 - INFO - codeparrot_training - Step 15420: {'lr': 0.0003931267720725131, 'samples': 7895552, 'steps': 15420, 'batch_loss/train': 0.8310729628428817}
+12/25/2021 00:15:19 - INFO - codeparrot_training - Step 15421: {'lr': 0.00039311384759786695, 'samples': 7896064, 'steps': 15421, 'batch_loss/train': 0.7724769804626703}
+12/25/2021 00:15:34 - INFO - codeparrot_training - Step 15422: {'lr': 0.00039310092255425414, 'samples': 7896576, 'steps': 15422, 'batch_loss/train': 0.8304917574860156}
+12/25/2021 00:15:44 - INFO - codeparrot_training - Step 15423: {'lr': 0.0003930879969417261, 'samples': 7897088, 'steps': 15423, 'batch_loss/train': 0.7945666725281626}
+12/25/2021 00:15:55 - INFO - codeparrot_training - Step 15424: {'lr': 0.0003930750707603342, 'samples': 7897600, 'steps': 15424, 'batch_loss/train': 0.8140885727480054}
+12/25/2021 00:16:06 - INFO - codeparrot_training - Step 15425: {'lr': 0.0003930621440101298, 'samples': 7898112, 'steps': 15425, 'batch_loss/train': 0.8673714464530349}
+12/25/2021 00:16:18 - INFO - codeparrot_training - Step 15426: {'lr': 0.0003930492166911644, 'samples': 7898624, 'steps': 15426, 'batch_loss/train': 0.8208811087533832}
+12/25/2021 00:16:28 - INFO - codeparrot_training - Step 15427: {'lr': 0.0003930362888034893, 'samples': 7899136, 'steps': 15427, 'batch_loss/train': 0.6008962830528617}
+12/25/2021 00:16:39 - INFO - codeparrot_training - Step 15428: {'lr': 0.0003930233603471559, 'samples': 7899648, 'steps': 15428, 'batch_loss/train': 0.8424033559858799}
+12/25/2021 00:16:51 - INFO - codeparrot_training - Step 15429: {'lr': 0.0003930104313222157, 'samples': 7900160, 'steps': 15429, 'batch_loss/train': 0.8384014121256769}
+12/25/2021 00:17:02 - INFO - codeparrot_training - Step 15430: {'lr': 0.00039299750172871995, 'samples': 7900672, 'steps': 15430, 'batch_loss/train': 0.7091637207195163}
+12/25/2021 00:17:12 - INFO - codeparrot_training - Step 15431: {'lr': 0.00039298457156672015, 'samples': 7901184, 'steps': 15431, 'batch_loss/train': 0.817709757538978}
+12/25/2021 00:17:26 - INFO - codeparrot_training - Step 15432: {'lr': 0.00039297164083626767, 'samples': 7901696, 'steps': 15432, 'batch_loss/train': 0.6525339372456074}
+12/25/2021 00:17:37 - INFO - codeparrot_training - Step 15433: {'lr': 0.00039295870953741396, 'samples': 7902208, 'steps': 15433, 'batch_loss/train': 0.8550559850409627}
+12/25/2021 00:17:47 - INFO - codeparrot_training - Step 15434: {'lr': 0.00039294577767021036, 'samples': 7902720, 'steps': 15434, 'batch_loss/train': 0.8230439687613398}
+12/25/2021 00:18:00 - INFO - codeparrot_training - Step 15435: {'lr': 0.00039293284523470837, 'samples': 7903232, 'steps': 15435, 'batch_loss/train': 0.7900687619112432}
+12/25/2021 00:18:10 - INFO - codeparrot_training - Step 15436: {'lr': 0.0003929199122309593, 'samples': 7903744, 'steps': 15436, 'batch_loss/train': 0.8334807460196316}
+12/25/2021 00:18:21 - INFO - codeparrot_training - Step 15437: {'lr': 0.0003929069786590147, 'samples': 7904256, 'steps': 15437, 'batch_loss/train': 0.7249587115366012}
+12/25/2021 00:18:31 - INFO - codeparrot_training - Step 15438: {'lr': 0.00039289404451892584, 'samples': 7904768, 'steps': 15438, 'batch_loss/train': 0.8580064000561833}
+12/25/2021 00:18:45 - INFO - codeparrot_training - Step 15439: {'lr': 0.0003928811098107442, 'samples': 7905280, 'steps': 15439, 'batch_loss/train': 0.6998079603072256}
+12/25/2021 00:18:56 - INFO - codeparrot_training - Step 15440: {'lr': 0.00039286817453452127, 'samples': 7905792, 'steps': 15440, 'batch_loss/train': 0.6649850859539583}
+12/25/2021 00:19:06 - INFO - codeparrot_training - Step 15441: {'lr': 0.0003928552386903084, 'samples': 7906304, 'steps': 15441, 'batch_loss/train': 0.8246154179796576}
+12/25/2021 00:19:18 - INFO - codeparrot_training - Step 15442: {'lr': 0.0003928423022781571, 'samples': 7906816, 'steps': 15442, 'batch_loss/train': 0.8495868630707264}
+12/25/2021 00:19:29 - INFO - codeparrot_training - Step 15443: {'lr': 0.0003928293652981187, 'samples': 7907328, 'steps': 15443, 'batch_loss/train': 0.8034689659252763}
+12/25/2021 00:19:40 - INFO - codeparrot_training - Step 15444: {'lr': 0.0003928164277502446, 'samples': 7907840, 'steps': 15444, 'batch_loss/train': 0.8321050174999982}
+12/25/2021 00:19:52 - INFO - codeparrot_training - Step 15445: {'lr': 0.0003928034896345864, 'samples': 7908352, 'steps': 15445, 'batch_loss/train': 0.792326987022534}
+12/25/2021 00:20:02 - INFO - codeparrot_training - Step 15446: {'lr': 0.00039279055095119543, 'samples': 7908864, 'steps': 15446, 'batch_loss/train': 0.8171819006092846}
+12/25/2021 00:20:13 - INFO - codeparrot_training - Step 15447: {'lr': 0.00039277761170012314, 'samples': 7909376, 'steps': 15447, 'batch_loss/train': 1.5732653397135437}
+12/25/2021 00:20:24 - INFO - codeparrot_training - Step 15448: {'lr': 0.000392764671881421, 'samples': 7909888, 'steps': 15448, 'batch_loss/train': 0.7629914609715343}
+12/25/2021 00:20:38 - INFO - codeparrot_training - Step 15449: {'lr': 0.00039275173149514033, 'samples': 7910400, 'steps': 15449, 'batch_loss/train': 1.6077060787938535}
+12/25/2021 00:20:49 - INFO - codeparrot_training - Step 15450: {'lr': 0.00039273879054133276, 'samples': 7910912, 'steps': 15450, 'batch_loss/train': 1.080953678349033}
+12/25/2021 00:20:59 - INFO - codeparrot_training - Step 15451: {'lr': 0.00039272584902004965, 'samples': 7911424, 'steps': 15451, 'batch_loss/train': 0.6728944568894804}
+12/25/2021 00:21:11 - INFO - codeparrot_training - Step 15452: {'lr': 0.0003927129069313425, 'samples': 7911936, 'steps': 15452, 'batch_loss/train': 0.7973935091868043}
+12/25/2021 00:21:22 - INFO - codeparrot_training - Step 15453: {'lr': 0.00039269996427526265, 'samples': 7912448, 'steps': 15453, 'batch_loss/train': 0.8017470501363277}
+12/25/2021 00:21:33 - INFO - codeparrot_training - Step 15454: {'lr': 0.0003926870210518616, 'samples': 7912960, 'steps': 15454, 'batch_loss/train': 0.8062455449253321}
+12/25/2021 00:21:43 - INFO - codeparrot_training - Step 15455: {'lr': 0.0003926740772611909, 'samples': 7913472, 'steps': 15455, 'batch_loss/train': 0.7315845232224092}
+12/25/2021 00:21:55 - INFO - codeparrot_training - Step 15456: {'lr': 0.00039266113290330196, 'samples': 7913984, 'steps': 15456, 'batch_loss/train': 0.8114470988512039}
+12/25/2021 00:22:06 - INFO - codeparrot_training - Step 15457: {'lr': 0.0003926481879782461, 'samples': 7914496, 'steps': 15457, 'batch_loss/train': 0.8648897334933281}
+12/25/2021 00:22:16 - INFO - codeparrot_training - Step 15458: {'lr': 0.00039263524248607496, 'samples': 7915008, 'steps': 15458, 'batch_loss/train': 0.8705814396962523}
+12/25/2021 00:22:29 - INFO - codeparrot_training - Step 15459: {'lr': 0.00039262229642684, 'samples': 7915520, 'steps': 15459, 'batch_loss/train': 0.9686509789898992}
+12/25/2021 00:22:39 - INFO - codeparrot_training - Step 15460: {'lr': 0.0003926093498005926, 'samples': 7916032, 'steps': 15460, 'batch_loss/train': 1.1495653428137302}
+12/25/2021 00:22:50 - INFO - codeparrot_training - Step 15461: {'lr': 0.00039259640260738433, 'samples': 7916544, 'steps': 15461, 'batch_loss/train': 0.7696927483193576}
+12/25/2021 00:23:04 - INFO - codeparrot_training - Step 15462: {'lr': 0.0003925834548472665, 'samples': 7917056, 'steps': 15462, 'batch_loss/train': 0.7790194143308327}
+12/25/2021 00:23:15 - INFO - codeparrot_training - Step 15463: {'lr': 0.0003925705065202908, 'samples': 7917568, 'steps': 15463, 'batch_loss/train': 0.7402936359867454}
+12/25/2021 00:23:26 - INFO - codeparrot_training - Step 15464: {'lr': 0.0003925575576265086, 'samples': 7918080, 'steps': 15464, 'batch_loss/train': 0.7631677582394332}
+12/25/2021 00:23:36 - INFO - codeparrot_training - Step 15465: {'lr': 0.0003925446081659713, 'samples': 7918592, 'steps': 15465, 'batch_loss/train': 1.3681001856457442}
+12/25/2021 00:23:48 - INFO - codeparrot_training - Step 15466: {'lr': 0.00039253165813873047, 'samples': 7919104, 'steps': 15466, 'batch_loss/train': 0.9209087183699012}
+12/25/2021 00:23:59 - INFO - codeparrot_training - Step 15467: {'lr': 0.00039251870754483767, 'samples': 7919616, 'steps': 15467, 'batch_loss/train': 0.6643075267784297}
+12/25/2021 00:24:10 - INFO - codeparrot_training - Step 15468: {'lr': 0.00039250575638434423, 'samples': 7920128, 'steps': 15468, 'batch_loss/train': 0.8092904724180698}
+12/25/2021 00:24:24 - INFO - codeparrot_training - Step 15469: {'lr': 0.00039249280465730165, 'samples': 7920640, 'steps': 15469, 'batch_loss/train': 0.8748049465939403}
+12/25/2021 00:24:35 - INFO - codeparrot_training - Step 15470: {'lr': 0.0003924798523637616, 'samples': 7921152, 'steps': 15470, 'batch_loss/train': 0.7931233043782413}
+12/25/2021 00:24:45 - INFO - codeparrot_training - Step 15471: {'lr': 0.0003924668995037754, 'samples': 7921664, 'steps': 15471, 'batch_loss/train': 1.6996760331094265}
+12/25/2021 00:24:56 - INFO - codeparrot_training - Step 15472: {'lr': 0.0003924539460773946, 'samples': 7922176, 'steps': 15472, 'batch_loss/train': 0.799569989554584}
+12/25/2021 00:25:08 - INFO - codeparrot_training - Step 15473: {'lr': 0.00039244099208467074, 'samples': 7922688, 'steps': 15473, 'batch_loss/train': 0.8034088630229235}
+12/25/2021 00:25:19 - INFO - codeparrot_training - Step 15474: {'lr': 0.0003924280375256553, 'samples': 7923200, 'steps': 15474, 'batch_loss/train': 0.8535936614498496}
+12/25/2021 00:25:29 - INFO - codeparrot_training - Step 15475: {'lr': 0.00039241508240039956, 'samples': 7923712, 'steps': 15475, 'batch_loss/train': 0.8388318466022611}
+12/25/2021 00:25:41 - INFO - codeparrot_training - Step 15476: {'lr': 0.0003924021267089555, 'samples': 7924224, 'steps': 15476, 'batch_loss/train': 0.7392398132942617}
+12/25/2021 00:25:52 - INFO - codeparrot_training - Step 15477: {'lr': 0.00039238917045137414, 'samples': 7924736, 'steps': 15477, 'batch_loss/train': 0.7558491444215178}
+12/25/2021 00:26:02 - INFO - codeparrot_training - Step 15478: {'lr': 0.0003923762136277074, 'samples': 7925248, 'steps': 15478, 'batch_loss/train': 0.7909296401776373}
+12/25/2021 00:26:16 - INFO - codeparrot_training - Step 15479: {'lr': 0.0003923632562380064, 'samples': 7925760, 'steps': 15479, 'batch_loss/train': 0.9313461170531809}
+12/25/2021 00:26:27 - INFO - codeparrot_training - Step 15480: {'lr': 0.00039235029828232296, 'samples': 7926272, 'steps': 15480, 'batch_loss/train': 0.849990067537874}
+12/25/2021 00:26:37 - INFO - codeparrot_training - Step 15481: {'lr': 0.0003923373397607084, 'samples': 7926784, 'steps': 15481, 'batch_loss/train': 0.8472864180803299}
+12/25/2021 00:26:48 - INFO - codeparrot_training - Step 15482: {'lr': 0.0003923243806732144, 'samples': 7927296, 'steps': 15482, 'batch_loss/train': 0.8863506549969316}
+12/25/2021 00:27:01 - INFO - codeparrot_training - Step 15483: {'lr': 0.00039231142101989235, 'samples': 7927808, 'steps': 15483, 'batch_loss/train': 0.8423961414955556}
+12/25/2021 00:27:11 - INFO - codeparrot_training - Step 15484: {'lr': 0.0003922984608007939, 'samples': 7928320, 'steps': 15484, 'batch_loss/train': 0.8887643441557884}
+12/25/2021 00:27:22 - INFO - codeparrot_training - Step 15485: {'lr': 0.0003922855000159704, 'samples': 7928832, 'steps': 15485, 'batch_loss/train': 0.7831525625661016}
+12/25/2021 00:27:34 - INFO - codeparrot_training - Step 15486: {'lr': 0.00039227253866547354, 'samples': 7929344, 'steps': 15486, 'batch_loss/train': 0.7329606304410845}
+12/25/2021 00:27:45 - INFO - codeparrot_training - Step 15487: {'lr': 0.0003922595767493548, 'samples': 7929856, 'steps': 15487, 'batch_loss/train': 0.667101523373276}
+12/25/2021 00:27:56 - INFO - codeparrot_training - Step 15488: {'lr': 0.00039224661426766566, 'samples': 7930368, 'steps': 15488, 'batch_loss/train': 0.9813191811554134}
+12/25/2021 00:28:09 - INFO - codeparrot_training - Step 15489: {'lr': 0.00039223365122045774, 'samples': 7930880, 'steps': 15489, 'batch_loss/train': 1.569396206876263}
+12/25/2021 00:28:20 - INFO - codeparrot_training - Step 15490: {'lr': 0.00039222068760778243, 'samples': 7931392, 'steps': 15490, 'batch_loss/train': 0.7854859274812043}
+12/25/2021 00:28:31 - INFO - codeparrot_training - Step 15491: {'lr': 0.00039220772342969147, 'samples': 7931904, 'steps': 15491, 'batch_loss/train': 0.8249241779558361}
+12/25/2021 00:28:41 - INFO - codeparrot_training - Step 15492: {'lr': 0.00039219475868623624, 'samples': 7932416, 'steps': 15492, 'batch_loss/train': 0.9155715396627784}
+12/25/2021 00:28:53 - INFO - codeparrot_training - Step 15493: {'lr': 0.0003921817933774684, 'samples': 7932928, 'steps': 15493, 'batch_loss/train': 0.8992560263723135}
+12/25/2021 00:29:04 - INFO - codeparrot_training - Step 15494: {'lr': 0.00039216882750343934, 'samples': 7933440, 'steps': 15494, 'batch_loss/train': 0.8340519033372402}
+12/25/2021 00:29:14 - INFO - codeparrot_training - Step 15495: {'lr': 0.0003921558610642008, 'samples': 7933952, 'steps': 15495, 'batch_loss/train': 0.8282835800200701}
+12/25/2021 00:29:26 - INFO - codeparrot_training - Step 15496: {'lr': 0.00039214289405980416, 'samples': 7934464, 'steps': 15496, 'batch_loss/train': 0.8108610678464174}
+12/25/2021 00:29:37 - INFO - codeparrot_training - Step 15497: {'lr': 0.0003921299264903011, 'samples': 7934976, 'steps': 15497, 'batch_loss/train': 0.9232405844377354}
+12/25/2021 00:29:48 - INFO - codeparrot_training - Step 15498: {'lr': 0.0003921169583557431, 'samples': 7935488, 'steps': 15498, 'batch_loss/train': 0.8240866083651781}
+12/25/2021 00:30:01 - INFO - codeparrot_training - Step 15499: {'lr': 0.00039210398965618164, 'samples': 7936000, 'steps': 15499, 'batch_loss/train': 0.7807441803161055}
+12/25/2021 00:30:12 - INFO - codeparrot_training - Step 15500: {'lr': 0.00039209102039166856, 'samples': 7936512, 'steps': 15500, 'batch_loss/train': 0.8909327271394432}
+12/25/2021 00:30:23 - INFO - codeparrot_training - Step 15501: {'lr': 0.0003920780505622551, 'samples': 7937024, 'steps': 15501, 'batch_loss/train': 0.8480931399390101}
+12/25/2021 00:30:33 - INFO - codeparrot_training - Step 15502: {'lr': 0.000392065080167993, 'samples': 7937536, 'steps': 15502, 'batch_loss/train': 0.8588917988818139}
+12/25/2021 00:30:45 - INFO - codeparrot_training - Step 15503: {'lr': 0.00039205210920893377, 'samples': 7938048, 'steps': 15503, 'batch_loss/train': 0.7960372469387949}
+12/25/2021 00:30:56 - INFO - codeparrot_training - Step 15504: {'lr': 0.000392039137685129, 'samples': 7938560, 'steps': 15504, 'batch_loss/train': 0.8583042211830616}
+12/25/2021 00:31:06 - INFO - codeparrot_training - Step 15505: {'lr': 0.00039202616559663023, 'samples': 7939072, 'steps': 15505, 'batch_loss/train': 0.87407529912889}
+12/25/2021 00:31:18 - INFO - codeparrot_training - Step 15506: {'lr': 0.000392013192943489, 'samples': 7939584, 'steps': 15506, 'batch_loss/train': 0.8212019093334675}
+12/25/2021 00:31:29 - INFO - codeparrot_training - Step 15507: {'lr': 0.00039200021972575705, 'samples': 7940096, 'steps': 15507, 'batch_loss/train': 0.8646645043045282}
+12/25/2021 00:31:40 - INFO - codeparrot_training - Step 15508: {'lr': 0.0003919872459434858, 'samples': 7940608, 'steps': 15508, 'batch_loss/train': 0.8546788354869932}
+12/25/2021 00:31:53 - INFO - codeparrot_training - Step 15509: {'lr': 0.0003919742715967269, 'samples': 7941120, 'steps': 15509, 'batch_loss/train': 0.8729835527483374}
+12/25/2021 00:32:04 - INFO - codeparrot_training - Step 15510: {'lr': 0.0003919612966855318, 'samples': 7941632, 'steps': 15510, 'batch_loss/train': 0.8323172730160877}
+12/25/2021 00:32:15 - INFO - codeparrot_training - Step 15511: {'lr': 0.00039194832120995234, 'samples': 7942144, 'steps': 15511, 'batch_loss/train': 0.8231093473732471}
+12/25/2021 00:32:25 - INFO - codeparrot_training - Step 15512: {'lr': 0.0003919353451700398, 'samples': 7942656, 'steps': 15512, 'batch_loss/train': 0.8115687659010291}
+12/25/2021 00:32:37 - INFO - codeparrot_training - Step 15513: {'lr': 0.0003919223685658461, 'samples': 7943168, 'steps': 15513, 'batch_loss/train': 0.692241829354316}
+12/25/2021 00:32:48 - INFO - codeparrot_training - Step 15514: {'lr': 0.0003919093913974224, 'samples': 7943680, 'steps': 15514, 'batch_loss/train': 0.7884855680167675}
+12/25/2021 00:32:59 - INFO - codeparrot_training - Step 15515: {'lr': 0.00039189641366482074, 'samples': 7944192, 'steps': 15515, 'batch_loss/train': 0.9363048588857055}
+12/25/2021 00:33:13 - INFO - codeparrot_training - Step 15516: {'lr': 0.0003918834353680925, 'samples': 7944704, 'steps': 15516, 'batch_loss/train': 0.8053292147815228}
+12/25/2021 00:33:23 - INFO - codeparrot_training - Step 15517: {'lr': 0.0003918704565072893, 'samples': 7945216, 'steps': 15517, 'batch_loss/train': 1.5121963080018759}
+12/25/2021 00:33:34 - INFO - codeparrot_training - Step 15518: {'lr': 0.0003918574770824627, 'samples': 7945728, 'steps': 15518, 'batch_loss/train': 1.117984197102487}
+12/25/2021 00:33:46 - INFO - codeparrot_training - Step 15519: {'lr': 0.0003918444970936642, 'samples': 7946240, 'steps': 15519, 'batch_loss/train': 0.8285683011636138}
+12/25/2021 00:33:57 - INFO - codeparrot_training - Step 15520: {'lr': 0.00039183151654094574, 'samples': 7946752, 'steps': 15520, 'batch_loss/train': 0.8389555234462023}
+12/25/2021 00:34:07 - INFO - codeparrot_training - Step 15521: {'lr': 0.00039181853542435865, 'samples': 7947264, 'steps': 15521, 'batch_loss/train': 0.8526093261316419}
+12/25/2021 00:34:18 - INFO - codeparrot_training - Step 15522: {'lr': 0.0003918055537439546, 'samples': 7947776, 'steps': 15522, 'batch_loss/train': 0.8167966110631824}
+12/25/2021 00:34:30 - INFO - codeparrot_training - Step 15523: {'lr': 0.0003917925714997852, 'samples': 7948288, 'steps': 15523, 'batch_loss/train': 0.8556069027399644}
+12/25/2021 00:34:40 - INFO - codeparrot_training - Step 15524: {'lr': 0.0003917795886919021, 'samples': 7948800, 'steps': 15524, 'batch_loss/train': 0.8426658986136317}
+12/25/2021 00:34:51 - INFO - codeparrot_training - Step 15525: {'lr': 0.0003917666053203569, 'samples': 7949312, 'steps': 15525, 'batch_loss/train': 0.9090210068970919}
+12/25/2021 00:35:05 - INFO - codeparrot_training - Step 15526: {'lr': 0.0003917536213852012, 'samples': 7949824, 'steps': 15526, 'batch_loss/train': 1.5696737598627806}
+12/25/2021 00:35:15 - INFO - codeparrot_training - Step 15527: {'lr': 0.0003917406368864866, 'samples': 7950336, 'steps': 15527, 'batch_loss/train': 0.8645992139354348}
+12/25/2021 00:35:26 - INFO - codeparrot_training - Step 15528: {'lr': 0.00039172765182426473, 'samples': 7950848, 'steps': 15528, 'batch_loss/train': 0.8126124059781432}
+12/25/2021 00:35:38 - INFO - codeparrot_training - Step 15529: {'lr': 0.00039171466619858733, 'samples': 7951360, 'steps': 15529, 'batch_loss/train': 0.8865252118557692}
+12/25/2021 00:35:49 - INFO - codeparrot_training - Step 15530: {'lr': 0.00039170168000950584, 'samples': 7951872, 'steps': 15530, 'batch_loss/train': 0.8211094690486789}
+12/25/2021 00:35:59 - INFO - codeparrot_training - Step 15531: {'lr': 0.00039168869325707204, 'samples': 7952384, 'steps': 15531, 'batch_loss/train': 0.8324412847869098}
+12/25/2021 00:36:10 - INFO - codeparrot_training - Step 15532: {'lr': 0.0003916757059413374, 'samples': 7952896, 'steps': 15532, 'batch_loss/train': 0.7325259856879711}
+12/25/2021 00:36:22 - INFO - codeparrot_training - Step 15533: {'lr': 0.00039166271806235364, 'samples': 7953408, 'steps': 15533, 'batch_loss/train': 0.6985779809765518}
+12/25/2021 00:36:32 - INFO - codeparrot_training - Step 15534: {'lr': 0.00039164972962017254, 'samples': 7953920, 'steps': 15534, 'batch_loss/train': 0.7995972139760852}
+12/25/2021 00:36:43 - INFO - codeparrot_training - Step 15535: {'lr': 0.0003916367406148455, 'samples': 7954432, 'steps': 15535, 'batch_loss/train': 0.7749213967472315}
+12/25/2021 00:36:57 - INFO - codeparrot_training - Step 15536: {'lr': 0.0003916237510464243, 'samples': 7954944, 'steps': 15536, 'batch_loss/train': 0.7736589964479208}
+12/25/2021 00:37:08 - INFO - codeparrot_training - Step 15537: {'lr': 0.0003916107609149605, 'samples': 7955456, 'steps': 15537, 'batch_loss/train': 0.7918870653957129}
+12/25/2021 00:37:18 - INFO - codeparrot_training - Step 15538: {'lr': 0.0003915977702205058, 'samples': 7955968, 'steps': 15538, 'batch_loss/train': 0.8460940374061465}
+12/25/2021 00:37:30 - INFO - codeparrot_training - Step 15539: {'lr': 0.00039158477896311184, 'samples': 7956480, 'steps': 15539, 'batch_loss/train': 0.7648451839340851}
+12/25/2021 00:37:41 - INFO - codeparrot_training - Step 15540: {'lr': 0.00039157178714283025, 'samples': 7956992, 'steps': 15540, 'batch_loss/train': 0.7378618272487074}
+12/25/2021 00:37:52 - INFO - codeparrot_training - Step 15541: {'lr': 0.00039155879475971265, 'samples': 7957504, 'steps': 15541, 'batch_loss/train': 0.8679680735804141}
+12/25/2021 00:38:02 - INFO - codeparrot_training - Step 15542: {'lr': 0.00039154580181381086, 'samples': 7958016, 'steps': 15542, 'batch_loss/train': 0.8437802498228848}
+12/25/2021 00:38:14 - INFO - codeparrot_training - Step 15543: {'lr': 0.00039153280830517626, 'samples': 7958528, 'steps': 15543, 'batch_loss/train': 0.89771568775177}
+12/25/2021 00:38:25 - INFO - codeparrot_training - Step 15544: {'lr': 0.00039151981423386073, 'samples': 7959040, 'steps': 15544, 'batch_loss/train': 0.8372146440669894}
+12/25/2021 00:38:36 - INFO - codeparrot_training - Step 15545: {'lr': 0.00039150681959991584, 'samples': 7959552, 'steps': 15545, 'batch_loss/train': 0.9180911555886269}
+12/25/2021 00:38:49 - INFO - codeparrot_training - Step 15546: {'lr': 0.00039149382440339334, 'samples': 7960064, 'steps': 15546, 'batch_loss/train': 0.8079301053658128}
+12/25/2021 00:39:00 - INFO - codeparrot_training - Step 15547: {'lr': 0.0003914808286443447, 'samples': 7960576, 'steps': 15547, 'batch_loss/train': 0.7537226434797049}
+12/25/2021 00:39:11 - INFO - codeparrot_training - Step 15548: {'lr': 0.0003914678323228218, 'samples': 7961088, 'steps': 15548, 'batch_loss/train': 0.9934687539935112}
+12/25/2021 00:39:23 - INFO - codeparrot_training - Step 15549: {'lr': 0.00039145483543887613, 'samples': 7961600, 'steps': 15549, 'batch_loss/train': 0.8111543254926801}
+12/25/2021 00:39:33 - INFO - codeparrot_training - Step 15550: {'lr': 0.0003914418379925595, 'samples': 7962112, 'steps': 15550, 'batch_loss/train': 1.337262315209955}
+12/25/2021 00:39:44 - INFO - codeparrot_training - Step 15551: {'lr': 0.00039142883998392354, 'samples': 7962624, 'steps': 15551, 'batch_loss/train': 0.7343388134613633}
+12/25/2021 00:39:54 - INFO - codeparrot_training - Step 15552: {'lr': 0.00039141584141301987, 'samples': 7963136, 'steps': 15552, 'batch_loss/train': 1.006969394395128}
+12/25/2021 00:40:06 - INFO - codeparrot_training - Step 15553: {'lr': 0.0003914028422799002, 'samples': 7963648, 'steps': 15553, 'batch_loss/train': 0.7408300954848528}
+12/25/2021 00:40:17 - INFO - codeparrot_training - Step 15554: {'lr': 0.0003913898425846163, 'samples': 7964160, 'steps': 15554, 'batch_loss/train': 0.9307961594313383}
+12/25/2021 00:40:28 - INFO - codeparrot_training - Step 15555: {'lr': 0.0003913768423272197, 'samples': 7964672, 'steps': 15555, 'batch_loss/train': 0.8014033641666174}
+12/25/2021 00:40:41 - INFO - codeparrot_training - Step 15556: {'lr': 0.00039136384150776217, 'samples': 7965184, 'steps': 15556, 'batch_loss/train': 0.8081126278266311}
+12/25/2021 00:40:52 - INFO - codeparrot_training - Step 15557: {'lr': 0.0003913508401262954, 'samples': 7965696, 'steps': 15557, 'batch_loss/train': 0.7548124867025763}
+12/25/2021 00:41:02 - INFO - codeparrot_training - Step 15558: {'lr': 0.00039133783818287105, 'samples': 7966208, 'steps': 15558, 'batch_loss/train': 0.7962747167330235}
+12/25/2021 00:41:15 - INFO - codeparrot_training - Step 15559: {'lr': 0.00039132483567754086, 'samples': 7966720, 'steps': 15559, 'batch_loss/train': 0.8701520282775164}
+12/25/2021 00:41:25 - INFO - codeparrot_training - Step 15560: {'lr': 0.0003913118326103564, 'samples': 7967232, 'steps': 15560, 'batch_loss/train': 0.8612917094724253}
+12/25/2021 00:41:36 - INFO - codeparrot_training - Step 15561: {'lr': 0.00039129882898136955, 'samples': 7967744, 'steps': 15561, 'batch_loss/train': 0.850821046391502}
+12/25/2021 00:41:47 - INFO - codeparrot_training - Step 15562: {'lr': 0.0003912858247906318, 'samples': 7968256, 'steps': 15562, 'batch_loss/train': 0.755170030053705}
+12/25/2021 00:41:59 - INFO - codeparrot_training - Step 15563: {'lr': 0.0003912728200381951, 'samples': 7968768, 'steps': 15563, 'batch_loss/train': 0.8073657415807247}
+12/25/2021 00:42:09 - INFO - codeparrot_training - Step 15564: {'lr': 0.00039125981472411085, 'samples': 7969280, 'steps': 15564, 'batch_loss/train': 0.8094406686723232}
+12/25/2021 00:42:20 - INFO - codeparrot_training - Step 15565: {'lr': 0.00039124680884843104, 'samples': 7969792, 'steps': 15565, 'batch_loss/train': 0.8039568189997226}
+12/25/2021 00:42:34 - INFO - codeparrot_training - Step 15566: {'lr': 0.0003912338024112072, 'samples': 7970304, 'steps': 15566, 'batch_loss/train': 0.755577010801062}
+12/25/2021 00:42:45 - INFO - codeparrot_training - Step 15567: {'lr': 0.0003912207954124911, 'samples': 7970816, 'steps': 15567, 'batch_loss/train': 0.7332959161140025}
+12/25/2021 00:42:55 - INFO - codeparrot_training - Step 15568: {'lr': 0.00039120778785233445, 'samples': 7971328, 'steps': 15568, 'batch_loss/train': 0.8438756903633475}
+12/25/2021 00:43:07 - INFO - codeparrot_training - Step 15569: {'lr': 0.0003911947797307889, 'samples': 7971840, 'steps': 15569, 'batch_loss/train': 0.9080109111964703}
+12/25/2021 00:43:18 - INFO - codeparrot_training - Step 15570: {'lr': 0.0003911817710479063, 'samples': 7972352, 'steps': 15570, 'batch_loss/train': 0.6607720986939967}
+12/25/2021 00:43:28 - INFO - codeparrot_training - Step 15571: {'lr': 0.0003911687618037382, 'samples': 7972864, 'steps': 15571, 'batch_loss/train': 0.7699328698217869}
+12/25/2021 00:43:39 - INFO - codeparrot_training - Step 15572: {'lr': 0.0003911557519983365, 'samples': 7973376, 'steps': 15572, 'batch_loss/train': 0.8451412077993155}
+12/25/2021 00:43:51 - INFO - codeparrot_training - Step 15573: {'lr': 0.0003911427416317528, 'samples': 7973888, 'steps': 15573, 'batch_loss/train': 0.7718981048092246}
+12/25/2021 00:44:02 - INFO - codeparrot_training - Step 15574: {'lr': 0.00039112973070403877, 'samples': 7974400, 'steps': 15574, 'batch_loss/train': 0.8797804759815335}
+12/25/2021 00:44:13 - INFO - codeparrot_training - Step 15575: {'lr': 0.0003911167192152463, 'samples': 7974912, 'steps': 15575, 'batch_loss/train': 0.8555625090375543}
+12/25/2021 00:44:24 - INFO - codeparrot_training - Step 15576: {'lr': 0.0003911037071654271, 'samples': 7975424, 'steps': 15576, 'batch_loss/train': 0.7032338932622224}
+12/25/2021 00:44:35 - INFO - codeparrot_training - Step 15577: {'lr': 0.0003910906945546327, 'samples': 7975936, 'steps': 15577, 'batch_loss/train': 0.8043194133788347}
+12/25/2021 00:44:46 - INFO - codeparrot_training - Step 15578: {'lr': 0.00039107768138291497, 'samples': 7976448, 'steps': 15578, 'batch_loss/train': 0.7788636186160147}
+12/25/2021 00:44:59 - INFO - codeparrot_training - Step 15579: {'lr': 0.00039106466765032575, 'samples': 7976960, 'steps': 15579, 'batch_loss/train': 0.7821403611451387}
+12/25/2021 00:45:10 - INFO - codeparrot_training - Step 15580: {'lr': 0.0003910516533569166, 'samples': 7977472, 'steps': 15580, 'batch_loss/train': 0.7623580417130142}
+12/25/2021 00:45:21 - INFO - codeparrot_training - Step 15581: {'lr': 0.00039103863850273947, 'samples': 7977984, 'steps': 15581, 'batch_loss/train': 0.8365695457905531}
+12/25/2021 00:45:33 - INFO - codeparrot_training - Step 15582: {'lr': 0.00039102562308784584, 'samples': 7978496, 'steps': 15582, 'batch_loss/train': 0.7589267203584313}
+12/25/2021 00:45:43 - INFO - codeparrot_training - Step 15583: {'lr': 0.00039101260711228757, 'samples': 7979008, 'steps': 15583, 'batch_loss/train': 0.8801112612709403}
+12/25/2021 00:45:54 - INFO - codeparrot_training - Step 15584: {'lr': 0.00039099959057611644, 'samples': 7979520, 'steps': 15584, 'batch_loss/train': 0.836783423088491}
+12/25/2021 00:46:05 - INFO - codeparrot_training - Step 15585: {'lr': 0.0003909865734793843, 'samples': 7980032, 'steps': 15585, 'batch_loss/train': 0.8447759822010994}
+12/25/2021 00:46:18 - INFO - codeparrot_training - Step 15586: {'lr': 0.0003909735558221426, 'samples': 7980544, 'steps': 15586, 'batch_loss/train': 1.4221013626083732}
+12/25/2021 00:46:29 - INFO - codeparrot_training - Step 15587: {'lr': 0.00039096053760444337, 'samples': 7981056, 'steps': 15587, 'batch_loss/train': 0.765137389767915}
+12/25/2021 00:46:40 - INFO - codeparrot_training - Step 15588: {'lr': 0.00039094751882633817, 'samples': 7981568, 'steps': 15588, 'batch_loss/train': 0.8962667817249894}
+12/25/2021 00:46:52 - INFO - codeparrot_training - Step 15589: {'lr': 0.00039093449948787896, 'samples': 7982080, 'steps': 15589, 'batch_loss/train': 0.938039437867701}
+12/25/2021 00:47:02 - INFO - codeparrot_training - Step 15590: {'lr': 0.0003909214795891174, 'samples': 7982592, 'steps': 15590, 'batch_loss/train': 0.7523462832905352}
+12/25/2021 00:47:13 - INFO - codeparrot_training - Step 15591: {'lr': 0.0003909084591301052, 'samples': 7983104, 'steps': 15591, 'batch_loss/train': 0.8182441758690402}
+12/25/2021 00:47:25 - INFO - codeparrot_training - Step 15592: {'lr': 0.0003908954381108942, 'samples': 7983616, 'steps': 15592, 'batch_loss/train': 0.8076259540393949}
+12/25/2021 00:47:35 - INFO - codeparrot_training - Step 15593: {'lr': 0.00039088241653153604, 'samples': 7984128, 'steps': 15593, 'batch_loss/train': 0.862928718328476}
+12/25/2021 00:47:46 - INFO - codeparrot_training - Step 15594: {'lr': 0.0003908693943920827, 'samples': 7984640, 'steps': 15594, 'batch_loss/train': 0.7839058823883533}
+12/25/2021 00:48:00 - INFO - codeparrot_training - Step 15595: {'lr': 0.0003908563716925858, 'samples': 7985152, 'steps': 15595, 'batch_loss/train': 0.8448459999635816}
+12/25/2021 00:48:10 - INFO - codeparrot_training - Step 15596: {'lr': 0.00039084334843309714, 'samples': 7985664, 'steps': 15596, 'batch_loss/train': 0.8715806817635894}
+12/25/2021 00:48:21 - INFO - codeparrot_training - Step 15597: {'lr': 0.0003908303246136685, 'samples': 7986176, 'steps': 15597, 'batch_loss/train': 0.9483963567763567}
+12/25/2021 00:48:32 - INFO - codeparrot_training - Step 15598: {'lr': 0.00039081730023435177, 'samples': 7986688, 'steps': 15598, 'batch_loss/train': 0.8258726913481951}
+12/25/2021 00:48:44 - INFO - codeparrot_training - Step 15599: {'lr': 0.00039080427529519844, 'samples': 7987200, 'steps': 15599, 'batch_loss/train': 0.7841024221852422}
+12/25/2021 00:48:55 - INFO - codeparrot_training - Step 15600: {'lr': 0.0003907912497962607, 'samples': 7987712, 'steps': 15600, 'batch_loss/train': 0.5916137634776533}
+12/25/2021 00:49:05 - INFO - codeparrot_training - Step 15601: {'lr': 0.0003907782237375899, 'samples': 7988224, 'steps': 15601, 'batch_loss/train': 0.7409629048779607}
+12/25/2021 00:49:19 - INFO - codeparrot_training - Step 15602: {'lr': 0.0003907651971192382, 'samples': 7988736, 'steps': 15602, 'batch_loss/train': 1.0718247359618545}
+12/25/2021 00:49:30 - INFO - codeparrot_training - Step 15603: {'lr': 0.00039075216994125705, 'samples': 7989248, 'steps': 15603, 'batch_loss/train': 0.8195392405614257}
+12/25/2021 00:49:40 - INFO - codeparrot_training - Step 15604: {'lr': 0.0003907391422036986, 'samples': 7989760, 'steps': 15604, 'batch_loss/train': 0.7676490461453795}
+12/25/2021 00:49:52 - INFO - codeparrot_training - Step 15605: {'lr': 0.0003907261139066144, 'samples': 7990272, 'steps': 15605, 'batch_loss/train': 0.7542807147838175}
+12/25/2021 00:50:03 - INFO - codeparrot_training - Step 15606: {'lr': 0.0003907130850500562, 'samples': 7990784, 'steps': 15606, 'batch_loss/train': 0.8313349899835885}
+12/25/2021 00:50:13 - INFO - codeparrot_training - Step 15607: {'lr': 0.0003907000556340761, 'samples': 7991296, 'steps': 15607, 'batch_loss/train': 0.8789976816624403}
+12/25/2021 00:50:24 - INFO - codeparrot_training - Step 15608: {'lr': 0.00039068702565872555, 'samples': 7991808, 'steps': 15608, 'batch_loss/train': 0.7688020030036569}
+12/25/2021 00:50:36 - INFO - codeparrot_training - Step 15609: {'lr': 0.0003906739951240565, 'samples': 7992320, 'steps': 15609, 'batch_loss/train': 0.8901801048777997}
+12/25/2021 00:50:46 - INFO - codeparrot_training - Step 15610: {'lr': 0.00039066096403012084, 'samples': 7992832, 'steps': 15610, 'batch_loss/train': 0.8095833538100123}
+12/25/2021 00:50:57 - INFO - codeparrot_training - Step 15611: {'lr': 0.0003906479323769703, 'samples': 7993344, 'steps': 15611, 'batch_loss/train': 0.6379567254334688}
+12/25/2021 00:51:11 - INFO - codeparrot_training - Step 15612: {'lr': 0.00039063490016465663, 'samples': 7993856, 'steps': 15612, 'batch_loss/train': 1.3505712519399822}
+12/25/2021 00:51:21 - INFO - codeparrot_training - Step 15613: {'lr': 0.0003906218673932318, 'samples': 7994368, 'steps': 15613, 'batch_loss/train': 0.8107848167419434}
+12/25/2021 00:51:32 - INFO - codeparrot_training - Step 15614: {'lr': 0.00039060883406274744, 'samples': 7994880, 'steps': 15614, 'batch_loss/train': 0.795276123448275}
+12/25/2021 00:51:44 - INFO - codeparrot_training - Step 15615: {'lr': 0.0003905958001732555, 'samples': 7995392, 'steps': 15615, 'batch_loss/train': 0.798854848369956}
+12/25/2021 00:51:55 - INFO - codeparrot_training - Step 15616: {'lr': 0.00039058276572480767, 'samples': 7995904, 'steps': 15616, 'batch_loss/train': 0.8527885056100786}
+12/25/2021 00:52:05 - INFO - codeparrot_training - Step 15617: {'lr': 0.00039056973071745595, 'samples': 7996416, 'steps': 15617, 'batch_loss/train': 0.7480744551867247}
+12/25/2021 00:52:16 - INFO - codeparrot_training - Step 15618: {'lr': 0.00039055669515125196, 'samples': 7996928, 'steps': 15618, 'batch_loss/train': 0.7616115676937625}
+12/25/2021 00:52:28 - INFO - codeparrot_training - Step 15619: {'lr': 0.00039054365902624767, 'samples': 7997440, 'steps': 15619, 'batch_loss/train': 0.9089390505105257}
+12/25/2021 00:52:39 - INFO - codeparrot_training - Step 15620: {'lr': 0.0003905306223424948, 'samples': 7997952, 'steps': 15620, 'batch_loss/train': 0.7680186476791278}
+12/25/2021 00:52:49 - INFO - codeparrot_training - Step 15621: {'lr': 0.0003905175851000453, 'samples': 7998464, 'steps': 15621, 'batch_loss/train': 0.8272782019339502}
+12/25/2021 00:53:01 - INFO - codeparrot_training - Step 15622: {'lr': 0.0003905045472989509, 'samples': 7998976, 'steps': 15622, 'batch_loss/train': 0.8188977288082242}
+12/25/2021 00:53:12 - INFO - codeparrot_training - Step 15623: {'lr': 0.00039049150893926353, 'samples': 7999488, 'steps': 15623, 'batch_loss/train': 0.7710812175646424}
+12/25/2021 00:53:22 - INFO - codeparrot_training - Step 15624: {'lr': 0.00039047847002103493, 'samples': 8000000, 'steps': 15624, 'batch_loss/train': 0.9041711688041687}
+12/25/2021 00:53:36 - INFO - codeparrot_training - Step 15625: {'lr': 0.00039046543054431694, 'samples': 8000512, 'steps': 15625, 'batch_loss/train': 0.8444310743361712}
+12/25/2021 00:53:47 - INFO - codeparrot_training - Step 15626: {'lr': 0.00039045239050916153, 'samples': 8001024, 'steps': 15626, 'batch_loss/train': 0.7852856387617067}
+12/25/2021 00:53:58 - INFO - codeparrot_training - Step 15627: {'lr': 0.00039043934991562037, 'samples': 8001536, 'steps': 15627, 'batch_loss/train': 0.9021553881466389}
+12/25/2021 00:54:10 - INFO - codeparrot_training - Step 15628: {'lr': 0.0003904263087637454, 'samples': 8002048, 'steps': 15628, 'batch_loss/train': 0.7989698708988726}
+12/25/2021 00:54:20 - INFO - codeparrot_training - Step 15629: {'lr': 0.0003904132670535885, 'samples': 8002560, 'steps': 15629, 'batch_loss/train': 0.8259442932903767}
+12/25/2021 00:54:31 - INFO - codeparrot_training - Step 15630: {'lr': 0.0003904002247852013, 'samples': 8003072, 'steps': 15630, 'batch_loss/train': 0.7882327167317271}
+12/25/2021 00:54:42 - INFO - codeparrot_training - Step 15631: {'lr': 0.00039038718195863605, 'samples': 8003584, 'steps': 15631, 'batch_loss/train': 0.8365611680783331}
+12/25/2021 00:54:56 - INFO - codeparrot_training - Step 15632: {'lr': 0.00039037413857394423, 'samples': 8004096, 'steps': 15632, 'batch_loss/train': 0.7803334966301918}
+12/25/2021 00:55:06 - INFO - codeparrot_training - Step 15633: {'lr': 0.0003903610946311779, 'samples': 8004608, 'steps': 15633, 'batch_loss/train': 0.8393072276376188}
+12/25/2021 00:55:17 - INFO - codeparrot_training - Step 15634: {'lr': 0.00039034805013038877, 'samples': 8005120, 'steps': 15634, 'batch_loss/train': 1.8175356816500425}
+12/25/2021 00:55:29 - INFO - codeparrot_training - Step 15635: {'lr': 0.0003903350050716289, 'samples': 8005632, 'steps': 15635, 'batch_loss/train': 0.8105579894036055}
+12/25/2021 00:55:40 - INFO - codeparrot_training - Step 15636: {'lr': 0.00039032195945494996, 'samples': 8006144, 'steps': 15636, 'batch_loss/train': 0.7940618945285678}
+12/25/2021 00:55:51 - INFO - codeparrot_training - Step 15637: {'lr': 0.00039030891328040396, 'samples': 8006656, 'steps': 15637, 'batch_loss/train': 0.7389607694931328}
+12/25/2021 00:56:01 - INFO - codeparrot_training - Step 15638: {'lr': 0.0003902958665480426, 'samples': 8007168, 'steps': 15638, 'batch_loss/train': 0.6845337934792042}
+12/25/2021 00:56:13 - INFO - codeparrot_training - Step 15639: {'lr': 0.00039028281925791795, 'samples': 8007680, 'steps': 15639, 'batch_loss/train': 0.8781865369528532}
+12/25/2021 00:56:24 - INFO - codeparrot_training - Step 15640: {'lr': 0.0003902697714100817, 'samples': 8008192, 'steps': 15640, 'batch_loss/train': 0.8711416008882225}
+12/25/2021 00:56:35 - INFO - codeparrot_training - Step 15641: {'lr': 0.0003902567230045858, 'samples': 8008704, 'steps': 15641, 'batch_loss/train': 0.7773706265725195}
+12/25/2021 00:56:48 - INFO - codeparrot_training - Step 15642: {'lr': 0.0003902436740414822, 'samples': 8009216, 'steps': 15642, 'batch_loss/train': 0.8316805632784963}
+12/25/2021 00:56:59 - INFO - codeparrot_training - Step 15643: {'lr': 0.0003902306245208226, 'samples': 8009728, 'steps': 15643, 'batch_loss/train': 0.9593033967539668}
+12/25/2021 00:57:10 - INFO - codeparrot_training - Step 15644: {'lr': 0.0003902175744426591, 'samples': 8010240, 'steps': 15644, 'batch_loss/train': 0.7876972891390324}
+12/25/2021 00:57:20 - INFO - codeparrot_training - Step 15645: {'lr': 0.00039020452380704343, 'samples': 8010752, 'steps': 15645, 'batch_loss/train': 0.9239841103553772}
+12/25/2021 00:57:32 - INFO - codeparrot_training - Step 15646: {'lr': 0.0003901914726140275, 'samples': 8011264, 'steps': 15646, 'batch_loss/train': 0.7829052079468966}
+12/25/2021 00:57:43 - INFO - codeparrot_training - Step 15647: {'lr': 0.00039017842086366323, 'samples': 8011776, 'steps': 15647, 'batch_loss/train': 0.8907040655612946}
+12/25/2021 00:57:53 - INFO - codeparrot_training - Step 15648: {'lr': 0.0003901653685560025, 'samples': 8012288, 'steps': 15648, 'batch_loss/train': 0.8123979223892093}
+12/25/2021 00:58:05 - INFO - codeparrot_training - Step 15649: {'lr': 0.0003901523156910972, 'samples': 8012800, 'steps': 15649, 'batch_loss/train': 0.831674643792212}
+12/25/2021 00:58:16 - INFO - codeparrot_training - Step 15650: {'lr': 0.0003901392622689992, 'samples': 8013312, 'steps': 15650, 'batch_loss/train': 0.7798086651600897}
+12/25/2021 00:58:27 - INFO - codeparrot_training - Step 15651: {'lr': 0.0003901262082897603, 'samples': 8013824, 'steps': 15651, 'batch_loss/train': 0.9306235343683511}
+12/25/2021 00:58:40 - INFO - codeparrot_training - Step 15652: {'lr': 0.0003901131537534326, 'samples': 8014336, 'steps': 15652, 'batch_loss/train': 0.7771784961223602}
+12/25/2021 00:58:51 - INFO - codeparrot_training - Step 15653: {'lr': 0.0003901000986600679, 'samples': 8014848, 'steps': 15653, 'batch_loss/train': 0.7306192917749286}
+12/25/2021 00:59:02 - INFO - codeparrot_training - Step 15654: {'lr': 0.0003900870430097181, 'samples': 8015360, 'steps': 15654, 'batch_loss/train': 0.8658047588542104}
+12/25/2021 00:59:14 - INFO - codeparrot_training - Step 15655: {'lr': 0.0003900739868024351, 'samples': 8015872, 'steps': 15655, 'batch_loss/train': 0.802291358821094}
+12/25/2021 00:59:24 - INFO - codeparrot_training - Step 15656: {'lr': 0.0003900609300382708, 'samples': 8016384, 'steps': 15656, 'batch_loss/train': 0.837952318135649}
+12/25/2021 00:59:35 - INFO - codeparrot_training - Step 15657: {'lr': 0.00039004787271727716, 'samples': 8016896, 'steps': 15657, 'batch_loss/train': 0.822870985371992}
+12/25/2021 00:59:45 - INFO - codeparrot_training - Step 15658: {'lr': 0.0003900348148395061, 'samples': 8017408, 'steps': 15658, 'batch_loss/train': 0.8294438743032515}
+12/25/2021 00:59:58 - INFO - codeparrot_training - Step 15659: {'lr': 0.0003900217564050094, 'samples': 8017920, 'steps': 15659, 'batch_loss/train': 0.7942709615454078}
+12/25/2021 01:00:08 - INFO - codeparrot_training - Step 15660: {'lr': 0.00039000869741383915, 'samples': 8018432, 'steps': 15660, 'batch_loss/train': 0.8996332613751292}
+12/25/2021 01:00:19 - INFO - codeparrot_training - Step 15661: {'lr': 0.00038999563786604717, 'samples': 8018944, 'steps': 15661, 'batch_loss/train': 0.8115709372796118}
+12/25/2021 01:00:33 - INFO - codeparrot_training - Step 15662: {'lr': 0.0003899825777616853, 'samples': 8019456, 'steps': 15662, 'batch_loss/train': 0.8351846979930997}
+12/25/2021 01:00:43 - INFO - codeparrot_training - Step 15663: {'lr': 0.0003899695171008057, 'samples': 8019968, 'steps': 15663, 'batch_loss/train': 0.7678010510280728}
+12/25/2021 01:00:54 - INFO - codeparrot_training - Step 15664: {'lr': 0.00038995645588346006, 'samples': 8020480, 'steps': 15664, 'batch_loss/train': 0.7469604378566146}
+12/25/2021 01:01:06 - INFO - codeparrot_training - Step 15665: {'lr': 0.0003899433941097004, 'samples': 8020992, 'steps': 15665, 'batch_loss/train': 0.8263297425583005}
+12/25/2021 01:01:17 - INFO - codeparrot_training - Step 15666: {'lr': 0.0003899303317795787, 'samples': 8021504, 'steps': 15666, 'batch_loss/train': 0.714073384529911}
+12/25/2021 01:01:27 - INFO - codeparrot_training - Step 15667: {'lr': 0.0003899172688931468, 'samples': 8022016, 'steps': 15667, 'batch_loss/train': 0.741092776414007}
+12/25/2021 01:01:38 - INFO - codeparrot_training - Step 15668: {'lr': 0.0003899042054504566, 'samples': 8022528, 'steps': 15668, 'batch_loss/train': 0.8543092459440231}
+12/25/2021 01:01:50 - INFO - codeparrot_training - Step 15669: {'lr': 0.00038989114145156017, 'samples': 8023040, 'steps': 15669, 'batch_loss/train': 0.8005679533816874}
+12/25/2021 01:02:00 - INFO - codeparrot_training - Step 15670: {'lr': 0.0003898780768965095, 'samples': 8023552, 'steps': 15670, 'batch_loss/train': 0.7964179976843297}
+12/25/2021 01:02:11 - INFO - codeparrot_training - Step 15671: {'lr': 0.0003898650117853562, 'samples': 8024064, 'steps': 15671, 'batch_loss/train': 0.8297726735472679}
+12/25/2021 01:02:25 - INFO - codeparrot_training - Step 15672: {'lr': 0.00038985194611815255, 'samples': 8024576, 'steps': 15672, 'batch_loss/train': 0.7566685490310192}
+12/25/2021 01:02:36 - INFO - codeparrot_training - Step 15673: {'lr': 0.0003898388798949503, 'samples': 8025088, 'steps': 15673, 'batch_loss/train': 0.5992351775057614}
+12/25/2021 01:02:47 - INFO - codeparrot_training - Step 15674: {'lr': 0.0003898258131158016, 'samples': 8025600, 'steps': 15674, 'batch_loss/train': 0.8505495525896549}
+12/25/2021 01:02:59 - INFO - codeparrot_training - Step 15675: {'lr': 0.00038981274578075807, 'samples': 8026112, 'steps': 15675, 'batch_loss/train': 0.748377921525389}
+12/25/2021 01:03:09 - INFO - codeparrot_training - Step 15676: {'lr': 0.00038979967788987203, 'samples': 8026624, 'steps': 15676, 'batch_loss/train': 0.7041781803127378}
+12/25/2021 01:03:20 - INFO - codeparrot_training - Step 15677: {'lr': 0.0003897866094431951, 'samples': 8027136, 'steps': 15677, 'batch_loss/train': 0.8204400455579162}
+12/25/2021 01:03:30 - INFO - codeparrot_training - Step 15678: {'lr': 0.00038977354044077953, 'samples': 8027648, 'steps': 15678, 'batch_loss/train': 0.7606696139555424}
+12/25/2021 01:03:42 - INFO - codeparrot_training - Step 15679: {'lr': 0.0003897604708826771, 'samples': 8028160, 'steps': 15679, 'batch_loss/train': 0.7910135770216584}
+12/25/2021 01:03:53 - INFO - codeparrot_training - Step 15680: {'lr': 0.0003897474007689397, 'samples': 8028672, 'steps': 15680, 'batch_loss/train': 0.7602348843356594}
+12/25/2021 01:04:04 - INFO - codeparrot_training - Step 15681: {'lr': 0.00038973433009961955, 'samples': 8029184, 'steps': 15681, 'batch_loss/train': 0.7013574067968875}
+12/25/2021 01:04:17 - INFO - codeparrot_training - Step 15682: {'lr': 0.0003897212588747684, 'samples': 8029696, 'steps': 15682, 'batch_loss/train': 0.8649849254870787}
+12/25/2021 01:04:28 - INFO - codeparrot_training - Step 15683: {'lr': 0.0003897081870944383, 'samples': 8030208, 'steps': 15683, 'batch_loss/train': 0.7846765033900738}
+12/25/2021 01:04:39 - INFO - codeparrot_training - Step 15684: {'lr': 0.00038969511475868114, 'samples': 8030720, 'steps': 15684, 'batch_loss/train': 0.9033584278076887}
+12/25/2021 01:04:51 - INFO - codeparrot_training - Step 15685: {'lr': 0.000389682041867549, 'samples': 8031232, 'steps': 15685, 'batch_loss/train': 0.8118885159492493}
+12/25/2021 01:05:02 - INFO - codeparrot_training - Step 15686: {'lr': 0.0003896689684210938, 'samples': 8031744, 'steps': 15686, 'batch_loss/train': 0.7150546838529408}
+12/25/2021 01:05:12 - INFO - codeparrot_training - Step 15687: {'lr': 0.00038965589441936754, 'samples': 8032256, 'steps': 15687, 'batch_loss/train': 0.8802613383159041}
+12/25/2021 01:05:23 - INFO - codeparrot_training - Step 15688: {'lr': 0.00038964281986242214, 'samples': 8032768, 'steps': 15688, 'batch_loss/train': 0.6905770096927881}
+12/25/2021 01:05:35 - INFO - codeparrot_training - Step 15689: {'lr': 0.00038962974475030966, 'samples': 8033280, 'steps': 15689, 'batch_loss/train': 0.8207397861406207}
+12/25/2021 01:05:45 - INFO - codeparrot_training - Step 15690: {'lr': 0.00038961666908308203, 'samples': 8033792, 'steps': 15690, 'batch_loss/train': 0.8059776993468404}
+12/25/2021 01:05:56 - INFO - codeparrot_training - Step 15691: {'lr': 0.00038960359286079114, 'samples': 8034304, 'steps': 15691, 'batch_loss/train': 0.8229903252795339}
+12/25/2021 01:06:10 - INFO - codeparrot_training - Step 15692: {'lr': 0.0003895905160834892, 'samples': 8034816, 'steps': 15692, 'batch_loss/train': 0.7868875470012426}
+12/25/2021 01:06:21 - INFO - codeparrot_training - Step 15693: {'lr': 0.00038957743875122795, 'samples': 8035328, 'steps': 15693, 'batch_loss/train': 0.930713227018714}
+12/25/2021 01:06:31 - INFO - codeparrot_training - Step 15694: {'lr': 0.0003895643608640597, 'samples': 8035840, 'steps': 15694, 'batch_loss/train': 0.7515664519742131}
+12/25/2021 01:06:43 - INFO - codeparrot_training - Step 15695: {'lr': 0.0003895512824220361, 'samples': 8036352, 'steps': 15695, 'batch_loss/train': 0.6789912935346365}
+12/25/2021 01:06:54 - INFO - codeparrot_training - Step 15696: {'lr': 0.0003895382034252093, 'samples': 8036864, 'steps': 15696, 'batch_loss/train': 0.7572893109172583}
+12/25/2021 01:07:04 - INFO - codeparrot_training - Step 15697: {'lr': 0.00038952512387363135, 'samples': 8037376, 'steps': 15697, 'batch_loss/train': 0.8829627772793174}
+12/25/2021 01:07:15 - INFO - codeparrot_training - Step 15698: {'lr': 0.00038951204376735417, 'samples': 8037888, 'steps': 15698, 'batch_loss/train': 0.7392695050220937}
+12/25/2021 01:07:27 - INFO - codeparrot_training - Step 15699: {'lr': 0.00038949896310642973, 'samples': 8038400, 'steps': 15699, 'batch_loss/train': 0.7797246011905372}
+12/25/2021 01:07:38 - INFO - codeparrot_training - Step 15700: {'lr': 0.00038948588189091014, 'samples': 8038912, 'steps': 15700, 'batch_loss/train': 0.8238237909972668}
+12/25/2021 01:07:48 - INFO - codeparrot_training - Step 15701: {'lr': 0.00038947280012084737, 'samples': 8039424, 'steps': 15701, 'batch_loss/train': 0.8965264977887273}
+12/25/2021 01:08:02 - INFO - codeparrot_training - Step 15702: {'lr': 0.00038945971779629336, 'samples': 8039936, 'steps': 15702, 'batch_loss/train': 0.757955034263432}
+12/25/2021 01:08:13 - INFO - codeparrot_training - Step 15703: {'lr': 0.0003894466349173002, 'samples': 8040448, 'steps': 15703, 'batch_loss/train': 0.7798960972577333}
+12/25/2021 01:08:23 - INFO - codeparrot_training - Step 15704: {'lr': 0.00038943355148391985, 'samples': 8040960, 'steps': 15704, 'batch_loss/train': 0.780336843803525}
+12/25/2021 01:08:35 - INFO - codeparrot_training - Step 15705: {'lr': 0.00038942046749620437, 'samples': 8041472, 'steps': 15705, 'batch_loss/train': 0.9025689139962196}
+12/25/2021 01:08:46 - INFO - codeparrot_training - Step 15706: {'lr': 0.00038940738295420576, 'samples': 8041984, 'steps': 15706, 'batch_loss/train': 0.8348572133108974}
+12/25/2021 01:08:57 - INFO - codeparrot_training - Step 15707: {'lr': 0.00038939429785797596, 'samples': 8042496, 'steps': 15707, 'batch_loss/train': 0.9253094987943769}
+12/25/2021 01:09:07 - INFO - codeparrot_training - Step 15708: {'lr': 0.00038938121220756717, 'samples': 8043008, 'steps': 15708, 'batch_loss/train': 0.8840648680925369}
+12/25/2021 01:09:19 - INFO - codeparrot_training - Step 15709: {'lr': 0.0003893681260030312, 'samples': 8043520, 'steps': 15709, 'batch_loss/train': 0.8569790851324797}
+12/25/2021 01:09:30 - INFO - codeparrot_training - Step 15710: {'lr': 0.0003893550392444203, 'samples': 8044032, 'steps': 15710, 'batch_loss/train': 0.8894339427351952}
+12/25/2021 01:09:41 - INFO - codeparrot_training - Step 15711: {'lr': 0.00038934195193178635, 'samples': 8044544, 'steps': 15711, 'batch_loss/train': 0.7771852947771549}
+12/25/2021 01:09:54 - INFO - codeparrot_training - Step 15712: {'lr': 0.00038932886406518137, 'samples': 8045056, 'steps': 15712, 'batch_loss/train': 0.8696241073776037}
+12/25/2021 01:10:05 - INFO - codeparrot_training - Step 15713: {'lr': 0.0003893157756446575, 'samples': 8045568, 'steps': 15713, 'batch_loss/train': 0.7652731547132134}
+12/25/2021 01:10:16 - INFO - codeparrot_training - Step 15714: {'lr': 0.0003893026866702666, 'samples': 8046080, 'steps': 15714, 'batch_loss/train': 0.8657754063606262}
+12/25/2021 01:10:28 - INFO - codeparrot_training - Step 15715: {'lr': 0.0003892895971420609, 'samples': 8046592, 'steps': 15715, 'batch_loss/train': 0.8399825226515532}
+12/25/2021 01:10:38 - INFO - codeparrot_training - Step 15716: {'lr': 0.0003892765070600923, 'samples': 8047104, 'steps': 15716, 'batch_loss/train': 0.8654966567410156}
+12/25/2021 01:10:49 - INFO - codeparrot_training - Step 15717: {'lr': 0.00038926341642441295, 'samples': 8047616, 'steps': 15717, 'batch_loss/train': 0.7958465637639165}
+12/25/2021 01:10:59 - INFO - codeparrot_training - Step 15718: {'lr': 0.0003892503252350749, 'samples': 8048128, 'steps': 15718, 'batch_loss/train': 0.8577659204602242}
+12/25/2021 01:11:14 - INFO - codeparrot_training - Step 15719: {'lr': 0.00038923723349212994, 'samples': 8048640, 'steps': 15719, 'batch_loss/train': 0.7846201597712934}
+12/25/2021 01:11:24 - INFO - codeparrot_training - Step 15720: {'lr': 0.0003892241411956304, 'samples': 8049152, 'steps': 15720, 'batch_loss/train': 0.797103806398809}
+12/25/2021 01:11:35 - INFO - codeparrot_training - Step 15721: {'lr': 0.0003892110483456284, 'samples': 8049664, 'steps': 15721, 'batch_loss/train': 0.6394203954841942}
+12/25/2021 01:11:47 - INFO - codeparrot_training - Step 15722: {'lr': 0.0003891979549421757, 'samples': 8050176, 'steps': 15722, 'batch_loss/train': 0.8317654971033335}
+12/25/2021 01:11:57 - INFO - codeparrot_training - Step 15723: {'lr': 0.0003891848609853245, 'samples': 8050688, 'steps': 15723, 'batch_loss/train': 0.7907711057923734}
+12/25/2021 01:12:08 - INFO - codeparrot_training - Step 15724: {'lr': 0.0003891717664751268, 'samples': 8051200, 'steps': 15724, 'batch_loss/train': 0.9412051662802696}
+12/25/2021 01:12:20 - INFO - codeparrot_training - Step 15725: {'lr': 0.00038915867141163475, 'samples': 8051712, 'steps': 15725, 'batch_loss/train': 0.8463269295170903}
+12/25/2021 01:12:31 - INFO - codeparrot_training - Step 15726: {'lr': 0.0003891455757949004, 'samples': 8052224, 'steps': 15726, 'batch_loss/train': 0.9003653433173895}
+12/25/2021 01:12:41 - INFO - codeparrot_training - Step 15727: {'lr': 0.00038913247962497574, 'samples': 8052736, 'steps': 15727, 'batch_loss/train': 0.8189238319173455}
+12/25/2021 01:12:52 - INFO - codeparrot_training - Step 15728: {'lr': 0.00038911938290191287, 'samples': 8053248, 'steps': 15728, 'batch_loss/train': 0.8456539362668991}
+12/25/2021 01:13:04 - INFO - codeparrot_training - Step 15729: {'lr': 0.0003891062856257639, 'samples': 8053760, 'steps': 15729, 'batch_loss/train': 0.8315775259397924}
+12/25/2021 01:13:14 - INFO - codeparrot_training - Step 15730: {'lr': 0.0003890931877965808, 'samples': 8054272, 'steps': 15730, 'batch_loss/train': 0.7180466895224527}
+12/25/2021 01:13:25 - INFO - codeparrot_training - Step 15731: {'lr': 0.00038908008941441574, 'samples': 8054784, 'steps': 15731, 'batch_loss/train': 0.619721140130423}
+12/25/2021 01:13:39 - INFO - codeparrot_training - Step 15732: {'lr': 0.0003890669904793208, 'samples': 8055296, 'steps': 15732, 'batch_loss/train': 0.7848477009683847}
+12/25/2021 01:13:49 - INFO - codeparrot_training - Step 15733: {'lr': 0.00038905389099134797, 'samples': 8055808, 'steps': 15733, 'batch_loss/train': 0.8551715640351176}
+12/25/2021 01:14:00 - INFO - codeparrot_training - Step 15734: {'lr': 0.0003890407909505494, 'samples': 8056320, 'steps': 15734, 'batch_loss/train': 0.7273200983181596}
+12/25/2021 01:14:12 - INFO - codeparrot_training - Step 15735: {'lr': 0.00038902769035697717, 'samples': 8056832, 'steps': 15735, 'batch_loss/train': 0.7942839420866221}
+12/25/2021 01:14:23 - INFO - codeparrot_training - Step 15736: {'lr': 0.0003890145892106832, 'samples': 8057344, 'steps': 15736, 'batch_loss/train': 0.7505403193645179}
+12/25/2021 01:14:33 - INFO - codeparrot_training - Step 15737: {'lr': 0.0003890014875117199, 'samples': 8057856, 'steps': 15737, 'batch_loss/train': 0.8676652563735843}
+12/25/2021 01:14:44 - INFO - codeparrot_training - Step 15738: {'lr': 0.000388988385260139, 'samples': 8058368, 'steps': 15738, 'batch_loss/train': 0.9023545440286398}
+12/25/2021 01:14:56 - INFO - codeparrot_training - Step 15739: {'lr': 0.0003889752824559929, 'samples': 8058880, 'steps': 15739, 'batch_loss/train': 0.8071632222272456}
+12/25/2021 01:15:07 - INFO - codeparrot_training - Step 15740: {'lr': 0.00038896217909933353, 'samples': 8059392, 'steps': 15740, 'batch_loss/train': 0.8287861885037273}
+12/25/2021 01:15:17 - INFO - codeparrot_training - Step 15741: {'lr': 0.0003889490751902129, 'samples': 8059904, 'steps': 15741, 'batch_loss/train': 0.8391963667236269}
+12/25/2021 01:15:31 - INFO - codeparrot_training - Step 15742: {'lr': 0.0003889359707286833, 'samples': 8060416, 'steps': 15742, 'batch_loss/train': 0.9243177846074104}
+12/25/2021 01:15:42 - INFO - codeparrot_training - Step 15743: {'lr': 0.0003889228657147967, 'samples': 8060928, 'steps': 15743, 'batch_loss/train': 0.7521049389615655}
+12/25/2021 01:15:52 - INFO - codeparrot_training - Step 15744: {'lr': 0.00038890976014860536, 'samples': 8061440, 'steps': 15744, 'batch_loss/train': 0.863966217264533}
+12/25/2021 01:16:04 - INFO - codeparrot_training - Step 15745: {'lr': 0.00038889665403016104, 'samples': 8061952, 'steps': 15745, 'batch_loss/train': 0.7828999310731888}
+12/25/2021 01:16:15 - INFO - codeparrot_training - Step 15746: {'lr': 0.00038888354735951624, 'samples': 8062464, 'steps': 15746, 'batch_loss/train': 0.7836721306666732}
+12/25/2021 01:16:25 - INFO - codeparrot_training - Step 15747: {'lr': 0.0003888704401367229, 'samples': 8062976, 'steps': 15747, 'batch_loss/train': 0.7520188391208649}
+12/25/2021 01:16:39 - INFO - codeparrot_training - Step 15748: {'lr': 0.0003888573323618331, 'samples': 8063488, 'steps': 15748, 'batch_loss/train': 0.8477816851809621}
+12/25/2021 01:16:50 - INFO - codeparrot_training - Step 15749: {'lr': 0.00038884422403489893, 'samples': 8064000, 'steps': 15749, 'batch_loss/train': 0.7981779668480158}
+12/25/2021 01:17:00 - INFO - codeparrot_training - Step 15750: {'lr': 0.00038883111515597256, 'samples': 8064512, 'steps': 15750, 'batch_loss/train': 0.8079640376381576}
+12/25/2021 01:17:11 - INFO - codeparrot_training - Step 15751: {'lr': 0.0003888180057251061, 'samples': 8065024, 'steps': 15751, 'batch_loss/train': 0.8195306742563844}
+12/25/2021 01:17:23 - INFO - codeparrot_training - Step 15752: {'lr': 0.00038880489574235174, 'samples': 8065536, 'steps': 15752, 'batch_loss/train': 0.7093187631107867}
+12/25/2021 01:17:34 - INFO - codeparrot_training - Step 15753: {'lr': 0.00038879178520776137, 'samples': 8066048, 'steps': 15753, 'batch_loss/train': 0.7841576496139169}
+12/25/2021 01:17:44 - INFO - codeparrot_training - Step 15754: {'lr': 0.0003887786741213874, 'samples': 8066560, 'steps': 15754, 'batch_loss/train': 0.865578860975802}
+12/25/2021 01:17:56 - INFO - codeparrot_training - Step 15755: {'lr': 0.00038876556248328175, 'samples': 8067072, 'steps': 15755, 'batch_loss/train': 0.7194801014848053}
+12/25/2021 01:18:07 - INFO - codeparrot_training - Step 15756: {'lr': 0.0003887524502934967, 'samples': 8067584, 'steps': 15756, 'batch_loss/train': 0.7807535557076335}
+12/25/2021 01:18:17 - INFO - codeparrot_training - Step 15757: {'lr': 0.00038873933755208424, 'samples': 8068096, 'steps': 15757, 'batch_loss/train': 0.8337992522865534}
+12/25/2021 01:18:31 - INFO - codeparrot_training - Step 15758: {'lr': 0.00038872622425909653, 'samples': 8068608, 'steps': 15758, 'batch_loss/train': 0.8307599449763075}
+12/25/2021 01:18:42 - INFO - codeparrot_training - Step 15759: {'lr': 0.0003887131104145858, 'samples': 8069120, 'steps': 15759, 'batch_loss/train': 0.7859542621299624}
+12/25/2021 01:18:52 - INFO - codeparrot_training - Step 15760: {'lr': 0.00038869999601860413, 'samples': 8069632, 'steps': 15760, 'batch_loss/train': 0.8759892955422401}
+12/25/2021 01:19:03 - INFO - codeparrot_training - Step 15761: {'lr': 0.0003886868810712036, 'samples': 8070144, 'steps': 15761, 'batch_loss/train': 0.7202123799361289}
+12/25/2021 01:19:15 - INFO - codeparrot_training - Step 15762: {'lr': 0.0003886737655724364, 'samples': 8070656, 'steps': 15762, 'batch_loss/train': 1.1478245612233877}
+12/25/2021 01:19:26 - INFO - codeparrot_training - Step 15763: {'lr': 0.00038866064952235467, 'samples': 8071168, 'steps': 15763, 'batch_loss/train': 0.7654831726104021}
+12/25/2021 01:19:36 - INFO - codeparrot_training - Step 15764: {'lr': 0.0003886475329210106, 'samples': 8071680, 'steps': 15764, 'batch_loss/train': 0.8525100278202444}
+12/25/2021 01:19:48 - INFO - codeparrot_training - Step 15765: {'lr': 0.0003886344157684562, 'samples': 8072192, 'steps': 15765, 'batch_loss/train': 0.8039464661851525}
+12/25/2021 01:19:59 - INFO - codeparrot_training - Step 15766: {'lr': 0.0003886212980647438, 'samples': 8072704, 'steps': 15766, 'batch_loss/train': 0.7589243678376079}
+12/25/2021 01:20:10 - INFO - codeparrot_training - Step 15767: {'lr': 0.00038860817980992533, 'samples': 8073216, 'steps': 15767, 'batch_loss/train': 0.8870594874024391}
+12/25/2021 01:20:22 - INFO - codeparrot_training - Step 15768: {'lr': 0.00038859506100405325, 'samples': 8073728, 'steps': 15768, 'batch_loss/train': 0.8176291091367602}
+12/25/2021 01:20:33 - INFO - codeparrot_training - Step 15769: {'lr': 0.00038858194164717943, 'samples': 8074240, 'steps': 15769, 'batch_loss/train': 0.7526822052896023}
+12/25/2021 01:20:43 - INFO - codeparrot_training - Step 15770: {'lr': 0.00038856882173935614, 'samples': 8074752, 'steps': 15770, 'batch_loss/train': 0.7799402549862862}
+12/25/2021 01:20:57 - INFO - codeparrot_training - Step 15771: {'lr': 0.00038855570128063557, 'samples': 8075264, 'steps': 15771, 'batch_loss/train': 0.5921095956582576}
+12/25/2021 01:21:08 - INFO - codeparrot_training - Step 15772: {'lr': 0.0003885425802710698, 'samples': 8075776, 'steps': 15772, 'batch_loss/train': 0.7451295657083392}
+12/25/2021 01:21:18 - INFO - codeparrot_training - Step 15773: {'lr': 0.0003885294587107111, 'samples': 8076288, 'steps': 15773, 'batch_loss/train': 0.8002108056098223}
+12/25/2021 01:21:29 - INFO - codeparrot_training - Step 15774: {'lr': 0.0003885163365996116, 'samples': 8076800, 'steps': 15774, 'batch_loss/train': 0.8798824055120349}
+12/25/2021 01:21:41 - INFO - codeparrot_training - Step 15775: {'lr': 0.0003885032139378234, 'samples': 8077312, 'steps': 15775, 'batch_loss/train': 0.8160007442347705}
+12/25/2021 01:21:52 - INFO - codeparrot_training - Step 15776: {'lr': 0.0003884900907253988, 'samples': 8077824, 'steps': 15776, 'batch_loss/train': 0.7782416632398963}
+12/25/2021 01:22:03 - INFO - codeparrot_training - Step 15777: {'lr': 0.00038847696696238973, 'samples': 8078336, 'steps': 15777, 'batch_loss/train': 0.796853574924171}
+12/25/2021 01:22:16 - INFO - codeparrot_training - Step 15778: {'lr': 0.0003884638426488486, 'samples': 8078848, 'steps': 15778, 'batch_loss/train': 0.7981440995354205}
+12/25/2021 01:22:27 - INFO - codeparrot_training - Step 15779: {'lr': 0.00038845071778482754, 'samples': 8079360, 'steps': 15779, 'batch_loss/train': 0.8315826123580337}
+12/25/2021 01:22:38 - INFO - codeparrot_training - Step 15780: {'lr': 0.00038843759237037866, 'samples': 8079872, 'steps': 15780, 'batch_loss/train': 0.8533467542147264}
+12/25/2021 01:22:49 - INFO - codeparrot_training - Step 15781: {'lr': 0.0003884244664055542, 'samples': 8080384, 'steps': 15781, 'batch_loss/train': 0.8294198457151651}
+12/25/2021 01:23:00 - INFO - codeparrot_training - Step 15782: {'lr': 0.0003884113398904063, 'samples': 8080896, 'steps': 15782, 'batch_loss/train': 0.76695159857627}
+12/25/2021 01:23:11 - INFO - codeparrot_training - Step 15783: {'lr': 0.0003883982128249872, 'samples': 8081408, 'steps': 15783, 'batch_loss/train': 0.964668293017894}
+12/25/2021 01:23:21 - INFO - codeparrot_training - Step 15784: {'lr': 0.0003883850852093491, 'samples': 8081920, 'steps': 15784, 'batch_loss/train': 0.7925855591893196}
+12/25/2021 01:23:33 - INFO - codeparrot_training - Step 15785: {'lr': 0.00038837195704354417, 'samples': 8082432, 'steps': 15785, 'batch_loss/train': 0.6926341284997761}
+12/25/2021 01:23:44 - INFO - codeparrot_training - Step 15786: {'lr': 0.00038835882832762453, 'samples': 8082944, 'steps': 15786, 'batch_loss/train': 0.8618613248690963}
+12/25/2021 01:23:55 - INFO - codeparrot_training - Step 15787: {'lr': 0.00038834569906164246, 'samples': 8083456, 'steps': 15787, 'batch_loss/train': 0.7856345595791936}
+12/25/2021 01:24:09 - INFO - codeparrot_training - Step 15788: {'lr': 0.0003883325692456501, 'samples': 8083968, 'steps': 15788, 'batch_loss/train': 0.7576914150267839}
+12/25/2021 01:24:19 - INFO - codeparrot_training - Step 15789: {'lr': 0.0003883194388796997, 'samples': 8084480, 'steps': 15789, 'batch_loss/train': 0.8791575022041798}
+12/25/2021 01:24:30 - INFO - codeparrot_training - Step 15790: {'lr': 0.00038830630796384344, 'samples': 8084992, 'steps': 15790, 'batch_loss/train': 0.8359487438574433}
+12/25/2021 01:24:42 - INFO - codeparrot_training - Step 15791: {'lr': 0.00038829317649813344, 'samples': 8085504, 'steps': 15791, 'batch_loss/train': 2.3388342964462936}
+12/25/2021 01:24:53 - INFO - codeparrot_training - Step 15792: {'lr': 0.0003882800444826221, 'samples': 8086016, 'steps': 15792, 'batch_loss/train': 0.8238516272976995}
+12/25/2021 01:25:03 - INFO - codeparrot_training - Step 15793: {'lr': 0.0003882669119173615, 'samples': 8086528, 'steps': 15793, 'batch_loss/train': 0.8959995210170746}
+12/25/2021 01:25:14 - INFO - codeparrot_training - Step 15794: {'lr': 0.0003882537788024039, 'samples': 8087040, 'steps': 15794, 'batch_loss/train': 0.8046516655012965}
+12/25/2021 01:25:29 - INFO - codeparrot_training - Step 15795: {'lr': 0.00038824064513780134, 'samples': 8087552, 'steps': 15795, 'batch_loss/train': 0.8112784763798118}
+12/25/2021 01:25:39 - INFO - codeparrot_training - Step 15796: {'lr': 0.00038822751092360626, 'samples': 8088064, 'steps': 15796, 'batch_loss/train': 1.3510772194713354}
+12/25/2021 01:25:50 - INFO - codeparrot_training - Step 15797: {'lr': 0.0003882143761598708, 'samples': 8088576, 'steps': 15797, 'batch_loss/train': 0.7776253074407578}
+12/25/2021 01:26:02 - INFO - codeparrot_training - Step 15798: {'lr': 0.00038820124084664717, 'samples': 8089088, 'steps': 15798, 'batch_loss/train': 0.7244692739332095}
+12/25/2021 01:26:12 - INFO - codeparrot_training - Step 15799: {'lr': 0.0003881881049839875, 'samples': 8089600, 'steps': 15799, 'batch_loss/train': 0.9769402123056352}
+12/25/2021 01:26:23 - INFO - codeparrot_training - Step 15800: {'lr': 0.00038817496857194425, 'samples': 8090112, 'steps': 15800, 'batch_loss/train': 0.8827284863218665}
+12/25/2021 01:26:33 - INFO - codeparrot_training - Step 15801: {'lr': 0.0003881618316105694, 'samples': 8090624, 'steps': 15801, 'batch_loss/train': 0.7763396454975009}
+12/25/2021 01:26:46 - INFO - codeparrot_training - Step 15802: {'lr': 0.0003881486940999153, 'samples': 8091136, 'steps': 15802, 'batch_loss/train': 0.8585425550118089}
+12/25/2021 01:26:56 - INFO - codeparrot_training - Step 15803: {'lr': 0.0003881355560400341, 'samples': 8091648, 'steps': 15803, 'batch_loss/train': 0.8608677983283997}
+12/25/2021 01:27:07 - INFO - codeparrot_training - Step 15804: {'lr': 0.00038812241743097815, 'samples': 8092160, 'steps': 15804, 'batch_loss/train': 0.7936427155509591}
+12/25/2021 01:27:19 - INFO - codeparrot_training - Step 15805: {'lr': 0.00038810927827279964, 'samples': 8092672, 'steps': 15805, 'batch_loss/train': 0.7100028721615672}
+12/25/2021 01:27:30 - INFO - codeparrot_training - Step 15806: {'lr': 0.0003880961385655507, 'samples': 8093184, 'steps': 15806, 'batch_loss/train': 0.8852280862629414}
+12/25/2021 01:27:40 - INFO - codeparrot_training - Step 15807: {'lr': 0.00038808299830928375, 'samples': 8093696, 'steps': 15807, 'batch_loss/train': 0.8328166026622057}
+12/25/2021 01:27:55 - INFO - codeparrot_training - Step 15808: {'lr': 0.0003880698575040509, 'samples': 8094208, 'steps': 15808, 'batch_loss/train': 1.552181909326464}
+12/25/2021 01:28:05 - INFO - codeparrot_training - Step 15809: {'lr': 0.0003880567161499044, 'samples': 8094720, 'steps': 15809, 'batch_loss/train': 0.7883434616960585}
+12/25/2021 01:28:16 - INFO - codeparrot_training - Step 15810: {'lr': 0.00038804357424689653, 'samples': 8095232, 'steps': 15810, 'batch_loss/train': 0.8242688747122884}
+12/25/2021 01:28:27 - INFO - codeparrot_training - Step 15811: {'lr': 0.0003880304317950796, 'samples': 8095744, 'steps': 15811, 'batch_loss/train': 0.8659042678773403}
+12/25/2021 01:28:39 - INFO - codeparrot_training - Step 15812: {'lr': 0.0003880172887945057, 'samples': 8096256, 'steps': 15812, 'batch_loss/train': 0.9363572802394629}
+12/25/2021 01:28:50 - INFO - codeparrot_training - Step 15813: {'lr': 0.00038800414524522726, 'samples': 8096768, 'steps': 15813, 'batch_loss/train': 0.7141980035230517}
+12/25/2021 01:29:00 - INFO - codeparrot_training - Step 15814: {'lr': 0.00038799100114729636, 'samples': 8097280, 'steps': 15814, 'batch_loss/train': 0.7787153943208978}
+12/25/2021 01:29:12 - INFO - codeparrot_training - Step 15815: {'lr': 0.0003879778565007654, 'samples': 8097792, 'steps': 15815, 'batch_loss/train': 1.5909388340078294}
+12/25/2021 01:29:23 - INFO - codeparrot_training - Step 15816: {'lr': 0.0003879647113056866, 'samples': 8098304, 'steps': 15816, 'batch_loss/train': 0.8117691529914737}
+12/25/2021 01:29:34 - INFO - codeparrot_training - Step 15817: {'lr': 0.00038795156556211216, 'samples': 8098816, 'steps': 15817, 'batch_loss/train': 0.8949981573969126}
+12/25/2021 01:29:44 - INFO - codeparrot_training - Step 15818: {'lr': 0.00038793841927009444, 'samples': 8099328, 'steps': 15818, 'batch_loss/train': 0.821864596568048}
+12/25/2021 01:29:58 - INFO - codeparrot_training - Step 15819: {'lr': 0.00038792527242968554, 'samples': 8099840, 'steps': 15819, 'batch_loss/train': 0.7330413246527314}
+12/25/2021 01:30:09 - INFO - codeparrot_training - Step 15820: {'lr': 0.0003879121250409379, 'samples': 8100352, 'steps': 15820, 'batch_loss/train': 1.0355707705020905}
+12/25/2021 01:30:19 - INFO - codeparrot_training - Step 15821: {'lr': 0.0003878989771039038, 'samples': 8100864, 'steps': 15821, 'batch_loss/train': 0.7631393475458026}
+12/25/2021 01:30:32 - INFO - codeparrot_training - Step 15822: {'lr': 0.0003878858286186353, 'samples': 8101376, 'steps': 15822, 'batch_loss/train': 0.8185333721339703}
+12/25/2021 01:30:42 - INFO - codeparrot_training - Step 15823: {'lr': 0.00038787267958518483, 'samples': 8101888, 'steps': 15823, 'batch_loss/train': 0.7538043493404984}
+12/25/2021 01:30:53 - INFO - codeparrot_training - Step 15824: {'lr': 0.00038785953000360475, 'samples': 8102400, 'steps': 15824, 'batch_loss/train': 1.027272627223283}
+12/25/2021 01:31:05 - INFO - codeparrot_training - Step 15825: {'lr': 0.0003878463798739471, 'samples': 8102912, 'steps': 15825, 'batch_loss/train': 0.9033350525423884}
+12/25/2021 01:31:16 - INFO - codeparrot_training - Step 15826: {'lr': 0.0003878332291962644, 'samples': 8103424, 'steps': 15826, 'batch_loss/train': 0.9149735840037465}
+12/25/2021 01:31:26 - INFO - codeparrot_training - Step 15827: {'lr': 0.00038782007797060874, 'samples': 8103936, 'steps': 15827, 'batch_loss/train': 0.9362528212368488}
+12/25/2021 01:31:37 - INFO - codeparrot_training - Step 15828: {'lr': 0.0003878069261970325, 'samples': 8104448, 'steps': 15828, 'batch_loss/train': 0.6363034762907773}
+12/25/2021 01:31:51 - INFO - codeparrot_training - Step 15829: {'lr': 0.000387793773875588, 'samples': 8104960, 'steps': 15829, 'batch_loss/train': 0.7258311687037349}
+12/25/2021 01:32:01 - INFO - codeparrot_training - Step 15830: {'lr': 0.0003877806210063275, 'samples': 8105472, 'steps': 15830, 'batch_loss/train': 0.8605827707797289}
+12/25/2021 01:32:12 - INFO - codeparrot_training - Step 15831: {'lr': 0.0003877674675893033, 'samples': 8105984, 'steps': 15831, 'batch_loss/train': 0.7228332534432411}
+12/25/2021 01:32:24 - INFO - codeparrot_training - Step 15832: {'lr': 0.0003877543136245676, 'samples': 8106496, 'steps': 15832, 'batch_loss/train': 0.640756132081151}
+12/25/2021 01:32:35 - INFO - codeparrot_training - Step 15833: {'lr': 0.0003877411591121728, 'samples': 8107008, 'steps': 15833, 'batch_loss/train': 0.8831069339066744}
+12/25/2021 01:32:46 - INFO - codeparrot_training - Step 15834: {'lr': 0.0003877280040521711, 'samples': 8107520, 'steps': 15834, 'batch_loss/train': 0.6902056368999183}
+12/25/2021 01:32:59 - INFO - codeparrot_training - Step 15835: {'lr': 0.0003877148484446149, 'samples': 8108032, 'steps': 15835, 'batch_loss/train': 1.0067432979121804}
+12/25/2021 01:33:10 - INFO - codeparrot_training - Step 15836: {'lr': 0.0003877016922895564, 'samples': 8108544, 'steps': 15836, 'batch_loss/train': 0.8549411841668189}
+12/25/2021 01:33:21 - INFO - codeparrot_training - Step 15837: {'lr': 0.0003876885355870481, 'samples': 8109056, 'steps': 15837, 'batch_loss/train': 0.8040331108495593}
+12/25/2021 01:33:31 - INFO - codeparrot_training - Step 15838: {'lr': 0.0003876753783371421, 'samples': 8109568, 'steps': 15838, 'batch_loss/train': 0.8002834897488356}
+12/25/2021 01:33:43 - INFO - codeparrot_training - Step 15839: {'lr': 0.0003876622205398907, 'samples': 8110080, 'steps': 15839, 'batch_loss/train': 0.8838485758751631}
+12/25/2021 01:33:54 - INFO - codeparrot_training - Step 15840: {'lr': 0.00038764906219534637, 'samples': 8110592, 'steps': 15840, 'batch_loss/train': 0.9330827724188566}
+12/25/2021 01:34:05 - INFO - codeparrot_training - Step 15841: {'lr': 0.00038763590330356134, 'samples': 8111104, 'steps': 15841, 'batch_loss/train': 0.8955740034580231}
+12/25/2021 01:34:17 - INFO - codeparrot_training - Step 15842: {'lr': 0.00038762274386458794, 'samples': 8111616, 'steps': 15842, 'batch_loss/train': 0.9341829782351851}
+12/25/2021 01:34:27 - INFO - codeparrot_training - Step 15843: {'lr': 0.00038760958387847847, 'samples': 8112128, 'steps': 15843, 'batch_loss/train': 0.7551649492233992}
+12/25/2021 01:34:38 - INFO - codeparrot_training - Step 15844: {'lr': 0.00038759642334528524, 'samples': 8112640, 'steps': 15844, 'batch_loss/train': 0.8448627507314086}
+12/25/2021 01:34:51 - INFO - codeparrot_training - Step 15845: {'lr': 0.00038758326226506057, 'samples': 8113152, 'steps': 15845, 'batch_loss/train': 0.843301868531853}
+12/25/2021 01:35:02 - INFO - codeparrot_training - Step 15846: {'lr': 0.00038757010063785683, 'samples': 8113664, 'steps': 15846, 'batch_loss/train': 1.5293164160102606}
+12/25/2021 01:35:13 - INFO - codeparrot_training - Step 15847: {'lr': 0.0003875569384637263, 'samples': 8114176, 'steps': 15847, 'batch_loss/train': 0.9010554095730186}
+12/25/2021 01:35:23 - INFO - codeparrot_training - Step 15848: {'lr': 0.0003875437757427214, 'samples': 8114688, 'steps': 15848, 'batch_loss/train': 0.8444194495677948}
+12/25/2021 01:35:36 - INFO - codeparrot_training - Step 15849: {'lr': 0.00038753061247489423, 'samples': 8115200, 'steps': 15849, 'batch_loss/train': 0.9140803748741746}
+12/25/2021 01:35:46 - INFO - codeparrot_training - Step 15850: {'lr': 0.0003875174486602974, 'samples': 8115712, 'steps': 15850, 'batch_loss/train': 1.711788178421557}
+12/25/2021 01:35:57 - INFO - codeparrot_training - Step 15851: {'lr': 0.000387504284298983, 'samples': 8116224, 'steps': 15851, 'batch_loss/train': 1.260687910602428}
+12/25/2021 01:36:09 - INFO - codeparrot_training - Step 15852: {'lr': 0.00038749111939100355, 'samples': 8116736, 'steps': 15852, 'batch_loss/train': 0.808910702355206}
+12/25/2021 01:36:20 - INFO - codeparrot_training - Step 15853: {'lr': 0.00038747795393641137, 'samples': 8117248, 'steps': 15853, 'batch_loss/train': 0.8862286945804954}
+12/25/2021 01:36:30 - INFO - codeparrot_training - Step 15854: {'lr': 0.00038746478793525867, 'samples': 8117760, 'steps': 15854, 'batch_loss/train': 0.8333350396715105}
+12/25/2021 01:36:41 - INFO - codeparrot_training - Step 15855: {'lr': 0.0003874516213875979, 'samples': 8118272, 'steps': 15855, 'batch_loss/train': 0.7371831117197871}
+12/25/2021 01:36:53 - INFO - codeparrot_training - Step 15856: {'lr': 0.00038743845429348145, 'samples': 8118784, 'steps': 15856, 'batch_loss/train': 0.8397204801440239}
+12/25/2021 01:37:03 - INFO - codeparrot_training - Step 15857: {'lr': 0.0003874252866529616, 'samples': 8119296, 'steps': 15857, 'batch_loss/train': 0.8299220823682845}
+12/25/2021 01:37:14 - INFO - codeparrot_training - Step 15858: {'lr': 0.00038741211846609057, 'samples': 8119808, 'steps': 15858, 'batch_loss/train': 0.88418132904917}
+12/25/2021 01:37:28 - INFO - codeparrot_training - Step 15859: {'lr': 0.000387398949732921, 'samples': 8120320, 'steps': 15859, 'batch_loss/train': 1.6038665059022605}
+12/25/2021 01:37:38 - INFO - codeparrot_training - Step 15860: {'lr': 0.000387385780453505, 'samples': 8120832, 'steps': 15860, 'batch_loss/train': 0.7689180788584054}
+12/25/2021 01:37:49 - INFO - codeparrot_training - Step 15861: {'lr': 0.000387372610627895, 'samples': 8121344, 'steps': 15861, 'batch_loss/train': 0.8917086201254278}
+12/25/2021 01:38:01 - INFO - codeparrot_training - Step 15862: {'lr': 0.00038735944025614343, 'samples': 8121856, 'steps': 15862, 'batch_loss/train': 0.7735841209068894}
+12/25/2021 01:38:12 - INFO - codeparrot_training - Step 15863: {'lr': 0.00038734626933830253, 'samples': 8122368, 'steps': 15863, 'batch_loss/train': 0.8367095682770014}
+12/25/2021 01:38:22 - INFO - codeparrot_training - Step 15864: {'lr': 0.0003873330978744247, 'samples': 8122880, 'steps': 15864, 'batch_loss/train': 0.8241643570363522}
+12/25/2021 01:38:36 - INFO - codeparrot_training - Step 15865: {'lr': 0.00038731992586456244, 'samples': 8123392, 'steps': 15865, 'batch_loss/train': 0.8427147883921862}
+12/25/2021 01:38:47 - INFO - codeparrot_training - Step 15866: {'lr': 0.000387306753308768, 'samples': 8123904, 'steps': 15866, 'batch_loss/train': 0.8458883622661233}
+12/25/2021 01:38:57 - INFO - codeparrot_training - Step 15867: {'lr': 0.0003872935802070936, 'samples': 8124416, 'steps': 15867, 'batch_loss/train': 0.7779077213490382}
+12/25/2021 01:39:08 - INFO - codeparrot_training - Step 15868: {'lr': 0.0003872804065595919, 'samples': 8124928, 'steps': 15868, 'batch_loss/train': 0.8522523127030581}
+12/25/2021 01:39:21 - INFO - codeparrot_training - Step 15869: {'lr': 0.00038726723236631505, 'samples': 8125440, 'steps': 15869, 'batch_loss/train': 0.7877747411839664}
+12/25/2021 01:39:31 - INFO - codeparrot_training - Step 15870: {'lr': 0.0003872540576273156, 'samples': 8125952, 'steps': 15870, 'batch_loss/train': 0.8664722796529531}
+12/25/2021 01:39:42 - INFO - codeparrot_training - Step 15871: {'lr': 0.00038724088234264574, 'samples': 8126464, 'steps': 15871, 'batch_loss/train': 0.5499703856185079}
+12/25/2021 01:39:54 - INFO - codeparrot_training - Step 15872: {'lr': 0.0003872277065123581, 'samples': 8126976, 'steps': 15872, 'batch_loss/train': 0.8324263896793127}
+12/25/2021 01:40:04 - INFO - codeparrot_training - Step 15873: {'lr': 0.00038721453013650483, 'samples': 8127488, 'steps': 15873, 'batch_loss/train': 0.7686089789494872}
+12/25/2021 01:40:15 - INFO - codeparrot_training - Step 15874: {'lr': 0.0003872013532151384, 'samples': 8128000, 'steps': 15874, 'batch_loss/train': 0.8209060980007052}
+12/25/2021 01:40:26 - INFO - codeparrot_training - Step 15875: {'lr': 0.00038718817574831115, 'samples': 8128512, 'steps': 15875, 'batch_loss/train': 0.6660781520185992}
+12/25/2021 01:40:39 - INFO - codeparrot_training - Step 15876: {'lr': 0.00038717499773607557, 'samples': 8129024, 'steps': 15876, 'batch_loss/train': 0.8291748436167836}
+12/25/2021 01:40:50 - INFO - codeparrot_training - Step 15877: {'lr': 0.00038716181917848396, 'samples': 8129536, 'steps': 15877, 'batch_loss/train': 0.7278742502676323}
+12/25/2021 01:41:01 - INFO - codeparrot_training - Step 15878: {'lr': 0.0003871486400755888, 'samples': 8130048, 'steps': 15878, 'batch_loss/train': 0.8116934881545603}
+12/25/2021 01:41:13 - INFO - codeparrot_training - Step 15879: {'lr': 0.0003871354604274424, 'samples': 8130560, 'steps': 15879, 'batch_loss/train': 0.9245752098504454}
+12/25/2021 01:41:24 - INFO - codeparrot_training - Step 15880: {'lr': 0.00038712228023409716, 'samples': 8131072, 'steps': 15880, 'batch_loss/train': 0.7718422044999897}
+12/25/2021 01:41:34 - INFO - codeparrot_training - Step 15881: {'lr': 0.00038710909949560556, 'samples': 8131584, 'steps': 15881, 'batch_loss/train': 0.8212699617724866}
+12/25/2021 01:41:46 - INFO - codeparrot_training - Step 15882: {'lr': 0.00038709591821201993, 'samples': 8132096, 'steps': 15882, 'batch_loss/train': 0.7212107892846689}
+12/25/2021 01:41:57 - INFO - codeparrot_training - Step 15883: {'lr': 0.00038708273638339276, 'samples': 8132608, 'steps': 15883, 'batch_loss/train': 0.7743928264826536}
+12/25/2021 01:42:08 - INFO - codeparrot_training - Step 15884: {'lr': 0.0003870695540097763, 'samples': 8133120, 'steps': 15884, 'batch_loss/train': 0.7857242487370968}
+12/25/2021 01:42:18 - INFO - codeparrot_training - Step 15885: {'lr': 0.00038705637109122306, 'samples': 8133632, 'steps': 15885, 'batch_loss/train': 0.7918857175391167}
+12/25/2021 01:42:32 - INFO - codeparrot_training - Step 15886: {'lr': 0.00038704318762778543, 'samples': 8134144, 'steps': 15886, 'batch_loss/train': 0.7338874759152532}
+12/25/2021 01:42:43 - INFO - codeparrot_training - Step 15887: {'lr': 0.0003870300036195159, 'samples': 8134656, 'steps': 15887, 'batch_loss/train': 0.8313284711912274}
+12/25/2021 01:42:53 - INFO - codeparrot_training - Step 15888: {'lr': 0.00038701681906646673, 'samples': 8135168, 'steps': 15888, 'batch_loss/train': 0.8071038937196136}
+12/25/2021 01:43:05 - INFO - codeparrot_training - Step 15889: {'lr': 0.00038700363396869045, 'samples': 8135680, 'steps': 15889, 'batch_loss/train': 0.7605591872707009}
+12/25/2021 01:43:16 - INFO - codeparrot_training - Step 15890: {'lr': 0.0003869904483262395, 'samples': 8136192, 'steps': 15890, 'batch_loss/train': 0.8158892346546054}
+12/25/2021 01:43:26 - INFO - codeparrot_training - Step 15891: {'lr': 0.00038697726213916616, 'samples': 8136704, 'steps': 15891, 'batch_loss/train': 0.835092926165089}
+12/25/2021 01:43:39 - INFO - codeparrot_training - Step 15892: {'lr': 0.00038696407540752306, 'samples': 8137216, 'steps': 15892, 'batch_loss/train': 0.8660615645349026}
+12/25/2021 01:43:49 - INFO - codeparrot_training - Step 15893: {'lr': 0.00038695088813136245, 'samples': 8137728, 'steps': 15893, 'batch_loss/train': 0.7833918277174234}
+12/25/2021 01:44:00 - INFO - codeparrot_training - Step 15894: {'lr': 0.0003869377003107368, 'samples': 8138240, 'steps': 15894, 'batch_loss/train': 0.7370122694410384}
+12/25/2021 01:44:10 - INFO - codeparrot_training - Step 15895: {'lr': 0.00038692451194569853, 'samples': 8138752, 'steps': 15895, 'batch_loss/train': 0.8058617315255105}
+12/25/2021 01:44:24 - INFO - codeparrot_training - Step 15896: {'lr': 0.0003869113230363002, 'samples': 8139264, 'steps': 15896, 'batch_loss/train': 0.8570855716243386}
+12/25/2021 01:44:35 - INFO - codeparrot_training - Step 15897: {'lr': 0.00038689813358259415, 'samples': 8139776, 'steps': 15897, 'batch_loss/train': 0.8876968119293451}
+12/25/2021 01:44:45 - INFO - codeparrot_training - Step 15898: {'lr': 0.0003868849435846328, 'samples': 8140288, 'steps': 15898, 'batch_loss/train': 0.850636709947139}
+12/25/2021 01:44:58 - INFO - codeparrot_training - Step 15899: {'lr': 0.0003868717530424685, 'samples': 8140800, 'steps': 15899, 'batch_loss/train': 0.8473618859425187}
+12/25/2021 01:45:08 - INFO - codeparrot_training - Step 15900: {'lr': 0.0003868585619561539, 'samples': 8141312, 'steps': 15900, 'batch_loss/train': 1.1239904006943107}
+12/25/2021 01:45:19 - INFO - codeparrot_training - Step 15901: {'lr': 0.00038684537032574124, 'samples': 8141824, 'steps': 15901, 'batch_loss/train': 0.7259607380256057}
+12/25/2021 01:45:31 - INFO - codeparrot_training - Step 15902: {'lr': 0.00038683217815128315, 'samples': 8142336, 'steps': 15902, 'batch_loss/train': 0.8668377576395869}
+12/25/2021 01:45:41 - INFO - codeparrot_training - Step 15903: {'lr': 0.0003868189854328319, 'samples': 8142848, 'steps': 15903, 'batch_loss/train': 0.7397450185380876}
+12/25/2021 01:45:52 - INFO - codeparrot_training - Step 15904: {'lr': 0.0003868057921704401, 'samples': 8143360, 'steps': 15904, 'batch_loss/train': 0.8425621276255697}
+12/25/2021 01:46:03 - INFO - codeparrot_training - Step 15905: {'lr': 0.0003867925983641601, 'samples': 8143872, 'steps': 15905, 'batch_loss/train': 0.9375513000413775}
+12/25/2021 01:46:16 - INFO - codeparrot_training - Step 15906: {'lr': 0.0003867794040140443, 'samples': 8144384, 'steps': 15906, 'batch_loss/train': 0.8249609540216625}
+12/25/2021 01:46:27 - INFO - codeparrot_training - Step 15907: {'lr': 0.0003867662091201454, 'samples': 8144896, 'steps': 15907, 'batch_loss/train': 0.8533682487905025}
+12/25/2021 01:46:38 - INFO - codeparrot_training - Step 15908: {'lr': 0.0003867530136825156, 'samples': 8145408, 'steps': 15908, 'batch_loss/train': 0.8363103144802153}
+12/25/2021 01:46:50 - INFO - codeparrot_training - Step 15909: {'lr': 0.0003867398177012074, 'samples': 8145920, 'steps': 15909, 'batch_loss/train': 0.7907789656892419}
+12/25/2021 01:47:00 - INFO - codeparrot_training - Step 15910: {'lr': 0.0003867266211762734, 'samples': 8146432, 'steps': 15910, 'batch_loss/train': 0.7807363520842046}
+12/25/2021 01:47:11 - INFO - codeparrot_training - Step 15911: {'lr': 0.00038671342410776595, 'samples': 8146944, 'steps': 15911, 'batch_loss/train': 0.8284837482497096}
+12/25/2021 01:47:25 - INFO - codeparrot_training - Step 15912: {'lr': 0.00038670022649573755, 'samples': 8147456, 'steps': 15912, 'batch_loss/train': 0.8006750317290425}
+12/25/2021 01:47:35 - INFO - codeparrot_training - Step 15913: {'lr': 0.0003866870283402406, 'samples': 8147968, 'steps': 15913, 'batch_loss/train': 0.8742643436416984}
+12/25/2021 01:47:46 - INFO - codeparrot_training - Step 15914: {'lr': 0.0003866738296413277, 'samples': 8148480, 'steps': 15914, 'batch_loss/train': 0.8479123343713582}
+12/25/2021 01:47:56 - INFO - codeparrot_training - Step 15915: {'lr': 0.0003866606303990513, 'samples': 8148992, 'steps': 15915, 'batch_loss/train': 0.7559634274803102}
+12/25/2021 01:48:09 - INFO - codeparrot_training - Step 15916: {'lr': 0.0003866474306134638, 'samples': 8149504, 'steps': 15916, 'batch_loss/train': 0.8192490248475224}
+12/25/2021 01:48:19 - INFO - codeparrot_training - Step 15917: {'lr': 0.00038663423028461767, 'samples': 8150016, 'steps': 15917, 'batch_loss/train': 0.7710335599258542}
+12/25/2021 01:48:30 - INFO - codeparrot_training - Step 15918: {'lr': 0.0003866210294125655, 'samples': 8150528, 'steps': 15918, 'batch_loss/train': 1.0272972490638494}
+12/25/2021 01:48:42 - INFO - codeparrot_training - Step 15919: {'lr': 0.00038660782799735966, 'samples': 8151040, 'steps': 15919, 'batch_loss/train': 0.82004225673154}
+12/25/2021 01:48:53 - INFO - codeparrot_training - Step 15920: {'lr': 0.0003865946260390527, 'samples': 8151552, 'steps': 15920, 'batch_loss/train': 0.817459037527442}
+12/25/2021 01:49:03 - INFO - codeparrot_training - Step 15921: {'lr': 0.0003865814235376971, 'samples': 8152064, 'steps': 15921, 'batch_loss/train': 0.8045809753239155}
+12/25/2021 01:49:15 - INFO - codeparrot_training - Step 15922: {'lr': 0.00038656822049334526, 'samples': 8152576, 'steps': 15922, 'batch_loss/train': 0.8840352231636643}
+12/25/2021 01:49:26 - INFO - codeparrot_training - Step 15923: {'lr': 0.00038655501690604976, 'samples': 8153088, 'steps': 15923, 'batch_loss/train': 0.86929767485708}
+12/25/2021 01:49:36 - INFO - codeparrot_training - Step 15924: {'lr': 0.00038654181277586317, 'samples': 8153600, 'steps': 15924, 'batch_loss/train': 0.8093113685026765}
+12/25/2021 01:49:50 - INFO - codeparrot_training - Step 15925: {'lr': 0.0003865286081028378, 'samples': 8154112, 'steps': 15925, 'batch_loss/train': 0.7946366625837982}
+12/25/2021 01:50:01 - INFO - codeparrot_training - Step 15926: {'lr': 0.0003865154028870262, 'samples': 8154624, 'steps': 15926, 'batch_loss/train': 0.8584465961903334}
+12/25/2021 01:50:11 - INFO - codeparrot_training - Step 15927: {'lr': 0.000386502197128481, 'samples': 8155136, 'steps': 15927, 'batch_loss/train': 0.7386957972776145}
+12/25/2021 01:50:22 - INFO - codeparrot_training - Step 15928: {'lr': 0.00038648899082725454, 'samples': 8155648, 'steps': 15928, 'batch_loss/train': 0.7640315662138164}
+12/25/2021 01:50:34 - INFO - codeparrot_training - Step 15929: {'lr': 0.00038647578398339947, 'samples': 8156160, 'steps': 15929, 'batch_loss/train': 0.8132463060319424}
+12/25/2021 01:50:45 - INFO - codeparrot_training - Step 15930: {'lr': 0.0003864625765969681, 'samples': 8156672, 'steps': 15930, 'batch_loss/train': 0.758939404040575}
+12/25/2021 01:50:55 - INFO - codeparrot_training - Step 15931: {'lr': 0.00038644936866801314, 'samples': 8157184, 'steps': 15931, 'batch_loss/train': 0.7920699408277869}
+12/25/2021 01:51:07 - INFO - codeparrot_training - Step 15932: {'lr': 0.0003864361601965869, 'samples': 8157696, 'steps': 15932, 'batch_loss/train': 0.8473845645785332}
+12/25/2021 01:51:18 - INFO - codeparrot_training - Step 15933: {'lr': 0.0003864229511827422, 'samples': 8158208, 'steps': 15933, 'batch_loss/train': 0.8401345312595367}
+12/25/2021 01:51:28 - INFO - codeparrot_training - Step 15934: {'lr': 0.0003864097416265311, 'samples': 8158720, 'steps': 15934, 'batch_loss/train': 0.7683365680277348}
+12/25/2021 01:51:42 - INFO - codeparrot_training - Step 15935: {'lr': 0.00038639653152800656, 'samples': 8159232, 'steps': 15935, 'batch_loss/train': 0.8957844823598862}
+12/25/2021 01:51:53 - INFO - codeparrot_training - Step 15936: {'lr': 0.00038638332088722084, 'samples': 8159744, 'steps': 15936, 'batch_loss/train': 0.7911417931318283}
+12/25/2021 01:52:04 - INFO - codeparrot_training - Step 15937: {'lr': 0.0003863701097042266, 'samples': 8160256, 'steps': 15937, 'batch_loss/train': 1.0067486630287021}
+12/25/2021 01:52:14 - INFO - codeparrot_training - Step 15938: {'lr': 0.00038635689797907627, 'samples': 8160768, 'steps': 15938, 'batch_loss/train': 0.8668714445084333}
+12/25/2021 01:52:26 - INFO - codeparrot_training - Step 15939: {'lr': 0.0003863436857118223, 'samples': 8161280, 'steps': 15939, 'batch_loss/train': 0.8365232376381755}
+12/25/2021 01:52:37 - INFO - codeparrot_training - Step 15940: {'lr': 0.00038633047290251743, 'samples': 8161792, 'steps': 15940, 'batch_loss/train': 0.7780972379259765}
+12/25/2021 01:52:47 - INFO - codeparrot_training - Step 15941: {'lr': 0.000386317259551214, 'samples': 8162304, 'steps': 15941, 'batch_loss/train': 0.727162878960371}
+12/25/2021 01:53:01 - INFO - codeparrot_training - Step 15942: {'lr': 0.00038630404565796473, 'samples': 8162816, 'steps': 15942, 'batch_loss/train': 0.7797388387843966}
+12/25/2021 01:53:12 - INFO - codeparrot_training - Step 15943: {'lr': 0.0003862908312228219, 'samples': 8163328, 'steps': 15943, 'batch_loss/train': 0.8519325125962496}
+12/25/2021 01:53:23 - INFO - codeparrot_training - Step 15944: {'lr': 0.00038627761624583835, 'samples': 8163840, 'steps': 15944, 'batch_loss/train': 0.9391738567501307}
+12/25/2021 01:53:35 - INFO - codeparrot_training - Step 15945: {'lr': 0.0003862644007270663, 'samples': 8164352, 'steps': 15945, 'batch_loss/train': 0.7426668554544449}
+12/25/2021 01:53:45 - INFO - codeparrot_training - Step 15946: {'lr': 0.0003862511846665585, 'samples': 8164864, 'steps': 15946, 'batch_loss/train': 0.8808911424130201}
+12/25/2021 01:53:56 - INFO - codeparrot_training - Step 15947: {'lr': 0.0003862379680643675, 'samples': 8165376, 'steps': 15947, 'batch_loss/train': 0.7879922252614051}
+12/25/2021 01:54:07 - INFO - codeparrot_training - Step 15948: {'lr': 0.0003862247509205457, 'samples': 8165888, 'steps': 15948, 'batch_loss/train': 0.8925350410863757}
+12/25/2021 01:54:19 - INFO - codeparrot_training - Step 15949: {'lr': 0.0003862115332351458, 'samples': 8166400, 'steps': 15949, 'batch_loss/train': 0.5835096794180572}
+12/25/2021 01:54:29 - INFO - codeparrot_training - Step 15950: {'lr': 0.0003861983150082201, 'samples': 8166912, 'steps': 15950, 'batch_loss/train': 0.9149036314338446}
+12/25/2021 01:54:40 - INFO - codeparrot_training - Step 15951: {'lr': 0.00038618509623982155, 'samples': 8167424, 'steps': 15951, 'batch_loss/train': 0.7576398244127631}
+12/25/2021 01:54:53 - INFO - codeparrot_training - Step 15952: {'lr': 0.00038617187693000234, 'samples': 8167936, 'steps': 15952, 'batch_loss/train': 0.8431260804645717}
+12/25/2021 01:55:03 - INFO - codeparrot_training - Step 15953: {'lr': 0.00038615865707881524, 'samples': 8168448, 'steps': 15953, 'batch_loss/train': 0.8190409708768129}
+12/25/2021 01:55:14 - INFO - codeparrot_training - Step 15954: {'lr': 0.0003861454366863126, 'samples': 8168960, 'steps': 15954, 'batch_loss/train': 0.7545430640457198}
+12/25/2021 01:55:26 - INFO - codeparrot_training - Step 15955: {'lr': 0.0003861322157525473, 'samples': 8169472, 'steps': 15955, 'batch_loss/train': 0.787816857919097}
+12/25/2021 01:55:36 - INFO - codeparrot_training - Step 15956: {'lr': 0.0003861189942775716, 'samples': 8169984, 'steps': 15956, 'batch_loss/train': 0.8659446869278327}
+12/25/2021 01:55:47 - INFO - codeparrot_training - Step 15957: {'lr': 0.0003861057722614382, 'samples': 8170496, 'steps': 15957, 'batch_loss/train': 0.7620205436833203}
+12/25/2021 01:55:59 - INFO - codeparrot_training - Step 15958: {'lr': 0.00038609254970419963, 'samples': 8171008, 'steps': 15958, 'batch_loss/train': 0.7407871743198484}
+12/25/2021 01:56:10 - INFO - codeparrot_training - Step 15959: {'lr': 0.0003860793266059085, 'samples': 8171520, 'steps': 15959, 'batch_loss/train': 0.8457195097580552}
+12/25/2021 01:56:20 - INFO - codeparrot_training - Step 15960: {'lr': 0.0003860661029666173, 'samples': 8172032, 'steps': 15960, 'batch_loss/train': 0.7798801818862557}
+12/25/2021 01:56:31 - INFO - codeparrot_training - Step 15961: {'lr': 0.0003860528787863787, 'samples': 8172544, 'steps': 15961, 'batch_loss/train': 0.7474884039256722}
+12/25/2021 01:56:43 - INFO - codeparrot_training - Step 15962: {'lr': 0.0003860396540652452, 'samples': 8173056, 'steps': 15962, 'batch_loss/train': 0.8923864169046283}
+12/25/2021 01:56:53 - INFO - codeparrot_training - Step 15963: {'lr': 0.00038602642880326935, 'samples': 8173568, 'steps': 15963, 'batch_loss/train': 0.8600718812085688}
+12/25/2021 01:57:04 - INFO - codeparrot_training - Step 15964: {'lr': 0.0003860132030005038, 'samples': 8174080, 'steps': 15964, 'batch_loss/train': 0.8738114880397916}
+12/25/2021 01:57:18 - INFO - codeparrot_training - Step 15965: {'lr': 0.00038599997665700114, 'samples': 8174592, 'steps': 15965, 'batch_loss/train': 0.8058833004906774}
+12/25/2021 01:57:28 - INFO - codeparrot_training - Step 15966: {'lr': 0.000385986749772814, 'samples': 8175104, 'steps': 15966, 'batch_loss/train': 0.8185350354760885}
+12/25/2021 01:57:39 - INFO - codeparrot_training - Step 15967: {'lr': 0.0003859735223479948, 'samples': 8175616, 'steps': 15967, 'batch_loss/train': 0.986338971182704}
+12/25/2021 01:57:51 - INFO - codeparrot_training - Step 15968: {'lr': 0.00038596029438259623, 'samples': 8176128, 'steps': 15968, 'batch_loss/train': 0.8111048098653555}
+12/25/2021 01:58:02 - INFO - codeparrot_training - Step 15969: {'lr': 0.00038594706587667085, 'samples': 8176640, 'steps': 15969, 'batch_loss/train': 0.922180250287056}
+12/25/2021 01:58:13 - INFO - codeparrot_training - Step 15970: {'lr': 0.00038593383683027134, 'samples': 8177152, 'steps': 15970, 'batch_loss/train': 1.156101196538657}
+12/25/2021 01:58:23 - INFO - codeparrot_training - Step 15971: {'lr': 0.0003859206072434501, 'samples': 8177664, 'steps': 15971, 'batch_loss/train': 1.1727699318435043}
+12/25/2021 01:58:36 - INFO - codeparrot_training - Step 15972: {'lr': 0.00038590737711625994, 'samples': 8178176, 'steps': 15972, 'batch_loss/train': 0.6796718371333554}
+12/25/2021 01:58:46 - INFO - codeparrot_training - Step 15973: {'lr': 0.0003858941464487533, 'samples': 8178688, 'steps': 15973, 'batch_loss/train': 0.8828242023009807}
+12/25/2021 01:58:57 - INFO - codeparrot_training - Step 15974: {'lr': 0.00038588091524098295, 'samples': 8179200, 'steps': 15974, 'batch_loss/train': 0.7550649229669943}
+12/25/2021 01:59:09 - INFO - codeparrot_training - Step 15975: {'lr': 0.00038586768349300126, 'samples': 8179712, 'steps': 15975, 'batch_loss/train': 0.7840683097019792}
+12/25/2021 01:59:20 - INFO - codeparrot_training - Step 15976: {'lr': 0.00038585445120486105, 'samples': 8180224, 'steps': 15976, 'batch_loss/train': 0.7015423662960529}
+12/25/2021 01:59:30 - INFO - codeparrot_training - Step 15977: {'lr': 0.0003858412183766148, 'samples': 8180736, 'steps': 15977, 'batch_loss/train': 0.837539890781045}
+12/25/2021 01:59:43 - INFO - codeparrot_training - Step 15978: {'lr': 0.0003858279850083152, 'samples': 8181248, 'steps': 15978, 'batch_loss/train': 0.8729233774356544}
+12/25/2021 01:59:53 - INFO - codeparrot_training - Step 15979: {'lr': 0.0003858147511000148, 'samples': 8181760, 'steps': 15979, 'batch_loss/train': 0.8719982132315636}
+12/25/2021 02:00:04 - INFO - codeparrot_training - Step 15980: {'lr': 0.0003858015166517662, 'samples': 8182272, 'steps': 15980, 'batch_loss/train': 0.7959411516785622}
+12/25/2021 02:00:15 - INFO - codeparrot_training - Step 15981: {'lr': 0.00038578828166362214, 'samples': 8182784, 'steps': 15981, 'batch_loss/train': 0.7907535424456}
+12/25/2021 02:00:27 - INFO - codeparrot_training - Step 15982: {'lr': 0.00038577504613563496, 'samples': 8183296, 'steps': 15982, 'batch_loss/train': 0.9062036825343966}
+12/25/2021 02:00:38 - INFO - codeparrot_training - Step 15983: {'lr': 0.00038576181006785766, 'samples': 8183808, 'steps': 15983, 'batch_loss/train': 0.9249244048260152}
+12/25/2021 02:00:49 - INFO - codeparrot_training - Step 15984: {'lr': 0.0003857485734603425, 'samples': 8184320, 'steps': 15984, 'batch_loss/train': 0.9262448074296117}
+12/25/2021 02:01:01 - INFO - codeparrot_training - Step 15985: {'lr': 0.0003857353363131424, 'samples': 8184832, 'steps': 15985, 'batch_loss/train': 0.9019403057172894}
+12/25/2021 02:01:11 - INFO - codeparrot_training - Step 15986: {'lr': 0.00038572209862630983, 'samples': 8185344, 'steps': 15986, 'batch_loss/train': 0.908678999170661}
+12/25/2021 02:01:22 - INFO - codeparrot_training - Step 15987: {'lr': 0.0003857088603998974, 'samples': 8185856, 'steps': 15987, 'batch_loss/train': 0.7979239327833056}
+12/25/2021 02:01:34 - INFO - codeparrot_training - Step 15988: {'lr': 0.00038569562163395777, 'samples': 8186368, 'steps': 15988, 'batch_loss/train': 0.923509752843529}
+12/25/2021 02:01:45 - INFO - codeparrot_training - Step 15989: {'lr': 0.0003856823823285436, 'samples': 8186880, 'steps': 15989, 'batch_loss/train': 0.5822119442746043}
+12/25/2021 02:01:56 - INFO - codeparrot_training - Step 15990: {'lr': 0.00038566914248370755, 'samples': 8187392, 'steps': 15990, 'batch_loss/train': 0.790259781293571}
+12/25/2021 02:02:06 - INFO - codeparrot_training - Step 15991: {'lr': 0.0003856559020995022, 'samples': 8187904, 'steps': 15991, 'batch_loss/train': 0.8976043476723135}
+12/25/2021 02:02:19 - INFO - codeparrot_training - Step 15992: {'lr': 0.0003856426611759802, 'samples': 8188416, 'steps': 15992, 'batch_loss/train': 0.8077692771330476}
+12/25/2021 02:02:29 - INFO - codeparrot_training - Step 15993: {'lr': 0.00038562941971319423, 'samples': 8188928, 'steps': 15993, 'batch_loss/train': 0.9481079075485468}
+12/25/2021 02:02:40 - INFO - codeparrot_training - Step 15994: {'lr': 0.00038561617771119686, 'samples': 8189440, 'steps': 15994, 'batch_loss/train': 0.9331595590338111}
+12/25/2021 02:02:52 - INFO - codeparrot_training - Step 15995: {'lr': 0.0003856029351700407, 'samples': 8189952, 'steps': 15995, 'batch_loss/train': 0.8227151832543314}
+12/25/2021 02:03:03 - INFO - codeparrot_training - Step 15996: {'lr': 0.0003855896920897786, 'samples': 8190464, 'steps': 15996, 'batch_loss/train': 0.7849228528793901}
+12/25/2021 02:03:13 - INFO - codeparrot_training - Step 15997: {'lr': 0.00038557644847046296, 'samples': 8190976, 'steps': 15997, 'batch_loss/train': 0.8737126723863184}
+12/25/2021 02:03:26 - INFO - codeparrot_training - Step 15998: {'lr': 0.00038556320431214664, 'samples': 8191488, 'steps': 15998, 'batch_loss/train': 0.8017204981297255}
+12/25/2021 02:03:36 - INFO - codeparrot_training - Step 15999: {'lr': 0.00038554995961488214, 'samples': 8192000, 'steps': 15999, 'batch_loss/train': 0.8557989597320557}
+12/25/2021 02:03:47 - INFO - codeparrot_training - Step 16000: {'lr': 0.00038553671437872226, 'samples': 8192512, 'steps': 16000, 'batch_loss/train': 0.5661846497096121}
+12/25/2021 02:03:57 - INFO - codeparrot_training - Step 16001: {'lr': 0.00038552346860371955, 'samples': 8193024, 'steps': 16001, 'batch_loss/train': 0.8278540319297463}
+12/25/2021 02:04:11 - INFO - codeparrot_training - Step 16002: {'lr': 0.00038551022228992674, 'samples': 8193536, 'steps': 16002, 'batch_loss/train': 0.5938393741380423}
+12/25/2021 02:04:21 - INFO - codeparrot_training - Step 16003: {'lr': 0.00038549697543739637, 'samples': 8194048, 'steps': 16003, 'batch_loss/train': 0.8776170946657658}
+12/25/2021 02:04:32 - INFO - codeparrot_training - Step 16004: {'lr': 0.0003854837280461813, 'samples': 8194560, 'steps': 16004, 'batch_loss/train': 0.8427702859044075}
+12/25/2021 02:04:44 - INFO - codeparrot_training - Step 16005: {'lr': 0.00038547048011633396, 'samples': 8195072, 'steps': 16005, 'batch_loss/train': 0.7575284410268068}
+12/25/2021 02:04:55 - INFO - codeparrot_training - Step 16006: {'lr': 0.0003854572316479072, 'samples': 8195584, 'steps': 16006, 'batch_loss/train': 0.9957738658413291}
+12/25/2021 02:05:05 - INFO - codeparrot_training - Step 16007: {'lr': 0.0003854439826409536, 'samples': 8196096, 'steps': 16007, 'batch_loss/train': 1.1693482715636492}
+12/25/2021 02:05:16 - INFO - codeparrot_training - Step 16008: {'lr': 0.0003854307330955259, 'samples': 8196608, 'steps': 16008, 'batch_loss/train': 0.8145033726468682}
+12/25/2021 02:05:28 - INFO - codeparrot_training - Step 16009: {'lr': 0.0003854174830116767, 'samples': 8197120, 'steps': 16009, 'batch_loss/train': 1.078247170895338}
+12/25/2021 02:05:39 - INFO - codeparrot_training - Step 16010: {'lr': 0.00038540423238945875, 'samples': 8197632, 'steps': 16010, 'batch_loss/train': 0.9409205941483378}
+12/25/2021 02:05:49 - INFO - codeparrot_training - Step 16011: {'lr': 0.0003853909812289248, 'samples': 8198144, 'steps': 16011, 'batch_loss/train': 0.8196765496395528}
+12/25/2021 02:06:02 - INFO - codeparrot_training - Step 16012: {'lr': 0.0003853777295301273, 'samples': 8198656, 'steps': 16012, 'batch_loss/train': 0.7268450483679771}
+12/25/2021 02:06:13 - INFO - codeparrot_training - Step 16013: {'lr': 0.00038536447729311906, 'samples': 8199168, 'steps': 16013, 'batch_loss/train': 0.8359199985861778}
+12/25/2021 02:06:23 - INFO - codeparrot_training - Step 16014: {'lr': 0.00038535122451795287, 'samples': 8199680, 'steps': 16014, 'batch_loss/train': 0.6864448846317828}
+12/25/2021 02:06:35 - INFO - codeparrot_training - Step 16015: {'lr': 0.00038533797120468116, 'samples': 8200192, 'steps': 16015, 'batch_loss/train': 0.8538241358473897}
+12/25/2021 02:06:46 - INFO - codeparrot_training - Step 16016: {'lr': 0.00038532471735335693, 'samples': 8200704, 'steps': 16016, 'batch_loss/train': 0.7892446191981435}
+12/25/2021 02:06:57 - INFO - codeparrot_training - Step 16017: {'lr': 0.0003853114629640326, 'samples': 8201216, 'steps': 16017, 'batch_loss/train': 0.8845113404095173}
+12/25/2021 02:07:07 - INFO - codeparrot_training - Step 16018: {'lr': 0.0003852982080367611, 'samples': 8201728, 'steps': 16018, 'batch_loss/train': 0.6081043148878962}
+12/25/2021 02:07:20 - INFO - codeparrot_training - Step 16019: {'lr': 0.00038528495257159496, 'samples': 8202240, 'steps': 16019, 'batch_loss/train': 0.7931799464859068}
+12/25/2021 02:07:30 - INFO - codeparrot_training - Step 16020: {'lr': 0.00038527169656858695, 'samples': 8202752, 'steps': 16020, 'batch_loss/train': 0.7702388390898705}
+12/25/2021 02:07:41 - INFO - codeparrot_training - Step 16021: {'lr': 0.0003852584400277897, 'samples': 8203264, 'steps': 16021, 'batch_loss/train': 0.9468609434552491}
+12/25/2021 02:07:53 - INFO - codeparrot_training - Step 16022: {'lr': 0.00038524518294925605, 'samples': 8203776, 'steps': 16022, 'batch_loss/train': 0.8058160310611129}
+12/25/2021 02:08:04 - INFO - codeparrot_training - Step 16023: {'lr': 0.00038523192533303853, 'samples': 8204288, 'steps': 16023, 'batch_loss/train': 0.9166689086705446}
+12/25/2021 02:08:14 - INFO - codeparrot_training - Step 16024: {'lr': 0.00038521866717919, 'samples': 8204800, 'steps': 16024, 'batch_loss/train': 0.9957166203530505}
+12/25/2021 02:08:26 - INFO - codeparrot_training - Step 16025: {'lr': 0.0003852054084877631, 'samples': 8205312, 'steps': 16025, 'batch_loss/train': 0.8418481200933456}
+12/25/2021 02:08:37 - INFO - codeparrot_training - Step 16026: {'lr': 0.00038519214925881046, 'samples': 8205824, 'steps': 16026, 'batch_loss/train': 0.8600256172940135}
+12/25/2021 02:08:48 - INFO - codeparrot_training - Step 16027: {'lr': 0.000385178889492385, 'samples': 8206336, 'steps': 16027, 'batch_loss/train': 0.8112637223675847}
+12/25/2021 02:08:58 - INFO - codeparrot_training - Step 16028: {'lr': 0.00038516562918853924, 'samples': 8206848, 'steps': 16028, 'batch_loss/train': 0.7726600728929043}
+12/25/2021 02:09:11 - INFO - codeparrot_training - Step 16029: {'lr': 0.00038515236834732604, 'samples': 8207360, 'steps': 16029, 'batch_loss/train': 0.7598995317239314}
+12/25/2021 02:09:22 - INFO - codeparrot_training - Step 16030: {'lr': 0.00038513910696879797, 'samples': 8207872, 'steps': 16030, 'batch_loss/train': 0.7537999115884304}
+12/25/2021 02:09:32 - INFO - codeparrot_training - Step 16031: {'lr': 0.00038512584505300787, 'samples': 8208384, 'steps': 16031, 'batch_loss/train': 0.8204616480506957}
+12/25/2021 02:09:45 - INFO - codeparrot_training - Step 16032: {'lr': 0.00038511258260000845, 'samples': 8208896, 'steps': 16032, 'batch_loss/train': 0.8652409724891186}
+12/25/2021 02:09:55 - INFO - codeparrot_training - Step 16033: {'lr': 0.00038509931960985244, 'samples': 8209408, 'steps': 16033, 'batch_loss/train': 0.8952907249331474}
+12/25/2021 02:10:06 - INFO - codeparrot_training - Step 16034: {'lr': 0.0003850860560825925, 'samples': 8209920, 'steps': 16034, 'batch_loss/train': 0.8826564839109778}
+12/25/2021 02:10:18 - INFO - codeparrot_training - Step 16035: {'lr': 0.0003850727920182814, 'samples': 8210432, 'steps': 16035, 'batch_loss/train': 0.8212894881144166}
+12/25/2021 02:10:29 - INFO - codeparrot_training - Step 16036: {'lr': 0.0003850595274169719, 'samples': 8210944, 'steps': 16036, 'batch_loss/train': 0.7932083439081907}
+12/25/2021 02:10:39 - INFO - codeparrot_training - Step 16037: {'lr': 0.00038504626227871676, 'samples': 8211456, 'steps': 16037, 'batch_loss/train': 0.7684995280578732}
+12/25/2021 02:10:50 - INFO - codeparrot_training - Step 16038: {'lr': 0.0003850329966035686, 'samples': 8211968, 'steps': 16038, 'batch_loss/train': 0.8060618788003922}
+12/25/2021 02:11:02 - INFO - codeparrot_training - Step 16039: {'lr': 0.00038501973039158023, 'samples': 8212480, 'steps': 16039, 'batch_loss/train': 0.8994606621563435}
+12/25/2021 02:11:13 - INFO - codeparrot_training - Step 16040: {'lr': 0.00038500646364280445, 'samples': 8212992, 'steps': 16040, 'batch_loss/train': 0.7925277790054679}
+12/25/2021 02:11:23 - INFO - codeparrot_training - Step 16041: {'lr': 0.0003849931963572939, 'samples': 8213504, 'steps': 16041, 'batch_loss/train': 0.6804145281203091}
+12/25/2021 02:11:36 - INFO - codeparrot_training - Step 16042: {'lr': 0.00038497992853510143, 'samples': 8214016, 'steps': 16042, 'batch_loss/train': 0.7541121831163764}
+12/25/2021 02:11:47 - INFO - codeparrot_training - Step 16043: {'lr': 0.0003849666601762797, 'samples': 8214528, 'steps': 16043, 'batch_loss/train': 0.798967189155519}
+12/25/2021 02:11:57 - INFO - codeparrot_training - Step 16044: {'lr': 0.00038495339128088145, 'samples': 8215040, 'steps': 16044, 'batch_loss/train': 0.7961586341261864}
+12/25/2021 02:12:09 - INFO - codeparrot_training - Step 16045: {'lr': 0.00038494012184895954, 'samples': 8215552, 'steps': 16045, 'batch_loss/train': 0.8044637273997068}
+12/25/2021 02:12:20 - INFO - codeparrot_training - Step 16046: {'lr': 0.00038492685188056664, 'samples': 8216064, 'steps': 16046, 'batch_loss/train': 0.7534742979332805}
+12/25/2021 02:12:31 - INFO - codeparrot_training - Step 16047: {'lr': 0.00038491358137575555, 'samples': 8216576, 'steps': 16047, 'batch_loss/train': 0.797695537796244}
+12/25/2021 02:12:43 - INFO - codeparrot_training - Step 16048: {'lr': 0.000384900310334579, 'samples': 8217088, 'steps': 16048, 'batch_loss/train': 0.8077402408234775}
+12/25/2021 02:12:54 - INFO - codeparrot_training - Step 16049: {'lr': 0.00038488703875708965, 'samples': 8217600, 'steps': 16049, 'batch_loss/train': 0.8062938784714788}
+12/25/2021 02:13:04 - INFO - codeparrot_training - Step 16050: {'lr': 0.0003848737666433404, 'samples': 8218112, 'steps': 16050, 'batch_loss/train': 0.8183341817930341}
+12/25/2021 02:13:15 - INFO - codeparrot_training - Step 16051: {'lr': 0.00038486049399338407, 'samples': 8218624, 'steps': 16051, 'batch_loss/train': 0.8031514943577349}
+12/25/2021 02:13:27 - INFO - codeparrot_training - Step 16052: {'lr': 0.00038484722080727325, 'samples': 8219136, 'steps': 16052, 'batch_loss/train': 0.8830859381705523}
+12/25/2021 02:13:37 - INFO - codeparrot_training - Step 16053: {'lr': 0.0003848339470850609, 'samples': 8219648, 'steps': 16053, 'batch_loss/train': 0.8541720771463588}
+12/25/2021 02:13:48 - INFO - codeparrot_training - Step 16054: {'lr': 0.0003848206728267995, 'samples': 8220160, 'steps': 16054, 'batch_loss/train': 0.8824032871052623}
+12/25/2021 02:14:00 - INFO - codeparrot_training - Step 16055: {'lr': 0.0003848073980325422, 'samples': 8220672, 'steps': 16055, 'batch_loss/train': 0.9452198547078297}
+12/25/2021 02:14:11 - INFO - codeparrot_training - Step 16056: {'lr': 0.0003847941227023415, 'samples': 8221184, 'steps': 16056, 'batch_loss/train': 0.9067675499245524}
+12/25/2021 02:14:21 - INFO - codeparrot_training - Step 16057: {'lr': 0.00038478084683625025, 'samples': 8221696, 'steps': 16057, 'batch_loss/train': 0.6366102094762027}
+12/25/2021 02:14:35 - INFO - codeparrot_training - Step 16058: {'lr': 0.00038476757043432125, 'samples': 8222208, 'steps': 16058, 'batch_loss/train': 0.758772318251431}
+12/25/2021 02:14:46 - INFO - codeparrot_training - Step 16059: {'lr': 0.00038475429349660734, 'samples': 8222720, 'steps': 16059, 'batch_loss/train': 0.7825368791818619}
+12/25/2021 02:14:56 - INFO - codeparrot_training - Step 16060: {'lr': 0.00038474101602316117, 'samples': 8223232, 'steps': 16060, 'batch_loss/train': 0.7972139772027731}
+12/25/2021 02:15:07 - INFO - codeparrot_training - Step 16061: {'lr': 0.0003847277380140356, 'samples': 8223744, 'steps': 16061, 'batch_loss/train': 0.7779015469131991}
+12/25/2021 02:15:19 - INFO - codeparrot_training - Step 16062: {'lr': 0.0003847144594692835, 'samples': 8224256, 'steps': 16062, 'batch_loss/train': 0.8281307513825595}
+12/25/2021 02:15:30 - INFO - codeparrot_training - Step 16063: {'lr': 0.0003847011803889575, 'samples': 8224768, 'steps': 16063, 'batch_loss/train': 0.8663481143303216}
+12/25/2021 02:15:40 - INFO - codeparrot_training - Step 16064: {'lr': 0.00038468790077311044, 'samples': 8225280, 'steps': 16064, 'batch_loss/train': 0.6960632111877203}
+12/25/2021 02:15:52 - INFO - codeparrot_training - Step 16065: {'lr': 0.0003846746206217952, 'samples': 8225792, 'steps': 16065, 'batch_loss/train': 0.9468915048055351}
+12/25/2021 02:16:03 - INFO - codeparrot_training - Step 16066: {'lr': 0.00038466133993506454, 'samples': 8226304, 'steps': 16066, 'batch_loss/train': 0.7841430846601725}
+12/25/2021 02:16:13 - INFO - codeparrot_training - Step 16067: {'lr': 0.00038464805871297114, 'samples': 8226816, 'steps': 16067, 'batch_loss/train': 0.6967691984027624}
+12/25/2021 02:16:27 - INFO - codeparrot_training - Step 16068: {'lr': 0.00038463477695556804, 'samples': 8227328, 'steps': 16068, 'batch_loss/train': 0.7953929621726274}
+12/25/2021 02:16:37 - INFO - codeparrot_training - Step 16069: {'lr': 0.0003846214946629077, 'samples': 8227840, 'steps': 16069, 'batch_loss/train': 0.6268124002963305}
+12/25/2021 02:16:48 - INFO - codeparrot_training - Step 16070: {'lr': 0.00038460821183504336, 'samples': 8228352, 'steps': 16070, 'batch_loss/train': 0.8324579335749149}
+12/25/2021 02:16:58 - INFO - codeparrot_training - Step 16071: {'lr': 0.0003845949284720275, 'samples': 8228864, 'steps': 16071, 'batch_loss/train': 0.9602774975355715}
+12/25/2021 02:17:11 - INFO - codeparrot_training - Step 16072: {'lr': 0.00038458164457391296, 'samples': 8229376, 'steps': 16072, 'batch_loss/train': 0.7889931909739971}
+12/25/2021 02:17:21 - INFO - codeparrot_training - Step 16073: {'lr': 0.0003845683601407527, 'samples': 8229888, 'steps': 16073, 'batch_loss/train': 0.8188540693372488}
+12/25/2021 02:17:32 - INFO - codeparrot_training - Step 16074: {'lr': 0.00038455507517259934, 'samples': 8230400, 'steps': 16074, 'batch_loss/train': 1.860931719187647}
+12/25/2021 02:17:44 - INFO - codeparrot_training - Step 16075: {'lr': 0.00038454178966950596, 'samples': 8230912, 'steps': 16075, 'batch_loss/train': 0.7472907162737101}
+12/25/2021 02:17:54 - INFO - codeparrot_training - Step 16076: {'lr': 0.00038452850363152513, 'samples': 8231424, 'steps': 16076, 'batch_loss/train': 0.8430562992580235}
+12/25/2021 02:18:05 - INFO - codeparrot_training - Step 16077: {'lr': 0.00038451521705870986, 'samples': 8231936, 'steps': 16077, 'batch_loss/train': 0.845568910241127}
+12/25/2021 02:18:18 - INFO - codeparrot_training - Step 16078: {'lr': 0.0003845019299511128, 'samples': 8232448, 'steps': 16078, 'batch_loss/train': 0.8897799476981163}
+12/25/2021 02:18:28 - INFO - codeparrot_training - Step 16079: {'lr': 0.0003844886423087869, 'samples': 8232960, 'steps': 16079, 'batch_loss/train': 0.8258010167628527}
+12/25/2021 02:18:39 - INFO - codeparrot_training - Step 16080: {'lr': 0.00038447535413178483, 'samples': 8233472, 'steps': 16080, 'batch_loss/train': 0.829025040846318}
+12/25/2021 02:18:50 - INFO - codeparrot_training - Step 16081: {'lr': 0.0003844620654201596, 'samples': 8233984, 'steps': 16081, 'batch_loss/train': 0.9346692012622952}
+12/25/2021 02:19:02 - INFO - codeparrot_training - Step 16082: {'lr': 0.000384448776173964, 'samples': 8234496, 'steps': 16082, 'batch_loss/train': 0.8145050131715834}
+12/25/2021 02:19:12 - INFO - codeparrot_training - Step 16083: {'lr': 0.0003844354863932508, 'samples': 8235008, 'steps': 16083, 'batch_loss/train': 0.7777903089299798}
+12/25/2021 02:19:23 - INFO - codeparrot_training - Step 16084: {'lr': 0.0003844221960780728, 'samples': 8235520, 'steps': 16084, 'batch_loss/train': 0.9084560540504754}
+12/25/2021 02:19:35 - INFO - codeparrot_training - Step 16085: {'lr': 0.000384408905228483, 'samples': 8236032, 'steps': 16085, 'batch_loss/train': 0.7596675539389253}
+12/25/2021 02:19:46 - INFO - codeparrot_training - Step 16086: {'lr': 0.00038439561384453406, 'samples': 8236544, 'steps': 16086, 'batch_loss/train': 0.8080680230632424}
+12/25/2021 02:19:56 - INFO - codeparrot_training - Step 16087: {'lr': 0.000384382321926279, 'samples': 8237056, 'steps': 16087, 'batch_loss/train': 0.9012317303568125}
+12/25/2021 02:20:10 - INFO - codeparrot_training - Step 16088: {'lr': 0.00038436902947377056, 'samples': 8237568, 'steps': 16088, 'batch_loss/train': 0.7921625766903162}
+12/25/2021 02:20:21 - INFO - codeparrot_training - Step 16089: {'lr': 0.00038435573648706157, 'samples': 8238080, 'steps': 16089, 'batch_loss/train': 0.8104747767793015}
+12/25/2021 02:20:31 - INFO - codeparrot_training - Step 16090: {'lr': 0.00038434244296620487, 'samples': 8238592, 'steps': 16090, 'batch_loss/train': 0.9291906571015716}
+12/25/2021 02:20:42 - INFO - codeparrot_training - Step 16091: {'lr': 0.0003843291489112534, 'samples': 8239104, 'steps': 16091, 'batch_loss/train': 0.7777676261030138}
+12/25/2021 02:20:54 - INFO - codeparrot_training - Step 16092: {'lr': 0.0003843158543222599, 'samples': 8239616, 'steps': 16092, 'batch_loss/train': 0.6837736679008231}
+12/25/2021 02:21:05 - INFO - codeparrot_training - Step 16093: {'lr': 0.00038430255919927726, 'samples': 8240128, 'steps': 16093, 'batch_loss/train': 0.8517035860568285}
+12/25/2021 02:21:15 - INFO - codeparrot_training - Step 16094: {'lr': 0.00038428926354235846, 'samples': 8240640, 'steps': 16094, 'batch_loss/train': 0.8731510024517775}
+12/25/2021 02:21:27 - INFO - codeparrot_training - Step 16095: {'lr': 0.0003842759673515561, 'samples': 8241152, 'steps': 16095, 'batch_loss/train': 0.8405044543324038}
+12/25/2021 02:21:38 - INFO - codeparrot_training - Step 16096: {'lr': 0.0003842626706269233, 'samples': 8241664, 'steps': 16096, 'batch_loss/train': 0.8264044355601072}
+12/25/2021 02:21:49 - INFO - codeparrot_training - Step 16097: {'lr': 0.00038424937336851284, 'samples': 8242176, 'steps': 16097, 'batch_loss/train': 0.8894099835306406}
+12/25/2021 02:22:01 - INFO - codeparrot_training - Step 16098: {'lr': 0.0003842360755763775, 'samples': 8242688, 'steps': 16098, 'batch_loss/train': 0.7954582301899791}
+12/25/2021 02:22:12 - INFO - codeparrot_training - Step 16099: {'lr': 0.0003842227772505702, 'samples': 8243200, 'steps': 16099, 'batch_loss/train': 0.8231162172742188}
+12/25/2021 02:22:22 - INFO - codeparrot_training - Step 16100: {'lr': 0.00038420947839114386, 'samples': 8243712, 'steps': 16100, 'batch_loss/train': 0.8821257147938013}
+12/25/2021 02:22:33 - INFO - codeparrot_training - Step 16101: {'lr': 0.0003841961789981513, 'samples': 8244224, 'steps': 16101, 'batch_loss/train': 0.853860404342413}
+12/25/2021 02:22:45 - INFO - codeparrot_training - Step 16102: {'lr': 0.00038418287907164545, 'samples': 8244736, 'steps': 16102, 'batch_loss/train': 0.7823797035962343}
+12/25/2021 02:22:56 - INFO - codeparrot_training - Step 16103: {'lr': 0.0003841695786116791, 'samples': 8245248, 'steps': 16103, 'batch_loss/train': 0.8867076030001044}
+12/25/2021 02:23:07 - INFO - codeparrot_training - Step 16104: {'lr': 0.0003841562776183051, 'samples': 8245760, 'steps': 16104, 'batch_loss/train': 0.830942084081471}
+12/25/2021 02:23:19 - INFO - codeparrot_training - Step 16105: {'lr': 0.00038414297609157657, 'samples': 8246272, 'steps': 16105, 'batch_loss/train': 0.7915238274727017}
+12/25/2021 02:23:30 - INFO - codeparrot_training - Step 16106: {'lr': 0.000384129674031546, 'samples': 8246784, 'steps': 16106, 'batch_loss/train': 0.9486546241678298}
+12/25/2021 02:23:40 - INFO - codeparrot_training - Step 16107: {'lr': 0.0003841163714382666, 'samples': 8247296, 'steps': 16107, 'batch_loss/train': 0.7764795202529058}
+12/25/2021 02:23:52 - INFO - codeparrot_training - Step 16108: {'lr': 0.0003841030683117912, 'samples': 8247808, 'steps': 16108, 'batch_loss/train': 0.795268782414496}
+12/25/2021 02:24:03 - INFO - codeparrot_training - Step 16109: {'lr': 0.00038408976465217253, 'samples': 8248320, 'steps': 16109, 'batch_loss/train': 0.8978043971583247}
+12/25/2021 02:24:14 - INFO - codeparrot_training - Step 16110: {'lr': 0.00038407646045946365, 'samples': 8248832, 'steps': 16110, 'batch_loss/train': 0.7513648503227159}
+12/25/2021 02:24:24 - INFO - codeparrot_training - Step 16111: {'lr': 0.0003840631557337173, 'samples': 8249344, 'steps': 16111, 'batch_loss/train': 0.6768448045477271}
+12/25/2021 02:24:36 - INFO - codeparrot_training - Step 16112: {'lr': 0.0003840498504749865, 'samples': 8249856, 'steps': 16112, 'batch_loss/train': 0.8626173892989755}
+12/25/2021 02:24:47 - INFO - codeparrot_training - Step 16113: {'lr': 0.0003840365446833242, 'samples': 8250368, 'steps': 16113, 'batch_loss/train': 0.8779346612282097}
+12/25/2021 02:24:58 - INFO - codeparrot_training - Step 16114: {'lr': 0.00038402323835878317, 'samples': 8250880, 'steps': 16114, 'batch_loss/train': 0.7885295065352693}
+12/25/2021 02:25:10 - INFO - codeparrot_training - Step 16115: {'lr': 0.0003840099315014164, 'samples': 8251392, 'steps': 16115, 'batch_loss/train': 0.8517162532079965}
+12/25/2021 02:25:20 - INFO - codeparrot_training - Step 16116: {'lr': 0.0003839966241112766, 'samples': 8251904, 'steps': 16116, 'batch_loss/train': 0.7740895696915686}
+12/25/2021 02:25:31 - INFO - codeparrot_training - Step 16117: {'lr': 0.0003839833161884169, 'samples': 8252416, 'steps': 16117, 'batch_loss/train': 0.7529205842874944}
+12/25/2021 02:25:44 - INFO - codeparrot_training - Step 16118: {'lr': 0.00038397000773289015, 'samples': 8252928, 'steps': 16118, 'batch_loss/train': 0.8813658097060397}
+12/25/2021 02:25:54 - INFO - codeparrot_training - Step 16119: {'lr': 0.00038395669874474915, 'samples': 8253440, 'steps': 16119, 'batch_loss/train': 0.7670102324336767}
+12/25/2021 02:26:05 - INFO - codeparrot_training - Step 16120: {'lr': 0.00038394338922404696, 'samples': 8253952, 'steps': 16120, 'batch_loss/train': 0.8111936482600868}
+12/25/2021 02:26:17 - INFO - codeparrot_training - Step 16121: {'lr': 0.00038393007917083644, 'samples': 8254464, 'steps': 16121, 'batch_loss/train': 0.783370922319591}
+12/25/2021 02:26:28 - INFO - codeparrot_training - Step 16122: {'lr': 0.00038391676858517043, 'samples': 8254976, 'steps': 16122, 'batch_loss/train': 0.8042816944653168}
+12/25/2021 02:26:39 - INFO - codeparrot_training - Step 16123: {'lr': 0.00038390345746710196, 'samples': 8255488, 'steps': 16123, 'batch_loss/train': 0.7798807388171554}
+12/25/2021 02:26:49 - INFO - codeparrot_training - Step 16124: {'lr': 0.00038389014581668394, 'samples': 8256000, 'steps': 16124, 'batch_loss/train': 0.6217466522939503}
+12/25/2021 02:27:01 - INFO - codeparrot_training - Step 16125: {'lr': 0.0003838768336339692, 'samples': 8256512, 'steps': 16125, 'batch_loss/train': 0.8432097621262074}
+12/25/2021 02:27:12 - INFO - codeparrot_training - Step 16126: {'lr': 0.0003838635209190107, 'samples': 8257024, 'steps': 16126, 'batch_loss/train': 0.7852634442970157}
+12/25/2021 02:27:22 - INFO - codeparrot_training - Step 16127: {'lr': 0.00038385020767186146, 'samples': 8257536, 'steps': 16127, 'batch_loss/train': 0.9125803597271442}
+12/25/2021 02:27:35 - INFO - codeparrot_training - Step 16128: {'lr': 0.00038383689389257425, 'samples': 8258048, 'steps': 16128, 'batch_loss/train': 0.8589435648173094}
+12/25/2021 02:27:46 - INFO - codeparrot_training - Step 16129: {'lr': 0.0003838235795812022, 'samples': 8258560, 'steps': 16129, 'batch_loss/train': 0.8678293521516025}
+12/25/2021 02:27:57 - INFO - codeparrot_training - Step 16130: {'lr': 0.00038381026473779804, 'samples': 8259072, 'steps': 16130, 'batch_loss/train': 0.8520138985477388}
+12/25/2021 02:28:09 - INFO - codeparrot_training - Step 16131: {'lr': 0.00038379694936241474, 'samples': 8259584, 'steps': 16131, 'batch_loss/train': 0.9291203459724784}
+12/25/2021 02:28:19 - INFO - codeparrot_training - Step 16132: {'lr': 0.0003837836334551054, 'samples': 8260096, 'steps': 16132, 'batch_loss/train': 0.7545004175044596}
+12/25/2021 02:28:30 - INFO - codeparrot_training - Step 16133: {'lr': 0.0003837703170159228, 'samples': 8260608, 'steps': 16133, 'batch_loss/train': 0.8118537589907646}
+12/25/2021 02:28:40 - INFO - codeparrot_training - Step 16134: {'lr': 0.00038375700004491994, 'samples': 8261120, 'steps': 16134, 'batch_loss/train': 0.8234759420156479}
+12/25/2021 02:28:53 - INFO - codeparrot_training - Step 16135: {'lr': 0.0003837436825421496, 'samples': 8261632, 'steps': 16135, 'batch_loss/train': 0.8515349454246461}
+12/25/2021 02:29:04 - INFO - codeparrot_training - Step 16136: {'lr': 0.00038373036450766514, 'samples': 8262144, 'steps': 16136, 'batch_loss/train': 0.746354472823441}
+12/25/2021 02:29:14 - INFO - codeparrot_training - Step 16137: {'lr': 0.00038371704594151914, 'samples': 8262656, 'steps': 16137, 'batch_loss/train': 0.8614595294930041}
+12/25/2021 02:29:27 - INFO - codeparrot_training - Step 16138: {'lr': 0.00038370372684376464, 'samples': 8263168, 'steps': 16138, 'batch_loss/train': 0.8568549691699445}
+12/25/2021 02:29:37 - INFO - codeparrot_training - Step 16139: {'lr': 0.0003836904072144546, 'samples': 8263680, 'steps': 16139, 'batch_loss/train': 0.6737520538736135}
+12/25/2021 02:29:48 - INFO - codeparrot_training - Step 16140: {'lr': 0.00038367708705364204, 'samples': 8264192, 'steps': 16140, 'batch_loss/train': 0.8398873191326857}
+12/25/2021 02:30:00 - INFO - codeparrot_training - Step 16141: {'lr': 0.0003836637663613798, 'samples': 8264704, 'steps': 16141, 'batch_loss/train': 0.8552912138402462}
+12/25/2021 02:30:10 - INFO - codeparrot_training - Step 16142: {'lr': 0.0003836504451377209, 'samples': 8265216, 'steps': 16142, 'batch_loss/train': 0.8001596452668309}
+12/25/2021 02:30:21 - INFO - codeparrot_training - Step 16143: {'lr': 0.00038363712338271825, 'samples': 8265728, 'steps': 16143, 'batch_loss/train': 0.8731149146333337}
+12/25/2021 02:30:32 - INFO - codeparrot_training - Step 16144: {'lr': 0.0003836238010964249, 'samples': 8266240, 'steps': 16144, 'batch_loss/train': 0.8250919877900742}
+12/25/2021 02:30:44 - INFO - codeparrot_training - Step 16145: {'lr': 0.00038361047827889375, 'samples': 8266752, 'steps': 16145, 'batch_loss/train': 0.7390557007165626}
+12/25/2021 02:30:55 - INFO - codeparrot_training - Step 16146: {'lr': 0.0003835971549301779, 'samples': 8267264, 'steps': 16146, 'batch_loss/train': 0.732437239959836}
+12/25/2021 02:31:05 - INFO - codeparrot_training - Step 16147: {'lr': 0.00038358383105033006, 'samples': 8267776, 'steps': 16147, 'batch_loss/train': 0.9339723063167185}
+12/25/2021 02:31:18 - INFO - codeparrot_training - Step 16148: {'lr': 0.0003835705066394034, 'samples': 8268288, 'steps': 16148, 'batch_loss/train': 0.855466884560883}
+12/25/2021 02:31:28 - INFO - codeparrot_training - Step 16149: {'lr': 0.00038355718169745084, 'samples': 8268800, 'steps': 16149, 'batch_loss/train': 0.9499933803454041}
+12/25/2021 02:31:39 - INFO - codeparrot_training - Step 16150: {'lr': 0.0003835438562245254, 'samples': 8269312, 'steps': 16150, 'batch_loss/train': 0.9050011802464724}
+12/25/2021 02:31:51 - INFO - codeparrot_training - Step 16151: {'lr': 0.00038353053022067995, 'samples': 8269824, 'steps': 16151, 'batch_loss/train': 0.8764250101521611}
+12/25/2021 02:32:01 - INFO - codeparrot_training - Step 16152: {'lr': 0.00038351720368596755, 'samples': 8270336, 'steps': 16152, 'batch_loss/train': 0.8196594431065023}
+12/25/2021 02:32:12 - INFO - codeparrot_training - Step 16153: {'lr': 0.00038350387662044116, 'samples': 8270848, 'steps': 16153, 'batch_loss/train': 0.7788875987753272}
+12/25/2021 02:32:24 - INFO - codeparrot_training - Step 16154: {'lr': 0.0003834905490241537, 'samples': 8271360, 'steps': 16154, 'batch_loss/train': 0.8461709609255195}
+12/25/2021 02:32:35 - INFO - codeparrot_training - Step 16155: {'lr': 0.0003834772208971584, 'samples': 8271872, 'steps': 16155, 'batch_loss/train': 1.3943219548091292}
+12/25/2021 02:32:45 - INFO - codeparrot_training - Step 16156: {'lr': 0.00038346389223950793, 'samples': 8272384, 'steps': 16156, 'batch_loss/train': 0.8177695901831612}
+12/25/2021 02:32:56 - INFO - codeparrot_training - Step 16157: {'lr': 0.00038345056305125544, 'samples': 8272896, 'steps': 16157, 'batch_loss/train': 0.802061190828681}
+12/25/2021 02:33:09 - INFO - codeparrot_training - Step 16158: {'lr': 0.00038343723333245387, 'samples': 8273408, 'steps': 16158, 'batch_loss/train': 0.660091666970402}
+12/25/2021 02:33:20 - INFO - codeparrot_training - Step 16159: {'lr': 0.00038342390308315636, 'samples': 8273920, 'steps': 16159, 'batch_loss/train': 0.7810402475297451}
+12/25/2021 02:33:30 - INFO - codeparrot_training - Step 16160: {'lr': 0.0003834105723034157, 'samples': 8274432, 'steps': 16160, 'batch_loss/train': 0.842733591562137}
+12/25/2021 02:33:42 - INFO - codeparrot_training - Step 16161: {'lr': 0.00038339724099328495, 'samples': 8274944, 'steps': 16161, 'batch_loss/train': 0.7191121784271672}
+12/25/2021 02:33:53 - INFO - codeparrot_training - Step 16162: {'lr': 0.00038338390915281716, 'samples': 8275456, 'steps': 16162, 'batch_loss/train': 0.6876327644567937}
+12/25/2021 02:34:04 - INFO - codeparrot_training - Step 16163: {'lr': 0.0003833705767820653, 'samples': 8275968, 'steps': 16163, 'batch_loss/train': 0.8216088060289621}
+12/25/2021 02:34:17 - INFO - codeparrot_training - Step 16164: {'lr': 0.0003833572438810825, 'samples': 8276480, 'steps': 16164, 'batch_loss/train': 0.7792325129266828}
+12/25/2021 02:34:28 - INFO - codeparrot_training - Step 16165: {'lr': 0.0003833439104499216, 'samples': 8276992, 'steps': 16165, 'batch_loss/train': 0.833079076372087}
+12/25/2021 02:34:38 - INFO - codeparrot_training - Step 16166: {'lr': 0.0003833305764886356, 'samples': 8277504, 'steps': 16166, 'batch_loss/train': 0.8044096622616053}
+12/25/2021 02:34:50 - INFO - codeparrot_training - Step 16167: {'lr': 0.00038331724199727757, 'samples': 8278016, 'steps': 16167, 'batch_loss/train': 0.8251318573020399}
+12/25/2021 02:35:01 - INFO - codeparrot_training - Step 16168: {'lr': 0.00038330390697590056, 'samples': 8278528, 'steps': 16168, 'batch_loss/train': 0.7515134192071855}
+12/25/2021 02:35:12 - INFO - codeparrot_training - Step 16169: {'lr': 0.00038329057142455757, 'samples': 8279040, 'steps': 16169, 'batch_loss/train': 0.8703766325488687}
+12/25/2021 02:35:22 - INFO - codeparrot_training - Step 16170: {'lr': 0.00038327723534330155, 'samples': 8279552, 'steps': 16170, 'batch_loss/train': 0.7304678549990058}
+12/25/2021 02:35:35 - INFO - codeparrot_training - Step 16171: {'lr': 0.0003832638987321856, 'samples': 8280064, 'steps': 16171, 'batch_loss/train': 0.8240309120155871}
+12/25/2021 02:35:46 - INFO - codeparrot_training - Step 16172: {'lr': 0.0003832505615912627, 'samples': 8280576, 'steps': 16172, 'batch_loss/train': 1.0469013368710876}
+12/25/2021 02:35:56 - INFO - codeparrot_training - Step 16173: {'lr': 0.00038323722392058593, 'samples': 8281088, 'steps': 16173, 'batch_loss/train': 0.8479386363178492}
+12/25/2021 02:36:09 - INFO - codeparrot_training - Step 16174: {'lr': 0.0003832238857202081, 'samples': 8281600, 'steps': 16174, 'batch_loss/train': 0.8659068867564201}
+12/25/2021 02:36:20 - INFO - codeparrot_training - Step 16175: {'lr': 0.0003832105469901825, 'samples': 8282112, 'steps': 16175, 'batch_loss/train': 0.9240828398615122}
+12/25/2021 02:36:30 - INFO - codeparrot_training - Step 16176: {'lr': 0.0003831972077305621, 'samples': 8282624, 'steps': 16176, 'batch_loss/train': 0.866184108890593}
+12/25/2021 02:36:41 - INFO - codeparrot_training - Step 16177: {'lr': 0.0003831838679413999, 'samples': 8283136, 'steps': 16177, 'batch_loss/train': 0.8343033920973539}
+12/25/2021 02:36:53 - INFO - codeparrot_training - Step 16178: {'lr': 0.0003831705276227489, 'samples': 8283648, 'steps': 16178, 'batch_loss/train': 0.8500022701919079}
+12/25/2021 02:37:04 - INFO - codeparrot_training - Step 16179: {'lr': 0.0003831571867746622, 'samples': 8284160, 'steps': 16179, 'batch_loss/train': 0.8047098175156862}
+12/25/2021 02:37:15 - INFO - codeparrot_training - Step 16180: {'lr': 0.0003831438453971927, 'samples': 8284672, 'steps': 16180, 'batch_loss/train': 0.9802279439754784}
+12/25/2021 02:37:27 - INFO - codeparrot_training - Step 16181: {'lr': 0.00038313050349039366, 'samples': 8285184, 'steps': 16181, 'batch_loss/train': 0.8271002685651183}
+12/25/2021 02:37:37 - INFO - codeparrot_training - Step 16182: {'lr': 0.000383117161054318, 'samples': 8285696, 'steps': 16182, 'batch_loss/train': 0.8083352847024798}
+12/25/2021 02:37:48 - INFO - codeparrot_training - Step 16183: {'lr': 0.0003831038180890187, 'samples': 8286208, 'steps': 16183, 'batch_loss/train': 0.7051412118598819}
+12/25/2021 02:38:00 - INFO - codeparrot_training - Step 16184: {'lr': 0.00038309047459454893, 'samples': 8286720, 'steps': 16184, 'batch_loss/train': 0.7563889320008457}
+12/25/2021 02:38:11 - INFO - codeparrot_training - Step 16185: {'lr': 0.0003830771305709616, 'samples': 8287232, 'steps': 16185, 'batch_loss/train': 0.7882638117298484}
+12/25/2021 02:38:22 - INFO - codeparrot_training - Step 16186: {'lr': 0.00038306378601831, 'samples': 8287744, 'steps': 16186, 'batch_loss/train': 0.9089311957359314}
+12/25/2021 02:38:32 - INFO - codeparrot_training - Step 16187: {'lr': 0.00038305044093664685, 'samples': 8288256, 'steps': 16187, 'batch_loss/train': 0.7887330874800682}
+12/25/2021 02:38:44 - INFO - codeparrot_training - Step 16188: {'lr': 0.00038303709532602553, 'samples': 8288768, 'steps': 16188, 'batch_loss/train': 0.8721259208396077}
+12/25/2021 02:38:55 - INFO - codeparrot_training - Step 16189: {'lr': 0.0003830237491864989, 'samples': 8289280, 'steps': 16189, 'batch_loss/train': 0.9919768180698156}
+12/25/2021 02:39:06 - INFO - codeparrot_training - Step 16190: {'lr': 0.0003830104025181201, 'samples': 8289792, 'steps': 16190, 'batch_loss/train': 0.8124116510152817}
+12/25/2021 02:39:18 - INFO - codeparrot_training - Step 16191: {'lr': 0.0003829970553209421, 'samples': 8290304, 'steps': 16191, 'batch_loss/train': 0.8019555388018489}
+12/25/2021 02:39:28 - INFO - codeparrot_training - Step 16192: {'lr': 0.0003829837075950181, 'samples': 8290816, 'steps': 16192, 'batch_loss/train': 0.8329824283719063}
+12/25/2021 02:39:39 - INFO - codeparrot_training - Step 16193: {'lr': 0.000382970359340401, 'samples': 8291328, 'steps': 16193, 'batch_loss/train': 0.8318270607851446}
+12/25/2021 02:39:52 - INFO - codeparrot_training - Step 16194: {'lr': 0.00038295701055714404, 'samples': 8291840, 'steps': 16194, 'batch_loss/train': 0.8721837925259024}
+12/25/2021 02:40:02 - INFO - codeparrot_training - Step 16195: {'lr': 0.00038294366124530017, 'samples': 8292352, 'steps': 16195, 'batch_loss/train': 0.7231748431222513}
+12/25/2021 02:40:13 - INFO - codeparrot_training - Step 16196: {'lr': 0.00038293031140492254, 'samples': 8292864, 'steps': 16196, 'batch_loss/train': 0.777944527566433}
+12/25/2021 02:40:24 - INFO - codeparrot_training - Step 16197: {'lr': 0.0003829169610360641, 'samples': 8293376, 'steps': 16197, 'batch_loss/train': 0.8974739853292704}
+12/25/2021 02:40:36 - INFO - codeparrot_training - Step 16198: {'lr': 0.0003829036101387781, 'samples': 8293888, 'steps': 16198, 'batch_loss/train': 0.8058635968482122}
+12/25/2021 02:40:46 - INFO - codeparrot_training - Step 16199: {'lr': 0.00038289025871311743, 'samples': 8294400, 'steps': 16199, 'batch_loss/train': 0.8138997131027281}
+12/25/2021 02:40:57 - INFO - codeparrot_training - Step 16200: {'lr': 0.0003828769067591353, 'samples': 8294912, 'steps': 16200, 'batch_loss/train': 0.8115601791068912}
+12/25/2021 02:41:09 - INFO - codeparrot_training - Step 16201: {'lr': 0.0003828635542768849, 'samples': 8295424, 'steps': 16201, 'batch_loss/train': 0.9758891286328435}
+12/25/2021 02:41:19 - INFO - codeparrot_training - Step 16202: {'lr': 0.000382850201266419, 'samples': 8295936, 'steps': 16202, 'batch_loss/train': 0.7352871701586992}
+12/25/2021 02:41:30 - INFO - codeparrot_training - Step 16203: {'lr': 0.0003828368477277909, 'samples': 8296448, 'steps': 16203, 'batch_loss/train': 0.8047132124193013}
+12/25/2021 02:41:44 - INFO - codeparrot_training - Step 16204: {'lr': 0.00038282349366105373, 'samples': 8296960, 'steps': 16204, 'batch_loss/train': 0.7303614737465978}
+12/25/2021 02:41:54 - INFO - codeparrot_training - Step 16205: {'lr': 0.0003828101390662605, 'samples': 8297472, 'steps': 16205, 'batch_loss/train': 0.8570972718298435}
+12/25/2021 02:42:05 - INFO - codeparrot_training - Step 16206: {'lr': 0.00038279678394346415, 'samples': 8297984, 'steps': 16206, 'batch_loss/train': 0.8039840771816671}
+12/25/2021 02:42:15 - INFO - codeparrot_training - Step 16207: {'lr': 0.0003827834282927181, 'samples': 8298496, 'steps': 16207, 'batch_loss/train': 0.8151399600319564}
+12/25/2021 02:42:28 - INFO - codeparrot_training - Step 16208: {'lr': 0.00038277007211407523, 'samples': 8299008, 'steps': 16208, 'batch_loss/train': 0.8584961043670774}
+12/25/2021 02:42:39 - INFO - codeparrot_training - Step 16209: {'lr': 0.0003827567154075887, 'samples': 8299520, 'steps': 16209, 'batch_loss/train': 0.7867444818839431}
+12/25/2021 02:42:49 - INFO - codeparrot_training - Step 16210: {'lr': 0.00038274335817331154, 'samples': 8300032, 'steps': 16210, 'batch_loss/train': 0.9490944603458047}
+12/25/2021 02:43:02 - INFO - codeparrot_training - Step 16211: {'lr': 0.0003827300004112969, 'samples': 8300544, 'steps': 16211, 'batch_loss/train': 1.1683026031823829}
+12/25/2021 02:43:13 - INFO - codeparrot_training - Step 16212: {'lr': 0.00038271664212159793, 'samples': 8301056, 'steps': 16212, 'batch_loss/train': 0.7080003125593066}
+12/25/2021 02:43:24 - INFO - codeparrot_training - Step 16213: {'lr': 0.00038270328330426766, 'samples': 8301568, 'steps': 16213, 'batch_loss/train': 0.6375029543414712}
+12/25/2021 02:43:34 - INFO - codeparrot_training - Step 16214: {'lr': 0.0003826899239593593, 'samples': 8302080, 'steps': 16214, 'batch_loss/train': 0.6934953164309263}
+12/25/2021 02:43:46 - INFO - codeparrot_training - Step 16215: {'lr': 0.0003826765640869259, 'samples': 8302592, 'steps': 16215, 'batch_loss/train': 0.791712237522006}
+12/25/2021 02:43:57 - INFO - codeparrot_training - Step 16216: {'lr': 0.0003826632036870206, 'samples': 8303104, 'steps': 16216, 'batch_loss/train': 0.8386116125620902}
+12/25/2021 02:44:07 - INFO - codeparrot_training - Step 16217: {'lr': 0.00038264984275969644, 'samples': 8303616, 'steps': 16217, 'batch_loss/train': 0.8120864052325487}
+12/25/2021 02:44:20 - INFO - codeparrot_training - Step 16218: {'lr': 0.0003826364813050066, 'samples': 8304128, 'steps': 16218, 'batch_loss/train': 0.8275433601811528}
+12/25/2021 02:44:31 - INFO - codeparrot_training - Step 16219: {'lr': 0.0003826231193230042, 'samples': 8304640, 'steps': 16219, 'batch_loss/train': 1.2695331145077944}
+12/25/2021 02:44:41 - INFO - codeparrot_training - Step 16220: {'lr': 0.0003826097568137424, 'samples': 8305152, 'steps': 16220, 'batch_loss/train': 0.8420792364049703}
+12/25/2021 02:44:52 - INFO - codeparrot_training - Step 16221: {'lr': 0.00038259639377727416, 'samples': 8305664, 'steps': 16221, 'batch_loss/train': 0.7659246348775923}
+12/25/2021 02:45:05 - INFO - codeparrot_training - Step 16222: {'lr': 0.0003825830302136528, 'samples': 8306176, 'steps': 16222, 'batch_loss/train': 0.8562729209661484}
+12/25/2021 02:45:15 - INFO - codeparrot_training - Step 16223: {'lr': 0.0003825696661229314, 'samples': 8306688, 'steps': 16223, 'batch_loss/train': 0.7829266441985965}
+12/25/2021 02:45:26 - INFO - codeparrot_training - Step 16224: {'lr': 0.00038255630150516305, 'samples': 8307200, 'steps': 16224, 'batch_loss/train': 0.9104764088988304}
+12/25/2021 02:45:38 - INFO - codeparrot_training - Step 16225: {'lr': 0.0003825429363604009, 'samples': 8307712, 'steps': 16225, 'batch_loss/train': 0.6452954738633707}
+12/25/2021 02:45:49 - INFO - codeparrot_training - Step 16226: {'lr': 0.00038252957068869806, 'samples': 8308224, 'steps': 16226, 'batch_loss/train': 0.7890948755666614}
+12/25/2021 02:45:59 - INFO - codeparrot_training - Step 16227: {'lr': 0.0003825162044901077, 'samples': 8308736, 'steps': 16227, 'batch_loss/train': 0.7174768336117268}
+12/25/2021 02:46:11 - INFO - codeparrot_training - Step 16228: {'lr': 0.00038250283776468293, 'samples': 8309248, 'steps': 16228, 'batch_loss/train': 0.6789648090489209}
+12/25/2021 02:46:22 - INFO - codeparrot_training - Step 16229: {'lr': 0.000382489470512477, 'samples': 8309760, 'steps': 16229, 'batch_loss/train': 0.7255231295712292}
+12/25/2021 02:46:33 - INFO - codeparrot_training - Step 16230: {'lr': 0.0003824761027335428, 'samples': 8310272, 'steps': 16230, 'batch_loss/train': 0.9285817821510136}
+12/25/2021 02:46:43 - INFO - codeparrot_training - Step 16231: {'lr': 0.0003824627344279338, 'samples': 8310784, 'steps': 16231, 'batch_loss/train': 0.8836229434236884}
+12/25/2021 02:46:55 - INFO - codeparrot_training - Step 16232: {'lr': 0.0003824493655957028, 'samples': 8311296, 'steps': 16232, 'batch_loss/train': 0.8141471054404974}
+12/25/2021 02:47:06 - INFO - codeparrot_training - Step 16233: {'lr': 0.00038243599623690323, 'samples': 8311808, 'steps': 16233, 'batch_loss/train': 0.8879043301567435}
+12/25/2021 02:47:16 - INFO - codeparrot_training - Step 16234: {'lr': 0.0003824226263515882, 'samples': 8312320, 'steps': 16234, 'batch_loss/train': 0.7990043358877301}
+12/25/2021 02:47:29 - INFO - codeparrot_training - Step 16235: {'lr': 0.0003824092559398107, 'samples': 8312832, 'steps': 16235, 'batch_loss/train': 0.9992855554446578}
+12/25/2021 02:47:39 - INFO - codeparrot_training - Step 16236: {'lr': 0.000382395885001624, 'samples': 8313344, 'steps': 16236, 'batch_loss/train': 0.6943497508764267}
+12/25/2021 02:47:50 - INFO - codeparrot_training - Step 16237: {'lr': 0.00038238251353708136, 'samples': 8313856, 'steps': 16237, 'batch_loss/train': 0.818963487399742}
+12/25/2021 02:48:02 - INFO - codeparrot_training - Step 16238: {'lr': 0.0003823691415462358, 'samples': 8314368, 'steps': 16238, 'batch_loss/train': 0.8258743102196604}
+12/25/2021 02:48:13 - INFO - codeparrot_training - Step 16239: {'lr': 0.00038235576902914047, 'samples': 8314880, 'steps': 16239, 'batch_loss/train': 0.9781196531839669}
+12/25/2021 02:48:23 - INFO - codeparrot_training - Step 16240: {'lr': 0.00038234239598584864, 'samples': 8315392, 'steps': 16240, 'batch_loss/train': 0.777174765476957}
+12/25/2021 02:48:34 - INFO - codeparrot_training - Step 16241: {'lr': 0.00038232902241641333, 'samples': 8315904, 'steps': 16241, 'batch_loss/train': 0.8433862077072263}
+12/25/2021 02:48:48 - INFO - codeparrot_training - Step 16242: {'lr': 0.00038231564832088785, 'samples': 8316416, 'steps': 16242, 'batch_loss/train': 0.7381761316210032}
+12/25/2021 02:48:59 - INFO - codeparrot_training - Step 16243: {'lr': 0.00038230227369932525, 'samples': 8316928, 'steps': 16243, 'batch_loss/train': 0.8026910526677966}
+12/25/2021 02:49:10 - INFO - codeparrot_training - Step 16244: {'lr': 0.0003822888985517788, 'samples': 8317440, 'steps': 16244, 'batch_loss/train': 0.8288120809011161}
+12/25/2021 02:49:22 - INFO - codeparrot_training - Step 16245: {'lr': 0.0003822755228783017, 'samples': 8317952, 'steps': 16245, 'batch_loss/train': 0.7907813740894198}
+12/25/2021 02:49:32 - INFO - codeparrot_training - Step 16246: {'lr': 0.000382262146678947, 'samples': 8318464, 'steps': 16246, 'batch_loss/train': 0.7615100733237341}
+12/25/2021 02:49:43 - INFO - codeparrot_training - Step 16247: {'lr': 0.000382248769953768, 'samples': 8318976, 'steps': 16247, 'batch_loss/train': 0.8002092554233968}
+12/25/2021 02:49:57 - INFO - codeparrot_training - Step 16248: {'lr': 0.0003822353927028177, 'samples': 8319488, 'steps': 16248, 'batch_loss/train': 0.8524952782317996}
+12/25/2021 02:50:08 - INFO - codeparrot_training - Step 16249: {'lr': 0.00038222201492614955, 'samples': 8320000, 'steps': 16249, 'batch_loss/train': 0.8053049091249704}
+12/25/2021 02:50:18 - INFO - codeparrot_training - Step 16250: {'lr': 0.0003822086366238165, 'samples': 8320512, 'steps': 16250, 'batch_loss/train': 0.7493419107049704}
+12/25/2021 02:50:30 - INFO - codeparrot_training - Step 16251: {'lr': 0.00038219525779587194, 'samples': 8321024, 'steps': 16251, 'batch_loss/train': 0.7699570660479367}
+12/25/2021 02:50:41 - INFO - codeparrot_training - Step 16252: {'lr': 0.00038218187844236886, 'samples': 8321536, 'steps': 16252, 'batch_loss/train': 0.7990143317729235}
+12/25/2021 02:50:52 - INFO - codeparrot_training - Step 16253: {'lr': 0.0003821684985633606, 'samples': 8322048, 'steps': 16253, 'batch_loss/train': 0.8389142705127597}
+12/25/2021 02:51:02 - INFO - codeparrot_training - Step 16254: {'lr': 0.00038215511815890027, 'samples': 8322560, 'steps': 16254, 'batch_loss/train': 1.1116315193939954}
+12/25/2021 02:51:14 - INFO - codeparrot_training - Step 16255: {'lr': 0.000382141737229041, 'samples': 8323072, 'steps': 16255, 'batch_loss/train': 0.7991490121930838}
+12/25/2021 02:51:25 - INFO - codeparrot_training - Step 16256: {'lr': 0.0003821283557738362, 'samples': 8323584, 'steps': 16256, 'batch_loss/train': 0.661286910995841}
+12/25/2021 02:51:36 - INFO - codeparrot_training - Step 16257: {'lr': 0.00038211497379333885, 'samples': 8324096, 'steps': 16257, 'batch_loss/train': 1.0016185706481338}
+12/25/2021 02:51:49 - INFO - codeparrot_training - Step 16258: {'lr': 0.0003821015912876023, 'samples': 8324608, 'steps': 16258, 'batch_loss/train': 0.7847919738851488}
+12/25/2021 02:52:00 - INFO - codeparrot_training - Step 16259: {'lr': 0.0003820882082566797, 'samples': 8325120, 'steps': 16259, 'batch_loss/train': 0.7772012120112777}
+12/25/2021 02:52:11 - INFO - codeparrot_training - Step 16260: {'lr': 0.00038207482470062435, 'samples': 8325632, 'steps': 16260, 'batch_loss/train': 0.6735875172307715}
+12/25/2021 02:52:21 - INFO - codeparrot_training - Step 16261: {'lr': 0.00038206144061948925, 'samples': 8326144, 'steps': 16261, 'batch_loss/train': 0.847744164057076}
+12/25/2021 02:52:33 - INFO - codeparrot_training - Step 16262: {'lr': 0.0003820480560133277, 'samples': 8326656, 'steps': 16262, 'batch_loss/train': 0.8696646196767688}
+12/25/2021 02:52:44 - INFO - codeparrot_training - Step 16263: {'lr': 0.000382034670882193, 'samples': 8327168, 'steps': 16263, 'batch_loss/train': 0.9551706224447116}
+12/25/2021 02:52:55 - INFO - codeparrot_training - Step 16264: {'lr': 0.0003820212852261383, 'samples': 8327680, 'steps': 16264, 'batch_loss/train': 0.8641198491677642}
+12/25/2021 02:53:08 - INFO - codeparrot_training - Step 16265: {'lr': 0.0003820078990452168, 'samples': 8328192, 'steps': 16265, 'batch_loss/train': 0.8823937671259046}
+12/25/2021 02:53:19 - INFO - codeparrot_training - Step 16266: {'lr': 0.0003819945123394818, 'samples': 8328704, 'steps': 16266, 'batch_loss/train': 0.637250320520252}
+12/25/2021 02:53:30 - INFO - codeparrot_training - Step 16267: {'lr': 0.00038198112510898636, 'samples': 8329216, 'steps': 16267, 'batch_loss/train': 0.8441781578585505}
+12/25/2021 02:53:42 - INFO - codeparrot_training - Step 16268: {'lr': 0.00038196773735378386, 'samples': 8329728, 'steps': 16268, 'batch_loss/train': 0.6463514685165137}
+12/25/2021 02:53:52 - INFO - codeparrot_training - Step 16269: {'lr': 0.0003819543490739275, 'samples': 8330240, 'steps': 16269, 'batch_loss/train': 0.7859427556395531}
+12/25/2021 02:54:03 - INFO - codeparrot_training - Step 16270: {'lr': 0.00038194096026947043, 'samples': 8330752, 'steps': 16270, 'batch_loss/train': 0.8431342211551964}
+12/25/2021 02:54:14 - INFO - codeparrot_training - Step 16271: {'lr': 0.0003819275709404659, 'samples': 8331264, 'steps': 16271, 'batch_loss/train': 0.8546801628544927}
+12/25/2021 02:54:26 - INFO - codeparrot_training - Step 16272: {'lr': 0.00038191418108696716, 'samples': 8331776, 'steps': 16272, 'batch_loss/train': 0.8469636179506779}
+12/25/2021 02:54:36 - INFO - codeparrot_training - Step 16273: {'lr': 0.0003819007907090275, 'samples': 8332288, 'steps': 16273, 'batch_loss/train': 0.7885841981042176}
+12/25/2021 02:54:47 - INFO - codeparrot_training - Step 16274: {'lr': 0.0003818873998067001, 'samples': 8332800, 'steps': 16274, 'batch_loss/train': 0.7810239517129958}
+12/25/2021 02:55:01 - INFO - codeparrot_training - Step 16275: {'lr': 0.0003818740083800382, 'samples': 8333312, 'steps': 16275, 'batch_loss/train': 0.9006401170045137}
+12/25/2021 02:55:11 - INFO - codeparrot_training - Step 16276: {'lr': 0.0003818606164290949, 'samples': 8333824, 'steps': 16276, 'batch_loss/train': 0.8330425946041942}
+12/25/2021 02:55:22 - INFO - codeparrot_training - Step 16277: {'lr': 0.0003818472239539237, 'samples': 8334336, 'steps': 16277, 'batch_loss/train': 0.8336154632270336}
+12/25/2021 02:55:34 - INFO - codeparrot_training - Step 16278: {'lr': 0.0003818338309545777, 'samples': 8334848, 'steps': 16278, 'batch_loss/train': 0.8230243781581521}
+12/25/2021 02:55:45 - INFO - codeparrot_training - Step 16279: {'lr': 0.00038182043743111016, 'samples': 8335360, 'steps': 16279, 'batch_loss/train': 0.8242060896009207}
+12/25/2021 02:55:55 - INFO - codeparrot_training - Step 16280: {'lr': 0.0003818070433835743, 'samples': 8335872, 'steps': 16280, 'batch_loss/train': 0.759116203757003}
+12/25/2021 02:56:07 - INFO - codeparrot_training - Step 16281: {'lr': 0.0003817936488120235, 'samples': 8336384, 'steps': 16281, 'batch_loss/train': 0.8300940189510584}
+12/25/2021 02:56:18 - INFO - codeparrot_training - Step 16282: {'lr': 0.0003817802537165109, 'samples': 8336896, 'steps': 16282, 'batch_loss/train': 0.799283092841506}
+12/25/2021 02:56:28 - INFO - codeparrot_training - Step 16283: {'lr': 0.00038176685809708966, 'samples': 8337408, 'steps': 16283, 'batch_loss/train': 0.8662338946014643}
+12/25/2021 02:56:39 - INFO - codeparrot_training - Step 16284: {'lr': 0.00038175346195381323, 'samples': 8337920, 'steps': 16284, 'batch_loss/train': 0.9057999240467325}
+12/25/2021 02:56:52 - INFO - codeparrot_training - Step 16285: {'lr': 0.0003817400652867348, 'samples': 8338432, 'steps': 16285, 'batch_loss/train': 1.4642799436114728}
+12/25/2021 02:57:02 - INFO - codeparrot_training - Step 16286: {'lr': 0.00038172666809590763, 'samples': 8338944, 'steps': 16286, 'batch_loss/train': 1.2755515538156033}
+12/25/2021 02:57:13 - INFO - codeparrot_training - Step 16287: {'lr': 0.0003817132703813848, 'samples': 8339456, 'steps': 16287, 'batch_loss/train': 0.9616307532414794}
+12/25/2021 02:57:27 - INFO - codeparrot_training - Step 16288: {'lr': 0.0003816998721432199, 'samples': 8339968, 'steps': 16288, 'batch_loss/train': 0.8111745901405811}
+12/25/2021 02:57:37 - INFO - codeparrot_training - Step 16289: {'lr': 0.00038168647338146603, 'samples': 8340480, 'steps': 16289, 'batch_loss/train': 0.7330580805428326}
+12/25/2021 02:57:48 - INFO - codeparrot_training - Step 16290: {'lr': 0.0003816730740961764, 'samples': 8340992, 'steps': 16290, 'batch_loss/train': 0.781814088113606}
+12/25/2021 02:57:59 - INFO - codeparrot_training - Step 16291: {'lr': 0.00038165967428740435, 'samples': 8341504, 'steps': 16291, 'batch_loss/train': 0.8783562872558832}
+12/25/2021 02:58:11 - INFO - codeparrot_training - Step 16292: {'lr': 0.0003816462739552032, 'samples': 8342016, 'steps': 16292, 'batch_loss/train': 0.7450939053669572}
+12/25/2021 02:58:21 - INFO - codeparrot_training - Step 16293: {'lr': 0.00038163287309962615, 'samples': 8342528, 'steps': 16293, 'batch_loss/train': 0.9064376140013337}
+12/25/2021 02:58:32 - INFO - codeparrot_training - Step 16294: {'lr': 0.00038161947172072653, 'samples': 8343040, 'steps': 16294, 'batch_loss/train': 0.826167767867446}
+12/25/2021 02:58:46 - INFO - codeparrot_training - Step 16295: {'lr': 0.0003816060698185575, 'samples': 8343552, 'steps': 16295, 'batch_loss/train': 1.0067956410348415}
+12/25/2021 02:58:57 - INFO - codeparrot_training - Step 16296: {'lr': 0.0003815926673931725, 'samples': 8344064, 'steps': 16296, 'batch_loss/train': 0.8287309063598514}
+12/25/2021 02:59:07 - INFO - codeparrot_training - Step 16297: {'lr': 0.0003815792644446247, 'samples': 8344576, 'steps': 16297, 'batch_loss/train': 0.7022109534591436}
+12/25/2021 02:59:19 - INFO - codeparrot_training - Step 16298: {'lr': 0.0003815658609729674, 'samples': 8345088, 'steps': 16298, 'batch_loss/train': 0.7975855451077223}
+12/25/2021 02:59:30 - INFO - codeparrot_training - Step 16299: {'lr': 0.000381552456978254, 'samples': 8345600, 'steps': 16299, 'batch_loss/train': 0.8270023120567203}
+12/25/2021 02:59:40 - INFO - codeparrot_training - Step 16300: {'lr': 0.00038153905246053767, 'samples': 8346112, 'steps': 16300, 'batch_loss/train': 0.7898675173055381}
+12/25/2021 02:59:52 - INFO - codeparrot_training - Step 16301: {'lr': 0.0003815256474198718, 'samples': 8346624, 'steps': 16301, 'batch_loss/train': 0.8794332067482173}
+12/25/2021 03:00:03 - INFO - codeparrot_training - Step 16302: {'lr': 0.00038151224185630953, 'samples': 8347136, 'steps': 16302, 'batch_loss/train': 0.7721956996247172}
+12/25/2021 03:00:14 - INFO - codeparrot_training - Step 16303: {'lr': 0.00038149883576990426, 'samples': 8347648, 'steps': 16303, 'batch_loss/train': 0.8384956512600183}
+12/25/2021 03:00:24 - INFO - codeparrot_training - Step 16304: {'lr': 0.0003814854291607093, 'samples': 8348160, 'steps': 16304, 'batch_loss/train': 0.6014195396564901}
+12/25/2021 03:00:38 - INFO - codeparrot_training - Step 16305: {'lr': 0.00038147202202877783, 'samples': 8348672, 'steps': 16305, 'batch_loss/train': 0.7817904027178884}
+12/25/2021 03:00:49 - INFO - codeparrot_training - Step 16306: {'lr': 0.0003814586143741633, 'samples': 8349184, 'steps': 16306, 'batch_loss/train': 0.7968473830260336}
+12/25/2021 03:00:59 - INFO - codeparrot_training - Step 16307: {'lr': 0.0003814452061969189, 'samples': 8349696, 'steps': 16307, 'batch_loss/train': 0.8895552940666676}
+12/25/2021 03:01:11 - INFO - codeparrot_training - Step 16308: {'lr': 0.0003814317974970981, 'samples': 8350208, 'steps': 16308, 'batch_loss/train': 0.8768477402627468}
+12/25/2021 03:01:22 - INFO - codeparrot_training - Step 16309: {'lr': 0.00038141838827475405, 'samples': 8350720, 'steps': 16309, 'batch_loss/train': 0.7282009613700211}
+12/25/2021 03:01:33 - INFO - codeparrot_training - Step 16310: {'lr': 0.00038140497852994014, 'samples': 8351232, 'steps': 16310, 'batch_loss/train': 0.8366803848184645}
+12/25/2021 03:01:45 - INFO - codeparrot_training - Step 16311: {'lr': 0.0003813915682627096, 'samples': 8351744, 'steps': 16311, 'batch_loss/train': 0.7656125624198467}
+12/25/2021 03:01:55 - INFO - codeparrot_training - Step 16312: {'lr': 0.0003813781574731159, 'samples': 8352256, 'steps': 16312, 'batch_loss/train': 0.8573290696367621}
+12/25/2021 03:02:06 - INFO - codeparrot_training - Step 16313: {'lr': 0.00038136474616121206, 'samples': 8352768, 'steps': 16313, 'batch_loss/train': 0.8767125280573964}
+12/25/2021 03:02:16 - INFO - codeparrot_training - Step 16314: {'lr': 0.0003813513343270518, 'samples': 8353280, 'steps': 16314, 'batch_loss/train': 0.9904765579849482}
+12/25/2021 03:02:34 - INFO - codeparrot_training - Step 16315: {'lr': 0.00038133792197068815, 'samples': 8353792, 'steps': 16315, 'batch_loss/train': 0.7749294840032235}
+12/25/2021 03:02:44 - INFO - codeparrot_training - Step 16316: {'lr': 0.0003813245090921745, 'samples': 8354304, 'steps': 16316, 'batch_loss/train': 0.9286512201651931}
+12/25/2021 03:02:55 - INFO - codeparrot_training - Step 16317: {'lr': 0.00038131109569156416, 'samples': 8354816, 'steps': 16317, 'batch_loss/train': 0.7767377435229719}
+12/25/2021 03:03:07 - INFO - codeparrot_training - Step 16318: {'lr': 0.00038129768176891054, 'samples': 8355328, 'steps': 16318, 'batch_loss/train': 0.8014679723419249}
+12/25/2021 03:03:18 - INFO - codeparrot_training - Step 16319: {'lr': 0.00038128426732426685, 'samples': 8355840, 'steps': 16319, 'batch_loss/train': 0.76744638197124}
+12/25/2021 03:03:28 - INFO - codeparrot_training - Step 16320: {'lr': 0.0003812708523576865, 'samples': 8356352, 'steps': 16320, 'batch_loss/train': 0.7214752165600657}
+12/25/2021 03:03:40 - INFO - codeparrot_training - Step 16321: {'lr': 0.0003812574368692229, 'samples': 8356864, 'steps': 16321, 'batch_loss/train': 0.7971192426048219}
+12/25/2021 03:03:51 - INFO - codeparrot_training - Step 16322: {'lr': 0.00038124402085892915, 'samples': 8357376, 'steps': 16322, 'batch_loss/train': 0.7164738974533975}
+12/25/2021 03:04:01 - INFO - codeparrot_training - Step 16323: {'lr': 0.0003812306043268589, 'samples': 8357888, 'steps': 16323, 'batch_loss/train': 0.7719359621405602}
+12/25/2021 03:04:12 - INFO - codeparrot_training - Step 16324: {'lr': 0.00038121718727306516, 'samples': 8358400, 'steps': 16324, 'batch_loss/train': 0.7943692915141582}
+12/25/2021 03:04:26 - INFO - codeparrot_training - Step 16325: {'lr': 0.00038120376969760143, 'samples': 8358912, 'steps': 16325, 'batch_loss/train': 0.7947669941931963}
+12/25/2021 03:04:36 - INFO - codeparrot_training - Step 16326: {'lr': 0.0003811903516005211, 'samples': 8359424, 'steps': 16326, 'batch_loss/train': 0.9899771269410849}
+12/25/2021 03:04:47 - INFO - codeparrot_training - Step 16327: {'lr': 0.0003811769329818775, 'samples': 8359936, 'steps': 16327, 'batch_loss/train': 0.7655866574496031}
+12/25/2021 03:04:59 - INFO - codeparrot_training - Step 16328: {'lr': 0.000381163513841724, 'samples': 8360448, 'steps': 16328, 'batch_loss/train': 0.8454933380708098}
+12/25/2021 03:05:10 - INFO - codeparrot_training - Step 16329: {'lr': 0.00038115009418011376, 'samples': 8360960, 'steps': 16329, 'batch_loss/train': 1.033647095784545}
+12/25/2021 03:05:20 - INFO - codeparrot_training - Step 16330: {'lr': 0.0003811366739971003, 'samples': 8361472, 'steps': 16330, 'batch_loss/train': 0.7833782411180437}
+12/25/2021 03:05:33 - INFO - codeparrot_training - Step 16331: {'lr': 0.000381123253292737, 'samples': 8361984, 'steps': 16331, 'batch_loss/train': 0.824759311042726}
+12/25/2021 03:05:43 - INFO - codeparrot_training - Step 16332: {'lr': 0.00038110983206707705, 'samples': 8362496, 'steps': 16332, 'batch_loss/train': 0.7552850181236863}
+12/25/2021 03:05:54 - INFO - codeparrot_training - Step 16333: {'lr': 0.000381096410320174, 'samples': 8363008, 'steps': 16333, 'batch_loss/train': 0.6612557023763657}
+12/25/2021 03:06:04 - INFO - codeparrot_training - Step 16334: {'lr': 0.00038108298805208116, 'samples': 8363520, 'steps': 16334, 'batch_loss/train': 0.8151645949110389}
+12/25/2021 03:06:18 - INFO - codeparrot_training - Step 16335: {'lr': 0.00038106956526285176, 'samples': 8364032, 'steps': 16335, 'batch_loss/train': 0.8989729033783078}
+12/25/2021 03:06:29 - INFO - codeparrot_training - Step 16336: {'lr': 0.0003810561419525393, 'samples': 8364544, 'steps': 16336, 'batch_loss/train': 1.3498526024632156}
+12/25/2021 03:06:40 - INFO - codeparrot_training - Step 16337: {'lr': 0.00038104271812119706, 'samples': 8365056, 'steps': 16337, 'batch_loss/train': 0.7144277915358543}
+12/25/2021 03:06:52 - INFO - codeparrot_training - Step 16338: {'lr': 0.00038102929376887854, 'samples': 8365568, 'steps': 16338, 'batch_loss/train': 0.7862965976819396}
+12/25/2021 03:07:02 - INFO - codeparrot_training - Step 16339: {'lr': 0.00038101586889563693, 'samples': 8366080, 'steps': 16339, 'batch_loss/train': 0.8331911994609982}
+12/25/2021 03:07:13 - INFO - codeparrot_training - Step 16340: {'lr': 0.0003810024435015258, 'samples': 8366592, 'steps': 16340, 'batch_loss/train': 0.810480953194201}
+12/25/2021 03:07:25 - INFO - codeparrot_training - Step 16341: {'lr': 0.00038098901758659834, 'samples': 8367104, 'steps': 16341, 'batch_loss/train': 0.8134991200640798}
+12/25/2021 03:07:36 - INFO - codeparrot_training - Step 16342: {'lr': 0.00038097559115090804, 'samples': 8367616, 'steps': 16342, 'batch_loss/train': 0.8433480272069573}
+12/25/2021 03:07:46 - INFO - codeparrot_training - Step 16343: {'lr': 0.0003809621641945082, 'samples': 8368128, 'steps': 16343, 'batch_loss/train': 0.7810773374512792}
+12/25/2021 03:07:57 - INFO - codeparrot_training - Step 16344: {'lr': 0.0003809487367174522, 'samples': 8368640, 'steps': 16344, 'batch_loss/train': 0.7124492945149541}
+12/25/2021 03:08:11 - INFO - codeparrot_training - Step 16345: {'lr': 0.0003809353087197936, 'samples': 8369152, 'steps': 16345, 'batch_loss/train': 0.8122470653615892}
+12/25/2021 03:08:21 - INFO - codeparrot_training - Step 16346: {'lr': 0.0003809218802015856, 'samples': 8369664, 'steps': 16346, 'batch_loss/train': 0.8174110765103251}
+12/25/2021 03:08:32 - INFO - codeparrot_training - Step 16347: {'lr': 0.00038090845116288164, 'samples': 8370176, 'steps': 16347, 'batch_loss/train': 1.6463056881912053}
+12/25/2021 03:08:44 - INFO - codeparrot_training - Step 16348: {'lr': 0.00038089502160373504, 'samples': 8370688, 'steps': 16348, 'batch_loss/train': 0.7560862839454785}
+12/25/2021 03:08:55 - INFO - codeparrot_training - Step 16349: {'lr': 0.0003808815915241993, 'samples': 8371200, 'steps': 16349, 'batch_loss/train': 0.8990575261414051}
+12/25/2021 03:09:05 - INFO - codeparrot_training - Step 16350: {'lr': 0.00038086816092432787, 'samples': 8371712, 'steps': 16350, 'batch_loss/train': 0.7955160373821855}
+12/25/2021 03:09:19 - INFO - codeparrot_training - Step 16351: {'lr': 0.00038085472980417393, 'samples': 8372224, 'steps': 16351, 'batch_loss/train': 0.8065568981692195}
+12/25/2021 03:09:30 - INFO - codeparrot_training - Step 16352: {'lr': 0.000380841298163791, 'samples': 8372736, 'steps': 16352, 'batch_loss/train': 0.8769071912392974}
+12/25/2021 03:09:40 - INFO - codeparrot_training - Step 16353: {'lr': 0.00038082786600323254, 'samples': 8373248, 'steps': 16353, 'batch_loss/train': 0.7477641692385077}
+12/25/2021 03:09:51 - INFO - codeparrot_training - Step 16354: {'lr': 0.0003808144333225518, 'samples': 8373760, 'steps': 16354, 'batch_loss/train': 0.7459174729883671}
+12/25/2021 03:10:03 - INFO - codeparrot_training - Step 16355: {'lr': 0.0003808010001218023, 'samples': 8374272, 'steps': 16355, 'batch_loss/train': 0.8904078425839543}
+12/25/2021 03:10:13 - INFO - codeparrot_training - Step 16356: {'lr': 0.00038078756640103745, 'samples': 8374784, 'steps': 16356, 'batch_loss/train': 0.9255089508369565}
+12/25/2021 03:10:24 - INFO - codeparrot_training - Step 16357: {'lr': 0.00038077413216031054, 'samples': 8375296, 'steps': 16357, 'batch_loss/train': 0.7476654928177595}
+12/25/2021 03:10:36 - INFO - codeparrot_training - Step 16358: {'lr': 0.0003807606973996751, 'samples': 8375808, 'steps': 16358, 'batch_loss/train': 0.8408073158934712}
+12/25/2021 03:10:47 - INFO - codeparrot_training - Step 16359: {'lr': 0.00038074726211918456, 'samples': 8376320, 'steps': 16359, 'batch_loss/train': 0.8173728152178228}
+12/25/2021 03:10:57 - INFO - codeparrot_training - Step 16360: {'lr': 0.00038073382631889223, 'samples': 8376832, 'steps': 16360, 'batch_loss/train': 0.7536002132110298}
+12/25/2021 03:11:11 - INFO - codeparrot_training - Step 16361: {'lr': 0.0003807203899988515, 'samples': 8377344, 'steps': 16361, 'batch_loss/train': 0.8604493821039796}
+12/25/2021 03:11:22 - INFO - codeparrot_training - Step 16362: {'lr': 0.00038070695315911595, 'samples': 8377856, 'steps': 16362, 'batch_loss/train': 0.7734404196962714}
+12/25/2021 03:11:32 - INFO - codeparrot_training - Step 16363: {'lr': 0.0003806935157997389, 'samples': 8378368, 'steps': 16363, 'batch_loss/train': 0.8833962343633175}
+12/25/2021 03:11:44 - INFO - codeparrot_training - Step 16364: {'lr': 0.0003806800779207737, 'samples': 8378880, 'steps': 16364, 'batch_loss/train': 0.9135098652914166}
+12/25/2021 03:11:55 - INFO - codeparrot_training - Step 16365: {'lr': 0.000380666639522274, 'samples': 8379392, 'steps': 16365, 'batch_loss/train': 0.6967317988164723}
+12/25/2021 03:12:05 - INFO - codeparrot_training - Step 16366: {'lr': 0.000380653200604293, 'samples': 8379904, 'steps': 16366, 'batch_loss/train': 0.8212092723697424}
+12/25/2021 03:12:16 - INFO - codeparrot_training - Step 16367: {'lr': 0.00038063976116688413, 'samples': 8380416, 'steps': 16367, 'batch_loss/train': 0.8110054866410792}
+12/25/2021 03:12:28 - INFO - codeparrot_training - Step 16368: {'lr': 0.000380626321210101, 'samples': 8380928, 'steps': 16368, 'batch_loss/train': 0.8403459768742323}
+12/25/2021 03:12:39 - INFO - codeparrot_training - Step 16369: {'lr': 0.0003806128807339969, 'samples': 8381440, 'steps': 16369, 'batch_loss/train': 0.8076573088765144}
+12/25/2021 03:12:49 - INFO - codeparrot_training - Step 16370: {'lr': 0.0003805994397386253, 'samples': 8381952, 'steps': 16370, 'batch_loss/train': 0.7928742929361761}
+12/25/2021 03:13:01 - INFO - codeparrot_training - Step 16371: {'lr': 0.00038058599822403963, 'samples': 8382464, 'steps': 16371, 'batch_loss/train': 0.8355450322851539}
+12/25/2021 03:13:12 - INFO - codeparrot_training - Step 16372: {'lr': 0.00038057255619029334, 'samples': 8382976, 'steps': 16372, 'batch_loss/train': 0.7147802908439189}
+12/25/2021 03:13:23 - INFO - codeparrot_training - Step 16373: {'lr': 0.0003805591136374399, 'samples': 8383488, 'steps': 16373, 'batch_loss/train': 0.8613752662204206}
+12/25/2021 03:13:33 - INFO - codeparrot_training - Step 16374: {'lr': 0.00038054567056553266, 'samples': 8384000, 'steps': 16374, 'batch_loss/train': 0.7096129877027124}
+12/25/2021 03:13:48 - INFO - codeparrot_training - Step 16375: {'lr': 0.0003805322269746252, 'samples': 8384512, 'steps': 16375, 'batch_loss/train': 0.8322852025739849}
+12/25/2021 03:13:58 - INFO - codeparrot_training - Step 16376: {'lr': 0.0003805187828647709, 'samples': 8385024, 'steps': 16376, 'batch_loss/train': 0.8532070713117719}
+12/25/2021 03:14:09 - INFO - codeparrot_training - Step 16377: {'lr': 0.0003805053382360231, 'samples': 8385536, 'steps': 16377, 'batch_loss/train': 0.7727809818461537}
+12/25/2021 03:14:21 - INFO - codeparrot_training - Step 16378: {'lr': 0.00038049189308843545, 'samples': 8386048, 'steps': 16378, 'batch_loss/train': 0.6201814038213342}
+12/25/2021 03:14:32 - INFO - codeparrot_training - Step 16379: {'lr': 0.00038047844742206127, 'samples': 8386560, 'steps': 16379, 'batch_loss/train': 0.7912314990535378}
+12/25/2021 03:14:42 - INFO - codeparrot_training - Step 16380: {'lr': 0.00038046500123695403, 'samples': 8387072, 'steps': 16380, 'batch_loss/train': 0.7682696841657162}
+12/25/2021 03:14:56 - INFO - codeparrot_training - Step 16381: {'lr': 0.00038045155453316724, 'samples': 8387584, 'steps': 16381, 'batch_loss/train': 0.7935175374150276}
+12/25/2021 03:15:07 - INFO - codeparrot_training - Step 16382: {'lr': 0.00038043810731075434, 'samples': 8388096, 'steps': 16382, 'batch_loss/train': 0.8303677807562053}
+12/25/2021 03:15:17 - INFO - codeparrot_training - Step 16383: {'lr': 0.00038042465956976873, 'samples': 8388608, 'steps': 16383, 'batch_loss/train': 0.8093399005010724}
+12/25/2021 03:15:28 - INFO - codeparrot_training - Step 16384: {'lr': 0.0003804112113102639, 'samples': 8389120, 'steps': 16384, 'batch_loss/train': 0.8039600357878953}
+12/25/2021 03:15:40 - INFO - codeparrot_training - Step 16385: {'lr': 0.0003803977625322934, 'samples': 8389632, 'steps': 16385, 'batch_loss/train': 0.8676012698560953}
+12/25/2021 03:15:50 - INFO - codeparrot_training - Step 16386: {'lr': 0.0003803843132359107, 'samples': 8390144, 'steps': 16386, 'batch_loss/train': 0.7880402319133282}
+12/25/2021 03:16:01 - INFO - codeparrot_training - Step 16387: {'lr': 0.000380370863421169, 'samples': 8390656, 'steps': 16387, 'batch_loss/train': 0.82987698353827}
+12/25/2021 03:16:14 - INFO - codeparrot_training - Step 16388: {'lr': 0.0003803574130881221, 'samples': 8391168, 'steps': 16388, 'batch_loss/train': 0.9423878313973546}
+12/25/2021 03:16:24 - INFO - codeparrot_training - Step 16389: {'lr': 0.0003803439622368233, 'samples': 8391680, 'steps': 16389, 'batch_loss/train': 1.5762659348547459}
+12/25/2021 03:16:35 - INFO - codeparrot_training - Step 16390: {'lr': 0.00038033051086732616, 'samples': 8392192, 'steps': 16390, 'batch_loss/train': 0.8115044236183167}
+12/25/2021 03:16:48 - INFO - codeparrot_training - Step 16391: {'lr': 0.00038031705897968417, 'samples': 8392704, 'steps': 16391, 'batch_loss/train': 0.7338745906017721}
+12/25/2021 03:16:59 - INFO - codeparrot_training - Step 16392: {'lr': 0.0003803036065739507, 'samples': 8393216, 'steps': 16392, 'batch_loss/train': 0.8738591875880957}
+12/25/2021 03:17:09 - INFO - codeparrot_training - Step 16393: {'lr': 0.00038029015365017926, 'samples': 8393728, 'steps': 16393, 'batch_loss/train': 0.8754670964553952}
+12/25/2021 03:17:21 - INFO - codeparrot_training - Step 16394: {'lr': 0.00038027670020842345, 'samples': 8394240, 'steps': 16394, 'batch_loss/train': 0.6716324593871832}
+12/25/2021 03:17:32 - INFO - codeparrot_training - Step 16395: {'lr': 0.0003802632462487366, 'samples': 8394752, 'steps': 16395, 'batch_loss/train': 0.7741752951405942}
+12/25/2021 03:17:43 - INFO - codeparrot_training - Step 16396: {'lr': 0.00038024979177117226, 'samples': 8395264, 'steps': 16396, 'batch_loss/train': 0.8425773023627698}
+12/25/2021 03:17:53 - INFO - codeparrot_training - Step 16397: {'lr': 0.00038023633677578396, 'samples': 8395776, 'steps': 16397, 'batch_loss/train': 0.7516240701079369}
+12/25/2021 03:18:05 - INFO - codeparrot_training - Step 16398: {'lr': 0.00038022288126262515, 'samples': 8396288, 'steps': 16398, 'batch_loss/train': 0.7779428055509925}
+12/25/2021 03:18:16 - INFO - codeparrot_training - Step 16399: {'lr': 0.0003802094252317494, 'samples': 8396800, 'steps': 16399, 'batch_loss/train': 0.8505194000899792}
+12/25/2021 03:18:26 - INFO - codeparrot_training - Step 16400: {'lr': 0.00038019596868321, 'samples': 8397312, 'steps': 16400, 'batch_loss/train': 0.8677960052154958}
+12/25/2021 03:18:39 - INFO - codeparrot_training - Step 16401: {'lr': 0.0003801825116170607, 'samples': 8397824, 'steps': 16401, 'batch_loss/train': 0.8925122581422329}
+12/25/2021 03:18:50 - INFO - codeparrot_training - Step 16402: {'lr': 0.0003801690540333549, 'samples': 8398336, 'steps': 16402, 'batch_loss/train': 0.5527537409216166}
+12/25/2021 03:19:01 - INFO - codeparrot_training - Step 16403: {'lr': 0.000380155595932146, 'samples': 8398848, 'steps': 16403, 'batch_loss/train': 0.8026828377041966}
+12/25/2021 03:19:13 - INFO - codeparrot_training - Step 16404: {'lr': 0.0003801421373134876, 'samples': 8399360, 'steps': 16404, 'batch_loss/train': 0.836663456633687}
+12/25/2021 03:19:24 - INFO - codeparrot_training - Step 16405: {'lr': 0.00038012867817743335, 'samples': 8399872, 'steps': 16405, 'batch_loss/train': 0.8296491596847773}
+12/25/2021 03:19:34 - INFO - codeparrot_training - Step 16406: {'lr': 0.0003801152185240364, 'samples': 8400384, 'steps': 16406, 'batch_loss/train': 0.7445092252455652}
+12/25/2021 03:19:45 - INFO - codeparrot_training - Step 16407: {'lr': 0.0003801017583533506, 'samples': 8400896, 'steps': 16407, 'batch_loss/train': 0.8346738899126649}
+12/25/2021 03:19:57 - INFO - codeparrot_training - Step 16408: {'lr': 0.0003800882976654293, 'samples': 8401408, 'steps': 16408, 'batch_loss/train': 0.731676128692925}
+12/25/2021 03:20:08 - INFO - codeparrot_training - Step 16409: {'lr': 0.0003800748364603261, 'samples': 8401920, 'steps': 16409, 'batch_loss/train': 0.8197162933647633}
+12/25/2021 03:20:18 - INFO - codeparrot_training - Step 16410: {'lr': 0.00038006137473809446, 'samples': 8402432, 'steps': 16410, 'batch_loss/train': 0.8964916691184044}
+12/25/2021 03:20:31 - INFO - codeparrot_training - Step 16411: {'lr': 0.0003800479124987878, 'samples': 8402944, 'steps': 16411, 'batch_loss/train': 0.8020818531513214}
+12/25/2021 03:20:42 - INFO - codeparrot_training - Step 16412: {'lr': 0.0003800344497424598, 'samples': 8403456, 'steps': 16412, 'batch_loss/train': 0.8265873305499554}
+12/25/2021 03:20:53 - INFO - codeparrot_training - Step 16413: {'lr': 0.00038002098646916396, 'samples': 8403968, 'steps': 16413, 'batch_loss/train': 0.9385354509577155}
+12/25/2021 03:21:05 - INFO - codeparrot_training - Step 16414: {'lr': 0.0003800075226789538, 'samples': 8404480, 'steps': 16414, 'batch_loss/train': 0.6658437331207097}
+12/25/2021 03:21:15 - INFO - codeparrot_training - Step 16415: {'lr': 0.0003799940583718827, 'samples': 8404992, 'steps': 16415, 'batch_loss/train': 0.8669708520174026}
+12/25/2021 03:21:26 - INFO - codeparrot_training - Step 16416: {'lr': 0.0003799805935480044, 'samples': 8405504, 'steps': 16416, 'batch_loss/train': 0.8121983092278242}
+12/25/2021 03:21:36 - INFO - codeparrot_training - Step 16417: {'lr': 0.0003799671282073723, 'samples': 8406016, 'steps': 16417, 'batch_loss/train': 0.8629690702073276}
+12/25/2021 03:21:48 - INFO - codeparrot_training - Step 16418: {'lr': 0.0003799536623500399, 'samples': 8406528, 'steps': 16418, 'batch_loss/train': 0.7434429600834846}
+12/25/2021 03:21:59 - INFO - codeparrot_training - Step 16419: {'lr': 0.00037994019597606095, 'samples': 8407040, 'steps': 16419, 'batch_loss/train': 0.6952060237526894}
+12/25/2021 03:22:10 - INFO - codeparrot_training - Step 16420: {'lr': 0.00037992672908548875, 'samples': 8407552, 'steps': 16420, 'batch_loss/train': 0.7852361318655312}
+12/25/2021 03:22:23 - INFO - codeparrot_training - Step 16421: {'lr': 0.00037991326167837705, 'samples': 8408064, 'steps': 16421, 'batch_loss/train': 0.8495915979146957}
+12/25/2021 03:22:34 - INFO - codeparrot_training - Step 16422: {'lr': 0.0003798997937547792, 'samples': 8408576, 'steps': 16422, 'batch_loss/train': 0.7924232976511121}
+12/25/2021 03:22:44 - INFO - codeparrot_training - Step 16423: {'lr': 0.00037988632531474873, 'samples': 8409088, 'steps': 16423, 'batch_loss/train': 1.0281326174736023}
+12/25/2021 03:22:56 - INFO - codeparrot_training - Step 16424: {'lr': 0.0003798728563583394, 'samples': 8409600, 'steps': 16424, 'batch_loss/train': 0.8153260499238968}
+12/25/2021 03:23:07 - INFO - codeparrot_training - Step 16425: {'lr': 0.00037985938688560463, 'samples': 8410112, 'steps': 16425, 'batch_loss/train': 0.8157568015158176}
+12/25/2021 03:23:18 - INFO - codeparrot_training - Step 16426: {'lr': 0.0003798459168965979, 'samples': 8410624, 'steps': 16426, 'batch_loss/train': 0.7279916242696345}
+12/25/2021 03:23:28 - INFO - codeparrot_training - Step 16427: {'lr': 0.0003798324463913729, 'samples': 8411136, 'steps': 16427, 'batch_loss/train': 0.8510133742820472}
+12/25/2021 03:23:40 - INFO - codeparrot_training - Step 16428: {'lr': 0.000379818975369983, 'samples': 8411648, 'steps': 16428, 'batch_loss/train': 0.794634415069595}
+12/25/2021 03:23:51 - INFO - codeparrot_training - Step 16429: {'lr': 0.00037980550383248196, 'samples': 8412160, 'steps': 16429, 'batch_loss/train': 0.8521801605820656}
+12/25/2021 03:24:01 - INFO - codeparrot_training - Step 16430: {'lr': 0.00037979203177892324, 'samples': 8412672, 'steps': 16430, 'batch_loss/train': 0.7866526050493121}
+12/25/2021 03:24:14 - INFO - codeparrot_training - Step 16431: {'lr': 0.00037977855920936045, 'samples': 8413184, 'steps': 16431, 'batch_loss/train': 0.8104956718161702}
+12/25/2021 03:24:25 - INFO - codeparrot_training - Step 16432: {'lr': 0.00037976508612384705, 'samples': 8413696, 'steps': 16432, 'batch_loss/train': 0.8834657943807542}
+12/25/2021 03:24:35 - INFO - codeparrot_training - Step 16433: {'lr': 0.00037975161252243664, 'samples': 8414208, 'steps': 16433, 'batch_loss/train': 0.910928484518081}
+12/25/2021 03:24:47 - INFO - codeparrot_training - Step 16434: {'lr': 0.0003797381384051829, 'samples': 8414720, 'steps': 16434, 'batch_loss/train': 0.837822275236249}
+12/25/2021 03:24:58 - INFO - codeparrot_training - Step 16435: {'lr': 0.00037972466377213926, 'samples': 8415232, 'steps': 16435, 'batch_loss/train': 0.753268264234066}
+12/25/2021 03:25:08 - INFO - codeparrot_training - Step 16436: {'lr': 0.0003797111886233593, 'samples': 8415744, 'steps': 16436, 'batch_loss/train': 0.7353754403302446}
+12/25/2021 03:25:19 - INFO - codeparrot_training - Step 16437: {'lr': 0.00037969771295889664, 'samples': 8416256, 'steps': 16437, 'batch_loss/train': 0.8474216526374221}
+12/25/2021 03:25:32 - INFO - codeparrot_training - Step 16438: {'lr': 0.00037968423677880493, 'samples': 8416768, 'steps': 16438, 'batch_loss/train': 0.8273716932162642}
+12/25/2021 03:25:42 - INFO - codeparrot_training - Step 16439: {'lr': 0.0003796707600831376, 'samples': 8417280, 'steps': 16439, 'batch_loss/train': 0.833724650554359}
+12/25/2021 03:25:53 - INFO - codeparrot_training - Step 16440: {'lr': 0.00037965728287194835, 'samples': 8417792, 'steps': 16440, 'batch_loss/train': 0.9830353688448668}
+12/25/2021 03:26:05 - INFO - codeparrot_training - Step 16441: {'lr': 0.00037964380514529065, 'samples': 8418304, 'steps': 16441, 'batch_loss/train': 0.7767963903024793}
+12/25/2021 03:26:16 - INFO - codeparrot_training - Step 16442: {'lr': 0.0003796303269032181, 'samples': 8418816, 'steps': 16442, 'batch_loss/train': 0.7797692895401269}
+12/25/2021 03:26:26 - INFO - codeparrot_training - Step 16443: {'lr': 0.00037961684814578434, 'samples': 8419328, 'steps': 16443, 'batch_loss/train': 0.8390476023778319}
+12/25/2021 03:26:38 - INFO - codeparrot_training - Step 16444: {'lr': 0.0003796033688730429, 'samples': 8419840, 'steps': 16444, 'batch_loss/train': 0.7752347416244447}
+12/25/2021 03:26:49 - INFO - codeparrot_training - Step 16445: {'lr': 0.0003795898890850475, 'samples': 8420352, 'steps': 16445, 'batch_loss/train': 0.7760807042941451}
+12/25/2021 03:26:59 - INFO - codeparrot_training - Step 16446: {'lr': 0.00037957640878185153, 'samples': 8420864, 'steps': 16446, 'batch_loss/train': 0.7619779882952571}
+12/25/2021 03:27:12 - INFO - codeparrot_training - Step 16447: {'lr': 0.0003795629279635088, 'samples': 8421376, 'steps': 16447, 'batch_loss/train': 0.8889281153678894}
+12/25/2021 03:27:22 - INFO - codeparrot_training - Step 16448: {'lr': 0.00037954944663007274, 'samples': 8421888, 'steps': 16448, 'batch_loss/train': 0.8099018186330795}
+12/25/2021 03:27:33 - INFO - codeparrot_training - Step 16449: {'lr': 0.0003795359647815969, 'samples': 8422400, 'steps': 16449, 'batch_loss/train': 0.8250860443804413}
+12/25/2021 03:27:43 - INFO - codeparrot_training - Step 16450: {'lr': 0.0003795224824181351, 'samples': 8422912, 'steps': 16450, 'batch_loss/train': 0.7922704815864563}
+12/25/2021 03:27:56 - INFO - codeparrot_training - Step 16451: {'lr': 0.0003795089995397407, 'samples': 8423424, 'steps': 16451, 'batch_loss/train': 0.7929414631798863}
+12/25/2021 03:28:07 - INFO - codeparrot_training - Step 16452: {'lr': 0.0003794955161464675, 'samples': 8423936, 'steps': 16452, 'batch_loss/train': 0.9027003515511751}
+12/25/2021 03:28:17 - INFO - codeparrot_training - Step 16453: {'lr': 0.0003794820322383691, 'samples': 8424448, 'steps': 16453, 'batch_loss/train': 0.8533775340765715}
+12/25/2021 03:28:29 - INFO - codeparrot_training - Step 16454: {'lr': 0.0003794685478154989, 'samples': 8424960, 'steps': 16454, 'batch_loss/train': 0.8236110154539347}
+12/25/2021 03:28:40 - INFO - codeparrot_training - Step 16455: {'lr': 0.0003794550628779107, 'samples': 8425472, 'steps': 16455, 'batch_loss/train': 0.7584734526462853}
+12/25/2021 03:28:51 - INFO - codeparrot_training - Step 16456: {'lr': 0.000379441577425658, 'samples': 8425984, 'steps': 16456, 'batch_loss/train': 0.7601137375459075}
+12/25/2021 03:29:03 - INFO - codeparrot_training - Step 16457: {'lr': 0.0003794280914587945, 'samples': 8426496, 'steps': 16457, 'batch_loss/train': 0.8395616477355361}
+12/25/2021 03:29:13 - INFO - codeparrot_training - Step 16458: {'lr': 0.0003794146049773737, 'samples': 8427008, 'steps': 16458, 'batch_loss/train': 0.601382864639163}
+12/25/2021 03:29:24 - INFO - codeparrot_training - Step 16459: {'lr': 0.0003794011179814494, 'samples': 8427520, 'steps': 16459, 'batch_loss/train': 0.8463073363527656}
+12/25/2021 03:29:35 - INFO - codeparrot_training - Step 16460: {'lr': 0.0003793876304710751, 'samples': 8428032, 'steps': 16460, 'batch_loss/train': 0.7563352892175317}
+12/25/2021 03:29:47 - INFO - codeparrot_training - Step 16461: {'lr': 0.0003793741424463044, 'samples': 8428544, 'steps': 16461, 'batch_loss/train': 0.7561961910687387}
+12/25/2021 03:29:58 - INFO - codeparrot_training - Step 16462: {'lr': 0.000379360653907191, 'samples': 8429056, 'steps': 16462, 'batch_loss/train': 1.0054340222850442}
+12/25/2021 03:30:08 - INFO - codeparrot_training - Step 16463: {'lr': 0.00037934716485378843, 'samples': 8429568, 'steps': 16463, 'batch_loss/train': 0.8225608076900244}
+12/25/2021 03:30:21 - INFO - codeparrot_training - Step 16464: {'lr': 0.00037933367528615044, 'samples': 8430080, 'steps': 16464, 'batch_loss/train': 0.9183127526193857}
+12/25/2021 03:30:31 - INFO - codeparrot_training - Step 16465: {'lr': 0.00037932018520433054, 'samples': 8430592, 'steps': 16465, 'batch_loss/train': 0.8509008605033159}
+12/25/2021 03:30:42 - INFO - codeparrot_training - Step 16466: {'lr': 0.00037930669460838247, 'samples': 8431104, 'steps': 16466, 'batch_loss/train': 0.8368670279160142}
+12/25/2021 03:30:55 - INFO - codeparrot_training - Step 16467: {'lr': 0.0003792932034983597, 'samples': 8431616, 'steps': 16467, 'batch_loss/train': 1.0684367178473622}
+12/25/2021 03:31:05 - INFO - codeparrot_training - Step 16468: {'lr': 0.000379279711874316, 'samples': 8432128, 'steps': 16468, 'batch_loss/train': 0.7960388326318935}
+12/25/2021 03:31:16 - INFO - codeparrot_training - Step 16469: {'lr': 0.00037926621973630506, 'samples': 8432640, 'steps': 16469, 'batch_loss/train': 0.7981840176507831}
+12/25/2021 03:31:27 - INFO - codeparrot_training - Step 16470: {'lr': 0.0003792527270843804, 'samples': 8433152, 'steps': 16470, 'batch_loss/train': 0.779503648635}
+12/25/2021 03:31:39 - INFO - codeparrot_training - Step 16471: {'lr': 0.0003792392339185957, 'samples': 8433664, 'steps': 16471, 'batch_loss/train': 0.8255496290512383}
+12/25/2021 03:31:49 - INFO - codeparrot_training - Step 16472: {'lr': 0.0003792257402390046, 'samples': 8434176, 'steps': 16472, 'batch_loss/train': 0.769402094418183}
+12/25/2021 03:32:00 - INFO - codeparrot_training - Step 16473: {'lr': 0.0003792122460456608, 'samples': 8434688, 'steps': 16473, 'batch_loss/train': 0.8440640748012811}
+12/25/2021 03:32:12 - INFO - codeparrot_training - Step 16474: {'lr': 0.0003791987513386178, 'samples': 8435200, 'steps': 16474, 'batch_loss/train': 1.0737783601507545}
+12/25/2021 03:32:23 - INFO - codeparrot_training - Step 16475: {'lr': 0.0003791852561179294, 'samples': 8435712, 'steps': 16475, 'batch_loss/train': 0.8259078186238185}
+12/25/2021 03:32:33 - INFO - codeparrot_training - Step 16476: {'lr': 0.0003791717603836492, 'samples': 8436224, 'steps': 16476, 'batch_loss/train': 0.7899503069929779}
+12/25/2021 03:32:46 - INFO - codeparrot_training - Step 16477: {'lr': 0.0003791582641358309, 'samples': 8436736, 'steps': 16477, 'batch_loss/train': 0.8505193097516894}
+12/25/2021 03:32:56 - INFO - codeparrot_training - Step 16478: {'lr': 0.000379144767374528, 'samples': 8437248, 'steps': 16478, 'batch_loss/train': 0.8115126470220275}
+12/25/2021 03:33:07 - INFO - codeparrot_training - Step 16479: {'lr': 0.0003791312700997944, 'samples': 8437760, 'steps': 16479, 'batch_loss/train': 0.8243734799325466}
+12/25/2021 03:33:18 - INFO - codeparrot_training - Step 16480: {'lr': 0.0003791177723116835, 'samples': 8438272, 'steps': 16480, 'batch_loss/train': 0.8393291682004929}
+12/25/2021 03:33:30 - INFO - codeparrot_training - Step 16481: {'lr': 0.0003791042740102492, 'samples': 8438784, 'steps': 16481, 'batch_loss/train': 0.8002667257096618}
+12/25/2021 03:33:40 - INFO - codeparrot_training - Step 16482: {'lr': 0.00037909077519554497, 'samples': 8439296, 'steps': 16482, 'batch_loss/train': 0.9083249159157276}
+12/25/2021 03:33:51 - INFO - codeparrot_training - Step 16483: {'lr': 0.0003790772758676246, 'samples': 8439808, 'steps': 16483, 'batch_loss/train': 0.7681462168693542}
+12/25/2021 03:34:03 - INFO - codeparrot_training - Step 16484: {'lr': 0.0003790637760265417, 'samples': 8440320, 'steps': 16484, 'batch_loss/train': 0.7831322737038136}
+12/25/2021 03:34:14 - INFO - codeparrot_training - Step 16485: {'lr': 0.00037905027567234994, 'samples': 8440832, 'steps': 16485, 'batch_loss/train': 0.6631510443985462}
+12/25/2021 03:34:24 - INFO - codeparrot_training - Step 16486: {'lr': 0.00037903677480510313, 'samples': 8441344, 'steps': 16486, 'batch_loss/train': 0.8327266471460462}
+12/25/2021 03:34:36 - INFO - codeparrot_training - Step 16487: {'lr': 0.0003790232734248547, 'samples': 8441856, 'steps': 16487, 'batch_loss/train': 0.7892580246552825}
+12/25/2021 03:34:47 - INFO - codeparrot_training - Step 16488: {'lr': 0.0003790097715316585, 'samples': 8442368, 'steps': 16488, 'batch_loss/train': 0.7624923280673102}
+12/25/2021 03:34:58 - INFO - codeparrot_training - Step 16489: {'lr': 0.00037899626912556817, 'samples': 8442880, 'steps': 16489, 'batch_loss/train': 0.7753078872337937}
+12/25/2021 03:35:08 - INFO - codeparrot_training - Step 16490: {'lr': 0.0003789827662066373, 'samples': 8443392, 'steps': 16490, 'batch_loss/train': 0.8057362074032426}
+12/25/2021 03:35:22 - INFO - codeparrot_training - Step 16491: {'lr': 0.0003789692627749197, 'samples': 8443904, 'steps': 16491, 'batch_loss/train': 0.7815865671727806}
+12/25/2021 03:35:32 - INFO - codeparrot_training - Step 16492: {'lr': 0.00037895575883046905, 'samples': 8444416, 'steps': 16492, 'batch_loss/train': 0.6906238934025168}
+12/25/2021 03:35:43 - INFO - codeparrot_training - Step 16493: {'lr': 0.000378942254373339, 'samples': 8444928, 'steps': 16493, 'batch_loss/train': 0.6305379341356456}
+12/25/2021 03:35:55 - INFO - codeparrot_training - Step 16494: {'lr': 0.00037892874940358314, 'samples': 8445440, 'steps': 16494, 'batch_loss/train': 0.7956684986129403}
+12/25/2021 03:36:05 - INFO - codeparrot_training - Step 16495: {'lr': 0.0003789152439212554, 'samples': 8445952, 'steps': 16495, 'batch_loss/train': 0.8217930993996561}
+12/25/2021 03:36:16 - INFO - codeparrot_training - Step 16496: {'lr': 0.0003789017379264093, 'samples': 8446464, 'steps': 16496, 'batch_loss/train': 0.8296674899756908}
+12/25/2021 03:36:29 - INFO - codeparrot_training - Step 16497: {'lr': 0.0003788882314190984, 'samples': 8446976, 'steps': 16497, 'batch_loss/train': 0.7899437178857625}
+12/25/2021 03:36:39 - INFO - codeparrot_training - Step 16498: {'lr': 0.00037887472439937666, 'samples': 8447488, 'steps': 16498, 'batch_loss/train': 0.6996634872630239}
+12/25/2021 03:36:50 - INFO - codeparrot_training - Step 16499: {'lr': 0.00037886121686729775, 'samples': 8448000, 'steps': 16499, 'batch_loss/train': 0.797478562220931}
+12/25/2021 03:37:00 - INFO - codeparrot_training - Step 16500: {'lr': 0.0003788477088229152, 'samples': 8448512, 'steps': 16500, 'batch_loss/train': 0.7477188266348094}
+12/25/2021 03:37:12 - INFO - codeparrot_training - Step 16501: {'lr': 0.00037883420026628287, 'samples': 8449024, 'steps': 16501, 'batch_loss/train': 0.950902255717665}
+12/25/2021 03:37:23 - INFO - codeparrot_training - Step 16502: {'lr': 0.00037882069119745434, 'samples': 8449536, 'steps': 16502, 'batch_loss/train': 0.7583601241931319}
+12/25/2021 03:37:34 - INFO - codeparrot_training - Step 16503: {'lr': 0.0003788071816164834, 'samples': 8450048, 'steps': 16503, 'batch_loss/train': 0.8168062679469585}
+12/25/2021 03:37:46 - INFO - codeparrot_training - Step 16504: {'lr': 0.00037879367152342377, 'samples': 8450560, 'steps': 16504, 'batch_loss/train': 0.78849514760077}
+12/25/2021 03:37:56 - INFO - codeparrot_training - Step 16505: {'lr': 0.0003787801609183291, 'samples': 8451072, 'steps': 16505, 'batch_loss/train': 0.7755010211840272}
+12/25/2021 03:38:07 - INFO - codeparrot_training - Step 16506: {'lr': 0.0003787666498012531, 'samples': 8451584, 'steps': 16506, 'batch_loss/train': 0.7951684494037181}
+12/25/2021 03:38:20 - INFO - codeparrot_training - Step 16507: {'lr': 0.00037875313817224964, 'samples': 8452096, 'steps': 16507, 'batch_loss/train': 0.5416113164974377}
+12/25/2021 03:38:30 - INFO - codeparrot_training - Step 16508: {'lr': 0.00037873962603137226, 'samples': 8452608, 'steps': 16508, 'batch_loss/train': 0.7746973051689565}
+12/25/2021 03:38:41 - INFO - codeparrot_training - Step 16509: {'lr': 0.00037872611337867474, 'samples': 8453120, 'steps': 16509, 'batch_loss/train': 0.8164829509332776}
+12/25/2021 03:38:53 - INFO - codeparrot_training - Step 16510: {'lr': 0.00037871260021421076, 'samples': 8453632, 'steps': 16510, 'batch_loss/train': 0.8254687869921327}
+12/25/2021 03:39:04 - INFO - codeparrot_training - Step 16511: {'lr': 0.00037869908653803414, 'samples': 8454144, 'steps': 16511, 'batch_loss/train': 0.7941197762265801}
+12/25/2021 03:39:14 - INFO - codeparrot_training - Step 16512: {'lr': 0.0003786855723501985, 'samples': 8454656, 'steps': 16512, 'batch_loss/train': 0.8040883066132665}
+12/25/2021 03:39:25 - INFO - codeparrot_training - Step 16513: {'lr': 0.00037867205765075763, 'samples': 8455168, 'steps': 16513, 'batch_loss/train': 0.821681444067508}
+12/25/2021 03:39:37 - INFO - codeparrot_training - Step 16514: {'lr': 0.0003786585424397653, 'samples': 8455680, 'steps': 16514, 'batch_loss/train': 0.7770571578294039}
+12/25/2021 03:39:47 - INFO - codeparrot_training - Step 16515: {'lr': 0.0003786450267172751, 'samples': 8456192, 'steps': 16515, 'batch_loss/train': 0.6866654111072421}
+12/25/2021 03:39:58 - INFO - codeparrot_training - Step 16516: {'lr': 0.00037863151048334086, 'samples': 8456704, 'steps': 16516, 'batch_loss/train': 0.8063623425550759}
+12/25/2021 03:40:11 - INFO - codeparrot_training - Step 16517: {'lr': 0.0003786179937380163, 'samples': 8457216, 'steps': 16517, 'batch_loss/train': 0.7917315142694861}
+12/25/2021 03:40:21 - INFO - codeparrot_training - Step 16518: {'lr': 0.00037860447648135524, 'samples': 8457728, 'steps': 16518, 'batch_loss/train': 0.8119336636736989}
+12/25/2021 03:40:32 - INFO - codeparrot_training - Step 16519: {'lr': 0.0003785909587134113, 'samples': 8458240, 'steps': 16519, 'batch_loss/train': 0.8167871756013483}
+12/25/2021 03:40:44 - INFO - codeparrot_training - Step 16520: {'lr': 0.0003785774404342382, 'samples': 8458752, 'steps': 16520, 'batch_loss/train': 0.7268245306331664}
+12/25/2021 03:40:55 - INFO - codeparrot_training - Step 16521: {'lr': 0.00037856392164388984, 'samples': 8459264, 'steps': 16521, 'batch_loss/train': 1.3858943413943052}
+12/25/2021 03:41:06 - INFO - codeparrot_training - Step 16522: {'lr': 0.00037855040234241976, 'samples': 8459776, 'steps': 16522, 'batch_loss/train': 0.7487788200378418}
+12/25/2021 03:41:16 - INFO - codeparrot_training - Step 16523: {'lr': 0.0003785368825298819, 'samples': 8460288, 'steps': 16523, 'batch_loss/train': 0.8955449759960175}
+12/25/2021 03:41:28 - INFO - codeparrot_training - Step 16524: {'lr': 0.00037852336220632995, 'samples': 8460800, 'steps': 16524, 'batch_loss/train': 0.682218772592023}
+12/25/2021 03:41:39 - INFO - codeparrot_training - Step 16525: {'lr': 0.00037850984137181767, 'samples': 8461312, 'steps': 16525, 'batch_loss/train': 0.6752700781216845}
+12/25/2021 03:41:49 - INFO - codeparrot_training - Step 16526: {'lr': 0.00037849632002639864, 'samples': 8461824, 'steps': 16526, 'batch_loss/train': 0.7811495019122958}
+12/25/2021 03:42:02 - INFO - codeparrot_training - Step 16527: {'lr': 0.00037848279817012686, 'samples': 8462336, 'steps': 16527, 'batch_loss/train': 0.7766978833824396}
+12/25/2021 03:42:13 - INFO - codeparrot_training - Step 16528: {'lr': 0.00037846927580305594, 'samples': 8462848, 'steps': 16528, 'batch_loss/train': 0.8493122756481171}
+12/25/2021 03:42:23 - INFO - codeparrot_training - Step 16529: {'lr': 0.0003784557529252397, 'samples': 8463360, 'steps': 16529, 'batch_loss/train': 0.8459546724334359}
+12/25/2021 03:42:35 - INFO - codeparrot_training - Step 16530: {'lr': 0.0003784422295367319, 'samples': 8463872, 'steps': 16530, 'batch_loss/train': 0.8420109911821783}
+12/25/2021 03:42:46 - INFO - codeparrot_training - Step 16531: {'lr': 0.0003784287056375863, 'samples': 8464384, 'steps': 16531, 'batch_loss/train': 0.7454065852798522}
+12/25/2021 03:42:57 - INFO - codeparrot_training - Step 16532: {'lr': 0.00037841518122785667, 'samples': 8464896, 'steps': 16532, 'batch_loss/train': 0.8109003826975822}
+12/25/2021 03:43:07 - INFO - codeparrot_training - Step 16533: {'lr': 0.0003784016563075967, 'samples': 8465408, 'steps': 16533, 'batch_loss/train': 0.7368392455391586}
+12/25/2021 03:43:19 - INFO - codeparrot_training - Step 16534: {'lr': 0.00037838813087686036, 'samples': 8465920, 'steps': 16534, 'batch_loss/train': 0.8313487195409834}
+12/25/2021 03:43:30 - INFO - codeparrot_training - Step 16535: {'lr': 0.0003783746049357012, 'samples': 8466432, 'steps': 16535, 'batch_loss/train': 0.8405038439668715}
+12/25/2021 03:43:40 - INFO - codeparrot_training - Step 16536: {'lr': 0.0003783610784841731, 'samples': 8466944, 'steps': 16536, 'batch_loss/train': 0.8064529099501669}
+12/25/2021 03:43:53 - INFO - codeparrot_training - Step 16537: {'lr': 0.00037834755152232983, 'samples': 8467456, 'steps': 16537, 'batch_loss/train': 0.8049694681540132}
+12/25/2021 03:44:04 - INFO - codeparrot_training - Step 16538: {'lr': 0.0003783340240502251, 'samples': 8467968, 'steps': 16538, 'batch_loss/train': 0.8242783132009208}
+12/25/2021 03:44:14 - INFO - codeparrot_training - Step 16539: {'lr': 0.00037832049606791274, 'samples': 8468480, 'steps': 16539, 'batch_loss/train': 0.7106008271221071}
+12/25/2021 03:44:26 - INFO - codeparrot_training - Step 16540: {'lr': 0.00037830696757544665, 'samples': 8468992, 'steps': 16540, 'batch_loss/train': 0.8009513840079308}
+12/25/2021 03:44:37 - INFO - codeparrot_training - Step 16541: {'lr': 0.00037829343857288046, 'samples': 8469504, 'steps': 16541, 'batch_loss/train': 0.8087261221371591}
+12/25/2021 03:44:48 - INFO - codeparrot_training - Step 16542: {'lr': 0.0003782799090602679, 'samples': 8470016, 'steps': 16542, 'batch_loss/train': 0.7671624538488686}
+12/25/2021 03:44:58 - INFO - codeparrot_training - Step 16543: {'lr': 0.0003782663790376629, 'samples': 8470528, 'steps': 16543, 'batch_loss/train': 0.8415856389328837}
+12/25/2021 03:45:10 - INFO - codeparrot_training - Step 16544: {'lr': 0.00037825284850511934, 'samples': 8471040, 'steps': 16544, 'batch_loss/train': 0.739308618940413}
+12/25/2021 03:45:21 - INFO - codeparrot_training - Step 16545: {'lr': 0.00037823931746269073, 'samples': 8471552, 'steps': 16545, 'batch_loss/train': 0.7557910224422812}
+12/25/2021 03:45:32 - INFO - codeparrot_training - Step 16546: {'lr': 0.0003782257859104311, 'samples': 8472064, 'steps': 16546, 'batch_loss/train': 0.8061896306462586}
+12/25/2021 03:45:45 - INFO - codeparrot_training - Step 16547: {'lr': 0.00037821225384839413, 'samples': 8472576, 'steps': 16547, 'batch_loss/train': 0.8988741151988506}
+12/25/2021 03:45:55 - INFO - codeparrot_training - Step 16548: {'lr': 0.0003781987212766337, 'samples': 8473088, 'steps': 16548, 'batch_loss/train': 0.7664727522060275}
+12/25/2021 03:46:06 - INFO - codeparrot_training - Step 16549: {'lr': 0.00037818518819520347, 'samples': 8473600, 'steps': 16549, 'batch_loss/train': 0.8005831367336214}
+12/25/2021 03:46:18 - INFO - codeparrot_training - Step 16550: {'lr': 0.00037817165460415735, 'samples': 8474112, 'steps': 16550, 'batch_loss/train': 0.726163043640554}
+12/25/2021 03:46:28 - INFO - codeparrot_training - Step 16551: {'lr': 0.00037815812050354916, 'samples': 8474624, 'steps': 16551, 'batch_loss/train': 0.7795983799733222}
+12/25/2021 03:46:39 - INFO - codeparrot_training - Step 16552: {'lr': 0.00037814458589343264, 'samples': 8475136, 'steps': 16552, 'batch_loss/train': 0.869534901343286}
+12/25/2021 03:46:50 - INFO - codeparrot_training - Step 16553: {'lr': 0.00037813105077386165, 'samples': 8475648, 'steps': 16553, 'batch_loss/train': 0.8297166768461466}
+12/25/2021 03:47:03 - INFO - codeparrot_training - Step 16554: {'lr': 0.00037811751514489, 'samples': 8476160, 'steps': 16554, 'batch_loss/train': 0.6709253331646323}
+12/25/2021 03:47:14 - INFO - codeparrot_training - Step 16555: {'lr': 0.00037810397900657147, 'samples': 8476672, 'steps': 16555, 'batch_loss/train': 0.8448412213474512}
+12/25/2021 03:47:25 - INFO - codeparrot_training - Step 16556: {'lr': 0.00037809044235895993, 'samples': 8477184, 'steps': 16556, 'batch_loss/train': 0.740744206123054}
+12/25/2021 03:47:38 - INFO - codeparrot_training - Step 16557: {'lr': 0.00037807690520210915, 'samples': 8477696, 'steps': 16557, 'batch_loss/train': 0.8634712006896734}
+12/25/2021 03:47:48 - INFO - codeparrot_training - Step 16558: {'lr': 0.00037806336753607285, 'samples': 8478208, 'steps': 16558, 'batch_loss/train': 0.5663075284101069}
+12/25/2021 03:47:59 - INFO - codeparrot_training - Step 16559: {'lr': 0.000378049829360905, 'samples': 8478720, 'steps': 16559, 'batch_loss/train': 1.0266973900143057}
+12/25/2021 03:48:09 - INFO - codeparrot_training - Step 16560: {'lr': 0.0003780362906766595, 'samples': 8479232, 'steps': 16560, 'batch_loss/train': 0.7004072163254023}
+12/25/2021 03:48:21 - INFO - codeparrot_training - Step 16561: {'lr': 0.00037802275148338994, 'samples': 8479744, 'steps': 16561, 'batch_loss/train': 0.8039108701050282}
+12/25/2021 03:48:32 - INFO - codeparrot_training - Step 16562: {'lr': 0.00037800921178115035, 'samples': 8480256, 'steps': 16562, 'batch_loss/train': 0.8419303754344583}
+12/25/2021 03:48:43 - INFO - codeparrot_training - Step 16563: {'lr': 0.0003779956715699944, 'samples': 8480768, 'steps': 16563, 'batch_loss/train': 0.7792437979951501}
+12/25/2021 03:48:55 - INFO - codeparrot_training - Step 16564: {'lr': 0.0003779821308499759, 'samples': 8481280, 'steps': 16564, 'batch_loss/train': 0.8435241850093007}
+12/25/2021 03:49:05 - INFO - codeparrot_training - Step 16565: {'lr': 0.0003779685896211489, 'samples': 8481792, 'steps': 16565, 'batch_loss/train': 0.6361147145507857}
+12/25/2021 03:49:16 - INFO - codeparrot_training - Step 16566: {'lr': 0.00037795504788356703, 'samples': 8482304, 'steps': 16566, 'batch_loss/train': 0.735586043796502}
+12/25/2021 03:49:29 - INFO - codeparrot_training - Step 16567: {'lr': 0.0003779415056372843, 'samples': 8482816, 'steps': 16567, 'batch_loss/train': 0.8960874630138278}
+12/25/2021 03:49:40 - INFO - codeparrot_training - Step 16568: {'lr': 0.0003779279628823543, 'samples': 8483328, 'steps': 16568, 'batch_loss/train': 0.8110686857253313}
+12/25/2021 03:49:50 - INFO - codeparrot_training - Step 16569: {'lr': 0.0003779144196188312, 'samples': 8483840, 'steps': 16569, 'batch_loss/train': 0.7972037107683718}
+12/25/2021 03:50:02 - INFO - codeparrot_training - Step 16570: {'lr': 0.00037790087584676856, 'samples': 8484352, 'steps': 16570, 'batch_loss/train': 0.7254444495774806}
+12/25/2021 03:50:13 - INFO - codeparrot_training - Step 16571: {'lr': 0.00037788733156622037, 'samples': 8484864, 'steps': 16571, 'batch_loss/train': 0.9556894423440099}
+12/25/2021 03:50:24 - INFO - codeparrot_training - Step 16572: {'lr': 0.0003778737867772404, 'samples': 8485376, 'steps': 16572, 'batch_loss/train': 0.8679171307012439}
+12/25/2021 03:50:34 - INFO - codeparrot_training - Step 16573: {'lr': 0.00037786024147988263, 'samples': 8485888, 'steps': 16573, 'batch_loss/train': 0.8097782908007503}
+12/25/2021 03:50:46 - INFO - codeparrot_training - Step 16574: {'lr': 0.00037784669567420063, 'samples': 8486400, 'steps': 16574, 'batch_loss/train': 1.1774125043302774}
+12/25/2021 03:50:57 - INFO - codeparrot_training - Step 16575: {'lr': 0.0003778331493602486, 'samples': 8486912, 'steps': 16575, 'batch_loss/train': 0.7441344138933346}
+12/25/2021 03:51:07 - INFO - codeparrot_training - Step 16576: {'lr': 0.00037781960253808024, 'samples': 8487424, 'steps': 16576, 'batch_loss/train': 0.754784211050719}
+12/25/2021 03:51:20 - INFO - codeparrot_training - Step 16577: {'lr': 0.00037780605520774935, 'samples': 8487936, 'steps': 16577, 'batch_loss/train': 0.7040003549773246}
+12/25/2021 03:51:31 - INFO - codeparrot_training - Step 16578: {'lr': 0.0003777925073693098, 'samples': 8488448, 'steps': 16578, 'batch_loss/train': 0.8811511285603046}
+12/25/2021 03:51:41 - INFO - codeparrot_training - Step 16579: {'lr': 0.00037777895902281553, 'samples': 8488960, 'steps': 16579, 'batch_loss/train': 0.7976763565093279}
+12/25/2021 03:51:53 - INFO - codeparrot_training - Step 16580: {'lr': 0.00037776541016832044, 'samples': 8489472, 'steps': 16580, 'batch_loss/train': 0.8060139836743474}
+12/25/2021 03:52:04 - INFO - codeparrot_training - Step 16581: {'lr': 0.0003777518608058782, 'samples': 8489984, 'steps': 16581, 'batch_loss/train': 0.8140704685356468}
+12/25/2021 03:52:14 - INFO - codeparrot_training - Step 16582: {'lr': 0.0003777383109355429, 'samples': 8490496, 'steps': 16582, 'batch_loss/train': 0.9451856901869178}
+12/25/2021 03:52:25 - INFO - codeparrot_training - Step 16583: {'lr': 0.00037772476055736824, 'samples': 8491008, 'steps': 16583, 'batch_loss/train': 0.7788053378462791}
+12/25/2021 03:52:38 - INFO - codeparrot_training - Step 16584: {'lr': 0.0003777112096714082, 'samples': 8491520, 'steps': 16584, 'batch_loss/train': 0.7775973826646805}
+12/25/2021 03:52:49 - INFO - codeparrot_training - Step 16585: {'lr': 0.00037769765827771665, 'samples': 8492032, 'steps': 16585, 'batch_loss/train': 0.8107525454834104}
+12/25/2021 03:52:59 - INFO - codeparrot_training - Step 16586: {'lr': 0.0003776841063763474, 'samples': 8492544, 'steps': 16586, 'batch_loss/train': 0.7395923510193825}
+12/25/2021 03:53:11 - INFO - codeparrot_training - Step 16587: {'lr': 0.0003776705539673543, 'samples': 8493056, 'steps': 16587, 'batch_loss/train': 0.7230852670036256}
+12/25/2021 03:53:22 - INFO - codeparrot_training - Step 16588: {'lr': 0.0003776570010507913, 'samples': 8493568, 'steps': 16588, 'batch_loss/train': 0.7370801763609052}
+12/25/2021 03:53:32 - INFO - codeparrot_training - Step 16589: {'lr': 0.00037764344762671227, 'samples': 8494080, 'steps': 16589, 'batch_loss/train': 0.8609027564525604}
+12/25/2021 03:53:43 - INFO - codeparrot_training - Step 16590: {'lr': 0.0003776298936951711, 'samples': 8494592, 'steps': 16590, 'batch_loss/train': 0.830739120952785}
+12/25/2021 03:53:55 - INFO - codeparrot_training - Step 16591: {'lr': 0.00037761633925622164, 'samples': 8495104, 'steps': 16591, 'batch_loss/train': 0.8052471922710538}
+12/25/2021 03:54:06 - INFO - codeparrot_training - Step 16592: {'lr': 0.0003776027843099178, 'samples': 8495616, 'steps': 16592, 'batch_loss/train': 0.8935459610074759}
+12/25/2021 03:54:16 - INFO - codeparrot_training - Step 16593: {'lr': 0.0003775892288563135, 'samples': 8496128, 'steps': 16593, 'batch_loss/train': 0.6191854854114354}
+12/25/2021 03:54:30 - INFO - codeparrot_training - Step 16594: {'lr': 0.00037757567289546255, 'samples': 8496640, 'steps': 16594, 'batch_loss/train': 0.6453753454843536}
+12/25/2021 03:54:40 - INFO - codeparrot_training - Step 16595: {'lr': 0.000377562116427419, 'samples': 8497152, 'steps': 16595, 'batch_loss/train': 0.7863879706710577}
+12/25/2021 03:54:51 - INFO - codeparrot_training - Step 16596: {'lr': 0.00037754855945223666, 'samples': 8497664, 'steps': 16596, 'batch_loss/train': 0.9586450178176165}
+12/25/2021 03:55:03 - INFO - codeparrot_training - Step 16597: {'lr': 0.00037753500196996924, 'samples': 8498176, 'steps': 16597, 'batch_loss/train': 0.8055119905620813}
+12/25/2021 03:55:13 - INFO - codeparrot_training - Step 16598: {'lr': 0.0003775214439806709, 'samples': 8498688, 'steps': 16598, 'batch_loss/train': 0.8896419415250421}
+12/25/2021 03:55:24 - INFO - codeparrot_training - Step 16599: {'lr': 0.0003775078854843955, 'samples': 8499200, 'steps': 16599, 'batch_loss/train': 0.7959301364608109}
+12/25/2021 03:55:35 - INFO - codeparrot_training - Step 16600: {'lr': 0.0003774943264811968, 'samples': 8499712, 'steps': 16600, 'batch_loss/train': 0.8302432345226407}
+12/25/2021 03:55:47 - INFO - codeparrot_training - Step 16601: {'lr': 0.0003774807669711289, 'samples': 8500224, 'steps': 16601, 'batch_loss/train': 0.7830287925899029}
+12/25/2021 03:55:57 - INFO - codeparrot_training - Step 16602: {'lr': 0.0003774672069542455, 'samples': 8500736, 'steps': 16602, 'batch_loss/train': 0.8227236882084981}
+12/25/2021 03:56:08 - INFO - codeparrot_training - Step 16603: {'lr': 0.00037745364643060065, 'samples': 8501248, 'steps': 16603, 'batch_loss/train': 0.7878961353562772}
+12/25/2021 03:56:20 - INFO - codeparrot_training - Step 16604: {'lr': 0.0003774400854002482, 'samples': 8501760, 'steps': 16604, 'batch_loss/train': 0.726678610779345}
+12/25/2021 03:56:31 - INFO - codeparrot_training - Step 16605: {'lr': 0.00037742652386324216, 'samples': 8502272, 'steps': 16605, 'batch_loss/train': 0.762860338203609}
+12/25/2021 03:56:42 - INFO - codeparrot_training - Step 16606: {'lr': 0.00037741296181963634, 'samples': 8502784, 'steps': 16606, 'batch_loss/train': 0.8711648182943463}
+12/25/2021 03:56:54 - INFO - codeparrot_training - Step 16607: {'lr': 0.00037739939926948466, 'samples': 8503296, 'steps': 16607, 'batch_loss/train': 0.7261677663773298}
+12/25/2021 03:57:05 - INFO - codeparrot_training - Step 16608: {'lr': 0.00037738583621284115, 'samples': 8503808, 'steps': 16608, 'batch_loss/train': 0.8561877384781837}
+12/25/2021 03:57:15 - INFO - codeparrot_training - Step 16609: {'lr': 0.0003773722726497596, 'samples': 8504320, 'steps': 16609, 'batch_loss/train': 0.6730571042280644}
+12/25/2021 03:57:27 - INFO - codeparrot_training - Step 16610: {'lr': 0.000377358708580294, 'samples': 8504832, 'steps': 16610, 'batch_loss/train': 0.6267926581203938}
+12/25/2021 03:57:38 - INFO - codeparrot_training - Step 16611: {'lr': 0.0003773451440044983, 'samples': 8505344, 'steps': 16611, 'batch_loss/train': 0.7693609306588769}
+12/25/2021 03:57:49 - INFO - codeparrot_training - Step 16612: {'lr': 0.00037733157892242634, 'samples': 8505856, 'steps': 16612, 'batch_loss/train': 0.8431441392749548}
+12/25/2021 03:57:59 - INFO - codeparrot_training - Step 16613: {'lr': 0.00037731801333413205, 'samples': 8506368, 'steps': 16613, 'batch_loss/train': 0.8202112372964621}
+12/25/2021 03:58:12 - INFO - codeparrot_training - Step 16614: {'lr': 0.0003773044472396695, 'samples': 8506880, 'steps': 16614, 'batch_loss/train': 0.8036119181197137}
+12/25/2021 03:58:23 - INFO - codeparrot_training - Step 16615: {'lr': 0.00037729088063909253, 'samples': 8507392, 'steps': 16615, 'batch_loss/train': 0.7770014917477965}
+12/25/2021 03:58:33 - INFO - codeparrot_training - Step 16616: {'lr': 0.00037727731353245507, 'samples': 8507904, 'steps': 16616, 'batch_loss/train': 0.8533467063680291}
+12/25/2021 03:58:45 - INFO - codeparrot_training - Step 16617: {'lr': 0.0003772637459198111, 'samples': 8508416, 'steps': 16617, 'batch_loss/train': 0.8291139649227262}
+12/25/2021 03:58:56 - INFO - codeparrot_training - Step 16618: {'lr': 0.0003772501778012144, 'samples': 8508928, 'steps': 16618, 'batch_loss/train': 0.9490412268787622}
+12/25/2021 03:59:07 - INFO - codeparrot_training - Step 16619: {'lr': 0.00037723660917671914, 'samples': 8509440, 'steps': 16619, 'batch_loss/train': 1.052719285711646}
+12/25/2021 03:59:19 - INFO - codeparrot_training - Step 16620: {'lr': 0.0003772230400463792, 'samples': 8509952, 'steps': 16620, 'batch_loss/train': 0.8003109847195446}
+12/25/2021 03:59:29 - INFO - codeparrot_training - Step 16621: {'lr': 0.00037720947041024845, 'samples': 8510464, 'steps': 16621, 'batch_loss/train': 1.0083906565560028}
+12/25/2021 03:59:40 - INFO - codeparrot_training - Step 16622: {'lr': 0.0003771959002683809, 'samples': 8510976, 'steps': 16622, 'batch_loss/train': 0.7835095576010644}
+12/25/2021 03:59:51 - INFO - codeparrot_training - Step 16623: {'lr': 0.0003771823296208304, 'samples': 8511488, 'steps': 16623, 'batch_loss/train': 0.8393483646214008}
+12/25/2021 04:00:03 - INFO - codeparrot_training - Step 16624: {'lr': 0.00037716875846765104, 'samples': 8512000, 'steps': 16624, 'batch_loss/train': 0.7517706081271172}
+12/25/2021 04:00:14 - INFO - codeparrot_training - Step 16625: {'lr': 0.0003771551868088967, 'samples': 8512512, 'steps': 16625, 'batch_loss/train': 0.8402067485731095}
+12/25/2021 04:00:25 - INFO - codeparrot_training - Step 16626: {'lr': 0.0003771416146446214, 'samples': 8513024, 'steps': 16626, 'batch_loss/train': 0.8476774012669921}
+12/25/2021 04:00:37 - INFO - codeparrot_training - Step 16627: {'lr': 0.000377128041974879, 'samples': 8513536, 'steps': 16627, 'batch_loss/train': 0.8483178850729018}
+12/25/2021 04:00:47 - INFO - codeparrot_training - Step 16628: {'lr': 0.0003771144687997235, 'samples': 8514048, 'steps': 16628, 'batch_loss/train': 0.8186574587598443}
+12/25/2021 04:00:58 - INFO - codeparrot_training - Step 16629: {'lr': 0.00037710089511920885, 'samples': 8514560, 'steps': 16629, 'batch_loss/train': 0.7525997310876846}
+12/25/2021 04:01:11 - INFO - codeparrot_training - Step 16630: {'lr': 0.00037708732093338904, 'samples': 8515072, 'steps': 16630, 'batch_loss/train': 0.8002572609111667}
+12/25/2021 04:01:21 - INFO - codeparrot_training - Step 16631: {'lr': 0.00037707374624231806, 'samples': 8515584, 'steps': 16631, 'batch_loss/train': 0.7531296997331083}
+12/25/2021 04:01:32 - INFO - codeparrot_training - Step 16632: {'lr': 0.00037706017104604985, 'samples': 8516096, 'steps': 16632, 'batch_loss/train': 0.8644985544960946}
+12/25/2021 04:01:42 - INFO - codeparrot_training - Step 16633: {'lr': 0.00037704659534463836, 'samples': 8516608, 'steps': 16633, 'batch_loss/train': 0.8625244228169322}
+12/25/2021 04:01:54 - INFO - codeparrot_training - Step 16634: {'lr': 0.0003770330191381376, 'samples': 8517120, 'steps': 16634, 'batch_loss/train': 0.7983301468193531}
+12/25/2021 04:02:05 - INFO - codeparrot_training - Step 16635: {'lr': 0.00037701944242660146, 'samples': 8517632, 'steps': 16635, 'batch_loss/train': 0.8187095366884023}
+12/25/2021 04:02:16 - INFO - codeparrot_training - Step 16636: {'lr': 0.00037700586521008405, 'samples': 8518144, 'steps': 16636, 'batch_loss/train': 0.7138143037445843}
+12/25/2021 04:02:28 - INFO - codeparrot_training - Step 16637: {'lr': 0.0003769922874886392, 'samples': 8518656, 'steps': 16637, 'batch_loss/train': 0.7799130799248815}
+12/25/2021 04:02:38 - INFO - codeparrot_training - Step 16638: {'lr': 0.000376978709262321, 'samples': 8519168, 'steps': 16638, 'batch_loss/train': 0.7998257642611861}
+12/25/2021 04:02:49 - INFO - codeparrot_training - Step 16639: {'lr': 0.0003769651305311834, 'samples': 8519680, 'steps': 16639, 'batch_loss/train': 0.7067429006565362}
+12/25/2021 04:03:01 - INFO - codeparrot_training - Step 16640: {'lr': 0.00037695155129528036, 'samples': 8520192, 'steps': 16640, 'batch_loss/train': 0.8946420215070248}
+12/25/2021 04:03:12 - INFO - codeparrot_training - Step 16641: {'lr': 0.000376937971554666, 'samples': 8520704, 'steps': 16641, 'batch_loss/train': 1.3274777377955616}
+12/25/2021 04:03:22 - INFO - codeparrot_training - Step 16642: {'lr': 0.00037692439130939407, 'samples': 8521216, 'steps': 16642, 'batch_loss/train': 0.6658538654446602}
+12/25/2021 04:03:33 - INFO - codeparrot_training - Step 16643: {'lr': 0.0003769108105595187, 'samples': 8521728, 'steps': 16643, 'batch_loss/train': 0.8461403069086373}
+12/25/2021 04:03:46 - INFO - codeparrot_training - Step 16644: {'lr': 0.00037689722930509396, 'samples': 8522240, 'steps': 16644, 'batch_loss/train': 0.6072911680676043}
+12/25/2021 04:03:57 - INFO - codeparrot_training - Step 16645: {'lr': 0.00037688364754617364, 'samples': 8522752, 'steps': 16645, 'batch_loss/train': 0.7474903869442642}
+12/25/2021 04:04:07 - INFO - codeparrot_training - Step 16646: {'lr': 0.0003768700652828119, 'samples': 8523264, 'steps': 16646, 'batch_loss/train': 0.7459417106583714}
+12/25/2021 04:04:20 - INFO - codeparrot_training - Step 16647: {'lr': 0.00037685648251506264, 'samples': 8523776, 'steps': 16647, 'batch_loss/train': 0.7201112443581223}
+12/25/2021 04:04:30 - INFO - codeparrot_training - Step 16648: {'lr': 0.00037684289924298, 'samples': 8524288, 'steps': 16648, 'batch_loss/train': 0.8634482966735959}
+12/25/2021 04:04:41 - INFO - codeparrot_training - Step 16649: {'lr': 0.0003768293154666178, 'samples': 8524800, 'steps': 16649, 'batch_loss/train': 0.8697161339223385}
+12/25/2021 04:04:53 - INFO - codeparrot_training - Step 16650: {'lr': 0.0003768157311860302, 'samples': 8525312, 'steps': 16650, 'batch_loss/train': 0.9556110184639692}
+12/25/2021 04:05:03 - INFO - codeparrot_training - Step 16651: {'lr': 0.00037680214640127107, 'samples': 8525824, 'steps': 16651, 'batch_loss/train': 0.7613786077126861}
+12/25/2021 04:05:14 - INFO - codeparrot_training - Step 16652: {'lr': 0.0003767885611123945, 'samples': 8526336, 'steps': 16652, 'batch_loss/train': 0.7624295821879059}
+12/25/2021 04:05:25 - INFO - codeparrot_training - Step 16653: {'lr': 0.0003767749753194545, 'samples': 8526848, 'steps': 16653, 'batch_loss/train': 0.802471979521215}
+12/25/2021 04:05:37 - INFO - codeparrot_training - Step 16654: {'lr': 0.000376761389022505, 'samples': 8527360, 'steps': 16654, 'batch_loss/train': 0.6946359314024448}
+12/25/2021 04:05:48 - INFO - codeparrot_training - Step 16655: {'lr': 0.0003767478022216001, 'samples': 8527872, 'steps': 16655, 'batch_loss/train': 0.8241288680583239}
+12/25/2021 04:05:58 - INFO - codeparrot_training - Step 16656: {'lr': 0.00037673421491679393, 'samples': 8528384, 'steps': 16656, 'batch_loss/train': 0.7735501201823354}
+12/25/2021 04:06:10 - INFO - codeparrot_training - Step 16657: {'lr': 0.00037672062710814025, 'samples': 8528896, 'steps': 16657, 'batch_loss/train': 0.734732729382813}
+12/25/2021 04:06:21 - INFO - codeparrot_training - Step 16658: {'lr': 0.0003767070387956932, 'samples': 8529408, 'steps': 16658, 'batch_loss/train': 0.7430945299565792}
+12/25/2021 04:06:32 - INFO - codeparrot_training - Step 16659: {'lr': 0.00037669344997950683, 'samples': 8529920, 'steps': 16659, 'batch_loss/train': 0.8033862560987473}
+12/25/2021 04:06:45 - INFO - codeparrot_training - Step 16660: {'lr': 0.00037667986065963524, 'samples': 8530432, 'steps': 16660, 'batch_loss/train': 0.8128122547641397}
+12/25/2021 04:06:55 - INFO - codeparrot_training - Step 16661: {'lr': 0.0003766662708361323, 'samples': 8530944, 'steps': 16661, 'batch_loss/train': 0.8029925227165222}
+12/25/2021 04:07:06 - INFO - codeparrot_training - Step 16662: {'lr': 0.000376652680509052, 'samples': 8531456, 'steps': 16662, 'batch_loss/train': 0.7580370707437396}
+12/25/2021 04:07:16 - INFO - codeparrot_training - Step 16663: {'lr': 0.0003766390896784485, 'samples': 8531968, 'steps': 16663, 'batch_loss/train': 0.5628888821229339}
+12/25/2021 04:07:29 - INFO - codeparrot_training - Step 16664: {'lr': 0.0003766254983443758, 'samples': 8532480, 'steps': 16664, 'batch_loss/train': 0.7270012283697724}
+12/25/2021 04:07:39 - INFO - codeparrot_training - Step 16665: {'lr': 0.00037661190650688795, 'samples': 8532992, 'steps': 16665, 'batch_loss/train': 0.6384776596678421}
+12/25/2021 04:07:50 - INFO - codeparrot_training - Step 16666: {'lr': 0.00037659831416603896, 'samples': 8533504, 'steps': 16666, 'batch_loss/train': 0.8827766422182322}
+12/25/2021 04:08:02 - INFO - codeparrot_training - Step 16667: {'lr': 0.00037658472132188293, 'samples': 8534016, 'steps': 16667, 'batch_loss/train': 0.8269816106185317}
+12/25/2021 04:08:12 - INFO - codeparrot_training - Step 16668: {'lr': 0.0003765711279744738, 'samples': 8534528, 'steps': 16668, 'batch_loss/train': 0.73791917366907}
+12/25/2021 04:08:23 - INFO - codeparrot_training - Step 16669: {'lr': 0.0003765575341238656, 'samples': 8535040, 'steps': 16669, 'batch_loss/train': 0.8481732900254428}
+12/25/2021 04:08:35 - INFO - codeparrot_training - Step 16670: {'lr': 0.00037654393977011255, 'samples': 8535552, 'steps': 16670, 'batch_loss/train': 0.8000491447746754}
+12/25/2021 04:08:46 - INFO - codeparrot_training - Step 16671: {'lr': 0.0003765303449132685, 'samples': 8536064, 'steps': 16671, 'batch_loss/train': 0.8287209486588836}
+12/25/2021 04:08:56 - INFO - codeparrot_training - Step 16672: {'lr': 0.00037651674955338754, 'samples': 8536576, 'steps': 16672, 'batch_loss/train': 0.7714840499684215}
+12/25/2021 04:09:10 - INFO - codeparrot_training - Step 16673: {'lr': 0.00037650315369052383, 'samples': 8537088, 'steps': 16673, 'batch_loss/train': 0.8203267510980368}
+12/25/2021 04:09:20 - INFO - codeparrot_training - Step 16674: {'lr': 0.0003764895573247313, 'samples': 8537600, 'steps': 16674, 'batch_loss/train': 0.6649383117910475}
+12/25/2021 04:09:31 - INFO - codeparrot_training - Step 16675: {'lr': 0.00037647596045606416, 'samples': 8538112, 'steps': 16675, 'batch_loss/train': 0.8307843180373311}
+12/25/2021 04:09:42 - INFO - codeparrot_training - Step 16676: {'lr': 0.00037646236308457623, 'samples': 8538624, 'steps': 16676, 'batch_loss/train': 0.8384478408843279}
+12/25/2021 04:09:56 - INFO - codeparrot_training - Step 16677: {'lr': 0.0003764487652103217, 'samples': 8539136, 'steps': 16677, 'batch_loss/train': 0.5985100935213268}
+12/25/2021 04:10:06 - INFO - codeparrot_training - Step 16678: {'lr': 0.00037643516683335464, 'samples': 8539648, 'steps': 16678, 'batch_loss/train': 0.7695278450846672}
+12/25/2021 04:10:17 - INFO - codeparrot_training - Step 16679: {'lr': 0.0003764215679537291, 'samples': 8540160, 'steps': 16679, 'batch_loss/train': 0.8905997835099697}
+12/25/2021 04:10:29 - INFO - codeparrot_training - Step 16680: {'lr': 0.00037640796857149914, 'samples': 8540672, 'steps': 16680, 'batch_loss/train': 0.8428367357701063}
+12/25/2021 04:10:40 - INFO - codeparrot_training - Step 16681: {'lr': 0.00037639436868671885, 'samples': 8541184, 'steps': 16681, 'batch_loss/train': 0.8353266492486}
+12/25/2021 04:10:50 - INFO - codeparrot_training - Step 16682: {'lr': 0.0003763807682994423, 'samples': 8541696, 'steps': 16682, 'batch_loss/train': 0.9855530862696469}
+12/25/2021 04:11:02 - INFO - codeparrot_training - Step 16683: {'lr': 0.00037636716740972346, 'samples': 8542208, 'steps': 16683, 'batch_loss/train': 0.7413860354572535}
+12/25/2021 04:11:13 - INFO - codeparrot_training - Step 16684: {'lr': 0.0003763535660176165, 'samples': 8542720, 'steps': 16684, 'batch_loss/train': 0.8318873876705766}
+12/25/2021 04:11:23 - INFO - codeparrot_training - Step 16685: {'lr': 0.0003763399641231755, 'samples': 8543232, 'steps': 16685, 'batch_loss/train': 0.7351667629554868}
+12/25/2021 04:11:34 - INFO - codeparrot_training - Step 16686: {'lr': 0.0003763263617264545, 'samples': 8543744, 'steps': 16686, 'batch_loss/train': 0.7680886490270495}
+12/25/2021 04:11:48 - INFO - codeparrot_training - Step 16687: {'lr': 0.00037631275882750757, 'samples': 8544256, 'steps': 16687, 'batch_loss/train': 0.8841645289212465}
+12/25/2021 04:11:59 - INFO - codeparrot_training - Step 16688: {'lr': 0.0003762991554263888, 'samples': 8544768, 'steps': 16688, 'batch_loss/train': 0.7944960384629667}
+12/25/2021 04:12:09 - INFO - codeparrot_training - Step 16689: {'lr': 0.00037628555152315236, 'samples': 8545280, 'steps': 16689, 'batch_loss/train': 0.7439304627478123}
+12/25/2021 04:12:21 - INFO - codeparrot_training - Step 16690: {'lr': 0.00037627194711785215, 'samples': 8545792, 'steps': 16690, 'batch_loss/train': 0.7636669613420963}
+12/25/2021 04:12:32 - INFO - codeparrot_training - Step 16691: {'lr': 0.0003762583422105423, 'samples': 8546304, 'steps': 16691, 'batch_loss/train': 0.810523965395987}
+12/25/2021 04:12:43 - INFO - codeparrot_training - Step 16692: {'lr': 0.00037624473680127713, 'samples': 8546816, 'steps': 16692, 'batch_loss/train': 0.7420337973162532}
+12/25/2021 04:12:56 - INFO - codeparrot_training - Step 16693: {'lr': 0.00037623113089011053, 'samples': 8547328, 'steps': 16693, 'batch_loss/train': 0.8775714319199324}
+12/25/2021 04:13:07 - INFO - codeparrot_training - Step 16694: {'lr': 0.00037621752447709644, 'samples': 8547840, 'steps': 16694, 'batch_loss/train': 0.7410791693255305}
+12/25/2021 04:13:17 - INFO - codeparrot_training - Step 16695: {'lr': 0.0003762039175622893, 'samples': 8548352, 'steps': 16695, 'batch_loss/train': 0.8371320944279432}
+12/25/2021 04:13:28 - INFO - codeparrot_training - Step 16696: {'lr': 0.00037619031014574295, 'samples': 8548864, 'steps': 16696, 'batch_loss/train': 0.8016345559153706}
+12/25/2021 04:13:40 - INFO - codeparrot_training - Step 16697: {'lr': 0.0003761767022275116, 'samples': 8549376, 'steps': 16697, 'batch_loss/train': 0.721653460059315}
+12/25/2021 04:13:51 - INFO - codeparrot_training - Step 16698: {'lr': 0.00037616309380764936, 'samples': 8549888, 'steps': 16698, 'batch_loss/train': 0.8414503233507276}
+12/25/2021 04:14:01 - INFO - codeparrot_training - Step 16699: {'lr': 0.0003761494848862103, 'samples': 8550400, 'steps': 16699, 'batch_loss/train': 0.7424035912845284}
+12/25/2021 04:14:13 - INFO - codeparrot_training - Step 16700: {'lr': 0.0003761358754632484, 'samples': 8550912, 'steps': 16700, 'batch_loss/train': 1.4238585326820612}
+12/25/2021 04:14:24 - INFO - codeparrot_training - Step 16701: {'lr': 0.000376122265538818, 'samples': 8551424, 'steps': 16701, 'batch_loss/train': 0.7585296733304858}
+12/25/2021 04:14:35 - INFO - codeparrot_training - Step 16702: {'lr': 0.0003761086551129731, 'samples': 8551936, 'steps': 16702, 'batch_loss/train': 0.8075391612946987}
+12/25/2021 04:14:48 - INFO - codeparrot_training - Step 16703: {'lr': 0.00037609504418576774, 'samples': 8552448, 'steps': 16703, 'batch_loss/train': 0.7992858774960041}
+12/25/2021 04:14:59 - INFO - codeparrot_training - Step 16704: {'lr': 0.00037608143275725614, 'samples': 8552960, 'steps': 16704, 'batch_loss/train': 0.7491212114691734}
+12/25/2021 04:15:10 - INFO - codeparrot_training - Step 16705: {'lr': 0.00037606782082749235, 'samples': 8553472, 'steps': 16705, 'batch_loss/train': 0.8708731951192021}
+12/25/2021 04:15:20 - INFO - codeparrot_training - Step 16706: {'lr': 0.0003760542083965305, 'samples': 8553984, 'steps': 16706, 'batch_loss/train': 0.7283955793827772}
+12/25/2021 04:15:33 - INFO - codeparrot_training - Step 16707: {'lr': 0.0003760405954644247, 'samples': 8554496, 'steps': 16707, 'batch_loss/train': 0.8372174296528101}
+12/25/2021 04:15:44 - INFO - codeparrot_training - Step 16708: {'lr': 0.00037602698203122913, 'samples': 8555008, 'steps': 16708, 'batch_loss/train': 0.8319190966431051}
+12/25/2021 04:15:55 - INFO - codeparrot_training - Step 16709: {'lr': 0.00037601336809699784, 'samples': 8555520, 'steps': 16709, 'batch_loss/train': 1.0880826972424984}
+12/25/2021 04:16:08 - INFO - codeparrot_training - Step 16710: {'lr': 0.00037599975366178496, 'samples': 8556032, 'steps': 16710, 'batch_loss/train': 0.7835386430379003}
+12/25/2021 04:16:19 - INFO - codeparrot_training - Step 16711: {'lr': 0.0003759861387256447, 'samples': 8556544, 'steps': 16711, 'batch_loss/train': 1.0227637367788702}
+12/25/2021 04:16:30 - INFO - codeparrot_training - Step 16712: {'lr': 0.0003759725232886311, 'samples': 8557056, 'steps': 16712, 'batch_loss/train': 0.7972689643502235}
+12/25/2021 04:16:40 - INFO - codeparrot_training - Step 16713: {'lr': 0.00037595890735079825, 'samples': 8557568, 'steps': 16713, 'batch_loss/train': 0.8617054848000407}
+12/25/2021 04:16:53 - INFO - codeparrot_training - Step 16714: {'lr': 0.00037594529091220034, 'samples': 8558080, 'steps': 16714, 'batch_loss/train': 0.80406145285815}
+12/25/2021 04:17:03 - INFO - codeparrot_training - Step 16715: {'lr': 0.00037593167397289163, 'samples': 8558592, 'steps': 16715, 'batch_loss/train': 0.6784041188657284}
+12/25/2021 04:17:14 - INFO - codeparrot_training - Step 16716: {'lr': 0.00037591805653292606, 'samples': 8559104, 'steps': 16716, 'batch_loss/train': 0.691033324226737}
+12/25/2021 04:17:26 - INFO - codeparrot_training - Step 16717: {'lr': 0.0003759044385923578, 'samples': 8559616, 'steps': 16717, 'batch_loss/train': 0.7961978958919644}
+12/25/2021 04:17:37 - INFO - codeparrot_training - Step 16718: {'lr': 0.0003758908201512411, 'samples': 8560128, 'steps': 16718, 'batch_loss/train': 0.8703258624300361}
+12/25/2021 04:17:47 - INFO - codeparrot_training - Step 16719: {'lr': 0.00037587720120963006, 'samples': 8560640, 'steps': 16719, 'batch_loss/train': 0.7380960467271507}
+12/25/2021 04:17:59 - INFO - codeparrot_training - Step 16720: {'lr': 0.00037586358176757865, 'samples': 8561152, 'steps': 16720, 'batch_loss/train': 0.920890144072473}
+12/25/2021 04:18:10 - INFO - codeparrot_training - Step 16721: {'lr': 0.00037584996182514133, 'samples': 8561664, 'steps': 16721, 'batch_loss/train': 1.04406201466918}
+12/25/2021 04:18:20 - INFO - codeparrot_training - Step 16722: {'lr': 0.00037583634138237197, 'samples': 8562176, 'steps': 16722, 'batch_loss/train': 0.7928624846972525}
+12/25/2021 04:18:31 - INFO - codeparrot_training - Step 16723: {'lr': 0.00037582272043932484, 'samples': 8562688, 'steps': 16723, 'batch_loss/train': 0.7397365440847352}
+12/25/2021 04:18:45 - INFO - codeparrot_training - Step 16724: {'lr': 0.00037580909899605414, 'samples': 8563200, 'steps': 16724, 'batch_loss/train': 0.6649538045749068}
+12/25/2021 04:18:56 - INFO - codeparrot_training - Step 16725: {'lr': 0.00037579547705261394, 'samples': 8563712, 'steps': 16725, 'batch_loss/train': 0.8215033332817256}
+12/25/2021 04:19:07 - INFO - codeparrot_training - Step 16726: {'lr': 0.00037578185460905843, 'samples': 8564224, 'steps': 16726, 'batch_loss/train': 0.8163546514697373}
+12/25/2021 04:19:19 - INFO - codeparrot_training - Step 16727: {'lr': 0.0003757682316654417, 'samples': 8564736, 'steps': 16727, 'batch_loss/train': 0.8572987858206034}
+12/25/2021 04:19:29 - INFO - codeparrot_training - Step 16728: {'lr': 0.0003757546082218181, 'samples': 8565248, 'steps': 16728, 'batch_loss/train': 0.8037804765626788}
+12/25/2021 04:19:40 - INFO - codeparrot_training - Step 16729: {'lr': 0.00037574098427824154, 'samples': 8565760, 'steps': 16729, 'batch_loss/train': 0.8352682497352362}
+12/25/2021 04:19:52 - INFO - codeparrot_training - Step 16730: {'lr': 0.0003757273598347664, 'samples': 8566272, 'steps': 16730, 'batch_loss/train': 0.8697860867250711}
+12/25/2021 04:20:02 - INFO - codeparrot_training - Step 16731: {'lr': 0.00037571373489144665, 'samples': 8566784, 'steps': 16731, 'batch_loss/train': 0.8067708157468587}
+12/25/2021 04:20:13 - INFO - codeparrot_training - Step 16732: {'lr': 0.00037570010944833665, 'samples': 8567296, 'steps': 16732, 'batch_loss/train': 0.8181959111243486}
+12/25/2021 04:20:24 - INFO - codeparrot_training - Step 16733: {'lr': 0.0003756864835054904, 'samples': 8567808, 'steps': 16733, 'batch_loss/train': 0.7223282610066235}
+12/25/2021 04:20:38 - INFO - codeparrot_training - Step 16734: {'lr': 0.0003756728570629622, 'samples': 8568320, 'steps': 16734, 'batch_loss/train': 0.854135949164629}
+12/25/2021 04:20:48 - INFO - codeparrot_training - Step 16735: {'lr': 0.0003756592301208062, 'samples': 8568832, 'steps': 16735, 'batch_loss/train': 0.867919348180294}
+12/25/2021 04:20:59 - INFO - codeparrot_training - Step 16736: {'lr': 0.00037564560267907643, 'samples': 8569344, 'steps': 16736, 'batch_loss/train': 0.8571986358147115}
+12/25/2021 04:21:11 - INFO - codeparrot_training - Step 16737: {'lr': 0.0003756319747378272, 'samples': 8569856, 'steps': 16737, 'batch_loss/train': 1.0261741261929274}
+12/25/2021 04:21:22 - INFO - codeparrot_training - Step 16738: {'lr': 0.00037561834629711277, 'samples': 8570368, 'steps': 16738, 'batch_loss/train': 0.8690635357052088}
+12/25/2021 04:21:32 - INFO - codeparrot_training - Step 16739: {'lr': 0.0003756047173569872, 'samples': 8570880, 'steps': 16739, 'batch_loss/train': 1.0075305809732527}
+12/25/2021 04:21:46 - INFO - codeparrot_training - Step 16740: {'lr': 0.00037559108791750465, 'samples': 8571392, 'steps': 16740, 'batch_loss/train': 0.8820587508380413}
+12/25/2021 04:21:57 - INFO - codeparrot_training - Step 16741: {'lr': 0.00037557745797871944, 'samples': 8571904, 'steps': 16741, 'batch_loss/train': 0.922706002369523}
+12/25/2021 04:22:07 - INFO - codeparrot_training - Step 16742: {'lr': 0.00037556382754068564, 'samples': 8572416, 'steps': 16742, 'batch_loss/train': 0.7966108587570488}
+12/25/2021 04:22:18 - INFO - codeparrot_training - Step 16743: {'lr': 0.00037555019660345747, 'samples': 8572928, 'steps': 16743, 'batch_loss/train': 0.7386943942401558}
+12/25/2021 04:22:30 - INFO - codeparrot_training - Step 16744: {'lr': 0.00037553656516708906, 'samples': 8573440, 'steps': 16744, 'batch_loss/train': 0.8106554327532649}
+12/25/2021 04:22:40 - INFO - codeparrot_training - Step 16745: {'lr': 0.0003755229332316347, 'samples': 8573952, 'steps': 16745, 'batch_loss/train': 1.6150413770228624}
+12/25/2021 04:22:51 - INFO - codeparrot_training - Step 16746: {'lr': 0.0003755093007971486, 'samples': 8574464, 'steps': 16746, 'batch_loss/train': 0.750589590985328}
+12/25/2021 04:23:03 - INFO - codeparrot_training - Step 16747: {'lr': 0.0003754956678636849, 'samples': 8574976, 'steps': 16747, 'batch_loss/train': 0.9121319097466767}
+12/25/2021 04:23:14 - INFO - codeparrot_training - Step 16748: {'lr': 0.0003754820344312978, 'samples': 8575488, 'steps': 16748, 'batch_loss/train': 1.5113547146320343}
+12/25/2021 04:23:24 - INFO - codeparrot_training - Step 16749: {'lr': 0.0003754684005000415, 'samples': 8576000, 'steps': 16749, 'batch_loss/train': 0.8710870193317533}
+12/25/2021 04:23:38 - INFO - codeparrot_training - Step 16750: {'lr': 0.0003754547660699702, 'samples': 8576512, 'steps': 16750, 'batch_loss/train': 0.8505454044789076}
+12/25/2021 04:23:49 - INFO - codeparrot_training - Step 16751: {'lr': 0.0003754411311411381, 'samples': 8577024, 'steps': 16751, 'batch_loss/train': 0.80067571811378}
+12/25/2021 04:23:59 - INFO - codeparrot_training - Step 16752: {'lr': 0.00037542749571359946, 'samples': 8577536, 'steps': 16752, 'batch_loss/train': 0.7034958554431796}
+12/25/2021 04:24:10 - INFO - codeparrot_training - Step 16753: {'lr': 0.0003754138597874085, 'samples': 8578048, 'steps': 16753, 'batch_loss/train': 0.7743125660344958}
+12/25/2021 04:24:22 - INFO - codeparrot_training - Step 16754: {'lr': 0.0003754002233626194, 'samples': 8578560, 'steps': 16754, 'batch_loss/train': 0.7833639597520232}
+12/25/2021 04:24:33 - INFO - codeparrot_training - Step 16755: {'lr': 0.00037538658643928625, 'samples': 8579072, 'steps': 16755, 'batch_loss/train': 0.7990532154217362}
+12/25/2021 04:24:44 - INFO - codeparrot_training - Step 16756: {'lr': 0.0003753729490174634, 'samples': 8579584, 'steps': 16756, 'batch_loss/train': 0.7921490548178554}
+12/25/2021 04:24:55 - INFO - codeparrot_training - Step 16757: {'lr': 0.0003753593110972051, 'samples': 8580096, 'steps': 16757, 'batch_loss/train': 0.9167395504191518}
+12/25/2021 04:25:06 - INFO - codeparrot_training - Step 16758: {'lr': 0.00037534567267856554, 'samples': 8580608, 'steps': 16758, 'batch_loss/train': 0.749888158403337}
+12/25/2021 04:25:17 - INFO - codeparrot_training - Step 16759: {'lr': 0.00037533203376159885, 'samples': 8581120, 'steps': 16759, 'batch_loss/train': 0.8290657559409738}
+12/25/2021 04:25:31 - INFO - codeparrot_training - Step 16760: {'lr': 0.0003753183943463594, 'samples': 8581632, 'steps': 16760, 'batch_loss/train': 0.8132038963958621}
+12/25/2021 04:25:41 - INFO - codeparrot_training - Step 16761: {'lr': 0.00037530475443290127, 'samples': 8582144, 'steps': 16761, 'batch_loss/train': 0.8011262258514762}
+12/25/2021 04:25:52 - INFO - codeparrot_training - Step 16762: {'lr': 0.0003752911140212787, 'samples': 8582656, 'steps': 16762, 'batch_loss/train': 0.9268913585692644}
+12/25/2021 04:26:02 - INFO - codeparrot_training - Step 16763: {'lr': 0.000375277473111546, 'samples': 8583168, 'steps': 16763, 'batch_loss/train': 0.8020074982196093}
+12/25/2021 04:26:15 - INFO - codeparrot_training - Step 16764: {'lr': 0.00037526383170375743, 'samples': 8583680, 'steps': 16764, 'batch_loss/train': 0.7643739888444543}
+12/25/2021 04:26:25 - INFO - codeparrot_training - Step 16765: {'lr': 0.0003752501897979671, 'samples': 8584192, 'steps': 16765, 'batch_loss/train': 0.88400295143947}
+12/25/2021 04:26:36 - INFO - codeparrot_training - Step 16766: {'lr': 0.0003752365473942293, 'samples': 8584704, 'steps': 16766, 'batch_loss/train': 0.8554494008421898}
+12/25/2021 04:26:48 - INFO - codeparrot_training - Step 16767: {'lr': 0.0003752229044925983, 'samples': 8585216, 'steps': 16767, 'batch_loss/train': 0.8141784938052297}
+12/25/2021 04:26:58 - INFO - codeparrot_training - Step 16768: {'lr': 0.00037520926109312834, 'samples': 8585728, 'steps': 16768, 'batch_loss/train': 0.7900130702182651}
+12/25/2021 04:27:09 - INFO - codeparrot_training - Step 16769: {'lr': 0.00037519561719587366, 'samples': 8586240, 'steps': 16769, 'batch_loss/train': 0.7626943355426192}
+12/25/2021 04:27:23 - INFO - codeparrot_training - Step 16770: {'lr': 0.0003751819728008884, 'samples': 8586752, 'steps': 16770, 'batch_loss/train': 0.7388465732801706}
+12/25/2021 04:27:34 - INFO - codeparrot_training - Step 16771: {'lr': 0.00037516832790822694, 'samples': 8587264, 'steps': 16771, 'batch_loss/train': 0.7580350628122687}
+12/25/2021 04:27:44 - INFO - codeparrot_training - Step 16772: {'lr': 0.00037515468251794336, 'samples': 8587776, 'steps': 16772, 'batch_loss/train': 0.7898198114708066}
+12/25/2021 04:27:55 - INFO - codeparrot_training - Step 16773: {'lr': 0.0003751410366300922, 'samples': 8588288, 'steps': 16773, 'batch_loss/train': 0.790811381302774}
+12/25/2021 04:28:07 - INFO - codeparrot_training - Step 16774: {'lr': 0.00037512739024472743, 'samples': 8588800, 'steps': 16774, 'batch_loss/train': 0.720656436868012}
+12/25/2021 04:28:17 - INFO - codeparrot_training - Step 16775: {'lr': 0.0003751137433619034, 'samples': 8589312, 'steps': 16775, 'batch_loss/train': 0.8315798453986645}
+12/25/2021 04:28:28 - INFO - codeparrot_training - Step 16776: {'lr': 0.0003751000959816744, 'samples': 8589824, 'steps': 16776, 'batch_loss/train': 0.7864353025797755}
+12/25/2021 04:28:40 - INFO - codeparrot_training - Step 16777: {'lr': 0.0003750864481040946, 'samples': 8590336, 'steps': 16777, 'batch_loss/train': 0.7324558054096997}
+12/25/2021 04:28:51 - INFO - codeparrot_training - Step 16778: {'lr': 0.00037507279972921834, 'samples': 8590848, 'steps': 16778, 'batch_loss/train': 0.7810623636469245}
+12/25/2021 04:29:02 - INFO - codeparrot_training - Step 16779: {'lr': 0.00037505915085709983, 'samples': 8591360, 'steps': 16779, 'batch_loss/train': 0.8001713114790618}
+12/25/2021 04:29:15 - INFO - codeparrot_training - Step 16780: {'lr': 0.00037504550148779336, 'samples': 8591872, 'steps': 16780, 'batch_loss/train': 0.7363702841103077}
+12/25/2021 04:29:26 - INFO - codeparrot_training - Step 16781: {'lr': 0.00037503185162135325, 'samples': 8592384, 'steps': 16781, 'batch_loss/train': 0.7494247816503048}
+12/25/2021 04:29:36 - INFO - codeparrot_training - Step 16782: {'lr': 0.0003750182012578337, 'samples': 8592896, 'steps': 16782, 'batch_loss/train': 0.8237836356274784}
+12/25/2021 04:29:47 - INFO - codeparrot_training - Step 16783: {'lr': 0.0003750045503972889, 'samples': 8593408, 'steps': 16783, 'batch_loss/train': 0.8554332396015525}
+12/25/2021 04:29:59 - INFO - codeparrot_training - Step 16784: {'lr': 0.0003749908990397733, 'samples': 8593920, 'steps': 16784, 'batch_loss/train': 0.7756406227126718}
+12/25/2021 04:30:10 - INFO - codeparrot_training - Step 16785: {'lr': 0.00037497724718534096, 'samples': 8594432, 'steps': 16785, 'batch_loss/train': 0.7669764935271814}
+12/25/2021 04:30:20 - INFO - codeparrot_training - Step 16786: {'lr': 0.00037496359483404646, 'samples': 8594944, 'steps': 16786, 'batch_loss/train': 0.8374728402122855}
+12/25/2021 04:30:33 - INFO - codeparrot_training - Step 16787: {'lr': 0.0003749499419859438, 'samples': 8595456, 'steps': 16787, 'batch_loss/train': 0.9900995716452599}
+12/25/2021 04:30:43 - INFO - codeparrot_training - Step 16788: {'lr': 0.00037493628864108724, 'samples': 8595968, 'steps': 16788, 'batch_loss/train': 0.80385383637622}
+12/25/2021 04:30:54 - INFO - codeparrot_training - Step 16789: {'lr': 0.0003749226347995314, 'samples': 8596480, 'steps': 16789, 'batch_loss/train': 0.7412880454212427}
+12/25/2021 04:31:07 - INFO - codeparrot_training - Step 16790: {'lr': 0.00037490898046133015, 'samples': 8596992, 'steps': 16790, 'batch_loss/train': 0.7800582079216838}
+12/25/2021 04:31:18 - INFO - codeparrot_training - Step 16791: {'lr': 0.000374895325626538, 'samples': 8597504, 'steps': 16791, 'batch_loss/train': 0.8001766074448824}
+12/25/2021 04:31:29 - INFO - codeparrot_training - Step 16792: {'lr': 0.0003748816702952092, 'samples': 8598016, 'steps': 16792, 'batch_loss/train': 0.7999563883058727}
+12/25/2021 04:31:39 - INFO - codeparrot_training - Step 16793: {'lr': 0.000374868014467398, 'samples': 8598528, 'steps': 16793, 'batch_loss/train': 0.7717184991342947}
+12/25/2021 04:31:51 - INFO - codeparrot_training - Step 16794: {'lr': 0.0003748543581431588, 'samples': 8599040, 'steps': 16794, 'batch_loss/train': 0.8096832735463977}
+12/25/2021 04:32:02 - INFO - codeparrot_training - Step 16795: {'lr': 0.00037484070132254576, 'samples': 8599552, 'steps': 16795, 'batch_loss/train': 0.9273629480740055}
+12/25/2021 04:32:12 - INFO - codeparrot_training - Step 16796: {'lr': 0.0003748270440056133, 'samples': 8600064, 'steps': 16796, 'batch_loss/train': 0.7405969118699431}
+12/25/2021 04:32:25 - INFO - codeparrot_training - Step 16797: {'lr': 0.00037481338619241555, 'samples': 8600576, 'steps': 16797, 'batch_loss/train': 0.8248808346688747}
+12/25/2021 04:32:35 - INFO - codeparrot_training - Step 16798: {'lr': 0.000374799727883007, 'samples': 8601088, 'steps': 16798, 'batch_loss/train': 0.7495758039876819}
+12/25/2021 04:32:46 - INFO - codeparrot_training - Step 16799: {'lr': 0.0003747860690774418, 'samples': 8601600, 'steps': 16799, 'batch_loss/train': 0.7080374551005661}
+12/25/2021 04:32:58 - INFO - codeparrot_training - Step 16800: {'lr': 0.0003747724097757743, 'samples': 8602112, 'steps': 16800, 'batch_loss/train': 0.7591205672360957}
+12/25/2021 04:33:09 - INFO - codeparrot_training - Step 16801: {'lr': 0.00037475874997805876, 'samples': 8602624, 'steps': 16801, 'batch_loss/train': 0.6869521522894502}
+12/25/2021 04:33:19 - INFO - codeparrot_training - Step 16802: {'lr': 0.00037474508968434963, 'samples': 8603136, 'steps': 16802, 'batch_loss/train': 0.8975872443988919}
+12/25/2021 04:33:30 - INFO - codeparrot_training - Step 16803: {'lr': 0.00037473142889470106, 'samples': 8603648, 'steps': 16803, 'batch_loss/train': 0.7286734813824296}
+12/25/2021 04:33:44 - INFO - codeparrot_training - Step 16804: {'lr': 0.00037471776760916747, 'samples': 8604160, 'steps': 16804, 'batch_loss/train': 0.844454251229763}
+12/25/2021 04:33:54 - INFO - codeparrot_training - Step 16805: {'lr': 0.00037470410582780313, 'samples': 8604672, 'steps': 16805, 'batch_loss/train': 0.8757756883278489}
+12/25/2021 04:34:05 - INFO - codeparrot_training - Step 16806: {'lr': 0.0003746904435506624, 'samples': 8605184, 'steps': 16806, 'batch_loss/train': 0.7178453872911632}
+12/25/2021 04:34:17 - INFO - codeparrot_training - Step 16807: {'lr': 0.00037467678077779935, 'samples': 8605696, 'steps': 16807, 'batch_loss/train': 0.8316476369509473}
+12/25/2021 04:34:28 - INFO - codeparrot_training - Step 16808: {'lr': 0.0003746631175092687, 'samples': 8606208, 'steps': 16808, 'batch_loss/train': 0.8450525214429945}
+12/25/2021 04:34:38 - INFO - codeparrot_training - Step 16809: {'lr': 0.0003746494537451245, 'samples': 8606720, 'steps': 16809, 'batch_loss/train': 1.079945339821279}
+12/25/2021 04:34:53 - INFO - codeparrot_training - Step 16810: {'lr': 0.0003746357894854211, 'samples': 8607232, 'steps': 16810, 'batch_loss/train': 0.7586823347955942}
+12/25/2021 04:35:03 - INFO - codeparrot_training - Step 16811: {'lr': 0.0003746221247302129, 'samples': 8607744, 'steps': 16811, 'batch_loss/train': 0.8975166026502848}
+12/25/2021 04:35:14 - INFO - codeparrot_training - Step 16812: {'lr': 0.00037460845947955425, 'samples': 8608256, 'steps': 16812, 'batch_loss/train': 0.8366717818425968}
+12/25/2021 04:35:24 - INFO - codeparrot_training - Step 16813: {'lr': 0.00037459479373349924, 'samples': 8608768, 'steps': 16813, 'batch_loss/train': 0.9382120068185031}
+12/25/2021 04:35:37 - INFO - codeparrot_training - Step 16814: {'lr': 0.0003745811274921025, 'samples': 8609280, 'steps': 16814, 'batch_loss/train': 0.8180460128933191}
+12/25/2021 04:35:47 - INFO - codeparrot_training - Step 16815: {'lr': 0.00037456746075541827, 'samples': 8609792, 'steps': 16815, 'batch_loss/train': 0.7871474418789148}
+12/25/2021 04:35:58 - INFO - codeparrot_training - Step 16816: {'lr': 0.00037455379352350083, 'samples': 8610304, 'steps': 16816, 'batch_loss/train': 1.0414102021604776}
+12/25/2021 04:36:10 - INFO - codeparrot_training - Step 16817: {'lr': 0.00037454012579640446, 'samples': 8610816, 'steps': 16817, 'batch_loss/train': 0.8451581979170442}
+12/25/2021 04:36:20 - INFO - codeparrot_training - Step 16818: {'lr': 0.00037452645757418365, 'samples': 8611328, 'steps': 16818, 'batch_loss/train': 0.815602975897491}
+12/25/2021 04:36:31 - INFO - codeparrot_training - Step 16819: {'lr': 0.00037451278885689265, 'samples': 8611840, 'steps': 16819, 'batch_loss/train': 0.7941820891574025}
+12/25/2021 04:36:45 - INFO - codeparrot_training - Step 16820: {'lr': 0.0003744991196445857, 'samples': 8612352, 'steps': 16820, 'batch_loss/train': 0.8423488661646843}
+12/25/2021 04:36:55 - INFO - codeparrot_training - Step 16821: {'lr': 0.00037448544993731747, 'samples': 8612864, 'steps': 16821, 'batch_loss/train': 0.8763151094317436}
+12/25/2021 04:37:06 - INFO - codeparrot_training - Step 16822: {'lr': 0.000374471779735142, 'samples': 8613376, 'steps': 16822, 'batch_loss/train': 1.2840434511890635}
+12/25/2021 04:37:17 - INFO - codeparrot_training - Step 16823: {'lr': 0.00037445810903811365, 'samples': 8613888, 'steps': 16823, 'batch_loss/train': 0.9142883643507957}
+12/25/2021 04:37:29 - INFO - codeparrot_training - Step 16824: {'lr': 0.0003744444378462869, 'samples': 8614400, 'steps': 16824, 'batch_loss/train': 0.9053923459723592}
+12/25/2021 04:37:39 - INFO - codeparrot_training - Step 16825: {'lr': 0.0003744307661597161, 'samples': 8614912, 'steps': 16825, 'batch_loss/train': 0.7743001570925117}
+12/25/2021 04:37:50 - INFO - codeparrot_training - Step 16826: {'lr': 0.00037441709397845554, 'samples': 8615424, 'steps': 16826, 'batch_loss/train': 0.7293683758471161}
+12/25/2021 04:38:04 - INFO - codeparrot_training - Step 16827: {'lr': 0.00037440342130255956, 'samples': 8615936, 'steps': 16827, 'batch_loss/train': 0.8242256743833423}
+12/25/2021 04:38:14 - INFO - codeparrot_training - Step 16828: {'lr': 0.0003743897481320826, 'samples': 8616448, 'steps': 16828, 'batch_loss/train': 0.8289335928857327}
+12/25/2021 04:38:25 - INFO - codeparrot_training - Step 16829: {'lr': 0.00037437607446707893, 'samples': 8616960, 'steps': 16829, 'batch_loss/train': 0.9635726604610682}
+12/25/2021 04:38:37 - INFO - codeparrot_training - Step 16830: {'lr': 0.000374362400307603, 'samples': 8617472, 'steps': 16830, 'batch_loss/train': 0.8408830380067229}
+12/25/2021 04:38:48 - INFO - codeparrot_training - Step 16831: {'lr': 0.00037434872565370904, 'samples': 8617984, 'steps': 16831, 'batch_loss/train': 0.851435306482017}
+12/25/2021 04:38:58 - INFO - codeparrot_training - Step 16832: {'lr': 0.0003743350505054516, 'samples': 8618496, 'steps': 16832, 'batch_loss/train': 0.8041081479750574}
+12/25/2021 04:39:09 - INFO - codeparrot_training - Step 16833: {'lr': 0.00037432137486288487, 'samples': 8619008, 'steps': 16833, 'batch_loss/train': 0.7768758498132229}
+12/25/2021 04:39:21 - INFO - codeparrot_training - Step 16834: {'lr': 0.0003743076987260633, 'samples': 8619520, 'steps': 16834, 'batch_loss/train': 0.7301510344259441}
+12/25/2021 04:39:31 - INFO - codeparrot_training - Step 16835: {'lr': 0.00037429402209504124, 'samples': 8620032, 'steps': 16835, 'batch_loss/train': 0.8032632139511406}
+12/25/2021 04:39:42 - INFO - codeparrot_training - Step 16836: {'lr': 0.0003742803449698732, 'samples': 8620544, 'steps': 16836, 'batch_loss/train': 0.8658873476088047}
+12/25/2021 04:39:54 - INFO - codeparrot_training - Step 16837: {'lr': 0.0003742666673506133, 'samples': 8621056, 'steps': 16837, 'batch_loss/train': 0.8268053364008665}
+12/25/2021 04:40:05 - INFO - codeparrot_training - Step 16838: {'lr': 0.0003742529892373161, 'samples': 8621568, 'steps': 16838, 'batch_loss/train': 0.8435197463259101}
+12/25/2021 04:40:15 - INFO - codeparrot_training - Step 16839: {'lr': 0.0003742393106300359, 'samples': 8622080, 'steps': 16839, 'batch_loss/train': 0.8032750058919191}
+12/25/2021 04:40:28 - INFO - codeparrot_training - Step 16840: {'lr': 0.0003742256315288272, 'samples': 8622592, 'steps': 16840, 'batch_loss/train': 0.8487167488783598}
+12/25/2021 04:40:39 - INFO - codeparrot_training - Step 16841: {'lr': 0.00037421195193374423, 'samples': 8623104, 'steps': 16841, 'batch_loss/train': 0.8966254452243447}
+12/25/2021 04:40:49 - INFO - codeparrot_training - Step 16842: {'lr': 0.00037419827184484146, 'samples': 8623616, 'steps': 16842, 'batch_loss/train': 0.757526075351052}
+12/25/2021 04:41:00 - INFO - codeparrot_training - Step 16843: {'lr': 0.0003741845912621732, 'samples': 8624128, 'steps': 16843, 'batch_loss/train': 0.8758406322449446}
+12/25/2021 04:41:12 - INFO - codeparrot_training - Step 16844: {'lr': 0.000374170910185794, 'samples': 8624640, 'steps': 16844, 'batch_loss/train': 0.9332855828106403}
+12/25/2021 04:41:23 - INFO - codeparrot_training - Step 16845: {'lr': 0.00037415722861575807, 'samples': 8625152, 'steps': 16845, 'batch_loss/train': 0.8676942409947515}
+12/25/2021 04:41:33 - INFO - codeparrot_training - Step 16846: {'lr': 0.00037414354655211987, 'samples': 8625664, 'steps': 16846, 'batch_loss/train': 0.8006712384521961}
+12/25/2021 04:41:45 - INFO - codeparrot_training - Step 16847: {'lr': 0.0003741298639949339, 'samples': 8626176, 'steps': 16847, 'batch_loss/train': 0.8401034455746412}
+12/25/2021 04:41:56 - INFO - codeparrot_training - Step 16848: {'lr': 0.00037411618094425434, 'samples': 8626688, 'steps': 16848, 'batch_loss/train': 0.765834906604141}
+12/25/2021 04:42:07 - INFO - codeparrot_training - Step 16849: {'lr': 0.00037410249740013575, 'samples': 8627200, 'steps': 16849, 'batch_loss/train': 0.7458612332120538}
+12/25/2021 04:42:19 - INFO - codeparrot_training - Step 16850: {'lr': 0.00037408881336263247, 'samples': 8627712, 'steps': 16850, 'batch_loss/train': 0.7210748337674886}
+12/25/2021 04:42:30 - INFO - codeparrot_training - Step 16851: {'lr': 0.00037407512883179893, 'samples': 8628224, 'steps': 16851, 'batch_loss/train': 0.8079910955857486}
+12/25/2021 04:42:41 - INFO - codeparrot_training - Step 16852: {'lr': 0.00037406144380768957, 'samples': 8628736, 'steps': 16852, 'batch_loss/train': 0.7502630657982081}
+12/25/2021 04:42:51 - INFO - codeparrot_training - Step 16853: {'lr': 0.0003740477582903587, 'samples': 8629248, 'steps': 16853, 'batch_loss/train': 0.8051105607300997}
+12/25/2021 04:43:03 - INFO - codeparrot_training - Step 16854: {'lr': 0.00037403407227986084, 'samples': 8629760, 'steps': 16854, 'batch_loss/train': 0.7492449590936303}
+12/25/2021 04:43:14 - INFO - codeparrot_training - Step 16855: {'lr': 0.00037402038577625033, 'samples': 8630272, 'steps': 16855, 'batch_loss/train': 0.7248593939002603}
+12/25/2021 04:43:24 - INFO - codeparrot_training - Step 16856: {'lr': 0.0003740066987795816, 'samples': 8630784, 'steps': 16856, 'batch_loss/train': 0.8419830687344074}
+12/25/2021 04:43:37 - INFO - codeparrot_training - Step 16857: {'lr': 0.00037399301128990904, 'samples': 8631296, 'steps': 16857, 'batch_loss/train': 1.2562970221042633}
+12/25/2021 04:43:48 - INFO - codeparrot_training - Step 16858: {'lr': 0.000373979323307287, 'samples': 8631808, 'steps': 16858, 'batch_loss/train': 0.9367145309224725}
+12/25/2021 04:43:59 - INFO - codeparrot_training - Step 16859: {'lr': 0.0003739656348317701, 'samples': 8632320, 'steps': 16859, 'batch_loss/train': 0.8665110496804118}
+12/25/2021 04:44:11 - INFO - codeparrot_training - Step 16860: {'lr': 0.00037395194586341263, 'samples': 8632832, 'steps': 16860, 'batch_loss/train': 0.7645210912451148}
+12/25/2021 04:44:21 - INFO - codeparrot_training - Step 16861: {'lr': 0.00037393825640226903, 'samples': 8633344, 'steps': 16861, 'batch_loss/train': 0.8444813657552004}
+12/25/2021 04:44:32 - INFO - codeparrot_training - Step 16862: {'lr': 0.0003739245664483936, 'samples': 8633856, 'steps': 16862, 'batch_loss/train': 0.7573119085282087}
+12/25/2021 04:44:42 - INFO - codeparrot_training - Step 16863: {'lr': 0.00037391087600184103, 'samples': 8634368, 'steps': 16863, 'batch_loss/train': 0.852228369563818}
+12/25/2021 04:44:55 - INFO - codeparrot_training - Step 16864: {'lr': 0.0003738971850626656, 'samples': 8634880, 'steps': 16864, 'batch_loss/train': 0.7812547390349209}
+12/25/2021 04:45:05 - INFO - codeparrot_training - Step 16865: {'lr': 0.00037388349363092166, 'samples': 8635392, 'steps': 16865, 'batch_loss/train': 0.7754620788618922}
+12/25/2021 04:45:16 - INFO - codeparrot_training - Step 16866: {'lr': 0.0003738698017066637, 'samples': 8635904, 'steps': 16866, 'batch_loss/train': 0.8738084305077791}
+12/25/2021 04:45:29 - INFO - codeparrot_training - Step 16867: {'lr': 0.00037385610928994633, 'samples': 8636416, 'steps': 16867, 'batch_loss/train': 0.7871058732271194}
+12/25/2021 04:45:39 - INFO - codeparrot_training - Step 16868: {'lr': 0.00037384241638082374, 'samples': 8636928, 'steps': 16868, 'batch_loss/train': 1.4962820969522}
+12/25/2021 04:45:50 - INFO - codeparrot_training - Step 16869: {'lr': 0.0003738287229793504, 'samples': 8637440, 'steps': 16869, 'batch_loss/train': 0.9379601497203112}
+12/25/2021 04:46:02 - INFO - codeparrot_training - Step 16870: {'lr': 0.00037381502908558095, 'samples': 8637952, 'steps': 16870, 'batch_loss/train': 0.9421974755823612}
+12/25/2021 04:46:13 - INFO - codeparrot_training - Step 16871: {'lr': 0.0003738013346995696, 'samples': 8638464, 'steps': 16871, 'batch_loss/train': 0.853887845762074}
+12/25/2021 04:46:23 - INFO - codeparrot_training - Step 16872: {'lr': 0.00037378763982137095, 'samples': 8638976, 'steps': 16872, 'batch_loss/train': 0.8635143684223294}
+12/25/2021 04:46:34 - INFO - codeparrot_training - Step 16873: {'lr': 0.0003737739444510394, 'samples': 8639488, 'steps': 16873, 'batch_loss/train': 0.8265854506753385}
+12/25/2021 04:46:47 - INFO - codeparrot_training - Step 16874: {'lr': 0.00037376024858862934, 'samples': 8640000, 'steps': 16874, 'batch_loss/train': 0.8448872733861208}
+12/25/2021 04:46:57 - INFO - codeparrot_training - Step 16875: {'lr': 0.00037374655223419516, 'samples': 8640512, 'steps': 16875, 'batch_loss/train': 0.793537843041122}
+12/25/2021 04:47:08 - INFO - codeparrot_training - Step 16876: {'lr': 0.00037373285538779157, 'samples': 8641024, 'steps': 16876, 'batch_loss/train': 0.7814443272072822}
+12/25/2021 04:47:20 - INFO - codeparrot_training - Step 16877: {'lr': 0.0003737191580494728, 'samples': 8641536, 'steps': 16877, 'batch_loss/train': 0.8900720013771206}
+12/25/2021 04:47:31 - INFO - codeparrot_training - Step 16878: {'lr': 0.00037370546021929334, 'samples': 8642048, 'steps': 16878, 'batch_loss/train': 0.830570001155138}
+12/25/2021 04:47:41 - INFO - codeparrot_training - Step 16879: {'lr': 0.0003736917618973078, 'samples': 8642560, 'steps': 16879, 'batch_loss/train': 0.7548836001660675}
+12/25/2021 04:47:53 - INFO - codeparrot_training - Step 16880: {'lr': 0.00037367806308357044, 'samples': 8643072, 'steps': 16880, 'batch_loss/train': 0.8298603799194098}
+12/25/2021 04:48:04 - INFO - codeparrot_training - Step 16881: {'lr': 0.0003736643637781357, 'samples': 8643584, 'steps': 16881, 'batch_loss/train': 0.7812337651848793}
+12/25/2021 04:48:14 - INFO - codeparrot_training - Step 16882: {'lr': 0.0003736506639810583, 'samples': 8644096, 'steps': 16882, 'batch_loss/train': 0.7866130210459232}
+12/25/2021 04:48:25 - INFO - codeparrot_training - Step 16883: {'lr': 0.00037363696369239254, 'samples': 8644608, 'steps': 16883, 'batch_loss/train': 0.833422499417793}
+12/25/2021 04:48:37 - INFO - codeparrot_training - Step 16884: {'lr': 0.0003736232629121928, 'samples': 8645120, 'steps': 16884, 'batch_loss/train': 0.8255998343229294}
+12/25/2021 04:48:48 - INFO - codeparrot_training - Step 16885: {'lr': 0.00037360956164051367, 'samples': 8645632, 'steps': 16885, 'batch_loss/train': 0.7343484321609139}
+12/25/2021 04:48:58 - INFO - codeparrot_training - Step 16886: {'lr': 0.0003735958598774097, 'samples': 8646144, 'steps': 16886, 'batch_loss/train': 0.7365163564682007}
+12/25/2021 04:49:11 - INFO - codeparrot_training - Step 16887: {'lr': 0.0003735821576229351, 'samples': 8646656, 'steps': 16887, 'batch_loss/train': 0.7812972385436296}
+12/25/2021 04:49:22 - INFO - codeparrot_training - Step 16888: {'lr': 0.0003735684548771446, 'samples': 8647168, 'steps': 16888, 'batch_loss/train': 0.8191139097325504}
+12/25/2021 04:49:32 - INFO - codeparrot_training - Step 16889: {'lr': 0.00037355475164009257, 'samples': 8647680, 'steps': 16889, 'batch_loss/train': 0.8778741369023919}
+12/25/2021 04:49:45 - INFO - codeparrot_training - Step 16890: {'lr': 0.0003735410479118335, 'samples': 8648192, 'steps': 16890, 'batch_loss/train': 0.781808169092983}
+12/25/2021 04:49:55 - INFO - codeparrot_training - Step 16891: {'lr': 0.0003735273436924218, 'samples': 8648704, 'steps': 16891, 'batch_loss/train': 0.8211659854277968}
+12/25/2021 04:50:06 - INFO - codeparrot_training - Step 16892: {'lr': 0.00037351363898191215, 'samples': 8649216, 'steps': 16892, 'batch_loss/train': 0.9147819066420197}
+12/25/2021 04:50:16 - INFO - codeparrot_training - Step 16893: {'lr': 0.00037349993378035887, 'samples': 8649728, 'steps': 16893, 'batch_loss/train': 0.5834653661586344}
+12/25/2021 04:50:29 - INFO - codeparrot_training - Step 16894: {'lr': 0.0003734862280878164, 'samples': 8650240, 'steps': 16894, 'batch_loss/train': 0.8009211886674166}
+12/25/2021 04:50:39 - INFO - codeparrot_training - Step 16895: {'lr': 0.00037347252190433937, 'samples': 8650752, 'steps': 16895, 'batch_loss/train': 0.75249785464257}
+12/25/2021 04:50:50 - INFO - codeparrot_training - Step 16896: {'lr': 0.0003734588152299823, 'samples': 8651264, 'steps': 16896, 'batch_loss/train': 0.7644891669042408}
+12/25/2021 04:51:02 - INFO - codeparrot_training - Step 16897: {'lr': 0.0003734451080647995, 'samples': 8651776, 'steps': 16897, 'batch_loss/train': 0.8142156768590212}
+12/25/2021 04:51:13 - INFO - codeparrot_training - Step 16898: {'lr': 0.0003734314004088455, 'samples': 8652288, 'steps': 16898, 'batch_loss/train': 0.8041269518435001}
+12/25/2021 04:51:24 - INFO - codeparrot_training - Step 16899: {'lr': 0.0003734176922621749, 'samples': 8652800, 'steps': 16899, 'batch_loss/train': 0.829131368547678}
+12/25/2021 04:51:36 - INFO - codeparrot_training - Step 16900: {'lr': 0.0003734039836248423, 'samples': 8653312, 'steps': 16900, 'batch_loss/train': 0.8460450582206249}
+12/25/2021 04:51:47 - INFO - codeparrot_training - Step 16901: {'lr': 0.0003733902744969019, 'samples': 8653824, 'steps': 16901, 'batch_loss/train': 0.7268404867500067}
+12/25/2021 04:51:57 - INFO - codeparrot_training - Step 16902: {'lr': 0.00037337656487840845, 'samples': 8654336, 'steps': 16902, 'batch_loss/train': 0.8798059429973364}
+12/25/2021 04:52:09 - INFO - codeparrot_training - Step 16903: {'lr': 0.0003733628547694163, 'samples': 8654848, 'steps': 16903, 'batch_loss/train': 0.7025984893552959}
+12/25/2021 04:52:20 - INFO - codeparrot_training - Step 16904: {'lr': 0.00037334914416998, 'samples': 8655360, 'steps': 16904, 'batch_loss/train': 0.8321634414605796}
+12/25/2021 04:52:30 - INFO - codeparrot_training - Step 16905: {'lr': 0.0003733354330801541, 'samples': 8655872, 'steps': 16905, 'batch_loss/train': 0.9225273355841637}
+12/25/2021 04:52:41 - INFO - codeparrot_training - Step 16906: {'lr': 0.0003733217214999932, 'samples': 8656384, 'steps': 16906, 'batch_loss/train': 0.8796259518712759}
+12/25/2021 04:52:53 - INFO - codeparrot_training - Step 16907: {'lr': 0.0003733080094295515, 'samples': 8656896, 'steps': 16907, 'batch_loss/train': 0.7861633766442537}
+12/25/2021 04:53:04 - INFO - codeparrot_training - Step 16908: {'lr': 0.0003732942968688839, 'samples': 8657408, 'steps': 16908, 'batch_loss/train': 0.8392008277587593}
+12/25/2021 04:53:15 - INFO - codeparrot_training - Step 16909: {'lr': 0.0003732805838180446, 'samples': 8657920, 'steps': 16909, 'batch_loss/train': 0.7890594693599269}
+12/25/2021 04:53:27 - INFO - codeparrot_training - Step 16910: {'lr': 0.00037326687027708827, 'samples': 8658432, 'steps': 16910, 'batch_loss/train': 0.8801270104013383}
+12/25/2021 04:53:37 - INFO - codeparrot_training - Step 16911: {'lr': 0.0003732531562460695, 'samples': 8658944, 'steps': 16911, 'batch_loss/train': 0.7697160290554166}
+12/25/2021 04:53:48 - INFO - codeparrot_training - Step 16912: {'lr': 0.0003732394417250426, 'samples': 8659456, 'steps': 16912, 'batch_loss/train': 0.8670120844617486}
+12/25/2021 04:54:00 - INFO - codeparrot_training - Step 16913: {'lr': 0.0003732257267140623, 'samples': 8659968, 'steps': 16913, 'batch_loss/train': 0.8218140280805528}
+12/25/2021 04:54:11 - INFO - codeparrot_training - Step 16914: {'lr': 0.00037321201121318293, 'samples': 8660480, 'steps': 16914, 'batch_loss/train': 0.705955928307958}
+12/25/2021 04:54:21 - INFO - codeparrot_training - Step 16915: {'lr': 0.0003731982952224593, 'samples': 8660992, 'steps': 16915, 'batch_loss/train': 0.8162917965673842}
+12/25/2021 04:54:32 - INFO - codeparrot_training - Step 16916: {'lr': 0.0003731845787419456, 'samples': 8661504, 'steps': 16916, 'batch_loss/train': 0.8141737142577767}
+12/25/2021 04:54:45 - INFO - codeparrot_training - Step 16917: {'lr': 0.0003731708617716966, 'samples': 8662016, 'steps': 16917, 'batch_loss/train': 0.8149023531004786}
+12/25/2021 04:54:55 - INFO - codeparrot_training - Step 16918: {'lr': 0.0003731571443117668, 'samples': 8662528, 'steps': 16918, 'batch_loss/train': 0.7836297894828022}
+12/25/2021 04:55:06 - INFO - codeparrot_training - Step 16919: {'lr': 0.00037314342636221066, 'samples': 8663040, 'steps': 16919, 'batch_loss/train': 0.8819235051050782}
+12/25/2021 04:55:18 - INFO - codeparrot_training - Step 16920: {'lr': 0.0003731297079230827, 'samples': 8663552, 'steps': 16920, 'batch_loss/train': 0.8513206010684371}
+12/25/2021 04:55:29 - INFO - codeparrot_training - Step 16921: {'lr': 0.0003731159889944376, 'samples': 8664064, 'steps': 16921, 'batch_loss/train': 0.7505997074767947}
+12/25/2021 04:55:39 - INFO - codeparrot_training - Step 16922: {'lr': 0.00037310226957632973, 'samples': 8664576, 'steps': 16922, 'batch_loss/train': 0.7619612785056233}
+12/25/2021 04:55:51 - INFO - codeparrot_training - Step 16923: {'lr': 0.00037308854966881376, 'samples': 8665088, 'steps': 16923, 'batch_loss/train': 0.8756872545927763}
+12/25/2021 04:56:02 - INFO - codeparrot_training - Step 16924: {'lr': 0.0003730748292719442, 'samples': 8665600, 'steps': 16924, 'batch_loss/train': 0.8660275805741549}
+12/25/2021 04:56:12 - INFO - codeparrot_training - Step 16925: {'lr': 0.00037306110838577556, 'samples': 8666112, 'steps': 16925, 'batch_loss/train': 0.8338968120515347}
+12/25/2021 04:56:23 - INFO - codeparrot_training - Step 16926: {'lr': 0.00037304738701036245, 'samples': 8666624, 'steps': 16926, 'batch_loss/train': 0.8496685037389398}
+12/25/2021 04:56:36 - INFO - codeparrot_training - Step 16927: {'lr': 0.00037303366514575937, 'samples': 8667136, 'steps': 16927, 'batch_loss/train': 0.6638684456702322}
+12/25/2021 04:56:46 - INFO - codeparrot_training - Step 16928: {'lr': 0.0003730199427920209, 'samples': 8667648, 'steps': 16928, 'batch_loss/train': 0.8140806192532182}
+12/25/2021 04:56:57 - INFO - codeparrot_training - Step 16929: {'lr': 0.00037300621994920165, 'samples': 8668160, 'steps': 16929, 'batch_loss/train': 0.7958425553515553}
+12/25/2021 04:57:09 - INFO - codeparrot_training - Step 16930: {'lr': 0.00037299249661735607, 'samples': 8668672, 'steps': 16930, 'batch_loss/train': 1.0119575143326074}
+12/25/2021 04:57:20 - INFO - codeparrot_training - Step 16931: {'lr': 0.0003729787727965387, 'samples': 8669184, 'steps': 16931, 'batch_loss/train': 0.8294768524356186}
+12/25/2021 04:57:31 - INFO - codeparrot_training - Step 16932: {'lr': 0.0003729650484868043, 'samples': 8669696, 'steps': 16932, 'batch_loss/train': 0.8029115973040462}
+12/25/2021 04:57:44 - INFO - codeparrot_training - Step 16933: {'lr': 0.00037295132368820715, 'samples': 8670208, 'steps': 16933, 'batch_loss/train': 0.7087505388772115}
+12/25/2021 04:57:54 - INFO - codeparrot_training - Step 16934: {'lr': 0.00037293759840080205, 'samples': 8670720, 'steps': 16934, 'batch_loss/train': 0.7133074882440269}
+12/25/2021 04:58:05 - INFO - codeparrot_training - Step 16935: {'lr': 0.00037292387262464344, 'samples': 8671232, 'steps': 16935, 'batch_loss/train': 0.7368608319666237}
+12/25/2021 04:58:16 - INFO - codeparrot_training - Step 16936: {'lr': 0.00037291014635978595, 'samples': 8671744, 'steps': 16936, 'batch_loss/train': 1.0861839968711138}
+12/25/2021 04:58:27 - INFO - codeparrot_training - Step 16937: {'lr': 0.00037289641960628413, 'samples': 8672256, 'steps': 16937, 'batch_loss/train': 0.7455763346515596}
+12/25/2021 04:58:38 - INFO - codeparrot_training - Step 16938: {'lr': 0.0003728826923641925, 'samples': 8672768, 'steps': 16938, 'batch_loss/train': 0.73654621001333}
+12/25/2021 04:58:49 - INFO - codeparrot_training - Step 16939: {'lr': 0.00037286896463356573, 'samples': 8673280, 'steps': 16939, 'batch_loss/train': 0.7829347690567374}
+12/25/2021 04:59:01 - INFO - codeparrot_training - Step 16940: {'lr': 0.00037285523641445833, 'samples': 8673792, 'steps': 16940, 'batch_loss/train': 0.7066250217612833}
+12/25/2021 04:59:11 - INFO - codeparrot_training - Step 16941: {'lr': 0.00037284150770692495, 'samples': 8674304, 'steps': 16941, 'batch_loss/train': 0.6985812222119421}
+12/25/2021 04:59:22 - INFO - codeparrot_training - Step 16942: {'lr': 0.0003728277785110201, 'samples': 8674816, 'steps': 16942, 'batch_loss/train': 0.8073779544793069}
+12/25/2021 04:59:35 - INFO - codeparrot_training - Step 16943: {'lr': 0.0003728140488267983, 'samples': 8675328, 'steps': 16943, 'batch_loss/train': 0.7262226333841681}
+12/25/2021 04:59:45 - INFO - codeparrot_training - Step 16944: {'lr': 0.0003728003186543143, 'samples': 8675840, 'steps': 16944, 'batch_loss/train': 0.7448132731951773}
+12/25/2021 04:59:56 - INFO - codeparrot_training - Step 16945: {'lr': 0.00037278658799362266, 'samples': 8676352, 'steps': 16945, 'batch_loss/train': 0.8564401036128402}
+12/25/2021 05:00:06 - INFO - codeparrot_training - Step 16946: {'lr': 0.00037277285684477775, 'samples': 8676864, 'steps': 16946, 'batch_loss/train': 0.7912777378223836}
+12/25/2021 05:00:19 - INFO - codeparrot_training - Step 16947: {'lr': 0.0003727591252078344, 'samples': 8677376, 'steps': 16947, 'batch_loss/train': 0.8023835401982069}
+12/25/2021 05:00:29 - INFO - codeparrot_training - Step 16948: {'lr': 0.0003727453930828471, 'samples': 8677888, 'steps': 16948, 'batch_loss/train': 0.7704978481051512}
+12/25/2021 05:00:40 - INFO - codeparrot_training - Step 16949: {'lr': 0.0003727316604698704, 'samples': 8678400, 'steps': 16949, 'batch_loss/train': 0.8058857824653387}
+12/25/2021 05:00:52 - INFO - codeparrot_training - Step 16950: {'lr': 0.0003727179273689591, 'samples': 8678912, 'steps': 16950, 'batch_loss/train': 0.8283862844109535}
+12/25/2021 05:01:02 - INFO - codeparrot_training - Step 16951: {'lr': 0.0003727041937801676, 'samples': 8679424, 'steps': 16951, 'batch_loss/train': 0.806168888695538}
+12/25/2021 05:01:13 - INFO - codeparrot_training - Step 16952: {'lr': 0.0003726904597035505, 'samples': 8679936, 'steps': 16952, 'batch_loss/train': 0.771311673335731}
+12/25/2021 05:01:25 - INFO - codeparrot_training - Step 16953: {'lr': 0.0003726767251391625, 'samples': 8680448, 'steps': 16953, 'batch_loss/train': 0.8209850583225489}
+12/25/2021 05:01:36 - INFO - codeparrot_training - Step 16954: {'lr': 0.00037266299008705824, 'samples': 8680960, 'steps': 16954, 'batch_loss/train': 0.7592252916656435}
+12/25/2021 05:01:46 - INFO - codeparrot_training - Step 16955: {'lr': 0.00037264925454729217, 'samples': 8681472, 'steps': 16955, 'batch_loss/train': 0.8462404278106987}
+12/25/2021 05:01:57 - INFO - codeparrot_training - Step 16956: {'lr': 0.00037263551851991896, 'samples': 8681984, 'steps': 16956, 'batch_loss/train': 0.7634237920865417}
+12/25/2021 05:02:10 - INFO - codeparrot_training - Step 16957: {'lr': 0.00037262178200499327, 'samples': 8682496, 'steps': 16957, 'batch_loss/train': 0.8196874542627484}
+12/25/2021 05:02:21 - INFO - codeparrot_training - Step 16958: {'lr': 0.0003726080450025697, 'samples': 8683008, 'steps': 16958, 'batch_loss/train': 0.7169225828256458}
+12/25/2021 05:02:31 - INFO - codeparrot_training - Step 16959: {'lr': 0.0003725943075127027, 'samples': 8683520, 'steps': 16959, 'batch_loss/train': 0.8817387595772743}
+12/25/2021 05:02:43 - INFO - codeparrot_training - Step 16960: {'lr': 0.0003725805695354472, 'samples': 8684032, 'steps': 16960, 'batch_loss/train': 1.0477619240991771}
+12/25/2021 05:02:54 - INFO - codeparrot_training - Step 16961: {'lr': 0.00037256683107085754, 'samples': 8684544, 'steps': 16961, 'batch_loss/train': 0.8922459445893764}
+12/25/2021 05:03:05 - INFO - codeparrot_training - Step 16962: {'lr': 0.0003725530921189884, 'samples': 8685056, 'steps': 16962, 'batch_loss/train': 0.7681152317672968}
+12/25/2021 05:03:17 - INFO - codeparrot_training - Step 16963: {'lr': 0.0003725393526798946, 'samples': 8685568, 'steps': 16963, 'batch_loss/train': 0.808703288435936}
+12/25/2021 05:03:27 - INFO - codeparrot_training - Step 16964: {'lr': 0.00037252561275363046, 'samples': 8686080, 'steps': 16964, 'batch_loss/train': 0.8164129443466663}
+12/25/2021 05:03:38 - INFO - codeparrot_training - Step 16965: {'lr': 0.0003725118723402507, 'samples': 8686592, 'steps': 16965, 'batch_loss/train': 0.7724475581198931}
+12/25/2021 05:03:48 - INFO - codeparrot_training - Step 16966: {'lr': 0.0003724981314398102, 'samples': 8687104, 'steps': 16966, 'batch_loss/train': 0.6600355408154428}
+12/25/2021 05:04:01 - INFO - codeparrot_training - Step 16967: {'lr': 0.0003724843900523633, 'samples': 8687616, 'steps': 16967, 'batch_loss/train': 1.0596976913511753}
+12/25/2021 05:04:12 - INFO - codeparrot_training - Step 16968: {'lr': 0.0003724706481779646, 'samples': 8688128, 'steps': 16968, 'batch_loss/train': 0.7758840350434184}
+12/25/2021 05:04:23 - INFO - codeparrot_training - Step 16969: {'lr': 0.000372456905816669, 'samples': 8688640, 'steps': 16969, 'batch_loss/train': 0.7719105272553861}
+12/25/2021 05:04:35 - INFO - codeparrot_training - Step 16970: {'lr': 0.0003724431629685309, 'samples': 8689152, 'steps': 16970, 'batch_loss/train': 0.843370673013851}
+12/25/2021 05:04:45 - INFO - codeparrot_training - Step 16971: {'lr': 0.000372429419633605, 'samples': 8689664, 'steps': 16971, 'batch_loss/train': 0.8245174754410982}
+12/25/2021 05:04:56 - INFO - codeparrot_training - Step 16972: {'lr': 0.000372415675811946, 'samples': 8690176, 'steps': 16972, 'batch_loss/train': 0.7421648184536025}
+12/25/2021 05:05:09 - INFO - codeparrot_training - Step 16973: {'lr': 0.0003724019315036084, 'samples': 8690688, 'steps': 16973, 'batch_loss/train': 0.7741259718313813}
+12/25/2021 05:05:20 - INFO - codeparrot_training - Step 16974: {'lr': 0.00037238818670864705, 'samples': 8691200, 'steps': 16974, 'batch_loss/train': 0.8205073582939804}
+12/25/2021 05:05:30 - INFO - codeparrot_training - Step 16975: {'lr': 0.0003723744414271164, 'samples': 8691712, 'steps': 16975, 'batch_loss/train': 0.5250114519149065}
+12/25/2021 05:05:41 - INFO - codeparrot_training - Step 16976: {'lr': 0.0003723606956590713, 'samples': 8692224, 'steps': 16976, 'batch_loss/train': 0.8636396112851799}
+12/25/2021 05:05:53 - INFO - codeparrot_training - Step 16977: {'lr': 0.00037234694940456616, 'samples': 8692736, 'steps': 16977, 'batch_loss/train': 1.7329059895128012}
+12/25/2021 05:06:04 - INFO - codeparrot_training - Step 16978: {'lr': 0.0003723332026636558, 'samples': 8693248, 'steps': 16978, 'batch_loss/train': 0.7181051638908684}
+12/25/2021 05:06:14 - INFO - codeparrot_training - Step 16979: {'lr': 0.0003723194554363948, 'samples': 8693760, 'steps': 16979, 'batch_loss/train': 0.8630260471254587}
+12/25/2021 05:06:26 - INFO - codeparrot_training - Step 16980: {'lr': 0.0003723057077228378, 'samples': 8694272, 'steps': 16980, 'batch_loss/train': 0.808372332714498}
+12/25/2021 05:06:37 - INFO - codeparrot_training - Step 16981: {'lr': 0.00037229195952303955, 'samples': 8694784, 'steps': 16981, 'batch_loss/train': 0.6976062250323594}
+12/25/2021 05:06:48 - INFO - codeparrot_training - Step 16982: {'lr': 0.0003722782108370546, 'samples': 8695296, 'steps': 16982, 'batch_loss/train': 0.709970714058727}
+12/25/2021 05:07:00 - INFO - codeparrot_training - Step 16983: {'lr': 0.00037226446166493764, 'samples': 8695808, 'steps': 16983, 'batch_loss/train': 0.6320819370448589}
+12/25/2021 05:07:11 - INFO - codeparrot_training - Step 16984: {'lr': 0.0003722507120067434, 'samples': 8696320, 'steps': 16984, 'batch_loss/train': 0.7729596709832549}
+12/25/2021 05:07:22 - INFO - codeparrot_training - Step 16985: {'lr': 0.00037223696186252644, 'samples': 8696832, 'steps': 16985, 'batch_loss/train': 0.7636933021713048}
+12/25/2021 05:07:32 - INFO - codeparrot_training - Step 16986: {'lr': 0.0003722232112323415, 'samples': 8697344, 'steps': 16986, 'batch_loss/train': 0.8066178378649056}
+12/25/2021 05:07:45 - INFO - codeparrot_training - Step 16987: {'lr': 0.00037220946011624326, 'samples': 8697856, 'steps': 16987, 'batch_loss/train': 0.8255515063647181}
+12/25/2021 05:07:55 - INFO - codeparrot_training - Step 16988: {'lr': 0.00037219570851428627, 'samples': 8698368, 'steps': 16988, 'batch_loss/train': 0.6923258695751429}
+12/25/2021 05:08:06 - INFO - codeparrot_training - Step 16989: {'lr': 0.00037218195642652535, 'samples': 8698880, 'steps': 16989, 'batch_loss/train': 0.7696397416293621}
+12/25/2021 05:08:18 - INFO - codeparrot_training - Step 16990: {'lr': 0.00037216820385301507, 'samples': 8699392, 'steps': 16990, 'batch_loss/train': 0.5952057163231075}
+12/25/2021 05:08:28 - INFO - codeparrot_training - Step 16991: {'lr': 0.0003721544507938102, 'samples': 8699904, 'steps': 16991, 'batch_loss/train': 0.7983366781845689}
+12/25/2021 05:08:39 - INFO - codeparrot_training - Step 16992: {'lr': 0.00037214069724896524, 'samples': 8700416, 'steps': 16992, 'batch_loss/train': 0.8746267631649971}
+12/25/2021 05:08:51 - INFO - codeparrot_training - Step 16993: {'lr': 0.0003721269432185351, 'samples': 8700928, 'steps': 16993, 'batch_loss/train': 1.0383064737543464}
+12/25/2021 05:09:02 - INFO - codeparrot_training - Step 16994: {'lr': 0.0003721131887025742, 'samples': 8701440, 'steps': 16994, 'batch_loss/train': 0.8653882518410683}
+12/25/2021 05:09:12 - INFO - codeparrot_training - Step 16995: {'lr': 0.00037209943370113753, 'samples': 8701952, 'steps': 16995, 'batch_loss/train': 0.7376897372305393}
+12/25/2021 05:09:23 - INFO - codeparrot_training - Step 16996: {'lr': 0.0003720856782142796, 'samples': 8702464, 'steps': 16996, 'batch_loss/train': 0.9481252499390393}
+12/25/2021 05:09:36 - INFO - codeparrot_training - Step 16997: {'lr': 0.000372071922242055, 'samples': 8702976, 'steps': 16997, 'batch_loss/train': 0.7774981781840324}
+12/25/2021 05:09:46 - INFO - codeparrot_training - Step 16998: {'lr': 0.0003720581657845186, 'samples': 8703488, 'steps': 16998, 'batch_loss/train': 1.001218719407916}
+12/25/2021 05:09:57 - INFO - codeparrot_training - Step 16999: {'lr': 0.00037204440884172505, 'samples': 8704000, 'steps': 16999, 'batch_loss/train': 0.8737264340743423}
+12/25/2021 05:10:09 - INFO - codeparrot_training - Step 17000: {'lr': 0.000372030651413729, 'samples': 8704512, 'steps': 17000, 'batch_loss/train': 0.775111373513937}
+12/25/2021 05:10:20 - INFO - codeparrot_training - Step 17001: {'lr': 0.00037201689350058507, 'samples': 8705024, 'steps': 17001, 'batch_loss/train': 0.7977651349501684}
+12/25/2021 05:10:30 - INFO - codeparrot_training - Step 17002: {'lr': 0.00037200313510234813, 'samples': 8705536, 'steps': 17002, 'batch_loss/train': 0.8370692068710923}
+12/25/2021 05:10:43 - INFO - codeparrot_training - Step 17003: {'lr': 0.00037198937621907275, 'samples': 8706048, 'steps': 17003, 'batch_loss/train': 0.7835679426789284}
+12/25/2021 05:10:54 - INFO - codeparrot_training - Step 17004: {'lr': 0.00037197561685081373, 'samples': 8706560, 'steps': 17004, 'batch_loss/train': 0.818569521070458}
+12/25/2021 05:11:04 - INFO - codeparrot_training - Step 17005: {'lr': 0.0003719618569976256, 'samples': 8707072, 'steps': 17005, 'batch_loss/train': 0.9426284385845065}
+12/25/2021 05:11:15 - INFO - codeparrot_training - Step 17006: {'lr': 0.0003719480966595633, 'samples': 8707584, 'steps': 17006, 'batch_loss/train': 0.798375753685832}
+12/25/2021 05:11:27 - INFO - codeparrot_training - Step 17007: {'lr': 0.00037193433583668136, 'samples': 8708096, 'steps': 17007, 'batch_loss/train': 0.7254099519923329}
+12/25/2021 05:11:38 - INFO - codeparrot_training - Step 17008: {'lr': 0.00037192057452903457, 'samples': 8708608, 'steps': 17008, 'batch_loss/train': 0.844433113001287}
+12/25/2021 05:11:48 - INFO - codeparrot_training - Step 17009: {'lr': 0.00037190681273667757, 'samples': 8709120, 'steps': 17009, 'batch_loss/train': 0.7963527720421553}
+12/25/2021 05:12:00 - INFO - codeparrot_training - Step 17010: {'lr': 0.00037189305045966513, 'samples': 8709632, 'steps': 17010, 'batch_loss/train': 0.7469498068094254}
+12/25/2021 05:12:11 - INFO - codeparrot_training - Step 17011: {'lr': 0.0003718792876980519, 'samples': 8710144, 'steps': 17011, 'batch_loss/train': 0.8230086555704474}
+12/25/2021 05:12:22 - INFO - codeparrot_training - Step 17012: {'lr': 0.0003718655244518927, 'samples': 8710656, 'steps': 17012, 'batch_loss/train': 0.8152289055287838}
+12/25/2021 05:12:34 - INFO - codeparrot_training - Step 17013: {'lr': 0.0003718517607212422, 'samples': 8711168, 'steps': 17013, 'batch_loss/train': 0.8193493811413646}
+12/25/2021 05:12:45 - INFO - codeparrot_training - Step 17014: {'lr': 0.00037183799650615507, 'samples': 8711680, 'steps': 17014, 'batch_loss/train': 0.8222498865798116}
+12/25/2021 05:12:56 - INFO - codeparrot_training - Step 17015: {'lr': 0.00037182423180668613, 'samples': 8712192, 'steps': 17015, 'batch_loss/train': 0.8117305459454656}
+12/25/2021 05:13:08 - INFO - codeparrot_training - Step 17016: {'lr': 0.00037181046662289, 'samples': 8712704, 'steps': 17016, 'batch_loss/train': 0.8326842095702887}
+12/25/2021 05:13:19 - INFO - codeparrot_training - Step 17017: {'lr': 0.00037179670095482145, 'samples': 8713216, 'steps': 17017, 'batch_loss/train': 0.8051888970658183}
+12/25/2021 05:13:29 - INFO - codeparrot_training - Step 17018: {'lr': 0.00037178293480253516, 'samples': 8713728, 'steps': 17018, 'batch_loss/train': 0.8654617122374475}
+12/25/2021 05:13:40 - INFO - codeparrot_training - Step 17019: {'lr': 0.00037176916816608597, 'samples': 8714240, 'steps': 17019, 'batch_loss/train': 0.7680071946233511}
+12/25/2021 05:13:53 - INFO - codeparrot_training - Step 17020: {'lr': 0.0003717554010455285, 'samples': 8714752, 'steps': 17020, 'batch_loss/train': 0.801099980250001}
+12/25/2021 05:14:03 - INFO - codeparrot_training - Step 17021: {'lr': 0.0003717416334409176, 'samples': 8715264, 'steps': 17021, 'batch_loss/train': 0.5832780604250729}
+12/25/2021 05:14:14 - INFO - codeparrot_training - Step 17022: {'lr': 0.00037172786535230785, 'samples': 8715776, 'steps': 17022, 'batch_loss/train': 0.8202964058145881}
+12/25/2021 05:14:26 - INFO - codeparrot_training - Step 17023: {'lr': 0.0003717140967797541, 'samples': 8716288, 'steps': 17023, 'batch_loss/train': 0.7297754213213921}
+12/25/2021 05:14:37 - INFO - codeparrot_training - Step 17024: {'lr': 0.0003717003277233111, 'samples': 8716800, 'steps': 17024, 'batch_loss/train': 0.6359574077650905}
+12/25/2021 05:14:47 - INFO - codeparrot_training - Step 17025: {'lr': 0.00037168655818303346, 'samples': 8717312, 'steps': 17025, 'batch_loss/train': 0.8652881570160389}
+12/25/2021 05:14:58 - INFO - codeparrot_training - Step 17026: {'lr': 0.0003716727881589761, 'samples': 8717824, 'steps': 17026, 'batch_loss/train': 0.8711988758295774}
+12/25/2021 05:15:10 - INFO - codeparrot_training - Step 17027: {'lr': 0.0003716590176511936, 'samples': 8718336, 'steps': 17027, 'batch_loss/train': 0.8255058235954493}
+12/25/2021 05:15:20 - INFO - codeparrot_training - Step 17028: {'lr': 0.00037164524665974085, 'samples': 8718848, 'steps': 17028, 'batch_loss/train': 0.7768983574351296}
+12/25/2021 05:15:31 - INFO - codeparrot_training - Step 17029: {'lr': 0.00037163147518467257, 'samples': 8719360, 'steps': 17029, 'batch_loss/train': 0.7421838426962495}
+12/25/2021 05:15:43 - INFO - codeparrot_training - Step 17030: {'lr': 0.0003716177032260434, 'samples': 8719872, 'steps': 17030, 'batch_loss/train': 0.7593359113670886}
+12/25/2021 05:15:54 - INFO - codeparrot_training - Step 17031: {'lr': 0.0003716039307839081, 'samples': 8720384, 'steps': 17031, 'batch_loss/train': 0.7846761122345924}
+12/25/2021 05:16:04 - INFO - codeparrot_training - Step 17032: {'lr': 0.0003715901578583216, 'samples': 8720896, 'steps': 17032, 'batch_loss/train': 0.8314266912639141}
+12/25/2021 05:16:17 - INFO - codeparrot_training - Step 17033: {'lr': 0.00037157638444933845, 'samples': 8721408, 'steps': 17033, 'batch_loss/train': 0.7595108640380204}
+12/25/2021 05:16:28 - INFO - codeparrot_training - Step 17034: {'lr': 0.00037156261055701356, 'samples': 8721920, 'steps': 17034, 'batch_loss/train': 0.7954403317999095}
+12/25/2021 05:16:38 - INFO - codeparrot_training - Step 17035: {'lr': 0.00037154883618140165, 'samples': 8722432, 'steps': 17035, 'batch_loss/train': 0.7787006911821663}
+12/25/2021 05:16:50 - INFO - codeparrot_training - Step 17036: {'lr': 0.0003715350613225574, 'samples': 8722944, 'steps': 17036, 'batch_loss/train': 0.7244045082479715}
+12/25/2021 05:17:01 - INFO - codeparrot_training - Step 17037: {'lr': 0.0003715212859805357, 'samples': 8723456, 'steps': 17037, 'batch_loss/train': 0.7764649079181254}
+12/25/2021 05:17:11 - INFO - codeparrot_training - Step 17038: {'lr': 0.0003715075101553912, 'samples': 8723968, 'steps': 17038, 'batch_loss/train': 0.8228448508307338}
+12/25/2021 05:17:22 - INFO - codeparrot_training - Step 17039: {'lr': 0.0003714937338471787, 'samples': 8724480, 'steps': 17039, 'batch_loss/train': 0.9349382780492306}
+12/25/2021 05:17:34 - INFO - codeparrot_training - Step 17040: {'lr': 0.00037147995705595307, 'samples': 8724992, 'steps': 17040, 'batch_loss/train': 0.6677048946730793}
+12/25/2021 05:17:45 - INFO - codeparrot_training - Step 17041: {'lr': 0.000371466179781769, 'samples': 8725504, 'steps': 17041, 'batch_loss/train': 0.7491424176841974}
+12/25/2021 05:17:55 - INFO - codeparrot_training - Step 17042: {'lr': 0.0003714524020246812, 'samples': 8726016, 'steps': 17042, 'batch_loss/train': 0.8117257002741098}
+12/25/2021 05:18:08 - INFO - codeparrot_training - Step 17043: {'lr': 0.00037143862378474454, 'samples': 8726528, 'steps': 17043, 'batch_loss/train': 0.8114864882081747}
+12/25/2021 05:18:19 - INFO - codeparrot_training - Step 17044: {'lr': 0.0003714248450620137, 'samples': 8727040, 'steps': 17044, 'batch_loss/train': 0.8313294323161244}
+12/25/2021 05:18:29 - INFO - codeparrot_training - Step 17045: {'lr': 0.0003714110658565437, 'samples': 8727552, 'steps': 17045, 'batch_loss/train': 0.8326535443775356}
+12/25/2021 05:18:41 - INFO - codeparrot_training - Step 17046: {'lr': 0.00037139728616838893, 'samples': 8728064, 'steps': 17046, 'batch_loss/train': 0.8670677645131946}
+12/25/2021 05:18:52 - INFO - codeparrot_training - Step 17047: {'lr': 0.00037138350599760447, 'samples': 8728576, 'steps': 17047, 'batch_loss/train': 0.8820416778326035}
+12/25/2021 05:19:03 - INFO - codeparrot_training - Step 17048: {'lr': 0.0003713697253442451, 'samples': 8729088, 'steps': 17048, 'batch_loss/train': 0.9414411610923707}
+12/25/2021 05:19:13 - INFO - codeparrot_training - Step 17049: {'lr': 0.00037135594420836544, 'samples': 8729600, 'steps': 17049, 'batch_loss/train': 0.7101630161050707}
+12/25/2021 05:19:26 - INFO - codeparrot_training - Step 17050: {'lr': 0.00037134216259002037, 'samples': 8730112, 'steps': 17050, 'batch_loss/train': 0.7099400307051837}
+12/25/2021 05:19:37 - INFO - codeparrot_training - Step 17051: {'lr': 0.0003713283804892647, 'samples': 8730624, 'steps': 17051, 'batch_loss/train': 0.835782659240067}
+12/25/2021 05:19:47 - INFO - codeparrot_training - Step 17052: {'lr': 0.00037131459790615317, 'samples': 8731136, 'steps': 17052, 'batch_loss/train': 0.7469722246751189}
+12/25/2021 05:19:59 - INFO - codeparrot_training - Step 17053: {'lr': 0.00037130081484074064, 'samples': 8731648, 'steps': 17053, 'batch_loss/train': 0.7161566922441125}
+12/25/2021 05:20:10 - INFO - codeparrot_training - Step 17054: {'lr': 0.00037128703129308193, 'samples': 8732160, 'steps': 17054, 'batch_loss/train': 0.7126652075676247}
+12/25/2021 05:20:21 - INFO - codeparrot_training - Step 17055: {'lr': 0.0003712732472632317, 'samples': 8732672, 'steps': 17055, 'batch_loss/train': 0.8200038126669824}
+12/25/2021 05:20:33 - INFO - codeparrot_training - Step 17056: {'lr': 0.00037125946275124485, 'samples': 8733184, 'steps': 17056, 'batch_loss/train': 0.8452499764971435}
+12/25/2021 05:20:43 - INFO - codeparrot_training - Step 17057: {'lr': 0.00037124567775717615, 'samples': 8733696, 'steps': 17057, 'batch_loss/train': 0.6267070721369237}
+12/25/2021 05:20:54 - INFO - codeparrot_training - Step 17058: {'lr': 0.0003712318922810804, 'samples': 8734208, 'steps': 17058, 'batch_loss/train': 0.8093329521361738}
+12/25/2021 05:21:04 - INFO - codeparrot_training - Step 17059: {'lr': 0.00037121810632301244, 'samples': 8734720, 'steps': 17059, 'batch_loss/train': 0.6699704579077661}
+12/25/2021 05:21:16 - INFO - codeparrot_training - Step 17060: {'lr': 0.00037120431988302705, 'samples': 8735232, 'steps': 17060, 'batch_loss/train': 0.6628342038020492}
+12/25/2021 05:21:27 - INFO - codeparrot_training - Step 17061: {'lr': 0.0003711905329611791, 'samples': 8735744, 'steps': 17061, 'batch_loss/train': 0.7603456387296319}
+12/25/2021 05:21:38 - INFO - codeparrot_training - Step 17062: {'lr': 0.0003711767455575233, 'samples': 8736256, 'steps': 17062, 'batch_loss/train': 0.7674389842431992}
+12/25/2021 05:21:50 - INFO - codeparrot_training - Step 17063: {'lr': 0.00037116295767211454, 'samples': 8736768, 'steps': 17063, 'batch_loss/train': 0.8636061288416386}
+12/25/2021 05:22:01 - INFO - codeparrot_training - Step 17064: {'lr': 0.00037114916930500766, 'samples': 8737280, 'steps': 17064, 'batch_loss/train': 0.7856367046479136}
+12/25/2021 05:22:12 - INFO - codeparrot_training - Step 17065: {'lr': 0.00037113538045625735, 'samples': 8737792, 'steps': 17065, 'batch_loss/train': 0.8325524749234319}
+12/25/2021 05:22:24 - INFO - codeparrot_training - Step 17066: {'lr': 0.0003711215911259185, 'samples': 8738304, 'steps': 17066, 'batch_loss/train': 0.8270903588272631}
+12/25/2021 05:22:34 - INFO - codeparrot_training - Step 17067: {'lr': 0.00037110780131404596, 'samples': 8738816, 'steps': 17067, 'batch_loss/train': 0.6566957010654733}
+12/25/2021 05:22:45 - INFO - codeparrot_training - Step 17068: {'lr': 0.0003710940110206946, 'samples': 8739328, 'steps': 17068, 'batch_loss/train': 0.7230028910562396}
+12/25/2021 05:22:56 - INFO - codeparrot_training - Step 17069: {'lr': 0.00037108022024591903, 'samples': 8739840, 'steps': 17069, 'batch_loss/train': 0.7805981310084462}
+12/25/2021 05:23:08 - INFO - codeparrot_training - Step 17070: {'lr': 0.00037106642898977434, 'samples': 8740352, 'steps': 17070, 'batch_loss/train': 0.7856095964089036}
+12/25/2021 05:23:18 - INFO - codeparrot_training - Step 17071: {'lr': 0.0003710526372523152, 'samples': 8740864, 'steps': 17071, 'batch_loss/train': 0.7707490520551801}
+12/25/2021 05:23:29 - INFO - codeparrot_training - Step 17072: {'lr': 0.0003710388450335964, 'samples': 8741376, 'steps': 17072, 'batch_loss/train': 0.8724807128310204}
+12/25/2021 05:23:42 - INFO - codeparrot_training - Step 17073: {'lr': 0.000371025052333673, 'samples': 8741888, 'steps': 17073, 'batch_loss/train': 0.7088010662700981}
+12/25/2021 05:23:52 - INFO - codeparrot_training - Step 17074: {'lr': 0.00037101125915259964, 'samples': 8742400, 'steps': 17074, 'batch_loss/train': 0.7696491181850433}
+12/25/2021 05:24:03 - INFO - codeparrot_training - Step 17075: {'lr': 0.0003709974654904311, 'samples': 8742912, 'steps': 17075, 'batch_loss/train': 0.7994547141715884}
+12/25/2021 05:24:15 - INFO - codeparrot_training - Step 17076: {'lr': 0.0003709836713472225, 'samples': 8743424, 'steps': 17076, 'batch_loss/train': 0.6993579147383571}
+12/25/2021 05:24:26 - INFO - codeparrot_training - Step 17077: {'lr': 0.0003709698767230284, 'samples': 8743936, 'steps': 17077, 'batch_loss/train': 0.8109991308301687}
+12/25/2021 05:24:36 - INFO - codeparrot_training - Step 17078: {'lr': 0.00037095608161790376, 'samples': 8744448, 'steps': 17078, 'batch_loss/train': 0.7571219063829631}
+12/25/2021 05:24:47 - INFO - codeparrot_training - Step 17079: {'lr': 0.00037094228603190343, 'samples': 8744960, 'steps': 17079, 'batch_loss/train': 0.7960456013679504}
+12/25/2021 05:24:59 - INFO - codeparrot_training - Step 17080: {'lr': 0.00037092848996508226, 'samples': 8745472, 'steps': 17080, 'batch_loss/train': 0.9401393355801702}
+12/25/2021 05:25:09 - INFO - codeparrot_training - Step 17081: {'lr': 0.00037091469341749505, 'samples': 8745984, 'steps': 17081, 'batch_loss/train': 0.7447575032711029}
+12/25/2021 05:25:20 - INFO - codeparrot_training - Step 17082: {'lr': 0.00037090089638919666, 'samples': 8746496, 'steps': 17082, 'batch_loss/train': 0.8495045732706785}
+12/25/2021 05:25:33 - INFO - codeparrot_training - Step 17083: {'lr': 0.00037088709888024197, 'samples': 8747008, 'steps': 17083, 'batch_loss/train': 0.7843368935864419}
+12/25/2021 05:25:43 - INFO - codeparrot_training - Step 17084: {'lr': 0.00037087330089068576, 'samples': 8747520, 'steps': 17084, 'batch_loss/train': 0.8121597226709127}
+12/25/2021 05:25:54 - INFO - codeparrot_training - Step 17085: {'lr': 0.00037085950242058297, 'samples': 8748032, 'steps': 17085, 'batch_loss/train': 0.720646555069834}
+12/25/2021 05:26:06 - INFO - codeparrot_training - Step 17086: {'lr': 0.0003708457034699885, 'samples': 8748544, 'steps': 17086, 'batch_loss/train': 0.7477453174069524}
+12/25/2021 05:26:17 - INFO - codeparrot_training - Step 17087: {'lr': 0.0003708319040389571, 'samples': 8749056, 'steps': 17087, 'batch_loss/train': 0.803238358348608}
+12/25/2021 05:26:27 - INFO - codeparrot_training - Step 17088: {'lr': 0.00037081810412754364, 'samples': 8749568, 'steps': 17088, 'batch_loss/train': 0.800892467610538}
+12/25/2021 05:26:40 - INFO - codeparrot_training - Step 17089: {'lr': 0.0003708043037358031, 'samples': 8750080, 'steps': 17089, 'batch_loss/train': 0.7398656863952056}
+12/25/2021 05:26:51 - INFO - codeparrot_training - Step 17090: {'lr': 0.00037079050286379023, 'samples': 8750592, 'steps': 17090, 'batch_loss/train': 0.7577791521325707}
+12/25/2021 05:27:01 - INFO - codeparrot_training - Step 17091: {'lr': 0.0003707767015115599, 'samples': 8751104, 'steps': 17091, 'batch_loss/train': 0.7902941983193159}
+12/25/2021 05:27:12 - INFO - codeparrot_training - Step 17092: {'lr': 0.000370762899679167, 'samples': 8751616, 'steps': 17092, 'batch_loss/train': 0.8260375175741501}
+12/25/2021 05:27:24 - INFO - codeparrot_training - Step 17093: {'lr': 0.0003707490973666665, 'samples': 8752128, 'steps': 17093, 'batch_loss/train': 0.7915805159136653}
+12/25/2021 05:27:34 - INFO - codeparrot_training - Step 17094: {'lr': 0.0003707352945741131, 'samples': 8752640, 'steps': 17094, 'batch_loss/train': 0.7801563115790486}
+12/25/2021 05:27:45 - INFO - codeparrot_training - Step 17095: {'lr': 0.00037072149130156173, 'samples': 8753152, 'steps': 17095, 'batch_loss/train': 0.8081841710954905}
+12/25/2021 05:27:57 - INFO - codeparrot_training - Step 17096: {'lr': 0.0003707076875490674, 'samples': 8753664, 'steps': 17096, 'batch_loss/train': 0.9831717004999518}
+12/25/2021 05:28:08 - INFO - codeparrot_training - Step 17097: {'lr': 0.0003706938833166847, 'samples': 8754176, 'steps': 17097, 'batch_loss/train': 0.7952755680307746}
+12/25/2021 05:28:19 - INFO - codeparrot_training - Step 17098: {'lr': 0.0003706800786044688, 'samples': 8754688, 'steps': 17098, 'batch_loss/train': 0.6150395916774869}
+12/25/2021 05:28:31 - INFO - codeparrot_training - Step 17099: {'lr': 0.00037066627341247454, 'samples': 8755200, 'steps': 17099, 'batch_loss/train': 0.7736872346140444}
+12/25/2021 05:28:41 - INFO - codeparrot_training - Step 17100: {'lr': 0.00037065246774075673, 'samples': 8755712, 'steps': 17100, 'batch_loss/train': 0.8054636428132653}
+12/25/2021 05:28:52 - INFO - codeparrot_training - Step 17101: {'lr': 0.00037063866158937016, 'samples': 8756224, 'steps': 17101, 'batch_loss/train': 0.6889229714870453}
+12/25/2021 05:29:03 - INFO - codeparrot_training - Step 17102: {'lr': 0.0003706248549583699, 'samples': 8756736, 'steps': 17102, 'batch_loss/train': 0.8030995186418295}
+12/25/2021 05:29:15 - INFO - codeparrot_training - Step 17103: {'lr': 0.00037061104784781075, 'samples': 8757248, 'steps': 17103, 'batch_loss/train': 0.8032166035845876}
+12/25/2021 05:29:26 - INFO - codeparrot_training - Step 17104: {'lr': 0.0003705972402577476, 'samples': 8757760, 'steps': 17104, 'batch_loss/train': 0.7925503524020314}
+12/25/2021 05:29:36 - INFO - codeparrot_training - Step 17105: {'lr': 0.00037058343218823535, 'samples': 8758272, 'steps': 17105, 'batch_loss/train': 0.6788564736489207}
+12/25/2021 05:29:49 - INFO - codeparrot_training - Step 17106: {'lr': 0.000370569623639329, 'samples': 8758784, 'steps': 17106, 'batch_loss/train': 0.8527213279157877}
+12/25/2021 05:29:59 - INFO - codeparrot_training - Step 17107: {'lr': 0.0003705558146110832, 'samples': 8759296, 'steps': 17107, 'batch_loss/train': 0.7974973483942449}
+12/25/2021 05:30:10 - INFO - codeparrot_training - Step 17108: {'lr': 0.00037054200510355307, 'samples': 8759808, 'steps': 17108, 'batch_loss/train': 0.8022144790738821}
+12/25/2021 05:30:24 - INFO - codeparrot_training - Step 17109: {'lr': 0.00037052819511679345, 'samples': 8760320, 'steps': 17109, 'batch_loss/train': 0.8363966040778905}
+12/25/2021 05:30:35 - INFO - codeparrot_training - Step 17110: {'lr': 0.00037051438465085924, 'samples': 8760832, 'steps': 17110, 'batch_loss/train': 0.7322226818650961}
+12/25/2021 05:30:45 - INFO - codeparrot_training - Step 17111: {'lr': 0.0003705005737058053, 'samples': 8761344, 'steps': 17111, 'batch_loss/train': 0.793107071891427}
+12/25/2021 05:30:58 - INFO - codeparrot_training - Step 17112: {'lr': 0.00037048676228168667, 'samples': 8761856, 'steps': 17112, 'batch_loss/train': 0.6431608846178278}
+12/25/2021 05:31:08 - INFO - codeparrot_training - Step 17113: {'lr': 0.00037047295037855813, 'samples': 8762368, 'steps': 17113, 'batch_loss/train': 0.7216192702762783}
+12/25/2021 05:31:19 - INFO - codeparrot_training - Step 17114: {'lr': 0.0003704591379964745, 'samples': 8762880, 'steps': 17114, 'batch_loss/train': 0.6937162929680198}
+12/25/2021 05:31:30 - INFO - codeparrot_training - Step 17115: {'lr': 0.000370445325135491, 'samples': 8763392, 'steps': 17115, 'batch_loss/train': 0.6918797986581922}
+12/25/2021 05:31:44 - INFO - codeparrot_training - Step 17116: {'lr': 0.0003704315117956623, 'samples': 8763904, 'steps': 17116, 'batch_loss/train': 0.8787906486541033}
+12/25/2021 05:31:54 - INFO - codeparrot_training - Step 17117: {'lr': 0.00037041769797704335, 'samples': 8764416, 'steps': 17117, 'batch_loss/train': 0.7820621030405164}
+12/25/2021 05:32:05 - INFO - codeparrot_training - Step 17118: {'lr': 0.00037040388367968915, 'samples': 8764928, 'steps': 17118, 'batch_loss/train': 0.7833555764518678}
+12/25/2021 05:32:17 - INFO - codeparrot_training - Step 17119: {'lr': 0.00037039006890365455, 'samples': 8765440, 'steps': 17119, 'batch_loss/train': 0.8891285564750433}
+12/25/2021 05:32:28 - INFO - codeparrot_training - Step 17120: {'lr': 0.0003703762536489944, 'samples': 8765952, 'steps': 17120, 'batch_loss/train': 0.7905563646927476}
+12/25/2021 05:32:38 - INFO - codeparrot_training - Step 17121: {'lr': 0.0003703624379157639, 'samples': 8766464, 'steps': 17121, 'batch_loss/train': 0.831133765168488}
+12/25/2021 05:32:50 - INFO - codeparrot_training - Step 17122: {'lr': 0.0003703486217040177, 'samples': 8766976, 'steps': 17122, 'batch_loss/train': 0.8065251596271992}
+12/25/2021 05:33:01 - INFO - codeparrot_training - Step 17123: {'lr': 0.00037033480501381076, 'samples': 8767488, 'steps': 17123, 'batch_loss/train': 0.865512371994555}
+12/25/2021 05:33:11 - INFO - codeparrot_training - Step 17124: {'lr': 0.0003703209878451982, 'samples': 8768000, 'steps': 17124, 'batch_loss/train': 0.7592856697738171}
+12/25/2021 05:33:22 - INFO - codeparrot_training - Step 17125: {'lr': 0.00037030717019823474, 'samples': 8768512, 'steps': 17125, 'batch_loss/train': 0.7127336743287742}
+12/25/2021 05:33:36 - INFO - codeparrot_training - Step 17126: {'lr': 0.00037029335207297543, 'samples': 8769024, 'steps': 17126, 'batch_loss/train': 0.8838270250707865}
+12/25/2021 05:33:47 - INFO - codeparrot_training - Step 17127: {'lr': 0.00037027953346947513, 'samples': 8769536, 'steps': 17127, 'batch_loss/train': 0.7983716493472457}
+12/25/2021 05:33:57 - INFO - codeparrot_training - Step 17128: {'lr': 0.0003702657143877889, 'samples': 8770048, 'steps': 17128, 'batch_loss/train': 0.8672707006335258}
+12/25/2021 05:34:09 - INFO - codeparrot_training - Step 17129: {'lr': 0.00037025189482797153, 'samples': 8770560, 'steps': 17129, 'batch_loss/train': 0.8403270551934838}
+12/25/2021 05:34:20 - INFO - codeparrot_training - Step 17130: {'lr': 0.00037023807479007805, 'samples': 8771072, 'steps': 17130, 'batch_loss/train': 0.7310327524319291}
+12/25/2021 05:34:31 - INFO - codeparrot_training - Step 17131: {'lr': 0.0003702242542741634, 'samples': 8771584, 'steps': 17131, 'batch_loss/train': 0.5109979594126344}
+12/25/2021 05:34:41 - INFO - codeparrot_training - Step 17132: {'lr': 0.00037021043328028247, 'samples': 8772096, 'steps': 17132, 'batch_loss/train': 0.770905896788463}
+12/25/2021 05:34:53 - INFO - codeparrot_training - Step 17133: {'lr': 0.00037019661180849025, 'samples': 8772608, 'steps': 17133, 'batch_loss/train': 0.8295010104775429}
+12/25/2021 05:35:04 - INFO - codeparrot_training - Step 17134: {'lr': 0.0003701827898588417, 'samples': 8773120, 'steps': 17134, 'batch_loss/train': 0.8354463633149862}
+12/25/2021 05:35:15 - INFO - codeparrot_training - Step 17135: {'lr': 0.0003701689674313918, 'samples': 8773632, 'steps': 17135, 'batch_loss/train': 0.7758597326464951}
+12/25/2021 05:35:28 - INFO - codeparrot_training - Step 17136: {'lr': 0.0003701551445261954, 'samples': 8774144, 'steps': 17136, 'batch_loss/train': 0.8007802008651197}
+12/25/2021 05:35:39 - INFO - codeparrot_training - Step 17137: {'lr': 0.0003701413211433076, 'samples': 8774656, 'steps': 17137, 'batch_loss/train': 0.9960801098495722}
+12/25/2021 05:35:50 - INFO - codeparrot_training - Step 17138: {'lr': 0.0003701274972827832, 'samples': 8775168, 'steps': 17138, 'batch_loss/train': 0.7930916622281075}
+12/25/2021 05:36:02 - INFO - codeparrot_training - Step 17139: {'lr': 0.00037011367294467724, 'samples': 8775680, 'steps': 17139, 'batch_loss/train': 0.7727675884962082}
+12/25/2021 05:36:12 - INFO - codeparrot_training - Step 17140: {'lr': 0.0003700998481290446, 'samples': 8776192, 'steps': 17140, 'batch_loss/train': 1.0492531957570463}
+12/25/2021 05:36:23 - INFO - codeparrot_training - Step 17141: {'lr': 0.00037008602283594043, 'samples': 8776704, 'steps': 17141, 'batch_loss/train': 0.7697528246790171}
+12/25/2021 05:36:34 - INFO - codeparrot_training - Step 17142: {'lr': 0.0003700721970654196, 'samples': 8777216, 'steps': 17142, 'batch_loss/train': 0.7902096423786134}
+12/25/2021 05:36:46 - INFO - codeparrot_training - Step 17143: {'lr': 0.00037005837081753693, 'samples': 8777728, 'steps': 17143, 'batch_loss/train': 0.793646652251482}
+12/25/2021 05:36:56 - INFO - codeparrot_training - Step 17144: {'lr': 0.00037004454409234755, 'samples': 8778240, 'steps': 17144, 'batch_loss/train': 0.8268961990252137}
+12/25/2021 05:37:07 - INFO - codeparrot_training - Step 17145: {'lr': 0.00037003071688990636, 'samples': 8778752, 'steps': 17145, 'batch_loss/train': 0.8262108414201066}
+12/25/2021 05:37:21 - INFO - codeparrot_training - Step 17146: {'lr': 0.00037001688921026844, 'samples': 8779264, 'steps': 17146, 'batch_loss/train': 0.7126466673798859}
+12/25/2021 05:37:31 - INFO - codeparrot_training - Step 17147: {'lr': 0.0003700030610534886, 'samples': 8779776, 'steps': 17147, 'batch_loss/train': 0.8005399061366916}
+12/25/2021 05:37:42 - INFO - codeparrot_training - Step 17148: {'lr': 0.000369989232419622, 'samples': 8780288, 'steps': 17148, 'batch_loss/train': 0.8152961293235421}
+12/25/2021 05:37:54 - INFO - codeparrot_training - Step 17149: {'lr': 0.0003699754033087235, 'samples': 8780800, 'steps': 17149, 'batch_loss/train': 0.754080421756953}
+12/25/2021 05:38:05 - INFO - codeparrot_training - Step 17150: {'lr': 0.00036996157372084804, 'samples': 8781312, 'steps': 17150, 'batch_loss/train': 0.7759597929543816}
+12/25/2021 05:38:16 - INFO - codeparrot_training - Step 17151: {'lr': 0.00036994774365605067, 'samples': 8781824, 'steps': 17151, 'batch_loss/train': 0.6168080973438919}
+12/25/2021 05:38:28 - INFO - codeparrot_training - Step 17152: {'lr': 0.0003699339131143864, 'samples': 8782336, 'steps': 17152, 'batch_loss/train': 0.6827954089385457}
+12/25/2021 05:38:38 - INFO - codeparrot_training - Step 17153: {'lr': 0.00036992008209591013, 'samples': 8782848, 'steps': 17153, 'batch_loss/train': 0.737398182740435}
+12/25/2021 05:38:49 - INFO - codeparrot_training - Step 17154: {'lr': 0.0003699062506006769, 'samples': 8783360, 'steps': 17154, 'batch_loss/train': 0.7487293141894042}
+12/25/2021 05:38:59 - INFO - codeparrot_training - Step 17155: {'lr': 0.00036989241862874167, 'samples': 8783872, 'steps': 17155, 'batch_loss/train': 0.827027621679008}
+12/25/2021 05:39:13 - INFO - codeparrot_training - Step 17156: {'lr': 0.0003698785861801595, 'samples': 8784384, 'steps': 17156, 'batch_loss/train': 0.8330007204785943}
+12/25/2021 05:39:24 - INFO - codeparrot_training - Step 17157: {'lr': 0.00036986475325498537, 'samples': 8784896, 'steps': 17157, 'batch_loss/train': 0.7616052106022835}
+12/25/2021 05:39:34 - INFO - codeparrot_training - Step 17158: {'lr': 0.00036985091985327414, 'samples': 8785408, 'steps': 17158, 'batch_loss/train': 0.8466999679803848}
+12/25/2021 05:39:47 - INFO - codeparrot_training - Step 17159: {'lr': 0.000369837085975081, 'samples': 8785920, 'steps': 17159, 'batch_loss/train': 0.790565887466073}
+12/25/2021 05:39:57 - INFO - codeparrot_training - Step 17160: {'lr': 0.00036982325162046077, 'samples': 8786432, 'steps': 17160, 'batch_loss/train': 0.8181645576842129}
+12/25/2021 05:40:08 - INFO - codeparrot_training - Step 17161: {'lr': 0.00036980941678946863, 'samples': 8786944, 'steps': 17161, 'batch_loss/train': 0.782793365418911}
+12/25/2021 05:40:20 - INFO - codeparrot_training - Step 17162: {'lr': 0.0003697955814821594, 'samples': 8787456, 'steps': 17162, 'batch_loss/train': 0.8024579202756286}
+12/25/2021 05:40:31 - INFO - codeparrot_training - Step 17163: {'lr': 0.00036978174569858823, 'samples': 8787968, 'steps': 17163, 'batch_loss/train': 0.7688863810617477}
+12/25/2021 05:40:41 - INFO - codeparrot_training - Step 17164: {'lr': 0.0003697679094388101, 'samples': 8788480, 'steps': 17164, 'batch_loss/train': 0.7994425594806671}
+12/25/2021 05:40:52 - INFO - codeparrot_training - Step 17165: {'lr': 0.0003697540727028799, 'samples': 8788992, 'steps': 17165, 'batch_loss/train': 0.8119599288329482}
+12/25/2021 05:41:06 - INFO - codeparrot_training - Step 17166: {'lr': 0.00036974023549085275, 'samples': 8789504, 'steps': 17166, 'batch_loss/train': 0.7908940459601581}
+12/25/2021 05:41:16 - INFO - codeparrot_training - Step 17167: {'lr': 0.0003697263978027836, 'samples': 8790016, 'steps': 17167, 'batch_loss/train': 0.787070064805448}
+12/25/2021 05:41:27 - INFO - codeparrot_training - Step 17168: {'lr': 0.00036971255963872757, 'samples': 8790528, 'steps': 17168, 'batch_loss/train': 0.8024102123454213}
+12/25/2021 05:41:39 - INFO - codeparrot_training - Step 17169: {'lr': 0.00036969872099873956, 'samples': 8791040, 'steps': 17169, 'batch_loss/train': 0.7616748907603323}
+12/25/2021 05:41:49 - INFO - codeparrot_training - Step 17170: {'lr': 0.0003696848818828746, 'samples': 8791552, 'steps': 17170, 'batch_loss/train': 1.2399832950904965}
+12/25/2021 05:42:00 - INFO - codeparrot_training - Step 17171: {'lr': 0.0003696710422911879, 'samples': 8792064, 'steps': 17171, 'batch_loss/train': 0.8060918838018551}
+12/25/2021 05:42:14 - INFO - codeparrot_training - Step 17172: {'lr': 0.00036965720222373414, 'samples': 8792576, 'steps': 17172, 'batch_loss/train': 0.8064326541498303}
+12/25/2021 05:42:24 - INFO - codeparrot_training - Step 17173: {'lr': 0.00036964336168056854, 'samples': 8793088, 'steps': 17173, 'batch_loss/train': 0.8085316345095634}
+12/25/2021 05:42:35 - INFO - codeparrot_training - Step 17174: {'lr': 0.00036962952066174626, 'samples': 8793600, 'steps': 17174, 'batch_loss/train': 0.7349209170788527}
+12/25/2021 05:42:46 - INFO - codeparrot_training - Step 17175: {'lr': 0.0003696156791673221, 'samples': 8794112, 'steps': 17175, 'batch_loss/train': 0.8086433010175824}
+12/25/2021 05:42:58 - INFO - codeparrot_training - Step 17176: {'lr': 0.00036960183719735105, 'samples': 8794624, 'steps': 17176, 'batch_loss/train': 0.769500915077515}
+12/25/2021 05:43:08 - INFO - codeparrot_training - Step 17177: {'lr': 0.00036958799475188844, 'samples': 8795136, 'steps': 17177, 'batch_loss/train': 1.007725934498012}
+12/25/2021 05:43:19 - INFO - codeparrot_training - Step 17178: {'lr': 0.000369574151830989, 'samples': 8795648, 'steps': 17178, 'batch_loss/train': 0.7485896209254861}
+12/25/2021 05:43:31 - INFO - codeparrot_training - Step 17179: {'lr': 0.0003695603084347079, 'samples': 8796160, 'steps': 17179, 'batch_loss/train': 0.7761750807985663}
+12/25/2021 05:43:42 - INFO - codeparrot_training - Step 17180: {'lr': 0.00036954646456310023, 'samples': 8796672, 'steps': 17180, 'batch_loss/train': 0.7554480084218085}
+12/25/2021 05:43:52 - INFO - codeparrot_training - Step 17181: {'lr': 0.0003695326202162209, 'samples': 8797184, 'steps': 17181, 'batch_loss/train': 0.7695747809484601}
+12/25/2021 05:44:04 - INFO - codeparrot_training - Step 17182: {'lr': 0.0003695187753941249, 'samples': 8797696, 'steps': 17182, 'batch_loss/train': 0.8344891214510426}
+12/25/2021 05:44:15 - INFO - codeparrot_training - Step 17183: {'lr': 0.00036950493009686746, 'samples': 8798208, 'steps': 17183, 'batch_loss/train': 0.8149739978834987}
+12/25/2021 05:44:25 - INFO - codeparrot_training - Step 17184: {'lr': 0.0003694910843245036, 'samples': 8798720, 'steps': 17184, 'batch_loss/train': 0.9017830584198236}
+12/25/2021 05:44:39 - INFO - codeparrot_training - Step 17185: {'lr': 0.0003694772380770882, 'samples': 8799232, 'steps': 17185, 'batch_loss/train': 0.7965011243941262}
+12/25/2021 05:44:50 - INFO - codeparrot_training - Step 17186: {'lr': 0.0003694633913546765, 'samples': 8799744, 'steps': 17186, 'batch_loss/train': 0.7136217532679439}
+12/25/2021 05:45:01 - INFO - codeparrot_training - Step 17187: {'lr': 0.0003694495441573235, 'samples': 8800256, 'steps': 17187, 'batch_loss/train': 0.7999111721292138}
+12/25/2021 05:45:11 - INFO - codeparrot_training - Step 17188: {'lr': 0.0003694356964850841, 'samples': 8800768, 'steps': 17188, 'batch_loss/train': 0.6560873351991177}
+12/25/2021 05:45:23 - INFO - codeparrot_training - Step 17189: {'lr': 0.0003694218483380136, 'samples': 8801280, 'steps': 17189, 'batch_loss/train': 0.7716332674026489}
+12/25/2021 05:45:34 - INFO - codeparrot_training - Step 17190: {'lr': 0.00036940799971616677, 'samples': 8801792, 'steps': 17190, 'batch_loss/train': 0.810953987762332}
+12/25/2021 05:45:44 - INFO - codeparrot_training - Step 17191: {'lr': 0.0003693941506195989, 'samples': 8802304, 'steps': 17191, 'batch_loss/train': 0.756384102627635}
+12/25/2021 05:45:57 - INFO - codeparrot_training - Step 17192: {'lr': 0.000369380301048365, 'samples': 8802816, 'steps': 17192, 'batch_loss/train': 0.8056000221986324}
+12/25/2021 05:46:07 - INFO - codeparrot_training - Step 17193: {'lr': 0.0003693664510025201, 'samples': 8803328, 'steps': 17193, 'batch_loss/train': 0.8632957097142935}
+12/25/2021 05:46:18 - INFO - codeparrot_training - Step 17194: {'lr': 0.0003693526004821192, 'samples': 8803840, 'steps': 17194, 'batch_loss/train': 0.9539960715919733}
+12/25/2021 05:46:32 - INFO - codeparrot_training - Step 17195: {'lr': 0.0003693387494872174, 'samples': 8804352, 'steps': 17195, 'batch_loss/train': 0.9601670550182462}
+12/25/2021 05:46:42 - INFO - codeparrot_training - Step 17196: {'lr': 0.0003693248980178699, 'samples': 8804864, 'steps': 17196, 'batch_loss/train': 0.6505533329909667}
+12/25/2021 05:46:53 - INFO - codeparrot_training - Step 17197: {'lr': 0.0003693110460741316, 'samples': 8805376, 'steps': 17197, 'batch_loss/train': 0.8875416368246078}
+12/25/2021 05:47:05 - INFO - codeparrot_training - Step 17198: {'lr': 0.00036929719365605765, 'samples': 8805888, 'steps': 17198, 'batch_loss/train': 0.8395707728341222}
+12/25/2021 05:47:15 - INFO - codeparrot_training - Step 17199: {'lr': 0.00036928334076370304, 'samples': 8806400, 'steps': 17199, 'batch_loss/train': 0.8049160344526172}
+12/25/2021 05:47:26 - INFO - codeparrot_training - Step 17200: {'lr': 0.000369269487397123, 'samples': 8806912, 'steps': 17200, 'batch_loss/train': 0.7998269181698561}
+12/25/2021 05:47:37 - INFO - codeparrot_training - Step 17201: {'lr': 0.00036925563355637243, 'samples': 8807424, 'steps': 17201, 'batch_loss/train': 0.9319567214697599}
+12/25/2021 05:47:51 - INFO - codeparrot_training - Step 17202: {'lr': 0.0003692417792415066, 'samples': 8807936, 'steps': 17202, 'batch_loss/train': 0.7968158777803183}
+12/25/2021 05:48:01 - INFO - codeparrot_training - Step 17203: {'lr': 0.0003692279244525804, 'samples': 8808448, 'steps': 17203, 'batch_loss/train': 0.8134445394389331}
+12/25/2021 05:48:12 - INFO - codeparrot_training - Step 17204: {'lr': 0.000369214069189649, 'samples': 8808960, 'steps': 17204, 'batch_loss/train': 0.7873349864967167}
+12/25/2021 05:48:24 - INFO - codeparrot_training - Step 17205: {'lr': 0.0003692002134527674, 'samples': 8809472, 'steps': 17205, 'batch_loss/train': 0.8352088769897819}
+12/25/2021 05:48:34 - INFO - codeparrot_training - Step 17206: {'lr': 0.0003691863572419909, 'samples': 8809984, 'steps': 17206, 'batch_loss/train': 0.7591881887055933}
+12/25/2021 05:48:45 - INFO - codeparrot_training - Step 17207: {'lr': 0.0003691725005573744, 'samples': 8810496, 'steps': 17207, 'batch_loss/train': 0.8510277699679136}
+12/25/2021 05:48:57 - INFO - codeparrot_training - Step 17208: {'lr': 0.000369158643398973, 'samples': 8811008, 'steps': 17208, 'batch_loss/train': 0.6452690217993222}
+12/25/2021 05:49:08 - INFO - codeparrot_training - Step 17209: {'lr': 0.00036914478576684185, 'samples': 8811520, 'steps': 17209, 'batch_loss/train': 0.8176303561776876}
+12/25/2021 05:49:18 - INFO - codeparrot_training - Step 17210: {'lr': 0.000369130927661036, 'samples': 8812032, 'steps': 17210, 'batch_loss/train': 0.8321163556538522}
+12/25/2021 05:49:29 - INFO - codeparrot_training - Step 17211: {'lr': 0.00036911706908161057, 'samples': 8812544, 'steps': 17211, 'batch_loss/train': 0.84617964271456}
+12/25/2021 05:49:43 - INFO - codeparrot_training - Step 17212: {'lr': 0.0003691032100286207, 'samples': 8813056, 'steps': 17212, 'batch_loss/train': 0.725850717164576}
+12/25/2021 05:49:53 - INFO - codeparrot_training - Step 17213: {'lr': 0.0003690893505021214, 'samples': 8813568, 'steps': 17213, 'batch_loss/train': 0.813361641485244}
+12/25/2021 05:50:04 - INFO - codeparrot_training - Step 17214: {'lr': 0.0003690754905021677, 'samples': 8814080, 'steps': 17214, 'batch_loss/train': 0.759377745911479}
+12/25/2021 05:50:16 - INFO - codeparrot_training - Step 17215: {'lr': 0.000369061630028815, 'samples': 8814592, 'steps': 17215, 'batch_loss/train': 0.8136732103303075}
+12/25/2021 05:50:27 - INFO - codeparrot_training - Step 17216: {'lr': 0.00036904776908211815, 'samples': 8815104, 'steps': 17216, 'batch_loss/train': 0.6879623420536518}
+12/25/2021 05:50:37 - INFO - codeparrot_training - Step 17217: {'lr': 0.0003690339076621323, 'samples': 8815616, 'steps': 17217, 'batch_loss/train': 0.8923871610313654}
+12/25/2021 05:50:50 - INFO - codeparrot_training - Step 17218: {'lr': 0.00036902004576891255, 'samples': 8816128, 'steps': 17218, 'batch_loss/train': 0.8098624097183347}
+12/25/2021 05:51:00 - INFO - codeparrot_training - Step 17219: {'lr': 0.000369006183402514, 'samples': 8816640, 'steps': 17219, 'batch_loss/train': 0.7620040588080883}
+12/25/2021 05:51:11 - INFO - codeparrot_training - Step 17220: {'lr': 0.00036899232056299196, 'samples': 8817152, 'steps': 17220, 'batch_loss/train': 0.7384964972734451}
+12/25/2021 05:51:21 - INFO - codeparrot_training - Step 17221: {'lr': 0.00036897845725040123, 'samples': 8817664, 'steps': 17221, 'batch_loss/train': 0.7824685508385301}
+12/25/2021 05:51:33 - INFO - codeparrot_training - Step 17222: {'lr': 0.00036896459346479716, 'samples': 8818176, 'steps': 17222, 'batch_loss/train': 0.7398649463430047}
+12/25/2021 05:51:44 - INFO - codeparrot_training - Step 17223: {'lr': 0.0003689507292062348, 'samples': 8818688, 'steps': 17223, 'batch_loss/train': 0.7668903039302677}
+12/25/2021 05:51:55 - INFO - codeparrot_training - Step 17224: {'lr': 0.0003689368644747692, 'samples': 8819200, 'steps': 17224, 'batch_loss/train': 0.8208004613406956}
+12/25/2021 05:52:09 - INFO - codeparrot_training - Step 17225: {'lr': 0.00036892299927045554, 'samples': 8819712, 'steps': 17225, 'batch_loss/train': 0.5844693616963923}
+12/25/2021 05:52:19 - INFO - codeparrot_training - Step 17226: {'lr': 0.000368909133593349, 'samples': 8820224, 'steps': 17226, 'batch_loss/train': 0.8876215191558003}
+12/25/2021 05:52:30 - INFO - codeparrot_training - Step 17227: {'lr': 0.00036889526744350457, 'samples': 8820736, 'steps': 17227, 'batch_loss/train': 0.8609638772904873}
+12/25/2021 05:52:42 - INFO - codeparrot_training - Step 17228: {'lr': 0.0003688814008209775, 'samples': 8821248, 'steps': 17228, 'batch_loss/train': 0.7903991714119911}
+12/25/2021 05:52:52 - INFO - codeparrot_training - Step 17229: {'lr': 0.0003688675337258228, 'samples': 8821760, 'steps': 17229, 'batch_loss/train': 0.7894077077507973}
+12/25/2021 05:53:03 - INFO - codeparrot_training - Step 17230: {'lr': 0.00036885366615809574, 'samples': 8822272, 'steps': 17230, 'batch_loss/train': 0.7709722374565899}
+12/25/2021 05:53:15 - INFO - codeparrot_training - Step 17231: {'lr': 0.00036883979811785136, 'samples': 8822784, 'steps': 17231, 'batch_loss/train': 0.8407090781256557}
+12/25/2021 05:53:26 - INFO - codeparrot_training - Step 17232: {'lr': 0.0003688259296051448, 'samples': 8823296, 'steps': 17232, 'batch_loss/train': 0.7226608591154218}
+12/25/2021 05:53:36 - INFO - codeparrot_training - Step 17233: {'lr': 0.0003688120606200312, 'samples': 8823808, 'steps': 17233, 'batch_loss/train': 0.6584227411076427}
+12/25/2021 05:53:47 - INFO - codeparrot_training - Step 17234: {'lr': 0.00036879819116256575, 'samples': 8824320, 'steps': 17234, 'batch_loss/train': 0.7364468658342957}
+12/25/2021 05:54:01 - INFO - codeparrot_training - Step 17235: {'lr': 0.0003687843212328035, 'samples': 8824832, 'steps': 17235, 'batch_loss/train': 0.8319362620823085}
+12/25/2021 05:54:11 - INFO - codeparrot_training - Step 17236: {'lr': 0.0003687704508307997, 'samples': 8825344, 'steps': 17236, 'batch_loss/train': 0.8988587693311274}
+12/25/2021 05:54:22 - INFO - codeparrot_training - Step 17237: {'lr': 0.0003687565799566094, 'samples': 8825856, 'steps': 17237, 'batch_loss/train': 0.8252285839989781}
+12/25/2021 05:54:34 - INFO - codeparrot_training - Step 17238: {'lr': 0.00036874270861028777, 'samples': 8826368, 'steps': 17238, 'batch_loss/train': 0.8260625600814819}
+12/25/2021 05:54:45 - INFO - codeparrot_training - Step 17239: {'lr': 0.00036872883679189004, 'samples': 8826880, 'steps': 17239, 'batch_loss/train': 0.838415885809809}
+12/25/2021 05:54:55 - INFO - codeparrot_training - Step 17240: {'lr': 0.0003687149645014711, 'samples': 8827392, 'steps': 17240, 'batch_loss/train': 0.8419815097004175}
+12/25/2021 05:55:09 - INFO - codeparrot_training - Step 17241: {'lr': 0.0003687010917390865, 'samples': 8827904, 'steps': 17241, 'batch_loss/train': 0.8275818657130003}
+12/25/2021 05:55:20 - INFO - codeparrot_training - Step 17242: {'lr': 0.00036868721850479106, 'samples': 8828416, 'steps': 17242, 'batch_loss/train': 0.7847740761935711}
+12/25/2021 05:55:30 - INFO - codeparrot_training - Step 17243: {'lr': 0.0003686733447986401, 'samples': 8828928, 'steps': 17243, 'batch_loss/train': 0.8192842146381736}
+12/25/2021 05:55:41 - INFO - codeparrot_training - Step 17244: {'lr': 0.00036865947062068865, 'samples': 8829440, 'steps': 17244, 'batch_loss/train': 0.7871213546022773}
+12/25/2021 05:55:54 - INFO - codeparrot_training - Step 17245: {'lr': 0.00036864559597099203, 'samples': 8829952, 'steps': 17245, 'batch_loss/train': 0.7378698829561472}
+12/25/2021 05:56:04 - INFO - codeparrot_training - Step 17246: {'lr': 0.0003686317208496053, 'samples': 8830464, 'steps': 17246, 'batch_loss/train': 0.9209167528897524}
+12/25/2021 05:56:15 - INFO - codeparrot_training - Step 17247: {'lr': 0.0003686178452565836, 'samples': 8830976, 'steps': 17247, 'batch_loss/train': 0.8059413126902655}
+12/25/2021 05:56:27 - INFO - codeparrot_training - Step 17248: {'lr': 0.00036860396919198227, 'samples': 8831488, 'steps': 17248, 'batch_loss/train': 0.8309496017172933}
+12/25/2021 05:56:38 - INFO - codeparrot_training - Step 17249: {'lr': 0.0003685900926558562, 'samples': 8832000, 'steps': 17249, 'batch_loss/train': 0.8492163764312863}
+12/25/2021 05:56:48 - INFO - codeparrot_training - Step 17250: {'lr': 0.0003685762156482607, 'samples': 8832512, 'steps': 17250, 'batch_loss/train': 0.8308644741773605}
+12/25/2021 05:56:59 - INFO - codeparrot_training - Step 17251: {'lr': 0.000368562338169251, 'samples': 8833024, 'steps': 17251, 'batch_loss/train': 0.8423826210200787}
+12/25/2021 05:57:12 - INFO - codeparrot_training - Step 17252: {'lr': 0.00036854846021888227, 'samples': 8833536, 'steps': 17252, 'batch_loss/train': 0.8134873230010271}
+12/25/2021 05:57:22 - INFO - codeparrot_training - Step 17253: {'lr': 0.0003685345817972095, 'samples': 8834048, 'steps': 17253, 'batch_loss/train': 0.7132485271431506}
+12/25/2021 05:57:33 - INFO - codeparrot_training - Step 17254: {'lr': 0.00036852070290428805, 'samples': 8834560, 'steps': 17254, 'batch_loss/train': 0.8196551776491106}
+12/25/2021 05:57:45 - INFO - codeparrot_training - Step 17255: {'lr': 0.00036850682354017307, 'samples': 8835072, 'steps': 17255, 'batch_loss/train': 0.8841849556192756}
+12/25/2021 05:57:56 - INFO - codeparrot_training - Step 17256: {'lr': 0.0003684929437049196, 'samples': 8835584, 'steps': 17256, 'batch_loss/train': 0.8413330428302288}
+12/25/2021 05:58:06 - INFO - codeparrot_training - Step 17257: {'lr': 0.000368479063398583, 'samples': 8836096, 'steps': 17257, 'batch_loss/train': 0.6746061585145071}
+12/25/2021 05:58:18 - INFO - codeparrot_training - Step 17258: {'lr': 0.0003684651826212184, 'samples': 8836608, 'steps': 17258, 'batch_loss/train': 0.7552834236994386}
+12/25/2021 05:58:29 - INFO - codeparrot_training - Step 17259: {'lr': 0.0003684513013728809, 'samples': 8837120, 'steps': 17259, 'batch_loss/train': 0.777313694357872}
+12/25/2021 05:58:40 - INFO - codeparrot_training - Step 17260: {'lr': 0.00036843741965362576, 'samples': 8837632, 'steps': 17260, 'batch_loss/train': 0.7562119869980961}
+12/25/2021 05:58:52 - INFO - codeparrot_training - Step 17261: {'lr': 0.00036842353746350826, 'samples': 8838144, 'steps': 17261, 'batch_loss/train': 0.8283456321805716}
+12/25/2021 05:59:03 - INFO - codeparrot_training - Step 17262: {'lr': 0.00036840965480258335, 'samples': 8838656, 'steps': 17262, 'batch_loss/train': 0.8363459454849362}
+12/25/2021 05:59:14 - INFO - codeparrot_training - Step 17263: {'lr': 0.0003683957716709064, 'samples': 8839168, 'steps': 17263, 'batch_loss/train': 0.9010779391974211}
+12/25/2021 05:59:24 - INFO - codeparrot_training - Step 17264: {'lr': 0.0003683818880685327, 'samples': 8839680, 'steps': 17264, 'batch_loss/train': 0.7892210716381669}
+12/25/2021 05:59:36 - INFO - codeparrot_training - Step 17265: {'lr': 0.0003683680039955172, 'samples': 8840192, 'steps': 17265, 'batch_loss/train': 0.7559919310733676}
+12/25/2021 05:59:47 - INFO - codeparrot_training - Step 17266: {'lr': 0.00036835411945191515, 'samples': 8840704, 'steps': 17266, 'batch_loss/train': 0.781342061702162}
+12/25/2021 05:59:57 - INFO - codeparrot_training - Step 17267: {'lr': 0.0003683402344377819, 'samples': 8841216, 'steps': 17267, 'batch_loss/train': 0.8051368105225265}
+12/25/2021 06:00:10 - INFO - codeparrot_training - Step 17268: {'lr': 0.00036832634895317255, 'samples': 8841728, 'steps': 17268, 'batch_loss/train': 0.9045368121005595}
+12/25/2021 06:00:20 - INFO - codeparrot_training - Step 17269: {'lr': 0.00036831246299814225, 'samples': 8842240, 'steps': 17269, 'batch_loss/train': 0.8010994454380125}
+12/25/2021 06:00:31 - INFO - codeparrot_training - Step 17270: {'lr': 0.00036829857657274634, 'samples': 8842752, 'steps': 17270, 'batch_loss/train': 0.9919133512303233}
+12/25/2021 06:00:44 - INFO - codeparrot_training - Step 17271: {'lr': 0.00036828468967704, 'samples': 8843264, 'steps': 17271, 'batch_loss/train': 0.6956812762655318}
+12/25/2021 06:00:54 - INFO - codeparrot_training - Step 17272: {'lr': 0.0003682708023110783, 'samples': 8843776, 'steps': 17272, 'batch_loss/train': 0.7350250878371298}
+12/25/2021 06:01:05 - INFO - codeparrot_training - Step 17273: {'lr': 0.0003682569144749166, 'samples': 8844288, 'steps': 17273, 'batch_loss/train': 0.647052991669625}
+12/25/2021 06:01:15 - INFO - codeparrot_training - Step 17274: {'lr': 0.00036824302616861006, 'samples': 8844800, 'steps': 17274, 'batch_loss/train': 0.8193786414340138}
+12/25/2021 06:01:27 - INFO - codeparrot_training - Step 17275: {'lr': 0.00036822913739221384, 'samples': 8845312, 'steps': 17275, 'batch_loss/train': 0.8136151032522321}
+12/25/2021 06:01:38 - INFO - codeparrot_training - Step 17276: {'lr': 0.0003682152481457833, 'samples': 8845824, 'steps': 17276, 'batch_loss/train': 0.8512329300865531}
+12/25/2021 06:01:49 - INFO - codeparrot_training - Step 17277: {'lr': 0.00036820135842937344, 'samples': 8846336, 'steps': 17277, 'batch_loss/train': 0.7783723613247275}
+12/25/2021 06:02:01 - INFO - codeparrot_training - Step 17278: {'lr': 0.00036818746824303974, 'samples': 8846848, 'steps': 17278, 'batch_loss/train': 0.776592331007123}
+12/25/2021 06:02:11 - INFO - codeparrot_training - Step 17279: {'lr': 0.0003681735775868372, 'samples': 8847360, 'steps': 17279, 'batch_loss/train': 0.9105262234807014}
+12/25/2021 06:02:22 - INFO - codeparrot_training - Step 17280: {'lr': 0.00036815968646082125, 'samples': 8847872, 'steps': 17280, 'batch_loss/train': 0.9032530598342419}
+12/25/2021 06:02:35 - INFO - codeparrot_training - Step 17281: {'lr': 0.0003681457948650469, 'samples': 8848384, 'steps': 17281, 'batch_loss/train': 0.7415383302140981}
+12/25/2021 06:02:45 - INFO - codeparrot_training - Step 17282: {'lr': 0.0003681319027995695, 'samples': 8848896, 'steps': 17282, 'batch_loss/train': 0.8926421753130853}
+12/25/2021 06:02:56 - INFO - codeparrot_training - Step 17283: {'lr': 0.0003681180102644443, 'samples': 8849408, 'steps': 17283, 'batch_loss/train': 0.836852471344173}
+12/25/2021 06:03:07 - INFO - codeparrot_training - Step 17284: {'lr': 0.0003681041172597264, 'samples': 8849920, 'steps': 17284, 'batch_loss/train': 0.9254018319770694}
+12/25/2021 06:03:18 - INFO - codeparrot_training - Step 17285: {'lr': 0.0003680902237854712, 'samples': 8850432, 'steps': 17285, 'batch_loss/train': 0.79186587408185}
+12/25/2021 06:03:29 - INFO - codeparrot_training - Step 17286: {'lr': 0.00036807632984173385, 'samples': 8850944, 'steps': 17286, 'batch_loss/train': 0.7811263110488653}
+12/25/2021 06:03:40 - INFO - codeparrot_training - Step 17287: {'lr': 0.00036806243542856967, 'samples': 8851456, 'steps': 17287, 'batch_loss/train': 0.7241918281652033}
+12/25/2021 06:03:52 - INFO - codeparrot_training - Step 17288: {'lr': 0.0003680485405460337, 'samples': 8851968, 'steps': 17288, 'batch_loss/train': 0.9191487282514572}
+12/25/2021 06:04:03 - INFO - codeparrot_training - Step 17289: {'lr': 0.00036803464519418133, 'samples': 8852480, 'steps': 17289, 'batch_loss/train': 0.8602727898396552}
+12/25/2021 06:04:14 - INFO - codeparrot_training - Step 17290: {'lr': 0.0003680207493730678, 'samples': 8852992, 'steps': 17290, 'batch_loss/train': 0.9003111515194178}
+12/25/2021 06:04:26 - INFO - codeparrot_training - Step 17291: {'lr': 0.00036800685308274836, 'samples': 8853504, 'steps': 17291, 'batch_loss/train': 0.9448501076549292}
+12/25/2021 06:04:36 - INFO - codeparrot_training - Step 17292: {'lr': 0.00036799295632327815, 'samples': 8854016, 'steps': 17292, 'batch_loss/train': 0.8012983910739422}
+12/25/2021 06:04:47 - INFO - codeparrot_training - Step 17293: {'lr': 0.00036797905909471257, 'samples': 8854528, 'steps': 17293, 'batch_loss/train': 0.892436935682781}
+12/25/2021 06:04:59 - INFO - codeparrot_training - Step 17294: {'lr': 0.0003679651613971068, 'samples': 8855040, 'steps': 17294, 'batch_loss/train': 0.8247943129390478}
+12/25/2021 06:05:10 - INFO - codeparrot_training - Step 17295: {'lr': 0.00036795126323051604, 'samples': 8855552, 'steps': 17295, 'batch_loss/train': 0.6962253591045737}
+12/25/2021 06:05:20 - INFO - codeparrot_training - Step 17296: {'lr': 0.00036793736459499567, 'samples': 8856064, 'steps': 17296, 'batch_loss/train': 0.8119937884621322}
+12/25/2021 06:05:31 - INFO - codeparrot_training - Step 17297: {'lr': 0.0003679234654906008, 'samples': 8856576, 'steps': 17297, 'batch_loss/train': 0.8557657487690449}
+12/25/2021 06:05:43 - INFO - codeparrot_training - Step 17298: {'lr': 0.00036790956591738677, 'samples': 8857088, 'steps': 17298, 'batch_loss/train': 0.8500382946804166}
+12/25/2021 06:05:54 - INFO - codeparrot_training - Step 17299: {'lr': 0.0003678956658754088, 'samples': 8857600, 'steps': 17299, 'batch_loss/train': 0.8305372996255755}
+12/25/2021 06:06:04 - INFO - codeparrot_training - Step 17300: {'lr': 0.0003678817653647223, 'samples': 8858112, 'steps': 17300, 'batch_loss/train': 0.769153090659529}
+12/25/2021 06:06:17 - INFO - codeparrot_training - Step 17301: {'lr': 0.0003678678643853823, 'samples': 8858624, 'steps': 17301, 'batch_loss/train': 0.8107721908017993}
+12/25/2021 06:06:28 - INFO - codeparrot_training - Step 17302: {'lr': 0.0003678539629374442, 'samples': 8859136, 'steps': 17302, 'batch_loss/train': 0.8316402575001121}
+12/25/2021 06:06:38 - INFO - codeparrot_training - Step 17303: {'lr': 0.0003678400610209632, 'samples': 8859648, 'steps': 17303, 'batch_loss/train': 0.9490910302847624}
+12/25/2021 06:06:50 - INFO - codeparrot_training - Step 17304: {'lr': 0.0003678261586359947, 'samples': 8860160, 'steps': 17304, 'batch_loss/train': 0.7164638976100832}
+12/25/2021 06:07:01 - INFO - codeparrot_training - Step 17305: {'lr': 0.00036781225578259386, 'samples': 8860672, 'steps': 17305, 'batch_loss/train': 0.7079206863418221}
+12/25/2021 06:07:12 - INFO - codeparrot_training - Step 17306: {'lr': 0.0003677983524608159, 'samples': 8861184, 'steps': 17306, 'batch_loss/train': 0.9506425615400076}
+12/25/2021 06:07:22 - INFO - codeparrot_training - Step 17307: {'lr': 0.0003677844486707163, 'samples': 8861696, 'steps': 17307, 'batch_loss/train': 0.8129914905875921}
+12/25/2021 06:07:34 - INFO - codeparrot_training - Step 17308: {'lr': 0.00036777054441235006, 'samples': 8862208, 'steps': 17308, 'batch_loss/train': 0.8563566855154932}
+12/25/2021 06:07:45 - INFO - codeparrot_training - Step 17309: {'lr': 0.0003677566396857728, 'samples': 8862720, 'steps': 17309, 'batch_loss/train': 0.8674702383577824}
+12/25/2021 06:07:55 - INFO - codeparrot_training - Step 17310: {'lr': 0.0003677427344910394, 'samples': 8863232, 'steps': 17310, 'batch_loss/train': 0.8358895787969232}
+12/25/2021 06:08:08 - INFO - codeparrot_training - Step 17311: {'lr': 0.00036772882882820545, 'samples': 8863744, 'steps': 17311, 'batch_loss/train': 0.7306287875398993}
+12/25/2021 06:08:19 - INFO - codeparrot_training - Step 17312: {'lr': 0.0003677149226973261, 'samples': 8864256, 'steps': 17312, 'batch_loss/train': 0.8093151347711682}
+12/25/2021 06:08:29 - INFO - codeparrot_training - Step 17313: {'lr': 0.00036770101609845667, 'samples': 8864768, 'steps': 17313, 'batch_loss/train': 0.8037114106118679}
+12/25/2021 06:08:41 - INFO - codeparrot_training - Step 17314: {'lr': 0.0003676871090316524, 'samples': 8865280, 'steps': 17314, 'batch_loss/train': 0.8632569825276732}
+12/25/2021 06:08:52 - INFO - codeparrot_training - Step 17315: {'lr': 0.0003676732014969687, 'samples': 8865792, 'steps': 17315, 'batch_loss/train': 0.9286961993202567}
+12/25/2021 06:09:02 - INFO - codeparrot_training - Step 17316: {'lr': 0.0003676592934944608, 'samples': 8866304, 'steps': 17316, 'batch_loss/train': 0.8093081833794713}
+12/25/2021 06:09:13 - INFO - codeparrot_training - Step 17317: {'lr': 0.00036764538502418386, 'samples': 8866816, 'steps': 17317, 'batch_loss/train': 0.9293639780953526}
+12/25/2021 06:09:26 - INFO - codeparrot_training - Step 17318: {'lr': 0.00036763147608619335, 'samples': 8867328, 'steps': 17318, 'batch_loss/train': 0.7940994258970022}
+12/25/2021 06:09:36 - INFO - codeparrot_training - Step 17319: {'lr': 0.00036761756668054454, 'samples': 8867840, 'steps': 17319, 'batch_loss/train': 0.7405308838933706}
+12/25/2021 06:09:47 - INFO - codeparrot_training - Step 17320: {'lr': 0.0003676036568072927, 'samples': 8868352, 'steps': 17320, 'batch_loss/train': 0.8616985755506903}
+12/25/2021 06:09:59 - INFO - codeparrot_training - Step 17321: {'lr': 0.00036758974646649304, 'samples': 8868864, 'steps': 17321, 'batch_loss/train': 0.807452242821455}
+12/25/2021 06:10:09 - INFO - codeparrot_training - Step 17322: {'lr': 0.00036757583565820103, 'samples': 8869376, 'steps': 17322, 'batch_loss/train': 0.8254247857257724}
+12/25/2021 06:10:20 - INFO - codeparrot_training - Step 17323: {'lr': 0.0003675619243824718, 'samples': 8869888, 'steps': 17323, 'batch_loss/train': 0.7898417352698743}
+12/25/2021 06:10:32 - INFO - codeparrot_training - Step 17324: {'lr': 0.00036754801263936084, 'samples': 8870400, 'steps': 17324, 'batch_loss/train': 0.8572938917204738}
+12/25/2021 06:10:43 - INFO - codeparrot_training - Step 17325: {'lr': 0.0003675341004289233, 'samples': 8870912, 'steps': 17325, 'batch_loss/train': 0.8903050748631358}
+12/25/2021 06:10:53 - INFO - codeparrot_training - Step 17326: {'lr': 0.00036752018775121467, 'samples': 8871424, 'steps': 17326, 'batch_loss/train': 0.7560677705332637}
+12/25/2021 06:11:06 - INFO - codeparrot_training - Step 17327: {'lr': 0.00036750627460629, 'samples': 8871936, 'steps': 17327, 'batch_loss/train': 0.7570600626058877}
+12/25/2021 06:11:17 - INFO - codeparrot_training - Step 17328: {'lr': 0.0003674923609942049, 'samples': 8872448, 'steps': 17328, 'batch_loss/train': 0.7924507949501276}
+12/25/2021 06:11:27 - INFO - codeparrot_training - Step 17329: {'lr': 0.0003674784469150144, 'samples': 8872960, 'steps': 17329, 'batch_loss/train': 0.7820098977535963}
+12/25/2021 06:11:38 - INFO - codeparrot_training - Step 17330: {'lr': 0.00036746453236877403, 'samples': 8873472, 'steps': 17330, 'batch_loss/train': 0.7168837389908731}
+12/25/2021 06:11:50 - INFO - codeparrot_training - Step 17331: {'lr': 0.000367450617355539, 'samples': 8873984, 'steps': 17331, 'batch_loss/train': 1.0078589647309855}
+12/25/2021 06:12:01 - INFO - codeparrot_training - Step 17332: {'lr': 0.00036743670187536464, 'samples': 8874496, 'steps': 17332, 'batch_loss/train': 0.8487690822221339}
+12/25/2021 06:12:12 - INFO - codeparrot_training - Step 17333: {'lr': 0.0003674227859283064, 'samples': 8875008, 'steps': 17333, 'batch_loss/train': 0.6980200614780188}
+12/25/2021 06:12:24 - INFO - codeparrot_training - Step 17334: {'lr': 0.0003674088695144194, 'samples': 8875520, 'steps': 17334, 'batch_loss/train': 0.8561439355835319}
+12/25/2021 06:12:34 - INFO - codeparrot_training - Step 17335: {'lr': 0.0003673949526337591, 'samples': 8876032, 'steps': 17335, 'batch_loss/train': 0.7016499261371791}
+12/25/2021 06:12:45 - INFO - codeparrot_training - Step 17336: {'lr': 0.00036738103528638076, 'samples': 8876544, 'steps': 17336, 'batch_loss/train': 0.648280308349058}
+12/25/2021 06:12:57 - INFO - codeparrot_training - Step 17337: {'lr': 0.0003673671174723398, 'samples': 8877056, 'steps': 17337, 'batch_loss/train': 0.8724385090172291}
+12/25/2021 06:13:07 - INFO - codeparrot_training - Step 17338: {'lr': 0.00036735319919169147, 'samples': 8877568, 'steps': 17338, 'batch_loss/train': 0.8258048743009567}
+12/25/2021 06:13:18 - INFO - codeparrot_training - Step 17339: {'lr': 0.00036733928044449114, 'samples': 8878080, 'steps': 17339, 'batch_loss/train': 0.8446066798642278}
+12/25/2021 06:13:29 - INFO - codeparrot_training - Step 17340: {'lr': 0.0003673253612307941, 'samples': 8878592, 'steps': 17340, 'batch_loss/train': 0.8150220136158168}
+12/25/2021 06:13:41 - INFO - codeparrot_training - Step 17341: {'lr': 0.0003673114415506558, 'samples': 8879104, 'steps': 17341, 'batch_loss/train': 0.7038753349334002}
+12/25/2021 06:13:52 - INFO - codeparrot_training - Step 17342: {'lr': 0.0003672975214041314, 'samples': 8879616, 'steps': 17342, 'batch_loss/train': 0.79065768327564}
+12/25/2021 06:14:02 - INFO - codeparrot_training - Step 17343: {'lr': 0.0003672836007912764, 'samples': 8880128, 'steps': 17343, 'batch_loss/train': 0.8401235141791403}
+12/25/2021 06:14:15 - INFO - codeparrot_training - Step 17344: {'lr': 0.00036726967971214614, 'samples': 8880640, 'steps': 17344, 'batch_loss/train': 0.8591272979974747}
+12/25/2021 06:14:25 - INFO - codeparrot_training - Step 17345: {'lr': 0.00036725575816679587, 'samples': 8881152, 'steps': 17345, 'batch_loss/train': 0.7184110749512911}
+12/25/2021 06:14:36 - INFO - codeparrot_training - Step 17346: {'lr': 0.00036724183615528095, 'samples': 8881664, 'steps': 17346, 'batch_loss/train': 0.8183328243903816}
+12/25/2021 06:14:48 - INFO - codeparrot_training - Step 17347: {'lr': 0.0003672279136776568, 'samples': 8882176, 'steps': 17347, 'batch_loss/train': 0.8509383341297507}
+12/25/2021 06:14:59 - INFO - codeparrot_training - Step 17348: {'lr': 0.0003672139907339787, 'samples': 8882688, 'steps': 17348, 'batch_loss/train': 0.7889105910435319}
+12/25/2021 06:15:10 - INFO - codeparrot_training - Step 17349: {'lr': 0.00036720006732430204, 'samples': 8883200, 'steps': 17349, 'batch_loss/train': 0.7534478532616049}
+12/25/2021 06:15:20 - INFO - codeparrot_training - Step 17350: {'lr': 0.00036718614344868216, 'samples': 8883712, 'steps': 17350, 'batch_loss/train': 0.8664698367938399}
+12/25/2021 06:15:32 - INFO - codeparrot_training - Step 17351: {'lr': 0.0003671722191071745, 'samples': 8884224, 'steps': 17351, 'batch_loss/train': 0.7885325280949473}
+12/25/2021 06:15:43 - INFO - codeparrot_training - Step 17352: {'lr': 0.00036715829429983426, 'samples': 8884736, 'steps': 17352, 'batch_loss/train': 0.677269549574703}
+12/25/2021 06:15:54 - INFO - codeparrot_training - Step 17353: {'lr': 0.0003671443690267168, 'samples': 8885248, 'steps': 17353, 'batch_loss/train': 0.7831704868003726}
+12/25/2021 06:16:06 - INFO - codeparrot_training - Step 17354: {'lr': 0.0003671304432878777, 'samples': 8885760, 'steps': 17354, 'batch_loss/train': 0.6443128366954625}
+12/25/2021 06:16:16 - INFO - codeparrot_training - Step 17355: {'lr': 0.0003671165170833721, 'samples': 8886272, 'steps': 17355, 'batch_loss/train': 0.8150873696431518}
+12/25/2021 06:16:27 - INFO - codeparrot_training - Step 17356: {'lr': 0.0003671025904132555, 'samples': 8886784, 'steps': 17356, 'batch_loss/train': 0.8245222175028175}
+12/25/2021 06:16:40 - INFO - codeparrot_training - Step 17357: {'lr': 0.00036708866327758315, 'samples': 8887296, 'steps': 17357, 'batch_loss/train': 0.7705566422082484}
+12/25/2021 06:16:50 - INFO - codeparrot_training - Step 17358: {'lr': 0.0003670747356764106, 'samples': 8887808, 'steps': 17358, 'batch_loss/train': 0.6782016432262026}
+12/25/2021 06:17:01 - INFO - codeparrot_training - Step 17359: {'lr': 0.000367060807609793, 'samples': 8888320, 'steps': 17359, 'batch_loss/train': 1.1025715228170156}
+12/25/2021 06:17:13 - INFO - codeparrot_training - Step 17360: {'lr': 0.0003670468790777859, 'samples': 8888832, 'steps': 17360, 'batch_loss/train': 0.7848197855055332}
+12/25/2021 06:17:24 - INFO - codeparrot_training - Step 17361: {'lr': 0.0003670329500804446, 'samples': 8889344, 'steps': 17361, 'batch_loss/train': 0.7547322893515229}
+12/25/2021 06:17:34 - INFO - codeparrot_training - Step 17362: {'lr': 0.00036701902061782445, 'samples': 8889856, 'steps': 17362, 'batch_loss/train': 0.7704257583245635}
+12/25/2021 06:17:45 - INFO - codeparrot_training - Step 17363: {'lr': 0.00036700509068998086, 'samples': 8890368, 'steps': 17363, 'batch_loss/train': 0.8262847103178501}
+12/25/2021 06:17:57 - INFO - codeparrot_training - Step 17364: {'lr': 0.0003669911602969692, 'samples': 8890880, 'steps': 17364, 'batch_loss/train': 0.7317970981821418}
+12/25/2021 06:18:07 - INFO - codeparrot_training - Step 17365: {'lr': 0.0003669772294388449, 'samples': 8891392, 'steps': 17365, 'batch_loss/train': 0.8317115046083927}
+12/25/2021 06:18:18 - INFO - codeparrot_training - Step 17366: {'lr': 0.0003669632981156632, 'samples': 8891904, 'steps': 17366, 'batch_loss/train': 0.8449640218168497}
+12/25/2021 06:18:31 - INFO - codeparrot_training - Step 17367: {'lr': 0.0003669493663274797, 'samples': 8892416, 'steps': 17367, 'batch_loss/train': 0.9459993746131659}
+12/25/2021 06:18:41 - INFO - codeparrot_training - Step 17368: {'lr': 0.00036693543407434963, 'samples': 8892928, 'steps': 17368, 'batch_loss/train': 0.7527595912106335}
+12/25/2021 06:18:52 - INFO - codeparrot_training - Step 17369: {'lr': 0.0003669215013563284, 'samples': 8893440, 'steps': 17369, 'batch_loss/train': 0.8039830820634961}
+12/25/2021 06:19:04 - INFO - codeparrot_training - Step 17370: {'lr': 0.0003669075681734715, 'samples': 8893952, 'steps': 17370, 'batch_loss/train': 0.8196515720337629}
+12/25/2021 06:19:15 - INFO - codeparrot_training - Step 17371: {'lr': 0.00036689363452583425, 'samples': 8894464, 'steps': 17371, 'batch_loss/train': 0.7886779754189774}
+12/25/2021 06:19:25 - INFO - codeparrot_training - Step 17372: {'lr': 0.00036687970041347204, 'samples': 8894976, 'steps': 17372, 'batch_loss/train': 0.7890283425804228}
+12/25/2021 06:19:36 - INFO - codeparrot_training - Step 17373: {'lr': 0.00036686576583644024, 'samples': 8895488, 'steps': 17373, 'batch_loss/train': 0.8475205721333623}
+12/25/2021 06:19:49 - INFO - codeparrot_training - Step 17374: {'lr': 0.00036685183079479436, 'samples': 8896000, 'steps': 17374, 'batch_loss/train': 0.8267627423629165}
+12/25/2021 06:19:59 - INFO - codeparrot_training - Step 17375: {'lr': 0.00036683789528858964, 'samples': 8896512, 'steps': 17375, 'batch_loss/train': 0.8540192320942879}
+12/25/2021 06:20:10 - INFO - codeparrot_training - Step 17376: {'lr': 0.00036682395931788154, 'samples': 8897024, 'steps': 17376, 'batch_loss/train': 0.7792487149126828}
+12/25/2021 06:20:22 - INFO - codeparrot_training - Step 17377: {'lr': 0.0003668100228827255, 'samples': 8897536, 'steps': 17377, 'batch_loss/train': 0.879600495332852}
+12/25/2021 06:20:32 - INFO - codeparrot_training - Step 17378: {'lr': 0.00036679608598317703, 'samples': 8898048, 'steps': 17378, 'batch_loss/train': 0.7788811279460788}
+12/25/2021 06:20:43 - INFO - codeparrot_training - Step 17379: {'lr': 0.00036678214861929126, 'samples': 8898560, 'steps': 17379, 'batch_loss/train': 0.8339707474224269}
+12/25/2021 06:20:55 - INFO - codeparrot_training - Step 17380: {'lr': 0.0003667682107911238, 'samples': 8899072, 'steps': 17380, 'batch_loss/train': 0.8452870724722743}
+12/25/2021 06:21:06 - INFO - codeparrot_training - Step 17381: {'lr': 0.0003667542724987302, 'samples': 8899584, 'steps': 17381, 'batch_loss/train': 0.8210428059101105}
+12/25/2021 06:21:16 - INFO - codeparrot_training - Step 17382: {'lr': 0.0003667403337421654, 'samples': 8900096, 'steps': 17382, 'batch_loss/train': 0.8437640465563163}
+12/25/2021 06:21:27 - INFO - codeparrot_training - Step 17383: {'lr': 0.00036672639452148536, 'samples': 8900608, 'steps': 17383, 'batch_loss/train': 0.771002198336646}
+12/25/2021 06:21:39 - INFO - codeparrot_training - Step 17384: {'lr': 0.00036671245483674514, 'samples': 8901120, 'steps': 17384, 'batch_loss/train': 0.7774600340053439}
+12/25/2021 06:21:50 - INFO - codeparrot_training - Step 17385: {'lr': 0.0003666985146880003, 'samples': 8901632, 'steps': 17385, 'batch_loss/train': 0.8147623077966273}
+12/25/2021 06:22:00 - INFO - codeparrot_training - Step 17386: {'lr': 0.0003666845740753062, 'samples': 8902144, 'steps': 17386, 'batch_loss/train': 0.9571607792750001}
+12/25/2021 06:22:13 - INFO - codeparrot_training - Step 17387: {'lr': 0.00036667063299871837, 'samples': 8902656, 'steps': 17387, 'batch_loss/train': 0.8104799287393689}
+12/25/2021 06:22:23 - INFO - codeparrot_training - Step 17388: {'lr': 0.00036665669145829213, 'samples': 8903168, 'steps': 17388, 'batch_loss/train': 0.7564617437310517}
+12/25/2021 06:22:34 - INFO - codeparrot_training - Step 17389: {'lr': 0.0003666427494540828, 'samples': 8903680, 'steps': 17389, 'batch_loss/train': 0.8002532478421926}
+12/25/2021 06:22:46 - INFO - codeparrot_training - Step 17390: {'lr': 0.00036662880698614607, 'samples': 8904192, 'steps': 17390, 'batch_loss/train': 0.8140713572502136}
+12/25/2021 06:22:57 - INFO - codeparrot_training - Step 17391: {'lr': 0.00036661486405453725, 'samples': 8904704, 'steps': 17391, 'batch_loss/train': 0.7687893072143197}
+12/25/2021 06:23:07 - INFO - codeparrot_training - Step 17392: {'lr': 0.0003666009206593117, 'samples': 8905216, 'steps': 17392, 'batch_loss/train': 0.8748242845758796}
+12/25/2021 06:23:19 - INFO - codeparrot_training - Step 17393: {'lr': 0.0003665869768005249, 'samples': 8905728, 'steps': 17393, 'batch_loss/train': 0.8501117685809731}
+12/25/2021 06:23:30 - INFO - codeparrot_training - Step 17394: {'lr': 0.0003665730324782324, 'samples': 8906240, 'steps': 17394, 'batch_loss/train': 0.8477291194722056}
+12/25/2021 06:23:41 - INFO - codeparrot_training - Step 17395: {'lr': 0.00036655908769248947, 'samples': 8906752, 'steps': 17395, 'batch_loss/train': 0.8678005691617727}
+12/25/2021 06:23:51 - INFO - codeparrot_training - Step 17396: {'lr': 0.0003665451424433516, 'samples': 8907264, 'steps': 17396, 'batch_loss/train': 0.7923067584633827}
+12/25/2021 06:24:04 - INFO - codeparrot_training - Step 17397: {'lr': 0.00036653119673087434, 'samples': 8907776, 'steps': 17397, 'batch_loss/train': 0.7290579518303275}
+12/25/2021 06:24:15 - INFO - codeparrot_training - Step 17398: {'lr': 0.00036651725055511297, 'samples': 8908288, 'steps': 17398, 'batch_loss/train': 0.7167352255200967}
+12/25/2021 06:24:25 - INFO - codeparrot_training - Step 17399: {'lr': 0.00036650330391612296, 'samples': 8908800, 'steps': 17399, 'batch_loss/train': 0.8150149323046207}
+12/25/2021 06:24:37 - INFO - codeparrot_training - Step 17400: {'lr': 0.00036648935681395995, 'samples': 8909312, 'steps': 17400, 'batch_loss/train': 0.8821622189134359}
+12/25/2021 06:24:48 - INFO - codeparrot_training - Step 17401: {'lr': 0.00036647540924867917, 'samples': 8909824, 'steps': 17401, 'batch_loss/train': 0.7694982807151973}
+12/25/2021 06:24:58 - INFO - codeparrot_training - Step 17402: {'lr': 0.00036646146122033607, 'samples': 8910336, 'steps': 17402, 'batch_loss/train': 0.834856373257935}
+12/25/2021 06:25:11 - INFO - codeparrot_training - Step 17403: {'lr': 0.0003664475127289862, 'samples': 8910848, 'steps': 17403, 'batch_loss/train': 0.7484819306991994}
+12/25/2021 06:25:22 - INFO - codeparrot_training - Step 17404: {'lr': 0.0003664335637746851, 'samples': 8911360, 'steps': 17404, 'batch_loss/train': 0.7945677083916962}
+12/25/2021 06:25:32 - INFO - codeparrot_training - Step 17405: {'lr': 0.000366419614357488, 'samples': 8911872, 'steps': 17405, 'batch_loss/train': 0.8812666898593307}
+12/25/2021 06:25:44 - INFO - codeparrot_training - Step 17406: {'lr': 0.0003664056644774505, 'samples': 8912384, 'steps': 17406, 'batch_loss/train': 0.7111737192608416}
+12/25/2021 06:25:55 - INFO - codeparrot_training - Step 17407: {'lr': 0.0003663917141346281, 'samples': 8912896, 'steps': 17407, 'batch_loss/train': 0.8680298179388046}
+12/25/2021 06:26:06 - INFO - codeparrot_training - Step 17408: {'lr': 0.00036637776332907603, 'samples': 8913408, 'steps': 17408, 'batch_loss/train': 0.8710408583283424}
+12/25/2021 06:26:16 - INFO - codeparrot_training - Step 17409: {'lr': 0.00036636381206085007, 'samples': 8913920, 'steps': 17409, 'batch_loss/train': 0.7672727997414768}
+12/25/2021 06:26:28 - INFO - codeparrot_training - Step 17410: {'lr': 0.00036634986033000545, 'samples': 8914432, 'steps': 17410, 'batch_loss/train': 0.8321215459145606}
+12/25/2021 06:26:39 - INFO - codeparrot_training - Step 17411: {'lr': 0.00036633590813659774, 'samples': 8914944, 'steps': 17411, 'batch_loss/train': 0.7823754716664553}
+12/25/2021 06:26:49 - INFO - codeparrot_training - Step 17412: {'lr': 0.0003663219554806824, 'samples': 8915456, 'steps': 17412, 'batch_loss/train': 0.8264126181602478}
+12/25/2021 06:27:02 - INFO - codeparrot_training - Step 17413: {'lr': 0.00036630800236231486, 'samples': 8915968, 'steps': 17413, 'batch_loss/train': 0.8462514355778694}
+12/25/2021 06:27:13 - INFO - codeparrot_training - Step 17414: {'lr': 0.0003662940487815506, 'samples': 8916480, 'steps': 17414, 'batch_loss/train': 0.6566808423958719}
+12/25/2021 06:27:23 - INFO - codeparrot_training - Step 17415: {'lr': 0.0003662800947384452, 'samples': 8916992, 'steps': 17415, 'batch_loss/train': 0.9131703218445182}
+12/25/2021 06:27:35 - INFO - codeparrot_training - Step 17416: {'lr': 0.000366266140233054, 'samples': 8917504, 'steps': 17416, 'batch_loss/train': 0.8549003629013896}
+12/25/2021 06:27:46 - INFO - codeparrot_training - Step 17417: {'lr': 0.0003662521852654325, 'samples': 8918016, 'steps': 17417, 'batch_loss/train': 0.8635540874674916}
+12/25/2021 06:27:57 - INFO - codeparrot_training - Step 17418: {'lr': 0.00036623822983563627, 'samples': 8918528, 'steps': 17418, 'batch_loss/train': 0.8263587718829513}
+12/25/2021 06:28:09 - INFO - codeparrot_training - Step 17419: {'lr': 0.00036622427394372064, 'samples': 8919040, 'steps': 17419, 'batch_loss/train': 0.8798807505518198}
+12/25/2021 06:28:19 - INFO - codeparrot_training - Step 17420: {'lr': 0.0003662103175897413, 'samples': 8919552, 'steps': 17420, 'batch_loss/train': 0.8186856126412749}
+12/25/2021 06:28:30 - INFO - codeparrot_training - Step 17421: {'lr': 0.00036619636077375343, 'samples': 8920064, 'steps': 17421, 'batch_loss/train': 0.8478096220642328}
+12/25/2021 06:28:41 - INFO - codeparrot_training - Step 17422: {'lr': 0.0003661824034958129, 'samples': 8920576, 'steps': 17422, 'batch_loss/train': 0.8655264256522059}
+12/25/2021 06:28:53 - INFO - codeparrot_training - Step 17423: {'lr': 0.00036616844575597493, 'samples': 8921088, 'steps': 17423, 'batch_loss/train': 0.8330664969980717}
+12/25/2021 06:29:04 - INFO - codeparrot_training - Step 17424: {'lr': 0.00036615448755429505, 'samples': 8921600, 'steps': 17424, 'batch_loss/train': 0.841694189235568}
+12/25/2021 06:29:14 - INFO - codeparrot_training - Step 17425: {'lr': 0.00036614052889082885, 'samples': 8922112, 'steps': 17425, 'batch_loss/train': 0.7405771990306675}
+12/25/2021 06:29:27 - INFO - codeparrot_training - Step 17426: {'lr': 0.00036612656976563174, 'samples': 8922624, 'steps': 17426, 'batch_loss/train': 0.8007215103134513}
+12/25/2021 06:29:37 - INFO - codeparrot_training - Step 17427: {'lr': 0.0003661126101787591, 'samples': 8923136, 'steps': 17427, 'batch_loss/train': 0.8317997781559825}
+12/25/2021 06:29:48 - INFO - codeparrot_training - Step 17428: {'lr': 0.00036609865013026676, 'samples': 8923648, 'steps': 17428, 'batch_loss/train': 0.6807360252132639}
+12/25/2021 06:30:00 - INFO - codeparrot_training - Step 17429: {'lr': 0.0003660846896202099, 'samples': 8924160, 'steps': 17429, 'batch_loss/train': 1.5827063405886292}
+12/25/2021 06:30:11 - INFO - codeparrot_training - Step 17430: {'lr': 0.0003660707286486442, 'samples': 8924672, 'steps': 17430, 'batch_loss/train': 0.9250199971720576}
+12/25/2021 06:30:21 - INFO - codeparrot_training - Step 17431: {'lr': 0.0003660567672156251, 'samples': 8925184, 'steps': 17431, 'batch_loss/train': 0.7911776434630156}
+12/25/2021 06:30:32 - INFO - codeparrot_training - Step 17432: {'lr': 0.0003660428053212082, 'samples': 8925696, 'steps': 17432, 'batch_loss/train': 0.7495663054287434}
+12/25/2021 06:30:45 - INFO - codeparrot_training - Step 17433: {'lr': 0.0003660288429654488, 'samples': 8926208, 'steps': 17433, 'batch_loss/train': 0.8315925328060985}
+12/25/2021 06:30:55 - INFO - codeparrot_training - Step 17434: {'lr': 0.0003660148801484025, 'samples': 8926720, 'steps': 17434, 'batch_loss/train': 0.8217172026634216}
+12/25/2021 06:31:06 - INFO - codeparrot_training - Step 17435: {'lr': 0.0003660009168701249, 'samples': 8927232, 'steps': 17435, 'batch_loss/train': 0.773083757609129}
+12/25/2021 06:31:18 - INFO - codeparrot_training - Step 17436: {'lr': 0.00036598695313067156, 'samples': 8927744, 'steps': 17436, 'batch_loss/train': 0.6873998296796344}
+12/25/2021 06:31:28 - INFO - codeparrot_training - Step 17437: {'lr': 0.0003659729889300978, 'samples': 8928256, 'steps': 17437, 'batch_loss/train': 0.7631347207352519}
+12/25/2021 06:31:39 - INFO - codeparrot_training - Step 17438: {'lr': 0.00036595902426845916, 'samples': 8928768, 'steps': 17438, 'batch_loss/train': 0.8004321996122599}
+12/25/2021 06:31:51 - INFO - codeparrot_training - Step 17439: {'lr': 0.00036594505914581136, 'samples': 8929280, 'steps': 17439, 'batch_loss/train': 0.7429881563875824}
+12/25/2021 06:32:02 - INFO - codeparrot_training - Step 17440: {'lr': 0.0003659310935622096, 'samples': 8929792, 'steps': 17440, 'batch_loss/train': 0.8600389467319474}
+12/25/2021 06:32:12 - INFO - codeparrot_training - Step 17441: {'lr': 0.0003659171275177097, 'samples': 8930304, 'steps': 17441, 'batch_loss/train': 0.7702525313943624}
+12/25/2021 06:32:23 - INFO - codeparrot_training - Step 17442: {'lr': 0.0003659031610123671, 'samples': 8930816, 'steps': 17442, 'batch_loss/train': 0.8319746782071888}
+12/25/2021 06:32:36 - INFO - codeparrot_training - Step 17443: {'lr': 0.0003658891940462373, 'samples': 8931328, 'steps': 17443, 'batch_loss/train': 0.865491196513176}
+12/25/2021 06:32:46 - INFO - codeparrot_training - Step 17444: {'lr': 0.00036587522661937576, 'samples': 8931840, 'steps': 17444, 'batch_loss/train': 0.7817246387712657}
+12/25/2021 06:32:57 - INFO - codeparrot_training - Step 17445: {'lr': 0.0003658612587318381, 'samples': 8932352, 'steps': 17445, 'batch_loss/train': 0.7843131460249424}
+12/25/2021 06:33:09 - INFO - codeparrot_training - Step 17446: {'lr': 0.0003658472903836798, 'samples': 8932864, 'steps': 17446, 'batch_loss/train': 0.8150057559832931}
+12/25/2021 06:33:20 - INFO - codeparrot_training - Step 17447: {'lr': 0.0003658333215749564, 'samples': 8933376, 'steps': 17447, 'batch_loss/train': 0.736543252132833}
+12/25/2021 06:33:30 - INFO - codeparrot_training - Step 17448: {'lr': 0.0003658193523057235, 'samples': 8933888, 'steps': 17448, 'batch_loss/train': 0.8731275340542197}
+12/25/2021 06:33:42 - INFO - codeparrot_training - Step 17449: {'lr': 0.0003658053825760366, 'samples': 8934400, 'steps': 17449, 'batch_loss/train': 0.7878011409193277}
+12/25/2021 06:33:53 - INFO - codeparrot_training - Step 17450: {'lr': 0.00036579141238595115, 'samples': 8934912, 'steps': 17450, 'batch_loss/train': 0.7260540304705501}
+12/25/2021 06:34:04 - INFO - codeparrot_training - Step 17451: {'lr': 0.00036577744173552285, 'samples': 8935424, 'steps': 17451, 'batch_loss/train': 0.8659751610830426}
+12/25/2021 06:34:16 - INFO - codeparrot_training - Step 17452: {'lr': 0.00036576347062480715, 'samples': 8935936, 'steps': 17452, 'batch_loss/train': 0.7270058700814843}
+12/25/2021 06:34:27 - INFO - codeparrot_training - Step 17453: {'lr': 0.0003657494990538595, 'samples': 8936448, 'steps': 17453, 'batch_loss/train': 0.6993022486567497}
+12/25/2021 06:34:37 - INFO - codeparrot_training - Step 17454: {'lr': 0.00036573552702273563, 'samples': 8936960, 'steps': 17454, 'batch_loss/train': 0.8078706124797463}
+12/25/2021 06:34:48 - INFO - codeparrot_training - Step 17455: {'lr': 0.00036572155453149104, 'samples': 8937472, 'steps': 17455, 'batch_loss/train': 0.713283383869566}
+12/25/2021 06:35:00 - INFO - codeparrot_training - Step 17456: {'lr': 0.00036570758158018115, 'samples': 8937984, 'steps': 17456, 'batch_loss/train': 0.70717708254233}
+12/25/2021 06:35:11 - INFO - codeparrot_training - Step 17457: {'lr': 0.0003656936081688617, 'samples': 8938496, 'steps': 17457, 'batch_loss/train': 0.6310438867658377}
+12/25/2021 06:35:21 - INFO - codeparrot_training - Step 17458: {'lr': 0.000365679634297588, 'samples': 8939008, 'steps': 17458, 'batch_loss/train': 0.7631240736227483}
+12/25/2021 06:35:34 - INFO - codeparrot_training - Step 17459: {'lr': 0.00036566565996641587, 'samples': 8939520, 'steps': 17459, 'batch_loss/train': 0.7502413596957922}
+12/25/2021 06:35:45 - INFO - codeparrot_training - Step 17460: {'lr': 0.0003656516851754008, 'samples': 8940032, 'steps': 17460, 'batch_loss/train': 0.7712232791818678}
+12/25/2021 06:35:55 - INFO - codeparrot_training - Step 17461: {'lr': 0.0003656377099245982, 'samples': 8940544, 'steps': 17461, 'batch_loss/train': 0.8671118777710944}
+12/25/2021 06:36:07 - INFO - codeparrot_training - Step 17462: {'lr': 0.00036562373421406377, 'samples': 8941056, 'steps': 17462, 'batch_loss/train': 0.794335660059005}
+12/25/2021 06:36:18 - INFO - codeparrot_training - Step 17463: {'lr': 0.000365609758043853, 'samples': 8941568, 'steps': 17463, 'batch_loss/train': 0.8260528426617384}
+12/25/2021 06:36:29 - INFO - codeparrot_training - Step 17464: {'lr': 0.0003655957814140215, 'samples': 8942080, 'steps': 17464, 'batch_loss/train': 0.8164424132555723}
+12/25/2021 06:36:39 - INFO - codeparrot_training - Step 17465: {'lr': 0.00036558180432462483, 'samples': 8942592, 'steps': 17465, 'batch_loss/train': 0.830485075712204}
+12/25/2021 06:36:52 - INFO - codeparrot_training - Step 17466: {'lr': 0.00036556782677571854, 'samples': 8943104, 'steps': 17466, 'batch_loss/train': 0.857560420408845}
+12/25/2021 06:37:02 - INFO - codeparrot_training - Step 17467: {'lr': 0.0003655538487673582, 'samples': 8943616, 'steps': 17467, 'batch_loss/train': 0.6089750733226538}
+12/25/2021 06:37:13 - INFO - codeparrot_training - Step 17468: {'lr': 0.0003655398702995994, 'samples': 8944128, 'steps': 17468, 'batch_loss/train': 0.7589163966476917}
+12/25/2021 06:37:25 - INFO - codeparrot_training - Step 17469: {'lr': 0.0003655258913724977, 'samples': 8944640, 'steps': 17469, 'batch_loss/train': 0.77393215498887}
+12/25/2021 06:37:35 - INFO - codeparrot_training - Step 17470: {'lr': 0.00036551191198610865, 'samples': 8945152, 'steps': 17470, 'batch_loss/train': 0.8750169444829226}
+12/25/2021 06:37:46 - INFO - codeparrot_training - Step 17471: {'lr': 0.0003654979321404879, 'samples': 8945664, 'steps': 17471, 'batch_loss/train': 0.7714402242563665}
+12/25/2021 06:37:59 - INFO - codeparrot_training - Step 17472: {'lr': 0.00036548395183569094, 'samples': 8946176, 'steps': 17472, 'batch_loss/train': 0.7904062662273645}
+12/25/2021 06:38:10 - INFO - codeparrot_training - Step 17473: {'lr': 0.00036546997107177344, 'samples': 8946688, 'steps': 17473, 'batch_loss/train': 0.8401390672661364}
+12/25/2021 06:38:20 - INFO - codeparrot_training - Step 17474: {'lr': 0.0003654559898487909, 'samples': 8947200, 'steps': 17474, 'batch_loss/train': 0.7598392039071769}
+12/25/2021 06:38:32 - INFO - codeparrot_training - Step 17475: {'lr': 0.00036544200816679894, 'samples': 8947712, 'steps': 17475, 'batch_loss/train': 0.8148228228092194}
+12/25/2021 06:38:43 - INFO - codeparrot_training - Step 17476: {'lr': 0.0003654280260258532, 'samples': 8948224, 'steps': 17476, 'batch_loss/train': 0.7977593307732604}
+12/25/2021 06:38:54 - INFO - codeparrot_training - Step 17477: {'lr': 0.00036541404342600915, 'samples': 8948736, 'steps': 17477, 'batch_loss/train': 0.8087447155267}
+12/25/2021 06:39:04 - INFO - codeparrot_training - Step 17478: {'lr': 0.0003654000603673224, 'samples': 8949248, 'steps': 17478, 'batch_loss/train': 0.8449163034092635}
+12/25/2021 06:39:16 - INFO - codeparrot_training - Step 17479: {'lr': 0.00036538607684984863, 'samples': 8949760, 'steps': 17479, 'batch_loss/train': 0.7880113758146763}
+12/25/2021 06:39:27 - INFO - codeparrot_training - Step 17480: {'lr': 0.00036537209287364344, 'samples': 8950272, 'steps': 17480, 'batch_loss/train': 0.7587065203115344}
+12/25/2021 06:39:37 - INFO - codeparrot_training - Step 17481: {'lr': 0.0003653581084387624, 'samples': 8950784, 'steps': 17481, 'batch_loss/train': 0.9208804350346327}
+12/25/2021 06:39:50 - INFO - codeparrot_training - Step 17482: {'lr': 0.0003653441235452609, 'samples': 8951296, 'steps': 17482, 'batch_loss/train': 0.8329276763834059}
+12/25/2021 06:40:01 - INFO - codeparrot_training - Step 17483: {'lr': 0.00036533013819319487, 'samples': 8951808, 'steps': 17483, 'batch_loss/train': 0.7580092360731214}
+12/25/2021 06:40:11 - INFO - codeparrot_training - Step 17484: {'lr': 0.00036531615238261973, 'samples': 8952320, 'steps': 17484, 'batch_loss/train': 0.9084412958472967}
+12/25/2021 06:40:24 - INFO - codeparrot_training - Step 17485: {'lr': 0.00036530216611359106, 'samples': 8952832, 'steps': 17485, 'batch_loss/train': 0.7212890683440492}
+12/25/2021 06:40:35 - INFO - codeparrot_training - Step 17486: {'lr': 0.0003652881793861645, 'samples': 8953344, 'steps': 17486, 'batch_loss/train': 0.8253106465563178}
+12/25/2021 06:40:45 - INFO - codeparrot_training - Step 17487: {'lr': 0.0003652741922003958, 'samples': 8953856, 'steps': 17487, 'batch_loss/train': 0.7835287684574723}
+12/25/2021 06:40:56 - INFO - codeparrot_training - Step 17488: {'lr': 0.00036526020455634035, 'samples': 8954368, 'steps': 17488, 'batch_loss/train': 0.8386829970404506}
+12/25/2021 06:41:08 - INFO - codeparrot_training - Step 17489: {'lr': 0.0003652462164540538, 'samples': 8954880, 'steps': 17489, 'batch_loss/train': 0.8457741970196366}
+12/25/2021 06:41:19 - INFO - codeparrot_training - Step 17490: {'lr': 0.0003652322278935919, 'samples': 8955392, 'steps': 17490, 'batch_loss/train': 0.8108110325410962}
+12/25/2021 06:41:30 - INFO - codeparrot_training - Step 17491: {'lr': 0.0003652182388750101, 'samples': 8955904, 'steps': 17491, 'batch_loss/train': 0.6465431621181779}
+12/25/2021 06:41:42 - INFO - codeparrot_training - Step 17492: {'lr': 0.0003652042493983641, 'samples': 8956416, 'steps': 17492, 'batch_loss/train': 0.8066728254780173}
+12/25/2021 06:41:53 - INFO - codeparrot_training - Step 17493: {'lr': 0.0003651902594637095, 'samples': 8956928, 'steps': 17493, 'batch_loss/train': 1.004271681420505}
+12/25/2021 06:42:03 - INFO - codeparrot_training - Step 17494: {'lr': 0.00036517626907110203, 'samples': 8957440, 'steps': 17494, 'batch_loss/train': 0.6365663467440754}
+12/25/2021 06:42:14 - INFO - codeparrot_training - Step 17495: {'lr': 0.000365162278220597, 'samples': 8957952, 'steps': 17495, 'batch_loss/train': 0.8705560937523842}
+12/25/2021 06:42:26 - INFO - codeparrot_training - Step 17496: {'lr': 0.00036514828691225045, 'samples': 8958464, 'steps': 17496, 'batch_loss/train': 0.8482341710478067}
+12/25/2021 06:42:36 - INFO - codeparrot_training - Step 17497: {'lr': 0.0003651342951461177, 'samples': 8958976, 'steps': 17497, 'batch_loss/train': 0.8688390105962753}
+12/25/2021 06:42:47 - INFO - codeparrot_training - Step 17498: {'lr': 0.0003651203029222544, 'samples': 8959488, 'steps': 17498, 'batch_loss/train': 0.8372709983959794}
+12/25/2021 06:43:00 - INFO - codeparrot_training - Step 17499: {'lr': 0.0003651063102407163, 'samples': 8960000, 'steps': 17499, 'batch_loss/train': 0.8981794789433479}
+12/25/2021 06:43:00 - INFO - codeparrot_training - Evaluating and saving model checkpoint
+12/25/2021 06:46:22 - INFO - codeparrot_training - Step 17500: {'loss/eval': 0.8102298974990845, 'perplexity': 2.248424768447876}