diff --git "a/log/debug_0.log" "b/log/debug_0.log" --- "a/log/debug_0.log" +++ "b/log/debug_0.log" @@ -41548,3 +41548,1009 @@ Use FP16 precision: False 02/26/2022 06:39:07 - INFO - codeparrot_training - Step 40998: {'lr': 4.2150779698548165e-05, 'samples': 20991488, 'steps': 40998, 'loss/train': 1.6610727310180664} 02/26/2022 06:39:13 - INFO - codeparrot_training - Step 40999: {'lr': 4.214168786625644e-05, 'samples': 20992000, 'steps': 40999, 'loss/train': 1.473726749420166} 02/26/2022 06:39:13 - INFO - codeparrot_training - Evaluating and saving model checkpoint +02/26/2022 06:39:31 - WARNING - huggingface_hub.repository - Several commits (41) will be pushed upstream. +02/26/2022 06:39:31 - WARNING - huggingface_hub.repository - The progress bars may be unreliable. +02/26/2022 06:40:06 - WARNING - huggingface_hub.repository - To https://huggingface.co/ncoop57/multi-code-clippy + e25c2d7..2427a89 floral-grass-11 -> floral-grass-11 + +02/26/2022 06:40:11 - INFO - codeparrot_training - Step 41000: {'lr': 4.213259692436367e-05, 'samples': 20992512, 'steps': 41000, 'loss/train': 2.428166151046753} +02/26/2022 06:40:17 - INFO - codeparrot_training - Step 41001: {'lr': 4.212350687290892e-05, 'samples': 20993024, 'steps': 41001, 'loss/train': 1.1785485744476318} +02/26/2022 06:40:20 - INFO - codeparrot_training - Step 41002: {'lr': 4.211441771193103e-05, 'samples': 20993536, 'steps': 41002, 'loss/train': 2.117093324661255} +02/26/2022 06:40:26 - INFO - codeparrot_training - Step 41003: {'lr': 4.210532944146897e-05, 'samples': 20994048, 'steps': 41003, 'loss/train': 2.542660713195801} +02/26/2022 06:40:29 - INFO - codeparrot_training - Step 41004: {'lr': 4.209624206156168e-05, 'samples': 20994560, 'steps': 41004, 'loss/train': 0.4339028596878052} +02/26/2022 06:40:35 - INFO - codeparrot_training - Step 41005: {'lr': 4.208715557224799e-05, 'samples': 20995072, 'steps': 41005, 'loss/train': 2.0721898078918457} +02/26/2022 06:40:38 - INFO - codeparrot_training - Step 41006: {'lr': 4.207806997356697e-05, 'samples': 20995584, 'steps': 41006, 'loss/train': 0.9623445868492126} +02/26/2022 06:40:45 - INFO - codeparrot_training - Step 41007: {'lr': 4.20689852655575e-05, 'samples': 20996096, 'steps': 41007, 'loss/train': 1.8240349292755127} +02/26/2022 06:40:48 - INFO - codeparrot_training - Step 41008: {'lr': 4.2059901448258445e-05, 'samples': 20996608, 'steps': 41008, 'loss/train': 1.4623123407363892} +02/26/2022 06:40:53 - INFO - codeparrot_training - Step 41009: {'lr': 4.20508185217087e-05, 'samples': 20997120, 'steps': 41009, 'loss/train': 0.836247444152832} +02/26/2022 06:40:57 - INFO - codeparrot_training - Step 41010: {'lr': 4.204173648594728e-05, 'samples': 20997632, 'steps': 41010, 'loss/train': 1.8821682929992676} +02/26/2022 06:41:02 - INFO - codeparrot_training - Step 41011: {'lr': 4.2032655341012996e-05, 'samples': 20998144, 'steps': 41011, 'loss/train': 2.2221384048461914} +02/26/2022 06:41:06 - INFO - codeparrot_training - Step 41012: {'lr': 4.202357508694482e-05, 'samples': 20998656, 'steps': 41012, 'loss/train': 2.626143455505371} +02/26/2022 06:41:11 - INFO - codeparrot_training - Step 41013: {'lr': 4.2014495723781524e-05, 'samples': 20999168, 'steps': 41013, 'loss/train': 1.1708762645721436} +02/26/2022 06:41:15 - INFO - codeparrot_training - Step 41014: {'lr': 4.200541725156215e-05, 'samples': 20999680, 'steps': 41014, 'loss/train': 0.8321356177330017} +02/26/2022 06:41:20 - INFO - codeparrot_training - Step 41015: {'lr': 4.199633967032546e-05, 'samples': 21000192, 'steps': 41015, 'loss/train': 1.5895556211471558} +02/26/2022 06:41:26 - INFO - codeparrot_training - Step 41016: {'lr': 4.198726298011052e-05, 'samples': 21000704, 'steps': 41016, 'loss/train': 1.6041032075881958} +02/26/2022 06:41:30 - INFO - codeparrot_training - Step 41017: {'lr': 4.1978187180955974e-05, 'samples': 21001216, 'steps': 41017, 'loss/train': 2.1447529792785645} +02/26/2022 06:41:35 - INFO - codeparrot_training - Step 41018: {'lr': 4.19691122729009e-05, 'samples': 21001728, 'steps': 41018, 'loss/train': 2.028188705444336} +02/26/2022 06:41:39 - INFO - codeparrot_training - Step 41019: {'lr': 4.196003825598402e-05, 'samples': 21002240, 'steps': 41019, 'loss/train': 3.0181140899658203} +02/26/2022 06:41:44 - INFO - codeparrot_training - Step 41020: {'lr': 4.1950965130244376e-05, 'samples': 21002752, 'steps': 41020, 'loss/train': 1.7762588262557983} +02/26/2022 06:41:48 - INFO - codeparrot_training - Step 41021: {'lr': 4.194189289572065e-05, 'samples': 21003264, 'steps': 41021, 'loss/train': 2.4327194690704346} +02/26/2022 06:41:54 - INFO - codeparrot_training - Step 41022: {'lr': 4.193282155245182e-05, 'samples': 21003776, 'steps': 41022, 'loss/train': 2.31196665763855} +02/26/2022 06:41:58 - INFO - codeparrot_training - Step 41023: {'lr': 4.192375110047667e-05, 'samples': 21004288, 'steps': 41023, 'loss/train': 1.6307587623596191} +02/26/2022 06:42:03 - INFO - codeparrot_training - Step 41024: {'lr': 4.191468153983419e-05, 'samples': 21004800, 'steps': 41024, 'loss/train': 0.5155414938926697} +02/26/2022 06:42:07 - INFO - codeparrot_training - Step 41025: {'lr': 4.190561287056305e-05, 'samples': 21005312, 'steps': 41025, 'loss/train': 1.6448475122451782} +02/26/2022 06:42:12 - INFO - codeparrot_training - Step 41026: {'lr': 4.1896545092702244e-05, 'samples': 21005824, 'steps': 41026, 'loss/train': 2.102656364440918} +02/26/2022 06:42:16 - INFO - codeparrot_training - Step 41027: {'lr': 4.188747820629049e-05, 'samples': 21006336, 'steps': 41027, 'loss/train': 0.018176639452576637} +02/26/2022 06:42:22 - INFO - codeparrot_training - Step 41028: {'lr': 4.187841221136676e-05, 'samples': 21006848, 'steps': 41028, 'loss/train': 2.1290993690490723} +02/26/2022 06:42:25 - INFO - codeparrot_training - Step 41029: {'lr': 4.186934710796983e-05, 'samples': 21007360, 'steps': 41029, 'loss/train': 0.5570828318595886} +02/26/2022 06:42:29 - INFO - codeparrot_training - Step 41030: {'lr': 4.1860282896138524e-05, 'samples': 21007872, 'steps': 41030, 'loss/train': 1.7246832847595215} +02/26/2022 06:42:34 - INFO - codeparrot_training - Step 41031: {'lr': 4.185121957591162e-05, 'samples': 21008384, 'steps': 41031, 'loss/train': 2.7483699321746826} +02/26/2022 06:42:38 - INFO - codeparrot_training - Step 41032: {'lr': 4.184215714732803e-05, 'samples': 21008896, 'steps': 41032, 'loss/train': 1.555988073348999} +02/26/2022 06:42:44 - INFO - codeparrot_training - Step 41033: {'lr': 4.183309561042658e-05, 'samples': 21009408, 'steps': 41033, 'loss/train': 1.2177904844284058} +02/26/2022 06:42:50 - INFO - codeparrot_training - Step 41034: {'lr': 4.1824034965246035e-05, 'samples': 21009920, 'steps': 41034, 'loss/train': 1.9417407512664795} +02/26/2022 06:42:53 - INFO - codeparrot_training - Step 41035: {'lr': 4.181497521182514e-05, 'samples': 21010432, 'steps': 41035, 'loss/train': 1.621850609779358} +02/26/2022 06:42:59 - INFO - codeparrot_training - Step 41036: {'lr': 4.180591635020287e-05, 'samples': 21010944, 'steps': 41036, 'loss/train': 1.9137673377990723} +02/26/2022 06:43:02 - INFO - codeparrot_training - Step 41037: {'lr': 4.179685838041794e-05, 'samples': 21011456, 'steps': 41037, 'loss/train': 2.069483518600464} +02/26/2022 06:43:08 - INFO - codeparrot_training - Step 41038: {'lr': 4.1787801302509146e-05, 'samples': 21011968, 'steps': 41038, 'loss/train': 0.8556708693504333} +02/26/2022 06:43:11 - INFO - codeparrot_training - Step 41039: {'lr': 4.177874511651525e-05, 'samples': 21012480, 'steps': 41039, 'loss/train': 3.206566095352173} +02/26/2022 06:43:17 - INFO - codeparrot_training - Step 41040: {'lr': 4.176968982247514e-05, 'samples': 21012992, 'steps': 41040, 'loss/train': 1.8868523836135864} +02/26/2022 06:43:20 - INFO - codeparrot_training - Step 41041: {'lr': 4.176063542042757e-05, 'samples': 21013504, 'steps': 41041, 'loss/train': 2.053576707839966} +02/26/2022 06:43:24 - INFO - codeparrot_training - Step 41042: {'lr': 4.175158191041128e-05, 'samples': 21014016, 'steps': 41042, 'loss/train': 8.96193790435791} +02/26/2022 06:43:30 - INFO - codeparrot_training - Step 41043: {'lr': 4.174252929246508e-05, 'samples': 21014528, 'steps': 41043, 'loss/train': 1.664588212966919} +02/26/2022 06:43:33 - INFO - codeparrot_training - Step 41044: {'lr': 4.173347756662779e-05, 'samples': 21015040, 'steps': 41044, 'loss/train': 2.246711015701294} +02/26/2022 06:43:39 - INFO - codeparrot_training - Step 41045: {'lr': 4.172442673293814e-05, 'samples': 21015552, 'steps': 41045, 'loss/train': 1.0297152996063232} +02/26/2022 06:43:42 - INFO - codeparrot_training - Step 41046: {'lr': 4.1715376791434916e-05, 'samples': 21016064, 'steps': 41046, 'loss/train': 1.606587290763855} +02/26/2022 06:43:48 - INFO - codeparrot_training - Step 41047: {'lr': 4.170632774215682e-05, 'samples': 21016576, 'steps': 41047, 'loss/train': 1.7754837274551392} +02/26/2022 06:43:51 - INFO - codeparrot_training - Step 41048: {'lr': 4.169727958514275e-05, 'samples': 21017088, 'steps': 41048, 'loss/train': 2.855811595916748} +02/26/2022 06:43:57 - INFO - codeparrot_training - Step 41049: {'lr': 4.16882323204314e-05, 'samples': 21017600, 'steps': 41049, 'loss/train': 1.797804355621338} +02/26/2022 06:44:03 - INFO - codeparrot_training - Step 41050: {'lr': 4.167918594806142e-05, 'samples': 21018112, 'steps': 41050, 'loss/train': 1.7380183935165405} +02/26/2022 06:44:06 - INFO - codeparrot_training - Step 41051: {'lr': 4.16701404680718e-05, 'samples': 21018624, 'steps': 41051, 'loss/train': 1.6924335956573486} +02/26/2022 06:44:10 - INFO - codeparrot_training - Step 41052: {'lr': 4.1661095880501014e-05, 'samples': 21019136, 'steps': 41052, 'loss/train': 1.2786972522735596} +02/26/2022 06:44:16 - INFO - codeparrot_training - Step 41053: {'lr': 4.1652052185388e-05, 'samples': 21019648, 'steps': 41053, 'loss/train': 1.8639967441558838} +02/26/2022 06:44:19 - INFO - codeparrot_training - Step 41054: {'lr': 4.164300938277138e-05, 'samples': 21020160, 'steps': 41054, 'loss/train': 0.5331993103027344} +02/26/2022 06:44:25 - INFO - codeparrot_training - Step 41055: {'lr': 4.1633967472690075e-05, 'samples': 21020672, 'steps': 41055, 'loss/train': 2.0341267585754395} +02/26/2022 06:44:28 - INFO - codeparrot_training - Step 41056: {'lr': 4.162492645518256e-05, 'samples': 21021184, 'steps': 41056, 'loss/train': 2.191824197769165} +02/26/2022 06:44:34 - INFO - codeparrot_training - Step 41057: {'lr': 4.161588633028776e-05, 'samples': 21021696, 'steps': 41057, 'loss/train': 1.7723459005355835} +02/26/2022 06:44:37 - INFO - codeparrot_training - Step 41058: {'lr': 4.160684709804427e-05, 'samples': 21022208, 'steps': 41058, 'loss/train': 1.047770380973816} +02/26/2022 06:44:43 - INFO - codeparrot_training - Step 41059: {'lr': 4.1597808758491006e-05, 'samples': 21022720, 'steps': 41059, 'loss/train': 1.1358656883239746} +02/26/2022 06:44:48 - INFO - codeparrot_training - Step 41060: {'lr': 4.1588771311666415e-05, 'samples': 21023232, 'steps': 41060, 'loss/train': 1.1257461309432983} +02/26/2022 06:44:52 - INFO - codeparrot_training - Step 41061: {'lr': 4.157973475760943e-05, 'samples': 21023744, 'steps': 41061, 'loss/train': 2.379237651824951} +02/26/2022 06:44:57 - INFO - codeparrot_training - Step 41062: {'lr': 4.1570699096358606e-05, 'samples': 21024256, 'steps': 41062, 'loss/train': 1.2789474725723267} +02/26/2022 06:45:01 - INFO - codeparrot_training - Step 41063: {'lr': 4.1561664327952774e-05, 'samples': 21024768, 'steps': 41063, 'loss/train': 1.6425762176513672} +02/26/2022 06:45:06 - INFO - codeparrot_training - Step 41064: {'lr': 4.15526304524306e-05, 'samples': 21025280, 'steps': 41064, 'loss/train': 2.6840994358062744} +02/26/2022 06:45:10 - INFO - codeparrot_training - Step 41065: {'lr': 4.1543597469830777e-05, 'samples': 21025792, 'steps': 41065, 'loss/train': 1.8795808553695679} +02/26/2022 06:45:15 - INFO - codeparrot_training - Step 41066: {'lr': 4.15345653801919e-05, 'samples': 21026304, 'steps': 41066, 'loss/train': 2.257610321044922} +02/26/2022 06:45:19 - INFO - codeparrot_training - Step 41067: {'lr': 4.1525534183552846e-05, 'samples': 21026816, 'steps': 41067, 'loss/train': 2.4211978912353516} +02/26/2022 06:45:25 - INFO - codeparrot_training - Step 41068: {'lr': 4.151650387995218e-05, 'samples': 21027328, 'steps': 41068, 'loss/train': 1.8978255987167358} +02/26/2022 06:45:29 - INFO - codeparrot_training - Step 41069: {'lr': 4.1507474469428625e-05, 'samples': 21027840, 'steps': 41069, 'loss/train': 1.6763325929641724} +02/26/2022 06:45:34 - INFO - codeparrot_training - Step 41070: {'lr': 4.149844595202076e-05, 'samples': 21028352, 'steps': 41070, 'loss/train': 1.2078220844268799} +02/26/2022 06:45:38 - INFO - codeparrot_training - Step 41071: {'lr': 4.1489418327767455e-05, 'samples': 21028864, 'steps': 41071, 'loss/train': 1.511915683746338} +02/26/2022 06:45:43 - INFO - codeparrot_training - Step 41072: {'lr': 4.148039159670722e-05, 'samples': 21029376, 'steps': 41072, 'loss/train': 1.2254576683044434} +02/26/2022 06:45:47 - INFO - codeparrot_training - Step 41073: {'lr': 4.14713657588788e-05, 'samples': 21029888, 'steps': 41073, 'loss/train': 1.8093395233154297} +02/26/2022 06:45:52 - INFO - codeparrot_training - Step 41074: {'lr': 4.1462340814320766e-05, 'samples': 21030400, 'steps': 41074, 'loss/train': 1.608319640159607} +02/26/2022 06:45:56 - INFO - codeparrot_training - Step 41075: {'lr': 4.1453316763071927e-05, 'samples': 21030912, 'steps': 41075, 'loss/train': 1.9729677438735962} +02/26/2022 06:46:01 - INFO - codeparrot_training - Step 41076: {'lr': 4.1444293605170766e-05, 'samples': 21031424, 'steps': 41076, 'loss/train': 1.6831915378570557} +02/26/2022 06:46:05 - INFO - codeparrot_training - Step 41077: {'lr': 4.143527134065617e-05, 'samples': 21031936, 'steps': 41077, 'loss/train': 1.9879294633865356} +02/26/2022 06:46:12 - INFO - codeparrot_training - Step 41078: {'lr': 4.142624996956651e-05, 'samples': 21032448, 'steps': 41078, 'loss/train': 5.675451278686523} +02/26/2022 06:46:15 - INFO - codeparrot_training - Step 41079: {'lr': 4.141722949194063e-05, 'samples': 21032960, 'steps': 41079, 'loss/train': 0.2515413165092468} +02/26/2022 06:46:21 - INFO - codeparrot_training - Step 41080: {'lr': 4.140820990781705e-05, 'samples': 21033472, 'steps': 41080, 'loss/train': 1.8496679067611694} +02/26/2022 06:46:24 - INFO - codeparrot_training - Step 41081: {'lr': 4.139919121723459e-05, 'samples': 21033984, 'steps': 41081, 'loss/train': 1.4130698442459106} +02/26/2022 06:46:30 - INFO - codeparrot_training - Step 41082: {'lr': 4.139017342023163e-05, 'samples': 21034496, 'steps': 41082, 'loss/train': 1.170663833618164} +02/26/2022 06:46:33 - INFO - codeparrot_training - Step 41083: {'lr': 4.1381156516846984e-05, 'samples': 21035008, 'steps': 41083, 'loss/train': 1.9587359428405762} +02/26/2022 06:46:39 - INFO - codeparrot_training - Step 41084: {'lr': 4.137214050711921e-05, 'samples': 21035520, 'steps': 41084, 'loss/train': 1.8764231204986572} +02/26/2022 06:46:42 - INFO - codeparrot_training - Step 41085: {'lr': 4.1363125391086915e-05, 'samples': 21036032, 'steps': 41085, 'loss/train': 0.9248769879341125} +02/26/2022 06:46:48 - INFO - codeparrot_training - Step 41086: {'lr': 4.135411116878876e-05, 'samples': 21036544, 'steps': 41086, 'loss/train': 1.3095935583114624} +02/26/2022 06:46:51 - INFO - codeparrot_training - Step 41087: {'lr': 4.1345097840263355e-05, 'samples': 21037056, 'steps': 41087, 'loss/train': 1.5368452072143555} +02/26/2022 06:46:58 - INFO - codeparrot_training - Step 41088: {'lr': 4.133608540554931e-05, 'samples': 21037568, 'steps': 41088, 'loss/train': 1.305829405784607} +02/26/2022 06:47:01 - INFO - codeparrot_training - Step 41089: {'lr': 4.132707386468512e-05, 'samples': 21038080, 'steps': 41089, 'loss/train': 1.9796684980392456} +02/26/2022 06:47:07 - INFO - codeparrot_training - Step 41090: {'lr': 4.131806321770959e-05, 'samples': 21038592, 'steps': 41090, 'loss/train': 1.7605584859848022} +02/26/2022 06:47:10 - INFO - codeparrot_training - Step 41091: {'lr': 4.1309053464661186e-05, 'samples': 21039104, 'steps': 41091, 'loss/train': 3.3215723037719727} +02/26/2022 06:47:16 - INFO - codeparrot_training - Step 41092: {'lr': 4.130004460557854e-05, 'samples': 21039616, 'steps': 41092, 'loss/train': 2.083867311477661} +02/26/2022 06:47:19 - INFO - codeparrot_training - Step 41093: {'lr': 4.129103664050016e-05, 'samples': 21040128, 'steps': 41093, 'loss/train': 2.3799123764038086} +02/26/2022 06:47:25 - INFO - codeparrot_training - Step 41094: {'lr': 4.128202956946478e-05, 'samples': 21040640, 'steps': 41094, 'loss/train': 1.8778314590454102} +02/26/2022 06:47:28 - INFO - codeparrot_training - Step 41095: {'lr': 4.1273023392510906e-05, 'samples': 21041152, 'steps': 41095, 'loss/train': 1.3559863567352295} +02/26/2022 06:47:34 - INFO - codeparrot_training - Step 41096: {'lr': 4.126401810967711e-05, 'samples': 21041664, 'steps': 41096, 'loss/train': 1.9984766244888306} +02/26/2022 06:47:37 - INFO - codeparrot_training - Step 41097: {'lr': 4.125501372100193e-05, 'samples': 21042176, 'steps': 41097, 'loss/train': 1.7497897148132324} +02/26/2022 06:47:44 - INFO - codeparrot_training - Step 41098: {'lr': 4.124601022652405e-05, 'samples': 21042688, 'steps': 41098, 'loss/train': 1.542076826095581} +02/26/2022 06:47:47 - INFO - codeparrot_training - Step 41099: {'lr': 4.123700762628196e-05, 'samples': 21043200, 'steps': 41099, 'loss/train': 1.0483652353286743} +02/26/2022 06:47:53 - INFO - codeparrot_training - Step 41100: {'lr': 4.122800592031425e-05, 'samples': 21043712, 'steps': 41100, 'loss/train': 1.0628455877304077} +02/26/2022 06:47:56 - INFO - codeparrot_training - Step 41101: {'lr': 4.121900510865942e-05, 'samples': 21044224, 'steps': 41101, 'loss/train': 0.1522289514541626} +02/26/2022 06:48:02 - INFO - codeparrot_training - Step 41102: {'lr': 4.121000519135615e-05, 'samples': 21044736, 'steps': 41102, 'loss/train': 1.7213683128356934} +02/26/2022 06:48:06 - INFO - codeparrot_training - Step 41103: {'lr': 4.120100616844289e-05, 'samples': 21045248, 'steps': 41103, 'loss/train': 1.6357460021972656} +02/26/2022 06:48:11 - INFO - codeparrot_training - Step 41104: {'lr': 4.1192008039958234e-05, 'samples': 21045760, 'steps': 41104, 'loss/train': 1.7782361507415771} +02/26/2022 06:48:15 - INFO - codeparrot_training - Step 41105: {'lr': 4.118301080594064e-05, 'samples': 21046272, 'steps': 41105, 'loss/train': 0.8308981657028198} +02/26/2022 06:48:21 - INFO - codeparrot_training - Step 41106: {'lr': 4.117401446642877e-05, 'samples': 21046784, 'steps': 41106, 'loss/train': 2.545792818069458} +02/26/2022 06:48:25 - INFO - codeparrot_training - Step 41107: {'lr': 4.116501902146113e-05, 'samples': 21047296, 'steps': 41107, 'loss/train': 2.341170072555542} +02/26/2022 06:48:28 - INFO - codeparrot_training - Step 41108: {'lr': 4.1156024471076245e-05, 'samples': 21047808, 'steps': 41108, 'loss/train': 1.9347031116485596} +02/26/2022 06:48:34 - INFO - codeparrot_training - Step 41109: {'lr': 4.114703081531254e-05, 'samples': 21048320, 'steps': 41109, 'loss/train': 1.3439594507217407} +02/26/2022 06:48:37 - INFO - codeparrot_training - Step 41110: {'lr': 4.1138038054208735e-05, 'samples': 21048832, 'steps': 41110, 'loss/train': 2.016472816467285} +02/26/2022 06:48:43 - INFO - codeparrot_training - Step 41111: {'lr': 4.112904618780317e-05, 'samples': 21049344, 'steps': 41111, 'loss/train': 1.6328643560409546} +02/26/2022 06:48:46 - INFO - codeparrot_training - Step 41112: {'lr': 4.11200552161346e-05, 'samples': 21049856, 'steps': 41112, 'loss/train': 0.8337056040763855} +02/26/2022 06:48:52 - INFO - codeparrot_training - Step 41113: {'lr': 4.111106513924123e-05, 'samples': 21050368, 'steps': 41113, 'loss/train': 2.245283603668213} +02/26/2022 06:48:56 - INFO - codeparrot_training - Step 41114: {'lr': 4.110207595716181e-05, 'samples': 21050880, 'steps': 41114, 'loss/train': 0.634177029132843} +02/26/2022 06:49:02 - INFO - codeparrot_training - Step 41115: {'lr': 4.1093087669934695e-05, 'samples': 21051392, 'steps': 41115, 'loss/train': 1.2829649448394775} +02/26/2022 06:49:05 - INFO - codeparrot_training - Step 41116: {'lr': 4.108410027759857e-05, 'samples': 21051904, 'steps': 41116, 'loss/train': 2.4708104133605957} +02/26/2022 06:49:11 - INFO - codeparrot_training - Step 41117: {'lr': 4.107511378019171e-05, 'samples': 21052416, 'steps': 41117, 'loss/train': 2.2025561332702637} +02/26/2022 06:49:14 - INFO - codeparrot_training - Step 41118: {'lr': 4.1066128177752764e-05, 'samples': 21052928, 'steps': 41118, 'loss/train': 1.4762216806411743} +02/26/2022 06:49:20 - INFO - codeparrot_training - Step 41119: {'lr': 4.1057143470320134e-05, 'samples': 21053440, 'steps': 41119, 'loss/train': 3.272343158721924} +02/26/2022 06:49:23 - INFO - codeparrot_training - Step 41120: {'lr': 4.104815965793249e-05, 'samples': 21053952, 'steps': 41120, 'loss/train': 1.0439702272415161} +02/26/2022 06:49:29 - INFO - codeparrot_training - Step 41121: {'lr': 4.1039176740628044e-05, 'samples': 21054464, 'steps': 41121, 'loss/train': 1.5443142652511597} +02/26/2022 06:49:33 - INFO - codeparrot_training - Step 41122: {'lr': 4.103019471844546e-05, 'samples': 21054976, 'steps': 41122, 'loss/train': 1.2620333433151245} +02/26/2022 06:49:38 - INFO - codeparrot_training - Step 41123: {'lr': 4.102121359142313e-05, 'samples': 21055488, 'steps': 41123, 'loss/train': 2.318340301513672} +02/26/2022 06:49:41 - INFO - codeparrot_training - Step 41124: {'lr': 4.101223335959961e-05, 'samples': 21056000, 'steps': 41124, 'loss/train': 0.699405312538147} +02/26/2022 06:49:48 - INFO - codeparrot_training - Step 41125: {'lr': 4.100325402301333e-05, 'samples': 21056512, 'steps': 41125, 'loss/train': 0.6871204972267151} +02/26/2022 06:49:51 - INFO - codeparrot_training - Step 41126: {'lr': 4.0994275581702736e-05, 'samples': 21057024, 'steps': 41126, 'loss/train': 2.4336421489715576} +02/26/2022 06:49:57 - INFO - codeparrot_training - Step 41127: {'lr': 4.098529803570625e-05, 'samples': 21057536, 'steps': 41127, 'loss/train': 2.231067180633545} +02/26/2022 06:50:00 - INFO - codeparrot_training - Step 41128: {'lr': 4.097632138506244e-05, 'samples': 21058048, 'steps': 41128, 'loss/train': 1.0571078062057495} +02/26/2022 06:50:06 - INFO - codeparrot_training - Step 41129: {'lr': 4.0967345629809694e-05, 'samples': 21058560, 'steps': 41129, 'loss/train': 0.187117800116539} +02/26/2022 06:50:09 - INFO - codeparrot_training - Step 41130: {'lr': 4.095837076998646e-05, 'samples': 21059072, 'steps': 41130, 'loss/train': 1.3468377590179443} +02/26/2022 06:50:15 - INFO - codeparrot_training - Step 41131: {'lr': 4.094939680563117e-05, 'samples': 21059584, 'steps': 41131, 'loss/train': 1.6845265626907349} +02/26/2022 06:50:18 - INFO - codeparrot_training - Step 41132: {'lr': 4.094042373678225e-05, 'samples': 21060096, 'steps': 41132, 'loss/train': 1.4617278575897217} +02/26/2022 06:50:24 - INFO - codeparrot_training - Step 41133: {'lr': 4.093145156347822e-05, 'samples': 21060608, 'steps': 41133, 'loss/train': 2.399596691131592} +02/26/2022 06:50:27 - INFO - codeparrot_training - Step 41134: {'lr': 4.092248028575746e-05, 'samples': 21061120, 'steps': 41134, 'loss/train': 2.0908172130584717} +02/26/2022 06:50:33 - INFO - codeparrot_training - Step 41135: {'lr': 4.091350990365841e-05, 'samples': 21061632, 'steps': 41135, 'loss/train': 0.8410221934318542} +02/26/2022 06:50:37 - INFO - codeparrot_training - Step 41136: {'lr': 4.090454041721942e-05, 'samples': 21062144, 'steps': 41136, 'loss/train': 1.5373375415802002} +02/26/2022 06:50:42 - INFO - codeparrot_training - Step 41137: {'lr': 4.0895571826479045e-05, 'samples': 21062656, 'steps': 41137, 'loss/train': 1.8123527765274048} +02/26/2022 06:50:46 - INFO - codeparrot_training - Step 41138: {'lr': 4.0886604131475655e-05, 'samples': 21063168, 'steps': 41138, 'loss/train': 1.6958438158035278} +02/26/2022 06:50:52 - INFO - codeparrot_training - Step 41139: {'lr': 4.087763733224767e-05, 'samples': 21063680, 'steps': 41139, 'loss/train': 1.895423173904419} +02/26/2022 06:50:55 - INFO - codeparrot_training - Step 41140: {'lr': 4.086867142883338e-05, 'samples': 21064192, 'steps': 41140, 'loss/train': 0.5312969088554382} +02/26/2022 06:51:01 - INFO - codeparrot_training - Step 41141: {'lr': 4.0859706421271376e-05, 'samples': 21064704, 'steps': 41141, 'loss/train': 2.028679847717285} +02/26/2022 06:51:04 - INFO - codeparrot_training - Step 41142: {'lr': 4.085074230959998e-05, 'samples': 21065216, 'steps': 41142, 'loss/train': 2.403795003890991} +02/26/2022 06:51:10 - INFO - codeparrot_training - Step 41143: {'lr': 4.084177909385758e-05, 'samples': 21065728, 'steps': 41143, 'loss/train': 1.3857519626617432} +02/26/2022 06:51:13 - INFO - codeparrot_training - Step 41144: {'lr': 4.083281677408254e-05, 'samples': 21066240, 'steps': 41144, 'loss/train': 1.2701811790466309} +02/26/2022 06:51:19 - INFO - codeparrot_training - Step 41145: {'lr': 4.0823855350313356e-05, 'samples': 21066752, 'steps': 41145, 'loss/train': 1.6163908243179321} +02/26/2022 06:51:23 - INFO - codeparrot_training - Step 41146: {'lr': 4.081489482258829e-05, 'samples': 21067264, 'steps': 41146, 'loss/train': 0.041384462267160416} +02/26/2022 06:51:28 - INFO - codeparrot_training - Step 41147: {'lr': 4.0805935190945916e-05, 'samples': 21067776, 'steps': 41147, 'loss/train': 2.0430448055267334} +02/26/2022 06:51:32 - INFO - codeparrot_training - Step 41148: {'lr': 4.079697645542435e-05, 'samples': 21068288, 'steps': 41148, 'loss/train': 2.744699716567993} +02/26/2022 06:51:37 - INFO - codeparrot_training - Step 41149: {'lr': 4.0788018616062186e-05, 'samples': 21068800, 'steps': 41149, 'loss/train': 2.1895534992218018} +02/26/2022 06:51:41 - INFO - codeparrot_training - Step 41150: {'lr': 4.077906167289766e-05, 'samples': 21069312, 'steps': 41150, 'loss/train': 2.1466238498687744} +02/26/2022 06:51:46 - INFO - codeparrot_training - Step 41151: {'lr': 4.0770105625969306e-05, 'samples': 21069824, 'steps': 41151, 'loss/train': 2.0979676246643066} +02/26/2022 06:51:50 - INFO - codeparrot_training - Step 41152: {'lr': 4.076115047531526e-05, 'samples': 21070336, 'steps': 41152, 'loss/train': 1.7607640027999878} +02/26/2022 06:51:56 - INFO - codeparrot_training - Step 41153: {'lr': 4.0752196220974065e-05, 'samples': 21070848, 'steps': 41153, 'loss/train': 1.2090706825256348} +02/26/2022 06:51:59 - INFO - codeparrot_training - Step 41154: {'lr': 4.0743242862983975e-05, 'samples': 21071360, 'steps': 41154, 'loss/train': 3.4084408283233643} +02/26/2022 06:52:05 - INFO - codeparrot_training - Step 41155: {'lr': 4.073429040138349e-05, 'samples': 21071872, 'steps': 41155, 'loss/train': 1.9405903816223145} +02/26/2022 06:52:09 - INFO - codeparrot_training - Step 41156: {'lr': 4.072533883621074e-05, 'samples': 21072384, 'steps': 41156, 'loss/train': 1.894167423248291} +02/26/2022 06:52:14 - INFO - codeparrot_training - Step 41157: {'lr': 4.071638816750425e-05, 'samples': 21072896, 'steps': 41157, 'loss/train': 2.133634328842163} +02/26/2022 06:52:18 - INFO - codeparrot_training - Step 41158: {'lr': 4.070743839530222e-05, 'samples': 21073408, 'steps': 41158, 'loss/train': 1.4407835006713867} +02/26/2022 06:52:23 - INFO - codeparrot_training - Step 41159: {'lr': 4.069848951964314e-05, 'samples': 21073920, 'steps': 41159, 'loss/train': 2.2803404331207275} +02/26/2022 06:52:26 - INFO - codeparrot_training - Step 41160: {'lr': 4.068954154056528e-05, 'samples': 21074432, 'steps': 41160, 'loss/train': 2.0037155151367188} +02/26/2022 06:52:32 - INFO - codeparrot_training - Step 41161: {'lr': 4.0680594458106956e-05, 'samples': 21074944, 'steps': 41161, 'loss/train': 2.6778759956359863} +02/26/2022 06:52:35 - INFO - codeparrot_training - Step 41162: {'lr': 4.067164827230643e-05, 'samples': 21075456, 'steps': 41162, 'loss/train': 1.4494116306304932} +02/26/2022 06:52:41 - INFO - codeparrot_training - Step 41163: {'lr': 4.066270298320215e-05, 'samples': 21075968, 'steps': 41163, 'loss/train': 1.5724364519119263} +02/26/2022 06:52:44 - INFO - codeparrot_training - Step 41164: {'lr': 4.0653758590832395e-05, 'samples': 21076480, 'steps': 41164, 'loss/train': 2.2255280017852783} +02/26/2022 06:52:50 - INFO - codeparrot_training - Step 41165: {'lr': 4.064481509523543e-05, 'samples': 21076992, 'steps': 41165, 'loss/train': 1.8004752397537231} +02/26/2022 06:52:53 - INFO - codeparrot_training - Step 41166: {'lr': 4.0635872496449566e-05, 'samples': 21077504, 'steps': 41166, 'loss/train': 1.2163745164871216} +02/26/2022 06:52:59 - INFO - codeparrot_training - Step 41167: {'lr': 4.062693079451321e-05, 'samples': 21078016, 'steps': 41167, 'loss/train': 1.349444031715393} +02/26/2022 06:53:03 - INFO - codeparrot_training - Step 41168: {'lr': 4.0617989989464586e-05, 'samples': 21078528, 'steps': 41168, 'loss/train': 1.8627488613128662} +02/26/2022 06:53:08 - INFO - codeparrot_training - Step 41169: {'lr': 4.0609050081342024e-05, 'samples': 21079040, 'steps': 41169, 'loss/train': 1.115132212638855} +02/26/2022 06:53:11 - INFO - codeparrot_training - Step 41170: {'lr': 4.0600111070183715e-05, 'samples': 21079552, 'steps': 41170, 'loss/train': 1.0146816968917847} +02/26/2022 06:53:18 - INFO - codeparrot_training - Step 41171: {'lr': 4.0591172956028126e-05, 'samples': 21080064, 'steps': 41171, 'loss/train': 1.741151213645935} +02/26/2022 06:53:21 - INFO - codeparrot_training - Step 41172: {'lr': 4.058223573891343e-05, 'samples': 21080576, 'steps': 41172, 'loss/train': 0.8500745892524719} +02/26/2022 06:53:27 - INFO - codeparrot_training - Step 41173: {'lr': 4.057329941887794e-05, 'samples': 21081088, 'steps': 41173, 'loss/train': 3.3174288272857666} +02/26/2022 06:53:30 - INFO - codeparrot_training - Step 41174: {'lr': 4.056436399595989e-05, 'samples': 21081600, 'steps': 41174, 'loss/train': 1.672269582748413} +02/26/2022 06:53:36 - INFO - codeparrot_training - Step 41175: {'lr': 4.0555429470197666e-05, 'samples': 21082112, 'steps': 41175, 'loss/train': 1.6578810214996338} +02/26/2022 06:53:39 - INFO - codeparrot_training - Step 41176: {'lr': 4.0546495841629475e-05, 'samples': 21082624, 'steps': 41176, 'loss/train': 1.4162365198135376} +02/26/2022 06:53:45 - INFO - codeparrot_training - Step 41177: {'lr': 4.053756311029358e-05, 'samples': 21083136, 'steps': 41177, 'loss/train': 1.2575935125350952} +02/26/2022 06:53:50 - INFO - codeparrot_training - Step 41178: {'lr': 4.052863127622825e-05, 'samples': 21083648, 'steps': 41178, 'loss/train': 2.2112715244293213} +02/26/2022 06:53:54 - INFO - codeparrot_training - Step 41179: {'lr': 4.0519700339471694e-05, 'samples': 21084160, 'steps': 41179, 'loss/train': 2.177452564239502} +02/26/2022 06:54:00 - INFO - codeparrot_training - Step 41180: {'lr': 4.0510770300062285e-05, 'samples': 21084672, 'steps': 41180, 'loss/train': 1.827593207359314} +02/26/2022 06:54:03 - INFO - codeparrot_training - Step 41181: {'lr': 4.0501841158038206e-05, 'samples': 21085184, 'steps': 41181, 'loss/train': 1.6736212968826294} +02/26/2022 06:54:09 - INFO - codeparrot_training - Step 41182: {'lr': 4.049291291343771e-05, 'samples': 21085696, 'steps': 41182, 'loss/train': 2.174193859100342} +02/26/2022 06:54:12 - INFO - codeparrot_training - Step 41183: {'lr': 4.048398556629901e-05, 'samples': 21086208, 'steps': 41183, 'loss/train': 1.22590172290802} +02/26/2022 06:54:18 - INFO - codeparrot_training - Step 41184: {'lr': 4.047505911666044e-05, 'samples': 21086720, 'steps': 41184, 'loss/train': 1.1328811645507812} +02/26/2022 06:54:21 - INFO - codeparrot_training - Step 41185: {'lr': 4.046613356456011e-05, 'samples': 21087232, 'steps': 41185, 'loss/train': 2.1060800552368164} +02/26/2022 06:54:27 - INFO - codeparrot_training - Step 41186: {'lr': 4.045720891003649e-05, 'samples': 21087744, 'steps': 41186, 'loss/train': 1.4242898225784302} +02/26/2022 06:54:30 - INFO - codeparrot_training - Step 41187: {'lr': 4.0448285153127486e-05, 'samples': 21088256, 'steps': 41187, 'loss/train': 3.2226996421813965} +02/26/2022 06:54:36 - INFO - codeparrot_training - Step 41188: {'lr': 4.0439362293871576e-05, 'samples': 21088768, 'steps': 41188, 'loss/train': 0.7156848311424255} +02/26/2022 06:54:39 - INFO - codeparrot_training - Step 41189: {'lr': 4.043044033230681e-05, 'samples': 21089280, 'steps': 41189, 'loss/train': 0.9726080298423767} +02/26/2022 06:54:45 - INFO - codeparrot_training - Step 41190: {'lr': 4.0421519268471624e-05, 'samples': 21089792, 'steps': 41190, 'loss/train': 1.661525845527649} +02/26/2022 06:54:48 - INFO - codeparrot_training - Step 41191: {'lr': 4.0412599102404e-05, 'samples': 21090304, 'steps': 41191, 'loss/train': 1.864445686340332} +02/26/2022 06:54:54 - INFO - codeparrot_training - Step 41192: {'lr': 4.040367983414228e-05, 'samples': 21090816, 'steps': 41192, 'loss/train': 2.1463263034820557} +02/26/2022 06:54:58 - INFO - codeparrot_training - Step 41193: {'lr': 4.039476146372459e-05, 'samples': 21091328, 'steps': 41193, 'loss/train': 1.0734728574752808} +02/26/2022 06:55:03 - INFO - codeparrot_training - Step 41194: {'lr': 4.038584399118925e-05, 'samples': 21091840, 'steps': 41194, 'loss/train': 1.345886468887329} +02/26/2022 06:55:07 - INFO - codeparrot_training - Step 41195: {'lr': 4.037692741657439e-05, 'samples': 21092352, 'steps': 41195, 'loss/train': 0.40856385231018066} +02/26/2022 06:55:12 - INFO - codeparrot_training - Step 41196: {'lr': 4.036801173991822e-05, 'samples': 21092864, 'steps': 41196, 'loss/train': 2.2371835708618164} +02/26/2022 06:55:16 - INFO - codeparrot_training - Step 41197: {'lr': 4.0359096961258864e-05, 'samples': 21093376, 'steps': 41197, 'loss/train': 1.3627609014511108} +02/26/2022 06:55:21 - INFO - codeparrot_training - Step 41198: {'lr': 4.0350183080634595e-05, 'samples': 21093888, 'steps': 41198, 'loss/train': 1.2348918914794922} +02/26/2022 06:55:25 - INFO - codeparrot_training - Step 41199: {'lr': 4.034127009808361e-05, 'samples': 21094400, 'steps': 41199, 'loss/train': 1.4219896793365479} +02/26/2022 06:55:30 - INFO - codeparrot_training - Step 41200: {'lr': 4.033235801364402e-05, 'samples': 21094912, 'steps': 41200, 'loss/train': 1.7162977457046509} +02/26/2022 06:55:34 - INFO - codeparrot_training - Step 41201: {'lr': 4.032344682735401e-05, 'samples': 21095424, 'steps': 41201, 'loss/train': 2.4636213779449463} +02/26/2022 06:55:39 - INFO - codeparrot_training - Step 41202: {'lr': 4.0314536539251796e-05, 'samples': 21095936, 'steps': 41202, 'loss/train': 1.429274559020996} +02/26/2022 06:55:43 - INFO - codeparrot_training - Step 41203: {'lr': 4.0305627149375524e-05, 'samples': 21096448, 'steps': 41203, 'loss/train': 1.6399781703948975} +02/26/2022 06:55:48 - INFO - codeparrot_training - Step 41204: {'lr': 4.029671865776338e-05, 'samples': 21096960, 'steps': 41204, 'loss/train': 1.4864203929901123} +02/26/2022 06:55:52 - INFO - codeparrot_training - Step 41205: {'lr': 4.028781106445345e-05, 'samples': 21097472, 'steps': 41205, 'loss/train': 1.7550987005233765} +02/26/2022 06:55:58 - INFO - codeparrot_training - Step 41206: {'lr': 4.0278904369483973e-05, 'samples': 21097984, 'steps': 41206, 'loss/train': 0.5205437541007996} +02/26/2022 06:56:02 - INFO - codeparrot_training - Step 41207: {'lr': 4.026999857289304e-05, 'samples': 21098496, 'steps': 41207, 'loss/train': 0.7449386715888977} +02/26/2022 06:56:07 - INFO - codeparrot_training - Step 41208: {'lr': 4.0261093674718975e-05, 'samples': 21099008, 'steps': 41208, 'loss/train': 0.026629606261849403} +02/26/2022 06:56:11 - INFO - codeparrot_training - Step 41209: {'lr': 4.025218967499963e-05, 'samples': 21099520, 'steps': 41209, 'loss/train': 1.4720178842544556} +02/26/2022 06:56:16 - INFO - codeparrot_training - Step 41210: {'lr': 4.024328657377338e-05, 'samples': 21100032, 'steps': 41210, 'loss/train': 2.110401153564453} +02/26/2022 06:56:20 - INFO - codeparrot_training - Step 41211: {'lr': 4.023438437107829e-05, 'samples': 21100544, 'steps': 41211, 'loss/train': 1.2986823320388794} +02/26/2022 06:56:25 - INFO - codeparrot_training - Step 41212: {'lr': 4.0225483066952476e-05, 'samples': 21101056, 'steps': 41212, 'loss/train': 1.8058794736862183} +02/26/2022 06:56:29 - INFO - codeparrot_training - Step 41213: {'lr': 4.021658266143402e-05, 'samples': 21101568, 'steps': 41213, 'loss/train': 2.134857416152954} +02/26/2022 06:56:34 - INFO - codeparrot_training - Step 41214: {'lr': 4.020768315456119e-05, 'samples': 21102080, 'steps': 41214, 'loss/train': 2.508793592453003} +02/26/2022 06:56:38 - INFO - codeparrot_training - Step 41215: {'lr': 4.019878454637202e-05, 'samples': 21102592, 'steps': 41215, 'loss/train': 1.2010328769683838} +02/26/2022 06:56:44 - INFO - codeparrot_training - Step 41216: {'lr': 4.018988683690461e-05, 'samples': 21103104, 'steps': 41216, 'loss/train': 1.67734956741333} +02/26/2022 06:56:47 - INFO - codeparrot_training - Step 41217: {'lr': 4.0180990026197075e-05, 'samples': 21103616, 'steps': 41217, 'loss/train': 1.0418322086334229} +02/26/2022 06:56:53 - INFO - codeparrot_training - Step 41218: {'lr': 4.01720941142876e-05, 'samples': 21104128, 'steps': 41218, 'loss/train': 2.3684756755828857} +02/26/2022 06:56:56 - INFO - codeparrot_training - Step 41219: {'lr': 4.016319910121424e-05, 'samples': 21104640, 'steps': 41219, 'loss/train': 1.4005308151245117} +02/26/2022 06:57:02 - INFO - codeparrot_training - Step 41220: {'lr': 4.0154304987015056e-05, 'samples': 21105152, 'steps': 41220, 'loss/train': 2.0739009380340576} +02/26/2022 06:57:05 - INFO - codeparrot_training - Step 41221: {'lr': 4.0145411771728256e-05, 'samples': 21105664, 'steps': 41221, 'loss/train': 2.0402870178222656} +02/26/2022 06:57:11 - INFO - codeparrot_training - Step 41222: {'lr': 4.013651945539187e-05, 'samples': 21106176, 'steps': 41222, 'loss/train': 1.9704837799072266} +02/26/2022 06:57:15 - INFO - codeparrot_training - Step 41223: {'lr': 4.012762803804401e-05, 'samples': 21106688, 'steps': 41223, 'loss/train': 1.009820818901062} +02/26/2022 06:57:20 - INFO - codeparrot_training - Step 41224: {'lr': 4.011873751972267e-05, 'samples': 21107200, 'steps': 41224, 'loss/train': 1.7188966274261475} +02/26/2022 06:57:24 - INFO - codeparrot_training - Step 41225: {'lr': 4.010984790046615e-05, 'samples': 21107712, 'steps': 41225, 'loss/train': 2.1077184677124023} +02/26/2022 06:57:30 - INFO - codeparrot_training - Step 41226: {'lr': 4.010095918031228e-05, 'samples': 21108224, 'steps': 41226, 'loss/train': 2.5008511543273926} +02/26/2022 06:57:33 - INFO - codeparrot_training - Step 41227: {'lr': 4.009207135929929e-05, 'samples': 21108736, 'steps': 41227, 'loss/train': 1.7562178373336792} +02/26/2022 06:57:39 - INFO - codeparrot_training - Step 41228: {'lr': 4.008318443746517e-05, 'samples': 21109248, 'steps': 41228, 'loss/train': 1.1937103271484375} +02/26/2022 06:57:42 - INFO - codeparrot_training - Step 41229: {'lr': 4.007429841484814e-05, 'samples': 21109760, 'steps': 41229, 'loss/train': 0.6701145172119141} +02/26/2022 06:57:48 - INFO - codeparrot_training - Step 41230: {'lr': 4.0065413291486026e-05, 'samples': 21110272, 'steps': 41230, 'loss/train': 1.6751470565795898} +02/26/2022 06:57:52 - INFO - codeparrot_training - Step 41231: {'lr': 4.0056529067417105e-05, 'samples': 21110784, 'steps': 41231, 'loss/train': 1.5667650699615479} +02/26/2022 06:57:55 - INFO - codeparrot_training - Step 41232: {'lr': 4.004764574267927e-05, 'samples': 21111296, 'steps': 41232, 'loss/train': 1.8498036861419678} +02/26/2022 06:58:01 - INFO - codeparrot_training - Step 41233: {'lr': 4.003876331731071e-05, 'samples': 21111808, 'steps': 41233, 'loss/train': 2.22662353515625} +02/26/2022 06:58:04 - INFO - codeparrot_training - Step 41234: {'lr': 4.0029881791349424e-05, 'samples': 21112320, 'steps': 41234, 'loss/train': 1.0748449563980103} +02/26/2022 06:58:10 - INFO - codeparrot_training - Step 41235: {'lr': 4.0021001164833456e-05, 'samples': 21112832, 'steps': 41235, 'loss/train': 0.7685216069221497} +02/26/2022 06:58:13 - INFO - codeparrot_training - Step 41236: {'lr': 4.001212143780078e-05, 'samples': 21113344, 'steps': 41236, 'loss/train': 1.6989455223083496} +02/26/2022 06:58:19 - INFO - codeparrot_training - Step 41237: {'lr': 4.000324261028956e-05, 'samples': 21113856, 'steps': 41237, 'loss/train': 0.07501186430454254} +02/26/2022 06:58:22 - INFO - codeparrot_training - Step 41238: {'lr': 3.999436468233778e-05, 'samples': 21114368, 'steps': 41238, 'loss/train': 2.3117334842681885} +02/26/2022 06:58:29 - INFO - codeparrot_training - Step 41239: {'lr': 3.9985487653983435e-05, 'samples': 21114880, 'steps': 41239, 'loss/train': 1.8053890466690063} +02/26/2022 06:58:32 - INFO - codeparrot_training - Step 41240: {'lr': 3.997661152526452e-05, 'samples': 21115392, 'steps': 41240, 'loss/train': 1.7694995403289795} +02/26/2022 06:58:38 - INFO - codeparrot_training - Step 41241: {'lr': 3.9967736296219164e-05, 'samples': 21115904, 'steps': 41241, 'loss/train': 0.1313379853963852} +02/26/2022 06:58:41 - INFO - codeparrot_training - Step 41242: {'lr': 3.9958861966885305e-05, 'samples': 21116416, 'steps': 41242, 'loss/train': 2.506037473678589} +02/26/2022 06:58:47 - INFO - codeparrot_training - Step 41243: {'lr': 3.994998853730108e-05, 'samples': 21116928, 'steps': 41243, 'loss/train': 1.5256882905960083} +02/26/2022 06:58:50 - INFO - codeparrot_training - Step 41244: {'lr': 3.994111600750427e-05, 'samples': 21117440, 'steps': 41244, 'loss/train': 2.7465505599975586} +02/26/2022 06:58:56 - INFO - codeparrot_training - Step 41245: {'lr': 3.993224437753309e-05, 'samples': 21117952, 'steps': 41245, 'loss/train': 1.1976745128631592} +02/26/2022 06:58:59 - INFO - codeparrot_training - Step 41246: {'lr': 3.992337364742543e-05, 'samples': 21118464, 'steps': 41246, 'loss/train': 0.7530762553215027} +02/26/2022 06:59:05 - INFO - codeparrot_training - Step 41247: {'lr': 3.991450381721945e-05, 'samples': 21118976, 'steps': 41247, 'loss/train': 1.2591278553009033} +02/26/2022 06:59:08 - INFO - codeparrot_training - Step 41248: {'lr': 3.99056348869529e-05, 'samples': 21119488, 'steps': 41248, 'loss/train': 1.8351786136627197} +02/26/2022 06:59:14 - INFO - codeparrot_training - Step 41249: {'lr': 3.9896766856663936e-05, 'samples': 21120000, 'steps': 41249, 'loss/train': 0.7252730131149292} +02/26/2022 06:59:17 - INFO - codeparrot_training - Step 41250: {'lr': 3.988789972639045e-05, 'samples': 21120512, 'steps': 41250, 'loss/train': 1.743416428565979} +02/26/2022 06:59:23 - INFO - codeparrot_training - Step 41251: {'lr': 3.987903349617064e-05, 'samples': 21121024, 'steps': 41251, 'loss/train': 2.4336726665496826} +02/26/2022 06:59:26 - INFO - codeparrot_training - Step 41252: {'lr': 3.987016816604219e-05, 'samples': 21121536, 'steps': 41252, 'loss/train': 1.9759290218353271} +02/26/2022 06:59:32 - INFO - codeparrot_training - Step 41253: {'lr': 3.986130373604327e-05, 'samples': 21122048, 'steps': 41253, 'loss/train': 1.8637784719467163} +02/26/2022 06:59:35 - INFO - codeparrot_training - Step 41254: {'lr': 3.985244020621173e-05, 'samples': 21122560, 'steps': 41254, 'loss/train': 1.6633825302124023} +02/26/2022 06:59:41 - INFO - codeparrot_training - Step 41255: {'lr': 3.984357757658569e-05, 'samples': 21123072, 'steps': 41255, 'loss/train': 1.6736080646514893} +02/26/2022 06:59:45 - INFO - codeparrot_training - Step 41256: {'lr': 3.9834715847203e-05, 'samples': 21123584, 'steps': 41256, 'loss/train': 2.252772569656372} +02/26/2022 06:59:50 - INFO - codeparrot_training - Step 41257: {'lr': 3.982585501810168e-05, 'samples': 21124096, 'steps': 41257, 'loss/train': 2.448148012161255} +02/26/2022 06:59:54 - INFO - codeparrot_training - Step 41258: {'lr': 3.981699508931966e-05, 'samples': 21124608, 'steps': 41258, 'loss/train': 1.6163902282714844} +02/26/2022 06:59:59 - INFO - codeparrot_training - Step 41259: {'lr': 3.980813606089481e-05, 'samples': 21125120, 'steps': 41259, 'loss/train': 2.9076037406921387} +02/26/2022 07:00:03 - INFO - codeparrot_training - Step 41260: {'lr': 3.979927793286522e-05, 'samples': 21125632, 'steps': 41260, 'loss/train': 2.1136412620544434} +02/26/2022 07:00:08 - INFO - codeparrot_training - Step 41261: {'lr': 3.979042070526881e-05, 'samples': 21126144, 'steps': 41261, 'loss/train': 2.231005907058716} +02/26/2022 07:00:12 - INFO - codeparrot_training - Step 41262: {'lr': 3.978156437814345e-05, 'samples': 21126656, 'steps': 41262, 'loss/train': 1.4403915405273438} +02/26/2022 07:00:17 - INFO - codeparrot_training - Step 41263: {'lr': 3.97727089515271e-05, 'samples': 21127168, 'steps': 41263, 'loss/train': 1.971002459526062} +02/26/2022 07:00:21 - INFO - codeparrot_training - Step 41264: {'lr': 3.976385442545774e-05, 'samples': 21127680, 'steps': 41264, 'loss/train': 1.0498101711273193} +02/26/2022 07:00:27 - INFO - codeparrot_training - Step 41265: {'lr': 3.975500079997327e-05, 'samples': 21128192, 'steps': 41265, 'loss/train': 2.522651195526123} +02/26/2022 07:00:30 - INFO - codeparrot_training - Step 41266: {'lr': 3.974614807511162e-05, 'samples': 21128704, 'steps': 41266, 'loss/train': 1.9527454376220703} +02/26/2022 07:00:36 - INFO - codeparrot_training - Step 41267: {'lr': 3.973729625091066e-05, 'samples': 21129216, 'steps': 41267, 'loss/train': 1.787041187286377} +02/26/2022 07:00:39 - INFO - codeparrot_training - Step 41268: {'lr': 3.972844532740841e-05, 'samples': 21129728, 'steps': 41268, 'loss/train': 1.775451898574829} +02/26/2022 07:00:45 - INFO - codeparrot_training - Step 41269: {'lr': 3.971959530464272e-05, 'samples': 21130240, 'steps': 41269, 'loss/train': 1.4558331966400146} +02/26/2022 07:00:49 - INFO - codeparrot_training - Step 41270: {'lr': 3.971074618265153e-05, 'samples': 21130752, 'steps': 41270, 'loss/train': 1.5109256505966187} +02/26/2022 07:00:55 - INFO - codeparrot_training - Step 41271: {'lr': 3.970189796147267e-05, 'samples': 21131264, 'steps': 41271, 'loss/train': 2.0873231887817383} +02/26/2022 07:00:58 - INFO - codeparrot_training - Step 41272: {'lr': 3.9693050641144145e-05, 'samples': 21131776, 'steps': 41272, 'loss/train': 1.465606451034546} +02/26/2022 07:01:02 - INFO - codeparrot_training - Step 41273: {'lr': 3.9684204221703826e-05, 'samples': 21132288, 'steps': 41273, 'loss/train': 2.0423688888549805} +02/26/2022 07:01:07 - INFO - codeparrot_training - Step 41274: {'lr': 3.967535870318958e-05, 'samples': 21132800, 'steps': 41274, 'loss/train': 2.768829584121704} +02/26/2022 07:01:11 - INFO - codeparrot_training - Step 41275: {'lr': 3.966651408563926e-05, 'samples': 21133312, 'steps': 41275, 'loss/train': 1.856337308883667} +02/26/2022 07:01:17 - INFO - codeparrot_training - Step 41276: {'lr': 3.965767036909085e-05, 'samples': 21133824, 'steps': 41276, 'loss/train': 1.9268488883972168} +02/26/2022 07:01:20 - INFO - codeparrot_training - Step 41277: {'lr': 3.9648827553582204e-05, 'samples': 21134336, 'steps': 41277, 'loss/train': 1.5484291315078735} +02/26/2022 07:01:26 - INFO - codeparrot_training - Step 41278: {'lr': 3.963998563915119e-05, 'samples': 21134848, 'steps': 41278, 'loss/train': 2.0642435550689697} +02/26/2022 07:01:29 - INFO - codeparrot_training - Step 41279: {'lr': 3.9631144625835614e-05, 'samples': 21135360, 'steps': 41279, 'loss/train': 2.2309176921844482} +02/26/2022 07:01:35 - INFO - codeparrot_training - Step 41280: {'lr': 3.962230451367349e-05, 'samples': 21135872, 'steps': 41280, 'loss/train': 1.3947393894195557} +02/26/2022 07:01:38 - INFO - codeparrot_training - Step 41281: {'lr': 3.961346530270252e-05, 'samples': 21136384, 'steps': 41281, 'loss/train': 2.2639381885528564} +02/26/2022 07:01:44 - INFO - codeparrot_training - Step 41282: {'lr': 3.96046269929608e-05, 'samples': 21136896, 'steps': 41282, 'loss/train': 1.8505698442459106} +02/26/2022 07:01:47 - INFO - codeparrot_training - Step 41283: {'lr': 3.9595789584485925e-05, 'samples': 21137408, 'steps': 41283, 'loss/train': 2.3372275829315186} +02/26/2022 07:01:55 - INFO - codeparrot_training - Step 41284: {'lr': 3.958695307731594e-05, 'samples': 21137920, 'steps': 41284, 'loss/train': 1.7233986854553223} +02/26/2022 07:01:58 - INFO - codeparrot_training - Step 41285: {'lr': 3.957811747148857e-05, 'samples': 21138432, 'steps': 41285, 'loss/train': 1.3501551151275635} +02/26/2022 07:02:04 - INFO - codeparrot_training - Step 41286: {'lr': 3.956928276704186e-05, 'samples': 21138944, 'steps': 41286, 'loss/train': 1.230549693107605} +02/26/2022 07:02:07 - INFO - codeparrot_training - Step 41287: {'lr': 3.9560448964013394e-05, 'samples': 21139456, 'steps': 41287, 'loss/train': 0.4091601073741913} +02/26/2022 07:02:13 - INFO - codeparrot_training - Step 41288: {'lr': 3.95516160624412e-05, 'samples': 21139968, 'steps': 41288, 'loss/train': 0.35843050479888916} +02/26/2022 07:02:16 - INFO - codeparrot_training - Step 41289: {'lr': 3.9542784062363004e-05, 'samples': 21140480, 'steps': 41289, 'loss/train': 0.051794614642858505} +02/26/2022 07:02:22 - INFO - codeparrot_training - Step 41290: {'lr': 3.9533952963816815e-05, 'samples': 21140992, 'steps': 41290, 'loss/train': 1.6985957622528076} +02/26/2022 07:02:25 - INFO - codeparrot_training - Step 41291: {'lr': 3.95251227668402e-05, 'samples': 21141504, 'steps': 41291, 'loss/train': 0.6630358099937439} +02/26/2022 07:02:31 - INFO - codeparrot_training - Step 41292: {'lr': 3.9516293471471204e-05, 'samples': 21142016, 'steps': 41292, 'loss/train': 0.9668679237365723} +02/26/2022 07:02:34 - INFO - codeparrot_training - Step 41293: {'lr': 3.9507465077747526e-05, 'samples': 21142528, 'steps': 41293, 'loss/train': 1.6144204139709473} +02/26/2022 07:02:42 - INFO - codeparrot_training - Step 41294: {'lr': 3.949863758570707e-05, 'samples': 21143040, 'steps': 41294, 'loss/train': 1.9905365705490112} +02/26/2022 07:02:45 - INFO - codeparrot_training - Step 41295: {'lr': 3.948981099538759e-05, 'samples': 21143552, 'steps': 41295, 'loss/train': 1.3369977474212646} +02/26/2022 07:02:51 - INFO - codeparrot_training - Step 41296: {'lr': 3.948098530682695e-05, 'samples': 21144064, 'steps': 41296, 'loss/train': 1.4646605253219604} +02/26/2022 07:02:54 - INFO - codeparrot_training - Step 41297: {'lr': 3.9472160520062836e-05, 'samples': 21144576, 'steps': 41297, 'loss/train': 1.7085332870483398} +02/26/2022 07:03:00 - INFO - codeparrot_training - Step 41298: {'lr': 3.946333663513321e-05, 'samples': 21145088, 'steps': 41298, 'loss/train': 1.3035117387771606} +02/26/2022 07:03:05 - INFO - codeparrot_training - Step 41299: {'lr': 3.945451365207581e-05, 'samples': 21145600, 'steps': 41299, 'loss/train': 2.3040616512298584} +02/26/2022 07:03:09 - INFO - codeparrot_training - Step 41300: {'lr': 3.944569157092839e-05, 'samples': 21146112, 'steps': 41300, 'loss/train': 0.05751051381230354} +02/26/2022 07:03:14 - INFO - codeparrot_training - Step 41301: {'lr': 3.9436870391728716e-05, 'samples': 21146624, 'steps': 41301, 'loss/train': 1.4843560457229614} +02/26/2022 07:03:18 - INFO - codeparrot_training - Step 41302: {'lr': 3.942805011451469e-05, 'samples': 21147136, 'steps': 41302, 'loss/train': 2.106691360473633} +02/26/2022 07:03:25 - INFO - codeparrot_training - Step 41303: {'lr': 3.941923073932405e-05, 'samples': 21147648, 'steps': 41303, 'loss/train': 1.0581002235412598} +02/26/2022 07:03:29 - INFO - codeparrot_training - Step 41304: {'lr': 3.941041226619455e-05, 'samples': 21148160, 'steps': 41304, 'loss/train': 1.5383330583572388} +02/26/2022 07:03:34 - INFO - codeparrot_training - Step 41305: {'lr': 3.9401594695163886e-05, 'samples': 21148672, 'steps': 41305, 'loss/train': 1.645405650138855} +02/26/2022 07:03:38 - INFO - codeparrot_training - Step 41306: {'lr': 3.939277802627e-05, 'samples': 21149184, 'steps': 41306, 'loss/train': 1.3650903701782227} +02/26/2022 07:03:43 - INFO - codeparrot_training - Step 41307: {'lr': 3.93839622595506e-05, 'samples': 21149696, 'steps': 41307, 'loss/train': 2.1440048217773438} +02/26/2022 07:03:47 - INFO - codeparrot_training - Step 41308: {'lr': 3.9375147395043384e-05, 'samples': 21150208, 'steps': 41308, 'loss/train': 0.9623491168022156} +02/26/2022 07:03:50 - INFO - codeparrot_training - Step 41309: {'lr': 3.93663334327862e-05, 'samples': 21150720, 'steps': 41309, 'loss/train': 1.1603679656982422} +02/26/2022 07:03:56 - INFO - codeparrot_training - Step 41310: {'lr': 3.935752037281667e-05, 'samples': 21151232, 'steps': 41310, 'loss/train': 0.5403485894203186} +02/26/2022 07:03:59 - INFO - codeparrot_training - Step 41311: {'lr': 3.9348708215172694e-05, 'samples': 21151744, 'steps': 41311, 'loss/train': 1.7832581996917725} +02/26/2022 07:04:05 - INFO - codeparrot_training - Step 41312: {'lr': 3.9339896959891985e-05, 'samples': 21152256, 'steps': 41312, 'loss/train': 2.46216082572937} +02/26/2022 07:04:12 - INFO - codeparrot_training - Step 41313: {'lr': 3.933108660701223e-05, 'samples': 21152768, 'steps': 41313, 'loss/train': 1.0073262453079224} +02/26/2022 07:04:16 - INFO - codeparrot_training - Step 41314: {'lr': 3.932227715657119e-05, 'samples': 21153280, 'steps': 41314, 'loss/train': 1.5049607753753662} +02/26/2022 07:04:21 - INFO - codeparrot_training - Step 41315: {'lr': 3.931346860860666e-05, 'samples': 21153792, 'steps': 41315, 'loss/train': 2.0568690299987793} +02/26/2022 07:04:25 - INFO - codeparrot_training - Step 41316: {'lr': 3.930466096315624e-05, 'samples': 21154304, 'steps': 41316, 'loss/train': 3.55737042427063} +02/26/2022 07:04:30 - INFO - codeparrot_training - Step 41317: {'lr': 3.9295854220257886e-05, 'samples': 21154816, 'steps': 41317, 'loss/train': 2.4277520179748535} +02/26/2022 07:04:34 - INFO - codeparrot_training - Step 41318: {'lr': 3.928704837994909e-05, 'samples': 21155328, 'steps': 41318, 'loss/train': 1.5596942901611328} +02/26/2022 07:04:39 - INFO - codeparrot_training - Step 41319: {'lr': 3.927824344226771e-05, 'samples': 21155840, 'steps': 41319, 'loss/train': 2.4670939445495605} +02/26/2022 07:04:43 - INFO - codeparrot_training - Step 41320: {'lr': 3.926943940725136e-05, 'samples': 21156352, 'steps': 41320, 'loss/train': 1.4914158582687378} +02/26/2022 07:04:48 - INFO - codeparrot_training - Step 41321: {'lr': 3.926063627493795e-05, 'samples': 21156864, 'steps': 41321, 'loss/train': 1.478821039199829} +02/26/2022 07:04:52 - INFO - codeparrot_training - Step 41322: {'lr': 3.925183404536492e-05, 'samples': 21157376, 'steps': 41322, 'loss/train': 1.0644373893737793} +02/26/2022 07:04:57 - INFO - codeparrot_training - Step 41323: {'lr': 3.924303271857019e-05, 'samples': 21157888, 'steps': 41323, 'loss/train': 1.0851390361785889} +02/26/2022 07:05:01 - INFO - codeparrot_training - Step 41324: {'lr': 3.923423229459133e-05, 'samples': 21158400, 'steps': 41324, 'loss/train': 1.8833128213882446} +02/26/2022 07:05:06 - INFO - codeparrot_training - Step 41325: {'lr': 3.9225432773466184e-05, 'samples': 21158912, 'steps': 41325, 'loss/train': 1.6743628978729248} +02/26/2022 07:05:10 - INFO - codeparrot_training - Step 41326: {'lr': 3.921663415523227e-05, 'samples': 21159424, 'steps': 41326, 'loss/train': 1.2833172082901} +02/26/2022 07:05:16 - INFO - codeparrot_training - Step 41327: {'lr': 3.92078364399274e-05, 'samples': 21159936, 'steps': 41327, 'loss/train': 1.1480040550231934} +02/26/2022 07:05:19 - INFO - codeparrot_training - Step 41328: {'lr': 3.919903962758917e-05, 'samples': 21160448, 'steps': 41328, 'loss/train': 1.569909930229187} +02/26/2022 07:05:22 - INFO - codeparrot_training - Step 41329: {'lr': 3.9190243718255385e-05, 'samples': 21160960, 'steps': 41329, 'loss/train': 0.3647741377353668} +02/26/2022 07:05:30 - INFO - codeparrot_training - Step 41330: {'lr': 3.9181448711963666e-05, 'samples': 21161472, 'steps': 41330, 'loss/train': 1.9107706546783447} +02/26/2022 07:05:33 - INFO - codeparrot_training - Step 41331: {'lr': 3.9172654608751635e-05, 'samples': 21161984, 'steps': 41331, 'loss/train': 2.3226635456085205} +02/26/2022 07:05:39 - INFO - codeparrot_training - Step 41332: {'lr': 3.9163861408656994e-05, 'samples': 21162496, 'steps': 41332, 'loss/train': 2.380817174911499} +02/26/2022 07:05:42 - INFO - codeparrot_training - Step 41333: {'lr': 3.9155069111717455e-05, 'samples': 21163008, 'steps': 41333, 'loss/train': 1.2203632593154907} +02/26/2022 07:05:48 - INFO - codeparrot_training - Step 41334: {'lr': 3.9146277717970664e-05, 'samples': 21163520, 'steps': 41334, 'loss/train': 0.7109491229057312} +02/26/2022 07:05:53 - INFO - codeparrot_training - Step 41335: {'lr': 3.913748722745425e-05, 'samples': 21164032, 'steps': 41335, 'loss/train': 3.091419219970703} +02/26/2022 07:05:57 - INFO - codeparrot_training - Step 41336: {'lr': 3.912869764020583e-05, 'samples': 21164544, 'steps': 41336, 'loss/train': 1.5819402933120728} +02/26/2022 07:06:02 - INFO - codeparrot_training - Step 41337: {'lr': 3.911990895626319e-05, 'samples': 21165056, 'steps': 41337, 'loss/train': 1.4858388900756836} +02/26/2022 07:06:06 - INFO - codeparrot_training - Step 41338: {'lr': 3.911112117566387e-05, 'samples': 21165568, 'steps': 41338, 'loss/train': 1.230688214302063} +02/26/2022 07:06:13 - INFO - codeparrot_training - Step 41339: {'lr': 3.910233429844556e-05, 'samples': 21166080, 'steps': 41339, 'loss/train': 1.9165751934051514} +02/26/2022 07:06:16 - INFO - codeparrot_training - Step 41340: {'lr': 3.909354832464582e-05, 'samples': 21166592, 'steps': 41340, 'loss/train': 2.2020111083984375} +02/26/2022 07:06:22 - INFO - codeparrot_training - Step 41341: {'lr': 3.9084763254302406e-05, 'samples': 21167104, 'steps': 41341, 'loss/train': 2.00919771194458} +02/26/2022 07:06:25 - INFO - codeparrot_training - Step 41342: {'lr': 3.907597908745289e-05, 'samples': 21167616, 'steps': 41342, 'loss/train': 2.7273736000061035} +02/26/2022 07:06:31 - INFO - codeparrot_training - Step 41343: {'lr': 3.90671958241349e-05, 'samples': 21168128, 'steps': 41343, 'loss/train': 1.630610466003418} +02/26/2022 07:06:34 - INFO - codeparrot_training - Step 41344: {'lr': 3.905841346438602e-05, 'samples': 21168640, 'steps': 41344, 'loss/train': 1.4005275964736938} +02/26/2022 07:06:40 - INFO - codeparrot_training - Step 41345: {'lr': 3.904963200824396e-05, 'samples': 21169152, 'steps': 41345, 'loss/train': 1.5225865840911865} +02/26/2022 07:06:43 - INFO - codeparrot_training - Step 41346: {'lr': 3.904085145574629e-05, 'samples': 21169664, 'steps': 41346, 'loss/train': 1.817198634147644} +02/26/2022 07:06:49 - INFO - codeparrot_training - Step 41347: {'lr': 3.9032071806930636e-05, 'samples': 21170176, 'steps': 41347, 'loss/train': 2.483788251876831} +02/26/2022 07:06:52 - INFO - codeparrot_training - Step 41348: {'lr': 3.902329306183453e-05, 'samples': 21170688, 'steps': 41348, 'loss/train': 1.8209511041641235} +02/26/2022 07:06:59 - INFO - codeparrot_training - Step 41349: {'lr': 3.9014515220495705e-05, 'samples': 21171200, 'steps': 41349, 'loss/train': 2.0334019660949707} +02/26/2022 07:07:03 - INFO - codeparrot_training - Step 41350: {'lr': 3.9005738282951704e-05, 'samples': 21171712, 'steps': 41350, 'loss/train': 2.1247360706329346} +02/26/2022 07:07:08 - INFO - codeparrot_training - Step 41351: {'lr': 3.899696224924007e-05, 'samples': 21172224, 'steps': 41351, 'loss/train': 1.9253935813903809} +02/26/2022 07:07:12 - INFO - codeparrot_training - Step 41352: {'lr': 3.89881871193985e-05, 'samples': 21172736, 'steps': 41352, 'loss/train': 1.7527488470077515} +02/26/2022 07:07:17 - INFO - codeparrot_training - Step 41353: {'lr': 3.8979412893464516e-05, 'samples': 21173248, 'steps': 41353, 'loss/train': 1.6387213468551636} +02/26/2022 07:07:21 - INFO - codeparrot_training - Step 41354: {'lr': 3.897063957147573e-05, 'samples': 21173760, 'steps': 41354, 'loss/train': 1.3716071844100952} +02/26/2022 07:07:26 - INFO - codeparrot_training - Step 41355: {'lr': 3.8961867153469665e-05, 'samples': 21174272, 'steps': 41355, 'loss/train': 2.152237892150879} +02/26/2022 07:07:30 - INFO - codeparrot_training - Step 41356: {'lr': 3.895309563948407e-05, 'samples': 21174784, 'steps': 41356, 'loss/train': 0.7340816259384155} +02/26/2022 07:07:35 - INFO - codeparrot_training - Step 41357: {'lr': 3.8944325029556274e-05, 'samples': 21175296, 'steps': 41357, 'loss/train': 0.9668439030647278} +02/26/2022 07:07:39 - INFO - codeparrot_training - Step 41358: {'lr': 3.893555532372403e-05, 'samples': 21175808, 'steps': 41358, 'loss/train': 0.7590364813804626} +02/26/2022 07:07:44 - INFO - codeparrot_training - Step 41359: {'lr': 3.89267865220248e-05, 'samples': 21176320, 'steps': 41359, 'loss/train': 1.936675786972046} +02/26/2022 07:07:48 - INFO - codeparrot_training - Step 41360: {'lr': 3.891801862449629e-05, 'samples': 21176832, 'steps': 41360, 'loss/train': 1.2729203701019287} +02/26/2022 07:07:55 - INFO - codeparrot_training - Step 41361: {'lr': 3.890925163117587e-05, 'samples': 21177344, 'steps': 41361, 'loss/train': 1.1969263553619385} +02/26/2022 07:07:59 - INFO - codeparrot_training - Step 41362: {'lr': 3.890048554210121e-05, 'samples': 21177856, 'steps': 41362, 'loss/train': 2.4606263637542725} +02/26/2022 07:08:02 - INFO - codeparrot_training - Step 41363: {'lr': 3.889172035730981e-05, 'samples': 21178368, 'steps': 41363, 'loss/train': 1.202028512954712} +02/26/2022 07:08:08 - INFO - codeparrot_training - Step 41364: {'lr': 3.8882956076839285e-05, 'samples': 21178880, 'steps': 41364, 'loss/train': 1.791395664215088} +02/26/2022 07:08:11 - INFO - codeparrot_training - Step 41365: {'lr': 3.887419270072715e-05, 'samples': 21179392, 'steps': 41365, 'loss/train': 1.1219316720962524} +02/26/2022 07:08:17 - INFO - codeparrot_training - Step 41366: {'lr': 3.886543022901093e-05, 'samples': 21179904, 'steps': 41366, 'loss/train': 1.7659783363342285} +02/26/2022 07:08:20 - INFO - codeparrot_training - Step 41367: {'lr': 3.88566686617281e-05, 'samples': 21180416, 'steps': 41367, 'loss/train': 2.1345179080963135} +02/26/2022 07:08:26 - INFO - codeparrot_training - Step 41368: {'lr': 3.8847907998916326e-05, 'samples': 21180928, 'steps': 41368, 'loss/train': 1.6918641328811646} +02/26/2022 07:08:29 - INFO - codeparrot_training - Step 41369: {'lr': 3.8839148240613075e-05, 'samples': 21181440, 'steps': 41369, 'loss/train': 2.7087740898132324} +02/26/2022 07:08:34 - INFO - codeparrot_training - Step 41370: {'lr': 3.883038938685585e-05, 'samples': 21181952, 'steps': 41370, 'loss/train': 1.932759404182434} +02/26/2022 07:08:38 - INFO - codeparrot_training - Step 41371: {'lr': 3.882163143768211e-05, 'samples': 21182464, 'steps': 41371, 'loss/train': 1.4846620559692383} +02/26/2022 07:08:43 - INFO - codeparrot_training - Step 41372: {'lr': 3.8812874393129524e-05, 'samples': 21182976, 'steps': 41372, 'loss/train': 1.9349771738052368} +02/26/2022 07:08:47 - INFO - codeparrot_training - Step 41373: {'lr': 3.8804118253235515e-05, 'samples': 21183488, 'steps': 41373, 'loss/train': 1.2578426599502563} +02/26/2022 07:08:52 - INFO - codeparrot_training - Step 41374: {'lr': 3.87953630180376e-05, 'samples': 21184000, 'steps': 41374, 'loss/train': 2.2274463176727295} +02/26/2022 07:09:00 - INFO - codeparrot_training - Step 41375: {'lr': 3.878660868757322e-05, 'samples': 21184512, 'steps': 41375, 'loss/train': 1.3964370489120483} +02/26/2022 07:09:03 - INFO - codeparrot_training - Step 41376: {'lr': 3.877785526188002e-05, 'samples': 21185024, 'steps': 41376, 'loss/train': 1.1004981994628906} +02/26/2022 07:09:09 - INFO - codeparrot_training - Step 41377: {'lr': 3.8769102740995346e-05, 'samples': 21185536, 'steps': 41377, 'loss/train': 1.451279640197754} +02/26/2022 07:09:12 - INFO - codeparrot_training - Step 41378: {'lr': 3.876035112495688e-05, 'samples': 21186048, 'steps': 41378, 'loss/train': 2.0096492767333984} +02/26/2022 07:09:18 - INFO - codeparrot_training - Step 41379: {'lr': 3.8751600413801877e-05, 'samples': 21186560, 'steps': 41379, 'loss/train': 1.3239006996154785} +02/26/2022 07:09:21 - INFO - codeparrot_training - Step 41380: {'lr': 3.874285060756799e-05, 'samples': 21187072, 'steps': 41380, 'loss/train': 1.61467444896698} +02/26/2022 07:09:27 - INFO - codeparrot_training - Step 41381: {'lr': 3.8734101706292604e-05, 'samples': 21187584, 'steps': 41381, 'loss/train': 1.8403139114379883} +02/26/2022 07:09:30 - INFO - codeparrot_training - Step 41382: {'lr': 3.8725353710013345e-05, 'samples': 21188096, 'steps': 41382, 'loss/train': 1.2576487064361572} +02/26/2022 07:09:36 - INFO - codeparrot_training - Step 41383: {'lr': 3.871660661876747e-05, 'samples': 21188608, 'steps': 41383, 'loss/train': 2.07369327545166} +02/26/2022 07:09:39 - INFO - codeparrot_training - Step 41384: {'lr': 3.870786043259264e-05, 'samples': 21189120, 'steps': 41384, 'loss/train': 1.441272497177124} +02/26/2022 07:09:47 - INFO - codeparrot_training - Step 41385: {'lr': 3.869911515152616e-05, 'samples': 21189632, 'steps': 41385, 'loss/train': 1.5089815855026245} +02/26/2022 07:09:50 - INFO - codeparrot_training - Step 41386: {'lr': 3.869037077560569e-05, 'samples': 21190144, 'steps': 41386, 'loss/train': 2.227071762084961} +02/26/2022 07:09:56 - INFO - codeparrot_training - Step 41387: {'lr': 3.868162730486849e-05, 'samples': 21190656, 'steps': 41387, 'loss/train': 1.7476576566696167} +02/26/2022 07:09:59 - INFO - codeparrot_training - Step 41388: {'lr': 3.8672884739352125e-05, 'samples': 21191168, 'steps': 41388, 'loss/train': 0.731699526309967} +02/26/2022 07:10:04 - INFO - codeparrot_training - Step 41389: {'lr': 3.8664143079094025e-05, 'samples': 21191680, 'steps': 41389, 'loss/train': 1.8979896306991577} +02/26/2022 07:10:08 - INFO - codeparrot_training - Step 41390: {'lr': 3.865540232413156e-05, 'samples': 21192192, 'steps': 41390, 'loss/train': 1.416177749633789} +02/26/2022 07:10:14 - INFO - codeparrot_training - Step 41391: {'lr': 3.864666247450233e-05, 'samples': 21192704, 'steps': 41391, 'loss/train': 1.3912047147750854} +02/26/2022 07:10:17 - INFO - codeparrot_training - Step 41392: {'lr': 3.8637923530243676e-05, 'samples': 21193216, 'steps': 41392, 'loss/train': 0.915386974811554} +02/26/2022 07:10:23 - INFO - codeparrot_training - Step 41393: {'lr': 3.8629185491393024e-05, 'samples': 21193728, 'steps': 41393, 'loss/train': 1.6362178325653076} +02/26/2022 07:10:26 - INFO - codeparrot_training - Step 41394: {'lr': 3.862044835798778e-05, 'samples': 21194240, 'steps': 41394, 'loss/train': 1.5786510705947876} +02/26/2022 07:10:34 - INFO - codeparrot_training - Step 41395: {'lr': 3.8611712130065454e-05, 'samples': 21194752, 'steps': 41395, 'loss/train': 2.140014410018921} +02/26/2022 07:10:37 - INFO - codeparrot_training - Step 41396: {'lr': 3.860297680766345e-05, 'samples': 21195264, 'steps': 41396, 'loss/train': 0.8324285745620728} +02/26/2022 07:10:43 - INFO - codeparrot_training - Step 41397: {'lr': 3.859424239081916e-05, 'samples': 21195776, 'steps': 41397, 'loss/train': 0.053798526525497437} +02/26/2022 07:10:46 - INFO - codeparrot_training - Step 41398: {'lr': 3.858550887956996e-05, 'samples': 21196288, 'steps': 41398, 'loss/train': 1.1822596788406372} +02/26/2022 07:10:52 - INFO - codeparrot_training - Step 41399: {'lr': 3.8576776273953366e-05, 'samples': 21196800, 'steps': 41399, 'loss/train': 2.7903246879577637} +02/26/2022 07:10:55 - INFO - codeparrot_training - Step 41400: {'lr': 3.85680445740067e-05, 'samples': 21197312, 'steps': 41400, 'loss/train': 0.7123786211013794} +02/26/2022 07:11:01 - INFO - codeparrot_training - Step 41401: {'lr': 3.855931377976743e-05, 'samples': 21197824, 'steps': 41401, 'loss/train': 2.029703140258789} +02/26/2022 07:11:04 - INFO - codeparrot_training - Step 41402: {'lr': 3.855058389127283e-05, 'samples': 21198336, 'steps': 41402, 'loss/train': 1.6012340784072876} +02/26/2022 07:11:08 - INFO - codeparrot_training - Step 41403: {'lr': 3.8541854908560464e-05, 'samples': 21198848, 'steps': 41403, 'loss/train': 1.6181527376174927} +02/26/2022 07:11:13 - INFO - codeparrot_training - Step 41404: {'lr': 3.853312683166765e-05, 'samples': 21199360, 'steps': 41404, 'loss/train': 0.7273722887039185} +02/26/2022 07:11:17 - INFO - codeparrot_training - Step 41405: {'lr': 3.852439966063176e-05, 'samples': 21199872, 'steps': 41405, 'loss/train': 2.57423996925354} +02/26/2022 07:11:22 - INFO - codeparrot_training - Step 41406: {'lr': 3.851567339549014e-05, 'samples': 21200384, 'steps': 41406, 'loss/train': 1.1345417499542236} +02/26/2022 07:11:26 - INFO - codeparrot_training - Step 41407: {'lr': 3.850694803628027e-05, 'samples': 21200896, 'steps': 41407, 'loss/train': 1.637454867362976} +02/26/2022 07:11:33 - INFO - codeparrot_training - Step 41408: {'lr': 3.8498223583039476e-05, 'samples': 21201408, 'steps': 41408, 'loss/train': 1.715193271636963} +02/26/2022 07:11:37 - INFO - codeparrot_training - Step 41409: {'lr': 3.8489500035805145e-05, 'samples': 21201920, 'steps': 41409, 'loss/train': 1.8838248252868652} +02/26/2022 07:11:42 - INFO - codeparrot_training - Step 41410: {'lr': 3.848077739461459e-05, 'samples': 21202432, 'steps': 41410, 'loss/train': 2.3701303005218506} +02/26/2022 07:11:45 - INFO - codeparrot_training - Step 41411: {'lr': 3.847205565950524e-05, 'samples': 21202944, 'steps': 41411, 'loss/train': 1.4260499477386475} +02/26/2022 07:11:51 - INFO - codeparrot_training - Step 41412: {'lr': 3.8463334830514397e-05, 'samples': 21203456, 'steps': 41412, 'loss/train': 1.1480962038040161} +02/26/2022 07:11:57 - INFO - codeparrot_training - Step 41413: {'lr': 3.845461490767957e-05, 'samples': 21203968, 'steps': 41413, 'loss/train': 2.6985738277435303} +02/26/2022 07:12:00 - INFO - codeparrot_training - Step 41414: {'lr': 3.844589589103789e-05, 'samples': 21204480, 'steps': 41414, 'loss/train': 1.3860639333724976} +02/26/2022 07:12:06 - INFO - codeparrot_training - Step 41415: {'lr': 3.843717778062686e-05, 'samples': 21204992, 'steps': 41415, 'loss/train': 2.0419063568115234} +02/26/2022 07:12:09 - INFO - codeparrot_training - Step 41416: {'lr': 3.842846057648375e-05, 'samples': 21205504, 'steps': 41416, 'loss/train': 2.8303675651550293} +02/26/2022 07:12:15 - INFO - codeparrot_training - Step 41417: {'lr': 3.841974427864603e-05, 'samples': 21206016, 'steps': 41417, 'loss/train': 1.1914162635803223} +02/26/2022 07:12:18 - INFO - codeparrot_training - Step 41418: {'lr': 3.841102888715081e-05, 'samples': 21206528, 'steps': 41418, 'loss/train': 1.8867751359939575} +02/26/2022 07:12:24 - INFO - codeparrot_training - Step 41419: {'lr': 3.840231440203565e-05, 'samples': 21207040, 'steps': 41419, 'loss/train': 1.3146039247512817} +02/26/2022 07:12:27 - INFO - codeparrot_training - Step 41420: {'lr': 3.8393600823337707e-05, 'samples': 21207552, 'steps': 41420, 'loss/train': 2.1114535331726074} +02/26/2022 07:12:34 - INFO - codeparrot_training - Step 41421: {'lr': 3.83848881510945e-05, 'samples': 21208064, 'steps': 41421, 'loss/train': 2.3817951679229736} +02/26/2022 07:12:38 - INFO - codeparrot_training - Step 41422: {'lr': 3.837617638534313e-05, 'samples': 21208576, 'steps': 41422, 'loss/train': 2.4134585857391357} +02/26/2022 07:12:43 - INFO - codeparrot_training - Step 41423: {'lr': 3.8367465526121084e-05, 'samples': 21209088, 'steps': 41423, 'loss/train': 1.5053220987319946} +02/26/2022 07:12:47 - INFO - codeparrot_training - Step 41424: {'lr': 3.835875557346552e-05, 'samples': 21209600, 'steps': 41424, 'loss/train': 1.760952353477478} +02/26/2022 07:12:52 - INFO - codeparrot_training - Step 41425: {'lr': 3.8350046527413944e-05, 'samples': 21210112, 'steps': 41425, 'loss/train': 1.8469682931900024} +02/26/2022 07:12:56 - INFO - codeparrot_training - Step 41426: {'lr': 3.834133838800355e-05, 'samples': 21210624, 'steps': 41426, 'loss/train': 1.6918387413024902} +02/26/2022 07:13:01 - INFO - codeparrot_training - Step 41427: {'lr': 3.833263115527163e-05, 'samples': 21211136, 'steps': 41427, 'loss/train': 1.2684355974197388} +02/26/2022 07:13:05 - INFO - codeparrot_training - Step 41428: {'lr': 3.832392482925548e-05, 'samples': 21211648, 'steps': 41428, 'loss/train': 2.085402011871338} +02/26/2022 07:13:10 - INFO - codeparrot_training - Step 41429: {'lr': 3.831521940999247e-05, 'samples': 21212160, 'steps': 41429, 'loss/train': 2.738940477371216} +02/26/2022 07:13:14 - INFO - codeparrot_training - Step 41430: {'lr': 3.830651489751985e-05, 'samples': 21212672, 'steps': 41430, 'loss/train': 0.6943312883377075} +02/26/2022 07:13:19 - INFO - codeparrot_training - Step 41431: {'lr': 3.8297811291874876e-05, 'samples': 21213184, 'steps': 41431, 'loss/train': 0.8365955948829651} +02/26/2022 07:13:23 - INFO - codeparrot_training - Step 41432: {'lr': 3.8289108593094815e-05, 'samples': 21213696, 'steps': 41432, 'loss/train': 1.7320804595947266} +02/26/2022 07:13:30 - INFO - codeparrot_training - Step 41433: {'lr': 3.828040680121703e-05, 'samples': 21214208, 'steps': 41433, 'loss/train': 1.596526861190796} +02/26/2022 07:13:33 - INFO - codeparrot_training - Step 41434: {'lr': 3.827170591627877e-05, 'samples': 21214720, 'steps': 41434, 'loss/train': 1.6446852684020996} +02/26/2022 07:13:39 - INFO - codeparrot_training - Step 41435: {'lr': 3.8263005938317305e-05, 'samples': 21215232, 'steps': 41435, 'loss/train': 1.9777724742889404} +02/26/2022 07:13:42 - INFO - codeparrot_training - Step 41436: {'lr': 3.8254306867369856e-05, 'samples': 21215744, 'steps': 41436, 'loss/train': 2.7991063594818115} +02/26/2022 07:13:48 - INFO - codeparrot_training - Step 41437: {'lr': 3.8245608703473684e-05, 'samples': 21216256, 'steps': 41437, 'loss/train': 1.8059407472610474} +02/26/2022 07:13:51 - INFO - codeparrot_training - Step 41438: {'lr': 3.823691144666613e-05, 'samples': 21216768, 'steps': 41438, 'loss/train': 1.3553271293640137} +02/26/2022 07:13:57 - INFO - codeparrot_training - Step 41439: {'lr': 3.82282150969844e-05, 'samples': 21217280, 'steps': 41439, 'loss/train': 2.0456159114837646} +02/26/2022 07:14:00 - INFO - codeparrot_training - Step 41440: {'lr': 3.821951965446577e-05, 'samples': 21217792, 'steps': 41440, 'loss/train': 2.8711917400360107} +02/26/2022 07:14:06 - INFO - codeparrot_training - Step 41441: {'lr': 3.821082511914739e-05, 'samples': 21218304, 'steps': 41441, 'loss/train': 1.0734338760375977} +02/26/2022 07:14:09 - INFO - codeparrot_training - Step 41442: {'lr': 3.820213149106666e-05, 'samples': 21218816, 'steps': 41442, 'loss/train': 0.9205026626586914} +02/26/2022 07:14:16 - INFO - codeparrot_training - Step 41443: {'lr': 3.8193438770260744e-05, 'samples': 21219328, 'steps': 41443, 'loss/train': 2.3073084354400635} +02/26/2022 07:14:20 - INFO - codeparrot_training - Step 41444: {'lr': 3.818474695676685e-05, 'samples': 21219840, 'steps': 41444, 'loss/train': 1.3472200632095337} +02/26/2022 07:14:25 - INFO - codeparrot_training - Step 41445: {'lr': 3.8176056050622214e-05, 'samples': 21220352, 'steps': 41445, 'loss/train': 1.788814902305603} +02/26/2022 07:14:29 - INFO - codeparrot_training - Step 41446: {'lr': 3.816736605186416e-05, 'samples': 21220864, 'steps': 41446, 'loss/train': 2.5812249183654785} +02/26/2022 07:14:34 - INFO - codeparrot_training - Step 41447: {'lr': 3.8158676960529825e-05, 'samples': 21221376, 'steps': 41447, 'loss/train': 1.7620497941970825} +02/26/2022 07:14:38 - INFO - codeparrot_training - Step 41448: {'lr': 3.8149988776656455e-05, 'samples': 21221888, 'steps': 41448, 'loss/train': 0.7768648266792297} +02/26/2022 07:14:43 - INFO - codeparrot_training - Step 41449: {'lr': 3.8141301500281196e-05, 'samples': 21222400, 'steps': 41449, 'loss/train': 1.3608688116073608} +02/26/2022 07:14:47 - INFO - codeparrot_training - Step 41450: {'lr': 3.8132615131441396e-05, 'samples': 21222912, 'steps': 41450, 'loss/train': 1.1408246755599976} +02/26/2022 07:14:52 - INFO - codeparrot_training - Step 41451: {'lr': 3.812392967017414e-05, 'samples': 21223424, 'steps': 41451, 'loss/train': 1.055207371711731} +02/26/2022 07:14:56 - INFO - codeparrot_training - Step 41452: {'lr': 3.8115245116516816e-05, 'samples': 21223936, 'steps': 41452, 'loss/train': 2.232064962387085} +02/26/2022 07:15:02 - INFO - codeparrot_training - Step 41453: {'lr': 3.810656147050637e-05, 'samples': 21224448, 'steps': 41453, 'loss/train': 1.3543843030929565} +02/26/2022 07:15:06 - INFO - codeparrot_training - Step 41454: {'lr': 3.8097878732180206e-05, 'samples': 21224960, 'steps': 41454, 'loss/train': 1.2970480918884277} +02/26/2022 07:15:11 - INFO - codeparrot_training - Step 41455: {'lr': 3.808919690157536e-05, 'samples': 21225472, 'steps': 41455, 'loss/train': 0.9547430276870728} +02/26/2022 07:15:15 - INFO - codeparrot_training - Step 41456: {'lr': 3.808051597872925e-05, 'samples': 21225984, 'steps': 41456, 'loss/train': 0.621574342250824} +02/26/2022 07:15:20 - INFO - codeparrot_training - Step 41457: {'lr': 3.8071835963678775e-05, 'samples': 21226496, 'steps': 41457, 'loss/train': 1.4541332721710205} +02/26/2022 07:15:24 - INFO - codeparrot_training - Step 41458: {'lr': 3.806315685646134e-05, 'samples': 21227008, 'steps': 41458, 'loss/train': 1.678794264793396} +02/26/2022 07:15:29 - INFO - codeparrot_training - Step 41459: {'lr': 3.805447865711398e-05, 'samples': 21227520, 'steps': 41459, 'loss/train': 1.676421880722046} +02/26/2022 07:15:33 - INFO - codeparrot_training - Step 41460: {'lr': 3.804580136567398e-05, 'samples': 21228032, 'steps': 41460, 'loss/train': 1.8396148681640625} +02/26/2022 07:15:38 - INFO - codeparrot_training - Step 41461: {'lr': 3.803712498217846e-05, 'samples': 21228544, 'steps': 41461, 'loss/train': 2.3146557807922363} +02/26/2022 07:15:42 - INFO - codeparrot_training - Step 41462: {'lr': 3.802844950666462e-05, 'samples': 21229056, 'steps': 41462, 'loss/train': 1.413842797279358} +02/26/2022 07:15:47 - INFO - codeparrot_training - Step 41463: {'lr': 3.80197749391695e-05, 'samples': 21229568, 'steps': 41463, 'loss/train': 1.1379414796829224} +02/26/2022 07:15:51 - INFO - codeparrot_training - Step 41464: {'lr': 3.8011101279730424e-05, 'samples': 21230080, 'steps': 41464, 'loss/train': 2.032546281814575} +02/26/2022 07:15:56 - INFO - codeparrot_training - Step 41465: {'lr': 3.800242852838448e-05, 'samples': 21230592, 'steps': 41465, 'loss/train': 1.5792001485824585} +02/26/2022 07:15:59 - INFO - codeparrot_training - Step 41466: {'lr': 3.799375668516883e-05, 'samples': 21231104, 'steps': 41466, 'loss/train': 1.4508529901504517} +02/26/2022 07:16:05 - INFO - codeparrot_training - Step 41467: {'lr': 3.798508575012052e-05, 'samples': 21231616, 'steps': 41467, 'loss/train': 1.586324691772461} +02/26/2022 07:16:08 - INFO - codeparrot_training - Step 41468: {'lr': 3.797641572327687e-05, 'samples': 21232128, 'steps': 41468, 'loss/train': 2.8964133262634277} +02/26/2022 07:16:15 - INFO - codeparrot_training - Step 41469: {'lr': 3.796774660467489e-05, 'samples': 21232640, 'steps': 41469, 'loss/train': 1.8242436647415161} +02/26/2022 07:16:18 - INFO - codeparrot_training - Step 41470: {'lr': 3.795907839435178e-05, 'samples': 21233152, 'steps': 41470, 'loss/train': 2.016366958618164} +02/26/2022 07:16:24 - INFO - codeparrot_training - Step 41471: {'lr': 3.7950411092344594e-05, 'samples': 21233664, 'steps': 41471, 'loss/train': 1.2429040670394897} +02/26/2022 07:16:27 - INFO - codeparrot_training - Step 41472: {'lr': 3.794174469869058e-05, 'samples': 21234176, 'steps': 41472, 'loss/train': 2.246628522872925} +02/26/2022 07:16:33 - INFO - codeparrot_training - Step 41473: {'lr': 3.7933079213426756e-05, 'samples': 21234688, 'steps': 41473, 'loss/train': 0.5318734645843506} +02/26/2022 07:16:36 - INFO - codeparrot_training - Step 41474: {'lr': 3.7924414636590326e-05, 'samples': 21235200, 'steps': 41474, 'loss/train': 0.15288417041301727} +02/26/2022 07:16:42 - INFO - codeparrot_training - Step 41475: {'lr': 3.791575096821828e-05, 'samples': 21235712, 'steps': 41475, 'loss/train': 1.821983814239502} +02/26/2022 07:16:45 - INFO - codeparrot_training - Step 41476: {'lr': 3.7907088208347874e-05, 'samples': 21236224, 'steps': 41476, 'loss/train': 2.4748477935791016} +02/26/2022 07:16:52 - INFO - codeparrot_training - Step 41477: {'lr': 3.7898426357016155e-05, 'samples': 21236736, 'steps': 41477, 'loss/train': 1.8321831226348877} +02/26/2022 07:16:55 - INFO - codeparrot_training - Step 41478: {'lr': 3.788976541426023e-05, 'samples': 21237248, 'steps': 41478, 'loss/train': 2.3670949935913086} +02/26/2022 07:16:59 - INFO - codeparrot_training - Step 41479: {'lr': 3.7881105380117134e-05, 'samples': 21237760, 'steps': 41479, 'loss/train': 2.263601064682007} +02/26/2022 07:17:05 - INFO - codeparrot_training - Step 41480: {'lr': 3.787244625462411e-05, 'samples': 21238272, 'steps': 41480, 'loss/train': 2.211785078048706} +02/26/2022 07:17:08 - INFO - codeparrot_training - Step 41481: {'lr': 3.786378803781812e-05, 'samples': 21238784, 'steps': 41481, 'loss/train': 1.4981693029403687} +02/26/2022 07:17:14 - INFO - codeparrot_training - Step 41482: {'lr': 3.7855130729736345e-05, 'samples': 21239296, 'steps': 41482, 'loss/train': 2.750112771987915} +02/26/2022 07:17:17 - INFO - codeparrot_training - Step 41483: {'lr': 3.7846474330415796e-05, 'samples': 21239808, 'steps': 41483, 'loss/train': 0.07967755198478699} +02/26/2022 07:17:23 - INFO - codeparrot_training - Step 41484: {'lr': 3.783781883989354e-05, 'samples': 21240320, 'steps': 41484, 'loss/train': 1.5107117891311646} +02/26/2022 07:17:26 - INFO - codeparrot_training - Step 41485: {'lr': 3.782916425820676e-05, 'samples': 21240832, 'steps': 41485, 'loss/train': 1.8773701190948486} +02/26/2022 07:17:32 - INFO - codeparrot_training - Step 41486: {'lr': 3.78205105853924e-05, 'samples': 21241344, 'steps': 41486, 'loss/train': 2.269402503967285} +02/26/2022 07:17:35 - INFO - codeparrot_training - Step 41487: {'lr': 3.781185782148775e-05, 'samples': 21241856, 'steps': 41487, 'loss/train': 1.4000815153121948} +02/26/2022 07:17:41 - INFO - codeparrot_training - Step 41488: {'lr': 3.7803205966529555e-05, 'samples': 21242368, 'steps': 41488, 'loss/train': 1.6193434000015259} +02/26/2022 07:17:44 - INFO - codeparrot_training - Step 41489: {'lr': 3.779455502055515e-05, 'samples': 21242880, 'steps': 41489, 'loss/train': 1.8121392726898193} +02/26/2022 07:17:51 - INFO - codeparrot_training - Step 41490: {'lr': 3.77859049836014e-05, 'samples': 21243392, 'steps': 41490, 'loss/train': 0.7978044152259827} +02/26/2022 07:17:54 - INFO - codeparrot_training - Step 41491: {'lr': 3.7777255855705574e-05, 'samples': 21243904, 'steps': 41491, 'loss/train': 2.133714437484741} +02/26/2022 07:18:00 - INFO - codeparrot_training - Step 41492: {'lr': 3.7768607636904485e-05, 'samples': 21244416, 'steps': 41492, 'loss/train': 2.0368926525115967} +02/26/2022 07:18:03 - INFO - codeparrot_training - Step 41493: {'lr': 3.775996032723533e-05, 'samples': 21244928, 'steps': 41493, 'loss/train': 1.4956350326538086} +02/26/2022 07:18:09 - INFO - codeparrot_training - Step 41494: {'lr': 3.775131392673506e-05, 'samples': 21245440, 'steps': 41494, 'loss/train': 1.3492099046707153} +02/26/2022 07:18:12 - INFO - codeparrot_training - Step 41495: {'lr': 3.774266843544089e-05, 'samples': 21245952, 'steps': 41495, 'loss/train': 2.071652412414551} +02/26/2022 07:18:18 - INFO - codeparrot_training - Step 41496: {'lr': 3.7734023853389616e-05, 'samples': 21246464, 'steps': 41496, 'loss/train': 2.0169267654418945} +02/26/2022 07:18:21 - INFO - codeparrot_training - Step 41497: {'lr': 3.7725380180618414e-05, 'samples': 21246976, 'steps': 41497, 'loss/train': 2.1661300659179688} +02/26/2022 07:18:27 - INFO - codeparrot_training - Step 41498: {'lr': 3.771673741716425e-05, 'samples': 21247488, 'steps': 41498, 'loss/train': 1.2068510055541992} +02/26/2022 07:18:30 - INFO - codeparrot_training - Step 41499: {'lr': 3.77080955630642e-05, 'samples': 21248000, 'steps': 41499, 'loss/train': 0.5352388024330139} +02/26/2022 07:18:36 - INFO - codeparrot_training - Step 41500: {'lr': 3.76994546183553e-05, 'samples': 21248512, 'steps': 41500, 'loss/train': 1.529056191444397} +02/26/2022 07:18:39 - INFO - codeparrot_training - Step 41501: {'lr': 3.7690814583074496e-05, 'samples': 21249024, 'steps': 41501, 'loss/train': 1.5785040855407715} +02/26/2022 07:18:45 - INFO - codeparrot_training - Step 41502: {'lr': 3.768217545725877e-05, 'samples': 21249536, 'steps': 41502, 'loss/train': 2.4972565174102783} +02/26/2022 07:18:49 - INFO - codeparrot_training - Step 41503: {'lr': 3.767353724094527e-05, 'samples': 21250048, 'steps': 41503, 'loss/train': 2.246795654296875} +02/26/2022 07:18:54 - INFO - codeparrot_training - Step 41504: {'lr': 3.766489993417088e-05, 'samples': 21250560, 'steps': 41504, 'loss/train': 1.4457815885543823} +02/26/2022 07:18:58 - INFO - codeparrot_training - Step 41505: {'lr': 3.765626353697266e-05, 'samples': 21251072, 'steps': 41505, 'loss/train': 0.6029650568962097} +02/26/2022 07:19:03 - INFO - codeparrot_training - Step 41506: {'lr': 3.764762804938751e-05, 'samples': 21251584, 'steps': 41506, 'loss/train': 1.3602945804595947} +02/26/2022 07:19:07 - INFO - codeparrot_training - Step 41507: {'lr': 3.763899347145255e-05, 'samples': 21252096, 'steps': 41507, 'loss/train': 1.9018856287002563} +02/26/2022 07:19:12 - INFO - codeparrot_training - Step 41508: {'lr': 3.76303598032047e-05, 'samples': 21252608, 'steps': 41508, 'loss/train': 0.3855888545513153} +02/26/2022 07:19:16 - INFO - codeparrot_training - Step 41509: {'lr': 3.7621727044680974e-05, 'samples': 21253120, 'steps': 41509, 'loss/train': 2.094248056411743} +02/26/2022 07:19:21 - INFO - codeparrot_training - Step 41510: {'lr': 3.761309519591827e-05, 'samples': 21253632, 'steps': 41510, 'loss/train': 1.4153131246566772} +02/26/2022 07:19:25 - INFO - codeparrot_training - Step 41511: {'lr': 3.760446425695368e-05, 'samples': 21254144, 'steps': 41511, 'loss/train': 1.2816791534423828} +02/26/2022 07:19:30 - INFO - codeparrot_training - Step 41512: {'lr': 3.759583422782406e-05, 'samples': 21254656, 'steps': 41512, 'loss/train': 0.9876706600189209} +02/26/2022 07:19:34 - INFO - codeparrot_training - Step 41513: {'lr': 3.7587205108566556e-05, 'samples': 21255168, 'steps': 41513, 'loss/train': 0.522168755531311} +02/26/2022 07:19:39 - INFO - codeparrot_training - Step 41514: {'lr': 3.7578576899217896e-05, 'samples': 21255680, 'steps': 41514, 'loss/train': 1.8396189212799072} +02/26/2022 07:19:43 - INFO - codeparrot_training - Step 41515: {'lr': 3.756994959981524e-05, 'samples': 21256192, 'steps': 41515, 'loss/train': 0.3136066198348999} +02/26/2022 07:19:49 - INFO - codeparrot_training - Step 41516: {'lr': 3.7561323210395434e-05, 'samples': 21256704, 'steps': 41516, 'loss/train': 2.4214723110198975} +02/26/2022 07:19:52 - INFO - codeparrot_training - Step 41517: {'lr': 3.755269773099548e-05, 'samples': 21257216, 'steps': 41517, 'loss/train': 2.0351264476776123} +02/26/2022 07:19:58 - INFO - codeparrot_training - Step 41518: {'lr': 3.754407316165226e-05, 'samples': 21257728, 'steps': 41518, 'loss/train': 1.9207797050476074} +02/26/2022 07:20:01 - INFO - codeparrot_training - Step 41519: {'lr': 3.7535449502402814e-05, 'samples': 21258240, 'steps': 41519, 'loss/train': 1.4459257125854492} +02/26/2022 07:20:07 - INFO - codeparrot_training - Step 41520: {'lr': 3.752682675328406e-05, 'samples': 21258752, 'steps': 41520, 'loss/train': 1.9852283000946045} +02/26/2022 07:20:10 - INFO - codeparrot_training - Step 41521: {'lr': 3.751820491433283e-05, 'samples': 21259264, 'steps': 41521, 'loss/train': 1.5598645210266113} +02/26/2022 07:20:16 - INFO - codeparrot_training - Step 41522: {'lr': 3.750958398558621e-05, 'samples': 21259776, 'steps': 41522, 'loss/train': 1.1238679885864258} +02/26/2022 07:20:19 - INFO - codeparrot_training - Step 41523: {'lr': 3.7500963967081054e-05, 'samples': 21260288, 'steps': 41523, 'loss/train': 2.8799936771392822} +02/26/2022 07:20:25 - INFO - codeparrot_training - Step 41524: {'lr': 3.7492344858854275e-05, 'samples': 21260800, 'steps': 41524, 'loss/train': 1.6685857772827148} +02/26/2022 07:20:28 - INFO - codeparrot_training - Step 41525: {'lr': 3.748372666094277e-05, 'samples': 21261312, 'steps': 41525, 'loss/train': 1.3893134593963623} +02/26/2022 07:20:35 - INFO - codeparrot_training - Step 41526: {'lr': 3.7475109373383556e-05, 'samples': 21261824, 'steps': 41526, 'loss/train': 1.341504454612732} +02/26/2022 07:20:40 - INFO - codeparrot_training - Step 41527: {'lr': 3.746649299621349e-05, 'samples': 21262336, 'steps': 41527, 'loss/train': 1.371767520904541} +02/26/2022 07:20:44 - INFO - codeparrot_training - Step 41528: {'lr': 3.745787752946947e-05, 'samples': 21262848, 'steps': 41528, 'loss/train': 1.3130661249160767} +02/26/2022 07:20:49 - INFO - codeparrot_training - Step 41529: {'lr': 3.744926297318838e-05, 'samples': 21263360, 'steps': 41529, 'loss/train': 2.644075870513916} +02/26/2022 07:20:53 - INFO - codeparrot_training - Step 41530: {'lr': 3.7440649327407205e-05, 'samples': 21263872, 'steps': 41530, 'loss/train': 1.7530325651168823} +02/26/2022 07:20:58 - INFO - codeparrot_training - Step 41531: {'lr': 3.743203659216277e-05, 'samples': 21264384, 'steps': 41531, 'loss/train': 1.6723353862762451} +02/26/2022 07:21:02 - INFO - codeparrot_training - Step 41532: {'lr': 3.7423424767492024e-05, 'samples': 21264896, 'steps': 41532, 'loss/train': 1.9476895332336426} +02/26/2022 07:21:07 - INFO - codeparrot_training - Step 41533: {'lr': 3.7414813853431734e-05, 'samples': 21265408, 'steps': 41533, 'loss/train': 1.081854224205017} +02/26/2022 07:21:11 - INFO - codeparrot_training - Step 41534: {'lr': 3.740620385001897e-05, 'samples': 21265920, 'steps': 41534, 'loss/train': 0.943854808807373} +02/26/2022 07:21:17 - INFO - codeparrot_training - Step 41535: {'lr': 3.739759475729049e-05, 'samples': 21266432, 'steps': 41535, 'loss/train': 2.0230562686920166} +02/26/2022 07:21:20 - INFO - codeparrot_training - Step 41536: {'lr': 3.738898657528322e-05, 'samples': 21266944, 'steps': 41536, 'loss/train': 1.4306625127792358} +02/26/2022 07:21:26 - INFO - codeparrot_training - Step 41537: {'lr': 3.738037930403399e-05, 'samples': 21267456, 'steps': 41537, 'loss/train': 0.8857371807098389} +02/26/2022 07:21:29 - INFO - codeparrot_training - Step 41538: {'lr': 3.737177294357971e-05, 'samples': 21267968, 'steps': 41538, 'loss/train': 1.7231508493423462} +02/26/2022 07:21:35 - INFO - codeparrot_training - Step 41539: {'lr': 3.736316749395727e-05, 'samples': 21268480, 'steps': 41539, 'loss/train': 1.501214623451233} +02/26/2022 07:21:38 - INFO - codeparrot_training - Step 41540: {'lr': 3.735456295520348e-05, 'samples': 21268992, 'steps': 41540, 'loss/train': 1.1314055919647217} +02/26/2022 07:21:44 - INFO - codeparrot_training - Step 41541: {'lr': 3.734595932735518e-05, 'samples': 21269504, 'steps': 41541, 'loss/train': 2.9809787273406982} +02/26/2022 07:21:47 - INFO - codeparrot_training - Step 41542: {'lr': 3.733735661044932e-05, 'samples': 21270016, 'steps': 41542, 'loss/train': 0.18138311803340912} +02/26/2022 07:21:53 - INFO - codeparrot_training - Step 41543: {'lr': 3.732875480452269e-05, 'samples': 21270528, 'steps': 41543, 'loss/train': 2.3136279582977295} +02/26/2022 07:21:56 - INFO - codeparrot_training - Step 41544: {'lr': 3.732015390961213e-05, 'samples': 21271040, 'steps': 41544, 'loss/train': 2.3509738445281982} +02/26/2022 07:22:02 - INFO - codeparrot_training - Step 41545: {'lr': 3.731155392575447e-05, 'samples': 21271552, 'steps': 41545, 'loss/train': 0.1376008242368698} +02/26/2022 07:22:05 - INFO - codeparrot_training - Step 41546: {'lr': 3.7302954852986626e-05, 'samples': 21272064, 'steps': 41546, 'loss/train': 2.445629358291626} +02/26/2022 07:22:11 - INFO - codeparrot_training - Step 41547: {'lr': 3.7294356691345316e-05, 'samples': 21272576, 'steps': 41547, 'loss/train': 1.8725117444992065} +02/26/2022 07:22:14 - INFO - codeparrot_training - Step 41548: {'lr': 3.728575944086757e-05, 'samples': 21273088, 'steps': 41548, 'loss/train': 0.10358990728855133} +02/26/2022 07:22:20 - INFO - codeparrot_training - Step 41549: {'lr': 3.7277163101589935e-05, 'samples': 21273600, 'steps': 41549, 'loss/train': 1.79083251953125} +02/26/2022 07:22:23 - INFO - codeparrot_training - Step 41550: {'lr': 3.726856767354947e-05, 'samples': 21274112, 'steps': 41550, 'loss/train': 1.5838149785995483} +02/26/2022 07:22:30 - INFO - codeparrot_training - Step 41551: {'lr': 3.725997315678287e-05, 'samples': 21274624, 'steps': 41551, 'loss/train': 0.5059872269630432} +02/26/2022 07:22:33 - INFO - codeparrot_training - Step 41552: {'lr': 3.725137955132707e-05, 'samples': 21275136, 'steps': 41552, 'loss/train': 1.694729208946228} +02/26/2022 07:22:39 - INFO - codeparrot_training - Step 41553: {'lr': 3.724278685721871e-05, 'samples': 21275648, 'steps': 41553, 'loss/train': 2.1793203353881836} +02/26/2022 07:22:42 - INFO - codeparrot_training - Step 41554: {'lr': 3.723419507449477e-05, 'samples': 21276160, 'steps': 41554, 'loss/train': 2.447911262512207} +02/26/2022 07:22:48 - INFO - codeparrot_training - Step 41555: {'lr': 3.7225604203191904e-05, 'samples': 21276672, 'steps': 41555, 'loss/train': 2.4053971767425537} +02/26/2022 07:22:51 - INFO - codeparrot_training - Step 41556: {'lr': 3.721701424334709e-05, 'samples': 21277184, 'steps': 41556, 'loss/train': 1.8048169612884521} +02/26/2022 07:22:57 - INFO - codeparrot_training - Step 41557: {'lr': 3.720842519499693e-05, 'samples': 21277696, 'steps': 41557, 'loss/train': 1.8096309900283813} +02/26/2022 07:23:00 - INFO - codeparrot_training - Step 41558: {'lr': 3.719983705817834e-05, 'samples': 21278208, 'steps': 41558, 'loss/train': 1.048996090888977} +02/26/2022 07:23:06 - INFO - codeparrot_training - Step 41559: {'lr': 3.719124983292802e-05, 'samples': 21278720, 'steps': 41559, 'loss/train': 0.7377447485923767} +02/26/2022 07:23:09 - INFO - codeparrot_training - Step 41560: {'lr': 3.718266351928287e-05, 'samples': 21279232, 'steps': 41560, 'loss/train': 1.9465328454971313} +02/26/2022 07:23:15 - INFO - codeparrot_training - Step 41561: {'lr': 3.717407811727963e-05, 'samples': 21279744, 'steps': 41561, 'loss/train': 2.427617073059082} +02/26/2022 07:23:19 - INFO - codeparrot_training - Step 41562: {'lr': 3.716549362695504e-05, 'samples': 21280256, 'steps': 41562, 'loss/train': 1.2041329145431519} +02/26/2022 07:23:24 - INFO - codeparrot_training - Step 41563: {'lr': 3.7156910048345846e-05, 'samples': 21280768, 'steps': 41563, 'loss/train': 1.2262251377105713} +02/26/2022 07:23:28 - INFO - codeparrot_training - Step 41564: {'lr': 3.7148327381488906e-05, 'samples': 21281280, 'steps': 41564, 'loss/train': 1.2153651714324951} +02/26/2022 07:23:33 - INFO - codeparrot_training - Step 41565: {'lr': 3.7139745626420976e-05, 'samples': 21281792, 'steps': 41565, 'loss/train': 1.364759922027588} +02/26/2022 07:23:37 - INFO - codeparrot_training - Step 41566: {'lr': 3.713116478317877e-05, 'samples': 21282304, 'steps': 41566, 'loss/train': 1.4748543500900269} +02/26/2022 07:23:42 - INFO - codeparrot_training - Step 41567: {'lr': 3.712258485179904e-05, 'samples': 21282816, 'steps': 41567, 'loss/train': 1.450737714767456} +02/26/2022 07:23:46 - INFO - codeparrot_training - Step 41568: {'lr': 3.7114005832318526e-05, 'samples': 21283328, 'steps': 41568, 'loss/train': 1.6766945123672485} +02/26/2022 07:23:51 - INFO - codeparrot_training - Step 41569: {'lr': 3.7105427724774074e-05, 'samples': 21283840, 'steps': 41569, 'loss/train': 0.7602059245109558} +02/26/2022 07:23:55 - INFO - codeparrot_training - Step 41570: {'lr': 3.709685052920234e-05, 'samples': 21284352, 'steps': 41570, 'loss/train': 1.4825658798217773} +02/26/2022 07:24:01 - INFO - codeparrot_training - Step 41571: {'lr': 3.708827424564012e-05, 'samples': 21284864, 'steps': 41571, 'loss/train': 0.09666864573955536} +02/26/2022 07:24:04 - INFO - codeparrot_training - Step 41572: {'lr': 3.707969887412405e-05, 'samples': 21285376, 'steps': 41572, 'loss/train': 2.673663854598999} +02/26/2022 07:24:10 - INFO - codeparrot_training - Step 41573: {'lr': 3.707112441469102e-05, 'samples': 21285888, 'steps': 41573, 'loss/train': 2.849592447280884} +02/26/2022 07:24:15 - INFO - codeparrot_training - Step 41574: {'lr': 3.706255086737767e-05, 'samples': 21286400, 'steps': 41574, 'loss/train': 2.052672863006592} +02/26/2022 07:24:19 - INFO - codeparrot_training - Step 41575: {'lr': 3.705397823222073e-05, 'samples': 21286912, 'steps': 41575, 'loss/train': 1.2658662796020508} +02/26/2022 07:24:25 - INFO - codeparrot_training - Step 41576: {'lr': 3.704540650925686e-05, 'samples': 21287424, 'steps': 41576, 'loss/train': 2.061177968978882} +02/26/2022 07:24:28 - INFO - codeparrot_training - Step 41577: {'lr': 3.7036835698522925e-05, 'samples': 21287936, 'steps': 41577, 'loss/train': 1.895163893699646} +02/26/2022 07:24:31 - INFO - codeparrot_training - Step 41578: {'lr': 3.7028265800055555e-05, 'samples': 21288448, 'steps': 41578, 'loss/train': 2.684748411178589} +02/26/2022 07:24:37 - INFO - codeparrot_training - Step 41579: {'lr': 3.701969681389147e-05, 'samples': 21288960, 'steps': 41579, 'loss/train': 0.38307473063468933} +02/26/2022 07:24:40 - INFO - codeparrot_training - Step 41580: {'lr': 3.7011128740067315e-05, 'samples': 21289472, 'steps': 41580, 'loss/train': 1.5973625183105469} +02/26/2022 07:24:46 - INFO - codeparrot_training - Step 41581: {'lr': 3.700256157861992e-05, 'samples': 21289984, 'steps': 41581, 'loss/train': 0.266282856464386} +02/26/2022 07:24:52 - INFO - codeparrot_training - Step 41582: {'lr': 3.6993995329585864e-05, 'samples': 21290496, 'steps': 41582, 'loss/train': 1.240788221359253} +02/26/2022 07:24:56 - INFO - codeparrot_training - Step 41583: {'lr': 3.6985429993002e-05, 'samples': 21291008, 'steps': 41583, 'loss/train': 2.1780056953430176} +02/26/2022 07:24:59 - INFO - codeparrot_training - Step 41584: {'lr': 3.697686556890481e-05, 'samples': 21291520, 'steps': 41584, 'loss/train': 2.1679952144622803} +02/26/2022 07:25:05 - INFO - codeparrot_training - Step 41585: {'lr': 3.696830205733112e-05, 'samples': 21292032, 'steps': 41585, 'loss/train': 1.212868332862854} +02/26/2022 07:25:10 - INFO - codeparrot_training - Step 41586: {'lr': 3.6959739458317545e-05, 'samples': 21292544, 'steps': 41586, 'loss/train': 2.5805232524871826} +02/26/2022 07:25:14 - INFO - codeparrot_training - Step 41587: {'lr': 3.695117777190088e-05, 'samples': 21293056, 'steps': 41587, 'loss/train': 1.4765158891677856} +02/26/2022 07:25:19 - INFO - codeparrot_training - Step 41588: {'lr': 3.694261699811763e-05, 'samples': 21293568, 'steps': 41588, 'loss/train': 1.8507057428359985} +02/26/2022 07:25:23 - INFO - codeparrot_training - Step 41589: {'lr': 3.693405713700462e-05, 'samples': 21294080, 'steps': 41589, 'loss/train': 1.4172418117523193} +02/26/2022 07:25:28 - INFO - codeparrot_training - Step 41590: {'lr': 3.692549818859839e-05, 'samples': 21294592, 'steps': 41590, 'loss/train': 1.536205768585205} +02/26/2022 07:25:32 - INFO - codeparrot_training - Step 41591: {'lr': 3.691694015293576e-05, 'samples': 21295104, 'steps': 41591, 'loss/train': 0.9635187387466431} +02/26/2022 07:25:38 - INFO - codeparrot_training - Step 41592: {'lr': 3.69083830300532e-05, 'samples': 21295616, 'steps': 41592, 'loss/train': 1.1006048917770386} +02/26/2022 07:25:41 - INFO - codeparrot_training - Step 41593: {'lr': 3.689982681998752e-05, 'samples': 21296128, 'steps': 41593, 'loss/train': 0.6185737252235413} +02/26/2022 07:25:47 - INFO - codeparrot_training - Step 41594: {'lr': 3.689127152277524e-05, 'samples': 21296640, 'steps': 41594, 'loss/train': 1.6980297565460205} +02/26/2022 07:25:50 - INFO - codeparrot_training - Step 41595: {'lr': 3.688271713845318e-05, 'samples': 21297152, 'steps': 41595, 'loss/train': 0.10553835332393646} +02/26/2022 07:25:56 - INFO - codeparrot_training - Step 41596: {'lr': 3.687416366705787e-05, 'samples': 21297664, 'steps': 41596, 'loss/train': 1.4553296566009521} +02/26/2022 07:25:59 - INFO - codeparrot_training - Step 41597: {'lr': 3.686561110862596e-05, 'samples': 21298176, 'steps': 41597, 'loss/train': 1.349586844444275} +02/26/2022 07:26:05 - INFO - codeparrot_training - Step 41598: {'lr': 3.6857059463194036e-05, 'samples': 21298688, 'steps': 41598, 'loss/train': 1.4395700693130493} +02/26/2022 07:26:08 - INFO - codeparrot_training - Step 41599: {'lr': 3.6848508730798844e-05, 'samples': 21299200, 'steps': 41599, 'loss/train': 1.942911148071289} +02/26/2022 07:26:14 - INFO - codeparrot_training - Step 41600: {'lr': 3.6839958911476953e-05, 'samples': 21299712, 'steps': 41600, 'loss/train': 1.5435937643051147} +02/26/2022 07:26:17 - INFO - codeparrot_training - Step 41601: {'lr': 3.683141000526502e-05, 'samples': 21300224, 'steps': 41601, 'loss/train': 1.9384915828704834} +02/26/2022 07:26:23 - INFO - codeparrot_training - Step 41602: {'lr': 3.682286201219956e-05, 'samples': 21300736, 'steps': 41602, 'loss/train': 1.2798683643341064} +02/26/2022 07:26:26 - INFO - codeparrot_training - Step 41603: {'lr': 3.681431493231732e-05, 'samples': 21301248, 'steps': 41603, 'loss/train': 1.2349262237548828} +02/26/2022 07:26:32 - INFO - codeparrot_training - Step 41604: {'lr': 3.6805768765654865e-05, 'samples': 21301760, 'steps': 41604, 'loss/train': 1.3032633066177368} +02/26/2022 07:26:35 - INFO - codeparrot_training - Step 41605: {'lr': 3.679722351224879e-05, 'samples': 21302272, 'steps': 41605, 'loss/train': 0.6310141086578369} +02/26/2022 07:26:41 - INFO - codeparrot_training - Step 41606: {'lr': 3.678867917213569e-05, 'samples': 21302784, 'steps': 41606, 'loss/train': 1.987351894378662} +02/26/2022 07:26:44 - INFO - codeparrot_training - Step 41607: {'lr': 3.678013574535222e-05, 'samples': 21303296, 'steps': 41607, 'loss/train': 3.2760982513427734} +02/26/2022 07:26:50 - INFO - codeparrot_training - Step 41608: {'lr': 3.6771593231934934e-05, 'samples': 21303808, 'steps': 41608, 'loss/train': 1.3467310667037964} +02/26/2022 07:26:54 - INFO - codeparrot_training - Step 41609: {'lr': 3.6763051631920426e-05, 'samples': 21304320, 'steps': 41609, 'loss/train': 0.9354490041732788} +02/26/2022 07:26:59 - INFO - codeparrot_training - Step 41610: {'lr': 3.6754510945345265e-05, 'samples': 21304832, 'steps': 41610, 'loss/train': 1.13763427734375} +02/26/2022 07:27:03 - INFO - codeparrot_training - Step 41611: {'lr': 3.6745971172246126e-05, 'samples': 21305344, 'steps': 41611, 'loss/train': 1.8417457342147827} +02/26/2022 07:27:08 - INFO - codeparrot_training - Step 41612: {'lr': 3.67374323126595e-05, 'samples': 21305856, 'steps': 41612, 'loss/train': 2.6171836853027344} +02/26/2022 07:27:12 - INFO - codeparrot_training - Step 41613: {'lr': 3.6728894366622026e-05, 'samples': 21306368, 'steps': 41613, 'loss/train': 1.8170359134674072} +02/26/2022 07:27:18 - INFO - codeparrot_training - Step 41614: {'lr': 3.672035733417023e-05, 'samples': 21306880, 'steps': 41614, 'loss/train': 0.8051912188529968} +02/26/2022 07:27:21 - INFO - codeparrot_training - Step 41615: {'lr': 3.671182121534064e-05, 'samples': 21307392, 'steps': 41615, 'loss/train': 2.0435030460357666} +02/26/2022 07:27:27 - INFO - codeparrot_training - Step 41616: {'lr': 3.670328601016995e-05, 'samples': 21307904, 'steps': 41616, 'loss/train': 1.3559987545013428} +02/26/2022 07:27:30 - INFO - codeparrot_training - Step 41617: {'lr': 3.669475171869457e-05, 'samples': 21308416, 'steps': 41617, 'loss/train': 1.9512840509414673} +02/26/2022 07:27:36 - INFO - codeparrot_training - Step 41618: {'lr': 3.668621834095129e-05, 'samples': 21308928, 'steps': 41618, 'loss/train': 1.828302025794983} +02/26/2022 07:27:40 - INFO - codeparrot_training - Step 41619: {'lr': 3.66776858769764e-05, 'samples': 21309440, 'steps': 41619, 'loss/train': 2.477667808532715} +02/26/2022 07:27:45 - INFO - codeparrot_training - Step 41620: {'lr': 3.6669154326806594e-05, 'samples': 21309952, 'steps': 41620, 'loss/train': 0.9591473937034607} +02/26/2022 07:27:49 - INFO - codeparrot_training - Step 41621: {'lr': 3.6660623690478344e-05, 'samples': 21310464, 'steps': 41621, 'loss/train': 1.0352134704589844} +02/26/2022 07:27:54 - INFO - codeparrot_training - Step 41622: {'lr': 3.665209396802838e-05, 'samples': 21310976, 'steps': 41622, 'loss/train': 2.271552324295044} +02/26/2022 07:27:58 - INFO - codeparrot_training - Step 41623: {'lr': 3.6643565159492963e-05, 'samples': 21311488, 'steps': 41623, 'loss/train': 1.494215965270996} +02/26/2022 07:28:03 - INFO - codeparrot_training - Step 41624: {'lr': 3.663503726490883e-05, 'samples': 21312000, 'steps': 41624, 'loss/train': 1.996005892753601} +02/26/2022 07:28:07 - INFO - codeparrot_training - Step 41625: {'lr': 3.662651028431238e-05, 'samples': 21312512, 'steps': 41625, 'loss/train': 1.11830472946167} +02/26/2022 07:28:12 - INFO - codeparrot_training - Step 41626: {'lr': 3.661798421774032e-05, 'samples': 21313024, 'steps': 41626, 'loss/train': 2.4957258701324463} +02/26/2022 07:28:16 - INFO - codeparrot_training - Step 41627: {'lr': 3.660945906522895e-05, 'samples': 21313536, 'steps': 41627, 'loss/train': 0.8284900784492493} +02/26/2022 07:28:22 - INFO - codeparrot_training - Step 41628: {'lr': 3.660093482681495e-05, 'samples': 21314048, 'steps': 41628, 'loss/train': 1.233595371246338} +02/26/2022 07:28:25 - INFO - codeparrot_training - Step 41629: {'lr': 3.659241150253473e-05, 'samples': 21314560, 'steps': 41629, 'loss/train': 1.0313550233840942} +02/26/2022 07:28:31 - INFO - codeparrot_training - Step 41630: {'lr': 3.658388909242491e-05, 'samples': 21315072, 'steps': 41630, 'loss/train': 2.564741849899292} +02/26/2022 07:28:34 - INFO - codeparrot_training - Step 41631: {'lr': 3.657536759652194e-05, 'samples': 21315584, 'steps': 41631, 'loss/train': 1.961073398590088} +02/26/2022 07:28:40 - INFO - codeparrot_training - Step 41632: {'lr': 3.656684701486235e-05, 'samples': 21316096, 'steps': 41632, 'loss/train': 2.1633036136627197} +02/26/2022 07:28:43 - INFO - codeparrot_training - Step 41633: {'lr': 3.655832734748252e-05, 'samples': 21316608, 'steps': 41633, 'loss/train': 1.0260932445526123} +02/26/2022 07:28:49 - INFO - codeparrot_training - Step 41634: {'lr': 3.6549808594419115e-05, 'samples': 21317120, 'steps': 41634, 'loss/train': 1.5241156816482544} +02/26/2022 07:28:53 - INFO - codeparrot_training - Step 41635: {'lr': 3.654129075570855e-05, 'samples': 21317632, 'steps': 41635, 'loss/train': 1.3140246868133545} +02/26/2022 07:28:58 - INFO - codeparrot_training - Step 41636: {'lr': 3.653277383138734e-05, 'samples': 21318144, 'steps': 41636, 'loss/train': 1.7592339515686035} +02/26/2022 07:29:02 - INFO - codeparrot_training - Step 41637: {'lr': 3.652425782149185e-05, 'samples': 21318656, 'steps': 41637, 'loss/train': 1.9927699565887451} +02/26/2022 07:29:07 - INFO - codeparrot_training - Step 41638: {'lr': 3.6515742726058734e-05, 'samples': 21319168, 'steps': 41638, 'loss/train': 1.6085721254348755} +02/26/2022 07:29:11 - INFO - codeparrot_training - Step 41639: {'lr': 3.650722854512437e-05, 'samples': 21319680, 'steps': 41639, 'loss/train': 0.17155827581882477} +02/26/2022 07:29:16 - INFO - codeparrot_training - Step 41640: {'lr': 3.6498715278725256e-05, 'samples': 21320192, 'steps': 41640, 'loss/train': 0.1545640230178833} +02/26/2022 07:29:20 - INFO - codeparrot_training - Step 41641: {'lr': 3.6490202926897784e-05, 'samples': 21320704, 'steps': 41641, 'loss/train': 1.3149207830429077} +02/26/2022 07:29:25 - INFO - codeparrot_training - Step 41642: {'lr': 3.648169148967856e-05, 'samples': 21321216, 'steps': 41642, 'loss/train': 1.4005154371261597} +02/26/2022 07:29:29 - INFO - codeparrot_training - Step 41643: {'lr': 3.647318096710389e-05, 'samples': 21321728, 'steps': 41643, 'loss/train': 0.5686456561088562} +02/26/2022 07:29:35 - INFO - codeparrot_training - Step 41644: {'lr': 3.646467135921044e-05, 'samples': 21322240, 'steps': 41644, 'loss/train': 0.6416675448417664} +02/26/2022 07:29:38 - INFO - codeparrot_training - Step 41645: {'lr': 3.645616266603441e-05, 'samples': 21322752, 'steps': 41645, 'loss/train': 2.630011558532715} +02/26/2022 07:29:44 - INFO - codeparrot_training - Step 41646: {'lr': 3.6447654887612453e-05, 'samples': 21323264, 'steps': 41646, 'loss/train': 2.4160327911376953} +02/26/2022 07:29:47 - INFO - codeparrot_training - Step 41647: {'lr': 3.6439148023980905e-05, 'samples': 21323776, 'steps': 41647, 'loss/train': 2.6682546138763428} +02/26/2022 07:29:53 - INFO - codeparrot_training - Step 41648: {'lr': 3.643064207517624e-05, 'samples': 21324288, 'steps': 41648, 'loss/train': 1.207150936126709} +02/26/2022 07:29:56 - INFO - codeparrot_training - Step 41649: {'lr': 3.6422137041234844e-05, 'samples': 21324800, 'steps': 41649, 'loss/train': 4.113279342651367} +02/26/2022 07:30:02 - INFO - codeparrot_training - Step 41650: {'lr': 3.641363292219324e-05, 'samples': 21325312, 'steps': 41650, 'loss/train': 0.5875191688537598} +02/26/2022 07:30:05 - INFO - codeparrot_training - Step 41651: {'lr': 3.640512971808782e-05, 'samples': 21325824, 'steps': 41651, 'loss/train': 2.2507638931274414} +02/26/2022 07:30:11 - INFO - codeparrot_training - Step 41652: {'lr': 3.639662742895497e-05, 'samples': 21326336, 'steps': 41652, 'loss/train': 1.445509672164917} +02/26/2022 07:30:15 - INFO - codeparrot_training - Step 41653: {'lr': 3.6388126054831135e-05, 'samples': 21326848, 'steps': 41653, 'loss/train': 1.7996963262557983} +02/26/2022 07:30:18 - INFO - codeparrot_training - Step 41654: {'lr': 3.637962559575275e-05, 'samples': 21327360, 'steps': 41654, 'loss/train': 0.9225202202796936} +02/26/2022 07:30:24 - INFO - codeparrot_training - Step 41655: {'lr': 3.637112605175624e-05, 'samples': 21327872, 'steps': 41655, 'loss/train': 1.8934005498886108} +02/26/2022 07:30:28 - INFO - codeparrot_training - Step 41656: {'lr': 3.6362627422877936e-05, 'samples': 21328384, 'steps': 41656, 'loss/train': 0.6428785920143127} +02/26/2022 07:30:33 - INFO - codeparrot_training - Step 41657: {'lr': 3.635412970915433e-05, 'samples': 21328896, 'steps': 41657, 'loss/train': 0.699927568435669} +02/26/2022 07:30:37 - INFO - codeparrot_training - Step 41658: {'lr': 3.634563291062182e-05, 'samples': 21329408, 'steps': 41658, 'loss/train': 1.4965465068817139} +02/26/2022 07:30:42 - INFO - codeparrot_training - Step 41659: {'lr': 3.633713702731678e-05, 'samples': 21329920, 'steps': 41659, 'loss/train': 2.6621553897857666} +02/26/2022 07:30:46 - INFO - codeparrot_training - Step 41660: {'lr': 3.6328642059275526e-05, 'samples': 21330432, 'steps': 41660, 'loss/train': 2.6097216606140137} +02/26/2022 07:30:51 - INFO - codeparrot_training - Step 41661: {'lr': 3.632014800653463e-05, 'samples': 21330944, 'steps': 41661, 'loss/train': 1.7781643867492676} +02/26/2022 07:30:55 - INFO - codeparrot_training - Step 41662: {'lr': 3.631165486913027e-05, 'samples': 21331456, 'steps': 41662, 'loss/train': 1.2566637992858887} +02/26/2022 07:31:00 - INFO - codeparrot_training - Step 41663: {'lr': 3.6303162647098956e-05, 'samples': 21331968, 'steps': 41663, 'loss/train': 1.3554425239562988} +02/26/2022 07:31:04 - INFO - codeparrot_training - Step 41664: {'lr': 3.6294671340477006e-05, 'samples': 21332480, 'steps': 41664, 'loss/train': 1.8000521659851074} +02/26/2022 07:31:10 - INFO - codeparrot_training - Step 41665: {'lr': 3.6286180949300944e-05, 'samples': 21332992, 'steps': 41665, 'loss/train': 1.0072382688522339} +02/26/2022 07:31:14 - INFO - codeparrot_training - Step 41666: {'lr': 3.627769147360691e-05, 'samples': 21333504, 'steps': 41666, 'loss/train': 2.0703353881835938} +02/26/2022 07:31:19 - INFO - codeparrot_training - Step 41667: {'lr': 3.626920291343141e-05, 'samples': 21334016, 'steps': 41667, 'loss/train': 2.1244912147521973} +02/26/2022 07:31:23 - INFO - codeparrot_training - Step 41668: {'lr': 3.626071526881072e-05, 'samples': 21334528, 'steps': 41668, 'loss/train': 2.1796233654022217} +02/26/2022 07:31:28 - INFO - codeparrot_training - Step 41669: {'lr': 3.625222853978133e-05, 'samples': 21335040, 'steps': 41669, 'loss/train': 1.580825924873352} +02/26/2022 07:31:32 - INFO - codeparrot_training - Step 41670: {'lr': 3.6243742726379536e-05, 'samples': 21335552, 'steps': 41670, 'loss/train': 1.9262468814849854} +02/26/2022 07:31:37 - INFO - codeparrot_training - Step 41671: {'lr': 3.623525782864165e-05, 'samples': 21336064, 'steps': 41671, 'loss/train': 1.7846593856811523} +02/26/2022 07:31:41 - INFO - codeparrot_training - Step 41672: {'lr': 3.6226773846604e-05, 'samples': 21336576, 'steps': 41672, 'loss/train': 0.3570833206176758} +02/26/2022 07:31:46 - INFO - codeparrot_training - Step 41673: {'lr': 3.6218290780303005e-05, 'samples': 21337088, 'steps': 41673, 'loss/train': 1.769381046295166} +02/26/2022 07:31:50 - INFO - codeparrot_training - Step 41674: {'lr': 3.6209808629774995e-05, 'samples': 21337600, 'steps': 41674, 'loss/train': 1.4203745126724243} +02/26/2022 07:31:56 - INFO - codeparrot_training - Step 41675: {'lr': 3.6201327395056244e-05, 'samples': 21338112, 'steps': 41675, 'loss/train': 1.7463834285736084} +02/26/2022 07:32:00 - INFO - codeparrot_training - Step 41676: {'lr': 3.619284707618309e-05, 'samples': 21338624, 'steps': 41676, 'loss/train': 2.070387125015259} +02/26/2022 07:32:05 - INFO - codeparrot_training - Step 41677: {'lr': 3.6184367673191946e-05, 'samples': 21339136, 'steps': 41677, 'loss/train': 0.94215327501297} +02/26/2022 07:32:09 - INFO - codeparrot_training - Step 41678: {'lr': 3.6175889186119e-05, 'samples': 21339648, 'steps': 41678, 'loss/train': 0.7357382774353027} +02/26/2022 07:32:14 - INFO - codeparrot_training - Step 41679: {'lr': 3.6167411615000786e-05, 'samples': 21340160, 'steps': 41679, 'loss/train': 1.9225282669067383} +02/26/2022 07:32:18 - INFO - codeparrot_training - Step 41680: {'lr': 3.615893495987335e-05, 'samples': 21340672, 'steps': 41680, 'loss/train': 0.03728966787457466} +02/26/2022 07:32:23 - INFO - codeparrot_training - Step 41681: {'lr': 3.6150459220773175e-05, 'samples': 21341184, 'steps': 41681, 'loss/train': 2.291738748550415} +02/26/2022 07:32:27 - INFO - codeparrot_training - Step 41682: {'lr': 3.61419843977365e-05, 'samples': 21341696, 'steps': 41682, 'loss/train': 1.8549846410751343} +02/26/2022 07:32:33 - INFO - codeparrot_training - Step 41683: {'lr': 3.613351049079977e-05, 'samples': 21342208, 'steps': 41683, 'loss/train': 1.6001858711242676} +02/26/2022 07:32:38 - INFO - codeparrot_training - Step 41684: {'lr': 3.612503749999904e-05, 'samples': 21342720, 'steps': 41684, 'loss/train': 1.2245246171951294} +02/26/2022 07:32:42 - INFO - codeparrot_training - Step 41685: {'lr': 3.6116565425370815e-05, 'samples': 21343232, 'steps': 41685, 'loss/train': 1.3882091045379639} +02/26/2022 07:32:47 - INFO - codeparrot_training - Step 41686: {'lr': 3.610809426695122e-05, 'samples': 21343744, 'steps': 41686, 'loss/train': 0.8962826132774353} +02/26/2022 07:32:51 - INFO - codeparrot_training - Step 41687: {'lr': 3.609962402477676e-05, 'samples': 21344256, 'steps': 41687, 'loss/train': 1.2971596717834473} +02/26/2022 07:32:56 - INFO - codeparrot_training - Step 41688: {'lr': 3.6091154698883495e-05, 'samples': 21344768, 'steps': 41688, 'loss/train': 1.413360357284546} +02/26/2022 07:33:00 - INFO - codeparrot_training - Step 41689: {'lr': 3.608268628930783e-05, 'samples': 21345280, 'steps': 41689, 'loss/train': 1.5986542701721191} +02/26/2022 07:33:06 - INFO - codeparrot_training - Step 41690: {'lr': 3.6074218796085966e-05, 'samples': 21345792, 'steps': 41690, 'loss/train': 1.52005934715271} +02/26/2022 07:33:09 - INFO - codeparrot_training - Step 41691: {'lr': 3.606575221925426e-05, 'samples': 21346304, 'steps': 41691, 'loss/train': 1.6590601205825806} +02/26/2022 07:33:15 - INFO - codeparrot_training - Step 41692: {'lr': 3.605728655884896e-05, 'samples': 21346816, 'steps': 41692, 'loss/train': 1.6791789531707764} +02/26/2022 07:33:18 - INFO - codeparrot_training - Step 41693: {'lr': 3.604882181490629e-05, 'samples': 21347328, 'steps': 41693, 'loss/train': 2.900899887084961} +02/26/2022 07:33:24 - INFO - codeparrot_training - Step 41694: {'lr': 3.604035798746255e-05, 'samples': 21347840, 'steps': 41694, 'loss/train': 2.037975311279297} +02/26/2022 07:33:27 - INFO - codeparrot_training - Step 41695: {'lr': 3.603189507655391e-05, 'samples': 21348352, 'steps': 41695, 'loss/train': 0.7879558801651001} +02/26/2022 07:33:33 - INFO - codeparrot_training - Step 41696: {'lr': 3.602343308221675e-05, 'samples': 21348864, 'steps': 41696, 'loss/train': 0.37129315733909607} +02/26/2022 07:33:36 - INFO - codeparrot_training - Step 41697: {'lr': 3.601497200448725e-05, 'samples': 21349376, 'steps': 41697, 'loss/train': 2.123992681503296} +02/26/2022 07:33:42 - INFO - codeparrot_training - Step 41698: {'lr': 3.6006511843401675e-05, 'samples': 21349888, 'steps': 41698, 'loss/train': 0.8518533706665039} +02/26/2022 07:33:45 - INFO - codeparrot_training - Step 41699: {'lr': 3.5998052598996186e-05, 'samples': 21350400, 'steps': 41699, 'loss/train': 2.4207725524902344} +02/26/2022 07:33:51 - INFO - codeparrot_training - Step 41700: {'lr': 3.5989594271307156e-05, 'samples': 21350912, 'steps': 41700, 'loss/train': 1.3484591245651245} +02/26/2022 07:33:55 - INFO - codeparrot_training - Step 41701: {'lr': 3.598113686037075e-05, 'samples': 21351424, 'steps': 41701, 'loss/train': 1.8877475261688232} +02/26/2022 07:34:00 - INFO - codeparrot_training - Step 41702: {'lr': 3.597268036622317e-05, 'samples': 21351936, 'steps': 41702, 'loss/train': 0.37708383798599243} +02/26/2022 07:34:04 - INFO - codeparrot_training - Step 41703: {'lr': 3.596422478890063e-05, 'samples': 21352448, 'steps': 41703, 'loss/train': 3.590773820877075} +02/26/2022 07:34:09 - INFO - codeparrot_training - Step 41704: {'lr': 3.5955770128439424e-05, 'samples': 21352960, 'steps': 41704, 'loss/train': 1.172747015953064} +02/26/2022 07:34:13 - INFO - codeparrot_training - Step 41705: {'lr': 3.594731638487575e-05, 'samples': 21353472, 'steps': 41705, 'loss/train': 2.263465166091919} +02/26/2022 07:34:18 - INFO - codeparrot_training - Step 41706: {'lr': 3.59388635582458e-05, 'samples': 21353984, 'steps': 41706, 'loss/train': 1.7478835582733154} +02/26/2022 07:34:22 - INFO - codeparrot_training - Step 41707: {'lr': 3.593041164858574e-05, 'samples': 21354496, 'steps': 41707, 'loss/train': 2.535195827484131} +02/26/2022 07:34:27 - INFO - codeparrot_training - Step 41708: {'lr': 3.592196065593184e-05, 'samples': 21355008, 'steps': 41708, 'loss/train': 1.4918303489685059} +02/26/2022 07:34:31 - INFO - codeparrot_training - Step 41709: {'lr': 3.591351058032033e-05, 'samples': 21355520, 'steps': 41709, 'loss/train': 1.8929601907730103} +02/26/2022 07:34:37 - INFO - codeparrot_training - Step 41710: {'lr': 3.5905061421787316e-05, 'samples': 21356032, 'steps': 41710, 'loss/train': 1.9910062551498413} +02/26/2022 07:34:40 - INFO - codeparrot_training - Step 41711: {'lr': 3.589661318036902e-05, 'samples': 21356544, 'steps': 41711, 'loss/train': 1.3086901903152466} +02/26/2022 07:34:46 - INFO - codeparrot_training - Step 41712: {'lr': 3.588816585610169e-05, 'samples': 21357056, 'steps': 41712, 'loss/train': 1.525822401046753} +02/26/2022 07:34:50 - INFO - codeparrot_training - Step 41713: {'lr': 3.587971944902146e-05, 'samples': 21357568, 'steps': 41713, 'loss/train': 1.63988196849823} +02/26/2022 07:34:55 - INFO - codeparrot_training - Step 41714: {'lr': 3.5871273959164534e-05, 'samples': 21358080, 'steps': 41714, 'loss/train': 2.04854416847229} +02/26/2022 07:34:59 - INFO - codeparrot_training - Step 41715: {'lr': 3.586282938656702e-05, 'samples': 21358592, 'steps': 41715, 'loss/train': 1.877226710319519} +02/26/2022 07:35:04 - INFO - codeparrot_training - Step 41716: {'lr': 3.585438573126518e-05, 'samples': 21359104, 'steps': 41716, 'loss/train': 1.7811907529830933} +02/26/2022 07:35:08 - INFO - codeparrot_training - Step 41717: {'lr': 3.5845942993295103e-05, 'samples': 21359616, 'steps': 41717, 'loss/train': 2.4954702854156494} +02/26/2022 07:35:13 - INFO - codeparrot_training - Step 41718: {'lr': 3.583750117269313e-05, 'samples': 21360128, 'steps': 41718, 'loss/train': 1.5006673336029053} +02/26/2022 07:35:17 - INFO - codeparrot_training - Step 41719: {'lr': 3.5829060269495204e-05, 'samples': 21360640, 'steps': 41719, 'loss/train': 1.727968692779541} +02/26/2022 07:35:24 - INFO - codeparrot_training - Step 41720: {'lr': 3.5820620283737615e-05, 'samples': 21361152, 'steps': 41720, 'loss/train': 1.1878557205200195} +02/26/2022 07:35:27 - INFO - codeparrot_training - Step 41721: {'lr': 3.58121812154564e-05, 'samples': 21361664, 'steps': 41721, 'loss/train': 0.7967495322227478} +02/26/2022 07:35:33 - INFO - codeparrot_training - Step 41722: {'lr': 3.580374306468795e-05, 'samples': 21362176, 'steps': 41722, 'loss/train': 1.8414092063903809} +02/26/2022 07:35:36 - INFO - codeparrot_training - Step 41723: {'lr': 3.5795305831468086e-05, 'samples': 21362688, 'steps': 41723, 'loss/train': 1.4105950593948364} +02/26/2022 07:35:42 - INFO - codeparrot_training - Step 41724: {'lr': 3.578686951583321e-05, 'samples': 21363200, 'steps': 41724, 'loss/train': 0.7590596675872803} +02/26/2022 07:35:45 - INFO - codeparrot_training - Step 41725: {'lr': 3.5778434117819284e-05, 'samples': 21363712, 'steps': 41725, 'loss/train': 2.1910815238952637} +02/26/2022 07:35:51 - INFO - codeparrot_training - Step 41726: {'lr': 3.576999963746258e-05, 'samples': 21364224, 'steps': 41726, 'loss/train': 2.05096697807312} +02/26/2022 07:35:54 - INFO - codeparrot_training - Step 41727: {'lr': 3.576156607479919e-05, 'samples': 21364736, 'steps': 41727, 'loss/train': 2.4411516189575195} +02/26/2022 07:36:00 - INFO - codeparrot_training - Step 41728: {'lr': 3.575313342986522e-05, 'samples': 21365248, 'steps': 41728, 'loss/train': 1.9012272357940674} +02/26/2022 07:36:03 - INFO - codeparrot_training - Step 41729: {'lr': 3.574470170269672e-05, 'samples': 21365760, 'steps': 41729, 'loss/train': 1.4051686525344849} +02/26/2022 07:36:09 - INFO - codeparrot_training - Step 41730: {'lr': 3.5736270893329955e-05, 'samples': 21366272, 'steps': 41730, 'loss/train': 1.2901688814163208} +02/26/2022 07:36:12 - INFO - codeparrot_training - Step 41731: {'lr': 3.572784100180096e-05, 'samples': 21366784, 'steps': 41731, 'loss/train': 1.1237056255340576} +02/26/2022 07:36:18 - INFO - codeparrot_training - Step 41732: {'lr': 3.571941202814588e-05, 'samples': 21367296, 'steps': 41732, 'loss/train': 2.126596212387085} +02/26/2022 07:36:21 - INFO - codeparrot_training - Step 41733: {'lr': 3.571098397240072e-05, 'samples': 21367808, 'steps': 41733, 'loss/train': 1.5708905458450317} +02/26/2022 07:36:27 - INFO - codeparrot_training - Step 41734: {'lr': 3.570255683460172e-05, 'samples': 21368320, 'steps': 41734, 'loss/train': 1.101157307624817} +02/26/2022 07:36:30 - INFO - codeparrot_training - Step 41735: {'lr': 3.569413061478491e-05, 'samples': 21368832, 'steps': 41735, 'loss/train': 2.1775007247924805} +02/26/2022 07:36:36 - INFO - codeparrot_training - Step 41736: {'lr': 3.56857053129864e-05, 'samples': 21369344, 'steps': 41736, 'loss/train': 2.413322687149048} +02/26/2022 07:36:40 - INFO - codeparrot_training - Step 41737: {'lr': 3.5677280929242214e-05, 'samples': 21369856, 'steps': 41737, 'loss/train': 2.2208516597747803} +02/26/2022 07:36:45 - INFO - codeparrot_training - Step 41738: {'lr': 3.566885746358858e-05, 'samples': 21370368, 'steps': 41738, 'loss/train': 1.4122841358184814} +02/26/2022 07:36:49 - INFO - codeparrot_training - Step 41739: {'lr': 3.56604349160615e-05, 'samples': 21370880, 'steps': 41739, 'loss/train': 1.4783846139907837} +02/26/2022 07:36:54 - INFO - codeparrot_training - Step 41740: {'lr': 3.5652013286697036e-05, 'samples': 21371392, 'steps': 41740, 'loss/train': 1.8731080293655396} +02/26/2022 07:36:58 - INFO - codeparrot_training - Step 41741: {'lr': 3.564359257553129e-05, 'samples': 21371904, 'steps': 41741, 'loss/train': 2.161520481109619} +02/26/2022 07:37:03 - INFO - codeparrot_training - Step 41742: {'lr': 3.563517278260025e-05, 'samples': 21372416, 'steps': 41742, 'loss/train': 1.2099199295043945} +02/26/2022 07:37:07 - INFO - codeparrot_training - Step 41743: {'lr': 3.562675390794015e-05, 'samples': 21372928, 'steps': 41743, 'loss/train': 2.234713315963745} +02/26/2022 07:37:12 - INFO - codeparrot_training - Step 41744: {'lr': 3.561833595158698e-05, 'samples': 21373440, 'steps': 41744, 'loss/train': 1.2447516918182373} +02/26/2022 07:37:15 - INFO - codeparrot_training - Step 41745: {'lr': 3.560991891357676e-05, 'samples': 21373952, 'steps': 41745, 'loss/train': 2.3983891010284424} +02/26/2022 07:37:22 - INFO - codeparrot_training - Step 41746: {'lr': 3.56015027939455e-05, 'samples': 21374464, 'steps': 41746, 'loss/train': 3.4015278816223145} +02/26/2022 07:37:25 - INFO - codeparrot_training - Step 41747: {'lr': 3.559308759272939e-05, 'samples': 21374976, 'steps': 41747, 'loss/train': 1.4039788246154785} +02/26/2022 07:37:31 - INFO - codeparrot_training - Step 41748: {'lr': 3.558467330996443e-05, 'samples': 21375488, 'steps': 41748, 'loss/train': 1.170341968536377} +02/26/2022 07:37:34 - INFO - codeparrot_training - Step 41749: {'lr': 3.557625994568664e-05, 'samples': 21376000, 'steps': 41749, 'loss/train': 2.9517874717712402} +02/26/2022 07:37:40 - INFO - codeparrot_training - Step 41750: {'lr': 3.5567847499932e-05, 'samples': 21376512, 'steps': 41750, 'loss/train': 1.657469391822815} +02/26/2022 07:37:43 - INFO - codeparrot_training - Step 41751: {'lr': 3.555943597273667e-05, 'samples': 21377024, 'steps': 41751, 'loss/train': 1.6412954330444336} +02/26/2022 07:37:49 - INFO - codeparrot_training - Step 41752: {'lr': 3.5551025364136544e-05, 'samples': 21377536, 'steps': 41752, 'loss/train': 2.201308488845825} +02/26/2022 07:37:52 - INFO - codeparrot_training - Step 41753: {'lr': 3.554261567416786e-05, 'samples': 21378048, 'steps': 41753, 'loss/train': 2.0442068576812744} +02/26/2022 07:37:58 - INFO - codeparrot_training - Step 41754: {'lr': 3.5534206902866404e-05, 'samples': 21378560, 'steps': 41754, 'loss/train': 1.6880371570587158} +02/26/2022 07:38:01 - INFO - codeparrot_training - Step 41755: {'lr': 3.552579905026837e-05, 'samples': 21379072, 'steps': 41755, 'loss/train': 1.3798959255218506} +02/26/2022 07:38:07 - INFO - codeparrot_training - Step 41756: {'lr': 3.551739211640964e-05, 'samples': 21379584, 'steps': 41756, 'loss/train': 1.8287084102630615} +02/26/2022 07:38:11 - INFO - codeparrot_training - Step 41757: {'lr': 3.5508986101326415e-05, 'samples': 21380096, 'steps': 41757, 'loss/train': 1.1338351964950562} +02/26/2022 07:38:16 - INFO - codeparrot_training - Step 41758: {'lr': 3.550058100505449e-05, 'samples': 21380608, 'steps': 41758, 'loss/train': 0.45335105061531067} +02/26/2022 07:38:20 - INFO - codeparrot_training - Step 41759: {'lr': 3.549217682762998e-05, 'samples': 21381120, 'steps': 41759, 'loss/train': 2.351400852203369} +02/26/2022 07:38:25 - INFO - codeparrot_training - Step 41760: {'lr': 3.548377356908886e-05, 'samples': 21381632, 'steps': 41760, 'loss/train': 1.165387749671936} +02/26/2022 07:38:29 - INFO - codeparrot_training - Step 41761: {'lr': 3.54753712294672e-05, 'samples': 21382144, 'steps': 41761, 'loss/train': 1.49990713596344} +02/26/2022 07:38:34 - INFO - codeparrot_training - Step 41762: {'lr': 3.546696980880085e-05, 'samples': 21382656, 'steps': 41762, 'loss/train': 2.260895252227783} +02/26/2022 07:38:38 - INFO - codeparrot_training - Step 41763: {'lr': 3.545856930712593e-05, 'samples': 21383168, 'steps': 41763, 'loss/train': 1.9449162483215332} +02/26/2022 07:38:43 - INFO - codeparrot_training - Step 41764: {'lr': 3.5450169724478315e-05, 'samples': 21383680, 'steps': 41764, 'loss/train': 0.7249825596809387} +02/26/2022 07:38:47 - INFO - codeparrot_training - Step 41765: {'lr': 3.5441771060894104e-05, 'samples': 21384192, 'steps': 41765, 'loss/train': 1.3583165407180786} +02/26/2022 07:38:52 - INFO - codeparrot_training - Step 41766: {'lr': 3.543337331640922e-05, 'samples': 21384704, 'steps': 41766, 'loss/train': 1.5960205793380737} +02/26/2022 07:38:56 - INFO - codeparrot_training - Step 41767: {'lr': 3.5424976491059635e-05, 'samples': 21385216, 'steps': 41767, 'loss/train': 2.4699699878692627} +02/26/2022 07:39:02 - INFO - codeparrot_training - Step 41768: {'lr': 3.541658058488126e-05, 'samples': 21385728, 'steps': 41768, 'loss/train': 0.7365851402282715} +02/26/2022 07:39:05 - INFO - codeparrot_training - Step 41769: {'lr': 3.540818559791017e-05, 'samples': 21386240, 'steps': 41769, 'loss/train': 2.187325954437256} +02/26/2022 07:39:11 - INFO - codeparrot_training - Step 41770: {'lr': 3.539979153018228e-05, 'samples': 21386752, 'steps': 41770, 'loss/train': 2.2277119159698486} +02/26/2022 07:39:14 - INFO - codeparrot_training - Step 41771: {'lr': 3.53913983817335e-05, 'samples': 21387264, 'steps': 41771, 'loss/train': 1.6255269050598145} +02/26/2022 07:39:20 - INFO - codeparrot_training - Step 41772: {'lr': 3.538300615259979e-05, 'samples': 21387776, 'steps': 41772, 'loss/train': 7.131189823150635} +02/26/2022 07:39:24 - INFO - codeparrot_training - Step 41773: {'lr': 3.537461484281721e-05, 'samples': 21388288, 'steps': 41773, 'loss/train': 2.6381707191467285} +02/26/2022 07:39:29 - INFO - codeparrot_training - Step 41774: {'lr': 3.53662244524216e-05, 'samples': 21388800, 'steps': 41774, 'loss/train': 1.708308458328247} +02/26/2022 07:39:33 - INFO - codeparrot_training - Step 41775: {'lr': 3.535783498144895e-05, 'samples': 21389312, 'steps': 41775, 'loss/train': 2.2258992195129395} +02/26/2022 07:39:38 - INFO - codeparrot_training - Step 41776: {'lr': 3.534944642993512e-05, 'samples': 21389824, 'steps': 41776, 'loss/train': 1.870118260383606} +02/26/2022 07:39:42 - INFO - codeparrot_training - Step 41777: {'lr': 3.534105879791616e-05, 'samples': 21390336, 'steps': 41777, 'loss/train': 2.0420596599578857} +02/26/2022 07:39:47 - INFO - codeparrot_training - Step 41778: {'lr': 3.5332672085427926e-05, 'samples': 21390848, 'steps': 41778, 'loss/train': 0.742152988910675} +02/26/2022 07:39:51 - INFO - codeparrot_training - Step 41779: {'lr': 3.532428629250636e-05, 'samples': 21391360, 'steps': 41779, 'loss/train': 1.2266942262649536} +02/26/2022 07:39:56 - INFO - codeparrot_training - Step 41780: {'lr': 3.5315901419187364e-05, 'samples': 21391872, 'steps': 41780, 'loss/train': 1.7314984798431396} +02/26/2022 07:40:00 - INFO - codeparrot_training - Step 41781: {'lr': 3.530751746550689e-05, 'samples': 21392384, 'steps': 41781, 'loss/train': 1.7999262809753418} +02/26/2022 07:40:06 - INFO - codeparrot_training - Step 41782: {'lr': 3.529913443150087e-05, 'samples': 21392896, 'steps': 41782, 'loss/train': 1.9495538473129272} +02/26/2022 07:40:10 - INFO - codeparrot_training - Step 41783: {'lr': 3.529075231720516e-05, 'samples': 21393408, 'steps': 41783, 'loss/train': 1.362709403038025} +02/26/2022 07:40:15 - INFO - codeparrot_training - Step 41784: {'lr': 3.528237112265564e-05, 'samples': 21393920, 'steps': 41784, 'loss/train': 1.2696821689605713} +02/26/2022 07:40:19 - INFO - codeparrot_training - Step 41785: {'lr': 3.527399084788832e-05, 'samples': 21394432, 'steps': 41785, 'loss/train': 1.9738383293151855} +02/26/2022 07:40:24 - INFO - codeparrot_training - Step 41786: {'lr': 3.526561149293906e-05, 'samples': 21394944, 'steps': 41786, 'loss/train': 1.3871738910675049} +02/26/2022 07:40:28 - INFO - codeparrot_training - Step 41787: {'lr': 3.5257233057843645e-05, 'samples': 21395456, 'steps': 41787, 'loss/train': 1.9540824890136719} +02/26/2022 07:40:33 - INFO - codeparrot_training - Step 41788: {'lr': 3.5248855542638184e-05, 'samples': 21395968, 'steps': 41788, 'loss/train': 1.787583827972412} +02/26/2022 07:40:37 - INFO - codeparrot_training - Step 41789: {'lr': 3.5240478947358297e-05, 'samples': 21396480, 'steps': 41789, 'loss/train': 0.7123517394065857} +02/26/2022 07:40:42 - INFO - codeparrot_training - Step 41790: {'lr': 3.52321032720401e-05, 'samples': 21396992, 'steps': 41790, 'loss/train': 0.757858395576477} +02/26/2022 07:40:46 - INFO - codeparrot_training - Step 41791: {'lr': 3.5223728516719286e-05, 'samples': 21397504, 'steps': 41791, 'loss/train': 2.3760859966278076} +02/26/2022 07:40:51 - INFO - codeparrot_training - Step 41792: {'lr': 3.521535468143197e-05, 'samples': 21398016, 'steps': 41792, 'loss/train': 1.1649057865142822} +02/26/2022 07:40:55 - INFO - codeparrot_training - Step 41793: {'lr': 3.520698176621373e-05, 'samples': 21398528, 'steps': 41793, 'loss/train': 0.3401975631713867} +02/26/2022 07:41:01 - INFO - codeparrot_training - Step 41794: {'lr': 3.519860977110065e-05, 'samples': 21399040, 'steps': 41794, 'loss/train': 2.129559278488159} +02/26/2022 07:41:04 - INFO - codeparrot_training - Step 41795: {'lr': 3.519023869612845e-05, 'samples': 21399552, 'steps': 41795, 'loss/train': 1.4806514978408813} +02/26/2022 07:41:10 - INFO - codeparrot_training - Step 41796: {'lr': 3.518186854133315e-05, 'samples': 21400064, 'steps': 41796, 'loss/train': 1.207190990447998} +02/26/2022 07:41:13 - INFO - codeparrot_training - Step 41797: {'lr': 3.517349930675043e-05, 'samples': 21400576, 'steps': 41797, 'loss/train': 2.6549975872039795} +02/26/2022 07:41:19 - INFO - codeparrot_training - Step 41798: {'lr': 3.5165130992416275e-05, 'samples': 21401088, 'steps': 41798, 'loss/train': 2.072608470916748} +02/26/2022 07:41:22 - INFO - codeparrot_training - Step 41799: {'lr': 3.515676359836642e-05, 'samples': 21401600, 'steps': 41799, 'loss/train': 0.135090172290802} +02/26/2022 07:41:28 - INFO - codeparrot_training - Step 41800: {'lr': 3.514839712463683e-05, 'samples': 21402112, 'steps': 41800, 'loss/train': 2.0122764110565186} +02/26/2022 07:41:32 - INFO - codeparrot_training - Step 41801: {'lr': 3.5140031571263276e-05, 'samples': 21402624, 'steps': 41801, 'loss/train': 1.4339104890823364} +02/26/2022 07:41:37 - INFO - codeparrot_training - Step 41802: {'lr': 3.5131666938281626e-05, 'samples': 21403136, 'steps': 41802, 'loss/train': 0.9168344140052795} +02/26/2022 07:41:40 - INFO - codeparrot_training - Step 41803: {'lr': 3.51233032257276e-05, 'samples': 21403648, 'steps': 41803, 'loss/train': 1.9832981824874878} +02/26/2022 07:41:46 - INFO - codeparrot_training - Step 41804: {'lr': 3.51149404336372e-05, 'samples': 21404160, 'steps': 41804, 'loss/train': 2.1262660026550293} +02/26/2022 07:41:50 - INFO - codeparrot_training - Step 41805: {'lr': 3.510657856204613e-05, 'samples': 21404672, 'steps': 41805, 'loss/train': 2.0327484607696533} +02/26/2022 07:41:56 - INFO - codeparrot_training - Step 41806: {'lr': 3.5098217610990244e-05, 'samples': 21405184, 'steps': 41806, 'loss/train': 1.4959701299667358} +02/26/2022 07:42:01 - INFO - codeparrot_training - Step 41807: {'lr': 3.5089857580505316e-05, 'samples': 21405696, 'steps': 41807, 'loss/train': 0.739684522151947} +02/26/2022 07:42:05 - INFO - codeparrot_training - Step 41808: {'lr': 3.508149847062725e-05, 'samples': 21406208, 'steps': 41808, 'loss/train': 1.3491206169128418} +02/26/2022 07:42:11 - INFO - codeparrot_training - Step 41809: {'lr': 3.5073140281391776e-05, 'samples': 21406720, 'steps': 41809, 'loss/train': 1.8846805095672607} +02/26/2022 07:42:15 - INFO - codeparrot_training - Step 41810: {'lr': 3.506478301283475e-05, 'samples': 21407232, 'steps': 41810, 'loss/train': 2.0595109462738037} +02/26/2022 07:42:20 - INFO - codeparrot_training - Step 41811: {'lr': 3.505642666499187e-05, 'samples': 21407744, 'steps': 41811, 'loss/train': 1.2388486862182617} +02/26/2022 07:42:24 - INFO - codeparrot_training - Step 41812: {'lr': 3.504807123789908e-05, 'samples': 21408256, 'steps': 41812, 'loss/train': 1.553773045539856} +02/26/2022 07:42:29 - INFO - codeparrot_training - Step 41813: {'lr': 3.503971673159204e-05, 'samples': 21408768, 'steps': 41813, 'loss/train': 1.818275809288025} +02/26/2022 07:42:33 - INFO - codeparrot_training - Step 41814: {'lr': 3.5031363146106695e-05, 'samples': 21409280, 'steps': 41814, 'loss/train': 2.6383988857269287} +02/26/2022 07:42:38 - INFO - codeparrot_training - Step 41815: {'lr': 3.50230104814786e-05, 'samples': 21409792, 'steps': 41815, 'loss/train': 1.3958686590194702} +02/26/2022 07:42:42 - INFO - codeparrot_training - Step 41816: {'lr': 3.501465873774376e-05, 'samples': 21410304, 'steps': 41816, 'loss/train': 2.5607266426086426} +02/26/2022 07:42:47 - INFO - codeparrot_training - Step 41817: {'lr': 3.500630791493778e-05, 'samples': 21410816, 'steps': 41817, 'loss/train': 2.1913537979125977} +02/26/2022 07:42:51 - INFO - codeparrot_training - Step 41818: {'lr': 3.499795801309663e-05, 'samples': 21411328, 'steps': 41818, 'loss/train': 2.8457465171813965} +02/26/2022 07:42:57 - INFO - codeparrot_training - Step 41819: {'lr': 3.498960903225584e-05, 'samples': 21411840, 'steps': 41819, 'loss/train': 1.5430333614349365} +02/26/2022 07:43:01 - INFO - codeparrot_training - Step 41820: {'lr': 3.4981260972451354e-05, 'samples': 21412352, 'steps': 41820, 'loss/train': 3.1928465366363525} +02/26/2022 07:43:06 - INFO - codeparrot_training - Step 41821: {'lr': 3.4972913833718864e-05, 'samples': 21412864, 'steps': 41821, 'loss/train': 1.643866777420044} +02/26/2022 07:43:10 - INFO - codeparrot_training - Step 41822: {'lr': 3.496456761609412e-05, 'samples': 21413376, 'steps': 41822, 'loss/train': 2.3708415031433105} +02/26/2022 07:43:15 - INFO - codeparrot_training - Step 41823: {'lr': 3.495622231961285e-05, 'samples': 21413888, 'steps': 41823, 'loss/train': 0.815904974937439} +02/26/2022 07:43:19 - INFO - codeparrot_training - Step 41824: {'lr': 3.494787794431087e-05, 'samples': 21414400, 'steps': 41824, 'loss/train': 1.3587661981582642} +02/26/2022 07:43:25 - INFO - codeparrot_training - Step 41825: {'lr': 3.493953449022391e-05, 'samples': 21414912, 'steps': 41825, 'loss/train': 2.3958585262298584} +02/26/2022 07:43:28 - INFO - codeparrot_training - Step 41826: {'lr': 3.493119195738764e-05, 'samples': 21415424, 'steps': 41826, 'loss/train': 2.8388452529907227} +02/26/2022 07:43:34 - INFO - codeparrot_training - Step 41827: {'lr': 3.492285034583792e-05, 'samples': 21415936, 'steps': 41827, 'loss/train': 1.6827870607376099} +02/26/2022 07:43:37 - INFO - codeparrot_training - Step 41828: {'lr': 3.491450965561041e-05, 'samples': 21416448, 'steps': 41828, 'loss/train': 1.5402657985687256} +02/26/2022 07:43:44 - INFO - codeparrot_training - Step 41829: {'lr': 3.490616988674083e-05, 'samples': 21416960, 'steps': 41829, 'loss/train': 1.8274123668670654} +02/26/2022 07:43:47 - INFO - codeparrot_training - Step 41830: {'lr': 3.489783103926486e-05, 'samples': 21417472, 'steps': 41830, 'loss/train': 1.3994922637939453} +02/26/2022 07:43:53 - INFO - codeparrot_training - Step 41831: {'lr': 3.488949311321835e-05, 'samples': 21417984, 'steps': 41831, 'loss/train': 1.6066696643829346} +02/26/2022 07:43:56 - INFO - codeparrot_training - Step 41832: {'lr': 3.488115610863693e-05, 'samples': 21418496, 'steps': 41832, 'loss/train': 1.883328914642334} +02/26/2022 07:44:00 - INFO - codeparrot_training - Step 41833: {'lr': 3.4872820025556364e-05, 'samples': 21419008, 'steps': 41833, 'loss/train': 1.6999083757400513} +02/26/2022 07:44:05 - INFO - codeparrot_training - Step 41834: {'lr': 3.4864484864012225e-05, 'samples': 21419520, 'steps': 41834, 'loss/train': 2.2516164779663086} +02/26/2022 07:44:09 - INFO - codeparrot_training - Step 41835: {'lr': 3.485615062404041e-05, 'samples': 21420032, 'steps': 41835, 'loss/train': 1.5778331756591797} +02/26/2022 07:44:14 - INFO - codeparrot_training - Step 41836: {'lr': 3.484781730567651e-05, 'samples': 21420544, 'steps': 41836, 'loss/train': 2.472184181213379} +02/26/2022 07:44:18 - INFO - codeparrot_training - Step 41837: {'lr': 3.483948490895625e-05, 'samples': 21421056, 'steps': 41837, 'loss/train': 1.3338651657104492} +02/26/2022 07:44:23 - INFO - codeparrot_training - Step 41838: {'lr': 3.483115343391527e-05, 'samples': 21421568, 'steps': 41838, 'loss/train': 1.1206046342849731} +02/26/2022 07:44:27 - INFO - codeparrot_training - Step 41839: {'lr': 3.4822822880589325e-05, 'samples': 21422080, 'steps': 41839, 'loss/train': 1.0529612302780151} +02/26/2022 07:44:33 - INFO - codeparrot_training - Step 41840: {'lr': 3.481449324901412e-05, 'samples': 21422592, 'steps': 41840, 'loss/train': 1.7585954666137695} +02/26/2022 07:44:37 - INFO - codeparrot_training - Step 41841: {'lr': 3.4806164539225274e-05, 'samples': 21423104, 'steps': 41841, 'loss/train': 1.643898367881775} +02/26/2022 07:44:42 - INFO - codeparrot_training - Step 41842: {'lr': 3.479783675125844e-05, 'samples': 21423616, 'steps': 41842, 'loss/train': 1.2547779083251953} +02/26/2022 07:44:46 - INFO - codeparrot_training - Step 41843: {'lr': 3.47895098851494e-05, 'samples': 21424128, 'steps': 41843, 'loss/train': 0.6766678094863892} +02/26/2022 07:44:51 - INFO - codeparrot_training - Step 41844: {'lr': 3.4781183940933744e-05, 'samples': 21424640, 'steps': 41844, 'loss/train': 1.009781002998352} +02/26/2022 07:44:55 - INFO - codeparrot_training - Step 41845: {'lr': 3.4772858918647176e-05, 'samples': 21425152, 'steps': 41845, 'loss/train': 1.7243602275848389} +02/26/2022 07:45:00 - INFO - codeparrot_training - Step 41846: {'lr': 3.476453481832528e-05, 'samples': 21425664, 'steps': 41846, 'loss/train': 1.997341275215149} +02/26/2022 07:45:04 - INFO - codeparrot_training - Step 41847: {'lr': 3.475621164000381e-05, 'samples': 21426176, 'steps': 41847, 'loss/train': 0.5192564129829407} +02/26/2022 07:45:09 - INFO - codeparrot_training - Step 41848: {'lr': 3.474788938371834e-05, 'samples': 21426688, 'steps': 41848, 'loss/train': 1.4176605939865112} +02/26/2022 07:45:13 - INFO - codeparrot_training - Step 41849: {'lr': 3.473956804950468e-05, 'samples': 21427200, 'steps': 41849, 'loss/train': 2.113344192504883} +02/26/2022 07:45:20 - INFO - codeparrot_training - Step 41850: {'lr': 3.473124763739824e-05, 'samples': 21427712, 'steps': 41850, 'loss/train': 2.7613272666931152} +02/26/2022 07:45:23 - INFO - codeparrot_training - Step 41851: {'lr': 3.472292814743483e-05, 'samples': 21428224, 'steps': 41851, 'loss/train': 1.2220218181610107} +02/26/2022 07:45:28 - INFO - codeparrot_training - Step 41852: {'lr': 3.4714609579649975e-05, 'samples': 21428736, 'steps': 41852, 'loss/train': 2.3839950561523438} +02/26/2022 07:45:32 - INFO - codeparrot_training - Step 41853: {'lr': 3.470629193407948e-05, 'samples': 21429248, 'steps': 41853, 'loss/train': 2.0858848094940186} +02/26/2022 07:45:38 - INFO - codeparrot_training - Step 41854: {'lr': 3.469797521075879e-05, 'samples': 21429760, 'steps': 41854, 'loss/train': 1.7080988883972168} +02/26/2022 07:45:41 - INFO - codeparrot_training - Step 41855: {'lr': 3.468965940972363e-05, 'samples': 21430272, 'steps': 41855, 'loss/train': 1.432517170906067} +02/26/2022 07:45:47 - INFO - codeparrot_training - Step 41856: {'lr': 3.468134453100957e-05, 'samples': 21430784, 'steps': 41856, 'loss/train': 0.24918366968631744} +02/26/2022 07:45:51 - INFO - codeparrot_training - Step 41857: {'lr': 3.4673030574652346e-05, 'samples': 21431296, 'steps': 41857, 'loss/train': 2.2553653717041016} +02/26/2022 07:45:54 - INFO - codeparrot_training - Step 41858: {'lr': 3.4664717540687395e-05, 'samples': 21431808, 'steps': 41858, 'loss/train': 1.7428793907165527} +02/26/2022 07:46:00 - INFO - codeparrot_training - Step 41859: {'lr': 3.465640542915044e-05, 'samples': 21432320, 'steps': 41859, 'loss/train': 2.9964118003845215} +02/26/2022 07:46:05 - INFO - codeparrot_training - Step 41860: {'lr': 3.464809424007703e-05, 'samples': 21432832, 'steps': 41860, 'loss/train': 2.4415841102600098} +02/26/2022 07:46:09 - INFO - codeparrot_training - Step 41861: {'lr': 3.463978397350287e-05, 'samples': 21433344, 'steps': 41861, 'loss/train': 1.4502977132797241} +02/26/2022 07:46:12 - INFO - codeparrot_training - Step 41862: {'lr': 3.463147462946348e-05, 'samples': 21433856, 'steps': 41862, 'loss/train': 1.4036734104156494} +02/26/2022 07:46:18 - INFO - codeparrot_training - Step 41863: {'lr': 3.462316620799447e-05, 'samples': 21434368, 'steps': 41863, 'loss/train': 1.6313860416412354} +02/26/2022 07:46:21 - INFO - codeparrot_training - Step 41864: {'lr': 3.461485870913137e-05, 'samples': 21434880, 'steps': 41864, 'loss/train': 2.0481882095336914} +02/26/2022 07:46:27 - INFO - codeparrot_training - Step 41865: {'lr': 3.460655213290986e-05, 'samples': 21435392, 'steps': 41865, 'loss/train': 1.6504580974578857} +02/26/2022 07:46:30 - INFO - codeparrot_training - Step 41866: {'lr': 3.459824647936552e-05, 'samples': 21435904, 'steps': 41866, 'loss/train': 1.0296905040740967} +02/26/2022 07:46:37 - INFO - codeparrot_training - Step 41867: {'lr': 3.458994174853386e-05, 'samples': 21436416, 'steps': 41867, 'loss/train': 2.121839761734009} +02/26/2022 07:46:41 - INFO - codeparrot_training - Step 41868: {'lr': 3.4581637940450465e-05, 'samples': 21436928, 'steps': 41868, 'loss/train': 2.0996737480163574} +02/26/2022 07:46:46 - INFO - codeparrot_training - Step 41869: {'lr': 3.457333505515095e-05, 'samples': 21437440, 'steps': 41869, 'loss/train': 1.441436767578125} +02/26/2022 07:46:50 - INFO - codeparrot_training - Step 41870: {'lr': 3.4565033092670895e-05, 'samples': 21437952, 'steps': 41870, 'loss/train': 0.4527837932109833} +02/26/2022 07:46:55 - INFO - codeparrot_training - Step 41871: {'lr': 3.45567320530458e-05, 'samples': 21438464, 'steps': 41871, 'loss/train': 1.5662294626235962} +02/26/2022 07:47:01 - INFO - codeparrot_training - Step 41872: {'lr': 3.454843193631127e-05, 'samples': 21438976, 'steps': 41872, 'loss/train': 2.2271969318389893} +02/26/2022 07:47:04 - INFO - codeparrot_training - Step 41873: {'lr': 3.4540132742502785e-05, 'samples': 21439488, 'steps': 41873, 'loss/train': 2.4509475231170654} +02/26/2022 07:47:10 - INFO - codeparrot_training - Step 41874: {'lr': 3.453183447165603e-05, 'samples': 21440000, 'steps': 41874, 'loss/train': 1.315755844116211} +02/26/2022 07:47:13 - INFO - codeparrot_training - Step 41875: {'lr': 3.452353712380646e-05, 'samples': 21440512, 'steps': 41875, 'loss/train': 2.3272464275360107} +02/26/2022 07:47:19 - INFO - codeparrot_training - Step 41876: {'lr': 3.451524069898962e-05, 'samples': 21441024, 'steps': 41876, 'loss/train': 1.9262360334396362} +02/26/2022 07:47:22 - INFO - codeparrot_training - Step 41877: {'lr': 3.4506945197241044e-05, 'samples': 21441536, 'steps': 41877, 'loss/train': 0.9264810681343079} +02/26/2022 07:47:29 - INFO - codeparrot_training - Step 41878: {'lr': 3.449865061859633e-05, 'samples': 21442048, 'steps': 41878, 'loss/train': 2.1967406272888184} +02/26/2022 07:47:33 - INFO - codeparrot_training - Step 41879: {'lr': 3.449035696309094e-05, 'samples': 21442560, 'steps': 41879, 'loss/train': 3.3565893173217773} +02/26/2022 07:47:38 - INFO - codeparrot_training - Step 41880: {'lr': 3.4482064230760474e-05, 'samples': 21443072, 'steps': 41880, 'loss/train': 0.9036532044410706} +02/26/2022 07:47:42 - INFO - codeparrot_training - Step 41881: {'lr': 3.447377242164032e-05, 'samples': 21443584, 'steps': 41881, 'loss/train': 1.2806609869003296} +02/26/2022 07:47:47 - INFO - codeparrot_training - Step 41882: {'lr': 3.4465481535766146e-05, 'samples': 21444096, 'steps': 41882, 'loss/train': 1.8677949905395508} +02/26/2022 07:47:51 - INFO - codeparrot_training - Step 41883: {'lr': 3.445719157317343e-05, 'samples': 21444608, 'steps': 41883, 'loss/train': 0.9789207577705383} +02/26/2022 07:47:56 - INFO - codeparrot_training - Step 41884: {'lr': 3.4448902533897654e-05, 'samples': 21445120, 'steps': 41884, 'loss/train': 1.8151228427886963} +02/26/2022 07:48:00 - INFO - codeparrot_training - Step 41885: {'lr': 3.444061441797428e-05, 'samples': 21445632, 'steps': 41885, 'loss/train': 1.6921089887619019} +02/26/2022 07:48:06 - INFO - codeparrot_training - Step 41886: {'lr': 3.44323272254389e-05, 'samples': 21446144, 'steps': 41886, 'loss/train': 2.488142728805542} +02/26/2022 07:48:10 - INFO - codeparrot_training - Step 41887: {'lr': 3.4424040956326954e-05, 'samples': 21446656, 'steps': 41887, 'loss/train': 1.718224048614502} +02/26/2022 07:48:15 - INFO - codeparrot_training - Step 41888: {'lr': 3.441575561067406e-05, 'samples': 21447168, 'steps': 41888, 'loss/train': 0.5454226136207581} +02/26/2022 07:48:19 - INFO - codeparrot_training - Step 41889: {'lr': 3.44074711885155e-05, 'samples': 21447680, 'steps': 41889, 'loss/train': 1.5699777603149414} +02/26/2022 07:48:24 - INFO - codeparrot_training - Step 41890: {'lr': 3.439918768988695e-05, 'samples': 21448192, 'steps': 41890, 'loss/train': 2.2480530738830566} +02/26/2022 07:48:28 - INFO - codeparrot_training - Step 41891: {'lr': 3.4390905114823736e-05, 'samples': 21448704, 'steps': 41891, 'loss/train': 1.9418888092041016} +02/26/2022 07:48:33 - INFO - codeparrot_training - Step 41892: {'lr': 3.438262346336155e-05, 'samples': 21449216, 'steps': 41892, 'loss/train': 1.5452089309692383} +02/26/2022 07:48:37 - INFO - codeparrot_training - Step 41893: {'lr': 3.437434273553561e-05, 'samples': 21449728, 'steps': 41893, 'loss/train': 1.7702889442443848} +02/26/2022 07:48:42 - INFO - codeparrot_training - Step 41894: {'lr': 3.4366062931381585e-05, 'samples': 21450240, 'steps': 41894, 'loss/train': 1.9535242319107056} +02/26/2022 07:48:45 - INFO - codeparrot_training - Step 41895: {'lr': 3.4357784050934816e-05, 'samples': 21450752, 'steps': 41895, 'loss/train': 2.064274787902832} +02/26/2022 07:48:51 - INFO - codeparrot_training - Step 41896: {'lr': 3.43495060942309e-05, 'samples': 21451264, 'steps': 41896, 'loss/train': 1.08790922164917} +02/26/2022 07:48:55 - INFO - codeparrot_training - Step 41897: {'lr': 3.434122906130521e-05, 'samples': 21451776, 'steps': 41897, 'loss/train': 1.9326579570770264} +02/26/2022 07:49:01 - INFO - codeparrot_training - Step 41898: {'lr': 3.433295295219321e-05, 'samples': 21452288, 'steps': 41898, 'loss/train': 2.16262149810791} +02/26/2022 07:49:05 - INFO - codeparrot_training - Step 41899: {'lr': 3.432467776693029e-05, 'samples': 21452800, 'steps': 41899, 'loss/train': 1.4047818183898926} +02/26/2022 07:49:10 - INFO - codeparrot_training - Step 41900: {'lr': 3.431640350555204e-05, 'samples': 21453312, 'steps': 41900, 'loss/train': 2.2607452869415283} +02/26/2022 07:49:14 - INFO - codeparrot_training - Step 41901: {'lr': 3.430813016809384e-05, 'samples': 21453824, 'steps': 41901, 'loss/train': 0.7123552560806274} +02/26/2022 07:49:19 - INFO - codeparrot_training - Step 41902: {'lr': 3.42998577545911e-05, 'samples': 21454336, 'steps': 41902, 'loss/train': 1.88678777217865} +02/26/2022 07:49:23 - INFO - codeparrot_training - Step 41903: {'lr': 3.429158626507922e-05, 'samples': 21454848, 'steps': 41903, 'loss/train': 1.1145275831222534} +02/26/2022 07:49:28 - INFO - codeparrot_training - Step 41904: {'lr': 3.4283315699593756e-05, 'samples': 21455360, 'steps': 41904, 'loss/train': 1.7459561824798584} +02/26/2022 07:49:32 - INFO - codeparrot_training - Step 41905: {'lr': 3.4275046058170054e-05, 'samples': 21455872, 'steps': 41905, 'loss/train': 1.6811538934707642} +02/26/2022 07:49:37 - INFO - codeparrot_training - Step 41906: {'lr': 3.426677734084358e-05, 'samples': 21456384, 'steps': 41906, 'loss/train': 1.0550471544265747} +02/26/2022 07:49:41 - INFO - codeparrot_training - Step 41907: {'lr': 3.425850954764967e-05, 'samples': 21456896, 'steps': 41907, 'loss/train': 1.8260973691940308} +02/26/2022 07:49:46 - INFO - codeparrot_training - Step 41908: {'lr': 3.425024267862384e-05, 'samples': 21457408, 'steps': 41908, 'loss/train': 1.8912158012390137} +02/26/2022 07:49:50 - INFO - codeparrot_training - Step 41909: {'lr': 3.424197673380147e-05, 'samples': 21457920, 'steps': 41909, 'loss/train': 2.2257046699523926} +02/26/2022 07:49:55 - INFO - codeparrot_training - Step 41910: {'lr': 3.423371171321796e-05, 'samples': 21458432, 'steps': 41910, 'loss/train': 2.71388578414917} +02/26/2022 07:49:59 - INFO - codeparrot_training - Step 41911: {'lr': 3.422544761690866e-05, 'samples': 21458944, 'steps': 41911, 'loss/train': 2.782745838165283} +02/26/2022 07:50:06 - INFO - codeparrot_training - Step 41912: {'lr': 3.421718444490907e-05, 'samples': 21459456, 'steps': 41912, 'loss/train': 2.449758291244507} +02/26/2022 07:50:09 - INFO - codeparrot_training - Step 41913: {'lr': 3.420892219725455e-05, 'samples': 21459968, 'steps': 41913, 'loss/train': 0.5024000406265259} +02/26/2022 07:50:15 - INFO - codeparrot_training - Step 41914: {'lr': 3.420066087398049e-05, 'samples': 21460480, 'steps': 41914, 'loss/train': 2.586467742919922} +02/26/2022 07:50:18 - INFO - codeparrot_training - Step 41915: {'lr': 3.419240047512223e-05, 'samples': 21460992, 'steps': 41915, 'loss/train': 1.3416094779968262} +02/26/2022 07:50:24 - INFO - codeparrot_training - Step 41916: {'lr': 3.418414100071524e-05, 'samples': 21461504, 'steps': 41916, 'loss/train': 1.6230154037475586} +02/26/2022 07:50:27 - INFO - codeparrot_training - Step 41917: {'lr': 3.417588245079487e-05, 'samples': 21462016, 'steps': 41917, 'loss/train': 2.0060741901397705} +02/26/2022 07:50:33 - INFO - codeparrot_training - Step 41918: {'lr': 3.416762482539648e-05, 'samples': 21462528, 'steps': 41918, 'loss/train': 1.5923959016799927} +02/26/2022 07:50:36 - INFO - codeparrot_training - Step 41919: {'lr': 3.4159368124555446e-05, 'samples': 21463040, 'steps': 41919, 'loss/train': 0.3508755564689636} +02/26/2022 07:50:42 - INFO - codeparrot_training - Step 41920: {'lr': 3.415111234830709e-05, 'samples': 21463552, 'steps': 41920, 'loss/train': 1.2949495315551758} +02/26/2022 07:50:45 - INFO - codeparrot_training - Step 41921: {'lr': 3.414285749668688e-05, 'samples': 21464064, 'steps': 41921, 'loss/train': 1.8322685956954956} +02/26/2022 07:50:52 - INFO - codeparrot_training - Step 41922: {'lr': 3.413460356973008e-05, 'samples': 21464576, 'steps': 41922, 'loss/train': 1.1594280004501343} +02/26/2022 07:50:56 - INFO - codeparrot_training - Step 41923: {'lr': 3.4126350567472205e-05, 'samples': 21465088, 'steps': 41923, 'loss/train': 1.1350784301757812} +02/26/2022 07:51:01 - INFO - codeparrot_training - Step 41924: {'lr': 3.41180984899484e-05, 'samples': 21465600, 'steps': 41924, 'loss/train': 0.9808856844902039} +02/26/2022 07:51:05 - INFO - codeparrot_training - Step 41925: {'lr': 3.410984733719413e-05, 'samples': 21466112, 'steps': 41925, 'loss/train': 1.1718684434890747} +02/26/2022 07:51:10 - INFO - codeparrot_training - Step 41926: {'lr': 3.410159710924468e-05, 'samples': 21466624, 'steps': 41926, 'loss/train': 1.5446263551712036} +02/26/2022 07:51:14 - INFO - codeparrot_training - Step 41927: {'lr': 3.409334780613557e-05, 'samples': 21467136, 'steps': 41927, 'loss/train': 1.1448591947555542} +02/26/2022 07:51:19 - INFO - codeparrot_training - Step 41928: {'lr': 3.408509942790186e-05, 'samples': 21467648, 'steps': 41928, 'loss/train': 1.2616558074951172} +02/26/2022 07:51:23 - INFO - codeparrot_training - Step 41929: {'lr': 3.407685197457908e-05, 'samples': 21468160, 'steps': 41929, 'loss/train': 1.2948966026306152} +02/26/2022 07:51:28 - INFO - codeparrot_training - Step 41930: {'lr': 3.4068605446202464e-05, 'samples': 21468672, 'steps': 41930, 'loss/train': 1.7025885581970215} +02/26/2022 07:51:32 - INFO - codeparrot_training - Step 41931: {'lr': 3.406035984280748e-05, 'samples': 21469184, 'steps': 41931, 'loss/train': 2.1909499168395996} +02/26/2022 07:51:37 - INFO - codeparrot_training - Step 41932: {'lr': 3.4052115164429214e-05, 'samples': 21469696, 'steps': 41932, 'loss/train': 1.654496192932129} +02/26/2022 07:51:41 - INFO - codeparrot_training - Step 41933: {'lr': 3.4043871411103214e-05, 'samples': 21470208, 'steps': 41933, 'loss/train': 1.3355154991149902} +02/26/2022 07:51:48 - INFO - codeparrot_training - Step 41934: {'lr': 3.40356285828646e-05, 'samples': 21470720, 'steps': 41934, 'loss/train': 1.9920549392700195} +02/26/2022 07:51:51 - INFO - codeparrot_training - Step 41935: {'lr': 3.402738667974883e-05, 'samples': 21471232, 'steps': 41935, 'loss/train': 1.2140552997589111} +02/26/2022 07:51:57 - INFO - codeparrot_training - Step 41936: {'lr': 3.401914570179118e-05, 'samples': 21471744, 'steps': 41936, 'loss/train': 1.9474793672561646} +02/26/2022 07:52:00 - INFO - codeparrot_training - Step 41937: {'lr': 3.4010905649026924e-05, 'samples': 21472256, 'steps': 41937, 'loss/train': 1.204066514968872} +02/26/2022 07:52:06 - INFO - codeparrot_training - Step 41938: {'lr': 3.400266652149131e-05, 'samples': 21472768, 'steps': 41938, 'loss/train': 1.4890319108963013} +02/26/2022 07:52:09 - INFO - codeparrot_training - Step 41939: {'lr': 3.3994428319219726e-05, 'samples': 21473280, 'steps': 41939, 'loss/train': 1.913551926612854} +02/26/2022 07:52:15 - INFO - codeparrot_training - Step 41940: {'lr': 3.3986191042247454e-05, 'samples': 21473792, 'steps': 41940, 'loss/train': 1.6753807067871094} +02/26/2022 07:52:18 - INFO - codeparrot_training - Step 41941: {'lr': 3.397795469060971e-05, 'samples': 21474304, 'steps': 41941, 'loss/train': 2.238720178604126} +02/26/2022 07:52:24 - INFO - codeparrot_training - Step 41942: {'lr': 3.396971926434178e-05, 'samples': 21474816, 'steps': 41942, 'loss/train': 1.5360300540924072} +02/26/2022 07:52:27 - INFO - codeparrot_training - Step 41943: {'lr': 3.3961484763479015e-05, 'samples': 21475328, 'steps': 41943, 'loss/train': 1.2779909372329712} +02/26/2022 07:52:34 - INFO - codeparrot_training - Step 41944: {'lr': 3.395325118805661e-05, 'samples': 21475840, 'steps': 41944, 'loss/train': 1.166858434677124} +02/26/2022 07:52:37 - INFO - codeparrot_training - Step 41945: {'lr': 3.394501853810999e-05, 'samples': 21476352, 'steps': 41945, 'loss/train': 1.1693891286849976} +02/26/2022 07:52:42 - INFO - codeparrot_training - Step 41946: {'lr': 3.393678681367418e-05, 'samples': 21476864, 'steps': 41946, 'loss/train': 0.8781642913818359} +02/26/2022 07:52:46 - INFO - codeparrot_training - Step 41947: {'lr': 3.392855601478462e-05, 'samples': 21477376, 'steps': 41947, 'loss/train': 1.5784435272216797} +02/26/2022 07:52:51 - INFO - codeparrot_training - Step 41948: {'lr': 3.392032614147647e-05, 'samples': 21477888, 'steps': 41948, 'loss/train': 1.5444133281707764} +02/26/2022 07:52:55 - INFO - codeparrot_training - Step 41949: {'lr': 3.391209719378513e-05, 'samples': 21478400, 'steps': 41949, 'loss/train': 1.3093897104263306} +02/26/2022 07:53:00 - INFO - codeparrot_training - Step 41950: {'lr': 3.390386917174565e-05, 'samples': 21478912, 'steps': 41950, 'loss/train': 1.2384485006332397} +02/26/2022 07:53:04 - INFO - codeparrot_training - Step 41951: {'lr': 3.3895642075393416e-05, 'samples': 21479424, 'steps': 41951, 'loss/train': 2.4142026901245117} +02/26/2022 07:53:09 - INFO - codeparrot_training - Step 41952: {'lr': 3.3887415904763655e-05, 'samples': 21479936, 'steps': 41952, 'loss/train': 1.362563133239746} +02/26/2022 07:53:13 - INFO - codeparrot_training - Step 41953: {'lr': 3.387919065989156e-05, 'samples': 21480448, 'steps': 41953, 'loss/train': 1.158187985420227} +02/26/2022 07:53:19 - INFO - codeparrot_training - Step 41954: {'lr': 3.3870966340812355e-05, 'samples': 21480960, 'steps': 41954, 'loss/train': 1.6217172145843506} +02/26/2022 07:53:23 - INFO - codeparrot_training - Step 41955: {'lr': 3.386274294756134e-05, 'samples': 21481472, 'steps': 41955, 'loss/train': 1.2747089862823486} +02/26/2022 07:53:29 - INFO - codeparrot_training - Step 41956: {'lr': 3.385452048017371e-05, 'samples': 21481984, 'steps': 41956, 'loss/train': 1.8110721111297607} +02/26/2022 07:53:32 - INFO - codeparrot_training - Step 41957: {'lr': 3.38462989386846e-05, 'samples': 21482496, 'steps': 41957, 'loss/train': 1.302634358406067} +02/26/2022 07:53:38 - INFO - codeparrot_training - Step 41958: {'lr': 3.383807832312938e-05, 'samples': 21483008, 'steps': 41958, 'loss/train': 1.5550804138183594} +02/26/2022 07:53:41 - INFO - codeparrot_training - Step 41959: {'lr': 3.382985863354321e-05, 'samples': 21483520, 'steps': 41959, 'loss/train': 1.358167290687561} +02/26/2022 07:53:47 - INFO - codeparrot_training - Step 41960: {'lr': 3.3821639869961257e-05, 'samples': 21484032, 'steps': 41960, 'loss/train': 1.4872336387634277} +02/26/2022 07:53:50 - INFO - codeparrot_training - Step 41961: {'lr': 3.381342203241872e-05, 'samples': 21484544, 'steps': 41961, 'loss/train': 1.9987504482269287} +02/26/2022 07:53:56 - INFO - codeparrot_training - Step 41962: {'lr': 3.380520512095086e-05, 'samples': 21485056, 'steps': 41962, 'loss/train': 2.2526466846466064} +02/26/2022 07:53:59 - INFO - codeparrot_training - Step 41963: {'lr': 3.37969891355929e-05, 'samples': 21485568, 'steps': 41963, 'loss/train': 2.975898265838623} +02/26/2022 07:54:05 - INFO - codeparrot_training - Step 41964: {'lr': 3.3788774076379956e-05, 'samples': 21486080, 'steps': 41964, 'loss/train': 1.1899324655532837} +02/26/2022 07:54:08 - INFO - codeparrot_training - Step 41965: {'lr': 3.3780559943347194e-05, 'samples': 21486592, 'steps': 41965, 'loss/train': 0.22895056009292603} +02/26/2022 07:54:14 - INFO - codeparrot_training - Step 41966: {'lr': 3.3772346736529985e-05, 'samples': 21487104, 'steps': 41966, 'loss/train': 0.9826042652130127} +02/26/2022 07:54:17 - INFO - codeparrot_training - Step 41967: {'lr': 3.376413445596324e-05, 'samples': 21487616, 'steps': 41967, 'loss/train': 1.99070143699646} +02/26/2022 07:54:23 - INFO - codeparrot_training - Step 41968: {'lr': 3.375592310168235e-05, 'samples': 21488128, 'steps': 41968, 'loss/train': 2.310971736907959} +02/26/2022 07:54:26 - INFO - codeparrot_training - Step 41969: {'lr': 3.374771267372237e-05, 'samples': 21488640, 'steps': 41969, 'loss/train': 1.9975749254226685} +02/26/2022 07:54:33 - INFO - codeparrot_training - Step 41970: {'lr': 3.373950317211857e-05, 'samples': 21489152, 'steps': 41970, 'loss/train': 0.6903871297836304} +02/26/2022 07:54:36 - INFO - codeparrot_training - Step 41971: {'lr': 3.37312945969061e-05, 'samples': 21489664, 'steps': 41971, 'loss/train': 1.5590122938156128} +02/26/2022 07:54:42 - INFO - codeparrot_training - Step 41972: {'lr': 3.3723086948120066e-05, 'samples': 21490176, 'steps': 41972, 'loss/train': 1.0656887292861938} +02/26/2022 07:54:45 - INFO - codeparrot_training - Step 41973: {'lr': 3.371488022579558e-05, 'samples': 21490688, 'steps': 41973, 'loss/train': 0.576991856098175} +02/26/2022 07:54:51 - INFO - codeparrot_training - Step 41974: {'lr': 3.370667442996794e-05, 'samples': 21491200, 'steps': 41974, 'loss/train': 0.9533164501190186} +02/26/2022 07:54:55 - INFO - codeparrot_training - Step 41975: {'lr': 3.369846956067224e-05, 'samples': 21491712, 'steps': 41975, 'loss/train': 1.4333529472351074} +02/26/2022 07:55:00 - INFO - codeparrot_training - Step 41976: {'lr': 3.3690265617943585e-05, 'samples': 21492224, 'steps': 41976, 'loss/train': 1.68449866771698} +02/26/2022 07:55:03 - INFO - codeparrot_training - Step 41977: {'lr': 3.368206260181711e-05, 'samples': 21492736, 'steps': 41977, 'loss/train': 1.1230305433273315} +02/26/2022 07:55:09 - INFO - codeparrot_training - Step 41978: {'lr': 3.367386051232804e-05, 'samples': 21493248, 'steps': 41978, 'loss/train': 0.6900342702865601} +02/26/2022 07:55:12 - INFO - codeparrot_training - Step 41979: {'lr': 3.366565934951146e-05, 'samples': 21493760, 'steps': 41979, 'loss/train': 1.8926395177841187} +02/26/2022 07:55:19 - INFO - codeparrot_training - Step 41980: {'lr': 3.365745911340248e-05, 'samples': 21494272, 'steps': 41980, 'loss/train': 1.38222336769104} +02/26/2022 07:55:22 - INFO - codeparrot_training - Step 41981: {'lr': 3.364925980403621e-05, 'samples': 21494784, 'steps': 41981, 'loss/train': 1.3039599657058716} +02/26/2022 07:55:28 - INFO - codeparrot_training - Step 41982: {'lr': 3.3641061421447876e-05, 'samples': 21495296, 'steps': 41982, 'loss/train': 1.8142094612121582} +02/26/2022 07:55:31 - INFO - codeparrot_training - Step 41983: {'lr': 3.3632863965672475e-05, 'samples': 21495808, 'steps': 41983, 'loss/train': 1.3767694234848022} +02/26/2022 07:55:37 - INFO - codeparrot_training - Step 41984: {'lr': 3.3624667436745305e-05, 'samples': 21496320, 'steps': 41984, 'loss/train': 3.4410488605499268} +02/26/2022 07:55:41 - INFO - codeparrot_training - Step 41985: {'lr': 3.3616471834701204e-05, 'samples': 21496832, 'steps': 41985, 'loss/train': 5.851458549499512} +02/26/2022 07:55:46 - INFO - codeparrot_training - Step 41986: {'lr': 3.360827715957551e-05, 'samples': 21497344, 'steps': 41986, 'loss/train': 1.6347200870513916} +02/26/2022 07:55:50 - INFO - codeparrot_training - Step 41987: {'lr': 3.3600083411403195e-05, 'samples': 21497856, 'steps': 41987, 'loss/train': 1.8506697416305542} +02/26/2022 07:55:55 - INFO - codeparrot_training - Step 41988: {'lr': 3.3591890590219495e-05, 'samples': 21498368, 'steps': 41988, 'loss/train': 1.601239800453186} +02/26/2022 07:55:59 - INFO - codeparrot_training - Step 41989: {'lr': 3.358369869605934e-05, 'samples': 21498880, 'steps': 41989, 'loss/train': 2.545621871948242} +02/26/2022 07:56:05 - INFO - codeparrot_training - Step 41990: {'lr': 3.3575507728957926e-05, 'samples': 21499392, 'steps': 41990, 'loss/train': 1.1321842670440674} +02/26/2022 07:56:08 - INFO - codeparrot_training - Step 41991: {'lr': 3.356731768895027e-05, 'samples': 21499904, 'steps': 41991, 'loss/train': 1.6649385690689087} +02/26/2022 07:56:14 - INFO - codeparrot_training - Step 41992: {'lr': 3.355912857607157e-05, 'samples': 21500416, 'steps': 41992, 'loss/train': 0.2660706043243408} +02/26/2022 07:56:18 - INFO - codeparrot_training - Step 41993: {'lr': 3.355094039035681e-05, 'samples': 21500928, 'steps': 41993, 'loss/train': 1.1076467037200928} +02/26/2022 07:56:23 - INFO - codeparrot_training - Step 41994: {'lr': 3.35427531318411e-05, 'samples': 21501440, 'steps': 41994, 'loss/train': 1.601947546005249} +02/26/2022 07:56:27 - INFO - codeparrot_training - Step 41995: {'lr': 3.3534566800559444e-05, 'samples': 21501952, 'steps': 41995, 'loss/train': 2.1484107971191406} +02/26/2022 07:56:32 - INFO - codeparrot_training - Step 41996: {'lr': 3.352638139654704e-05, 'samples': 21502464, 'steps': 41996, 'loss/train': 1.9688382148742676} +02/26/2022 07:56:36 - INFO - codeparrot_training - Step 41997: {'lr': 3.3518196919838874e-05, 'samples': 21502976, 'steps': 41997, 'loss/train': 1.4797433614730835} +02/26/2022 07:56:41 - INFO - codeparrot_training - Step 41998: {'lr': 3.351001337047e-05, 'samples': 21503488, 'steps': 41998, 'loss/train': 1.3362501859664917} +02/26/2022 07:56:45 - INFO - codeparrot_training - Step 41999: {'lr': 3.350183074847549e-05, 'samples': 21504000, 'steps': 41999, 'loss/train': 1.3207478523254395} +02/26/2022 07:56:45 - INFO - codeparrot_training - Evaluating and saving model checkpoint